/*
* linux/kernel/exit.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/config.h>
#include <linux/malloc.h>
#include <linux/interrupt.h>
#include <linux/smp_lock.h>
#include <linux/module.h>
#ifdef CONFIG_BSD_PROCESS_ACCT
#include <linux/acct.h>
#endif
#include <asm/uaccess.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 *);
25 static void release_task(struct task_struct * p)
{
27 if (p != current) {
#ifdef CONFIG_SMP
/*
* Wait to make sure the process isn't on the
* runqueue (active on some other CPU still)
*/
for (;;) {
task_lock(p);
if (!p->has_cpu)
break;
task_unlock(p);
do {
barrier();
} while (p->has_cpu);
}
task_unlock(p);
#endif
atomic_dec(&p->user->processes);
free_uid(p->user);
unhash_process(p);
release_thread(p);
current->cmin_flt += p->min_flt + p->cmin_flt;
current->cmaj_flt += p->maj_flt + p->cmaj_flt;
current->cnswap += p->nswap + p->cnswap;
/*
* Potentially available timeslices are retrieved
* here - this way the parent does not get penalized
* for creating too many processes.
*
* (this cannot be used to artificially 'generate'
* timeslices, because any timeslice recovered here
* was given away by the parent in the first place.)
*/
current->counter += p->counter;
62 if (current->counter >= MAX_COUNTER)
current->counter = MAX_COUNTER;
free_task_struct(p);
65 } else {
printk("task releasing itself\n");
}
}
/*
* 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...
*/
75 int session_of_pgrp(int pgrp)
{
struct task_struct *p;
int fallback;
fallback = -1;
read_lock(&tasklist_lock);
82 for_each_task(p) {
83 if (p->session <= 0)
84 continue;
85 if (p->pgrp == pgrp) {
fallback = p->session;
87 break;
}
89 if (p->pid == pgrp)
fallback = p->session;
}
92 read_unlock(&tasklist_lock);
93 return fallback;
}
/*
* Determine if a process group is "orphaned", according to the POSIX
* definition in 2.2.2.52. Orphaned process groups are not to be affected
* by terminal-generated stop signals. Newly orphaned process groups are
* to receive a SIGHUP and a SIGCONT.
*
* "I ask you, have you ever known what it is to be an orphan?"
*/
104 static int will_become_orphaned_pgrp(int pgrp, struct task_struct * ignored_task)
{
struct task_struct *p;
read_lock(&tasklist_lock);
109 for_each_task(p) {
if ((p == ignored_task) || (p->pgrp != pgrp) ||
(p->state == TASK_ZOMBIE) ||
112 (p->p_pptr->pid == 1))
113 continue;
if ((p->p_pptr->pgrp != pgrp) &&
115 (p->p_pptr->session == p->session)) {
116 read_unlock(&tasklist_lock);
117 return 0;
}
}
120 read_unlock(&tasklist_lock);
121 return 1; /* (sighing) "Often!" */
}
124 int is_orphaned_pgrp(int pgrp)
{
126 return will_become_orphaned_pgrp(pgrp, 0);
}
129 static inline int has_stopped_jobs(int pgrp)
{
int retval = 0;
struct task_struct * p;
read_lock(&tasklist_lock);
135 for_each_task(p) {
136 if (p->pgrp != pgrp)
137 continue;
138 if (p->state != TASK_STOPPED)
139 continue;
retval = 1;
141 break;
}
143 read_unlock(&tasklist_lock);
144 return retval;
}
/*
* When we die, we re-parent all our children.
