Blame view
kernel/sys.c
57.6 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 |
#include <linux/kernel.h> |
1da177e4c
|
18 |
#include <linux/workqueue.h> |
c59ede7b7
|
19 |
#include <linux/capability.h> |
1da177e4c
|
20 21 22 23 24 25 26 27 |
#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
|
28 |
#include <linux/signal.h> |
9f46080c4
|
29 |
#include <linux/cn_proc.h> |
3cfc348bf
|
30 |
#include <linux/getcpu.h> |
6eaeeaba3
|
31 |
#include <linux/task_io_accounting_ops.h> |
1d9d02fee
|
32 |
#include <linux/seccomp.h> |
4047727e5
|
33 |
#include <linux/cpu.h> |
e28cbf229
|
34 |
#include <linux/personality.h> |
e3d5a27d5
|
35 |
#include <linux/ptrace.h> |
5ad4e53bd
|
36 |
#include <linux/fs_struct.h> |
b32dfe377
|
37 38 |
#include <linux/file.h> #include <linux/mount.h> |
5a0e3ad6a
|
39 |
#include <linux/gfp.h> |
40dc166cb
|
40 |
#include <linux/syscore_ops.h> |
be27425dc
|
41 42 |
#include <linux/version.h> #include <linux/ctype.h> |
1da177e4c
|
43 44 45 |
#include <linux/compat.h> #include <linux/syscalls.h> |
00d7c05ab
|
46 |
#include <linux/kprobes.h> |
acce292c8
|
47 |
#include <linux/user_namespace.h> |
7fe5e0429
|
48 |
#include <linux/binfmts.h> |
1da177e4c
|
49 |
|
4a22f1663
|
50 51 52 53 |
#include <linux/sched.h> #include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> |
04c6862c0
|
54 |
#include <linux/kmsg_dump.h> |
be27425dc
|
55 56 |
/* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> |
04c6862c0
|
57 |
|
1da177e4c
|
58 59 60 61 62 |
#include <asm/uaccess.h> #include <asm/io.h> #include <asm/unistd.h> #ifndef SET_UNALIGN_CTL |
ec94fc3d5
|
63 |
# define SET_UNALIGN_CTL(a, b) (-EINVAL) |
1da177e4c
|
64 65 |
#endif #ifndef GET_UNALIGN_CTL |
ec94fc3d5
|
66 |
# define GET_UNALIGN_CTL(a, b) (-EINVAL) |
1da177e4c
|
67 68 |
#endif #ifndef SET_FPEMU_CTL |
ec94fc3d5
|
69 |
# define SET_FPEMU_CTL(a, b) (-EINVAL) |
1da177e4c
|
70 71 |
#endif #ifndef GET_FPEMU_CTL |
ec94fc3d5
|
72 |
# define GET_FPEMU_CTL(a, b) (-EINVAL) |
1da177e4c
|
73 74 |
#endif #ifndef SET_FPEXC_CTL |
ec94fc3d5
|
75 |
# define SET_FPEXC_CTL(a, b) (-EINVAL) |
1da177e4c
|
76 77 |
#endif #ifndef GET_FPEXC_CTL |
ec94fc3d5
|
78 |
# define GET_FPEXC_CTL(a, b) (-EINVAL) |
1da177e4c
|
79 |
#endif |
651d765d0
|
80 |
#ifndef GET_ENDIAN |
ec94fc3d5
|
81 |
# define GET_ENDIAN(a, b) (-EINVAL) |
651d765d0
|
82 83 |
#endif #ifndef SET_ENDIAN |
ec94fc3d5
|
84 |
# define SET_ENDIAN(a, b) (-EINVAL) |
651d765d0
|
85 |
#endif |
8fb402bcc
|
86 87 88 89 90 91 |
#ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif |
fe3d197f8
|
92 |
#ifndef MPX_ENABLE_MANAGEMENT |
46a6e0cf1
|
93 |
# define MPX_ENABLE_MANAGEMENT() (-EINVAL) |
fe3d197f8
|
94 95 |
#endif #ifndef MPX_DISABLE_MANAGEMENT |
46a6e0cf1
|
96 |
# define MPX_DISABLE_MANAGEMENT() (-EINVAL) |
fe3d197f8
|
97 |
#endif |
9791554b4
|
98 99 100 101 102 103 |
#ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif |
1da177e4c
|
104 105 106 107 108 109 110 111 |
/* * 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
|
112 113 |
EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); |
1da177e4c
|
114 115 116 117 118 119 120 121 122 123 124 125 126 |
/* * 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
|
127 128 129 130 131 132 133 134 |
* 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
|
135 136 |
if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) |
fc832ad36
|
137 |
return true; |
c4a4d6037
|
138 |
if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) |
fc832ad36
|
139 140 141 142 143 |
return true; return false; } /* |
c69e8d9c0
|
144 145 146 |
* set the priority of a task * - the caller must hold the RCU read lock */ |
1da177e4c
|
147 148 149 |
static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; |
fc832ad36
|
150 |
if (!set_one_prio_perm(p)) { |
1da177e4c
|
151 152 153 |
error = -EPERM; goto out; } |
e43379f10
|
154 |
if (niceval < task_nice(p) && !can_nice(p, niceval)) { |
1da177e4c
|
155 156 157 158 159 160 161 162 163 164 165 166 167 168 |
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
|
169 |
SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) |
1da177e4c
|
170 171 172 |
{ struct task_struct *g, *p; struct user_struct *user; |
86a264abe
|
173 |
const struct cred *cred = current_cred(); |
1da177e4c
|
174 |
int error = -EINVAL; |
41487c65b
|
175 |
struct pid *pgrp; |
7b44ab978
|
176 |
kuid_t uid; |
1da177e4c
|
177 |
|
3e88c553d
|
178 |
if (which > PRIO_USER || which < PRIO_PROCESS) |
1da177e4c
|
179 180 181 182 |
goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; |
c4a4d2f43
|
183 184 185 186 |
if (niceval < MIN_NICE) niceval = MIN_NICE; if (niceval > MAX_NICE) niceval = MAX_NICE; |
1da177e4c
|
187 |
|
d4581a239
|
188 |
rcu_read_lock(); |
1da177e4c
|
189 190 |
read_lock(&tasklist_lock); switch (which) { |
ec94fc3d5
|
191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) error = set_one_prio(p, niceval, error); break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { error = set_one_prio(p, niceval, error); } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) |
86a264abe
|
216 |
goto out_unlock; /* No processes for this user */ |
ec94fc3d5
|
217 218 |
} do_each_thread(g, p) { |
8639b4613
|
219 |
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) |
ec94fc3d5
|
220 221 222 223 224 |
error = set_one_prio(p, niceval, error); } while_each_thread(g, p); if (!uid_eq(uid, cred->uid)) free_uid(user); /* For find_user() */ break; |
1da177e4c
|
225 226 227 |
} out_unlock: read_unlock(&tasklist_lock); |
d4581a239
|
228 |
rcu_read_unlock(); |
1da177e4c
|
229 230 231 232 233 234 235 236 237 238 |
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
|
239 |
SYSCALL_DEFINE2(getpriority, int, which, int, who) |
1da177e4c
|
240 241 242 |
{ struct task_struct *g, *p; struct user_struct *user; |
86a264abe
|
243 |
const struct cred *cred = current_cred(); |
1da177e4c
|
244 |
long niceval, retval = -ESRCH; |
41487c65b
|
245 |
struct pid *pgrp; |
7b44ab978
|
246 |
kuid_t uid; |
1da177e4c
|
247 |
|
3e88c553d
|
248 |
if (which > PRIO_USER || which < PRIO_PROCESS) |
1da177e4c
|
249 |
return -EINVAL; |
701188374
|
250 |
rcu_read_lock(); |
1da177e4c
|
251 252 |
read_lock(&tasklist_lock); switch (which) { |
ec94fc3d5
|
253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 |
case PRIO_PROCESS: if (who) p = find_task_by_vpid(who); else p = current; if (p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } break; case PRIO_PGRP: if (who) pgrp = find_vpid(who); else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: uid = make_kuid(cred->user_ns, who); user = cred->user; if (!who) uid = cred->uid; else if (!uid_eq(uid, cred->uid)) { user = find_user(uid); if (!user) goto out_unlock; /* No processes for this user */ } do_each_thread(g, p) { |
