blob: 7e033809ef5fdd5406803bb7f6abf5bbdbaf8a75 [file] [log] [blame]
Linus Torvalds1da177e2005-04-16 15:20:36 -07001/*
2 * linux/kernel/sys.c
3 *
4 * Copyright (C) 1991, 1992 Linus Torvalds
5 */
6
7#include <linux/config.h>
8#include <linux/module.h>
9#include <linux/mm.h>
10#include <linux/utsname.h>
11#include <linux/mman.h>
12#include <linux/smp_lock.h>
13#include <linux/notifier.h>
14#include <linux/reboot.h>
15#include <linux/prctl.h>
16#include <linux/init.h>
17#include <linux/highuid.h>
18#include <linux/fs.h>
Eric W. Biedermandc009d92005-06-25 14:57:52 -070019#include <linux/kernel.h>
20#include <linux/kexec.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070021#include <linux/workqueue.h>
22#include <linux/device.h>
23#include <linux/key.h>
24#include <linux/times.h>
25#include <linux/posix-timers.h>
26#include <linux/security.h>
27#include <linux/dcookies.h>
28#include <linux/suspend.h>
29#include <linux/tty.h>
Jesper Juhl7ed20e12005-05-01 08:59:14 -070030#include <linux/signal.h>
Linus Torvalds1da177e2005-04-16 15:20:36 -070031
32#include <linux/compat.h>
33#include <linux/syscalls.h>
34
35#include <asm/uaccess.h>
36#include <asm/io.h>
37#include <asm/unistd.h>
38
39#ifndef SET_UNALIGN_CTL
40# define SET_UNALIGN_CTL(a,b) (-EINVAL)
41#endif
42#ifndef GET_UNALIGN_CTL
43# define GET_UNALIGN_CTL(a,b) (-EINVAL)
44#endif
45#ifndef SET_FPEMU_CTL
46# define SET_FPEMU_CTL(a,b) (-EINVAL)
47#endif
48#ifndef GET_FPEMU_CTL
49# define GET_FPEMU_CTL(a,b) (-EINVAL)
50#endif
51#ifndef SET_FPEXC_CTL
52# define SET_FPEXC_CTL(a,b) (-EINVAL)
53#endif
54#ifndef GET_FPEXC_CTL
55# define GET_FPEXC_CTL(a,b) (-EINVAL)
56#endif
57
58/*
59 * this is where the system-wide overflow UID and GID are defined, for
60 * architectures that now have 32-bit UID/GID but didn't in the past
61 */
62
63int overflowuid = DEFAULT_OVERFLOWUID;
64int overflowgid = DEFAULT_OVERFLOWGID;
65
66#ifdef CONFIG_UID16
67EXPORT_SYMBOL(overflowuid);
68EXPORT_SYMBOL(overflowgid);
69#endif
70
71/*
72 * the same as above, but for filesystems which can only store a 16-bit
73 * UID and GID. as such, this is needed on all architectures
74 */
75
76int fs_overflowuid = DEFAULT_FS_OVERFLOWUID;
77int fs_overflowgid = DEFAULT_FS_OVERFLOWUID;
78
79EXPORT_SYMBOL(fs_overflowuid);
80EXPORT_SYMBOL(fs_overflowgid);
81
82/*
83 * this indicates whether you can reboot with ctrl-alt-del: the default is yes
84 */
85
86int C_A_D = 1;
87int cad_pid = 1;
88
89/*
90 * Notifier list for kernel code which wants to be called
91 * at shutdown. This is used to stop any idling DMA operations
92 * and the like.
93 */
94
95static struct notifier_block *reboot_notifier_list;
96static DEFINE_RWLOCK(notifier_lock);
97
98/**
99 * notifier_chain_register - Add notifier to a notifier chain
100 * @list: Pointer to root list pointer
101 * @n: New entry in notifier chain
102 *
103 * Adds a notifier to a notifier chain.
104 *
105 * Currently always returns zero.
106 */
107
108int notifier_chain_register(struct notifier_block **list, struct notifier_block *n)
109{
110 write_lock(&notifier_lock);
111 while(*list)
112 {
113 if(n->priority > (*list)->priority)
114 break;
115 list= &((*list)->next);
116 }
117 n->next = *list;
118 *list=n;
119 write_unlock(&notifier_lock);
120 return 0;
121}
122
123EXPORT_SYMBOL(notifier_chain_register);
124
125/**
126 * notifier_chain_unregister - Remove notifier from a notifier chain
127 * @nl: Pointer to root list pointer
128 * @n: New entry in notifier chain
129 *
130 * Removes a notifier from a notifier chain.
131 *
132 * Returns zero on success, or %-ENOENT on failure.
133 */
134
135int notifier_chain_unregister(struct notifier_block **nl, struct notifier_block *n)
136{
137 write_lock(&notifier_lock);
138 while((*nl)!=NULL)
139 {
140 if((*nl)==n)
141 {
142 *nl=n->next;
143 write_unlock(&notifier_lock);
144 return 0;
145 }
146 nl=&((*nl)->next);
147 }
148 write_unlock(&notifier_lock);
149 return -ENOENT;
150}
151
152EXPORT_SYMBOL(notifier_chain_unregister);
153
154/**
155 * notifier_call_chain - Call functions in a notifier chain
156 * @n: Pointer to root pointer of notifier chain
157 * @val: Value passed unmodified to notifier function
158 * @v: Pointer passed unmodified to notifier function
159 *
160 * Calls each function in a notifier chain in turn.
161 *
162 * If the return value of the notifier can be and'd
163 * with %NOTIFY_STOP_MASK, then notifier_call_chain
164 * will return immediately, with the return value of
165 * the notifier function which halted execution.
166 * Otherwise, the return value is the return value
167 * of the last notifier function called.
168 */
169
170int notifier_call_chain(struct notifier_block **n, unsigned long val, void *v)
171{
172 int ret=NOTIFY_DONE;
173 struct notifier_block *nb = *n;
174
175 while(nb)
176 {
177 ret=nb->notifier_call(nb,val,v);
178 if(ret&NOTIFY_STOP_MASK)
179 {
180 return ret;
181 }
182 nb=nb->next;
183 }
184 return ret;
185}
186
187EXPORT_SYMBOL(notifier_call_chain);
188
189/**
190 * register_reboot_notifier - Register function to be called at reboot time
191 * @nb: Info about notifier function to be called
192 *
193 * Registers a function with the list of functions
194 * to be called at reboot time.
195 *
196 * Currently always returns zero, as notifier_chain_register
197 * always returns zero.
198 */
199
200int register_reboot_notifier(struct notifier_block * nb)
201{
202 return notifier_chain_register(&reboot_notifier_list, nb);
203}
204
205EXPORT_SYMBOL(register_reboot_notifier);
206
207/**
208 * unregister_reboot_notifier - Unregister previously registered reboot notifier
209 * @nb: Hook to be unregistered
210 *
211 * Unregisters a previously registered reboot
212 * notifier function.
213 *
214 * Returns zero on success, or %-ENOENT on failure.
