Blame view
kernel/sys.c
50.2 KB
1da177e4c
|
1 2 3 4 5 |
/* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ |
9984de1a5
|
6 |
#include <linux/export.h> |
1da177e4c
|
7 8 9 |
#include <linux/mm.h> #include <linux/utsname.h> #include <linux/mman.h> |
1da177e4c
|
10 11 |
#include <linux/reboot.h> #include <linux/prctl.h> |
1da177e4c
|
12 13 |
#include <linux/highuid.h> #include <linux/fs.h> |
74da1ff71
|
14 |
#include <linux/kmod.h> |
cdd6c482c
|
15 |
#include <linux/perf_event.h> |
3e88c553d
|
16 |
#include <linux/resource.h> |
dc009d924
|
17 18 |
#include <linux/kernel.h> #include <linux/kexec.h> |
1da177e4c
|
19 |
#include <linux/workqueue.h> |
c59ede7b7
|
20 |
#include <linux/capability.h> |
1da177e4c
|
21 22 23 24 25 26 27 28 |
#include <linux/device.h> #include <linux/key.h> #include <linux/times.h> #include <linux/posix-timers.h> #include <linux/security.h> #include <linux/dcookies.h> #include <linux/suspend.h> #include <linux/tty.h> |
7ed20e1ad
|
29 |
#include <linux/signal.h> |
9f46080c4
|
30 |
#include <linux/cn_proc.h> |
3cfc348bf
|
31 |
#include <linux/getcpu.h> |
6eaeeaba3
|
32 |
#include <linux/task_io_accounting_ops.h> |
1d9d02fee
|
33 |
#include <linux/seccomp.h> |
4047727e5
|
34 |
#include <linux/cpu.h> |
e28cbf229
|
35 |
#include <linux/personality.h> |
e3d5a27d5
|
36 |
#include <linux/ptrace.h> |
5ad4e53bd
|
37 |
#include <linux/fs_struct.h> |
b32dfe377
|
38 39 |
#include <linux/file.h> #include <linux/mount.h> |
5a0e3ad6a
|
40 |
#include <linux/gfp.h> |
40dc166cb
|
41 |
#include <linux/syscore_ops.h> |
be27425dc
|
42 43 |
#include <linux/version.h> #include <linux/ctype.h> |
1da177e4c
|
44 45 46 |
#include <linux/compat.h> #include <linux/syscalls.h> |
00d7c05ab
|
47 |
#include <linux/kprobes.h> |
acce292c8
|
48 |
#include <linux/user_namespace.h> |
7fe5e0429
|
49 |
#include <linux/binfmts.h> |
1da177e4c
|
50 |
|
4a22f1663
|
51 52 53 54 |
#include <linux/sched.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> |
04c6862c0
|
55 |
#include <linux/kmsg_dump.h> |
be27425dc
|
56 57 |
/* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> |
04c6862c0
|
58 |
|
1da177e4c
|
59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 |
#include <asm/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> #ifndef SET_UNALIGN_CTL # define SET_UNALIGN_CTL(a,b) (-EINVAL) #endif #ifndef GET_UNALIGN_CTL # define GET_UNALIGN_CTL(a,b) (-EINVAL) #endif #ifndef SET_FPEMU_CTL # define SET_FPEMU_CTL(a,b) (-EINVAL) #endif #ifndef GET_FPEMU_CTL # define GET_FPEMU_CTL(a,b) (-EINVAL) #endif #ifndef SET_FPEXC_CTL # define SET_FPEXC_CTL(a,b) (-EINVAL) #endif #ifndef GET_FPEXC_CTL # define GET_FPEXC_CTL(a,b) (-EINVAL) #endif |
651d765d0
|
81 82 83 84 85 86 |
#ifndef GET_ENDIAN # define GET_ENDIAN(a,b) (-EINVAL) #endif #ifndef SET_ENDIAN # define SET_ENDIAN(a,b) (-EINVAL) #endif |
8fb402bcc
|
87 88 89 90 91 92 |
#ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif |
1da177e4c
|
93 94 95 96 97 98 99 100 |
/* * this is where the system-wide overflow UID and GID are defined, for * architectures that now have 32-bit UID/GID but didn't in the past */ int overflowuid = DEFAULT_OVERFLOWUID; int overflowgid = DEFAULT_OVERFLOWGID; |
1da177e4c
|
101 102 |
EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); |
1da177e4c
|
103 104 105 106 107 108 109 110 111 112 113 114 115 |
/* * the same as above, but for filesystems which can only store a 16-bit * UID and GID. as such, this is needed on all architectures */ int fs_overflowuid = DEFAULT_FS_OVERFLOWUID; int fs_overflowgid = DEFAULT_FS_OVERFLOWUID; EXPORT_SYMBOL(fs_overflowuid); EXPORT_SYMBOL(fs_overflowgid); /* |
fc832ad36
|
116 117 118 119 120 121 122 123 |
* Returns true if current's euid is same as p's uid or euid, * or has CAP_SYS_NICE to p's user_ns. * * Called with rcu_read_lock, creds are safe */ static bool set_one_prio_perm(struct task_struct *p) { const struct cred *cred = current_cred(), *pcred = __task_cred(p); |
5af662030
|
124 125 |
if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) |
fc832ad36
|
126 |
return true; |
c4a4d6037
|
127 |
if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) |
fc832ad36
|
128 129 130 131 132 |
return true; return false; } /* |
c69e8d9c0
|
133 134 135 |
* set the priority of a task * - the caller must hold the RCU read lock */ |
1da177e4c
|
136 137 138 |
static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; |
fc832ad36
|
139 |
if (!set_one_prio_perm(p)) { |
1da177e4c
|
140 141 142 |
error = -EPERM; goto out; } |
e43379f10
|
143 |
if (niceval < task_nice(p) && !can_nice(p, niceval)) { |
1da177e4c
|
144 145 146 147 148 149 150 151 152 153 154 155 156 157 |
error = -EACCES; goto out; } no_nice = security_task_setnice(p, niceval); if (no_nice) { error = no_nice; goto out; } if (error == -ESRCH) error = 0; set_user_nice(p, niceval); out: return error; } |
754fe8d29
|
158 |
SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) |
1da177e4c
|
159 160 161 |
{ struct task_struct *g, *p; struct user_struct *user; |
86a264abe
|
162 |
const struct cred *cred = current_cred(); |
1da177e4c
|
163 |
int error = -EINVAL; |
41487c65b
|
164 |
struct pid *pgrp; |
7b44ab978
|
165 |
kuid_t uid; |
1da177e4c
|
166 |
|
3e88c553d
|
167 |
if (which > PRIO_USER || which < PRIO_PROCESS) |
1da177e4c
|
168 169 170 171 172 173 174 175 |
goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; if (niceval < -20) niceval = -20; if (niceval > 19) niceval = 19; |
d4581a239
|
176 |
rcu_read_lock(); |
1da177e4c
|
177 178 179 |
read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: |
41487c65b
|
180 |
if (who) |
228ebcbe6
|
181 |
p = find_task_by_vpid(who); |
41487c65b
|
182 183 |
else p = current; |
1da177e4c
|
184 185 186 187 |
if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: |
41487c65b
|
188 |
if (who) |
b488893a3
|
189 |
pgrp = find_vpid(who); |
41487c65b
|
190 191 |
else pgrp = task_pgrp(current); |
2d70b68d4
|
192 |
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { |
1da177e4c
|
193 |
error = set_one_prio(p, niceval, error); |
2d70b68d4
|
194 |
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p); |
1da177e4c
|
195 196 |
break; case PRIO_USER: |
7b44ab978
|
197 |
uid = make_kuid(cred->user_ns, who); |
74ba508f6
|
198 |
user = cred->user; |
1da177e4c
|
199 |
if (!who) |
078de5f70
|
200 201 |
uid = cred->uid; else if (!uid_eq(uid, cred->uid) && |
7b44ab978
|
202 |
!(user = find_user(uid))) |
86a264abe
|
203 |
goto out_unlock; /* No processes for this user */ |
1da177e4c
|
204 |
|
dfc6a736d
|
205 |
do_each_thread(g, p) { |
078de5f70
|
206 |
if (uid_eq(task_uid(p), uid)) |
1da177e4c
|
207 |
error = set_one_prio(p, niceval, error); |
dfc6a736d
|
208 |
} while_each_thread(g, p); |
078de5f70
|
209 |
if (!uid_eq(uid, cred->uid)) |
1da177e4c
|
210 211 212 213 214 |
free_uid(user); /* For find_user() */ break; } out_unlock: read_unlock(&tasklist_lock); |
d4581a239
|
215 |
rcu_read_unlock(); |
1da177e4c
|
216 217 218 219 220 221 222 223 224 225 |
out: return error; } /* * Ugh. To avoid negative return values, "getpriority()" will * not return the normal nice-value, but a negated value that * has been offset by 20 (ie it returns 40..1 instead of -20..19) * to stay compatible. */ |
754fe8d29
|
226 |
SYSCALL_DEFINE2(getpriority, int, which, int, who) |
1da177e4c
|
227 228 229 |
{ struct task_struct *g, *p; struct user_struct *user; |
86a264abe
|
230 |
const struct cred *cred = current_cred(); |
1da177e4c
|
231 |
long niceval, retval = -ESRCH; |
41487c65b
|
232 |
struct pid *pgrp; |
7b44ab978
|
233 |
kuid_t uid; |
1da177e4c
|
234 |
|
3e88c553d
|
235 |
if (which > PRIO_USER || which < PRIO_PROCESS) |
1da177e4c
|
236 |
return -EINVAL; |
701188374
|
237 |
rcu_read_lock(); |
1da177e4c
|
238 239 240 |
read_lock(&tasklist_lock); switch (which) { case PRIO_PROCESS: |
41487c65b
|
241 |
if (who) |
228ebcbe6
|
242 |
p = find_task_by_vpid(who); |
41487c65b
|
243 244 |
