#include <linux/init_task.h>
#include <linux/perf_event.h>
#include <trace/events/sched.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/oom.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/pgtable.h>
#include <asm/mmu_context.h>
-#include "cred-internals.h"
static void exit_mm(struct task_struct * tsk);
-static void __unhash_process(struct task_struct *p)
+static void __unhash_process(struct task_struct *p, bool group_dead)
{
nr_threads--;
detach_pid(p, PIDTYPE_PID);
- if (thread_group_leader(p)) {
+ if (group_dead) {
detach_pid(p, PIDTYPE_PGID);
detach_pid(p, PIDTYPE_SID);
list_del_rcu(&p->tasks);
- __get_cpu_var(process_counts)--;
+ list_del_init(&p->sibling);
+ __this_cpu_dec(process_counts);
}
list_del_rcu(&p->thread_group);
- list_del_init(&p->sibling);
}
/*
static void __exit_signal(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
+ bool group_dead = thread_group_leader(tsk);
struct sighand_struct *sighand;
+ struct tty_struct *uninitialized_var(tty);
- BUG_ON(!sig);
- BUG_ON(!atomic_read(&sig->count));
-
- sighand = rcu_dereference(tsk->sighand);
+ sighand = rcu_dereference_check(tsk->sighand,
+ rcu_read_lock_held() ||
+ lockdep_tasklist_lock_is_held());
spin_lock(&sighand->siglock);
posix_cpu_timers_exit(tsk);
- if (atomic_dec_and_test(&sig->count))
+ if (group_dead) {
posix_cpu_timers_exit_group(tsk);
- else {
+ tty = sig->tty;
+ sig->tty = NULL;
+ } else {
+ /*
+ * This can only happen if the caller is de_thread().
+ * FIXME: this is the temporary hack, we should teach
+ * posix-cpu-timers to handle this case correctly.
+ */
+ if (unlikely(has_group_leader_pid(tsk)))
+ posix_cpu_timers_exit_group(tsk);
+
/*
* If there is any task waiting for the group exit
* then notify it:
*/
- if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count)
+ if (sig->notify_count > 0 && !--sig->notify_count)
wake_up_process(sig->group_exit_task);
if (tsk == sig->curr_target)
* We won't ever get here for the group leader, since it
* will have been the last reference on the signal_struct.
*/
- sig->utime = cputime_add(sig->utime, task_utime(tsk));
- sig->stime = cputime_add(sig->stime, task_stime(tsk));
- sig->gtime = cputime_add(sig->gtime, task_gtime(tsk));
+ sig->utime = cputime_add(sig->utime, tsk->utime);
+ sig->stime = cputime_add(sig->stime, tsk->stime);
+ sig->gtime = cputime_add(sig->gtime, tsk->gtime);
sig->min_flt += tsk->min_flt;
sig->maj_flt += tsk->maj_flt;
sig->nvcsw += tsk->nvcsw;
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 = NULL; /* Marker for below. */
}
- __unhash_process(tsk);
+ sig->nr_threads--;
+ __unhash_process(tsk, group_dead);
/*
* Do this under ->siglock, we can race with another thread
* doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals.
*/
flush_sigqueue(&tsk->pending);
-
- tsk->signal = NULL;
tsk->sighand = NULL;
spin_unlock(&sighand->siglock);
__cleanup_sighand(sighand);
clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
- if (sig) {
+ if (group_dead) {
flush_sigqueue(&sig->shared_pending);
- taskstats_tgid_free(sig);
- /*
- * Make sure ->signal can't go away under rq->lock,
- * see account_group_exec_runtime().
- */
- task_rq_unlock_wait(tsk);
- __cleanup_signal(sig);
+ tty_kref_put(tty);
}
}
{
struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
-#ifdef CONFIG_PERF_EVENTS
- WARN_ON_ONCE(tsk->perf_event_ctxp);
-#endif
+ perf_event_delayed_put(tsk);
trace_sched_process_free(tsk);
put_task_struct(tsk);
}
repeat:
tracehook_prepare_release_task(p);
/* don't need to get the RCU readlock here - the process is dead and
- * can't be modifying its own credentials */
+ * can't be modifying its own credentials. But shut RCU-lockdep up */
+ rcu_read_lock();
atomic_dec(&__task_cred(p)->user->processes);
+ rcu_read_unlock();
proc_flush_task(p);
{
struct task_struct *curr = current->group_leader;
- if (task_session(curr) != pid) {
+ if (task_session(curr) != pid)
change_pid(curr, PIDTYPE_SID, pid);
- proc_sid_connector(curr);
- }
if (task_pgrp(curr) != pid)
change_pid(curr, PIDTYPE_PGID, pid);
/*
* It is safe to dereference the fd table without RCU or
* ->file_lock because this is the last reference to the
- * files structure.
+ * files structure. But use RCU to shut RCU-lockdep up.
*/
+ rcu_read_lock();
fdt = files_fdtable(files);
+ rcu_read_unlock();
for (;;) {
unsigned long set;
i = j * __NFDBITS;
* at the end of the RCU grace period. Otherwise,
* you can free files immediately.
*/
+ rcu_read_lock();
fdt = files_fdtable(files);
if (fdt != &files->fdtab)
kmem_cache_free(files_cachep, files);
free_fdtable(fdt);
+ rcu_read_unlock();
}
}
enter_lazy_tlb(mm, current);
/* We don't want this task to be frozen prematurely */
clear_freeze_flag(tsk);
+ if (tsk->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
+ atomic_dec(&mm->oom_disable_count);
task_unlock(tsk);
mm_update_next_owner(mm);
mmput(mm);
* space.
