Series comparison

-[PATCH mptcp-next v7 00/11] BPF path manager, part 5
+[PATCH mptcp-next v8 00/12] BPF path manager, part 5
 From: Geliang Tang <tanggeliang@kylinos.cn>
+v8:
+ - address Matt's comments in v7.
 v7:
  - addresss Matt's comments in v6 [1].
  - drop "type" from struct mptcp_pm_ops as Matt suggested.
  - map "pm_type" to new sysctl as Matt suggested.
 ...
 In order to implement BPF path manager, it's necessary to unify the
 interfaces of the path manager. This set contains some cleanups and
 refactoring to unify the interfaces in kernel space. Finally, define
 a struct mptcp_pm_ops for a path manager.
-Geliang Tang (11):
+Geliang Tang (12):
   mptcp: pm: define struct mptcp_pm_ops
   mptcp: sysctl: new sysctl to set path manager by name
   mptcp: sysctl: map pm_type to path_manager
+  mptcp: sysctl: map path_manager to pm_type
   mptcp: sysctl: add available_path_managers
-  mptcp: pm: in-kernel: register mptcp_kernel_pm
+  mptcp: pm: in-kernel: register mptcp_pm_kernel
-  mptcp: pm: userspace: register mptcp_userspace_pm
+  mptcp: pm: userspace: register mptcp_pm_userspace
   mptcp: pm: initialize and release mptcp_pm_ops
-  mptcp: pm: drop pm_type in mptcp_pm_data
+  mptcp: pm: add get_local_id() interface
-  mptcp: sysctl: drop get_pm_type helper
+  mptcp: pm: add get_priority() interface
-  mptcp: pm: make get_local_id helpers static
+  selftests: mptcp: add pm_type mapping tests
-  mptcp: pm: make is_backup helpers static
+  selftests: mptcp: add path_manager sysctl test
- Documentation/networking/mptcp-sysctl.rst |  26 +++++
+ Documentation/networking/mptcp-sysctl.rst     |  23 +++
- include/net/mptcp.h                       |  19 ++++
+ include/net/mptcp.h                           |  19 +++
- net/mptcp/ctrl.c                          | 107 ++++++++++++++++-
+ net/mptcp/ctrl.c                              | 112 +++++++++++++-
- net/mptcp/pm.c                            | 133 +++++++++++++++++++---
+ net/mptcp/pm.c                                | 145 ++++++++++++++----
- net/mptcp/pm_kernel.c                     |  16 ++-
+ net/mptcp/pm_kernel.c                         |  35 ++++-
- net/mptcp/pm_userspace.c                  |  26 ++++-
+ net/mptcp/pm_userspace.c                      |  36 ++++-
- net/mptcp/protocol.h                      |  25 ++--
+ net/mptcp/protocol.h                          |  18 ++-
-files changed, 317 insertions(+), 35 deletions(-)
+ .../testing/selftests/net/mptcp/mptcp_join.sh |  49 +++++-
 files changed, 393 insertions(+), 44 deletions(-)
 --
 .43.0

-[PATCH mptcp-next v7 01/11] mptcp: pm: define struct mptcp_pm_ops
+[PATCH mptcp-next v8 01/12] mptcp: pm: define struct mptcp_pm_ops
 ...
 Add a set of functions to register, unregister, find and validate a
 given struct ops.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- include/net/mptcp.h  | 17 ++++++++++++++
+ include/net/mptcp.h  | 12 ++++++++++
  net/mptcp/pm.c       | 55 ++++++++++++++++++++++++++++++++++++++++++++
  net/mptcp/protocol.h |  5 ++++
-files changed, 77 insertions(+)
+files changed, 72 insertions(+)
 diff --git a/include/net/mptcp.h b/include/net/mptcp.h
 index XXXXXXX..XXXXXXX 100644
 --- a/include/net/mptcp.h
 +++ b/include/net/mptcp.h
 ...
  } ____cacheline_aligned_in_smp;
 +#define MPTCP_PM_NAME_MAX    16
 +
 +struct mptcp_pm_ops {
-+    int (*get_local_id)(struct mptcp_sock *msk,
-+                struct mptcp_pm_addr_entry *skc);
-+    bool (*get_priority)(struct mptcp_sock *msk,
-+                 struct mptcp_addr_info *skc);
-+
 +    char            name[MPTCP_PM_NAME_MAX];
 +    struct module        *owner;
 +    struct list_head    list;
 +
 +    void (*init)(struct mptcp_sock *msk);
 ...
 +
  /* path manager helpers */
  /* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
 @@ -XXX,XX +XXX,XX @@ void __init mptcp_pm_init(void)
- {
+     mptcp_pm_kernel_register();
      mptcp_pm_nl_init();
  }
 +
 +/* Must be called with rcu read lock held */
 +struct mptcp_pm_ops *mptcp_pm_find(const char *name)
 ...
 +    return NULL;
 +}
 +
 +int mptcp_pm_validate(struct mptcp_pm_ops *pm)
 +{
-+    if (!pm->get_local_id || !pm->get_priority) {
++    if (!pm->init) {
 +        pr_err("%s does not implement required ops\n", pm->name);
 +        return -EINVAL;
 +    }
 +
 +    return 0;
 ...

-[PATCH mptcp-next v7 02/11] mptcp: sysctl: new sysctl to set path manager by name
+[PATCH mptcp-next v8 02/12] mptcp: sysctl: new sysctl to set path manager by name
 ...
 This sysctl makes the old one "pm_type" deprecated.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- Documentation/networking/mptcp-sysctl.rst | 22 ++++++++++
+ Documentation/networking/mptcp-sysctl.rst | 19 +++++++++
  net/mptcp/ctrl.c                          | 50 +++++++++++++++++++++++
  net/mptcp/protocol.h                      |  1 +
-files changed, 73 insertions(+)
+files changed, 70 insertions(+)
 diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
 index XXXXXXX..XXXXXXX 100644
 --- a/Documentation/networking/mptcp-sysctl.rst
 +++ b/Documentation/networking/mptcp-sysctl.rst
 ...
 +    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.
-+    User-defined BPF-based path managers can also be set via this
-+    sysctl.
 +
 +    This is a per-namespace sysctl.
 +
 +    * "kernel"          - In-kernel path manager
 +    * "userspace"       - Userspace path manager
-+    * all other strings - BPF-based path managers
 +
 +    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
 @@ -XXX,XX +XXX,XX @@ pm_type - INTEGER
      This is a per-namespace sysctl.
-+    (Deprecated, use path_manager instead.).
++    Deprecated since v6.15, use path_manager instead.
 +
      * 0 - In-kernel path manager
      * 1 - Userspace path manager
 diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
 ...

-[PATCH mptcp-next v7 03/11] mptcp: sysctl: map pm_type to path_manager
+[PATCH mptcp-next v8 03/12] mptcp: sysctl: map pm_type to path_manager
 ...
 This patch adds a new proc_handler "proc_pm_type" for "pm_type" to
 map old path manager sysctl "pm_type" to the newly added "path_manager".
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/ctrl.c | 33 ++++++++++++++++++++++++++++++---
+ net/mptcp/ctrl.c | 28 +++++++++++++++++++++++++++-
-file changed, 30 insertions(+), 3 deletions(-)
+file changed, 27 insertions(+), 1 deletion(-)
 diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/ctrl.c
 +++ b/net/mptcp/ctrl.c
 ...
 +            void *buffer, size_t *lenp, loff_t *ppos)
 +{
 +    struct mptcp_pernet *pernet = container_of(ctl->data,
 +                           struct mptcp_pernet,
 +                           pm_type);
-+    unsigned int val = READ_ONCE(*(u8 *)ctl->data);
++    u8 pm_type = READ_ONCE(*(u8 *)ctl->data);
 +    const struct ctl_table tbl = {
-+        .maxlen = sizeof(val),
++        .maxlen = sizeof(pm_type),
-+        .data = &val,
++        .data = &pm_type,
 +    };
 +    int ret;
 +
-+    if (val > mptcp_pm_type_max)
++    ret = proc_dou8vec_minmax(&tbl, write, buffer, lenp, ppos);
 +        return -ERANGE;
 +
 +    ret = proc_douintvec(&tbl, write, buffer, lenp, ppos);
 +    if (write && ret == 0) {
 +        char *path_manager = "kernel";
 +
-+        if (val == MPTCP_PM_TYPE_USERSPACE)
++        if (pm_type == MPTCP_PM_TYPE_USERSPACE)
 +            path_manager = "userspace";
 +        mptcp_set_path_manager(pernet->path_manager, path_manager);
-+        WRITE_ONCE(*(u8 *)ctl->data, val);
++        WRITE_ONCE(*(u8 *)ctl->data, pm_type);
 +    }
 +
 +    return ret;
 +}
 +
 ...
 @@ -XXX,XX +XXX,XX @@ static struct ctl_table mptcp_sysctl_table[] = {
          .procname = "pm_type",
          .maxlen = sizeof(u8),
          .mode = 0644,
 -        .proc_handler = proc_dou8vec_minmax,
--        .extra1       = SYSCTL_ZERO,
--        .extra2       = &mptcp_pm_type_max
 +        .proc_handler = proc_pm_type,
+         .extra1       = SYSCTL_ZERO,
+         .extra2       = &mptcp_pm_type_max
      },
-     {
-         .procname = "scheduler",
 --
 .43.0

