Merging upstream version 6.10.4.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

9 files changed, 108 insertions, 22 deletions

diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
index c30405e768..7884217f33 100644
--- a/net/mptcp/mib.c
+++ b/net/mptcp/mib.c
@@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
 	SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
 	SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
+	SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
 	SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
+	SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
 	SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
 	SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
 	SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
index 2704afd0df..66aa67f49d 100644
--- a/net/mptcp/mib.h
+++ b/net/mptcp/mib.h
@@ -14,7 +14,9 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_RETRANSSEGS,		/* Segments retransmitted at the MPTCP-level */
 	MPTCP_MIB_JOINNOTOKEN,		/* Received MP_JOIN but the token was not found */
 	MPTCP_MIB_JOINSYNRX,		/* Received a SYN + MP_JOIN */
+	MPTCP_MIB_JOINSYNBACKUPRX,	/* Received a SYN + MP_JOIN + backup flag */
 	MPTCP_MIB_JOINSYNACKRX,		/* Received a SYN/ACK + MP_JOIN */
+	MPTCP_MIB_JOINSYNACKBACKUPRX,	/* Received a SYN/ACK + MP_JOIN + backup flag */
 	MPTCP_MIB_JOINSYNACKMAC,	/* HMAC was wrong on SYN/ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKRX,		/* Received an ACK + MP_JOIN */
 	MPTCP_MIB_JOINACKMAC,		/* HMAC was wrong on ACK + MP_JOIN */
diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 8e8dcfbc29..8a68382a4f 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 		return true;
 	} else if (subflow_req->mp_join) {
 		opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
-		opts->backup = subflow_req->backup;
+		opts->backup = subflow_req->request_bkup;
 		opts->join_id = subflow_req->local_id;
 		opts->thmac = subflow_req->thmac;
 		opts->nonce = subflow_req->local_nonce;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 55406720c6..23bb89c94e 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_get_local_id(msk, &skc_local);
 }
 
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+{
+	struct mptcp_addr_info skc_local;
+
+	mptcp_local_address((struct sock_common *)skc, &skc_local);
+
+	if (mptcp_pm_is_userspace(msk))
+		return mptcp_userspace_pm_is_backup(msk, &skc_local);
+
+	return mptcp_pm_nl_is_backup(msk, &skc_local);
+}
+
 int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
 					 u8 *flags, int *ifindex)
 {
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ea9e5817b9..37954a0b08 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -471,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
 	slow = lock_sock_fast(ssk);
 	if (prio) {
 		subflow->send_mp_prio = 1;
-		subflow->backup = backup;
 		subflow->request_bkup = backup;
 	}
 
@@ -1102,6 +1101,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	return ret;
 }
 
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+	struct mptcp_pm_addr_entry *entry;
+	bool backup = false;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return backup;
+}
+
 #define MPTCP_PM_CMD_GRP_OFFSET       0
 #define MPTCP_PM_EV_GRP_OFFSET        1
 
@@ -1401,6 +1418,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
 	ret = remove_anno_list_by_saddr(msk, addr);
 	if (ret || force) {
 		spin_lock_bh(&msk->pm.lock);
+		msk->pm.add_addr_signaled -= ret;
 		mptcp_pm_remove_addr(msk, &list);
 		spin_unlock_bh(&msk->pm.lock);
 	}
@@ -1534,16 +1552,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
 {
 	struct mptcp_rm_list alist = { .nr = 0 };
 	struct mptcp_pm_addr_entry *entry;
+	int anno_nr = 0;
 
 	list_for_each_entry(entry, rm_list, list) {
-		if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
-		     lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
-		    alist.nr < MPTCP_RM_IDS_MAX)
-			alist.ids[alist.nr++] = entry->addr.id;
+		if (alist.nr >= MPTCP_RM_IDS_MAX)
+			break;
+
+		/* only delete if either announced or matching a subflow */
+		if (remove_anno_list_by_saddr(msk, &entry->addr))
+			anno_nr++;
+		else if (!lookup_subflow_by_saddr(&msk->conn_list,
+						  &entry->addr))
+			continue;
+
+		alist.ids[alist.nr++] = entry->addr.id;
 	}
 
 	if (alist.nr) {
 		spin_lock_bh(&msk->pm.lock);
+		msk->pm.add_addr_signaled -= anno_nr;
 		mptcp_pm_remove_addr(msk, &alist);
 		spin_unlock_bh(&msk->pm.lock);
 	}
@@ -1556,17 +1583,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 	struct mptcp_pm_addr_entry *entry;
 
 	list_for_each_entry(entry, rm_list, list) {
-		if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
-		    slist.nr < MPTCP_RM_IDS_MAX)
+		if (slist.nr < MPTCP_RM_IDS_MAX &&
+		    lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
 			slist.ids[slist.nr++] = entry->addr.id;
 
