#include <linux/taskstats_kern.h>
#include <linux/delayacct.h>
#include <linux/freezer.h>
-#include <linux/cpuset.h>
+#include <linux/cgroup.h>
#include <linux/syscalls.h>
#include <linux/signal.h>
#include <linux/posix-timers.h>
* If there is any task waiting for the group exit
* then notify it:
*/
- if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count) {
+ if (sig->group_exit_task && atomic_read(&sig->count) == sig->notify_count)
wake_up_process(sig->group_exit_task);
- sig->group_exit_task = NULL;
- }
+
if (tsk == sig->curr_target)
sig->curr_target = next_thread(tsk);
/*
int zap_leader;
repeat:
atomic_dec(&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));
}
write_unlock_irq(&tasklist_lock);
- proc_flush_task(p);
release_thread(p);
call_rcu(&p->rcu, delayed_put_task_struct);
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
if (p == ignored_task
|| p->exit_state
- || is_init(p->real_parent))
+ || is_global_init(p->real_parent))
continue;
if (task_pgrp(p->real_parent) != pgrp &&
task_session(p->real_parent) == task_session(p)) {
struct task_struct *p;
do_each_pid_task(pgrp, PIDTYPE_PGID, p) {
- if (p->state != TASK_STOPPED)
+ if (!task_is_stopped(p))
continue;
retval = 1;
break;
{
struct task_struct *curr = current->group_leader;
- if (process_session(curr) != session) {
+ if (task_session_nr(curr) != session) {
detach_pid(curr, PIDTYPE_SID);
- set_signal_session(curr->signal, session);
+ set_task_session(curr, session);
attach_pid(curr, PIDTYPE_SID, find_pid(session));
}
- if (process_group(curr) != pgrp) {
+ if (task_pgrp_nr(curr) != pgrp) {
detach_pid(curr, PIDTYPE_PGID);
- curr->signal->pgrp = pgrp;
+ set_task_pgrp(curr, pgrp);
attach_pid(curr, PIDTYPE_PGID, find_pid(pgrp));
}
}
current->fs = fs;
atomic_inc(&fs->count);
- exit_task_namespaces(current);
- current->nsproxy = init_task.nsproxy;
- get_task_namespaces(current);
+ if (current->nsproxy != init_task.nsproxy) {
+ get_nsproxy(init_task.nsproxy);
+ switch_task_namespaces(current, init_task.nsproxy);
+ }
- exit_files(current);
+ exit_files(current);
current->files = init_task.files;
atomic_inc(¤t->files->count);
}
EXPORT_SYMBOL(reset_files_struct);
-static inline void __exit_files(struct task_struct *tsk)
+static void __exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
__exit_files(tsk);
}
-static inline void __put_fs_struct(struct fs_struct *fs)
+static 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)) {
__put_fs_struct(fs);
}
-static inline void __exit_fs(struct task_struct *tsk)
+static void __exit_fs(struct task_struct *tsk)
{
struct fs_struct * fs = tsk->fs;
mmput(mm);
}
-static inline void
-choose_new_parent(struct task_struct *p, struct task_struct *reaper)
-{
- /*
- * Make sure we're not reparenting to ourselves and that
- * the parent is not a zombie.
- */
- BUG_ON(p == reaper || reaper->exit_state);
- p->real_parent = reaper;
-}
-
static void
reparent_thread(struct task_struct *p, struct task_struct *father, int traced)
{
p->parent = p->real_parent;
add_parent(p);
- if (p->state == TASK_TRACED) {
+ if (task_is_traced(p)) {
/*
* If it was at a trace stop, turn it into
* a normal stop since it's no longer being
* the child reaper process (ie "init") in our pid
* space.
*/
-static void
-forget_original_parent(struct task_struct *father, struct list_head *to_release)
+static void forget_original_parent(struct task_struct *father)
{
- struct task_struct *p, *reaper = father;
- struct list_head *_p, *_n;
+ struct task_struct *p, *n, *reaper = father;
+ struct list_head ptrace_dead;
+
+ INIT_LIST_HEAD(&ptrace_dead);
+
+ write_lock_irq(&tasklist_lock);
do {
reaper = next_thread(reaper);
if (reaper == father) {
- reaper = child_reaper(father);
+ reaper = task_child_reaper(father);
break;
}
- } while (reaper->exit_state);
+ } while (reaper->flags & PF_EXITING);
/*
* There are only two places where our children can be:
*
* Search them and reparent children.