-[PATCH mptcp-next v7 09/11] mptcp: sysctl: drop get_pm_type helper
+[PATCH mptcp-next v8 04/12] mptcp: sysctl: map path_manager to pm_type
 From: Geliang Tang <tanggeliang@kylinos.cn>
-The helper mptcp_get_pm_type() is unused now, it's replaced by the
+This patch maps the newly added path manager sysctl "path_manager"
-new one mptcp_get_path_manager(). So drop it.
+to the old one "pm_type".
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/ctrl.c     | 5 -----
+ net/mptcp/ctrl.c | 11 ++++++++++-
- net/mptcp/protocol.h | 1 -
+file changed, 10 insertions(+), 1 deletion(-)
 files changed, 6 deletions(-)
 diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/ctrl.c
 +++ b/net/mptcp/ctrl.c
-@@ -XXX,XX +XXX,XX @@ unsigned int mptcp_close_timeout(const struct sock *sk)
+@@ -XXX,XX +XXX,XX @@ static int mptcp_set_path_manager(char *path_manager, const char *name)
-     return mptcp_get_pernet(sock_net(sk))->close_timeout;
+ 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 val[MPTCP_PM_NAME_MAX];
      const struct ctl_table tbl = {
@@ -XXX,XX +XXX,XX @@ static int proc_path_manager(const struct ctl_table *ctl, int write,
      strscpy(val, *path_manager, MPTCP_PM_NAME_MAX);
      ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
 -    if (write && ret == 0)
 +    if (write && ret == 0) {
 +        u8 pm_type = MPTCP_PM_TYPE_KERNEL;
 +
 +        if (!strncmp(val, "userspace", MPTCP_PM_NAME_MAX))
 +            pm_type = MPTCP_PM_TYPE_USERSPACE;
 +        pernet->pm_type = pm_type;
          ret = mptcp_set_path_manager(*path_manager, val);
 +    }
      return ret;
  }
--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;
-diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
-index XXXXXXX..XXXXXXX 100644
---- a/net/mptcp/protocol.h
-+++ b/net/mptcp/protocol.h
-@@ -XXX,XX +XXX,XX @@ int mptcp_is_checksum_enabled(const struct net *net);
- 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);
 --
 .43.0

-[PATCH mptcp-next v7 04/11] mptcp: sysctl: add available_path_managers
+[PATCH mptcp-next v8 05/12] mptcp: sysctl: add available_path_managers
 From: Geliang Tang <tanggeliang@kylinos.cn>
 Similarly to net.mptcp.available_schedulers, this patch adds a new one
-net.mptcp.available_path_managers to list the available path mangers.
+net.mptcp.available_path_managers to list the available path managers.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
  Documentation/networking/mptcp-sysctl.rst |  4 ++++
  include/net/mptcp.h                       |  2 ++
 ...
  #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 {
-     int (*get_local_id)(struct mptcp_sock *msk,
+     char            name[MPTCP_PM_NAME_MAX];
 diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/ctrl.c
 +++ b/net/mptcp/ctrl.c
 @@ -XXX,XX +XXX,XX @@ static int proc_pm_type(const struct ctl_table *ctl, int write,
 ...

-[PATCH mptcp-next v7 05/11] mptcp: pm: in-kernel: register mptcp_kernel_pm
+[PATCH mptcp-next v8 06/12] mptcp: pm: in-kernel: register mptcp_pm_kernel
 From: Geliang Tang <tanggeliang@kylinos.cn>
 This patch defines the original in-kernel netlink path manager as a
-new struct mptcp_pm_ops named "mptcp_kernel_pm", and register it in
+new struct mptcp_pm_ops named "mptcp_pm_kernel", and register it in
-mptcp_pm_nl_init().
+mptcp_pm_kernel_register().
 This mptcp_pm_ops will be skipped in mptcp_pm_unregister().
-Only get_local_id() and get_priority() interfaces are implemented here.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/pm.c        | 3 +++
+ net/mptcp/pm.c        |  4 ++++
- net/mptcp/pm_kernel.c | 9 +++++++++
+ net/mptcp/pm_kernel.c | 26 ++++++++++++++++++++++++++
- net/mptcp/protocol.h  | 2 ++
+ net/mptcp/protocol.h  |  3 +++
-files changed, 14 insertions(+)
+files changed, 33 insertions(+)
 diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm.c
 +++ b/net/mptcp/pm.c
 @@ -XXX,XX +XXX,XX @@ int mptcp_pm_register(struct mptcp_pm_ops *pm)
  void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
  {
-+    if (pm == &mptcp_kernel_pm)
++    /* skip unregistering the default path manager */
 +    if (pm == &mptcp_pm_kernel)
 +        return;
 +
      spin_lock(&mptcp_pm_list_lock);
      list_del_rcu(&pm->list);
      spin_unlock(&mptcp_pm_list_lock);
 ...
 +++ b/net/mptcp/pm_kernel.c
 @@ -XXX,XX +XXX,XX @@ static struct pernet_operations mptcp_pm_pernet_ops = {
      .size = sizeof(struct pm_nl_pernet),
  };
-+struct mptcp_pm_ops mptcp_kernel_pm = {
++static void mptcp_pm_nl_initialize(struct mptcp_sock *msk)
-+    .get_local_id        = mptcp_pm_nl_get_local_id,
++{
-+    .get_priority        = mptcp_pm_nl_is_backup,
++    bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
 +    struct mptcp_pm_data *pm = &msk->pm;
 +
 +    /* pm->work_pending must be only be set to 'true' when
 +     * pm is the default path manager
 +     */
 +    WRITE_ONCE(pm->work_pending,
 +           (!!mptcp_pm_get_local_addr_max(msk) &&
 +            subflows_allowed) ||
 +           !!mptcp_pm_get_add_addr_signal_max(msk));
 +    WRITE_ONCE(pm->accept_addr,
 +           !!mptcp_pm_get_add_addr_accept_max(msk) &&
 +           subflows_allowed);
 +    WRITE_ONCE(pm->accept_subflow, subflows_allowed);
 +}
 +
 +struct mptcp_pm_ops mptcp_pm_kernel = {
 +    .init            = mptcp_pm_nl_initialize,
 +    .name            = "kernel",
 +    .owner            = THIS_MODULE,
 +};
 +
- void __init mptcp_pm_nl_init(void)
+ void __init mptcp_pm_kernel_register(void)
  {
      if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
-@@ -XXX,XX +XXX,XX @@ void __init mptcp_pm_nl_init(void)
+         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_kernel_pm);
++    mptcp_pm_register(&mptcp_pm_kernel);
  }
 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/protocol.h
 +++ b/net/mptcp/protocol.h
 @@ -XXX,XX +XXX,XX @@ 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);
-+extern struct mptcp_pm_ops mptcp_kernel_pm;
++/* 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_validate(struct mptcp_pm_ops *pm);
  int mptcp_pm_register(struct mptcp_pm_ops *pm);
 --
 .43.0

-[PATCH mptcp-next v7 06/11] mptcp: pm: userspace: register mptcp_userspace_pm
+[PATCH mptcp-next v8 07/12] mptcp: pm: userspace: register mptcp_pm_userspace
 From: Geliang Tang <tanggeliang@kylinos.cn>
 This patch defines the original userspace path manager as a new
 struct mptcp_pm_ops named "mptcp_userspace_pm", and register it
-in mptcp_pm_data_init().
+in mptcp_pm_init(). mptcp_userspace_pm_is_release() is a wrapper
+of mptcp_userspace_pm_free_local_addr_list().
 Only get_local_id(), get_priority() and release() interfaces are
 implemented here. mptcp_userspace_pm_is_release() is a wrapper of
 mptcp_userspace_pm_free_local_addr_list().
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
  net/mptcp/pm.c           |  1 +
- net/mptcp/pm_userspace.c | 18 ++++++++++++++++++
+ net/mptcp/pm_userspace.c | 26 ++++++++++++++++++++++++++
  net/mptcp/protocol.h     |  1 +
-files changed, 20 insertions(+)
+files changed, 28 insertions(+)
 diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm.c
 +++ b/net/mptcp/pm.c
 @@ -XXX,XX +XXX,XX @@ 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();
-+    mptcp_userspace_pm_init();
  }
- /* Must be called with rcu read lock held */
 diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm_userspace.c
 +++ b/net/mptcp/pm_userspace.c
 @@ -XXX,XX +XXX,XX @@ int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
      sock_put(sk);
      return ret;
  }
 +
++static void mptcp_userspace_pm_init(struct mptcp_sock *msk)
++{
++    struct mptcp_pm_data *pm = &msk->pm;
++
++    WRITE_ONCE(pm->work_pending, 0);
++    WRITE_ONCE(pm->accept_addr, 0);
++    WRITE_ONCE(pm->accept_subflow, 0);
++}
++
 +static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
 +{
 +    mptcp_userspace_pm_free_local_addr_list(msk);
 +}
 +
-+static struct mptcp_pm_ops mptcp_userspace_pm = {
++static struct mptcp_pm_ops mptcp_pm_userspace = {
-+    .get_local_id        = mptcp_userspace_pm_get_local_id,
++    .init            = mptcp_userspace_pm_init,
 +    .get_priority        = mptcp_userspace_pm_is_backup,
 +    .release        = mptcp_userspace_pm_release,
 +    .name            = "userspace",
 +    .owner            = THIS_MODULE,
 +};
 +
-+void __init mptcp_userspace_pm_init(void)
++void __init mptcp_pm_userspace_register(void)
 +{
-+    mptcp_pm_register(&mptcp_userspace_pm);
++    mptcp_pm_register(&mptcp_pm_userspace);
 +}
 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/protocol.h
 +++ b/net/mptcp/protocol.h
 @@ -XXX,XX +XXX,XX @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
  }
+ void __init mptcp_pm_kernel_register(void);
++void __init mptcp_pm_userspace_register(void);
  void __init mptcp_pm_nl_init(void);
-+void __init mptcp_userspace_pm_init(void);
  void mptcp_pm_worker(struct mptcp_sock *msk);
  void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);
- unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
 --
 .43.0

