#include <linux/completion.h>
#include <linux/personality.h>
#include <linux/tty.h>
-#include <linux/mnt_namespace.h>
#include <linux/iocontext.h>
#include <linux/key.h>
#include <linux/security.h>
#include <linux/cn_proc.h>
#include <linux/mutex.h>
#include <linux/futex.h>
-#include <linux/compat.h>
#include <linux/pipe_fs_i.h>
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
#include <linux/blkdev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/tracehook.h>
+#include <linux/fs_struct.h>
+#include <linux/init_task.h>
+#include <linux/perf_counter.h>
+#include <trace/events/sched.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 inline int task_detached(struct task_struct *p)
-{
- return p->exit_signal == -1;
-}
-
static void __unhash_process(struct task_struct *p)
{
nr_threads--;
* 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, tsk->utime);
- sig->stime = cputime_add(sig->stime, tsk->stime);
- sig->gtime = cputime_add(sig->gtime, tsk->gtime);
+ 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->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);
-#ifdef CONFIG_TASK_XACCT
- sig->rchar += tsk->rchar;
- sig->wchar += tsk->wchar;
- sig->syscr += tsk->syscr;
- sig->syscw += tsk->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
- sig->ioac.read_bytes += tsk->ioac.read_bytes;
- sig->ioac.write_bytes += tsk->ioac.write_bytes;
- sig->ioac.cancelled_write_bytes +=
- tsk->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
+ task_io_accounting_add(&sig->ioac, &tsk->ioac);
sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
sig = NULL; /* Marker for below. */
}
if (sig) {
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);
}
}
static void delayed_put_task_struct(struct rcu_head *rhp)
{
- put_task_struct(container_of(rhp, struct task_struct, rcu));
+ struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
+
+#ifdef CONFIG_PERF_COUNTERS
+ WARN_ON_ONCE(tsk->perf_counter_ctxp);
+#endif
+ trace_sched_process_free(tsk);
+ put_task_struct(tsk);
}
int zap_leader;
repeat:
tracehook_prepare_release_task(p);
- atomic_dec(&p->user->processes);
+ /* don't need to get the RCU readlock here - the process is dead and
+ * can't be modifying its own credentials */
+ atomic_dec(&__task_cred(p)->user->processes);
+
proc_flush_task(p);
+
write_lock_irq(&tasklist_lock);
tracehook_finish_release_task(p);
__exit_signal(p);
/* cpus_allowed? */
/* rt_priority? */
/* signals? */
- security_task_reparent_to_init(current);
memcpy(current->signal->rlim, init_task.signal->rlim,
sizeof(current->signal->rlim));
- atomic_inc(&(INIT_USER->__count));
+
+ atomic_inc(&init_cred.usage);
+ commit_creds(&init_cred);
write_unlock_irq(&tasklist_lock);
- switch_uid(INIT_USER);
}
void __set_special_pids(struct pid *pid)
{
struct task_struct *curr = current->group_leader;
- pid_t nr = pid_nr(pid);
- if (task_session(curr) != pid) {
+ if (task_session(curr) != pid)
change_pid(curr, PIDTYPE_SID, pid);
- set_task_session(curr, nr);
- }
- if (task_pgrp(curr) != pid) {
+
+ if (task_pgrp(curr) != pid)
change_pid(curr, PIDTYPE_PGID, pid);
- set_task_pgrp(curr, nr);
- }
}
static void set_special_pids(struct pid *pid)
}
/*
- * Let kernel threads use this to say that they
- * allow a certain signal (since daemonize() will
- * have disabled all of them by default).
+ * 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)
{
return -EINVAL;
spin_lock_irq(¤t->sighand->siglock);
+ /* This is only needed for daemonize()'ed kthreads */
sigdelset(¤t->blocked, sig);
- if (!current->mm) {
- /* 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;
- }
+ /*
+ * 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;
void daemonize(const char *name, ...)
