From b639585e71e63008373d3a9fd060b87315fe7ea8 Mon Sep 17 00:00:00 2001 From: Wang Jinchao Date: Wed, 31 Jan 2024 10:54:41 +0800 Subject: fork: Using clone_flags for legacy clone check In the current implementation of clone(), there is a line that initializes `u64 clone_flags = args->flags` at the top. This means that there is no longer a need to use args->flags for the legacy clone check. Signed-off-by: Wang Jinchao Link: https://lore.kernel.org/r/202401311054+0800-wangjinchao@xfusion.com Signed-off-by: Christian Brauner --- kernel/fork.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 47ff3b35352e..95647c66309f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2875,8 +2875,8 @@ pid_t kernel_clone(struct kernel_clone_args *args) * here has the advantage that we don't need to have a separate helper * to check for legacy clone(). */ - if ((args->flags & CLONE_PIDFD) && - (args->flags & CLONE_PARENT_SETTID) && + if ((clone_flags & CLONE_PIDFD) && + (clone_flags & CLONE_PARENT_SETTID) && (args->pidfd == args->parent_tid)) return -EINVAL; -- cgit v1.2.3 From cdefbf2324ceda662e2667aa2f44e8b9de3d780f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Thu, 25 Jan 2024 17:17:34 +0100 Subject: pidfd: cleanup the usage of __pidfd_prepare's flags - make pidfd_create() static. - Don't pass O_RDWR | O_CLOEXEC to __pidfd_prepare() in copy_process(), __pidfd_prepare() adds these flags unconditionally. - Kill the flags check in __pidfd_prepare(). sys_pidfd_open() checks the flags itself, all other users of pidfd_prepare() pass flags = 0. If we need a sanity check for those other in kernel users then WARN_ON_ONCE(flags & ~PIDFD_NONBLOCK) makes more sense. - Don't pass O_RDWR to get_unused_fd_flags(), it ignores everything except O_CLOEXEC. - Don't pass O_CLOEXEC to anon_inode_getfile(), it ignores everything except O_ACCMODE | O_NONBLOCK. Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240125161734.GA778@redhat.com Signed-off-by: Christian Brauner --- include/linux/pid.h | 1 - kernel/fork.c | 9 +++------ kernel/pid.c | 2 +- 3 files changed, 4 insertions(+), 8 deletions(-) (limited to 'kernel/fork.c') diff --git a/include/linux/pid.h b/include/linux/pid.h index 395cacce1179..e6a041cb8bac 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -73,7 +73,6 @@ struct file; extern struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); -int pidfd_create(struct pid *pid, unsigned int flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); static inline struct pid *get_pid(struct pid *pid) diff --git a/kernel/fork.c b/kernel/fork.c index 95647c66309f..726a92043531 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2130,15 +2130,12 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re int pidfd; struct file *pidfd_file; - if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC)) - return -EINVAL; - - pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC); + pidfd = get_unused_fd_flags(O_CLOEXEC); if (pidfd < 0) return pidfd; pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, - flags | O_RDWR | O_CLOEXEC); + flags | O_RDWR); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); @@ -2524,7 +2521,7 @@ __latent_entropy struct task_struct *copy_process( */ if (clone_flags & CLONE_PIDFD) { /* Note that no task has been attached to @pid yet. */ - retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile); + retval = __pidfd_prepare(pid, 0, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; diff --git a/kernel/pid.c b/kernel/pid.c index b52b10865454..c7a3e359f8f5 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -595,7 +595,7 @@ struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags) * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. */ -int pidfd_create(struct pid *pid, unsigned int flags) +static int pidfd_create(struct pid *pid, unsigned int flags) { int pidfd; struct file *pidfd_file; -- cgit v1.2.3 From 64bef697d33b75fc06c5789b3f8108680271529f Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Wed, 31 Jan 2024 14:26:02 +0100 Subject: pidfd: implement PIDFD_THREAD flag for pidfd_open() With this flag: - pidfd_open() doesn't require that the target task must be a thread-group leader - pidfd_poll() succeeds when the task exits and becomes a zombie (iow, passes exit_notify()), even if it is a leader and thread-group is not empty. This means that the behaviour of pidfd_poll(PIDFD_THREAD, pid-of-group-leader) is not well defined if it races with exec() from its sub-thread; pidfd_poll() can succeed or not depending on whether pidfd_task_exited() is called before or after exchange_tids(). Perhaps we can improve this behaviour later, pidfd_poll() can probably take sig->group_exec_task into account. But this doesn't really differ from the case when the leader exits before other threads (so pidfd_poll() succeeds) and then another thread execs and pidfd_poll() will block again. thread_group_exited() is no longer used, perhaps it can die. Co-developed-by: Tycho Andersen Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240131132602.GA23641@redhat.com Tested-by: Tycho Andersen Reviewed-by: Tycho Andersen Signed-off-by: Christian Brauner --- fs/exec.c | 6 +++++- include/linux/pid.h | 3 ++- include/uapi/linux/pidfd.h | 3 ++- kernel/exit.c | 7 +++++++ kernel/fork.c | 38 +++++++++++++++++++++++++++++++------- kernel/pid.c | 14 +++----------- kernel/signal.c | 6 ++++-- 7 files changed, 54 insertions(+), 23 deletions(-) (limited to 'kernel/fork.c') diff --git a/fs/exec.c b/fs/exec.c index 8cdd5b2dd09c..b68f61bbcaa8 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1143,7 +1143,11 @@ static int de_thread(struct task_struct *tsk) BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; - + /* + * leader and tsk exhanged their pids, the old pid dies, + * wake up the PIDFD_THREAD waiters. + */ + do_notify_pidfd(leader); /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees diff --git a/include/linux/pid.h b/include/linux/pid.h index e6a041cb8bac..8124d57752b9 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -70,10 +70,11 @@ extern const struct file_operations pidfd_fops; struct file; -extern struct pid *pidfd_pid(const struct file *file); +struct pid *pidfd_pid(const struct file *file); struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags); struct task_struct *pidfd_get_task(int pidfd, unsigned int *flags); int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret); +void do_notify_pidfd(struct task_struct *task); static inline struct pid *get_pid(struct pid *pid) { diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 5406fbc13074..2e6461459877 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -7,6 +7,7 @@ #include /* Flags for pidfd_open(). */ -#define PIDFD_NONBLOCK O_NONBLOCK +#define PIDFD_NONBLOCK O_NONBLOCK +#define PIDFD_THREAD O_EXCL #endif /* _UAPI_LINUX_PIDFD_H */ diff --git a/kernel/exit.c b/kernel/exit.c index 3988a02efaef..c038d10dfb38 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -739,6 +739,13 @@ static void exit_notify(struct task_struct *tsk, int group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; + /* + * sub-thread or delay_group_leader(), wake up the + * PIDFD_THREAD waiters. + */ + if (!thread_group_empty(tsk)) + do_notify_pidfd(tsk); + if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && diff --git a/kernel/fork.c b/kernel/fork.c index 726a92043531..1a9b91055916 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -101,6 +101,7 @@ #include #include #include +#include #include #include @@ -2050,6 +2051,8 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) seq_put_decimal_ll(m, "Pid:\t", nr); + /* TODO: report PIDFD_THREAD */ + #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { @@ -2068,22 +2071,35 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) } #endif +static bool pidfd_task_exited(struct pid *pid, bool thread) +{ + struct task_struct *task; + bool exited; + + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + exited = !task || + (READ_ONCE(task->exit_state) && (thread || thread_group_empty(task))); + rcu_read_unlock(); + + return exited; +} + /* * Poll support for process exit notification. */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; + bool thread = file->f_flags & PIDFD_THREAD; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); - /* - * Inform pollers only when the whole thread group exits. - * If the thread group leader exits before all other threads in the - * group, then poll(2) should block, similar to the wait(2) family. + * Depending on PIDFD_THREAD, inform pollers when the thread + * or the whole thread-group exits. */ - if (thread_group_exited(pid)) + if (pidfd_task_exited(pid, thread)) poll_flags = EPOLLIN | EPOLLRDNORM; return poll_flags; @@ -2141,6 +2157,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re return PTR_ERR(pidfd_file); } get_pid(pid); /* held by pidfd_file now */ + /* + * anon_inode_getfile() ignores everything outside of the + * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. + */ + pidfd_file->f_flags |= (flags & PIDFD_THREAD); *ret = pidfd_file; return pidfd; } @@ -2154,7 +2175,8 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re * Allocate a new file that stashes @pid and reserve a new pidfd number in the * caller's file descriptor table. The pidfd is reserved but not installed yet. * - * The helper verifies that @pid is used as a thread group leader. + * The helper verifies that @pid is still in use, without PIDFD_THREAD the + * task identified by @pid must be a thread-group leader. * * If this function returns successfully the caller is responsible to either * call fd_install() passing the returned pidfd and pidfd file as arguments in @@ -2173,7 +2195,9 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - if (!pid || !pid_has_task(pid, PIDTYPE_TGID)) + bool thread = flags & PIDFD_THREAD; + + if (!pid || !pid_has_task(pid, thread ? PIDTYPE_PID : PIDTYPE_TGID)) return -EINVAL; return __pidfd_prepare(pid, flags, ret); diff --git a/kernel/pid.c b/kernel/pid.c index c7a3e359f8f5..e11144466828 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -552,11 +552,6 @@ struct pid *pidfd_get_pid(unsigned int fd, unsigned int *flags) * Return the task associated with @pidfd. The function takes a reference on * the returned task. The caller is responsible for releasing that reference. * - * Currently, the process identified by @pidfd is always a thread-group leader. - * This restriction currently exists for all aspects of pidfds including pidfd - * creation (CLONE_PIDFD cannot be used with CLONE_THREAD) and pidfd polling - * (only supports thread group leaders). - * * Return: On success, the task_struct associated with the pidfd. * On error, a negative errno number will be returned. */ @@ -615,11 +610,8 @@ static int pidfd_create(struct pid *pid, unsigned int flags) * @flags: flags to pass * * This creates a new pid file descriptor with the O_CLOEXEC flag set for - * the process identified by @pid. Currently, the process identified by - * @pid must be a thread-group leader. This restriction currently exists - * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot - * be used with CLONE_THREAD) and pidfd polling (only supports thread group - * leaders). + * the task identified by @pid. Without PIDFD_THREAD flag the