*/
- list_for_each_safe(_p, _n, &father->children) {
+ list_for_each_entry_safe(p, n, &father->children, sibling) {
int ptrace;
- p = list_entry(_p, struct task_struct, sibling);
ptrace = p->ptrace;
if (father == p->real_parent) {
/* reparent with a reaper, real father it's us */
- choose_new_parent(p, reaper);
+ p->real_parent = reaper;
reparent_thread(p, father, 0);
} else {
/* reparent ptraced task to its real parent */
* 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, to_release);
+ list_add(&p->ptrace_list, &ptrace_dead);
}
- list_for_each_safe(_p, _n, &father->ptrace_children) {
- p = list_entry(_p, struct task_struct, ptrace_list);
- choose_new_parent(p, reaper);
+
+ list_for_each_entry_safe(p, n, &father->ptrace_children, ptrace_list) {
+ p->real_parent = reaper;
reparent_thread(p, father, 1);
}
+
+ 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);
+ release_task(p);
+ }
+
}
/*
{
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)
* Now we'll wake all the threads in the group just to make
* sure someone gets all the pending signals.
*/
- 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_and_wake(t);
spin_unlock_irq(&tsk->sighand->siglock);
- read_unlock(&tasklist_lock);
}
- write_lock_irq(&tasklist_lock);
-
/*
* This does two things:
*
* as a result of our exiting, and if they have any stopped
* jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2)
*/
+ forget_original_parent(tsk);
+ exit_task_namespaces(tsk);
- INIT_LIST_HEAD(&ptrace_dead);
- forget_original_parent(tsk, &ptrace_dead);
- BUG_ON(!list_empty(&tsk->children));
- BUG_ON(!list_empty(&tsk->ptrace_children));
-
+ write_lock_irq(&tasklist_lock);
/*
* Check to see if any process groups have become orphaned
* as a result of our exiting, and if they have any stopped
* and we were the only connection outside, so our pgrp
* is about to become orphaned.
*/
-
t = tsk->real_parent;
-
+
pgrp = task_pgrp(tsk);
if ((task_pgrp(t) != pgrp) &&
(task_session(t) == task_session(tsk)) &&
/* Let father know we died
*
* Thread signals are configurable, but you aren't going to use
- * that to send signals to arbitary processes.
+ * that to send signals to arbitary processes.
* That stops right now.
*
* If the parent exec id doesn't match the exec id we saved
state = EXIT_DEAD;
tsk->exit_state = state;
- write_unlock_irq(&tasklist_lock);
+ if (thread_group_leader(tsk) &&
+ tsk->signal->notify_count < 0 &&
+ tsk->signal->group_exit_task)
+ wake_up_process(tsk->signal->group_exit_task);
- list_for_each_safe(_p, _n, &ptrace_dead) {
- list_del_init(_p);
- t = list_entry(_p, struct task_struct, ptrace_list);
- release_task(t);
- }
+ write_unlock_irq(&tasklist_lock);
/* If the process is dead, release it - nobody will wait for it */
if (state == EXIT_DEAD)
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);
+}
+
fastcall NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
panic("Aiee, killing interrupt handler!");
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
- 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(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
- current->comm, current->pid,
+ current->comm, task_pid_nr(current),
preempt_count());
acct_update_integrals(tsk);
}
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);
-#if defined(CONFIG_FUTEX) && defined(CONFIG_COMPAT)
+#ifdef CONFIG_COMPAT
if (unlikely(tsk->compat_robust_list))
compat_exit_robust_list(tsk);
+#endif
#endif
if (group_dead)
tty_audit_exit();
__exit_fs(tsk);
check_stack_usage();
exit_thread();
- cpuset_exit(tsk);
+ cgroup_exit(tsk, 1);
exit_keys(tsk);
if (group_dead && tsk->signal->leader)
module_put(tsk->binfmt->module);
proc_exit_connector(tsk);
- exit_task_namespaces(tsk);
exit_notify(tsk);
#ifdef CONFIG_NUMA
mpol_free(tsk->mempolicy);
tsk->mempolicy = NULL;
#endif
+#ifdef CONFIG_FUTEX
/*
* This must happen late, after the PID is not
* hashed anymore:
exit_pi_state_list(tsk);
if (unlikely(current->pi_state_cache))
kfree(current->pi_state_cache);
+#endif
/*
* Make sure we are holding no locks:
*/
static int eligible_child(pid_t pid, int options, struct task_struct *p)
{
int err;
+ struct pid_namespace *ns;
+ ns = current->nsproxy->pid_ns;
if (pid > 0) {
- if (p->pid != pid)
+ if (task_pid_nr_ns(p, ns) != pid)
return 0;
} else if (!pid) {
- if (process_group(p) != process_group(current))
+ if (task_pgrp_nr_ns(p, ns) != task_pgrp_vnr(current))
return 0;
} else if (pid != -1) {
- if (process_group(p) != -pid)
+ if (task_pgrp_nr_ns(p, ns) != -pid)
return 0;
}
int __user *stat_addr, struct rusage __user *ru)
{
unsigned long state;
- int retval;
- int status;
+ int retval, status, traced;
+ struct pid_namespace *ns;
+
+ ns = current->nsproxy->pid_ns;
if (unlikely(noreap)) {
- pid_t pid = p->pid;
+ pid_t pid = task_pid_nr_ns(p, ns);
uid_t uid = p->uid;
int exit_code = p->exit_code;
int why, status;
BUG_ON(state != EXIT_DEAD);
return 0;
}
- if (unlikely(p->exit_signal == -1 && p->ptrace == 0)) {
- /*
- * This can only happen in a race with a ptraced thread
- * dying on another processor.
