blob: 3b9df1aa35db366a7063bd5b0cfa0b88efb5fb00 [file] [log] [blame]
Roman Zippel80daa562008-01-14 04:51:16 +01001config ARCH
2 string
3 option env="ARCH"
4
5config KERNELVERSION
6 string
7 option env="KERNELVERSION"
8
Roman Zippelface4372006-06-08 22:12:45 -07009config DEFCONFIG_LIST
10 string
Paolo 'Blaisorblade' Giarrussob2670eac2006-10-19 23:28:23 -070011 depends on !UML
Roman Zippelface4372006-06-08 22:12:45 -070012 option defconfig_list
13 default "/lib/modules/$UNAME_RELEASE/.config"
14 default "/etc/kernel-config"
15 default "/boot/config-$UNAME_RELEASE"
Sam Ravnborg73531902008-05-25 23:03:18 +020016 default "$ARCH_DEFCONFIG"
Roman Zippelface4372006-06-08 22:12:45 -070017 default "arch/$ARCH/defconfig"
18
Peter Oberparleiterb99b87f2009-06-17 16:28:03 -070019config CONSTRUCTORS
20 bool
21 depends on !UML
Peter Oberparleiterb99b87f2009-06-17 16:28:03 -070022
Peter Zijlstrae360adb2010-10-14 14:01:34 +080023config IRQ_WORK
24 bool
Peter Zijlstrae360adb2010-10-14 14:01:34 +080025
David Daney1dbdc6f2012-04-19 14:59:57 -070026config BUILDTIME_EXTABLE_SORT
27 bool
28
Al Boldiff0cfc62007-07-31 00:39:23 -070029menu "General setup"
Linus Torvalds1da177e2005-04-16 15:20:36 -070030
Linus Torvalds1da177e2005-04-16 15:20:36 -070031config BROKEN
32 bool
Linus Torvalds1da177e2005-04-16 15:20:36 -070033
34config BROKEN_ON_SMP
35 bool
36 depends on BROKEN || !SMP
37 default y
38
Linus Torvalds1da177e2005-04-16 15:20:36 -070039config INIT_ENV_ARG_LIMIT
40 int
Adrian Bunkdd673bc2006-06-30 01:55:51 -070041 default 32 if !UML
42 default 128 if UML
Linus Torvalds1da177e2005-04-16 15:20:36 -070043 help
Randy Dunlap34ad92c2005-10-30 15:01:46 -080044 Maximum of each of the number of arguments and environment
45 variables passed to init from the kernel command line.
Linus Torvalds1da177e2005-04-16 15:20:36 -070046
Linus Torvalds1da177e2005-04-16 15:20:36 -070047
Roland McGrath84336462009-12-21 16:24:06 -080048config CROSS_COMPILE
49 string "Cross-compiler tool prefix"
50 help
51 Same as running 'make CROSS_COMPILE=prefix-' but stored for
52 default make runs in this kernel build directory. You don't
53 need to set this unless you want the configured kernel build
54 directory to select the cross-compiler automatically.
55
Jiri Slaby4bb16672013-05-22 10:56:24 +020056config COMPILE_TEST
57 bool "Compile also drivers which will not load"
58 default n
59 help
60 Some drivers can be compiled on a different platform than they are
61 intended to be run on. Despite they cannot be loaded there (or even
62 when they load they cannot be used due to missing HW support),
63 developers still, opposing to distributors, might want to build such
64 drivers to compile-test them.
65
66 If you are a developer and want to build everything available, say Y
67 here. If you are a user/distributor, say N here to exclude useless
68 drivers to be distributed.
69
Linus Torvalds1da177e2005-04-16 15:20:36 -070070config LOCALVERSION
71 string "Local version - append to kernel release"
72 help
73 Append an extra string to the end of your kernel version.
74 This will show up when you type uname, for example.
75 The string you set here will be appended after the contents of
76 any files with a filename matching localversion* in your
77 object and source tree, in that order. Your total string can
78 be a maximum of 64 characters.
79
Ryan Andersonaaebf432005-07-31 04:57:49 -040080config LOCALVERSION_AUTO
81 bool "Automatically append version information to the version string"
82 default y
83 help
84 This will try to automatically determine if the current tree is a
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020085 release tree by looking for git tags that belong to the current
86 top of tree revision.
Ryan Andersonaaebf432005-07-31 04:57:49 -040087
88 A string of the format -gxxxxxxxx will be added to the localversion
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020089 if a git-based tree is found. The string generated by this will be
Ryan Andersonaaebf432005-07-31 04:57:49 -040090 appended after any matching localversion* files, and after the value
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020091 set in CONFIG_LOCALVERSION.
Ryan Andersonaaebf432005-07-31 04:57:49 -040092
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020093 (The actual string used here is the first eight characters produced
94 by running the command:
95
96 $ git rev-parse --verify HEAD
97
98 which is done within the script "scripts/setlocalversion".)
Ryan Andersonaaebf432005-07-31 04:57:49 -040099
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800100config HAVE_KERNEL_GZIP
101 bool
102
103config HAVE_KERNEL_BZIP2
104 bool
105
106config HAVE_KERNEL_LZMA
107 bool
108
Lasse Collin3ebe1242011-01-12 17:01:23 -0800109config HAVE_KERNEL_XZ
110 bool
111
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800112config HAVE_KERNEL_LZO
113 bool
114
Kyungsik Leee76e1fd2013-07-08 16:01:46 -0700115config HAVE_KERNEL_LZ4
116 bool
117
Alain Knaff30d65db2009-01-04 22:46:17 +0100118choice
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800119 prompt "Kernel compression mode"
120 default KERNEL_GZIP
H. Peter Anvin2d3c6272013-11-14 21:43:47 -0800121 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800122 help
Alain Knaff30d65db2009-01-04 22:46:17 +0100123 The linux kernel is a kind of self-extracting executable.
124 Several compression algorithms are available, which differ
125 in efficiency, compression and decompression speed.
126 Compression speed is only relevant when building a kernel.
127 Decompression speed is relevant at each boot.
128
129 If you have any problems with bzip2 or lzma compressed
130 kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older
131 version of this functionality (bzip2 only), for 2.4, was
132 supplied by Christian Ludwig)
133
134 High compression options are mostly useful for users, who
135 are low on disk space (embedded systems), but for whom ram
136 size matters less.
137
138 If in doubt, select 'gzip'
139
140config KERNEL_GZIP
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800141 bool "Gzip"
142 depends on HAVE_KERNEL_GZIP
143 help
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800144 The old and tried gzip compression. It provides a good balance
145 between compression ratio and decompression speed.
Alain Knaff30d65db2009-01-04 22:46:17 +0100146
147config KERNEL_BZIP2
148 bool "Bzip2"
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800149 depends on HAVE_KERNEL_BZIP2
Alain Knaff30d65db2009-01-04 22:46:17 +0100150 help
151 Its compression ratio and speed is intermediate.
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700152 Decompression speed is slowest among the choices. The kernel
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800153 size is about 10% smaller with bzip2, in comparison to gzip.
154 Bzip2 uses a large amount of memory. For modern kernels you
155 will need at least 8MB RAM or more for booting.
Alain Knaff30d65db2009-01-04 22:46:17 +0100156
157config KERNEL_LZMA
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800158 bool "LZMA"
159 depends on HAVE_KERNEL_LZMA
160 help
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700161 This compression algorithm's ratio is best. Decompression speed
162 is between gzip and bzip2. Compression is slowest.
163 The kernel size is about 33% smaller with LZMA in comparison to gzip.
Alain Knaff30d65db2009-01-04 22:46:17 +0100164
Lasse Collin3ebe1242011-01-12 17:01:23 -0800165config KERNEL_XZ
166 bool "XZ"
167 depends on HAVE_KERNEL_XZ
168 help
169 XZ uses the LZMA2 algorithm and instruction set specific
170 BCJ filters which can improve compression ratio of executable
171 code. The size of the kernel is about 30% smaller with XZ in
172 comparison to gzip. On architectures for which there is a BCJ
173 filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
174 will create a few percent smaller kernel than plain LZMA.
175
176 The speed is about the same as with LZMA: The decompression
177 speed of XZ is better than that of bzip2 but worse than gzip
178 and LZO. Compression is slow.
179
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800180config KERNEL_LZO
181 bool "LZO"
182 depends on HAVE_KERNEL_LZO
183 help
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700184 Its compression ratio is the poorest among the choices. The kernel
Stephan Sperber681b3042010-07-14 11:23:08 +0200185 size is about 10% bigger than gzip; however its speed
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800186 (both compression and decompression) is the fastest.
187
Kyungsik Leee76e1fd2013-07-08 16:01:46 -0700188config KERNEL_LZ4
189 bool "LZ4"
190 depends on HAVE_KERNEL_LZ4
191 help
192 LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
193 A preliminary version of LZ4 de/compression tool is available at
194 <https://code.google.com/p/lz4/>.
195
196 Its compression ratio is worse than LZO. The size of the kernel
197 is about 8% bigger than LZO. But the decompression speed is
198 faster than LZO.
199
Alain Knaff30d65db2009-01-04 22:46:17 +0100200endchoice
201
Josh Triplettbd5dc172011-06-15 15:08:28 -0700202config DEFAULT_HOSTNAME
203 string "Default hostname"
204 default "(none)"
205 help
206 This option determines the default system hostname before userspace
207 calls sethostname(2). The kernel traditionally uses "(none)" here,
208 but you may wish to use a different default here to make a minimal
209 system more usable with less configuration.
210
Linus Torvalds1da177e2005-04-16 15:20:36 -0700211config SWAP
212 bool "Support for paging of anonymous memory (swap)"
David Howells93614012006-09-30 20:45:40 +0200213 depends on MMU && BLOCK
Linus Torvalds1da177e2005-04-16 15:20:36 -0700214 default y
215 help
216 This option allows you to choose whether you want to have support
Jesper Juhl92c35042006-01-15 02:40:08 +0100217 for so called swap devices or swap files in your kernel that are
Linus Torvalds1da177e2005-04-16 15:20:36 -0700218 used to provide more virtual memory than the actual RAM present
219 in your computer. If unsure say Y.
220
221config SYSVIPC
222 bool "System V IPC"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700223 ---help---
224 Inter Process Communication is a suite of library functions and
225 system calls which let processes (running programs) synchronize and
226 exchange information. It is generally considered to be a good thing,
227 and some programs won't run unless you say Y here. In particular, if
228 you want to run the DOS emulator dosemu under Linux (read the
229 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
230 you'll need to say Y here.
231
232 You can find documentation about IPC with "info ipc" and also in
233 section 6.4 of the Linux Programmer's Guide, available from
234 <http://www.tldp.org/guides.html>.
235
Eric W. Biedermana5494dc2007-02-14 00:34:06 -0800236config SYSVIPC_SYSCTL
237 bool
238 depends on SYSVIPC
239 depends on SYSCTL
240 default y
241
Linus Torvalds1da177e2005-04-16 15:20:36 -0700242config POSIX_MQUEUE
243 bool "POSIX Message Queues"
Kees Cook19c92392012-10-02 11:19:29 -0700244 depends on NET
Linus Torvalds1da177e2005-04-16 15:20:36 -0700245 ---help---
246 POSIX variant of message queues is a part of IPC. In POSIX message
247 queues every message has a priority which decides about succession
248 of receiving it by a process. If you want to compile and run
249 programs written e.g. for Solaris with use of its POSIX message
Robert P. J. Dayb0e37652007-05-09 07:25:13 +0200250 queues (functions mq_*) say Y here.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700251
252 POSIX message queues are visible as a filesystem called 'mqueue'
253 and can be mounted somewhere if you want to do filesystem
254 operations on message queues.
255
256 If unsure, say Y.
257
Serge E. Hallynbdc8e5f2009-04-06 19:01:11 -0700258config POSIX_MQUEUE_SYSCTL
259 bool
260 depends on POSIX_MQUEUE
261 depends on SYSCTL
262 default y
263
Konstantin Khlebnikov226b4cc2014-06-04 16:10:50 -0700264config CROSS_MEMORY_ATTACH
265 bool "Enable process_vm_readv/writev syscalls"
266 depends on MMU
267 default y
268 help
269 Enabling this option adds the system calls process_vm_readv and
270 process_vm_writev which allow a process with the correct privileges
Geert Uytterhoevena2a368d2014-08-12 13:46:11 -0700271 to directly read from or write to another process' address space.
Konstantin Khlebnikov226b4cc2014-06-04 16:10:50 -0700272 See the man page for more details.
