blob: 89093e178c27abb6538b82b99dbae6054d212d80 [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 HAVE_IRQ_WORK
24 bool
25
26config IRQ_WORK
27 bool
28 depends on HAVE_IRQ_WORK
29
David Daney1dbdc6f2012-04-19 14:59:57 -070030config BUILDTIME_EXTABLE_SORT
31 bool
32
Al Boldiff0cfc62007-07-31 00:39:23 -070033menu "General setup"
Linus Torvalds1da177e2005-04-16 15:20:36 -070034
35config EXPERIMENTAL
36 bool "Prompt for development and/or incomplete code/drivers"
37 ---help---
38 Some of the various things that Linux supports (such as network
39 drivers, file systems, network protocols, etc.) can be in a state
40 of development where the functionality, stability, or the level of
41 testing is not yet high enough for general use. This is usually
42 known as the "alpha-test" phase among developers. If a feature is
43 currently in alpha-test, then the developers usually discourage
44 uninformed widespread use of this feature by the general public to
45 avoid "Why doesn't this work?" type mail messages. However, active
46 testing and use of these systems is welcomed. Just be aware that it
47 may not meet the normal level of reliability or it may fail to work
48 in some special cases. Detailed bug reports from people familiar
49 with the kernel internals are usually welcomed by the developers
50 (before submitting bug reports, please read the documents
51 <file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>,
52 <file:Documentation/BUG-HUNTING>, and
53 <file:Documentation/oops-tracing.txt> in the kernel source).
54
55 This option will also make obsoleted drivers available. These are
56 drivers that have been replaced by something else, and/or are
57 scheduled to be removed in a future kernel release.
58
59 Unless you intend to help test and develop a feature or driver that
60 falls into this category, or you have a situation that requires
61 using these features, you should probably say N here, which will
62 cause the configurator to present you with fewer choices. If
63 you say Y here, you will be offered the choice of using features or
64 drivers that are currently considered to be in the alpha-test phase.
65
Linus Torvalds1da177e2005-04-16 15:20:36 -070066config BROKEN
67 bool
Linus Torvalds1da177e2005-04-16 15:20:36 -070068
69config BROKEN_ON_SMP
70 bool
71 depends on BROKEN || !SMP
72 default y
73
Linus Torvalds1da177e2005-04-16 15:20:36 -070074config INIT_ENV_ARG_LIMIT
75 int
Adrian Bunkdd673bc2006-06-30 01:55:51 -070076 default 32 if !UML
77 default 128 if UML
Linus Torvalds1da177e2005-04-16 15:20:36 -070078 help
Randy Dunlap34ad92c2005-10-30 15:01:46 -080079 Maximum of each of the number of arguments and environment
80 variables passed to init from the kernel command line.
Linus Torvalds1da177e2005-04-16 15:20:36 -070081
Linus Torvalds1da177e2005-04-16 15:20:36 -070082
Roland McGrath84336462009-12-21 16:24:06 -080083config CROSS_COMPILE
84 string "Cross-compiler tool prefix"
85 help
86 Same as running 'make CROSS_COMPILE=prefix-' but stored for
87 default make runs in this kernel build directory. You don't
88 need to set this unless you want the configured kernel build
89 directory to select the cross-compiler automatically.
90
Linus Torvalds1da177e2005-04-16 15:20:36 -070091config LOCALVERSION
92 string "Local version - append to kernel release"
93 help
94 Append an extra string to the end of your kernel version.
95 This will show up when you type uname, for example.
96 The string you set here will be appended after the contents of
97 any files with a filename matching localversion* in your
98 object and source tree, in that order. Your total string can
99 be a maximum of 64 characters.
100
Ryan Andersonaaebf432005-07-31 04:57:49 -0400101config LOCALVERSION_AUTO
102 bool "Automatically append version information to the version string"
103 default y
104 help
105 This will try to automatically determine if the current tree is a
Robert P. J. Day6e5a5422007-05-01 23:08:11 +0200106 release tree by looking for git tags that belong to the current
107 top of tree revision.
Ryan Andersonaaebf432005-07-31 04:57:49 -0400108
109 A string of the format -gxxxxxxxx will be added to the localversion
Robert P. J. Day6e5a5422007-05-01 23:08:11 +0200110 if a git-based tree is found. The string generated by this will be
Ryan Andersonaaebf432005-07-31 04:57:49 -0400111 appended after any matching localversion* files, and after the value
Robert P. J. Day6e5a5422007-05-01 23:08:11 +0200112 set in CONFIG_LOCALVERSION.
Ryan Andersonaaebf432005-07-31 04:57:49 -0400113
Robert P. J. Day6e5a5422007-05-01 23:08:11 +0200114 (The actual string used here is the first eight characters produced
115 by running the command:
116
117 $ git rev-parse --verify HEAD
118
119 which is done within the script "scripts/setlocalversion".)
Ryan Andersonaaebf432005-07-31 04:57:49 -0400120
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800121config HAVE_KERNEL_GZIP
122 bool
123
124config HAVE_KERNEL_BZIP2
125 bool
126
127config HAVE_KERNEL_LZMA
128 bool
129
Lasse Collin3ebe1242011-01-12 17:01:23 -0800130config HAVE_KERNEL_XZ
131 bool
132
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800133config HAVE_KERNEL_LZO
134 bool
135
Alain Knaff30d65db2009-01-04 22:46:17 +0100136choice
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800137 prompt "Kernel compression mode"
138 default KERNEL_GZIP
Lasse Collin3ebe1242011-01-12 17:01:23 -0800139 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800140 help
Alain Knaff30d65db2009-01-04 22:46:17 +0100141 The linux kernel is a kind of self-extracting executable.
142 Several compression algorithms are available, which differ
143 in efficiency, compression and decompression speed.