-[PATCH mptcp-next v7 07/11] mptcp: pm: initialize and release mptcp_pm_ops
+[PATCH mptcp-next v8 08/12] mptcp: pm: initialize and release mptcp_pm_ops
 ...
 this pointer. mptcp_pm_initialize() is invoked in mptcp_pm_data_reset(),
 while mptcp_pm_release() is invoked in mptcp_pm_destroy().
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/pm.c       | 42 +++++++++++++++++++++++++++++++++++++++---
+ net/mptcp/pm.c       | 57 +++++++++++++++++++++++++++-----------------
- net/mptcp/protocol.h |  3 +++
+ net/mptcp/protocol.h |  1 +
-files changed, 42 insertions(+), 3 deletions(-)
+files changed, 36 insertions(+), 22 deletions(-)
 diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm.c
 +++ b/net/mptcp/pm.c
 @@ -XXX,XX +XXX,XX @@ void mptcp_pm_worker(struct mptcp_sock *msk)
- void mptcp_pm_destroy(struct mptcp_sock *msk)
+     spin_unlock_bh(&msk->pm.lock);
  {
      mptcp_pm_free_anno_list(msk);
 -
 -    if (mptcp_pm_is_userspace(msk))
 -        mptcp_userspace_pm_free_local_addr_list(msk);
 +    mptcp_pm_release(msk);
  }
- void mptcp_pm_data_reset(struct mptcp_sock *msk)
++static void mptcp_pm_initialize(struct mptcp_sock *msk,
- {
++                struct mptcp_pm_ops *pm)
 +    const char *path_manager = mptcp_get_path_manager(sock_net((struct sock *)msk));
      u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
      struct mptcp_pm_data *pm = &msk->pm;
 +    int ret;
      pm->add_addr_signaled = 0;
      pm->add_addr_accepted = 0;
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
      pm->rm_list_rx.nr = 0;
      WRITE_ONCE(pm->pm_type, pm_type);
 +    rcu_read_lock();
 +    ret = mptcp_pm_initialize(msk, mptcp_pm_find(path_manager));
 +    rcu_read_unlock();
 +    if (ret)
 +        return;
 +
      if (pm_type == MPTCP_PM_TYPE_KERNEL) {
          bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_get_available(char *buf, size_t maxlen)
      }
      rcu_read_unlock();
  }
 +
 +int mptcp_pm_initialize(struct mptcp_sock *msk, struct mptcp_pm_ops *pm)
 +{
-+    if (!pm)
++    if (!pm || !bpf_try_module_get(pm, pm->owner)) {
-+        pm = &mptcp_kernel_pm;
++        pr_warn_once("pm %s fails, fallback to default pm",
-+
++                 pm->name);
-+    if (!bpf_try_module_get(pm, pm->owner))
++        pm = &mptcp_pm_kernel;
-+        return -EBUSY;
++    }
 +
 +    msk->pm.ops = pm;
 +    if (msk->pm.ops->init)
 +        msk->pm.ops->init(msk);
 +
 +    pr_debug("pm %s initialized\n", pm->name);
-+    return 0;
 +}
 +
-+void mptcp_pm_release(struct mptcp_sock *msk)
++static void mptcp_pm_release(struct mptcp_sock *msk)
 +{
 +    struct mptcp_pm_ops *pm = msk->pm.ops;
 +
 +    if (!pm)
 +        return;
 ...
 +    if (pm->release)
 +        pm->release(msk);
 +
 +    bpf_module_put(pm, pm->owner);
 +}
++
+ void mptcp_pm_destroy(struct mptcp_sock *msk)
+ {
+     mptcp_pm_free_anno_list(msk);
+-
+-    if (mptcp_pm_is_userspace(msk))
+-        mptcp_userspace_pm_free_local_addr_list(msk);
++    mptcp_pm_release(msk);
+ }
+ void mptcp_pm_data_reset(struct mptcp_sock *msk)
+ {
++    const char *path_manager = mptcp_get_path_manager(sock_net((struct sock *)msk));
+     u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
+     struct mptcp_pm_data *pm = &msk->pm;
+@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
+     pm->rm_list_rx.nr = 0;
+     WRITE_ONCE(pm->pm_type, pm_type);
+-    if (pm_type == MPTCP_PM_TYPE_KERNEL) {
+-        bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
+-
+-        /* pm->work_pending must be only be set to 'true' when
+-         * pm->pm_type is set to MPTCP_PM_TYPE_KERNEL
+-         */
+-        WRITE_ONCE(pm->work_pending,
+-               (!!mptcp_pm_get_local_addr_max(msk) &&
+-                subflows_allowed) ||
+-               !!mptcp_pm_get_add_addr_signal_max(msk));
+-        WRITE_ONCE(pm->accept_addr,
+-               !!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);
+-    }
++    rcu_read_lock();
++    mptcp_pm_initialize(msk, mptcp_pm_find(path_manager));
++    rcu_read_unlock();
+     WRITE_ONCE(pm->addr_signal, 0);
+     WRITE_ONCE(pm->remote_deny_join_id0, false);
 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/protocol.h
 +++ b/net/mptcp/protocol.h
 @@ -XXX,XX +XXX,XX @@ struct mptcp_pm_data {
      struct mptcp_addr_info remote;
      struct list_head anno_list;
      struct list_head userspace_pm_local_addr_list;
 +    struct mptcp_pm_ops *ops;
      spinlock_t    lock;        /*protects the whole PM data */
-@@ -XXX,XX +XXX,XX @@ int mptcp_pm_validate(struct mptcp_pm_ops *pm);
- int mptcp_pm_register(struct mptcp_pm_ops *pm);
- void mptcp_pm_unregister(struct mptcp_pm_ops *pm);
- void mptcp_pm_get_available(char *buf, size_t maxlen);
-+int mptcp_pm_initialize(struct mptcp_sock *msk, struct mptcp_pm_ops *pm);
-+void mptcp_pm_release(struct mptcp_sock *msk);
- void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 --
 .43.0

-[PATCH mptcp-next v7 10/11] mptcp: pm: make get_local_id helpers static
+[PATCH mptcp-next v8 09/12] mptcp: pm: add get_local_id() interface
 ...
 Then mptcp_pm_nl_get_local_id() and mptcp_userspace_pm_get_local_id()
 helpers can be static.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/pm.c           | 4 +---
+ include/net/mptcp.h      | 3 +++
- net/mptcp/pm_kernel.c    | 4 ++--
+ net/mptcp/pm.c           | 6 ++----
- net/mptcp/pm_userspace.c | 4 ++--
+ net/mptcp/pm_kernel.c    | 5 +++--
  net/mptcp/pm_userspace.c | 5 +++--
  net/mptcp/protocol.h     | 4 ----
-files changed, 5 insertions(+), 11 deletions(-)
+files changed, 11 insertions(+), 12 deletions(-)
+diff --git a/include/net/mptcp.h b/include/net/mptcp.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/net/mptcp.h
++++ b/include/net/mptcp.h
+@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
+ #define MPTCP_PM_BUF_MAX    (MPTCP_PM_NAME_MAX * MPTCP_PM_MAX)
+ struct mptcp_pm_ops {
++    int (*get_local_id)(struct mptcp_sock *msk,
++                struct mptcp_pm_addr_entry *skc);
++
+     char            name[MPTCP_PM_NAME_MAX];
+     struct module        *owner;
+     struct list_head    list;
 diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm.c
 +++ b/net/mptcp/pm.c
 @@ -XXX,XX +XXX,XX @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 ...
 -    return mptcp_pm_nl_get_local_id(msk, &skc_local);
 +    return msk->pm.ops->get_local_id(msk, &skc_local);
  }
  bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
+@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name)
+ int mptcp_pm_validate(struct mptcp_pm_ops *pm)
+ {
+-    if (!pm->init) {
++    if (!pm->init || !pm->get_local_id) {
+         pr_err("%s does not implement required ops\n", pm->name);
+         return -EINVAL;
+     }
 diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm_kernel.c
 +++ b/net/mptcp/pm_kernel.c
 @@ -XXX,XX +XXX,XX @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 ...
 +static int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 +                    struct mptcp_pm_addr_entry *skc)
  {
      struct mptcp_pm_addr_entry *entry;
      struct pm_nl_pernet *pernet;
+@@ -XXX,XX +XXX,XX @@ static void mptcp_pm_nl_initialize(struct mptcp_sock *msk)
+ }
+ struct mptcp_pm_ops mptcp_pm_kernel = {
++    .get_local_id        = mptcp_pm_nl_get_local_id,
+     .init            = mptcp_pm_nl_initialize,
+     .name            = "kernel",
+     .owner            = THIS_MODULE,
 diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm_userspace.c
 +++ b/net/mptcp/pm_userspace.c
 @@ -XXX,XX +XXX,XX @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id)
 ...
 +static int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 +                       struct mptcp_pm_addr_entry *skc)
  {
      __be16 msk_sport =  ((struct inet_sock *)
                   inet_sk((struct sock *)msk))->inet_sport;
+@@ -XXX,XX +XXX,XX @@ static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
+ }
+ static struct mptcp_pm_ops mptcp_pm_userspace = {
++    .get_local_id        = mptcp_userspace_pm_get_local_id,
+     .init            = mptcp_userspace_pm_init,
+     .release        = mptcp_userspace_pm_release,
+     .name            = "userspace",
 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/protocol.h
 +++ b/net/mptcp/protocol.h
 @@ -XXX,XX +XXX,XX @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 ...

-[PATCH mptcp-next v7 11/11] mptcp: pm: make is_backup helpers static
+[PATCH mptcp-next v8 10/12] mptcp: pm: add get_priority() interface
 ...
 Then mptcp_pm_nl_is_backup() and mptcp_userspace_pm_is_backup() helpers
 can be static.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/pm.c           | 5 +----
+ include/net/mptcp.h      | 2 ++
- net/mptcp/pm_kernel.c    | 3 ++-
+ net/mptcp/pm.c           | 7 ++-----
- net/mptcp/pm_userspace.c | 4 ++--
+ net/mptcp/pm_kernel.c    | 4 +++-
  net/mptcp/pm_userspace.c | 5 +++--
  net/mptcp/protocol.h     | 2 --
-files changed, 5 insertions(+), 9 deletions(-)
+files changed, 10 insertions(+), 10 deletions(-)
+diff --git a/include/net/mptcp.h b/include/net/mptcp.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/net/mptcp.h
++++ b/include/net/mptcp.h
+@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
+ struct mptcp_pm_ops {
+     int (*get_local_id)(struct mptcp_sock *msk,
+                 struct mptcp_pm_addr_entry *skc);
++    bool (*get_priority)(struct mptcp_sock *msk,
++                 struct mptcp_addr_info *skc);
+     char            name[MPTCP_PM_NAME_MAX];
+     struct module        *owner;
 diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm.c
 +++ b/net/mptcp/pm.c
 @@ -XXX,XX +XXX,XX @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 ...
 -    return mptcp_pm_nl_is_backup(msk, &skc_local);
 +    return msk->pm.ops->get_priority(msk, &skc_local);
  }
  static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name)
+ int mptcp_pm_validate(struct mptcp_pm_ops *pm)
+ {
+-    if (!pm->init || !pm->get_local_id) {
++    if (!pm->init || !pm->get_local_id || !pm->get_priority) {
+         pr_err("%s does not implement required ops\n", pm->name);
+         return -EINVAL;
+     }
 diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm_kernel.c
 +++ b/net/mptcp/pm_kernel.c
 @@ -XXX,XX +XXX,XX @@ static int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 ...
 +static 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;
+@@ -XXX,XX +XXX,XX @@ static void mptcp_pm_nl_initialize(struct mptcp_sock *msk)
+ struct mptcp_pm_ops mptcp_pm_kernel = {
+     .get_local_id        = mptcp_pm_nl_get_local_id,
++    .get_priority        = mptcp_pm_nl_is_backup,
+     .init            = mptcp_pm_nl_initialize,
+     .name            = "kernel",
+     .owner            = THIS_MODULE,
 diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/pm_userspace.c
 +++ b/net/mptcp/pm_userspace.c
 @@ -XXX,XX +XXX,XX @@ static int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 ...
 +static bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
 +                     struct mptcp_addr_info *skc)
  {
      struct mptcp_pm_addr_entry *entry;
      bool backup;
+@@ -XXX,XX +XXX,XX @@ static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
+ static struct mptcp_pm_ops mptcp_pm_userspace = {
+     .get_local_id        = mptcp_userspace_pm_get_local_id,
++    .get_priority        = mptcp_userspace_pm_is_backup,
+     .init            = mptcp_userspace_pm_init,
+     .release        = mptcp_userspace_pm_release,
+     .name            = "userspace",
 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
 index XXXXXXX..XXXXXXX 100644
 --- a/net/mptcp/protocol.h
 +++ b/net/mptcp/protocol.h
 @@ -XXX,XX +XXX,XX @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 ...

