A userland needs to record its init thread group's PID when bootstrapped and capture its exit status and UID once all processes in the userland have terminated, without serializing normal fork() and exit() paths inside the userland. Commit the bootstrap child reaper and bind pid_ns->userland in userland_copy() after copy_process() attaches PIDs and drops tasklist_lock, and invoke userland_exit() from zap_pid_ns_processes() after the userland's PID namespace has killed and reaped all member tasks. Co-developed-by: David Howells Signed-off-by: David Howells Signed-off-by: Jarkko Sakkinen --- include/linux/pid_namespace.h | 4 ++++ include/linux/userland.h | 17 ++++++++++++++ kernel/fork.c | 4 ++++ kernel/pid_namespace.c | 2 ++ kernel/userland.c | 43 +++++++++++++++++++++++++++++++++++ 5 files changed, 70 insertions(+) diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index b20baaa7e62b..ef703a3b8ed5 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -15,6 +15,7 @@ #define MAX_PID_NS_LEVEL 32 struct fs_pin; +struct userland; #if defined(CONFIG_SYSCTL) && defined(CONFIG_MEMFD_CREATE) /* modes for vm.memfd_noexec sysctl */ @@ -45,6 +46,9 @@ struct pid_namespace { struct user_namespace *user_ns; struct ucounts *ucounts; int reboot; /* group exit code if this pidns was rebooted */ +#ifdef CONFIG_USERLAND + struct userland *userland; +#endif struct ns_common ns; struct work_struct work; } __randomize_layout; diff --git a/include/linux/userland.h b/include/linux/userland.h index 9b9fefed63ac..a92709957529 100644 --- a/include/linux/userland.h +++ b/include/linux/userland.h @@ -9,11 +9,14 @@ #include #include +#include #include struct file; struct nsproxy; struct pid; +struct pid_namespace; +struct task_struct; struct user_namespace; /** @@ -57,6 +60,7 @@ struct userland { struct user_namespace *user_ns; struct nsproxy *ns; struct pid *init_pid; + kuid_t init_uid; spinlock_t lock; /* Guards userland lifecycle state */ wait_queue_head_t waitq; unsigned int flags; @@ -66,6 +70,9 @@ struct userland { #ifdef CONFIG_USERLAND void userland_put(struct userland *c); bool userland_is_file(struct file *file); +void userland_copy(struct task_struct *tsk, struct pid *pid, + struct userland *userland); +void userland_exit(struct pid_namespace *pid_ns, struct task_struct *tsk); #else static inline void userland_put(struct userland *c) { @@ -75,6 +82,16 @@ static inline bool userland_is_file(struct file *file) { return false; } + +static inline void userland_copy(struct task_struct *tsk, struct pid *pid, + struct userland *userland) +{ +} + +static inline void userland_exit(struct pid_namespace *pid_ns, + struct task_struct *tsk) +{ +} #endif /* CONFIG_USERLAND */ #endif /* _LINUX_USERLAND_H */ diff --git a/kernel/fork.c b/kernel/fork.c index 5efceb8d58a7..d87ab7cbad5e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -83,6 +83,7 @@ #include #include #include +#include #include #include #include @@ -2584,6 +2585,9 @@ __latent_entropy struct task_struct *copy_process( syscall_tracepoint_update(p); write_unlock_irq(&tasklist_lock); + if (likely(p->pid) && thread_group_leader(p)) + userland_copy(p, pid, NULL); + if (pidfile) fd_install(pidfd, pidfile); diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 127a5fd23e70..70606d9c5b52 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -24,6 +24,7 @@ #include #include #include +#include #include #include "pid_sysctl.h" @@ -280,6 +281,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) current->signal->group_exit_code = pid_ns->reboot; acct_exit_ns(pid_ns); + userland_exit(pid_ns, me); return; } diff --git a/kernel/userland.c b/kernel/userland.c index 7be0c4b5385b..44a1976f97c2 100644 --- a/kernel/userland.c +++ b/kernel/userland.c @@ -92,3 +92,46 @@ bool userland_is_file(struct file *file) { return file->f_op == &userland_fops; } + +void userland_copy(struct task_struct *tsk, struct pid *pid, struct userland *c) +{ + if (likely(!c || !is_child_reaper(pid))) + return; + + scoped_guard(spinlock, &c->lock) { + if (c->state != USERLAND_FORKING) + return; + refcount_inc(&c->usage); + ns_of_pid(pid)->userland = c; + WRITE_ONCE(c->init_pid, get_pid(pid)); + WRITE_ONCE(c->state, USERLAND_RUNNING); + } +} + +void userland_exit(struct pid_namespace *pid_ns, struct task_struct *tsk) +{ + struct userland *c = pid_ns->userland; + struct task_struct *leader; + kuid_t uid; + int status; + + if (!c) + return; + + leader = tsk->group_leader; + rcu_read_lock(); + uid = task_uid(leader); + rcu_read_unlock(); + status = (tsk->signal->flags & SIGNAL_GROUP_EXIT) ? + tsk->signal->group_exit_code : leader->exit_code; + + scoped_guard(spinlock, &c->lock) { + c->exit_code = status; + c->init_uid = uid; + WRITE_ONCE(c->state, USERLAND_DEAD); + } + + pid_ns->userland = NULL; + __wake_up(&c->waitq, TASK_NORMAL, 0, poll_to_key(EPOLLHUP)); + userland_put(c); +} -- 2.47.3