144 Compression speed is only relevant when building a kernel.
145 Decompression speed is relevant at each boot.
146
147 If you have any problems with bzip2 or lzma compressed
148 kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older
149 version of this functionality (bzip2 only), for 2.4, was
150 supplied by Christian Ludwig)
151
152 High compression options are mostly useful for users, who
153 are low on disk space (embedded systems), but for whom ram
154 size matters less.
155
156 If in doubt, select 'gzip'
157
158config KERNEL_GZIP
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800159 bool "Gzip"
160 depends on HAVE_KERNEL_GZIP
161 help
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800162 The old and tried gzip compression. It provides a good balance
163 between compression ratio and decompression speed.
Alain Knaff30d65db2009-01-04 22:46:17 +0100164
165config KERNEL_BZIP2
166 bool "Bzip2"
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800167 depends on HAVE_KERNEL_BZIP2
Alain Knaff30d65db2009-01-04 22:46:17 +0100168 help
169 Its compression ratio and speed is intermediate.
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700170 Decompression speed is slowest among the choices. The kernel
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800171 size is about 10% smaller with bzip2, in comparison to gzip.
172 Bzip2 uses a large amount of memory. For modern kernels you
173 will need at least 8MB RAM or more for booting.
Alain Knaff30d65db2009-01-04 22:46:17 +0100174
175config KERNEL_LZMA
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800176 bool "LZMA"
177 depends on HAVE_KERNEL_LZMA
178 help
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700179 This compression algorithm's ratio is best. Decompression speed
180 is between gzip and bzip2. Compression is slowest.
181 The kernel size is about 33% smaller with LZMA in comparison to gzip.
Alain Knaff30d65db2009-01-04 22:46:17 +0100182
Lasse Collin3ebe1242011-01-12 17:01:23 -0800183config KERNEL_XZ
184 bool "XZ"
185 depends on HAVE_KERNEL_XZ
186 help
187 XZ uses the LZMA2 algorithm and instruction set specific
188 BCJ filters which can improve compression ratio of executable
189 code. The size of the kernel is about 30% smaller with XZ in
190 comparison to gzip. On architectures for which there is a BCJ
191 filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
192 will create a few percent smaller kernel than plain LZMA.
193
194 The speed is about the same as with LZMA: The decompression
195 speed of XZ is better than that of bzip2 but worse than gzip
196 and LZO. Compression is slow.
197
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800198config KERNEL_LZO
199 bool "LZO"
200 depends on HAVE_KERNEL_LZO
201 help
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700202 Its compression ratio is the poorest among the choices. The kernel
Stephan Sperber681b3042010-07-14 11:23:08 +0200203 size is about 10% bigger than gzip; however its speed
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800204 (both compression and decompression) is the fastest.
205
Alain Knaff30d65db2009-01-04 22:46:17 +0100206endchoice
207
Josh Triplettbd5dc172011-06-15 15:08:28 -0700208config DEFAULT_HOSTNAME
209 string "Default hostname"
210 default "(none)"
211 help
212 This option determines the default system hostname before userspace
213 calls sethostname(2). The kernel traditionally uses "(none)" here,
214 but you may wish to use a different default here to make a minimal
215 system more usable with less configuration.
216
Linus Torvalds1da177e2005-04-16 15:20:36 -0700217config SWAP
218 bool "Support for paging of anonymous memory (swap)"
David Howells93614012006-09-30 20:45:40 +0200219 depends on MMU && BLOCK
Linus Torvalds1da177e2005-04-16 15:20:36 -0700220 default y
221 help
222 This option allows you to choose whether you want to have support
Jesper Juhl92c35042006-01-15 02:40:08 +0100223 for so called swap devices or swap files in your kernel that are
Linus Torvalds1da177e2005-04-16 15:20:36 -0700224 used to provide more virtual memory than the actual RAM present
225 in your computer. If unsure say Y.
226
227config SYSVIPC
228 bool "System V IPC"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700229 ---help---
230 Inter Process Communication is a suite of library functions and
231 system calls which let processes (running programs) synchronize and
232 exchange information. It is generally considered to be a good thing,
233 and some programs won't run unless you say Y here. In particular, if
234 you want to run the DOS emulator dosemu under Linux (read the
235 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
236 you'll need to say Y here.
237
238 You can find documentation about IPC with "info ipc" and also in
239 section 6.4 of the Linux Programmer's Guide, available from
240 <http://www.tldp.org/guides.html>.
241
Eric W. Biedermana5494dc2007-02-14 00:34:06 -0800242config SYSVIPC_SYSCTL
243 bool
244 depends on SYSVIPC
245 depends on SYSCTL
246 default y
247
Linus Torvalds1da177e2005-04-16 15:20:36 -0700248config POSIX_MQUEUE
249 bool "POSIX Message Queues"
250 depends on NET && EXPERIMENTAL
251 ---help---
252 POSIX variant of message queues is a part of IPC. In POSIX message
253 queues every message has a priority which decides about succession
254 of receiving it by a process. If you want to compile and run
255 programs written e.g. for Solaris with use of its POSIX message
Robert P. J. Dayb0e37652007-05-09 07:25:13 +0200256 queues (functions mq_*) say Y here.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700257
258 POSIX message queues are visible as a filesystem called 'mqueue'
259 and can be mounted somewhere if you want to do filesystem
260 operations on message queues.
261
262 If unsure, say Y.
263
Serge E. Hallynbdc8e5f2009-04-06 19:01:11 -0700264config POSIX_MQUEUE_SYSCTL
265 bool
266 depends on POSIX_MQUEUE
267 depends on SYSCTL
268 default y
269
Linus Torvalds1da177e2005-04-16 15:20:36 -0700270config BSD_PROCESS_ACCT
271 bool "BSD Process Accounting"
272 help
273 If you say Y here, a user level program will be able to instruct the
274 kernel (via a special system call) to write process accounting
275 information to a file: whenever a process exits, information about
276 that process will be appended to the file by the kernel. The
277 information includes things such as creation time, owning user,
278 command name, memory usage, controlling terminal etc. (the complete
279 list is in the struct acct in <file:include/linux/acct.h>). It is
280 up to the user level program to do useful things with this
281 information. This is generally a good idea, so say Y.