-New patch
+[PATCH mptcp-next v8 11/12] selftests: mptcp: add pm_type mapping tests
+From: Geliang Tang <tanggeliang@kylinos.cn>
+This patch adds a new helper set_path_manager() to set the newly added
+net.mptcp.path_manager, and test it inside a userspace pm test.
+Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
+---
+ tools/testing/selftests/net/mptcp/mptcp_join.sh | 15 +++++++++++++++
+file changed, 15 insertions(+)
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index XXXXXXX..XXXXXXX 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -XXX,XX +XXX,XX @@ userspace_tests()
+     if reset_with_events "userspace pm add & remove address" &&
+        continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
+         set_userspace_pm $ns1
++        if continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/path_manager'; then
++            local pm1 pm2
++
++            pm1=$(ip netns exec ${ns1} sysctl -n net.mptcp.path_manager)
++            if [ "$pm1" != "userspace" ]; then
++                mptcp_lib_pr_fail "ns1 pm_type mapping fails"
++                return 1
++            fi
++
++            pm2=$(ip netns exec ${ns2} sysctl -n net.mptcp.path_manager)
++            if [ "$pm2" != "kernel" ]; then
++                mptcp_lib_pr_fail "ns2 pm_type mapping fails"
++                return 1
++            fi
++        fi
+         pm_nl_set_limits $ns2 2 2
+         { speed=5 \
+             run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
+--
+.43.0

-[PATCH mptcp-next v7 08/11] mptcp: pm: drop pm_type in mptcp_pm_data
+[PATCH mptcp-next v8 12/12] selftests: mptcp: add path_manager sysctl test
 From: Geliang Tang <tanggeliang@kylinos.cn>
-Now pm->pm_type can be replaced by pm->ops->name, then "pm_type" filed
+This patch adds a new helper set_path_manager() to set the newly added
-of struct mptcp_pm_data can be dropped.
+net.mptcp.path_manager, and test it inside a userspace pm test.
 Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
 ---
- net/mptcp/pm.c       | 4 +---
+ .../testing/selftests/net/mptcp/mptcp_join.sh | 34 ++++++++++++++++++-
- net/mptcp/protocol.h | 5 ++---
+file changed, 33 insertions(+), 1 deletion(-)
 files changed, 3 insertions(+), 6 deletions(-)
-diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
-index XXXXXXX..XXXXXXX 100644
+index XXXXXXX..XXXXXXX 100755
---- a/net/mptcp/pm.c
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
-+++ b/net/mptcp/pm.c
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
-@@ -XXX,XX +XXX,XX @@ void mptcp_pm_destroy(struct mptcp_sock *msk)
+@@ -XXX,XX +XXX,XX @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
- void mptcp_pm_data_reset(struct mptcp_sock *msk)
+0 0 65535,
 0 0 0"
 +set_path_manager()
 +{
 +    local ns=$1
 +    local pm=$2
 +
 +    if ! ip netns exec ${ns} sysctl net.mptcp.available_path_managers |
 +         grep -wq "${pm}"; then
 +        mptcp_lib_pr_fail "path manager ${pm} not found"
 +        return 1
 +    fi
 +    ip netns exec ${ns} sysctl -q net.mptcp.path_manager="${pm}"
 +}
 +
  init_partial()
  {
-     const char *path_manager = mptcp_get_path_manager(sock_net((struct sock *)msk));
+     capout=$(mktemp)
--    u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
+@@ -XXX,XX +XXX,XX @@ userspace_tests()
-     struct mptcp_pm_data *pm = &msk->pm;
+     # userspace pm create destroy subflow
-     int ret;
+     if reset_with_events "userspace pm create destroy subflow" &&
+        continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
-@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
+-        set_userspace_pm $ns2
-     pm->subflows = 0;
++        if continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/path_manager'; then
-     pm->rm_list_tx.nr = 0;
++            local pm1 pm2
-     pm->rm_list_rx.nr = 0;
++
--    WRITE_ONCE(pm->pm_type, pm_type);
++            set_path_manager $ns1 "kernel"
++            set_path_manager $ns2 "userspace"
-     rcu_read_lock();
++
-     ret = mptcp_pm_initialize(msk, mptcp_pm_find(path_manager));
++            pm1=$(ip netns exec ${ns1} sysctl -n net.mptcp.pm_type)
-@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
++            if [ "$pm1" != "0" ]; then
-     if (ret)
++                mptcp_lib_pr_fail "ns1 pm_type mapping fails"
-         return;
++                return 1
++            fi
--    if (pm_type == MPTCP_PM_TYPE_KERNEL) {
++
-+    if (mptcp_pm_is_kernel(msk)) {
++            pm2=$(ip netns exec ${ns2} sysctl -n net.mptcp.pm_type)
-         bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
++            if [ "$pm2" != "1" ]; then
++                mptcp_lib_pr_fail "ns2 pm_type mapping fails"
-         /* pm->work_pending must be only be set to 'true' when
++                return 1
-diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
++            fi
-index XXXXXXX..XXXXXXX 100644
++        else
---- a/net/mptcp/protocol.h
++            set_userspace_pm $ns2
-+++ b/net/mptcp/protocol.h
++        fi
-@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_data {
+         pm_nl_set_limits $ns1 0 1
-     u8        add_addr_signaled;
+         { speed=5 \
-     u8        add_addr_accepted;
+             run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
      u8        local_addr_used;
 -    u8        pm_type;
      u8        subflows;
      u8        status;
      DECLARE_BITMAP(id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
@@ -XXX,XX +XXX,XX @@ static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
  static inline bool mptcp_pm_is_userspace(const struct mptcp_sock *msk)
  {
 -    return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_USERSPACE;
 +    return !strncmp(msk->pm.ops->name, "userspace", MPTCP_PM_NAME_MAX);
  }
  static inline bool mptcp_pm_is_kernel(const struct mptcp_sock *msk)
  {
 -    return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_KERNEL;
 +    return !strncmp(msk->pm.ops->name, "kernel", MPTCP_PM_NAME_MAX);
  }
  static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
 --
 .43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

v7:
 - addresss Matt's comments in v6 [1].
 - drop "type" from struct mptcp_pm_ops as Matt suggested.
 - map "pm_type" to new sysctl as Matt suggested.

Depends on:
 - mptcp: pm: code reorganisation, v2

Based-on: <20250228-mptcp-pm-reorg-code-v2-0-fa8b2542b7a5@kernel.org>

[1]
https://patchwork.kernel.org/project/mptcp/cover/cover.1740320007.git.tanggeliang@kylinos.cn/

v6:
 - add "name" in struct mptcp_pm_ops.
 - add some "sysctl" patches.
 - drop "struct mptcp_pm_param".
 - drop "pm_type" in mptcp_pm_data.

v5:
 - use "struct mptcp_pm_param *param" as unified parameters for all
   interfaces.
 - register in-kernel mptcp_pm_ops too.
 - only implement two interfaces "get_local_id" and "get_priority" in
   this set.

v4:
 - include a new patch "define BPF path manager type".

- add new interfaces:
	created established closed
	listerner_created listener_closed

- rename interfaces as:
	address_announced address_removed
	subflow_established subflow_closed
	get_priority set_priority

- rename functions as:
	mptcp_pm_validate
	mptcp_pm_register
	mptcp_pm_unregister
	mptcp_pm_initialize
	mptcp_pm_release

v3:
 - rename the 2nd parameter of get_local_id() from 'local' to 'skc'.
 - keep the 'msk_sport' check in mptcp_userspace_pm_get_local_id().
 - return 'err' instead of '0' in userspace_pm_subflow_create().
 - drop 'ret' variable inmptcp_pm_data_reset().
 - fix typos in commit log.

v2:
 - update get_local_id interface in patch 2.

get_addr() and dump_addr() interfaces of BPF userspace pm are dropped
as Matt suggested.

In order to implement BPF path manager, it's necessary to unify the
interfaces of the path manager. This set contains some cleanups and
refactoring to unify the interfaces in kernel space. Finally, define
a struct mptcp_pm_ops for a path manager.

Geliang Tang (11):
  mptcp: pm: define struct mptcp_pm_ops
  mptcp: sysctl: new sysctl to set path manager by name
  mptcp: sysctl: map pm_type to path_manager
  mptcp: sysctl: add available_path_managers
  mptcp: pm: in-kernel: register mptcp_kernel_pm
  mptcp: pm: userspace: register mptcp_userspace_pm
  mptcp: pm: initialize and release mptcp_pm_ops
  mptcp: pm: drop pm_type in mptcp_pm_data
  mptcp: sysctl: drop get_pm_type helper
  mptcp: pm: make get_local_id helpers static
  mptcp: pm: make is_backup helpers static

-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

In order to allow users to develop their own BPF-based path manager,
this patch defines a struct ops "mptcp_pm_ops" for a userspace path
manager, which contains a set of interfaces.