8639b4613
|
286 |
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { |
7aa2c016d
|
287 |
niceval = nice_to_rlimit(task_nice(p)); |
1da177e4c
|
288 289 290 |
if (niceval > retval) retval = niceval; } |
ec94fc3d5
|
291 292 293 294 |
} while_each_thread(g, p); if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; |
1da177e4c
|
295 296 297 |
} out_unlock: read_unlock(&tasklist_lock); |
701188374
|
298 |
rcu_read_unlock(); |
1da177e4c
|
299 300 301 |
return retval; } |
1da177e4c
|
302 303 304 305 306 307 308 309 310 311 312 313 314 |
/* * 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 |
ec94fc3d5
|
315 |
* 100% compatible with POSIX with saved IDs. |
1da177e4c
|
316 317 318 319 |
* * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ |
2813893f8
|
320 |
#ifdef CONFIG_MULTIUSER |
ae1251ab7
|
321 |
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) |
1da177e4c
|
322 |
{ |
a29c33f4e
|
323 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
324 325 |
const struct cred *old; struct cred *new; |
1da177e4c
|
326 |
int retval; |
a29c33f4e
|
327 328 329 330 331 332 333 334 335 |
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
|
336 |
|
d84f4f992
|
337 338 339 340 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
341 |
retval = -EPERM; |
1da177e4c
|
342 |
if (rgid != (gid_t) -1) { |
a29c33f4e
|
343 344 |
if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || |
c7b96acf1
|
345 |
ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
346 |
new->gid = krgid; |
1da177e4c
|
347 |
else |
d84f4f992
|
348 |
goto error; |
1da177e4c
|
349 350 |
} if (egid != (gid_t) -1) { |
a29c33f4e
|
351 352 353 |
if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || |
c7b96acf1
|
354 |
ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
355 |
new->egid = kegid; |
756184b7d
|
356 |
else |
d84f4f992
|
357 |
goto error; |
1da177e4c
|
358 |
} |
d84f4f992
|
359 |
|
1da177e4c
|
360 |
if (rgid != (gid_t) -1 || |
a29c33f4e
|
361 |
(egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) |
d84f4f992
|
362 363 364 365 366 367 368 369 |
new->sgid = new->egid; new->fsgid = new->egid; return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
370 371 372 |
} /* |
ec94fc3d5
|
373 |
* setgid() is implemented like SysV w/ SAVED_IDS |
1da177e4c
|
374 375 376 |
* * SMP: Same implicit races as above. */ |
ae1251ab7
|
377 |
SYSCALL_DEFINE1(setgid, gid_t, gid) |
1da177e4c
|
378 |
{ |
a29c33f4e
|
379 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
380 381 |
const struct cred *old; struct cred *new; |
1da177e4c
|
382 |
int retval; |
a29c33f4e
|
383 384 385 386 387 |
kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; |
1da177e4c
|
388 |
|
d84f4f992
|
389 390 391 392 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
393 |
retval = -EPERM; |
c7b96acf1
|
394 |
if (ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
395 396 397 |
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
|
398 |
else |
d84f4f992
|
399 |
goto error; |
1da177e4c
|
400 |
|
d84f4f992
|
401 402 403 404 405 |
return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
406 |
} |
54e991242
|
407 |
|
d84f4f992
|
408 409 410 411 |
/* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) |
1da177e4c
|
412 413 |
{ struct user_struct *new_user; |
078de5f70
|
414 |
new_user = alloc_uid(new->uid); |
1da177e4c
|
415 416 |
if (!new_user) return -EAGAIN; |
72fa59970
|
417 418 419 420 421 422 423 |
/* * 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
|
424 |
if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && |
72fa59970
|
425 426 427 428 |
new_user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; |
1da177e4c
|
429 |
|
d84f4f992
|
430 431 |
free_uid(new->user); new->user = new_user; |
1da177e4c
|
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 |
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 |
ec94fc3d5
|
448 |
* 100% compatible with POSIX with saved IDs. |
1da177e4c
|
449 |
*/ |
ae1251ab7
|
450 |
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) |
1da177e4c
|
451 |
{ |
a29c33f4e
|
452 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
453 454 |
const struct cred *old; struct cred *new; |
1da177e4c
|
455 |
int retval; |
a29c33f4e
|
456 457 458 459 460 461 462 463 464 |
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
|
465 |
|
d84f4f992
|
466 467 468 469 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
470 |
retval = -EPERM; |
1da177e4c
|
471 |
if (ruid != (uid_t) -1) { |
a29c33f4e
|
472 473 474 |
new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && |
c7b96acf1
|
475 |
!ns_capable(old->user_ns, CAP_SETUID)) |
d84f4f992
|
476 |
goto error; |
1da177e4c
|
477 478 479 |
} if (euid != (uid_t) -1) { |
a29c33f4e
|
480 481 482 483 |
new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && |
c7b96acf1
|
484 |
!ns_capable(old->user_ns, CAP_SETUID)) |
d84f4f992
|
485 |
goto error; |
1da177e4c
|
486 |
} |
a29c33f4e
|
487 |
if (!uid_eq(new->uid, old->uid)) { |
54e991242
|
488 489 490 491 |
retval = set_user(new); if (retval < 0) goto error; } |
1da177e4c
|
492 |
if (ruid != (uid_t) -1 || |
a29c33f4e
|
493 |
(euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) |
d84f4f992
|
494 495 |
new->suid = new->euid; new->fsuid = new->euid; |
1da177e4c
|
496 |
|
d84f4f992
|
497 498 499 |
retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; |
1da177e4c
|
500 |
|
d84f4f992
|
501 |
return commit_creds(new); |
1da177e4c
|
502 |
|
d84f4f992
|
503 504 505 506 |
error: abort_creds(new); return retval; } |
ec94fc3d5
|
507 |
|
1da177e4c
|
508 |
/* |
ec94fc3d5
|
509 510 |
* setuid() is implemented like SysV with SAVED_IDS * |
1da177e4c
|
511 |
* Note that SAVED_ID's is deficient in that a setuid root program |
ec94fc3d5
|
512 |
* like sendmail, for example, cannot set its uid to be a normal |
1da177e4c
|
513 514 515 516 |
* 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 |
ec94fc3d5
|
517 |
* regain them by swapping the real and effective uid. |
1da177e4c
|
518 |
*/ |
ae1251ab7
|
519 |
SYSCALL_DEFINE1(setuid, uid_t, uid) |
1da177e4c
|
520 |
{ |
a29c33f4e
|
521 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
522 523 |
const struct cred *old; struct cred *new; |
1da177e4c
|
524 |
int retval; |
a29c33f4e
|
525 526 527 528 529 |
kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; |
1da177e4c
|
530 |
|
d84f4f992
|
531 532 533 534 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
535 |
retval = -EPERM; |
c7b96acf1
|
536 |
if (ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
