Blame view
kernel/sys.c
60.7 KB
b24413180
|
1 |
// SPDX-License-Identifier: GPL-2.0 |
1da177e4c
|
2 3 4 5 6 |
/* * linux/kernel/sys.c * * Copyright (C) 1991, 1992 Linus Torvalds */ |
9984de1a5
|
7 |
#include <linux/export.h> |
1da177e4c
|
8 9 10 |
#include <linux/mm.h> #include <linux/utsname.h> #include <linux/mman.h> |
1da177e4c
|
11 12 |
#include <linux/reboot.h> #include <linux/prctl.h> |
1da177e4c
|
13 14 |
#include <linux/highuid.h> #include <linux/fs.h> |
74da1ff71
|
15 |
#include <linux/kmod.h> |
cdd6c482c
|
16 |
#include <linux/perf_event.h> |
3e88c553d
|
17 |
#include <linux/resource.h> |
dc009d924
|
18 |
#include <linux/kernel.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 |
#include <linux/sched.h> |
4eb5aaa3a
|
52 |
#include <linux/sched/autogroup.h> |
4f17722c7
|
53 |
#include <linux/sched/loadavg.h> |
03441a348
|
54 |
#include <linux/sched/stat.h> |
6e84f3152
|
55 |
#include <linux/sched/mm.h> |
f7ccbae45
|
56 |
#include <linux/sched/coredump.h> |
299300258
|
57 |
#include <linux/sched/task.h> |
32ef5517c
|
58 |
#include <linux/sched/cputime.h> |
4a22f1663
|
59 60 61 |
#include <linux/rcupdate.h> #include <linux/uidgid.h> #include <linux/cred.h> |
33f6a0681
|
62 |
#include <linux/nospec.h> |
04c6862c0
|
63 |
#include <linux/kmsg_dump.h> |
be27425dc
|
64 65 |
/* Move somewhere else to avoid recompiling? */ #include <generated/utsrelease.h> |
04c6862c0
|
66 |
|
7c0f6ba68
|
67 |
#include <linux/uaccess.h> |
1da177e4c
|
68 69 70 71 |
#include <asm/io.h> #include <asm/unistd.h> #ifndef SET_UNALIGN_CTL |
ec94fc3d5
|
72 |
# define SET_UNALIGN_CTL(a, b) (-EINVAL) |
1da177e4c
|
73 74 |
#endif #ifndef GET_UNALIGN_CTL |
ec94fc3d5
|
75 |
# define GET_UNALIGN_CTL(a, b) (-EINVAL) |
1da177e4c
|
76 77 |
#endif #ifndef SET_FPEMU_CTL |
ec94fc3d5
|
78 |
# define SET_FPEMU_CTL(a, b) (-EINVAL) |
1da177e4c
|
79 80 |
#endif #ifndef GET_FPEMU_CTL |
ec94fc3d5
|
81 |
# define GET_FPEMU_CTL(a, b) (-EINVAL) |
1da177e4c
|
82 83 |
#endif #ifndef SET_FPEXC_CTL |
ec94fc3d5
|
84 |
# define SET_FPEXC_CTL(a, b) (-EINVAL) |
1da177e4c
|
85 86 |
#endif #ifndef GET_FPEXC_CTL |
ec94fc3d5
|
87 |
# define GET_FPEXC_CTL(a, b) (-EINVAL) |
1da177e4c
|
88 |
#endif |
651d765d0
|
89 |
#ifndef GET_ENDIAN |
ec94fc3d5
|
90 |
# define GET_ENDIAN(a, b) (-EINVAL) |
651d765d0
|
91 92 |
#endif #ifndef SET_ENDIAN |
ec94fc3d5
|
93 |
# define SET_ENDIAN(a, b) (-EINVAL) |
651d765d0
|
94 |
#endif |
8fb402bcc
|
95 96 97 98 99 100 |
#ifndef GET_TSC_CTL # define GET_TSC_CTL(a) (-EINVAL) #endif #ifndef SET_TSC_CTL # define SET_TSC_CTL(a) (-EINVAL) #endif |
fe3d197f8
|
101 |
#ifndef MPX_ENABLE_MANAGEMENT |
46a6e0cf1
|
102 |
# define MPX_ENABLE_MANAGEMENT() (-EINVAL) |
fe3d197f8
|
103 104 |
#endif #ifndef MPX_DISABLE_MANAGEMENT |
46a6e0cf1
|
105 |
# define MPX_DISABLE_MANAGEMENT() (-EINVAL) |
fe3d197f8
|
106 |
#endif |
9791554b4
|
107 108 109 110 111 112 |
#ifndef GET_FP_MODE # define GET_FP_MODE(a) (-EINVAL) #endif #ifndef SET_FP_MODE # define SET_FP_MODE(a,b) (-EINVAL) #endif |
1da177e4c
|
113 114 115 116 117 118 119 120 |
/* * 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
|
121 122 |
EXPORT_SYMBOL(overflowuid); EXPORT_SYMBOL(overflowgid); |
1da177e4c
|
123 124 125 126 127 128 129 130 131 132 133 134 135 |
/* * 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
|
136 137 138 139 140 141 142 143 |
* 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
|
144 145 |
if (uid_eq(pcred->uid, cred->euid) || uid_eq(pcred->euid, cred->euid)) |
fc832ad36
|
146 |
return true; |
c4a4d6037
|
147 |
if (ns_capable(pcred->user_ns, CAP_SYS_NICE)) |
fc832ad36
|
148 149 150 151 152 |
return true; return false; } /* |
c69e8d9c0
|
153 154 155 |
* set the priority of a task * - the caller must hold the RCU read lock */ |
1da177e4c
|
156 157 158 |
static int set_one_prio(struct task_struct *p, int niceval, int error) { int no_nice; |
fc832ad36
|
159 |
if (!set_one_prio_perm(p)) { |
1da177e4c
|
160 161 162 |
error = -EPERM; goto out; } |
e43379f10
|
163 |
if (niceval < task_nice(p) && !can_nice(p, niceval)) { |
1da177e4c
|
164 165 166 167 168 169 170 171 172 173 174 175 176 177 |
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
|
178 |
SYSCALL_DEFINE3(setpriority, int, which, int, who, int, niceval) |
1da177e4c
|
179 180 181 |
{ struct task_struct *g, *p; struct user_struct *user; |
86a264abe
|
182 |
const struct cred *cred = current_cred(); |
1da177e4c
|
183 |
int error = -EINVAL; |
41487c65b
|
184 |
struct pid *pgrp; |
7b44ab978
|
185 |
kuid_t uid; |
1da177e4c
|
186 |
|
3e88c553d
|
187 |
if (which > PRIO_USER || which < PRIO_PROCESS) |
1da177e4c
|
188 189 190 191 |
goto out; /* normalize: avoid signed division (rounding problems) */ error = -ESRCH; |
c4a4d2f43
|
192 193 194 195 |
if (niceval < MIN_NICE) niceval = MIN_NICE; if (niceval > MAX_NICE) niceval = MAX_NICE; |
1da177e4c
|
196 |
|
d4581a239
|
197 |
rcu_read_lock(); |
1da177e4c
|
198 199 |
read_lock(&tasklist_lock); switch (which) { |
ec94fc3d5
|
200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 |
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
|
225 |
goto out_unlock; /* No processes for this user */ |
ec94fc3d5
|
226 227 |
} do_each_thread(g, p) { |
8639b4613
|
228 |
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) |
ec94fc3d5
|
229 230 231 232 233 |
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
|
234 235 236 |
} out_unlock: read_unlock(&tasklist_lock); |
d4581a239
|
237 |
rcu_read_unlock(); |
1da177e4c
|
238 239 240 241 242 243 244 245 246 247 |
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
|
248 |
SYSCALL_DEFINE2(getpriority, int, which, int, who) |
1da177e4c
|
249 250 251 |
{ struct task_struct *g, *p; struct user_struct *user; |
86a264abe
|
252 |
const struct cred *cred = current_cred(); |
1da177e4c
|
253 |
long niceval, retval = -ESRCH; |
41487c65b
|
254 |
struct pid *pgrp; |
7b44ab978
|
255 |
kuid_t uid; |
1da177e4c
|
256 |
|
3e88c553d
|
257 |
if (which > PRIO_USER || which < PRIO_PROCESS) |
1da177e4c
|
258 |
return -EINVAL; |
701188374
|
259 |
rcu_read_lock(); |
1da177e4c
|
260 261 |
read_lock(&tasklist_lock); switch (which) { |
ec94fc3d5
|
262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 |
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
|
295 |
if (uid_eq(task_uid(p), uid) && task_pid_vnr(p)) { |
7aa2c016d
|
296 |
niceval = nice_to_rlimit(task_nice(p)); |
1da177e4c
|
297 298 299 |
if (niceval > retval) retval = niceval; } |
ec94fc3d5
|
300 301 302 303 |
} while_each_thread(g, p); if (!uid_eq(uid, cred->uid)) free_uid(user); /* for find_user() */ break; |
1da177e4c
|
304 305 306 |
} out_unlock: read_unlock(&tasklist_lock); |
701188374
|
307 |
rcu_read_unlock(); |
1da177e4c
|
308 309 310 |
return retval; } |
1da177e4c
|
311 312 313 314 315 316 317 318 319 320 321 322 323 |
/* * 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
|
324 |
* 100% compatible with POSIX with saved IDs. |