Add a set of functions to register, unregister, find and validate a
given struct ops.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 include/net/mptcp.h  | 17 ++++++++++++++
 net/mptcp/pm.c       | 55 ++++++++++++++++++++++++++++++++++++++++++++
 net/mptcp/protocol.h |  5 ++++
 3 files changed, 77 insertions(+)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -XXX,XX +XXX,XX @@
 
 struct mptcp_info;
 struct mptcp_sock;
+struct mptcp_pm_addr_entry;
 struct seq_file;
 
 /* MPTCP sk_buff extension data */
@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
 	void (*release)(struct mptcp_sock *msk);
 } ____cacheline_aligned_in_smp;
 
+#define MPTCP_PM_NAME_MAX	16
+
+struct mptcp_pm_ops {
+	int (*get_local_id)(struct mptcp_sock *msk,
+			    struct mptcp_pm_addr_entry *skc);
+	bool (*get_priority)(struct mptcp_sock *msk,
+			     struct mptcp_addr_info *skc);
+
+	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);
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@
  */
 #define pr_fmt(fmt) "MPTCP: " fmt
 
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -XXX,XX +XXX,XX @@ 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,
@@ -XXX,XX +XXX,XX @@ void __init mptcp_pm_init(void)
 {
 	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;
+
+	list_for_each_entry_rcu(pm, &mptcp_pm_list, list) {
+		if (!strcmp(pm->name, name))
+			return pm;
+	}
+
+	return NULL;
+}
+
+int mptcp_pm_validate(struct mptcp_pm_ops *pm)
+{
+	if (!pm->get_local_id || !pm->get_priority) {
+		pr_err("%s does not implement required ops\n", pm->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mptcp_pm_register(struct mptcp_pm_ops *pm)
+{
+	int ret;
+
+	ret = mptcp_pm_validate(pm);
+	if (ret)
+		return ret;
+
+	spin_lock(&mptcp_pm_list_lock);
+	if (mptcp_pm_find(pm->name)) {
+		spin_unlock(&mptcp_pm_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&pm->list, &mptcp_pm_list);
+	spin_unlock(&mptcp_pm_list_lock);
+
+	pr_debug("%s registered\n", pm->name);
+	return 0;
+}
+
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
+{
+	spin_lock(&mptcp_pm_list_lock);
+	list_del_rcu(&pm->list);
+	spin_unlock(&mptcp_pm_list_lock);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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);
 
+struct mptcp_pm_ops *mptcp_pm_find(const char *name);
+int mptcp_pm_validate(struct mptcp_pm_ops *pm);
+int mptcp_pm_register(struct mptcp_pm_ops *pm);
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm);
+
 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,
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

A new net.mptcp.path_manager sysctl is added to determine which path
manager will be used by each newly-created MPTCP socket by setting the
name of it.

This sysctl makes the old one "pm_type" deprecated.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 Documentation/networking/mptcp-sysctl.rst | 22 ++++++++++
 net/mptcp/ctrl.c                          | 50 +++++++++++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 73 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index XXXXXXX..XXXXXXX 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -XXX,XX +XXX,XX @@ 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.
+	User-defined BPF-based path managers can also be set via this
+	sysctl.
+
+	This is a per-namespace sysctl.
+
+	* "kernel"          - In-kernel path manager
+	* "userspace"       - Userspace path manager
+	* all other strings - BPF-based path managers
+
+	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
@@ -XXX,XX +XXX,XX @@ pm_type - INTEGER
 
 	This is a per-namespace sysctl.
 
+	(Deprecated, use path_manager instead.).
+
 	* 0 - In-kernel path manager
 	* 1 - Userspace path manager
 
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ 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)
@@ -XXX,XX +XXX,XX @@ 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;
@@ -XXX,XX +XXX,XX @@ 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
@@ -XXX,XX +XXX,XX @@ 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;
+	int ret = 0;
+
+	rcu_read_lock();
+	pm = mptcp_pm_find(name);
+	if (pm)
+		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)
+{
+	char (*path_manager)[MPTCP_PM_NAME_MAX] = ctl->data;
+	char val[MPTCP_PM_NAME_MAX];
+	const struct ctl_table tbl = {
+		.data = val,
+		.maxlen = MPTCP_PM_NAME_MAX,
+	};
+	int ret;
+
+	strscpy(val, *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, val);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -XXX,XX +XXX,XX @@ 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,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -XXX,XX +XXX,XX @@ 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;
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch adds a new proc_handler "proc_pm_type" for "pm_type" to
map old path manager sysctl "pm_type" to the newly added "path_manager".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/ctrl.c | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ static int proc_path_manager(const struct ctl_table *ctl, int write,
 	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);
+	unsigned int val = READ_ONCE(*(u8 *)ctl->data);
+	const struct ctl_table tbl = {
+		.maxlen = sizeof(val),
+		.data = &val,
+	};
+	int ret;
+
+	if (val > mptcp_pm_type_max)
+		return -ERANGE;
+
+	ret = proc_douintvec(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		char *path_manager = "kernel";
+
+		if (val == MPTCP_PM_TYPE_USERSPACE)
+			path_manager = "userspace";
+		mptcp_set_path_manager(pernet->path_manager, path_manager);
+		WRITE_ONCE(*(u8 *)ctl->data, val);
+	}
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -XXX,XX +XXX,XX @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.procname = "pm_type",
 		.maxlen = sizeof(u8),
 		.mode = 0644,
-		.proc_handler = proc_dou8vec_minmax,
-		.extra1       = SYSCTL_ZERO,
-		.extra2       = &mptcp_pm_type_max
+		.proc_handler = proc_pm_type,
 	},
 	{
 		.procname = "scheduler",
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Similarly to net.mptcp.available_schedulers, this patch adds a new one
net.mptcp.available_path_managers to list the available path mangers.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 Documentation/networking/mptcp-sysctl.rst |  4 ++++
 include/net/mptcp.h                       |  2 ++
 net/mptcp/ctrl.c                          | 25 +++++++++++++++++++++++
 net/mptcp/pm.c                            | 19 +++++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 5 files changed, 51 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index XXXXXXX..XXXXXXX 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -XXX,XX +XXX,XX @@ 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.
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
 } ____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 {
 	int (*get_local_id)(struct mptcp_sock *msk,
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ static int proc_pm_type(const struct ctl_table *ctl, int write,
 	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",
@@ -XXX,XX +XXX,XX @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.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)
@@ -XXX,XX +XXX,XX @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	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));
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
 	list_del_rcu(&pm->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;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pm, &mptcp_pm_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs, "%s%s",
+				 offs == 0 ? "" : " ", pm->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
+	}
+	rcu_read_unlock();
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name);
 int mptcp_pm_validate(struct mptcp_pm_ops *pm);
 int mptcp_pm_register(struct mptcp_pm_ops *pm);
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm);
+void mptcp_pm_get_available(char *buf, size_t maxlen);
 
 void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch defines the original in-kernel netlink path manager as a
new struct mptcp_pm_ops named "mptcp_kernel_pm", and register it in
mptcp_pm_nl_init().

This mptcp_pm_ops will be skipped in mptcp_pm_unregister().

Only get_local_id() and get_priority() interfaces are implemented here.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c        | 3 +++
 net/mptcp/pm_kernel.c | 9 +++++++++
 net/mptcp/protocol.h  | 2 ++
 3 files changed, 14 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ int mptcp_pm_register(struct mptcp_pm_ops *pm)
 
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
 {
+	if (pm == &mptcp_kernel_pm)
+		return;
+
 	spin_lock(&mptcp_pm_list_lock);
 	list_del_rcu(&pm->list);
 	spin_unlock(&mptcp_pm_list_lock);
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -XXX,XX +XXX,XX @@ static struct pernet_operations mptcp_pm_pernet_ops = {
 	.size = sizeof(struct pm_nl_pernet),
 };
 
+struct mptcp_pm_ops mptcp_kernel_pm = {
+	.get_local_id		= mptcp_pm_nl_get_local_id,
+	.get_priority		= mptcp_pm_nl_is_backup,
+	.name			= "kernel",
+	.owner			= THIS_MODULE,
+};
+
 void __init mptcp_pm_nl_init(void)
 {
 	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
@@ -XXX,XX +XXX,XX @@ void __init mptcp_pm_nl_init(void)
 
 	if (genl_register_family(&mptcp_genl_family))
 		panic("Failed to register MPTCP PM netlink family\n");
+
+	mptcp_pm_register(&mptcp_kernel_pm);
 }
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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);
 
+extern struct mptcp_pm_ops mptcp_kernel_pm;
+
 struct mptcp_pm_ops *mptcp_pm_find(const char *name);
 int mptcp_pm_validate(struct mptcp_pm_ops *pm);
 int mptcp_pm_register(struct mptcp_pm_ops *pm);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch defines the original userspace path manager as a new
struct mptcp_pm_ops named "mptcp_userspace_pm", and register it
in mptcp_pm_data_init().

Only get_local_id(), get_priority() and release() interfaces are
implemented here. mptcp_userspace_pm_is_release() is a wrapper of
mptcp_userspace_pm_free_local_addr_list().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c           |  1 +
 net/mptcp/pm_userspace.c | 18 ++++++++++++++++++
 net/mptcp/protocol.h     |  1 +
 3 files changed, 20 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 void __init mptcp_pm_init(void)
 {
 	mptcp_pm_nl_init();
+	mptcp_userspace_pm_init();
 }
 
 /* Must be called with rcu read lock held */
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -XXX,XX +XXX,XX @@ int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
 	sock_put(sk);
 	return ret;
 }
+
+static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
+{
+	mptcp_userspace_pm_free_local_addr_list(msk);
+}
+
+static struct mptcp_pm_ops mptcp_userspace_pm = {
+	.get_local_id		= mptcp_userspace_pm_get_local_id,
+	.get_priority		= mptcp_userspace_pm_is_backup,
+	.release		= mptcp_userspace_pm_release,
+	.name			= "userspace",
+	.owner			= THIS_MODULE,
+};
+
+void __init mptcp_userspace_pm_init(void)
+{
+	mptcp_pm_register(&mptcp_userspace_pm);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 }
 
 void __init mptcp_pm_nl_init(void);
+void __init mptcp_userspace_pm_init(void);
 void mptcp_pm_worker(struct mptcp_sock *msk);
 void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Add a struct mptcp_pm_ops pointer "ops" in struct mptcp_pm_data, and two
functions mptcp_pm_initialize() and mptcp_pm_release(), to set and release
this pointer. mptcp_pm_initialize() is invoked in mptcp_pm_data_reset(),
while mptcp_pm_release() is invoked in mptcp_pm_destroy().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c       | 42 +++++++++++++++++++++++++++++++++++++++---
 net/mptcp/protocol.h |  3 +++
 2 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_worker(struct mptcp_sock *msk)
 void mptcp_pm_destroy(struct mptcp_sock *msk)
 {
 	mptcp_pm_free_anno_list(msk);
-
-	if (mptcp_pm_is_userspace(msk))
-		mptcp_userspace_pm_free_local_addr_list(msk);
+	mptcp_pm_release(msk);
 }
 
 void mptcp_pm_data_reset(struct mptcp_sock *msk)
 {
+	const char *path_manager = mptcp_get_path_manager(sock_net((struct sock *)msk));
 	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
 	struct mptcp_pm_data *pm = &msk->pm;
+	int ret;
 
 	pm->add_addr_signaled = 0;
 	pm->add_addr_accepted = 0;
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	pm->rm_list_rx.nr = 0;
 	WRITE_ONCE(pm->pm_type, pm_type);
 
