Merge branch 'mptcp-pm-misc-cleanups-part-3'

Matthieu Baerts says:

====================
mptcp: pm: misc cleanups, part 3

These cleanups lead the way to the unification of the path-manager
interfaces, and allow future extensions. The following patches are not
all linked to each others, but are all related to the path-managers,
except the last three.

- Patch 1: remove unused returned value in mptcp_nl_set_flags().
- Patch 2: new flag: avoid iterating over all connections if not needed.
- Patch 3: add a build check making sure there is enough space in cb-ctx.
- Patch 4: new mptcp_pm_genl_fill_addr helper to reduce duplicated code.
- Patch 5: simplify userspace_pm_append_new_local_addr helper.
- Patch 6: drop unneeded inet6_sk().
- Patch 7: use ipv6_addr_equal() instead of !ipv6_addr_cmp()
- Patch 8: scheduler: split an interface in two.
- Patch 9: scheduler: save 64 bytes of currently unused data.
- Patch 10: small optimisation to exit early in case of retransmissions.
====================

Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-0-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 93 insertions, 80 deletions

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 814b5f2e3ed5e..2c85ca92bb1c3 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -103,13 +103,14 @@ struct mptcp_out_options {
 #define MPTCP_SUBFLOWS_MAX	8
 
 struct mptcp_sched_data {
-	bool	reinject;
 	u8	subflows;
 	struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX];
 };
 
 struct mptcp_sched_ops {
-	int (*get_subflow)(struct mptcp_sock *msk,
+	int (*get_send)(struct mptcp_sock *msk,
+			struct mptcp_sched_data *data);
+	int (*get_retrans)(struct mptcp_sock *msk,
 			   struct mptcp_sched_data *data);
 
 	char			name[MPTCP_SCHED_NAME_MAX];
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 2dd81e6c26bdb..be6c0237e10bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -401,26 +401,30 @@ void mptcp_active_enable(struct sock *sk)
 void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
 {
 	struct mptcp_subflow_context *subflow;
+	u8 timeouts, to_max;
+	struct net *net;
 
-	if (!sk_is_mptcp(ssk))
+	/* Only check MPTCP SYN ... */
+	if (likely(!sk_is_mptcp(ssk) || ssk->sk_state != TCP_SYN_SENT))
 		return;
 
 	subflow = mptcp_subflow_ctx(ssk);
 
-	if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) {
-		struct net *net = sock_net(ssk);
-		u8 timeouts, to_max;
+	/* ... + MP_CAPABLE */
+	if (!subflow->request_mptcp) {
+		/* Mark as blackhole iif the 1st non-MPTCP SYN is accepted */
+		subflow->mpc_drop = 0;
+		return;
+	}
 
-		timeouts = inet_csk(ssk)->icsk_retransmits;
-		to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback;
+	net = sock_net(ssk);
+	timeouts = inet_csk(ssk)->icsk_retransmits;
+	to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback;
 
-		if (timeouts == to_max || (timeouts < to_max && expired)) {
-			MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
-			subflow->mpc_drop = 1;
-			mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
-		}
-	} else if (ssk->sk_state == TCP_SYN_SENT) {
-		subflow->mpc_drop = 0;
+	if (timeouts == to_max || (timeouts < to_max && expired)) {
+		MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
+		subflow->mpc_drop = 1;
+		mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
 	}
 }
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index b1f36dc1a0911..16cacce6c10fe 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -489,6 +489,27 @@ fail:
 	return ret;
 }
 
+int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
+			    struct netlink_callback *cb,
+			    struct mptcp_pm_addr_entry *entry)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
+			  cb->nlh->nlmsg_seq, &mptcp_genl_family,
+			  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
+	if (!hdr)
+		return -EINVAL;
+
+	if (mptcp_nl_fill_addr(msg, entry) < 0) {
+		genlmsg_cancel(msg, hdr);
+		return -EINVAL;
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+}
+
 static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	const struct genl_info *info = genl_info_dump(cb);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 99705a9c2238c..ef85a60151ad7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -64,7 +64,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 			addr_equals = a->addr.s_addr == b->addr.s_addr;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 		else
-			addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6);
+			addr_equals = ipv6_addr_equal(&a->addr6, &b->addr6);
 	} else if (a->family == AF_INET) {
 		if (ipv6_addr_v4mapped(&b->addr6))
 			addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3];
@@ -1798,7 +1798,6 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
 	int id = cb->args[0];
-	void *hdr;
 	int i;
 
 	pernet = pm_nl_get_pernet(net);
@@ -1813,19 +1812,10 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			if (entry->addr.id <= id)
 				continue;
 
