#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
-#include <linux/smp_lock.h>
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/completion.h>
#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
+#include <linux/signalfd.h>
#include <linux/mount.h>
#include <linux/proc_fs.h>
+#include <linux/kthread.h>
#include <linux/mempolicy.h>
#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/audit.h> /* for audit_free() */
#include <linux/resource.h>
#include <linux/blkdev.h>
+#include <linux/task_io_accounting_ops.h>
#include <asm/uaccess.h>
#include <asm/unistd.h>
sighand = rcu_dereference(tsk->sighand);
spin_lock(&sighand->siglock);
+ /*
+ * Notify that this sighand has been detached. This must
+ * be called with the tsk->sighand lock held. Also, this
+ * access tsk->sighand internally, so it must be called
+ * before tsk->sighand is reset.
+ */
+ signalfd_detach_locked(tsk);
+
posix_cpu_timers_exit(tsk);
if (atomic_dec_and_test(&sig->count))
posix_cpu_timers_exit_group(tsk);
sig->maj_flt += tsk->maj_flt;
sig->nvcsw += tsk->nvcsw;
sig->nivcsw += tsk->nivcsw;
- sig->sched_time += tsk->sched_time;
+ sig->inblock += task_io_get_inblock(tsk);
+ sig->oublock += task_io_get_oublock(tsk);
+ sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
sig = NULL; /* Marker for below. */
}
zap_leader = (leader->exit_signal == -1);
}
- sched_exit(p);
write_unlock_irq(&tasklist_lock);
proc_flush_task(p);
release_thread(p);
* This checks not only the pgrp, but falls back on the pid if no
* satisfactory pgrp is found. I dunno - gdb doesn't work correctly
* without this...
+ *
+ * The caller must hold rcu lock or the tasklist lock.
*/
-int session_of_pgrp(int pgrp)
+struct pid *session_of_pgrp(struct pid *pgrp)
{
struct task_struct *p;
- int sid = 0;
-
- read_lock(&tasklist_lock);
+ struct pid *sid = NULL;
- p = find_task_by_pid_type(PIDTYPE_PGID, pgrp);
+ p = pid_task(pgrp, PIDTYPE_PGID);
if (p == NULL)
- p = find_task_by_pid(pgrp);
+ p = pid_task(pgrp, PIDTYPE_PID);
if (p != NULL)
- sid = process_session(p);
-
- read_unlock(&tasklist_lock);
+ sid = task_session(p);
return sid;
}
*
* "I ask you, have you ever known what it is to be an orphan?"
*/
-static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task)
+static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task)
{
struct task_struct *p;
int ret = 1;
- do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
+ do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
if (p == ignored_task
|| p->exit_state
|| is_init(p->real_parent))
continue;
- if (process_group(p->real_parent) != pgrp &&
- process_session(p->real_parent) == process_session(p)) {
+ if (task_pgrp(p->real_parent) != pgrp &&
+ task_session(p->real_parent) == task_session(p)) {
ret = 0;
break;
}
- } while_each_task_pid(pgrp, PIDTYPE_PGID, p);
+ } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
return ret; /* (sighing) "Often!" */
}
-int is_orphaned_pgrp(int pgrp)
+int is_current_pgrp_orphaned(void)
{
int retval;
read_lock(&tasklist_lock);
- retval = will_become_orphaned_pgrp(pgrp, NULL);
+ retval = will_become_orphaned_pgrp(task_pgrp(current), NULL);
read_unlock(&tasklist_lock);
return retval;
}
-static int has_stopped_jobs(int pgrp)
+static int has_stopped_jobs(struct pid *pgrp)
{
int retval = 0;
struct task_struct *p;
- do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
+ do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
if (p->state != TASK_STOPPED)
continue;
retval = 1;
break;
- } while_each_task_pid(pgrp, PIDTYPE_PGID, p);
+ } while_each_pid_task(pgrp, PIDTYPE_PGID, p);
return retval;
}
/**
- * reparent_to_init - Reparent the calling kernel thread to the init task
- * of the pid space that the thread belongs to.