{
va_list args;
- struct fs_struct *fs;
sigset_t blocked;
va_start(args, name);
/* Become as one with the init task */
- exit_fs(current); /* current->fs->count--; */
- fs = init_task.fs;
- current->fs = fs;
- atomic_inc(&fs->count);
-
+ daemonize_fs_struct();
exit_files(current);
current->files = init_task.files;
atomic_inc(¤t->files->count);
}
}
-void put_fs_struct(struct fs_struct *fs)
-{
- /* No need to hold fs->lock if we are killing it */
- if (atomic_dec_and_test(&fs->count)) {
- path_put(&fs->root);
- path_put(&fs->pwd);
- kmem_cache_free(fs_cachep, fs);
- }
-}
-
-void exit_fs(struct task_struct *tsk)
-{
- struct fs_struct * fs = tsk->fs;
-
- if (fs) {
- task_lock(tsk);
- tsk->fs = NULL;
- task_unlock(tsk);
- put_fs_struct(fs);
- }
-}
-
-EXPORT_SYMBOL_GPL(exit_fs);
-
#ifdef CONFIG_MM_OWNER
/*
* Task p is exiting and it owned mm, lets find a new owner for it
* If there are other users of the mm and the owner (us) is exiting
* we need to find a new owner to take on the responsibility.
*/
- if (!mm)
- return 0;
if (atomic_read(&mm->mm_users) <= 1)
return 0;
if (mm->owner != p)
/*
* Search in the siblings
*/
- list_for_each_entry(c, &p->parent->children, sibling) {
+ list_for_each_entry(c, &p->real_parent->children, sibling) {
if (c->mm == mm)
goto assign_new_owner;
}
} while_each_thread(g, c);
read_unlock(&tasklist_lock);
+ /*
+ * We found no owner yet mm_users > 1: this implies that we are
+ * most likely racing with swapoff (try_to_unuse()) or /proc or
+ * ptrace or page migration (get_task_mm()). Mark owner as NULL.
+ */
+ mm->owner = NULL;
return;
assign_new_owner:
put_task_struct(c);
goto retry;
}
- cgroup_mm_owner_callbacks(mm->owner, c);
mm->owner = c;
task_unlock(c);
put_task_struct(c);
}
/*
- * Return nonzero if @parent's children should reap themselves.
- *
- * Called with write_lock_irq(&tasklist_lock) held.
- */
-static int ignoring_children(struct task_struct *parent)
-{
- int ret;
- struct sighand_struct *psig = parent->sighand;
- unsigned long flags;
- spin_lock_irqsave(&psig->siglock, flags);
- ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
- (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
- spin_unlock_irqrestore(&psig->siglock, flags);
- return ret;
-}
-
-/*
- * Detach all tasks we were using ptrace on.
- * Any that need to be release_task'd are put on the @dead list.
- *
- * Called with write_lock(&tasklist_lock) held.
+ * When we die, we re-parent all our children.
+ * Try to give them to another thread in our thread
+ * group, and if no such member exists, give it to
+ * the child reaper process (ie "init") in our pid
+ * space.
*/
-static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
+static struct task_struct *find_new_reaper(struct task_struct *father)
{
- struct task_struct *p, *n;
- int ign = -1;
-
- list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
- __ptrace_unlink(p);
+ struct pid_namespace *pid_ns = task_active_pid_ns(father);
+ struct task_struct *thread;
- if (p->exit_state != EXIT_ZOMBIE)
+ 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;
+ 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!");
+ zap_pid_ns_processes(pid_ns);
+ write_lock_irq(&tasklist_lock);
/*
- * If it's a zombie, our attachedness prevented normal
- * parent notification or self-reaping. Do notification
- * now if it would have happened earlier. If it should
- * reap itself, add it to the @dead list. We can't call
- * release_task() here because we already hold tasklist_lock.
- *
- * If it's our own child, there is no notification to do.
- * But if our normal children self-reap, then this child
- * was prevented by ptrace and we must reap it now.
+ * We can not clear ->child_reaper or leave it alone.
+ * There may by stealth EXIT_DEAD tasks on ->children,
+ * forget_original_parent() must move them somewhere.
*/
- if (!task_detached(p) && thread_group_empty(p)) {
- if (!same_thread_group(p->real_parent, parent))
- do_notify_parent(p, p->exit_signal);
- else {
- if (ign < 0)
- ign = ignoring_children(parent);
- if (ign)
- p->exit_signal = -1;
- }
- }
-
- if (task_detached(p)) {
- /*
- * Mark it as in the process of being reaped.
- */
- p->exit_state = EXIT_DEAD;
- list_add(&p->ptrace_entry, dead);
- }
+ pid_ns->child_reaper = init_pid_ns.child_reaper;
}
+
+ return pid_ns->child_reaper;
}
/*
- * Finish up exit-time ptrace cleanup.
- *
- * Called without locks.
+* Any that need to be release_task'd are put on the @dead list.
*/
-static void ptrace_exit_finish(struct task_struct *parent,
- struct list_head *dead)
-{
- struct task_struct *p, *n;
-
- BUG_ON(!list_empty(&parent->ptraced));
-
- list_for_each_entry_safe(p, n, dead, ptrace_entry) {
- list_del_init(&p->ptrace_entry);
- release_task(p);
- }
-}
-
-static void reparent_thread(struct task_struct *p, struct task_struct *father)
+static void reparent_thread(struct task_struct *father, struct task_struct *p,
+ struct list_head *dead)
{
if (p->pdeath_signal)
- /* We already hold the tasklist_lock here. */
group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
list_move_tail(&p->sibling, &p->real_parent->children);
- /* If this is a threaded reparent there is no need to
+ if (task_detached(p))
+ return;
+ /*
+ * If this is a threaded reparent there is no need to
* notify anyone anything has happened.
*/
if (same_thread_group(p->real_parent, father))
return;
/* We don't want people slaying init. */
- if (!task_detached(p))
- p->exit_signal = SIGCHLD;
+ p->exit_signal = SIGCHLD;
- /* If we'd notified the old parent about this child's death,
- * also notify the new parent.
- */
- if (!ptrace_reparented(p) &&
- p->exit_state == EXIT_ZOMBIE &&
- !task_detached(p) && thread_group_empty(p))
+ /* If it has exited notify the new parent about this child's death. */
+ if (!task_ptrace(p) &&
+ p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
do_notify_parent(p, p->exit_signal);
+ if (task_detached(p)) {
+ p->exit_state = EXIT_DEAD;
+ list_move_tail(&p->sibling, dead);
+ }
+ }
kill_orphaned_pgrp(p, father);
}
-/*
- * When we die, we re-parent all our children.
- * Try to give them to another thread in our thread
- * group, and if no such member exists, give it to
- * the child reaper process (ie "init") in our pid
- * space.
- */
static void forget_original_parent(struct task_struct *father)
{
- struct task_struct *p, *n, *reaper = father;
- LIST_HEAD(ptrace_dead);
+ struct task_struct *p, *n, *reaper;
+ LIST_HEAD(dead_children);
- write_lock_irq(&tasklist_lock);
+ exit_ptrace(father);
- /*
- * First clean up ptrace if we were using it.
- */
- ptrace_exit(father, &ptrace_dead);
-
- do {
- reaper = next_thread(reaper);
- if (reaper == father) {
- reaper = task_child_reaper(father);
- break;
- }
- } while (reaper->flags & PF_EXITING);
+ write_lock_irq(&tasklist_lock);
+ 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(p->ptrace);
+ BUG_ON(task_ptrace(p));
p->parent = p->real_parent;
}
- reparent_thread(p, father);
+ reparent_thread(father, p, &dead_children);
}
-
write_unlock_irq(&tasklist_lock);
+
BUG_ON(!list_empty(&father->children));
- ptrace_exit_finish(father, &ptrace_dead);
+ list_for_each_entry_safe(p, n, &dead_children, sibling) {
+ list_del_init(&p->sibling);
+ release_task(p);
+ }
}
/*
*/
if (tsk->exit_signal != SIGCHLD && !task_detached(tsk) &&
(tsk->parent_exec_id != tsk->real_parent->self_exec_id ||
- tsk->self_exec_id != tsk->parent_exec_id) &&
- !capable(CAP_KILL))
+ tsk->self_exec_id != tsk->parent_exec_id))
tsk->exit_signal = SIGCHLD;
signal = tracehook_notify_death(tsk, &cookie, group_dead);
- if (signal > 0)
+ if (signal >= 0)
signal = do_notify_parent(tsk, signal);
- tsk->exit_state = signal < 0 ? EXIT_DEAD : EXIT_ZOMBIE;
+ 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->notify_count < 0 &&
- tsk->signal->group_exit_task)
+ tsk->signal->group_exit_task &&
+ 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 the process is dead, release it - nobody will wait for it */
- if (signal < 0)
+ if (signal == DEATH_REAP)
release_task(tsk);
}
{
static DEFINE_SPINLOCK(low_water_lock);
static int lowest_to_date = THREAD_SIZE;
- unsigned long *n = end_of_stack(current);
unsigned long free;
- while (*n == 0)
- n++;
- free = (unsigned long)n - (unsigned long)end_of_stack(current);
+ free = stack_not_used(current);
if (free >= lowest_to_date)
return;
static inline void check_stack_usage(void) {}
#endif
-static inline void exit_child_reaper(struct task_struct *tsk)
-{
- if (likely(tsk->group_leader != task_child_reaper(tsk)))
- return;
-
- if (tsk->nsproxy->pid_ns == &init_pid_ns)
- panic("Attempted to kill init!");
-
- /*
- * @tsk is the last thread in the 'cgroup-init' and is exiting.
