summaryrefslogtreecommitdiff
path: root/kernel/exit.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/exit.c')
-rw-r--r--kernel/exit.c117
1 files changed, 58 insertions, 59 deletions
diff --git a/kernel/exit.c b/kernel/exit.c
index c2e6c7b7779f..343eb97543d5 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -68,6 +68,7 @@
#include <linux/rethook.h>
#include <linux/sysfs.h>
#include <linux/user_events.h>
+#include <linux/unwind_deferred.h>
#include <linux/uaccess.h>
#include <linux/pidfs.h>
@@ -133,8 +134,13 @@ struct release_task_post {
static void __unhash_process(struct release_task_post *post, struct task_struct *p,
bool group_dead)
{
+ struct pid *pid = task_pid(p);
+
nr_threads--;
+
detach_pid(post->pids, p, PIDTYPE_PID);
+ wake_up_all(&pid->wait_pidfd);
+
if (group_dead) {
detach_pid(post->pids, p, PIDTYPE_TGID);
detach_pid(post->pids, p, PIDTYPE_PGID);
@@ -253,7 +259,8 @@ repeat:
pidfs_exit(p);
cgroup_release(p);
- thread_pid = get_pid(p->thread_pid);
+ /* Retrieve @thread_pid before __unhash_process() may set it to NULL. */
+ thread_pid = task_pid(p);
write_lock_irq(&tasklist_lock);
ptrace_release_task(p);
@@ -268,6 +275,9 @@ repeat:
leader = p->group_leader;
if (leader != p && thread_group_empty(leader)
&& leader->exit_state == EXIT_ZOMBIE) {
+ /* for pidfs_exit() and do_notify_parent() */
+ if (leader->signal->flags & SIGNAL_GROUP_EXIT)
+ leader->exit_code = leader->signal->group_exit_code;
/*
* If we were the last child thread and the leader has
* exited already, and the leader's parent ignores SIGCHLD,
@@ -279,8 +289,8 @@ repeat:
}
write_unlock_irq(&tasklist_lock);
+ /* @thread_pid can't go away until free_pids() below */
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);
@@ -412,44 +422,30 @@ kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent)
}
}
-static void coredump_task_exit(struct task_struct *tsk)
+static void coredump_task_exit(struct task_struct *tsk,
+ struct core_state *core_state)
{
- struct core_state *core_state;
+ struct core_thread self;
+ self.task = tsk;
+ if (self.task->flags & PF_SIGNALED)
+ self.next = xchg(&core_state->dumper.next, &self);
+ else
+ self.task = NULL;
/*
- * Serialize with any possible pending coredump.
- * We must hold siglock around checking core_state
- * and setting PF_POSTCOREDUMP. The core-inducing thread
- * will increment ->nr_threads for each thread in the
- * group without PF_POSTCOREDUMP set.
+ * Implies mb(), the result of xchg() must be visible
+ * to core_state->dumper.
*/
- spin_lock_irq(&tsk->sighand->siglock);
- tsk->flags |= PF_POSTCOREDUMP;
- core_state = tsk->signal->core_state;
- spin_unlock_irq(&tsk->sighand->siglock);
- if (core_state) {
- struct core_thread self;
-
- self.task = current;
- if (self.task->flags & PF_SIGNALED)
- self.next = xchg(&core_state->dumper.next, &self);
- else
- self.task = NULL;
- /*
- * Implies mb(), the result of xchg() must be visible
- * to core_state->dumper.
