#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/cpu.h>
#include <linux/acct.h>
#include <linux/tsacct_kern.h>
#include <linux/file.h>
+#include <linux/fdtable.h>
#include <linux/binfmts.h>
#include <linux/nsproxy.h>
#include <linux/pid_namespace.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 <trace/sched.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/pgtable.h>
#include <asm/mmu_context.h>
+#include "cred-internals.h"
+
+DEFINE_TRACE(sched_process_free);
+DEFINE_TRACE(sched_process_exit);
+DEFINE_TRACE(sched_process_wait);
static void exit_mm(struct task_struct * tsk);
__get_cpu_var(process_counts)--;
}
list_del_rcu(&p->thread_group);
- remove_parent(p);
+ list_del_init(&p->sibling);
}
/*
BUG_ON(!sig);
BUG_ON(!atomic_read(&sig->count));
- rcu_read_lock();
sighand = rcu_dereference(tsk->sighand);
spin_lock(&sighand->siglock);
* 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);
+ 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);
+ /*
+ * 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);
- rcu_read_unlock();
__cleanup_sighand(sighand);
clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
- flush_sigqueue(&tsk->pending);
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);
+
+ trace_sched_process_free(tsk);
+ put_task_struct(tsk);
}
+
void release_task(struct task_struct * p)
{
struct task_struct *leader;
int zap_leader;
repeat:
- atomic_dec(&p->user->processes);
+ 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 */
+ atomic_dec(&__task_cred(p)->user->processes);
+
proc_flush_task(p);
write_lock_irq(&tasklist_lock);
- ptrace_unlink(p);
- BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
+ tracehook_finish_release_task(p);
__exit_signal(p);
/*
zap_leader = 0;
leader = p->group_leader;
if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
- BUG_ON(leader->exit_signal == -1);
+ BUG_ON(task_detached(leader));
do_notify_parent(leader, leader->exit_signal);
/*
* If we were the last child thread and the leader has
* do_notify_parent() will have marked it self-reaping in
* that case.
*/
- zap_leader = (leader->exit_signal == -1);
+ zap_leader = task_detached(leader);
+
+ /*
+ * This maintains the invariant that release_task()
+ * only runs on a task in EXIT_DEAD, just for sanity.
+ */
+ if (zap_leader)
+ leader->exit_state = EXIT_DEAD;
}
write_unlock_irq(&tasklist_lock);
ptrace_unlink(current);
/* Reparent to init */
- remove_parent(current);
current->real_parent = current->parent = kthreadd_task;
- add_parent(current);
+ list_move_tail(¤t->sibling, ¤t->real_parent->children);
/* Set the exit signal to SIGCHLD so we signal init on exit */
current->exit_signal = SIGCHLD;
/* 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) {
- detach_pid(curr, PIDTYPE_SID);
- attach_pid(curr, PIDTYPE_SID, pid);
- set_task_session(curr, nr);
- }
- if (task_pgrp(curr) != pid) {
- detach_pid(curr, PIDTYPE_PGID);
- attach_pid(curr, PIDTYPE_PGID, pid);
- set_task_pgrp(curr, nr);
- }
+ if (task_session(curr) != pid)
+ change_pid(curr, PIDTYPE_SID, pid);
+
+ if (task_pgrp(curr) != pid)
+ change_pid(curr, PIDTYPE_PGID, pid);
}
static void set_special_pids(struct pid *pid)
void daemonize(const char *name, ...)
{
va_list args;
- struct fs_struct *fs;
sigset_t blocked;
va_start(args, name);
* We don't want to have TIF_FREEZE set if the system-wide hibernation
* or suspend transition begins right now.
