1 files changed, 88 insertions, 19 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 9df4eaddfd48..3a1967bc7bad 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -15,7 +15,6 @@
 #include <net/inet_common.h>
 #include <net/inet_hashtables.h>
 #include <net/protocol.h>
-#include <net/tcp.h>
 #include <net/tcp_states.h>
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 #include <net/transp_v6.h>
@@ -1265,6 +1264,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 		mpext = mptcp_get_ext(skb);
 		if (!mptcp_skb_can_collapse_to(data_seq, skb, mpext)) {
 			TCP_SKB_CB(skb)->eor = 1;
+			tcp_mark_push(tcp_sk(ssk), skb);
 			goto alloc_skb;
 		}
 
@@ -1691,15 +1691,6 @@ out:
 	}
 }
 
-static void mptcp_set_nospace(struct sock *sk)
-{
-	/* enable autotune */
-	set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
-
-	/* will be cleared on avail space */
-	set_bit(MPTCP_NOSPACE, &mptcp_sk(sk)->flags);
-}
-
 static int mptcp_disconnect(struct sock *sk, int flags);
 
 static int mptcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
@@ -1770,6 +1761,30 @@ static int do_copy_data_nocache(struct sock *sk, int copy,
 	return 0;
 }
 
+/* open-code sk_stream_memory_free() plus sent limit computation to
+ * avoid indirect calls in fast-path.
+ * Called under the msk socket lock, so we can avoid a bunch of ONCE
+ * annotations.
+ */
+static u32 mptcp_send_limit(const struct sock *sk)
+{
+	const struct mptcp_sock *msk = mptcp_sk(sk);
+	u32 limit, not_sent;
+
+	if (sk->sk_wmem_queued >= READ_ONCE(sk->sk_sndbuf))
+		return 0;
+
+	limit = mptcp_notsent_lowat(sk);
+	if (limit == UINT_MAX)
+		return UINT_MAX;
+
+	not_sent = msk->write_seq - msk->snd_nxt;
+	if (not_sent >= limit)
+		return 0;
+
+	return limit - not_sent;
+}
+
 static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
@@ -1814,6 +1829,12 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		struct mptcp_data_frag *dfrag;
 		bool dfrag_collapsed;
 		size_t psize, offset;
+		u32 copy_limit;
+
+		/* ensure fitting the notsent_lowat() constraint */
+		copy_limit = mptcp_send_limit(sk);
+		if (!copy_limit)
+			goto wait_for_memory;
 
 		/* reuse tail pfrag, if possible, or carve a new one from the
 		 * page allocator
@@ -1821,9 +1842,6 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		dfrag = mptcp_pending_tail(sk);
 		dfrag_collapsed = mptcp_frag_can_collapse_to(msk, pfrag, dfrag);
 		if (!dfrag_collapsed) {
-			if (!sk_stream_memory_free(sk))
-				goto wait_for_memory;
-
 			if (!mptcp_page_frag_refill(sk, pfrag))
 				goto wait_for_memory;
 
@@ -1838,6 +1856,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		offset = dfrag->offset + dfrag->data_len;
 		psize = pfrag->size - offset;
 		psize = min_t(size_t, psize, msg_data_left(msg));
+		psize = min_t(size_t, psize, copy_limit);
 		total_ts = psize + frag_truesize;
 
 		if (!sk_wmem_schedule(sk, total_ts))
@@ -1873,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		continue;
 
 wait_for_memory:
-		mptcp_set_nospace(sk);
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 		__mptcp_push_pending(sk, msg->msg_flags);
 		ret = sk_stream_wait_memory(sk, &timeo);
 		if (ret)
@@ -3182,8 +3201,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk)
 
 	return (struct ipv6_pinfo *)(((u8 *)sk) + offset);
 }
+
+static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk)
+{
+	const struct ipv6_pinfo *np = inet6_sk(sk);
+	struct ipv6_txoptions *opt;
+	struct ipv6_pinfo *newnp;
+
+	newnp = inet6_sk(newsk);
+
+	rcu_read_lock();
+	opt = rcu_dereference(np->opt);
+	if (opt) {
+		opt = ipv6_dup_options(newsk, opt);
+		if (!opt)
+			net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__);
+	}
+	RCU_INIT_POINTER(newnp->opt, opt);
+	rcu_read_unlock();
+}
 #endif
 
+static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk)
+{
+	struct ip_options_rcu *inet_opt, *newopt = NULL;
+	const struct inet_sock *inet = inet_sk(sk);
+	struct inet_sock *newinet;
+
+	newinet = inet_sk(newsk);
+
+	rcu_read_lock();
+	inet_opt = rcu_dereference(inet->inet_opt);
+	if (inet_opt) {
+		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+				      inet_opt->opt.optlen, GFP_ATOMIC);
+		if (newopt)
+			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
+			       inet_opt->opt.optlen);
+		else
+			net_warn_ratelimited("%s: Failed to copy ip options\n", __func__);
+	}
+	RCU_INIT_POINTER(newinet->inet_opt, newopt);
+	rcu_read_unlock();
+}
+
 struct sock *mptcp_sk_clone_init(const struct sock *sk,
 				 const struct mptcp_options_received *mp_opt,
 				 struct sock *ssk,
@@ -3204,6 +3265,13 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 
 	__mptcp_init_sock(nsk);
 
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (nsk->sk_family == AF_INET6)
+		mptcp_copy_ip6_options(nsk, sk);
+	else
+#endif
+		mptcp_copy_ip_options(nsk, sk);
+
 	msk = mptcp_sk(nsk);
 	WRITE_ONCE(msk->local_key, subflow_req->local_key);
 	WRITE_ONCE(msk->token, subflow_req->token);
@@ -3215,7 +3283,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk,
 	WRITE_ONCE(msk->write_seq, subflow_req->idsn + 1);
 	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 	WRITE_ONCE(msk->snd_una, msk->write_seq);
-	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + req->rsk_rcv_wnd);
+	WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd);
 	msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq;
 	mptcp_init_sched(msk, mptcp_sk(sk)->sched);
 
@@ -3719,6 +3787,7 @@ static struct proto mptcp_prot = {
 	.unhash		= mptcp_unhash,
 	.get_port	= mptcp_get_port,
 	.forward_alloc_get	= mptcp_forward_alloc_get,
+	.stream_memory_free	= mptcp_stream_memory_free,
 	.sockets_allocated	= &mptcp_sockets_allocated,
 
 	.memory_allocated	= &tcp_memory_allocated,
@@ -3892,12 +3961,12 @@ static __poll_t mptcp_check_writeable(struct mptcp_sock *msk)
 {
 	struct sock *sk = (struct sock *)msk;
 
-	if (sk_stream_is_writeable(sk))
+	if (__mptcp_stream_is_writeable(sk, 1))
 		return EPOLLOUT | EPOLLWRNORM;
 
-	mptcp_set_nospace(sk);
-	smp_mb__after_atomic(); /* msk->flags is changed by write_space cb */
-	if (sk_stream_is_writeable(sk))
+	set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+	smp_mb__after_atomic(); /* NOSPACE is changed by mptcp_write_space() */
+	if (__mptcp_stream_is_writeable(sk, 1))
 		return EPOLLOUT | EPOLLWRNORM;
 
 	return 0;