1 files changed, 133 insertions, 41 deletions
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 0cbea3b6d0a4..7e1518bb6115 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -216,7 +216,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 
 	seq = MPTCP_SKB_CB(skb)->map_seq;
 	end_seq = MPTCP_SKB_CB(skb)->end_seq;
-	max_seq = READ_ONCE(msk->rcv_wnd_sent);
+	max_seq = atomic64_read(&msk->rcv_wnd_sent);
 
 	pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
 		 RB_EMPTY_ROOT(&msk->out_of_order_queue));
@@ -225,7 +225,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 		mptcp_drop(sk, skb);
 		pr_debug("oow by %lld, rcv_wnd_sent %llu\n",
 			 (unsigned long long)end_seq - (unsigned long)max_seq,
-			 (unsigned long long)msk->rcv_wnd_sent);
+			 (unsigned long long)atomic64_read(&msk->rcv_wnd_sent));
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_NODSSWINDOW);
 		return;
 	}
@@ -500,19 +500,24 @@ 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)
+{
+	if (tcp_can_send_ack(ssk))
+		tcp_send_ack(ssk);
+}
+
 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);
 }
 
@@ -1141,18 +1146,21 @@ struct mptcp_sendmsg_info {
 	bool data_lock_held;
 };
 
-static int mptcp_check_allowed_size(struct mptcp_sock *msk, u64 data_seq,
-				    int avail_size)
+static int mptcp_check_allowed_size(const struct mptcp_sock *msk, struct sock *ssk,
+				    u64 data_seq, int avail_size)
 {
 	u64 window_end = mptcp_wnd_end(msk);
+	u64 mptcp_snd_wnd;
 
 	if (__mptcp_check_fallback(msk))
 		return avail_size;
 
-	if (!before64(data_seq + avail_size, window_end)) {
-		u64 allowed_size = window_end - data_seq;
+	mptcp_snd_wnd = window_end - data_seq;
+	avail_size = min_t(unsigned int, mptcp_snd_wnd, avail_size);
 
-		return min_t(unsigned int, allowed_size, avail_size);
+	if (unlikely(tcp_sk(ssk)->snd_wnd < mptcp_snd_wnd)) {
+		tcp_sk(ssk)->snd_wnd = min_t(u64, U32_MAX, mptcp_snd_wnd);
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_SNDWNDSHARED);
 	}
 
 	return avail_size;
@@ -1229,6 +1237,22 @@ static void mptcp_update_data_checksum(struct sk_buff *skb, int added)
 	mpext->csum = csum_fold(csum_block_add(csum, skb_checksum(skb, offset, added, 0), offset));
 }
 
+static void mptcp_update_infinite_map(struct mptcp_sock *msk,
+				      struct sock *ssk,
+				      struct mptcp_ext *mpext)
+{
+	if (!mpext)
+		return;
+
+	mpext->infinite_map = 1;
+	mpext->data_len = 0;
+
+	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX);
+	mptcp_subflow_ctx(ssk)->send_infinite_map = 0;
+	pr_fallback(msk);
+	mptcp_do_fallback(ssk);
+}
+
 static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
 			      struct mptcp_data_frag *dfrag,
 			      struct mptcp_sendmsg_info *info)
@@ -1289,7 +1313,7 @@ alloc_skb:
 	}
 
 	/* Zero window and all data acked? Probe. */
-	copy = mptcp_check_allowed_size(msk, data_seq, copy);
+	copy = mptcp_check_allowed_size(msk, ssk, data_seq, copy);
 	if (copy == 0) {
 		u64 snd_una = READ_ONCE(msk->snd_una);
 