+ * reparent_to_kthreadd - Reparent the calling kernel thread to kthreadd
*
* If a kernel thread is launched as a result of a system call, or if
- * it ever exits, it should generally reparent itself to init so that
- * it is correctly cleaned up on exit.
+ * it ever exits, it should generally reparent itself to kthreadd so it
+ * isn't in the way of other processes and is correctly cleaned up on exit.
*
* The various task state such as scheduling policy and priority may have
* been inherited from a user process, so we reset them to sane values here.
*
- * NOTE that reparent_to_init() gives the caller full capabilities.
+ * NOTE that reparent_to_kthreadd() gives the caller full capabilities.
*/
-static void reparent_to_init(void)
+static void reparent_to_kthreadd(void)
{
write_lock_irq(&tasklist_lock);
ptrace_unlink(current);
/* Reparent to init */
remove_parent(current);
- current->parent = child_reaper(current);
- current->real_parent = child_reaper(current);
+ current->real_parent = current->parent = kthreadd_task;
add_parent(current);
/* Set the exit signal to SIGCHLD so we signal init on exit */
current->exit_signal = SIGCHLD;
- if (!has_rt_policy(current) && (task_nice(current) < 0))
+ if (task_nice(current) < 0)
set_user_nice(current, 0);
/* cpus_allowed? */
/* rt_priority? */
if (process_session(curr) != session) {
detach_pid(curr, PIDTYPE_SID);
set_signal_session(curr->signal, session);
- attach_pid(curr, PIDTYPE_SID, session);
+ attach_pid(curr, PIDTYPE_SID, find_pid(session));
}
if (process_group(curr) != pgrp) {
detach_pid(curr, PIDTYPE_PGID);
curr->signal->pgrp = pgrp;
- attach_pid(curr, PIDTYPE_PGID, pgrp);
+ attach_pid(curr, PIDTYPE_PGID, find_pid(pgrp));
}
}
return -EINVAL;
spin_lock_irq(¤t->sighand->siglock);
- sigaddset(¤t->blocked, sig);
+ current->sighand->action[(sig)-1].sa.sa_handler = SIG_IGN;
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
return 0;
current->fs = fs;
atomic_inc(&fs->count);
- put_and_finalize_nsproxy(current->nsproxy);
+ exit_task_namespaces(current);
current->nsproxy = init_task.nsproxy;
get_task_namespaces(current);
current->files = init_task.files;
atomic_inc(¤t->files->count);
- reparent_to_init();
+ reparent_to_kthreadd();
}
EXPORT_SYMBOL(daemonize);
while (set) {
if (set & 1) {
struct file * file = xchg(&fdt->fd[i], NULL);
- if (file)
+ if (file) {
filp_close(file, files);
+ cond_resched();
+ }
}
i++;
set >>= 1;
* than we are, and it was the only connection
* outside, so the child pgrp is now orphaned.
*/
- if ((process_group(p) != process_group(father)) &&
- (process_session(p) == process_session(father))) {
- int pgrp = process_group(p);
+ if ((task_pgrp(p) != task_pgrp(father)) &&
+ (task_session(p) == task_session(father))) {
+ struct pid *pgrp = task_pgrp(p);
if (will_become_orphaned_pgrp(pgrp, NULL) &&
has_stopped_jobs(pgrp)) {
- __kill_pg_info(SIGHUP, SEND_SIG_PRIV, pgrp);
- __kill_pg_info(SIGCONT, SEND_SIG_PRIV, pgrp);
+ __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
+ __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
}
}
}
int state;
struct task_struct *t;
struct list_head ptrace_dead, *_p, *_n;
+ struct pid *pgrp;
if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT)
&& !thread_group_empty(tsk)) {
read_lock(&tasklist_lock);
spin_lock_irq(&tsk->sighand->siglock);
for (t = next_thread(tsk); t != tsk; t = next_thread(t))
- if (!signal_pending(t) && !(t->flags & PF_EXITING)) {
- recalc_sigpending_tsk(t);
- if (signal_pending(t))
- signal_wake_up(t, 0);
- }
+ if (!signal_pending(t) && !(t->flags & PF_EXITING))
+ recalc_sigpending_and_wake(t);
spin_unlock_irq(&tsk->sighand->siglock);