*/
static struct task_struct *find_new_reaper(struct task_struct *father)
+ __releases(&tasklist_lock)
+ __acquires(&tasklist_lock)
{
struct pid_namespace *pid_ns = task_active_pid_ns(father);
struct task_struct *thread;
/*
* Any that need to be release_task'd are put on the @dead list.
*/
-static void reparent_thread(struct task_struct *father, struct task_struct *p,
+static void reparent_leader(struct task_struct *father, struct task_struct *p,
struct list_head *dead)
{
- if (p->pdeath_signal)
- group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
-
list_move_tail(&p->sibling, &p->real_parent->children);
if (task_detached(p))
struct task_struct *p, *n, *reaper;
LIST_HEAD(dead_children);
- exit_ptrace(father);
-
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);
list_for_each_entry_safe(p, n, &father->children, sibling) {
- p->real_parent = reaper;
- if (p->parent == father) {
- BUG_ON(task_ptrace(p));
- p->parent = p->real_parent;
- }
- reparent_thread(father, p, &dead_children);
+ struct task_struct *t = p;
+ do {
+ t->real_parent = reaper;
+ if (t->parent == father) {
+ BUG_ON(task_ptrace(t));
+ 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);
tsk->exit_state = signal == DEATH_REAP ? EXIT_DEAD : EXIT_ZOMBIE;
- /* mt-exec, de_thread() is waiting for us */
- if (thread_group_leader(tsk) &&
- tsk->signal->group_exit_task &&
- tsk->signal->notify_count < 0)
+ /* 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);
tracehook_report_death(tsk, signal, cookie, group_dead);
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
+ /*
+ * If do_exit is called because this processes oopsed, it's possible
+ * that get_fs() was left as KERNEL_DS, so reset it to USER_DS before
+ * continuing. Amongst other possible reasons, this is to prevent
+ * mm_release()->clear_child_tid() from writing to a user-controlled
+ * kernel address.
+ */
+ set_fs(USER_DS);
+
tracehook_report_exit(&code);
validate_creds_for_do_exit(tsk);
* an exiting task cleaning up the robust pi futexes.
*/
smp_mb();
- spin_unlock_wait(&tsk->pi_lock);
+ raw_spin_unlock_wait(&tsk->pi_lock);
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
preempt_count());
acct_update_integrals(tsk);
-
+ /* sync mm's RSS info before statistics gathering */
+ if (tsk->mm)
+ sync_mm_rss(tsk, tsk->mm);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
hrtimer_cancel(&tsk->signal->real_timer);
exit_fs(tsk);
check_stack_usage();
exit_thread();
+
+ /*
+ * 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);
+
cgroup_exit(tsk, 1);
- if (group_dead && tsk->signal->leader)
+ if (group_dead)
disassociate_ctty(1);
module_put(task_thread_info(tsk)->exec_domain->module);
proc_exit_connector(tsk);
/*
- * Flush inherited counters to the parent - before the parent
- * gets woken up by child-exit notifications.
+ * FIXME: do that only when needed, using sched_exit tracepoint
*/
- perf_event_exit_task(tsk);
+ ptrace_put_breakpoints(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
+ task_lock(tsk);
mpol_put(tsk->mempolicy);
tsk->mempolicy = NULL;
+ task_unlock(tsk);
#endif
#ifdef CONFIG_FUTEX
- if (unlikely(!list_empty(&tsk->pi_state_list)))
- exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
#endif
tsk->flags |= PF_EXITPIDONE;
if (tsk->io_context)
- exit_io_context();
+ exit_io_context(tsk);
if (tsk->splice_pipe)
__free_pipe_info(tsk->splice_pipe);
if (unlikely(wo->wo_flags & WNOWAIT)) {
int exit_code = p->exit_code;
- int why, status;
+ int why;
get_task_struct(p);
read_unlock(&tasklist_lock);
struct signal_struct *psig;
struct signal_struct *sig;
unsigned long maxrss;
+ cputime_t tgutime, tgstime;
/*
* The resource counters for the group leader are in its
* 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.
+ *
+ * We use thread_group_times() to get times for the thread
+ * group, which consolidates times for all threads in the
+ * group including the group leader.
*/
+ thread_group_times(p, &tgutime, &tgstime);
spin_lock_irq(&p->real_parent->sighand->siglock);
psig = p->real_parent->signal;
sig = p->signal;
psig->cutime =
cputime_add(psig->cutime,
- cputime_add(p->utime,
- cputime_add(sig->utime,
- sig->cutime)));
+ cputime_add(tgutime,
+ sig->cutime));
psig->cstime =
cputime_add(psig->cstime,
- cputime_add(p->stime,
- cputime_add(sig->stime,
- sig->cstime)));
+ cputime_add(tgstime,
+ sig->cstime));
psig->cgtime =
cputime_add(psig->cgtime,
cputime_add(p->gtime,
if (!unlikely(wo->wo_flags & WNOWAIT))
*p_code = 0;
- /* don't need the RCU readlock here as we're holding a spinlock */
- uid = __task_cred(p)->uid;
+ uid = task_uid(p);
unlock_sig:
spin_unlock_irq(&p->sighand->siglock);
if (!exit_code)
}
if (!unlikely(wo->wo_flags & WNOWAIT))
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
- uid = __task_cred(p)->uid;
+ uid = task_uid(p);
spin_unlock_irq(&p->sighand->siglock);
pid = task_pid_vnr(p);
struct task_struct *p;
list_for_each_entry(p, &tsk->children, sibling) {
- /*
- * Do not consider detached threads.
- */
- if (!task_detached(p)) {
- int ret = wait_consider_task(wo, 0, p);
- if (ret)
- return ret;
- }
+ int ret = wait_consider_task(wo, 0, p);
+ if (ret)
+ return ret;
}
return 0;