Merge branch 'mptcp-path-manager-fixes'

Mat Martineau says:

====================
mptcp: Path manager fixes for 5.19

The MPTCP userspace path manager is new in 5.19, and these patches fix
some issues in that new code.

Patches 1-3 fix path manager locking issues.

Patches 4 and 5 allow userspace path managers to change priority of
established subflows using the existing MPTCP_PM_CMD_SET_FLAGS generic
netlink command. Includes corresponding self test update.

Patches 6 and 7 fix accounting of available endpoint IDs and the
MPTCP_MIB_RMSUBFLOW counter.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 192 insertions, 31 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index aead331866a0..bd8f0f425be4 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -1584,6 +1584,9 @@ mp_rst:
 		*ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
 				      TCPOLEN_MPTCP_PRIO,
 				      opts->backup, TCPOPT_NOP);
+
+		MPTCP_INC_STATS(sock_net((const struct sock *)tp),
+				MPTCP_MIB_MPPRIOTX);
 	}
 
 mp_capable_done:
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index e099f2a12504..7c7395b58944 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -717,9 +717,10 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
 	}
 }
 
-static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
-					struct mptcp_addr_info *addr,
-					u8 bkup)
+int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+				 struct mptcp_addr_info *addr,
+				 struct mptcp_addr_info *rem,
+				 u8 bkup)
 {
 	struct mptcp_subflow_context *subflow;
 
@@ -727,24 +728,29 @@ static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		struct sock *sk = (struct sock *)msk;
-		struct mptcp_addr_info local;
+		struct mptcp_addr_info local, remote;
+		bool slow;
 
 		local_address((struct sock_common *)ssk, &local);
 		if (!mptcp_addresses_equal(&local, addr, addr->port))
 			continue;
 
+		if (rem && rem->family != AF_UNSPEC) {
+			remote_address((struct sock_common *)ssk, &remote);
+			if (!mptcp_addresses_equal(&remote, rem, rem->port))
+				continue;
+		}
+
+		slow = lock_sock_fast(ssk);
 		if (subflow->backup != bkup)
 			msk->last_snd = NULL;
 		subflow->backup = bkup;
 		subflow->send_mp_prio = 1;
 		subflow->request_bkup = bkup;
-		__MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIOTX);
 
-		spin_unlock_bh(&msk->pm.lock);
 		pr_debug("send ack for mp_prio");
-		mptcp_subflow_send_ack(ssk);
-		spin_lock_bh(&msk->pm.lock);
+		__mptcp_subflow_send_ack(ssk);
+		unlock_sock_fast(ssk, slow);
 
 		return 0;
 	}
@@ -801,7 +807,8 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			removed = true;
 			__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
-		__set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap);
+		if (rm_type == MPTCP_MIB_RMSUBFLOW)
+			__set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap);
 		if (!removed)
 			continue;
 
@@ -1816,8 +1823,10 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 
 	list.ids[list.nr++] = addr->id;
 
+	spin_lock_bh(&msk->pm.lock);
 	mptcp_pm_nl_rm_subflow_received(msk, &list);
 	mptcp_pm_create_subflow_or_signal_addr(msk);
+	spin_unlock_bh(&msk->pm.lock);
 }
 
 static int mptcp_nl_set_flags(struct net *net,
@@ -1835,12 +1844,10 @@ static int mptcp_nl_set_flags(struct net *net,
 			goto next;
 
 		lock_sock(sk);
-		spin_lock_bh(&msk->pm.lock);
 		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
-			ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup);
+			ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
 		if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
 			mptcp_pm_nl_fullmesh(msk, addr);
-		spin_unlock_bh(&msk->pm.lock);
 		release_sock(sk);
 
 next:
@@ -1854,6 +1861,9 @@ next:
 static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry;
+	struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, };
+	struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
+	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
 	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
@@ -1866,6 +1876,12 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		return ret;
 
+	if (attr_rem) {
+		ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote);
+		if (ret < 0)
+			return ret;
+	}
+
 	if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
 		bkup = 1;
 	if (addr.addr.family == AF_UNSPEC) {
@@ -1874,6 +1890,10 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info)
 			return -EOPNOTSUPP;
 	}
 
+	if (token)
+		return mptcp_userspace_pm_set_flags(sock_net(skb->sk),
+						    token, &addr, &remote, bkup);
+
 	spin_lock_bh(&pernet->lock);
 	entry = __lookup_addr(pernet, &addr.addr, lookup_by_id);
 	if (!entry) {
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index f56378e4f597..9e82250cbb70 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -5,6 +5,7 @@
  */
 