+	rcu_read_lock();
+	ret = mptcp_pm_initialize(msk, mptcp_pm_find(path_manager));
+	rcu_read_unlock();
+	if (ret)
+		return;
+
 	if (pm_type == MPTCP_PM_TYPE_KERNEL) {
 		bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
 
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_get_available(char *buf, size_t maxlen)
 	}
 	rcu_read_unlock();
 }
+
+int mptcp_pm_initialize(struct mptcp_sock *msk, struct mptcp_pm_ops *pm)
+{
+	if (!pm)
+		pm = &mptcp_kernel_pm;
+
+	if (!bpf_try_module_get(pm, pm->owner))
+		return -EBUSY;
+
+	msk->pm.ops = pm;
+	if (msk->pm.ops->init)
+		msk->pm.ops->init(msk);
+
+	pr_debug("pm %s initialized\n", pm->name);
+	return 0;
+}
+
+void mptcp_pm_release(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_ops *pm = msk->pm.ops;
+
+	if (!pm)
+		return;
+
+	msk->pm.ops = NULL;
+	if (pm->release)
+		pm->release(msk);
+
+	bpf_module_put(pm, pm->owner);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_data {
 	struct mptcp_addr_info remote;
 	struct list_head anno_list;
 	struct list_head userspace_pm_local_addr_list;
+	struct mptcp_pm_ops *ops;
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
@@ -XXX,XX +XXX,XX @@ int mptcp_pm_validate(struct mptcp_pm_ops *pm);
 int mptcp_pm_register(struct mptcp_pm_ops *pm);
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm);
 void mptcp_pm_get_available(char *buf, size_t maxlen);
+int mptcp_pm_initialize(struct mptcp_sock *msk, struct mptcp_pm_ops *pm);
+void mptcp_pm_release(struct mptcp_sock *msk);
 
 void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Now pm->pm_type can be replaced by pm->ops->name, then "pm_type" filed
of struct mptcp_pm_data can be dropped.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c       | 4 +---
 net/mptcp/protocol.h | 5 ++---
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_destroy(struct mptcp_sock *msk)
 void mptcp_pm_data_reset(struct mptcp_sock *msk)
 {
 	const char *path_manager = mptcp_get_path_manager(sock_net((struct sock *)msk));
-	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
 	struct mptcp_pm_data *pm = &msk->pm;
 	int ret;
 
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	pm->subflows = 0;
 	pm->rm_list_tx.nr = 0;
 	pm->rm_list_rx.nr = 0;
-	WRITE_ONCE(pm->pm_type, pm_type);
 
 	rcu_read_lock();
 	ret = mptcp_pm_initialize(msk, mptcp_pm_find(path_manager));
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	if (ret)
 		return;
 
-	if (pm_type == MPTCP_PM_TYPE_KERNEL) {
+	if (mptcp_pm_is_kernel(msk)) {
 		bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
 
 		/* pm->work_pending must be only be set to 'true' when
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_data {
 	u8		add_addr_signaled;
 	u8		add_addr_accepted;
 	u8		local_addr_used;
-	u8		pm_type;
 	u8		subflows;
 	u8		status;
 	DECLARE_BITMAP(id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
@@ -XXX,XX +XXX,XX @@ static inline bool mptcp_pm_should_rm_signal(struct mptcp_sock *msk)
 
 static inline bool mptcp_pm_is_userspace(const struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_USERSPACE;
+	return !strncmp(msk->pm.ops->name, "userspace", MPTCP_PM_NAME_MAX);
 }
 
 static inline bool mptcp_pm_is_kernel(const struct mptcp_sock *msk)
 {
-	return READ_ONCE(msk->pm.pm_type) == MPTCP_PM_TYPE_KERNEL;
+	return !strncmp(msk->pm.ops->name, "kernel", MPTCP_PM_NAME_MAX);
 }
 
 static inline unsigned int mptcp_add_addr_len(int family, bool echo, bool port)
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

The helper mptcp_get_pm_type() is unused now, it's replaced by the
new one mptcp_get_path_manager(). So drop it.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/ctrl.c     | 5 -----
 net/mptcp/protocol.h | 1 -
 2 files changed, 6 deletions(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ unsigned int mptcp_close_timeout(const struct sock *sk)
 	return mptcp_get_pernet(sock_net(sk))->close_timeout;
 }
 
-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;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ int mptcp_is_checksum_enabled(const struct net *net);
 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);
 
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Now mptcp_pm_get_local_id() can directly invoke get_local_id() interface
through "ops" of "msk->pm". Instead of using mptcp_pm_is_userspace() to
check which get_local_id() helper to invoke.

Then mptcp_pm_nl_get_local_id() and mptcp_userspace_pm_get_local_id()
helpers can be static.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c           | 4 +---
 net/mptcp/pm_kernel.c    | 4 ++--
 net/mptcp/pm_userspace.c | 4 ++--
 net/mptcp/protocol.h     | 4 ----
 4 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	skc_local.addr.id = 0;
 	skc_local.flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 
-	if (mptcp_pm_is_userspace(msk))
-		return mptcp_userspace_pm_get_local_id(msk, &skc_local);
-	return mptcp_pm_nl_get_local_id(msk, &skc_local);
+	return msk->pm.ops->get_local_id(msk, &skc_local);
 }
 
 bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	return err;
 }
 
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
-			     struct mptcp_pm_addr_entry *skc)
+static int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
+				    struct mptcp_pm_addr_entry *skc)
 {
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -XXX,XX +XXX,XX @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id)
 	return NULL;
 }
 
-int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
-				    struct mptcp_pm_addr_entry *skc)
+static int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
+					   struct mptcp_pm_addr_entry *skc)
 {
 	__be16 msk_sport =  ((struct inet_sock *)
 			     inet_sk((struct sock *)msk))->inet_sport;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 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_pm_addr_entry *skc);
-int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
-				    struct mptcp_pm_addr_entry *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);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Now mptcp_pm_is_backup() can directly invoke get_priority() interface
through "ops" of "msk->pm". Instead of using mptcp_pm_is_userspace()
to check which is_backup() helper to invoke.

Then mptcp_pm_nl_is_backup() and mptcp_userspace_pm_is_backup() helpers
can be static.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c           | 5 +----
 net/mptcp/pm_kernel.c    | 3 ++-
 net/mptcp/pm_userspace.c | 4 ++--
 net/mptcp/protocol.h     | 2 --
 4 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 
 	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);
+	return msk->pm.ops->get_priority(msk, &skc_local);
 }
 
 static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 	return ret;
 }
 
-bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+static 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;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 	return mptcp_userspace_pm_append_new_local_addr(msk, skc, true);
 }
 
-bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
-				  struct mptcp_addr_info *skc)
+static bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+					 struct mptcp_addr_info *skc)
 {
 	struct mptcp_pm_addr_entry *entry;
 	bool backup;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *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_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
 int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

v8:
 - address Matt's comments in v7.

v7:
 - addresss Matt's comments in v6 [1].
 - drop "type" from struct mptcp_pm_ops as Matt suggested.
 - map "pm_type" to new sysctl as Matt suggested.

Depends on:
 - mptcp: pm: code reorganisation, v2

Based-on: <20250228-mptcp-pm-reorg-code-v2-0-fa8b2542b7a5@kernel.org>

[1]
https://patchwork.kernel.org/project/mptcp/cover/cover.1740320007.git.tanggeliang@kylinos.cn/

v6:
 - add "name" in struct mptcp_pm_ops.
 - add some "sysctl" patches.
 - drop "struct mptcp_pm_param".
 - drop "pm_type" in mptcp_pm_data.

v4:
 - include a new patch "define BPF path manager type".

- add new interfaces:
	created established closed
	listerner_created listener_closed

- rename interfaces as:
	address_announced address_removed
	subflow_established subflow_closed
	get_priority set_priority

- rename functions as:
	mptcp_pm_validate
	mptcp_pm_register
	mptcp_pm_unregister
	mptcp_pm_initialize
	mptcp_pm_release

v2:
 - update get_local_id interface in patch 2.

get_addr() and dump_addr() interfaces of BPF userspace pm are dropped
as Matt suggested.

Geliang Tang (12):
  mptcp: pm: define struct mptcp_pm_ops
  mptcp: sysctl: new sysctl to set path manager by name
  mptcp: sysctl: map pm_type to path_manager
  mptcp: sysctl: map path_manager to pm_type
  mptcp: sysctl: add available_path_managers
  mptcp: pm: in-kernel: register mptcp_pm_kernel
  mptcp: pm: userspace: register mptcp_pm_userspace
  mptcp: pm: initialize and release mptcp_pm_ops
  mptcp: pm: add get_local_id() interface
  mptcp: pm: add get_priority() interface
  selftests: mptcp: add pm_type mapping tests
  selftests: mptcp: add path_manager sysctl test

-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

In order to allow users to develop their own BPF-based path manager,
this patch defines a struct ops "mptcp_pm_ops" for a userspace path
manager, which contains a set of interfaces.