read_unlock(&tasklist_lock);
}
t = tsk->real_parent;
- if ((process_group(t) != process_group(tsk)) &&
- (process_session(t) == process_session(tsk)) &&
- will_become_orphaned_pgrp(process_group(tsk), tsk) &&
- has_stopped_jobs(process_group(tsk))) {
- __kill_pg_info(SIGHUP, SEND_SIG_PRIV, process_group(tsk));
- __kill_pg_info(SIGCONT, SEND_SIG_PRIV, process_group(tsk));
+ pgrp = task_pgrp(tsk);
+ if ((task_pgrp(t) != pgrp) &&
+ (task_session(t) == task_session(tsk)) &&
+ will_become_orphaned_pgrp(pgrp, tsk) &&
+ has_stopped_jobs(pgrp)) {
+ __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
+ __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
}
/* Let father know we died
fastcall NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
- struct nsproxy *ns;
int group_dead;
profile_task_exit(tsk);
if (unlikely(tsk->flags & PF_EXITING)) {
printk(KERN_ALERT
"Fixing recursive fault but reboot is needed!\n");
+ /*
+ * We can do this unlocked here. The futex code uses
+ * this flag just to verify whether the pi state
+ * cleanup has been done or not. In the worst case it
+ * loops once more. We pretend that the cleanup was
+ * done as there is no way to return. Either the
+ * OWNER_DIED bit is set by now or we push the blocked
+ * 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();
}
+ /*
+ * tsk->flags are checked in the futex code to protect against
+ * an exiting task cleaning up the robust pi futexes.
+ */
+ spin_lock_irq(&tsk->pi_lock);
tsk->flags |= PF_EXITING;
+ spin_unlock_irq(&tsk->pi_lock);
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
}
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
- hrtimer_cancel(&tsk->signal->real_timer);
+ hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
}
acct_collect(code, group_dead);
tsk->exit_code = code;
proc_exit_connector(tsk);
- ns = preexit_task_namespaces(tsk);
+ exit_task_namespaces(tsk);
exit_notify(tsk);
- exit_task_namespaces(tsk, ns);
#ifdef CONFIG_NUMA
mpol_free(tsk->mempolicy);
tsk->mempolicy = NULL;
* Make sure we are holding no locks:
*/
debug_check_no_locks_held(tsk);
+ /*
+ * We can do this unlocked here. The futex code uses this flag
+ * just to verify whether the pi state cleanup has been done
+ * or not. In the worst case it loops once more.
+ */
+ tsk->flags |= PF_EXITPIDONE;
if (tsk->io_context)
exit_io_context();
static int eligible_child(pid_t pid, int options, struct task_struct *p)
{
+ int err;
+
if (pid > 0) {
if (p->pid != pid)
return 0;
if (delay_group_leader(p))
return 2;
- if (security_task_wait(p))
- return 0;
+ err = security_task_wait(p);
+ if (err)
+ return err;
return 1;
}
p->nvcsw + sig->nvcsw + sig->cnvcsw;
psig->cnivcsw +=
p->nivcsw + sig->nivcsw + sig->cnivcsw;
+ psig->cinblock +=
+ task_io_get_inblock(p) +
+ sig->inblock + sig->cinblock;
+ psig->coublock +=
+ task_io_get_oublock(p) +
+ sig->oublock + sig->coublock;
spin_unlock_irq(&p->parent->sighand->siglock);
}
DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
int flag, retval;
+ int allowed, denied;
add_wait_queue(¤t->signal->wait_chldexit,&wait);
repeat:
* match our criteria, even if we are not able to reap it yet.
*/
flag = 0;
+ allowed = denied = 0;
current->state = TASK_INTERRUPTIBLE;
read_lock(&tasklist_lock);
tsk = current;
if (!ret)
continue;
+ if (unlikely(ret < 0)) {
+ denied = ret;
+ continue;
+ }
+ allowed = 1;
+
switch (p->state) {
case TASK_TRACED:
/*
goto repeat;
}
retval = -ECHILD;
+ if (unlikely(denied) && !allowed)
+ retval = denied;
end:
current->state = TASK_RUNNING;
remove_wait_queue(¤t->signal->wait_chldexit,&wait);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff