#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/personality.h>
#include <linux/tty.h>
-#include <linux/namespace.h>
+#include <linux/mnt_namespace.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/binfmts.h>
+#include <linux/nsproxy.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/cpuset.h>
#include <linux/syscalls.h>
#include <linux/signal.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 <asm/uaccess.h>
#include <asm/unistd.h>
#include <asm/mmu_context.h>
extern void sem_exit (void);
-extern struct task_struct *child_reaper;
static void exit_mm(struct task_struct * tsk);
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. */
}
flush_sigqueue(&tsk->pending);
if (sig) {
flush_sigqueue(&sig->shared_pending);
+ taskstats_tgid_free(sig);
__cleanup_signal(sig);
}
}
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 = -1;
+ struct pid *sid = NULL;
+
+ p = pid_task(pgrp, PIDTYPE_PGID);
+ if (p == NULL)
+ p = pid_task(pgrp, PIDTYPE_PID);
+ if (p != NULL)
+ sid = task_session(p);
- read_lock(&tasklist_lock);
- do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
- if (p->signal->session > 0) {
- sid = p->signal->session;
- goto out;
- }
- } while_each_task_pid(pgrp, PIDTYPE_PGID, p);
- p = find_task_by_pid(pgrp);
- if (p)
- sid = p->signal->session;
-out:
- read_unlock(&tasklist_lock);
-
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
- || p->real_parent->pid == 1)
+ || is_init(p->real_parent))
continue;
- if (process_group(p->real_parent) != pgrp
- && p->real_parent->signal->session == p->signal->session) {
+ 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;
-
- /* If p is stopped by a debugger on a signal that won't
- stop it, then don't count p as stopped. This isn't
- perfect but it's a good approximation. */
- if (unlikely (p->ptrace)
- && p->exit_code != SIGSTOP
- && p->exit_code != SIGTSTP
- && p->exit_code != SIGTTOU
- && p->exit_code != SIGTTIN)
- 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.
+ * 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->real_parent = child_reaper;
+ 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 ((current->policy == SCHED_NORMAL ||
- current->policy == SCHED_BATCH)
- && (task_nice(current) < 0))
+ if (task_nice(current) < 0)
set_user_nice(current, 0);
/* cpus_allowed? */
/* rt_priority? */
{
struct task_struct *curr = current->group_leader;
- if (curr->signal->session != session) {
+ if (process_session(curr) != session) {
detach_pid(curr, PIDTYPE_SID);
- curr->signal->session = session;
- attach_pid(curr, PIDTYPE_SID, session);
+ set_signal_session(curr->signal, 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));
}
}
-void set_special_pids(pid_t session, pid_t pgrp)
+static void set_special_pids(pid_t session, pid_t pgrp)
{
write_lock_irq(&tasklist_lock);
__set_special_pids(session, 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;
exit_mm(current);
set_special_pids(1, 1);
- mutex_lock(&tty_mutex);
- current->signal->tty = NULL;
- mutex_unlock(&tty_mutex);
+ proc_clear_tty(current);
/* Block and flush all signals */
sigfillset(&blocked);
fs = init_task.fs;
current->fs = fs;
atomic_inc(&fs->count);
- exit_namespace(current);
- current->namespace = init_task.namespace;
- get_namespace(current->namespace);
+
+ exit_task_namespaces(current);
+ current->nsproxy = init_task.nsproxy;
+ get_task_namespaces(current);
+
exit_files(current);
current->files = init_task.files;
atomic_inc(¤t->files->count);
- reparent_to_init();
+ reparent_to_kthreadd();
}
EXPORT_SYMBOL(daemonize);
for (;;) {
unsigned long set;
i = j * __NFDBITS;
- if (i >= fdt->max_fdset || i >= fdt->max_fds)
+ if (i >= fdt->max_fds)
break;
set = fdt->open_fds->fds_bits[j++];
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;
* you can free files immediately.