target task + * must be a thread-group leader. * * Return: On success, a cloexec pidfd is returned. * On error, a negative errno number will be returned. @@ -629,7 +621,7 @@ SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags) int fd; struct pid *p; - if (flags & ~PIDFD_NONBLOCK) + if (flags & ~(PIDFD_NONBLOCK | PIDFD_THREAD)) return -EINVAL; if (pid <= 0) diff --git a/kernel/signal.c b/kernel/signal.c index 9561a3962ca6..9b40109f0c56 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2019,7 +2019,7 @@ ret: return ret; } -static void do_notify_pidfd(struct task_struct *task) +void do_notify_pidfd(struct task_struct *task) { struct pid *pid; @@ -2051,7 +2051,8 @@ bool do_notify_parent(struct task_struct *tsk, int sig) WARN_ON_ONCE(!tsk->ptrace && (tsk->group_leader != tsk || !thread_group_empty(tsk))); /* - * tsk is a group leader and has no threads, wake up the pidfd waiters. + * tsk is a group leader and has no threads, wake up the + * non-PIDFD_THREAD waiters. */ if (thread_group_empty(tsk)) do_notify_pidfd(tsk); @@ -3926,6 +3927,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, prepare_kill_siginfo(sig, &kinfo); } + /* TODO: respect PIDFD_THREAD */ ret = kill_pid_info(sig, &kinfo, pid); err: -- cgit v1.2.3 From 43f0df54c96fa5abcab9df8649c1e52119bf0238 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 2 Feb 2024 14:12:26 +0100 Subject: pidfd_poll: report POLLHUP when pid_task() == NULL Add another wake_up_all(wait_pidfd) into __change_pid() and change pidfd_poll() to include EPOLLHUP if task == NULL. This allows to wait until the target process/thread is reaped. TODO: change do_notify_pidfd() to use the keyed wakeups. Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240202131226.GA26018@redhat.com Signed-off-by: Christian Brauner --- kernel/fork.c | 22 +++++++--------------- kernel/pid.c | 5 +++++ 2 files changed, 12 insertions(+), 15 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 1a9b91055916..aa08193d124f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2071,20 +2071,6 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) } #endif -static bool pidfd_task_exited(struct pid *pid, bool thread) -{ - struct task_struct *task; - bool exited; - - rcu_read_lock(); - task = pid_task(pid, PIDTYPE_PID); - exited = !task || - (READ_ONCE(task->exit_state) && (thread || thread_group_empty(task))); - rcu_read_unlock(); - - return exited; -} - /* * Poll support for process exit notification. */ @@ -2092,6 +2078,7 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { struct pid *pid = file->private_data; bool thread = file->f_flags & PIDFD_THREAD; + struct task_struct *task; __poll_t poll_flags = 0; poll_wait(file, &pid->wait_pidfd, pts); @@ -2099,8 +2086,13 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) * Depending on PIDFD_THREAD, inform pollers when the thread * or the whole thread-group exits. */ - if (pidfd_task_exited(pid, thread)) + rcu_read_lock(); + task = pid_task(pid, PIDTYPE_PID); + if (!task) + poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP; + else if (task->exit_state && (thread || thread_group_empty(task))) poll_flags = EPOLLIN | EPOLLRDNORM; + rcu_read_unlock(); return poll_flags; } diff --git a/kernel/pid.c b/kernel/pid.c index e11144466828..62461c7c82b8 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -349,6 +349,11 @@ static void __change_pid(struct task_struct *task, enum pid_type type, hlist_del_rcu(&task->pid_links[type]); *pid_ptr = new; + if (type == PIDTYPE_PID) { + WARN_ON_ONCE(pid_has_task(pid, PIDTYPE_PID)); + wake_up_all(&pid->wait_pidfd); + } + for (tmp = PIDTYPE_MAX; --tmp >= 0; ) if (pid_has_task(pid, tmp)) return; -- cgit v1.2.3 From 83b290c9e3b5d95891f43a4aeadf6071cbff25d3 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 5 Feb 2024 15:55:32 +0100 Subject: pidfd: clone: allow CLONE_THREAD | CLONE_PIDFD together copy_process() just needs to pass PIDFD_THREAD to __pidfd_prepare() if clone_flags & CLONE_THREAD. We can also add another CLONE_ flag (or perhaps reuse CLONE_DETACHED) to enforce PIDFD_THREAD without CLONE_THREAD. Originally-from: Tycho Andersen Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240205145532.GA28823@redhat.com Reviewed-by: Tycho Andersen Signed-off-by: Christian Brauner --- kernel/fork.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index aa08193d124f..4b6d994505ca 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2311,9 +2311,8 @@ __latent_entropy struct task_struct *copy_process( /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. - * - CLONE_THREAD is blocked until someone really needs it. */ - if (clone_flags & (CLONE_DETACHED | CLONE_THREAD)) + if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } @@ -2536,8 +2535,10 @@ __latent_entropy struct task_struct *copy_process( * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { + int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; + /* Note that no task has been attached to @pid yet. */ - retval = __pidfd_prepare(pid, 0, &pidfile); + retval = __pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; -- cgit v1.2.3 From 81b9d8ac0640b285a3c369cd41a85f6c240d3a60 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Fri, 9 Feb 2024 14:06:50 +0100 Subject: pidfd: change pidfd_send_signal() to respect PIDFD_THREAD Turn kill_pid_info() into kill_pid_info_type(), this allows to pass any pid_type to group_send_sig_info(), despite its name it should work fine even if type = PIDTYPE_PID. Change pidfd_send_signal() to use PIDTYPE_PID or PIDTYPE_TGID depending on PIDFD_THREAD. While at it kill another TODO comment in pidfd_show_fdinfo(). As Christian expains fdinfo