537 538 |
new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { |
54e991242
|
539 540 541 |
retval = set_user(new); if (retval < 0) goto error; |
d84f4f992
|
542 |
} |
a29c33f4e
|
543 |
} else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { |
d84f4f992
|
544 |
goto error; |
1da177e4c
|
545 |
} |
1da177e4c
|
546 |
|
a29c33f4e
|
547 |
new->fsuid = new->euid = kuid; |
d84f4f992
|
548 549 550 551 |
retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; |
1da177e4c
|
552 |
|
d84f4f992
|
553 |
return commit_creds(new); |
1da177e4c
|
554 |
|
d84f4f992
|
555 556 557 |
error: abort_creds(new); return retval; |
1da177e4c
|
558 559 560 561 562 563 564 |
} /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ |
ae1251ab7
|
565 |
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) |
1da177e4c
|
566 |
{ |
a29c33f4e
|
567 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
568 569 |
const struct cred *old; struct cred *new; |
1da177e4c
|
570 |
int retval; |
a29c33f4e
|
571 572 573 574 575 576 577 578 579 580 581 582 583 584 |
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
|
585 |
|
d84f4f992
|
586 587 588 |
new = prepare_creds(); if (!new) return -ENOMEM; |
d84f4f992
|
589 |
old = current_cred(); |
1da177e4c
|
590 |
|
d84f4f992
|
591 |
retval = -EPERM; |
c7b96acf1
|
592 |
if (!ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
593 594 |
if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) |
d84f4f992
|
595 |
goto error; |
a29c33f4e
|
596 597 |
if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) |
d84f4f992
|
598 |
goto error; |
a29c33f4e
|
599 600 |
if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) |
d84f4f992
|
601 |
goto error; |
1da177e4c
|
602 |
} |
d84f4f992
|
603 |
|
1da177e4c
|
604 |
if (ruid != (uid_t) -1) { |
a29c33f4e
|
605 606 |
new->uid = kruid; if (!uid_eq(kruid, old->uid)) { |
54e991242
|
607 608 609 610 |
retval = set_user(new); if (retval < 0) goto error; } |
1da177e4c
|
611 |
} |
d84f4f992
|
612 |
if (euid != (uid_t) -1) |
a29c33f4e
|
613 |
new->euid = keuid; |
1da177e4c
|
614 |
if (suid != (uid_t) -1) |
a29c33f4e
|
615 |
new->suid = ksuid; |
d84f4f992
|
616 |
new->fsuid = new->euid; |
1da177e4c
|
617 |
|
d84f4f992
|
618 619 620 |
retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; |
1da177e4c
|
621 |
|
d84f4f992
|
622 |
return commit_creds(new); |
1da177e4c
|
623 |
|
d84f4f992
|
624 625 626 |
error: abort_creds(new); return retval; |
1da177e4c
|
627 |
} |
a29c33f4e
|
628 |
SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) |
1da177e4c
|
629 |
{ |
86a264abe
|
630 |
const struct cred *cred = current_cred(); |
1da177e4c
|
631 |
int retval; |
a29c33f4e
|
632 633 634 635 636 |
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
|
637 |
|
ec94fc3d5
|
638 639 640 641 642 643 |
retval = put_user(ruid, ruidp); if (!retval) { retval = put_user(euid, euidp); if (!retval) return put_user(suid, suidp); } |
1da177e4c
|
644 645 646 647 648 649 |
return retval; } /* * Same as above, but for rgid, egid, sgid. */ |
ae1251ab7
|
650 |
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) |
1da177e4c
|
651 |
{ |
a29c33f4e
|
652 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
653 654 |
const struct cred *old; struct cred *new; |
1da177e4c
|
655 |
int retval; |
a29c33f4e
|
656 657 658 659 660 661 662 663 664 665 666 667 |
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
|
668 |
|
d84f4f992
|
669 670 671 672 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
673 |
retval = -EPERM; |
c7b96acf1
|
674 |
if (!ns_capable(old->user_ns, CAP_SETGID)) { |
a29c33f4e
|
675 676 |
if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) |
d84f4f992
|
677 |
goto error; |
a29c33f4e
|
678 679 |
if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) |
d84f4f992
|
680 |
goto error; |
a29c33f4e
|
681 682 |
if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) |
d84f4f992
|
683 |
goto error; |
1da177e4c
|
684 |
} |
d84f4f992
|
685 |
|
1da177e4c
|
686 |
if (rgid != (gid_t) -1) |
a29c33f4e
|
687 |
new->gid = krgid; |
d84f4f992
|
688 |
if (egid != (gid_t) -1) |
a29c33f4e
|
689 |
new->egid = kegid; |
1da177e4c
|
690 |
if (sgid != (gid_t) -1) |
a29c33f4e
|
691 |
new->sgid = ksgid; |
d84f4f992
|
692 |
new->fsgid = new->egid; |
1da177e4c
|
693 |
|
d84f4f992
|
694 695 696 697 698 |
return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
699 |
} |
a29c33f4e
|
700 |
SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) |
1da177e4c
|
701 |
{ |
86a264abe
|
702 |
const struct cred *cred = current_cred(); |
1da177e4c
|
703 |
int retval; |
a29c33f4e
|
704 705 706 707 708 |
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
|
709 |
|
ec94fc3d5
|
710 711 712 713 714 715 |
retval = put_user(rgid, rgidp); if (!retval) { retval = put_user(egid, egidp); if (!retval) retval = put_user(sgid, sgidp); } |
1da177e4c
|
716 717 718 719 720 721 722 723 724 725 726 |
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
|
727 |
SYSCALL_DEFINE1(setfsuid, uid_t, uid) |
1da177e4c
|
728 |
{ |
d84f4f992
|
729 730 731 |
const struct cred *old; struct cred *new; uid_t old_fsuid; |
a29c33f4e
|
732 733 734 735 736 737 738 739 |
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
|
740 |
|
d84f4f992
|
741 742 |
new = prepare_creds(); if (!new) |
a29c33f4e
|
743 |
return old_fsuid; |
1da177e4c
|
744 |
|
a29c33f4e
|
745 746 |
if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || |
c7b96acf1
|
747 |
ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
748 749 |
if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; |
d84f4f992
|
750 751 |
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; |
1da177e4c
|
752 |
} |
1da177e4c
|
753 |
} |
d84f4f992
|
754 755 |
abort_creds(new); return old_fsuid; |
1da177e4c
|
756 |
|
d84f4f992
|
757 758 |
change_okay: commit_creds(new); |
1da177e4c
|
759 760 761 762 |
return old_fsuid; } /* |
f42df9e65
|
763 |
* Samma på svenska.. |
1da177e4c
|
764 |
*/ |
ae1251ab7
|
765 |
SYSCALL_DEFINE1(setfsgid, gid_t, gid) |
1da177e4c
|
766 |
{ |
d84f4f992
|
767 768 769 |
const struct cred *old; struct cred *new; gid_t old_fsgid; |
a29c33f4e
|
770 771 772 773 774 775 776 777 |
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
|
778 779 780 |
new = prepare_creds(); if (!new) |
a29c33f4e
|
781 |
return old_fsgid; |
1da177e4c
|
782 |
|
a29c33f4e
|
783 784 |
if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || |
c7b96acf1
|
785 |
ns_capable(old->user_ns, CAP_SETGID)) { |
a29c33f4e
|
786 787 |
if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; |
d84f4f992
|
788 |
goto change_okay; |
1da177e4c
|
789 |
} |
1da177e4c
|
790 |
} |