*/
- current->flags |= PF_NOFREEZE;
+ current->flags |= (PF_NOFREEZE | PF_KTHREAD);
if (current->nsproxy != &init_nsproxy) {
get_nsproxy(&init_nsproxy);
/* 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)
+#ifdef CONFIG_MM_OWNER
+/*
+ * Task p is exiting and it owned mm, lets find a new owner for it
+ */
+static inline int
+mm_need_new_owner(struct mm_struct *mm, struct task_struct *p)
{
- /* 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);
- if (fs->altroot.dentry)
- path_put(&fs->altroot);
- kmem_cache_free(fs_cachep, fs);
- }
+ /*
+ * 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 (atomic_read(&mm->mm_users) <= 1)
+ return 0;
+ if (mm->owner != p)
+ return 0;
+ return 1;
}
-void exit_fs(struct task_struct *tsk)
+void mm_update_next_owner(struct mm_struct *mm)
{
- struct fs_struct * fs = tsk->fs;
+ struct task_struct *c, *g, *p = current;
- if (fs) {
- task_lock(tsk);
- tsk->fs = NULL;
- task_unlock(tsk);
- put_fs_struct(fs);
+retry:
+ if (!mm_need_new_owner(mm, p))
+ return;
+
+ read_lock(&tasklist_lock);
+ /*
+ * Search in the children
+ */
+ list_for_each_entry(c, &p->children, sibling) {
+ if (c->mm == mm)
+ goto assign_new_owner;
}
-}
-EXPORT_SYMBOL_GPL(exit_fs);
+ /*
+ * Search in the siblings
+ */
+ list_for_each_entry(c, &p->parent->children, sibling) {
+ if (c->mm == mm)
+ goto assign_new_owner;
+ }
+
+ /*
+ * 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);
+
+ 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:
+ BUG_ON(c == p);
+ get_task_struct(c);
+ /*
+ * The task_lock protects c->mm from changing.
+ * We always want mm->owner->mm == mm
+ */
+ task_lock(c);
+ /*
+ * Delay read_unlock() till we have the task_lock()
+ * to ensure that c does not slip away underneath us
+ */
+ read_unlock(&tasklist_lock);
+ if (c->mm != mm) {
+ task_unlock(c);
+ put_task_struct(c);
+ goto retry;
+ }
+ mm->owner = c;
+ task_unlock(c);
+ put_task_struct(c);
+}
+#endif /* CONFIG_MM_OWNER */
/*
* Turn us into a lazy TLB process if we
static void exit_mm(struct task_struct * tsk)
{
struct mm_struct *mm = tsk->mm;
+ struct core_state *core_state;
mm_release(tsk, mm);
if (!mm)
return;
/*
* Serialize with any possible pending coredump.
- * We must hold mmap_sem around checking core_waiters
+ * We must hold mmap_sem around checking core_state
* and clearing tsk->mm. The core-inducing thread
- * will increment core_waiters for each thread in the
+ * will increment ->nr_threads for each thread in the
* group with ->mm != NULL.
*/
down_read(&mm->mmap_sem);
- if (mm->core_waiters) {
+ core_state = mm->core_state;
+ if (core_state) {
+ struct core_thread self;
up_read(&mm->mmap_sem);
- down_write(&mm->mmap_sem);
- if (!--mm->core_waiters)
- complete(mm->core_startup_done);
- up_write(&mm->mmap_sem);
- wait_for_completion(&mm->core_done);
+ self.task = tsk;
+ self.next = xchg(&core_state->dumper.next, &self);
+ /*
+ * 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);
+
+ for (;;) {
+ set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+ if (!self.task) /* see coredump_finish() */
+ break;
+ schedule();
+ }
+ __set_task_state(tsk, TASK_RUNNING);
down_read(&mm->mmap_sem);
}
atomic_inc(&mm->mm_count);
/* We don't want this task to be frozen prematurely */
clear_freeze_flag(tsk);
task_unlock(tsk);
+ mm_update_next_owner(mm);
mmput(mm);
}
-static void
-reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
+/*
+ * 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 struct task_struct *find_new_reaper(struct task_struct *father)
{
- if (p->pdeath_signal)
- /* We already hold the tasklist_lock here. */
- group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
+ struct pid_namespace *pid_ns = task_active_pid_ns(father);
+ struct task_struct *thread;
- /* Move the child from its dying parent to the new one. */
- if (unlikely(traced)) {
- /* Preserve ptrace links if someone else is tracing this child. */
- list_del_init(&p->ptrace_list);
- if (p->parent != p->real_parent)
- list_add(&p->ptrace_list, &p->real_parent->ptrace_children);
- } else {
- /* If this child is being traced, then we're the one tracing it
- * anyway, so let go of it.