215 */
216
217int unregister_reboot_notifier(struct notifier_block * nb)
218{
219 return notifier_chain_unregister(&reboot_notifier_list, nb);
220}
221
222EXPORT_SYMBOL(unregister_reboot_notifier);
223
224static int set_one_prio(struct task_struct *p, int niceval, int error)
225{
226 int no_nice;
227
228 if (p->uid != current->euid &&
229 p->euid != current->euid && !capable(CAP_SYS_NICE)) {
230 error = -EPERM;
231 goto out;
232 }
Matt Mackalle43379f2005-05-01 08:59:00 -0700233 if (niceval < task_nice(p) && !can_nice(p, niceval)) {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700234 error = -EACCES;
235 goto out;
236 }
237 no_nice = security_task_setnice(p, niceval);
238 if (no_nice) {
239 error = no_nice;
240 goto out;
241 }
242 if (error == -ESRCH)
243 error = 0;
244 set_user_nice(p, niceval);
245out:
246 return error;
247}
248
249asmlinkage long sys_setpriority(int which, int who, int niceval)
250{
251 struct task_struct *g, *p;
252 struct user_struct *user;
253 int error = -EINVAL;
254
255 if (which > 2 || which < 0)
256 goto out;
257
258 /* normalize: avoid signed division (rounding problems) */
259 error = -ESRCH;
260 if (niceval < -20)
261 niceval = -20;
262 if (niceval > 19)
263 niceval = 19;
264
265 read_lock(&tasklist_lock);
266 switch (which) {
267 case PRIO_PROCESS:
268 if (!who)
269 who = current->pid;
270 p = find_task_by_pid(who);
271 if (p)
272 error = set_one_prio(p, niceval, error);
273 break;
274 case PRIO_PGRP:
275 if (!who)
276 who = process_group(current);
277 do_each_task_pid(who, PIDTYPE_PGID, p) {
278 error = set_one_prio(p, niceval, error);
279 } while_each_task_pid(who, PIDTYPE_PGID, p);
280 break;
281 case PRIO_USER:
282 user = current->user;
283 if (!who)
284 who = current->uid;
285 else
286 if ((who != current->uid) && !(user = find_user(who)))
287 goto out_unlock; /* No processes for this user */
288
289 do_each_thread(g, p)
290 if (p->uid == who)
291 error = set_one_prio(p, niceval, error);
292 while_each_thread(g, p);
293 if (who != current->uid)
294 free_uid(user); /* For find_user() */
295 break;
296 }
297out_unlock:
298 read_unlock(&tasklist_lock);
299out:
300 return error;
301}
302
303/*
304 * Ugh. To avoid negative return values, "getpriority()" will
305 * not return the normal nice-value, but a negated value that
306 * has been offset by 20 (ie it returns 40..1 instead of -20..19)
307 * to stay compatible.
308 */
309asmlinkage long sys_getpriority(int which, int who)
310{
311 struct task_struct *g, *p;
312 struct user_struct *user;
313 long niceval, retval = -ESRCH;
314
315 if (which > 2 || which < 0)
316 return -EINVAL;
317
318 read_lock(&tasklist_lock);
319 switch (which) {
320 case PRIO_PROCESS:
321 if (!who)
322 who = current->pid;
323 p = find_task_by_pid(who);
324 if (p) {
325 niceval = 20 - task_nice(p);
326 if (niceval > retval)
327 retval = niceval;
328 }
329 break;
330 case PRIO_PGRP:
331 if (!who)
332 who = process_group(current);
333 do_each_task_pid(who, PIDTYPE_PGID, p) {
334 niceval = 20 - task_nice(p);
335 if (niceval > retval)
336 retval = niceval;
337 } while_each_task_pid(who, PIDTYPE_PGID, p);
338 break;
339 case PRIO_USER:
340 user = current->user;
341 if (!who)
342 who = current->uid;
343 else
344 if ((who != current->uid) && !(user = find_user(who)))
345 goto out_unlock; /* No processes for this user */
346
347 do_each_thread(g, p)
348 if (p->uid == who) {
349 niceval = 20 - task_nice(p);
350 if (niceval > retval)
351 retval = niceval;
352 }
353 while_each_thread(g, p);
354 if (who != current->uid)
355 free_uid(user); /* for find_user() */
356 break;
357 }
358out_unlock:
359 read_unlock(&tasklist_lock);
360
361 return retval;
362}
363
Eric W. Biederman4a00ea12005-07-26 11:24:14 -0600364void kernel_restart(char *cmd)
365{
366 notifier_call_chain(&reboot_notifier_list, SYS_RESTART, cmd);
367 system_state = SYSTEM_RESTART;
368 device_suspend(PMSG_FREEZE);
369 device_shutdown();
370 if (!cmd) {
371 printk(KERN_EMERG "Restarting system.\n");
372 } else {
373 printk(KERN_EMERG "Restarting system with command '%s'.\n", cmd);
374 }
375 printk(".\n");
376 machine_restart(cmd);
377}
378EXPORT_SYMBOL_GPL(kernel_restart);
379
380void kernel_kexec(void)
381{
382#ifdef CONFIG_KEXEC
383 struct kimage *image;
384 image = xchg(&kexec_image, 0);
385 if (!image) {
386 return;
387 }
388 notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
389 system_state = SYSTEM_RESTART;
390 device_suspend(PMSG_FREEZE);
391 device_shutdown();
392 printk(KERN_EMERG "Starting new kernel\n");
393 machine_shutdown();
394 machine_kexec(image);
395#endif
396}
397EXPORT_SYMBOL_GPL(kernel_kexec);
398
399void kernel_halt(void)
400{
401 notifier_call_chain(&reboot_notifier_list, SYS_HALT, NULL);
402 system_state = SYSTEM_HALT;
403 device_suspend(PMSG_SUSPEND);
404 device_shutdown();
405 printk(KERN_EMERG "System halted.\n");
406 machine_halt();
407}
408EXPORT_SYMBOL_GPL(kernel_halt);
409
410void kernel_power_off(void)
411{
412 notifier_call_chain(&reboot_notifier_list, SYS_POWER_OFF, NULL);
413 system_state = SYSTEM_POWER_OFF;
414 device_suspend(PMSG_SUSPEND);
415 device_shutdown();
416 printk(KERN_EMERG "Power down.\n");
417 machine_power_off();
418}
419EXPORT_SYMBOL_GPL(kernel_power_off);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700420
421/*
422 * Reboot system call: for obvious reasons only root may call it,
423 * and even root needs to set up some magic numbers in the registers
424 * so that some mistake won't make this reboot the whole machine.
425 * You can also set the meaning of the ctrl-alt-del-key here.
426 *
427 * reboot doesn't sync: do that yourself before calling this.