else p = current; |
1da177e4c
|
245 246 247 248 249 250 251 |
if (p) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } break; case PRIO_PGRP: |
41487c65b
|
252 |
if (who) |
b488893a3
|
253 |
pgrp = find_vpid(who); |
41487c65b
|
254 255 |
else pgrp = task_pgrp(current); |
2d70b68d4
|
256 |
do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { |
1da177e4c
|
257 258 259 |
niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; |
2d70b68d4
|
260 |
} while_each_pid_thread(pgrp, PIDTYPE_PGID, p); |
1da177e4c
|
261 262 |
break; case PRIO_USER: |
7b44ab978
|
263 |
uid = make_kuid(cred->user_ns, who); |
74ba508f6
|
264 |
user = cred->user; |
1da177e4c
|
265 |
if (!who) |
078de5f70
|
266 267 |
uid = cred->uid; else if (!uid_eq(uid, cred->uid) && |
7b44ab978
|
268 |
!(user = find_user(uid))) |
86a264abe
|
269 |
goto out_unlock; /* No processes for this user */ |
1da177e4c
|
270 |
|
dfc6a736d
|
271 |
do_each_thread(g, p) { |
078de5f70
|
272 |
if (uid_eq(task_uid(p), uid)) { |
1da177e4c
|
273 274 275 276 |
niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } |
dfc6a736d
|
277 |
} while_each_thread(g, p); |
078de5f70
|
278 |
if (!uid_eq(uid, cred->uid)) |
1da177e4c
|
279 280 281 282 283 |
free_uid(user); /* for find_user() */ break; } out_unlock: read_unlock(&tasklist_lock); |
701188374
|
284 |
rcu_read_unlock(); |
1da177e4c
|
285 286 287 |
return retval; } |
1da177e4c
|
288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 |
/* * Unprivileged users may change the real gid to the effective gid * or vice versa. (BSD-style) * * If you set the real gid at all, or set the effective gid to a value not * equal to the real gid, then the saved gid is set to the new effective gid. * * This makes it possible for a setgid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setregid() will be * 100% compatible with BSD. A program which uses just setgid() will be * 100% compatible with POSIX with saved IDs. * * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ |
ae1251ab7
|
306 |
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) |
1da177e4c
|
307 |
{ |
a29c33f4e
|
308 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
309 310 |
const struct cred *old; struct cred *new; |
1da177e4c
|
311 |
int retval; |
a29c33f4e
|
312 313 314 315 316 317 318 319 320 |
kgid_t krgid, kegid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; |
1da177e4c
|
321 |
|
d84f4f992
|
322 323 324 325 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
326 |
retval = -EPERM; |
1da177e4c
|
327 |
if (rgid != (gid_t) -1) { |
a29c33f4e
|
328 329 |
if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || |
c7b96acf1
|
330 |
ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
331 |
new->gid = krgid; |
1da177e4c
|
332 |
else |
d84f4f992
|
333 |
goto error; |
1da177e4c
|
334 335 |
} if (egid != (gid_t) -1) { |
a29c33f4e
|
336 337 338 |
if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || |
c7b96acf1
|
339 |
ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
340 |
new->egid = kegid; |
756184b7d
|
341 |
else |
d84f4f992
|
342 |
goto error; |
1da177e4c
|
343 |
} |
d84f4f992
|
344 |
|
1da177e4c
|
345 |
if (rgid != (gid_t) -1 || |
a29c33f4e
|
346 |
(egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) |
d84f4f992
|
347 348 349 350 351 352 353 354 |
new->sgid = new->egid; new->fsgid = new->egid; return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
355 356 357 358 359 360 361 |
} /* * setgid() is implemented like SysV w/ SAVED_IDS * * SMP: Same implicit races as above. */ |
ae1251ab7
|
362 |
SYSCALL_DEFINE1(setgid, gid_t, gid) |
1da177e4c
|
363 |
{ |
a29c33f4e
|
364 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
365 366 |
const struct cred *old; struct cred *new; |
1da177e4c
|
367 |
int retval; |
a29c33f4e
|
368 369 370 371 372 |
kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; |
1da177e4c
|
373 |
|
d84f4f992
|
374 375 376 377 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
378 |
retval = -EPERM; |
c7b96acf1
|
379 |
if (ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
380 381 382 |
new->gid = new->egid = new->sgid = new->fsgid = kgid; else if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->sgid)) new->egid = new->fsgid = kgid; |
1da177e4c
|
383 |
else |
d84f4f992
|
384 |
goto error; |
1da177e4c
|
385 |
|
d84f4f992
|
386 387 388 389 390 |
return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
391 |
} |
54e991242
|
392 |
|
d84f4f992
|
393 394 395 396 |
/* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) |
1da177e4c
|
397 398 |
{ struct user_struct *new_user; |
078de5f70
|
399 |
new_user = alloc_uid(new->uid); |
1da177e4c
|
400 401 |
if (!new_user) return -EAGAIN; |
72fa59970
|
402 403 404 405 406 407 408 |
/* * We don't fail in case of NPROC limit excess here because too many * poorly written programs don't check set*uid() return code, assuming * it never fails if called by root. We may still enforce NPROC limit * for programs doing set*uid()+execve() by harmlessly deferring the * failure to the execve() stage. */ |
78d7d407b
|
409 |
if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && |
72fa59970
|
410 411 412 413 |
new_user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; |
1da177e4c
|
414 |
|
d84f4f992
|
415 416 |
free_uid(new->user); new->user = new_user; |
1da177e4c
|
417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 |
return 0; } /* * Unprivileged users may change the real uid to the effective uid * or vice versa. (BSD-style) * * If you set the real uid at all, or set the effective uid to a value not * equal to the real uid, then the saved uid is set to the new effective uid. * * This makes it possible for a setuid program to completely drop its * privileges, which is often a useful assertion to make when you are doing * a security audit over a program. * * The general idea is that a program which uses just setreuid() will be * 100% compatible with BSD. A program which uses just setuid() will be * 100% compatible with POSIX with saved IDs. */ |
ae1251ab7
|
435 |
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) |
1da177e4c
|
436 |
{ |
a29c33f4e
|
437 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
438 439 |
const struct cred *old; struct cred *new; |
1da177e4c
|
440 |
int retval; |
a29c33f4e
|
441 442 443 444 445 446 447 448 449 |
kuid_t kruid, keuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; |
1da177e4c
|
450 |
|
d84f4f992
|
451 452 453 454 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
455 |
retval = -EPERM; |
1da177e4c
|
456 |
if (ruid != (uid_t) -1) { |
a29c33f4e
|
457 458 459 |
new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && |
c7b96acf1
|
460 |
!ns_capable(old->user_ns, CAP_SETUID)) |
d84f4f992
|
461 |
goto error; |
1da177e4c
|
462 463 464 |
} if (euid != (uid_t) -1) { |
a29c33f4e
|
465 466 467 468 |
new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && |
c7b96acf1
|
469 |
!ns_capable(old->user_ns, CAP_SETUID)) |
d84f4f992
|
470 |
goto error; |
1da177e4c
|
471 |
} |
a29c33f4e
|
472 |
if (!uid_eq(new->uid, old->uid)) { |
54e991242
|
473 474 475 476 |
retval = set_user(new); if (retval < 0) goto error; } |
1da177e4c
|
477 |
if (ruid != (uid_t) -1 || |
a29c33f4e
|
478 |
(euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) |
d84f4f992
|
479 480 |
new->suid = new->euid; new->fsuid = new->euid; |
1da177e4c
|
481 |
|
d84f4f992
|
482 483 484 |
retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; |
1da177e4c
|
485 |
|
d84f4f992
|
486 |
return commit_creds(new); |
1da177e4c
|
487 |
|
d84f4f992
|
488 489 490 491 |
error: abort_creds(new); return retval; } |
1da177e4c
|
492 493 494 495 496 497 498 499 500 501 502 503 |