- * Terminate all remaining processes in the namespace and reap them
- * before exiting @tsk.
- *
- * Note that @tsk (last thread of cgroup-init) may not necessarily
- * be the child-reaper (i.e main thread of cgroup-init) of the
- * namespace i.e the child_reaper may have already exited.
- *
- * Even after a child_reaper exits, we let it inherit orphaned children,
- * because, pid_ns->child_reaper remains valid as long as there is
- * at least one living sub-thread in the cgroup init.
-
- * This living sub-thread of the cgroup-init will be notified when
- * a child inherited by the 'child-reaper' exits (do_notify_parent()
- * uses __group_send_sig_info()). Further, when reaping child processes,
- * do_wait() iterates over children of all living sub threads.
-
- * i.e even though 'child_reaper' thread is listed as the parent of the
- * orphaned children, any living sub-thread in the cgroup-init can
- * perform the role of the child_reaper.
- */
- zap_pid_ns_processes(tsk->nsproxy->pid_ns);
-}
-
NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
* task into the wait for ever nirwana as well.
*/
tsk->flags |= PF_EXITPIDONE;
- if (tsk->io_context)
- exit_io_context();
set_current_state(TASK_UNINTERRUPTIBLE);
schedule();
}
+ exit_irq_thread();
+
exit_signals(tsk); /* sets PF_EXITING */
/*
* tsk->flags are checked in the futex code to protect against
preempt_count());
acct_update_integrals(tsk);
- if (tsk->mm) {
- update_hiwater_rss(tsk->mm);
- update_hiwater_vm(tsk->mm);
- }
+
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
- exit_child_reaper(tsk);
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
}
acct_collect(code, group_dead);
-#ifdef CONFIG_FUTEX
- if (unlikely(tsk->robust_list))
- exit_robust_list(tsk);
-#ifdef CONFIG_COMPAT
- if (unlikely(tsk->compat_robust_list))
- compat_exit_robust_list(tsk);
-#endif
-#endif
if (group_dead)
tty_audit_exit();
if (unlikely(tsk->audit_context))
if (group_dead)
acct_process();
+ trace_sched_process_exit(tsk);
+
exit_sem(tsk);
exit_files(tsk);
exit_fs(tsk);
check_stack_usage();
exit_thread();
cgroup_exit(tsk, 1);
- exit_keys(tsk);
if (group_dead && tsk->signal->leader)
disassociate_ctty(1);
module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
+
+ /*
+ * Flush inherited counters to the parent - before the parent
+ * gets woken up by child-exit notifications.
+ */
+ perf_counter_exit_task(tsk);
+
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
mpol_put(tsk->mempolicy);
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
- /*
- * This must happen late, after the PID is not
- * hashed anymore:
- */
if (unlikely(!list_empty(&tsk->pi_state_list)))
exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
preempt_disable();
/* causes final put_task_struct in finish_task_switch(). */
tsk->state = TASK_DEAD;
-
schedule();
BUG();
/* Avoid "noreturn function does return". */
EXPORT_SYMBOL(complete_and_exit);
-asmlinkage long sys_exit(int error_code)
+SYSCALL_DEFINE1(exit, int, error_code)
{
do_exit((error_code&0xff)<<8);
}
* wait4()-ing process will get the correct exit code - even if this
* thread is not the thread group leader.