d84f4f992
|
791 |
|
d84f4f992
|
792 793 794 795 796 |
abort_creds(new); return old_fsgid; change_okay: commit_creds(new); |
1da177e4c
|
797 798 |
return old_fsgid; } |
2813893f8
|
799 |
#endif /* CONFIG_MULTIUSER */ |
1da177e4c
|
800 |
|
4a22f1663
|
801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 |
/** * 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
|
861 862 |
void do_sys_times(struct tms *tms) { |
0cf55e1ec
|
863 |
cputime_t tgutime, tgstime, cutime, cstime; |
f06febc96
|
864 |
|
e80d0a1ae
|
865 |
thread_group_cputime_adjusted(current, &tgutime, &tgstime); |
f06febc96
|
866 867 |
cutime = current->signal->cutime; cstime = current->signal->cstime; |
0cf55e1ec
|
868 869 |
tms->tms_utime = cputime_to_clock_t(tgutime); tms->tms_stime = cputime_to_clock_t(tgstime); |
f06febc96
|
870 871 872 |
tms->tms_cutime = cputime_to_clock_t(cutime); tms->tms_cstime = cputime_to_clock_t(cstime); } |
58fd3aa28
|
873 |
SYSCALL_DEFINE1(times, struct tms __user *, tbuf) |
1da177e4c
|
874 |
{ |
1da177e4c
|
875 876 |
if (tbuf) { struct tms tmp; |
f06febc96
|
877 878 |
do_sys_times(&tmp); |
1da177e4c
|
879 880 881 |
if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } |
e3d5a27d5
|
882 |
force_successful_syscall_return(); |
1da177e4c
|
883 884 885 886 887 888 889 890 891 892 893 894 |
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 * |
98611e4e6
|
895 |
* !PF_FORKNOEXEC check to conform completely to POSIX. |
1da177e4c
|
896 |
*/ |
b290ebe2c
|
897 |
SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) |
1da177e4c
|
898 899 |
{ struct task_struct *p; |
ee0acf90d
|
900 |
struct task_struct *group_leader = current->group_leader; |
4e021306c
|
901 902 |
struct pid *pgrp; int err; |
1da177e4c
|
903 904 |
if (!pid) |
b488893a3
|
905 |
pid = task_pid_vnr(group_leader); |
1da177e4c
|
906 907 908 909 |
if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; |
950eaaca6
|
910 |
rcu_read_lock(); |
1da177e4c
|
911 912 913 914 915 916 917 |
/* 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
|
918 |
p = find_task_by_vpid(pid); |
1da177e4c
|
919 920 921 922 923 924 |
if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; |
4e021306c
|
925 |
if (same_thread_group(p->real_parent, group_leader)) { |
1da177e4c
|
926 |
err = -EPERM; |
41487c65b
|
927 |
if (task_session(p) != task_session(group_leader)) |
1da177e4c
|
928 929 |
goto out; err = -EACCES; |
98611e4e6
|
930 |
if (!(p->flags & PF_FORKNOEXEC)) |
1da177e4c
|
931 932 933 |
goto out; } else { err = -ESRCH; |
ee0acf90d
|
934 |
if (p != group_leader) |
1da177e4c
|
935 936 937 938 939 940 |
goto out; } err = -EPERM; if (p->signal->leader) goto out; |
4e021306c
|
941 |
pgrp = task_pid(p); |
1da177e4c
|
942 |
if (pgid != pid) { |
b488893a3
|
943 |
struct task_struct *g; |
1da177e4c
|
944 |
|
4e021306c
|
945 946 |
pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); |
41487c65b
|
947 |
if (!g || task_session(g) != task_session(group_leader)) |
f020bc468
|
948 |
goto out; |
1da177e4c
|
949 |
} |
1da177e4c
|
950 951 952 |
err = security_task_setpgid(p, pgid); if (err) goto out; |
1b0f7ffd0
|
953 |
if (task_pgrp(p) != pgrp) |
83beaf3c6
|
954 |
change_pid(p, PIDTYPE_PGID, pgrp); |
1da177e4c
|
955 956 957 958 959 |
err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); |
950eaaca6
|
960 |
rcu_read_unlock(); |
1da177e4c
|
961 962 |
return err; } |
dbf040d9d
|
963 |
SYSCALL_DEFINE1(getpgid, pid_t, pid) |
1da177e4c
|
964 |
{ |
12a3de0a9
|
965 966 967 968 969 |
struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); |
756184b7d
|
970 |
if (!pid) |
12a3de0a9
|
971 |
grp = task_pgrp(current); |
756184b7d
|
972 |
else { |
1da177e4c
|
973 |
retval = -ESRCH; |
12a3de0a9
|
974 975 976 977 978 979 980 981 982 983 |
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
|
984 |
} |
12a3de0a9
|
985 986 987 988 |
retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; |
1da177e4c
|
989 990 991 |
} #ifdef __ARCH_WANT_SYS_GETPGRP |
dbf040d9d
|
992 |
SYSCALL_DEFINE0(getpgrp) |
1da177e4c
|
993 |
{ |
12a3de0a9
|
994 |
return sys_getpgid(0); |
1da177e4c
|
995 996 997 |
} #endif |
dbf040d9d
|
998 |
SYSCALL_DEFINE1(getsid, pid_t, pid) |
1da177e4c
|
999 |
{ |
1dd768c08
|
1000 1001 1002 1003 1004 |
struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); |
756184b7d
|
1005 |
if (!pid) |
1dd768c08
|
1006 |
sid = task_session(current); |
756184b7d
|
1007 |
else { |
1da177e4c
|
1008 |
retval = -ESRCH; |
1dd768c08
|
1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 |
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
|
1019 |
} |
1dd768c08
|
1020 1021 1022 1023 |
retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; |
1da177e4c
|
1024 |
} |
81dabb464
|
1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 |
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
|
1035 |
SYSCALL_DEFINE0(setsid) |
1da177e4c
|
1036 |
{ |
e19f247a3
|
1037 |
struct task_struct *group_leader = current->group_leader; |
e4cc0a9c8
|
1038 1039 |
struct pid *sid = task_pid(group_leader); pid_t session = pid_vnr(sid); |
1da177e4c
|
1040 |
int err = -EPERM; |
1da177e4c
|
1041 |
write_lock_irq(&tasklist_lock); |
390e2ff07
|
1042 1043 1044 |
/* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; |
430c62312
|
1045 1046 |
/* Fail if a process group id already exists that equals the * proposed session id. |
390e2ff07
|
1047 |
*/ |
6806aac6d
|
1048 |
if (pid_task(sid, PIDTYPE_PGID)) |
1da177e4c
|
1049 |
goto out; |
e19f247a3
|
1050 |
group_leader->signal->leader = 1; |
81dabb464
|
1051 |
set_special_pids(sid); |
24ec839c4
|
1052 |
|
9c9f4ded9
|
1053 |
proc_clear_tty(group_leader); |
24ec839c4
|
1054 |
|
e4cc0a9c8
|
1055 |
err = session; |
1da177e4c
|
1056 1057 |
out: write_unlock_irq(&tasklist_lock); |
5091faa44
|
1058 |
if (err > 0) { |
0d0df599f
|
1059 |
proc_sid_connector(group_leader); |
5091faa44
|
1060 1061 |
sched_autogroup_create_attach(group_leader); } |
1da177e4c
|
1062 1063 |
return err; } |
1da177e4c
|
1064 |
DECLARE_RWSEM(uts_sem); |
e28cbf229
|
1065 1066 |
#ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ |
46da27664
|
1067 |
(personality(current->personality) == PER_LINUX32 && \ |
e28cbf229
|
1068 1069 1070 1071 1072 |
copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif |
be27425dc
|
1073 1074 1075 |
/* * 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 |
39afb5ee4
|
1076 |
* And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60. |
be27425dc
|
1077 |
*/ |
2702b1526
|
1078 |
static int override_release(char __user *release, size_t len) |
be27425dc
|
1079 1080 |
{ int ret = 0; |
be27425dc
|
1081 1082 |
if (current->personality & UNAME26) { |