@@ -1360,6 +1384,8 @@ alloc_skb:
 out:
 	if (READ_ONCE(msk->csum_enabled))
 		mptcp_update_data_checksum(skb, copy);
+	if (mptcp_subflow_ctx(ssk)->send_infinite_map)
+		mptcp_update_infinite_map(msk, ssk, mpext);
 	trace_mptcp_sendmsg_frag(mpext);
 	mptcp_subflow_ctx(ssk)->rel_write_seq += copy;
 	return copy;
@@ -1480,11 +1506,16 @@ static struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	 * to check that subflow has a non empty cwin.
 	 */
 	ssk = send_info[SSK_MODE_ACTIVE].ssk;
-	if (!ssk || !sk_stream_memory_free(ssk) || !tcp_sk(ssk)->snd_wnd)
+	if (!ssk || !sk_stream_memory_free(ssk))
 		return NULL;
 
-	burst = min_t(int, MPTCP_SEND_BURST_SIZE, tcp_sk(ssk)->snd_wnd);
+	burst = min_t(int, MPTCP_SEND_BURST_SIZE, mptcp_wnd_end(msk) - msk->snd_nxt);
 	wmem = READ_ONCE(ssk->sk_wmem_queued);
+	if (!burst) {
+		msk->last_snd = NULL;
+		return ssk;
+	}
+
 	subflow = mptcp_subflow_ctx(ssk);
 	subflow->avg_pacing_rate = div_u64((u64)subflow->avg_pacing_rate * wmem +
 					   READ_ONCE(ssk->sk_pacing_rate) * burst,
@@ -1877,7 +1908,7 @@ 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;
@@ -1895,7 +1926,7 @@ 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;
@@ -2012,7 +2043,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk)
 }
 
 static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
-			 int nonblock, int flags, int *addr_len)
+			 int flags, int *addr_len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct scm_timestamping_internal tss;
@@ -2030,7 +2061,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		goto out_err;
 	}
 
-	timeo = sock_rcvtimeo(sk, nonblock);
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	len = min_t(size_t, len, INT_MAX);
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
@@ -2305,6 +2336,11 @@ 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 */
@@ -2465,6 +2501,7 @@ static void __mptcp_retrans(struct sock *sk)
 		dfrag->already_sent = max(dfrag->already_sent, info.sent);
 		tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle,
 			 info.size_goal);
+		WRITE_ONCE(msk->allow_infinite_fallback, false);
 	}
 
 	release_sock(ssk);
@@ -2476,10 +2513,50 @@ 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 sock *ssk = msk->first;
+	bool slow;
+
+	if (!ssk)
+		return;
+
+	pr_debug("MP_FAIL doesn't respond, reset the subflow");
+
+	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);
@@ -2516,6 +2593,10 @@ static void mptcp_worker(struct work_struct *work)
 	if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags))
 		__mptcp_retrans(sk);
 
+	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);
 	sock_put(sk);
@@ -2539,6 +2620,7 @@ static int __mptcp_init_sock(struct sock *sk)
 	msk->first = NULL;
 	inet_csk(sk)->icsk_sync_mss = mptcp_sync_mss;
 	WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk)));
+	WRITE_ONCE(msk->allow_infinite_fallback, true);
 	msk->recovery = false;
 
 	mptcp_pm_data_init(msk);
@@ -2587,8 +2669,8 @@ 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;
 }
@@ -2733,7 +2815,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
 	/* join list will be eventually flushed (with rst) at sock lock release time*/
 	list_splice_init(&msk->conn_list, &conn_list);
 
-	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+	mptcp_stop_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 	msk->pm.status = 0;
 
@@ -2760,6 +2842,7 @@ 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);
@@ -2778,10 +2861,16 @@ 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);
 	}
@@ -2790,13 +2879,13 @@ 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)
@@ -2830,18 +2919,18 @@ 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);
 	}
 