*/
-asmlinkage void sys_exit_group(int error_code)
+SYSCALL_DEFINE1(exit_group, int, error_code)
{
do_group_exit((error_code & 0xff) << 8);
+ /* NOTREACHED */
+ return 0;
}
+struct wait_opts {
+ enum pid_type wo_type;
+ int wo_flags;
+ struct pid *wo_pid;
+
+ struct siginfo __user *wo_info;
+ int __user *wo_stat;
+ struct rusage __user *wo_rusage;
+
+ int notask_error;
+};
+
static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
{
struct pid *pid = NULL;
return pid;
}
-static int eligible_child(enum pid_type type, struct pid *pid, int options,
- struct task_struct *p)
+static int eligible_child(struct wait_opts *wo, struct task_struct *p)
{
int err;
- if (type < PIDTYPE_MAX) {
- if (task_pid_type(p, type) != pid)
+ if (wo->wo_type < PIDTYPE_MAX) {
+ if (task_pid_type(p, wo->wo_type) != wo->wo_pid)
return 0;
}
* set; otherwise, wait for non-clone children *only*. (Note:
* A "clone" child here is one that reports to its parent
* using a signal other than SIGCHLD.) */
- if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
- && !(options & __WALL))
+ if (((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE))
+ && !(wo->wo_flags & __WALL))
return 0;
err = security_task_wait(p);
return 1;
}
-static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
- int why, int status,
- struct siginfo __user *infop,
- struct rusage __user *rusagep)
+static int wait_noreap_copyout(struct wait_opts *wo, struct task_struct *p,
+ pid_t pid, uid_t uid, int why, int status)
{
- int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;
+ struct siginfo __user *infop;
+ int retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
put_task_struct(p);
+ infop = wo->wo_info;
if (!retval)
retval = put_user(SIGCHLD, &infop->si_signo);
if (!retval)
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
-static int wait_task_zombie(struct task_struct *p, int options,
- struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p)
{
unsigned long state;
int retval, status, traced;
pid_t pid = task_pid_vnr(p);
+ uid_t uid = __task_cred(p)->uid;
+ struct siginfo __user *infop;
- if (!likely(options & WEXITED))
+ if (!likely(wo->wo_flags & WEXITED))
return 0;
- if (unlikely(options & WNOWAIT)) {
- uid_t uid = p->uid;
+ if (unlikely(wo->wo_flags & WNOWAIT)) {
int exit_code = p->exit_code;
int why, status;
why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
status = exit_code & 0x7f;
}
- return wait_noreap_copyout(p, pid, uid, why,
- status, infop, ru);
+ return wait_noreap_copyout(wo, p, pid, uid, why, status);
}
/*
}
traced = ptrace_reparented(p);
-
- if (likely(!traced)) {
+ /*
+ * It can be ptraced but not reparented, check
+ * !task_detached() to filter out sub-threads.
+ */
+ if (likely(!traced) && likely(!task_detached(p))) {
struct signal_struct *psig;
struct signal_struct *sig;
* 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 p->parent->signal fields,
+ * 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.
*/
- spin_lock_irq(&p->parent->sighand->siglock);
- psig = p->parent->signal;
+ spin_lock_irq(&p->real_parent->sighand->siglock);
+ psig = p->real_parent->signal;
sig = p->signal;
psig->cutime =
cputime_add(psig->cutime,
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
-#ifdef CONFIG_TASK_XACCT
- psig->rchar += p->rchar + sig->rchar;
- psig->wchar += p->wchar + sig->wchar;
- psig->syscr += p->syscr + sig->syscr;
- psig->syscw += p->syscw + sig->syscw;
-#endif /* CONFIG_TASK_XACCT */
-#ifdef CONFIG_TASK_IO_ACCOUNTING
- psig->ioac.read_bytes +=
- p->ioac.read_bytes + sig->ioac.read_bytes;
- psig->ioac.write_bytes +=
- p->ioac.write_bytes + sig->ioac.write_bytes;
- psig->ioac.cancelled_write_bytes +=
- p->ioac.cancelled_write_bytes +
- sig->ioac.cancelled_write_bytes;
-#endif /* CONFIG_TASK_IO_ACCOUNTING */
- spin_unlock_irq(&p->parent->sighand->siglock);
+ task_io_accounting_add(&psig->ioac, &p->ioac);
+ task_io_accounting_add(&psig->ioac, &sig->ioac);
+ spin_unlock_irq(&p->real_parent->sighand->siglock);
}
/*
*/
read_unlock(&tasklist_lock);
- retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+ retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
status = (p->signal->flags & SIGNAL_GROUP_EXIT)
? p->signal->group_exit_code : p->exit_code;
- if (!retval && stat_addr)
- retval = put_user(status, stat_addr);
+ if (!retval && wo->wo_stat)
+ retval = put_user(status, wo->wo_stat);
+
+ infop = wo->wo_info;
if (!retval && infop)
retval = put_user(SIGCHLD, &infop->si_signo);
if (!retval && infop)
if (!retval && infop)
retval = put_user(pid, &infop->si_pid);
if (!retval && infop)
- retval = put_user(p->uid, &infop->si_uid);
+ retval = put_user(uid, &infop->si_uid);
if (!retval)
retval = pid;
return retval;
}
+static int *task_stopped_code(struct task_struct *p, bool ptrace)
+{
+ if (ptrace) {
+ if (task_is_stopped_or_traced(p))
+ return &p->exit_code;
+ } else {
+ if (p->signal->flags & SIGNAL_STOP_STOPPED)
+ return &p->signal->group_exit_code;
+ }
+ return NULL;
+}
+
/*
* Handle sys_wait4 work for one task in state TASK_STOPPED. We hold
* read_lock(&tasklist_lock) on entry. If we return zero, we still hold
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
-static int wait_task_stopped(int ptrace, struct task_struct *p,
- int options, struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_stopped(struct wait_opts *wo,
+ int ptrace, struct task_struct *p)
{
- int retval, exit_code, why;
+ struct siginfo __user *infop;
+ int retval, exit_code, *p_code, why;
uid_t uid = 0; /* unneeded, required by compiler */
pid_t pid;
- if (!(options & WUNTRACED))
+ /*
+ * Traditionally we see ptrace'd stopped tasks regardless of options.
+ */
+ if (!ptrace && !(wo->wo_flags & WUNTRACED))
return 0;
exit_code = 0;
spin_lock_irq(&p->sighand->siglock);
- if (unlikely(!task_is_stopped_or_traced(p)))
+ p_code = task_stopped_code(p, ptrace);
+ if (unlikely(!p_code))
goto unlock_sig;
- if (!ptrace && p->signal->group_stop_count > 0)
- /*
- * A group stop is in progress and this is the group leader.
- * We won't report until all threads have stopped.
- */
- goto unlock_sig;
-
- exit_code = p->exit_code;
+ exit_code = *p_code;
if (!exit_code)
goto unlock_sig;
- if (!unlikely(options & WNOWAIT))
- p->exit_code = 0;
+ if (!unlikely(wo->wo_flags & WNOWAIT))
+ *p_code = 0;
- uid = p->uid;
+ /* don't need the RCU readlock here as we're holding a spinlock */
+ uid = __task_cred(p)->uid;
unlock_sig:
spin_unlock_irq(&p->sighand->siglock);
if (!exit_code)
why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
read_unlock(&tasklist_lock);
- if (unlikely(options & WNOWAIT))
- return wait_noreap_copyout(p, pid, uid,
- why, exit_code,
- infop, ru);
+ if (unlikely(wo->wo_flags & WNOWAIT))
+ return wait_noreap_copyout(wo, p, pid, uid, why, exit_code);
+
+ retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
+ if (!retval && wo->wo_stat)
+ retval = put_user((exit_code << 8) | 0x7f, wo->wo_stat);
- retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
- if (!retval && stat_addr)
- retval = put_user((exit_code << 8) | 0x7f, stat_addr);
+ infop = wo->wo_info;
if (!retval && infop)
retval = put_user(SIGCHLD, &infop->si_signo);
if (!retval && infop)
* the lock and this task is uninteresting. If we return nonzero, we have
* released the lock and the system call should return.
*/
-static int wait_task_continued(struct task_struct *p, int options,
- struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_task_continued(struct wait_opts *wo, struct task_struct *p)
{
int retval;
pid_t pid;
uid_t uid;
- if (!unlikely(options & WCONTINUED))
+ if (!unlikely(wo->wo_flags & WCONTINUED))
return 0;
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
spin_unlock_irq(&p->sighand->siglock);
return 0;
}
- if (!unlikely(options & WNOWAIT))
+ if (!unlikely(wo->wo_flags & WNOWAIT))
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
+ uid = __task_cred(p)->uid;
spin_unlock_irq(&p->sighand->siglock);
pid = task_pid_vnr(p);
- uid = p->uid;
get_task_struct(p);
read_unlock(&tasklist_lock);
- if (!infop) {
- retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+ if (!wo->wo_info) {
+ retval = wo->wo_rusage
+ ? getrusage(p, RUSAGE_BOTH, wo->wo_rusage) : 0;
put_task_struct(p);
- if (!retval && stat_addr)
- retval = put_user(0xffff, stat_addr);
+ if (!retval && wo->wo_stat)
+ retval = put_user(0xffff, wo->wo_stat);
if (!retval)
retval = pid;
} else {
- retval = wait_noreap_copyout(p, pid, uid,
- CLD_CONTINUED, SIGCONT,
- infop, ru);
+ retval = wait_noreap_copyout(wo, p, pid, uid,
+ CLD_CONTINUED, SIGCONT);
BUG_ON(retval == 0);
}
/*
* Consider @p for a wait by @parent.