273
Aneesh Kumar K.V990d6c22011-01-29 18:43:26 +0530274config FHANDLE
275 bool "open by fhandle syscalls"
276 select EXPORTFS
277 help
278 If you say Y here, a user level program will be able to map
279 file names to handle and then later use the handle for
280 different file system operations. This is useful in implementing
281 userspace file servers, which now track files using handles instead
282 of names. The handle would remain the same even if file names
283 get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
284 syscalls.
285
Josh Triplett69369a72014-04-03 14:48:27 -0700286config USELIB
287 bool "uselib syscall"
288 default y
289 help
290 This option enables the uselib syscall, a system call used in the
291 dynamic linker from libc5 and earlier. glibc does not use this
292 system call. If you intend to run programs built on libc5 or
293 earlier, you may need to enable this syscall. Current systems
294 running glibc can safely disable this.
295
Linus Torvalds1da177e2005-04-16 15:20:36 -0700296config AUDIT
297 bool "Auditing support"
Chris Wright804a6a492005-05-11 10:52:45 +0100298 depends on NET
Linus Torvalds1da177e2005-04-16 15:20:36 -0700299 help
300 Enable auditing infrastructure that can be used with another
301 kernel subsystem, such as SELinux (which requires this for
302 logging of avc messages output). Does not do system-call
303 auditing without CONFIG_AUDITSYSCALL.
304
AKASHI Takahiro7a017722014-02-25 18:16:24 +0900305config HAVE_ARCH_AUDITSYSCALL
306 bool
307
Linus Torvalds1da177e2005-04-16 15:20:36 -0700308config AUDITSYSCALL
309 bool "Enable system-call auditing support"
AKASHI Takahiro7a017722014-02-25 18:16:24 +0900310 depends on AUDIT && HAVE_ARCH_AUDITSYSCALL
Linus Torvalds1da177e2005-04-16 15:20:36 -0700311 default y if SECURITY_SELINUX
312 help
313 Enable low-overhead system-call auditing infrastructure that
314 can be used independently or with another kernel subsystem,
Eric Paris67640b62009-12-17 20:12:06 -0500315 such as SELinux.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700316
Eric Paris939a67f2009-12-17 20:12:06 -0500317config AUDIT_WATCH
318 def_bool y
319 depends on AUDITSYSCALL
320 select FSNOTIFY
Linus Torvalds1da177e2005-04-16 15:20:36 -0700321
Al Viro74c3cbe2007-07-22 08:04:18 -0400322config AUDIT_TREE
323 def_bool y
Eric Paris63c882a2009-05-21 17:02:01 -0400324 depends on AUDITSYSCALL
Eric Paris28a3a7e2009-12-17 20:12:05 -0500325 select FSNOTIFY
Al Viro74c3cbe2007-07-22 08:04:18 -0400326
Thomas Gleixnerd9817eb2010-09-27 12:45:59 +0000327source "kernel/irq/Kconfig"
Thomas Gleixner764e0da2012-05-21 23:16:18 +0200328source "kernel/time/Kconfig"
Thomas Gleixnerd9817eb2010-09-27 12:45:59 +0000329
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200330menu "CPU/Task time and stats accounting"
331
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200332config VIRT_CPU_ACCOUNTING
333 bool
334
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200335choice
336 prompt "Cputime accounting"
337 default TICK_CPU_ACCOUNTING if !PPC64
Stephen Rothwell02fc8d32013-02-08 14:19:38 +1100338 default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200339
340# Kind of a stub config for the pure tick based cputime accounting
341config TICK_CPU_ACCOUNTING
342 bool "Simple tick based cputime accounting"
Frederic Weisbeckerc58b0df2013-04-26 15:16:31 +0200343 depends on !S390 && !NO_HZ_FULL
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200344 help
345 This is the basic tick based cputime accounting that maintains
346 statistics about user, system and idle time spent on per jiffies
347 granularity.
348
349 If unsure, say Y.
350
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200351config VIRT_CPU_ACCOUNTING_NATIVE
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200352 bool "Deterministic task and CPU time accounting"
Frederic Weisbeckerc58b0df2013-04-26 15:16:31 +0200353 depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200354 select VIRT_CPU_ACCOUNTING
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200355 help
356 Select this option to enable more accurate task and CPU time
357 accounting. This is done by reading a CPU counter on each
358 kernel entry and exit and on transitions within the kernel
359 between system, softirq and hardirq state, so there is a
360 small performance impact. In the case of s390 or IBM POWER > 5,
361 this also enables accounting of stolen time on logically-partitioned
362 systems.
363
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200364config VIRT_CPU_ACCOUNTING_GEN
365 bool "Full dynticks CPU time accounting"
Kevin Hilmanff3fb252013-09-16 15:28:19 -0700366 depends on HAVE_CONTEXT_TRACKING
Kevin Hilman554b0002013-09-16 15:28:21 -0700367 depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200368 select VIRT_CPU_ACCOUNTING
369 select CONTEXT_TRACKING
370 help
371 Select this option to enable task and CPU time accounting on full
372 dynticks systems. This accounting is implemented by watching every
373 kernel-user boundaries using the context tracking subsystem.
374 The accounting is thus performed at the expense of some significant
375 overhead.
376
377 For now this is only useful if you are working on the full
378 dynticks subsystem development.
379
380 If unsure, say N.
381
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200382config IRQ_TIME_ACCOUNTING
383 bool "Fine granularity task level IRQ time accounting"
Frederic Weisbeckerc58b0df2013-04-26 15:16:31 +0200384 depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200385 help
386 Select this option to enable fine granularity task irq time
387 accounting. This is done by reading a timestamp on each
388 transitions between softirq and hardirq state, so there can be a
389 small performance impact.
390
391 If in doubt, say N here.
392
393endchoice
394
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200395config BSD_PROCESS_ACCT
396 bool "BSD Process Accounting"
Iulia Manda28138932015-04-15 16:16:41 -0700397 depends on MULTIUSER
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200398 help
399 If you say Y here, a user level program will be able to instruct the
400 kernel (via a special system call) to write process accounting
401 information to a file: whenever a process exits, information about
402 that process will be appended to the file by the kernel. The
403 information includes things such as creation time, owning user,
404 command name, memory usage, controlling terminal etc. (the complete
405 list is in the struct acct in <file:include/linux/acct.h>). It is
406 up to the user level program to do useful things with this
407 information. This is generally a good idea, so say Y.
408
409config BSD_PROCESS_ACCT_V3
410 bool "BSD Process Accounting version 3 file format"
411 depends on BSD_PROCESS_ACCT
412 default n
413 help
414 If you say Y here, the process accounting information is written
415 in a new file format that also logs the process IDs of each
416 process and it's parent. Note that this file format is incompatible
417 with previous v0/v1/v2 file formats, so you will need updated tools
418 for processing it. A preliminary version of these tools is available
419 at <http://www.gnu.org/software/acct/>.
420
421config TASKSTATS
Kees Cook19c92392012-10-02 11:19:29 -0700422 bool "Export task/process statistics through netlink"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200423 depends on NET
Iulia Manda28138932015-04-15 16:16:41 -0700424 depends on MULTIUSER
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200425 default n
426 help
427 Export selected statistics for tasks/processes through the
428 generic netlink interface. Unlike BSD process accounting, the
429 statistics are available during the lifetime of tasks/processes as
430 responses to commands. Like BSD accounting, they are sent to user
431 space on task exit.
432
433 Say N if unsure.
434
435config TASK_DELAY_ACCT
Kees Cook19c92392012-10-02 11:19:29 -0700436 bool "Enable per-task delay accounting"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200437 depends on TASKSTATS
438 help
439 Collect information on time spent by a task waiting for system
440 resources like cpu, synchronous block I/O completion and swapping
441 in pages. Such statistics can help in setting a task's priorities
442 relative to other tasks for cpu, io, rss limits etc.
443
444 Say N if unsure.
445
446config TASK_XACCT
Kees Cook19c92392012-10-02 11:19:29 -0700447 bool "Enable extended accounting over taskstats"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200448 depends on TASKSTATS
449 help
450 Collect extended task accounting data and send the data
451 to userland for processing over the taskstats interface.
452
453 Say N if unsure.
454
455config TASK_IO_ACCOUNTING
Kees Cook19c92392012-10-02 11:19:29 -0700456 bool "Enable per-task storage I/O accounting"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200457 depends on TASK_XACCT
458 help
459 Collect information on the number of bytes of storage I/O which this
460 task has caused.
461
462 Say N if unsure.
463
464endmenu # "CPU/Task time and stats accounting"
465
Mike Travisc903ff82009-01-15 12:28:29 -0800466menu "RCU Subsystem"
467
468choice
469 prompt "RCU Implementation"
Paul E. McKenney31c9a242009-04-02 21:06:25 -0700470 default TREE_RCU
Mike Travisc903ff82009-01-15 12:28:29 -0800471
Mike Travisc903ff82009-01-15 12:28:29 -0800472config TREE_RCU
473 bool "Tree-based hierarchical RCU"
Paul E. McKenney687d7a92010-07-21 06:52:40 -0700474 depends on !PREEMPT && SMP
Mike Travisc903ff82009-01-15 12:28:29 -0800475 help
476 This option selects the RCU implementation that is
477 designed for very large SMP system with hundreds or
Paul E. McKenneyc17ef452009-06-23 17:12:47 -0700478 thousands of CPUs. It also scales down nicely to
479 smaller systems.
Mike Travisc903ff82009-01-15 12:28:29 -0800480
Pranith Kumar28f65692014-09-22 14:00:48 -0400481config PREEMPT_RCU
Paul E. McKenneya57eb942010-06-29 16:49:16 -0700482 bool "Preemptible tree-based hierarchical RCU"
Paul E. McKenney9fc52d82013-01-08 15:48:33 -0800483 depends on PREEMPT
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700484 help
485 This option selects the RCU implementation that is
486 designed for very large SMP systems with hundreds or
487 thousands of CPUs, but for which real-time response
Paul E. McKenneybbe3eae2009-09-13 09:15:08 -0700488 is also required. It also scales down nicely to
489 smaller systems.
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700490
Paul E. McKenney9fc52d82013-01-08 15:48:33 -0800491 Select this option if you are unsure.
492
Paul E. McKenney9b1d82f2009-10-25 19:03:50 -0700493config TINY_RCU
494 bool "UP-only small-memory-footprint RCU"
Paul E. McKenney8008e122011-06-08 16:31:33 -0700495 depends on !PREEMPT && !SMP
Paul E. McKenney9b1d82f2009-10-25 19:03:50 -0700496 help
497 This option selects the RCU implementation that is
498 designed for UP systems from which real-time response
499 is not required. This option greatly reduces the
500 memory footprint of RCU.
501
Mike Travisc903ff82009-01-15 12:28:29 -0800502endchoice
503
Pranith Kumar83fe27e2014-12-05 11:24:45 -0500504config SRCU
505 bool
506 help
507 This option selects the sleepable version of RCU. This version
508 permits arbitrary sleeping or blocking within RCU read-side critical
509 sections.
510
Paul E. McKenney8315f422014-06-27 13:42:20 -0700511config TASKS_RCU
512 bool "Task_based RCU implementation using voluntary context switch"
513 default n
Pranith Kumar83fe27e2014-12-05 11:24:45 -0500514 select SRCU
Paul E. McKenney8315f422014-06-27 13:42:20 -0700515 help
516 This option enables a task-based RCU implementation that uses
517 only voluntary context switch (not preemption!), idle, and
518 user-mode execution as quiescent states.
519
520 If unsure, say N.
521
Paul E. McKenney6bfc09e2012-10-19 12:49:17 -0700522config RCU_STALL_COMMON
Pranith Kumar28f65692014-09-22 14:00:48 -0400523 def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
Paul E. McKenney6bfc09e2012-10-19 12:49:17 -0700524 help
525 This option enables RCU CPU stall code that is common between
526 the TINY and TREE variants of RCU. The purpose is to allow
527 the tiny variants to disable RCU CPU stall warnings, while
528 making these warnings mandatory for the tree variants.
529
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100530config CONTEXT_TRACKING
531 bool
532
Frederic Weisbecker2b1d5022012-07-11 20:26:30 +0200533config RCU_USER_QS
534 bool "Consider userspace as in RCU extended quiescent state"
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100535 depends on HAVE_CONTEXT_TRACKING && SMP
536 select CONTEXT_TRACKING
Frederic Weisbecker2b1d5022012-07-11 20:26:30 +0200537 help
538 This option sets hooks on kernel / userspace boundaries and
539 puts RCU in extended quiescent state when the CPU runs in
540 userspace. It means that when a CPU runs in userspace, it is
541 excluded from the global RCU state machine and thus doesn't
Paul Gortmakeraf71bef2012-10-24 11:07:09 -0700542 try to keep the timer tick on for RCU.