282
283config BSD_PROCESS_ACCT_V3
284 bool "BSD Process Accounting version 3 file format"
285 depends on BSD_PROCESS_ACCT
286 default n
287 help
288 If you say Y here, the process accounting information is written
289 in a new file format that also logs the process IDs of each
290 process and it's parent. Note that this file format is incompatible
291 with previous v0/v1/v2 file formats, so you will need updated tools
292 for processing it. A preliminary version of these tools is available
S.Çağlar Onur37a4c942008-06-18 11:45:13 +0300293 at <http://www.gnu.org/software/acct/>.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700294
Aneesh Kumar K.V990d6c22011-01-29 18:43:26 +0530295config FHANDLE
296 bool "open by fhandle syscalls"
297 select EXPORTFS
298 help
299 If you say Y here, a user level program will be able to map
300 file names to handle and then later use the handle for
301 different file system operations. This is useful in implementing
302 userspace file servers, which now track files using handles instead
303 of names. The handle would remain the same even if file names
304 get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
305 syscalls.
306
Shailabh Nagarc7572492006-07-14 00:24:40 -0700307config TASKSTATS
308 bool "Export task/process statistics through netlink (EXPERIMENTAL)"
309 depends on NET
310 default n
311 help
312 Export selected statistics for tasks/processes through the
313 generic netlink interface. Unlike BSD process accounting, the
314 statistics are available during the lifetime of tasks/processes as
315 responses to commands. Like BSD accounting, they are sent to user
316 space on task exit.
317
318 Say N if unsure.
319
Shailabh Nagarca74e922006-07-14 00:24:36 -0700320config TASK_DELAY_ACCT
321 bool "Enable per-task delay accounting (EXPERIMENTAL)"
Shailabh Nagar6f449932006-07-14 00:24:41 -0700322 depends on TASKSTATS
Shailabh Nagarca74e922006-07-14 00:24:36 -0700323 help
324 Collect information on time spent by a task waiting for system
325 resources like cpu, synchronous block I/O completion and swapping
326 in pages. Such statistics can help in setting a task's priorities
327 relative to other tasks for cpu, io, rss limits etc.
328
329 Say N if unsure.
330
Alexey Dobriyan18f705f2007-02-10 01:46:44 -0800331config TASK_XACCT
332 bool "Enable extended accounting over taskstats (EXPERIMENTAL)"
333 depends on TASKSTATS
334 help
335 Collect extended task accounting data and send the data
336 to userland for processing over the taskstats interface.
337
338 Say N if unsure.
339
340config TASK_IO_ACCOUNTING
341 bool "Enable per-task storage I/O accounting (EXPERIMENTAL)"
342 depends on TASK_XACCT
343 help
344 Collect information on the number of bytes of storage I/O which this
345 task has caused.
346
347 Say N if unsure.
348
Linus Torvalds1da177e2005-04-16 15:20:36 -0700349config AUDIT
350 bool "Auditing support"
Chris Wright804a6a492005-05-11 10:52:45 +0100351 depends on NET
Linus Torvalds1da177e2005-04-16 15:20:36 -0700352 help
353 Enable auditing infrastructure that can be used with another
354 kernel subsystem, such as SELinux (which requires this for
355 logging of avc messages output). Does not do system-call
356 auditing without CONFIG_AUDITSYSCALL.
357
358config AUDITSYSCALL
359 bool "Enable system-call auditing support"
Will Deacon8f827a12012-07-06 15:48:16 +0100360 depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || (ARM && AEABI && !OABI_COMPAT))
Linus Torvalds1da177e2005-04-16 15:20:36 -0700361 default y if SECURITY_SELINUX
362 help
363 Enable low-overhead system-call auditing infrastructure that
364 can be used independently or with another kernel subsystem,
Eric Paris67640b62009-12-17 20:12:06 -0500365 such as SELinux.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700366
Eric Paris939a67f2009-12-17 20:12:06 -0500367config AUDIT_WATCH
368 def_bool y
369 depends on AUDITSYSCALL
370 select FSNOTIFY
Linus Torvalds1da177e2005-04-16 15:20:36 -0700371
Al Viro74c3cbe2007-07-22 08:04:18 -0400372config AUDIT_TREE
373 def_bool y
Eric Paris63c882a2009-05-21 17:02:01 -0400374 depends on AUDITSYSCALL
Eric Paris28a3a7e2009-12-17 20:12:05 -0500375 select FSNOTIFY
Al Viro74c3cbe2007-07-22 08:04:18 -0400376
Eric Paris633b4542012-01-03 14:23:08 -0500377config AUDIT_LOGINUID_IMMUTABLE
378 bool "Make audit loginuid immutable"
379 depends on AUDIT
380 help
Linus Torvaldsf429ee32012-01-17 16:06:51 -0800381 The config option toggles if a task setting its loginuid requires
Eric Paris633b4542012-01-03 14:23:08 -0500382 CAP_SYS_AUDITCONTROL or if that task should require no special permissions
383 but should instead only allow setting its loginuid if it was never
384 previously set. On systems which use systemd or a similar central
385 process to restart login services this should be set to true. On older
386 systems in which an admin would typically have to directly stop and
387 start processes this should be set to false. Setting this to true allows
388 one to drop potentially dangerous capabilites from the login tasks,
389 but may not be backwards compatible with older init systems.