*
- * -ECHILD should be in *@notask_error before the first call.
+ * -ECHILD should be in ->notask_error before the first call.
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
* Returns zero if the search for a child should continue;
- * then *@notask_error is 0 if @p is an eligible child,
+ * then ->notask_error is 0 if @p is an eligible child,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int wait_consider_task(struct task_struct *parent, int ptrace,
- struct task_struct *p, int *notask_error,
- enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop,
- int __user *stat_addr, struct rusage __user *ru)
+static int wait_consider_task(struct wait_opts *wo, struct task_struct *parent,
+ int ptrace, struct task_struct *p)
{
- int ret = eligible_child(type, pid, options, p);
+ int ret = eligible_child(wo, p);
if (!ret)
return ret;
* to look for security policy problems, rather
* than for mysterious wait bugs.
*/
- if (*notask_error)
- *notask_error = ret;
+ if (wo->notask_error)
+ wo->notask_error = ret;
+ return 0;
}
- if (likely(!ptrace) && unlikely(p->ptrace)) {
+ if (likely(!ptrace) && unlikely(task_ptrace(p))) {
/*
* This child is hidden by ptrace.
* We aren't allowed to see it now, but eventually we will.
*/
- *notask_error = 0;
+ wo->notask_error = 0;
return 0;
}
* We don't reap group leaders with subthreads.
*/
if (p->exit_state == EXIT_ZOMBIE && !delay_group_leader(p))
- return wait_task_zombie(p, options, infop, stat_addr, ru);
+ return wait_task_zombie(wo, p);
/*
* It's stopped or running now, so it might
* later continue, exit, or stop again.
*/
- *notask_error = 0;
+ wo->notask_error = 0;
- if (task_is_stopped_or_traced(p))
- return wait_task_stopped(ptrace, p, options,
- infop, stat_addr, ru);
+ if (task_stopped_code(p, ptrace))
+ return wait_task_stopped(wo, ptrace, p);
- return wait_task_continued(p, options, infop, stat_addr, ru);
+ return wait_task_continued(wo, p);
}
/*
* Do the work of do_wait() for one thread in the group, @tsk.
*
- * -ECHILD should be in *@notask_error before the first call.
+ * -ECHILD should be in ->notask_error before the first call.
* Returns nonzero for a final return, when we have unlocked tasklist_lock.
* Returns zero if the search for a child should continue; then
- * *@notask_error is 0 if there were any eligible children,
+ * ->notask_error is 0 if there were any eligible children,
* or another error from security_task_wait(), or still -ECHILD.
*/
-static int do_wait_thread(struct task_struct *tsk, int *notask_error,
- enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop, int __user *stat_addr,
- struct rusage __user *ru)
+static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk)
{
struct task_struct *p;
* Do not consider detached threads.
*/
if (!task_detached(p)) {
- int ret = wait_consider_task(tsk, 0, p, notask_error,
- type, pid, options,
- infop, stat_addr, ru);
+ int ret = wait_consider_task(wo, tsk, 0, p);
if (ret)
return ret;
}
return 0;
}
-static int ptrace_do_wait(struct task_struct *tsk, int *notask_error,
- enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop, int __user *stat_addr,
- struct rusage __user *ru)
+static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk)
{
struct task_struct *p;
- /*
- * Traditionally we see ptrace'd stopped tasks regardless of options.
- */
- options |= WUNTRACED;
-
list_for_each_entry(p, &tsk->ptraced, ptrace_entry) {
- int ret = wait_consider_task(tsk, 1, p, notask_error,
- type, pid, options,
- infop, stat_addr, ru);
+ int ret = wait_consider_task(wo, tsk, 1, p);
if (ret)
return ret;
}
return 0;
}
-static long do_wait(enum pid_type type, struct pid *pid, int options,
- struct siginfo __user *infop, int __user *stat_addr,
- struct rusage __user *ru)
+static long do_wait(struct wait_opts *wo)
{
DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
int retval;
+ trace_sched_process_wait(wo->wo_pid);
+
add_wait_queue(¤t->signal->wait_chldexit,&wait);
repeat:
/*
* If there is nothing that can match our critiera just get out.
