* Copyright (C) 1991, 1992 Linus Torvalds
*/
-#include <linux/config.h>
#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/tracehook.h>
+#include <linux/pid_namespace.h>
#include <linux/ptrace.h>
#include <linux/profile.h>
#include <linux/mount.h>
#include <linux/proc_fs.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/posix-timers.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/vs_limit.h>
+#include <linux/vs_context.h>
+#include <linux/vs_network.h>
+#include <linux/vs_pid.h>
+#include <linux/vserver/global.h>
#include <asm/uaccess.h>
+#include <asm/unistd.h>
#include <asm/pgtable.h>
#include <asm/mmu_context.h>
extern void sem_exit (void);
-extern struct task_struct *child_reaper;
-int getrusage(struct task_struct *, int, struct rusage *);
+static void exit_mm(struct task_struct * tsk);
static void __unhash_process(struct task_struct *p)
{
nr_threads--;
- /* tasklist_lock is held, is this sufficient? */
- if (p->vx_info) {
- atomic_dec(&p->vx_info->cacct.nr_threads);
- atomic_dec(&p->vx_info->limit.res[RLIMIT_NPROC]);
- }
detach_pid(p, PIDTYPE_PID);
- detach_pid(p, PIDTYPE_TGID);
if (thread_group_leader(p)) {
detach_pid(p, PIDTYPE_PGID);
detach_pid(p, PIDTYPE_SID);
- if (p->pid)
- __get_cpu_var(process_counts)--;
+
+ list_del_rcu(&p->tasks);
+ __get_cpu_var(process_counts)--;
+ }
+ list_del_rcu(&p->thread_group);
+ remove_parent(p);
+}
+
+/*
+ * This function expects the tasklist_lock write-locked.
+ */
+static void __exit_signal(struct task_struct *tsk)
+{
+ struct signal_struct *sig = tsk->signal;
+ struct sighand_struct *sighand;
+
+ BUG_ON(!sig);
+ BUG_ON(!atomic_read(&sig->count));
+
+ rcu_read_lock();
+ sighand = rcu_dereference(tsk->sighand);
+ spin_lock(&sighand->siglock);
+
+ posix_cpu_timers_exit(tsk);
+ if (atomic_dec_and_test(&sig->count))
+ posix_cpu_timers_exit_group(tsk);
+ else {
+ /*
+ * 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) {
+ wake_up_process(sig->group_exit_task);
+ sig->group_exit_task = NULL;
+ }
+ if (tsk == sig->curr_target)
+ sig->curr_target = next_thread(tsk);
+ /*
+ * Accumulate here the counters for all threads but the
+ * group leader as they die, so they can be added into
+ * the process-wide totals when those are taken.
+ * The group leader stays around as a zombie as long
+ * as there are other threads. When it gets reaped,
+ * the exit.c code will add its counts into these totals.
+ * 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->min_flt += tsk->min_flt;
+ sig->maj_flt += tsk->maj_flt;
+ sig->nvcsw += tsk->nvcsw;
+ sig->nivcsw += tsk->nivcsw;
+ sig->sched_time += tsk->sched_time;
+ sig = NULL; /* Marker for below. */
+ }
+
+ __unhash_process(tsk);
+
+ 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);
+ __cleanup_signal(sig);
}
+}
- REMOVE_LINKS(p);
+static void delayed_put_task_struct(struct rcu_head *rhp)
+{
+ put_task_struct(container_of(rhp, struct task_struct, rcu));
}
void release_task(struct task_struct * p)
{
+ struct task_struct *leader;
int zap_leader;
- task_t *leader;
- struct dentry *proc_dentry;
-
-repeat:
- BUG_ON(p->state < TASK_ZOMBIE);
-
+ int inhibited_leader;
+repeat:
+ tracehook_release_task(p);
atomic_dec(&p->user->processes);
- spin_lock(&p->proc_lock);
- proc_dentry = proc_pid_unhash(p);
write_lock_irq(&tasklist_lock);
- if (unlikely(p->ptrace))
- __ptrace_unlink(p);
- BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
+ BUG_ON(tracehook_check_released(p));
__exit_signal(p);
- __exit_sighand(p);
- __unhash_process(p);
/*
* If we are the last non-leader member of the thread
* group leader's parent process. (if it wants notification.)
*/
zap_leader = 0;
+ inhibited_leader = 0;
leader = p->group_leader;
- if (leader != p && thread_group_empty(leader) && leader->state == TASK_ZOMBIE) {
+ if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) {
BUG_ON(leader->exit_signal == -1);
- do_notify_parent(leader, leader->exit_signal);
+ if (tracehook_inhibit_wait_zombie(leader))
+ inhibited_leader = 1;
+ else
+ do_notify_parent(leader, leader->exit_signal);
/*
* If we were the last child thread and the leader has
* exited already, and the leader's parent ignores SIGCHLD,
zap_leader = (leader->exit_signal == -1);
}
- p->parent->cutime += p->utime + p->cutime;
- p->parent->cstime += p->stime + p->cstime;
- p->parent->cmin_flt += p->min_flt + p->cmin_flt;
- p->parent->cmaj_flt += p->maj_flt + p->cmaj_flt;
- p->parent->cnvcsw += p->nvcsw + p->cnvcsw;
- p->parent->cnivcsw += p->nivcsw + p->cnivcsw;
sched_exit(p);
write_unlock_irq(&tasklist_lock);
- spin_unlock(&p->proc_lock);
- proc_pid_flush(proc_dentry);
+ proc_flush_task(p);
release_thread(p);
- put_task_struct(p);
+ call_rcu(&p->rcu, delayed_put_task_struct);
p = leader;
if (unlikely(zap_leader))
goto repeat;
-}
-/* we are using it only for SMP init */
-
-void unhash_process(struct task_struct *p)
-{
- struct dentry *proc_dentry;
-
- spin_lock(&p->proc_lock);
- proc_dentry = proc_pid_unhash(p);
- write_lock_irq(&tasklist_lock);
- __unhash_process(p);
- write_unlock_irq(&tasklist_lock);
- spin_unlock(&p->proc_lock);
- proc_pid_flush(proc_dentry);
+ /*
+ * If tracing usurps normal reaping of the leader, tracing needs
+ * to be notified it would normally be reapable now.
+ */
+ if (unlikely(inhibited_leader))
+ tracehook_report_delayed_group_leader(leader);
}
/*
int session_of_pgrp(int pgrp)
{
struct task_struct *p;
- struct list_head *l;
- struct pid *pid;
- int sid = -1;
+ int sid = 0;
read_lock(&tasklist_lock);
- for_each_task_pid(pgrp, PIDTYPE_PGID, p, l, pid)
- if (p->signal->session > 0) {
- sid = p->signal->session;
- goto out;
- }
- p = find_task_by_pid(pgrp);
- if (p)
- sid = p->signal->session;
-out:
+
+ p = find_task_by_pid_type(PIDTYPE_PGID, pgrp);
+ if (p == NULL)
+ p = find_task_by_pid(pgrp);
+ if (p != NULL)
+ sid = process_session(p);
+
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, task_t *ignored_task)
+static int will_become_orphaned_pgrp(int pgrp, struct task_struct *ignored_task)
{
struct task_struct *p;
- struct list_head *l;
- struct pid *pid;
int ret = 1;
- for_each_task_pid(pgrp, PIDTYPE_PGID, p, l, pid) {
+ do_each_task_pid(pgrp, PIDTYPE_PGID, p) {
if (p == ignored_task
- || p->state >= TASK_ZOMBIE
- || p->real_parent->pid == 1)
+ || p->exit_state
+ || is_init(p->parent))
continue;
- if (process_group(p->real_parent) != pgrp
- && p->real_parent->signal->session == p->signal->session) {
+ if (process_group(p->parent) != pgrp &&
+ process_session(p->parent) == process_session(p)) {
ret = 0;
break;
}
- }
+ } while_each_task_pid(pgrp, PIDTYPE_PGID, p);
return ret; /* (sighing) "Often!" */
}
return retval;
}
-static inline int has_stopped_jobs(int pgrp)
+static int has_stopped_jobs(int pgrp)
{
int retval = 0;
struct task_struct *p;
- struct list_head *l;
- struct pid *pid;
- for_each_task_pid(pgrp, PIDTYPE_PGID, p, l, pid) {
+ do_each_task_pid(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);
return retval;
}
/**
- * reparent_to_init() - Reparent the calling kernel thread to the init task.
+ * reparent_to_init - Reparent the calling kernel thread to the init task
+ * of the pid space that the thread belongs to.
*
* 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
*
* NOTE that reparent_to_init() gives the caller full capabilities.
*/
-void reparent_to_init(void)
+static void reparent_to_init(void)
{
write_lock_irq(&tasklist_lock);
- ptrace_unlink(current);
/* Reparent to init */
- REMOVE_LINKS(current);
- /* FIXME handle vchild_reaper/initpid */
- current->parent = child_reaper;
- current->real_parent = child_reaper;
- SET_LINKS(current);
+ remove_parent(current);
+ current->parent = child_reaper(current);
+ add_parent(current);
/* Set the exit signal to SIGCHLD so we signal init on exit */
current->exit_signal = SIGCHLD;
- if ((current->policy == SCHED_NORMAL) && (task_nice(current) < 0))
+ if (!has_rt_policy(current) && (task_nice(current) < 0))
set_user_nice(current, 0);
/* cpus_allowed? */
/* rt_priority? */
/* signals? */
security_task_reparent_to_init(current);
- memcpy(current->rlim, init_task.rlim, sizeof(*(current->rlim)));
+ memcpy(current->signal->rlim, init_task.signal->rlim,
+ sizeof(current->signal->rlim));
atomic_inc(&(INIT_USER->__count));
- switch_uid(INIT_USER);
-
write_unlock_irq(&tasklist_lock);
+ switch_uid(INIT_USER);
}
void __set_special_pids(pid_t session, pid_t pgrp)
{
- struct task_struct *curr = current;
+ 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;
+ set_signal_session(curr->signal, session);
attach_pid(curr, PIDTYPE_SID, session);
}
if (process_group(curr) != 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);
*/
int allow_signal(int sig)
{
- if (sig < 1 || sig > _NSIG)
+ if (!valid_signal(sig) || sig < 1)
return -EINVAL;
spin_lock_irq(¤t->sighand->siglock);
Let the signal code know it'll be handled, so
that they don't get converted to SIGKILL or
just silently dropped */
- current->sighand->action[(sig)-1].sa.sa_handler = (void *)2;
+ current->sighand->action[(sig)-1].sa.sa_handler = (void __user *)2;
}
recalc_sigpending();
spin_unlock_irq(¤t->sighand->siglock);
int disallow_signal(int sig)
{
- if (sig < 1 || sig > _NSIG)
+ if (!valid_signal(sig) || sig < 1)
return -EINVAL;
spin_lock_irq(¤t->sighand->siglock);
exit_mm(current);
set_special_pids(1, 1);
- current->signal->tty = NULL;
+ proc_clear_tty(current);
/* Block and flush all signals */
sigfillset(&blocked);
fs = init_task.fs;
current->fs = fs;
atomic_inc(&fs->count);
+
+ 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);
EXPORT_SYMBOL(daemonize);
-static inline void close_files(struct files_struct * files)
+static void close_files(struct files_struct * files)
{
int i, j;
+ struct fdtable *fdt;
j = 0;
+
+ /*
+ * It is safe to dereference the fd table without RCU or
+ * ->file_lock because this is the last reference to the
+ * files structure.
+ */
+ fdt = files_fdtable(files);
for (;;) {
unsigned long set;
i = j * __NFDBITS;
- if (i >= files->max_fdset || i >= files->max_fds)
+ if (i >= fdt->max_fds)
break;
- set = files->open_fds->fds_bits[j++];
+ set = fdt->open_fds->fds_bits[j++];
while (set) {
if (set & 1) {
- struct file * file = xchg(&files->fd[i], NULL);
+ struct file * file = xchg(&fdt->fd[i], NULL);
if (file)
filp_close(file, files);
- vx_openfd_dec(fd);
+ vx_openfd_dec(i);
}
i++;
set >>= 1;
+ cond_resched();
}
}
}
void fastcall put_files_struct(struct files_struct *files)
{
+ struct fdtable *fdt;
+
if (atomic_dec_and_test(&files->count)) {
close_files(files);
/*
* Free the fd and fdset arrays if we expanded them.
+ * If the fdtable was embedded, pass files for freeing
+ * at the end of the RCU grace period. Otherwise,
+ * you can free files immediately.
*/
- if (files->fd != &files->fd_array[0])
- free_fd_array(files->fd, files->max_fds);
- if (files->max_fdset > __FD_SETSIZE) {
- free_fdset(files->open_fds, files->max_fdset);
- free_fdset(files->close_on_exec, files->max_fdset);
- }
- kmem_cache_free(files_cachep, files);
+ fdt = files_fdtable(files);
+ 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;
dput(fs->altroot);
mntput(fs->altrootmnt);
}
+ atomic_dec(&vs_global_fs);
kmem_cache_free(fs_cachep, fs);
}
}
* Turn us into a lazy TLB process if we
* aren't already..
*/
-static inline void __exit_mm(struct task_struct * tsk)
+static void exit_mm(struct task_struct * tsk)
{
struct mm_struct *mm = tsk->mm;
down_read(&mm->mmap_sem);
}
atomic_inc(&mm->mm_count);
- if (mm != tsk->active_mm) BUG();
+ BUG_ON(mm != tsk->active_mm);
/* more a memory barrier than a real lock */
task_lock(tsk);
tsk->mm = NULL;
mmput(mm);
}
-void exit_mm(struct task_struct *tsk)
+static inline void
+choose_new_parent(struct task_struct *p, struct task_struct *reaper)
{
- __exit_mm(tsk);
-}
+ /* check for reaper context */
+ vxwprintk((p->xid != reaper->xid) && (reaper != child_reaper(p)),
+ "rogue reaper: %p[%d,#%u] <> %p[%d,#%u]",
+ p, p->pid, p->xid, reaper, reaper->pid, reaper->xid);
-EXPORT_SYMBOL(exit_mm);
+ if (p == reaper)
+ reaper = vx_child_reaper(p);
-static inline void choose_new_parent(task_t *p, task_t *reaper, task_t *child_reaper)
-{
/*
* Make sure we're not reparenting to ourselves and that
* the parent is not a zombie.
*/
- if (p == reaper || reaper->state >= TASK_ZOMBIE)
- p->real_parent = child_reaper;
- else
- p->real_parent = reaper;
- if (p->parent == p->real_parent)
- BUG();
+ BUG_ON(p == reaper || reaper->exit_state);
+ p->parent = reaper;
}
-static inline void reparent_thread(task_t *p, task_t *father, int traced)
+static void
+reparent_thread(struct task_struct *p, struct task_struct *father)
{
- /* We don't want people slaying init. */
- if (p->exit_signal != -1)
- p->exit_signal = SIGCHLD;
- p->self_exec_id++;
-
if (p->pdeath_signal)
/* We already hold the tasklist_lock here. */
- group_send_sig_info(p->pdeath_signal, (void *) 0, p);
+ group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
/* 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;
- list_del_init(&p->sibling);
- p->parent = p->real_parent;
- list_add_tail(&p->sibling, &p->parent->children);
+ list_move_tail(&p->sibling, &p->parent->children);
- /* If we'd notified the old parent about this child's death,
- * also notify the new parent.
- */
- if (p->state == TASK_ZOMBIE && p->exit_signal != -1 &&
- thread_group_empty(p))
- do_notify_parent(p, p->exit_signal);
- }
+ /* If this is a threaded reparent there is no need to
+ * notify anyone anything has happened.
+ */
+ if (p->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 (!tracehook_inhibit_wait_zombie(p) &&
+ p->exit_state == EXIT_ZOMBIE &&
+ p->exit_signal != -1 && thread_group_empty(p))
+ do_notify_parent(p, p->exit_signal);
/*
* process group orphan check
* outside, so the child pgrp is now orphaned.
*/
if ((process_group(p) != process_group(father)) &&
- (p->signal->session == father->signal->session)) {
+ (process_session(p) == process_session(father))) {
int pgrp = process_group(p);
- if (will_become_orphaned_pgrp(pgrp, NULL) && has_stopped_jobs(pgrp)) {
- __kill_pg_info(SIGHUP, (void *)1, pgrp);
- __kill_pg_info(SIGCONT, (void *)1, pgrp);
+ 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);
}
}
}
* 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 inline void forget_original_parent(struct task_struct * father)
+static void
+forget_original_parent(struct task_struct *father)
{
struct task_struct *p, *reaper = father;
struct list_head *_p, *_n;
- /* FIXME handle vchild_reaper/initpid */
- reaper = father->group_leader;
- if (reaper == father)
- reaper = child_reaper;
+ do {
+ reaper = next_thread(reaper);
+ if (reaper == father) {
+ // reaper = child_reaper(father);
+ reaper = vx_child_reaper(father);
+ break;
+ }
+ } while (reaper->exit_state);
- /*
- * 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_safe(_p, _n, &father->children) {
- p = list_entry(_p,struct task_struct,sibling);
- if (father == p->real_parent) {
- choose_new_parent(p, reaper, child_reaper);
- reparent_thread(p, father, 0);
- } else {
- ptrace_unlink (p);
- if (p->state == TASK_ZOMBIE && p->exit_signal != -1 &&
- thread_group_empty(p))
- do_notify_parent(p, p->exit_signal);
- }
- }
- list_for_each_safe(_p, _n, &father->ptrace_children) {
- p = list_entry(_p,struct task_struct,ptrace_list);
- choose_new_parent(p, reaper, child_reaper);
- reparent_thread(p, father, 1);
+ p = list_entry(_p, struct task_struct, sibling);
+ choose_new_parent(p, reaper);
+ reparent_thread(p, father);
}
}
{
int state;
struct task_struct *t;
+ int noreap;
+ void *cookie;
- if (signal_pending(tsk) && !tsk->signal->group_exit
+ if (signal_pending(tsk) && !(tsk->signal->flags & SIGNAL_GROUP_EXIT)
&& !thread_group_empty(tsk)) {
/*
* This occurs when there was a race between our exit
* is about to become orphaned.
*/
- t = tsk->real_parent;
+ t = tsk->parent;
if ((process_group(t) != process_group(tsk)) &&
- (t->signal->session == tsk->signal->session) &&
+ (process_session(t) == process_session(tsk)) &&
will_become_orphaned_pgrp(process_group(tsk), tsk) &&
has_stopped_jobs(process_group(tsk))) {
- __kill_pg_info(SIGHUP, (void *)1, process_group(tsk));
- __kill_pg_info(SIGCONT, (void *)1, process_group(tsk));
+ __kill_pg_info(SIGHUP, SEND_SIG_PRIV, process_group(tsk));
+ __kill_pg_info(SIGCONT, SEND_SIG_PRIV, process_group(tsk));
}
/* Let father know we died
&& !capable(CAP_KILL))
tsk->exit_signal = SIGCHLD;
+ if (!tracehook_notify_death(tsk, &noreap, &cookie)
+ && tsk->exit_signal != -1 && thread_group_empty(tsk))
+ do_notify_parent(tsk, tsk->exit_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 && !noreap)
+ state = EXIT_DEAD;
+ tsk->exit_state = state;
- state = TASK_ZOMBIE;
- if (tsk->exit_signal == -1 && tsk->ptrace == 0)
- state = TASK_DEAD;
- tsk->state = state;
- tsk->flags |= PF_DEAD;
+ write_unlock_irq(&tasklist_lock);
- /*
- * In the preemption case it must be impossible for the task
- * to get runnable again, so use "_raw_" unlock to keep
- * preempt_count elevated until we schedule().
- *
- * To avoid deadlock on SMP, interrupts must be unmasked. If we
- * don't, subsequently called functions (e.g, wait_task_inactive()
- * via release_task()) will spin, with interrupt flags
- * unwittingly blocked, until the other task sleeps. That task
- * may itself be waiting for smp_call_function() to answer and
- * complete, and with interrupts blocked that will never happen.
- */
- _raw_write_unlock(&tasklist_lock);
- local_irq_enable();
+ tracehook_report_death(tsk, state, cookie);
/* If the process is dead, release it - nobody will wait for it */
- if (state == TASK_DEAD)
+ if (state == EXIT_DEAD)
release_task(tsk);
-
}
-asmlinkage NORET_TYPE void do_exit(long code)
+fastcall NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
+ int group_dead;
+
+ profile_task_exit(tsk);
+
+ WARN_ON(atomic_read(&tsk->fs_excl));
if (unlikely(in_interrupt()))
panic("Aiee, killing interrupt handler!");
if (unlikely(!tsk->pid))
panic("Attempted to kill the idle task!");
- if (unlikely(tsk->pid == 1))
- panic("Attempted to kill init!");
- if (tsk->io_context)
- exit_io_context();
+ 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!");
+ }
+
+
+ tracehook_report_exit(&code);
+
+ /*
+ * We're taking recursive faults here in do_exit. Safest is to just
+ * leave this task alone and wait for reboot.