* Try to give them to another thread in our process
* group, and if no such member exists, give it to
* the global child reaper process (ie "init")
*/
153 static inline void forget_original_parent(struct task_struct * father)
{
struct task_struct * p, *reaper;
read_lock(&tasklist_lock);
/* Next in our thread group */
reaper = next_thread(father);
161 if (reaper == father)
reaper = child_reaper;
164 for_each_task(p) {
165 if (p->p_opptr == father) {
/* We dont want people slaying init */
p->exit_signal = SIGCHLD;
p->self_exec_id++;
p->p_opptr = reaper;
170 if (p->pdeath_signal) send_sig(p->pdeath_signal, p, 0);
}
}
173 read_unlock(&tasklist_lock);
}
176 static inline void close_files(struct files_struct * files)
{
int i, j;
j = 0;
181 for (;;) {
unsigned long set;
i = j * __NFDBITS;
184 if (i >= files->max_fdset || i >= files->max_fds)
185 break;
set = files->open_fds->fds_bits[j++];
187 while (set) {
188 if (set & 1) {
struct file * file = xchg(&files->fd[i], NULL);
190 if (file)
filp_close(file, files);
}
i++;
set >>= 1;
}
}
}
199 void put_files_struct(struct files_struct *files)
{
201 if (atomic_dec_and_test(&files->count)) {
close_files(files);
/*
* Free the fd and fdset arrays if we expanded them.
*/
206 if (files->fd != &files->fd_array[0])
free_fd_array(files->fd, files->max_fds);
208 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);
}
}
216 static inline void __exit_files(struct task_struct *tsk)
{
struct files_struct * files = tsk->files;
220 if (files) {
task_lock(tsk);
tsk->files = NULL;
task_unlock(tsk);
put_files_struct(files);
}
}
228 void exit_files(struct task_struct *tsk)
{
__exit_files(tsk);
}
233 static inline void __put_fs_struct(struct fs_struct *fs)
{
/* No need to hold fs->lock if we are killing it */
236 if (atomic_dec_and_test(&fs->count)) {
dput(fs->root);
mntput(fs->rootmnt);
dput(fs->pwd);
mntput(fs->pwdmnt);
241 if (fs->altroot) {
dput(fs->altroot);
mntput(fs->altrootmnt);
}
kmem_cache_free(fs_cachep, fs);
}
}
249 void put_fs_struct(struct fs_struct *fs)
{
__put_fs_struct(fs);
}
254 static inline void __exit_fs(struct task_struct *tsk)
{
struct fs_struct * fs = tsk->fs;
258 if (fs) {
task_lock(tsk);
tsk->fs = NULL;
task_unlock(tsk);
__put_fs_struct(fs);
}
}
266 void exit_fs(struct task_struct *tsk)
{
__exit_fs(tsk);
}
/*
* We can use these to temporarily drop into
* "lazy TLB" mode and back.
*/
275 struct mm_struct * start_lazy_tlb(void)
{
struct mm_struct *mm = current->mm;
current->mm = NULL;
/* active_mm is still 'mm' */
atomic_inc(&mm->mm_count);
enter_lazy_tlb(mm, current, smp_processor_id());
282 return mm;
}
285 void end_lazy_tlb(struct mm_struct *mm)
{
struct mm_struct *active_mm = current->active_mm;
current->mm = mm;
290 if (mm != active_mm) {
current->active_mm = mm;
activate_mm(active_mm, mm);
}
mmdrop(active_mm);
}
/*
* Turn us into a lazy TLB process if we
* aren't already..
*/
301 static inline void __exit_mm(struct task_struct * tsk)
{
struct mm_struct * mm = tsk->mm;
mm_release();
306 if (mm) {
atomic_inc(&mm->mm_count);
308 if (mm != tsk->active_mm) BUG();
/* more a memory barrier than a real lock */
task_lock(tsk);
tsk->mm = NULL;
task_unlock(tsk);
enter_lazy_tlb(mm, current, smp_processor_id());
mmput(mm);
}
}
318 void exit_mm(struct task_struct *tsk)
{
__exit_mm(tsk);
}
/*
* Send signals to all our closest relatives so that they know
* to properly mourn us..
*/
327 static void exit_notify(void)
{
struct task_struct * p, *t;
forget_original_parent(current);
/*
* Check to see if any process groups have become orphaned
* 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)
*
* Case i: Our father is in a different pgrp than we are
* and we were the only connection outside, so our pgrp
* is about to become orphaned.