/* * setuid() is implemented like SysV with SAVED_IDS * * Note that SAVED_ID's is deficient in that a setuid root program * like sendmail, for example, cannot set its uid to be a normal * user and then switch back, because if you're root, setuid() sets * the saved uid too. If you don't like this, blame the bright people * in the POSIX committee and/or USG. Note that the BSD-style setreuid() * will allow a root program to temporarily drop privileges and be able to * regain them by swapping the real and effective uid. */ |
ae1251ab7
|
504 |
SYSCALL_DEFINE1(setuid, uid_t, uid) |
1da177e4c
|
505 |
{ |
a29c33f4e
|
506 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
507 508 |
const struct cred *old; struct cred *new; |
1da177e4c
|
509 |
int retval; |
a29c33f4e
|
510 511 512 513 514 |
kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; |
1da177e4c
|
515 |
|
d84f4f992
|
516 517 518 519 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
520 |
retval = -EPERM; |
c7b96acf1
|
521 |
if (ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
522 523 |
new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { |
54e991242
|
524 525 526 |
retval = set_user(new); if (retval < 0) goto error; |
d84f4f992
|
527 |
} |
a29c33f4e
|
528 |
} else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { |
d84f4f992
|
529 |
goto error; |
1da177e4c
|
530 |
} |
1da177e4c
|
531 |
|
a29c33f4e
|
532 |
new->fsuid = new->euid = kuid; |
d84f4f992
|
533 534 535 536 |
retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; |
1da177e4c
|
537 |
|
d84f4f992
|
538 |
return commit_creds(new); |
1da177e4c
|
539 |
|
d84f4f992
|
540 541 542 |
error: abort_creds(new); return retval; |
1da177e4c
|
543 544 545 546 547 548 549 |
} /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ |
ae1251ab7
|
550 |
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) |
1da177e4c
|
551 |
{ |
a29c33f4e
|
552 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
553 554 |
const struct cred *old; struct cred *new; |
1da177e4c
|
555 |
int retval; |
a29c33f4e
|
556 557 558 559 560 561 562 563 564 565 566 567 568 569 |
kuid_t kruid, keuid, ksuid; kruid = make_kuid(ns, ruid); keuid = make_kuid(ns, euid); ksuid = make_kuid(ns, suid); if ((ruid != (uid_t) -1) && !uid_valid(kruid)) return -EINVAL; if ((euid != (uid_t) -1) && !uid_valid(keuid)) return -EINVAL; if ((suid != (uid_t) -1) && !uid_valid(ksuid)) return -EINVAL; |
1da177e4c
|
570 |
|
d84f4f992
|
571 572 573 |
new = prepare_creds(); if (!new) return -ENOMEM; |
d84f4f992
|
574 |
old = current_cred(); |
1da177e4c
|
575 |
|
d84f4f992
|
576 |
retval = -EPERM; |
c7b96acf1
|
577 |
if (!ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
578 579 |
if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) |
d84f4f992
|
580 |
goto error; |
a29c33f4e
|
581 582 |
if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) |
d84f4f992
|
583 |
goto error; |
a29c33f4e
|
584 585 |
if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) |
d84f4f992
|
586 |
goto error; |
1da177e4c
|
587 |
} |
d84f4f992
|
588 |
|
1da177e4c
|
589 |
if (ruid != (uid_t) -1) { |
a29c33f4e
|
590 591 |
new->uid = kruid; if (!uid_eq(kruid, old->uid)) { |
54e991242
|
592 593 594 595 |
retval = set_user(new); if (retval < 0) goto error; } |
1da177e4c
|
596 |
} |
d84f4f992
|
597 |
if (euid != (uid_t) -1) |
a29c33f4e
|
598 |
new->euid = keuid; |
1da177e4c
|
599 |
if (suid != (uid_t) -1) |
a29c33f4e
|
600 |
new->suid = ksuid; |
d84f4f992
|
601 |
new->fsuid = new->euid; |
1da177e4c
|
602 |
|
d84f4f992
|
603 604 605 |
retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; |
1da177e4c
|
606 |
|
d84f4f992
|
607 |
return commit_creds(new); |
1da177e4c
|
608 |
|
d84f4f992
|
609 610 611 |
error: abort_creds(new); return retval; |
1da177e4c
|
612 |
} |
a29c33f4e
|
613 |
SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) |
1da177e4c
|
614 |
{ |
86a264abe
|
615 |
const struct cred *cred = current_cred(); |
1da177e4c
|
616 |
int retval; |
a29c33f4e
|
617 618 619 620 621 |
uid_t ruid, euid, suid; ruid = from_kuid_munged(cred->user_ns, cred->uid); euid = from_kuid_munged(cred->user_ns, cred->euid); suid = from_kuid_munged(cred->user_ns, cred->suid); |
1da177e4c
|
622 |
|
a29c33f4e
|
623 624 625 |
if (!(retval = put_user(ruid, ruidp)) && !(retval = put_user(euid, euidp))) retval = put_user(suid, suidp); |
1da177e4c
|
626 627 628 629 630 631 632 |
return retval; } /* * Same as above, but for rgid, egid, sgid. */ |
ae1251ab7
|
633 |
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) |
1da177e4c
|
634 |
{ |
a29c33f4e
|
635 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
636 637 |
const struct cred *old; struct cred *new; |
1da177e4c
|
638 |
int retval; |
a29c33f4e
|
639 640 641 642 643 644 645 646 647 648 649 650 |
kgid_t krgid, kegid, ksgid; krgid = make_kgid(ns, rgid); kegid = make_kgid(ns, egid); ksgid = make_kgid(ns, sgid); if ((rgid != (gid_t) -1) && !gid_valid(krgid)) return -EINVAL; if ((egid != (gid_t) -1) && !gid_valid(kegid)) return -EINVAL; if ((sgid != (gid_t) -1) && !gid_valid(ksgid)) return -EINVAL; |
1da177e4c
|
651 |
|
d84f4f992
|
652 653 654 655 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
656 |
retval = -EPERM; |
c7b96acf1
|
657 |
if (!ns_capable(old->user_ns, CAP_SETGID)) { |
a29c33f4e
|
658 659 |
if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) |
d84f4f992
|
660 |
goto error; |
a29c33f4e
|
661 662 |
if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) |
d84f4f992
|
663 |
goto error; |
a29c33f4e
|
664 665 |
if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) |
d84f4f992
|
666 |
goto error; |
1da177e4c
|
667 |
} |
d84f4f992
|
668 |
|
1da177e4c
|
669 |
if (rgid != (gid_t) -1) |
a29c33f4e
|
670 |
new->gid = krgid; |
d84f4f992
|
671 |
if (egid != (gid_t) -1) |
a29c33f4e
|
672 |
new->egid = kegid; |
1da177e4c
|
673 |
if (sgid != (gid_t) -1) |
a29c33f4e
|
674 |
new->sgid = ksgid; |
d84f4f992
|
675 |
new->fsgid = new->egid; |
1da177e4c
|
676 |
|
d84f4f992
|
677 678 679 680 681 |
return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
682 |
} |
a29c33f4e
|
683 |
SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) |
1da177e4c
|
684 |
{ |
86a264abe
|
685 |
const struct cred *cred = current_cred(); |
1da177e4c
|
686 |
int retval; |
a29c33f4e
|
687 688 689 690 691 |
gid_t rgid, egid, sgid; rgid = from_kgid_munged(cred->user_ns, cred->gid); egid = from_kgid_munged(cred->user_ns, cred->egid); sgid = from_kgid_munged(cred->user_ns, cred->sgid); |
1da177e4c
|
692 |
|
a29c33f4e
|
693 694 695 |
if (!(retval = put_user(rgid, rgidp)) && !(retval = put_user(egid, egidp))) retval = put_user(sgid, sgidp); |
1da177e4c
|
696 697 698 699 700 701 702 703 704 705 706 |
return retval; } /* * "setfsuid()" sets the fsuid - the uid used for filesystem checks. This * is used for "access()" and for the NFS daemon (letting nfsd stay at * whatever uid it wants to). It normally shadows "euid", except when * explicitly set by setfsuid() or for access.. */ |
ae1251ab7
|
707 |
SYSCALL_DEFINE1(setfsuid, uid_t, uid) |
1da177e4c
|
708 |
{ |
d84f4f992
|
709 710 711 |
const struct cred *old; struct cred *new; uid_t old_fsuid; |
a29c33f4e
|
712 713 714 715 716 717 718 719 |
kuid_t kuid; old = current_cred(); old_fsuid = from_kuid_munged(old->user_ns, old->fsuid); kuid = make_kuid(old->user_ns, uid); if (!uid_valid(kuid)) return old_fsuid; |
1da177e4c
|
720 |
|
d84f4f992
|
721 722 |
new = prepare_creds(); if (!new) |
a29c33f4e
|
723 |
return old_fsuid; |
1da177e4c
|
724 |
|
a29c33f4e
|
725 726 |
if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || |
c7b96acf1
|
727 |
ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
728 729 |
if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; |
d84f4f992
|
730 731 |
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; |
1da177e4c
|
732 |
} |
1da177e4c
|
733 |
} |
d84f4f992
|
734 735 |
abort_creds(new); return old_fsuid; |
1da177e4c
|
736 |
|
d84f4f992
|
737 738 |
change_okay: commit_creds(new); |
1da177e4c
|
739 740 741 742 |
return old_fsuid; } /* |
f42df9e65
|
743 |
* Samma på svenska.. |
1da177e4c
|
744 |
*/ |
ae1251ab7
|
745 |