428 */
429asmlinkage long sys_reboot(int magic1, int magic2, unsigned int cmd, void __user * arg)
430{
431 char buffer[256];
432
433 /* We only trust the superuser with rebooting the system. */
434 if (!capable(CAP_SYS_BOOT))
435 return -EPERM;
436
437 /* For safety, we require "magic" arguments. */
438 if (magic1 != LINUX_REBOOT_MAGIC1 ||
439 (magic2 != LINUX_REBOOT_MAGIC2 &&
440 magic2 != LINUX_REBOOT_MAGIC2A &&
441 magic2 != LINUX_REBOOT_MAGIC2B &&
442 magic2 != LINUX_REBOOT_MAGIC2C))
443 return -EINVAL;
444
445 lock_kernel();
446 switch (cmd) {
447 case LINUX_REBOOT_CMD_RESTART:
Eric W. Biederman4a00ea12005-07-26 11:24:14 -0600448 kernel_restart(NULL);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700449 break;
450
451 case LINUX_REBOOT_CMD_CAD_ON:
452 C_A_D = 1;
453 break;
454
455 case LINUX_REBOOT_CMD_CAD_OFF:
456 C_A_D = 0;
457 break;
458
459 case LINUX_REBOOT_CMD_HALT:
Eric W. Biederman4a00ea12005-07-26 11:24:14 -0600460 kernel_halt();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700461 unlock_kernel();
462 do_exit(0);
463 break;
464
465 case LINUX_REBOOT_CMD_POWER_OFF:
Eric W. Biederman4a00ea12005-07-26 11:24:14 -0600466 kernel_power_off();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700467 unlock_kernel();
468 do_exit(0);
469 break;
470
471 case LINUX_REBOOT_CMD_RESTART2:
472 if (strncpy_from_user(&buffer[0], arg, sizeof(buffer) - 1) < 0) {
473 unlock_kernel();
474 return -EFAULT;
475 }
476 buffer[sizeof(buffer) - 1] = '\0';
477
Eric W. Biederman4a00ea12005-07-26 11:24:14 -0600478 kernel_restart(buffer);
Linus Torvalds1da177e2005-04-16 15:20:36 -0700479 break;
480
Eric W. Biedermandc009d92005-06-25 14:57:52 -0700481 case LINUX_REBOOT_CMD_KEXEC:
Eric W. Biederman4a00ea12005-07-26 11:24:14 -0600482 kernel_kexec();
483 unlock_kernel();
484 return -EINVAL;
485
Linus Torvalds1da177e2005-04-16 15:20:36 -0700486#ifdef CONFIG_SOFTWARE_SUSPEND
487 case LINUX_REBOOT_CMD_SW_SUSPEND:
488 {
489 int ret = software_suspend();
490 unlock_kernel();
491 return ret;
492 }
493#endif
494
495 default:
496 unlock_kernel();
497 return -EINVAL;
498 }
499 unlock_kernel();
500 return 0;
501}
502
503static void deferred_cad(void *dummy)
504{
505 notifier_call_chain(&reboot_notifier_list, SYS_RESTART, NULL);
506 machine_restart(NULL);
507}
508
509/*
510 * This function gets called by ctrl-alt-del - ie the keyboard interrupt.
511 * As it's called within an interrupt, it may NOT sync: the only choice
512 * is whether to reboot at once, or just ignore the ctrl-alt-del.
513 */
514void ctrl_alt_del(void)
515{
516 static DECLARE_WORK(cad_work, deferred_cad, NULL);
517
518 if (C_A_D)
519 schedule_work(&cad_work);
520 else
521 kill_proc(cad_pid, SIGINT, 1);
522}
523
524
525/*
526 * Unprivileged users may change the real gid to the effective gid
527 * or vice versa. (BSD-style)
528 *
529 * If you set the real gid at all, or set the effective gid to a value not
530 * equal to the real gid, then the saved gid is set to the new effective gid.
531 *
532 * This makes it possible for a setgid program to completely drop its
533 * privileges, which is often a useful assertion to make when you are doing
534 * a security audit over a program.
535 *
536 * The general idea is that a program which uses just setregid() will be
537 * 100% compatible with BSD. A program which uses just setgid() will be
538 * 100% compatible with POSIX with saved IDs.
539 *
540 * SMP: There are not races, the GIDs are checked only by filesystem
541 * operations (as far as semantic preservation is concerned).
542 */
543asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
544{
545 int old_rgid = current->gid;
546 int old_egid = current->egid;
547 int new_rgid = old_rgid;
548 int new_egid = old_egid;
549 int retval;
550
551 retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE);
552 if (retval)
553 return retval;
554
555 if (rgid != (gid_t) -1) {
556 if ((old_rgid == rgid) ||
557 (current->egid==rgid) ||
558 capable(CAP_SETGID))
559 new_rgid = rgid;
560 else
561 return -EPERM;
562 }
563 if (egid != (gid_t) -1) {
564 if ((old_rgid == egid) ||
565 (current->egid == egid) ||
566 (current->sgid == egid) ||
567 capable(CAP_SETGID))
568 new_egid = egid;
569 else {
570 return -EPERM;
571 }
572 }
573 if (new_egid != old_egid)
574 {
Alan Coxd6e71142005-06-23 00:09:43 -0700575 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700576 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700577 }
578 if (rgid != (gid_t) -1 ||
579 (egid != (gid_t) -1 && egid != old_rgid))
580 current->sgid = new_egid;
581 current->fsgid = new_egid;
582 current->egid = new_egid;
583 current->gid = new_rgid;
584 key_fsgid_changed(current);
585 return 0;
586}
587
588/*
589 * setgid() is implemented like SysV w/ SAVED_IDS
590 *
591 * SMP: Same implicit races as above.
592 */
593asmlinkage long sys_setgid(gid_t gid)
594{
595 int old_egid = current->egid;
596 int retval;
597
598 retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID);
599 if (retval)
600 return retval;
601
602 if (capable(CAP_SETGID))
603 {
604 if(old_egid != gid)
605 {
Alan Coxd6e71142005-06-23 00:09:43 -0700606 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700607 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700608 }
609 current->gid = current->egid = current->sgid = current->fsgid = gid;
610 }
611 else if ((gid == current->gid) || (gid == current->sgid))
612 {
613 if(old_egid != gid)
614 {
Alan Coxd6e71142005-06-23 00:09:43 -0700615 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700616 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700617 }
618 current->egid = current->fsgid = gid;
619 }
620 else
621 return -EPERM;
622
623 key_fsgid_changed(current);
624 return 0;
625}
626
627static int set_user(uid_t new_ruid, int dumpclear)
628{
629 struct user_struct *new_user;
630
631 new_user = alloc_uid(new_ruid);
632 if (!new_user)
633 return -EAGAIN;
634
635 if (atomic_read(&new_user->processes) >=
636 current->signal->rlim[RLIMIT_NPROC].rlim_cur &&
637 new_user != &root_user) {
638 free_uid(new_user);
639 return -EAGAIN;
640 }
641
642 switch_uid(new_user);
643
644 if(dumpclear)
645 {
Alan Coxd6e71142005-06-23 00:09:43 -0700646 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700647 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700648 }
649 current->uid = new_ruid;
650 return 0;
651}
652
653/*
654 * Unprivileged users may change the real uid to the effective uid
655 * or vice versa. (BSD-style)
656 *
657 * If you set the real uid at all, or set the effective uid to a value not
658 * equal to the real uid, then the saved uid is set to the new effective uid.
659 *
660 * This makes it possible for a setuid program to completely drop its
661 * privileges, which is often a useful assertion to make when you are doing
662 * a security audit over a program.
663 *
664 * The general idea is that a program which uses just setreuid() will be
665 * 100% compatible with BSD. A program which uses just setuid() will be
666 * 100% compatible with POSIX with saved IDs.