 #include "protocol.h"
+#include "mib.h"
 
 void mptcp_free_local_addr_list(struct mptcp_sock *msk)
 {
@@ -306,15 +307,11 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
 				      const struct mptcp_addr_info *local,
 				      const struct mptcp_addr_info *remote)
 {
-	struct sock *sk = &msk->sk.icsk_inet.sk;
 	struct mptcp_subflow_context *subflow;
-	struct sock *found = NULL;
 
 	if (local->family != remote->family)
 		return NULL;
 
-	lock_sock(sk);
-
 	mptcp_for_each_subflow(msk, subflow) {
 		const struct inet_sock *issk;
 		struct sock *ssk;
@@ -347,16 +344,11 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
 		}
 
 		if (issk->inet_sport == local->port &&
-		    issk->inet_dport == remote->port) {
-			found = ssk;
-			goto found;
-		}
+		    issk->inet_dport == remote->port)
+			return ssk;
 	}
 
-found:
-	release_sock(sk);
-
-	return found;
+	return NULL;
 }
 
 int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info)
@@ -412,18 +404,51 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	sk = &msk->sk.icsk_inet.sk;
+	lock_sock(sk);
 	ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r);
 	if (ssk) {
 		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 
 		mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN);
 		mptcp_close_ssk(sk, ssk, subflow);
+		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW);
 		err = 0;
 	} else {
 		err = -ESRCH;
 	}
+	release_sock(sk);
 
- destroy_err:
+destroy_err:
 	sock_put((struct sock *)msk);
 	return err;
 }
+
+int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
+				 struct mptcp_pm_addr_entry *loc,
+				 struct mptcp_pm_addr_entry *rem, u8 bkup)
+{
+	struct mptcp_sock *msk;
+	int ret = -EINVAL;
+	u32 token_val;
+
+	token_val = nla_get_u32(token);
+
+	msk = mptcp_token_get_sock(net, token_val);
+	if (!msk)
+		return ret;
+
+	if (!mptcp_pm_is_userspace(msk))
+		goto set_flags_err;
+
+	if (loc->addr.family == AF_UNSPEC ||
+	    rem->addr.family == AF_UNSPEC)
+		goto set_flags_err;
+
+	lock_sock((struct sock *)msk);
+	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup);
+	release_sock((struct sock *)msk);
+
+set_flags_err:
+	sock_put((struct sock *)msk);
+	return ret;
+}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index e475212f2618..cc21fafd9726 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -506,13 +506,18 @@ static inline bool tcp_can_send_ack(const struct sock *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);
 }
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c14d70c036d0..480c5320b86e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -607,6 +607,7 @@ void __init mptcp_subflow_init(void);
 void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how);
 void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
 		     struct mptcp_subflow_context *subflow);
+void __mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_send_ack(struct sock *ssk);
 void mptcp_subflow_reset(struct sock *ssk);
 void mptcp_subflow_queue_clean(struct sock *ssk);
@@ -771,6 +772,10 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);
 void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
 void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq);
+int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+				 struct mptcp_addr_info *addr,
+				 struct mptcp_addr_info *rem,
+				 u8 bkup);
 bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 			      const struct mptcp_pm_addr_entry *entry);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
@@ -787,7 +792,9 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
 int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk,
 						   unsigned int id,
 						   u8 *flags, int *ifindex);
-
+int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token,
+				 struct mptcp_pm_addr_entry *loc,
+				 struct mptcp_pm_addr_entry *rem, u8 bkup);
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
 			   bool echo);
diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
index 6a2f4b981e1d..cb79f0719e3b 100644
--- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
+++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c
@@ -39,7 +39,7 @@ static void syntax(char *argv[])
 	fprintf(stderr, "\tdsf lip <local-ip> lport <local-port> rip <remote-ip> rport <remote-port> token <token>\n");
 	fprintf(stderr, "\tdel <id> [<ip>]\n");
 	fprintf(stderr, "\tget <id>\n");
-	fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>]\n");
+	fprintf(stderr, "\tset [<ip>] [id <nr>] flags [no]backup|[no]fullmesh [port <nr>] [token <token>] [rip <ip>] [rport <port>]\n");
 	fprintf(stderr, "\tflush\n");
 	fprintf(stderr, "\tdump\n");
 	fprintf(stderr, "\tlimits [<rcv addr max> <subflow max>]\n");
@@ -1279,7 +1279,10 @@ int set_flags(int fd, int pm_family, int argc, char *argv[])
 	struct rtattr *rta, *nest;
 	struct nlmsghdr *nh;
 	u_int32_t flags = 0;
+	u_int32_t token = 0;
+	u_int16_t rport = 0;
 	u_int16_t family;
+	void *rip = NULL;
 	int nest_start;
 	int use_id = 0;
 	u_int8_t id;
@@ -1339,7 +1342,13 @@ int set_flags(int fd, int pm_family, int argc, char *argv[])
 		error(1, 0, " missing flags keyword");
 
 	for (; arg < argc; arg++) {
-		if (!strcmp(argv[arg], "flags")) {
+		if (!strcmp(argv[arg], "token")) {
+			if (++arg >= argc)
+				error(1, 0, " missing token value");
+
+			/* token */
+			token = atoi(argv[arg]);
+		} else if (!strcmp(argv[arg], "flags")) {
 			char *tok, *str;
 
