1 files changed, 80 insertions, 85 deletions

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 17e13396024a..a3f1c1461874 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -167,8 +167,8 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
 
 static void __mptcp_rmem_reclaim(struct sock *sk, int amount)
 {
-	amount >>= SK_MEM_QUANTUM_SHIFT;
-	mptcp_sk(sk)->rmem_fwd_alloc -= amount << SK_MEM_QUANTUM_SHIFT;
+	amount >>= PAGE_SHIFT;
+	mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT;
 	__sk_mem_reduce_allocated(sk, amount);
 }
 
@@ -181,8 +181,8 @@ static void mptcp_rmem_uncharge(struct sock *sk, int size)
 	reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk);
 
 	/* see sk_mem_uncharge() for the rationale behind the following schema */
-	if (unlikely(reclaimable >= SK_RECLAIM_THRESHOLD))
-		__mptcp_rmem_reclaim(sk, SK_RECLAIM_CHUNK);
+	if (unlikely(reclaimable >= PAGE_SIZE))
+		__mptcp_rmem_reclaim(sk, reclaimable);
 }
 
 static void mptcp_rfree(struct sk_buff *skb)
@@ -323,20 +323,16 @@ static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size)
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	int amt, amount;
 
-	if (size < msk->rmem_fwd_alloc)
+	if (size <= msk->rmem_fwd_alloc)
 		return true;
 
+	size -= msk->rmem_fwd_alloc;
 	amt = sk_mem_pages(size);
-	amount = amt << SK_MEM_QUANTUM_SHIFT;
-	msk->rmem_fwd_alloc += amount;
-	if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) {
-		if (ssk->sk_forward_alloc < amount) {
-			msk->rmem_fwd_alloc -= amount;
-			return false;
-		}
+	amount = amt << PAGE_SHIFT;
+	if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV))
+		return false;
 
-		ssk->sk_forward_alloc -= amount;
-	}
+	msk->rmem_fwd_alloc += amount;
 	return true;
 }
 
@@ -500,19 +496,24 @@ static void mptcp_set_timeout(struct sock *sk)
 	__mptcp_set_timeout(sk, tout);
 }
 
-static bool tcp_can_send_ack(const struct sock *ssk)
+static inline bool tcp_can_send_ack(const struct sock *ssk)
 {
 	return !((1 << inet_sk_state_load(ssk)) &
 	       (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN));
 }
 
-void mptcp_subflow_send_ack(struct sock *ssk)
+void __mptcp_subflow_send_ack(struct sock *ssk)
+{
+	if (tcp_can_send_ack(ssk))
+		tcp_send_ack(ssk);
+}
+
+static void mptcp_subflow_send_ack(struct sock *ssk)
 {
 	bool slow;
 
 	slow = lock_sock_fast(ssk);
-	if (tcp_can_send_ack(ssk))
-		tcp_send_ack(ssk);
+	__mptcp_subflow_send_ack(ssk);
 	unlock_sock_fast(ssk, slow);
 }
 
@@ -966,25 +967,6 @@ static bool mptcp_frag_can_collapse_to(const struct mptcp_sock *msk,
 		df->data_seq + df->data_len == msk->write_seq;
 }
 
-static void __mptcp_mem_reclaim_partial(struct sock *sk)
-{
-	int reclaimable = mptcp_sk(sk)->rmem_fwd_alloc - sk_unused_reserved_mem(sk);
-
-	lockdep_assert_held_once(&sk->sk_lock.slock);
-
-	if (reclaimable > SK_MEM_QUANTUM)
-		__mptcp_rmem_reclaim(sk, reclaimable - 1);
-
-	sk_mem_reclaim_partial(sk);
-}
-
-static void mptcp_mem_reclaim_partial(struct sock *sk)
-{
-	mptcp_data_lock(sk);
-	__mptcp_mem_reclaim_partial(sk);
-	mptcp_data_unlock(sk);
-}
-
 static void dfrag_uncharge(struct sock *sk, int len)
 {
 	sk_mem_uncharge(sk, len);
@@ -1004,7 +986,6 @@ static void __mptcp_clean_una(struct sock *sk)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_data_frag *dtmp, *dfrag;
-	bool cleaned = false;
 	u64 snd_una;
 