+ */
+ if (unlikely(tsk->flags & PF_EXITING)) {
+ printk(KERN_ALERT
+ "Fixing recursive fault but reboot is needed!\n");
+ if (tsk->io_context)
+ exit_io_context();
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ schedule();
+ }
+
tsk->flags |= PF_EXITING;
- del_timer_sync(&tsk->real_timer);
+
+ ptrace_exit(tsk);
if (unlikely(in_atomic()))
printk(KERN_INFO "note: %s[%d] exited with preempt_count %d\n",
current->comm, current->pid,
preempt_count());
- profile_exit_task(tsk);
-
- if (unlikely(current->ptrace & PT_TRACE_EXIT)) {
- current->ptrace_message = code;
- ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
+ 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) {
+ hrtimer_cancel(&tsk->signal->real_timer);
+ exit_itimers(tsk->signal);
+ }
+ acct_collect(code, group_dead);
+ if (unlikely(tsk->robust_list))
+ exit_robust_list(tsk);
+#if defined(CONFIG_FUTEX) && defined(CONFIG_COMPAT)
+ if (unlikely(tsk->compat_robust_list))
+ compat_exit_robust_list(tsk);
+#endif
+ if (unlikely(tsk->audit_context))
+ audit_free(tsk);
- acct_process(code);
- __exit_mm(tsk);
+ taskstats_exit(tsk, group_dead);
+ exit_mm(tsk);
+
+ if (group_dead)
+ acct_process();
exit_sem(tsk);
__exit_files(tsk);
__exit_fs(tsk);
- exit_namespace(tsk);
exit_thread();
+ cpuset_exit(tsk);
+ exit_keys(tsk);
- if (tsk->signal->leader)
+ if (group_dead && tsk->signal->leader)
disassociate_ctty(1);
- module_put(tsk->thread_info->exec_domain->module);
+ module_put(task_thread_info(tsk)->exec_domain->module);
if (tsk->binfmt)
module_put(tsk->binfmt->module);
tsk->exit_code = code;
+ proc_exit_connector(tsk);
+ exit_task_namespaces(tsk);
+ // ns = exit_task_namespaces_early(tsk);
+ /* needs to stay before exit_notify() */
+ exit_vx_info_early(tsk, code);
exit_notify(tsk);
+ // exit_task_namespaces(tsk, ns);
+#ifdef CONFIG_NUMA
+ mpol_free(tsk->mempolicy);
+ tsk->mempolicy = NULL;
+#endif
+ /*
+ * This must happen late, after the PID is not
+ * hashed anymore:
+ */
+ if (unlikely(!list_empty(&tsk->pi_state_list)))
+ exit_pi_state_list(tsk);
+ if (unlikely(current->pi_state_cache))
+ kfree(current->pi_state_cache);
+ /*
+ * Make sure we are holding no locks:
+ */
+ debug_check_no_locks_held(tsk);
+
+ if (tsk->io_context)
+ exit_io_context();
+
+ if (tsk->splice_pipe)
+ __free_pipe_info(tsk->splice_pipe);
+
+ /* needs to stay after exit_notify() */
+ exit_vx_info(tsk, code);
+ exit_nx_info(tsk);
+
+ preempt_disable();
+ /* 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);
+
NORET_TYPE void complete_and_exit(struct completion *comp, long code)
{
if (comp)
complete(comp);
-
+
do_exit(code);
}
do_exit((error_code&0xff)<<8);
}
-task_t fastcall *next_thread(task_t *p)
-{
- struct pid_link *link = p->pids + PIDTYPE_TGID;
- struct list_head *tmp, *head = &link->pidptr->task_list;
-
-#ifdef CONFIG_SMP
- if (!p->sighand)
- BUG();
- if (!spin_is_locked(&p->sighand->siglock) &&
- !rwlock_is_locked(&tasklist_lock))
- BUG();
-#endif
- tmp = link->pid_chain.next;
- if (tmp == head)
- tmp = head->next;
-
- return pid_task(tmp, PIDTYPE_TGID);
-}
-
-EXPORT_SYMBOL(next_thread);
-
/*
* Take down every thread in the group. This is called by fatal signals
* as well as by sys_exit_group (below).
{
BUG_ON(exit_code & 0x80); /* core dumps don't get here */
- if (current->signal->group_exit)
+ if (current->signal->flags & SIGNAL_GROUP_EXIT)
exit_code = current->signal->group_exit_code;
else if (!thread_group_empty(current)) {
struct signal_struct *const sig = current->signal;
struct sighand_struct *const sighand = current->sighand;
- read_lock(&tasklist_lock);
spin_lock_irq(&sighand->siglock);
- if (sig->group_exit)
+ if (sig->flags & SIGNAL_GROUP_EXIT)
/* Another thread got here before we took the lock. */
exit_code = sig->group_exit_code;
else {
- sig->group_exit = 1;
sig->group_exit_code = exit_code;
zap_other_threads(current);
}
spin_unlock_irq(&sighand->siglock);
- read_unlock(&tasklist_lock);
}
do_exit(exit_code);
do_group_exit((error_code & 0xff) << 8);
}
-static int eligible_child(pid_t pid, int options, task_t *p)
+static int eligible_child(pid_t pid, int options, struct task_struct *p)
{
if (pid > 0) {
if (p->pid != pid)
}
/*
- * Do not consider detached threads that are
- * not ptraced:
+ * Do not consider detached threads.
*/
- if (p->exit_signal == -1 && !p->ptrace)
+ if (p->exit_signal == -1)
return 0;
/* Wait for all children (clone and not) if __WALL is set;
* 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 1;
}
+static int wait_noreap_copyout(struct task_struct *p, pid_t pid, uid_t uid,
+ int why, int status,
+ struct siginfo __user *infop,
+ struct rusage __user *rusagep)
+{
+ int retval = rusagep ? getrusage(p, RUSAGE_BOTH, rusagep) : 0;
+
+ put_task_struct(p);
+ if (!retval)
+ retval = put_user(SIGCHLD, &infop->si_signo);
+ if (!retval)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval)
+ retval = put_user((short)why, &infop->si_code);
+ if (!retval)
+ retval = put_user(pid, &infop->si_pid);
+ if (!retval)
+ retval = put_user(uid, &infop->si_uid);
+ if (!retval)
+ retval = put_user(status, &infop->si_status);
+ if (!retval)
+ retval = pid;
+ return retval;
+}
+
/*
- * Handle sys_wait4 work for one task in state TASK_ZOMBIE. We hold
+ * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. 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_zombie(task_t *p, unsigned int *stat_addr, struct rusage *ru)
+static int wait_task_zombie(struct task_struct *p, int noreap,
+ struct siginfo __user *infop,
+ int __user *stat_addr, struct rusage __user *ru)
{
unsigned long state;
int retval;
+ int status;
+
+ if (unlikely(noreap)) {
+ pid_t pid = p->pid;
+ uid_t uid = p->uid;
+ int exit_code = p->exit_code;
+ int why, status;
+
+ if (unlikely(p->exit_state != EXIT_ZOMBIE))
+ return 0;
+ if (unlikely(p->exit_signal == -1))
+ return 0;
+ get_task_struct(p);
+ read_unlock(&tasklist_lock);
+ if ((exit_code & 0x7f) == 0) {
+ why = CLD_EXITED;
+ status = exit_code >> 8;
+ } else {
+ why = (exit_code & 0x80) ? CLD_DUMPED : CLD_KILLED;
+ status = exit_code & 0x7f;
+ }
+ return wait_noreap_copyout(p, pid, uid, why,
+ status, infop, ru);
+ }
/*
* Try to move the task's state to DEAD
* only one thread is allowed to do this:
*/
- state = xchg(&p->state, TASK_DEAD);
- if (state != TASK_ZOMBIE) {
- BUG_ON(state != TASK_DEAD);
+ state = xchg(&p->exit_state, EXIT_DEAD);
+ if (state != EXIT_ZOMBIE) {
+ BUG_ON(state != EXIT_DEAD);
return 0;
}
- if (unlikely(p->exit_signal == -1 && p->ptrace == 0))
+ BUG_ON(p->exit_signal == -1);
+
+ if (likely(p->signal)) {
+ struct signal_struct *psig;
+ struct signal_struct *sig;
+
/*
- * This can only happen in a race with a ptraced thread
- * dying on another processor.
+ * The resource counters for the group leader are in its
+ * own task_struct. Those for dead threads in the group
+ * are in its signal_struct, as are those for the child
+ * processes it has previously reaped. All these
+ * accumulate in the parent's signal_struct c* fields.
+ *
+ * We don't bother to take a lock here to protect these
+ * p->signal fields, because they are only touched by
+ * __exit_signal, which runs with tasklist_lock
+ * write-locked anyway, and so is excluded here. We do
+ * 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.
*/
- return 0;
+ 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)));
+ psig->cstime =
+ cputime_add(psig->cstime,
+ cputime_add(p->stime,
+ cputime_add(sig->stime,
+ sig->cstime)));
+ psig->cmin_flt +=
+ p->min_flt + sig->min_flt + sig->cmin_flt;
+ psig->cmaj_flt +=
+ p->maj_flt + sig->maj_flt + sig->cmaj_flt;
+ psig->cnvcsw +=
+ p->nvcsw + sig->nvcsw + sig->cnvcsw;
+ psig->cnivcsw +=
+ p->nivcsw + sig->nivcsw + sig->cnivcsw;
+ spin_unlock_irq(&p->parent->sighand->siglock);
+ }
/*
* Now we are sure this task is interesting, and no other
- * thread can reap it because we set its state to TASK_DEAD.
+ * thread can reap it because we set its state to EXIT_DEAD.
*/
read_unlock(&tasklist_lock);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
- if (!retval && stat_addr) {
- if (p->signal->group_exit)
- retval = put_user(p->signal->group_exit_code, stat_addr);
- else
- retval = put_user(p->exit_code, stat_addr);
+ status = (p->signal->flags & SIGNAL_GROUP_EXIT)
+ ? p->signal->group_exit_code : p->exit_code;
+ if (!retval && stat_addr)
+ retval = put_user(status, stat_addr);
+ if (!retval && infop)
+ retval = put_user(SIGCHLD, &infop->si_signo);
+ if (!retval && infop)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval && infop) {
+ int why;
+
+ if ((status & 0x7f) == 0) {
+ why = CLD_EXITED;
+ status >>= 8;
+ } else {
+ why = (status & 0x80) ? CLD_DUMPED : CLD_KILLED;
+ status &= 0x7f;
+ }
+ retval = put_user((short)why, &infop->si_code);
+ if (!retval)
+ retval = put_user(status, &infop->si_status);
}
+ if (!retval && infop)
+ retval = put_user(p->pid, &infop->si_pid);
+ if (!retval && infop)
+ retval = put_user(p->uid, &infop->si_uid);
if (retval) {
- p->state = TASK_ZOMBIE;
+ // TODO: is this safe?
+ p->exit_state = EXIT_ZOMBIE;
return retval;
}
retval = p->pid;
- if (p->real_parent != p->parent) {
- write_lock_irq(&tasklist_lock);
- /* Double-check with lock held. */
- if (p->real_parent != p->parent) {
- __ptrace_unlink(p);
- p->state = TASK_ZOMBIE;
- /* If this is a detached thread, this is where it goes away. */
- if (p->exit_signal == -1) {
- /* release_task takes the lock itself. */
- write_unlock_irq(&tasklist_lock);
- release_task (p);
- }
- else {
- do_notify_parent(p, p->exit_signal);
- write_unlock_irq(&tasklist_lock);
- }
- p = NULL;
- }
- else
- write_unlock_irq(&tasklist_lock);
- }
- if (p != NULL)
- release_task(p);
+ release_task(p);
+
BUG_ON(!retval);
return retval;
}
* 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(task_t *p, int delayed_group_leader,
- unsigned int *stat_addr, struct rusage *ru)
+static int wait_task_stopped(struct task_struct *p, int delayed_group_leader,
+ int noreap, struct siginfo __user *infop,
+ int __user *stat_addr, struct rusage __user *ru)
{
int retval, exit_code;
if (!p->exit_code)
return 0;
- if (delayed_group_leader && !(p->ptrace & PT_PTRACED) &&
+ if (delayed_group_leader &&
p->signal && p->signal->group_stop_count > 0)
/*
* A group stop is in progress and this is the group leader.
*/
get_task_struct(p);
read_unlock(&tasklist_lock);
+
+ if (unlikely(noreap)) {
+ pid_t pid = p->pid;
+ uid_t uid = p->uid;
+
+ exit_code = p->exit_code;
+ if (unlikely(!exit_code) ||
+ unlikely(p->state & TASK_TRACED))
+ goto bail_ref;
+ return wait_noreap_copyout(p, pid, uid, CLD_STOPPED,
+ (exit_code << 8) | 0x7f,
+ infop, ru);
+ }
+
write_lock_irq(&tasklist_lock);
/*
* This uses xchg to be atomic with the thread resuming and setting
* it. It must also be done with the write lock held to prevent a
- * race with the TASK_ZOMBIE case.
+ * race with the EXIT_ZOMBIE case.
*/
exit_code = xchg(&p->exit_code, 0);
- if (unlikely(p->state > TASK_STOPPED)) {
+ if (unlikely(p->exit_state)) {
/*
* The task resumed and then died. Let the next iteration
- * catch it in TASK_ZOMBIE. Note that exit_code might
+ * catch it in EXIT_ZOMBIE. Note that exit_code might
* already be zero here if it resumed and did _exit(0).
* The task itself is dead and won't touch exit_code again;
* other processors in this function are locked out.
* resumed, or it resumed and then died.
*/
write_unlock_irq(&tasklist_lock);
+bail_ref:
put_task_struct(p);
- read_lock(&tasklist_lock);
- return 0;
+ /*
+ * We are returning to the wait loop without having successfully
+ * removed the process and having released the lock. We cannot
+ * continue, since the "p" task pointer is potentially stale.
+ *
+ * Return -EAGAIN, and do_wait() will restart the loop from the
+ * beginning. Do _not_ re-acquire the lock.
+ */
+ return -EAGAIN;
}
/* move to end of parent's list to avoid starvation */
remove_parent(p);
- add_parent(p, p->parent);
+ add_parent(p);
write_unlock_irq(&tasklist_lock);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
if (!retval && stat_addr)
retval = put_user((exit_code << 8) | 0x7f, stat_addr);
+ if (!retval && infop)
+ retval = put_user(SIGCHLD, &infop->si_signo);
+ if (!retval && infop)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval && infop)
+ retval = put_user((short)CLD_STOPPED, &infop->si_code);
+ if (!retval && infop)
+ retval = put_user(exit_code, &infop->si_status);
+ if (!retval && infop)
+ retval = put_user(p->pid, &infop->si_pid);
+ if (!retval && infop)
+ retval = put_user(p->uid, &infop->si_uid);
if (!retval)
retval = p->pid;
put_task_struct(p);
return retval;
}
-asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru)
+/*
+ * Handle do_wait work for one task in a live, non-stopped state.
+ * 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_continued(struct task_struct *p, int noreap,
+ struct siginfo __user *infop,
+ int __user *stat_addr, struct rusage __user *ru)
+{
+ int retval;
+ pid_t pid;
+ uid_t uid;
+
+ if (unlikely(!p->signal))
+ return 0;
+
+ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED))
+ return 0;
+
+ spin_lock_irq(&p->sighand->siglock);
+ /* Re-check with the lock held. */
+ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) {
+ spin_unlock_irq(&p->sighand->siglock);
+ return 0;
+ }
+ if (!noreap)
+ p->signal->flags &= ~SIGNAL_STOP_CONTINUED;
+ spin_unlock_irq(&p->sighand->siglock);
+
+ pid = p->pid;
+ uid = p->uid;
+ get_task_struct(p);
+ read_unlock(&tasklist_lock);
+
+ if (!infop) {
+ retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
+ put_task_struct(p);
+ if (!retval && stat_addr)
+ retval = put_user(0xffff, stat_addr);
+ if (!retval)
+ retval = p->pid;
+ } else {
+ retval = wait_noreap_copyout(p, pid, uid,
+ CLD_CONTINUED, SIGCONT,
+ infop, ru);
+ BUG_ON(retval == 0);
+ }
+
+ return retval;
+}
+
+
+static long do_wait(pid_t 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;
- if (options & ~(WNOHANG|WUNTRACED|__WNOTHREAD|__WCLONE|__WALL))
- return -EINVAL;
-
- add_wait_queue(¤t->wait_chldexit,&wait);
+ add_wait_queue(¤t->signal->wait_chldexit,&wait);
repeat:
+ /*
+ * 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 = 0;
current->state = TASK_INTERRUPTIBLE;
read_lock(&tasklist_lock);
int ret;
list_for_each(_p,&tsk->children) {
- p = list_entry(_p,struct task_struct,sibling);
+ p = list_entry(_p, struct task_struct, sibling);
ret = eligible_child(pid, options, p);
if (!ret)
continue;
- flag = 1;
switch (p->state) {
+ case TASK_TRACED:
+ flag = 1;
+ continue;
case TASK_STOPPED:
- if (!(options & WUNTRACED) &&
- !(p->ptrace & PT_PTRACED))
+ /*
+ * It's stopped now, so it might later
+ * continue, exit, or stop again.
+ */
+ flag = 1;
+ if (!(options & WUNTRACED))
+ continue;
+ if (tracehook_inhibit_wait_stopped(p))
continue;
retval = wait_task_stopped(p, ret == 2,
+ (options & WNOWAIT),
+ infop,
stat_addr, ru);
+ if (retval == -EAGAIN)
+ goto repeat;
if (retval != 0) /* He released the lock. */
- goto end_wait4;
+ goto end;
break;
- case TASK_ZOMBIE:
+ default:
+ // case EXIT_DEAD:
+ if (p->exit_state == EXIT_DEAD)
+ 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;
+ if (tracehook_inhibit_wait_zombie(p)) {
+ flag = 1;
+ continue;
+ }
+ retval = wait_task_zombie(
+ p, (options & WNOWAIT),
+ infop, stat_addr, ru);
+ /* He released the lock. */
+ if (retval != 0)
+ goto end;
+ break;
+ }
+check_continued:
/*
- * Eligible but we cannot release it yet:
+ * It's running now, so it might later
+ * exit, stop, or stop and then continue.
*/
- if (ret == 2)
+ flag = 1;
+ if (!unlikely(options & WCONTINUED))
+ continue;
+ if (tracehook_inhibit_wait_continued(p))
continue;
- retval = wait_task_zombie(p, stat_addr, ru);
+ retval = wait_task_continued(
+ p, (options & WNOWAIT),
+ infop, stat_addr, ru);
if (retval != 0) /* He released the lock. */
- goto end_wait4;
+ goto end;
break;
}
}
- if (!flag) {
- list_for_each (_p,&tsk->ptrace_children) {
- p = list_entry(_p,struct task_struct,ptrace_list);
- if (!eligible_child(pid, options, p))
- continue;
- flag = 1;
- break;
- }
+
+ retval = ptrace_do_wait(tsk, pid, options,
+ infop, stat_addr, ru);
+ if (retval != -ECHILD) {
+ flag = 1;
+ if (retval != 0) /* He released the lock. */
+ goto end;
}
+
if (options & __WNOTHREAD)
break;
tsk = next_thread(tsk);
- if (tsk->signal != current->signal)
- BUG();
+ BUG_ON(tsk->signal != current->signal);
} while (tsk != current);
+
read_unlock(&tasklist_lock);
if (flag) {
retval = 0;
if (options & WNOHANG)
- goto end_wait4;
+ goto end;
retval = -ERESTARTSYS;
if (signal_pending(current))
- goto end_wait4;
+ goto end;
schedule();
goto repeat;
}
retval = -ECHILD;
-end_wait4:
+end:
current->state = TASK_RUNNING;
- remove_wait_queue(¤t->wait_chldexit,&wait);
+ remove_wait_queue(¤t->signal->wait_chldexit,&wait);
+ if (infop) {
+ if (retval > 0)
+ retval = 0;
+ else {
+ /*
+ * For a WNOHANG return, clear out all the fields
+ * we would set so the user can easily tell the
+ * difference.
+ */
+ if (!retval)
+ retval = put_user(0, &infop->si_signo);
+ if (!retval)
+ retval = put_user(0, &infop->si_errno);
+ if (!retval)
+ retval = put_user(0, &infop->si_code);
+ if (!retval)
+ retval = put_user(0, &infop->si_pid);
+ if (!retval)
+ retval = put_user(0, &infop->si_uid);
+ if (!retval)
+ retval = put_user(0, &infop->si_status);
+ }
+ }
return retval;
}
-#if !defined(__alpha__) && !defined(__ia64__) && \
- !defined(__arm__) && !defined(__s390__)
+asmlinkage long sys_waitid(int which, pid_t pid,
+ struct siginfo __user *infop, int options,
+ struct rusage __user *ru)
+{
+ long ret;
+
+ if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED))
+ return -EINVAL;
+ if (!(options & (WEXITED|WSTOPPED|WCONTINUED)))
+ return -EINVAL;
+
+ switch (which) {
+ case P_ALL:
+ pid = -1;
+ break;
+ case P_PID:
+ if (pid <= 0)
+ return -EINVAL;
+ break;
+ case P_PGID:
+ if (pid <= 0)
+ return -EINVAL;
+ pid = -pid;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ ret = do_wait(pid, options, infop, NULL, ru);
+
+ /* avoid REGPARM breakage on x86: */
+ prevent_tail_call(ret);
+ return ret;
+}
+
+asmlinkage long sys_wait4(pid_t pid, int __user *stat_addr,
+ int options, struct rusage __user *ru)
+{
+ long ret;
+
+ if (options & ~(WNOHANG|WUNTRACED|WCONTINUED|
+ __WNOTHREAD|__WCLONE|__WALL))
+ return -EINVAL;
+ ret = do_wait(pid, options | WEXITED, NULL, stat_addr, ru);
+
+ /* avoid REGPARM breakage on x86: */
+ prevent_tail_call(ret);
+ return ret;
+}
+
+#ifdef __ARCH_WANT_SYS_WAITPID
/*
* sys_waitpid() remains for compatibility. waitpid() should be
* implemented by calling sys_wait4() from libc.a.
*/
-asmlinkage long sys_waitpid(pid_t pid,unsigned int * stat_addr, int options)
+asmlinkage long sys_waitpid(pid_t pid, int __user *stat_addr, int options)
{
return sys_wait4(pid, stat_addr, options, NULL);
}
git://git.onelab.eu / linux-2.6.git / blobdiff