#include <asm/pgtable.h>
#include <asm/mmu_context.h>
-static void exit_mm(struct task_struct * tsk);
+static void exit_mm(struct task_struct *tsk);
static void __unhash_process(struct task_struct *p, bool group_dead)
{
if (tsk == sig->curr_target)
sig->curr_target = next_thread(tsk);
- /*
- * Accumulate here the counters for all threads but the
- * group leader as they die, so they can be added into
- * the process-wide totals when those are taken.
- * The group leader stays around as a zombie as long
- * as there are other threads. When it gets reaped,
- * the exit.c code will add its counts into these totals.
- * We won't ever get here for the group leader, since it
- * will have been the last reference on the signal_struct.
- */
- task_cputime(tsk, &utime, &stime);
- sig->utime += utime;
- sig->stime += stime;
- sig->gtime += task_gtime(tsk);
- sig->min_flt += tsk->min_flt;
- sig->maj_flt += tsk->maj_flt;
- sig->nvcsw += tsk->nvcsw;
- sig->nivcsw += tsk->nivcsw;
- sig->inblock += task_io_get_inblock(tsk);
- sig->oublock += task_io_get_oublock(tsk);
- task_io_accounting_add(&sig->ioac, &tsk->ioac);
- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
}
+ /*
+ * 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,
+ * but we want to avoid the race with thread_group_cputime() which can
+ * see the empty ->thread_head list.
+ */
+ task_cputime(tsk, &utime, &stime);
+ write_seqlock(&sig->stats_lock);
+ sig->utime += utime;
+ sig->stime += stime;
+ sig->gtime += task_gtime(tsk);
+ sig->min_flt += tsk->min_flt;
+ sig->maj_flt += tsk->maj_flt;
+ sig->nvcsw += tsk->nvcsw;
+ sig->nivcsw += tsk->nivcsw;
+ sig->inblock += task_io_get_inblock(tsk);
+ sig->oublock += task_io_get_oublock(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);
+ write_sequnlock(&sig->stats_lock);
/*
* Do this under ->siglock, we can race with another thread
spin_unlock(&sighand->siglock);
__cleanup_sighand(sighand);
- clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
+ clear_tsk_thread_flag(tsk, TIF_SIGPENDING);
if (group_dead) {
flush_sigqueue(&sig->shared_pending);
tty_kref_put(tty);
}
-void release_task(struct task_struct * p)
+void release_task(struct task_struct *p)
{
struct task_struct *leader;
int zap_leader;
*/
zap_leader = 0;
leader = p->group_leader;
- if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
+ if (leader != p && thread_group_empty(leader)
+ && leader->exit_state == EXIT_ZOMBIE) {
/*
* If we were the last child thread and the leader has
* exited already, and the leader's parent ignores SIGCHLD,
goto repeat;
}
-/*
- * This checks not only the pgrp, but falls back on the pid if no
- * satisfactory pgrp is found. I dunno - gdb doesn't work correctly
- * without this...
- *
- * The caller must hold rcu lock or the tasklist lock.
- */
-struct pid *session_of_pgrp(struct pid *pgrp)
-{
- struct task_struct *p;
- struct pid *sid = NULL;
-
- p = pid_task(pgrp, PIDTYPE_PGID);
- if (p == NULL)
- p = pid_task(pgrp, PIDTYPE_PID);
- if (p != NULL)
- sid = task_session(p);
-
- return sid;
-}
-
/*
* Determine if a process group is "orphaned", according to the POSIX
* definition in 2.2.2.52. Orphaned process groups are not to be affected
*
* "I ask you, have you ever known what it is to be an orphan?"
*/
-static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
+static int will_become_orphaned_pgrp(struct pid *pgrp,
+ struct task_struct *ignored_task)
{
struct task_struct *p;
struct task_struct *ignored_task = tsk;
if (!parent)
- /* exit: our father is in a different pgrp than
- * we are and we were the only connection outside.
- */
+ /* exit: our father is in a different pgrp than
+ * we are and we were the only connection outside.
+ */
parent = tsk->real_parent;
else
/* reparent: our child is in a different pgrp than
}
}
-void __set_special_pids(struct pid *pid)
-{
- struct task_struct *curr = current->group_leader;
-
- if (task_session(curr) != pid)
- change_pid(curr, PIDTYPE_SID, pid);
-
- if (task_pgrp(curr) != pid)
- change_pid(curr, PIDTYPE_PGID, pid);
-}
-
-/*
- * Let kernel threads use this to say that they allow a certain signal.
- * Must not be used if kthread was cloned with CLONE_SIGHAND.
- */
-int allow_signal(int sig)
-{
- if (!valid_signal(sig) || sig < 1)
- return -EINVAL;
-
- spin_lock_irq(¤t->sighand->siglock);
- /* This is only needed for daemonize()'ed kthreads */
- sigdelset(¤t->blocked, sig);
- /*
- * Kernel threads handle their own signals. Let the signal code
- * know it'll be handled, so that they don't get converted to
- * SIGKILL or just silently dropped.
- */
- current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
- recalc_sigpending();
- spin_unlock_irq(¤t->sighand->siglock);
- return 0;
-}
-
-EXPORT_SYMBOL(allow_signal);
-
-int disallow_signal(int sig)
-{
- if (!valid_signal(sig) || sig < 1)
- return -EINVAL;
-
- spin_lock_irq(¤t->sighand->siglock);
- current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
- recalc_sigpending();
- spin_unlock_irq(¤t->sighand->siglock);
- return 0;
-}
-
-EXPORT_SYMBOL(disallow_signal);
-
-#ifdef CONFIG_MM_OWNER
+#ifdef CONFIG_MEMCG
/*
* A task is exiting. If it owned this mm, find a new owner for the mm.
*/
}
/*
- * Search through everything else. We should not get
- * here often
+ * Search through everything else, we should not get here often.
*/
- do_each_thread(g, c) {
- if (c->mm == mm)
- goto assign_new_owner;
- } while_each_thread(g, c);
-
+ for_each_process(g) {
+ if (g->flags & PF_KTHREAD)
+ continue;
+ for_each_thread(g, c) {
+ if (c->mm == mm)
+ goto assign_new_owner;
+ if (c->mm)
+ break;
+ }
+ }
read_unlock(&tasklist_lock);
/*
* We found no owner yet mm_users > 1: this implies that we are
task_unlock(c);
put_task_struct(c);
}
-#endif /* CONFIG_MM_OWNER */
+#endif /* CONFIG_MEMCG */
/*
* Turn us into a lazy TLB process if we
* aren't already..
*/
-static void exit_mm(struct task_struct * tsk)
+static void exit_mm(struct task_struct *tsk)
{
struct mm_struct *mm = tsk->mm;
struct core_state *core_state;
core_state = mm->core_state;
if (core_state) {
struct core_thread self;
+
up_read(&mm->mmap_sem);
self.task = tsk;
task_unlock(tsk);
mm_update_next_owner(mm);
mmput(mm);
+ if (test_thread_flag(TIF_MEMDIE))
+ exit_oom_victim();
+}
+
+static struct task_struct *find_alive_thread(struct task_struct *p)
+{
+ struct task_struct *t;
+
+ for_each_thread(p, t) {
+ if (!(t->flags & PF_EXITING))
+ return t;
+ }
+ return NULL;
+}
+
+static struct task_struct *find_child_reaper(struct task_struct *father)
+ __releases(&tasklist_lock)
+ __acquires(&tasklist_lock)
+{
+ struct pid_namespace *pid_ns = task_active_pid_ns(father);
+ struct task_struct *reaper = pid_ns->child_reaper;
+
+ if (likely(reaper != father))
+ return reaper;
+
+ reaper = find_alive_thread(father);
+ if (reaper) {
+ pid_ns->child_reaper = reaper;