667 */
668asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
669{
670 int old_ruid, old_euid, old_suid, new_ruid, new_euid;
671 int retval;
672
673 retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE);
674 if (retval)
675 return retval;
676
677 new_ruid = old_ruid = current->uid;
678 new_euid = old_euid = current->euid;
679 old_suid = current->suid;
680
681 if (ruid != (uid_t) -1) {
682 new_ruid = ruid;
683 if ((old_ruid != ruid) &&
684 (current->euid != ruid) &&
685 !capable(CAP_SETUID))
686 return -EPERM;
687 }
688
689 if (euid != (uid_t) -1) {
690 new_euid = euid;
691 if ((old_ruid != euid) &&
692 (current->euid != euid) &&
693 (current->suid != euid) &&
694 !capable(CAP_SETUID))
695 return -EPERM;
696 }
697
698 if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0)
699 return -EAGAIN;
700
701 if (new_euid != old_euid)
702 {
Alan Coxd6e71142005-06-23 00:09:43 -0700703 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700704 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700705 }
706 current->fsuid = current->euid = new_euid;
707 if (ruid != (uid_t) -1 ||
708 (euid != (uid_t) -1 && euid != old_ruid))
709 current->suid = current->euid;
710 current->fsuid = current->euid;
711
712 key_fsuid_changed(current);
713
714 return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE);
715}
716
717
718
719/*
720 * setuid() is implemented like SysV with SAVED_IDS
721 *
722 * Note that SAVED_ID's is deficient in that a setuid root program
723 * like sendmail, for example, cannot set its uid to be a normal
724 * user and then switch back, because if you're root, setuid() sets
725 * the saved uid too. If you don't like this, blame the bright people
726 * in the POSIX committee and/or USG. Note that the BSD-style setreuid()
727 * will allow a root program to temporarily drop privileges and be able to
728 * regain them by swapping the real and effective uid.
729 */
730asmlinkage long sys_setuid(uid_t uid)
731{
732 int old_euid = current->euid;
733 int old_ruid, old_suid, new_ruid, new_suid;
734 int retval;
735
736 retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID);
737 if (retval)
738 return retval;
739
740 old_ruid = new_ruid = current->uid;
741 old_suid = current->suid;
742 new_suid = old_suid;
743
744 if (capable(CAP_SETUID)) {
745 if (uid != old_ruid && set_user(uid, old_euid != uid) < 0)
746 return -EAGAIN;
747 new_suid = uid;
748 } else if ((uid != current->uid) && (uid != new_suid))
749 return -EPERM;
750
751 if (old_euid != uid)
752 {
Alan Coxd6e71142005-06-23 00:09:43 -0700753 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700754 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700755 }
756 current->fsuid = current->euid = uid;
757 current->suid = new_suid;
758
759 key_fsuid_changed(current);
760
761 return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID);
762}
763
764
765/*
766 * This function implements a generic ability to update ruid, euid,
767 * and suid. This allows you to implement the 4.4 compatible seteuid().
768 */
769asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
770{
771 int old_ruid = current->uid;
772 int old_euid = current->euid;
773 int old_suid = current->suid;
774 int retval;
775
776 retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES);
777 if (retval)
778 return retval;
779
780 if (!capable(CAP_SETUID)) {
781 if ((ruid != (uid_t) -1) && (ruid != current->uid) &&
782 (ruid != current->euid) && (ruid != current->suid))
783 return -EPERM;
784 if ((euid != (uid_t) -1) && (euid != current->uid) &&
785 (euid != current->euid) && (euid != current->suid))
786 return -EPERM;
787 if ((suid != (uid_t) -1) && (suid != current->uid) &&
788 (suid != current->euid) && (suid != current->suid))
789 return -EPERM;
790 }
791 if (ruid != (uid_t) -1) {
792 if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0)
793 return -EAGAIN;
794 }
795 if (euid != (uid_t) -1) {
796 if (euid != current->euid)
797 {
Alan Coxd6e71142005-06-23 00:09:43 -0700798 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700799 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700800 }
801 current->euid = euid;
802 }
803 current->fsuid = current->euid;
804 if (suid != (uid_t) -1)
805 current->suid = suid;
806
807 key_fsuid_changed(current);
808
809 return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES);
810}
811
812asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid)
813{
814 int retval;
815
816 if (!(retval = put_user(current->uid, ruid)) &&
817 !(retval = put_user(current->euid, euid)))
818 retval = put_user(current->suid, suid);
819
820 return retval;
821}
822
823/*
824 * Same as above, but for rgid, egid, sgid.
825 */
826asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
827{
828 int retval;
829
830 retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES);
831 if (retval)
832 return retval;
833
834 if (!capable(CAP_SETGID)) {
835 if ((rgid != (gid_t) -1) && (rgid != current->gid) &&
836 (rgid != current->egid) && (rgid != current->sgid))
837 return -EPERM;
838 if ((egid != (gid_t) -1) && (egid != current->gid) &&
839 (egid != current->egid) && (egid != current->sgid))
840 return -EPERM;
841 if ((sgid != (gid_t) -1) && (sgid != current->gid) &&
842 (sgid != current->egid) && (sgid != current->sgid))
843 return -EPERM;
844 }
845 if (egid != (gid_t) -1) {
846 if (egid != current->egid)
847 {
Alan Coxd6e71142005-06-23 00:09:43 -0700848 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700849 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700850 }
851 current->egid = egid;
852 }
853 current->fsgid = current->egid;
854 if (rgid != (gid_t) -1)
855 current->gid = rgid;
856 if (sgid != (gid_t) -1)
857 current->sgid = sgid;
858
859 key_fsgid_changed(current);
860 return 0;
861}
862
863asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid)
864{
865 int retval;
866
867 if (!(retval = put_user(current->gid, rgid)) &&
868 !(retval = put_user(current->egid, egid)))
869 retval = put_user(current->sgid, sgid);
870
871 return retval;
872}
873
874
875/*
876 * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This
877 * is used for "access()" and for the NFS daemon (letting nfsd stay at
878 * whatever uid it wants to). It normally shadows "euid", except when
879 * explicitly set by setfsuid() or for access..
880 */
881asmlinkage long sys_setfsuid(uid_t uid)
882{
883 int old_fsuid;
884
885 old_fsuid = current->fsuid;
886 if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS))
887 return old_fsuid;
888
889 if (uid == current->uid || uid == current->euid ||
890 uid == current->suid || uid == current->fsuid ||
891 capable(CAP_SETUID))
892 {
893 if (uid != old_fsuid)
894 {
Alan Coxd6e71142005-06-23 00:09:43 -0700895 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700896 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700897 }
898 current->fsuid = uid;
899 }
900
901 key_fsuid_changed(current);
902
903 security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS);
904
905 return old_fsuid;
906}
907
908/*
909 * Samma på svenska..
910 */
911asmlinkage long sys_setfsgid(gid_t gid)
912{
913 int old_fsgid;
914
915 old_fsgid = current->fsgid;
916 if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS))
917 return old_fsgid;
918
919 if (gid == current->gid || gid == current->egid ||
920 gid == current->sgid || gid == current->fsgid ||
921 capable(CAP_SETGID))
922 {
923 if (gid != old_fsgid)
924 {
Alan Coxd6e71142005-06-23 00:09:43 -0700925 current->mm->dumpable = suid_dumpable;
akpm@osdl.orgd59dd462005-05-01 08:58:47 -0700926 smp_wmb();
Linus Torvalds1da177e2005-04-16 15:20:36 -0700927 }
928 current->fsgid = gid;
929 key_fsgid_changed(current);
930 }
931 return old_fsgid;
932}
933
934asmlinkage long sys_times(struct tms __user * tbuf)
935{
936 /*
937 * In the SMP world we might just be unlucky and have one of
938 * the times increment as we use it. Since the value is an
939 * atomically safe type this is just fine. Conceptually its
940 * as if the syscall took an instant longer to occur.
941 */
942 if (tbuf) {
943 struct tms tmp;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700944 cputime_t utime, stime, cutime, cstime;
945
Christoph Lameter71a22242005-06-23 00:10:05 -0700946#ifdef CONFIG_SMP
947 if (thread_group_empty(current)) {
948 /*
949 * Single thread case without the use of any locks.
950 *
951 * We may race with release_task if two threads are
952 * executing. However, release task first adds up the
953 * counters (__exit_signal) before removing the task
954 * from the process tasklist (__unhash_process).
955 * __exit_signal also acquires and releases the
956 * siglock which results in the proper memory ordering
957 * so that the list modifications are always visible
958 * after the counters have been updated.
959 *
960 * If the counters have been updated by the second thread
961 * but the thread has not yet been removed from the list
962 * then the other branch will be executing which will
963 * block on tasklist_lock until the exit handling of the
964 * other task is finished.
965 *
966 * This also implies that the sighand->siglock cannot
967 * be held by another processor. So we can also
968 * skip acquiring that lock.
969 */
970 utime = cputime_add(current->signal->utime, current->utime);
971 stime = cputime_add(current->signal->utime, current->stime);
972 cutime = current->signal->cutime;
973 cstime = current->signal->cstime;
974 } else
975#endif
976 {
Linus Torvalds1da177e2005-04-16 15:20:36 -0700977
Christoph Lameter71a22242005-06-23 00:10:05 -0700978 /* Process with multiple threads */
979 struct task_struct *tsk = current;
980 struct task_struct *t;
Linus Torvalds1da177e2005-04-16 15:20:36 -0700981
Christoph Lameter71a22242005-06-23 00:10:05 -0700982 read_lock(&tasklist_lock);
983 utime = tsk->signal->utime;
984 stime = tsk->signal->stime;
985 t = tsk;
986 do {
987 utime = cputime_add(utime, t->utime);
988 stime = cputime_add(stime, t->stime);
989 t = next_thread(t);
990 } while (t != tsk);
991
992 /*
993 * While we have tasklist_lock read-locked, no dying thread
994 * can be updating current->signal->[us]time. Instead,
995 * we got their counts included in the live thread loop.
996 * However, another thread can come in right now and
997 * do a wait call that updates current->signal->c[us]time.
998 * To make sure we always see that pair updated atomically,
999 * we take the siglock around fetching them.
1000 */
1001 spin_lock_irq(&tsk->sighand->siglock);
1002 cutime = tsk->signal->cutime;
1003 cstime = tsk->signal->cstime;
1004 spin_unlock_irq(&tsk->sighand->siglock);
1005 read_unlock(&tasklist_lock);
1006 }
Linus Torvalds1da177e2005-04-16 15:20:36 -07001007 tmp.tms_utime = cputime_to_clock_t(utime);
1008 tmp.tms_stime = cputime_to_clock_t(stime);
1009 tmp.tms_cutime = cputime_to_clock_t(cutime);
1010 tmp.tms_cstime = cputime_to_clock_t(cstime);
1011 if (copy_to_user(tbuf, &tmp, sizeof(struct tms)))
1012 return -EFAULT;
1013 }
1014 return (long) jiffies_64_to_clock_t(get_jiffies_64());
1015}
1016
1017/*
1018 * This needs some heavy checking ...
1019 * I just haven't the stomach for it. I also don't fully
1020 * understand sessions/pgrp etc. Let somebody who does explain it.
1021 *
1022 * OK, I think I have the protection semantics right.... this is really
1023 * only important on a multi-user system anyway, to make sure one user
1024 * can't send a signal to a process owned by another. -TYT, 12/12/91
1025 *
1026 * Auch. Had to add the 'did_exec' flag to conform completely to POSIX.
1027 * LBT 04.03.94
1028 */
1029
1030asmlinkage long sys_setpgid(pid_t pid, pid_t pgid)
1031{
1032 struct task_struct *p;
1033 int err = -EINVAL;
1034
1035 if (!pid)
1036 pid = current->pid;
1037 if (!pgid)
1038 pgid = pid;
1039 if (pgid < 0)
1040 return -EINVAL;
1041
1042 /* From this point forward we keep holding onto the tasklist lock
1043 * so that our parent does not change from under us. -DaveM
1044 */
1045 write_lock_irq(&tasklist_lock);
1046
1047 err = -ESRCH;
1048 p = find_task_by_pid(pid);
1049 if (!p)
1050 goto out;
1051
1052 err = -EINVAL;
1053 if (!thread_group_leader(p))
1054 goto out;
1055
1056 if (p->parent == current || p->real_parent == current) {
1057 err = -EPERM;
1058 if (p->signal->session != current->signal->session)
1059 goto out;
1060 err = -EACCES;
1061 if (p->did_exec)
1062 goto out;
1063 } else {
1064 err = -ESRCH;
1065 if (p != current)
1066 goto out;
1067 }
1068
1069 err = -EPERM;
1070 if (p->signal->leader)
1071 goto out;
1072
1073 if (pgid != pid) {
1074 struct task_struct *p;
1075
1076 do_each_task_pid(pgid, PIDTYPE_PGID, p) {
1077 if (p->signal->session == current->signal->session)
1078 goto ok_pgid;
1079 } while_each_task_pid(pgid, PIDTYPE_PGID, p);
1080 goto out;
1081 }
1082
1083ok_pgid:
1084 err = security_task_setpgid(p, pgid);
1085 if (err)
1086 goto out;
1087
1088 if (process_group(p) != pgid) {
1089 detach_pid(p, PIDTYPE_PGID);
1090 p->signal->pgrp = pgid;
1091 attach_pid(p, PIDTYPE_PGID, pgid);
1092 }
1093
1094 err = 0;
1095out:
1096 /* All paths lead to here, thus we are safe. -DaveM */
1097 write_unlock_irq(&tasklist_lock);
1098 return err;
1099}
1100
1101asmlinkage long sys_getpgid(pid_t pid)
1102{
1103 if (!pid) {
1104 return process_group(current);
1105 } else {
1106 int retval;
1107 struct task_struct *p;
1108
1109 read_lock(&tasklist_lock);
1110 p = find_task_by_pid(pid);
1111
1112 retval = -ESRCH;
1113 if (p) {
1114 retval = security_task_getpgid(p);
1115 if (!retval)
1116 retval = process_group(p);
1117 }
1118 read_unlock(&tasklist_lock);
1119 return retval;
1120 }
1121}
1122
1123#ifdef __ARCH_WANT_SYS_GETPGRP
1124
1125asmlinkage long sys_getpgrp(void)
1126{
1127 /* SMP - assuming writes are word atomic this is fine */
1128 return process_group(current);
1129}
1130
1131#endif
1132
1133asmlinkage long sys_getsid(pid_t pid)
1134{
1135 if (!pid) {
1136 return current->signal->session;
1137 } else {
1138 int retval;
1139 struct task_struct *p;
1140
1141 read_lock(&tasklist_lock);
1142 p = find_task_by_pid(pid);
1143
1144 retval = -ESRCH;
1145 if(p) {
1146 retval = security_task_getsid(p);
1147 if (!retval)
1148 retval = p->signal->session;
1149 }
1150 read_unlock(&tasklist_lock);
1151 return retval;
1152 }
1153}
1154
1155asmlinkage long sys_setsid(void)
1156{
1157 struct pid *pid;
1158 int err = -EPERM;
1159
1160 if (!thread_group_leader(current))
1161 return -EINVAL;
1162
1163 down(&tty_sem);
1164 write_lock_irq(&tasklist_lock);
1165
1166 pid = find_pid(PIDTYPE_PGID, current->pid);
1167 if (pid)
1168 goto out;
1169
1170 current->signal->leader = 1;
1171 __set_special_pids(current->pid, current->pid);
1172 current->signal->tty = NULL;
1173 current->signal->tty_old_pgrp = 0;
1174 err = process_group(current);
1175out:
1176 write_unlock_irq(&tasklist_lock);
1177 up(&tty_sem);
1178 return err;
1179}
1180
1181/*
1182 * Supplementary group IDs
1183 */
1184
1185/* init to 2 - one for init_task, one to ensure it is never freed */
1186struct group_info init_groups = { .usage = ATOMIC_INIT(2) };
1187
1188struct group_info *groups_alloc(int gidsetsize)
1189{
1190 struct group_info *group_info;
1191 int nblocks;
1192 int i;
1193
1194 nblocks = (gidsetsize + NGROUPS_PER_BLOCK - 1) / NGROUPS_PER_BLOCK;
1195 /* Make sure we always allocate at least one indirect block pointer */
1196 nblocks = nblocks ? : 1;
1197 group_info = kmalloc(sizeof(*group_info) + nblocks*sizeof(gid_t *), GFP_USER);
1198 if (!group_info)
1199 return NULL;
1200 group_info->ngroups = gidsetsize;
1201 group_info->nblocks = nblocks;
1202 atomic_set(&group_info->usage, 1);
1203
1204 if (gidsetsize <= NGROUPS_SMALL) {
1205 group_info->blocks[0] = group_info->small_block;
1206 } else {
1207 for (i = 0; i < nblocks; i++) {
1208 gid_t *b;
1209 b = (void *)__get_free_page(GFP_USER);
1210 if (!b)
1211 goto out_undo_partial_alloc;
1212 group_info->blocks[i] = b;
1213 }
1214 }
1215 return group_info;
1216
1217out_undo_partial_alloc:
1218 while (--i >= 0) {
1219 free_page((unsigned long)group_info->blocks[i]);
1220 }
1221 kfree(group_info);
1222 return NULL;
1223}
1224
1225EXPORT_SYMBOL(groups_alloc);
1226
1227void groups_free(struct group_info *group_info)
1228{
1229 if (group_info->blocks[0] != group_info->small_block) {
1230 int i;
1231 for (i = 0; i < group_info->nblocks; i++)
1232 free_page((unsigned long)group_info->blocks[i]);
1233 }
1234 kfree(group_info);
1235}
1236
1237EXPORT_SYMBOL(groups_free);
1238
1239/* export the group_info to a user-space array */
1240static int groups_to_user(gid_t __user *grouplist,
1241 struct group_info *group_info)
1242{
1243 int i;
1244 int count = group_info->ngroups;
1245
1246 for (i = 0; i < group_info->nblocks; i++) {
1247 int cp_count = min(NGROUPS_PER_BLOCK, count);
1248 int off = i * NGROUPS_PER_BLOCK;
1249 int len = cp_count * sizeof(*grouplist);
1250
1251 if (copy_to_user(grouplist+off, group_info->blocks[i], len))
1252 return -EFAULT;
1253
1254 count -= cp_count;
1255 }
1256 return 0;
1257}
1258
1259/* fill a group_info from a user-space array - it must be allocated already */
1260static int groups_from_user(struct group_info *group_info,
1261 gid_t __user *grouplist)
1262 {
1263 int i;
1264 int count = group_info->ngroups;
1265
1266 for (i = 0; i < group_info->nblocks; i++) {
1267 int cp_count = min(NGROUPS_PER_BLOCK, count);
1268 int off = i * NGROUPS_PER_BLOCK;
1269 int len = cp_count * sizeof(*grouplist);
1270
1271 if (copy_from_user(group_info->blocks[i], grouplist+off, len))
1272 return -EFAULT;
1273
1274 count -= cp_count;
1275 }
1276 return 0;
1277}
1278
Domen Puncerebe8b542005-05-05 16:16:19 -07001279/* a simple Shell sort */
Linus Torvalds1da177e2005-04-16 15:20:36 -07001280static void groups_sort(struct group_info *group_info)
1281{
1282 int base, max, stride;
1283 int gidsetsize = group_info->ngroups;
1284
1285 for (stride = 1; stride < gidsetsize; stride = 3 * stride + 1)
1286 ; /* nothing */
1287 stride /= 3;
1288
1289 while (stride) {
1290 max = gidsetsize - stride;
1291 for (base = 0; base < max; base++) {
1292 int left = base;
1293 int right = left + stride;
1294 gid_t tmp = GROUP_AT(group_info, right);
1295
1296 while (left >= 0 && GROUP_AT(group_info, left) > tmp) {
1297 GROUP_AT(group_info, right) =
1298 GROUP_AT(group_info, left);
1299 right = left;
1300 left -= stride;
1301 }
1302 GROUP_AT(group_info, right) = tmp;
1303 }
1304 stride /= 3;
1305 }
1306}
1307
1308/* a simple bsearch */
David Howells3e301482005-06-23 22:00:56 -07001309int groups_search(struct group_info *group_info, gid_t grp)
Linus Torvalds1da177e2005-04-16 15:20:36 -07001310{
1311 int left, right;
1312
1313 if (!group_info)
1314 return 0;
1315
1316 left = 0;
1317 right = group_info->ngroups;
1318 while (left < right) {
1319 int mid = (left+right)/2;
1320 int cmp = grp - GROUP_AT(group_info, mid);
1321 if (cmp > 0)
1322 left = mid + 1;
1323 else if (cmp < 0)
1324 right = mid;
1325 else
1326 return 1;
1327 }
1328 return 0;
1329}
1330
1331/* validate and set current->group_info */
1332int set_current_groups(struct group_info *group_info)
1333{
1334 int retval;
1335 struct group_info *old_info;
1336
1337 retval = security_task_setgroups(group_info);
1338 if (retval)
1339 return retval;
1340
1341 groups_sort(group_info);
1342 get_group_info(group_info);
1343
1344 task_lock(current);
1345 old_info = current->group_info;
1346 current->group_info = group_info;
1347 task_unlock(current);
1348
1349 put_group_info(old_info);
1350
1351 return 0;
1352}
1353
1354EXPORT_SYMBOL(set_current_groups);
1355
1356asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist)
1357{
1358 int i = 0;
1359
1360 /*
1361 * SMP: Nobody else can change our grouplist. Thus we are
1362 * safe.
1363 */
1364
1365 if (gidsetsize < 0)
1366 return -EINVAL;
1367
1368 /* no need to grab task_lock here; it cannot change */
1369 get_group_info(current->group_info);
1370 i = current->group_info->ngroups;
1371 if (gidsetsize) {
1372 if (i > gidsetsize) {
1373 i = -EINVAL;
1374 goto out;
1375 }
1376 if (groups_to_user(grouplist, current->group_info)) {
1377 i = -EFAULT;
1378 goto out;
1379 }
1380 }
1381out:
1382 put_group_info(current->group_info);
1383 return i;
1384}
1385
1386/*
1387 * SMP: Our groups are copy-on-write. We can set them safely
1388 * without another task interfering.