2702b1526
|
1083 1084 |
const char *rest = UTS_RELEASE; char buf[65] = { 0 }; |
be27425dc
|
1085 1086 |
int ndots = 0; unsigned v; |
2702b1526
|
1087 |
size_t copy; |
be27425dc
|
1088 1089 1090 1091 1092 1093 1094 1095 |
while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } |
39afb5ee4
|
1096 |
v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; |
31fd84b95
|
1097 |
copy = clamp_t(size_t, len, 1, sizeof(buf)); |
2702b1526
|
1098 1099 |
copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); |
be27425dc
|
1100 1101 1102 |
} return ret; } |
e48fbb699
|
1103 |
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) |
1da177e4c
|
1104 1105 1106 1107 |
{ int errno = 0; down_read(&uts_sem); |
e9ff3990f
|
1108 |
if (copy_to_user(name, utsname(), sizeof *name)) |
1da177e4c
|
1109 1110 |
errno = -EFAULT; up_read(&uts_sem); |
e28cbf229
|
1111 |
|
be27425dc
|
1112 1113 |
if (!errno && override_release(name->release, sizeof(name->release))) errno = -EFAULT; |
e28cbf229
|
1114 1115 |
if (!errno && override_architecture(name)) errno = -EFAULT; |
1da177e4c
|
1116 1117 |
return errno; } |
5cacdb4ad
|
1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 |
#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
|
1133 1134 |
if (!error && override_release(name->release, sizeof(name->release))) error = -EFAULT; |
5cacdb4ad
|
1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 |
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
|
1169 1170 |
if (!error && override_release(name->release, sizeof(name->release))) error = -EFAULT; |
5cacdb4ad
|
1171 1172 1173 |
return error ? -EFAULT : 0; } #endif |
5a8a82b1d
|
1174 |
SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) |
1da177e4c
|
1175 1176 1177 |
{ int errno; char tmp[__NEW_UTS_LEN]; |
bb96a6f50
|
1178 |
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) |
1da177e4c
|
1179 |
return -EPERM; |
fc832ad36
|
1180 |
|
1da177e4c
|
1181 1182 1183 1184 1185 |
if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; down_write(&uts_sem); errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { |
9679e4dd6
|
1186 1187 1188 1189 |
struct new_utsname *u = utsname(); memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); |
1da177e4c
|
1190 |
errno = 0; |
499eea6bf
|
1191 |
uts_proc_notify(UTS_PROC_HOSTNAME); |
1da177e4c
|
1192 1193 1194 1195 1196 1197 |
} up_write(&uts_sem); return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME |
5a8a82b1d
|
1198 |
SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) |
1da177e4c
|
1199 1200 |
{ int i, errno; |
9679e4dd6
|
1201 |
struct new_utsname *u; |
1da177e4c
|
1202 1203 1204 1205 |
if (len < 0) return -EINVAL; down_read(&uts_sem); |
9679e4dd6
|
1206 1207 |
u = utsname(); i = 1 + strlen(u->nodename); |
1da177e4c
|
1208 1209 1210 |
if (i > len) i = len; errno = 0; |
9679e4dd6
|
1211 |
if (copy_to_user(name, u->nodename, i)) |
1da177e4c
|
1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 |
errno = -EFAULT; up_read(&uts_sem); return errno; } #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ |
5a8a82b1d
|
1223 |
SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) |
1da177e4c
|
1224 1225 1226 |
{ int errno; char tmp[__NEW_UTS_LEN]; |
fc832ad36
|
1227 |
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) |
1da177e4c
|
1228 1229 1230 1231 1232 1233 1234 |
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
|
1235 1236 1237 1238 |
struct new_utsname *u = utsname(); memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); |
1da177e4c
|
1239 |
errno = 0; |
499eea6bf
|
1240 |
uts_proc_notify(UTS_PROC_DOMAINNAME); |
1da177e4c
|
1241 1242 1243 1244 |
} up_write(&uts_sem); return errno; } |
e48fbb699
|
1245 |
SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) |
1da177e4c
|
1246 |
{ |
b95183453
|
1247 1248 1249 1250 1251 1252 1253 1254 |
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
|
1255 1256 1257 1258 1259 1260 1261 |
} #ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ |
e48fbb699
|
1262 1263 |
SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) |
1da177e4c
|
1264 1265 1266 1267 1268 1269 1270 1271 |
{ 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
|
1272 |
if (x.rlim_cur > 0x7FFFFFFF) |
1da177e4c
|
1273 |
x.rlim_cur = 0x7FFFFFFF; |
756184b7d
|
1274 |
if (x.rlim_max > 0x7FFFFFFF) |
1da177e4c
|
1275 |
x.rlim_max = 0x7FFFFFFF; |
ec94fc3d5
|
1276 |
return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; |
1da177e4c
|
1277 1278 1279 |
} #endif |
c022a0aca
|
1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 |
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
|
1312 |
/* make sure you are allowed to change @tsk limits before calling this */ |
5b41535aa
|
1313 1314 |
int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) |
1da177e4c
|
1315 |
{ |
5b41535aa
|
1316 |
struct rlimit *rlim; |
86f162f4c
|
1317 |
int retval = 0; |
1da177e4c
|
1318 1319 1320 |
if (resource >= RLIM_NLIMITS) return -EINVAL; |
5b41535aa
|
1321 1322 1323 1324 1325 1326 1327 |
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
|
1328 |
|
1c1e618dd
|
1329 1330 1331 1332 1333 1334 |
/* protect tsk->signal and tsk->sighand from disappearing */ read_lock(&tasklist_lock); if (!tsk->sighand) { retval = -ESRCH; goto out; } |
5b41535aa
|
1335 |
rlim = tsk->signal->rlim + resource; |
86f162f4c
|
1336 |
task_lock(tsk->group_leader); |
5b41535aa
|
1337 |
if (new_rlim) { |
fc832ad36
|
1338 1339 |
/* Keep the capable check against init_user_ns until cgroups can contain all limits */ |
5b41535aa
|
1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 |
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
|
1361 |
} |
7855c35da
|
1362 |
task_unlock(tsk->group_leader); |
1da177e4c
|
1363 |
|
d3561f78f
|
1364 1365 1366 1367 1368 1369 |
/* * 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
|
1370 1371 1372 |
if (!retval && new_rlim && resource == RLIMIT_CPU && new_rlim->rlim_cur != RLIM_INFINITY) update_rlimit_cpu(tsk, new_rlim->rlim_cur); |
ec9e16bac
|
1373 |
out: |
1c1e618dd
|
1374 |
read_unlock(&tasklist_lock); |
2fb9d2689
|
1375 |
return retval; |
1da177e4c
|
1376 |
} |
c022a0aca
|
1377 1378 1379 1380 |
/* rcu lock must be held */ static int check_prlimit_permission(struct task_struct *task) { const struct cred *cred = current_cred(), *tcred; |
fc832ad36
|
1381 1382 |
if (current == task) return 0; |
c022a0aca
|
1383 |
|
fc832ad36
|
1384 |
tcred = __task_cred(task); |
5af662030
|
1385 1386 1387 1388 1389 1390 |
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
|
1391 |
return 0; |
c4a4d6037
|
1392 |
if (ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) |
fc832ad36
|