+ return reaper;
+ }
+
+ write_unlock_irq(&tasklist_lock);
+ if (unlikely(pid_ns == &init_pid_ns)) {
+ panic("Attempted to kill init! exitcode=0x%08x\n",
+ father->signal->group_exit_code ?: father->exit_code);
+ }
+ zap_pid_ns_processes(pid_ns);
+ write_lock_irq(&tasklist_lock);
+
+ return father;
}
/*
* child_subreaper for its children (like a service manager)
* 3. give it to the init process (PID 1) in our pid namespace
*/
-static struct task_struct *find_new_reaper(struct task_struct *father)
- __releases(&tasklist_lock)
- __acquires(&tasklist_lock)
+static struct task_struct *find_new_reaper(struct task_struct *father,
+ struct task_struct *child_reaper)
{
- struct pid_namespace *pid_ns = task_active_pid_ns(father);
- struct task_struct *thread;
+ struct task_struct *thread, *reaper;
- thread = father;
- while_each_thread(father, thread) {
- if (thread->flags & PF_EXITING)
- continue;
- if (unlikely(pid_ns->child_reaper == father))
- pid_ns->child_reaper = thread;
+ thread = find_alive_thread(father);
+ if (thread)
return thread;
- }
-
- if (unlikely(pid_ns->child_reaper == father)) {
- write_unlock_irq(&tasklist_lock);
- if (unlikely(pid_ns == &init_pid_ns)) {
- panic("Attempted to kill init! exitcode=0x%08x\n",
- father->signal->group_exit_code ?:
- father->exit_code);
- }
-
- zap_pid_ns_processes(pid_ns);
- write_lock_irq(&tasklist_lock);
- } else if (father->signal->has_child_subreaper) {
- struct task_struct *reaper;
+ if (father->signal->has_child_subreaper) {
/*
- * Find the first ancestor marked as child_subreaper.
- * Note that the code below checks same_thread_group(reaper,
- * pid_ns->child_reaper). This is what we need to DTRT in a
- * PID namespace. However we still need the check above, see
- * http://marc.info/?l=linux-kernel&m=131385460420380
+ * Find the first ->is_child_subreaper ancestor in our pid_ns.
+ * We start from father to ensure we can not look into another
+ * namespace, this is safe because all its threads are dead.
*/
- for (reaper = father->real_parent;
- reaper != &init_task;
+ for (reaper = father;
+ !same_thread_group(reaper, child_reaper);
reaper = reaper->real_parent) {
- if (same_thread_group(reaper, pid_ns->child_reaper))
+ /* call_usermodehelper() descendants need this check */
+ if (reaper == &init_task)
break;
if (!reaper->signal->is_child_subreaper)
continue;
- thread = reaper;
- do {
- if (!(thread->flags & PF_EXITING))
- return reaper;
- } while_each_thread(reaper, thread);
+ thread = find_alive_thread(reaper);
+ if (thread)
+ return thread;
}
}
- return pid_ns->child_reaper;
+ return child_reaper;
}
/*
static void reparent_leader(struct task_struct *father, struct task_struct *p,
struct list_head *dead)
{
- list_move_tail(&p->sibling, &p->real_parent->children);
- /*
- * If this is a threaded reparent there is no need to
- * notify anyone anything has happened.
- */
- if (same_thread_group(p->real_parent, father))
+ if (unlikely(p->exit_state == EXIT_DEAD))
return;
- /*
- * We don't want people slaying init.
- *
- * Note: we do this even if it is EXIT_DEAD, wait_task_zombie()
- * can change ->exit_state to EXIT_ZOMBIE. If this is the final
- * state, do_notify_parent() was already called and ->exit_signal
- * doesn't matter.
