1 files changed, 55 insertions, 88 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index ec54413fb31f..a0041360ee9d 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -26,6 +26,7 @@
 #include "mib.h"
 
 #include <trace/events/mptcp.h>
+#include <trace/events/sock.h>
 
 static void mptcp_subflow_ops_undo_override(struct sock *ssk);
 
@@ -396,10 +397,15 @@ void mptcp_subflow_reset(struct sock *ssk)
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = subflow->conn;
 
+	/* mptcp_mp_fail_no_response() can reach here on an already closed
+	 * socket
+	 */
+	if (ssk->sk_state == TCP_CLOSE)
+		return;
+
 	/* must hold: tcp_done() could drop last reference on parent */
 	sock_hold(sk);
 
-	tcp_set_state(ssk, TCP_CLOSE);
 	tcp_send_active_reset(ssk, GFP_ATOMIC);
 	tcp_done(ssk);
 	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) &&
@@ -621,7 +627,7 @@ static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init
 static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init;
 static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init;
 static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init;
-static struct proto tcpv6_prot_override;
+static struct proto tcpv6_prot_override __ro_after_init;
 
 static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 {
@@ -692,9 +698,10 @@ static bool subflow_hmac_valid(const struct request_sock *req,
 
 static void mptcp_force_close(struct sock *sk)
 {
-	/* the msk is not yet exposed to user-space */
+	/* the msk is not yet exposed to user-space, and refcount is 2 */
 	inet_sk_state_store(sk, TCP_CLOSE);
 	sk_common_release(sk);
+	sock_put(sk);
 }
 
 static void subflow_ulp_fallback(struct sock *sk,
@@ -710,7 +717,7 @@ static void subflow_ulp_fallback(struct sock *sk,
 	mptcp_subflow_ops_undo_override(sk);
 }
 
-static void subflow_drop_ctx(struct sock *ssk)
+void mptcp_subflow_drop_ctx(struct sock *ssk)
 {
 	struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk);
 
@@ -749,6 +756,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_options_received mp_opt;
 	bool fallback, fallback_is_fatal;
 	struct sock *new_msk = NULL;
+	struct mptcp_sock *owner;
 	struct sock *child;
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
@@ -815,7 +823,7 @@ create_child:
 
 			if (new_msk)
 				mptcp_copy_inaddrs(new_msk, child);
-			subflow_drop_ctx(child);
+			mptcp_subflow_drop_ctx(child);
 			goto out;
 		}
 
@@ -823,6 +831,8 @@ create_child:
 		ctx->setsockopt_seq = listener->setsockopt_seq;
 
 		if (ctx->mp_capable) {
+			owner = mptcp_sk(new_msk);
+
 			/* this can't race with mptcp_close(), as the msk is
 			 * not yet exposted to user-space
 			 */
@@ -831,14 +841,14 @@ create_child:
 			/* record the newly created socket as the first msk
 			 * subflow, but don't link it yet into conn_list
 			 */
-			WRITE_ONCE(mptcp_sk(new_msk)->first, child);
+			WRITE_ONCE(owner->first, child);
 
 			/* new mpc subflow takes ownership of the newly
 			 * created mptcp socket
 			 */
 			mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq;
-			mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1);
-			mptcp_token_accept(subflow_req, mptcp_sk(new_msk));
+			mptcp_pm_new_connection(owner, child, 1);
+			mptcp_token_accept(subflow_req, owner);
 			ctx->conn = new_msk;
 			new_msk = NULL;
 
@@ -846,15 +856,21 @@ create_child:
 			 * uses the correct data
 			 */
 			mptcp_copy_inaddrs(ctx->conn, child);
+			mptcp_propagate_sndbuf(ctx->conn, child);
+
+			mptcp_rcv_space_init(owner, child);
+			list_add(&ctx->node, &owner->conn_list);
+			sock_hold(child);
 
 			/* with OoO packets we can reach here without ingress
 			 * mpc option
 			 */
-			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK)
+			if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) {
 				mptcp_subflow_fully_established(ctx, &mp_opt);
+				mptcp_pm_fully_established(owner, child, GFP_ATOMIC);
+				ctx->pm_notified = 1;
+			}
 		} else if (ctx->mp_join) {
-			struct mptcp_sock *owner;
-
 			owner = subflow_req->msk;
 			if (!owner) {
 				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
@@ -898,7 +914,7 @@ out:
 	return child;
 
 dispose_child:
-	subflow_drop_ctx(child);
+	mptcp_subflow_drop_ctx(child);
 	tcp_rsk(req)->drop_req = true;
 	inet_csk_prepare_for_destroy_sock(child);
 	tcp_done(child);
@@ -909,7 +925,7 @@ dispose_child:
 }
 
 static struct inet_connection_sock_af_ops subflow_specific __ro_after_init;
-static struct proto tcp_prot_override;
+static struct proto tcp_prot_override __ro_after_init;
 
 enum mapping_status {
 	MAPPING_OK,
@@ -1399,6 +1415,7 @@ void __mptcp_error_report(struct sock *sk)
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
 		int err = sock_error(ssk);
+		int ssk_state;
 
 		if (!err)
 			continue;
@@ -1409,7 +1426,14 @@ void __mptcp_error_report(struct sock *sk)
 		if (sk->sk_state != TCP_SYN_SENT && !__mptcp_check_fallback(msk))
 			continue;
 