*/
fdt = files_fdtable(files);
- if (fdt == &files->fdtab)
- fdt->free_files = files;
- else
+ if (fdt != &files->fdtab)
kmem_cache_free(files_cachep, files);
free_fdtable(fdt);
}
EXPORT_SYMBOL(put_files_struct);
+void reset_files_struct(struct task_struct *tsk, struct files_struct *files)
+{
+ struct files_struct *old;
+
+ old = tsk->files;
+ task_lock(tsk);
+ tsk->files = files;
+ task_unlock(tsk);
+ put_files_struct(old);
+}
+EXPORT_SYMBOL(reset_files_struct);
+
static inline void __exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
static void
reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
{
- /* We don't want people slaying init. */
- if (p->exit_signal != -1)
- p->exit_signal = SIGCHLD;
-
if (p->pdeath_signal)
/* We already hold the tasklist_lock here. */
group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
p->parent = p->real_parent;
add_parent(p);
- /* If we'd notified the old parent about this child's death,
- * also notify the new parent.
- */
- if (p->exit_state == EXIT_ZOMBIE && p->exit_signal != -1 &&
- thread_group_empty(p))
- do_notify_parent(p, p->exit_signal);
- else if (p->state == TASK_TRACED) {
+ if (p->state == TASK_TRACED) {
/*
* If it was at a trace stop, turn it into
* a normal stop since it's no longer being
}
}
+ /* 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)
+ return;
+
+ /* We don't want people slaying init. */
+ if (p->exit_signal != -1)
+ 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))
+ do_notify_parent(p, p->exit_signal);
+
/*
* process group orphan check
* Case ii: Our child is in a different pgrp
* than we are, and it was the only connection
* outside, so the child pgrp is now orphaned.
*/
- if ((process_group(p) != process_group(father)) &&
- (p->signal->session == father->signal->session)) {
- int pgrp = process_group(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);
+ 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_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp);
+ __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp);
}
}
}
* 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 global child reaper process (ie "init")
+ * the child reaper process (ie "init") in our pid
+ * space.
*/
static void
forget_original_parent(struct task_struct *father, struct list_head *to_release)
do {
reaper = next_thread(reaper);
if (reaper == father) {
- reaper = child_reaper;
+ reaper = child_reaper(father);
break;
}
} while (reaper->exit_state);
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)) &&
- (t->signal->session == tsk->signal->session) &&
- 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
panic("Aiee, killing interrupt handler!");
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
- if (unlikely(tsk == child_reaper))
- panic("Attempted to kill init!");
+ if (unlikely(tsk == child_reaper(tsk))) {
+ if (tsk->nsproxy->pid_ns != &init_pid_ns)
+ tsk->nsproxy->pid_ns->child_reaper = init_pid_ns.child_reaper;
+ else
+ panic("Attempted to kill init!");
+ }
+
if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
current->ptrace_message = code;
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);
#endif
if (unlikely(tsk->audit_context))
audit_free(tsk);
+
+ taskstats_exit(tsk, group_dead);
+
exit_mm(tsk);
if (group_dead)
exit_sem(tsk);
__exit_files(tsk);
__exit_fs(tsk);
- exit_namespace(tsk);
exit_thread();
cpuset_exit(tsk);
exit_keys(tsk);
tsk->exit_code = code;
proc_exit_connector(tsk);
+ exit_task_namespaces(tsk);
exit_notify(tsk);
#ifdef CONFIG_NUMA
mpol_free(tsk->mempolicy);
* 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();
if (tsk->splice_pipe)
__free_pipe_info(tsk->splice_pipe);
- /* PF_DEAD causes final put_task_struct after we schedule. */
preempt_disable();
- BUG_ON(tsk->flags & PF_DEAD);
- tsk->flags |= PF_DEAD;
+ /* causes final put_task_struct in finish_task_switch(). */
+ tsk->state = TASK_DEAD;
schedule();
BUG();
/* Avoid "noreturn function does return". */
- for (;;) ;
+ for (;;)
+ cpu_relax(); /* For when BUG is null */
}
EXPORT_SYMBOL_GPL(do_exit);
{
if (comp)
complete(comp);
-
+
do_exit(code);
}
static int eligible_child(pid_t pid, int options, struct task_struct *p)
{
+ int err;
+
if (pid > 0) {
if (p->pid != pid)
return 0;
* Do not consider thread group leaders that are
* in a non-empty thread group:
*/
- if (current->tgid != p->tgid && delay_group_leader(p))
+ 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