 			/* flags */
@@ -1378,12 +1387,72 @@ int set_flags(int fd, int pm_family, int argc, char *argv[])
 			rta->rta_len = RTA_LENGTH(2);
 			memcpy(RTA_DATA(rta), &port, 2);
 			off += NLMSG_ALIGN(rta->rta_len);
+		} else if (!strcmp(argv[arg], "rport")) {
+			if (++arg >= argc)
+				error(1, 0, " missing remote port");
+
+			rport = atoi(argv[arg]);
+		} else if (!strcmp(argv[arg], "rip")) {
+			if (++arg >= argc)
+				error(1, 0, " missing remote ip");
+
+			rip = argv[arg];
 		} else {
 			error(1, 0, "unknown keyword %s", argv[arg]);
 		}
 	}
 	nest->rta_len = off - nest_start;
 
+	/* token */
+	if (token) {
+		rta = (void *)(data + off);
+		rta->rta_type = MPTCP_PM_ATTR_TOKEN;
+		rta->rta_len = RTA_LENGTH(4);
+		memcpy(RTA_DATA(rta), &token, 4);
+		off += NLMSG_ALIGN(rta->rta_len);
+	}
+
+	/* remote addr/port */
+	if (rip) {
+		nest_start = off;
+		nest = (void *)(data + off);
+		nest->rta_type = NLA_F_NESTED | MPTCP_PM_ATTR_ADDR_REMOTE;
+		nest->rta_len = RTA_LENGTH(0);
+		off += NLMSG_ALIGN(nest->rta_len);
+
+		/* addr data */
+		rta = (void *)(data + off);
+		if (inet_pton(AF_INET, rip, RTA_DATA(rta))) {
+			family = AF_INET;
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR4;
+			rta->rta_len = RTA_LENGTH(4);
+		} else if (inet_pton(AF_INET6, rip, RTA_DATA(rta))) {
+			family = AF_INET6;
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_ADDR6;
+			rta->rta_len = RTA_LENGTH(16);
+		} else {
+			error(1, errno, "can't parse ip %s", (char *)rip);
+		}
+		off += NLMSG_ALIGN(rta->rta_len);
+
+		/* family */
+		rta = (void *)(data + off);
+		rta->rta_type = MPTCP_PM_ADDR_ATTR_FAMILY;
+		rta->rta_len = RTA_LENGTH(2);
+		memcpy(RTA_DATA(rta), &family, 2);
+		off += NLMSG_ALIGN(rta->rta_len);
+
+		if (rport) {
+			rta = (void *)(data + off);
+			rta->rta_type = MPTCP_PM_ADDR_ATTR_PORT;
+			rta->rta_len = RTA_LENGTH(2);
+			memcpy(RTA_DATA(rta), &rport, 2);
+			off += NLMSG_ALIGN(rta->rta_len);
+		}
+
+		nest->rta_len = off - nest_start;
+	}
+
 	do_nl_req(fd, nh, off, 0);
 	return 0;
 }
diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 78d0bb640b11..abe3d4ebe554 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -770,10 +770,42 @@ test_subflows()
 	rm -f "$evts"
 }
 
+test_prio()
+{
+	local count
+
+	# Send MP_PRIO signal from client to server machine
+	ip netns exec "$ns2" ./pm_nl_ctl set 10.0.1.2 port "$client4_port" flags backup token "$client4_token" rip 10.0.1.1 rport "$server4_port"
+	sleep 0.5
+
+	# Check TX
+	stdbuf -o0 -e0 printf "MP_PRIO TX                                                 \t"
+	count=$(ip netns exec "$ns2" nstat -as | grep MPTcpExtMPPrioTx | awk '{print $2}')
+	[ -z "$count" ] && count=0
+	if [ $count != 1 ]; then
+		stdbuf -o0 -e0 printf "[FAIL]\n"
+		exit 1
+	else
+		stdbuf -o0 -e0 printf "[OK]\n"
+	fi
+
+	# Check RX
+	stdbuf -o0 -e0 printf "MP_PRIO RX                                                 \t"
+	count=$(ip netns exec "$ns1" nstat -as | grep MPTcpExtMPPrioRx | awk '{print $2}')
+	[ -z "$count" ] && count=0
+	if [ $count != 1 ]; then
+		stdbuf -o0 -e0 printf "[FAIL]\n"
+		exit 1
+	else
+		stdbuf -o0 -e0 printf "[OK]\n"
+	fi
+}
+
 make_connection
 make_connection "v6"
 test_announce
 test_remove
 test_subflows
+test_prio
 
 exit 0