- */
- return 0;
- }
- if (likely(p->real_parent == p->parent) && likely(p->signal)) {
+ /* traced means p->ptrace, but not vice versa */
+ traced = (p->real_parent != p->parent);
+
+ if (likely(!traced)) {
struct signal_struct *psig;
struct signal_struct *sig;
retval = put_user(status, &infop->si_status);
}
if (!retval && infop)
- retval = put_user(p->pid, &infop->si_pid);
+ retval = put_user(task_pid_nr_ns(p, ns), &infop->si_pid);
if (!retval && infop)
retval = put_user(p->uid, &infop->si_uid);
- if (retval) {
- // TODO: is this safe?
- p->exit_state = EXIT_ZOMBIE;
- return retval;
- }
- retval = p->pid;
- if (p->real_parent != p->parent) {
+ if (!retval)
+ retval = task_pid_nr_ns(p, ns);
+
+ if (traced) {
write_lock_irq(&tasklist_lock);
- /* Double-check with lock held. */
- if (p->real_parent != p->parent) {
- __ptrace_unlink(p);
- // TODO: is this safe?
- p->exit_state = EXIT_ZOMBIE;
- /*
- * If this is not a detached task, notify the parent.
- * If it's still not detached after that, don't release
- * it now.
- */
+ /* We dropped tasklist, ptracer could die and untrace */
+ ptrace_unlink(p);
+ /*
+ * If this is not a detached task, notify the parent.
+ * If it's still not detached after that, don't release
+ * it now.
+ */
+ if (p->exit_signal != -1) {
+ do_notify_parent(p, p->exit_signal);
if (p->exit_signal != -1) {
- do_notify_parent(p, p->exit_signal);
- if (p->exit_signal != -1)
- p = NULL;
+ p->exit_state = EXIT_ZOMBIE;
+ p = NULL;
}
}
write_unlock_irq(&tasklist_lock);
}
if (p != NULL)
release_task(p);
- BUG_ON(!retval);
+
return retval;
}
int __user *stat_addr, struct rusage __user *ru)
{
int retval, exit_code;
+ pid_t pid;
if (!p->exit_code)
return 0;
if (delayed_group_leader && !(p->ptrace & PT_PTRACED) &&
- p->signal && p->signal->group_stop_count > 0)
+ 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.
* keep holding onto the tasklist_lock while we call getrusage and
* possibly take page faults for user memory.
*/
+ pid = task_pid_nr_ns(p, current->nsproxy->pid_ns);
get_task_struct(p);
read_unlock(&tasklist_lock);
if (unlikely(noreap)) {
- pid_t pid = p->pid;
uid_t uid = p->uid;
int why = (p->ptrace & PT_PTRACED) ? CLD_TRAPPED : CLD_STOPPED;
exit_code = p->exit_code;
- if (unlikely(!exit_code) ||
- unlikely(p->state & TASK_TRACED))
+ if (unlikely(!exit_code) || unlikely(p->exit_state))
goto bail_ref;
return wait_noreap_copyout(p, pid, uid,
- why, (exit_code << 8) | 0x7f,
+ why, exit_code,
infop, ru);
}
if (!retval && infop)
retval = put_user(exit_code, &infop->si_status);
if (!retval && infop)
- retval = put_user(p->pid, &infop->si_pid);
+ retval = put_user(pid, &infop->si_pid);
if (!retval && infop)
retval = put_user(p->uid, &infop->si_uid);
if (!retval)
- retval = p->pid;
+ retval = pid;
put_task_struct(p);
BUG_ON(!retval);
int retval;
pid_t pid;
uid_t uid;
-
- if (unlikely(!p->signal))
- return 0;
+ struct pid_namespace *ns;
if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
return 0;
p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
spin_unlock_irq(&p->sighand->siglock);
- pid = p->pid;
+ ns = current->nsproxy->pid_ns;
+ pid = task_pid_nr_ns(p, ns);
uid = p->uid;
get_task_struct(p);
read_unlock(&tasklist_lock);
if (!retval && stat_addr)
retval = put_user(0xffff, stat_addr);
if (!retval)
- retval = p->pid;
+ retval = task_pid_nr_ns(p, ns);
} else {
retval = wait_noreap_copyout(p, pid, uid,
CLD_CONTINUED, SIGCONT,
tsk = current;
do {
struct task_struct *p;
- struct list_head *_p;
int ret;
- list_for_each(_p,&tsk->children) {
- p = list_entry(_p, struct task_struct, sibling);
-
+ list_for_each_entry(p, &tsk->children, sibling) {
ret = eligible_child(pid, options, p);
if (!ret)
continue;
}
allowed = 1;
- switch (p->state) {
- case TASK_TRACED:
- /*
- * When we hit the race with PTRACE_ATTACH,
- * we will not report this child. But the
- * race means it has not yet been moved to
- * our ptrace_children list, so we need to
- * set the flag here to avoid a spurious ECHILD
- * when the race happens with the only child.
- */
- flag = 1;
- if (!my_ptrace_child(p))
- continue;
- /*FALLTHROUGH*/
- case TASK_STOPPED:
+ if (task_is_stopped_or_traced(p)) {
/*
* It's stopped now, so it might later
* continue, exit, or stop again.
+ *
+ * When we hit the race with PTRACE_ATTACH, we
+ * will not report this child. But the race
+ * means it has not yet been moved to our
+ * ptrace_children list, so we need to set the
+ * flag here to avoid a spurious ECHILD when
+ * the race happens with the only child.
*/
flag = 1;
- if (!(options & WUNTRACED) &&
- !my_ptrace_child(p))
- continue;
+
+ if (!my_ptrace_child(p)) {
+ if (task_is_traced(p))
+ continue;
+ if (!(options & WUNTRACED))
+ continue;
+ }
+
retval = wait_task_stopped(p, ret == 2,
- (options & WNOWAIT),
- infop,
- stat_addr, ru);
+ (options & WNOWAIT), infop,
+ stat_addr, ru);
if (retval == -EAGAIN)
goto repeat;
if (retval != 0) /* He released the lock. */
goto end;
- break;
- default:
- // case EXIT_DEAD:
- if (p->exit_state == EXIT_DEAD)
+ } else if (p->exit_state == EXIT_DEAD) {
+ continue;
+ } else if (p->exit_state == EXIT_ZOMBIE) {
+ /*
+ * Eligible but we cannot release it yet:
+ */
+ if (ret == 2)
+ goto check_continued;
+ if (!likely(options & WEXITED))
continue;
- // case EXIT_ZOMBIE:
- if (p->exit_state == EXIT_ZOMBIE) {
- /*
- * Eligible but we cannot release
- * it yet:
- */
- if (ret == 2)
- goto check_continued;
- if (!likely(options & WEXITED))
- continue;
- retval = wait_task_zombie(
- p, (options & WNOWAIT),
- infop, stat_addr, ru);
- /* He released the lock. */
- if (retval != 0)
- goto end;
- break;
- }
+ retval = wait_task_zombie(p,
+ (options & WNOWAIT), infop,
+ stat_addr, ru);
+ /* He released the lock. */
+ if (retval != 0)
+ goto end;
+ } else {
check_continued:
/*
* It's running now, so it might later
flag = 1;
if (!unlikely(options & WCONTINUED))
continue;
- retval = wait_task_continued(
- p, (options & WNOWAIT),
- infop, stat_addr, ru);
+ retval = wait_task_continued(p,
+ (options & WNOWAIT), infop,
+ stat_addr, ru);
if (retval != 0) /* He released the lock. */
goto end;
- break;
}
}
if (!flag) {
- list_for_each(_p, &tsk->ptrace_children) {
- p = list_entry(_p, struct task_struct,
- ptrace_list);
+ list_for_each_entry(p, &tsk->ptrace_children,
+ ptrace_list) {
if (!eligible_child(pid, options, p))
continue;
flag = 1;