1393 1394 1395 |
return 0; return -EPERM; |
c022a0aca
|
1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 |
} 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
|
1439 1440 1441 1442 1443 1444 |
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
|
1445 |
return do_prlimit(current, resource, &new_rlim, NULL); |
7855c35da
|
1446 |
} |
1da177e4c
|
1447 1448 1449 1450 1451 1452 1453 1454 |
/* * 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
|
1455 1456 1457 1458 1459 1460 1461 |
* 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
|
1462 |
* |
de047c1bc
|
1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 |
* 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
|
1477 |
* |
1da177e4c
|
1478 |
*/ |
f06febc96
|
1479 |
static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) |
679c9cd4a
|
1480 |
{ |
679c9cd4a
|
1481 1482 1483 1484 1485 1486 1487 |
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
|
1488 1489 1490 1491 |
static void k_getrusage(struct task_struct *p, int who, struct rusage *r) { struct task_struct *t; unsigned long flags; |
0cf55e1ec
|
1492 |
cputime_t tgutime, tgstime, utime, stime; |
1f10206cf
|
1493 |
unsigned long maxrss = 0; |
1da177e4c
|
1494 |
|
ec94fc3d5
|
1495 |
memset((char *)r, 0, sizeof (*r)); |
648616343
|
1496 |
utime = stime = 0; |
1da177e4c
|
1497 |
|
679c9cd4a
|
1498 |
if (who == RUSAGE_THREAD) { |
e80d0a1ae
|
1499 |
task_cputime_adjusted(current, &utime, &stime); |
f06febc96
|
1500 |
accumulate_thread_rusage(p, r); |
1f10206cf
|
1501 |
maxrss = p->signal->maxrss; |
679c9cd4a
|
1502 1503 |
goto out; } |
d6cf723a1
|
1504 |
if (!lock_task_sighand(p, &flags)) |
de047c1bc
|
1505 |
return; |
0f59cc4a3
|
1506 |
|
1da177e4c
|
1507 |
switch (who) { |
ec94fc3d5
|
1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 |
case RUSAGE_BOTH: case RUSAGE_CHILDREN: 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; r->ru_inblock = p->signal->cinblock; r->ru_oublock = p->signal->coublock; maxrss = p->signal->cmaxrss; if (who == RUSAGE_CHILDREN) |
1da177e4c
|
1521 |
break; |
0f59cc4a3
|
1522 |
|
ec94fc3d5
|
1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 |
case RUSAGE_SELF: thread_group_cputime_adjusted(p, &tgutime, &tgstime); utime += tgutime; stime += tgstime; 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; r->ru_inblock += p->signal->inblock; r->ru_oublock += p->signal->oublock; if (maxrss < p->signal->maxrss) maxrss = p->signal->maxrss; t = p; do { accumulate_thread_rusage(t, r); } while_each_thread(p, t); break; default: BUG(); |
1da177e4c
|
1543 |
} |
de047c1bc
|
1544 |
unlock_task_sighand(p, &flags); |
de047c1bc
|
1545 |
|
679c9cd4a
|
1546 |
out: |
0f59cc4a3
|
1547 1548 |
cputime_to_timeval(utime, &r->ru_utime); cputime_to_timeval(stime, &r->ru_stime); |
1f10206cf
|
1549 1550 1551 |
if (who != RUSAGE_CHILDREN) { struct mm_struct *mm = get_task_mm(p); |
ec94fc3d5
|
1552 |
|
1f10206cf
|
1553 1554 1555 1556 1557 1558 |
if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } } r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ |
1da177e4c
|
1559 1560 1561 1562 1563 |
} int getrusage(struct task_struct *p, int who, struct rusage __user *ru) { struct rusage r; |
ec94fc3d5
|
1564 |
|
1da177e4c
|
1565 |
k_getrusage(p, who, &r); |
1da177e4c
|
1566 1567 |
return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; } |
e48fbb699
|
1568 |
SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) |
1da177e4c
|
1569 |
{ |
679c9cd4a
|
1570 1571 |
if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) |
1da177e4c
|
1572 1573 1574 |
return -EINVAL; return getrusage(current, who, ru); } |
8d2d5c4a2
|
1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 |
#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
|
1588 |
SYSCALL_DEFINE1(umask, int, mask) |
1da177e4c
|
1589 1590 1591 1592 |
{ mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } |
3b7391de6
|
1593 |
|
6e399cd14
|
1594 |
static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) |
b32dfe377
|
1595 |
{ |
2903ff019
|
1596 |
struct fd exe; |
6e399cd14
|
1597 |
struct file *old_exe, *exe_file; |
496ad9aa8
|
1598 |
struct inode *inode; |
2903ff019
|
1599 |
int err; |
b32dfe377
|
1600 |
|
2903ff019
|
1601 1602 |
exe = fdget(fd); if (!exe.file) |
b32dfe377
|
1603 |
return -EBADF; |
496ad9aa8
|
1604 |
inode = file_inode(exe.file); |
b32dfe377
|
1605 1606 1607 1608 1609 1610 1611 |
/* * 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; |
90f8572b0
|
1612 |
if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path)) |
b32dfe377
|
1613 |
goto exit; |
496ad9aa8
|
1614 |
err = inode_permission(inode, MAY_EXEC); |
b32dfe377
|
1615 1616 |
if (err) goto exit; |
bafb282df
|
1617 |
/* |
4229fb1dc
|
1618 |
* Forbid mm->exe_file change if old file still mapped. |
bafb282df
|
1619 |
*/ |
6e399cd14
|
1620 |
exe_file = get_mm_exe_file(mm); |
bafb282df
|
1621 |
err = -EBUSY; |
6e399cd14
|
1622 |
if (exe_file) { |
4229fb1dc
|
1623 |
struct vm_area_struct *vma; |
6e399cd14
|
1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 |
down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!vma->vm_file) continue; if (path_equal(&vma->vm_file->f_path, &exe_file->f_path)) goto exit_err; } up_read(&mm->mmap_sem); fput(exe_file); |
bafb282df
|
1635 |
} |
b32dfe377
|
1636 1637 1638 1639 1640 1641 |
/* * 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
|
1642 1643 |
err = -EPERM; if (test_and_set_bit(MMF_EXE_FILE_CHANGED, &mm->flags)) |
71fe97e18
|
1644 |
goto exit; |
bafb282df
|
1645 |
|
4229fb1dc
|
1646 |
err = 0; |
6e399cd14
|
1647 1648 1649 1650 1651 |
/* set the new file, lockless */ get_file(exe.file); old_exe = xchg(&mm->exe_file, exe.file); if (old_exe) fput(old_exe); |
b32dfe377
|
1652 |
exit: |
2903ff019
|
1653 |
fdput(exe); |
b32dfe377
|
1654 |
return err; |
6e399cd14
|
1655 1656 1657 1658 |
exit_err: up_read(&mm->mmap_sem); fput(exe_file); goto exit; |
b32dfe377
|
1659 |
} |
f606b77f1
|
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 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 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 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 |