SYSCALL_DEFINE1(setfsgid, gid_t, gid) |
1da177e4c
|
746 |
{ |
d84f4f992
|
747 748 749 |
const struct cred *old; struct cred *new; gid_t old_fsgid; |
a29c33f4e
|
750 751 752 753 754 755 756 757 |
kgid_t kgid; old = current_cred(); old_fsgid = from_kgid_munged(old->user_ns, old->fsgid); kgid = make_kgid(old->user_ns, gid); if (!gid_valid(kgid)) return old_fsgid; |
d84f4f992
|
758 759 760 |
new = prepare_creds(); if (!new) |
a29c33f4e
|
761 |
return old_fsgid; |
1da177e4c
|
762 |
|
a29c33f4e
|
763 764 |
if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || |
c7b96acf1
|
765 |
ns_capable(old->user_ns, CAP_SETGID)) { |
a29c33f4e
|
766 767 |
if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; |
d84f4f992
|
768 |
goto change_okay; |
1da177e4c
|
769 |
} |
1da177e4c
|
770 |
} |
d84f4f992
|
771 |
|
d84f4f992
|
772 773 774 775 776 |
abort_creds(new); return old_fsgid; change_okay: commit_creds(new); |
1da177e4c
|
777 778 |
return old_fsgid; } |
4a22f1663
|
779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 |
/** * sys_getpid - return the thread group id of the current process * * Note, despite the name, this returns the tgid not the pid. The tgid and * the pid are identical unless CLONE_THREAD was specified on clone() in * which case the tgid is the same in all threads of the same group. * * This is SMP safe as current->tgid does not change. */ SYSCALL_DEFINE0(getpid) { return task_tgid_vnr(current); } /* Thread ID - the internal kernel "pid" */ SYSCALL_DEFINE0(gettid) { return task_pid_vnr(current); } /* * Accessing ->real_parent is not SMP-safe, it could * change from under us. However, we can use a stale * value of ->real_parent under rcu_read_lock(), see * release_task()->call_rcu(delayed_put_task_struct). */ SYSCALL_DEFINE0(getppid) { int pid; rcu_read_lock(); pid = task_tgid_vnr(rcu_dereference(current->real_parent)); rcu_read_unlock(); return pid; } SYSCALL_DEFINE0(getuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_uid()); } SYSCALL_DEFINE0(geteuid) { /* Only we change this so SMP safe */ return from_kuid_munged(current_user_ns(), current_euid()); } SYSCALL_DEFINE0(getgid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_gid()); } SYSCALL_DEFINE0(getegid) { /* Only we change this so SMP safe */ return from_kgid_munged(current_user_ns(), current_egid()); } |
f06febc96
|
839 840 |
void do_sys_times(struct tms *tms) { |
0cf55e1ec
|
841 |
cputime_t tgutime, tgstime, cutime, cstime; |
f06febc96
|
842 |
|
2b5fe6de5
|
843 |
spin_lock_irq(¤t->sighand->siglock); |
e80d0a1ae
|
844 |
thread_group_cputime_adjusted(current, &tgutime, &tgstime); |
f06febc96
|
845 846 847 |
cutime = current->signal->cutime; cstime = current->signal->cstime; spin_unlock_irq(¤t->sighand->siglock); |
0cf55e1ec
|
848 849 |
tms->tms_utime = cputime_to_clock_t(tgutime); tms->tms_stime = cputime_to_clock_t(tgstime); |
f06febc96
|
850 851 852 |
tms->tms_cutime = cputime_to_clock_t(cutime); tms->tms_cstime = cputime_to_clock_t(cstime); } |
58fd3aa28
|
853 |
SYSCALL_DEFINE1(times, struct tms __user *, tbuf) |
1da177e4c
|
854 |
{ |
1da177e4c
|
855 856 |
if (tbuf) { struct tms tmp; |
f06febc96
|
857 858 |
do_sys_times(&tmp); |
1da177e4c
|
859 860 861 |
if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } |
e3d5a27d5
|
862 |
force_successful_syscall_return(); |
1da177e4c
|
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 |
return (long) jiffies_64_to_clock_t(get_jiffies_64()); } /* * This needs some heavy checking ... * I just haven't the stomach for it. I also don't fully * understand sessions/pgrp etc. Let somebody who does explain it. * * OK, I think I have the protection semantics right.... this is really * only important on a multi-user system anyway, to make sure one user * can't send a signal to a process owned by another. -TYT, 12/12/91 * * Auch. Had to add the 'did_exec' flag to conform completely to POSIX. * LBT 04.03.94 */ |
b290ebe2c
|
878 |
SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) |
1da177e4c
|
879 880 |
{ struct task_struct *p; |
ee0acf90d
|
881 |
struct task_struct *group_leader = current->group_leader; |
4e021306c
|
882 883 |
struct pid *pgrp; int err; |
1da177e4c
|
884 885 |
if (!pid) |
b488893a3
|
886 |
pid = task_pid_vnr(group_leader); |
1da177e4c
|
887 888 889 890 |
if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; |
950eaaca6
|
891 |
rcu_read_lock(); |
1da177e4c
|
892 893 894 895 896 897 898 |
/* From this point forward we keep holding onto the tasklist lock * so that our parent does not change from under us. -DaveM */ write_lock_irq(&tasklist_lock); err = -ESRCH; |
4e021306c
|
899 |
p = find_task_by_vpid(pid); |
1da177e4c
|
900 901 902 903 904 905 |
if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; |
4e021306c
|
906 |
if (same_thread_group(p->real_parent, group_leader)) { |
1da177e4c
|
907 |
err = -EPERM; |
41487c65b
|
908 |
if (task_session(p) != task_session(group_leader)) |
1da177e4c
|
909 910 911 912 913 914 |
goto out; err = -EACCES; if (p->did_exec) goto out; } else { err = -ESRCH; |
ee0acf90d
|
915 |
if (p != group_leader) |
1da177e4c
|
916 917 918 919 920 921 |
goto out; } err = -EPERM; if (p->signal->leader) goto out; |
4e021306c
|
922 |
pgrp = task_pid(p); |
1da177e4c
|
923 |
if (pgid != pid) { |
b488893a3
|
924 |
struct task_struct *g; |
1da177e4c
|
925 |
|
4e021306c
|
926 927 |
pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); |
41487c65b
|
928 |
if (!g || task_session(g) != task_session(group_leader)) |
f020bc468
|
929 |
goto out; |
1da177e4c
|
930 |
} |
1da177e4c
|
931 932 933 |
err = security_task_setpgid(p, pgid); if (err) goto out; |
1b0f7ffd0
|
934 |
if (task_pgrp(p) != pgrp) |
83beaf3c6
|
935 |
change_pid(p, PIDTYPE_PGID, pgrp); |
1da177e4c
|
936 937 938 939 940 |
err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); |
950eaaca6
|
941 |
rcu_read_unlock(); |
1da177e4c
|
942 943 |
return err; } |
dbf040d9d
|
944 |
SYSCALL_DEFINE1(getpgid, pid_t, pid) |
1da177e4c
|
945 |
{ |
12a3de0a9
|
946 947 948 949 950 |
struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); |
756184b7d
|
951 |
if (!pid) |
12a3de0a9
|
952 |
grp = task_pgrp(current); |
756184b7d
|
953 |
else { |
1da177e4c
|
954 |
retval = -ESRCH; |
12a3de0a9
|
955 956 957 958 959 960 961 962 963 964 |
p = find_task_by_vpid(pid); if (!p) goto out; grp = task_pgrp(p); if (!grp) goto out; retval = security_task_getpgid(p); if (retval) goto out; |
1da177e4c
|
965 |
} |
12a3de0a9
|
966 967 968 969 |
retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; |
1da177e4c
|
970 971 972 |
} #ifdef __ARCH_WANT_SYS_GETPGRP |
dbf040d9d
|
973 |
SYSCALL_DEFINE0(getpgrp) |
1da177e4c
|
974 |
{ |
12a3de0a9
|
975 |
return sys_getpgid(0); |
1da177e4c
|
976 977 978 |
} #endif |
dbf040d9d
|
979 |
SYSCALL_DEFINE1(getsid, pid_t, pid) |
1da177e4c
|
980 |
{ |
1dd768c08
|
981 982 983 984 985 |
struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); |
756184b7d
|
986 |
if (!pid) |
1dd768c08
|
987 |
sid = task_session(current); |
756184b7d
|
988 |
else { |
1da177e4c
|
989 |
retval = -ESRCH; |
1dd768c08
|
990 991 992 993 994 995 996 997 998 999 |
p = find_task_by_vpid(pid); if (!p) goto out; sid = task_session(p); if (!sid) goto out; retval = security_task_getsid(p); if (retval) goto out; |
1da177e4c
|
1000 |
} |
1dd768c08
|
1001 1002 1003 1004 |
retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; |
1da177e4c
|
1005 |
} |
81dabb464
|
1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 |
static void set_special_pids(struct pid *pid) { struct task_struct *curr = current->group_leader; if (task_session(curr) != pid) change_pid(curr, PIDTYPE_SID, pid); if (task_pgrp(curr) != pid) change_pid(curr, PIDTYPE_PGID, pid); } |
b290ebe2c
|
1016 |
SYSCALL_DEFINE0(setsid) |
1da177e4c
|
1017 |
{ |
e19f247a3
|
1018 |
struct task_struct *group_leader = current->group_leader; |
e4cc0a9c8
|
1019 1020 |
struct pid *sid = task_pid(group_leader); pid_t session = pid_vnr(sid); |