-			hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
-					  cb->nlh->nlmsg_seq, &mptcp_genl_family,
-					  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
-			if (!hdr)
+			if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0)
 				break;
 
-			if (mptcp_nl_fill_addr(msg, entry) < 0) {
-				genlmsg_cancel(msg, hdr);
-				break;
-			}
-
 			id = entry->addr.id;
-			genlmsg_end(msg, hdr);
 		}
 	}
 	rcu_read_unlock();
@@ -1922,13 +1912,16 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 	spin_unlock_bh(&msk->pm.lock);
 }
 
-static int mptcp_nl_set_flags(struct net *net,
-			      struct mptcp_addr_info *addr,
-			      u8 bkup, u8 changed)
+static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr,
+			       u8 flags, u8 changed)
 {
+	u8 is_subflow = !!(flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
+	u8 bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	long s_slot = 0, s_num = 0;
 	struct mptcp_sock *msk;
-	int ret = -EINVAL;
+
+	if (changed == MPTCP_PM_ADDR_FLAG_FULLMESH && !is_subflow)
+		return;
 
 	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
 		struct sock *sk = (struct sock *)msk;
@@ -1938,8 +1931,9 @@ static int mptcp_nl_set_flags(struct net *net,
 
 		lock_sock(sk);
 		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
-			ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
-		if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
+			mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
+		/* Subflows will only be recreated if the SUBFLOW flag is set */
+		if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH))
 			mptcp_pm_nl_fullmesh(msk, addr);
 		release_sock(sk);
 
@@ -1948,7 +1942,7 @@ next:
 		cond_resched();
 	}
 
-	return ret;
+	return;
 }
 
 int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
@@ -1961,7 +1955,6 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
 	u8 lookup_by_id = 0;
-	u8 bkup = 0;
 
 	pernet = pm_nl_get_pernet(net);
 
@@ -1974,9 +1967,6 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 		}
 	}
 
-	if (local->flags & MPTCP_PM_ADDR_FLAG_BACKUP)
-		bkup = 1;
-
 	spin_lock_bh(&pernet->lock);
 	entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) :
 			       __lookup_addr(pernet, &local->addr);
@@ -1998,7 +1988,7 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	*local = *entry;
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_set_flags(net, &local->addr, bkup, changed);
+	mptcp_nl_set_flags(net, &local->addr, entry->flags, changed);
 	return 0;
 }
 
@@ -2032,9 +2022,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 		break;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	case AF_INET6: {
-		const struct ipv6_pinfo *np = inet6_sk(ssk);
-
-		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr))
+		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr))
 			return -EMSGSIZE;
 		if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr))
 			return -EMSGSIZE;
@@ -2261,9 +2249,7 @@ void mptcp_event_pm_listener(const struct sock *ssk,
 		break;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	case AF_INET6: {
-		const struct ipv6_pinfo *np = inet6_sk(ssk);
-
-		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr))
+		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr))
 			goto nla_put_failure;
 		break;
 	}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 277cf092a8704..6bf6a20ef7f3e 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -48,7 +48,6 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 						    bool needs_id)
 {
 	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-	struct mptcp_pm_addr_entry *match = NULL;
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *e;
 	bool addr_match = false;
@@ -63,16 +62,12 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		if (addr_match && entry->addr.id == 0 && needs_id)
 			entry->addr.id = e->addr.id;
 		id_match = (e->addr.id == entry->addr.id);
-		if (addr_match && id_match) {
-			match = e;
+		if (addr_match || id_match)
 			break;
-		} else if (addr_match || id_match) {
-			break;
-		}
 		__set_bit(e->addr.id, id_bitmap);
 	}
 
-	if (!match && !addr_match && !id_match) {
+	if (!addr_match && !id_match) {
 		/* Memory for the entry is allocated from the
 		 * sock option buffer.
 		 */
@@ -90,7 +85,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list);
 		msk->pm.local_addr_used++;
 		ret = e->addr.id;
-	} else if (match) {
+	} else if (addr_match && id_match) {
 		ret = entry->addr.id;
 	}
 