reports f_flags, userspace can already detect PIDFD_THREAD. Reviewed-by: Tycho Andersen Signed-off-by: Oleg Nesterov Link: https://lore.kernel.org/r/20240209130650.GA8048@redhat.com Signed-off-by: Christian Brauner --- kernel/fork.c | 2 -- kernel/signal.c | 39 +++++++++++++++++++++++---------------- 2 files changed, 23 insertions(+), 18 deletions(-) (limited to 'kernel/fork.c') diff --git a/kernel/fork.c b/kernel/fork.c index 4b6d994505ca..3f22ec90c5c6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2051,8 +2051,6 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) seq_put_decimal_ll(m, "Pid:\t", nr); - /* TODO: report PIDFD_THREAD */ - #ifdef CONFIG_PID_NS seq_put_decimal_ll(m, "\nNSpid:\t", nr); if (nr > 0) { diff --git a/kernel/signal.c b/kernel/signal.c index 1450689302d9..8b8169623850 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -47,6 +47,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -1436,7 +1437,8 @@ void lockdep_assert_task_sighand_held(struct task_struct *task) #endif /* - * send signal info to all the members of a group + * send signal info to all the members of a thread group or to the + * individual thread if type == PIDTYPE_PID. */ int group_send_sig_info(int sig, struct kernel_siginfo *info, struct task_struct *p, enum pid_type type) @@ -1478,7 +1480,8 @@ int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp) return ret; } -int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) +static int kill_pid_info_type(int sig, struct kernel_siginfo *info, + struct pid *pid, enum pid_type type) { int error = -ESRCH; struct task_struct *p; @@ -1487,11 +1490,10 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) - error = group_send_sig_info(sig, info, p, PIDTYPE_TGID); + error = group_send_sig_info(sig, info, p, type); rcu_read_unlock(); if (likely(!p || error != -ESRCH)) return error; - /* * The task was unhashed in between, try again. If it * is dead, pid_task() will return NULL, if we race with @@ -1500,6 +1502,11 @@ int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) } } +int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid) +{ + return kill_pid_info_type(sig, info, pid, PIDTYPE_TGID); +} + static int kill_proc_info(int sig, struct kernel_siginfo *info, pid_t pid) { int error; @@ -3873,14 +3880,10 @@ static struct pid *pidfd_to_pid(const struct file *file) * @info: signal info * @flags: future flags * - * The syscall currently only signals via PIDTYPE_PID which covers - * kill(, . It does not signal threads or process - * groups. - * In order to extend the syscall to threads and process groups the @flags - * argument should be used. In essence, the @flags argument will determine - * what is signaled and not the file descriptor itself. Put in other words, - * grouping is a property of the flags argument not a property of the file - * descriptor. + * Send the signal to the thread group or to the individual thread depending + * on PIDFD_THREAD. + * In the future extension to @flags may be used to override the default scope + * of @pidfd. * * Return: 0 on success, negative errno on failure */ @@ -3891,6 +3894,7 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, struct fd f; struct pid *pid; kernel_siginfo_t kinfo; + enum pid_type type; /* Enforce flags be set to 0 until we add an extension. */ if (flags) @@ -3911,6 +3915,11 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, if (!access_pidfd_pidns(pid)) goto err; + if (f.file->f_flags & PIDFD_THREAD) + type = PIDTYPE_PID; + else + type = PIDTYPE_TGID; + if (info) { ret = copy_siginfo_from_user_any(&kinfo, info); if (unlikely(ret)) @@ -3926,12 +3935,10 @@ SYSCALL_DEFINE4(pidfd_send_signal, int, pidfd, int, sig, (kinfo.si_code >= 0 || kinfo.si_code == SI_TKILL)) goto err; } else { - prepare_kill_siginfo(sig, &kinfo, PIDTYPE_TGID); + prepare_kill_siginfo(sig, &kinfo, type); } - /* TODO: respect PIDFD_THREAD */ - ret = kill_pid_info(sig, &kinfo, pid); - + ret = kill_pid_info_type(sig, &kinfo, pid, type); err: fdput(f); return ret; -- cgit v1.2.3 From 46faf9d8e1d52e4a91c382c6c72da6bd8e68297b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 5 Feb 2024 13:10:19 -0800 Subject: rcu-tasks: Initialize data to eliminate RCU-tasks/do_exit() deadlocks Holding a mutex across synchronize_rcu_tasks() and acquiring that same mutex in code called from do_exit() after its call to exit_tasks_rcu_start() but before its call to exit_tasks_rcu_stop() results in deadlock. This is by design, because tasks that are far enough into do_exit() are no longer present on the tasks list, making it a bit difficult for RCU Tasks to find them, let alone wait on them to do a voluntary context switch. However, such deadlocks are becoming more frequent. In addition, lockdep currently does not detect such deadlocks and they can be difficult to reproduce. In addition, if a task voluntarily context switches during that time (for example, if it blocks acquiring a mutex), then this task is in an RCU Tasks quiescent state. And with some adjustments, RCU Tasks could just as well take advantage of that fact. This commit therefore initializes the data structures that will be needed to rely on these quiescent states and to eliminate these deadlocks. Link: https://lore.kernel.org/all/20240118021842.290665-1-chenzhongjin@huawei.com/ Reported-by: Chen Zhongjin Reported-by: Yang Jihong Signed-off-by: Paul E. McKenney Tested-by: Yang Jihong Tested-by: Chen Zhongjin Reviewed-by: Frederic Weisbecker Signed-off-by: Boqun Feng --- init/init_task.c | 1 + kernel/fork.c | 1 + kernel/rcu/tasks.h | 2 ++ 3 files changed, 4 insertions(+) (limited to 'kernel/fork.c') diff --git a/init/init_task.c