390
Thomas Gleixnerd9817eb2010-09-27 12:45:59 +0000391source "kernel/irq/Kconfig"
Thomas Gleixner764e0da2012-05-21 23:16:18 +0200392source "kernel/time/Kconfig"
Thomas Gleixnerd9817eb2010-09-27 12:45:59 +0000393
Mike Travisc903ff82009-01-15 12:28:29 -0800394menu "RCU Subsystem"
395
396choice
397 prompt "RCU Implementation"
Paul E. McKenney31c9a242009-04-02 21:06:25 -0700398 default TREE_RCU
Mike Travisc903ff82009-01-15 12:28:29 -0800399
Mike Travisc903ff82009-01-15 12:28:29 -0800400config TREE_RCU
401 bool "Tree-based hierarchical RCU"
Paul E. McKenney687d7a92010-07-21 06:52:40 -0700402 depends on !PREEMPT && SMP
Mike Travisc903ff82009-01-15 12:28:29 -0800403 help
404 This option selects the RCU implementation that is
405 designed for very large SMP system with hundreds or
Paul E. McKenneyc17ef452009-06-23 17:12:47 -0700406 thousands of CPUs. It also scales down nicely to
407 smaller systems.
Mike Travisc903ff82009-01-15 12:28:29 -0800408
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700409config TREE_PREEMPT_RCU
Paul E. McKenneya57eb942010-06-29 16:49:16 -0700410 bool "Preemptible tree-based hierarchical RCU"
Paul E. McKenney8008e122011-06-08 16:31:33 -0700411 depends on PREEMPT && SMP
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700412 help
413 This option selects the RCU implementation that is
414 designed for very large SMP systems with hundreds or
415 thousands of CPUs, but for which real-time response
Paul E. McKenneybbe3eae2009-09-13 09:15:08 -0700416 is also required. It also scales down nicely to
417 smaller systems.
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700418
Paul E. McKenney9b1d82f2009-10-25 19:03:50 -0700419config TINY_RCU
420 bool "UP-only small-memory-footprint RCU"
Paul E. McKenney8008e122011-06-08 16:31:33 -0700421 depends on !PREEMPT && !SMP
Paul E. McKenney9b1d82f2009-10-25 19:03:50 -0700422 help
423 This option selects the RCU implementation that is
424 designed for UP systems from which real-time response
425 is not required. This option greatly reduces the
426 memory footprint of RCU.
427
Paul E. McKenneya57eb942010-06-29 16:49:16 -0700428config TINY_PREEMPT_RCU
429 bool "Preemptible UP-only small-memory-footprint RCU"
Paul E. McKenney8008e122011-06-08 16:31:33 -0700430 depends on PREEMPT && !SMP
Paul E. McKenneya57eb942010-06-29 16:49:16 -0700431 help
432 This option selects the RCU implementation that is designed
433 for real-time UP systems. This option greatly reduces the
434 memory footprint of RCU.
435
Mike Travisc903ff82009-01-15 12:28:29 -0800436endchoice
437
Paul E. McKenneya57eb942010-06-29 16:49:16 -0700438config PREEMPT_RCU
439 def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU )
440 help
441 This option enables preemptible-RCU code that is common between
442 the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations.
443
Frederic Weisbecker2b1d5022012-07-11 20:26:30 +0200444config RCU_USER_QS
445 bool "Consider userspace as in RCU extended quiescent state"
446 depends on HAVE_RCU_USER_QS && SMP
447 help
448 This option sets hooks on kernel / userspace boundaries and
449 puts RCU in extended quiescent state when the CPU runs in
450 userspace. It means that when a CPU runs in userspace, it is
451 excluded from the global RCU state machine and thus doesn't
452 to keep the timer tick on for RCU.
453
Frederic Weisbeckerd6771242012-10-11 01:48:28 +0200454 Unless you want to hack and help the development of the full
455 tickless feature, you shouldn't enable this option. It adds
456 unnecessary overhead.
457
458 If unsure say N
459
Frederic Weisbecker1fd2b442012-07-11 20:26:40 +0200460config RCU_USER_QS_FORCE
461 bool "Force userspace extended QS by default"
462 depends on RCU_USER_QS
463 help
464 Set the hooks in user/kernel boundaries by default in order to
465 test this feature that treats userspace as an extended quiescent
466 state until we have a real user like a full adaptive nohz option.
467
Frederic Weisbeckerd6771242012-10-11 01:48:28 +0200468 Unless you want to hack and help the development of the full
469 tickless feature, you shouldn't enable this option. It adds
470 unnecessary overhead.
471
472 If unsure say N
473
Mike Travisc903ff82009-01-15 12:28:29 -0800474config RCU_FANOUT
475 int "Tree-based hierarchical RCU fanout value"
476 range 2 64 if 64BIT
477 range 2 32 if !64BIT
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700478 depends on TREE_RCU || TREE_PREEMPT_RCU
Mike Travisc903ff82009-01-15 12:28:29 -0800479 default 64 if 64BIT
480 default 32 if !64BIT
481 help
482 This option controls the fanout of hierarchical implementations
483 of RCU, allowing RCU to work efficiently on machines with
Paul E. McKenney4d87ffa2010-08-04 17:31:12 -0700484 large numbers of CPUs. This value must be at least the fourth
485 root of NR_CPUS, which allows NR_CPUS to be insanely large.
486 The default value of RCU_FANOUT should be used for production
487 systems, but if you are stress-testing the RCU implementation
488 itself, small RCU_FANOUT values allow you to test large-system
489 code paths on small(er) systems.
Mike Travisc903ff82009-01-15 12:28:29 -0800490
491 Select a specific number if testing RCU itself.
492 Take the default if unsure.
493
Paul E. McKenney8932a632012-04-19 12:20:14 -0700494config RCU_FANOUT_LEAF
495 int "Tree-based hierarchical RCU leaf-level fanout value"
496 range 2 RCU_FANOUT if 64BIT
497 range 2 RCU_FANOUT if !64BIT
498 depends on TREE_RCU || TREE_PREEMPT_RCU
499 default 16
500 help
501 This option controls the leaf-level fanout of hierarchical
502 implementations of RCU, and allows trading off cache misses
503 against lock contention. Systems that synchronize their
504 scheduling-clock interrupts for energy-efficiency reasons will
505 want the default because the smaller leaf-level fanout keeps
506 lock contention levels acceptably low. Very large systems
507 (hundreds or thousands of CPUs) will instead want to set this
508 value to the maximum value possible in order to reduce the
509 number of cache misses incurred during RCU's grace-period
510 initialization. These systems tend to run CPU-bound, and thus
511 are not helped by synchronized interrupts, and thus tend to
512 skew them, which reduces lock contention enough that large
513 leaf-level fanouts work well.
