]>
Commit | Line | Data |
---|---|---|
fea681da | 1 | .\" Copyright (c) 1992 Drew Eckhardt <drew@cs.colorado.edu>, March 28, 1992 |
fb1fa92b | 2 | .\" and Copyright (c) Michael Kerrisk, 2001, 2002, 2005, 2013, 2019 |
2297bf0e | 3 | .\" |
95fb8859 | 4 | .\" SPDX-License-Identifier: GPL-1.0-or-later |
dccaff1e | 5 | .\" |
fea681da MK |
6 | .\" Modified by Michael Haardt <michael@moria.de> |
7 | .\" Modified 24 Jul 1993 by Rik Faith <faith@cs.unc.edu> | |
8 | .\" Modified 21 Aug 1994 by Michael Chastain <mec@shell.portal.com>: | |
9 | .\" New man page (copied from 'fork.2'). | |
10 | .\" Modified 10 June 1995 by Andries Brouwer <aeb@cwi.nl> | |
11 | .\" Modified 25 April 1998 by Xavier Leroy <Xavier.Leroy@inria.fr> | |
12 | .\" Modified 26 Jun 2001 by Michael Kerrisk | |
13 | .\" Mostly upgraded to 2.4.x | |
14 | .\" Added prototype for sys_clone() plus description | |
15 | .\" Added CLONE_THREAD with a brief description of thread groups | |
c13182ef | 16 | .\" Added CLONE_PARENT and revised entire page remove ambiguity |
fea681da MK |
17 | .\" between "calling process" and "parent process" |
18 | .\" Added CLONE_PTRACE and CLONE_VFORK | |
19 | .\" Added EPERM and EINVAL error codes | |
fd8a5be4 | 20 | .\" Renamed "__clone" to "clone" (which is the prototype in <sched.h>) |
fea681da | 21 | .\" various other minor tidy ups and clarifications. |
c11b1abf | 22 | .\" Modified 26 Jun 2001 by Michael Kerrisk <mtk.manpages@gmail.com> |
d9bfdb9c | 23 | .\" Updated notes for 2.4.7+ behavior of CLONE_THREAD |
c11b1abf | 24 | .\" Modified 15 Oct 2002 by Michael Kerrisk <mtk.manpages@gmail.com> |
fea681da MK |
25 | .\" Added description for CLONE_NEWNS, which was added in 2.4.19 |
26 | .\" Slightly rephrased, aeb. | |
27 | .\" Modified 1 Feb 2003 - added CLONE_SIGHAND restriction, aeb. | |
28 | .\" Modified 1 Jan 2004 - various updates, aeb | |
0967c11f | 29 | .\" Modified 2004-09-10 - added CLONE_PARENT_SETTID etc. - aeb. |
d9bfdb9c | 30 | .\" 2005-04-12, mtk, noted the PID caching behavior of NPTL's getpid() |
31830ef0 | 31 | .\" wrapper under BUGS. |
fd8a5be4 MK |
32 | .\" 2005-05-10, mtk, added CLONE_SYSVSEM, CLONE_UNTRACED, CLONE_STOPPED. |
33 | .\" 2005-05-17, mtk, Substantially enhanced discussion of CLONE_THREAD. | |
4e836144 | 34 | .\" 2008-11-18, mtk, order CLONE_* flags alphabetically |
82ee147a | 35 | .\" 2008-11-18, mtk, document CLONE_NEWPID |
43ce9dda | 36 | .\" 2008-11-19, mtk, document CLONE_NEWUTS |
667417b3 | 37 | .\" 2008-11-19, mtk, document CLONE_NEWIPC |
cfdc761b | 38 | .\" 2008-11-19, Jens Axboe, mtk, document CLONE_IO |
fea681da | 39 | .\" |
45186a5d | 40 | .TH CLONE 2 2021-03-22 "Linux man-pages (unreleased)" |
fea681da | 41 | .SH NAME |
a9e52b43 | 42 | clone, __clone2, clone3 \- create a child process |
48113faf AC |
43 | .SH LIBRARY |
44 | Standard C library | |
8fc3b2cf | 45 | .RI ( libc ", " \-lc ) |
fea681da | 46 | .SH SYNOPSIS |
c10859eb | 47 | .nf |
81f10dad | 48 | /* Prototype for the glibc wrapper function */ |
dbfe9c70 | 49 | .PP |
4f71ba5d | 50 | .B #define _GNU_SOURCE |
fea681da | 51 | .B #include <sched.h> |
dbfe9c70 | 52 | .PP |
81c2368f | 53 | .BI "int clone(int (*" "fn" ")(void *), void *" stack \ |
77ca5b1d | 54 | ", int " flags ", void *" "arg" ", ..." |
81c2368f MK |
55 | .BI " /* pid_t *" parent_tid ", void *" tls \ |
56 | ", pid_t *" child_tid " */ );" | |
dbfe9c70 | 57 | .PP |
faa0e55a MK |
58 | /* For the prototype of the raw clone() system call, see NOTES */ |
59 | .PP | |
a3805383 AC |
60 | .BR "#include <linux/sched.h>" " /* Definition of " "struct clone_args" " */" |
61 | .BR "#include <sched.h>" " /* Definition of " CLONE_* " constants */" | |
62 | .BR "#include <sys/syscall.h>" " /* Definition of " SYS_* " constants */" | |
63 | .B #include <unistd.h> | |
faa0e55a | 64 | .PP |
a3805383 AC |
65 | .BI "long syscall(SYS_clone3, struct clone_args *" cl_args ", size_t " size ); |
66 | .fi | |
bc2813df AC |
67 | .PP |
68 | .IR Note : | |
69 | glibc provides no wrapper for | |
70 | .BR clone3 (), | |
71 | necessitating the use of | |
72 | .BR syscall (2). | |
fea681da | 73 | .SH DESCRIPTION |
faa0e55a | 74 | These system calls |
8dd6b0bc | 75 | create a new ("child") process, in a manner similar to |
fea681da | 76 | .BR fork (2). |
efeece04 | 77 | .PP |
8dd6b0bc | 78 | By contrast with |
fea681da | 79 | .BR fork (2), |
225f5da8 | 80 | these system calls provide more precise control over what pieces of execution |
10337567 MK |
81 | context are shared between the calling process and the child process. |
82 | For example, using these system calls, the caller can control whether | |
83 | or not the two processes share the virtual address space, | |
84 | the table of file descriptors, and the table of signal handlers. | |
225f5da8 | 85 | These system calls also allow the new child process to be placed |
10337567 MK |
86 | in separate |
87 | .BR namespaces (7). | |
88 | .PP | |
89 | Note that in this manual | |
c13182ef | 90 | page, "calling process" normally corresponds to "parent process". |
a10c5a33 | 91 | But see the descriptions of |
c13182ef | 92 | .B CLONE_PARENT |
a10c5a33 MK |
93 | and |
94 | .B CLONE_THREAD | |
10337567 | 95 | below. |
efeece04 | 96 | .PP |
faa0e55a MK |
97 | This page describes the following interfaces: |
98 | .IP * 3 | |
99 | The glibc | |
100 | .BR clone () | |
101 | wrapper function and the underlying system call on which it is based. | |
102 | The main text describes the wrapper function; | |
103 | the differences for the raw system call | |
104 | are described toward the end of this page. | |
105 | .IP * | |
106 | The newer | |
107 | .BR clone3 () | |
108 | system call. | |
5261b0fe MK |
109 | .PP |
110 | In the remainder of this page, the terminology "the clone call" is used | |
324f6154 | 111 | when noting details that apply to all of these interfaces, |
faa0e55a MK |
112 | .\" |
113 | .SS The clone() wrapper function | |
faa0e55a MK |
114 | When the child process is created with the |
115 | .BR clone () | |
116 | wrapper function, | |
7495cbc7 MK |
117 | it commences execution by calling the function pointed to by the argument |
118 | .IR fn . | |
fea681da | 119 | (This differs from |
c13182ef | 120 | .BR fork (2), |
fea681da | 121 | where execution continues in the child from the point |
c13182ef MK |
122 | of the |
123 | .BR fork (2) | |
fea681da MK |
124 | call.) |
125 | The | |
fea681da | 126 | .I arg |
7495cbc7 MK |
127 | argument is passed as the argument of the function |
128 | .IR fn . | |
efeece04 | 129 | .PP |
c13182ef | 130 | When the |
fea681da | 131 | .IR fn ( arg ) |
4ba17a6d | 132 | function returns, the child process terminates. |
c13182ef | 133 | The integer returned by |
fea681da | 134 | .I fn |
4ba17a6d | 135 | is the exit status for the child process. |
c13182ef | 136 | The child process may also terminate explicitly by calling |
fea681da MK |
137 | .BR exit (2) |
138 | or after receiving a fatal signal. | |
efeece04 | 139 | .PP |
fea681da | 140 | The |
81c2368f | 141 | .I stack |
c13182ef MK |
142 | argument specifies the location of the stack used by the child process. |
143 | Since the child and calling process may share memory, | |
fea681da | 144 | it is not possible for the child process to execute in the |
c13182ef MK |
145 | same stack as the calling process. |
146 | The calling process must therefore | |
fea681da MK |
147 | set up memory space for the child stack and pass a pointer to this |
148 | space to | |
edcc65ff | 149 | .BR clone (). |
5fab2e7c | 150 | Stacks grow downward on all processors that run Linux |
fea681da | 151 | (except the HP PA processors), so |
81c2368f | 152 | .I stack |
fea681da MK |
153 | usually points to the topmost address of the memory space set up for |
154 | the child stack. | |
faa0e55a MK |
155 | Note that |
156 | .BR clone () | |
157 | does not provide a means whereby the caller can inform the kernel of the | |
158 | size of the stack area. | |
159 | .PP | |
160 | The remaining arguments to | |
161 | .BR clone () | |
162 | are discussed below. | |
163 | .\" | |
164 | .SS clone3() | |
faa0e55a MK |
165 | The |
166 | .BR clone3 () | |
167 | system call provides a superset of the functionality of the older | |
168 | .BR clone () | |
169 | interface. | |
170 | It also provides a number of API improvements, including: | |
171 | space for additional flags bits; | |
172 | cleaner separation in the use of various arguments; | |
173 | and the ability to specify the size of the child's stack area. | |
174 | .PP | |
175 | As with | |
176 | .BR fork (2), | |
177 | .BR clone3 () | |
178 | returns in both the parent and the child. | |
179 | It returns 0 in the child process and returns the PID of the child | |
180 | in the parent. | |
181 | .PP | |
182 | The | |
183 | .I cl_args | |
184 | argument of | |
185 | .BR clone3 () | |
186 | is a structure of the following form: | |
187 | .PP | |
188 | .in +4n | |
189 | .EX | |
190 | struct clone_args { | |
191 | u64 flags; /* Flags bit mask */ | |
192 | u64 pidfd; /* Where to store PID file descriptor | |
e71d103b | 193 | (\fIint *\fP) */ |
faa0e55a | 194 | u64 child_tid; /* Where to store child TID, |
861d36ba | 195 | in child\(aqs memory (\fIpid_t *\fP) */ |
faa0e55a | 196 | u64 parent_tid; /* Where to store child TID, |
e71d103b | 197 | in parent\(aqs memory (\fIpid_t *\fP) */ |
faa0e55a MK |
198 | u64 exit_signal; /* Signal to deliver to parent on |
199 | child termination */ | |
200 | u64 stack; /* Pointer to lowest byte of stack */ | |
201 | u64 stack_size; /* Size of stack */ | |
202 | u64 tls; /* Location of new TLS */ | |
f7d5e082 MK |
203 | u64 set_tid; /* Pointer to a \fIpid_t\fP array |
204 | (since Linux 5.5) */ | |
205 | u64 set_tid_size; /* Number of elements in \fIset_tid\fP | |
206 | (since Linux 5.5) */ | |
ed7c1377 MK |
207 | u64 cgroup; /* File descriptor for target cgroup |
208 | of child (since Linux 5.7) */ | |
faa0e55a MK |
209 | }; |
210 | .EE | |
211 | .in | |
212 | .PP | |
213 | The | |
214 | .I size | |
215 | argument that is supplied to | |
216 | .BR clone3 () | |
217 | should be initialized to the size of this structure. | |
218 | (The existence of the | |
219 | .I size | |
220 | argument permits future extensions to the | |
1ae6b2c7 | 221 | .I clone_args |
faa0e55a MK |
222 | structure.) |
223 | .PP | |
224 | The stack for the child process is specified via | |
225 | .IR cl_args.stack , | |
226 | which points to the lowest byte of the stack area, | |
227 | and | |
228 | .IR cl_args.stack_size , | |
229 | which specifies the size of the stack in bytes. | |
230 | In the case where the | |
1ae6b2c7 | 231 | .B CLONE_VM |
faa0e55a MK |
232 | flag (see below) is specified, a stack must be explicitly allocated |
233 | and specified. | |
234 | Otherwise, these two fields can be specified as NULL and 0, | |
235 | which causes the child to use the same stack area as the parent | |
236 | (in the child's own virtual address space). | |
237 | .PP | |
238 | The remaining fields in the | |
239 | .I cl_args | |
240 | argument are discussed below. | |
241 | .\" | |
242 | .SS Equivalence between clone() and clone3() arguments | |
faa0e55a MK |
243 | Unlike the older |
244 | .BR clone () | |
245 | interface, where arguments are passed individually, in the newer | |
246 | .BR clone3 () | |
247 | interface the arguments are packaged into the | |
248 | .I clone_args | |
249 | structure shown above. | |
250 | This structure allows for a superset of the information passed via the | |
251 | .BR clone () | |
252 | arguments. | |
253 | .PP | |
254 | The following table shows the equivalence between the arguments of | |
255 | .BR clone () | |
256 | and the fields in the | |
257 | .I clone_args | |
258 | argument supplied to | |
259 | .BR clone3 (): | |
0b174fe0 | 260 | .RS 4 |
faa0e55a MK |
261 | .TS |
262 | lb lb lb | |
263 | l l l | |
264 | li li l. | |
97883fae | 265 | clone() clone3() Notes |
faa0e55a | 266 | \fIcl_args\fP field |
0b174fe0 MK |
267 | flags & \(ti0xff flags T{ |
268 | For most flags; details below | |
269 | T} | |
faa0e55a MK |
270 | parent_tid pidfd See CLONE_PIDFD |
271 | child_tid child_tid See CLONE_CHILD_SETTID | |
272 | parent_tid parent_tid See CLONE_PARENT_SETTID | |
273 | flags & 0xff exit_signal | |
274 | stack stack | |
275 | \fP---\fP stack_size | |
276 | tls tls See CLONE_SETTLS | |
bf031aaa AR |
277 | \fP---\fP set_tid See below for details |
278 | \fP---\fP set_tid_size | |
ed7c1377 | 279 | \fP---\fP cgroup See CLONE_INTO_CGROUP |
faa0e55a MK |
280 | .TE |
281 | .RE | |
5fbce8f2 MK |
282 | .\" |
283 | .SS The child termination signal | |
faa0e55a MK |
284 | When the child process terminates, a signal may be sent to the parent. |
285 | The termination signal is specified in the low byte of | |
fea681da | 286 | .I flags |
faa0e55a MK |
287 | .RB ( clone ()) |
288 | or in | |
289 | .I cl_args.exit_signal | |
290 | .RB ( clone3 ()). | |
fd8a5be4 | 291 | If this signal is specified as anything other than |
fea681da MK |
292 | .BR SIGCHLD , |
293 | then the parent process must specify the | |
c13182ef MK |
294 | .B __WALL |
295 | or | |
fea681da | 296 | .B __WCLONE |
c13182ef MK |
297 | options when waiting for the child with |
298 | .BR wait (2). | |
faa0e55a | 299 | If no signal (i.e., zero) is specified, then the parent process is not signaled |
fea681da | 300 | when the child terminates. |
5fbce8f2 | 301 | .\" |
bf031aaa | 302 | .SS The set_tid array |
bf031aaa AR |
303 | By default, the kernel chooses the next sequential PID for the new |
304 | process in each of the PID namespaces where it is present. | |
305 | When creating a process with | |
306 | .BR clone3 (), | |
307 | the | |
308 | .I set_tid | |
b386cee3 MK |
309 | array (available since Linux 5.5) |
310 | can be used to select specific PIDs for the process in some | |
bf031aaa | 311 | or all of the PID namespaces where it is present. |
ee8bb310 | 312 | If the PID of the newly created process should be set only for the current |
bf031aaa AR |
313 | PID namespace or in the newly created PID namespace (if |
314 | .I flags | |
315 | contains | |
316 | .BR CLONE_NEWPID ) | |
317 | then the first element in the | |
318 | .I set_tid | |
319 | array has to be the desired PID and | |
320 | .I set_tid_size | |
321 | needs to be 1. | |
322 | .PP | |
323 | If the PID of the newly created process should have a certain value in | |
ee8bb310 | 324 | multiple PID namespaces, then the |
bf031aaa | 325 | .I set_tid |
09007c4b MK |
326 | array can have multiple entries. |
327 | The first entry defines the PID in the most | |
ee8bb310 MK |
328 | deeply nested PID namespace and each of the following entries contains |
329 | the PID in the | |
330 | corresponding ancestor PID namespace. | |
09007c4b | 331 | The number of PID namespaces in which a PID |
bf031aaa AR |
332 | should be set is defined by |
333 | .I set_tid_size | |
334 | which cannot be larger than the number of currently nested PID namespaces. | |
335 | .PP | |
336 | To create a process with the following PIDs in a PID namespace hierarchy: | |
0b174fe0 | 337 | .RS 4 |
bf031aaa | 338 | .TS |
ee8bb310 MK |
339 | lb lb lb |
340 | l l l. | |
341 | PID NS level Requested PID Notes | |
342 | 0 31496 Outermost PID namespace | |
bf031aaa | 343 | 1 42 |
ee8bb310 | 344 | 2 7 Innermost PID namespace |
bf031aaa AR |
345 | .TE |
346 | .RE | |
347 | .PP | |
348 | Set the array to: | |
349 | .PP | |
ee8bb310 | 350 | .in +4n |
bf031aaa | 351 | .EX |
ee8bb310 MK |
352 | set_tid[0] = 7; |
353 | set_tid[1] = 42; | |
354 | set_tid[2] = 31496; | |
355 | set_tid_size = 3; | |
bf031aaa | 356 | .EE |
ee8bb310 | 357 | .in |
bf031aaa AR |
358 | .PP |
359 | If only the PIDs in the two innermost PID namespaces | |
360 | need to be specified, set the array to: | |
361 | .PP | |
ee8bb310 | 362 | .in +4n |
bf031aaa | 363 | .EX |
ee8bb310 MK |
364 | set_tid[0] = 7; |
365 | set_tid[1] = 42; | |
366 | set_tid_size = 2; | |
bf031aaa | 367 | .EE |
ee8bb310 | 368 | .in |
bf031aaa AR |
369 | .PP |
370 | The PID in the PID namespaces outside the two innermost PID namespaces | |
95887a00 | 371 | is selected the same way as any other PID is selected. |
bf031aaa AR |
372 | .PP |
373 | The | |
374 | .I set_tid | |
375 | feature requires | |
1ae6b2c7 | 376 | .B CAP_SYS_ADMIN |
1e4d6750 MK |
377 | or |
378 | (since Linux 5.9) | |
379 | .\" commit 124ea650d3072b005457faed69909221c2905a1f | |
380 | .\" commit 1caef81da05a84a40dbf02110e967ce6d1135ff6 | |
1ae6b2c7 | 381 | .B CAP_CHECKPOINT_RESTORE |
bf031aaa AR |
382 | in all owning user namespaces of the target PID namespaces. |
383 | .PP | |
ee8bb310 MK |
384 | Callers may only choose a PID greater than 1 in a given PID namespace |
385 | if an | |
1ae6b2c7 | 386 | .B init |
ee8bb310 | 387 | process (i.e., a process with PID 1) already exists in that namespace. |
09007c4b | 388 | Otherwise the PID |
bf031aaa AR |
389 | entry for this PID namespace must be 1. |
390 | .\" | |
16853a31 | 391 | .SS The flags mask |
faa0e55a MK |
392 | Both |
393 | .BR clone () | |
394 | and | |
395 | .BR clone3 () | |
396 | allow a flags bit mask that modifies their behavior | |
397 | and allows the caller to specify what is shared between the calling process | |
398 | and the child process. | |
5261b0fe MK |
399 | This bit mask\(emthe |
400 | .I flags | |
401 | argument of | |
402 | .BR clone () | |
403 | or the | |
404 | .I cl_args.flags | |
405 | field passed to | |
406 | .BR clone3 ()\(emis | |
16853a31 MK |
407 | referred to as the |
408 | .I flags | |
409 | mask in the remainder of this page. | |
410 | .PP | |
411 | The | |
412 | .I flags | |
413 | mask is specified as a bitwise-OR of zero or more of | |
414 | the constants listed below. | |
5261b0fe | 415 | Except as noted below, these flags are available |
faa0e55a MK |
416 | (and have the same effect) in both |
417 | .BR clone () | |
418 | and | |
419 | .BR clone3 (). | |
fea681da | 420 | .TP |
f5dbc7c8 | 421 | .BR CLONE_CHILD_CLEARTID " (since Linux 2.5.49)" |
e2bf1234 | 422 | Clear (zero) the child thread ID at the location pointed to by |
81c2368f | 423 | .I child_tid |
faa0e55a MK |
424 | .RB ( clone ()) |
425 | or | |
426 | .I cl_args.child_tid | |
427 | .RB ( clone3 ()) | |
f5dbc7c8 MK |
428 | in child memory when the child exits, and do a wakeup on the futex |
429 | at that address. | |
430 | The address involved may be changed by the | |
431 | .BR set_tid_address (2) | |
432 | system call. | |
433 | This is used by threading libraries. | |
434 | .TP | |
435 | .BR CLONE_CHILD_SETTID " (since Linux 2.5.49)" | |
e2bf1234 | 436 | Store the child thread ID at the location pointed to by |
81c2368f | 437 | .I child_tid |
faa0e55a MK |
438 | .RB ( clone ()) |
439 | or | |
440 | .I cl_args.child_tid | |
441 | .RB ( clone3 ()) | |
8ef021ea | 442 | in the child's memory. |
5261b0fe | 443 | The store operation completes before the clone call |
6ab62ed8 | 444 | returns control to user space in the child process. |
5261b0fe | 445 | (Note that the store operation may not have completed before the clone call |
95887a00 | 446 | returns in the parent process, which is relevant if the |
1ae6b2c7 | 447 | .B CLONE_VM |
6ab62ed8 | 448 | flag is also employed.) |
f5dbc7c8 | 449 | .TP |
27f14b44 MK |
450 | .BR CLONE_CLEAR_SIGHAND " (since Linux 5.5)" |
451 | .\" commit b612e5df4587c934bd056bf05f4a1deca4de4f75 | |
452 | By default, signal dispositions in the child thread are the same as | |
453 | in the parent. | |
454 | If this flag is specified, | |
455 | then all signals that are handled in the parent | |
456 | are reset to their default dispositions | |
457 | .RB ( SIG_DFL ) | |
458 | in the child. | |
459 | .IP | |
460 | Specifying this flag together with | |
461 | .B CLONE_SIGHAND | |
462 | is nonsensical and disallowed. | |
463 | .TP | |
baa435c6 MK |
464 | .BR CLONE_DETACHED " (historical)" |
465 | For a while (during the Linux 2.5 development series) | |
466 | .\" added in 2.5.32; removed in 2.6.0-test4 | |
467 | there was a | |
468 | .B CLONE_DETACHED | |
469 | flag, | |
470 | which caused the parent not to receive a signal when the child terminated. | |
471 | Ultimately, the effect of this flag was subsumed under the | |
1ae6b2c7 | 472 | .B CLONE_THREAD |
baa435c6 MK |
473 | flag and by the time Linux 2.6.0 was released, this flag had no effect. |
474 | Starting in Linux 2.6.2, the need to give this flag together with | |
475 | .B CLONE_THREAD | |
476 | disappeared. | |
477 | .IP | |
478 | This flag is still defined, but it is usually ignored when calling | |
479 | .BR clone (). | |
480 | However, see the description of | |
1ae6b2c7 | 481 | .B CLONE_PIDFD |
baa435c6 MK |
482 | for some exceptions. |
483 | .TP | |
1603d6a1 | 484 | .BR CLONE_FILES " (since Linux 2.0)" |
fea681da | 485 | If |
f5dbc7c8 MK |
486 | .B CLONE_FILES |
487 | is set, the calling process and the child process share the same file | |
488 | descriptor table. | |
489 | Any file descriptor created by the calling process or by the child | |
490 | process is also valid in the other process. | |
491 | Similarly, if one of the processes closes a file descriptor, | |
492 | or changes its associated flags (using the | |
493 | .BR fcntl (2) | |
494 | .B F_SETFD | |
495 | operation), the other process is also affected. | |
8a76b19e KE |
496 | If a process sharing a file descriptor table calls |
497 | .BR execve (2), | |
498 | its file descriptor table is duplicated (unshared). | |
efeece04 | 499 | .IP |
fea681da | 500 | If |
f5dbc7c8 MK |
501 | .B CLONE_FILES |
502 | is not set, the child process inherits a copy of all file descriptors | |
5261b0fe | 503 | opened in the calling process at the time of the clone call. |
f5dbc7c8 MK |
504 | Subsequent operations that open or close file descriptors, |
505 | or change file descriptor flags, | |
506 | performed by either the calling | |
507 | process or the child process do not affect the other process. | |
db8ba2b4 | 508 | Note, however, |
839d161f MK |
509 | that the duplicated file descriptors in the child refer to the same |
510 | open file descriptions as the corresponding file descriptors | |
511 | in the calling process, | |
2433365b | 512 | and thus share file offsets and file status flags (see |
db8ba2b4 | 513 | .BR open (2)). |
fea681da | 514 | .TP |
1603d6a1 | 515 | .BR CLONE_FS " (since Linux 2.0)" |
fea681da MK |
516 | If |
517 | .B CLONE_FS | |
9ee4a2b6 | 518 | is set, the caller and the child process share the same filesystem |
c13182ef | 519 | information. |
9ee4a2b6 | 520 | This includes the root of the filesystem, the current |
c13182ef MK |
521 | working directory, and the umask. |
522 | Any call to | |
fea681da MK |
523 | .BR chroot (2), |
524 | .BR chdir (2), | |
525 | or | |
526 | .BR umask (2) | |
edcc65ff | 527 | performed by the calling process or the child process also affects the |
fea681da | 528 | other process. |
efeece04 | 529 | .IP |
c13182ef | 530 | If |
fea681da | 531 | .B CLONE_FS |
9ee4a2b6 | 532 | is not set, the child process works on a copy of the filesystem |
5261b0fe | 533 | information of the calling process at the time of the clone call. |
fea681da MK |
534 | Calls to |
535 | .BR chroot (2), | |
536 | .BR chdir (2), | |
4ba17a6d | 537 | or |
fea681da MK |
538 | .BR umask (2) |
539 | performed later by one of the processes do not affect the other process. | |
fea681da | 540 | .TP |
edc1b9fc MK |
541 | .BR CLONE_INTO_CGROUP " (since Linux 5.7)" |
542 | .\" commit ef2c41cf38a7559bbf91af42d5b6a4429db8fc68 | |
543 | By default, a child process is placed in the same version 2 | |
544 | cgroup as its parent. | |
545 | The | |
546 | .B CLONE_INTO_CGROUP | |
17d86030 | 547 | flag allows the child process to be created in a different version 2 cgroup. |
edc1b9fc | 548 | (Note that |
1ae6b2c7 | 549 | .B CLONE_INTO_CGROUP |
edc1b9fc MK |
550 | has effect only for version 2 cgroups.) |
551 | .IP | |
552 | In order to place the child process in a different cgroup, | |
553 | the caller specifies | |
1ae6b2c7 | 554 | .B CLONE_INTO_CGROUP |
edc1b9fc MK |
555 | in |
556 | .I cl_args.flags | |
557 | and passes a file descriptor that refers to a version 2 cgroup in the | |
558 | .I cl_args.cgroup | |
559 | field. | |
17d86030 | 560 | (This file descriptor can be obtained by opening a cgroup v2 directory |
edc1b9fc MK |
561 | using either the |
562 | .B O_RDONLY | |
563 | or the | |
564 | .B O_PATH | |
565 | flag.) | |
566 | Note that all of the usual restrictions (described in | |
567 | .BR cgroups (7)) | |
568 | on placing a process into a version 2 cgroup apply. | |
569 | .IP | |
b3041511 | 570 | Among the possible use cases for |
1ae6b2c7 | 571 | .B CLONE_INTO_CGROUP |
b3041511 MK |
572 | are the following: |
573 | .RS | |
574 | .IP * 3 | |
edc1b9fc MK |
575 | Spawning a process into a cgroup different from the parent's cgroup |
576 | makes it possible for a service manager to directly spawn new | |
577 | services into dedicated cgroups. | |
578 | This eliminates the accounting | |
579 | jitter that would be caused if the child process was first created in the | |
580 | same cgroup as the parent and then | |
581 | moved into the target cgroup. | |
4fe3acd9 MK |
582 | Furthermore, spawning the child process directly into a target cgroup |
583 | is significantly cheaper than moving the child process into | |
584 | the target cgroup after it has been created. | |
b3041511 | 585 | .IP * |
edc1b9fc | 586 | The |
1ae6b2c7 | 587 | .B CLONE_INTO_CGROUP |
edc1b9fc MK |
588 | flag also allows the creation of |
589 | frozen child processes by spawning them into a frozen cgroup. | |
590 | (See | |
591 | .BR cgroups (7) | |
592 | for a description of the freezer controller.) | |
b3041511 | 593 | .IP * |
edc1b9fc MK |
594 | For threaded applications (or even thread implementations which |
595 | make use of cgroups to limit individual threads), it is possible to | |
596 | establish a fixed cgroup layout before spawning each thread | |
597 | directly into its target cgroup. | |
b3041511 | 598 | .RE |
edc1b9fc | 599 | .TP |
a4cc375e | 600 | .BR CLONE_IO " (since Linux 2.6.25)" |
11f27a1c JA |
601 | If |
602 | .B CLONE_IO | |
603 | is set, then the new process shares an I/O context with | |
604 | the calling process. | |
605 | If this flag is not set, then (as with | |
606 | .BR fork (2)) | |
607 | the new process has its own I/O context. | |
efeece04 | 608 | .IP |
11f27a1c | 609 | .\" The following based on text from Jens Axboe |
d1f84ed7 | 610 | The I/O context is the I/O scope of the disk scheduler (i.e., |
11f27a1c JA |
611 | what the I/O scheduler uses to model scheduling of a process's I/O). |
612 | If processes share the same I/O context, | |
613 | they are treated as one by the I/O scheduler. | |
614 | As a consequence, they get to share disk time. | |
615 | For some I/O schedulers, | |
616 | .\" the anticipatory and CFQ scheduler | |
617 | if two processes share an I/O context, | |
618 | they will be allowed to interleave their disk access. | |
619 | If several threads are doing I/O on behalf of the same process | |
620 | .RB ( aio_read (3), | |
621 | for instance), they should employ | |
1ae6b2c7 | 622 | .B CLONE_IO |
11f27a1c JA |
623 | to get better I/O performance. |
624 | .\" with CFQ and AS. | |
efeece04 | 625 | .IP |
11f27a1c JA |
626 | If the kernel is not configured with the |
627 | .B CONFIG_BLOCK | |
628 | option, this flag is a no-op. | |
629 | .TP | |
c5af0674 MK |
630 | .BR CLONE_NEWCGROUP " (since Linux 4.6)" |
631 | Create the process in a new cgroup namespace. | |
632 | If this flag is not set, then (as with | |
633 | .BR fork (2)) | |
634 | the process is created in the same cgroup namespaces as the calling process. | |
efeece04 | 635 | .IP |
c5af0674 | 636 | For further information on cgroup namespaces, see |
b9fe4bc3 | 637 | .BR cgroup_namespaces (7). |
efeece04 | 638 | .IP |
c5af0674 MK |
639 | Only a privileged process |
640 | .RB ( CAP_SYS_ADMIN ) | |
641 | can employ | |
642 | .BR CLONE_NEWCGROUP . | |
643 | .\" | |
644 | .TP | |
8722311b | 645 | .BR CLONE_NEWIPC " (since Linux 2.6.19)" |
667417b3 MK |
646 | If |
647 | .B CLONE_NEWIPC | |
648 | is set, then create the process in a new IPC namespace. | |
649 | If this flag is not set, then (as with | |
06b30458 | 650 | .BR fork (2)), |
667417b3 MK |
651 | the process is created in the same IPC namespace as |
652 | the calling process. | |
efeece04 | 653 | .IP |
981eda4a MK |
654 | For further information on IPC namespaces, see |
655 | .BR ipc_namespaces (7). | |
656 | .IP | |
ab5dd83f MK |
657 | Only a privileged process |
658 | .RB ( CAP_SYS_ADMIN ) | |
659 | can employ | |
660 | .BR CLONE_NEWIPC . | |
667417b3 MK |
661 | This flag can't be specified in conjunction with |
662 | .BR CLONE_SYSVSEM . | |
663 | .TP | |
163bf178 | 664 | .BR CLONE_NEWNET " (since Linux 2.6.24)" |
33a0ccb2 | 665 | (The implementation of this flag was completed only |
9108d867 | 666 | by about kernel version 2.6.29.) |
efeece04 | 667 | .IP |
163bf178 MK |
668 | If |
669 | .B CLONE_NEWNET | |
670 | is set, then create the process in a new network namespace. | |
671 | If this flag is not set, then (as with | |
57ef8c39 | 672 | .BR fork (2)) |
163bf178 MK |
673 | the process is created in the same network namespace as |
674 | the calling process. | |
efeece04 | 675 | .IP |
73680728 | 676 | For further information on network namespaces, see |
40002795 | 677 | .BR network_namespaces (7). |
efeece04 | 678 | .IP |
ab5dd83f MK |
679 | Only a privileged process |
680 | .RB ( CAP_SYS_ADMIN ) | |
681 | can employ | |
682 | .BR CLONE_NEWNET . | |
163bf178 | 683 | .TP |
c10859eb | 684 | .BR CLONE_NEWNS " (since Linux 2.4.19)" |
3dd2331c MK |
685 | If |
686 | .B CLONE_NEWNS | |
687 | is set, the cloned child is started in a new mount namespace, | |
688 | initialized with a copy of the namespace of the parent. | |
689 | If | |
fea681da | 690 | .B CLONE_NEWNS |
3dd2331c | 691 | is not set, the child lives in the same mount |
4df2eb09 | 692 | namespace as the parent. |
efeece04 | 693 | .IP |
981eda4a MK |
694 | For further information on mount namespaces, see |
695 | .BR namespaces (7) | |
696 | and | |
697 | .BR mount_namespaces (7). | |
698 | .IP | |
ab5dd83f MK |
699 | Only a privileged process |
700 | .RB ( CAP_SYS_ADMIN ) | |
701 | can employ | |
702 | .BR CLONE_NEWNS . | |
fea681da MK |
703 | It is not permitted to specify both |
704 | .B CLONE_NEWNS | |
705 | and | |
706 | .B CLONE_FS | |
9219d208 | 707 | .\" See https://lwn.net/Articles/543273/ |
5261b0fe | 708 | in the same clone call. |
9d005472 MK |
709 | .TP |
710 | .BR CLONE_NEWPID " (since Linux 2.6.24)" | |
711 | .\" This explanation draws a lot of details from | |
712 | .\" http://lwn.net/Articles/259217/ | |
713 | .\" Authors: Pavel Emelyanov <xemul@openvz.org> | |
714 | .\" and Kir Kolyshkin <kir@openvz.org> | |
715 | .\" | |
716 | .\" The primary kernel commit is 30e49c263e36341b60b735cbef5ca37912549264 | |
717 | .\" Author: Pavel Emelyanov <xemul@openvz.org> | |
718 | If | |
719 | .B CLONE_NEWPID | |
720 | is set, then create the process in a new PID namespace. | |
721 | If this flag is not set, then (as with | |
722 | .BR fork (2)) | |
723 | the process is created in the same PID namespace as | |
724 | the calling process. | |
efeece04 | 725 | .IP |
9d005472 | 726 | For further information on PID namespaces, see |
7e0e902b MK |
727 | .BR namespaces (7) |
728 | and | |
39b3f005 | 729 | .BR pid_namespaces (7). |
efeece04 | 730 | .IP |
ab5dd83f MK |
731 | Only a privileged process |
732 | .RB ( CAP_SYS_ADMIN ) | |
733 | can employ | |
734 | .BR CLONE_NEWPID . | |
9d005472 | 735 | This flag can't be specified in conjunction with |
1ae6b2c7 | 736 | .B CLONE_THREAD |
f0007192 MK |
737 | or |
738 | .BR CLONE_PARENT . | |
70d21f17 | 739 | .TP |
1ae6b2c7 | 740 | .B CLONE_NEWUSER |
06b30458 MK |
741 | (This flag first became meaningful for |
742 | .BR clone () | |
4d2b3ed7 MK |
743 | in Linux 2.6.23, |
744 | the current | |
11a38815 | 745 | .BR clone () |
4d2b3ed7 MK |
746 | semantics were merged in Linux 3.5, |
747 | and the final pieces to make the user namespaces completely usable were | |
748 | merged in Linux 3.8.) | |
efeece04 | 749 | .IP |
70d21f17 EB |
750 | If |
751 | .B CLONE_NEWUSER | |
06b30458 MK |
752 | is set, then create the process in a new user namespace. |
753 | If this flag is not set, then (as with | |
57ef8c39 | 754 | .BR fork (2)) |
70d21f17 | 755 | the process is created in the same user namespace as the calling process. |
efeece04 | 756 | .IP |
981eda4a MK |
757 | For further information on user namespaces, see |
758 | .BR namespaces (7) | |
759 | and | |
760 | .BR user_namespaces (7). | |
761 | .IP | |
fefbcba8 | 762 | Before Linux 3.8, use of |
1ae6b2c7 | 763 | .B CLONE_NEWUSER |
fefbcba8 MK |
764 | required that the caller have three capabilities: |
765 | .BR CAP_SYS_ADMIN , | |
766 | .BR CAP_SETUID , | |
767 | and | |
768 | .BR CAP_SETGID . | |
769 | .\" Before Linux 2.6.29, it appears that only CAP_SYS_ADMIN was needed | |
06b30458 | 770 | Starting with Linux 3.8, |
9d005472 | 771 | no privileges are needed to create a user namespace. |
efeece04 | 772 | .IP |
5e72cf7d | 773 | This flag can't be specified in conjunction with |
1ae6b2c7 | 774 | .B CLONE_THREAD |
5e72cf7d MK |
775 | or |
776 | .BR CLONE_PARENT . | |
777 | For security reasons, | |
778 | .\" commit e66eded8309ebf679d3d3c1f5820d1f2ca332c71 | |
779 | .\" https://lwn.net/Articles/543273/ | |
780 | .\" The fix actually went into 3.9 and into 3.8.3. However, user namespaces | |
781 | .\" were, for practical purposes, unusable in earlier 3.8.x because of the | |
ab3311aa | 782 | .\" various filesystems that didn't support userns. |
1ae6b2c7 | 783 | .B CLONE_NEWUSER |
f0007192 | 784 | cannot be specified in conjunction with |
5e72cf7d | 785 | .BR CLONE_FS . |
82ee147a | 786 | .TP |
43ce9dda MK |
787 | .BR CLONE_NEWUTS " (since Linux 2.6.19)" |
788 | If | |
789 | .B CLONE_NEWUTS | |
e1b11906 MK |
790 | is set, then create the process in a new UTS namespace, |
791 | whose identifiers are initialized by duplicating the identifiers | |
792 | from the UTS namespace of the calling process. | |
43ce9dda | 793 | If this flag is not set, then (as with |
57ef8c39 | 794 | .BR fork (2)) |
43ce9dda MK |
795 | the process is created in the same UTS namespace as |
796 | the calling process. | |
efeece04 | 797 | .IP |
981eda4a MK |
798 | For further information on UTS namespaces, see |
799 | .BR uts_namespaces (7). | |
800 | .IP | |
ab5dd83f MK |
801 | Only a privileged process |
802 | .RB ( CAP_SYS_ADMIN ) | |
803 | can employ | |
804 | .BR CLONE_NEWUTS . | |
43ce9dda | 805 | .TP |
f5dbc7c8 MK |
806 | .BR CLONE_PARENT " (since Linux 2.3.12)" |
807 | If | |
808 | .B CLONE_PARENT | |
809 | is set, then the parent of the new child (as returned by | |
810 | .BR getppid (2)) | |
811 | will be the same as that of the calling process. | |
efeece04 | 812 | .IP |
f5dbc7c8 MK |
813 | If |
814 | .B CLONE_PARENT | |
815 | is not set, then (as with | |
816 | .BR fork (2)) | |
817 | the child's parent is the calling process. | |
efeece04 | 818 | .IP |
f5dbc7c8 MK |
819 | Note that it is the parent process, as returned by |
820 | .BR getppid (2), | |
821 | which is signaled when the child terminates, so that | |
822 | if | |
823 | .B CLONE_PARENT | |
824 | is set, then the parent of the calling process, rather than the | |
95887a00 | 825 | calling process itself, is signaled. |
a17b9d28 | 826 | .IP |
4269a6ab | 827 | The |
a17b9d28 | 828 | .B CLONE_PARENT |
4269a6ab MK |
829 | flag can't be used in clone calls by the |
830 | global init process (PID 1 in the initial PID namespace) | |
831 | and init processes in other PID namespaces. | |
832 | This restriction prevents the creation of multi-rooted process trees | |
833 | as well as the creation of unreapable zombies in the initial PID namespace. | |
f5dbc7c8 MK |
834 | .TP |
835 | .BR CLONE_PARENT_SETTID " (since Linux 2.5.49)" | |
e2bf1234 | 836 | Store the child thread ID at the location pointed to by |
81c2368f | 837 | .I parent_tid |
faa0e55a MK |
838 | .RB ( clone ()) |
839 | or | |
d5d482ec | 840 | .I cl_args.parent_tid |
faa0e55a | 841 | .RB ( clone3 ()) |
8ef021ea | 842 | in the parent's memory. |
f5dbc7c8 MK |
843 | (In Linux 2.5.32-2.5.48 there was a flag |
844 | .B CLONE_SETTID | |
845 | that did this.) | |
5261b0fe | 846 | The store operation completes before the clone call |
b5da2f91 | 847 | returns control to user space. |
f5dbc7c8 | 848 | .TP |
1c173eb3 | 849 | .BR CLONE_PID " (Linux 2.0 to 2.5.15)" |
f5dbc7c8 MK |
850 | If |
851 | .B CLONE_PID | |
852 | is set, the child process is created with the same process ID as | |
853 | the calling process. | |
854 | This is good for hacking the system, but otherwise | |
855 | of not much use. | |
1c173eb3 | 856 | From Linux 2.3.21 onward, this flag could be |
f5dbc7c8 | 857 | specified only by the system boot process (PID 0). |
1c173eb3 | 858 | The flag disappeared completely from the kernel sources in Linux 2.5.16. |
f5d5180f | 859 | Subsequently, the kernel silently ignored this bit if it was specified in the |
1ae6b2c7 | 860 | .I flags |
16853a31 | 861 | mask. |
f5d5180f MK |
862 | Much later, the same bit was recycled for use as the |
863 | .B CLONE_PIDFD | |
864 | flag. | |
f5dbc7c8 | 865 | .TP |
9f938981 | 866 | .BR CLONE_PIDFD " (since Linux 5.2)" |
4e98b074 | 867 | .\" commit b3e5838252665ee4cfa76b82bdf1198dca81e5be |
faa0e55a MK |
868 | If this flag is specified, |
869 | a PID file descriptor referring to the child process is allocated | |
870 | and placed at a specified location in the parent's memory. | |
b4ebffb2 | 871 | The close-on-exec flag is set on this new file descriptor. |
34a975f8 MK |
872 | PID file descriptors can be used for the purposes described in |
873 | .BR pidfd_open (2). | |
faa0e55a MK |
874 | .RS |
875 | .IP * 3 | |
876 | When using | |
877 | .BR clone3 (), | |
878 | the PID file descriptor is placed at the location pointed to by | |
879 | .IR cl_args.pidfd . | |
880 | .IP * | |
881 | When using | |
882 | .BR clone (), | |
883 | the PID file descriptor is placed at the location pointed to by | |
884 | .IR parent_tid . | |
9f938981 | 885 | Since the |
81c2368f | 886 | .I parent_tid |
b97cc7ae | 887 | argument is used to return the PID file descriptor, |
9f938981 CB |
888 | .B CLONE_PIDFD |
889 | cannot be used with | |
faa0e55a MK |
890 | .B CLONE_PARENT_SETTID |
891 | when calling | |
892 | .BR clone (). | |
893 | .RE | |
9f938981 CB |
894 | .IP |
895 | It is currently not possible to use this flag together with | |
896 | .B CLONE_THREAD. | |
b97cc7ae | 897 | This means that the process identified by the PID file descriptor |
f6183e5b | 898 | will always be a thread group leader. |
9f938981 | 899 | .IP |
baa435c6 | 900 | If the obsolete |
9f938981 | 901 | .B CLONE_DETACHED |
baa435c6 | 902 | flag is specified alongside |
1ae6b2c7 | 903 | .B CLONE_PIDFD |
baa435c6 MK |
904 | when calling |
905 | .BR clone (), | |
4e98b074 | 906 | an error is returned. |
baa435c6 MK |
907 | An error also results if |
908 | .B CLONE_DETACHED | |
909 | is specified when calling | |
910 | .BR clone3 (). | |
911 | This error behavior ensures that the bit corresponding to | |
1ae6b2c7 | 912 | .B CLONE_DETACHED |
baa435c6 | 913 | can be reused for further PID file descriptor features in the future. |
9f938981 | 914 | .TP |
1603d6a1 | 915 | .BR CLONE_PTRACE " (since Linux 2.2)" |
f5dbc7c8 MK |
916 | If |
917 | .B CLONE_PTRACE | |
918 | is specified, and the calling process is being traced, | |
919 | then trace the child also (see | |
920 | .BR ptrace (2)). | |
921 | .TP | |
922 | .BR CLONE_SETTLS " (since Linux 2.5.32)" | |
dd6d3d2e | 923 | The TLS (Thread Local Storage) descriptor is set to |
81c2368f | 924 | .IR tls . |
efeece04 | 925 | .IP |
dd6d3d2e | 926 | The interpretation of |
81c2368f | 927 | .I tls |
dd6d3d2e KF |
928 | and the resulting effect is architecture dependent. |
929 | On x86, | |
81c2368f | 930 | .I tls |
dd6d3d2e | 931 | is interpreted as a |
1ae6b2c7 | 932 | .I struct user_desc\~* |
35bf8cb4 | 933 | (see |
dd6d3d2e | 934 | .BR set_thread_area (2)). |
9ea5bc66 | 935 | On x86-64 it is the new value to be set for the %fs base register |
35bf8cb4 | 936 | (see the |
2551f801 | 937 | .B ARCH_SET_FS |
dd6d3d2e KF |
938 | argument to |
939 | .BR arch_prctl (2)). | |
940 | On architectures with a dedicated TLS register, it is the new value | |
941 | of that register. | |
f5d5180f MK |
942 | .IP |
943 | Use of this flag requires detailed knowledge and generally it | |
944 | should not be used except in libraries implementing threading. | |
f5dbc7c8 | 945 | .TP |
1603d6a1 | 946 | .BR CLONE_SIGHAND " (since Linux 2.0)" |
fea681da MK |
947 | If |
948 | .B CLONE_SIGHAND | |
314c8ff4 | 949 | is set, the calling process and the child process share the same table of |
c13182ef MK |
950 | signal handlers. |
951 | If the calling process or child process calls | |
fea681da | 952 | .BR sigaction (2) |
c13182ef MK |
953 | to change the behavior associated with a signal, the behavior is |
954 | changed in the other process as well. | |
955 | However, the calling process and child | |
fea681da | 956 | processes still have distinct signal masks and sets of pending |
c13182ef | 957 | signals. |
4ba17a6d | 958 | So, one of them may block or unblock signals using |
fea681da MK |
959 | .BR sigprocmask (2) |
960 | without affecting the other process. | |
efeece04 | 961 | .IP |
fea681da MK |
962 | If |
963 | .B CLONE_SIGHAND | |
964 | is not set, the child process inherits a copy of the signal handlers | |
5261b0fe | 965 | of the calling process at the time of the clone call. |
c13182ef | 966 | Calls to |
fea681da MK |
967 | .BR sigaction (2) |
968 | performed later by one of the processes have no effect on the other | |
969 | process. | |
efeece04 | 970 | .IP |
d6bec36e MK |
971 | Since Linux 2.6.0, |
972 | .\" Precisely: Linux 2.6.0-test6 | |
16853a31 | 973 | the |
29546c24 | 974 | .I flags |
16853a31 | 975 | mask must also include |
29546c24 MK |
976 | .B CLONE_VM |
977 | if | |
978 | .B CLONE_SIGHAND | |
fe10d82f | 979 | is specified. |
fea681da | 980 | .TP |
d6bec36e MK |
981 | .BR CLONE_STOPPED " (since Linux 2.6.0)" |
982 | .\" Precisely: Linux 2.6.0-test2 | |
a69b6bda MK |
983 | If |
984 | .B CLONE_STOPPED | |
985 | is set, then the child is initially stopped (as though it was sent a | |
986 | .B SIGSTOP | |
987 | signal), and must be resumed by sending it a | |
988 | .B SIGCONT | |
989 | signal. | |
efeece04 | 990 | .IP |
a60450a9 MK |
991 | This flag was |
992 | .I deprecated | |
993 | from Linux 2.6.25 onward, | |
994 | and was | |
995 | .I removed | |
28b44abc MK |
996 | altogether in Linux 2.6.38. |
997 | Since then, the kernel silently ignores it without error. | |
a5a061ee | 998 | .\" glibc 2.8 removed this defn from bits/sched.h |
c5af0674 | 999 | Starting with Linux 4.6, the same bit was reused for the |
1ae6b2c7 | 1000 | .B CLONE_NEWCGROUP |
c5af0674 | 1001 | flag. |
a69b6bda | 1002 | .TP |
f5dbc7c8 | 1003 | .BR CLONE_SYSVSEM " (since Linux 2.5.10)" |
fea681da | 1004 | If |
f5dbc7c8 MK |
1005 | .B CLONE_SYSVSEM |
1006 | is set, then the child and the calling process share | |
5ada4b94 MK |
1007 | a single list of System V semaphore adjustment |
1008 | .RI ( semadj ) | |
1009 | values (see | |
f5dbc7c8 | 1010 | .BR semop (2)). |
5ada4b94 MK |
1011 | In this case, the shared list accumulates |
1012 | .I semadj | |
1013 | values across all processes sharing the list, | |
1014 | and semaphore adjustments are performed only when the last process | |
1015 | that is sharing the list terminates (or ceases sharing the list using | |
1016 | .BR unshare (2)). | |
f5d401dd | 1017 | If this flag is not set, then the child has a separate |
5ada4b94 MK |
1018 | .I semadj |
1019 | list that is initially empty. | |
fea681da | 1020 | .TP |
d6bec36e MK |
1021 | .BR CLONE_THREAD " (since Linux 2.4.0)" |
1022 | .\" Precisely: Linux 2.6.0-test8 | |
fea681da MK |
1023 | If |
1024 | .B CLONE_THREAD | |
1025 | is set, the child is placed in the same thread group as the calling process. | |
fd8a5be4 MK |
1026 | To make the remainder of the discussion of |
1027 | .B CLONE_THREAD | |
1028 | more readable, the term "thread" is used to refer to the | |
1029 | processes within a thread group. | |
efeece04 | 1030 | .IP |
fd8a5be4 MK |
1031 | Thread groups were a feature added in Linux 2.4 to support the |
1032 | POSIX threads notion of a set of threads that share a single PID. | |
1033 | Internally, this shared PID is the so-called | |
1034 | thread group identifier (TGID) for the thread group. | |
c13182ef | 1035 | Since Linux 2.4, calls to |
fea681da | 1036 | .BR getpid (2) |
fd8a5be4 | 1037 | return the TGID of the caller. |
efeece04 | 1038 | .IP |
fd8a5be4 MK |
1039 | The threads within a group can be distinguished by their (system-wide) |
1040 | unique thread IDs (TID). | |
1041 | A new thread's TID is available as the function result | |
5261b0fe | 1042 | returned to the caller, |
fd8a5be4 MK |
1043 | and a thread can obtain |
1044 | its own TID using | |
1045 | .BR gettid (2). | |
efeece04 | 1046 | .IP |
5261b0fe | 1047 | When a clone call is made without specifying |
fd8a5be4 MK |
1048 | .BR CLONE_THREAD , |
1049 | then the resulting thread is placed in a new thread group | |
1050 | whose TGID is the same as the thread's TID. | |
1051 | This thread is the | |
1052 | .I leader | |
1053 | of the new thread group. | |
efeece04 | 1054 | .IP |
fd8a5be4 MK |
1055 | A new thread created with |
1056 | .B CLONE_THREAD | |
5261b0fe | 1057 | has the same parent process as the process that made the clone call |
c13182ef | 1058 | (i.e., like |
fd8a5be4 MK |
1059 | .BR CLONE_PARENT ), |
1060 | so that calls to | |
1061 | .BR getppid (2) | |
1062 | return the same value for all of the threads in a thread group. | |
1063 | When a | |
c13182ef | 1064 | .B CLONE_THREAD |
5261b0fe | 1065 | thread terminates, the thread that created it is not sent a |
fd8a5be4 MK |
1066 | .B SIGCHLD |
1067 | (or other termination) signal; | |
1068 | nor can the status of such a thread be obtained | |
1069 | using | |
1070 | .BR wait (2). | |
1071 | (The thread is said to be | |
1072 | .IR detached .) | |
efeece04 | 1073 | .IP |
e2fbf61d MK |
1074 | After all of the threads in a thread group terminate |
1075 | the parent process of the thread group is sent a | |
fd8a5be4 MK |
1076 | .B SIGCHLD |
1077 | (or other termination) signal. | |
efeece04 | 1078 | .IP |
fd8a5be4 MK |
1079 | If any of the threads in a thread group performs an |
1080 | .BR execve (2), | |
1081 | then all threads other than the thread group leader are terminated, | |
1082 | and the new program is executed in the thread group leader. | |
efeece04 | 1083 | .IP |
f7110f60 MK |
1084 | If one of the threads in a thread group creates a child using |
1085 | .BR fork (2), | |
1086 | then any thread in the group can | |
1087 | .BR wait (2) | |
1088 | for that child. | |
efeece04 | 1089 | .IP |
16853a31 | 1090 | Since Linux 2.5.35, the |
fd8a5be4 | 1091 | .I flags |
16853a31 | 1092 | mask must also include |
fd8a5be4 MK |
1093 | .B CLONE_SIGHAND |
1094 | if | |
1095 | .B CLONE_THREAD | |
6fd69f33 | 1096 | is specified |
d6bec36e MK |
1097 | (and note that, since Linux 2.6.0, |
1098 | .\" Precisely: Linux 2.6.0-test6 | |
1ae6b2c7 | 1099 | .B CLONE_SIGHAND |
6fd69f33 | 1100 | also requires |
1ae6b2c7 | 1101 | .B CLONE_VM |
6fd69f33 | 1102 | to be included). |
efeece04 | 1103 | .IP |
e2fbf61d MK |
1104 | Signal dispositions and actions are process-wide: |
1105 | if an unhandled signal is delivered to a thread, then | |
1106 | it will affect (terminate, stop, continue, be ignored in) | |
1107 | all members of the thread group. | |
efeece04 | 1108 | .IP |
99408a60 | 1109 | Each thread has its own signal mask, as set by |
f957eebd MK |
1110 | .BR sigprocmask (2). |
1111 | .IP | |
1112 | A signal may be process-directed or thread-directed. | |
1113 | A process-directed signal is targeted at a thread group (i.e., a TGID), | |
1114 | and is delivered to an arbitrarily selected thread from among those | |
1115 | that are not blocking the signal. | |
ed4f87f0 | 1116 | A signal may be process-directed because it was generated by the kernel |
f957eebd MK |
1117 | for reasons other than a hardware exception, or because it was sent using |
1118 | .BR kill (2) | |
1119 | or | |
1120 | .BR sigqueue (3). | |
1121 | A thread-directed signal is targeted at (i.e., delivered to) | |
1122 | a specific thread. | |
1123 | A signal may be thread directed because it was sent using | |
1124 | .BR tgkill (2) | |
1125 | or | |
1126 | .BR pthread_sigqueue (3), | |
1127 | or because the thread executed a machine language instruction that triggered | |
1128 | a hardware exception | |
1129 | (e.g., invalid memory access triggering | |
1ae6b2c7 | 1130 | .B SIGSEGV |
f957eebd MK |
1131 | or a floating-point exception triggering |
1132 | .BR SIGFPE ). | |
1133 | .IP | |
99408a60 MK |
1134 | A call to |
1135 | .BR sigpending (2) | |
f957eebd MK |
1136 | returns a signal set that is the union of the pending process-directed |
1137 | signals and the signals that are pending for the calling thread. | |
efeece04 | 1138 | .IP |
475c2753 | 1139 | If a process-directed signal is delivered to a thread group, |
e2fbf61d | 1140 | and the thread group has installed a handler for the signal, then |
95887a00 | 1141 | the handler is invoked in exactly one, arbitrarily selected |
e2fbf61d | 1142 | member of the thread group that has not blocked the signal. |
c13182ef | 1143 | If multiple threads in a group are waiting to accept the same signal using |
e2fbf61d MK |
1144 | .BR sigwaitinfo (2), |
1145 | the kernel will arbitrarily select one of these threads | |
475c2753 | 1146 | to receive the signal. |
a69b6bda | 1147 | .TP |
f5dbc7c8 | 1148 | .BR CLONE_UNTRACED " (since Linux 2.5.46)" |
a69b6bda | 1149 | If |
f5dbc7c8 MK |
1150 | .B CLONE_UNTRACED |
1151 | is specified, then a tracing process cannot force | |
1152 | .B CLONE_PTRACE | |
1153 | on this child process. | |
fea681da | 1154 | .TP |
1603d6a1 | 1155 | .BR CLONE_VFORK " (since Linux 2.2)" |
f5dbc7c8 MK |
1156 | If |
1157 | .B CLONE_VFORK | |
1158 | is set, the execution of the calling process is suspended | |
1159 | until the child releases its virtual memory | |
1160 | resources via a call to | |
1161 | .BR execve (2) | |
1162 | or | |
1163 | .BR _exit (2) | |
1164 | (as with | |
1165 | .BR vfork (2)). | |
efeece04 | 1166 | .IP |
f5dbc7c8 MK |
1167 | If |
1168 | .B CLONE_VFORK | |
4b4a853a | 1169 | is not set, then both the calling process and the child are schedulable |
f5dbc7c8 MK |
1170 | after the call, and an application should not rely on execution occurring |
1171 | in any particular order. | |
fea681da | 1172 | .TP |
1603d6a1 | 1173 | .BR CLONE_VM " (since Linux 2.0)" |
f5dbc7c8 MK |
1174 | If |
1175 | .B CLONE_VM | |
1176 | is set, the calling process and the child process run in the same memory | |
1177 | space. | |
1178 | In particular, memory writes performed by the calling process | |
1179 | or by the child process are also visible in the other process. | |
1180 | Moreover, any memory mapping or unmapping performed with | |
1181 | .BR mmap (2) | |
1182 | or | |
1183 | .BR munmap (2) | |
1184 | by the child or calling process also affects the other process. | |
efeece04 | 1185 | .IP |
f5dbc7c8 MK |
1186 | If |
1187 | .B CLONE_VM | |
1188 | is not set, the child process runs in a separate copy of the memory | |
5261b0fe | 1189 | space of the calling process at the time of the clone call. |
f5dbc7c8 MK |
1190 | Memory writes or file mappings/unmappings performed by one of the |
1191 | processes do not affect the other, as with | |
1192 | .BR fork (2). | |
52e5819c MK |
1193 | .IP |
1194 | If the | |
1ae6b2c7 | 1195 | .B CLONE_VM |
52e5819c | 1196 | flag is specified and the |
1ae6b2c7 | 1197 | .B CLONE_VFORK |
52e5819c MK |
1198 | flag is not specified, |
1199 | then any alternate signal stack that was established by | |
1200 | .BR sigaltstack (2) | |
1201 | is cleared in the child process. | |
47297adb | 1202 | .SH RETURN VALUE |
0bfa087b MK |
1203 | .\" gettid(2) returns current->pid; |
1204 | .\" getpid(2) returns current->tgid; | |
fea681da | 1205 | On success, the thread ID of the child process is returned |
c13182ef | 1206 | in the caller's thread of execution. |
84811e86 | 1207 | On failure, \-1 is returned |
95887a00 | 1208 | in the caller's context, no child process is created, and |
fea681da | 1209 | .I errno |
f6a4078b | 1210 | is set to indicate the error. |
fea681da MK |
1211 | .SH ERRORS |
1212 | .TP | |
3396ec7b AC |
1213 | .BR EACCES " (" clone3 "() only)" |
1214 | .B CLONE_INTO_CGROUP | |
1215 | was specified in | |
1216 | .IR cl_args.flags , | |
1217 | but the restrictions (described in | |
1218 | .BR cgroups (7)) | |
1219 | on placing the child process into the version 2 cgroup referred to by | |
1220 | .I cl_args.cgroup | |
1221 | are not met. | |
1222 | .TP | |
fea681da | 1223 | .B EAGAIN |
e1b6e186 MK |
1224 | Too many processes are already running; see |
1225 | .BR fork (2). | |
fea681da | 1226 | .TP |
6ba79da9 MK |
1227 | .BR EBUSY " (" clone3 "() only)" |
1228 | .B CLONE_INTO_CGROUP | |
1229 | was specified in | |
1230 | .IR cl_args.flags , | |
1231 | but the file descriptor specified in | |
1ae6b2c7 | 1232 | .I cl_args.cgroup |
6ba79da9 MK |
1233 | refers to a version 2 cgroup in which a domain controller is enabled. |
1234 | .TP | |
bf031aaa | 1235 | .BR EEXIST " (" clone3 "() only)" |
ee8bb310 | 1236 | One (or more) of the PIDs specified in |
bf031aaa AR |
1237 | .I set_tid |
1238 | already exists in the corresponding PID namespace. | |
1239 | .TP | |
fea681da | 1240 | .B EINVAL |
27f14b44 MK |
1241 | Both |
1242 | .B CLONE_SIGHAND | |
1243 | and | |
1244 | .B CLONE_CLEAR_SIGHAND | |
1245 | were specified in the | |
1246 | .I flags | |
1247 | mask. | |
1248 | .TP | |
1249 | .B EINVAL | |
fea681da | 1250 | .B CLONE_SIGHAND |
16853a31 MK |
1251 | was specified in the |
1252 | .I flags | |
1253 | mask, but | |
fea681da | 1254 | .B CLONE_VM |
2e8a7fb3 | 1255 | was not. |
d6bec36e MK |
1256 | (Since Linux 2.6.0.) |
1257 | .\" Precisely: Linux 2.6.0-test6 | |
fea681da MK |
1258 | .TP |
1259 | .B EINVAL | |
1260 | .B CLONE_THREAD | |
16853a31 MK |
1261 | was specified in the |
1262 | .I flags | |
1263 | mask, but | |
fea681da | 1264 | .B CLONE_SIGHAND |
6387216b MK |
1265 | was not. |
1266 | (Since Linux 2.5.35.) | |
29546c24 MK |
1267 | .\" .TP |
1268 | .\" .B EINVAL | |
1269 | .\" Precisely one of | |
1270 | .\" .B CLONE_DETACHED | |
1271 | .\" and | |
1272 | .\" .B CLONE_THREAD | |
6387216b MK |
1273 | .\" was specified. |
1274 | .\" (Since Linux 2.6.0-test6.) | |
fea681da MK |
1275 | .TP |
1276 | .B EINVAL | |
d6868c69 | 1277 | .B CLONE_THREAD |
16853a31 MK |
1278 | was specified in the |
1279 | .I flags | |
1280 | mask, but the current process previously called | |
d6868c69 JH |
1281 | .BR unshare (2) |
1282 | with the | |
1283 | .B CLONE_NEWPID | |
1284 | flag or used | |
1285 | .BR setns (2) | |
1286 | to reassociate itself with a PID namespace. | |
1287 | .TP | |
1288 | .B EINVAL | |
d34e5645 | 1289 | .\" commit e66eded8309ebf679d3d3c1f5820d1f2ca332c71 |
fea681da MK |
1290 | Both |
1291 | .B CLONE_FS | |
1292 | and | |
1293 | .B CLONE_NEWNS | |
16853a31 | 1294 | were specified in the |
1ae6b2c7 | 1295 | .I flags |
16853a31 | 1296 | mask. |
fea681da | 1297 | .TP |
d34e5645 MK |
1298 | .BR EINVAL " (since Linux 3.9)" |
1299 | Both | |
1300 | .B CLONE_NEWUSER | |
1301 | and | |
1302 | .B CLONE_FS | |
16853a31 | 1303 | were specified in the |
1ae6b2c7 | 1304 | .I flags |
16853a31 | 1305 | mask. |
d34e5645 | 1306 | .TP |
fea681da | 1307 | .B EINVAL |
82ee147a | 1308 | Both |
667417b3 MK |
1309 | .B CLONE_NEWIPC |
1310 | and | |
1311 | .B CLONE_SYSVSEM | |
16853a31 | 1312 | were specified in the |
1ae6b2c7 | 1313 | .I flags |
16853a31 | 1314 | mask. |
667417b3 MK |
1315 | .TP |
1316 | .B EINVAL | |
f0007192 | 1317 | One (or both) of |
1ae6b2c7 | 1318 | .B CLONE_NEWPID |
f0007192 | 1319 | or |
1ae6b2c7 | 1320 | .B CLONE_NEWUSER |
f0007192 | 1321 | and one (or both) of |
1ae6b2c7 | 1322 | .B CLONE_THREAD |
f0007192 | 1323 | or |
1ae6b2c7 | 1324 | .B CLONE_PARENT |
16853a31 | 1325 | were specified in the |
1ae6b2c7 | 1326 | .I flags |
16853a31 | 1327 | mask. |
82ee147a | 1328 | .TP |
be479fdf MK |
1329 | .BR EINVAL " (since Linux 2.6.32)" |
1330 | .\" commit 123be07b0b399670a7cc3d82fef0cb4f93ef885c | |
1ae6b2c7 | 1331 | .B CLONE_PARENT |
be479fdf MK |
1332 | was specified, and the caller is an init process. |
1333 | .TP | |
82ee147a | 1334 | .B EINVAL |
d4748fad | 1335 | Returned by the glibc |
edcc65ff | 1336 | .BR clone () |
d4748fad | 1337 | wrapper function when |
1ae6b2c7 | 1338 | .I fn |
d4748fad | 1339 | or |
1ae6b2c7 | 1340 | .I stack |
d4748fad | 1341 | is specified as NULL. |
fea681da | 1342 | .TP |
28cad2c1 | 1343 | .B EINVAL |
1ae6b2c7 | 1344 | .B CLONE_NEWIPC |
16853a31 | 1345 | was specified in the |
1ae6b2c7 | 1346 | .I flags |
16853a31 | 1347 | mask, |
667417b3 MK |
1348 | but the kernel was not configured with the |
1349 | .B CONFIG_SYSVIPC | |
1350 | and | |
1ae6b2c7 | 1351 | .B CONFIG_IPC_NS |
667417b3 MK |
1352 | options. |
1353 | .TP | |
1354 | .B EINVAL | |
1ae6b2c7 | 1355 | .B CLONE_NEWNET |
16853a31 | 1356 | was specified in the |
1ae6b2c7 | 1357 | .I flags |
16853a31 | 1358 | mask, |
163bf178 MK |
1359 | but the kernel was not configured with the |
1360 | .B CONFIG_NET_NS | |
1361 | option. | |
1362 | .TP | |
1363 | .B EINVAL | |
1ae6b2c7 | 1364 | .B CLONE_NEWPID |
16853a31 | 1365 | was specified in the |
1ae6b2c7 | 1366 | .I flags |
16853a31 | 1367 | mask, |
28cad2c1 MK |
1368 | but the kernel was not configured with the |
1369 | .B CONFIG_PID_NS | |
1370 | option. | |
1371 | .TP | |
43ce9dda | 1372 | .B EINVAL |
1ae6b2c7 | 1373 | .B CLONE_NEWUSER |
16853a31 | 1374 | was specified in the |
1ae6b2c7 | 1375 | .I flags |
16853a31 | 1376 | mask, |
231d0bbe MK |
1377 | but the kernel was not configured with the |
1378 | .B CONFIG_USER_NS | |
1379 | option. | |
1380 | .TP | |
1381 | .B EINVAL | |
1ae6b2c7 | 1382 | .B CLONE_NEWUTS |
16853a31 | 1383 | was specified in the |
1ae6b2c7 | 1384 | .I flags |
16853a31 | 1385 | mask, |
43ce9dda | 1386 | but the kernel was not configured with the |
832fe8ea | 1387 | .B CONFIG_UTS_NS |
43ce9dda MK |
1388 | option. |
1389 | .TP | |
c550a897 | 1390 | .B EINVAL |
81c2368f | 1391 | .I stack |
c550a897 MK |
1392 | is not aligned to a suitable boundary for this architecture. |
1393 | For example, on aarch64, | |
81c2368f | 1394 | .I stack |
c550a897 MK |
1395 | must be a multiple of 16. |
1396 | .TP | |
bc03b116 | 1397 | .BR EINVAL " (" clone3 "() only)" |
baa435c6 MK |
1398 | .B CLONE_DETACHED |
1399 | was specified in the | |
1400 | .I flags | |
1401 | mask. | |
1402 | .TP | |
bc03b116 | 1403 | .BR EINVAL " (" clone "() only)" |
9f938981 CB |
1404 | .B CLONE_PIDFD |
1405 | was specified together with | |
16853a31 MK |
1406 | .B CLONE_DETACHED |
1407 | in the | |
1408 | .I flags | |
1409 | mask. | |
9f938981 CB |
1410 | .TP |
1411 | .B EINVAL | |
1412 | .B CLONE_PIDFD | |
1413 | was specified together with | |
16853a31 MK |
1414 | .B CLONE_THREAD |
1415 | in the | |
1416 | .I flags | |
1417 | mask. | |
9f938981 | 1418 | .TP |
faa0e55a | 1419 | .BR "EINVAL " "(" clone "() only)" |
9f938981 CB |
1420 | .B CLONE_PIDFD |
1421 | was specified together with | |
16853a31 MK |
1422 | .B CLONE_PARENT_SETTID |
1423 | in the | |
1424 | .I flags | |
1425 | mask. | |
9f938981 | 1426 | .TP |
bf031aaa AR |
1427 | .BR EINVAL " (" clone3 "() only)" |
1428 | .I set_tid_size | |
ee8bb310 | 1429 | is greater than the number of nested PID namespaces. |
bf031aaa AR |
1430 | .TP |
1431 | .BR EINVAL " (" clone3 "() only)" | |
2a2b2a5d | 1432 | One of the PIDs specified in |
bf031aaa | 1433 | .I set_tid |
2a2b2a5d | 1434 | was an invalid. |
bf031aaa | 1435 | .TP |
ba9ae75d MK |
1436 | .BR EINVAL " (AArch64 only, Linux 4.6 and earlier)" |
1437 | .I stack | |
1874ca39 | 1438 | was not aligned to a 128-bit boundary. |
ba9ae75d | 1439 | .TP |
fea681da MK |
1440 | .B ENOMEM |
1441 | Cannot allocate sufficient memory to allocate a task structure for the | |
1442 | child, or to copy those parts of the caller's context that need to be | |
1443 | copied. | |
1444 | .TP | |
b20e22ae MK |
1445 | .BR ENOSPC " (since Linux 3.7)" |
1446 | .\" commit f2302505775fd13ba93f034206f1e2a587017929 | |
1447 | .B CLONE_NEWPID | |
16853a31 MK |
1448 | was specified in the |
1449 | .I flags | |
1450 | mask, | |
b20e22ae MK |
1451 | but the limit on the nesting depth of PID namespaces |
1452 | would have been exceeded; see | |
1453 | .BR pid_namespaces (7). | |
1454 | .TP | |
b5742ecc MK |
1455 | .BR ENOSPC " (since Linux 4.9; beforehand " EUSERS ) |
1456 | .B CLONE_NEWUSER | |
16853a31 | 1457 | was specified in the |
1ae6b2c7 | 1458 | .I flags |
16853a31 | 1459 | mask, and the call would cause the limit on the number of |
b5742ecc MK |
1460 | nested user namespaces to be exceeded. |
1461 | See | |
1462 | .BR user_namespaces (7). | |
efeece04 | 1463 | .IP |
b5742ecc MK |
1464 | From Linux 3.11 to Linux 4.8, the error diagnosed in this case was |
1465 | .BR EUSERS . | |
1466 | .TP | |
2f7a331e | 1467 | .BR ENOSPC " (since Linux 4.9)" |
16853a31 | 1468 | One of the values in the |
2f7a331e | 1469 | .I flags |
16853a31 | 1470 | mask specified the creation of a new user namespace, |
2f7a331e | 1471 | but doing so would have caused the limit defined by the corresponding file in |
1ae6b2c7 | 1472 | .I /proc/sys/user |
2f7a331e MK |
1473 | to be exceeded. |
1474 | For further details, see | |
1475 | .BR namespaces (7). | |
1476 | .TP | |
0b065634 | 1477 | .BR EOPNOTSUPP " (" clone3 "() only)" |
6ba79da9 MK |
1478 | .B CLONE_INTO_CGROUP |
1479 | was specified in | |
1480 | .IR cl_args.flags , | |
1481 | but the file descriptor specified in | |
1ae6b2c7 | 1482 | .I cl_args.cgroup |
6ba79da9 | 1483 | refers to a version 2 cgroup that is in the |
1ae6b2c7 | 1484 | .I domain invalid |
6ba79da9 MK |
1485 | state. |
1486 | .TP | |
fea681da | 1487 | .B EPERM |
aa825b59 | 1488 | .BR CLONE_NEWCGROUP , |
667417b3 | 1489 | .BR CLONE_NEWIPC , |
163bf178 | 1490 | .BR CLONE_NEWNET , |
43ce9dda MK |
1491 | .BR CLONE_NEWNS , |
1492 | .BR CLONE_NEWPID , | |
82ee147a | 1493 | or |
1ae6b2c7 | 1494 | .B CLONE_NEWUTS |
00b08db3 | 1495 | was specified by an unprivileged process (process without \fBCAP_SYS_ADMIN\fP). |
fea681da MK |
1496 | .TP |
1497 | .B EPERM | |
1498 | .B CLONE_PID | |
1499 | was specified by a process other than process 0. | |
1c173eb3 | 1500 | (This error occurs only on Linux 2.5.15 and earlier.) |
365d292a MK |
1501 | .TP |
1502 | .B EPERM | |
1ae6b2c7 | 1503 | .B CLONE_NEWUSER |
16853a31 | 1504 | was specified in the |
1ae6b2c7 | 1505 | .I flags |
16853a31 | 1506 | mask, |
365d292a MK |
1507 | but either the effective user ID or the effective group ID of the caller |
1508 | does not have a mapping in the parent namespace (see | |
f58fb24f | 1509 | .BR user_namespaces (7)). |
6fd119e7 | 1510 | .TP |
ac007938 MK |
1511 | .BR EPERM " (since Linux 3.9)" |
1512 | .\" commit 3151527ee007b73a0ebd296010f1c0454a919c7d | |
11a38815 | 1513 | .B CLONE_NEWUSER |
16853a31 | 1514 | was specified in the |
ac007938 | 1515 | .I flags |
16853a31 | 1516 | mask and the caller is in a chroot environment |
ac007938 MK |
1517 | .\" FIXME What is the rationale for this restriction? |
1518 | (i.e., the caller's root directory does not match the root directory | |
1519 | of the mount namespace in which it resides). | |
1520 | .TP | |
bf031aaa AR |
1521 | .BR EPERM " (" clone3 "() only)" |
1522 | .I set_tid_size | |
1523 | was greater than zero, and the caller lacks the | |
1524 | .B CAP_SYS_ADMIN | |
1525 | capability in one or more of the user namespaces that own the | |
1526 | corresponding PID namespaces. | |
1527 | .TP | |
6717ee86 MK |
1528 | .BR ERESTARTNOINTR " (since Linux 2.6.17)" |
1529 | .\" commit 4a2c7a7837da1b91468e50426066d988050e4d56 | |
1530 | System call was interrupted by a signal and will be restarted. | |
1531 | (This can be seen only during a trace.) | |
1532 | .TP | |
b5742ecc | 1533 | .BR EUSERS " (Linux 3.11 to Linux 4.8)" |
6fd119e7 | 1534 | .B CLONE_NEWUSER |
16853a31 | 1535 | was specified in the |
1ae6b2c7 | 1536 | .I flags |
16853a31 | 1537 | mask, |
b5742ecc MK |
1538 | and the limit on the number of nested user namespaces would be exceeded. |
1539 | See the discussion of the | |
1ae6b2c7 | 1540 | .B ENOSPC |
b5742ecc | 1541 | error above. |
faa0e55a MK |
1542 | .SH VERSIONS |
1543 | The | |
1544 | .BR clone3 () | |
1545 | system call first appeared in Linux 5.3. | |
92b72224 MK |
1546 | .\" There is no entry for |
1547 | .\" .BR clone () | |
1548 | .\" in libc5. | |
1549 | .\" glibc2 provides | |
1550 | .\" .BR clone () | |
1551 | .\" as described in this manual page. | |
3113c7f3 | 1552 | .SH STANDARDS |
faa0e55a MK |
1553 | These system calls |
1554 | are Linux-specific and should not be used in programs | |
a1d5f77c | 1555 | intended to be portable. |
fea681da | 1556 | .SH NOTES |
673d16da MK |
1557 | One use of these systems calls |
1558 | is to implement threads: multiple flows of control in a program that | |
1559 | run concurrently in a shared address space. | |
1560 | .PP | |
673d16da MK |
1561 | Note that the glibc |
1562 | .BR clone () | |
1563 | wrapper function makes some changes | |
1564 | in the memory pointed to by | |
1565 | .I stack | |
1566 | (changes required to set the stack up correctly for the child) | |
1567 | .I before | |
1568 | invoking the | |
1569 | .BR clone () | |
1570 | system call. | |
1571 | So, in cases where | |
1572 | .BR clone () | |
1573 | is used to recursively create children, | |
1574 | do not use the buffer employed for the parent's stack | |
1575 | as the stack of the child. | |
1576 | .PP | |
79bdcc4a MK |
1577 | The |
1578 | .BR kcmp (2) | |
1579 | system call can be used to test whether two processes share various | |
49dba87f | 1580 | resources such as a file descriptor table, |
79bdcc4a | 1581 | System V semaphore undo operations, or a virtual address space. |
efeece04 | 1582 | .PP |
c471c363 MK |
1583 | Handlers registered using |
1584 | .BR pthread_atfork (3) | |
5261b0fe | 1585 | are not executed during a clone call. |
efeece04 | 1586 | .PP |
ca8b1e32 | 1587 | In the Linux 2.4.x series, |
fd8a5be4 MK |
1588 | .B CLONE_THREAD |
1589 | generally does not make the parent of the new thread the same | |
1590 | as the parent of the calling process. | |
1591 | However, for kernel versions 2.4.7 to 2.4.18 the | |
1592 | .B CLONE_THREAD | |
1593 | flag implied the | |
c13182ef | 1594 | .B CLONE_PARENT |
ca8b1e32 | 1595 | flag (as in Linux 2.6.0 and later). |
efeece04 | 1596 | .PP |
34ccb744 | 1597 | On i386, |
a5a997ca MK |
1598 | .BR clone () |
1599 | should not be called through vsyscall, but directly through | |
1600 | .IR "int $0x80" . | |
673d16da MK |
1601 | .\" |
1602 | .SS C library/kernel differences | |
1603 | The raw | |
1604 | .BR clone () | |
1605 | system call corresponds more closely to | |
1606 | .BR fork (2) | |
1607 | in that execution in the child continues from the point of the | |
1608 | call. | |
1609 | As such, the | |
1610 | .I fn | |
1611 | and | |
1612 | .I arg | |
1613 | arguments of the | |
1614 | .BR clone () | |
1615 | wrapper function are omitted. | |
1616 | .PP | |
1617 | In contrast to the glibc wrapper, the raw | |
1618 | .BR clone () | |
1619 | system call accepts NULL as a | |
1620 | .I stack | |
1621 | argument (and | |
1622 | .BR clone3 () | |
1623 | likewise allows | |
1624 | .I cl_args.stack | |
1625 | to be NULL). | |
1626 | In this case, the child uses a duplicate of the parent's stack. | |
1627 | (Copy-on-write semantics ensure that the child gets separate copies | |
1628 | of stack pages when either process modifies the stack.) | |
1629 | In this case, for correct operation, the | |
1630 | .B CLONE_VM | |
1631 | option should not be specified. | |
1632 | (If the child | |
1633 | .I shares | |
1634 | the parent's memory because of the use of the | |
1ae6b2c7 | 1635 | .B CLONE_VM |
673d16da MK |
1636 | flag, |
1637 | then no copy-on-write duplication occurs and chaos is likely to result.) | |
1638 | .PP | |
1639 | The order of the arguments also differs in the raw system call, | |
1640 | and there are variations in the arguments across architectures, | |
1641 | as detailed in the following paragraphs. | |
1642 | .PP | |
1643 | The raw system call interface on x86-64 and some other architectures | |
1644 | (including sh, tile, and alpha) is: | |
1645 | .PP | |
161b8eda | 1646 | .in +4n |
673d16da MK |
1647 | .EX |
1648 | .BI "long clone(unsigned long " flags ", void *" stack , | |
1649 | .BI " int *" parent_tid ", int *" child_tid , | |
1650 | .BI " unsigned long " tls ); | |
1651 | .EE | |
1652 | .in | |
1653 | .PP | |
1654 | On x86-32, and several other common architectures | |
1655 | (including score, ARM, ARM 64, PA-RISC, arc, Power PC, xtensa, | |
1656 | and MIPS), | |
1657 | .\" CONFIG_CLONE_BACKWARDS | |
1658 | the order of the last two arguments is reversed: | |
1659 | .PP | |
161b8eda | 1660 | .in +4n |
673d16da MK |
1661 | .EX |
1662 | .BI "long clone(unsigned long " flags ", void *" stack , | |
1663 | .BI " int *" parent_tid ", unsigned long " tls , | |
1664 | .BI " int *" child_tid ); | |
1665 | .EE | |
1666 | .in | |
1667 | .PP | |
1668 | On the cris and s390 architectures, | |
1669 | .\" CONFIG_CLONE_BACKWARDS2 | |
1670 | the order of the first two arguments is reversed: | |
1671 | .PP | |
161b8eda | 1672 | .in +4n |
673d16da MK |
1673 | .EX |
1674 | .BI "long clone(void *" stack ", unsigned long " flags , | |
1675 | .BI " int *" parent_tid ", int *" child_tid , | |
1676 | .BI " unsigned long " tls ); | |
1677 | .EE | |
1678 | .in | |
1679 | .PP | |
1680 | On the microblaze architecture, | |
1681 | .\" CONFIG_CLONE_BACKWARDS3 | |
1682 | an additional argument is supplied: | |
1683 | .PP | |
161b8eda | 1684 | .in +4n |
673d16da MK |
1685 | .EX |
1686 | .BI "long clone(unsigned long " flags ", void *" stack , | |
1687 | .BI " int " stack_size , "\fR /* Size of stack */" | |
1688 | .BI " int *" parent_tid ", int *" child_tid , | |
1689 | .BI " unsigned long " tls ); | |
1690 | .EE | |
1691 | .in | |
1692 | .\" | |
1693 | .SS blackfin, m68k, and sparc | |
1694 | .\" Mike Frysinger noted in a 2013 mail: | |
1695 | .\" these arches don't define __ARCH_WANT_SYS_CLONE: | |
1696 | .\" blackfin ia64 m68k sparc | |
1697 | The argument-passing conventions on | |
1698 | blackfin, m68k, and sparc are different from the descriptions above. | |
1699 | For details, see the kernel (and glibc) source. | |
1700 | .SS ia64 | |
1701 | On ia64, a different interface is used: | |
1702 | .PP | |
161b8eda | 1703 | .in +4n |
673d16da | 1704 | .EX |
77ca5b1d | 1705 | .BI "int __clone2(int (*" "fn" ")(void *)," |
673d16da | 1706 | .BI " void *" stack_base ", size_t " stack_size , |
77ca5b1d | 1707 | .BI " int " flags ", void *" "arg" ", ..." |
673d16da MK |
1708 | .BI " /* pid_t *" parent_tid ", struct user_desc *" tls , |
1709 | .BI " pid_t *" child_tid " */ );" | |
1710 | .EE | |
1711 | .in | |
1712 | .PP | |
1713 | The prototype shown above is for the glibc wrapper function; | |
1714 | for the system call itself, | |
1715 | the prototype can be described as follows (it is identical to the | |
1716 | .BR clone () | |
1717 | prototype on microblaze): | |
1718 | .PP | |
161b8eda | 1719 | .in +4n |
673d16da MK |
1720 | .EX |
1721 | .BI "long clone2(unsigned long " flags ", void *" stack_base , | |
1722 | .BI " int " stack_size , "\fR /* Size of stack */" | |
1723 | .BI " int *" parent_tid ", int *" child_tid , | |
1724 | .BI " unsigned long " tls ); | |
1725 | .EE | |
1726 | .in | |
1727 | .PP | |
1728 | .BR __clone2 () | |
1729 | operates in the same way as | |
1730 | .BR clone (), | |
1731 | except that | |
1732 | .I stack_base | |
1733 | points to the lowest address of the child's stack area, | |
1734 | and | |
1735 | .I stack_size | |
1736 | specifies the size of the stack pointed to by | |
1737 | .IR stack_base . | |
1738 | .SS Linux 2.4 and earlier | |
1739 | In Linux 2.4 and earlier, | |
1740 | .BR clone () | |
1741 | does not take arguments | |
1742 | .IR parent_tid , | |
1743 | .IR tls , | |
1744 | and | |
1745 | .IR child_tid . | |
31830ef0 | 1746 | .SH BUGS |
abcf3b1d MK |
1747 | GNU C library versions 2.3.4 up to and including 2.24 |
1748 | contained a wrapper function for | |
0bfa087b | 1749 | .BR getpid (2) |
abcf3b1d MK |
1750 | that performed caching of PIDs. |
1751 | This caching relied on support in the glibc wrapper for | |
c60237c9 | 1752 | .BR clone (), |
abcf3b1d MK |
1753 | but limitations in the implementation |
1754 | meant that the cache was not up to date in some circumstances. | |
c60237c9 | 1755 | In particular, |
abcf3b1d | 1756 | if a signal was delivered to the child immediately after the |
c60237c9 MK |
1757 | .BR clone () |
1758 | call, then a call to | |
0b80cf56 | 1759 | .BR getpid (2) |
abcf3b1d | 1760 | in a handler for the signal could return the PID |
c60237c9 | 1761 | of the calling process ("the parent"), |
abcf3b1d | 1762 | if the clone wrapper had not yet had a chance to update the PID |
c60237c9 MK |
1763 | cache in the child. |
1764 | (This discussion ignores the case where the child was created using | |
9291ce36 | 1765 | .BR CLONE_THREAD , |
c60237c9 | 1766 | when |
0b80cf56 | 1767 | .BR getpid (2) |
c60237c9 MK |
1768 | .I should |
1769 | return the same value in the child and in the process that called | |
1770 | .BR clone (), | |
a1d48abb | 1771 | since the caller and the child are in the same thread group. |
e7d807b7 | 1772 | The stale-cache problem also does not occur if the |
a1d48abb JR |
1773 | .I flags |
1774 | argument includes | |
1775 | .BR CLONE_VM .) | |
abcf3b1d MK |
1776 | To get the truth, it was sometimes necessary to use code such as the following: |
1777 | .PP | |
47f743f1 MK |
1778 | .in +4n |
1779 | .EX | |
1780 | #include <syscall.h> | |
31830ef0 | 1781 | |
47f743f1 | 1782 | pid_t mypid; |
31830ef0 | 1783 | |
47f743f1 MK |
1784 | mypid = syscall(SYS_getpid); |
1785 | .EE | |
1786 | .in | |
c60237c9 MK |
1787 | .\" See also the following bug reports |
1788 | .\" https://bugzilla.redhat.com/show_bug.cgi?id=417521 | |
1789 | .\" http://sourceware.org/bugzilla/show_bug.cgi?id=6910 | |
abcf3b1d MK |
1790 | .PP |
1791 | Because of the stale-cache problem, as well as other problems noted in | |
1792 | .BR getpid (2), | |
1793 | the PID caching feature was removed in glibc 2.25. | |
a14af333 | 1794 | .SH EXAMPLES |
8c7b566c | 1795 | The following program demonstrates the use of |
9c13072a | 1796 | .BR clone () |
8c7b566c MK |
1797 | to create a child process that executes in a separate UTS namespace. |
1798 | The child changes the hostname in its UTS namespace. | |
1799 | Both parent and child then display the system hostname, | |
1800 | making it possible to see that the hostname | |
1801 | differs in the UTS namespaces of the parent and child. | |
1802 | For an example of the use of this program, see | |
1803 | .BR setns (2). | |
99c3a000 MK |
1804 | .PP |
1805 | Within the sample program, we allocate the memory that is to | |
1806 | be used for the child's stack using | |
1807 | .BR mmap (2) | |
1808 | rather than | |
1809 | .BR malloc (3) | |
1810 | for the following reasons: | |
1811 | .IP * 3 | |
1812 | .BR mmap (2) | |
1813 | allocates a block of memory that starts on a page | |
1814 | boundary and is a multiple of the page size. | |
1815 | This is useful if we want to establish a guard page (a page with protection | |
1816 | .BR PROT_NONE ) | |
1817 | at the end of the stack using | |
1818 | .BR mprotect (2). | |
1819 | .IP * | |
1820 | We can specify the | |
1ae6b2c7 | 1821 | .B MAP_STACK |
99c3a000 MK |
1822 | flag to request a mapping that is suitable for a stack. |
1823 | For the moment, this flag is a no-op on Linux, | |
1824 | but it exists and has effect on some other systems, | |
1825 | so we should include it for portability. | |
f30b7415 | 1826 | .SS Program source |
33857069 | 1827 | .\" SRC BEGIN (clone.c) |
e7d0bb47 | 1828 | .EX |
8c7b566c | 1829 | #define _GNU_SOURCE |
8c7b566c | 1830 | #include <sched.h> |
80ae7514 | 1831 | #include <signal.h> |
8eb90116 | 1832 | #include <stdint.h> |
8c7b566c MK |
1833 | #include <stdio.h> |
1834 | #include <stdlib.h> | |
80ae7514 | 1835 | #include <string.h> |
99c3a000 | 1836 | #include <sys/mman.h> |
80ae7514 AC |
1837 | #include <sys/utsname.h> |
1838 | #include <sys/wait.h> | |
1839 | #include <unistd.h> | |
8c7b566c | 1840 | |
d1a71985 | 1841 | #define errExit(msg) do { perror(msg); exit(EXIT_FAILURE); \e |
8c7b566c MK |
1842 | } while (0) |
1843 | ||
1844 | static int /* Start function for cloned child */ | |
1845 | childFunc(void *arg) | |
1846 | { | |
1847 | struct utsname uts; | |
1848 | ||
c6beb8a1 | 1849 | /* Change hostname in UTS namespace of child. */ |
8c7b566c MK |
1850 | |
1851 | if (sethostname(arg, strlen(arg)) == \-1) | |
1852 | errExit("sethostname"); | |
1853 | ||
c6beb8a1 | 1854 | /* Retrieve and display hostname. */ |
8c7b566c MK |
1855 | |
1856 | if (uname(&uts) == \-1) | |
1857 | errExit("uname"); | |
d1a71985 | 1858 | printf("uts.nodename in child: %s\en", uts.nodename); |
8c7b566c MK |
1859 | |
1860 | /* Keep the namespace open for a while, by sleeping. | |
1861 | This allows some experimentation\-\-for example, another | |
1862 | process might join the namespace. */ | |
9f1b9726 | 1863 | |
8c7b566c MK |
1864 | sleep(200); |
1865 | ||
1866 | return 0; /* Child terminates now */ | |
1867 | } | |
1868 | ||
1869 | #define STACK_SIZE (1024 * 1024) /* Stack size for cloned child */ | |
1870 | ||
1871 | int | |
1872 | main(int argc, char *argv[]) | |
1873 | { | |
1874 | char *stack; /* Start of stack buffer */ | |
1875 | char *stackTop; /* End of stack buffer */ | |
1876 | pid_t pid; | |
1877 | struct utsname uts; | |
1878 | ||
1879 | if (argc < 2) { | |
d1a71985 | 1880 | fprintf(stderr, "Usage: %s <child\-hostname>\en", argv[0]); |
8c7b566c MK |
1881 | exit(EXIT_SUCCESS); |
1882 | } | |
1883 | ||
c6beb8a1 | 1884 | /* Allocate memory to be used for the stack of the child. */ |
8c7b566c | 1885 | |
99c3a000 MK |
1886 | stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, |
1887 | MAP_PRIVATE | MAP_ANONYMOUS | MAP_STACK, \-1, 0); | |
8eea66b8 | 1888 | if (stack == MAP_FAILED) |
99c3a000 MK |
1889 | errExit("mmap"); |
1890 | ||
8c7b566c MK |
1891 | stackTop = stack + STACK_SIZE; /* Assume stack grows downward */ |
1892 | ||
1893 | /* Create child that has its own UTS namespace; | |
c6beb8a1 | 1894 | child commences execution in childFunc(). */ |
8c7b566c MK |
1895 | |
1896 | pid = clone(childFunc, stackTop, CLONE_NEWUTS | SIGCHLD, argv[1]); | |
1897 | if (pid == \-1) | |
1898 | errExit("clone"); | |
8eb90116 | 1899 | printf("clone() returned %jd\en", (intmax_t) pid); |
8c7b566c MK |
1900 | |
1901 | /* Parent falls through to here */ | |
1902 | ||
1903 | sleep(1); /* Give child time to change its hostname */ | |
1904 | ||
9f1b9726 | 1905 | /* Display hostname in parent\(aqs UTS namespace. This will be |
8c7b566c MK |
1906 | different from hostname in child\(aqs UTS namespace. */ |
1907 | ||
1908 | if (uname(&uts) == \-1) | |
1909 | errExit("uname"); | |
d1a71985 | 1910 | printf("uts.nodename in parent: %s\en", uts.nodename); |
8c7b566c MK |
1911 | |
1912 | if (waitpid(pid, NULL, 0) == \-1) /* Wait for child */ | |
1913 | errExit("waitpid"); | |
d1a71985 | 1914 | printf("child has terminated\en"); |
8c7b566c MK |
1915 | |
1916 | exit(EXIT_SUCCESS); | |
1917 | } | |
e7d0bb47 | 1918 | .EE |
33857069 | 1919 | .\" SRC END |
47297adb | 1920 | .SH SEE ALSO |
fea681da | 1921 | .BR fork (2), |
2b44301c | 1922 | .BR futex (2), |
fea681da MK |
1923 | .BR getpid (2), |
1924 | .BR gettid (2), | |
6f8746e4 | 1925 | .BR kcmp (2), |
99c3a000 | 1926 | .BR mmap (2), |
d8837668 | 1927 | .BR pidfd_open (2), |
f2d0bbf1 | 1928 | .BR set_thread_area (2), |
2b44301c | 1929 | .BR set_tid_address (2), |
8403481f | 1930 | .BR setns (2), |
f2d0bbf1 | 1931 | .BR tkill (2), |
5cc01e9c | 1932 | .BR unshare (2), |
fea681da | 1933 | .BR wait (2), |
3616b7c0 | 1934 | .BR capabilities (7), |
41096af1 | 1935 | .BR namespaces (7), |
3616b7c0 | 1936 | .BR pthreads (7) |