1389 */
1390
1391asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist)
1392{
1393 struct group_info *group_info;
1394 int retval;
1395
1396 if (!capable(CAP_SETGID))
1397 return -EPERM;
1398 if ((unsigned)gidsetsize > NGROUPS_MAX)
1399 return -EINVAL;
1400
1401 group_info = groups_alloc(gidsetsize);
1402 if (!group_info)
1403 return -ENOMEM;
1404 retval = groups_from_user(group_info, grouplist);
1405 if (retval) {
1406 put_group_info(group_info);
1407 return retval;
1408 }
1409
1410 retval = set_current_groups(group_info);
1411 put_group_info(group_info);
1412
1413 return retval;
1414}
1415
1416/*
1417 * Check whether we're fsgid/egid or in the supplemental group..
1418 */
1419int in_group_p(gid_t grp)
1420{
1421 int retval = 1;
1422 if (grp != current->fsgid) {
1423 get_group_info(current->group_info);
1424 retval = groups_search(current->group_info, grp);
1425 put_group_info(current->group_info);
1426 }
1427 return retval;
1428}
1429
1430EXPORT_SYMBOL(in_group_p);
1431
1432int in_egroup_p(gid_t grp)
1433{
1434 int retval = 1;
1435 if (grp != current->egid) {
1436 get_group_info(current->group_info);
1437 retval = groups_search(current->group_info, grp);
1438 put_group_info(current->group_info);
1439 }
1440 return retval;
1441}
1442
1443EXPORT_SYMBOL(in_egroup_p);
1444
1445DECLARE_RWSEM(uts_sem);
1446
1447EXPORT_SYMBOL(uts_sem);
1448
1449asmlinkage long sys_newuname(struct new_utsname __user * name)
1450{
1451 int errno = 0;
1452
1453 down_read(&uts_sem);
1454 if (copy_to_user(name,&system_utsname,sizeof *name))
1455 errno = -EFAULT;
1456 up_read(&uts_sem);
1457 return errno;
1458}
1459
1460asmlinkage long sys_sethostname(char __user *name, int len)
1461{
1462 int errno;
1463 char tmp[__NEW_UTS_LEN];
1464
1465 if (!capable(CAP_SYS_ADMIN))
1466 return -EPERM;
1467 if (len < 0 || len > __NEW_UTS_LEN)
1468 return -EINVAL;
1469 down_write(&uts_sem);
1470 errno = -EFAULT;
1471 if (!copy_from_user(tmp, name, len)) {
1472 memcpy(system_utsname.nodename, tmp, len);
1473 system_utsname.nodename[len] = 0;
1474 errno = 0;
1475 }
1476 up_write(&uts_sem);
1477 return errno;
1478}
1479
1480#ifdef __ARCH_WANT_SYS_GETHOSTNAME
1481
1482asmlinkage long sys_gethostname(char __user *name, int len)
1483{
1484 int i, errno;
1485
1486 if (len < 0)
1487 return -EINVAL;
1488 down_read(&uts_sem);
1489 i = 1 + strlen(system_utsname.nodename);
1490 if (i > len)
1491 i = len;
1492 errno = 0;
1493 if (copy_to_user(name, system_utsname.nodename, i))
1494 errno = -EFAULT;
1495 up_read(&uts_sem);
1496 return errno;
1497}
1498
1499#endif
1500
1501/*
1502 * Only setdomainname; getdomainname can be implemented by calling
1503 * uname()
1504 */
1505asmlinkage long sys_setdomainname(char __user *name, int len)
1506{
1507 int errno;
1508 char tmp[__NEW_UTS_LEN];
1509
1510 if (!capable(CAP_SYS_ADMIN))
1511 return -EPERM;
1512 if (len < 0 || len > __NEW_UTS_LEN)
1513 return -EINVAL;
1514
1515 down_write(&uts_sem);
1516 errno = -EFAULT;
1517 if (!copy_from_user(tmp, name, len)) {
1518 memcpy(system_utsname.domainname, tmp, len);
1519 system_utsname.domainname[len] = 0;
1520 errno = 0;
1521 }
1522 up_write(&uts_sem);
1523 return errno;
1524}
1525
1526asmlinkage long sys_getrlimit(unsigned int resource, struct rlimit __user *rlim)
1527{
1528 if (resource >= RLIM_NLIMITS)
1529 return -EINVAL;
1530 else {
1531 struct rlimit value;
1532 task_lock(current->group_leader);
1533 value = current->signal->rlim[resource];
1534 task_unlock(current->group_leader);
1535 return copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0;
1536 }
1537}
1538
1539#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT
1540
1541/*
1542 * Back compatibility for getrlimit. Needed for some apps.
1543 */
1544
1545asmlinkage long sys_old_getrlimit(unsigned int resource, struct rlimit __user *rlim)
1546{
1547 struct rlimit x;
1548 if (resource >= RLIM_NLIMITS)
1549 return -EINVAL;
1550
1551 task_lock(current->group_leader);
1552 x = current->signal->rlim[resource];
1553 task_unlock(current->group_leader);
1554 if(x.rlim_cur > 0x7FFFFFFF)
1555 x.rlim_cur = 0x7FFFFFFF;
1556 if(x.rlim_max > 0x7FFFFFFF)
1557 x.rlim_max = 0x7FFFFFFF;
1558 return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0;
1559}
1560
1561#endif
1562
1563asmlinkage long sys_setrlimit(unsigned int resource, struct rlimit __user *rlim)
1564{
1565 struct rlimit new_rlim, *old_rlim;
1566 int retval;
1567
1568 if (resource >= RLIM_NLIMITS)
1569 return -EINVAL;
1570 if(copy_from_user(&new_rlim, rlim, sizeof(*rlim)))
1571 return -EFAULT;
1572 if (new_rlim.rlim_cur > new_rlim.rlim_max)
1573 return -EINVAL;
1574 old_rlim = current->signal->rlim + resource;
1575 if ((new_rlim.rlim_max > old_rlim->rlim_max) &&
1576 !capable(CAP_SYS_RESOURCE))
1577 return -EPERM;
1578 if (resource == RLIMIT_NOFILE && new_rlim.rlim_max > NR_OPEN)
1579 return -EPERM;
1580
1581 retval = security_task_setrlimit(resource, &new_rlim);
1582 if (retval)
1583 return retval;
1584
1585 task_lock(current->group_leader);
1586 *old_rlim = new_rlim;
1587 task_unlock(current->group_leader);
1588
1589 if (resource == RLIMIT_CPU && new_rlim.rlim_cur != RLIM_INFINITY &&
1590 (cputime_eq(current->signal->it_prof_expires, cputime_zero) ||
1591 new_rlim.rlim_cur <= cputime_to_secs(
1592 current->signal->it_prof_expires))) {
1593 cputime_t cputime = secs_to_cputime(new_rlim.rlim_cur);
1594 read_lock(&tasklist_lock);
1595 spin_lock_irq(&current->sighand->siglock);
1596 set_process_cpu_timer(current, CPUCLOCK_PROF,
1597 &cputime, NULL);
1598 spin_unlock_irq(&current->sighand->siglock);
1599 read_unlock(&tasklist_lock);
1600 }
1601
1602 return 0;
1603}
1604
1605/*
1606 * It would make sense to put struct rusage in the task_struct,
1607 * except that would make the task_struct be *really big*. After
1608 * task_struct gets moved into malloc'ed memory, it would
1609 * make sense to do this. It will make moving the rest of the information
1610 * a lot simpler! (Which we're not doing right now because we're not
1611 * measuring them yet).