514
515 Select a specific number if testing RCU itself.
516
517 Select the maximum permissible value for large systems.
518
519 Take the default if unsure.
520
Mike Travisc903ff82009-01-15 12:28:29 -0800521config RCU_FANOUT_EXACT
522 bool "Disable tree-based hierarchical RCU auto-balancing"
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700523 depends on TREE_RCU || TREE_PREEMPT_RCU
Mike Travisc903ff82009-01-15 12:28:29 -0800524 default n
525 help
526 This option forces use of the exact RCU_FANOUT value specified,
527 regardless of imbalances in the hierarchy. This is useful for
528 testing RCU itself, and might one day be useful on systems with
529 strong NUMA behavior.
530
531 Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
532
533 Say N if unsure.
534
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800535config RCU_FAST_NO_HZ
536 bool "Accelerate last non-dyntick-idle CPU's grace periods"
Paul E. McKenneyb807fbf2011-11-03 14:56:12 -0700537 depends on NO_HZ && SMP
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800538 default n
539 help
540 This option causes RCU to attempt to accelerate grace periods
Paul E. McKenneyb807fbf2011-11-03 14:56:12 -0700541 in order to allow CPUs to enter dynticks-idle state more
542 quickly. On the other hand, this option increases the overhead
543 of the dynticks-idle checking, particularly on systems with
544 large numbers of CPUs.
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800545
546 Say Y if energy efficiency is critically important, particularly
547 if you have relatively few CPUs.
548
549 Say N if you are unsure.
550
Mike Travisc903ff82009-01-15 12:28:29 -0800551config TREE_RCU_TRACE
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700552 def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
Mike Travisc903ff82009-01-15 12:28:29 -0800553 select DEBUG_FS
554 help
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700555 This option provides tracing for the TREE_RCU and
556 TREE_PREEMPT_RCU implementations, permitting Makefile to
557 trivially select kernel/rcutree_trace.c.
Mike Travisc903ff82009-01-15 12:28:29 -0800558
Paul E. McKenney24278d12010-09-27 17:25:23 -0700559config RCU_BOOST
560 bool "Enable RCU priority boosting"
Paul E. McKenney27f4d282011-02-07 12:47:15 -0800561 depends on RT_MUTEXES && PREEMPT_RCU
Paul E. McKenney24278d12010-09-27 17:25:23 -0700562 default n
563 help
564 This option boosts the priority of preempted RCU readers that
565 block the current preemptible RCU grace period for too long.
566 This option also prevents heavy loads from blocking RCU
567 callback invocation for all flavors of RCU.
568
569 Say Y here if you are working with real-time apps or heavy loads
570 Say N here if you are unsure.
571
572config RCU_BOOST_PRIO
573 int "Real-time priority to boost RCU readers to"
574 range 1 99
575 depends on RCU_BOOST
576 default 1
577 help
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700578 This option specifies the real-time priority to which long-term
579 preempted RCU readers are to be boosted. If you are working
580 with a real-time application that has one or more CPU-bound
581 threads running at a real-time priority level, you should set
582 RCU_BOOST_PRIO to a priority higher then the highest-priority
583 real-time CPU-bound thread. The default RCU_BOOST_PRIO value
584 of 1 is appropriate in the common case, which is real-time
585 applications that do not have any CPU-bound threads.
586
587 Some real-time applications might not have a single real-time
588 thread that saturates a given CPU, but instead might have
589 multiple real-time threads that, taken together, fully utilize
590 that CPU. In this case, you should set RCU_BOOST_PRIO to
591 a priority higher than the lowest-priority thread that is
592 conspiring to prevent the CPU from running any non-real-time
593 tasks. For example, if one thread at priority 10 and another
594 thread at priority 5 are between themselves fully consuming
595 the CPU time on a given CPU, then RCU_BOOST_PRIO should be
596 set to priority 6 or higher.
Paul E. McKenney24278d12010-09-27 17:25:23 -0700597
598 Specify the real-time priority, or take the default if unsure.
599
600config RCU_BOOST_DELAY
601 int "Milliseconds to delay boosting after RCU grace-period start"
602 range 0 3000
603 depends on RCU_BOOST
604 default 500
605 help
606 This option specifies the time to wait after the beginning of
607 a given grace period before priority-boosting preempted RCU
608 readers blocking that grace period. Note that any RCU reader
609 blocking an expedited RCU grace period is boosted immediately.
610
611 Accept the default if unsure.
612
Mike Travisc903ff82009-01-15 12:28:29 -0800613endmenu # "RCU Subsystem"
614
Linus Torvalds1da177e2005-04-16 15:20:36 -0700615config IKCONFIG
Ross Birof2443ab2006-09-30 23:27:25 -0700616 tristate "Kernel .config support"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700617 ---help---
618 This option enables the complete Linux kernel ".config" file
619 contents to be saved in the kernel. It provides documentation
620 of which kernel options are used in a running kernel or in an
621 on-disk kernel. This information can be extracted from the kernel
622 image file with the script scripts/extract-ikconfig and used as
623 input to rebuild the current kernel or to build another kernel.
624 It can also be extracted from a running kernel by reading
625 /proc/config.gz if enabled (below).
626
627config IKCONFIG_PROC
628 bool "Enable access to .config through /proc/config.gz"
629 depends on IKCONFIG && PROC_FS
630 ---help---
631 This option enables access to the kernel configuration file
632 through /proc/config.gz.