/* * WARNING: we don't require any capability here so be very careful * in what is allowed for modification from userspace. */ static int validate_prctl_map(struct prctl_mm_map *prctl_map) { unsigned long mmap_max_addr = TASK_SIZE; struct mm_struct *mm = current->mm; int error = -EINVAL, i; static const unsigned char offsets[] = { offsetof(struct prctl_mm_map, start_code), offsetof(struct prctl_mm_map, end_code), offsetof(struct prctl_mm_map, start_data), offsetof(struct prctl_mm_map, end_data), offsetof(struct prctl_mm_map, start_brk), offsetof(struct prctl_mm_map, brk), offsetof(struct prctl_mm_map, start_stack), offsetof(struct prctl_mm_map, arg_start), offsetof(struct prctl_mm_map, arg_end), offsetof(struct prctl_mm_map, env_start), offsetof(struct prctl_mm_map, env_end), }; /* * Make sure the members are not somewhere outside * of allowed address space. */ for (i = 0; i < ARRAY_SIZE(offsets); i++) { u64 val = *(u64 *)((char *)prctl_map + offsets[i]); if ((unsigned long)val >= mmap_max_addr || (unsigned long)val < mmap_min_addr) goto out; } /* * Make sure the pairs are ordered. */ #define __prctl_check_order(__m1, __op, __m2) \ ((unsigned long)prctl_map->__m1 __op \ (unsigned long)prctl_map->__m2) ? 0 : -EINVAL error = __prctl_check_order(start_code, <, end_code); error |= __prctl_check_order(start_data, <, end_data); error |= __prctl_check_order(start_brk, <=, brk); error |= __prctl_check_order(arg_start, <=, arg_end); error |= __prctl_check_order(env_start, <=, env_end); if (error) goto out; #undef __prctl_check_order error = -EINVAL; /* * @brk should be after @end_data in traditional maps. */ if (prctl_map->start_brk <= prctl_map->end_data || prctl_map->brk <= prctl_map->end_data) goto out; /* * Neither we should allow to override limits if they set. */ if (check_data_rlimit(rlimit(RLIMIT_DATA), prctl_map->brk, prctl_map->start_brk, prctl_map->end_data, prctl_map->start_data)) goto out; /* * Someone is trying to cheat the auxv vector. */ if (prctl_map->auxv_size) { if (!prctl_map->auxv || prctl_map->auxv_size > sizeof(mm->saved_auxv)) goto out; } /* * Finally, make sure the caller has the rights to * change /proc/pid/exe link: only local root should * be allowed to. */ if (prctl_map->exe_fd != (u32)-1) { struct user_namespace *ns = current_user_ns(); const struct cred *cred = current_cred(); if (!uid_eq(cred->uid, make_kuid(ns, 0)) || !gid_eq(cred->gid, make_kgid(ns, 0))) goto out; } error = 0; out: return error; } |
4a00e9df2
|
1754 |
#ifdef CONFIG_CHECKPOINT_RESTORE |
f606b77f1
|
1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 |
static int prctl_set_mm_map(int opt, const void __user *addr, unsigned long data_size) { struct prctl_mm_map prctl_map = { .exe_fd = (u32)-1, }; unsigned long user_auxv[AT_VECTOR_SIZE]; struct mm_struct *mm = current->mm; int error; BUILD_BUG_ON(sizeof(user_auxv) != sizeof(mm->saved_auxv)); BUILD_BUG_ON(sizeof(struct prctl_mm_map) > 256); if (opt == PR_SET_MM_MAP_SIZE) return put_user((unsigned int)sizeof(prctl_map), (unsigned int __user *)addr); if (data_size != sizeof(prctl_map)) return -EINVAL; if (copy_from_user(&prctl_map, addr, sizeof(prctl_map))) return -EFAULT; error = validate_prctl_map(&prctl_map); if (error) return error; if (prctl_map.auxv_size) { memset(user_auxv, 0, sizeof(user_auxv)); if (copy_from_user(user_auxv, (const void __user *)prctl_map.auxv, prctl_map.auxv_size)) return -EFAULT; /* Last entry must be AT_NULL as specification requires */ user_auxv[AT_VECTOR_SIZE - 2] = AT_NULL; user_auxv[AT_VECTOR_SIZE - 1] = AT_NULL; } |
ddf1d398e
|
1790 |
if (prctl_map.exe_fd != (u32)-1) { |
6e399cd14
|
1791 |
error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); |
ddf1d398e
|
1792 1793 1794 1795 1796 |
if (error) return error; } down_write(&mm->mmap_sem); |
f606b77f1
|
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 |
/* * We don't validate if these members are pointing to * real present VMAs because application may have correspond * VMAs already unmapped and kernel uses these members for statistics * output in procfs mostly, except * * - @start_brk/@brk which are used in do_brk but kernel lookups * for VMAs when updating these memvers so anything wrong written * here cause kernel to swear at userspace program but won't lead * to any problem in kernel itself */ mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; /* * Note this update of @saved_auxv is lockless thus * if someone reads this member in procfs while we're * updating -- it may get partly updated results. It's * known and acceptable trade off: we leave it as is to * not introduce additional locks here making the kernel * more complex. */ if (prctl_map.auxv_size) memcpy(mm->saved_auxv, user_auxv, sizeof(user_auxv)); |
ddf1d398e
|
1832 1833 |
up_write(&mm->mmap_sem); return 0; |
f606b77f1
|
1834 1835 |
} #endif /* CONFIG_CHECKPOINT_RESTORE */ |
4a00e9df2
|
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 |
static int prctl_set_auxv(struct mm_struct *mm, unsigned long addr, unsigned long len) { /* * This doesn't move the auxiliary vector itself since it's pinned to * mm_struct, but it permits filling the vector with new values. It's * up to the caller to provide sane values here, otherwise userspace * tools which use this vector might be unhappy. */ unsigned long user_auxv[AT_VECTOR_SIZE]; if (len > sizeof(user_auxv)) return -EINVAL; if (copy_from_user(user_auxv, (const void __user *)addr, len)) 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, len); task_unlock(current); return 0; } |
028ee4be3
|
1865 1866 1867 |
static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { |
028ee4be3
|
1868 |
struct mm_struct *mm = current->mm; |
4a00e9df2
|
1869 |
struct prctl_mm_map prctl_map; |
fe8c7f5cb
|
1870 1871 |
struct vm_area_struct *vma; int error; |
028ee4be3
|
1872 |
|
f606b77f1
|
1873 1874 1875 |
if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && opt != PR_SET_MM_MAP && opt != PR_SET_MM_MAP_SIZE))) |
028ee4be3
|
1876 |
return -EINVAL; |
f606b77f1
|
1877 1878 1879 1880 |
#ifdef CONFIG_CHECKPOINT_RESTORE if (opt == PR_SET_MM_MAP || opt == PR_SET_MM_MAP_SIZE) return prctl_set_mm_map(opt, (const void __user *)addr, arg4); #endif |
79f0713d4
|
1881 |
if (!capable(CAP_SYS_RESOURCE)) |
028ee4be3
|
1882 |
return -EPERM; |
6e399cd14
|
1883 1884 |
if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); |
b32dfe377
|
1885 |
|
4a00e9df2
|
1886 1887 |
if (opt == PR_SET_MM_AUXV) return prctl_set_auxv(mm, addr, arg4); |
1ad75b9e1
|
1888 |
if (addr >= TASK_SIZE || addr < mmap_min_addr) |
028ee4be3
|
1889 |
return -EINVAL; |
fe8c7f5cb
|
1890 |
error = -EINVAL; |
ddf1d398e
|
1891 |
down_write(&mm->mmap_sem); |
028ee4be3
|
1892 |
vma = find_vma(mm, addr); |
4a00e9df2
|
1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 |
prctl_map.start_code = mm->start_code; prctl_map.end_code = mm->end_code; prctl_map.start_data = mm->start_data; prctl_map.end_data = mm->end_data; prctl_map.start_brk = mm->start_brk; prctl_map.brk = mm->brk; prctl_map.start_stack = mm->start_stack; prctl_map.arg_start = mm->arg_start; prctl_map.arg_end = mm->arg_end; prctl_map.env_start = mm->env_start; prctl_map.env_end = mm->env_end; prctl_map.auxv = NULL; prctl_map.auxv_size = 0; prctl_map.exe_fd = -1; |