1da177e4c
|
325 326 327 328 |
* * SMP: There are not races, the GIDs are checked only by filesystem * operations (as far as semantic preservation is concerned). */ |
2813893f8
|
329 |
#ifdef CONFIG_MULTIUSER |
ae1251ab7
|
330 |
SYSCALL_DEFINE2(setregid, gid_t, rgid, gid_t, egid) |
1da177e4c
|
331 |
{ |
a29c33f4e
|
332 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
333 334 |
const struct cred *old; struct cred *new; |
1da177e4c
|
335 |
int retval; |
a29c33f4e
|
336 337 338 339 340 341 342 343 344 |
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
|
345 |
|
d84f4f992
|
346 347 348 349 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
350 |
retval = -EPERM; |
1da177e4c
|
351 |
if (rgid != (gid_t) -1) { |
a29c33f4e
|
352 353 |
if (gid_eq(old->gid, krgid) || gid_eq(old->egid, krgid) || |
c7b96acf1
|
354 |
ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
355 |
new->gid = krgid; |
1da177e4c
|
356 |
else |
d84f4f992
|
357 |
goto error; |
1da177e4c
|
358 359 |
} if (egid != (gid_t) -1) { |
a29c33f4e
|
360 361 362 |
if (gid_eq(old->gid, kegid) || gid_eq(old->egid, kegid) || gid_eq(old->sgid, kegid) || |
c7b96acf1
|
363 |
ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
364 |
new->egid = kegid; |
756184b7d
|
365 |
else |
d84f4f992
|
366 |
goto error; |
1da177e4c
|
367 |
} |
d84f4f992
|
368 |
|
1da177e4c
|
369 |
if (rgid != (gid_t) -1 || |
a29c33f4e
|
370 |
(egid != (gid_t) -1 && !gid_eq(kegid, old->gid))) |
d84f4f992
|
371 372 373 374 375 376 377 378 |
new->sgid = new->egid; new->fsgid = new->egid; return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
379 380 381 |
} /* |
ec94fc3d5
|
382 |
* setgid() is implemented like SysV w/ SAVED_IDS |
1da177e4c
|
383 384 385 |
* * SMP: Same implicit races as above. */ |
ae1251ab7
|
386 |
SYSCALL_DEFINE1(setgid, gid_t, gid) |
1da177e4c
|
387 |
{ |
a29c33f4e
|
388 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
389 390 |
const struct cred *old; struct cred *new; |
1da177e4c
|
391 |
int retval; |
a29c33f4e
|
392 393 394 395 396 |
kgid_t kgid; kgid = make_kgid(ns, gid); if (!gid_valid(kgid)) return -EINVAL; |
1da177e4c
|
397 |
|
d84f4f992
|
398 399 400 401 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
402 |
retval = -EPERM; |
c7b96acf1
|
403 |
if (ns_capable(old->user_ns, CAP_SETGID)) |
a29c33f4e
|
404 405 406 |
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
|
407 |
else |
d84f4f992
|
408 |
goto error; |
1da177e4c
|
409 |
|
d84f4f992
|
410 411 412 413 414 |
return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
415 |
} |
54e991242
|
416 |
|
d84f4f992
|
417 418 419 420 |
/* * change the user struct in a credentials set to match the new UID */ static int set_user(struct cred *new) |
1da177e4c
|
421 422 |
{ struct user_struct *new_user; |
078de5f70
|
423 |
new_user = alloc_uid(new->uid); |
1da177e4c
|
424 425 |
if (!new_user) return -EAGAIN; |
72fa59970
|
426 427 428 429 430 431 432 |
/* * 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
|
433 |
if (atomic_read(&new_user->processes) >= rlimit(RLIMIT_NPROC) && |
72fa59970
|
434 435 436 437 |
new_user != INIT_USER) current->flags |= PF_NPROC_EXCEEDED; else current->flags &= ~PF_NPROC_EXCEEDED; |
1da177e4c
|
438 |
|
d84f4f992
|
439 440 |
free_uid(new->user); new->user = new_user; |
1da177e4c
|
441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 |
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
|
457 |
* 100% compatible with POSIX with saved IDs. |
1da177e4c
|
458 |
*/ |
ae1251ab7
|
459 |
SYSCALL_DEFINE2(setreuid, uid_t, ruid, uid_t, euid) |
1da177e4c
|
460 |
{ |
a29c33f4e
|
461 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
462 463 |
const struct cred *old; struct cred *new; |
1da177e4c
|
464 |
int retval; |
a29c33f4e
|
465 466 467 468 469 470 471 472 473 |
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
|
474 |
|
d84f4f992
|
475 476 477 478 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
479 |
retval = -EPERM; |
1da177e4c
|
480 |
if (ruid != (uid_t) -1) { |
a29c33f4e
|
481 482 483 |
new->uid = kruid; if (!uid_eq(old->uid, kruid) && !uid_eq(old->euid, kruid) && |
c7b96acf1
|
484 |
!ns_capable(old->user_ns, CAP_SETUID)) |
d84f4f992
|
485 |
goto error; |
1da177e4c
|
486 487 488 |
} if (euid != (uid_t) -1) { |
a29c33f4e
|
489 490 491 492 |
new->euid = keuid; if (!uid_eq(old->uid, keuid) && !uid_eq(old->euid, keuid) && !uid_eq(old->suid, keuid) && |
c7b96acf1
|
493 |
!ns_capable(old->user_ns, CAP_SETUID)) |
d84f4f992
|
494 |
goto error; |
1da177e4c
|
495 |
} |
a29c33f4e
|
496 |
if (!uid_eq(new->uid, old->uid)) { |
54e991242
|
497 498 499 500 |
retval = set_user(new); if (retval < 0) goto error; } |
1da177e4c
|
501 |
if (ruid != (uid_t) -1 || |
a29c33f4e
|
502 |
(euid != (uid_t) -1 && !uid_eq(keuid, old->uid))) |
d84f4f992
|
503 504 |
new->suid = new->euid; new->fsuid = new->euid; |
1da177e4c
|
505 |
|
d84f4f992
|
506 507 508 |
retval = security_task_fix_setuid(new, old, LSM_SETID_RE); if (retval < 0) goto error; |
1da177e4c
|
509 |
|
d84f4f992
|
510 |
return commit_creds(new); |
1da177e4c
|
511 |
|
d84f4f992
|
512 513 514 515 |
error: abort_creds(new); return retval; } |
ec94fc3d5
|
516 |
|
1da177e4c
|
517 |
/* |
ec94fc3d5
|
518 519 |
* setuid() is implemented like SysV with SAVED_IDS * |
1da177e4c
|
520 |
* Note that SAVED_ID's is deficient in that a setuid root program |
ec94fc3d5
|
521 |
* like sendmail, for example, cannot set its uid to be a normal |
1da177e4c
|
522 523 524 525 |
* 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
|
526 |
* regain them by swapping the real and effective uid. |
1da177e4c
|
527 |
*/ |
ae1251ab7
|
528 |
SYSCALL_DEFINE1(setuid, uid_t, uid) |
1da177e4c
|
529 |
{ |
a29c33f4e
|
530 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
531 532 |
const struct cred *old; struct cred *new; |
1da177e4c
|
533 |
int retval; |
a29c33f4e
|
534 535 536 537 538 |
kuid_t kuid; kuid = make_kuid(ns, uid); if (!uid_valid(kuid)) return -EINVAL; |
1da177e4c
|
539 |
|
d84f4f992
|
540 541 542 543 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
544 |
retval = -EPERM; |
c7b96acf1
|
545 |
if (ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
546 547 |
new->suid = new->uid = kuid; if (!uid_eq(kuid, old->uid)) { |
54e991242
|
548 549 550 |
retval = set_user(new); if (retval < 0) goto error; |
d84f4f992
|
551 |
} |
a29c33f4e
|
552 |
} else if (!uid_eq(kuid, old->uid) && !uid_eq(kuid, new->suid)) { |
d84f4f992
|
553 |
goto error; |
1da177e4c
|
554 |
} |
1da177e4c
|
555 |
|
a29c33f4e
|
556 |
new->fsuid = new->euid = kuid; |
d84f4f992
|
557 558 559 560 |
retval = security_task_fix_setuid(new, old, LSM_SETID_ID); if (retval < 0) goto error; |
1da177e4c
|
561 |
|
d84f4f992
|
562 |
return commit_creds(new); |
1da177e4c
|
563 |
|
d84f4f992
|
564 565 566 |
error: abort_creds(new); return retval; |
1da177e4c
|
567 568 569 570 571 572 573 |