- * We will clear @retval to zero if we see any child that might later
- * match our criteria, even if we are not able to reap it yet.
+ * 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.
*/
- retval = -ECHILD;
- if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
- goto end;
+ wo->notask_error = -ECHILD;
+ if ((wo->wo_type < PIDTYPE_MAX) &&
+ (!wo->wo_pid || hlist_empty(&wo->wo_pid->tasks[wo->wo_type])))
+ goto notask;
- current->state = TASK_INTERRUPTIBLE;
+ set_current_state(TASK_INTERRUPTIBLE);
read_lock(&tasklist_lock);
tsk = current;
do {
- int tsk_result = do_wait_thread(tsk, &retval,
- type, pid, options,
- infop, stat_addr, ru);
- if (!tsk_result)
- tsk_result = ptrace_do_wait(tsk, &retval,
- type, pid, options,
- infop, stat_addr, ru);
- if (tsk_result) {
- /*
- * tasklist_lock is unlocked and we have a final result.
- */
- retval = tsk_result;
+ retval = do_wait_thread(wo, tsk);
+ if (retval)
goto end;
- }
- if (options & __WNOTHREAD)
+ retval = ptrace_do_wait(wo, tsk);
+ if (retval)
+ goto end;
+
+ if (wo->wo_flags & __WNOTHREAD)
break;
- tsk = next_thread(tsk);
- BUG_ON(tsk->signal != current->signal);
- } while (tsk != current);
+ } while_each_thread(current, tsk);
read_unlock(&tasklist_lock);
- if (!retval && !(options & WNOHANG)) {
+notask:
+ retval = wo->notask_error;
+ if (!retval && !(wo->wo_flags & WNOHANG)) {
retval = -ERESTARTSYS;
if (!signal_pending(current)) {
schedule();
goto repeat;
}
}
-
end:
- current->state = TASK_RUNNING;
+ __set_current_state(TASK_RUNNING);
remove_wait_queue(¤t->signal->wait_chldexit,&wait);
- if (infop) {
+ if (wo->wo_info) {
+ struct siginfo __user *infop = wo->wo_info;
+
if (retval > 0)
retval = 0;
else {
return retval;
}
-asmlinkage long sys_waitid(int which, pid_t upid,
- struct siginfo __user *infop, int options,
- struct rusage __user *ru)
+SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *,
+ infop, int, options, struct rusage __user *, ru)
{
+ struct wait_opts wo;
struct pid *pid = NULL;
enum pid_type type;
long ret;
if (type < PIDTYPE_MAX)
pid = find_get_pid(upid);
- ret = do_wait(type, pid, options, infop, NULL, ru);
+
+ wo.wo_type = type;
+ wo.wo_pid = pid;
+ wo.wo_flags = options;
+ wo.wo_info = infop;
+ wo.wo_stat = NULL;
+ wo.wo_rusage = ru;
+ ret = do_wait(&wo);
put_pid(pid);
/* avoid REGPARM breakage on x86: */
return ret;
}
-asmlinkage long sys_wait4(pid_t upid, int __user *stat_addr,
- int options, struct rusage __user *ru)
+SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
+ int, options, struct rusage __user *, ru)
{
+ struct wait_opts wo;
struct pid *pid = NULL;
enum pid_type type;
long ret;
pid = find_get_pid(-upid);
} else if (upid == 0) {
type = PIDTYPE_PGID;
- pid = get_pid(task_pgrp(current));
+ pid = get_task_pid(current, PIDTYPE_PGID);
} else /* upid > 0 */ {
type = PIDTYPE_PID;
pid = find_get_pid(upid);
}
- ret = do_wait(type, pid, options | WEXITED, NULL, stat_addr, ru);
+ wo.wo_type = type;
+ wo.wo_pid = pid;
+ wo.wo_flags = options | WEXITED;
+ wo.wo_info = NULL;
+ wo.wo_stat = stat_addr;
+ wo.wo_rusage = ru;
+ ret = do_wait(&wo);
put_pid(pid);
/* avoid REGPARM breakage on x86: */
* sys_waitpid() remains for compatibility. waitpid() should be
* implemented by calling sys_wait4() from libc.a.
*/
-asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options)
+SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options)
{
return sys_wait4(pid, stat_addr, options, NULL);
}