-		if (remove_anno_list_by_saddr(msk, &entry->addr) &&
-		    alist.nr < MPTCP_RM_IDS_MAX)
+		if (alist.nr < MPTCP_RM_IDS_MAX &&
+		    remove_anno_list_by_saddr(msk, &entry->addr))
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
 	if (alist.nr) {
 		spin_lock_bh(&msk->pm.lock);
+		msk->pm.add_addr_signaled -= alist.nr;
 		mptcp_pm_remove_addr(msk, &alist);
 		spin_unlock_bh(&msk->pm.lock);
 	}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index f0a4590506..8eaa9fbe3e 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
 }
 
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+				  struct mptcp_addr_info *skc)
+{
+	struct mptcp_pm_addr_entry *entry;
+	bool backup = false;
+
+	spin_lock_bh(&msk->pm.lock);
+	list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, skc, false)) {
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+			break;
+		}
+	}
+	spin_unlock_bh(&msk->pm.lock);
+
+	return backup;
+}
+
 int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index bb7dca8aa2..ff8292d0cf 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	skb_orphan(skb);
 
 	/* try to fetch required memory from subflow */
-	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
+	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
 		goto drop;
+	}
 
 	has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
 
@@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 		sk_rbuf = ssk_rbuf;
 
 	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (__mptcp_rmem(sk) > sk_rbuf) {
-		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+	if (__mptcp_rmem(sk) > sk_rbuf)
 		return;
-	}
 
 	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
@@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 	}
 
 	mptcp_for_each_subflow(msk, subflow) {
+		bool backup = subflow->backup || subflow->request_bkup;
+
 		trace_mptcp_subflow_get_send(subflow);
 		ssk =  mptcp_subflow_tcp_sock(subflow);
 		if (!mptcp_subflow_active(subflow))
 			continue;
 
 		tout = max(tout, mptcp_timeout_from_subflow(subflow));
-		nr_active += !subflow->backup;
+		nr_active += !backup;
 		pace = subflow->avg_pacing_rate;
 		if (unlikely(!pace)) {
 			/* init pacing rate from socket */
@@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
 		}
 
 		linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
-		if (linger_time < send_info[subflow->backup].linger_time) {
-			send_info[subflow->backup].ssk = ssk;
-			send_info[subflow->backup].linger_time = linger_time;
+		if (linger_time < send_info[backup].linger_time) {
+			send_info[backup].ssk = ssk;
+			send_info[backup].linger_time = linger_time;
 		}
 	}
 	__mptcp_set_timeout(sk, tout);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7aa47e2dd5..8357046732 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -443,6 +443,7 @@ struct mptcp_subflow_request_sock {
 	u16	mp_capable : 1,
 		mp_join : 1,
 		backup : 1,
+		request_bkup : 1,
 		csum_reqd : 1,
 		allow_join_id0 : 1;
 	u8	local_id;
@@ -1103,6 +1104,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
 int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 612c38570a..c330946384 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
 		return NULL;
 	}
 	subflow_req->local_id = local_id;
+	subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
 
 	return msk;
 }
@@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req,
 			return 0;
 	} else if (opt_mp_join) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
+
+		if (mp_opt.backup)
+			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
 	}
 
 	if (opt_mp_capable && listener->request_mptcp) {
@@ -577,6 +581,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 		subflow->mp_join = 1;
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
 
+		if (subflow->backup)
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
 		if (subflow_use_different_dport(msk, sk)) {
 			pr_debug("synack inet_dport=%d %d",
 				 ntohs(inet_sk(sk)->inet_dport),
@@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk)
 		return err;
 
 	subflow_set_local_id(subflow, err);
+	subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
+
 	return 0;
 }
 
@@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
-	u32 incr;
+	struct tcp_sock *tp = tcp_sk(ssk);
+	u32 offset, incr, avail_len;
 
-	incr = limit >= skb->len ? skb->len + fin : limit;
+	offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
+	if (WARN_ON_ONCE(offset > skb->len))
+		goto out;
 
-	pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
-		 subflow->map_subflow_seq);
+	avail_len = skb->len - offset;
+	incr = limit >= avail_len ? avail_len + fin : limit;
+
+	pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
+		 offset, subflow->map_subflow_seq);
 	MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
 	tcp_sk(ssk)->copied_seq += incr;
+
+out:
 	if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
 		sk_eat_skb(ssk, skb);
 	if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
@@ -2005,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
 		new_ctx->fully_established = 1;
 		new_ctx->remote_key_valid = 1;
 		new_ctx->backup = subflow_req->backup;
+		new_ctx->request_bkup = subflow_req->request_bkup;
 		WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
 		new_ctx->token = subflow_req->token;
 		new_ctx->thmac = subflow_req->thmac;