} /* * This function implements a generic ability to update ruid, euid, * and suid. This allows you to implement the 4.4 compatible seteuid(). */ |
ae1251ab7
|
574 |
SYSCALL_DEFINE3(setresuid, uid_t, ruid, uid_t, euid, uid_t, suid) |
1da177e4c
|
575 |
{ |
a29c33f4e
|
576 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
577 578 |
const struct cred *old; struct cred *new; |
1da177e4c
|
579 |
int retval; |
a29c33f4e
|
580 581 582 583 584 585 586 587 588 589 590 591 592 593 |
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
|
594 |
|
d84f4f992
|
595 596 597 |
new = prepare_creds(); if (!new) return -ENOMEM; |
d84f4f992
|
598 |
old = current_cred(); |
1da177e4c
|
599 |
|
d84f4f992
|
600 |
retval = -EPERM; |
c7b96acf1
|
601 |
if (!ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
602 603 |
if (ruid != (uid_t) -1 && !uid_eq(kruid, old->uid) && !uid_eq(kruid, old->euid) && !uid_eq(kruid, old->suid)) |
d84f4f992
|
604 |
goto error; |
a29c33f4e
|
605 606 |
if (euid != (uid_t) -1 && !uid_eq(keuid, old->uid) && !uid_eq(keuid, old->euid) && !uid_eq(keuid, old->suid)) |
d84f4f992
|
607 |
goto error; |
a29c33f4e
|
608 609 |
if (suid != (uid_t) -1 && !uid_eq(ksuid, old->uid) && !uid_eq(ksuid, old->euid) && !uid_eq(ksuid, old->suid)) |
d84f4f992
|
610 |
goto error; |
1da177e4c
|
611 |
} |
d84f4f992
|
612 |
|
1da177e4c
|
613 |
if (ruid != (uid_t) -1) { |
a29c33f4e
|
614 615 |
new->uid = kruid; if (!uid_eq(kruid, old->uid)) { |
54e991242
|
616 617 618 619 |
retval = set_user(new); if (retval < 0) goto error; } |
1da177e4c
|
620 |
} |
d84f4f992
|
621 |
if (euid != (uid_t) -1) |
a29c33f4e
|
622 |
new->euid = keuid; |
1da177e4c
|
623 |
if (suid != (uid_t) -1) |
a29c33f4e
|
624 |
new->suid = ksuid; |
d84f4f992
|
625 |
new->fsuid = new->euid; |
1da177e4c
|
626 |
|
d84f4f992
|
627 628 629 |
retval = security_task_fix_setuid(new, old, LSM_SETID_RES); if (retval < 0) goto error; |
1da177e4c
|
630 |
|
d84f4f992
|
631 |
return commit_creds(new); |
1da177e4c
|
632 |
|
d84f4f992
|
633 634 635 |
error: abort_creds(new); return retval; |
1da177e4c
|
636 |
} |
a29c33f4e
|
637 |
SYSCALL_DEFINE3(getresuid, uid_t __user *, ruidp, uid_t __user *, euidp, uid_t __user *, suidp) |
1da177e4c
|
638 |
{ |
86a264abe
|
639 |
const struct cred *cred = current_cred(); |
1da177e4c
|
640 |
int retval; |
a29c33f4e
|
641 642 643 644 645 |
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
|
646 |
|
ec94fc3d5
|
647 648 649 650 651 652 |
retval = put_user(ruid, ruidp); if (!retval) { retval = put_user(euid, euidp); if (!retval) return put_user(suid, suidp); } |
1da177e4c
|
653 654 655 656 657 658 |
return retval; } /* * Same as above, but for rgid, egid, sgid. */ |
ae1251ab7
|
659 |
SYSCALL_DEFINE3(setresgid, gid_t, rgid, gid_t, egid, gid_t, sgid) |
1da177e4c
|
660 |
{ |
a29c33f4e
|
661 |
struct user_namespace *ns = current_user_ns(); |
d84f4f992
|
662 663 |
const struct cred *old; struct cred *new; |
1da177e4c
|
664 |
int retval; |
a29c33f4e
|
665 666 667 668 669 670 671 672 673 674 675 676 |
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
|
677 |
|
d84f4f992
|
678 679 680 681 |
new = prepare_creds(); if (!new) return -ENOMEM; old = current_cred(); |
d84f4f992
|
682 |
retval = -EPERM; |
c7b96acf1
|
683 |
if (!ns_capable(old->user_ns, CAP_SETGID)) { |
a29c33f4e
|
684 685 |
if (rgid != (gid_t) -1 && !gid_eq(krgid, old->gid) && !gid_eq(krgid, old->egid) && !gid_eq(krgid, old->sgid)) |
d84f4f992
|
686 |
goto error; |
a29c33f4e
|
687 688 |
if (egid != (gid_t) -1 && !gid_eq(kegid, old->gid) && !gid_eq(kegid, old->egid) && !gid_eq(kegid, old->sgid)) |
d84f4f992
|
689 |
goto error; |
a29c33f4e
|
690 691 |
if (sgid != (gid_t) -1 && !gid_eq(ksgid, old->gid) && !gid_eq(ksgid, old->egid) && !gid_eq(ksgid, old->sgid)) |
d84f4f992
|
692 |
goto error; |
1da177e4c
|
693 |
} |
d84f4f992
|
694 |
|
1da177e4c
|
695 |
if (rgid != (gid_t) -1) |
a29c33f4e
|
696 |
new->gid = krgid; |
d84f4f992
|
697 |
if (egid != (gid_t) -1) |
a29c33f4e
|
698 |
new->egid = kegid; |
1da177e4c
|
699 |
if (sgid != (gid_t) -1) |
a29c33f4e
|
700 |
new->sgid = ksgid; |
d84f4f992
|
701 |
new->fsgid = new->egid; |
1da177e4c
|
702 |
|
d84f4f992
|
703 704 705 706 707 |
return commit_creds(new); error: abort_creds(new); return retval; |
1da177e4c
|
708 |
} |
a29c33f4e
|
709 |
SYSCALL_DEFINE3(getresgid, gid_t __user *, rgidp, gid_t __user *, egidp, gid_t __user *, sgidp) |
1da177e4c
|
710 |
{ |
86a264abe
|
711 |
const struct cred *cred = current_cred(); |
1da177e4c
|
712 |
int retval; |
a29c33f4e
|
713 714 715 716 717 |
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
|
718 |
|
ec94fc3d5
|
719 720 721 722 723 724 |
retval = put_user(rgid, rgidp); if (!retval) { retval = put_user(egid, egidp); if (!retval) retval = put_user(sgid, sgidp); } |
1da177e4c
|
725 726 727 728 729 730 731 732 733 734 735 |
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
|
736 |
SYSCALL_DEFINE1(setfsuid, uid_t, uid) |
1da177e4c
|
737 |
{ |
d84f4f992
|
738 739 740 |
const struct cred *old; struct cred *new; uid_t old_fsuid; |
a29c33f4e
|
741 742 743 744 745 746 747 748 |
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
|
749 |
|
d84f4f992
|
750 751 |
new = prepare_creds(); if (!new) |
a29c33f4e
|
752 |
return old_fsuid; |
1da177e4c
|
753 |
|
a29c33f4e
|
754 755 |
if (uid_eq(kuid, old->uid) || uid_eq(kuid, old->euid) || uid_eq(kuid, old->suid) || uid_eq(kuid, old->fsuid) || |
c7b96acf1
|
756 |
ns_capable(old->user_ns, CAP_SETUID)) { |
a29c33f4e
|
757 758 |
if (!uid_eq(kuid, old->fsuid)) { new->fsuid = kuid; |
d84f4f992
|
759 760 |
if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) goto change_okay; |
1da177e4c
|
761 |
} |
1da177e4c
|
762 |
} |
d84f4f992
|
763 764 |
abort_creds(new); return old_fsuid; |
1da177e4c
|
765 |
|
d84f4f992
|
766 767 |
change_okay: commit_creds(new); |
1da177e4c
|
768 769 770 771 |
return old_fsuid; } /* |
f42df9e65
|
772 |
* Samma på svenska.. |
1da177e4c
|
773 |
*/ |
ae1251ab7
|
774 |
SYSCALL_DEFINE1(setfsgid, gid_t, gid) |
1da177e4c
|
775 |
{ |
d84f4f992
|
776 777 778 |
const struct cred *old; struct cred *new; gid_t old_fsgid; |
a29c33f4e
|
779 780 781 782 783 784 785 786 |
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
|
787 788 789 |
new = prepare_creds(); if (!new) |
a29c33f4e
|
790 |
return old_fsgid; |
1da177e4c
|
791 |
|
a29c33f4e
|
792 793 |
if (gid_eq(kgid, old->gid) || gid_eq(kgid, old->egid) || gid_eq(kgid, old->sgid) || gid_eq(kgid, old->fsgid) || |
c7b96acf1
|
794 |
ns_capable(old->user_ns, CAP_SETGID)) { |
a29c33f4e
|
795 796 |
if (!gid_eq(kgid, old->fsgid)) { new->fsgid = kgid; |
d84f4f992
|
797 |
goto change_okay; |
1da177e4c
|
798 |
} |
1da177e4c
|
799 |
} |
d84f4f992
|
800 |
|
d84f4f992
|
801 802 803 804 805 |
abort_creds(new); return old_fsgid; change_okay: commit_creds(new); |
1da177e4c
|
806 807 |
return old_fsgid; } |
2813893f8
|
808 |
#endif /* CONFIG_MULTIUSER */ |