b/init/init_task.c index 7ecb458eb3da..4daee6d761c8 100644 --- a/init/init_task.c +++ b/init/init_task.c @@ -147,6 +147,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = { .rcu_tasks_holdout = false, .rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list), .rcu_tasks_idle_cpu = -1, + .rcu_tasks_exit_list = LIST_HEAD_INIT(init_task.rcu_tasks_exit_list), #endif #ifdef CONFIG_TASKS_TRACE_RCU .trc_reader_nesting = 0, diff --git a/kernel/fork.c b/kernel/fork.c index 0d944e92a43f..af7203be1d2d 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1976,6 +1976,7 @@ static inline void rcu_copy_process(struct task_struct *p) p->rcu_tasks_holdout = false; INIT_LIST_HEAD(&p->rcu_tasks_holdout_list); p->rcu_tasks_idle_cpu = -1; + INIT_LIST_HEAD(&p->rcu_tasks_exit_list); #endif /* #ifdef CONFIG_TASKS_RCU */ #ifdef CONFIG_TASKS_TRACE_RCU p->trc_reader_nesting = 0; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 6961a1b5b783..edd14fee48c5 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -274,6 +274,8 @@ static void cblist_init_generic(struct rcu_tasks *rtp) rtpcp->rtpp = rtp; if (!rtpcp->rtp_blkd_tasks.next) INIT_LIST_HEAD(&rtpcp->rtp_blkd_tasks); + if (!rtpcp->rtp_exit_list.next) + INIT_LIST_HEAD(&rtpcp->rtp_exit_list); } pr_info("%s: Setting shift to %d and lim to %d rcu_task_cb_adjust=%d.\n", rtp->name, -- cgit v1.2.3 From 50f4f2d197e194ec0356962b99ca2b72e9a37bc8 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 12 Feb 2024 16:00:50 +0100 Subject: pidfd: move struct pidfd_fops Move the pidfd file operations over to their own file in preparation of implementing pidfs and to isolate them from other mostly unrelated functionality in other files. Link: https://lore.kernel.org/r/20240213-vfs-pidfd_fs-v1-1-f863f58cfce1@kernel.org Signed-off-by: Christian Brauner --- fs/Makefile | 2 +- fs/pidfs.c | 122 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/fork.c | 110 ---------------------------------------------------- 3 files changed, 123 insertions(+), 111 deletions(-) create mode 100644 fs/pidfs.c (limited to 'kernel/fork.c') diff --git a/fs/Makefile b/fs/Makefile index c09016257f05..125301673985 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -15,7 +15,7 @@ obj-y := open.o read_write.o file_table.o super.o \ pnode.o splice.o sync.o utimes.o d_path.o \ stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \ fs_types.o fs_context.o fs_parser.o fsopen.o init.o \ - kernel_read_file.o mnt_idmapping.o remap_range.o + kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o obj-$(CONFIG_BUFFER_HEAD) += buffer.o mpage.o obj-$(CONFIG_PROC_FS) += proc_namespace.o diff --git a/fs/pidfs.c b/fs/pidfs.c new file mode 100644 index 000000000000..eccb291862a0 --- /dev/null +++ b/fs/pidfs.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +static int pidfd_release(struct inode *inode, struct file *file) +{ + struct pid *pid = file->private_data; + + file->private_data = NULL; + put_pid(pid); + return 0; +} + +#ifdef CONFIG_PROC_FS +/** + * pidfd_show_fdinfo - print information about a pidfd + * @m: proc fdinfo file + * @f: file referencing a pidfd + * + * Pid: + * This function will print the pid that a given pidfd refers to in the + * pid namespace of the procfs instance. + * If the pid namespace of the process is not a descendant of the pid + * namespace of the procfs instance 0 will be shown as its pid. This is + * similar to calling getppid() on a process whose parent is outside of + * its pid namespace. + * + * NSpid: + * If pid namespaces are supported then this function will also print + * the pid of a given pidfd refers to for all descendant pid namespaces + * starting from the current pid namespace of the instance, i.e. the + * Pid field and the first entry in the NSpid field will be identical. + * If the pid namespace of the process is not a descendant of the pid + * namespace of the procfs instance 0 will be shown as its first NSpid + * entry and no others will be shown. + * Note that this differs from the Pid and NSpid fields in + * /proc//status where Pid and NSpid are always shown relative to + * the pid namespace of the procfs instance. The difference becomes + * obvious when sending around a pidfd between pid namespaces from a + * different branch of the tree, i.e. where no ancestral relation is + * present between the pid namespaces: + * - create two new pid namespaces ns1 and ns2 in the initial pid + * namespace (also take care to create new mount namespaces in the + * new pid namespace and mount procfs) + * - create a process with a pidfd in ns1 + * - send pidfd from ns1 to ns2 + * - read /proc/self/fdinfo/ and observe that both Pid and NSpid + * have exactly one entry, which is 0 + */ +static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct pid *pid = f->private_data; + struct pid_namespace *ns; + pid_t nr = -1; + + if (likely(pid_has_task(pid, PIDTYPE_PID))) { + ns = proc_pid_ns(file_inode(m->file)->i_sb); + nr = pid_nr_ns(pid, ns); + } + + seq_put_decimal_ll(m, "Pid:\t", nr); + +#ifdef CONFIG_PID_NS + seq_put_decimal_ll(m, "\nNSpid:\t", nr); + if (nr > 0) { + int i; + + /* If nr is non-zero it means that 'pid' is valid and that + * ns, i.e. the pid namespace associated with the procfs + * instance, is in the pid namespace hierarchy of pid. + * Start at one below the already printed level. + */ + for (i = ns->level + 1; i <= pid->level; i++) + seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); + } +#endif + seq_putc(m, '\n'); +} +#endif + +/* + * Poll support for process exit notification. + */ +static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) +{ + struct pid *pid = file->private_data; + bool thread = file->f_flags & PIDFD_THREAD; + struct task_struct *task; + __poll_t poll_flags = 0; + + poll_wait(file, &pid->wait_pidfd, pts); + /* + * Depending on PIDFD_THREAD, inform pollers when the thread + * or the whole thread-group exits. + */ + guard(rcu)(); + task = pid_task(pid, PIDTYPE_PID); + if (!task) + poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP; + else if (task->exit_state && (thread || thread_group_empty(task))) + poll_flags = EPOLLIN | EPOLLRDNORM; + + return poll_flags; +} + +const struct file_operations pidfd_fops = { + .release = pidfd_release, + .poll = pidfd_poll, +#ifdef CONFIG_PROC_FS + .show_fdinfo = pidfd_show_fdinfo, +#endif +}; diff --git a/kernel/fork.c b/kernel/fork.c index 3f22ec90c5c6..662a61f340ce 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1993,116 +1993,6 @@ struct pid *pidfd_pid(const struct file *file) return ERR_PTR(-EBADF); } -static int pidfd_release(struct inode *inode, struct file *file) -{ - struct pid *pid = file->private_data; - - file->private_data = NULL; - put_pid(pid); - return 0; -} - -#ifdef CONFIG_PROC_FS -/** - * pidfd_show_fdinfo - print information about a pidfd - * @m: proc fdinfo file - * @f: file referencing a pidfd - * - * Pid: - * This function will print the pid that a given pidfd refers to in the - * pid namespace of the procfs instance. - * If the pid namespace of the process is not a descendant of the pid - * namespace of the procfs instance 0 will be shown as its pid. This is - * similar to calling getppid() on a process whose parent is outside of - * its pid namespace. - * - * NSpid: - * If pid namespaces are supported then this function will also print - * the pid of a given pidfd refers to for all descendant pid namespaces - * starting from the current pid namespace of the instance, i.e. the - * Pid field and the first entry in the NSpid field will be identical. - * If the pid namespace of the process is not a descendant of the pid - * namespace of the procfs instance 0 will be shown as its first NSpid - * entry and no others will be shown. - * Note that this differs from the Pid and NSpid fields in - * /proc//status where Pid and NSpid are always shown relative to - * the pid namespace of the procfs instance. The difference becomes - * obvious when sending around a pidfd between pid namespaces from a - * different branch of the tree, i.e. where no ancestral relation is - * present between the pid namespaces: - * - create two new pid namespaces ns1 and ns2 in the initial pid - * namespace (also take care to create new mount namespaces in the - * new pid namespace and mount procfs) - * - create a process with a pidfd in ns1 - * - send pidfd from ns1 to ns2 - * - read /proc/self/fdinfo/ and observe that both Pid and NSpid - * have exactly one entry, which is 0 - */ -static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) -{ - struct pid *pid = f->private_data; - struct pid_namespace *ns; - pid_t nr = -1; - - if (likely(pid_has_task(pid, PIDTYPE_PID))) { - ns = proc_pid_ns(file_inode(m->file)->i_sb); - nr = pid_nr_ns(pid, ns); - } - - seq_put_decimal_ll(m, "Pid:\t", nr); - -#ifdef CONFIG_PID_NS - seq_put_decimal_ll(m, "\nNSpid:\t", nr); - if (nr > 0) { - int i; - - /* If nr is non-zero it means that 'pid' is valid and that - * ns, i.e. the pid namespace associated with the procfs - * instance, is in the pid namespace hierarchy of pid. - * Start at one below the already printed level. - */ - for (i = ns->level + 1; i <= pid->level; i++) - seq_put_decimal_ll(m, "\t", pid->numbers[i].nr); - } -#endif - seq_putc(m, '\n'); -} -#endif - -/* - * Poll support for process exit notification. - */ -static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) -{ - struct pid *pid = file->private_data; - bool thread = file->f_flags & PIDFD_THREAD; - struct task_struct *task; - __poll_t poll_flags = 0; - - poll_wait(file, &pid->wait_pidfd, pts); - /* - * Depending on PIDFD_THREAD, inform pollers when the thread - * or the whole thread-group exits. - */ - rcu_read_lock(); - task = pid_task(pid, PIDTYPE_PID); - if (!task) - poll_flags = EPOLLIN | EPOLLRDNORM | EPOLLHUP; - else if (task->exit_state && (thread || thread_group_empty(task))) - poll_flags = EPOLLIN | EPOLLRDNORM; - rcu_read_unlock(); - - return poll_flags; -} - -const struct file_operations pidfd_fops = { - .release = pidfd_release, - .poll = pidfd_poll, -#ifdef CONFIG_PROC_FS - .show_fdinfo = pidfd_show_fdinfo, -#endif -}; - /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd -- cgit v1.2.3 From cb12fd8e0dabb9a1c8aef55a6a41e2c255fcdf4b Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Mon, 12 Feb 2024 16:32:38 +0100 Subject: pidfd: add pidfs This moves pidfds from the anonymous inode infrastructure to a tiny pseudo filesystem. This has been on my todo for quite a while as it will unblock further work that we weren't able to do simply because of the very justified limitations of anonymous inodes. Moving pidfds to a tiny pseudo filesystem allows: * statx() on pidfds becomes useful for the first time. * pidfds can be compared simply via statx() and then comparing inode numbers. * pidfds have unique inode numbers for the system lifetime. * struct pid is now stashed in inode->i_private instead of file->private_data. This means it is now possible to introduce concepts that operate on a process once all file descriptors have been closed. A concrete example is kill-on-last-close. * file->private_data is freed up for per-file options for pidfds. * Each struct pid will refer to a different inode but the same struct pid will refer to the same inode if it's opened multiple times. In