1da177e4c
|
1021 |
int err = -EPERM; |
1da177e4c
|
1022 |
write_lock_irq(&tasklist_lock); |
390e2ff07
|
1023 1024 1025 |
/* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; |
430c62312
|
1026 1027 |
/* Fail if a process group id already exists that equals the * proposed session id. |
390e2ff07
|
1028 |
*/ |
6806aac6d
|
1029 |
if (pid_task(sid, PIDTYPE_PGID)) |
1da177e4c
|
1030 |
goto out; |
e19f247a3
|
1031 |
group_leader->signal->leader = 1; |
81dabb464
|
1032 |
set_special_pids(sid); |
24ec839c4
|
1033 |
|
9c9f4ded9
|
1034 |
proc_clear_tty(group_leader); |
24ec839c4
|
1035 |
|
e4cc0a9c8
|
1036 |
err = session; |
1da177e4c
|
1037 1038 |
out: write_unlock_irq(&tasklist_lock); |
5091faa44
|
1039 |
if (err > 0) { |
0d0df599f
|
1040 |
proc_sid_connector(group_leader); |
5091faa44
|
1041 1042 |
sched_autogroup_create_attach(group_leader); } |
1da177e4c
|
1043 1044 |
return err; } |
1da177e4c
|
1045 |
DECLARE_RWSEM(uts_sem); |
e28cbf229
|
1046 1047 |
#ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ |
46da27664
|
1048 |
(personality(current->personality) == PER_LINUX32 && \ |
e28cbf229
|
1049 1050 1051 1052 1053 |
copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif |
be27425dc
|
1054 1055 1056 1057 |
/* * Work around broken programs that cannot handle "Linux 3.0". * Instead we map 3.x to 2.6.40+x, so e.g. 3.0 would be 2.6.40 */ |
2702b1526
|
1058 |
static int override_release(char __user *release, size_t len) |
be27425dc
|
1059 1060 |
{ int ret = 0; |
be27425dc
|
1061 1062 |
if (current->personality & UNAME26) { |
2702b1526
|
1063 1064 |
const char *rest = UTS_RELEASE; char buf[65] = { 0 }; |
be27425dc
|
1065 1066 |
int ndots = 0; unsigned v; |
2702b1526
|
1067 |
size_t copy; |
be27425dc
|
1068 1069 1070 1071 1072 1073 1074 1075 1076 |
while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 40; |
31fd84b95
|
1077 |
copy = clamp_t(size_t, len, 1, sizeof(buf)); |
2702b1526
|
1078 1079 |
copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); |
be27425dc
|
1080 1081 1082 |
} return ret; } |
e48fbb699
|
1083 |
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) |
1da177e4c
|
1084 1085 1086 1087 |
{ int errno = 0; down_read(&uts_sem); |
e9ff3990f
|
1088 |
if (copy_to_user(name, utsname(), sizeof *name)) |
1da177e4c
|
1089 1090 |
errno = -EFAULT; up_read(&uts_sem); |
e28cbf229
|
1091 |
|
be27425dc
|
1092 1093 |
if (!errno && override_release(name->release, sizeof(name->release))) errno = -EFAULT; |
e28cbf229
|
1094 1095 |
if (!errno && override_architecture(name)) errno = -EFAULT; |
1da177e4c
|
1096 1097 |
return errno; } |
5cacdb4ad
|
1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 |
#ifdef __ARCH_WANT_SYS_OLD_UNAME /* * Old cruft */ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) { int error = 0; if (!name) return -EFAULT; down_read(&uts_sem); if (copy_to_user(name, utsname(), sizeof(*name))) error = -EFAULT; up_read(&uts_sem); |
be27425dc
|
1113 1114 |
if (!error && override_release(name->release, sizeof(name->release))) error = -EFAULT; |
5cacdb4ad
|
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 |
if (!error && override_architecture(name)) error = -EFAULT; return error; } SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { int error; if (!name) return -EFAULT; if (!access_ok(VERIFY_WRITE, name, sizeof(struct oldold_utsname))) return -EFAULT; down_read(&uts_sem); error = __copy_to_user(&name->sysname, &utsname()->sysname, __OLD_UTS_LEN); error |= __put_user(0, name->sysname + __OLD_UTS_LEN); error |= __copy_to_user(&name->nodename, &utsname()->nodename, __OLD_UTS_LEN); error |= __put_user(0, name->nodename + __OLD_UTS_LEN); error |= __copy_to_user(&name->release, &utsname()->release, __OLD_UTS_LEN); error |= __put_user(0, name->release + __OLD_UTS_LEN); error |= __copy_to_user(&name->version, &utsname()->version, __OLD_UTS_LEN); error |= __put_user(0, name->version + __OLD_UTS_LEN); error |= __copy_to_user(&name->machine, &utsname()->machine, __OLD_UTS_LEN); error |= __put_user(0, name->machine + __OLD_UTS_LEN); up_read(&uts_sem); if (!error && override_architecture(name)) error = -EFAULT; |
be27425dc
|
1149 1150 |
if (!error && override_release(name->release, sizeof(name->release))) error = -EFAULT; |
5cacdb4ad
|
1151 1152 1153 |
return error ? -EFAULT : 0; } #endif |
5a8a82b1d
|
1154 |
SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) |
1da177e4c
|
1155 1156 1157 |
{ int errno; char tmp[__NEW_UTS_LEN]; |
bb96a6f50
|
1158 |
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) |
1da177e4c
|
1159 |
return -EPERM; |
fc832ad36
|
1160 |
|
1da177e4c
|
1161 1162 1163 1164 1165 |
if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { |
9679e4dd6
|
1166 1167 1168 1169 |
struct new_utsname *u = utsname(); memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); |
1da177e4c
|
1170 |
errno = 0; |
499eea6bf
|
1171 |
uts_proc_notify(UTS_PROC_HOSTNAME); |
1da177e4c
|
1172 1173 1174 1175 1176 1177 |
} up_write(&uts_sem); return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME |
5a8a82b1d
|
1178 |
SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) |
1da177e4c
|
1179 1180 |
{ int i, errno; |
9679e4dd6
|
1181 |
struct new_utsname *u; |
1da177e4c
|
1182 1183 1184 1185 |
if (len < 0) return -EINVAL; down_read(&uts_sem); |
9679e4dd6
|
1186 1187 |
u = utsname(); i = 1 + strlen(u->nodename); |
1da177e4c
|
1188 1189 1190 |
if (i > len) i = len; errno = 0; |
9679e4dd6
|
1191 |
if (copy_to_user(name, u->nodename, i)) |
1da177e4c
|
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 |
errno = -EFAULT; up_read(&uts_sem); return errno; } #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ |
5a8a82b1d
|
1203 |
SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) |
1da177e4c
|
1204 1205 1206 |
{ int errno; char tmp[__NEW_UTS_LEN]; |
fc832ad36
|
1207 |
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) |
1da177e4c
|
1208 1209 1210 1211 1212 1213 1214 |
return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { |
9679e4dd6
|
1215 1216 1217 1218 |
struct new_utsname *u = utsname(); memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); |
1da177e4c
|
1219 |
errno = 0; |
499eea6bf
|
1220 |
uts_proc_notify(UTS_PROC_DOMAINNAME); |
1da177e4c
|
1221 1222 1223 1224 |
} up_write(&uts_sem); return errno; } |
e48fbb699
|
1225 |
SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) |
1da177e4c
|
1226 |
{ |
b95183453
|
1227 1228 1229 1230 1231 1232 1233 1234 |
struct rlimit value; int ret; ret = do_prlimit(current, resource, NULL, &value); if (!ret) ret = copy_to_user(rlim, &value, sizeof(*rlim)) ? -EFAULT : 0; return ret; |
1da177e4c
|
1235 1236 1237 1238 1239 1240 1241 1242 |
} #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ |
e48fbb699
|
1243 1244 |
SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) |
1da177e4c
|
1245 1246 1247 1248 1249 1250 1251 1252 |
{ struct rlimit x; if (resource >= RLIM_NLIMITS) return -EINVAL; task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); |
756184b7d
|
1253 |
if (x.rlim_cur > 0x7FFFFFFF) |
1da177e4c
|
1254 |
x.rlim_cur = 0x7FFFFFFF; |
756184b7d
|
1255 |
if (x.rlim_max > 0x7FFFFFFF) |
1da177e4c
|
1256 1257 1258 1259 1260 |
x.rlim_max = 0x7FFFFFFF; return copy_to_user(rlim, &x, sizeof(x))?-EFAULT:0; } #endif |
c022a0aca
|
1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 |
static inline bool rlim64_is_infinity(__u64 rlim64) { #if BITS_PER_LONG < 64 return rlim64 >= ULONG_MAX; #else return rlim64 == RLIM64_INFINITY; #endif } static void rlim_to_rlim64(const struct rlimit *rlim, struct rlimit64 *rlim64) { if (rlim->rlim_cur == RLIM_INFINITY) rlim64->rlim_cur = RLIM64_INFINITY; else rlim64->rlim_cur = rlim->rlim_cur; if (rlim->rlim_max == RLIM_INFINITY) rlim64->rlim_max = RLIM64_INFINITY; else rlim64->rlim_max = rlim->rlim_max; } static void rlim64_to_rlim(const struct rlimit64 *rlim64, struct rlimit *rlim) { if (rlim64_is_infinity(rlim64->rlim_cur)) rlim->rlim_cur = RLIM_INFINITY; else rlim->rlim_cur = (unsigned long)rlim64->rlim_cur; if (rlim64_is_infinity(rlim64->rlim_max)) rlim->rlim_max = RLIM_INFINITY; else rlim->rlim_max = (unsigned long)rlim64->rlim_max; } |