*/
t = current->p_pptr;
if ((t->pgrp != current->pgrp) &&
(t->session == current->session) &&
will_become_orphaned_pgrp(current->pgrp, current) &&
347 has_stopped_jobs(current->pgrp)) {
kill_pg(current->pgrp,SIGHUP,1);
kill_pg(current->pgrp,SIGCONT,1);
}
/* Let father know we died
*
* Thread signals are configurable, but you aren't going to use
* that to send signals to arbitary processes.
* That stops right now.
*
* If the parent exec id doesn't match the exec id we saved
* when we started then we know the parent has changed security
* domain.
*
* If our self_exec id doesn't match our parent_exec_id then
* we have changed execution domain as these two values started
* the same after a fork.
*
*/
if(current->exit_signal != SIGCHLD &&
( current->parent_exec_id != t->self_exec_id ||
current->self_exec_id != current->parent_exec_id)
371 && !capable(CAP_KILL))
current->exit_signal = SIGCHLD;
/*
* This loop does two things:
*
* A. Make init inherit all the child processes
* B. Check to see if any process groups have become orphaned
* 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)
*/
384 write_lock_irq(&tasklist_lock);
current->state = TASK_ZOMBIE;
do_notify_parent(current, current->exit_signal);
387 while (current->p_cptr != NULL) {
p = current->p_cptr;
current->p_cptr = p->p_osptr;
p->p_ysptr = NULL;
p->ptrace = 0;
p->p_pptr = p->p_opptr;
p->p_osptr = p->p_pptr->p_cptr;
395 if (p->p_osptr)
p->p_osptr->p_ysptr = p;
p->p_pptr->p_cptr = p;
398 if (p->state == TASK_ZOMBIE)
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 ((p->pgrp != current->pgrp) &&
407 (p->session == current->session)) {
int pgrp = p->pgrp;
410 write_unlock_irq(&tasklist_lock);
411 if (is_orphaned_pgrp(pgrp) && has_stopped_jobs(pgrp)) {
kill_pg(pgrp,SIGHUP,1);
kill_pg(pgrp,SIGCONT,1);
}
415 write_lock_irq(&tasklist_lock);
}
}
418 write_unlock_irq(&tasklist_lock);
}
421 NORET_TYPE void do_exit(long code)
{
struct task_struct *tsk = current;
425 if (in_interrupt())
panic("Aiee, killing interrupt handler!");
427 if (!tsk->pid)
panic("Attempted to kill the idle task!");
429 if (tsk->pid == 1)
panic("Attempted to kill init!");
tsk->flags |= PF_EXITING;
del_timer_sync(&tsk->real_timer);
fake_volatile:
#ifdef CONFIG_BSD_PROCESS_ACCT
acct_process(code);
#endif
__exit_mm(tsk);
440 lock_kernel();
sem_exit();
__exit_files(tsk);
__exit_fs(tsk);
exit_sighand(tsk);
exit_thread();
447 if (current->leader)
disassociate_ctty(1);
450 put_exec_domain(tsk->exec_domain);
451 if (tsk->binfmt && tsk->binfmt->module)
__MOD_DEC_USE_COUNT(tsk->binfmt->module);
tsk->exit_code = code;
exit_notify();
schedule();
457 BUG();
/*
* In order to get rid of the "volatile function does return" message
* I did this little loop that confuses gcc to think do_exit really
* is volatile. In fact it's schedule() that is volatile in some
* circumstances: when current->state = ZOMBIE, schedule() never
* returns.
*
* In fact the natural way to do all this is to have the label and the
* goto right after each other, but I put the fake_volatile label at
* the start of the function just in case something /really/ bad
* happens, and the schedule returns. This way we can try again. I'm
* not paranoid: it's just that everybody is out to get me.