contrast to now where each struct pid refers to the same inode. Even if we were to move to anon_inode_create_getfile() which creates new inodes we'd still be associating the same struct pid with multiple different inodes. The tiny pseudo filesystem is not visible anywhere in userspace exactly like e.g., pipefs and sockfs. There's no lookup, there's no complex inode operations, nothing. Dentries and inodes are always deleted when the last pidfd is closed. We allocate a new inode for each struct pid and we reuse that inode for all pidfds. We use iget_locked() to find that inode again based on the inode number which isn't recycled. We allocate a new dentry for each pidfd that uses the same inode. That is similar to anonymous inodes which reuse the same inode for thousands of dentries. For pidfds we're talking way less than that. There usually won't be a lot of concurrent openers of the same struct pid. They can probably often be counted on two hands. I know that systemd does use separate pidfd for the same struct pid for various complex process tracking issues. So I think with that things actually become way simpler. Especially because we don't have to care about lookup. Dentries and inodes continue to be always deleted. The code is entirely optional and fairly small. If it's not selected we fallback to anonymous inodes. Heavily inspired by nsfs which uses a similar stashing mechanism just for namespaces. Link: https://lore.kernel.org/r/20240213-vfs-pidfd_fs-v1-2-f863f58cfce1@kernel.org Signed-off-by: Christian Brauner --- fs/Kconfig | 7 ++ fs/pidfs.c | 156 ++++++++++++++++++++++++++++++++++++++++++++- include/linux/pid.h | 5 +- include/linux/pidfs.h | 8 +++ include/uapi/linux/magic.h | 1 + init/main.c | 2 + kernel/fork.c | 13 +--- kernel/nsproxy.c | 2 +- kernel/pid.c | 11 ++++ 9 files changed, 188 insertions(+), 17 deletions(-) create mode 100644 include/linux/pidfs.h (limited to 'kernel/fork.c') diff --git a/fs/Kconfig b/fs/Kconfig index 89fdbefd1075..f3dbd84a0e40 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -174,6 +174,13 @@ source "fs/proc/Kconfig" source "fs/kernfs/Kconfig" source "fs/sysfs/Kconfig" +config FS_PID + bool "Pseudo filesystem for process file descriptors" + depends on 64BIT + default y + help + Pidfs implements advanced features for process file descriptors. + config TMPFS bool "Tmpfs virtual memory file system support (former shm fs)" depends on SHMEM diff --git a/fs/pidfs.c b/fs/pidfs.c index eccb291862a0..6c3f010074af 100644 --- a/fs/pidfs.c +++ b/fs/pidfs.c @@ -1,9 +1,11 @@ // SPDX-License-Identifier: GPL-2.0 +#include #include #include #include #include #include +#include #include #include #include @@ -14,10 +16,12 @@ static int pidfd_release(struct inode *inode, struct file *file) { +#ifndef CONFIG_FS_PID struct pid *pid = file->private_data; file->private_data = NULL; put_pid(pid); +#endif return 0; } @@ -59,7 +63,7 @@ static int pidfd_release(struct inode *inode, struct file *file) */ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) { - struct pid *pid = f->private_data; + struct pid *pid = pidfd_pid(f); struct pid_namespace *ns; pid_t nr = -1; @@ -93,7 +97,7 @@ static void pidfd_show_fdinfo(struct seq_file *m, struct file *f) */ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) { - struct pid *pid = file->private_data; + struct pid *pid = pidfd_pid(file); bool thread = file->f_flags & PIDFD_THREAD; struct task_struct *task; __poll_t poll_flags = 0; @@ -113,10 +117,156 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts) return poll_flags; } -const struct file_operations pidfd_fops = { +static const struct file_operations pidfs_file_operations = { .release = pidfd_release, .poll = pidfd_poll, #ifdef CONFIG_PROC_FS .show_fdinfo = pidfd_show_fdinfo, #endif }; + +struct pid *pidfd_pid(const struct file *file) +{ + if (file->f_op != &pidfs_file_operations) + return ERR_PTR(-EBADF); +#ifdef CONFIG_FS_PID + return file_inode(file)->i_private; +#else + return file->private_data; +#endif +} + +#ifdef CONFIG_FS_PID +static struct vfsmount *pidfs_mnt __ro_after_init; +static struct super_block *pidfs_sb __ro_after_init; + +/* + * The vfs falls back to simple_setattr() if i_op->setattr() isn't + * implemented. Let's reject it completely until we have a clean + * permission concept for pidfds. + */ +static int pidfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, + struct iattr *attr) +{ + return -EOPNOTSUPP; +} + +static int pidfs_getattr(struct mnt_idmap *idmap, const struct path *path, + struct kstat *stat, u32 request_mask, + unsigned int query_flags) +{ + struct inode *inode = d_inode(path->dentry); + + generic_fillattr(&nop_mnt_idmap, request_mask, inode, stat); + return 0; +} + +static const struct inode_operations pidfs_inode_operations = { + .getattr = pidfs_getattr, + .setattr = pidfs_setattr, +}; + +static void pidfs_evict_inode(struct inode *inode) +{ + struct pid *pid = inode->i_private; + + clear_inode(inode); + put_pid(pid); +} + +static const struct super_operations pidfs_sops = { + .drop_inode = generic_delete_inode, + .evict_inode = pidfs_evict_inode, + .statfs = simple_statfs, +}; + +static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen) +{ + return dynamic_dname(buffer, buflen, "pidfd:[%lu]", + d_inode(dentry)->i_ino); +} + +static const struct dentry_operations pidfs_dentry_operations = { + .d_delete = always_delete_dentry, + .d_dname = pidfs_dname, +}; + +static int pidfs_init_fs_context(struct fs_context *fc) +{ + struct pseudo_fs_context *ctx; + + ctx = init_pseudo(fc, PID_FS_MAGIC); + if (!ctx) + return -ENOMEM; + + ctx->ops = &pidfs_sops; + ctx->dops = &pidfs_dentry_operations; + return 0; +} + +static struct file_system_type pidfs_type = { + .name = "pidfs", + .init_fs_context = pidfs_init_fs_context, + .kill_sb = kill_anon_super, +}; + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) +{ + + struct inode *inode; + struct file *pidfd_file; + + inode = iget_locked(pidfs_sb, pid->ino); + if (!inode) + return ERR_PTR(-ENOMEM); + + if (inode->i_state & I_NEW) { + /* + * Inode numbering for pidfs start at RESERVED_PIDS + 1. + * This avoids collisions with the root inode which is 1 + * for pseudo filesystems. + */ + inode->i_ino = pid->ino; + inode->i_mode = S_IFREG | S_IRUGO; + inode->i_op = &pidfs_inode_operations; + inode->i_fop = &pidfs_file_operations; + inode->i_flags |= S_IMMUTABLE; + inode->i_private = get_pid(pid); + simple_inode_init_ts(inode); + unlock_new_inode(inode); + } + + pidfd_file = alloc_file_pseudo(inode, pidfs_mnt, "", flags, + &pidfs_file_operations); + if (IS_ERR(pidfd_file)) + iput(inode); + + return pidfd_file; +} + +void __init pidfs_init(void) +{ + pidfs_mnt = kern_mount(&pidfs_type); + if (IS_ERR(pidfs_mnt)) + panic("Failed to mount pidfs pseudo filesystem"); + + pidfs_sb = pidfs_mnt->mnt_sb; +} + +#else /* !CONFIG_FS_PID */ + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags) +{ + struct file *pidfd_file; + + pidfd_file = anon_inode_getfile("[pidfd]", &pidfs_file_operations, pid, + flags | O_RDWR); + if (IS_ERR(pidfd_file)) + return pidfd_file; + + get_pid(pid); + return pidfd_file; +} + +void __init pidfs_init(void) { } +#endif diff --git a/include/linux/pid.h b/include/linux/pid.h index 8124d57752b9..956481128e8d 100644 --- a/include/linux/pid.h +++ b/include/linux/pid.h @@ -55,6 +55,9 @@ struct pid refcount_t count; unsigned int level; spinlock_t lock; +#ifdef CONFIG_FS_PID + unsigned long ino; +#endif /* lists of tasks that use this pid */ struct hlist_head tasks[PIDTYPE_MAX]; struct hlist_head inodes; @@ -66,8 +69,6 @@ struct pid extern struct pid init_struct_pid; -extern const struct file_operations pidfd_fops; - struct file; struct pid *pidfd_pid(const struct file *file); diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h new file mode 100644 index 000000000000..75bdf9807802 --- /dev/null +++ b/include/linux/pidfs.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PID_FS_H +#define _LINUX_PID_FS_H + +struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags); +void __init pidfs_init(void); + +#endif /* _LINUX_PID_FS_H */ diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h index 6325d1d0e90f..1b40a968ba91 100644 --- a/include/uapi/linux/magic.h +++ b/include/uapi/linux/magic.h @@ -101,5 +101,6 @@ #define DMA_BUF_MAGIC 0x444d4142 /* "DMAB" */ #define DEVMEM_MAGIC 0x454d444d /* "DMEM" */ #define SECRETMEM_MAGIC 0x5345434d /* "SECM" */ +#define PID_FS_MAGIC 0x50494446 /* "PIDF" */ #endif /* __LINUX_MAGIC_H__ */ diff --git a/init/main.c b/init/main.c index e24b0780fdff..2fbf6a3114d5 100644 --- a/init/main.c +++ b/init/main.c @@ -99,6 +99,7 @@ #include #include #include +#include #include #include @@ -1059,6 +1060,7 @@ void start_kernel(void) seq_file_init(); proc_root_init(); nsfs_init(); + pidfs_init(); cpuset_init(); cgroup_init(); taskstats_init_early(); diff --git a/kernel/fork.c b/kernel/fork.c index 662a61f340ce..2f839c290dcf 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -102,6 +102,7 @@ #include #include #include +#include #include #include @@ -1985,14 +1986,6 @@ static inline void rcu_copy_process(struct task_struct *p) #endif /* #ifdef CONFIG_TASKS_TRACE_RCU */ } -struct pid *pidfd_pid(const struct file *file) -{ - if (file->f_op == &pidfd_fops) - return file->private_data; - - return ERR_PTR(-EBADF); -} - /** * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd * @pid: the struct pid for which to create a pidfd @@ -2030,13 +2023,11 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re if (pidfd < 0) return pidfd; - pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid, - flags | O_RDWR); + pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR); if (IS_ERR(pidfd_file)) { put_unused_fd(pidfd); return PTR_ERR(pidfd_file); } - get_pid(pid); /* held by pidfd_file now */ /* * anon_inode_getfile() ignores everything outside of the * O_ACCMODE | O_NONBLOCK mask, set PIDFD_THREAD manually. diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 15781acaac1c..6ec3deec68c2 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -573,7 +573,7 @@ SYSCALL_DEFINE2(setns, int, fd, int, flags) if (proc_ns_file(f.file)) err = validate_ns(&nsset, ns); else - err = validate_nsset(&nsset, f.file->private_data); + err = validate_nsset(&nsset, pidfd_pid(f.file)); if (!err) { commit_nsset(&nsset); perf_event_namespaces(current); diff --git a/kernel/pid.c b/kernel/pid.c index c1d940fbd314..581cc34341fd 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -42,6 +42,7 @@ #include #include #include +#include #include #include @@ -65,6 +66,13 @@ int pid_max = PID_MAX_DEFAULT; int pid_max_min = RESERVED_PIDS + 1; int pid_max_max = PID_MAX_LIMIT; +#ifdef CONFIG_FS_PID +/* + * Pseudo filesystems start inode numbering after one. We use Reserved + * PIDs as a natural offset. + */ +static u64 pidfs_ino = RESERVED_PIDS; +#endif /* * PID-map pages start out as NULL, they get allocated upon @@ -272,6 +280,9 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid, spin_lock_irq(&pidmap_lock); if (!(ns->pid_allocated & PIDNS_ADDING)) goto out_unlock; +#ifdef CONFIG_FS_PID + pid->ino = ++pidfs_ino; +#endif for ( ; upid >= pid->numbers; --upid) { /* Make the PID visible to find_pid_ns. */ idr_replace(&upid->ns->idr, pid, upid->nr); -- cgit v1.2.3