028ee4be3
|
1907 1908 |
switch (opt) { case PR_SET_MM_START_CODE: |
4a00e9df2
|
1909 |
prctl_map.start_code = addr; |
fe8c7f5cb
|
1910 |
break; |
028ee4be3
|
1911 |
case PR_SET_MM_END_CODE: |
4a00e9df2
|
1912 |
prctl_map.end_code = addr; |
028ee4be3
|
1913 |
break; |
028ee4be3
|
1914 |
case PR_SET_MM_START_DATA: |
4a00e9df2
|
1915 |
prctl_map.start_data = addr; |
028ee4be3
|
1916 |
break; |
fe8c7f5cb
|
1917 |
case PR_SET_MM_END_DATA: |
4a00e9df2
|
1918 1919 1920 1921 |
prctl_map.end_data = addr; break; case PR_SET_MM_START_STACK: prctl_map.start_stack = addr; |
028ee4be3
|
1922 |
break; |
028ee4be3
|
1923 |
case PR_SET_MM_START_BRK: |
4a00e9df2
|
1924 |
prctl_map.start_brk = addr; |
028ee4be3
|
1925 |
break; |
028ee4be3
|
1926 |
case PR_SET_MM_BRK: |
4a00e9df2
|
1927 |
prctl_map.brk = addr; |
028ee4be3
|
1928 |
break; |
4a00e9df2
|
1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 |
case PR_SET_MM_ARG_START: prctl_map.arg_start = addr; break; case PR_SET_MM_ARG_END: prctl_map.arg_end = addr; break; case PR_SET_MM_ENV_START: prctl_map.env_start = addr; break; case PR_SET_MM_ENV_END: prctl_map.env_end = addr; break; default: goto out; } error = validate_prctl_map(&prctl_map); if (error) goto out; |
028ee4be3
|
1948 |
|
4a00e9df2
|
1949 |
switch (opt) { |
fe8c7f5cb
|
1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 |
/* * 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; } |
028ee4be3
|
1966 |
} |
4a00e9df2
|
1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 |
mm->start_code = prctl_map.start_code; mm->end_code = prctl_map.end_code; mm->start_data = prctl_map.start_data; mm->end_data = prctl_map.end_data; mm->start_brk = prctl_map.start_brk; mm->brk = prctl_map.brk; mm->start_stack = prctl_map.start_stack; mm->arg_start = prctl_map.arg_start; mm->arg_end = prctl_map.arg_end; mm->env_start = prctl_map.env_start; mm->env_end = prctl_map.env_end; |
028ee4be3
|
1978 |
error = 0; |
028ee4be3
|
1979 |
out: |
ddf1d398e
|
1980 |
up_write(&mm->mmap_sem); |
028ee4be3
|
1981 1982 |
return error; } |
300f786b2
|
1983 |
|
52b369415
|
1984 |
#ifdef CONFIG_CHECKPOINT_RESTORE |
300f786b2
|
1985 1986 1987 1988 |
static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return put_user(me->clear_child_tid, tid_addr); } |
52b369415
|
1989 |
#else |
300f786b2
|
1990 1991 1992 1993 |
static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return -EINVAL; } |
028ee4be3
|
1994 |
#endif |
c4ea37c26
|
1995 1996 |
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) |
1da177e4c
|
1997 |
{ |
b6dff3ec5
|
1998 1999 2000 |
struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; |
1da177e4c
|
2001 |
|
d84f4f992
|
2002 2003 |
error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) |
1da177e4c
|
2004 |
return error; |
d84f4f992
|
2005 |
error = 0; |
1da177e4c
|
2006 |
switch (option) { |
f3cbd435b
|
2007 2008 2009 |
case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; |
1da177e4c
|
2010 |
break; |
f3cbd435b
|
2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 |
} 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
|
2023 |
break; |
f3cbd435b
|
2024 2025 2026 |
} set_dumpable(me->mm, arg2); break; |
1da177e4c
|
2027 |
|
f3cbd435b
|
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 2087 2088 2089 2090 |
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: |
da8b44d5a
|
2091 2092 2093 2094 |
if (current->timer_slack_ns > ULONG_MAX) error = ULONG_MAX; else error = current->timer_slack_ns; |
f3cbd435b
|
2095 2096 2097 2098 |
break; case PR_SET_TIMERSLACK: if (arg2 <= 0) current->timer_slack_ns = |
6976675d9
|
2099 |
current->default_timer_slack_ns; |
f3cbd435b
|
2100 2101 2102 2103 2104 2105 2106 2107 2108 |
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
|
2109 |
return -EINVAL; |
f3cbd435b
|
2110 |
current->flags &= ~PF_MCE_PROCESS; |
4db96cf07
|
2111 |
break; |
f3cbd435b
|
2112 2113 2114 2115 2116 2117 2118 2119 2120 |
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
|
2121 |
else |
259e5e6c7
|
2122 |
return -EINVAL; |
259e5e6c7
|
2123 |
break; |
1da177e4c
|
2124 |
default: |
f3cbd435b
|
2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 |
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; |
1d4457f99
|
2153 |
task_set_no_new_privs(current); |
f3cbd435b
|
2154 2155 2156 2157 |
break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
1d4457f99
|
2158 |
return task_no_new_privs(current) ? 1 : 0; |
a0715cc22
|
2159 2160 2161 2162 2163 2164 2165 2166 |
case PR_GET_THP_DISABLE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; error = !!(me->mm->def_flags & VM_NOHUGEPAGE); break; case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; |
17b0573d7
|
2167 2168 |
if (down_write_killable(&me->mm->mmap_sem)) return -EINTR; |
a0715cc22
|
2169 2170 2171 2172 2173 2174 |
if (arg2) me->mm->def_flags |= VM_NOHUGEPAGE; else me->mm->def_flags &= ~VM_NOHUGEPAGE; up_write(&me->mm->mmap_sem); break; |
fe3d197f8
|
2175 |
case PR_MPX_ENABLE_MANAGEMENT: |
e9d1b4f3c
|
2176 2177 |
if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
46a6e0cf1
|
2178 |
error = MPX_ENABLE_MANAGEMENT(); |
fe3d197f8
|
2179 2180 |
break; case PR_MPX_DISABLE_MANAGEMENT: |
e9d1b4f3c
|
2181 2182 |
if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
46a6e0cf1
|
2183 |
error = MPX_DISABLE_MANAGEMENT(); |
fe3d197f8
|
2184 |
break; |
9791554b4
|
2185 2186 2187 2188 2189 2190 |
case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; |
f3cbd435b
|
2191 2192 2193 |
default: error = -EINVAL; break; |
1da177e4c
|
2194 2195 2196 |
} return error; } |
3cfc348bf
|
2197 |
|
836f92adf
|
2198 2199 |
SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, struct getcpu_cache __user *, unused) |
3cfc348bf
|
2200 2201 2202 |
{ int err = 0; int cpu = raw_smp_processor_id(); |
ec94fc3d5
|
2203 |
|
3cfc348bf
|
2204 2205 2206 2207 |
if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); |
3cfc348bf
|
2208 2209 |
return err ? -EFAULT : 0; } |
10a0a8d4e
|
2210 |
|
4a22f1663
|
2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 |
/** * 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
|
2222 |
get_monotonic_boottime(&tp); |
4a22f1663
|
2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 |
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 */ |
0baae41ea
|
2315 |
if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { |
4a22f1663
|
2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 |
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 */ |