Merge branch 'mptcp-pm-prep-work-for-new-ops-and-sysctl-knobs'

Matthieu Baerts says:

====================
mptcp: pm: prep work for new ops and sysctl knobs

Here are a few cleanups, preparation work for the new PM ops, and sysctl
knobs.

- Patch 1: reorg: move generic NL code used by all PMs to pm_netlink.c.

- Patch 2: use kmemdup() instead of kmalloc + copy.

- Patch 3: small cleanup to use pm var instead of msk->pm.

- Patch 4: reorg: id_avail_bitmap is only used by the in-kernel PM.

- Patch 5: use struct_group to easily reset a subset of PM data vars.

- Patch 6: introduce the minimal skeleton for the new PM ops.

- Patch 7: register in-kernel and userspace PM ops.

- Patch 8: new net.mptcp.path_manager sysctl knob, deprecating pm_type.

- Patch 9: map the new path_manager sysctl knob with pm_type.

- Patch 10: map the old pm_type sysctl knob with path_manager.

- Patch 11: new net.mptcp.available_path_managers sysctl knob.

- Patch 12: new test to validate path_manager and pm_type mapping.

Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
====================

Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-0-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

Documentation/networking/mptcp-sysctl.rst

@@ -30,6 +30,10 @@ allow_join_initial_addr_port - BOOLEAN
 
 	Default: 1
 
+available_path_managers - STRING
+	Shows the available path managers choices that are registered. More
+	path managers may be available, but not loaded.
+
 available_schedulers - STRING
 	Shows the available schedulers choices that are registered. More packet
 	schedulers may be available, but not loaded.
@@ -72,6 +76,23 @@ enabled - BOOLEAN
 
 	Default: 1 (enabled)
 
+path_manager - STRING
+	Set the default path manager name to use for each new MPTCP
+	socket. In-kernel path management will control subflow
+	connections and address advertisements according to
+	per-namespace values configured over the MPTCP netlink
+	API. Userspace path management puts per-MPTCP-connection subflow
+	connection decisions and address advertisements under control of
+	a privileged userspace program, at the cost of more netlink
+	traffic to propagate all of the related events and commands.
+
+	This is a per-namespace sysctl.
+
+	* "kernel"          - In-kernel path manager
+	* "userspace"       - Userspace path manager
+
+	Default: "kernel"
+
 pm_type - INTEGER
 	Set the default path manager type to use for each new MPTCP
 	socket. In-kernel path management will control subflow
@@ -84,6 +105,8 @@ pm_type - INTEGER
 
 	This is a per-namespace sysctl.
 
+	Deprecated since v6.15, use path_manager instead.
+
 	* 0 - In-kernel path manager
 	* 1 - Userspace path manager
 

include/net/mptcp.h

@@ -14,6 +14,7 @@
 
 struct mptcp_info;
 struct mptcp_sock;
+struct mptcp_pm_addr_entry;
 struct seq_file;
 
 /* MPTCP sk_buff extension data */
@@ -121,6 +122,19 @@ struct mptcp_sched_ops {
 	void (*release)(struct mptcp_sock *msk);
 } ____cacheline_aligned_in_smp;
 
+#define MPTCP_PM_NAME_MAX	16
+#define MPTCP_PM_MAX		128
+#define MPTCP_PM_BUF_MAX	(MPTCP_PM_NAME_MAX * MPTCP_PM_MAX)
+
+struct mptcp_pm_ops {
+	char			name[MPTCP_PM_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
 #ifdef CONFIG_MPTCP
 void mptcp_init(void);
 

net/mptcp/ctrl.c

@@ -39,6 +39,7 @@ struct mptcp_pernet {
 	u8 allow_join_initial_addr_port;
 	u8 pm_type;
 	char scheduler[MPTCP_SCHED_NAME_MAX];
+	char path_manager[MPTCP_PM_NAME_MAX];
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(const struct net *net)
@@ -83,6 +84,11 @@ int mptcp_get_pm_type(const struct net *net)
 	return mptcp_get_pernet(net)->pm_type;
 }
 
+const char *mptcp_get_path_manager(const struct net *net)
+{
+	return mptcp_get_pernet(net)->path_manager;
+}
+
 const char *mptcp_get_scheduler(const struct net *net)
 {
 	return mptcp_get_pernet(net)->scheduler;
@@ -101,6 +107,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->stale_loss_cnt = 4;
 	pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
 	strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler));
+	strscpy(pernet->path_manager, "kernel", sizeof(pernet->path_manager));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -174,6 +181,96 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table,
 	return ret;
 }
 