1c1e618dd
|
1293 |
/* make sure you are allowed to change @tsk limits before calling this */ |
5b41535aa
|
1294 1295 |
int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) |
1da177e4c
|
1296 |
{ |
5b41535aa
|
1297 |
struct rlimit *rlim; |
86f162f4c
|
1298 |
int retval = 0; |
1da177e4c
|
1299 1300 1301 |
if (resource >= RLIM_NLIMITS) return -EINVAL; |
5b41535aa
|
1302 1303 1304 1305 1306 1307 1308 |
if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; if (resource == RLIMIT_NOFILE && new_rlim->rlim_max > sysctl_nr_open) return -EPERM; } |
1da177e4c
|
1309 |
|
1c1e618dd
|
1310 1311 1312 1313 1314 1315 |
/* protect tsk->signal and tsk->sighand from disappearing */ read_lock(&tasklist_lock); if (!tsk->sighand) { retval = -ESRCH; goto out; } |
5b41535aa
|
1316 |
rlim = tsk->signal->rlim + resource; |
86f162f4c
|
1317 |
task_lock(tsk->group_leader); |
5b41535aa
|
1318 |
if (new_rlim) { |
fc832ad36
|
1319 1320 |
/* Keep the capable check against init_user_ns until cgroups can contain all limits */ |
5b41535aa
|
1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 |
if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; if (!retval) retval = security_task_setrlimit(tsk->group_leader, resource, new_rlim); if (resource == RLIMIT_CPU && new_rlim->rlim_cur == 0) { /* * The caller is asking for an immediate RLIMIT_CPU * expiry. But we use the zero value to mean "it was * never set". So let's cheat and make it one second * instead */ new_rlim->rlim_cur = 1; } } if (!retval) { if (old_rlim) *old_rlim = *rlim; if (new_rlim) *rlim = *new_rlim; |
9926e4c74
|
1342 |
} |
7855c35da
|
1343 |
task_unlock(tsk->group_leader); |
1da177e4c
|
1344 |
|
d3561f78f
|
1345 1346 1347 1348 1349 1350 |
/* * RLIMIT_CPU handling. Note that the kernel fails to return an error * code if it rejected the user's attempt to set RLIMIT_CPU. This is a * very long-standing error, and fixing it now risks breakage of * applications, so we live with it */ |
5b41535aa
|
1351 1352 1353 |
if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY) update_rlimit_cpu(tsk, new_rlim->rlim_cur); |
ec9e16bac
|
1354 |
out: |
1c1e618dd
|
1355 |
read_unlock(&tasklist_lock); |
2fb9d2689
|
1356 |
return retval; |
1da177e4c
|
1357 |
} |
c022a0aca
|
1358 1359 1360 1361 |
/* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task) { const struct cred *cred = current_cred(), *tcred; |
fc832ad36
|
1362 1363 |
if (current == task) return 0; |
c022a0aca
|
1364 |
|
fc832ad36
|
1365 |
tcred = __task_cred(task); |
5af662030
|
1366 1367 1368 1369 1370 1371 |
if (uid_eq(cred->uid, tcred->euid) && uid_eq(cred->uid, tcred->suid) && uid_eq(cred->uid, tcred->uid) && gid_eq(cred->gid, tcred->egid) && gid_eq(cred->gid, tcred->sgid) && gid_eq(cred->gid, tcred->gid)) |
fc832ad36
|
1372 |
return 0; |
c4a4d6037
|
1373 |
if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) |
fc832ad36
|
1374 1375 1376 |
return 0; return -EPERM; |
c022a0aca
|
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 |
} SYSCALL_DEFINE4(prlimit64, pid_t, pid, unsigned int, resource, const struct rlimit64 __user *, new_rlim, struct rlimit64 __user *, old_rlim) { struct rlimit64 old64, new64; struct rlimit old, new; struct task_struct *tsk; int ret; if (new_rlim) { if (copy_from_user(&new64, new_rlim, sizeof(new64))) return -EFAULT; rlim64_to_rlim(&new64, &new); } rcu_read_lock(); tsk = pid ? find_task_by_vpid(pid) : current; if (!tsk) { rcu_read_unlock(); return -ESRCH; } ret = check_prlimit_permission(tsk); if (ret) { rcu_read_unlock(); return ret; } get_task_struct(tsk); rcu_read_unlock(); ret = do_prlimit(tsk, resource, new_rlim ? &new : NULL, old_rlim ? &old : NULL); if (!ret && old_rlim) { rlim_to_rlim64(&old, &old64); if (copy_to_user(old_rlim, &old64, sizeof(old64))) ret = -EFAULT; } put_task_struct(tsk); return ret; } |
7855c35da
|
1420 1421 1422 1423 1424 1425 |
SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct rlimit __user *, rlim) { struct rlimit new_rlim; if (copy_from_user(&new_rlim, rlim, sizeof(*rlim))) return -EFAULT; |
5b41535aa
|
1426 |
return do_prlimit(current, resource, &new_rlim, NULL); |
7855c35da
|
1427 |
} |
1da177e4c
|
1428 1429 1430 1431 1432 1433 1434 1435 |
/* * It would make sense to put struct rusage in the task_struct, * except that would make the task_struct be *really big*. After * task_struct gets moved into malloc'ed memory, it would * make sense to do this. It will make moving the rest of the information * a lot simpler! (Which we're not doing right now because we're not * measuring them yet). * |
1da177e4c
|
1436 1437 1438 1439 1440 1441 1442 |
* When sampling multiple threads for RUSAGE_SELF, under SMP we might have * races with threads incrementing their own counters. But since word * reads are atomic, we either get new values or old values and we don't * care which for the sums. We always take the siglock to protect reading * the c* fields from p->signal from races with exit.c updating those * fields when reaping, so a sample either gets all the additions of a * given child after it's reaped, or none so this sample is before reaping. |
2dd0ebcd2
|
1443 |
* |
de047c1bc
|
1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 |
* Locking: * We need to take the siglock for CHILDEREN, SELF and BOTH * for the cases current multithreaded, non-current single threaded * non-current multithreaded. Thread traversal is now safe with * the siglock held. * Strictly speaking, we donot need to take the siglock if we are current and * single threaded, as no one else can take our signal_struct away, no one * else can reap the children to update signal->c* counters, and no one else * can race with the signal-> fields. If we do not take any lock, the * signal-> fields could be read out of order while another thread was just * exiting. So we should place a read memory barrier when we avoid the lock. * On the writer side, write memory barrier is implied in __exit_signal * as __exit_signal releases the siglock spinlock after updating the signal-> * fields. But we don't do this yet to keep things simple. |
2dd0ebcd2
|
1458 |
* |
1da177e4c
|
1459 |
*/ |
f06febc96
|
1460 |
static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) |
679c9cd4a
|
1461 |
{ |
679c9cd4a
|
1462 1463 1464 1465 1466 1467 1468 |
r->ru_nvcsw += t->nvcsw; r->ru_nivcsw += t->nivcsw; r->ru_minflt += t->min_flt; r->ru_majflt += t->maj_flt; r->ru_inblock += task_io_get_inblock(t); r->ru_oublock += task_io_get_oublock(t); } |
1da177e4c
|
1469 1470 1471 1472 |
static void k_getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; |
0cf55e1ec
|
1473 |
cputime_t tgutime, tgstime, utime, stime; |
1f10206cf
|
1474 |
unsigned long maxrss = 0; |
1da177e4c
|
1475 1476 |
memset((char *) r, 0, sizeof *r); |
648616343
|
1477 |
utime = stime = 0; |
1da177e4c
|
1478 |
|
679c9cd4a
|
1479 |
if (who == RUSAGE_THREAD) { |
e80d0a1ae
|
1480 |
task_cputime_adjusted(current, &utime, &stime); |
f06febc96
|
1481 |
accumulate_thread_rusage(p, r); |
1f10206cf
|
1482 |
maxrss = p->signal->maxrss; |
679c9cd4a
|
1483 1484 |
goto out; } |
d6cf723a1
|
1485 |
if (!lock_task_sighand(p, &flags)) |
de047c1bc
|
1486 |
return; |
0f59cc4a3
|
1487 |
|
1da177e4c
|
1488 |
switch (who) { |
0f59cc4a3
|
1489 |
case RUSAGE_BOTH: |
1da177e4c
|
1490 |
case RUSAGE_CHILDREN: |
1da177e4c
|
1491 1492 1493 1494 1495 1496 |
utime = p->signal->cutime; stime = p->signal->cstime; r->ru_nvcsw = p->signal->cnvcsw; r->ru_nivcsw = p->signal->cnivcsw; r->ru_minflt = p->signal->cmin_flt; r->ru_majflt = p->signal->cmaj_flt; |
6eaeeaba3
|
1497 1498 |
r->ru_inblock = p->signal->cinblock; r->ru_oublock = p->signal->coublock; |
1f10206cf