- */
+ /* We don't want people slaying init. */
p->exit_signal = SIGCHLD;
- if (p->exit_state == EXIT_DEAD)
- return;
-
/* If it has exited notify the new parent about this child's death. */
if (!p->ptrace &&
p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
if (do_notify_parent(p, p->exit_signal)) {
p->exit_state = EXIT_DEAD;
- list_move_tail(&p->sibling, dead);
+ list_add(&p->ptrace_entry, dead);
}
}
kill_orphaned_pgrp(p, father);
}
-static void forget_original_parent(struct task_struct *father)
+/*
+ * 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)
+ */
+static void forget_original_parent(struct task_struct *father,
+ struct list_head *dead)
{
- struct task_struct *p, *n, *reaper;
- LIST_HEAD(dead_children);
+ struct task_struct *p, *t, *reaper;
- write_lock_irq(&tasklist_lock);
- /*
- * Note that exit_ptrace() and find_new_reaper() might
- * drop tasklist_lock and reacquire it.
- */
- exit_ptrace(father);
- reaper = find_new_reaper(father);
+ if (unlikely(!list_empty(&father->ptraced)))
+ exit_ptrace(father, dead);
- list_for_each_entry_safe(p, n, &father->children, sibling) {
- struct task_struct *t = p;
- do {
+ /* Can drop and reacquire tasklist_lock */
+ reaper = find_child_reaper(father);
+ if (list_empty(&father->children))
+ return;
+
+ reaper = find_new_reaper(father, reaper);
+ list_for_each_entry(p, &father->children, sibling) {
+ for_each_thread(p, t) {
t->real_parent = reaper;
- if (t->parent == father) {
- BUG_ON(t->ptrace);
+ BUG_ON((!t->ptrace) != (t->parent == father));
+ if (likely(!t->ptrace))
t->parent = t->real_parent;
- }
if (t->pdeath_signal)
group_send_sig_info(t->pdeath_signal,
SEND_SIG_NOINFO, t);
- } while_each_thread(p, t);
- reparent_leader(father, p, &dead_children);
- }
- write_unlock_irq(&tasklist_lock);
-
- BUG_ON(!list_empty(&father->children));
-
- list_for_each_entry_safe(p, n, &dead_children, sibling) {
- list_del_init(&p->sibling);
- release_task(p);
+ }
+ /*
+ * If this is a threaded reparent there is no need to
+ * notify anyone anything has happened.
+ */
+ if (!same_thread_group(reaper, father))
+ reparent_leader(father, p, dead);
}
+ list_splice_tail_init(&father->children, &reaper->children);
}
/*
static void exit_notify(struct task_struct *tsk, int group_dead)
{
bool autoreap;
-
- /*
- * 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)
- */
- forget_original_parent(tsk);
+ struct task_struct *p, *n;
+ LIST_HEAD(dead);
write_lock_irq(&tasklist_lock);
+ forget_original_parent(tsk, &dead);
+
if (group_dead)
kill_orphaned_pgrp(tsk->group_leader, NULL);
}
tsk->exit_state = autoreap ? EXIT_DEAD : EXIT_ZOMBIE;
+ if (tsk->exit_state == EXIT_DEAD)
+ list_add(&tsk->ptrace_entry, &dead);
/* mt-exec, de_thread() is waiting for group leader */
if (unlikely(tsk->signal->notify_count < 0))
wake_up_process(tsk->signal->group_exit_task);
write_unlock_irq(&tasklist_lock);
- /* If the process is dead, release it - nobody will wait for it */
- if (autoreap)
- release_task(tsk);
+ list_for_each_entry_safe(p, n, &dead, ptrace_entry) {
+ list_del_init(&p->ptrace_entry);
+ release_task(p);
+ }
}
#ifdef CONFIG_DEBUG_STACK_USAGE
spin_lock(&low_water_lock);
if (free < lowest_to_date) {
- printk(KERN_WARNING "%s (%d) used greatest stack depth: "
- "%lu bytes left\n",
- current->comm, task_pid_nr(current), free);
+ pr_warn("%s (%d) used greatest stack depth: %lu bytes left\n",
+ current->comm, task_pid_nr(current), free);
lowest_to_date = free;
}
spin_unlock(&low_water_lock);
{
struct task_struct *tsk = current;
int group_dead;
+ TASKS_RCU(int tasks_rcu_i);
profile_task_exit(tsk);
* leave this task alone and wait for reboot.