633
Alistair John Strachan794543a2007-05-08 00:31:15 -0700634config LOG_BUF_SHIFT
635 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
636 range 12 21
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700637 default 17
Alistair John Strachan794543a2007-05-08 00:31:15 -0700638 help
639 Select kernel log buffer size as a power of 2.
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700640 Examples:
641 17 => 128 KB
642 16 => 64 KB
643 15 => 32 KB
644 14 => 16 KB
Alistair John Strachan794543a2007-05-08 00:31:15 -0700645 13 => 8 KB
646 12 => 4 KB
647
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800648#
649# Architectures with an unreliable sched_clock() should select this:
650#
651config HAVE_UNSTABLE_SCHED_CLOCK
652 bool
653
Li Zefan23964d22009-01-15 13:50:58 -0800654menuconfig CGROUPS
655 boolean "Control Group support"
Kirill A. Shutemov0dea1162010-03-10 15:22:20 -0800656 depends on EVENTFD
Paul Menageddbcc7e2007-10-18 23:39:30 -0700657 help
Li Zefan23964d22009-01-15 13:50:58 -0800658 This option adds support for grouping sets of processes together, for
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800659 use with process control subsystems such as Cpusets, CFS, memory
660 controls or device isolation.
661 See
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800662 - Documentation/scheduler/sched-design-CFS.txt (CFS)
Li Zefan45ce80f2009-01-15 13:50:59 -0800663 - Documentation/cgroups/ (features for grouping, isolation
664 and resource control)
Paul Menageddbcc7e2007-10-18 23:39:30 -0700665
666 Say N if unsure.
667
Li Zefan23964d22009-01-15 13:50:58 -0800668if CGROUPS
669
Paul Menage006cb992007-10-18 23:39:43 -0700670config CGROUP_DEBUG
671 bool "Example debug cgroup subsystem"
Paul Menage418d7d82008-04-29 01:00:05 -0700672 default n
Paul Menage006cb992007-10-18 23:39:43 -0700673 help
674 This option enables a simple cgroup subsystem that
675 exports useful debugging information about the cgroups
Li Zefan23964d22009-01-15 13:50:58 -0800676 framework.
Paul Menage006cb992007-10-18 23:39:43 -0700677
Li Zefan23964d22009-01-15 13:50:58 -0800678 Say N if unsure.
Paul Menage006cb992007-10-18 23:39:43 -0700679
Matt Helsleydc52ddc2008-10-18 20:27:21 -0700680config CGROUP_FREEZER
Li Zefan23964d22009-01-15 13:50:58 -0800681 bool "Freezer cgroup subsystem"
Li Zefan23964d22009-01-15 13:50:58 -0800682 help
683 Provides a way to freeze and unfreeze all tasks in a
Matt Helsleydc52ddc2008-10-18 20:27:21 -0700684 cgroup.
685
Serge E. Hallyn08ce5f12008-04-29 01:00:10 -0700686config CGROUP_DEVICE
687 bool "Device controller for cgroups"
Serge E. Hallyn08ce5f12008-04-29 01:00:10 -0700688 help
689 Provides a cgroup implementing whitelists for devices which
690 a process in the cgroup can mknod or open.
691
Linus Torvalds1da177e2005-04-16 15:20:36 -0700692config CPUSETS
693 bool "Cpuset support"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700694 help
Randy Dunlapd9fd8a62005-07-27 11:45:11 -0700695 This option will let you create and manage CPUSETs which
Linus Torvalds1da177e2005-04-16 15:20:36 -0700696 allow dynamically partitioning a system into sets of CPUs and
697 Memory Nodes and assigning tasks to run only within those sets.
698 This is primarily useful on large SMP or NUMA systems.
699
700 Say N if unsure.
701
Li Zefan23964d22009-01-15 13:50:58 -0800702config PROC_PID_CPUSET
703 bool "Include legacy /proc/<pid>/cpuset file"
704 depends on CPUSETS
705 default y
706
Srivatsa Vaddagirid842de82007-12-02 20:04:49 +0100707config CGROUP_CPUACCT
708 bool "Simple CPU accounting cgroup subsystem"
Srivatsa Vaddagirid842de82007-12-02 20:04:49 +0100709 help
710 Provides a simple Resource Controller for monitoring the
Li Zefan23964d22009-01-15 13:50:58 -0800711 total CPU consumed by the tasks in a cgroup.
Srivatsa Vaddagirid842de82007-12-02 20:04:49 +0100712
Pavel Emelianove552b662008-02-07 00:13:49 -0800713config RESOURCE_COUNTERS
714 bool "Resource counters"
715 help
716 This option enables controller independent resource accounting
Li Zefan23964d22009-01-15 13:50:58 -0800717 infrastructure that works with cgroups.
Pavel Emelianove552b662008-02-07 00:13:49 -0800718
Andrew Mortonc255a452012-07-31 16:43:02 -0700719config MEMCG
Balbir Singh00f0b822008-03-04 14:28:39 -0800720 bool "Memory Resource Controller for Control Groups"
Daniel Lezcano79ae9c22010-10-27 15:34:39 -0700721 depends on RESOURCE_COUNTERS
Balbir Singhcf475ad2008-04-29 01:00:16 -0700722 select MM_OWNER
Balbir Singh00f0b822008-03-04 14:28:39 -0800723 help
KAMEZAWA Hiroyuki84ad6d72008-10-29 14:01:06 -0700724 Provides a memory resource controller that manages both anonymous
Thadeu Lima de Souza Cascardo21acb9c2009-02-04 10:12:08 +0100725 memory and page cache. (See Documentation/cgroups/memory.txt)
Balbir Singh00f0b822008-03-04 14:28:39 -0800726
727 Note that setting this option increases fixed memory overhead
KAMEZAWA Hiroyuki84ad6d72008-10-29 14:01:06 -0700728 associated with each page of memory in the system. By this,
729 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
730 usage tracking struct at boot. Total amount of this is printed out
731 at boot.