+static int mptcp_set_path_manager(char *path_manager, const char *name)
+{
+	struct mptcp_pm_ops *pm_ops;
+	int ret = 0;
+
+	rcu_read_lock();
+	pm_ops = mptcp_pm_find(name);
+	if (pm_ops)
+		strscpy(path_manager, name, MPTCP_PM_NAME_MAX);
+	else
+		ret = -ENOENT;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int proc_path_manager(const struct ctl_table *ctl, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct mptcp_pernet *pernet = container_of(ctl->data,
+						   struct mptcp_pernet,
+						   path_manager);
+	char (*path_manager)[MPTCP_PM_NAME_MAX] = ctl->data;
+	char pm_name[MPTCP_PM_NAME_MAX];
+	const struct ctl_table tbl = {
+		.data = pm_name,
+		.maxlen = MPTCP_PM_NAME_MAX,
+	};
+	int ret;
+
+	strscpy(pm_name, *path_manager, MPTCP_PM_NAME_MAX);
+
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		ret = mptcp_set_path_manager(*path_manager, pm_name);
+		if (ret == 0) {
+			u8 pm_type = __MPTCP_PM_TYPE_NR;
+
+			if (strncmp(pm_name, "kernel", MPTCP_PM_NAME_MAX) == 0)
+				pm_type = MPTCP_PM_TYPE_KERNEL;
+			else if (strncmp(pm_name, "userspace", MPTCP_PM_NAME_MAX) == 0)
+				pm_type = MPTCP_PM_TYPE_USERSPACE;
+			pernet->pm_type = pm_type;
+		}
+	}
+
+	return ret;
+}
+
+static int proc_pm_type(const struct ctl_table *ctl, int write,
+			void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct mptcp_pernet *pernet = container_of(ctl->data,
+						   struct mptcp_pernet,
+						   pm_type);
+	int ret;
+
+	ret = proc_dou8vec_minmax(ctl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		u8 pm_type = READ_ONCE(*(u8 *)ctl->data);
+		char *pm_name = "";
+
+		if (pm_type == MPTCP_PM_TYPE_KERNEL)
+			pm_name = "kernel";
+		else if (pm_type == MPTCP_PM_TYPE_USERSPACE)
+			pm_name = "userspace";
+		mptcp_set_path_manager(pernet->path_manager, pm_name);
+	}
+
+	return ret;
+}
+
+static int proc_available_path_managers(const struct ctl_table *ctl,
+					int write, void *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table tbl = { .maxlen = MPTCP_PM_BUF_MAX, };
+	int ret;
+
+	tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+	if (!tbl.data)
+		return -ENOMEM;
+
+	mptcp_pm_get_available(tbl.data, MPTCP_PM_BUF_MAX);
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	kfree(tbl.data);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -218,7 +315,7 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.procname = "pm_type",
 		.maxlen = sizeof(u8),
 		.mode = 0644,
-		.proc_handler = proc_dou8vec_minmax,
+		.proc_handler = proc_pm_type,
 		.extra1       = SYSCTL_ZERO,
 		.extra2       = &mptcp_pm_type_max
 	},
@@ -253,6 +350,18 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.mode = 0644,
 		.proc_handler = proc_dou8vec_minmax,
 	},
+	{
+		.procname = "path_manager",
+		.maxlen	= MPTCP_PM_NAME_MAX,
+		.mode = 0644,
+		.proc_handler = proc_path_manager,
+	},
+	{
+		.procname = "available_path_managers",
+		.maxlen	= MPTCP_PM_BUF_MAX,
+		.mode = 0444,
+		.proc_handler = proc_available_path_managers,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -278,6 +387,8 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[8].data = &pernet->close_timeout;
 	table[9].data = &pernet->blackhole_timeout;
 	table[10].data = &pernet->syn_retrans_before_tcp_fallback;
+	table[11].data = &pernet->path_manager;
+	/* table[12] is for available_path_managers which is read-only info */
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));

net/mptcp/pm.c

@@ -5,6 +5,8 @@
  */
 #define pr_fmt(fmt) "MPTCP: " fmt
 
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -18,6 +20,9 @@ struct mptcp_pm_add_entry {
 	struct mptcp_sock	*sock;
 };
 
+static DEFINE_SPINLOCK(mptcp_pm_list_lock);
+static LIST_HEAD(mptcp_pm_list);
+
 /* path manager helpers */
 