- */
- if (atomic_dec_and_test(&core_state->nr_threads))
- complete(&core_state->startup);
+ if (atomic_dec_and_test(&core_state->nr_threads))
+ complete(&core_state->startup);
- for (;;) {
- set_current_state(TASK_IDLE|TASK_FREEZABLE);
- if (!self.task) /* see coredump_finish() */
- break;
- schedule();
- }
- __set_current_state(TASK_RUNNING);
+ for (;;) {
+ set_current_state(TASK_IDLE|TASK_FREEZABLE);
+ if (!self.task) /* see coredump_finish() */
+ break;
+ schedule();
}
+ __set_current_state(TASK_RUNNING);
}
#ifdef CONFIG_MEMCG
@@ -697,12 +693,7 @@ static void reparent_leader(struct task_struct *father, struct task_struct *p,
}
/*
- * This does two things:
- *
- * A. Make init inherit all the child processes
- * B. Check to see if any process groups have become orphaned
- * as a result of our exiting, and if they have any stopped
- * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
+ * Make init inherit all the child processes
*/
static void forget_original_parent(struct task_struct *father,
struct list_head *dead)
@@ -756,12 +747,6 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
kill_orphaned_pgrp(tsk->group_leader, NULL);
tsk->exit_state = EXIT_ZOMBIE;
- /*
- * Ignore thread-group leaders that exited before all
- * subthreads did.
- */
- if (!delay_group_leader(tsk))
- do_notify_pidfd(tsk);
if (unlikely(tsk->ptrace)) {
int sig = thread_group_leader(tsk) &&
@@ -774,6 +759,8 @@ static void exit_notify(struct task_struct *tsk, int group_dead)
do_notify_parent(tsk, tsk->exit_signal);
} else {
autoreap = true;
+ /* untraced sub-thread */
+ do_notify_pidfd(tsk);
}
if (autoreap) {
@@ -877,6 +864,7 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
{
struct sighand_struct *sighand = tsk->sighand;
struct signal_struct *signal = tsk->signal;
+ struct core_state *core_state;
spin_lock_irq(&sighand->siglock);
signal->quick_threads--;
@@ -886,7 +874,19 @@ static void synchronize_group_exit(struct task_struct *tsk, long code)
signal->group_exit_code = code;
signal->group_stop_count = 0;
}
+ /*
+ * Serialize with any possible pending coredump.
+ * We must hold siglock around checking core_state
+ * and setting PF_POSTCOREDUMP. The core-inducing thread
+ * will increment ->nr_threads for each thread in the
+ * group without PF_POSTCOREDUMP set.
+ */
+ tsk->flags |= PF_POSTCOREDUMP;
+ core_state = signal->core_state;
spin_unlock_irq(&sighand->siglock);
+
+ if (unlikely(core_state))
+ coredump_task_exit(tsk, core_state);
}
void __noreturn do_exit(long code)
@@ -895,15 +895,12 @@ void __noreturn do_exit(long code)
int group_dead;
WARN_ON(irqs_disabled());
-
- synchronize_group_exit(tsk, code);
-
WARN_ON(tsk->plug);
kcov_task_exit(tsk);
kmsan_task_exit(tsk);
- coredump_task_exit(tsk);
+ synchronize_group_exit(tsk, code);
ptrace_event(PTRACE_EVENT_EXIT, code);
user_events_exit(tsk);
@@ -937,12 +934,22 @@ void __noreturn do_exit(long code)
tsk->exit_code = code;
taskstats_exit(tsk, group_dead);
+ unwind_deferred_task_exit(tsk);
+ trace_sched_process_exit(tsk, group_dead);
+
+ /*
+ * Since sampling can touch ->mm, make sure to stop everything before we
+ * tear it down.
+ *
+ * Also flushes inherited counters to the parent - before the parent
+ * gets woken up by child-exit notifications.
+ */
+ perf_event_exit_task(tsk);
exit_mm();
if (group_dead)
acct_process();
- trace_sched_process_exit(tsk);
exit_sem(tsk);
exit_shm(tsk);
@@ -954,14 +961,6 @@ void __noreturn do_exit(long code)
exit_task_work(tsk);
exit_thread(tsk);
- /*
- * Flush inherited counters to the parent - before the parent
- * gets woken up by child-exit notifications.
- *
- * because of cgroup mode, must be called before cgroup_exit()
- */
- perf_event_exit_task(tsk);
-
sched_autogroup_exit_task(tsk);
cgroup_exit(tsk);
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-05 08:24:40 +0000