Balbir Singh00f0b822008-03-04 14:28:39 -0800732
733 Only enable when you're ok with these trade offs and really
KAMEZAWA Hiroyuki84ad6d72008-10-29 14:01:06 -0700734 sure you need the memory resource controller. Even when you enable
735 this, you can set "cgroup_disable=memory" at your boot option to
736 disable memory resource controller and you can avoid overheads.
Li Zefanc9d54092009-01-07 18:07:35 -0800737 (and lose benefits of memory resource controller)
Balbir Singh00f0b822008-03-04 14:28:39 -0800738
Balbir Singhcf475ad2008-04-29 01:00:16 -0700739 This config option also selects MM_OWNER config option, which
740 could in turn add some fork/exit overhead.
741
Andrew Mortonc255a452012-07-31 16:43:02 -0700742config MEMCG_SWAP
KAMEZAWA Hiroyuki65e0e812010-08-10 18:02:56 -0700743 bool "Memory Resource Controller Swap Extension"
Andrew Mortonc255a452012-07-31 16:43:02 -0700744 depends on MEMCG && SWAP
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -0800745 help
746 Add swap management feature to memory resource controller. When you
747 enable this, you can limit mem+swap usage per cgroup. In other words,
748 when you disable this, memory resource controller has no cares to
749 usage of swap...a process can exhaust all of the swap. This extension
750 is useful when you want to avoid exhaustion swap but this itself
751 adds more overheads and consumes memory for remembering information.
752 Especially if you use 32bit system or small memory system, please
753 be careful about enabling this. When memory resource controller
754 is disabled by boot option, this will be automatically disabled and
755 there will be no overhead from this. Even when you set this config=y,
WANG Cong00a66d22011-07-25 17:12:12 -0700756 if boot option "swapaccount=0" is set, swap will not be accounted.
KAMEZAWA Hiroyuki627991a2009-04-02 16:57:47 -0700757 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
758 size is 4096bytes, 512k per 1Gbytes of swap.
Andrew Mortonc255a452012-07-31 16:43:02 -0700759config MEMCG_SWAP_ENABLED
Michal Hockoa42c3902010-11-24 12:57:08 -0800760 bool "Memory Resource Controller Swap Extension enabled by default"
Andrew Mortonc255a452012-07-31 16:43:02 -0700761 depends on MEMCG_SWAP
Michal Hockoa42c3902010-11-24 12:57:08 -0800762 default y
763 help
764 Memory Resource Controller Swap Extension comes with its price in
765 a bigger memory consumption. General purpose distribution kernels
Jim Cromie43d547f2010-12-17 14:32:36 -0700766 which want to enable the feature but keep it disabled by default
Michal Hockoa42c3902010-11-24 12:57:08 -0800767 and let the user enable it by swapaccount boot command line
768 parameter should have this option unselected.
769 For those who want to have the feature enabled by default should
770 select this option (if, for some reason, they need to disable it
WANG Cong00a66d22011-07-25 17:12:12 -0700771 then swapaccount=0 does the trick).
Andrew Mortonc255a452012-07-31 16:43:02 -0700772config MEMCG_KMEM
Glauber Costae5671df2011-12-11 21:47:01 +0000773 bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)"
Andrew Mortonc255a452012-07-31 16:43:02 -0700774 depends on MEMCG && EXPERIMENTAL
Glauber Costae5671df2011-12-11 21:47:01 +0000775 default n
776 help
777 The Kernel Memory extension for Memory Resource Controller can limit
778 the amount of memory used by kernel objects in the system. Those are
779 fundamentally different from the entities handled by the standard
780 Memory Controller, which are page-based, and can be swapped. Users of
781 the kmem extension can use it to guarantee that no group of processes
782 will ever exhaust kernel resources alone.
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -0800783
Aneesh Kumar K.V2bc64a22012-07-31 16:42:12 -0700784config CGROUP_HUGETLB
785 bool "HugeTLB Resource Controller for Control Groups"
786 depends on RESOURCE_COUNTERS && HUGETLB_PAGE && EXPERIMENTAL
787 default n
788 help
789 Provides a cgroup Resource Controller for HugeTLB pages.
790 When you enable this, you can put a per cgroup limit on HugeTLB usage.
791 The limit is enforced during page fault. Since HugeTLB doesn't
792 support page reclaim, enforcing the limit at page fault time implies
793 that, the application will get SIGBUS signal if it tries to access
794 HugeTLB pages beyond its limit. This requires the application to know
795 beforehand how much HugeTLB pages it would require for its use. The
796 control group is tracked in the third page lru pointer. This means
797 that we cannot use the controller with huge page less than 3 pages.
798
Stephane Eraniane5d13672011-02-14 11:20:01 +0200799config CGROUP_PERF
800 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
801 depends on PERF_EVENTS && CGROUPS
802 help
803 This option extends the per-cpu mode to restrict monitoring to
Li Zefan2d0f2522011-03-03 14:26:20 +0800804 threads which belong to the cgroup specified and run on the
Stephane Eraniane5d13672011-02-14 11:20:01 +0200805 designated cpu.
806
807 Say N if unsure.
808
Dhaval Giani7c941432010-01-20 13:26:18 +0100809menuconfig CGROUP_SCHED
810 bool "Group CPU scheduler"
Dhaval Giani7c941432010-01-20 13:26:18 +0100811 default n
812 help
813 This feature lets CPU scheduler recognize task groups and control CPU
814 bandwidth allocation to such task groups. It uses cgroups to group
815 tasks.
816
817if CGROUP_SCHED
818config FAIR_GROUP_SCHED
819 bool "Group scheduling for SCHED_OTHER"
820 depends on CGROUP_SCHED
821 default CGROUP_SCHED
822
Paul Turnerab84d312011-07-21 09:43:28 -0700823config CFS_BANDWIDTH
824 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
825 depends on EXPERIMENTAL
826 depends on FAIR_GROUP_SCHED
827 default n
828 help
829 This option allows users to define CPU bandwidth rates (limits) for
830 tasks running within the fair group scheduler. Groups with no limit
831 set are considered to be unconstrained and will run with no
832 restriction.