1da177e4c
|
809 |
|
4a22f1663
|
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 |
/** * 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()); } |
ca2406ed5
|
870 |
static void do_sys_times(struct tms *tms) |
f06febc96
|
871 |
{ |
5613fda9a
|
872 |
u64 tgutime, tgstime, cutime, cstime; |
f06febc96
|
873 |
|
e80d0a1ae
|
874 |
thread_group_cputime_adjusted(current, &tgutime, &tgstime); |
f06febc96
|
875 876 |
cutime = current->signal->cutime; cstime = current->signal->cstime; |
5613fda9a
|
877 878 879 880 |
tms->tms_utime = nsec_to_clock_t(tgutime); tms->tms_stime = nsec_to_clock_t(tgstime); tms->tms_cutime = nsec_to_clock_t(cutime); tms->tms_cstime = nsec_to_clock_t(cstime); |
f06febc96
|
881 |
} |
58fd3aa28
|
882 |
SYSCALL_DEFINE1(times, struct tms __user *, tbuf) |
1da177e4c
|
883 |
{ |
1da177e4c
|
884 885 |
if (tbuf) { struct tms tmp; |
f06febc96
|
886 887 |
do_sys_times(&tmp); |
1da177e4c
|
888 889 890 |
if (copy_to_user(tbuf, &tmp, sizeof(struct tms))) return -EFAULT; } |
e3d5a27d5
|
891 |
force_successful_syscall_return(); |
1da177e4c
|
892 893 |
return (long) jiffies_64_to_clock_t(get_jiffies_64()); } |
ca2406ed5
|
894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 |
#ifdef CONFIG_COMPAT static compat_clock_t clock_t_to_compat_clock_t(clock_t x) { return compat_jiffies_to_clock_t(clock_t_to_jiffies(x)); } COMPAT_SYSCALL_DEFINE1(times, struct compat_tms __user *, tbuf) { if (tbuf) { struct tms tms; struct compat_tms tmp; do_sys_times(&tms); /* Convert our struct tms to the compat version. */ tmp.tms_utime = clock_t_to_compat_clock_t(tms.tms_utime); tmp.tms_stime = clock_t_to_compat_clock_t(tms.tms_stime); tmp.tms_cutime = clock_t_to_compat_clock_t(tms.tms_cutime); tmp.tms_cstime = clock_t_to_compat_clock_t(tms.tms_cstime); if (copy_to_user(tbuf, &tmp, sizeof(tmp))) return -EFAULT; } force_successful_syscall_return(); return compat_jiffies_to_clock_t(jiffies); } #endif |
1da177e4c
|
919 920 921 922 923 924 925 926 927 |
/* * 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
|
928 |
* !PF_FORKNOEXEC check to conform completely to POSIX. |
1da177e4c
|
929 |
*/ |
b290ebe2c
|
930 |
SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid) |
1da177e4c
|
931 932 |
{ struct task_struct *p; |
ee0acf90d
|
933 |
struct task_struct *group_leader = current->group_leader; |
4e021306c
|
934 935 |
struct pid *pgrp; int err; |
1da177e4c
|
936 937 |
if (!pid) |
b488893a3
|
938 |
pid = task_pid_vnr(group_leader); |
1da177e4c
|
939 940 941 942 |
if (!pgid) pgid = pid; if (pgid < 0) return -EINVAL; |
950eaaca6
|
943 |
rcu_read_lock(); |
1da177e4c
|
944 945 946 947 948 949 950 |
/* 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
|
951 |
p = find_task_by_vpid(pid); |
1da177e4c
|
952 953 954 955 956 957 |
if (!p) goto out; err = -EINVAL; if (!thread_group_leader(p)) goto out; |
4e021306c
|
958 |
if (same_thread_group(p->real_parent, group_leader)) { |
1da177e4c
|
959 |
err = -EPERM; |
41487c65b
|
960 |
if (task_session(p) != task_session(group_leader)) |
1da177e4c
|
961 962 |
goto out; err = -EACCES; |
98611e4e6
|
963 |
if (!(p->flags & PF_FORKNOEXEC)) |
1da177e4c
|
964 965 966 |
goto out; } else { err = -ESRCH; |
ee0acf90d
|
967 |
if (p != group_leader) |
1da177e4c
|
968 969 970 971 972 973 |
goto out; } err = -EPERM; if (p->signal->leader) goto out; |
4e021306c
|
974 |
pgrp = task_pid(p); |
1da177e4c
|
975 |
if (pgid != pid) { |
b488893a3
|
976 |
struct task_struct *g; |
1da177e4c
|
977 |
|
4e021306c
|
978 979 |
pgrp = find_vpid(pgid); g = pid_task(pgrp, PIDTYPE_PGID); |
41487c65b
|
980 |
if (!g || task_session(g) != task_session(group_leader)) |
f020bc468
|
981 |
goto out; |
1da177e4c
|
982 |
} |
1da177e4c
|
983 984 985 |
err = security_task_setpgid(p, pgid); if (err) goto out; |
1b0f7ffd0
|
986 |
if (task_pgrp(p) != pgrp) |
83beaf3c6
|
987 |
change_pid(p, PIDTYPE_PGID, pgrp); |
1da177e4c
|
988 989 990 991 992 |
err = 0; out: /* All paths lead to here, thus we are safe. -DaveM */ write_unlock_irq(&tasklist_lock); |
950eaaca6
|
993 |
rcu_read_unlock(); |
1da177e4c
|
994 995 |
return err; } |
dbf040d9d
|
996 |
SYSCALL_DEFINE1(getpgid, pid_t, pid) |
1da177e4c
|
997 |
{ |
12a3de0a9
|
998 999 1000 1001 1002 |
struct task_struct *p; struct pid *grp; int retval; rcu_read_lock(); |
756184b7d
|
1003 |
if (!pid) |
12a3de0a9
|
1004 |
grp = task_pgrp(current); |
756184b7d
|
1005 |
else { |
1da177e4c
|
1006 |
retval = -ESRCH; |
12a3de0a9
|
1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 |
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
|
1017 |
} |
12a3de0a9
|
1018 1019 1020 1021 |
retval = pid_vnr(grp); out: rcu_read_unlock(); return retval; |
1da177e4c
|
1022 1023 1024 |
} #ifdef __ARCH_WANT_SYS_GETPGRP |
dbf040d9d
|
1025 |
SYSCALL_DEFINE0(getpgrp) |
1da177e4c
|
1026 |
{ |
12a3de0a9
|
1027 |
return sys_getpgid(0); |
1da177e4c
|
1028 1029 1030 |
} #endif |
dbf040d9d
|
1031 |
SYSCALL_DEFINE1(getsid, pid_t, pid) |
1da177e4c
|
1032 |
{ |
1dd768c08
|
1033 1034 1035 1036 1037 |
struct task_struct *p; struct pid *sid; int retval; rcu_read_lock(); |
756184b7d
|
1038 |
if (!pid) |
1dd768c08
|
1039 |
sid = task_session(current); |
756184b7d
|
1040 |
else { |
1da177e4c
|
1041 |
retval = -ESRCH; |
1dd768c08
|
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 |
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
|
1052 |
} |
1dd768c08
|
1053 1054 1055 1056 |
retval = pid_vnr(sid); out: rcu_read_unlock(); return retval; |
1da177e4c
|
1057 |
} |
81dabb464
|
1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 |
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
|
1068 |
SYSCALL_DEFINE0(setsid) |
1da177e4c
|
1069 |
{ |
e19f247a3
|
1070 |
struct task_struct *group_leader = current->group_leader; |
e4cc0a9c8
|
1071 1072 |
struct pid *sid = task_pid(group_leader); pid_t session = pid_vnr(sid); |
1da177e4c
|
1073 |
int err = -EPERM; |
1da177e4c
|
1074 |
write_lock_irq(&tasklist_lock); |
390e2ff07
|
1075 1076 1077 |
/* Fail if I am already a session leader */ if (group_leader->signal->leader) goto out; |
430c62312
|
1078 1079 |
/* Fail if a process group id already exists that equals the * proposed session id. |
390e2ff07
|
1080 |
*/ |
6806aac6d
|
1081 |
if (pid_task(sid, PIDTYPE_PGID)) |
1da177e4c
|
1082 |
goto out; |
e19f247a3
|
1083 |
group_leader->signal->leader = 1; |
81dabb464
|
1084 |
set_special_pids(sid); |
24ec839c4
|
1085 |
|
9c9f4ded9
|
1086 |
proc_clear_tty(group_leader); |
24ec839c4
|
1087 |
|
e4cc0a9c8
|
1088 |
err = session; |
1da177e4c
|
1089 1090 |
out: write_unlock_irq(&tasklist_lock); |
5091faa44
|
1091 |
if (err > 0) { |
0d0df599f
|
1092 |
proc_sid_connector(group_leader); |
5091faa44
|
1093 1094 |
sched_autogroup_create_attach(group_leader); } |
1da177e4c
|
1095 1096 |
return err; } |
1da177e4c
|
1097 |
DECLARE_RWSEM(uts_sem); |
e28cbf229
|
1098 1099 |
#ifdef COMPAT_UTS_MACHINE #define override_architecture(name) \ |
46da27664
|
1100 |
(personality(current->personality) == PER_LINUX32 && \ |
e28cbf229
|
1101 1102 1103 1104 1105 |
copy_to_user(name->machine, COMPAT_UTS_MACHINE, \ sizeof(COMPAT_UTS_MACHINE))) #else #define override_architecture(name) 0 #endif |
be27425dc
|
1106 1107 1108 |
/* * 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
|
1109 |
* And we map 4.x to 2.6.60+x, so 4.0 would be 2.6.60. |
be27425dc
|
1110 |
*/ |
2702b1526
|
1111 |
static int override_release(char __user *release, size_t len) |
be27425dc
|
1112 1113 |
{ int ret = 0; |
be27425dc
|
1114 1115 |
if (current->personality & UNAME26) { |
2702b1526
|
1116 1117 |
const char *rest = UTS_RELEASE; char buf[65] = { 0 }; |
be27425dc
|
1118 1119 |
int ndots = 0; unsigned v; |
2702b1526
|
1120 |
size_t copy; |
be27425dc
|
1121 1122 1123 1124 1125 1126 1127 1128 |
while (*rest) { if (*rest == '.' && ++ndots >= 3) break; if (!isdigit(*rest) && *rest != '.') break; rest++; } |
39afb5ee4
|
1129 |
v = ((LINUX_VERSION_CODE >> 8) & 0xff) + 60; |
31fd84b95
|
1130 |
copy = clamp_t(size_t, len, 1, sizeof(buf)); |
2702b1526
|
1131 1132 |
copy = scnprintf(buf, copy, "2.6.%u%s", v, rest); ret = copy_to_user(release, buf, copy + 1); |
be27425dc
|
1133 1134 1135 |
} return ret; } |
e48fbb699
|
1136 |
SYSCALL_DEFINE1(newuname, struct new_utsname __user *, name) |
1da177e4c
|
1137 |
{ |
b692c405a
|
1138 |
struct new_utsname tmp; |
1da177e4c
|
1139 1140 |
down_read(&uts_sem); |
b692c405a
|
1141 |
memcpy(&tmp, utsname(), sizeof(tmp)); |
1da177e4c
|
1142 |
up_read(&uts_sem); |
b692c405a
|
1143 1144 |
if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; |
e28cbf229
|
1145 |
|
b692c405a
|
1146 1147 1148 1149 1150 |
if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; |
1da177e4c
|
1151 |
} |
5cacdb4ad
|
1152 1153 1154 1155 1156 1157 |
#ifdef __ARCH_WANT_SYS_OLD_UNAME /* * Old cruft */ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name) { |
b692c405a
|
1158 |
struct old_utsname tmp; |
5cacdb4ad
|
1159 1160 1161 1162 1163 |
if (!name) return -EFAULT; down_read(&uts_sem); |
b692c405a
|
1164 |
memcpy(&tmp, utsname(), sizeof(tmp)); |
5cacdb4ad
|
1165 |
up_read(&uts_sem); |
b692c405a
|
1166 1167 |
if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; |
5cacdb4ad
|
1168 |
|
b692c405a
|
1169 1170 1171 1172 1173 |
if (override_release(name->release, sizeof(name->release))) return -EFAULT; if (override_architecture(name)) return -EFAULT; return 0; |
5cacdb4ad
|
1174 1175 1176 1177 |
} SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { |
b692c405a
|
1178 |
struct oldold_utsname tmp = {}; |
5cacdb4ad
|
1179 1180 1181 |
if (!name) return -EFAULT; |
5cacdb4ad
|
1182 1183 |
down_read(&uts_sem); |
b692c405a
|
1184 1185 1186 1187 1188 |
memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN); memcpy(&tmp.release, &utsname()->release, __OLD_UTS_LEN); memcpy(&tmp.version, &utsname()->version, __OLD_UTS_LEN); memcpy(&tmp.machine, &utsname()->machine, __OLD_UTS_LEN); |
5cacdb4ad
|
1189 |
up_read(&uts_sem); |
b692c405a
|
1190 1191 |
if (copy_to_user(name, &tmp, sizeof(tmp))) return -EFAULT; |
5cacdb4ad
|
1192 |
|
b692c405a
|
1193 1194 1195 1196 1197 |
if (override_architecture(name)) return -EFAULT; if (override_release(name->release, sizeof(name->release))) return -EFAULT; return 0; |
5cacdb4ad
|
1198 1199 |
} #endif |
5a8a82b1d
|
1200 |
SYSCALL_DEFINE2(sethostname, char __user *, name, int, len) |
1da177e4c
|
1201 1202 1203 |
{ int errno; char tmp[__NEW_UTS_LEN]; |
bb96a6f50
|
1204 |
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) |
1da177e4c
|
1205 |
return -EPERM; |
fc832ad36
|
1206 |
|
1da177e4c
|
1207 1208 |
if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; |
1da177e4c
|
1209 1210 |
errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { |
b692c405a
|
1211 |
struct new_utsname *u; |
9679e4dd6
|
1212 |
|
b692c405a
|
1213 1214 |
down_write(&uts_sem); u = utsname(); |
9679e4dd6
|
1215 1216 |
memcpy(u->nodename, tmp, len); memset(u->nodename + len, 0, sizeof(u->nodename) - len); |
1da177e4c
|
1217 |
errno = 0; |
499eea6bf
|
1218 |
uts_proc_notify(UTS_PROC_HOSTNAME); |
b692c405a
|
1219 |
up_write(&uts_sem); |
1da177e4c
|
1220 |
} |
1da177e4c
|
1221 1222 1223 1224 |
return errno; } #ifdef __ARCH_WANT_SYS_GETHOSTNAME |
5a8a82b1d
|
1225 |
SYSCALL_DEFINE2(gethostname, char __user *, name, int, len) |
1da177e4c
|
1226 |
{ |
b692c405a
|
1227 |
int i; |
9679e4dd6
|
1228 |
struct new_utsname *u; |
b692c405a
|
1229 |
char tmp[__NEW_UTS_LEN + 1]; |
1da177e4c
|
1230 1231 1232 1233 |
if (len < 0) return -EINVAL; down_read(&uts_sem); |
9679e4dd6
|
1234 1235 |
u = utsname(); i = 1 + strlen(u->nodename); |
1da177e4c
|
1236 1237 |
if (i > len) i = len; |
b692c405a
|
1238 |
memcpy(tmp, u->nodename, i); |
1da177e4c
|
1239 |
up_read(&uts_sem); |
b692c405a
|
1240 1241 1242 |
if (copy_to_user(name, tmp, i)) return -EFAULT; return 0; |
1da177e4c
|
1243 1244 1245 1246 1247 1248 1249 1250 |
} #endif /* * Only setdomainname; getdomainname can be implemented by calling * uname() */ |
5a8a82b1d
|
1251 |
SYSCALL_DEFINE2(setdomainname, char __user *, name, int, len) |
1da177e4c
|
1252 1253 1254 |
{ int errno; char tmp[__NEW_UTS_LEN]; |
fc832ad36
|
1255 |
if (!ns_capable(current->nsproxy->uts_ns->user_ns, CAP_SYS_ADMIN)) |
1da177e4c
|
1256 1257 1258 |
return -EPERM; if (len < 0 || len > __NEW_UTS_LEN) return -EINVAL; |
1da177e4c
|
1259 1260 |
errno = -EFAULT; if (!copy_from_user(tmp, name, len)) { |
b692c405a
|
1261 |
struct new_utsname *u; |
9679e4dd6
|
1262 |
|
b692c405a
|
1263 1264 |
down_write(&uts_sem); u = utsname(); |
9679e4dd6
|
1265 1266 |
memcpy(u->domainname, tmp, len); memset(u->domainname + len, 0, sizeof(u->domainname) - len); |
1da177e4c
|
1267 |
errno = 0; |
499eea6bf
|
1268 |
uts_proc_notify(UTS_PROC_DOMAINNAME); |
b692c405a
|
1269 |
up_write(&uts_sem); |
1da177e4c
|
1270 |
} |
1da177e4c
|
1271 1272 |
return errno; } |
e48fbb699
|
1273 |
SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct rlimit __user *, rlim) |
1da177e4c
|
1274 |
{ |
b95183453
|
1275 1276 1277 1278 1279 1280 1281 1282 |
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
|
1283 |
} |
d9e968cb9
|
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 1312 1313 |
#ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(setrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; struct compat_rlimit r32; if (copy_from_user(&r32, rlim, sizeof(struct compat_rlimit))) return -EFAULT; if (r32.rlim_cur == COMPAT_RLIM_INFINITY) r.rlim_cur = RLIM_INFINITY; else r.rlim_cur = r32.rlim_cur; if (r32.rlim_max == COMPAT_RLIM_INFINITY) r.rlim_max = RLIM_INFINITY; else r.rlim_max = r32.rlim_max; return do_prlimit(current, resource, &r, NULL); } COMPAT_SYSCALL_DEFINE2(getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; int ret; ret = do_prlimit(current, resource, NULL, &r); if (!ret) { |
58c7ffc07
|
1314 |
struct compat_rlimit r32; |
d9e968cb9
|
1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 |
if (r.rlim_cur > COMPAT_RLIM_INFINITY) r32.rlim_cur = COMPAT_RLIM_INFINITY; else r32.rlim_cur = r.rlim_cur; if (r.rlim_max > COMPAT_RLIM_INFINITY) r32.rlim_max = COMPAT_RLIM_INFINITY; else r32.rlim_max = r.rlim_max; if (copy_to_user(rlim, &r32, sizeof(struct compat_rlimit))) return -EFAULT; } return ret; } #endif |
1da177e4c
|
1331 1332 1333 1334 1335 |
#ifdef __ARCH_WANT_SYS_OLD_GETRLIMIT /* * Back compatibility for getrlimit. Needed for some apps. */ |
e48fbb699
|
1336 1337 |
SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct rlimit __user *, rlim) |
1da177e4c
|
1338 1339 1340 1341 |
{ struct rlimit x; if (resource >= RLIM_NLIMITS) return -EINVAL; |
058dfcf9c
|
1342 |
resource = array_index_nospec(resource, RLIM_NLIMITS); |
1da177e4c
|
1343 1344 1345 |
task_lock(current->group_leader); x = current->signal->rlim[resource]; task_unlock(current->group_leader); |
756184b7d
|
1346 |
if (x.rlim_cur > 0x7FFFFFFF) |
1da177e4c
|
1347 |
x.rlim_cur = 0x7FFFFFFF; |
756184b7d
|
1348 |
if (x.rlim_max > 0x7FFFFFFF) |
1da177e4c
|
1349 |
x.rlim_max = 0x7FFFFFFF; |
ec94fc3d5
|
1350 |
return copy_to_user(rlim, &x, sizeof(x)) ? -EFAULT : 0; |
1da177e4c
|
1351 |
} |
613763a1f
|
1352 1353 1354 1355 1356 1357 1358 1359 |
#ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(old_getrlimit, unsigned int, resource, struct compat_rlimit __user *, rlim) { struct rlimit r; if (resource >= RLIM_NLIMITS) return -EINVAL; |
058dfcf9c
|
1360 |
resource = array_index_nospec(resource, RLIM_NLIMITS); |
613763a1f
|
1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 |
task_lock(current->group_leader); r = current->signal->rlim[resource]; task_unlock(current->group_leader); if (r.rlim_cur > 0x7FFFFFFF) r.rlim_cur = 0x7FFFFFFF; if (r.rlim_max > 0x7FFFFFFF) r.rlim_max = 0x7FFFFFFF; if (put_user(r.rlim_cur, &rlim->rlim_cur) || put_user(r.rlim_max, &rlim->rlim_max)) return -EFAULT; return 0; } #endif |
1da177e4c
|
1375 |
#endif |
c022a0aca
|
1376 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 |
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
|
1408 |
/* make sure you are allowed to change @tsk limits before calling this */ |
5b41535aa
|
1409 1410 |
int do_prlimit(struct task_struct *tsk, unsigned int resource, struct rlimit *new_rlim, struct rlimit *old_rlim) |
1da177e4c
|
1411 |
{ |
5b41535aa
|
1412 |
struct rlimit *rlim; |
86f162f4c
|
1413 |
int retval = 0; |
1da177e4c
|
1414 1415 1416 |
if (resource >= RLIM_NLIMITS) return -EINVAL; |
5b41535aa
|
1417 1418 1419 1420 1421 1422 1423 |
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
|
1424 |
|
1c1e618dd
|
1425 1426 1427 1428 1429 1430 |
/* protect tsk->signal and tsk->sighand from disappearing */ read_lock(&tasklist_lock); if (!tsk->sighand) { retval = -ESRCH; goto out; } |
5b41535aa
|
1431 |
rlim = tsk->signal->rlim + resource; |
86f162f4c
|
1432 |
task_lock(tsk->group_leader); |
5b41535aa
|
1433 |
if (new_rlim) { |
fc832ad36
|
1434 1435 |
/* Keep the capable check against init_user_ns until cgroups can contain all limits */ |
5b41535aa
|
1436 1437 1438 1439 |
if (new_rlim->rlim_max > rlim->rlim_max && !capable(CAP_SYS_RESOURCE)) retval = -EPERM; if (!retval) |
cad4ea546
|
1440 |
retval = security_task_setrlimit(tsk, resource, new_rlim); |
5b41535aa
|
1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 |
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
|
1456 |
} |
7855c35da
|
1457 |
task_unlock(tsk->group_leader); |
1da177e4c
|
1458 |
|
d3561f78f
|
1459 1460 1461 1462 1463 1464 |
/* * 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
|
1465 |
if (!retval && new_rlim && resource == RLIMIT_CPU && |
baa73d9e4
|
1466 1467 |
new_rlim->rlim_cur != RLIM_INFINITY && IS_ENABLED(CONFIG_POSIX_TIMERS)) |
5b41535aa
|
1468 |
update_rlimit_cpu(tsk, new_rlim->rlim_cur); |
ec9e16bac
|
1469 |
out: |
1c1e618dd
|
1470 |
read_unlock(&tasklist_lock); |
2fb9d2689
|
1471 |
return retval; |
1da177e4c
|
1472 |
} |
c022a0aca
|
1473 |
/* rcu lock must be held */ |
791ec491c
|
1474 1475 |
static int check_prlimit_permission(struct task_struct *task, unsigned int flags) |
c022a0aca
|
1476 1477 |
{ const struct cred *cred = current_cred(), *tcred; |
791ec491c
|
1478 |
bool id_match; |
c022a0aca
|
1479 |
|
fc832ad36
|
1480 1481 |
if (current == task) return 0; |
c022a0aca
|
1482 |
|
fc832ad36
|
1483 |
tcred = __task_cred(task); |
791ec491c
|
1484 1485 1486 1487 1488 1489 1490 1491 |
id_match = (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)); if (!id_match && !ns_capable(tcred->user_ns, CAP_SYS_RESOURCE)) return -EPERM; |
fc832ad36
|
1492 |
|
791ec491c
|
1493 |
return security_task_prlimit(cred, tcred, flags); |
c022a0aca
|
1494 1495 1496 1497 1498 1499 1500 1501 1502 |
} 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; |
791ec491c
|
1503 |
unsigned int checkflags = 0; |
c022a0aca
|
1504 |
int ret; |
791ec491c
|
1505 1506 |
if (old_rlim) checkflags |= LSM_PRLIMIT_READ; |
c022a0aca
|
1507 1508 1509 1510 |
if (new_rlim) { if (copy_from_user(&new64, new_rlim, sizeof(new64))) return -EFAULT; rlim64_to_rlim(&new64, &new); |
791ec491c
|
1511 |
checkflags |= LSM_PRLIMIT_WRITE; |
c022a0aca
|
1512 1513 1514 1515 1516 1517 1518 1519 |
} rcu_read_lock(); tsk = pid ? find_task_by_vpid(pid) : current; if (!tsk) { rcu_read_unlock(); return -ESRCH; } |
791ec491c
|
1520 |
ret = check_prlimit_permission(tsk, checkflags); |
c022a0aca
|
1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 |
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
|
1540 1541 1542 1543 1544 1545 |
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
|
1546 |
return do_prlimit(current, resource, &new_rlim, NULL); |
7855c35da
|
1547 |
} |
1da177e4c
|
1548 1549 1550 1551 1552 1553 1554 1555 |
/* * 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
|
1556 1557 1558 1559 1560 1561 1562 |
* 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
|
1563 |
* |
de047c1bc
|
1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 |
* 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
|
1578 |
* |
1da177e4c
|
1579 |
*/ |
f06febc96
|
1580 |
static void accumulate_thread_rusage(struct task_struct *t, struct rusage *r) |
679c9cd4a
|
1581 |
{ |
679c9cd4a
|
1582 1583 1584 1585 1586 1587 1588 |
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); } |
ce72a16fa
|
1589 |
void getrusage(struct task_struct *p, int who, struct rusage *r) |
1da177e4c
|
1590 1591 1592 |
{ struct task_struct *t; unsigned long flags; |
5613fda9a
|
1593 |
u64 tgutime, tgstime, utime, stime; |
1f10206cf
|
1594 |
unsigned long maxrss = 0; |
1da177e4c
|
1595 |
|
ec94fc3d5
|
1596 |
memset((char *)r, 0, sizeof (*r)); |
648616343
|
1597 |
utime = stime = 0; |
1da177e4c
|
1598 |
|
679c9cd4a
|
1599 |
if (who == RUSAGE_THREAD) { |
e80d0a1ae
|
1600 |
task_cputime_adjusted(current, &utime, &stime); |
f06febc96
|
1601 |
accumulate_thread_rusage(p, r); |
1f10206cf
|
1602 |
maxrss = p->signal->maxrss; |
679c9cd4a
|
1603 1604 |
goto out; } |
d6cf723a1
|
1605 |
if (!lock_task_sighand(p, &flags)) |
de047c1bc
|
1606 |
return; |
0f59cc4a3
|
1607 |
|
1da177e4c
|
1608 |
switch (who) { |
ec94fc3d5
|
1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 |
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
|
1622 |
break; |
0f59cc4a3
|
1623 |
|
ec94fc3d5
|
1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 |
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
|
1644 |
} |
de047c1bc
|
1645 |
unlock_task_sighand(p, &flags); |
de047c1bc
|
1646 |
|
679c9cd4a
|
1647 |
out: |
5613fda9a
|
1648 1649 |
r->ru_utime = ns_to_timeval(utime); r->ru_stime = ns_to_timeval(stime); |
1f10206cf
|
1650 1651 1652 |
if (who != RUSAGE_CHILDREN) { struct mm_struct *mm = get_task_mm(p); |
ec94fc3d5
|
1653 |
|
1f10206cf
|
1654 1655 1656 1657 1658 1659 |
if (mm) { setmax_mm_hiwater_rss(&maxrss, mm); mmput(mm); } } r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */ |
1da177e4c
|
1660 |
} |
ce72a16fa
|
1661 |
SYSCALL_DEFINE2(getrusage, int, who, struct rusage __user *, ru) |
1da177e4c
|
1662 1663 |
{ struct rusage r; |
ec94fc3d5
|
1664 |
|
679c9cd4a
|
1665 1666 |
if (who != RUSAGE_SELF && who != RUSAGE_CHILDREN && who != RUSAGE_THREAD) |
1da177e4c
|
1667 |
return -EINVAL; |
ce72a16fa
|
1668 1669 1670 |
getrusage(current, who, &r); return copy_to_user(ru, &r, sizeof(r)) ? -EFAULT : 0; |
1da177e4c
|
1671 |
} |
8d2d5c4a2
|
1672 1673 1674 1675 1676 1677 1678 1679 |
#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; |
ce72a16fa
|
1680 |
getrusage(current, who, &r); |
8d2d5c4a2
|
1681 1682 1683 |
return put_compat_rusage(&r, ru); } #endif |
e48fbb699
|
1684 |
SYSCALL_DEFINE1(umask, int, mask) |
1da177e4c
|
1685 1686 1687 1688 |
{ mask = xchg(¤t->fs->umask, mask & S_IRWXUGO); return mask; } |
3b7391de6
|
1689 |
|
6e399cd14
|
1690 |
static int prctl_set_mm_exe_file(struct mm_struct *mm, unsigned int fd) |
b32dfe377
|
1691 |
{ |
2903ff019
|
1692 |
struct fd exe; |
6e399cd14
|
1693 |
struct file *old_exe, *exe_file; |
496ad9aa8
|
1694 |
struct inode *inode; |
2903ff019
|
1695 |
int err; |
b32dfe377
|
1696 |
|
2903ff019
|
1697 1698 |
exe = fdget(fd); if (!exe.file) |
b32dfe377
|
1699 |
return -EBADF; |
496ad9aa8
|
1700 |
inode = file_inode(exe.file); |
b32dfe377
|
1701 1702 1703 1704 1705 1706 1707 |
/* * 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
|
1708 |
if (!S_ISREG(inode->i_mode) || path_noexec(&exe.file->f_path)) |
b32dfe377
|
1709 |
goto exit; |
496ad9aa8
|
1710 |
err = inode_permission(inode, MAY_EXEC); |
b32dfe377
|
1711 1712 |
if (err) goto exit; |
bafb282df
|
1713 |
/* |
4229fb1dc
|
1714 |
* Forbid mm->exe_file change if old file still mapped. |
bafb282df
|
1715 |
*/ |
6e399cd14
|
1716 |
exe_file = get_mm_exe_file(mm); |
bafb282df
|
1717 |
err = -EBUSY; |
6e399cd14
|
1718 |
if (exe_file) { |
4229fb1dc
|
1719 |
struct vm_area_struct *vma; |
6e399cd14
|
1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 |
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
|
1731 |
} |
4229fb1dc
|
1732 |
err = 0; |
6e399cd14
|
1733 1734 1735 1736 1737 |
/* set the new file, lockless */ get_file(exe.file); old_exe = xchg(&mm->exe_file, exe.file); if (old_exe) fput(old_exe); |
b32dfe377
|
1738 |
exit: |
2903ff019
|
1739 |
fdput(exe); |
b32dfe377
|
1740 |
return err; |
6e399cd14
|
1741 1742 1743 1744 |
exit_err: up_read(&mm->mmap_sem); fput(exe_file); goto exit; |
b32dfe377
|
1745 |
} |
f606b77f1
|
1746 1747 1748 1749 1750 1751 1752 1753 1754 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 1790 1791 1792 1793 1794 1795 1796 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 |
/* * 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 |
4d28df615
|
1824 |
* change /proc/pid/exe link: only local sys admin should |
f606b77f1
|
1825 1826 1827 |
* be allowed to. */ if (prctl_map->exe_fd != (u32)-1) { |
4d28df615
|
1828 |
if (!ns_capable(current_user_ns(), CAP_SYS_ADMIN)) |
f606b77f1
|
1829 1830 1831 1832 1833 1834 1835 |
goto out; } error = 0; out: return error; } |
4a00e9df2
|
1836 |
#ifdef CONFIG_CHECKPOINT_RESTORE |
f606b77f1
|
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 1865 1866 1867 1868 1869 1870 1871 |
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
|
1872 |
if (prctl_map.exe_fd != (u32)-1) { |
6e399cd14
|
1873 |
error = prctl_set_mm_exe_file(mm, prctl_map.exe_fd); |
ddf1d398e
|
1874 1875 1876 1877 1878 |
if (error) return error; } down_write(&mm->mmap_sem); |
f606b77f1
|
1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 |
/* * 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
|
1914 1915 |
up_write(&mm->mmap_sem); return 0; |
f606b77f1
|
1916 1917 |
} #endif /* CONFIG_CHECKPOINT_RESTORE */ |
4a00e9df2
|
1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 |
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
|
1947 1948 1949 |
static int prctl_set_mm(int opt, unsigned long addr, unsigned long arg4, unsigned long arg5) { |
028ee4be3
|
1950 |
struct mm_struct *mm = current->mm; |
4a00e9df2
|
1951 |
struct prctl_mm_map prctl_map; |
fe8c7f5cb
|
1952 1953 |
struct vm_area_struct *vma; int error; |
028ee4be3
|
1954 |
|
f606b77f1
|
1955 1956 1957 |
if (arg5 || (arg4 && (opt != PR_SET_MM_AUXV && opt != PR_SET_MM_MAP && opt != PR_SET_MM_MAP_SIZE))) |
028ee4be3
|
1958 |
return -EINVAL; |
f606b77f1
|
1959 1960 1961 1962 |
#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
|
1963 |
if (!capable(CAP_SYS_RESOURCE)) |
028ee4be3
|
1964 |
return -EPERM; |
6e399cd14
|
1965 1966 |
if (opt == PR_SET_MM_EXE_FILE) return prctl_set_mm_exe_file(mm, (unsigned int)addr); |
b32dfe377
|
1967 |
|
4a00e9df2
|
1968 1969 |
if (opt == PR_SET_MM_AUXV) return prctl_set_auxv(mm, addr, arg4); |
1ad75b9e1
|
1970 |
if (addr >= TASK_SIZE || addr < mmap_min_addr) |
028ee4be3
|
1971 |
return -EINVAL; |
fe8c7f5cb
|
1972 |
error = -EINVAL; |
ddf1d398e
|
1973 |
down_write(&mm->mmap_sem); |
028ee4be3
|
1974 |
vma = find_vma(mm, addr); |
4a00e9df2
|
1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 |
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
|
1989 1990 |
switch (opt) { case PR_SET_MM_START_CODE: |
4a00e9df2
|
1991 |
prctl_map.start_code = addr; |
fe8c7f5cb
|
1992 |
break; |
028ee4be3
|
1993 |
case PR_SET_MM_END_CODE: |
4a00e9df2
|
1994 |
prctl_map.end_code = addr; |
028ee4be3
|
1995 |
break; |
028ee4be3
|
1996 |
case PR_SET_MM_START_DATA: |
4a00e9df2
|
1997 |
prctl_map.start_data = addr; |
028ee4be3
|
1998 |
break; |
fe8c7f5cb
|
1999 |
case PR_SET_MM_END_DATA: |
4a00e9df2
|
2000 2001 2002 2003 |
prctl_map.end_data = addr; break; case PR_SET_MM_START_STACK: prctl_map.start_stack = addr; |
028ee4be3
|
2004 |
break; |
028ee4be3
|
2005 |
case PR_SET_MM_START_BRK: |
4a00e9df2
|
2006 |
prctl_map.start_brk = addr; |
028ee4be3
|
2007 |
break; |
028ee4be3
|
2008 |
case PR_SET_MM_BRK: |
4a00e9df2
|
2009 |
prctl_map.brk = addr; |
028ee4be3
|
2010 |
break; |
4a00e9df2
|
2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 |
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
|
2030 |
|
4a00e9df2
|
2031 |
switch (opt) { |
fe8c7f5cb
|
2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 |
/* * 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
|
2048 |
} |
4a00e9df2
|
2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 |
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
|
2060 |
error = 0; |
028ee4be3
|
2061 |
out: |
ddf1d398e
|
2062 |
up_write(&mm->mmap_sem); |
028ee4be3
|
2063 2064 |
return error; } |
300f786b2
|
2065 |
|
52b369415
|
2066 |
#ifdef CONFIG_CHECKPOINT_RESTORE |
300f786b2
|
2067 2068 2069 2070 |
static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return put_user(me->clear_child_tid, tid_addr); } |
52b369415
|
2071 |
#else |
300f786b2
|
2072 2073 2074 2075 |
static int prctl_get_tid_address(struct task_struct *me, int __user **tid_addr) { return -EINVAL; } |
028ee4be3
|
2076 |
#endif |
749860ce2
|
2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 |
static int propagate_has_child_subreaper(struct task_struct *p, void *data) { /* * If task has has_child_subreaper - all its decendants * already have these flag too and new decendants will * inherit it on fork, skip them. * * If we've found child_reaper - skip descendants in * it's subtree as they will never get out pidns. */ if (p->signal->has_child_subreaper || is_child_reaper(task_pid(p))) return 0; p->signal->has_child_subreaper = 1; return 1; } |
7d1254a14
|
2094 |
int __weak arch_prctl_spec_ctrl_get(struct task_struct *t, unsigned long which) |
33f6a0681
|
2095 2096 2097 |
{ return -EINVAL; } |
7d1254a14
|
2098 2099 |
int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which, unsigned long ctrl) |
33f6a0681
|
2100 2101 2102 |
{ return -EINVAL; } |
c4ea37c26
|
2103 2104 |
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, unsigned long, arg4, unsigned long, arg5) |
1da177e4c
|
2105 |
{ |
b6dff3ec5
|
2106 2107 2108 |
struct task_struct *me = current; unsigned char comm[sizeof(me->comm)]; long error; |
1da177e4c
|
2109 |
|
d84f4f992
|
2110 2111 |
error = security_task_prctl(option, arg2, arg3, arg4, arg5); if (error != -ENOSYS) |
1da177e4c
|
2112 |
return error; |
d84f4f992
|
2113 |
error = 0; |
1da177e4c
|
2114 |
switch (option) { |
f3cbd435b
|
2115 2116 2117 |
case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; |
1da177e4c
|
2118 |
break; |
f3cbd435b
|
2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 |
} 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
|
2131 |
break; |
f3cbd435b
|
2132 2133 2134 |
} set_dumpable(me->mm, arg2); break; |
1da177e4c
|
2135 |
|
f3cbd435b
|
2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 |
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
|
2199 2200 2201 2202 |
if (current->timer_slack_ns > ULONG_MAX) error = ULONG_MAX; else error = current->timer_slack_ns; |
f3cbd435b
|
2203 2204 2205 2206 |
break; case PR_SET_TIMERSLACK: if (arg2 <= 0) current->timer_slack_ns = |
6976675d9
|
2207 |
current->default_timer_slack_ns; |
f3cbd435b
|
2208 2209 2210 2211 2212 2213 2214 2215 2216 |
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
|
2217 |
return -EINVAL; |
f3cbd435b
|
2218 |
current->flags &= ~PF_MCE_PROCESS; |
4db96cf07
|
2219 |
break; |
f3cbd435b
|
2220 2221 2222 2223 2224 2225 2226 2227 2228 |
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
|
2229 |
else |
259e5e6c7
|
2230 |
return -EINVAL; |
259e5e6c7
|
2231 |
break; |
1da177e4c
|
2232 |
default: |
f3cbd435b
|
2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 |
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; |
749860ce2
|
2253 2254 2255 2256 |
if (!arg2) break; walk_process_tree(me, propagate_has_child_subreaper, NULL); |
f3cbd435b
|
2257 2258 2259 2260 2261 2262 2263 2264 |
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
|
2265 |
task_set_no_new_privs(current); |
f3cbd435b
|
2266 2267 2268 2269 |
break; case PR_GET_NO_NEW_PRIVS: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
1d4457f99
|
2270 |
return task_no_new_privs(current) ? 1 : 0; |
a0715cc22
|
2271 2272 2273 |
case PR_GET_THP_DISABLE: if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
186003323
|
2274 |
error = !!test_bit(MMF_DISABLE_THP, &me->mm->flags); |
a0715cc22
|
2275 2276 2277 2278 |
break; case PR_SET_THP_DISABLE: if (arg3 || arg4 || arg5) return -EINVAL; |
17b0573d7
|
2279 2280 |
if (down_write_killable(&me->mm->mmap_sem)) return -EINTR; |
a0715cc22
|
2281 |
if (arg2) |
186003323
|
2282 |
set_bit(MMF_DISABLE_THP, &me->mm->flags); |
a0715cc22
|
2283 |
else |
186003323
|
2284 |
clear_bit(MMF_DISABLE_THP, &me->mm->flags); |
a0715cc22
|
2285 2286 |
up_write(&me->mm->mmap_sem); break; |
fe3d197f8
|
2287 |
case PR_MPX_ENABLE_MANAGEMENT: |
e9d1b4f3c
|
2288 2289 |
if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
46a6e0cf1
|
2290 |
error = MPX_ENABLE_MANAGEMENT(); |
fe3d197f8
|
2291 2292 |
break; case PR_MPX_DISABLE_MANAGEMENT: |
e9d1b4f3c
|
2293 2294 |
if (arg2 || arg3 || arg4 || arg5) return -EINVAL; |
46a6e0cf1
|
2295 |
error = MPX_DISABLE_MANAGEMENT(); |
fe3d197f8
|
2296 |
break; |
9791554b4
|
2297 2298 2299 2300 2301 2302 |
case PR_SET_FP_MODE: error = SET_FP_MODE(me, arg2); break; case PR_GET_FP_MODE: error = GET_FP_MODE(me); break; |
33f6a0681
|
2303 2304 2305 |
case PR_GET_SPECULATION_CTRL: if (arg3 || arg4 || arg5) return -EINVAL; |
7d1254a14
|
2306 |
error = arch_prctl_spec_ctrl_get(me, arg2); |
33f6a0681
|
2307 2308 2309 2310 |
break; case PR_SET_SPECULATION_CTRL: if (arg4 || arg5) return -EINVAL; |
7d1254a14
|
2311 |
error = arch_prctl_spec_ctrl_set(me, arg2, arg3); |
33f6a0681
|
2312 |
break; |
f3cbd435b
|
2313 2314 2315 |
default: error = -EINVAL; break; |
1da177e4c
|
2316 2317 2318 |
} return error; } |
3cfc348bf
|
2319 |
|
836f92adf
|
2320 2321 |
SYSCALL_DEFINE3(getcpu, unsigned __user *, cpup, unsigned __user *, nodep, struct getcpu_cache __user *, unused) |
3cfc348bf
|
2322 2323 2324 |
{ int err = 0; int cpu = raw_smp_processor_id(); |
ec94fc3d5
|
2325 |
|
3cfc348bf
|
2326 2327 2328 2329 |
if (cpup) err |= put_user(cpu, cpup); if (nodep) err |= put_user(cpu_to_node(cpu), nodep); |
3cfc348bf
|
2330 2331 |
return err ? -EFAULT : 0; } |
10a0a8d4e
|
2332 |
|
4a22f1663
|
2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 |
/** * 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
|
2344 |
get_monotonic_boottime(&tp); |
4a22f1663
|
2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 |
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
|
2437 |
if (upper_32_bits(s.totalram) || upper_32_bits(s.totalswap)) { |
4a22f1663
|
2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 |
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 */ |