Add a set of functions to register, unregister, find and validate a
given struct ops.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 include/net/mptcp.h  | 12 ++++++++++
 net/mptcp/pm.c       | 55 ++++++++++++++++++++++++++++++++++++++++++++
 net/mptcp/protocol.h |  5 ++++
 3 files changed, 72 insertions(+)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -XXX,XX +XXX,XX @@
 
 struct mptcp_info;
 struct mptcp_sock;
+struct mptcp_pm_addr_entry;
 struct seq_file;
 
 /* MPTCP sk_buff extension data */
@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
 	void (*release)(struct mptcp_sock *msk);
 } ____cacheline_aligned_in_smp;
 
+#define MPTCP_PM_NAME_MAX	16
+
+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);
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@
  */
 #define pr_fmt(fmt) "MPTCP: " fmt
 
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -XXX,XX +XXX,XX @@ 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,
@@ -XXX,XX +XXX,XX @@ void __init mptcp_pm_init(void)
 	mptcp_pm_kernel_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;
+
+	list_for_each_entry_rcu(pm, &mptcp_pm_list, list) {
+		if (!strcmp(pm->name, name))
+			return pm;
+	}
+
+	return NULL;
+}
+
+int mptcp_pm_validate(struct mptcp_pm_ops *pm)
+{
+	if (!pm->init) {
+		pr_err("%s does not implement required ops\n", pm->name);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int mptcp_pm_register(struct mptcp_pm_ops *pm)
+{
+	int ret;
+
+	ret = mptcp_pm_validate(pm);
+	if (ret)
+		return ret;
+
+	spin_lock(&mptcp_pm_list_lock);
+	if (mptcp_pm_find(pm->name)) {
+		spin_unlock(&mptcp_pm_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&pm->list, &mptcp_pm_list);
+	spin_unlock(&mptcp_pm_list_lock);
+
+	pr_debug("%s registered\n", pm->name);
+	return 0;
+}
+
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
+{
+	spin_lock(&mptcp_pm_list_lock);
+	list_del_rcu(&pm->list);
+	spin_unlock(&mptcp_pm_list_lock);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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);
 
+struct mptcp_pm_ops *mptcp_pm_find(const char *name);
+int mptcp_pm_validate(struct mptcp_pm_ops *pm);
+int mptcp_pm_register(struct mptcp_pm_ops *pm);
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm);
+
 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,
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

A new net.mptcp.path_manager sysctl is added to determine which path
manager will be used by each newly-created MPTCP socket by setting the
name of it.

This sysctl makes the old one "pm_type" deprecated.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 Documentation/networking/mptcp-sysctl.rst | 19 +++++++++
 net/mptcp/ctrl.c                          | 50 +++++++++++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 70 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index XXXXXXX..XXXXXXX 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -XXX,XX +XXX,XX @@ 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
@@ -XXX,XX +XXX,XX @@ 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
 
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ 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)
@@ -XXX,XX +XXX,XX @@ 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;
@@ -XXX,XX +XXX,XX @@ 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
@@ -XXX,XX +XXX,XX @@ 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;
+	int ret = 0;
+
+	rcu_read_lock();
+	pm = mptcp_pm_find(name);
+	if (pm)
+		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)
+{
+	char (*path_manager)[MPTCP_PM_NAME_MAX] = ctl->data;
+	char val[MPTCP_PM_NAME_MAX];
+	const struct ctl_table tbl = {
+		.data = val,
+		.maxlen = MPTCP_PM_NAME_MAX,
+	};
+	int ret;
+
+	strscpy(val, *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, val);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -XXX,XX +XXX,XX @@ 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,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -XXX,XX +XXX,XX @@ 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;
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch adds a new proc_handler "proc_pm_type" for "pm_type" to
map old path manager sysctl "pm_type" to the newly added "path_manager".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/ctrl.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ static int proc_path_manager(const struct ctl_table *ctl, int write,
 	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);
+	u8 pm_type = READ_ONCE(*(u8 *)ctl->data);
+	const struct ctl_table tbl = {
+		.maxlen = sizeof(pm_type),
+		.data = &pm_type,
+	};
+	int ret;
+
+	ret = proc_dou8vec_minmax(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		char *path_manager = "kernel";
+
+		if (pm_type == MPTCP_PM_TYPE_USERSPACE)
+			path_manager = "userspace";
+		mptcp_set_path_manager(pernet->path_manager, path_manager);
+		WRITE_ONCE(*(u8 *)ctl->data, pm_type);
+	}
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -XXX,XX +XXX,XX @@ 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
 	},
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch maps the newly added path manager sysctl "path_manager"
to the old one "pm_type".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/ctrl.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_set_path_manager(char *path_manager, const char *name)
 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 val[MPTCP_PM_NAME_MAX];
 	const struct ctl_table tbl = {
@@ -XXX,XX +XXX,XX @@ static int proc_path_manager(const struct ctl_table *ctl, int write,
 	strscpy(val, *path_manager, MPTCP_PM_NAME_MAX);
 
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
-	if (write && ret == 0)
+	if (write && ret == 0) {
+		u8 pm_type = MPTCP_PM_TYPE_KERNEL;
+
+		if (!strncmp(val, "userspace", MPTCP_PM_NAME_MAX))
+			pm_type = MPTCP_PM_TYPE_USERSPACE;
+		pernet->pm_type = pm_type;
 		ret = mptcp_set_path_manager(*path_manager, val);
+	}
 
 	return ret;
 }
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Similarly to net.mptcp.available_schedulers, this patch adds a new one
net.mptcp.available_path_managers to list the available path managers.

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index XXXXXXX..XXXXXXX 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -XXX,XX +XXX,XX @@ 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.
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
 } ____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];
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -XXX,XX +XXX,XX @@ static int proc_pm_type(const struct ctl_table *ctl, int write,
 	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",
@@ -XXX,XX +XXX,XX @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.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)
@@ -XXX,XX +XXX,XX @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	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));
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
 	list_del_rcu(&pm->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;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pm, &mptcp_pm_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs, "%s%s",
+				 offs == 0 ? "" : " ", pm->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
+	}
+	rcu_read_unlock();
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name);
 int mptcp_pm_validate(struct mptcp_pm_ops *pm);
 int mptcp_pm_register(struct mptcp_pm_ops *pm);
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm);
+void mptcp_pm_get_available(char *buf, size_t maxlen);
 
 void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch defines the original in-kernel netlink path manager as a
new struct mptcp_pm_ops named "mptcp_pm_kernel", and register it in
mptcp_pm_kernel_register().

This mptcp_pm_ops will be skipped in mptcp_pm_unregister().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c        |  4 ++++
 net/mptcp/pm_kernel.c | 26 ++++++++++++++++++++++++++
 net/mptcp/protocol.h  |  3 +++
 3 files changed, 33 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ int mptcp_pm_register(struct mptcp_pm_ops *pm)
 
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm)
 {
+	/* skip unregistering the default path manager */
+	if (pm == &mptcp_pm_kernel)
+		return;
+
 	spin_lock(&mptcp_pm_list_lock);
 	list_del_rcu(&pm->list);
 	spin_unlock(&mptcp_pm_list_lock);
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -XXX,XX +XXX,XX @@ static struct pernet_operations mptcp_pm_pernet_ops = {
 	.size = sizeof(struct pm_nl_pernet),
 };
 
+static void mptcp_pm_nl_initialize(struct mptcp_sock *msk)
+{
+	bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
+	struct mptcp_pm_data *pm = &msk->pm;
+
+	/* pm->work_pending must be only be set to 'true' when
+	 * pm is the default path manager
+	 */
+	WRITE_ONCE(pm->work_pending,
+		   (!!mptcp_pm_get_local_addr_max(msk) &&
+		    subflows_allowed) ||
+		   !!mptcp_pm_get_add_addr_signal_max(msk));
+	WRITE_ONCE(pm->accept_addr,
+		   !!mptcp_pm_get_add_addr_accept_max(msk) &&
+		   subflows_allowed);
+	WRITE_ONCE(pm->accept_subflow, subflows_allowed);
+}
+
+struct mptcp_pm_ops mptcp_pm_kernel = {
+	.init			= mptcp_pm_nl_initialize,
+	.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");
+
+	mptcp_pm_register(&mptcp_pm_kernel);
 }
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ 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_validate(struct mptcp_pm_ops *pm);
 int mptcp_pm_register(struct mptcp_pm_ops *pm);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch defines the original userspace path manager as a new
struct mptcp_pm_ops named "mptcp_userspace_pm", and register it
in mptcp_pm_init(). mptcp_userspace_pm_is_release() is a wrapper
of mptcp_userspace_pm_free_local_addr_list().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c           |  1 +
 net/mptcp/pm_userspace.c | 26 ++++++++++++++++++++++++++
 net/mptcp/protocol.h     |  1 +
 3 files changed, 28 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ 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();
 }
 
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -XXX,XX +XXX,XX @@ int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
 	sock_put(sk);
 	return ret;
 }
+
+static void mptcp_userspace_pm_init(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_data *pm = &msk->pm;
+
+	WRITE_ONCE(pm->work_pending, 0);
+	WRITE_ONCE(pm->accept_addr, 0);
+	WRITE_ONCE(pm->accept_subflow, 0);
+}
+
+static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
+{
+	mptcp_userspace_pm_free_local_addr_list(msk);
+}
+
+static struct mptcp_pm_ops mptcp_pm_userspace = {
+	.init			= mptcp_userspace_pm_init,
+	.release		= mptcp_userspace_pm_release,
+	.name			= "userspace",
+	.owner			= THIS_MODULE,
+};
+
+void __init mptcp_pm_userspace_register(void)
+{
+	mptcp_pm_register(&mptcp_pm_userspace);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 }
 
 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);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/pm.c       | 57 +++++++++++++++++++++++++++-----------------
 net/mptcp/protocol.h |  1 +
 2 files changed, 36 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_worker(struct mptcp_sock *msk)
 	spin_unlock_bh(&msk->pm.lock);
 }
 
+static void mptcp_pm_initialize(struct mptcp_sock *msk,
+				struct mptcp_pm_ops *pm)
+{
+	if (!pm || !bpf_try_module_get(pm, pm->owner)) {
+		pr_warn_once("pm %s fails, fallback to default pm",
+			     pm->name);
+		pm = &mptcp_pm_kernel;
+	}
+
+	msk->pm.ops = pm;
+	if (msk->pm.ops->init)
+		msk->pm.ops->init(msk);
+
+	pr_debug("pm %s initialized\n", pm->name);
+}
+
+static void mptcp_pm_release(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_ops *pm = msk->pm.ops;
+
+	if (!pm)
+		return;
+
+	msk->pm.ops = NULL;
+	if (pm->release)
+		pm->release(msk);
+
+	bpf_module_put(pm, pm->owner);
+}
+
 void mptcp_pm_destroy(struct mptcp_sock *msk)
 {
 	mptcp_pm_free_anno_list(msk);
-
-	if (mptcp_pm_is_userspace(msk))
-		mptcp_userspace_pm_free_local_addr_list(msk);
+	mptcp_pm_release(msk);
 }
 
 void mptcp_pm_data_reset(struct mptcp_sock *msk)
 {
+	const char *path_manager = mptcp_get_path_manager(sock_net((struct sock *)msk));
 	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
 	struct mptcp_pm_data *pm = &msk->pm;
 