1612 *
1613 * This expects to be called with tasklist_lock read-locked or better,
1614 * and the siglock not locked. It may momentarily take the siglock.
1615 *
1616 * When sampling multiple threads for RUSAGE_SELF, under SMP we might have
1617 * races with threads incrementing their own counters. But since word
1618 * reads are atomic, we either get new values or old values and we don't
1619 * care which for the sums. We always take the siglock to protect reading
1620 * the c* fields from p->signal from races with exit.c updating those
1621 * fields when reaping, so a sample either gets all the additions of a
1622 * given child after it's reaped, or none so this sample is before reaping.
1623 */
1624
1625static void k_getrusage(struct task_struct *p, int who, struct rusage *r)
1626{
1627 struct task_struct *t;
1628 unsigned long flags;
1629 cputime_t utime, stime;
1630
1631 memset((char *) r, 0, sizeof *r);
1632
1633 if (unlikely(!p->signal))
1634 return;
1635
1636 switch (who) {
1637 case RUSAGE_CHILDREN:
1638 spin_lock_irqsave(&p->sighand->siglock, flags);
1639 utime = p->signal->cutime;
1640 stime = p->signal->cstime;
1641 r->ru_nvcsw = p->signal->cnvcsw;
1642 r->ru_nivcsw = p->signal->cnivcsw;
1643 r->ru_minflt = p->signal->cmin_flt;
1644 r->ru_majflt = p->signal->cmaj_flt;
1645 spin_unlock_irqrestore(&p->sighand->siglock, flags);
1646 cputime_to_timeval(utime, &r->ru_utime);
1647 cputime_to_timeval(stime, &r->ru_stime);
1648 break;
1649 case RUSAGE_SELF:
1650 spin_lock_irqsave(&p->sighand->siglock, flags);
1651 utime = stime = cputime_zero;
1652 goto sum_group;
1653 case RUSAGE_BOTH:
1654 spin_lock_irqsave(&p->sighand->siglock, flags);
1655 utime = p->signal->cutime;
1656 stime = p->signal->cstime;
1657 r->ru_nvcsw = p->signal->cnvcsw;
1658 r->ru_nivcsw = p->signal->cnivcsw;
1659 r->ru_minflt = p->signal->cmin_flt;
1660 r->ru_majflt = p->signal->cmaj_flt;
1661 sum_group:
1662 utime = cputime_add(utime, p->signal->utime);
1663 stime = cputime_add(stime, p->signal->stime);
1664 r->ru_nvcsw += p->signal->nvcsw;
1665 r->ru_nivcsw += p->signal->nivcsw;
1666 r->ru_minflt += p->signal->min_flt;
1667 r->ru_majflt += p->signal->maj_flt;
1668 t = p;
1669 do {
1670 utime = cputime_add(utime, t->utime);
1671 stime = cputime_add(stime, t->stime);
1672 r->ru_nvcsw += t->nvcsw;
1673 r->ru_nivcsw += t->nivcsw;
1674 r->ru_minflt += t->min_flt;
1675 r->ru_majflt += t->maj_flt;
1676 t = next_thread(t);
1677 } while (t != p);
1678 spin_unlock_irqrestore(&p->sighand->siglock, flags);
1679 cputime_to_timeval(utime, &r->ru_utime);
1680 cputime_to_timeval(stime, &r->ru_stime);
1681 break;
1682 default:
1683 BUG();
1684 }
1685}
1686
1687int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
1688{
1689 struct rusage r;
1690 read_lock(&tasklist_lock);
1691 k_getrusage(p, who, &r);
1692 read_unlock(&tasklist_lock);
1693 return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0;
1694}
1695
1696asmlinkage long sys_getrusage(int who, struct rusage __user *ru)
1697{
1698 if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN)
1699 return -EINVAL;
1700 return getrusage(current, who, ru);
1701}
1702
1703asmlinkage long sys_umask(int mask)
1704{
1705 mask = xchg(&current->fs->umask, mask & S_IRWXUGO);
1706 return mask;
1707}
1708
1709asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
1710 unsigned long arg4, unsigned long arg5)
1711{
1712 long error;
1713 int sig;
1714
1715 error = security_task_prctl(option, arg2, arg3, arg4, arg5);
1716 if (error)
1717 return error;
1718
1719 switch (option) {
1720 case PR_SET_PDEATHSIG:
1721 sig = arg2;
Jesper Juhl7ed20e12005-05-01 08:59:14 -07001722 if (!valid_signal(sig)) {
Linus Torvalds1da177e2005-04-16 15:20:36 -07001723 error = -EINVAL;
1724 break;
1725 }
1726 current->pdeath_signal = sig;
1727 break;
1728 case PR_GET_PDEATHSIG:
1729 error = put_user(current->pdeath_signal, (int __user *)arg2);
1730 break;
1731 case PR_GET_DUMPABLE:
1732 if (current->mm->dumpable)
1733 error = 1;
1734 break;
1735 case PR_SET_DUMPABLE:
Alan Coxd6e71142005-06-23 00:09:43 -07001736 if (arg2 < 0 || arg2 > 2) {
Linus Torvalds1da177e2005-04-16 15:20:36 -07001737 error = -EINVAL;
1738 break;
1739 }
1740 current->mm->dumpable = arg2;
1741 break;
1742
1743 case PR_SET_UNALIGN:
1744 error = SET_UNALIGN_CTL(current, arg2);
1745 break;
1746 case PR_GET_UNALIGN:
1747 error = GET_UNALIGN_CTL(current, arg2);
1748 break;
1749 case PR_SET_FPEMU:
1750 error = SET_FPEMU_CTL(current, arg2);
1751 break;
1752 case PR_GET_FPEMU:
1753 error = GET_FPEMU_CTL(current, arg2);
1754 break;
1755 case PR_SET_FPEXC:
1756 error = SET_FPEXC_CTL(current, arg2);
1757 break;
1758 case PR_GET_FPEXC:
1759 error = GET_FPEXC_CTL(current, arg2);
1760 break;
1761 case PR_GET_TIMING:
1762 error = PR_TIMING_STATISTICAL;
1763 break;
1764 case PR_SET_TIMING:
1765 if (arg2 == PR_TIMING_STATISTICAL)
1766 error = 0;
1767 else
1768 error = -EINVAL;
1769 break;
1770
1771 case PR_GET_KEEPCAPS:
1772 if (current->keep_capabilities)
1773 error = 1;
1774 break;
1775 case PR_SET_KEEPCAPS:
1776 if (arg2 != 0 && arg2 != 1) {
1777 error = -EINVAL;
1778 break;
1779 }
1780 current->keep_capabilities = arg2;
1781 break;
1782 case PR_SET_NAME: {
1783 struct task_struct *me = current;
1784 unsigned char ncomm[sizeof(me->comm)];
1785
1786 ncomm[sizeof(me->comm)-1] = 0;
1787 if (strncpy_from_user(ncomm, (char __user *)arg2,
1788 sizeof(me->comm)-1) < 0)
1789 return -EFAULT;
1790 set_task_comm(me, ncomm);
1791 return 0;
1792 }
1793 case PR_GET_NAME: {
1794 struct task_struct *me = current;
1795 unsigned char tcomm[sizeof(me->comm)];
1796
1797 get_task_comm(tcomm, me);
1798 if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm)))
1799 return -EFAULT;
1800 return 0;
1801 }
1802 default:
1803 error = -EINVAL;
1804 break;
1805 }
1806 return error;
1807}