- */
- p->ptrace = 0;
- remove_parent(p);
- p->parent = p->real_parent;
- add_parent(p);
+ 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 (task_is_traced(p)) {
- /*
- * If it was at a trace stop, turn it into
- * a normal stop since it's no longer being
- * traced.
- */
- ptrace_untrace(p);
- }
+ 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);
+ /*
+ * 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.
+ */
+ pid_ns->child_reaper = init_pid_ns.child_reaper;
}
- /* If this is a threaded reparent there is no need to
+ return pid_ns->child_reaper;
+}
+
+/*
+* 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,
+ 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))
+ return;
+ /*
+ * If this is a threaded reparent there is no need to
* notify anyone anything has happened.
*/
- if (p->real_parent->group_leader == father->group_leader)
+ if (same_thread_group(p->real_parent, father))
return;
/* We don't want people slaying init. */
- if (p->exit_signal != -1)
- 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 (!traced && p->exit_state == EXIT_ZOMBIE &&
- p->exit_signal != -1 && thread_group_empty(p))
+ /* 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)) {
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;
- struct list_head ptrace_dead;
+ struct task_struct *p, *n, *reaper;
+ LIST_HEAD(dead_children);
- INIT_LIST_HEAD(&ptrace_dead);
+ exit_ptrace(father);
write_lock_irq(&tasklist_lock);
+ reaper = find_new_reaper(father);
- do {
- reaper = next_thread(reaper);
- if (reaper == father) {
- reaper = task_child_reaper(father);
- break;
- }
- } while (reaper->flags & PF_EXITING);
-
- /*
- * There are only two places where our children can be:
- *
- * - in our child list
- * - in our ptraced child list
- *
- * Search them and reparent children.
- */
list_for_each_entry_safe(p, n, &father->children, sibling) {
- int ptrace;
-
- ptrace = p->ptrace;
-
- /* if father isn't the real parent, then ptrace must be enabled */
- BUG_ON(father != p->real_parent && !ptrace);
-
- if (father == p->real_parent) {
- /* reparent with a reaper, real father it's us */
- p->real_parent = reaper;
- reparent_thread(p, father, 0);
- } else {
- /* reparent ptraced task to its real parent */
- __ptrace_unlink (p);
- if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 &&
- thread_group_empty(p))
- do_notify_parent(p, p->exit_signal);
- }
-
- /*
- * if the ptraced child is a zombie with exit_signal == -1
- * we must collect it before we exit, or it will remain
- * zombie forever since we prevented it from self-reap itself
- * while it was being traced by us, to be able to see it in wait4.
- */
- if (unlikely(ptrace && p->exit_state == EXIT_ZOMBIE && p->exit_signal == -1))
- list_add(&p->ptrace_list, &ptrace_dead);
- }
-
- list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) {
p->real_parent = reaper;
- reparent_thread(p, father, 1);
+ if (p->parent == father) {
+ BUG_ON(p->ptrace);
+ p->parent = p->real_parent;
+ }
+ reparent_thread(father, p, &dead_children);
}
-
write_unlock_irq(&tasklist_lock);
+
BUG_ON(!list_empty(&father->children));
- BUG_ON(!list_empty(&father->ptrace_children));
- list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_list) {
- list_del_init(&p->ptrace_list);
+ list_for_each_entry_safe(p, n, &dead_children, sibling) {
+ list_del_init(&p->sibling);
release_task(p);
}
-
}
/*
*/
static void exit_notify(struct task_struct *tsk, int group_dead)
{
- int state;
+ int signal;
+ void *cookie;
/*
* This does two things:
* we have changed execution domain as these two values started
* the same after a fork.
