#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/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);
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. */
}
tsk->signal = NULL;
tsk->sighand = NULL;
spin_unlock(&sighand->siglock);
- rcu_read_unlock();
__cleanup_sighand(sighand);
clear_tsk_thread_flag(tsk,TIF_SIGPENDING);
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);
-/*
- * Do final ptrace-related cleanup of a zombie being reaped.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-static void ptrace_release_task(struct task_struct *p)
-{
- BUG_ON(!list_empty(&p->ptraced));
- ptrace_unlink(p);
- BUG_ON(!list_empty(&p->ptrace_entry));
+ 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_release_task(p);
+ tracehook_finish_release_task(p);
__exit_signal(p);
/*
* that case.
*/
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);
/* 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)
* 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);
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 (!mm)
- return 0;
if (atomic_read(&mm->mm_users) <= 1)
return 0;
if (mm->owner != p)
} 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);
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);
}
/*
+ * 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.
*
static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
{
struct task_struct *p, *n;
+ int ign = -1;
list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
__ptrace_unlink(p);
* 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.
*/
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)) {
* the child reaper process (ie "init") in our pid
* space.
*/
+static struct task_struct *find_new_reaper(struct task_struct *father)
+{
+ struct pid_namespace *pid_ns = task_active_pid_ns(father);
+ struct task_struct *thread;
+
+ 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);
+ /*
+ * 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;
+ }
+
+ return pid_ns->child_reaper;
+}
+
static void forget_original_parent(struct task_struct *father)
{
- struct task_struct *p, *n, *reaper = father;
+ struct task_struct *p, *n, *reaper;
LIST_HEAD(ptrace_dead);
write_lock_irq(&tasklist_lock);
-
+ reaper = find_new_reaper(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);
-
list_for_each_entry_safe(p, n, &father->children, sibling) {
p->real_parent = reaper;
if (p->parent == father) {
*/
static void exit_notify(struct task_struct *tsk, int group_dead)
{
- int state;
+ int signal;
+ void *cookie;
/*
* This does two things:
!capable(CAP_KILL))
tsk->exit_signal = SIGCHLD;
- /* 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 (!task_detached(tsk) && thread_group_empty(tsk)) {
- int signal = ptrace_reparented(tsk) ?
- SIGCHLD : tsk->exit_signal;
- do_notify_parent(tsk, signal);
- } else if (tsk->ptrace) {
- do_notify_parent(tsk, SIGCHLD);
- }
+ signal = tracehook_notify_death(tsk, &cookie, group_dead);
+ if (signal >= 0)
+ signal = do_notify_parent(tsk, signal);
- state = EXIT_ZOMBIE;
- if (task_detached(tsk) && 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 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();
}
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);
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;
}
static struct pid *task_pid_type(struct task_struct *task, enum pid_type type)
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,
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(options & WNOWAIT)) {
- uid_t uid = p->uid;
int exit_code = p->exit_code;
int why, status;
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 (!unlikely(options & WNOWAIT))
p->exit_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)
}
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);
* -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 still -ECHILD.
+ * 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,
int __user *stat_addr, struct rusage __user *ru)
{
int ret = eligible_child(type, pid, options, p);
- if (ret <= 0)
+ 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.
* -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 still -ECHILD.
+ * *@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 task_struct *tsk;
int retval;
+ trace_sched_process_wait(pid);
+
add_wait_queue(¤t->signal->wait_chldexit,&wait);
repeat:
/*
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;
* 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);
}