*/
if (unlikely(tsk->flags & PF_EXITING)) {
- printk(KERN_ALERT
- "Fixing recursive fault but reboot is needed!\n");
+ pr_alert("Fixing recursive fault but reboot is needed!\n");
/*
* We can do this unlocked here. The futex code uses
* this flag just to verify whether the pi state
smp_mb();
raw_spin_unlock_wait(&tsk->pi_lock);
- if (unlikely(in_atomic()))
- printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
- current->comm, task_pid_nr(current),
- preempt_count());
+ if (unlikely(in_atomic())) {
+ pr_info("note: %s[%d] exited with preempt_count %d\n",
+ current->comm, task_pid_nr(current),
+ preempt_count());
+ preempt_count_set(PREEMPT_ENABLED);
+ }
- acct_update_integrals(tsk);
/* sync mm's RSS info before statistics gathering */
if (tsk->mm)
sync_mm_rss(tsk->mm);
+ acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
disassociate_ctty(1);
exit_task_namespaces(tsk);
exit_task_work(tsk);
- check_stack_usage();
exit_thread();
/*
*/
perf_event_exit_task(tsk);
- cgroup_exit(tsk, 1);
+ cgroup_exit(tsk);
- module_put(task_thread_info(tsk)->exec_domain->module);
-
- proc_exit_connector(tsk);
/*
* FIXME: do that only when needed, using sched_exit tracepoint
*/
- ptrace_put_breakpoints(tsk);
+ flush_ptrace_hw_breakpoint(tsk);
+ TASKS_RCU(preempt_disable());
+ TASKS_RCU(tasks_rcu_i = __srcu_read_lock(&tasks_rcu_exit_srcu));
+ TASKS_RCU(preempt_enable());
exit_notify(tsk, group_dead);
+ proc_exit_connector(tsk);
#ifdef CONFIG_NUMA
task_lock(tsk);
mpol_put(tsk->mempolicy);
validate_creds_for_do_exit(tsk);
+ check_stack_usage();
preempt_disable();
if (tsk->nr_dirtied)
__this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied);
exit_rcu();
+ TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
/*
* The setting of TASK_RUNNING by try_to_wake_up() may be delayed
for (;;)
cpu_relax(); /* For when BUG is null */
}
-
EXPORT_SYMBOL_GPL(do_exit);
void complete_and_exit(struct completion *comp, long code)
do_exit(code);
}
-
EXPORT_SYMBOL(complete_and_exit);
SYSCALL_DEFINE1(exit, int, error_code)
exit_code = sig->group_exit_code;
else if (!thread_group_empty(current)) {
struct sighand_struct *const sighand = current->sighand;
+
spin_lock_irq(&sighand->siglock);
if (signal_group_exit(sig))
/* Another thread got here before we took the lock. */
*/
static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
{
- unsigned long state;
- int retval, status, traced;
+ int state, retval, status;
pid_t pid = task_pid_vnr(p);
uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p));
struct siginfo __user *infop;
get_task_struct(p);
read_unlock(&tasklist_lock);
+ sched_annotate_sleep();
+
if ((exit_code & 0x7f) == 0) {
why = CLD_EXITED;
status = exit_code >> 8;
}
return wait_noreap_copyout(wo, p, pid, uid, why, status);
}
-
/*
- * Try to move the task's state to DEAD
- * only one thread is allowed to do this:
+ * Move the task's state to DEAD/TRACE, only one thread can do this.
*/
- state = xchg(&p->exit_state, EXIT_DEAD);
- if (state != EXIT_ZOMBIE) {
- BUG_ON(state != EXIT_DEAD);
+ state = (ptrace_reparented(p) && thread_group_leader(p)) ?