*/
- if (tsk->exit_signal != SIGCHLD && tsk->exit_signal != -1 &&
+ 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)
+ signal = do_notify_parent(tsk, signal);
- /* If something other than our normal parent is ptracing us, then
- * send it a SIGCHLD instead of honoring exit_signal. exit_signal
- * only has special meaning to our real parent.
- */
- if (tsk->exit_signal != -1 && thread_group_empty(tsk)) {
- int signal = tsk->parent == tsk->real_parent ? tsk->exit_signal : SIGCHLD;
- do_notify_parent(tsk, signal);
- } else if (tsk->ptrace) {
- do_notify_parent(tsk, SIGCHLD);
- }
-
- state = EXIT_ZOMBIE;
- if (tsk->exit_signal == -1 && likely(!tsk->ptrace))
- state = EXIT_DEAD;
- tsk->exit_state = state;
+ 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 (state == EXIT_DEAD)
+ 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;
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
- if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
- current->ptrace_message = code;
- ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
- }
+ tracehook_report_exit(&code);
/*
* We're taking recursive faults here in do_exit. Safest is to just
* 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);
proc_exit_connector(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
- mpol_free(tsk->mempolicy);
+ mpol_put(tsk->mempolicy);
tsk->mempolicy = NULL;
#endif
#ifdef CONFIG_FUTEX
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);
}
NORET_TYPE void
do_group_exit(int exit_code)
{
+ struct signal_struct *sig = current->signal;
+
BUG_ON(exit_code & 0x80); /* core dumps don't get here */
- if (current->signal->flags & SIGNAL_GROUP_EXIT)
- exit_code = current->signal->group_exit_code;
+ if (signal_group_exit(sig))
+ exit_code = sig->group_exit_code;
else if (!thread_group_empty(current)) {
- struct signal_struct *const sig = current->signal;
struct sighand_struct *const sighand = current->sighand;
spin_lock_irq(&sighand->siglock);
if (signal_group_exit(sig))
* 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;
}
static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
return 0;
}
- /*
- * Do not consider detached threads that are
- * not ptraced:
- */
- if (p->exit_signal == -1 && !p->ptrace)
- return 0;
-
/* Wait for all children (clone and not) if __WALL is set;
* otherwise, wait for clone children *only* if __WCLONE is
* set; otherwise, wait for non-clone children *only*. (Note:
return 0;
err = security_task_wait(p);
- if (likely(!err))
- return 1;
+ if (err)
+ return err;
- if (type != PIDTYPE_PID)
- return 0;
- /* This child was explicitly requested, abort */
- read_unlock(&tasklist_lock);
- return err;
+ return 1;
}
static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
* 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 noreap,
+static int wait_task_zombie(struct task_struct *p, int options,
struct siginfo __user *infop,
int __user *stat_addr, struct rusage __user *ru)
{
unsigned long state;
int retval, status, traced;
pid_t pid = task_pid_vnr(p);
+ uid_t uid = __task_cred(p)->uid;
+
+ if (!likely(options & WEXITED))
+ return 0;
- if (unlikely(noreap)) {
- uid_t uid = p->uid;
+ if (unlikely(options & WNOWAIT)) {
int exit_code = p->exit_code;
int why, status;
return 0;
}
- /* traced means p->ptrace, but not vice versa */
- traced = (p->real_parent != p->parent);
+ traced = ptrace_reparented(p);
if (likely(!traced)) {
struct signal_struct *psig;
struct signal_struct *sig;
+ struct task_cputime cputime;
/*
* The resource counters for the group leader are in its
* need to protect the access to p->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_cputime() to get times for the thread
+ * group, which consolidates times for all threads in the
+ * group including the group leader.