-		inet_sk_state_store(sk, inet_sk_state_load(ssk));
+		/* We need to propagate only transition to CLOSE state.
+		 * Orphaned socket will see such state change via
+		 * subflow_sched_work_if_closed() and that path will properly
+		 * destroy the msk as needed.
+		 */
+		ssk_state = inet_sk_state_load(ssk);
+		if (ssk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DEAD))
+			inet_sk_state_store(sk, ssk_state);
 		sk->sk_err = -err;
 
 		/* This barrier is coupled with smp_rmb() in mptcp_poll() */
@@ -1423,6 +1447,13 @@ static void subflow_error_report(struct sock *ssk)
 {
 	struct sock *sk = mptcp_subflow_ctx(ssk)->conn;
 
+	/* bail early if this is a no-op, so that we avoid introducing a
+	 * problematic lockdep dependency between TCP accept queue lock
+	 * and msk socket spinlock
+	 */
+	if (!sk->sk_socket)
+		return;
+
 	mptcp_data_lock(sk);
 	if (!sock_owned_by_user(sk))
 		__mptcp_error_report(sk);
@@ -1438,6 +1469,8 @@ static void subflow_data_ready(struct sock *sk)
 	struct sock *parent = subflow->conn;
 	struct mptcp_sock *msk;
 
+	trace_sk_data_ready(sk);
+
 	msk = mptcp_sk(parent);
 	if (state & TCPF_LISTEN) {
 		/* MPJ subflow are removed from accept queue before reaching here,
@@ -1679,7 +1712,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	if (err)
 		return err;
 
-	lock_sock(sf->sk);
+	lock_sock_nested(sf->sk, SINGLE_DEPTH_NESTING);
 
 	/* the newly created socket has to be in the same cgroup as its parent */
 	mptcp_attach_cgroup(sk, sf->sk);
@@ -1792,79 +1825,6 @@ static void subflow_state_change(struct sock *sk)
 	}
 }
 
-void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)
-{
-	struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue;
-	struct mptcp_sock *msk, *next, *head = NULL;
-	struct request_sock *req;
-
-	/* build a list of all unaccepted mptcp sockets */
-	spin_lock_bh(&queue->rskq_lock);
-	for (req = queue->rskq_accept_head; req; req = req->dl_next) {
-		struct mptcp_subflow_context *subflow;
-		struct sock *ssk = req->sk;
-		struct mptcp_sock *msk;
-
-		if (!sk_is_mptcp(ssk))
-			continue;
-
-		subflow = mptcp_subflow_ctx(ssk);
-		if (!subflow || !subflow->conn)
-			continue;
-
-		/* skip if already in list */
-		msk = mptcp_sk(subflow->conn);
-		if (msk->dl_next || msk == head)
-			continue;
-
-		msk->dl_next = head;
-		head = msk;
-	}
-	spin_unlock_bh(&queue->rskq_lock);
-	if (!head)
-		return;
-
-	/* can't acquire the msk socket lock under the subflow one,
-	 * or will cause ABBA deadlock
-	 */
-	release_sock(listener_ssk);
-
-	for (msk = head; msk; msk = next) {
-		struct sock *sk = (struct sock *)msk;
-		bool do_cancel_work;
-
-		sock_hold(sk);
-		lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
-		next = msk->dl_next;
-		msk->first = NULL;
-		msk->dl_next = NULL;
-
-		do_cancel_work = __mptcp_close(sk, 0);
-		release_sock(sk);
-		if (do_cancel_work) {
-			/* lockdep will report a false positive ABBA deadlock
-			 * between cancel_work_sync and the listener socket.
-			 * The involved locks belong to different sockets WRT
-			 * the existing AB chain.
-			 * Using a per socket key is problematic as key
-			 * deregistration requires process context and must be
-			 * performed at socket disposal time, in atomic
-			 * context.
-			 * Just tell lockdep to consider the listener socket
-			 * released here.
-			 */
-			mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_);
-			mptcp_cancel_work(sk);
-			mutex_acquire(&listener_sk->sk_lock.dep_map,
-				      SINGLE_DEPTH_NESTING, 0, _RET_IP_);
-		}
-		sock_put(sk);
-	}
-
-	/* we are still under the listener msk socket lock */
-	lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING);
-}
-
 static int subflow_ulp_init(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -1921,6 +1881,13 @@ static void subflow_ulp_release(struct sock *ssk)
 		 * when the subflow is still unaccepted
 		 */
 		release = ctx->disposable || list_empty(&ctx->node);
+
+		/* inet_child_forget() does not call sk_state_change(),
+		 * explicitly trigger the socket close machinery
+		 */
+		if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW,
+						  &mptcp_sk(sk)->flags))
+			mptcp_schedule_work(sk);
 		sock_put(sk);
 	}