Frederic Weisbecker2b1d5022012-07-11 20:26:30 +0200543
Frederic Weisbeckerd6771242012-10-11 01:48:28 +0200544 Unless you want to hack and help the development of the full
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100545 dynticks mode, you shouldn't enable this option. It also
Paul Gortmakeraf71bef2012-10-24 11:07:09 -0700546 adds unnecessary overhead.
Frederic Weisbeckerd6771242012-10-11 01:48:28 +0200547
548 If unsure say N
549
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100550config CONTEXT_TRACKING_FORCE
551 bool "Force context tracking"
552 depends on CONTEXT_TRACKING
Frederic Weisbeckerd84d27a2013-07-24 21:59:29 +0200553 default y if !NO_HZ_FULL
Frederic Weisbecker1fd2b442012-07-11 20:26:40 +0200554 help
Frederic Weisbeckerd84d27a2013-07-24 21:59:29 +0200555 The major pre-requirement for full dynticks to work is to
556 support the context tracking subsystem. But there are also
557 other dependencies to provide in order to make the full
558 dynticks working.
559
560 This option stands for testing when an arch implements the
561 context tracking backend but doesn't yet fullfill all the
562 requirements to make the full dynticks feature working.
563 Without the full dynticks, there is no way to test the support
564 for context tracking and the subsystems that rely on it: RCU
565 userspace extended quiescent state and tickless cputime
566 accounting. This option copes with the absence of the full
567 dynticks subsystem by forcing the context tracking on all
568 CPUs in the system.
569
Paul Gortmaker99c8b1e2013-10-24 10:07:47 -0400570 Say Y only if you're working on the development of an
Frederic Weisbeckerd84d27a2013-07-24 21:59:29 +0200571 architecture backend for the context tracking.
572
573 Say N otherwise, this option brings an overhead that you
574 don't want in production.
575
Frederic Weisbeckerd6771242012-10-11 01:48:28 +0200576
Mike Travisc903ff82009-01-15 12:28:29 -0800577config RCU_FANOUT
578 int "Tree-based hierarchical RCU fanout value"
579 range 2 64 if 64BIT
580 range 2 32 if !64BIT
Pranith Kumar28f65692014-09-22 14:00:48 -0400581 depends on TREE_RCU || PREEMPT_RCU
Mike Travisc903ff82009-01-15 12:28:29 -0800582 default 64 if 64BIT
583 default 32 if !64BIT
584 help
585 This option controls the fanout of hierarchical implementations
586 of RCU, allowing RCU to work efficiently on machines with
Paul E. McKenney4d87ffa2010-08-04 17:31:12 -0700587 large numbers of CPUs. This value must be at least the fourth
588 root of NR_CPUS, which allows NR_CPUS to be insanely large.
589 The default value of RCU_FANOUT should be used for production
590 systems, but if you are stress-testing the RCU implementation
591 itself, small RCU_FANOUT values allow you to test large-system
592 code paths on small(er) systems.
Mike Travisc903ff82009-01-15 12:28:29 -0800593
594 Select a specific number if testing RCU itself.
595 Take the default if unsure.
596
Paul E. McKenney8932a632012-04-19 12:20:14 -0700597config RCU_FANOUT_LEAF
598 int "Tree-based hierarchical RCU leaf-level fanout value"
599 range 2 RCU_FANOUT if 64BIT
600 range 2 RCU_FANOUT if !64BIT
Pranith Kumar28f65692014-09-22 14:00:48 -0400601 depends on TREE_RCU || PREEMPT_RCU
Paul E. McKenney8932a632012-04-19 12:20:14 -0700602 default 16
603 help
604 This option controls the leaf-level fanout of hierarchical
605 implementations of RCU, and allows trading off cache misses
606 against lock contention. Systems that synchronize their
607 scheduling-clock interrupts for energy-efficiency reasons will
608 want the default because the smaller leaf-level fanout keeps
609 lock contention levels acceptably low. Very large systems
610 (hundreds or thousands of CPUs) will instead want to set this
611 value to the maximum value possible in order to reduce the
612 number of cache misses incurred during RCU's grace-period
613 initialization. These systems tend to run CPU-bound, and thus
614 are not helped by synchronized interrupts, and thus tend to
615 skew them, which reduces lock contention enough that large
616 leaf-level fanouts work well.
617
618 Select a specific number if testing RCU itself.
619
620 Select the maximum permissible value for large systems.
621
622 Take the default if unsure.
623
Mike Travisc903ff82009-01-15 12:28:29 -0800624config RCU_FANOUT_EXACT
625 bool "Disable tree-based hierarchical RCU auto-balancing"
Pranith Kumar28f65692014-09-22 14:00:48 -0400626 depends on TREE_RCU || PREEMPT_RCU
Mike Travisc903ff82009-01-15 12:28:29 -0800627 default n
628 help
629 This option forces use of the exact RCU_FANOUT value specified,
630 regardless of imbalances in the hierarchy. This is useful for
631 testing RCU itself, and might one day be useful on systems with
632 strong NUMA behavior.
633
634 Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
635
636 Say N if unsure.
637
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800638config RCU_FAST_NO_HZ
639 bool "Accelerate last non-dyntick-idle CPU's grace periods"
Frederic Weisbecker3451d022011-08-10 23:21:01 +0200640 depends on NO_HZ_COMMON && SMP
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800641 default n
642 help
Paul E. McKenneyc0f4dfd2012-12-28 11:30:36 -0800643 This option permits CPUs to enter dynticks-idle state even if
644 they have RCU callbacks queued, and prevents RCU from waking
645 these CPUs up more than roughly once every four jiffies (by
646 default, you can adjust this using the rcutree.rcu_idle_gp_delay
647 parameter), thus improving energy efficiency. On the other
648 hand, this option increases the duration of RCU grace periods,
649 for example, slowing down synchronize_rcu().
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800650
Paul E. McKenneyc0f4dfd2012-12-28 11:30:36 -0800651 Say Y if energy efficiency is critically important, and you
652 don't care about increased grace-period durations.
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800653
654 Say N if you are unsure.
655
Mike Travisc903ff82009-01-15 12:28:29 -0800656config TREE_RCU_TRACE
Pranith Kumar28f65692014-09-22 14:00:48 -0400657 def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU )
Mike Travisc903ff82009-01-15 12:28:29 -0800658 select DEBUG_FS
659 help
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700660 This option provides tracing for the TREE_RCU and
Pranith Kumar28f65692014-09-22 14:00:48 -0400661 PREEMPT_RCU implementations, permitting Makefile to
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700662 trivially select kernel/rcutree_trace.c.
Mike Travisc903ff82009-01-15 12:28:29 -0800663
Paul E. McKenney24278d12010-09-27 17:25:23 -0700664config RCU_BOOST
665 bool "Enable RCU priority boosting"
Paul E. McKenney27f4d282011-02-07 12:47:15 -0800666 depends on RT_MUTEXES && PREEMPT_RCU
Paul E. McKenney24278d12010-09-27 17:25:23 -0700667 default n
668 help
669 This option boosts the priority of preempted RCU readers that
670 block the current preemptible RCU grace period for too long.
671 This option also prevents heavy loads from blocking RCU
672 callback invocation for all flavors of RCU.
673
674 Say Y here if you are working with real-time apps or heavy loads
675 Say N here if you are unsure.
676
Clark Williams21871d72014-09-12 21:21:09 -0500677config RCU_KTHREAD_PRIO
678 int "Real-time priority to use for RCU worker threads"
Paul E. McKenneya94844b2014-12-12 07:37:48 -0800679 range 1 99 if RCU_BOOST
680 range 0 99 if !RCU_BOOST
681 default 1 if RCU_BOOST
682 default 0 if !RCU_BOOST
Paul E. McKenney24278d12010-09-27 17:25:23 -0700683 help
Clark Williams21871d72014-09-12 21:21:09 -0500684 This option specifies the SCHED_FIFO priority value that will be
685 assigned to the rcuc/n and rcub/n threads and is also the value
686 used for RCU_BOOST (if enabled). If you are working with a
687 real-time application that has one or more CPU-bound threads
688 running at a real-time priority level, you should set
689 RCU_KTHREAD_PRIO to a priority higher than the highest-priority
690 real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO
691 value of 1 is appropriate in the common case, which is real-time
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700692 applications that do not have any CPU-bound threads.
693
694 Some real-time applications might not have a single real-time
695 thread that saturates a given CPU, but instead might have
696 multiple real-time threads that, taken together, fully utilize
Clark Williams21871d72014-09-12 21:21:09 -0500697 that CPU. In this case, you should set RCU_KTHREAD_PRIO to
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700698 a priority higher than the lowest-priority thread that is
699 conspiring to prevent the CPU from running any non-real-time
700 tasks. For example, if one thread at priority 10 and another
701 thread at priority 5 are between themselves fully consuming
Clark Williams21871d72014-09-12 21:21:09 -0500702 the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700703 set to priority 6 or higher.
Paul E. McKenney24278d12010-09-27 17:25:23 -0700704
705 Specify the real-time priority, or take the default if unsure.
706
707config RCU_BOOST_DELAY
708 int "Milliseconds to delay boosting after RCU grace-period start"
709 range 0 3000
710 depends on RCU_BOOST
711 default 500
712 help
713 This option specifies the time to wait after the beginning of
714 a given grace period before priority-boosting preempted RCU
715 readers blocking that grace period. Note that any RCU reader
716 blocking an expedited RCU grace period is boosted immediately.
717
718 Accept the default if unsure.
719
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700720config RCU_NOCB_CPU
Paul E. McKenney9a5739d2013-03-28 20:48:36 -0700721 bool "Offload RCU callback processing from boot-selected CPUs"
Pranith Kumar28f65692014-09-22 14:00:48 -0400722 depends on TREE_RCU || PREEMPT_RCU
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700723 default n
724 help
725 Use this option to reduce OS jitter for aggressive HPC or
726 real-time workloads. It can also be used to offload RCU
727 callback invocation to energy-efficient CPUs in battery-powered
728 asymmetric multiprocessors.
729
730 This option offloads callback invocation from the set of
731 CPUs specified at boot time by the rcu_nocbs parameter.
Paul E. McKenneya4889852012-12-03 08:16:28 -0800732 For each such CPU, a kthread ("rcuox/N") will be created to
733 invoke callbacks, where the "N" is the CPU being offloaded,
734 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
735 "s" for RCU-sched. Nothing prevents this kthread from running
736 on the specified CPUs, but (1) the kthreads may be preempted
737 between each callback, and (2) affinity or cgroups can be used
738 to force the kthreads to run on whatever set of CPUs is desired.
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700739
Paul E. McKenney34ed62462013-01-07 13:37:42 -0800740 Say Y here if you want to help to debug reduced OS jitter.
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700741 Say N here if you are unsure.
742
Paul E. McKenney911af502013-02-11 10:23:27 -0800743choice
744 prompt "Build-forced no-CBs CPUs"
745 default RCU_NOCB_CPU_NONE
Stefan Hengelein45687792014-09-02 19:55:11 +0200746 depends on RCU_NOCB_CPU
Paul E. McKenney911af502013-02-11 10:23:27 -0800747 help
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700748 This option allows no-CBs CPUs (whose RCU callbacks are invoked
749 from kthreads rather than from softirq context) to be specified
750 at build time. Additional no-CBs CPUs may be specified by
751 the rcu_nocbs= boot parameter.
Paul E. McKenney911af502013-02-11 10:23:27 -0800752
753config RCU_NOCB_CPU_NONE
754 bool "No build_forced no-CBs CPUs"
Paul E. McKenney911af502013-02-11 10:23:27 -0800755 help
756 This option does not force any of the CPUs to be no-CBs CPUs.
757 Only CPUs designated by the rcu_nocbs= boot parameter will be
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700758 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
759 kthreads whose names begin with "rcuo". All other CPUs will
760 invoke their own RCU callbacks in softirq context.
761
762 Select this option if you want to choose no-CBs CPUs at
763 boot time, for example, to allow testing of different no-CBs
764 configurations without having to rebuild the kernel each time.
Paul E. McKenney911af502013-02-11 10:23:27 -0800765
766config RCU_NOCB_CPU_ZERO
767 bool "CPU 0 is a build_forced no-CBs CPU"
Paul E. McKenney911af502013-02-11 10:23:27 -0800768 help
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700769 This option forces CPU 0 to be a no-CBs CPU, so that its RCU
770 callbacks are invoked by a per-CPU kthread whose name begins
771 with "rcuo". Additional CPUs may be designated as no-CBs
772 CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
773 All other CPUs will invoke their own RCU callbacks in softirq
774 context.