*/
471 goto fake_volatile;
}
474 NORET_TYPE void up_and_exit(struct semaphore *sem, long code)
{
476 if (sem)
up(sem);
do_exit(code);
}
482 asmlinkage long sys_exit(int error_code)
{
do_exit((error_code&0xff)<<8);
}
487 asmlinkage long sys_wait4(pid_t pid,unsigned int * stat_addr, int options, struct rusage * ru)
{
int flag, retval;
DECLARE_WAITQUEUE(wait, current);
struct task_struct *tsk;
493 if (options & ~(WNOHANG|WUNTRACED|__WNOTHREAD|__WCLONE|__WALL))
494 return -EINVAL;
add_wait_queue(¤t->wait_chldexit,&wait);
repeat:
flag = 0;
current->state = TASK_INTERRUPTIBLE;
read_lock(&tasklist_lock);
tsk = current;
502 do {
struct task_struct *p;
504 for (p = tsk->p_cptr ; p ; p = p->p_osptr) {
505 if (pid>0) {
506 if (p->pid != pid)
507 continue;
508 } else if (!pid) {
509 if (p->pgrp != current->pgrp)
510 continue;
511 } else if (pid != -1) {
512 if (p->pgrp != -pid)
513 continue;
}
/* Wait for all children (clone and not) if __WALL is set;
* otherwise, wait for clone children *only* if __WCLONE is
* set; otherwise, wait for non-clone children *only*. (Note:
* A "clone" child here is one that reports to its parent
* using a signal other than SIGCHLD.) */
if (((p->exit_signal != SIGCHLD) ^ ((options & __WCLONE) != 0))
521 && !(options & __WALL))
522 continue;
flag = 1;
524 switch (p->state) {
525 case TASK_STOPPED:
526 if (!p->exit_code)
527 continue;
528 if (!(options & WUNTRACED) && !(p->ptrace & PT_PTRACED))
529 continue;
530 read_unlock(&tasklist_lock);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
532 if (!retval && stat_addr)
retval = put_user((p->exit_code << 8) | 0x7f, stat_addr);
534 if (!retval) {
p->exit_code = 0;
retval = p->pid;
}
538 goto end_wait4;
539 case TASK_ZOMBIE:
current->times.tms_cutime += p->times.tms_utime + p->times.tms_cutime;
current->times.tms_cstime += p->times.tms_stime + p->times.tms_cstime;
542 read_unlock(&tasklist_lock);
retval = ru ? getrusage(p, RUSAGE_BOTH, ru) : 0;
544 if (!retval && stat_addr)
retval = put_user(p->exit_code, stat_addr);
546 if (retval)
547 goto end_wait4;
retval = p->pid;
549 if (p->p_opptr != p->p_pptr) {
550 write_lock_irq(&tasklist_lock);
551 REMOVE_LINKS(p);
p->p_pptr = p->p_opptr;
553 SET_LINKS(p);
do_notify_parent(p, SIGCHLD);
555 write_unlock_irq(&tasklist_lock);
556 } else
release_task(p);
558 goto end_wait4;
559 default:
560 continue;
}
}
563 if (options & __WNOTHREAD)
564 break;
tsk = next_thread(tsk);
566 } while (tsk != current);
567 read_unlock(&tasklist_lock);
568 if (flag) {
retval = 0;
570 if (options & WNOHANG)
571 goto end_wait4;
retval = -ERESTARTSYS;
573 if (signal_pending(current))
574 goto end_wait4;
schedule();
576 goto repeat;
}
retval = -ECHILD;
end_wait4:
current->state = TASK_RUNNING;
remove_wait_queue(¤t->wait_chldexit,&wait);
582 return retval;
}
#if !defined(__alpha__) && !defined(__ia64__)
/*
* sys_waitpid() remains for compatibility. waitpid() should be
* implemented by calling sys_wait4() from libc.a.
*/
591 asmlinkage long sys_waitpid(pid_t pid,unsigned int * stat_addr, int options)
{
593 return sys_wait4(pid, stat_addr, options, NULL);
}
#endif