@@ -XXX,XX +XXX,XX @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	pm->rm_list_rx.nr = 0;
 	WRITE_ONCE(pm->pm_type, pm_type);
 
-	if (pm_type == MPTCP_PM_TYPE_KERNEL) {
-		bool subflows_allowed = !!mptcp_pm_get_subflows_max(msk);
-
-		/* pm->work_pending must be only be set to 'true' when
-		 * pm->pm_type is set to MPTCP_PM_TYPE_KERNEL
-		 */
-		WRITE_ONCE(pm->work_pending,
-			   (!!mptcp_pm_get_local_addr_max(msk) &&
-			    subflows_allowed) ||
-			   !!mptcp_pm_get_add_addr_signal_max(msk));
-		WRITE_ONCE(pm->accept_addr,
-			   !!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);
-	}
+	rcu_read_lock();
+	mptcp_pm_initialize(msk, mptcp_pm_find(path_manager));
+	rcu_read_unlock();
 
 	WRITE_ONCE(pm->addr_signal, 0);
 	WRITE_ONCE(pm->remote_deny_join_id0, false);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_data {
 	struct mptcp_addr_info remote;
 	struct list_head anno_list;
 	struct list_head userspace_pm_local_addr_list;
+	struct mptcp_pm_ops *ops;
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Now mptcp_pm_get_local_id() can directly invoke get_local_id() interface
through "ops" of "msk->pm". Instead of using mptcp_pm_is_userspace() to
check which get_local_id() helper to invoke.

Then mptcp_pm_nl_get_local_id() and mptcp_userspace_pm_get_local_id()
helpers can be static.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 include/net/mptcp.h      | 3 +++
 net/mptcp/pm.c           | 6 ++----
 net/mptcp/pm_kernel.c    | 5 +++--
 net/mptcp/pm_userspace.c | 5 +++--
 net/mptcp/protocol.h     | 4 ----
 5 files changed, 11 insertions(+), 12 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
 #define MPTCP_PM_BUF_MAX	(MPTCP_PM_NAME_MAX * MPTCP_PM_MAX)
 
 struct mptcp_pm_ops {
+	int (*get_local_id)(struct mptcp_sock *msk,
+			    struct mptcp_pm_addr_entry *skc);
+
 	char			name[MPTCP_PM_NAME_MAX];
 	struct module		*owner;
 	struct list_head	list;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	skc_local.addr.id = 0;
 	skc_local.flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 
-	if (mptcp_pm_is_userspace(msk))
-		return mptcp_userspace_pm_get_local_id(msk, &skc_local);
-	return mptcp_pm_nl_get_local_id(msk, &skc_local);
+	return msk->pm.ops->get_local_id(msk, &skc_local);
 }
 
 bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name)
 
 int mptcp_pm_validate(struct mptcp_pm_ops *pm)
 {
-	if (!pm->init) {
+	if (!pm->init || !pm->get_local_id) {
 		pr_err("%s does not implement required ops\n", pm->name);
 		return -EINVAL;
 	}
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	return err;
 }
 
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
-			     struct mptcp_pm_addr_entry *skc)
+static int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
+				    struct mptcp_pm_addr_entry *skc)
 {
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
@@ -XXX,XX +XXX,XX @@ static void mptcp_pm_nl_initialize(struct mptcp_sock *msk)
 }
 
 struct mptcp_pm_ops mptcp_pm_kernel = {
+	.get_local_id		= mptcp_pm_nl_get_local_id,
 	.init			= mptcp_pm_nl_initialize,
 	.name			= "kernel",
 	.owner			= THIS_MODULE,
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -XXX,XX +XXX,XX @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id)
 	return NULL;
 }
 
-int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
-				    struct mptcp_pm_addr_entry *skc)
+static int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
+					   struct mptcp_pm_addr_entry *skc)
 {
 	__be16 msk_sport =  ((struct inet_sock *)
 			     inet_sk((struct sock *)msk))->inet_sport;
@@ -XXX,XX +XXX,XX @@ static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
 }
 
 static struct mptcp_pm_ops mptcp_pm_userspace = {
+	.get_local_id		= mptcp_userspace_pm_get_local_id,
 	.init			= mptcp_userspace_pm_init,
 	.release		= mptcp_userspace_pm_release,
 	.name			= "userspace",
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 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_pm_addr_entry *skc);
-int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
-				    struct mptcp_pm_addr_entry *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);
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

Now mptcp_pm_is_backup() can directly invoke get_priority() interface
through "ops" of "msk->pm". Instead of using mptcp_pm_is_userspace()
to check which is_backup() helper to invoke.

Then mptcp_pm_nl_is_backup() and mptcp_userspace_pm_is_backup() helpers
can be static.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 include/net/mptcp.h      | 2 ++
 net/mptcp/pm.c           | 7 ++-----
 net/mptcp/pm_kernel.c    | 4 +++-
 net/mptcp/pm_userspace.c | 5 +++--
 net/mptcp/protocol.h     | 2 --
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index XXXXXXX..XXXXXXX 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -XXX,XX +XXX,XX @@ struct mptcp_sched_ops {
 struct mptcp_pm_ops {
 	int (*get_local_id)(struct mptcp_sock *msk,
 			    struct mptcp_pm_addr_entry *skc);
+	bool (*get_priority)(struct mptcp_sock *msk,
+			     struct mptcp_addr_info *skc);
 
 	char			name[MPTCP_PM_NAME_MAX];
 	struct module		*owner;
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -XXX,XX +XXX,XX @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 
 	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);
+	return msk->pm.ops->get_priority(msk, &skc_local);
 }
 
 static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
@@ -XXX,XX +XXX,XX @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name)
 
 int mptcp_pm_validate(struct mptcp_pm_ops *pm)
 {
-	if (!pm->init || !pm->get_local_id) {
+	if (!pm->init || !pm->get_local_id || !pm->get_priority) {
 		pr_err("%s does not implement required ops\n", pm->name);
 		return -EINVAL;
 	}
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 	return ret;
 }
 
-bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+static 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;
@@ -XXX,XX +XXX,XX @@ static void mptcp_pm_nl_initialize(struct mptcp_sock *msk)
 
 struct mptcp_pm_ops mptcp_pm_kernel = {
 	.get_local_id		= mptcp_pm_nl_get_local_id,
+	.get_priority		= mptcp_pm_nl_is_backup,
 	.init			= mptcp_pm_nl_initialize,
 	.name			= "kernel",
 	.owner			= THIS_MODULE,
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -XXX,XX +XXX,XX @@ static int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
 	return mptcp_userspace_pm_append_new_local_addr(msk, skc, true);
 }
 
-bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
-				  struct mptcp_addr_info *skc)
+static bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
+					 struct mptcp_addr_info *skc)
 {
 	struct mptcp_pm_addr_entry *entry;
 	bool backup;
@@ -XXX,XX +XXX,XX @@ static void mptcp_userspace_pm_release(struct mptcp_sock *msk)
 
 static struct mptcp_pm_ops mptcp_pm_userspace = {
 	.get_local_id		= mptcp_userspace_pm_get_local_id,
+	.get_priority		= mptcp_userspace_pm_is_backup,
 	.init			= mptcp_userspace_pm_init,
 	.release		= mptcp_userspace_pm_release,
 	.name			= "userspace",
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index XXXXXXX..XXXXXXX 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -XXX,XX +XXX,XX @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *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_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
 int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
-- 
2.43.0

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch adds a new helper set_path_manager() to set the newly added
net.mptcp.path_manager, and test it inside a userspace pm test.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

From: Geliang Tang <tanggeliang@kylinos.cn>

This patch adds a new helper set_path_manager() to set the newly added
net.mptcp.path_manager, and test it inside a userspace pm test.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 34 ++++++++++++++++++-
 1 file changed, 33 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index XXXXXXX..XXXXXXX 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -XXX,XX +XXX,XX @@ CBPF_MPTCP_SUBOPTION_ADD_ADDR="14,
 			       6 0 0 65535,
 			       6 0 0 0"
 
+set_path_manager()
+{
+	local ns=$1
+	local pm=$2
+
+	if ! ip netns exec ${ns} sysctl net.mptcp.available_path_managers |
+	     grep -wq "${pm}"; then
+		mptcp_lib_pr_fail "path manager ${pm} not found"
+		return 1
+	fi
+	ip netns exec ${ns} sysctl -q net.mptcp.path_manager="${pm}"
+}
+
 init_partial()
 {
 	capout=$(mktemp)
@@ -XXX,XX +XXX,XX @@ userspace_tests()
 	# userspace pm create destroy subflow
 	if reset_with_events "userspace pm create destroy subflow" &&
 	   continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/pm_type'; then
-		set_userspace_pm $ns2
+		if continue_if mptcp_lib_has_file '/proc/sys/net/mptcp/path_manager'; then
+			local pm1 pm2
+
+			set_path_manager $ns1 "kernel"
+			set_path_manager $ns2 "userspace"
+
+			pm1=$(ip netns exec ${ns1} sysctl -n net.mptcp.pm_type)
+			if [ "$pm1" != "0" ]; then
+				mptcp_lib_pr_fail "ns1 pm_type mapping fails"
+				return 1
+			fi
+
+			pm2=$(ip netns exec ${ns2} sysctl -n net.mptcp.pm_type)
+			if [ "$pm2" != "1" ]; then
+				mptcp_lib_pr_fail "ns2 pm_type mapping fails"
+				return 1
+			fi
+		else
+			set_userspace_pm $ns2
+		fi
 		pm_nl_set_limits $ns1 0 1
 		{ speed=5 \
 			run_tests $ns1 $ns2 10.0.1.1 & } 2>/dev/null
-- 
2.43.0