@@ -465,9 +460,7 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
 			break;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 		case AF_INET6: {
-			const struct ipv6_pinfo *pinfo = inet6_sk(ssk);
-
-			if (!ipv6_addr_equal(&local->addr6, &pinfo->saddr) ||
+			if (!ipv6_addr_equal(&local->addr6, &issk->pinet6->saddr) ||
 			    !ipv6_addr_equal(&remote->addr6, &ssk->sk_v6_daddr))
 				continue;
 			break;
@@ -641,7 +634,8 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 	struct mptcp_sock *msk;
 	int ret = -EINVAL;
 	struct sock *sk;
-	void *hdr;
+
+	BUILD_BUG_ON(sizeof(struct id_bitmap) > sizeof(cb->ctx));
 
 	bitmap = (struct id_bitmap *)cb->ctx;
 
@@ -657,19 +651,10 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 		if (test_bit(entry->addr.id, bitmap->map))
 			continue;
 
-		hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq, &mptcp_genl_family,
-				  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
-		if (!hdr)
+		if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0)
 			break;
 
-		if (mptcp_nl_fill_addr(msg, entry) < 0) {
-			genlmsg_cancel(msg, hdr);
-			break;
-		}
-
 		__set_bit(entry->addr.id, bitmap->map);
-		genlmsg_end(msg, hdr);
 	}
 	spin_unlock_bh(&msk->pm.lock);
 	release_sock(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ca65f8bff632f..256677c43ca65 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1057,6 +1057,9 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 					      struct request_sock *req);
 int mptcp_nl_fill_addr(struct sk_buff *skb,
 		       struct mptcp_pm_addr_entry *entry);
+int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
+			    struct netlink_callback *cb,
+			    struct mptcp_pm_addr_entry *entry);
 
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index df7dbcfa3b713..c16c6fbd4ba2f 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -16,13 +16,25 @@
 static DEFINE_SPINLOCK(mptcp_sched_list_lock);
 static LIST_HEAD(mptcp_sched_list);
 
-static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk,
+static int mptcp_sched_default_get_send(struct mptcp_sock *msk,
+					struct mptcp_sched_data *data)
+{
+	struct sock *ssk;
+
+	ssk = mptcp_subflow_get_send(msk);
+	if (!ssk)
+		return -EINVAL;
+
+	mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+	return 0;
+}
+
+static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk,
 					   struct mptcp_sched_data *data)
 {
 	struct sock *ssk;
 
-	ssk = data->reinject ? mptcp_subflow_get_retrans(msk) :
-			       mptcp_subflow_get_send(msk);
+	ssk = mptcp_subflow_get_retrans(msk);
 	if (!ssk)
 		return -EINVAL;
 
@@ -31,7 +43,8 @@ static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk,
 }
 
 static struct mptcp_sched_ops mptcp_sched_default = {
-	.get_subflow	= mptcp_sched_default_get_subflow,
+	.get_send	= mptcp_sched_default_get_send,
+	.get_retrans	= mptcp_sched_default_get_retrans,
 	.name		= "default",
 	.owner		= THIS_MODULE,
 };
@@ -73,7 +86,7 @@ void mptcp_get_available_schedulers(char *buf, size_t maxlen)
 
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
 {
-	if (!sched->get_subflow)
+	if (!sched->get_send)
 		return -EINVAL;
 
 	spin_lock(&mptcp_sched_list_lock);
@@ -144,7 +157,7 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 int mptcp_sched_get_send(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sched_data data;
+	struct mptcp_sched_data *data = NULL;
 
 	msk_owned_by_me(msk);
 
@@ -164,16 +177,15 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 			return 0;
 	}
 
-	data.reinject = false;
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_subflow(msk, &data);
-	return msk->sched->get_subflow(msk, &data);
+		return mptcp_sched_default_get_send(msk, data);
+	return msk->sched->get_send(msk, data);
 }
 
 int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sched_data data;
+	struct mptcp_sched_data *data = NULL;
 
 	msk_owned_by_me(msk);
 
@@ -186,8 +198,9 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 			return 0;
 	}
 
-	data.reinject = true;
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_subflow(msk, &data);
-	return msk->sched->get_subflow(msk, &data);
+		return mptcp_sched_default_get_retrans(msk, data);
+	if (msk->sched->get_retrans)
+		return msk->sched->get_retrans(msk, data);
+	return msk->sched->get_send(msk, data);
 }