 /* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
@@ -511,13 +516,13 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
 	 * be sure to serve this event only once.
 	 */
 	if (READ_ONCE(pm->work_pending) &&
-	    !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
+	    !(pm->status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
 		mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED);
 
-	if ((msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0)
+	if ((pm->status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0)
 		announce = true;
 
-	msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
+	pm->status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
 	spin_unlock_bh(&pm->lock);
 
 	if (announce)
@@ -978,10 +983,7 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
 	struct mptcp_pm_data *pm = &msk->pm;
 
-	pm->add_addr_signaled = 0;
-	pm->add_addr_accepted = 0;
-	pm->local_addr_used = 0;
-	pm->subflows = 0;
+	memset(&pm->reset, 0, sizeof(pm->reset));
 	pm->rm_list_tx.nr = 0;
 	pm->rm_list_rx.nr = 0;
 	WRITE_ONCE(pm->pm_type, pm_type);
@@ -1000,16 +1002,9 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 			   !!mptcp_pm_get_add_addr_accept_max(msk) &&
 			   subflows_allowed);
 		WRITE_ONCE(pm->accept_subflow, subflows_allowed);
-	} else {
-		WRITE_ONCE(pm->work_pending, 0);
-		WRITE_ONCE(pm->accept_addr, 0);
-		WRITE_ONCE(pm->accept_subflow, 0);
-	}
 
-	WRITE_ONCE(pm->addr_signal, 0);
-	WRITE_ONCE(pm->remote_deny_join_id0, false);
-	pm->status = 0;
-	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+		bitmap_fill(pm->id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+	}
 }
 
 void mptcp_pm_data_init(struct mptcp_sock *msk)
@@ -1022,5 +1017,75 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 
 void __init mptcp_pm_init(void)
 {
+	mptcp_pm_kernel_register();
+	mptcp_pm_userspace_register();
 	mptcp_pm_nl_init();
 }
+
+/* Must be called with rcu read lock held */
+struct mptcp_pm_ops *mptcp_pm_find(const char *name)
+{
+	struct mptcp_pm_ops *pm_ops;
+
+	list_for_each_entry_rcu(pm_ops, &mptcp_pm_list, list) {
+		if (!strcmp(pm_ops->name, name))
+			return pm_ops;
+	}
+
+	return NULL;
+}
+
+int mptcp_pm_validate(struct mptcp_pm_ops *pm_ops)
+{
+	return 0;
+}
+
+int mptcp_pm_register(struct mptcp_pm_ops *pm_ops)
+{
+	int ret;
+
+	ret = mptcp_pm_validate(pm_ops);
+	if (ret)
+		return ret;
+
+	spin_lock(&mptcp_pm_list_lock);
+	if (mptcp_pm_find(pm_ops->name)) {
+		spin_unlock(&mptcp_pm_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&pm_ops->list, &mptcp_pm_list);
+	spin_unlock(&mptcp_pm_list_lock);
+
+	pr_debug("%s registered\n", pm_ops->name);
+	return 0;
+}
+
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops)
+{
+	/* skip unregistering the default path manager */
+	if (WARN_ON_ONCE(pm_ops == &mptcp_pm_kernel))
+		return;
+
+	spin_lock(&mptcp_pm_list_lock);
+	list_del_rcu(&pm_ops->list);
+	spin_unlock(&mptcp_pm_list_lock);
+}
+
+/* Build string with list of available path manager values.
+ * Similar to tcp_get_available_congestion_control()
+ */
+void mptcp_pm_get_available(char *buf, size_t maxlen)
+{
+	struct mptcp_pm_ops *pm_ops;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pm_ops, &mptcp_pm_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs, "%s%s",
+				 offs == 0 ? "" : " ", pm_ops->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
+	}
+	rcu_read_unlock();
+}

net/mptcp/pm_kernel.c

@@ -710,11 +710,10 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 		return ret;
 
 	/* address not found, add to local list */
-	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	entry = kmemdup(skc, sizeof(*skc), GFP_ATOMIC);
 	if (!entry)
 		return -ENOMEM;
 
-	*entry = *skc;
 	entry->addr.port = 0;
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
 	if (ret < 0)
@@ -817,13 +816,12 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT);
+	entry = kmemdup(&addr, sizeof(addr), GFP_KERNEL_ACCOUNT);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "can't allocate addr");
 		return -ENOMEM;
 	}
 