 	/* on fallback we just need to ignore snd_una, as this is really
@@ -1027,7 +1008,6 @@ static void __mptcp_clean_una(struct sock *sk)
 		}
 
 		dfrag_clear(sk, dfrag);
-		cleaned = true;
 	}
 
 	dfrag = mptcp_rtx_head(sk);
@@ -1049,7 +1029,6 @@ static void __mptcp_clean_una(struct sock *sk)
 		dfrag->already_sent -= delta;
 
 		dfrag_uncharge(sk, delta);
-		cleaned = true;
 	}
 
 	/* all retransmitted data acked, recovery completed */
@@ -1057,9 +1036,6 @@ static void __mptcp_clean_una(struct sock *sk)
 		msk->recovery = false;
 
 out:
-	if (cleaned && tcp_under_memory_pressure(sk))
-		__mptcp_mem_reclaim_partial(sk);
-
 	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))
@@ -1211,12 +1187,6 @@ static struct sk_buff *mptcp_alloc_tx_skb(struct sock *sk, struct sock *ssk, boo
 {
 	gfp_t gfp = data_lock_held ? GFP_ATOMIC : sk->sk_allocation;
 
-	if (unlikely(tcp_under_memory_pressure(sk))) {
-		if (data_lock_held)
-			__mptcp_mem_reclaim_partial(sk);
-		else
-			mptcp_mem_reclaim_partial(sk);
-	}
 	return __mptcp_alloc_tx_skb(sk, ssk, gfp);
 }
 
@@ -1245,7 +1215,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk,
 	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
 	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
 	pr_fallback(msk);
-	__mptcp_do_fallback(msk);
+	mptcp_do_fallback(ssk);
 }
 
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
@@ -1903,7 +1873,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	if (msk->rcvq_space.copied <= msk->rcvq_space.space)
 		goto new_measure;
 
-	if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
 	    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
 		int rcvmem, rcvbuf;
 		u64 rcvwin, grow;
@@ -1921,7 +1891,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 
 		do_div(rcvwin, advmss);
 		rcvbuf = min_t(u64, rcvwin * rcvmem,
-			       sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+			       READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
 
 		if (rcvbuf > sk->sk_rcvbuf) {
 			u32 window_clamp;
@@ -2175,21 +2145,6 @@ static void mptcp_retransmit_timer(struct timer_list *t)
 	sock_put(sk);
 }
 
-static struct mptcp_subflow_context *
-mp_fail_response_expect_subflow(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow, *ret = NULL;
-
-	mptcp_for_each_subflow(msk, subflow) {
-		if (READ_ONCE(subflow->mp_fail_response_expect)) {
-			ret = subflow;
-			break;
-		}
-	}
-
-	return ret;
-}
-
 static void mptcp_timeout_timer(struct timer_list *t)
 {
 	struct sock *sk = from_timer(sk, t, sk_timer);
@@ -2346,6 +2301,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		kfree_rcu(subflow, rcu);
 	} else {
 		/* otherwise tcp will dispose of the ssk and subflow ctx */
+		if (ssk->sk_state == TCP_LISTEN) {
+			tcp_set_state(ssk, TCP_CLOSE);
+			mptcp_subflow_queue_clean(ssk);
+			inet_csk_listen_stop(ssk);
+		}
 		__tcp_close(ssk, 0);
 
 		/* close acquired an extra ref */
@@ -2518,27 +2478,50 @@ reset_timer:
 		mptcp_reset_timer(sk);
 }
 
+/* schedule the timeout timer for the relevant event: either close timeout
+ * or mp_fail timeout. The close timeout takes precedence on the mp_fail one
+ */
+void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout)
+{
+	struct sock *sk = (struct sock *)msk;
+	unsigned long timeout, close_timeout;
+
+	if (!fail_tout && !sock_flag(sk, SOCK_DEAD))
+		return;
+
+	close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN;
+
+	/* the close timeout takes precedence on the fail one, and here at least one of
+	 * them is active
+	 */
+	timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout;
+
+	sk_reset_timer(sk, &sk->sk_timer, timeout);
+}
+
 static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
 {
-	struct mptcp_subflow_context *subflow;
-	struct sock *ssk;
+	struct sock *ssk = msk->first;
 	bool slow;
 