-	sk_stop_timer(sk, &msk->sk.icsk_retransmit_timer);
+	mptcp_stop_timer(sk);
 	sk_stop_timer(sk, &sk->sk_timer);
 
 	if (mptcp_sk(sk)->token)
@@ -2916,7 +3005,7 @@ struct sock *mptcp_sk_clone(const struct sock *sk,
 		mptcp_crypto_key_sha(msk->remote_key, NULL, &ack_seq);
 		ack_seq++;
 		WRITE_ONCE(msk->ack_seq, ack_seq);
-		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+		atomic64_set(&msk->rcv_wnd_sent, ack_seq);
 	}
 
 	sock_reset_flag(nsk, SOCK_RCU_FREE);
@@ -3017,6 +3106,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk)
 	msk->rmem_fwd_alloc = 0;
 	mptcp_token_destroy(msk);
 	mptcp_pm_free_anno_list(msk);
+	mptcp_free_local_addr_list(msk);
 }
 
 static void mptcp_destroy(struct sock *sk)
@@ -3092,15 +3182,19 @@ static void mptcp_release_cb(struct sock *sk)
 		spin_lock_bh(&sk->sk_lock.slock);
 	}
 
-	/* be sure to set the current sk state before tacking actions
-	 * depending on sk_state
-	 */
-	if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
-		__mptcp_set_connected(sk);
 	if (__test_and_clear_bit(MPTCP_CLEAN_UNA, &msk->cb_flags))
 		__mptcp_clean_una_wakeup(sk);
-	if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
-		__mptcp_error_report(sk);
+	if (unlikely(&msk->cb_flags)) {
+		/* be sure to set the current sk state before tacking actions
+		 * depending on sk_state, that is processing MPTCP_ERROR_REPORT
+		 */
+		if (__test_and_clear_bit(MPTCP_CONNECTED, &msk->cb_flags))
+			__mptcp_set_connected(sk);
+		if (__test_and_clear_bit(MPTCP_ERROR_REPORT, &msk->cb_flags))
+			__mptcp_error_report(sk);
+		if (__test_and_clear_bit(MPTCP_RESET_SCHEDULER, &msk->cb_flags))
+			msk->last_snd = NULL;
+	}
 
 	__mptcp_update_rmem(sk);
 }
@@ -3204,9 +3298,9 @@ void mptcp_finish_connect(struct sock *ssk)
 	WRITE_ONCE(msk->write_seq, subflow->idsn + 1);
 	WRITE_ONCE(msk->snd_nxt, msk->write_seq);
 	WRITE_ONCE(msk->ack_seq, ack_seq);
-	WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 	WRITE_ONCE(msk->can_ack, 1);
 	WRITE_ONCE(msk->snd_una, msk->write_seq);
+	atomic64_set(&msk->rcv_wnd_sent, ack_seq);
 
 	mptcp_pm_new_connection(msk, ssk, 0);
 
@@ -3237,15 +3331,12 @@ bool mptcp_finish_join(struct sock *ssk)
 		return false;
 	}
 
-	if (!msk->pm.server_side)
+	if (!list_empty(&subflow->node))
 		goto out;
 
 	if (!mptcp_pm_allow_new_subflow(msk))
 		goto err_prohibited;
 
-	if (WARN_ON_ONCE(!list_empty(&subflow->node)))
-		goto err_prohibited;
-
 	/* active connections are already on conn_list.
 	 * If we can't acquire msk socket lock here, let the release callback
 	 * handle it
@@ -3271,6 +3362,7 @@ err_prohibited:
 	}
 
 	subflow->map_seq = READ_ONCE(msk->ack_seq);
+	WRITE_ONCE(msk->allow_infinite_fallback, false);
 
 out:
 	mptcp_event(MPTCP_EVENT_SUB_ESTABLISHED, msk, ssk, GFP_ATOMIC);
@@ -3703,8 +3795,8 @@ void __init mptcp_proto_init(void)
 	for_each_possible_cpu(cpu) {
 		delegated = per_cpu_ptr(&mptcp_delegated_actions, cpu);
 		INIT_LIST_HEAD(&delegated->head);
-		netif_tx_napi_add(&mptcp_napi_dev, &delegated->napi, mptcp_napi_poll,
-				  NAPI_POLL_WEIGHT);
+		netif_napi_add_tx(&mptcp_napi_dev, &delegated->napi,
+				  mptcp_napi_poll);
 		napi_enable(&delegated->napi);
 	}