+ EXIT_TRACE : EXIT_DEAD;
+ if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE)
return 0;
- }
+ /*
+ * We own this thread, nobody else can reap it.
+ */
+ read_unlock(&tasklist_lock);
+ sched_annotate_sleep();
- traced = ptrace_reparented(p);
/*
- * It can be ptraced but not reparented, check
- * thread_group_leader() to filter out sub-threads.
+ * Check thread_group_leader() to exclude the traced sub-threads.
*/
- if (likely(!traced) && thread_group_leader(p)) {
- struct signal_struct *psig;
- struct signal_struct *sig;
+ if (state == EXIT_DEAD && thread_group_leader(p)) {
+ struct signal_struct *sig = p->signal;
+ struct signal_struct *psig = current->signal;
unsigned long maxrss;
cputime_t tgutime, tgstime;
* accumulate in the parent's signal_struct c* fields.
*
* We don't bother to take a lock here to protect these
- * p->signal fields, because they are only touched by
- * __exit_signal, which runs with tasklist_lock
- * write-locked anyway, and so is excluded here. We do
- * need to protect the access to parent->signal fields,
- * as other threads in the parent group can be right
- * here reaping other children at the same time.
+ * p->signal fields because the whole thread group is dead
+ * and nobody can change them.
+ *
+ * psig->stats_lock also protects us from our sub-theads
+ * which can reap other children at the same time. Until
+ * we change k_getrusage()-like users to rely on this lock
+ * we have to take ->siglock as well.
*
- * We use thread_group_cputime_adjusted() to get times for the thread
- * group, which consolidates times for all threads in the
- * group including the group leader.
+ * We use thread_group_cputime_adjusted() to get times for
+ * the thread group, which consolidates times for all threads
+ * in the group including the group leader.
*/
thread_group_cputime_adjusted(p, &tgutime, &tgstime);
- spin_lock_irq(&p->real_parent->sighand->siglock);
- psig = p->real_parent->signal;
- sig = p->signal;
+ spin_lock_irq(¤t->sighand->siglock);
+ write_seqlock(&psig->stats_lock);
psig->cutime += tgutime + sig->cutime;
psig->cstime += tgstime + sig->cstime;
psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime;
psig->cmaxrss = maxrss;
task_io_accounting_add(&psig->ioac, &p->ioac);
task_io_accounting_add(&psig->ioac, &sig->ioac);
- spin_unlock_irq(&p->real_parent->sighand->siglock);
+ write_sequnlock(&psig->stats_lock);
+ spin_unlock_irq(¤t->sighand->siglock);
}
- /*
- * Now we are sure this task is interesting, and no other
- * thread can reap it because we set its state to EXIT_DEAD.
- */
- read_unlock(&tasklist_lock);
-
retval = wo->wo_rusage
? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
if (!retval)
retval = pid;
- if (traced) {
+ if (state == EXIT_TRACE) {
write_lock_irq(&tasklist_lock);
/* We dropped tasklist, ptracer could die and untrace */
ptrace_unlink(p);
- /*
- * If this is not a sub-thread, notify the parent.
- * If parent wants a zombie, don't release it now.
- */
- if (thread_group_leader(p) &&
- !do_notify_parent(p, p->exit_signal)) {
- p->exit_state = EXIT_ZOMBIE;
- p = NULL;
- }
+
+ /* If parent wants a zombie, don't release it now */
+ state = EXIT_ZOMBIE;
+ if (do_notify_parent(p, p->exit_signal))
+ state = EXIT_DEAD;
+ p->exit_state = state;
write_unlock_irq(&tasklist_lock);
}
- if (p != NULL)
+ if (state == EXIT_DEAD)
release_task(p);
return retval;
pid = task_pid_vnr(p);
why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
read_unlock(&tasklist_lock);
+ sched_annotate_sleep();
if (unlikely(wo->wo_flags & WNOWAIT))
return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
pid = task_pid_vnr(p);
get_task_struct(p);
read_unlock(&tasklist_lock);
+ sched_annotate_sleep();
if (!wo->wo_info) {
retval = wo->wo_rusage
static int wait_consider_task(struct wait_opts *wo, int ptrace,
struct task_struct *p)
{
- int ret = eligible_child(wo, p);
+ /*
+ * We can race with wait_task_zombie() from another thread.
+ * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition
+ * can't confuse the checks below.
+ */
+ int exit_state = ACCESS_ONCE(p->exit_state);
+ int ret;
+
+ if (unlikely(exit_state == EXIT_DEAD))
+ return 0;
+
+ ret = eligible_child(wo, p);
if (!ret)
return ret;
return 0;
}
- /* dead body doesn't have much to contribute */
- if (unlikely(p->exit_state == EXIT_DEAD)) {
+ if (unlikely(exit_state == EXIT_TRACE)) {
/*
- * But do not ignore this task until the tracer does
- * wait_task_zombie()->do_notify_parent().
+ * ptrace == 0 means we are the natural parent. In this case
+ * we should clear notask_error, debugger will notify us.
*/
- if (likely(!ptrace) && unlikely(ptrace_reparented(p)))
+ if (likely(!ptrace))
wo->notask_error = 0;
return 0;
}
- /* slay zombie? */
- if (p->exit_state == EXIT_ZOMBIE) {
+ if (likely(!ptrace) && unlikely(p->ptrace)) {
/*
- * A zombie ptracee is only visible to its ptracer.
- * Notification and reaping will be cascaded to the real
- * parent when the ptracer detaches.
+ * If it is traced by its real parent's group, just pretend
+ * the caller is ptrace_do_wait() and reap this child if it
+ * is zombie.
+ *
+ * This also hides group stop state from real parent; otherwise
+ * a single stop can be reported twice as group and ptrace stop.
+ * If a ptracer wants to distinguish these two events for its
+ * own children it should create a separate process which takes
+ * the role of real parent.
*/
- if (likely(!ptrace) && unlikely(p->ptrace)) {
- /* it will become visible, clear notask_error */
- wo->notask_error = 0;
- return 0;
- }
+ if (!ptrace_reparented(p))
+ ptrace = 1;
+ }
+ /* slay zombie? */
+ if (exit_state == EXIT_ZOMBIE) {
/* we don't reap group leaders with subthreads */
- if (!delay_group_leader(p))
- return wait_task_zombie(wo, p);
+ if (!delay_group_leader(p)) {
+ /*
+ * A zombie ptracee is only visible to its ptracer.
+ * Notification and reaping will be cascaded to the
+ * real parent when the ptracer detaches.
+ */
+ if (unlikely(ptrace) || likely(!p->ptrace))
+ return wait_task_zombie(wo, p);
+ }
/*
* Allow access to stopped/continued state via zombie by
if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED)))
wo->notask_error = 0;
} else {
- /*
- * If @p is ptraced by a task in its real parent's group,
- * hide group stop/continued state when looking at @p as
- * the real parent; otherwise, a single stop can be
- * reported twice as group and ptrace stops.
- *
- * If a ptracer wants to distinguish the two events for its
- * own children, it should create a separate process which
- * takes the role of real parent.
- */
- if (likely(!ptrace) && p->ptrace && !ptrace_reparented(p))
- return 0;
-
/*
* @p is alive and it's gonna stop, continue or exit, so
* there always is something to wait for.
list_for_each_entry(p, &tsk->children, sibling) {
int ret = wait_consider_task(wo, 0, p);
+
if (ret)
return ret;
}
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
int ret = wait_consider_task(wo, 1, p);
+
if (ret)
return ret;
}
add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait);
repeat:
/*
- * If there is nothing that can match our critiera just get out.
+ * If there is nothing that can match our criteria, just get out.
* We will clear ->notask_error to zero if we see any child that
* might later match our criteria, even if we are not able to reap
* it yet.