*/
+ thread_group_cputime(p, &cputime);
spin_lock_irq(&p->parent->sighand->siglock);
psig = p->parent->signal;
sig = p->signal;
psig->cutime =
cputime_add(psig->cutime,
- cputime_add(p->utime,
- cputime_add(sig->utime,
- sig->cutime)));
+ cputime_add(cputime.utime,
+ sig->cutime));
psig->cstime =
cputime_add(psig->cstime,
- cputime_add(p->stime,
- cputime_add(sig->stime,
- sig->cstime)));
+ cputime_add(cputime.stime,
+ sig->cstime));
psig->cgtime =
cputime_add(psig->cgtime,
cputime_add(p->gtime,
psig->coublock +=
task_io_get_oublock(p) +
sig->oublock + sig->coublock;
+ task_io_accounting_add(&psig->ioac, &p->ioac);
+ task_io_accounting_add(&psig->ioac, &sig->ioac);
spin_unlock_irq(&p->parent->sighand->siglock);
}
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;
* If it's still not detached after that, don't release
* it now.
*/
- if (p->exit_signal != -1) {
+ if (!task_detached(p)) {
do_notify_parent(p, p->exit_signal);
- if (p->exit_signal != -1) {
+ if (!task_detached(p)) {
p->exit_state = EXIT_ZOMBIE;
p = NULL;
}
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(struct task_struct *p,
- int noreap, struct siginfo __user *infop,
+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)
{
- int retval, exit_code, why;
+ int retval, exit_code, *p_code, why;
uid_t uid = 0; /* unneeded, required by compiler */
pid_t pid;
+ if (!(options & WUNTRACED))
+ return 0;
+
exit_code = 0;
spin_lock_irq(&p->sighand->siglock);
- if (unlikely(!task_is_stopped_or_traced(p)))
- goto unlock_sig;
-
- if (!(p->ptrace & PT_PTRACED) && 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.
- */
+ p_code = task_stopped_code(p, ptrace);
+ if (unlikely(!p_code))
goto unlock_sig;
- exit_code = p->exit_code;
+ exit_code = *p_code;
if (!exit_code)
goto unlock_sig;
- if (!noreap)
- p->exit_code = 0;
+ if (!unlikely(options & 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)
*/
get_task_struct(p);
pid = task_pid_vnr(p);
- why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED;
+ why = ptrace ? CLD_TRAPPED : CLD_STOPPED;
read_unlock(&tasklist_lock);
- if (unlikely(noreap))
+ if (unlikely(options & WNOWAIT))
return wait_noreap_copyout(p, pid, uid,
why, exit_code,
infop, ru);
* 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 noreap,
+static int wait_task_continued(struct task_struct *p, int options,
struct siginfo __user *infop,
int __user *stat_addr, struct rusage __user *ru)
{
pid_t pid;
uid_t uid;
+ if (!unlikely(options & WCONTINUED))
+ return 0;
+
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
return 0;
spin_unlock_irq(&p->sighand->siglock);
return 0;
}
- if (!noreap)
+ if (!unlikely(options & 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);
return retval;
}
+/*
+ * Consider @p for a wait by @parent.
+ *
+ * -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,
+ * 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)
+{
+ int ret = eligible_child(type, pid, options, p);
+ if (!ret)
+ return ret;
+
+ if (unlikely(ret < 0)) {
+ /*
+ * If we have not yet seen any eligible child,
+ * then let this error code replace -ECHILD.
+ * A permission error will give the user a clue
+ * to look for security policy problems, rather
+ * than for mysterious wait bugs.
+ */
+ if (*notask_error)
+ *notask_error = ret;
+ }
+
+ if (likely(!ptrace) && unlikely(p->ptrace)) {
+ /*
+ * This child is hidden by ptrace.
+ * We aren't allowed to see it now, but eventually we will.