-	*entry = addr;
 	if (entry->addr.port) {
 		ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry);
 		if (ret) {
@@ -1400,11 +1398,15 @@ static struct pernet_operations mptcp_pm_pernet_ops = {
 	.size = sizeof(struct pm_nl_pernet),
 };
 
-void __init mptcp_pm_nl_init(void)
+struct mptcp_pm_ops mptcp_pm_kernel = {
+	.name			= "kernel",
+	.owner			= THIS_MODULE,
+};
+
+void __init mptcp_pm_kernel_register(void)
 {
 	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
 		panic("Failed to register MPTCP PM pernet subsystem.\n");
 
-	if (genl_register_family(&mptcp_genl_family))
-		panic("Failed to register MPTCP PM netlink family\n");
+	mptcp_pm_register(&mptcp_pm_kernel);
 }

net/mptcp/pm_netlink.c

@@ -625,3 +625,9 @@ struct genl_family mptcp_genl_family __ro_after_init = {
 	.mcgrps		= mptcp_pm_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
 };
+
+void __init mptcp_pm_nl_init(void)
+{
+	if (genl_register_family(&mptcp_genl_family))
+		panic("Failed to register MPTCP PM netlink family\n");
+}

net/mptcp/pm_userspace.c

@@ -682,3 +682,13 @@ int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
 	sock_put(sk);
 	return ret;
 }
+
+static struct mptcp_pm_ops mptcp_pm_userspace = {
+	.name			= "userspace",
+	.owner			= THIS_MODULE,
+};
+
+void __init mptcp_pm_userspace_register(void)
+{
+	mptcp_pm_register(&mptcp_pm_userspace);
+}

net/mptcp/protocol.h

@@ -223,6 +223,8 @@ struct mptcp_pm_data {
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
+	struct_group(reset,
+
 	u8		addr_signal;
 	bool		server_side;
 	bool		work_pending;
@@ -235,6 +237,9 @@ struct mptcp_pm_data {
 	u8		pm_type;
 	u8		subflows;
 	u8		status;
+
+	);
+
 	DECLARE_BITMAP(id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	struct mptcp_rm_list rm_list_tx;
 	struct mptcp_rm_list rm_list_rx;
@@ -694,6 +699,7 @@ int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
+const char *mptcp_get_path_manager(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
 
 void mptcp_active_disable(struct sock *sk);
@@ -1045,6 +1051,15 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
 				struct mptcp_pm_addr_entry *entry);
 
+/* the default path manager, used in mptcp_pm_unregister */
+extern struct mptcp_pm_ops mptcp_pm_kernel;
+
+struct mptcp_pm_ops *mptcp_pm_find(const char *name);
+int mptcp_pm_register(struct mptcp_pm_ops *pm_ops);
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops);
+int mptcp_pm_validate(struct mptcp_pm_ops *pm_ops);
+void mptcp_pm_get_available(char *buf, size_t maxlen);
+
 void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 
 void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,
@@ -1147,6 +1162,8 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 	return local_id;
 }
 
+void __init mptcp_pm_kernel_register(void);
+void __init mptcp_pm_userspace_register(void);
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_worker(struct mptcp_sock *msk);
 void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);

tools/testing/selftests/net/mptcp/userspace_pm.sh

@@ -117,7 +117,36 @@ cleanup()
 trap cleanup EXIT
 
 # Create and configure network namespaces for testing
+print_title "Init"
 mptcp_lib_ns_init ns1 ns2
+
+# check path_manager and pm_type sysctl mapping
+if [ -f /proc/sys/net/mptcp/path_manager ]; then
+	ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=userspace
+	pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+	if [ "${pm_type}" != "1" ]; then
+		test_fail "unexpected pm_type: ${pm_type}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=error 2>/dev/null
+	pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+	if [ "${pm_type}" != "1" ]; then
+		test_fail "unexpected pm_type after error: ${pm_type}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	ip netns exec "$ns1" sysctl -q net.mptcp.pm_type=0
+	pm_name="$(ip netns exec "$ns1" sysctl -n net.mptcp.path_manager)"
+	if [ "${pm_name}" != "kernel" ]; then
+		test_fail "unexpected path-manager: ${pm_name}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+fi
+
 for i in "$ns1" "$ns2" ;do
 	ip netns exec "$i" sysctl -q net.mptcp.pm_type=1
 done
@@ -152,7 +181,6 @@ mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid
 sleep 0.5
 mptcp_lib_subtests_last_ts_reset
 
-print_title "Init"
 print_test "Created network namespaces ns1, ns2"
 test_pass