diff options
Diffstat (limited to 'kernel/exit.c')
| -rw-r--r-- | kernel/exit.c | 66 |
1 files changed, 41 insertions, 25 deletions
diff --git a/kernel/exit.c b/kernel/exit.c index 1dcddfe537ee..c2e6c7b7779f 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -69,6 +69,7 @@ #include <linux/sysfs.h> #include <linux/user_events.h> #include <linux/uaccess.h> +#include <linux/pidfs.h> #include <uapi/linux/wait.h> @@ -85,7 +86,7 @@ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL -static struct ctl_table kern_exit_table[] = { +static const struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, @@ -122,14 +123,22 @@ static __init int kernel_exit_sysfs_init(void) late_initcall(kernel_exit_sysfs_init); #endif -static void __unhash_process(struct task_struct *p, bool group_dead) +/* + * For things release_task() would like to do *after* tasklist_lock is released. + */ +struct release_task_post { + struct pid *pids[PIDTYPE_MAX]; +}; + +static void __unhash_process(struct release_task_post *post, struct task_struct *p, + bool group_dead) { nr_threads--; - detach_pid(p, PIDTYPE_PID); + detach_pid(post->pids, p, PIDTYPE_PID); if (group_dead) { - detach_pid(p, PIDTYPE_TGID); - detach_pid(p, PIDTYPE_PGID); - detach_pid(p, PIDTYPE_SID); + detach_pid(post->pids, p, PIDTYPE_TGID); + detach_pid(post->pids, p, PIDTYPE_PGID); + detach_pid(post->pids, p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); @@ -141,7 +150,7 @@ static void __unhash_process(struct task_struct *p, bool group_dead) /* * This function expects the tasklist_lock write-locked. */ -static void __exit_signal(struct task_struct *tsk) +static void __exit_signal(struct release_task_post *post, struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); @@ -174,9 +183,6 @@ static void __exit_signal(struct task_struct *tsk) sig->curr_target = next_thread(tsk); } - add_device_randomness((const void*) &tsk->se.sum_exec_runtime, - sizeof(unsigned long long)); - /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, @@ -197,23 +203,15 @@ static void __exit_signal(struct task_struct *tsk) task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; - __unhash_process(tsk, group_dead); + __unhash_process(post, tsk, group_dead); write_sequnlock(&sig->stats_lock); - /* - * Do this under ->siglock, we can race with another thread - * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. - */ - flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); - clear_tsk_thread_flag(tsk, TIF_SIGPENDING); - if (group_dead) { - flush_sigqueue(&sig->shared_pending); + if (group_dead) tty_kref_put(tty); - } } static void delayed_put_task_struct(struct rcu_head *rhp) @@ -239,22 +237,27 @@ void __weak release_thread(struct task_struct *dead_task) void release_task(struct task_struct *p) { + struct release_task_post post; struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: + memset(&post, 0, sizeof(post)); + /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); rcu_read_unlock(); + pidfs_exit(p); cgroup_release(p); + thread_pid = get_pid(p->thread_pid); + write_lock_irq(&tasklist_lock); ptrace_release_task(p); - thread_pid = get_pid(p->thread_pid); - __exit_signal(p); + __exit_signal(&post, p); /* * If we are the last non-leader member of the thread @@ -278,7 +281,20 @@ repeat: write_unlock_irq(&tasklist_lock); proc_flush_pid(thread_pid); put_pid(thread_pid); + add_device_randomness(&p->se.sum_exec_runtime, + sizeof(p->se.sum_exec_runtime)); + free_pids(post.pids); release_thread(p); + /* + * This task was already removed from the process/thread/pid lists + * and lock_task_sighand(p) can't succeed. Nobody else can touch + * ->pending or, if group dead, signal->shared_pending. We can call + * flush_sigqueue() lockless. + */ + flush_sigqueue(&p->pending); + if (thread_group_leader(p)) + flush_sigqueue(&p->signal->shared_pending); + put_task_struct_rcu_user(p); p = leader; @@ -741,10 +757,10 @@ static void exit_notify(struct task_struct *tsk, int group_dead) tsk->exit_state = EXIT_ZOMBIE; /* - * sub-thread or delay_group_leader(), wake up the - * PIDFD_THREAD waiters. + * Ignore thread-group leaders that exited before all + * subthreads did. */ - if (!thread_group_empty(tsk)) + if (!delay_group_leader(tsk)) do_notify_pidfd(tsk); if (unlikely(tsk->ptrace)) { |