|
1499 |
maxrss = p->signal->cmaxrss; |
0f59cc4a3
|
1500 1501 1502 |
if (who == RUSAGE_CHILDREN) break; |
1da177e4c
|
1503 |
case RUSAGE_SELF: |
e80d0a1ae
|
1504 |
thread_group_cputime_adjusted(p, &tgutime, &tgstime); |
648616343
|
1505 1506 |
utime += tgutime; stime += tgstime; |
1da177e4c
|
1507 1508 1509 1510 |
r->ru_nvcsw += p->signal->nvcsw; r->ru_nivcsw += p->signal->nivcsw; r->ru_minflt += p->signal->min_flt; r->ru_majflt += p->signal->maj_flt; |
6eaeeaba3
|
1511 1512 |
r->ru_inblock += p->signal->inblock; r->ru_oublock += p->signal->oublock; |
1f10206cf
|
1513 1514 |
if (maxrss < p->signal->maxrss) maxrss = p->signal->maxrss; |
1da177e4c
|
1515 1516 |
t = p; do { |
f06febc96
|
1517 |
accumulate_thread_rusage(t, r); |
1da177e4c
|
1518 1519 |
t = next_thread(t); } while (t != p); |
1da177e4c
|
1520 |
break; |
0f59cc4a3
|
1521 |
|
1da177e4c
|
1522 1523 1524 |
default: BUG(); } |
de047c1bc
|
1525 |
unlock_task_sighand(p, &flags); |
de047c1bc
|
1526 |
|
679c9cd4a
|
1527 |
out: |
0f59cc4a3
|
1528 1529 |
cputime_to_timeval(utime, &r->ru_utime); cputime_to_timeval(stime, &r->ru_stime); |
1f10206cf
|
1530 1531 1532 1533 1534 1535 1536 1537 1538 |
if (who != RUSAGE_CHILDREN) { struct mm_struct *mm = get_task_mm(p); if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } } r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ |
1da177e4c
|
1539 1540 1541 1542 1543 |
} int getrusage(struct task_struct *p, int who, struct rusage __user *ru) { struct rusage r; |
1da177e4c
|
1544 |
k_getrusage(p, who, &r); |
1da177e4c
|
1545 1546 |
return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } |
e48fbb699
|
1547 |
SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) |
1da177e4c
|
1548 |
{ |
679c9cd4a
|
1549 1550 |
if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) |
1da177e4c
|
1551 1552 1553 |
return -EINVAL; return getrusage(current, who, ru); } |
8d2d5c4a2
|
1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 |
#ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(getrusage, int, who, struct compat_rusage __user *, ru) { struct rusage r; if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) return -EINVAL; k_getrusage(current, who, &r); return put_compat_rusage(&r, ru); } #endif |
e48fbb699
|
1567 |
SYSCALL_DEFINE1(umask, int, mask) |
1da177e4c
|
1568 1569 1570 1571 |
{ mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } |
3b7391de6
|
1572 |
|
b32dfe377
|
1573 1574 |
static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) { |
2903ff019
|
1575 |
struct fd exe; |
496ad9aa8
|
1576 |
struct inode *inode; |
2903ff019
|
1577 |
int err; |
b32dfe377
|
1578 |
|
2903ff019
|
1579 1580 |
exe = fdget(fd); if (!exe.file) |
b32dfe377
|
1581 |
return -EBADF; |
496ad9aa8
|
1582 |
inode = file_inode(exe.file); |
b32dfe377
|
1583 1584 1585 1586 1587 1588 1589 |
/* * Because the original mm->exe_file points to executable file, make * sure that this one is executable as well, to avoid breaking an * overall picture. */ err = -EACCES; |
496ad9aa8
|
1590 |
if (!S_ISREG(inode->i_mode) || |
2903ff019
|
1591 |
exe.file->f_path.mnt->mnt_flags & MNT_NOEXEC) |
b32dfe377
|
1592 |
goto exit; |
496ad9aa8
|
1593 |
err = inode_permission(inode, MAY_EXEC); |
b32dfe377
|
1594 1595 |
if (err) goto exit; |
bafb282df
|
1596 1597 1598 |
down_write(&mm->mmap_sem); /* |
4229fb1dc
|
1599 |
* Forbid mm->exe_file change if old file still mapped. |
bafb282df
|
1600 1601 |
*/ err = -EBUSY; |
4229fb1dc
|
1602 1603 1604 1605 1606 1607 1608 1609 |
if (mm->exe_file) { struct vm_area_struct *vma; for (vma = mm->mmap; vma; vma = vma->vm_next) if (vma->vm_file && path_equal(&vma->vm_file->f_path, &mm->exe_file->f_path)) goto exit_unlock; |
bafb282df
|
1610 |
} |
b32dfe377
|
1611 1612 1613 1614 1615 1616 |
/* * The symlink can be changed only once, just to disallow arbitrary * transitions malicious software might bring in. This means one * could make a snapshot over all processes running and monitor * /proc/pid/exe changes to notice unusual activity if needed. */ |
bafb282df
|
1617 1618 1619 |
err = -EPERM; if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags)) goto exit_unlock; |
4229fb1dc
|
1620 |
err = 0; |
2903ff019
|
1621 |
set_mm_exe_file(mm, exe.file); /* this grabs a reference to exe.file */ |
bafb282df
|
1622 |
exit_unlock: |
b32dfe377
|
1623 1624 1625 |
up_write(&mm->mmap_sem); exit: |
2903ff019
|
1626 |
fdput(exe); |
b32dfe377
|
1627 1628 |
return err; } |
028ee4be3
|
1629 1630 1631 1632 |
static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { unsigned long rlim = rlimit(RLIMIT_DATA); |
028ee4be3
|
1633 |
struct mm_struct *mm = current->mm; |
fe8c7f5cb
|
1634 1635 |
struct vm_area_struct *vma; int error; |
028ee4be3
|
1636 |
|
fe8c7f5cb
|
1637 |
if (arg5 || (arg4 && opt != PR_SET_MM_AUXV)) |
028ee4be3
|
1638 |
return -EINVAL; |
79f0713d4
|
1639 |
if (!capable(CAP_SYS_RESOURCE)) |
028ee4be3
|
1640 |
return -EPERM; |
b32dfe377
|
1641 1642 |
if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); |
1ad75b9e1
|
1643 |
if (addr >= TASK_SIZE || addr < mmap_min_addr) |
028ee4be3
|
1644 |
return -EINVAL; |
fe8c7f5cb
|
1645 |
error = -EINVAL; |
028ee4be3
|
1646 1647 |
down_read(&mm->mmap_sem); vma = find_vma(mm, addr); |
028ee4be3
|
1648 1649 |
switch (opt) { case PR_SET_MM_START_CODE: |
fe8c7f5cb
|
1650 1651 |
mm->start_code = addr; break; |
028ee4be3
|
1652 |
case PR_SET_MM_END_CODE: |
fe8c7f5cb
|
1653 |
mm->end_code = addr; |
028ee4be3
|
1654 |
break; |
028ee4be3
|
1655 |
case PR_SET_MM_START_DATA: |
fe8c7f5cb
|
1656 |
mm->start_data = addr; |
028ee4be3
|
1657 |
break; |
fe8c7f5cb
|
1658 1659 |
case PR_SET_MM_END_DATA: mm->end_data = addr; |
028ee4be3
|
1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 |
break; case PR_SET_MM_START_BRK: if (addr <= mm->end_data) goto out; if (rlim < RLIM_INFINITY && (mm->brk - addr) + (mm->end_data - mm->start_data) > rlim) goto out; mm->start_brk = addr; break; case PR_SET_MM_BRK: if (addr <= mm->end_data) goto out; if (rlim < RLIM_INFINITY && (addr - mm->start_brk) + (mm->end_data - mm->start_data) > rlim) goto out; mm->brk = addr; break; |
fe8c7f5cb
|
1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 |
/* * If command line arguments and environment * are placed somewhere else on stack, we can * set them up here, ARG_START/END to setup * command line argumets and ENV_START/END * for environment. */ case PR_SET_MM_START_STACK: case PR_SET_MM_ARG_START: case PR_SET_MM_ARG_END: case PR_SET_MM_ENV_START: case PR_SET_MM_ENV_END: if (!vma) { error = -EFAULT; goto out; } |
fe8c7f5cb
|
1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 |
if (opt == PR_SET_MM_START_STACK) mm->start_stack = addr; else if (opt == PR_SET_MM_ARG_START) mm->arg_start = addr; else if (opt == PR_SET_MM_ARG_END) mm->arg_end = addr; else if (opt == PR_SET_MM_ENV_START) mm->env_start = addr; else if (opt == PR_SET_MM_ENV_END) mm->env_end = addr; break; /* * This doesn't move auxiliary vector itself * since it's pinned to mm_struct, but allow * to fill vector with new values. It's up * to a caller to provide sane values here * otherwise user space tools which use this * vector might be unhappy. */ case PR_SET_MM_AUXV: { unsigned long user_auxv[AT_VECTOR_SIZE]; if (arg4 > sizeof(user_auxv)) goto out; up_read(&mm->mmap_sem); if (copy_from_user(user_auxv, (const void __user *)addr, arg4)) return -EFAULT; /* Make sure the last entry is always AT_NULL */ user_auxv[AT_VECTOR_SIZE - 2] = 0; user_auxv[AT_VECTOR_SIZE - 1] = 0; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); task_lock(current); memcpy(mm->saved_auxv, user_auxv, arg4); task_unlock(current); return 0; } |
028ee4be3
|
1743 |
default: |
028ee4be3
|
1744 1745 1746 1747 |
goto out; } error = 0; |
028ee4be3
|
1748 1749 |
out: up_read(&mm->mmap_sem); |
028ee4be3
|
1750 1751 |
return error; } |
300f786b2
|
1752 |
|
52b369415
|
1753 |
#ifdef CONFIG_CHECKPOINT_RESTORE |
300f786b2