Paul E. McKenney911af502013-02-11 10:23:27 -0800775
776 Select this if CPU 0 needs to be a no-CBs CPU for real-time
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700777 or energy-efficiency reasons, but the real reason it exists
778 is to ensure that randconfig testing covers mixed systems.
Paul E. McKenney911af502013-02-11 10:23:27 -0800779
780config RCU_NOCB_CPU_ALL
781 bool "All CPUs are build_forced no-CBs CPUs"
Paul E. McKenney911af502013-02-11 10:23:27 -0800782 help
783 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs=
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700784 boot parameter will be ignored. All CPUs' RCU callbacks will
785 be executed in the context of per-CPU rcuo kthreads created for
786 this purpose. Assuming that the kthreads whose names start with
787 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
788 on the remaining CPUs, but might decrease memory locality during
789 RCU-callback invocation, thus potentially degrading throughput.
Paul E. McKenney911af502013-02-11 10:23:27 -0800790
791 Select this if all CPUs need to be no-CBs CPUs for real-time
792 or energy-efficiency reasons.
793
794endchoice
795
Paul E. McKenneyee425712015-02-19 10:51:32 -0800796config RCU_EXPEDITE_BOOT
797 bool
798 default n
799 help
800 This option enables expedited grace periods at boot time,
801 as if rcu_expedite_gp() had been invoked early in boot.
802 The corresponding rcu_unexpedite_gp() is invoked from
803 rcu_end_inkernel_boot(), which is intended to be invoked
804 at the end of the kernel-only boot sequence, just before
805 init is exec'ed.
806
807 Accept the default if unsure.
808
Mike Travisc903ff82009-01-15 12:28:29 -0800809endmenu # "RCU Subsystem"
810
Vivek Goyalde5b56b2014-08-08 14:25:41 -0700811config BUILD_BIN2C
812 bool
813 default n
814
Linus Torvalds1da177e2005-04-16 15:20:36 -0700815config IKCONFIG
Ross Birof2443ab2006-09-30 23:27:25 -0700816 tristate "Kernel .config support"
Vivek Goyalde5b56b2014-08-08 14:25:41 -0700817 select BUILD_BIN2C
Linus Torvalds1da177e2005-04-16 15:20:36 -0700818 ---help---
819 This option enables the complete Linux kernel ".config" file
820 contents to be saved in the kernel. It provides documentation
821 of which kernel options are used in a running kernel or in an
822 on-disk kernel. This information can be extracted from the kernel
823 image file with the script scripts/extract-ikconfig and used as
824 input to rebuild the current kernel or to build another kernel.
825 It can also be extracted from a running kernel by reading
826 /proc/config.gz if enabled (below).
827
828config IKCONFIG_PROC
829 bool "Enable access to .config through /proc/config.gz"
830 depends on IKCONFIG && PROC_FS
831 ---help---
832 This option enables access to the kernel configuration file
833 through /proc/config.gz.
834
Alistair John Strachan794543a2007-05-08 00:31:15 -0700835config LOG_BUF_SHIFT
836 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
837 range 12 21
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700838 default 17
Josh Triplett361e9df2014-10-03 16:00:54 -0700839 depends on PRINTK
Alistair John Strachan794543a2007-05-08 00:31:15 -0700840 help
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700841 Select the minimal kernel log buffer size as a power of 2.
842 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config
843 parameter, see below. Any higher size also might be forced
844 by "log_buf_len" boot parameter.
845
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700846 Examples:
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700847 17 => 128 KB
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700848 16 => 64 KB
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700849 15 => 32 KB
850 14 => 16 KB
Alistair John Strachan794543a2007-05-08 00:31:15 -0700851 13 => 8 KB
852 12 => 4 KB
853
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700854config LOG_CPU_MAX_BUF_SHIFT
855 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
Geert Uytterhoeven2240a312014-10-13 15:51:11 -0700856 depends on SMP
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700857 range 0 21
858 default 12 if !BASE_SMALL
859 default 0 if BASE_SMALL
Josh Triplett361e9df2014-10-03 16:00:54 -0700860 depends on PRINTK
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700861 help
862 This option allows to increase the default ring buffer size
863 according to the number of CPUs. The value defines the contribution
864 of each CPU as a power of 2. The used space is typically only few
865 lines however it might be much more when problems are reported,
866 e.g. backtraces.
867
868 The increased size means that a new buffer has to be allocated and
869 the original static one is unused. It makes sense only on systems
870 with more CPUs. Therefore this value is used only when the sum of
871 contributions is greater than the half of the default kernel ring
872 buffer as defined by LOG_BUF_SHIFT. The default values are set
873 so that more than 64 CPUs are needed to trigger the allocation.
874
875 Also this option is ignored when "log_buf_len" kernel parameter is
876 used as it forces an exact (power of two) size of the ring buffer.
877
878 The number of possible CPUs is used for this computation ignoring
879 hotplugging making the compuation optimal for the the worst case
880 scenerio while allowing a simple algorithm to be used from bootup.
881
882 Examples shift values and their meaning:
883 17 => 128 KB for each CPU
884 16 => 64 KB for each CPU
885 15 => 32 KB for each CPU
886 14 => 16 KB for each CPU
887 13 => 8 KB for each CPU
888 12 => 4 KB for each CPU
889
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800890#
891# Architectures with an unreliable sched_clock() should select this:
892#
893config HAVE_UNSTABLE_SCHED_CLOCK
894 bool
895
Stephen Boyd38ff87f2013-06-01 23:39:40 -0700896config GENERIC_SCHED_CLOCK
897 bool
898
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200899#
900# For architectures that want to enable the support for NUMA-affine scheduler
901# balancing logic:
902#
903config ARCH_SUPPORTS_NUMA_BALANCING
904 bool
905
Peter Zijlstrabe5e6102013-11-18 18:27:06 +0100906#
907# For architectures that know their GCC __int128 support is sound
908#
909config ARCH_SUPPORTS_INT128
910 bool
911
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200912# For architectures that (ab)use NUMA to represent different memory regions
913# all cpu-local but of different latencies, such as SuperH.
914#
915config ARCH_WANT_NUMA_VARIABLE_LOCALITY
916 bool
917
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200918config NUMA_BALANCING
919 bool "Memory placement aware NUMA scheduler"
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200920 depends on ARCH_SUPPORTS_NUMA_BALANCING
921 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
922 depends on SMP && NUMA && MIGRATION
923 help
924 This option adds support for automatic NUMA aware memory/task placement.
925 The mechanism is quite primitive and is based on migrating memory when
Paul Gortmaker6d56a412013-08-13 11:06:50 -0400926 it has references to the node the task is running on.
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200927
928 This system will be inactive on UMA systems.
929
Aneesh Kumar K.V6f7c97e2014-12-10 15:43:37 -0800930config NUMA_BALANCING_DEFAULT_ENABLED
931 bool "Automatically enable NUMA aware memory/task placement"
932 default y
933 depends on NUMA_BALANCING
934 help
935 If set, automatic NUMA balancing will be enabled if running on a NUMA
936 machine.
937
Li Zefan23964d22009-01-15 13:50:58 -0800938menuconfig CGROUPS
Christoph Jaeger6341e622014-12-20 15:41:11 -0500939 bool "Control Group support"
Tejun Heo2bd59d42014-02-11 11:52:49 -0500940 select KERNFS
Paul Menageddbcc7e2007-10-18 23:39:30 -0700941 help
Li Zefan23964d22009-01-15 13:50:58 -0800942 This option adds support for grouping sets of processes together, for
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800943 use with process control subsystems such as Cpusets, CFS, memory
944 controls or device isolation.
945 See
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800946 - Documentation/scheduler/sched-design-CFS.txt (CFS)
Li Zefan45ce80f2009-01-15 13:50:59 -0800947 - Documentation/cgroups/ (features for grouping, isolation
948 and resource control)
Paul Menageddbcc7e2007-10-18 23:39:30 -0700949
950 Say N if unsure.
951
Li Zefan23964d22009-01-15 13:50:58 -0800952if CGROUPS
953
Paul Menage006cb992007-10-18 23:39:43 -0700954config CGROUP_DEBUG
955 bool "Example debug cgroup subsystem"
Paul Menage418d7d82008-04-29 01:00:05 -0700956 default n
Paul Menage006cb992007-10-18 23:39:43 -0700957 help
958 This option enables a simple cgroup subsystem that
959 exports useful debugging information about the cgroups
Li Zefan23964d22009-01-15 13:50:58 -0800960 framework.
Paul Menage006cb992007-10-18 23:39:43 -0700961
Li Zefan23964d22009-01-15 13:50:58 -0800962 Say N if unsure.
Paul Menage006cb992007-10-18 23:39:43 -0700963
Matt Helsleydc52ddc2008-10-18 20:27:21 -0700964config CGROUP_FREEZER
Li Zefan23964d22009-01-15 13:50:58 -0800965 bool "Freezer cgroup subsystem"
Li Zefan23964d22009-01-15 13:50:58 -0800966 help
967 Provides a way to freeze and unfreeze all tasks in a
Matt Helsleydc52ddc2008-10-18 20:27:21 -0700968 cgroup.
969
Serge E. Hallyn08ce5f12008-04-29 01:00:10 -0700970config CGROUP_DEVICE
971 bool "Device controller for cgroups"
Serge E. Hallyn08ce5f12008-04-29 01:00:10 -0700972 help
973 Provides a cgroup implementing whitelists for devices which
974 a process in the cgroup can mknod or open.
975
Linus Torvalds1da177e2005-04-16 15:20:36 -0700976config CPUSETS
977 bool "Cpuset support"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700978 help
Randy Dunlapd9fd8a62005-07-27 11:45:11 -0700979 This option will let you create and manage CPUSETs which
Linus Torvalds1da177e2005-04-16 15:20:36 -0700980 allow dynamically partitioning a system into sets of CPUs and
981 Memory Nodes and assigning tasks to run only within those sets.
982 This is primarily useful on large SMP or NUMA systems.
983
984 Say N if unsure.
985
Li Zefan23964d22009-01-15 13:50:58 -0800986config PROC_PID_CPUSET
987 bool "Include legacy /proc/<pid>/cpuset file"
988 depends on CPUSETS
989 default y
990
Srivatsa Vaddagirid842de82007-12-02 20:04:49 +0100991config CGROUP_CPUACCT
992 bool "Simple CPU accounting cgroup subsystem"
Srivatsa Vaddagirid842de82007-12-02 20:04:49 +0100993 help
994 Provides a simple Resource Controller for monitoring the
Li Zefan23964d22009-01-15 13:50:58 -0800995 total CPU consumed by the tasks in a cgroup.
Srivatsa Vaddagirid842de82007-12-02 20:04:49 +0100996
Johannes Weiner3e32cb22014-12-10 15:42:31 -0800997config PAGE_COUNTER
998 bool
999
Andrew Mortonc255a452012-07-31 16:43:02 -07001000config MEMCG
Balbir Singh00f0b822008-03-04 14:28:39 -08001001 bool "Memory Resource Controller for Control Groups"
Johannes Weiner3e32cb22014-12-10 15:42:31 -08001002 select PAGE_COUNTER
Tejun Heo79bd9812013-11-22 18:20:42 -05001003 select EVENTFD
Balbir Singh00f0b822008-03-04 14:28:39 -08001004 help
KAMEZAWA Hiroyuki84ad6d72008-10-29 14:01:06 -07001005 Provides a memory resource controller that manages both anonymous
Thadeu Lima de Souza Cascardo21acb9c2009-02-04 10:12:08 +01001006 memory and page cache. (See Documentation/cgroups/memory.txt)
Balbir Singh00f0b822008-03-04 14:28:39 -08001007
Andrew Mortonc255a452012-07-31 16:43:02 -07001008config MEMCG_SWAP
KAMEZAWA Hiroyuki65e0e812010-08-10 18:02:56 -07001009 bool "Memory Resource Controller Swap Extension"
Andrew Mortonc255a452012-07-31 16:43:02 -07001010 depends on MEMCG && SWAP
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -08001011 help
1012 Add swap management feature to memory resource controller. When you
1013 enable this, you can limit mem+swap usage per cgroup. In other words,
1014 when you disable this, memory resource controller has no cares to
1015 usage of swap...a process can exhaust all of the swap. This extension
1016 is useful when you want to avoid exhaustion swap but this itself
1017 adds more overheads and consumes memory for remembering information.
1018 Especially if you use 32bit system or small memory system, please
1019 be careful about enabling this. When memory resource controller
1020 is disabled by boot option, this will be automatically disabled and
1021 there will be no overhead from this. Even when you set this config=y,
WANG Cong00a66d22011-07-25 17:12:12 -07001022 if boot option "swapaccount=0" is set, swap will not be accounted.
KAMEZAWA Hiroyuki627991a2009-04-02 16:57:47 -07001023 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
1024 size is 4096bytes, 512k per 1Gbytes of swap.
Andrew Mortonc255a452012-07-31 16:43:02 -07001025config MEMCG_SWAP_ENABLED
Michal Hockoa42c3902010-11-24 12:57:08 -08001026 bool "Memory Resource Controller Swap Extension enabled by default"
Andrew Mortonc255a452012-07-31 16:43:02 -07001027 depends on MEMCG_SWAP
Michal Hockoa42c3902010-11-24 12:57:08 -08001028 default y
1029 help
1030 Memory Resource Controller Swap Extension comes with its price in
1031 a bigger memory consumption. General purpose distribution kernels
Jim Cromie43d547f2010-12-17 14:32:36 -07001032 which want to enable the feature but keep it disabled by default
Michal Hocko07555ac2013-08-22 16:35:46 -07001033 and let the user enable it by swapaccount=1 boot command line
Michal Hockoa42c3902010-11-24 12:57:08 -08001034 parameter should have this option unselected.
1035 For those who want to have the feature enabled by default should
1036 select this option (if, for some reason, they need to disable it
WANG Cong00a66d22011-07-25 17:12:12 -07001037 then swapaccount=0 does the trick).
Andrew Mortonc255a452012-07-31 16:43:02 -07001038config MEMCG_KMEM
Kees Cook19c92392012-10-02 11:19:29 -07001039 bool "Memory Resource Controller Kernel Memory accounting"
1040 depends on MEMCG
Glauber Costa510fc4e2012-12-18 14:21:47 -08001041 depends on SLUB || SLAB
Glauber Costae5671df2011-12-11 21:47:01 +00001042 help
1043 The Kernel Memory extension for Memory Resource Controller can limit
1044 the amount of memory used by kernel objects in the system. Those are
1045 fundamentally different from the entities handled by the standard
1046 Memory Controller, which are page-based, and can be swapped. Users of
1047 the kmem extension can use it to guarantee that no group of processes
1048 will ever exhaust kernel resources alone.
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -08001049
Vladimir Davydov2ee06462014-06-04 16:07:28 -07001050 WARNING: Current implementation lacks reclaim support. That means
1051 allocation attempts will fail when close to the limit even if there
1052 are plenty of kmem available for reclaim. That makes this option
1053 unusable in real life so DO NOT SELECT IT unless for development
1054 purposes.
1055
Aneesh Kumar K.V2bc64a22012-07-31 16:42:12 -07001056config CGROUP_HUGETLB
1057 bool "HugeTLB Resource Controller for Control Groups"
Johannes Weiner71f87bee2014-12-10 15:42:34 -08001058 depends on HUGETLB_PAGE
1059 select PAGE_COUNTER
Aneesh Kumar K.V2bc64a22012-07-31 16:42:12 -07001060 default n
1061 help
1062 Provides a cgroup Resource Controller for HugeTLB pages.
1063 When you enable this, you can put a per cgroup limit on HugeTLB usage.
1064 The limit is enforced during page fault. Since HugeTLB doesn't
1065 support page reclaim, enforcing the limit at page fault time implies
1066 that, the application will get SIGBUS signal if it tries to access
1067 HugeTLB pages beyond its limit. This requires the application to know
1068 beforehand how much HugeTLB pages it would require for its use. The
1069 control group is tracked in the third page lru pointer. This means
1070 that we cannot use the controller with huge page less than 3 pages.
1071
Stephane Eraniane5d13672011-02-14 11:20:01 +02001072config CGROUP_PERF
1073 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
1074 depends on PERF_EVENTS && CGROUPS
1075 help
1076 This option extends the per-cpu mode to restrict monitoring to
Li Zefan2d0f2522011-03-03 14:26:20 +08001077 threads which belong to the cgroup specified and run on the
Stephane Eraniane5d13672011-02-14 11:20:01 +02001078 designated cpu.
1079
1080 Say N if unsure.
1081
Dhaval Giani7c941432010-01-20 13:26:18 +01001082menuconfig CGROUP_SCHED
1083 bool "Group CPU scheduler"
Dhaval Giani7c941432010-01-20 13:26:18 +01001084 default n
1085 help
1086 This feature lets CPU scheduler recognize task groups and control CPU
1087 bandwidth allocation to such task groups. It uses cgroups to group
1088 tasks.
1089
1090if CGROUP_SCHED
1091config FAIR_GROUP_SCHED
1092 bool "Group scheduling for SCHED_OTHER"
1093 depends on CGROUP_SCHED
1094 default CGROUP_SCHED
1095
Paul Turnerab84d312011-07-21 09:43:28 -07001096config CFS_BANDWIDTH
1097 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
Paul Turnerab84d312011-07-21 09:43:28 -07001098 depends on FAIR_GROUP_SCHED
1099 default n
1100 help
1101 This option allows users to define CPU bandwidth rates (limits) for
1102 tasks running within the fair group scheduler. Groups with no limit
1103 set are considered to be unconstrained and will run with no
1104 restriction.
1105 See tip/Documentation/scheduler/sched-bwc.txt for more information.
1106
Dhaval Giani7c941432010-01-20 13:26:18 +01001107config RT_GROUP_SCHED
1108 bool "Group scheduling for SCHED_RR/FIFO"
Dhaval Giani7c941432010-01-20 13:26:18 +01001109 depends on CGROUP_SCHED
1110 default n
1111 help
1112 This feature lets you explicitly allocate real CPU bandwidth
Li Zefan32bd7eb2010-03-24 13:17:19 +08001113 to task groups. If enabled, it will also make it impossible to
Dhaval Giani7c941432010-01-20 13:26:18 +01001114 schedule realtime tasks for non-root users until you allocate
1115 realtime bandwidth for them.
1116 See Documentation/scheduler/sched-rt-group.txt for more information.
1117
1118endif #CGROUP_SCHED
1119
Vivek Goyalafc24d42010-04-26 19:27:56 +02001120config BLK_CGROUP
Tejun Heo32e380a2012-03-05 13:14:54 -08001121 bool "Block IO controller"
Daniel Lezcano79ae9c22010-10-27 15:34:39 -07001122 depends on BLOCK
Vivek Goyalafc24d42010-04-26 19:27:56 +02001123 default n
1124 ---help---
1125 Generic block IO controller cgroup interface. This is the common
1126 cgroup interface which should be used by various IO controlling
1127 policies.
1128
1129 Currently, CFQ IO scheduler uses it to recognize task groups and
1130 control disk bandwidth allocation (proportional time slice allocation)
Vivek Goyale43473b2010-09-15 17:06:35 -04001131 to such task groups. It is also used by bio throttling logic in
1132 block layer to implement upper limit in IO rates on a device.
Vivek Goyalafc24d42010-04-26 19:27:56 +02001133
1134 This option only enables generic Block IO controller infrastructure.
Vivek Goyale43473b2010-09-15 17:06:35 -04001135 One needs to also enable actual IO controlling logic/policy. For
Michael Witten79e2e752011-01-16 21:43:10 +00001136 enabling proportional weight division of disk bandwidth in CFQ, set
1137 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
Michael Wittenc5e05912011-01-17 00:08:41 +00001138 CONFIG_BLK_DEV_THROTTLING=y.
Vivek Goyalafc24d42010-04-26 19:27:56 +02001139
1140 See Documentation/cgroups/blkio-controller.txt for more information.
1141
1142config DEBUG_BLK_CGROUP
1143 bool "Enable Block IO controller debugging"
1144 depends on BLK_CGROUP
1145 default n
1146 ---help---
1147 Enable some debugging help. Currently it exports additional stat
1148 files in a cgroup which can be useful for debugging.
1149
Li Zefan23964d22009-01-15 13:50:58 -08001150endif # CGROUPS
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -08001151
Cyrill Gorcunov067bce12012-01-12 17:20:49 -08001152config CHECKPOINT_RESTORE
1153 bool "Checkpoint/restore support" if EXPERT
1154 default n
1155 help
1156 Enables additional kernel features in a sake of checkpoint/restore.
1157 In particular it adds auxiliary prctl codes to setup process text,
1158 data and heap segment sizes, and a few additional /proc filesystem
1159 entries.
1160
1161 If unsure, say N here.
1162
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001163menuconfig NAMESPACES
David Rientjes6a108a12011-01-20 14:44:16 -08001164 bool "Namespaces support" if EXPERT
Iulia Manda28138932015-04-15 16:16:41 -07001165 depends on MULTIUSER
David Rientjes6a108a12011-01-20 14:44:16 -08001166 default !EXPERT
Pavel Emelyanovc5289a62008-02-08 04:18:19 -08001167 help
1168 Provides the way to make tasks work with different objects using
1169 the same id. For example same IPC id may refer to different objects
1170 or same user id or pid may refer to different tasks when used in
1171 different namespaces.
1172
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001173if NAMESPACES
1174
Pavel Emelyanov58bfdd6d2008-02-08 04:18:21 -08001175config UTS_NS
1176 bool "UTS namespace"
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001177 default y
Pavel Emelyanov58bfdd6d2008-02-08 04:18:21 -08001178 help
1179 In this namespace tasks see different info provided with the
1180 uname() system call
1181
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -08001182config IPC_NS
1183 bool "IPC namespace"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001184 depends on (SYSVIPC || POSIX_MQUEUE)
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001185 default y
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -08001186 help
1187 In this namespace tasks work with IPC ids which correspond to
Serge E. Hallyn614b84c2009-04-06 19:01:08 -07001188 different IPC objects in different namespaces.
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -08001189
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -08001190config USER_NS
Kees Cook19c92392012-10-02 11:19:29 -07001191 bool "User namespace"
Eric W. Biederman5673a942011-11-17 10:23:55 -08001192 default n
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -08001193 help
1194 This allows containers, i.e. vservers, to use user namespaces
1195 to provide different user info for different servers.
Eric W. Biedermane11f0ae2013-01-25 16:48:31 -08001196
1197 When user namespaces are enabled in the kernel it is
1198 recommended that the MEMCG and MEMCG_KMEM options also be
1199 enabled and that user-space use the memory control groups to
1200 limit the amount of memory a memory unprivileged users can
1201 use.
1202
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -08001203 If unsure, say N.
1204
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -08001205config PID_NS
Daniel Lezcano9bd38c22010-10-27 15:34:37 -07001206 bool "PID Namespaces"
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001207 default y
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -08001208 help
Heikki Orsila12d2b8f2008-07-06 15:48:02 +03001209 Support process id namespaces. This allows having multiple
Matt LaPlante692105b2009-01-26 11:12:25 +01001210 processes with the same pid as long as they are in different
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -08001211 pid namespaces. This is a building block of containers.
1212
Matt Helsleyd6eb6332009-01-26 12:25:55 -08001213config NET_NS
1214 bool "Network namespace"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001215 depends on NET
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001216 default y
Matt Helsleyd6eb6332009-01-26 12:25:55 -08001217 help
1218 Allow user space to create what appear to be multiple instances
1219 of the network stack.
1220
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001221endif # NAMESPACES
1222
Mike Galbraith5091faa2010-11-30 14:18:03 +01001223config SCHED_AUTOGROUP
1224 bool "Automatic process group scheduling"
Mike Galbraith5091faa2010-11-30 14:18:03 +01001225 select CGROUPS
1226 select CGROUP_SCHED
1227 select FAIR_GROUP_SCHED
1228 help
1229 This option optimizes the scheduler for common desktop workloads by
1230 automatically creating and populating task groups. This separation
1231 of workloads isolates aggressive CPU burners (like build jobs) from
1232 desktop applications. Task group autogeneration is currently based
1233 upon task session.
1234
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001235config SYSFS_DEPRECATED
Ferenc Wagner5d6a4ea2011-01-10 19:04:22 +01001236 bool "Enable deprecated sysfs features to support old userspace tools"
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001237 depends on SYSFS
1238 default n
1239 help
1240 This option adds code that switches the layout of the "block" class
1241 devices, to not show up in /sys/class/block/, but only in
1242 /sys/block/.
1243
1244 This switch is only active when the sysfs.deprecated=1 boot option is
1245 passed or the SYSFS_DEPRECATED_V2 option is set.
1246
1247 This option allows new kernels to run on old distributions and tools,
1248 which might get confused by /sys/class/block/. Since 2007/2008 all
1249 major distributions and tools handle this just fine.
1250
1251 Recent distributions and userspace tools after 2009/2010 depend on
1252 the existence of /sys/class/block/, and will not work with this
1253 option enabled.
1254
1255 Only if you are using a new kernel on an old distribution, you might
1256 need to say Y here.
1257
1258config SYSFS_DEPRECATED_V2
Ferenc Wagner5d6a4ea2011-01-10 19:04:22 +01001259 bool "Enable deprecated sysfs features by default"
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001260 default n
1261 depends on SYSFS
1262 depends on SYSFS_DEPRECATED
1263 help
1264 Enable deprecated sysfs by default.
1265
1266 See the CONFIG_SYSFS_DEPRECATED option for more details about this
1267 option.
1268
1269 Only if you are using a new kernel on an old distribution, you might
1270 need to say Y here. Even then, odds are you would not need it
1271 enabled, you can always pass the boot option if absolutely necessary.
1272
1273config RELAY
1274 bool "Kernel->user space relay support (formerly relayfs)"
1275 help
1276 This option enables support for relay interface support in
1277 certain file systems (such as debugfs).
1278 It is designed to provide an efficient mechanism for tools and
1279 facilities to relay large amounts of data from kernel space to
1280 user space.
1281
1282 If unsure, say N.
1283
Dimitri Gorokhovikf9916332007-03-06 01:42:17 -08001284config BLK_DEV_INITRD
1285 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
1286 depends on BROKEN || !FRV
1287 help
1288 The initial RAM filesystem is a ramfs which is loaded by the
1289 boot loader (loadlin or lilo) and that is mounted as root
1290 before the normal boot procedure. It is typically used to
1291 load modules needed to mount the "real" root file system,
1292 etc. See <file:Documentation/initrd.txt> for details.
1293
1294 If RAM disk support (BLK_DEV_RAM) is also included, this
1295 also enables initial RAM disk (initrd) support and adds
1296 15 Kbytes (more on some other architectures) to the kernel size.
1297
1298 If unsure say Y.
1299
Jean-Paul Samanc33df4e2007-02-10 01:44:43 -08001300if BLK_DEV_INITRD
1301
Sam Ravnborgdbec4862005-08-10 20:44:50 +02001302source "usr/Kconfig"
1303
Jean-Paul Samanc33df4e2007-02-10 01:44:43 -08001304endif
1305
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001306config CC_OPTIMIZE_FOR_SIZE
Ingo Molnar96fffeb2008-04-28 01:39:43 +02001307 bool "Optimize for size"
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001308 help
Masahiro Yamada31a4af72014-08-05 14:43:07 +09001309 Enabling this option will pass "-Os" instead of "-O2" to
1310 your compiler resulting in a smaller kernel.
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001311
Kirill Smelkov3a55fb02012-11-02 15:41:01 +04001312 If unsure, say N.
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001313
Randy Dunlap08470622006-09-30 23:28:13 -07001314config SYSCTL
1315 bool
1316
Randy Dunlapb943c462009-03-10 12:55:46 -07001317config ANON_INODES
1318 bool
1319
Mike Frysinger657a5202013-04-30 15:28:45 -07001320config HAVE_UID16
1321 bool
1322
1323config SYSCTL_EXCEPTION_TRACE
1324 bool
1325 help
1326 Enable support for /proc/sys/debug/exception-trace.
1327
1328config SYSCTL_ARCH_UNALIGN_NO_WARN
1329 bool
1330 help
1331 Enable support for /proc/sys/kernel/ignore-unaligned-usertrap
1332 Allows arch to define/use @no_unaligned_warning to possibly warn
1333 about unaligned access emulation going on under the hood.
1334
1335config SYSCTL_ARCH_UNALIGN_ALLOW
1336 bool
1337 help
1338 Enable support for /proc/sys/kernel/unaligned-trap
1339 Allows arches to define/use @unaligned_enabled to runtime toggle
1340 the unaligned access emulation.
1341 see arch/parisc/kernel/unaligned.c for reference
1342
Mike Frysinger657a5202013-04-30 15:28:45 -07001343config HAVE_PCSPKR_PLATFORM
1344 bool
1345
Alexei Starovoitovf89b7752014-10-23 18:41:08 -07001346# interpreter that classic socket filters depend on
1347config BPF
1348 bool
1349
David Rientjes6a108a12011-01-20 14:44:16 -08001350menuconfig EXPERT
1351 bool "Configure standard kernel features (expert users)"
Josh Triplettf505c552011-06-05 18:23:58 -07001352 # Unhide debug options, to make the on-by-default options visible
1353 select DEBUG_KERNEL
Linus Torvalds1da177e2005-04-16 15:20:36 -07001354 help
1355 This option allows certain base kernel options and settings
1356 to be disabled or tweaked. This is for specialized
1357 environments which can tolerate a "non-standard" kernel.
1358 Only use this if you really know what you are doing.
1359
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001360config UID16
David Rientjes6a108a12011-01-20 14:44:16 -08001361 bool "Enable 16-bit UID system calls" if EXPERT
Iulia Manda28138932015-04-15 16:16:41 -07001362 depends on HAVE_UID16 && MULTIUSER
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001363 default y
1364 help
1365 This enables the legacy 16-bit UID syscall wrappers.
1366
Iulia Manda28138932015-04-15 16:16:41 -07001367config MULTIUSER
1368 bool "Multiple users, groups and capabilities support" if EXPERT
1369 default y
1370 help
1371 This option enables support for non-root users, groups and
1372 capabilities.
1373
1374 If you say N here, all processes will run with UID 0, GID 0, and all
1375 possible capabilities. Saying N here also compiles out support for
1376 system calls related to UIDs, GIDs, and capabilities, such as setuid,
1377 setgid, and capset.
1378
1379 If unsure, say Y here.
1380
Fabian Frederickf6187762014-06-04 16:11:12 -07001381config SGETMASK_SYSCALL
1382 bool "sgetmask/ssetmask syscalls support" if EXPERT
1383 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH
1384 ---help---
1385 sys_sgetmask and sys_ssetmask are obsolete system calls
1386 no longer supported in libc but still enabled by default in some
1387 architectures.
1388
1389 If unsure, leave the default option here.
1390
Fabian Frederick6af9f7b2014-04-03 14:48:25 -07001391config SYSFS_SYSCALL
1392 bool "Sysfs syscall support" if EXPERT
1393 default y
1394 ---help---
1395 sys_sysfs is an obsolete system call no longer supported in libc.
1396 Note that disabling this option is more secure but might break
1397 compatibility with some systems.
1398
1399 If unsure say Y here.
1400
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001401config SYSCTL_SYSCALL
David Rientjes6a108a12011-01-20 14:44:16 -08001402 bool "Sysctl syscall support" if EXPERT
Eric W. Biederman26a70342009-11-05 05:26:41 -08001403 depends on PROC_SYSCTL
WANG Congc736de62011-11-02 13:39:25 -07001404 default n
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001405 select SYSCTL
1406 ---help---
Eric W. Biederman13bb7e32006-11-08 17:44:51 -08001407 sys_sysctl uses binary paths that have been found challenging
1408 to properly maintain and use. The interface in /proc/sys
1409 using paths with ascii names is now the primary path to this
1410 information.
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001411
Eric W. Biederman13bb7e32006-11-08 17:44:51 -08001412 Almost nothing using the binary sysctl interface so if you are
1413 trying to save some space it is probably safe to disable this,
1414 making your kernel marginally smaller.
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001415
WANG Congc736de62011-11-02 13:39:25 -07001416 If unsure say N here.
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001417
Linus Torvalds1da177e2005-04-16 15:20:36 -07001418config KALLSYMS
David Rientjes6a108a12011-01-20 14:44:16 -08001419 bool "Load all symbols for debugging/ksymoops" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001420 default y
1421 help
1422 Say Y here to let the kernel print out symbolic crash information and
1423 symbolic stack backtraces. This increases the size of the kernel
1424 somewhat, as all symbols have to be loaded into the kernel image.
1425
1426config KALLSYMS_ALL
1427 bool "Include all symbols in kallsyms"
1428 depends on DEBUG_KERNEL && KALLSYMS
1429 help
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001430 Normally kallsyms only contains the symbols of functions for nicer
1431 OOPS messages and backtraces (i.e., symbols from the text and inittext
1432 sections). This is sufficient for most cases. And only in very rare
1433 cases (e.g., when a debugger is used) all symbols are required (e.g.,
1434 names of variables from the data sections, etc).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001435
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001436 This option makes sure that all symbols are loaded into the kernel
1437 image (i.e., symbols from all sections) in cost of increased kernel
1438 size (depending on the kernel configuration, it may be 300KiB or
1439 something like this).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001440
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001441 Say N unless you really need all symbols.
Matt Mackalld59745c2005-05-01 08:59:02 -07001442
1443config PRINTK
1444 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001445 bool "Enable support for printk" if EXPERT
Frederic Weisbecker74876a92012-10-12 18:00:23 +02001446 select IRQ_WORK
Matt Mackalld59745c2005-05-01 08:59:02 -07001447 help
1448 This option enables normal printk support. Removing it
1449 eliminates most of the message strings from the kernel image
1450 and makes the kernel more or less silent. As this makes it
1451 very difficult to diagnose system problems, saying N here is
1452 strongly discouraged.
1453
Matt Mackallc8538a72005-05-01 08:59:01 -07001454config BUG
David Rientjes6a108a12011-01-20 14:44:16 -08001455 bool "BUG() support" if EXPERT
Matt Mackallc8538a72005-05-01 08:59:01 -07001456 default y
1457 help
1458 Disabling this option eliminates support for BUG and WARN, reducing
1459 the size of your kernel image and potentially quietly ignoring
1460 numerous fatal conditions. You should only consider disabling this
1461 option for embedded systems with no facilities for reporting errors.
1462 Just say Y.
1463
Matt Mackall708e9a72006-01-08 01:05:25 -08001464config ELF_CORE
Alex Kelly046d6622012-10-04 17:15:23 -07001465 depends on COREDUMP
Matt Mackall708e9a72006-01-08 01:05:25 -08001466 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001467 bool "Enable ELF core dumps" if EXPERT
Matt Mackall708e9a72006-01-08 01:05:25 -08001468 help
1469 Enable support for generating core dumps. Disabling saves about 4k.
1470
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001471
Stas Sergeeve5e1d3c2008-05-07 12:39:56 +02001472config PCSPKR_PLATFORM
David Rientjes6a108a12011-01-20 14:44:16 -08001473 bool "Enable PC-Speaker support" if EXPERT
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001474 depends on HAVE_PCSPKR_PLATFORM
Ralf Baechle15f304b2011-06-01 19:04:59 +01001475 select I8253_LOCK
Stas Sergeeve5e1d3c2008-05-07 12:39:56 +02001476 default y
1477 help
1478 This option allows to disable the internal PC-Speaker
1479 support, saving some memory.
1480
Linus Torvalds1da177e2005-04-16 15:20:36 -07001481config BASE_FULL
1482 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001483 bool "Enable full-sized data structures for core" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001484 help
1485 Disabling this option reduces the size of miscellaneous core
1486 kernel data structures. This saves memory on small machines,
1487 but may reduce performance.
1488
1489config FUTEX
David Rientjes6a108a12011-01-20 14:44:16 -08001490 bool "Enable futex support" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001491 default y
Ingo Molnar23f78d4a2006-06-27 02:54:53 -07001492 select RT_MUTEXES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001493 help
1494 Disabling this option will cause the kernel to be built without
1495 support for "fast userspace mutexes". The resulting kernel may not
1496 run glibc-based applications correctly.
1497
Heiko Carstens03b8c7b2014-03-02 13:09:47 +01001498config HAVE_FUTEX_CMPXCHG
1499 bool
Josh Triplett62b4d202014-10-03 16:19:24 -07001500 depends on FUTEX
Heiko Carstens03b8c7b2014-03-02 13:09:47 +01001501 help
1502 Architectures should select this if futex_atomic_cmpxchg_inatomic()
1503 is implemented and always working. This removes a couple of runtime
1504 checks.
1505
Linus Torvalds1da177e2005-04-16 15:20:36 -07001506config EPOLL
David Rientjes6a108a12011-01-20 14:44:16 -08001507 bool "Enable eventpoll support" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001508 default y
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001509 select ANON_INODES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001510 help
1511 Disabling this option will cause the kernel to be built without
1512 support for epoll family of system calls.
1513
Davide Libenzifba2afa2007-05-10 22:23:13 -07001514config SIGNALFD
David Rientjes6a108a12011-01-20 14:44:16 -08001515 bool "Enable signalfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001516 select ANON_INODES
Davide Libenzifba2afa2007-05-10 22:23:13 -07001517 default y
1518 help
1519 Enable the signalfd() system call that allows to receive signals
1520 on a file descriptor.
1521
1522 If unsure, say Y.
1523
Davide Libenzib215e282007-05-10 22:23:16 -07001524config TIMERFD
David Rientjes6a108a12011-01-20 14:44:16 -08001525 bool "Enable timerfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001526 select ANON_INODES
Davide Libenzib215e282007-05-10 22:23:16 -07001527 default y
1528 help
1529 Enable the timerfd() system call that allows to receive timer
1530 events on a file descriptor.
1531
1532 If unsure, say Y.
1533
Davide Libenzie1ad7462007-05-10 22:23:19 -07001534config EVENTFD
David Rientjes6a108a12011-01-20 14:44:16 -08001535 bool "Enable eventfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001536 select ANON_INODES
Davide Libenzie1ad7462007-05-10 22:23:19 -07001537 default y
1538 help
1539 Enable the eventfd() system call that allows to receive both
1540 kernel notification (ie. KAIO) or userspace notifications.
1541
1542 If unsure, say Y.
1543
Alexei Starovoitovf89b7752014-10-23 18:41:08 -07001544# syscall, maps, verifier
1545config BPF_SYSCALL
Ingo Molnare1abf2c2015-04-02 15:51:39 +02001546 bool "Enable bpf() system call"
Alexei Starovoitovf89b7752014-10-23 18:41:08 -07001547 select ANON_INODES
1548 select BPF
1549 default n
1550 help
1551 Enable the bpf() system call that allows to manipulate eBPF
1552 programs and maps via file descriptors.
1553
Linus Torvalds1da177e2005-04-16 15:20:36 -07001554config SHMEM
David Rientjes6a108a12011-01-20 14:44:16 -08001555 bool "Use full shmem filesystem" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001556 default y
1557 depends on MMU
1558 help
1559 The shmem is an internal filesystem used to manage shared memory.
1560 It is backed by swap and manages resource limits. It is also exported
1561 to userspace as tmpfs if TMPFS is enabled. Disabling this
1562 option replaces shmem and tmpfs with the much simpler ramfs code,
1563 which may be appropriate on small systems without swap.
1564
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001565config AIO
David Rientjes6a108a12011-01-20 14:44:16 -08001566 bool "Enable AIO support" if EXPERT
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001567 default y
1568 help
1569 This option enables POSIX asynchronous I/O which may by used
Mike Frysinger657a5202013-04-30 15:28:45 -07001570 by some high performance threaded applications. Disabling
1571 this option saves about 7k.
1572
Josh Triplettd3ac21c2014-08-17 19:41:09 -05001573config ADVISE_SYSCALLS
1574 bool "Enable madvise/fadvise syscalls" if EXPERT
1575 default y
1576 help
1577 This option enables the madvise and fadvise syscalls, used by
1578 applications to advise the kernel about their future memory or file
1579 usage, improving performance. If building an embedded system where no
1580 applications use these syscalls, you can disable this option to save
1581 space.
1582
Mike Frysinger657a5202013-04-30 15:28:45 -07001583config PCI_QUIRKS
1584 default y
1585 bool "Enable PCI quirk workarounds" if EXPERT
1586 depends on PCI
1587 help
1588 This enables workarounds for various PCI chipset
1589 bugs/quirks. Disable this only if your target machine is
1590 unaffected by PCI quirks.
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001591
Randy Dunlap6befe5f2011-04-26 12:33:21 -07001592config EMBEDDED
1593 bool "Embedded system"
Josh Triplett5d2acfc2014-04-07 15:39:09 -07001594 option allnoconfig_y
Randy Dunlap6befe5f2011-04-26 12:33:21 -07001595 select EXPERT
1596 help
1597 This option should be enabled if compiling the kernel for
1598 an embedded system so certain expert options are available
1599 for configuration.
1600
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001601config HAVE_PERF_EVENTS
Thomas Gleixner0793a612008-12-04 20:12:29 +01001602 bool
Mike Frysinger018df722009-06-12 13:17:43 -04001603 help
1604 See tools/perf/design.txt for details.
Thomas Gleixner0793a612008-12-04 20:12:29 +01001605
Peter Zijlstra906010b2009-09-21 16:08:49 +02001606config PERF_USE_VMALLOC
1607 bool
1608 help
1609 See tools/perf/design.txt for details
1610
Ingo Molnar57c0c152009-09-21 12:20:38 +02001611menu "Kernel Performance Events And Counters"
Thomas Gleixner0793a612008-12-04 20:12:29 +01001612
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001613config PERF_EVENTS
Ingo Molnar57c0c152009-09-21 12:20:38 +02001614 bool "Kernel performance events and counters"
Robert Richter392d65a2012-04-05 18:24:44 +02001615 default y if PROFILING
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001616 depends on HAVE_PERF_EVENTS
Ingo Molnar4c59e462008-12-08 19:38:33 +01001617 select ANON_INODES
Peter Zijlstrae360adb2010-10-14 14:01:34 +08001618 select IRQ_WORK
Pranith Kumar83fe27e2014-12-05 11:24:45 -05001619 select SRCU
Thomas Gleixner0793a612008-12-04 20:12:29 +01001620 help
Ingo Molnar57c0c152009-09-21 12:20:38 +02001621 Enable kernel support for various performance events provided
1622 by software and hardware.
Thomas Gleixner0793a612008-12-04 20:12:29 +01001623
Thadeu Lima de Souza Cascardodd770382009-10-30 19:32:25 -02001624 Software events are supported either built-in or via the
Ingo Molnar57c0c152009-09-21 12:20:38 +02001625 use of generic tracepoints.
1626
1627 Most modern CPUs support performance events via performance
1628 counter registers. These registers count the number of certain
Thomas Gleixner0793a612008-12-04 20:12:29 +01001629 types of hw events: such as instructions executed, cachemisses
1630 suffered, or branches mis-predicted - without slowing down the
1631 kernel or applications. These registers can also trigger interrupts
1632 when a threshold number of events have passed - and can thus be
1633 used to profile the code that runs on that CPU.
1634
Ingo Molnar57c0c152009-09-21 12:20:38 +02001635 The Linux Performance Event subsystem provides an abstraction of
Thadeu Lima de Souza Cascardodd770382009-10-30 19:32:25 -02001636 these software and hardware event capabilities, available via a
Ingo Molnar57c0c152009-09-21 12:20:38 +02001637 system call and used by the "perf" utility in tools/perf/. It
Thomas Gleixner0793a612008-12-04 20:12:29 +01001638 provides per task and per CPU counters, and it provides event
1639 capabilities on top of those.
1640
1641 Say Y if unsure.
1642
Peter Zijlstra906010b2009-09-21 16:08:49 +02001643config DEBUG_PERF_USE_VMALLOC
1644 default n
1645 bool "Debug: use vmalloc to back perf mmap() buffers"
1646 depends on PERF_EVENTS && DEBUG_KERNEL
1647 select PERF_USE_VMALLOC
1648 help
1649 Use vmalloc memory to back perf mmap() buffers.
1650
1651 Mostly useful for debugging the vmalloc code on platforms
1652 that don't require it.
1653
1654 Say N if unsure.
1655
Thomas Gleixner0793a612008-12-04 20:12:29 +01001656endmenu
1657
Christoph Lameterf8891e52006-06-30 01:55:45 -07001658config VM_EVENT_COUNTERS
1659 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001660 bool "Enable VM event counters for /proc/vmstat" if EXPERT
Christoph Lameterf8891e52006-06-30 01:55:45 -07001661 help
Paul Jackson2aea4fb2006-12-22 01:06:10 -08001662 VM event counters are needed for event counts to be shown.
1663 This option allows the disabling of the VM event counters
David Rientjes6a108a12011-01-20 14:44:16 -08001664 on EXPERT systems. /proc/vmstat will only show page counts
Paul Jackson2aea4fb2006-12-22 01:06:10 -08001665 if VM event counters are disabled.
Christoph Lameterf8891e52006-06-30 01:55:45 -07001666
Christoph Lameter41ecc552007-05-09 02:32:44 -07001667config SLUB_DEBUG
1668 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001669 bool "Enable SLUB debugging support" if EXPERT
Christoph Lameterf6acb632008-04-29 16:16:06 -07001670 depends on SLUB && SYSFS
Christoph Lameter41ecc552007-05-09 02:32:44 -07001671 help
1672 SLUB has extensive debug support features. Disabling these can
1673 result in significant savings in code size. This also disables
1674 SLUB sysfs support. /sys/slab will not exist and there will be
1675 no support for cache validation etc.
1676
Randy Dunlapb943c462009-03-10 12:55:46 -07001677config COMPAT_BRK
1678 bool "Disable heap randomization"
1679 default y
1680 help
1681 Randomizing heap placement makes heap exploits harder, but it
1682 also breaks ancient binaries (including anything libc5 based).
1683 This option changes the bootup default to heap randomization
Matt LaPlante692105b2009-01-26 11:12:25 +01001684 disabled, and can be overridden at runtime by setting
Randy Dunlapb943c462009-03-10 12:55:46 -07001685 /proc/sys/kernel/randomize_va_space to 2.
1686
1687 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1688
Christoph Lameter81819f02007-05-06 14:49:36 -07001689choice
1690 prompt "Choose SLAB allocator"
Christoph Lametera0acd822007-07-17 04:03:32 -07001691 default SLUB
Christoph Lameter81819f02007-05-06 14:49:36 -07001692 help
1693 This option allows to select a slab allocator.
1694
1695config SLAB
1696 bool "SLAB"
1697 help
1698 The regular slab allocator that is established and known to work
Christoph Lameter34013882007-05-09 02:32:47 -07001699 well in all environments. It organizes cache hot objects in
Simon Arlott02f56212008-11-05 22:18:19 +00001700 per cpu and per node queues.
Christoph Lameter81819f02007-05-06 14:49:36 -07001701
1702config SLUB
Christoph Lameter81819f02007-05-06 14:49:36 -07001703 bool "SLUB (Unqueued Allocator)"
1704 help
1705 SLUB is a slab allocator that minimizes cache line usage
1706 instead of managing queues of cached objects (SLAB approach).
1707 Per cpu caching is realized using slabs of objects instead
1708 of queues of objects. SLUB can use memory efficiently
Simon Arlott02f56212008-11-05 22:18:19 +00001709 and has enhanced diagnostics. SLUB is the default choice for
1710 a slab allocator.
Christoph Lameter81819f02007-05-06 14:49:36 -07001711
1712config SLOB
David Rientjes6a108a12011-01-20 14:44:16 -08001713 depends on EXPERT
Christoph Lameter81819f02007-05-06 14:49:36 -07001714 bool "SLOB (Simple Allocator)"
1715 help
Matt Mackall37291452008-02-04 22:29:38 -08001716 SLOB replaces the stock allocator with a drastically simpler
1717 allocator. SLOB is generally more space efficient but
1718 does not perform as well on large systems.
Christoph Lameter81819f02007-05-06 14:49:36 -07001719
1720endchoice
1721
Joonsoo Kim345c9052013-06-19 14:05:52 +09001722config SLUB_CPU_PARTIAL
1723 default y
Uwe Kleine-Königb39ffbf2013-07-17 16:54:59 +02001724 depends on SLUB && SMP
Joonsoo Kim345c9052013-06-19 14:05:52 +09001725 bool "SLUB per cpu partial cache"
1726 help
1727 Per cpu partial caches accellerate objects allocation and freeing
1728 that is local to a processor at the price of more indeterminism
1729 in the latency of the free. On overflow these caches will be cleared
1730 which requires the taking of locks that may cause latency spikes.
1731 Typically one would choose no for a realtime system.
1732
Jie Zhangea637632009-12-14 18:00:02 -08001733config MMAP_ALLOW_UNINITIALIZED
1734 bool "Allow mmapped anonymous memory to be uninitialized"
David Rientjes6a108a12011-01-20 14:44:16 -08001735 depends on EXPERT && !MMU
Jie Zhangea637632009-12-14 18:00:02 -08001736 default n
1737 help
1738 Normally, and according to the Linux spec, anonymous memory obtained
1739 from mmap() has it's contents cleared before it is passed to
1740 userspace. Enabling this config option allows you to request that
1741 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
1742 providing a huge performance boost. If this option is not enabled,
1743 then the flag will be ignored.
1744
1745 This is taken advantage of by uClibc's malloc(), and also by
1746 ELF-FDPIC binfmt's brk and stack allocator.
1747
1748 Because of the obvious security issues, this option should only be
1749 enabled on embedded devices where you control what is run in
1750 userspace. Since that isn't generally a problem on no-MMU systems,
1751 it is normally safe to say Y here.
1752
1753 See Documentation/nommu-mmap.txt for more information.
1754
Peter Foley82c04ff2014-04-18 15:07:11 -07001755config SYSTEM_TRUSTED_KEYRING
1756 bool "Provide system-wide ring of trusted keys"
1757 depends on KEYS
1758 help
1759 Provide a system keyring to which trusted keys can be added. Keys in
1760 the keyring are considered to be trusted. Keys may be added at will
1761 by the kernel from compiled-in data and from hardware key stores, but
1762 userspace may only add extra keys if those keys can be verified by
1763 keys already in the keyring.
1764
1765 Keys in this keyring are used by module signature checking.
1766
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05001767config PROFILING
Robert Richterb309a292010-02-26 15:01:23 +01001768 bool "Profiling support"
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05001769 help
1770 Say Y here to enable the extended profiling support mechanisms used
1771 by profilers such as OProfile.
1772
Ingo Molnar5f87f112008-07-23 14:15:22 +02001773#
1774# Place an empty function call at each tracepoint site. Can be
1775# dynamically changed for a probe function.
1776#
Mathieu Desnoyers97e1c182008-07-18 12:16:16 -04001777config TRACEPOINTS
Ingo Molnar5f87f112008-07-23 14:15:22 +02001778 bool
Mathieu Desnoyers97e1c182008-07-18 12:16:16 -04001779
Mathieu Desnoyersfb32e032008-02-02 15:10:33 -05001780source "arch/Kconfig"
1781
Linus Torvalds1da177e2005-04-16 15:20:36 -07001782endmenu # General setup
1783
Dmitry Baryshkovee7e5512008-06-29 14:18:46 +04001784config HAVE_GENERIC_DMA_COHERENT
1785 bool
1786 default n
1787
Linus Torvalds158a9622008-01-02 13:04:48 -08001788config SLABINFO
1789 bool
1790 depends on PROC_FS
Christoph Lameter0f389ec2008-04-14 18:53:02 +03001791 depends on SLAB || SLUB_DEBUG
Linus Torvalds158a9622008-01-02 13:04:48 -08001792 default y
1793
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001794config RT_MUTEXES
Christoph Jaeger6341e622014-12-20 15:41:11 -05001795 bool
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001796
Linus Torvalds1da177e2005-04-16 15:20:36 -07001797config BASE_SMALL
1798 int
1799 default 0 if BASE_FULL
1800 default 1 if !BASE_FULL
1801
Jan Engelhardt66da5732007-07-15 23:39:29 -07001802menuconfig MODULES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001803 bool "Enable loadable module support"
Yann E. MORIN11097a02013-08-11 16:07:50 +02001804 option modules
Linus Torvalds1da177e2005-04-16 15:20:36 -07001805 help
1806 Kernel modules are small pieces of compiled code which can
1807 be inserted in the running kernel, rather than being
1808 permanently built into the kernel. You use the "modprobe"
1809 tool to add (and sometimes remove) them. If you say Y here,
1810 many parts of the kernel can be built as modules (by
1811 answering M instead of Y where indicated): this is most
1812 useful for infrequently used options which are not required
1813 for booting. For more information, see the man pages for
1814 modprobe, lsmod, modinfo, insmod and rmmod.
1815
1816 If you say Y here, you will need to run "make
1817 modules_install" to put the modules under /lib/modules/
1818 where modprobe can find them (you may need to be root to do
1819 this).
1820
1821 If unsure, say Y.
1822
Robert P. J. Day0b0de142008-08-04 13:31:32 -04001823if MODULES
1824
Linus Torvalds826e4502008-05-04 17:04:16 -07001825config MODULE_FORCE_LOAD
1826 bool "Forced module loading"
Linus Torvalds826e4502008-05-04 17:04:16 -07001827 default n
1828 help
Rusty Russell91e37a72008-05-09 16:25:28 +10001829 Allow loading of modules without version information (ie. modprobe
1830 --force). Forced module loading sets the 'F' (forced) taint flag and
1831 is usually a really bad idea.
Linus Torvalds826e4502008-05-04 17:04:16 -07001832
Linus Torvalds1da177e2005-04-16 15:20:36 -07001833config MODULE_UNLOAD
1834 bool "Module unloading"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001835 help
1836 Without this option you will not be able to unload any
1837 modules (note that some modules may not be unloadable
Denys Vlasenkof7f5b672008-07-22 19:24:26 -05001838 anyway), which makes your kernel smaller, faster
1839 and simpler. If unsure, say Y.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001840
1841config MODULE_FORCE_UNLOAD
1842 bool "Forced module unloading"
Kees Cook19c92392012-10-02 11:19:29 -07001843 depends on MODULE_UNLOAD
Linus Torvalds1da177e2005-04-16 15:20:36 -07001844 help
1845 This option allows you to force a module to unload, even if the
1846 kernel believes it is unsafe: the kernel will remove the module
1847 without waiting for anyone to stop using it (using the -f option to
1848 rmmod). This is mainly for kernel developers and desperate users.
1849 If unsure, say N.
1850
Linus Torvalds1da177e2005-04-16 15:20:36 -07001851config MODVERSIONS
Sam Ravnborg0d541642005-12-26 23:04:02 +01001852 bool "Module versioning support"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001853 help
1854 Usually, you have to use modules compiled with your kernel.
1855 Saying Y here makes it sometimes possible to use modules
1856 compiled for different kernels, by adding enough information
1857 to the modules to (hopefully) spot any changes which would
1858 make them incompatible with the kernel you are running. If
1859 unsure, say N.
1860
1861config MODULE_SRCVERSION_ALL
1862 bool "Source checksum for all modules"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001863 help
1864 Modules which contain a MODULE_VERSION get an extra "srcversion"
1865 field inserted into their modinfo section, which contains a
1866 sum of the source files which made it. This helps maintainers
1867 see exactly which source was used to build a module (since
1868 others sometimes change the module source without updating
1869 the version). With this option, such a "srcversion" field
1870 will be created for all modules. If unsure, say N.
1871
Rusty Russell106a4ee2012-09-26 10:09:40 +01001872config MODULE_SIG
1873 bool "Module signature verification"
1874 depends on MODULES
David Howellsb56e5a12013-08-30 16:07:30 +01001875 select SYSTEM_TRUSTED_KEYRING
David Howells48ba2462012-09-26 10:11:03 +01001876 select KEYS
1877 select CRYPTO
1878 select ASYMMETRIC_KEY_TYPE
1879 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
1880 select PUBLIC_KEY_ALGO_RSA
1881 select ASN1
1882 select OID_REGISTRY
1883 select X509_CERTIFICATE_PARSER
Rusty Russell106a4ee2012-09-26 10:09:40 +01001884 help
1885 Check modules for valid signatures upon load: the signature
1886 is simply appended to the module. For more information see
1887 Documentation/module-signing.txt.
1888
David Howellsea0b6dc2012-09-26 10:09:50 +01001889 !!!WARNING!!! If you enable this option, you MUST make sure that the
1890 module DOES NOT get stripped after being signed. This includes the
1891 debuginfo strip done by some packagers (such as rpmbuild) and
1892 inclusion into an initramfs that wants the module size reduced.
1893
Rusty Russell106a4ee2012-09-26 10:09:40 +01001894config MODULE_SIG_FORCE
1895 bool "Require modules to be validly signed"
1896 depends on MODULE_SIG
1897 help
1898 Reject unsigned modules or signed modules for which we don't have a
1899 key. Without this, such modules will simply taint the kernel.
David Howellsea0b6dc2012-09-26 10:09:50 +01001900
Michal Marekd9d8d7e2013-01-25 13:41:31 +10301901config MODULE_SIG_ALL
1902 bool "Automatically sign all modules"
1903 default y
1904 depends on MODULE_SIG
1905 help
1906 Sign all modules during make modules_install. Without this option,
1907 modules must be signed manually, using the scripts/sign-file tool.
1908
1909comment "Do not forget to sign required modules with scripts/sign-file"
1910 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
1911
David Howellsea0b6dc2012-09-26 10:09:50 +01001912choice
1913 prompt "Which hash algorithm should modules be signed with?"
1914 depends on MODULE_SIG
1915 help
1916 This determines which sort of hashing algorithm will be used during
1917 signature generation. This algorithm _must_ be built into the kernel
1918 directly so that signature verification can take place. It is not
1919 possible to load a signed module containing the algorithm to check
1920 the signature on that module.
1921
1922config MODULE_SIG_SHA1
1923 bool "Sign modules with SHA-1"
1924 select CRYPTO_SHA1
1925
1926config MODULE_SIG_SHA224
1927 bool "Sign modules with SHA-224"
1928 select CRYPTO_SHA256
1929
1930config MODULE_SIG_SHA256
1931 bool "Sign modules with SHA-256"
1932 select CRYPTO_SHA256
1933
1934config MODULE_SIG_SHA384
1935 bool "Sign modules with SHA-384"
1936 select CRYPTO_SHA512
1937
1938config MODULE_SIG_SHA512
1939 bool "Sign modules with SHA-512"
1940 select CRYPTO_SHA512
1941
1942endchoice
1943
Michal Marek22753672013-01-25 13:41:00 +10301944config MODULE_SIG_HASH
1945 string
1946 depends on MODULE_SIG
1947 default "sha1" if MODULE_SIG_SHA1
1948 default "sha224" if MODULE_SIG_SHA224
1949 default "sha256" if MODULE_SIG_SHA256
1950 default "sha384" if MODULE_SIG_SHA384
1951 default "sha512" if MODULE_SIG_SHA512
1952
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09301953config MODULE_COMPRESS
1954 bool "Compress modules on installation"
1955 depends on MODULES
1956 help
1957 This option compresses the kernel modules when 'make
1958 modules_install' is run.
1959
1960 The modules will be compressed either using gzip or xz depend on the
1961 choice made in "Compression algorithm".
1962
1963 module-init-tools has support for gzip format while kmod handle gzip
1964 and xz compressed modules.
1965
1966 When a kernel module is installed from outside of the main kernel
1967 source and uses the Kbuild system for installing modules then that
1968 kernel module will also be compressed when it is installed.
1969
1970 This option provides little benefit when the modules are to be used inside
1971 an initrd or initramfs, it generally is more efficient to compress the whole
1972 initrd or initramfs instead.
1973
1974 This is fully compatible with signed modules while the signed module is
1975 compressed. module-init-tools or kmod handles decompression and provide to
1976 other layer the uncompressed but signed payload.
1977
1978choice
1979 prompt "Compression algorithm"
1980 depends on MODULE_COMPRESS
1981 default MODULE_COMPRESS_GZIP
1982 help
1983 This determines which sort of compression will be used during
1984 'make modules_install'.
1985
1986 GZIP (default) and XZ are supported.
1987
1988config MODULE_COMPRESS_GZIP
1989 bool "GZIP"
1990
1991config MODULE_COMPRESS_XZ
1992 bool "XZ"
1993
1994endchoice
1995
Robert P. J. Day0b0de142008-08-04 13:31:32 -04001996endif # MODULES
1997
Rusty Russell98a79d62008-12-13 21:19:41 +10301998config INIT_ALL_POSSIBLE
1999 bool
2000 help
Rusty Russell5f054e32012-03-29 15:38:31 +10302001 Back when each arch used to define their own cpu_online_mask and
2002 cpu_possible_mask, some of them chose to initialize cpu_possible_mask
Rusty Russell98a79d62008-12-13 21:19:41 +10302003 with all 1s, and others with all 0s. When they were centralised,
2004 it was better to provide this option than to break all the archs
Matt LaPlante692105b2009-01-26 11:12:25 +01002005 and have several arch maintainers pursuing me down dark alleys.
Rusty Russell98a79d62008-12-13 21:19:41 +10302006
Linus Torvalds1da177e2005-04-16 15:20:36 -07002007config STOP_MACHINE
2008 bool
2009 default y
2010 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
2011 help
2012 Need stop_machine() primitive.
Jens Axboe3a65dfe2005-11-04 08:43:35 +01002013
Jens Axboe3a65dfe2005-11-04 08:43:35 +01002014source "block/Kconfig"
Avi Kivitye98c3202007-10-16 23:27:31 -07002015
2016config PREEMPT_NOTIFIERS
2017 bool
Paul E. McKenneye260be62008-01-25 21:08:24 +01002018
Steffen Klassert16295be2010-01-06 19:47:10 +11002019config PADATA
2020 depends on SMP
2021 bool
2022
Andi Kleen754b7b62012-10-04 17:11:27 -07002023# Can be selected by architectures with broken toolchains
2024# that get confused by correct const<->read_only section
2025# mappings
2026config BROKEN_RODATA
2027 bool
2028
David Howells4520c6a2012-09-21 23:31:13 +01002029config ASN1
2030 tristate
2031 help
2032 Build a simple ASN.1 grammar compiler that produces a bytecode output
2033 that can be interpreted by the ASN.1 stream decoder and used to
2034 inform it as to what tags are to be expected in a stream and what
2035 functions to call on what tags.
2036
Thomas Gleixner6beb0002009-11-09 15:21:34 +00002037source "kernel/Kconfig.locks"