-	subflow = mp_fail_response_expect_subflow(msk);
-	if (subflow) {
-		pr_debug("MP_FAIL doesn't respond, reset the subflow");
+	if (!ssk)
+		return;
+
+	pr_debug("MP_FAIL doesn't respond, reset the subflow");
 
-		ssk = mptcp_subflow_tcp_sock(subflow);
-		slow = lock_sock_fast(ssk);
-		mptcp_subflow_reset(ssk);
-		unlock_sock_fast(ssk, slow);
-	}
+	slow = lock_sock_fast(ssk);
+	mptcp_subflow_reset(ssk);
+	WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0);
+	unlock_sock_fast(ssk, slow);
+
+	mptcp_reset_timeout(msk, 0);
 }
 
 static void mptcp_worker(struct work_struct *work)
 {
 	struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work);
 	struct sock *sk = &msk->sk.icsk_inet.sk;
+	unsigned long fail_tout;
 	int state;
 
 	lock_sock(sk);
@@ -2575,7 +2558,9 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		__mptcp_retrans(sk);
 
-	mptcp_mp_fail_no_response(msk);
+	fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0;
+	if (fail_tout && time_after(jiffies, fail_tout))
+		mptcp_mp_fail_no_response(msk);
 
 unlock:
 	release_sock(sk);
@@ -2649,8 +2634,8 @@ static int mptcp_init_sock(struct sock *sk)
 	mptcp_ca_reset(sk);
 
 	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];
+	sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+	sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
 
 	return 0;
 }
@@ -2822,6 +2807,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 static void mptcp_close(struct sock *sk, long timeout)
 {
 	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = mptcp_sk(sk);
 	bool do_cancel_work = false;
 
 	lock_sock(sk);
@@ -2840,10 +2826,16 @@ static void mptcp_close(struct sock *sk, long timeout)
 cleanup:
 	/* orphan all the subflows */
 	inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32;
-	mptcp_for_each_subflow(mptcp_sk(sk), subflow) {
+	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		bool slow = lock_sock_fast_nested(ssk);
 
+		/* since the close timeout takes precedence on the fail one,
+		 * cancel the latter
+		 */
+		if (ssk == msk->first)
+			subflow->fail_tout = 0;
+
 		sock_orphan(ssk);
 		unlock_sock_fast(ssk, slow);
 	}
@@ -2852,13 +2844,13 @@ cleanup:
 	sock_hold(sk);
 	pr_debug("msk=%p state=%d", sk, sk->sk_state);
 	if (mptcp_sk(sk)->token)
-		mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL);
+		mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
 
 	if (sk->sk_state == TCP_CLOSE) {
 		__mptcp_destroy_sock(sk);
 		do_cancel_work = true;
 	} else {
-		sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN);
+		mptcp_reset_timeout(msk, 0);
 	}
 	release_sock(sk);
 	if (do_cancel_work)
@@ -2892,12 +2884,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk)
 
 static int mptcp_disconnect(struct sock *sk, int flags)
 {
-	struct mptcp_subflow_context *subflow;
+	struct mptcp_subflow_context *subflow, *tmp;
 	struct mptcp_sock *msk = mptcp_sk(sk);
 
 	inet_sk_state_store(sk, TCP_CLOSE);
 
-	mptcp_for_each_subflow(msk, subflow) {
+	list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 
 		__mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_FASTCLOSE);
@@ -3437,7 +3429,10 @@ static struct proto mptcp_prot = {
 	.get_port	= mptcp_get_port,
 	.forward_alloc_get	= mptcp_forward_alloc_get,
 	.sockets_allocated	= &mptcp_sockets_allocated,
+
 	.memory_allocated	= &tcp_memory_allocated,
+	.per_cpu_fw_alloc	= &tcp_memory_per_cpu_fw_alloc,
+
 	.memory_pressure	= &tcp_memory_pressure,
 	.sysctl_wmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_wmem),
 	.sysctl_rmem_offset	= offsetof(struct net, ipv4.sysctl_tcp_rmem),