+ */
+ *notask_error = 0;
+ return 0;
+ }
+
+ if (p->exit_state == EXIT_DEAD)
+ 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);
+
+ /*
+ * It's stopped or running now, so it might
+ * later continue, exit, or stop again.
+ */
+ *notask_error = 0;
+
+ if (task_stopped_code(p, ptrace))
+ return wait_task_stopped(ptrace, p, options,
+ infop, stat_addr, ru);
+
+ return wait_task_continued(p, options, infop, stat_addr, ru);
+}
+
+/*
+ * Do the work of do_wait() for one thread in the group, @tsk.
+ *
+ * -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,
+ * 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)
+{
+ 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(tsk, 0, p, notask_error,
+ type, pid, options,
+ infop, stat_addr, ru);
+ 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)
+{
+ 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);
+ 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)
{
DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
- int flag, retval;
+ int retval;
+
+ trace_sched_process_wait(pid);
add_wait_queue(¤t->signal->wait_chldexit,&wait);
repeat:
- /* If there is nothing that can match our critier just get out */
+ /*
+ * 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.
+ */
retval = -ECHILD;
if ((type < PIDTYPE_MAX) && (!pid || hlist_empty(&pid->tasks[type])))
goto end;
- /*
- * We will set this flag if we see any child that might later
- * match our criteria, even if we are not able to reap it yet.
- */
- flag = retval = 0;
current->state = TASK_INTERRUPTIBLE;
read_lock(&tasklist_lock);
tsk = current;
do {
- struct task_struct *p;
-
- list_for_each_entry(p, &tsk->children, sibling) {
- int ret = eligible_child(type, pid, options, p);
- if (!ret)
- continue;
-
- if (unlikely(ret < 0)) {
- retval = ret;
- } else if (task_is_stopped_or_traced(p)) {
- /*
- * It's stopped now, so it might later
- * continue, exit, or stop again.
- */
- flag = 1;
- if (!(p->ptrace & PT_PTRACED) &&
- !(options & WUNTRACED))
- continue;
-
- retval = wait_task_stopped(p,
- (options & WNOWAIT), infop,
- stat_addr, ru);
- } else if (p->exit_state == EXIT_ZOMBIE &&
- !delay_group_leader(p)) {
- /*
- * We don't reap group leaders with subthreads.
- */
- if (!likely(options & WEXITED))
- continue;
- retval = wait_task_zombie(p,
- (options & WNOWAIT), infop,
- stat_addr, ru);
- } else if (p->exit_state != EXIT_DEAD) {
- /*
- * It's running now, so it might later
- * exit, stop, or stop and then continue.
- */
- flag = 1;
- if (!unlikely(options & WCONTINUED))
- continue;
- retval = wait_task_continued(p,
- (options & WNOWAIT), infop,
- stat_addr, ru);
- }
- if (retval != 0) /* tasklist_lock released */
- goto end;
- }
- if (!flag) {
- list_for_each_entry(p, &tsk->ptrace_children,
- ptrace_list) {
- flag = eligible_child(type, pid, options, p);
- if (!flag)
- continue;
- if (likely(flag > 0))
- break;
- retval = flag;
- goto end;
- }
+ 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;
+ goto end;
}
+
if (options & __WNOTHREAD)
break;
tsk = next_thread(tsk);
} while (tsk != current);
read_unlock(&tasklist_lock);
- if (flag) {
- if (options & WNOHANG)
- goto end;
+ if (!retval && !(options & WNOHANG)) {
retval = -ERESTARTSYS;
- if (signal_pending(current))
- goto end;
- schedule();
- goto repeat;
+ if (!signal_pending(current)) {
+ schedule();
+ goto repeat;
+ }
}
- retval = -ECHILD;
+
end:
current->state = TASK_RUNNING;
remove_wait_queue(¤t->signal->wait_chldexit,&wait);
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 pid *pid = NULL;
enum pid_type type;
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 pid *pid = NULL;
enum pid_type type;
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);
* 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);
}
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff