Merge tag 'v5.13-rc2' into spi-5.13

Linux 5.13-rc2

1 files changed, 58 insertions, 22 deletions

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index e1fbcab257e6..a5ede357cfbc 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -25,6 +25,8 @@
 #include "protocol.h"
 #include "mib.h"
 
+#include <trace/events/mptcp.h>
+
 static void mptcp_subflow_ops_undo_override(struct sock *ssk);
 
 static void SUBFLOW_REQ_INC_STATS(struct request_sock *req,
@@ -115,6 +117,16 @@ static bool subflow_use_different_sport(struct mptcp_sock *msk, const struct soc
 	return inet_sk(sk)->inet_sport != inet_sk((struct sock *)msk)->inet_sport;
 }
 
+static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
+{
+	struct mptcp_ext *mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
+
+	if (mpext) {
+		memset(mpext, 0, sizeof(*mpext));
+		mpext->reset_reason = reason;
+	}
+}
+
 /* Init mptcp request socket.
  *
  * Returns an error code if a JOIN has failed and a TCP reset
@@ -165,6 +177,7 @@ again:
 			if (mptcp_token_exists(subflow_req->token)) {
 				if (retries-- > 0)
 					goto again;
+				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
 			} else {
 				subflow_req->mp_capable = 1;
 			}
@@ -176,6 +189,8 @@ again:
 			subflow_req->mp_capable = 1;
 		else if (retries-- > 0)
 			goto again;
+		else
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_TOKENFALLBACKINIT);
 
 	} else if (mp_opt.mp_join && listener->request_mptcp) {
 		subflow_req->ssn_offset = TCP_SKB_CB(skb)->seq;
@@ -187,8 +202,10 @@ again:
 		subflow_req->msk = subflow_token_join_request(req);
 
 		/* Can't fall back to TCP in this case. */
-		if (!subflow_req->msk)
+		if (!subflow_req->msk) {
+			subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
 			return -EPERM;
+		}
 
 		if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
 			pr_debug("syn inet_sport=%d %d",
@@ -392,12 +409,15 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->remote_key = mp_opt.sndr_key;
 		pr_debug("subflow=%p, remote_key=%llu", subflow,
 			 subflow->remote_key);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK);
 		mptcp_finish_connect(sk);
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
-		if (!mp_opt.mp_join)
+		if (!mp_opt.mp_join) {
+			subflow->reset_reason = MPTCP_RST_EMPTCP;
 			goto do_reset;
+		}
 
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
@@ -406,6 +426,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 		if (!subflow_thmac_valid(subflow)) {
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
+			subflow->reset_reason = MPTCP_RST_EMPTCP;
 			goto do_reset;
 		}
 
@@ -434,6 +455,7 @@ fallback:
 	return;
 
 do_reset:
+	subflow->reset_transient = 0;
 	mptcp_subflow_reset(sk);
 }
 
@@ -477,6 +499,11 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (!ipv6_unicast_destination(skb))
 		goto drop;
 
+	if (ipv6_addr_v4mapped(&ipv6_hdr(skb)->saddr)) {
+		__IP6_INC_STATS(sock_net(sk), NULL, IPSTATS_MIB_INHDRERRORS);
+		return 0;
+	}
+
 	return tcp_conn_request(&mptcp_subflow_request_sock_ops,
 				&subflow_request_sock_ipv6_ops, sk, skb);
 
@@ -519,8 +546,7 @@ static void mptcp_sock_destruct(struct sock *sk)
 	 * ESTABLISHED state and will not have the SOCK_DEAD flag.
 	 * Both result in warnings from inet_sock_destruct.
 	 */
-
-	if (sk->sk_state == TCP_ESTABLISHED) {
+	if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
 		sk->sk_state = TCP_CLOSE;
 		WARN_ON_ONCE(sk->sk_socket);
 		sock_orphan(sk);
@@ -645,13 +671,18 @@ create_child:
 		 * to reset the context to non MPTCP status.
 		 */
 		if (!ctx || fallback) {
-			if (fallback_is_fatal)
+			if (fallback_is_fatal) {
+				subflow_add_reset_reason(skb, MPTCP_RST_EMPTCP);
 				goto dispose_child;
+			}
 
 			subflow_drop_ctx(child);
 			goto out;
 		}
 
+		/* ssk inherits options of listener sk */
+		ctx->setsockopt_seq = listener->setsockopt_seq;
+
 		if (ctx->mp_capable) {
 			/* this can't race with mptcp_close(), as the msk is
 			 * not yet exposted to user-space
@@ -667,6 +698,7 @@ create_child:
 			 * created mptcp socket
 			 */
 			new_msk->sk_destruct = mptcp_sock_destruct;
+			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));
 			ctx->conn = new_msk;
@@ -681,17 +713,14 @@ create_child:
 			struct mptcp_sock *owner;
 
 			owner = subflow_req->msk;
-			if (!owner)
+			if (!owner) {
+				subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
 				goto dispose_child;
+			}
 
 			/* move the msk reference ownership to the subflow */
 			subflow_req->msk = NULL;
 			ctx->conn = (struct sock *)owner;
-			if (!mptcp_finish_join(child))
-				goto dispose_child;
-
-			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
-			tcp_rsk(req)->drop_req = true;
 
 			if (subflow_use_different_sport(owner, sk)) {
 				pr_debug("ack inet_sport=%d %d",
@@ -699,10 +728,16 @@ create_child:
 					 ntohs(inet_sk((struct sock *)owner)->inet_sport));
 				if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
 					SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MISMATCHPORTACKRX);
-					goto out;
+					goto dispose_child;
 				}
 				SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINPORTACKRX);
 			}
+
+			if (!mptcp_finish_join(child))
+				goto dispose_child;
+
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINACKRX);
+			tcp_rsk(req)->drop_req = true;
 		}
 	}
 
@@ -828,9 +863,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 		goto validate_seq;
 	}
 
-	pr_debug("seq=%llu is64=%d ssn=%u data_len=%u data_fin=%d",
-		 mpext->data_seq, mpext->dsn64, mpext->subflow_seq,
-		 mpext->data_len, mpext->data_fin);
+	trace_get_mapping_status(mpext);
 
 	data_len = mpext->data_len;
 	if (data_len == 0) {
@@ -968,8 +1001,6 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	struct mptcp_sock *msk;
 	struct sk_buff *skb;
 
-	pr_debug("msk=%p ssk=%p data_avail=%d skb=%p", subflow->conn, ssk,
-		 subflow->data_avail, skb_peek(&ssk->sk_receive_queue));
 	if (!skb_peek(&ssk->sk_receive_queue))
 		subflow->data_avail = 0;
 	if (subflow->data_avail)
@@ -981,7 +1012,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 		u64 old_ack;
 
 		status = get_mapping_status(ssk, msk);
-		pr_debug("msk=%p ssk=%p status=%d", msk, ssk, status);
+		trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue));
 		if (status == MAPPING_INVALID) {
 			ssk->sk_err = EBADMSG;
 			goto fatal;
@@ -1046,6 +1077,8 @@ fatal:
 	smp_wmb();
 	ssk->sk_error_report(ssk);
 	tcp_set_state(ssk, TCP_CLOSE);
+	subflow->reset_transient = 0;
+	subflow->reset_reason = MPTCP_RST_EMPTCP;
 	tcp_send_active_reset(ssk, GFP_ATOMIC);
 	subflow->data_avail = 0;
 	return false;
@@ -1075,7 +1108,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
  * In mptcp, rwin is about the mptcp-level connection data.
  *
  * Data that is still on the ssk rx queue can thus be ignored,
- * as far as mptcp peer is concerened that data is still inflight.
+ * as far as mptcp peer is concerned that data is still inflight.
  * DSS ACK is updated when skb is moved to the mptcp rx queue.
  */
 void mptcp_space(const struct sock *ssk, int *space, int *full_space)
@@ -1224,7 +1257,8 @@ void mptcp_info2sockaddr(const struct mptcp_addr_info *info,
 }
 
 int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
-			    const struct mptcp_addr_info *remote)
+			    const struct mptcp_addr_info *remote,
+			    u8 flags, int ifindex)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct mptcp_subflow_context *subflow;
@@ -1268,7 +1302,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	if (addr.ss_family == AF_INET6)
 		addrlen = sizeof(struct sockaddr_in6);
 #endif
-	ssk->sk_bound_dev_if = loc->ifindex;
+	ssk->sk_bound_dev_if = ifindex;
 	err = kernel_bind(sf, (struct sockaddr *)&addr, addrlen);
 	if (err)
 		goto failed;
@@ -1280,10 +1314,11 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
 	subflow->local_id = local_id;
 	subflow->remote_id = remote_id;
 	subflow->request_join = 1;
-	subflow->request_bkup = !!(loc->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	mptcp_info2sockaddr(remote, &addr, ssk->sk_family);
 
 	mptcp_add_pending_subflow(msk, subflow);
+	mptcp_sockopt_sync(msk, ssk);
 	err = kernel_connect(sf, (struct sockaddr *)&addr, addrlen, O_NONBLOCK);
 	if (err && err != -EINPROGRESS)
 		goto failed_unlink;
@@ -1297,6 +1332,7 @@ failed_unlink:
 	spin_lock_bh(&msk->join_list_lock);
 	list_del(&subflow->node);
 	spin_unlock_bh(&msk->join_list_lock);
+	sock_put(mptcp_subflow_tcp_sock(subflow));
 
 failed:
 	subflow->disposable = 1;