|
1754 1755 1756 1757 |
static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return put_user(me->clear_child_tid, tid_addr); } |
52b369415
|
1758 |
#else |
300f786b2
|
1759 1760 1761 1762 |
static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return -EINVAL; } |
028ee4be3
|
1763 |
#endif |
c4ea37c26
|
1764 1765 |
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) |
1da177e4c
|
1766 |
{ |
b6dff3ec5
|
1767 1768 1769 |
struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; |
1da177e4c
|
1770 |
|
d84f4f992
|
1771 1772 |
error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) |
1da177e4c
|
1773 |
return error; |
d84f4f992
|
1774 |
error = 0; |
1da177e4c
|
1775 |
switch (option) { |
f3cbd435b
|
1776 1777 1778 |
case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; |
1da177e4c
|
1779 |
break; |
f3cbd435b
|
1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 |
} me->pdeath_signal = arg2; break; case PR_GET_PDEATHSIG: error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 != SUID_DUMP_DISABLE && arg2 != SUID_DUMP_USER) { error = -EINVAL; |
1da177e4c
|
1792 |
break; |
f3cbd435b
|
1793 1794 1795 |
} set_dumpable(me->mm, arg2); break; |
1da177e4c
|
1796 |
|
f3cbd435b
|
1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 |
case PR_SET_UNALIGN: error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; break; case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; break; case PR_SET_NAME: comm[sizeof(me->comm) - 1] = 0; if (strncpy_from_user(comm, (char __user *)arg2, sizeof(me->comm) - 1) < 0) return -EFAULT; set_task_comm(me, comm); proc_comm_connector(me); break; case PR_GET_NAME: get_task_comm(comm, me); if (copy_to_user((char __user *)arg2, comm, sizeof(comm))) return -EFAULT; break; case PR_GET_ENDIAN: error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: error = prctl_get_seccomp(); break; case PR_SET_SECCOMP: error = prctl_set_seccomp(arg2, (char __user *)arg3); break; case PR_GET_TSC: error = GET_TSC_CTL(arg2); break; case PR_SET_TSC: error = SET_TSC_CTL(arg2); break; case PR_TASK_PERF_EVENTS_DISABLE: error = perf_event_task_disable(); break; case PR_TASK_PERF_EVENTS_ENABLE: error = perf_event_task_enable(); break; case PR_GET_TIMERSLACK: error = current->timer_slack_ns; break; case PR_SET_TIMERSLACK: if (arg2 <= 0) current->timer_slack_ns = |
6976675d9
|
1865 |
current->default_timer_slack_ns; |
f3cbd435b
|
1866 1867 1868 1869 1870 1871 1872 1873 1874 |
else current->timer_slack_ns = arg2; break; case PR_MCE_KILL: if (arg4 | arg5) return -EINVAL; switch (arg2) { case PR_MCE_KILL_CLEAR: if (arg3 != 0) |
4db96cf07
|
1875 |
return -EINVAL; |
f3cbd435b
|
1876 |
current->flags &= ~PF_MCE_PROCESS; |
4db96cf07
|
1877 |
break; |
f3cbd435b
|
1878 1879 1880 1881 1882 1883 1884 1885 1886 |
case PR_MCE_KILL_SET: current->flags |= PF_MCE_PROCESS; if (arg3 == PR_MCE_KILL_EARLY) current->flags |= PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_LATE) current->flags &= ~PF_MCE_EARLY; else if (arg3 == PR_MCE_KILL_DEFAULT) current->flags &= ~(PF_MCE_EARLY|PF_MCE_PROCESS); |
1087e9b4f
|
1887 |
else |
259e5e6c7
|
1888 |
return -EINVAL; |
259e5e6c7
|
1889 |
break; |
1da177e4c
|
1890 |
default: |
f3cbd435b
|
1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 |
return -EINVAL; } break; case PR_MCE_KILL_GET: if (arg2 | arg3 | arg4 | arg5) return -EINVAL; if (current->flags & PF_MCE_PROCESS) error = (current->flags & PF_MCE_EARLY) ? PR_MCE_KILL_EARLY : PR_MCE_KILL_LATE; else error = PR_MCE_KILL_DEFAULT; break; case PR_SET_MM: error = prctl_set_mm(arg2, arg3, arg4, arg5); break; case PR_GET_TID_ADDRESS: error = prctl_get_tid_address(me, (int __user **)arg2); break; case PR_SET_CHILD_SUBREAPER: me->signal->is_child_subreaper = !!arg2; break; case PR_GET_CHILD_SUBREAPER: error = put_user(me->signal->is_child_subreaper, (int __user *)arg2); break; case PR_SET_NO_NEW_PRIVS: if (arg2 != 1 || arg3 || arg4 || arg5) return -EINVAL; current->no_new_privs = 1; break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; return current->no_new_privs ? 1 : 0; default: error = -EINVAL; break; |
1da177e4c
|
1929 1930 1931 |
} return error; } |
3cfc348bf
|
1932 |
|
836f92adf
|
1933 1934 |
SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, struct getcpu_cache __user *, unused) |
3cfc348bf
|
1935 1936 1937 1938 1939 1940 1941 |
{ int err = 0; int cpu = raw_smp_processor_id(); if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); |
3cfc348bf
|
1942 1943 |
return err ? -EFAULT : 0; } |
10a0a8d4e
|
1944 |
|
4a22f1663
|
1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 |
/** * do_sysinfo - fill in sysinfo struct * @info: pointer to buffer to fill */ static int do_sysinfo(struct sysinfo *info) { unsigned long mem_total, sav_total; unsigned int mem_unit, bitcount; struct timespec tp; memset(info, 0, sizeof(struct sysinfo)); |
45c64940c
|
1956 |
get_monotonic_boottime(&tp); |
4a22f1663
|
1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 |
info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0); get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT); info->procs = nr_threads; si_meminfo(info); si_swapinfo(info); /* * If the sum of all the available memory (i.e. ram + swap) * is less than can be stored in a 32 bit unsigned long then * we can be binary compatible with 2.2.x kernels. If not, * well, in that case 2.2.x was broken anyways... * * -Erik Andersen <andersee@debian.org> */ mem_total = info->totalram + info->totalswap; if (mem_total < info->totalram || mem_total < info->totalswap) goto out; bitcount = 0; mem_unit = info->mem_unit; while (mem_unit > 1) { bitcount++; mem_unit >>= 1; sav_total = mem_total; mem_total <<= 1; if (mem_total < sav_total) goto out; } /* * If mem_total did not overflow, multiply all memory values by * info->mem_unit and set it to 1. This leaves things compatible * with 2.2.x, and also retains compatibility with earlier 2.4.x * kernels... */ info->mem_unit = 1; info->totalram <<= bitcount; info->freeram <<= bitcount; info->sharedram <<= bitcount; info->bufferram <<= bitcount; info->totalswap <<= bitcount; info->freeswap <<= bitcount; info->totalhigh <<= bitcount; info->freehigh <<= bitcount; out: return 0; } SYSCALL_DEFINE1(sysinfo, struct sysinfo __user *, info) { struct sysinfo val; do_sysinfo(&val); if (copy_to_user(info, &val, sizeof(struct sysinfo))) return -EFAULT; return 0; } #ifdef CONFIG_COMPAT struct compat_sysinfo { s32 uptime; u32 loads[3]; u32 totalram; u32 freeram; u32 sharedram; u32 bufferram; u32 totalswap; u32 freeswap; u16 procs; u16 pad; u32 totalhigh; u32 freehigh; u32 mem_unit; char _f[20-2*sizeof(u32)-sizeof(int)]; }; COMPAT_SYSCALL_DEFINE1(sysinfo, struct compat_sysinfo __user *, info) { struct sysinfo s; do_sysinfo(&s); /* Check to see if any memory value is too large for 32-bit and scale * down if needed */ if ((s.totalram >> 32) || (s.totalswap >> 32)) { int bitcount = 0; while (s.mem_unit < PAGE_SIZE) { s.mem_unit <<= 1; bitcount++; } s.totalram >>= bitcount; s.freeram >>= bitcount; s.sharedram >>= bitcount; s.bufferram >>= bitcount; s.totalswap >>= bitcount; s.freeswap >>= bitcount; s.totalhigh >>= bitcount; s.freehigh >>= bitcount; } if (!access_ok(VERIFY_WRITE, info, sizeof(struct compat_sysinfo)) || __put_user(s.uptime, &info->uptime) || __put_user(s.loads[0], &info->loads[0]) || __put_user(s.loads[1], &info->loads[1]) || __put_user(s.loads[2], &info->loads[2]) || __put_user(s.totalram, &info->totalram) || __put_user(s.freeram, &info->freeram) || __put_user(s.sharedram, &info->sharedram) || __put_user(s.bufferram, &info->bufferram) || __put_user(s.totalswap, &info->totalswap) || __put_user(s.freeswap, &info->freeswap) || __put_user(s.procs, &info->procs) || __put_user(s.totalhigh, &info->totalhigh) || __put_user(s.freehigh, &info->freehigh) || __put_user(s.mem_unit, &info->mem_unit)) return -EFAULT; return 0; } #endif /* CONFIG_COMPAT */ |