833 See tip/Documentation/scheduler/sched-bwc.txt for more information.
834
Dhaval Giani7c941432010-01-20 13:26:18 +0100835config RT_GROUP_SCHED
836 bool "Group scheduling for SCHED_RR/FIFO"
837 depends on EXPERIMENTAL
838 depends on CGROUP_SCHED
839 default n
840 help
841 This feature lets you explicitly allocate real CPU bandwidth
Li Zefan32bd7eb2010-03-24 13:17:19 +0800842 to task groups. If enabled, it will also make it impossible to
Dhaval Giani7c941432010-01-20 13:26:18 +0100843 schedule realtime tasks for non-root users until you allocate
844 realtime bandwidth for them.
845 See Documentation/scheduler/sched-rt-group.txt for more information.
846
847endif #CGROUP_SCHED
848
Vivek Goyalafc24d42010-04-26 19:27:56 +0200849config BLK_CGROUP
Tejun Heo32e380a2012-03-05 13:14:54 -0800850 bool "Block IO controller"
Daniel Lezcano79ae9c22010-10-27 15:34:39 -0700851 depends on BLOCK
Vivek Goyalafc24d42010-04-26 19:27:56 +0200852 default n
853 ---help---
854 Generic block IO controller cgroup interface. This is the common
855 cgroup interface which should be used by various IO controlling
856 policies.
857
858 Currently, CFQ IO scheduler uses it to recognize task groups and
859 control disk bandwidth allocation (proportional time slice allocation)
Vivek Goyale43473b2010-09-15 17:06:35 -0400860 to such task groups. It is also used by bio throttling logic in
861 block layer to implement upper limit in IO rates on a device.
Vivek Goyalafc24d42010-04-26 19:27:56 +0200862
863 This option only enables generic Block IO controller infrastructure.
Vivek Goyale43473b2010-09-15 17:06:35 -0400864 One needs to also enable actual IO controlling logic/policy. For
Michael Witten79e2e752011-01-16 21:43:10 +0000865 enabling proportional weight division of disk bandwidth in CFQ, set
866 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
Michael Wittenc5e05912011-01-17 00:08:41 +0000867 CONFIG_BLK_DEV_THROTTLING=y.
Vivek Goyalafc24d42010-04-26 19:27:56 +0200868
869 See Documentation/cgroups/blkio-controller.txt for more information.
870
871config DEBUG_BLK_CGROUP
872 bool "Enable Block IO controller debugging"
873 depends on BLK_CGROUP
874 default n
875 ---help---
876 Enable some debugging help. Currently it exports additional stat
877 files in a cgroup which can be useful for debugging.
878
Li Zefan23964d22009-01-15 13:50:58 -0800879endif # CGROUPS
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -0800880
Cyrill Gorcunov067bce12012-01-12 17:20:49 -0800881config CHECKPOINT_RESTORE
882 bool "Checkpoint/restore support" if EXPERT
883 default n
884 help
885 Enables additional kernel features in a sake of checkpoint/restore.
886 In particular it adds auxiliary prctl codes to setup process text,
887 data and heap segment sizes, and a few additional /proc filesystem
888 entries.
889
890 If unsure, say N here.
891
Daniel Lezcano8dd2a822010-10-27 15:34:38 -0700892menuconfig NAMESPACES
David Rientjes6a108a12011-01-20 14:44:16 -0800893 bool "Namespaces support" if EXPERT
894 default !EXPERT
Pavel Emelyanovc5289a62008-02-08 04:18:19 -0800895 help
896 Provides the way to make tasks work with different objects using
897 the same id. For example same IPC id may refer to different objects
898 or same user id or pid may refer to different tasks when used in
899 different namespaces.
900
Daniel Lezcano8dd2a822010-10-27 15:34:38 -0700901if NAMESPACES
902
Pavel Emelyanov58bfdd6d2008-02-08 04:18:21 -0800903config UTS_NS
904 bool "UTS namespace"
Daniel Lezcano17a6d442010-10-27 15:34:37 -0700905 default y
Pavel Emelyanov58bfdd6d2008-02-08 04:18:21 -0800906 help
907 In this namespace tasks see different info provided with the
908 uname() system call
909
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -0800910config IPC_NS
911 bool "IPC namespace"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -0700912 depends on (SYSVIPC || POSIX_MQUEUE)
Daniel Lezcano17a6d442010-10-27 15:34:37 -0700913 default y
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -0800914 help
915 In this namespace tasks work with IPC ids which correspond to
Serge E. Hallyn614b84c2009-04-06 19:01:08 -0700916 different IPC objects in different namespaces.
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -0800917
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -0800918config USER_NS
919 bool "User namespace (EXPERIMENTAL)"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -0700920 depends on EXPERIMENTAL
Eric W. Biedermane1c972b2012-04-21 04:09:01 -0700921 depends on UIDGID_CONVERTED
Eric W. Biederman5673a942011-11-17 10:23:55 -0800922 select UIDGID_STRICT_TYPE_CHECKS
Eric W. Biedermane1c972b2012-04-21 04:09:01 -0700923
Eric W. Biederman5673a942011-11-17 10:23:55 -0800924 default n
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -0800925 help
926 This allows containers, i.e. vservers, to use user namespaces
927 to provide different user info for different servers.
928 If unsure, say N.
929
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -0800930config PID_NS
Daniel Lezcano9bd38c22010-10-27 15:34:37 -0700931 bool "PID Namespaces"
Daniel Lezcano17a6d442010-10-27 15:34:37 -0700932 default y
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -0800933 help
Heikki Orsila12d2b8f2008-07-06 15:48:02 +0300934 Support process id namespaces. This allows having multiple
Matt LaPlante692105b2009-01-26 11:12:25 +0100935 processes with the same pid as long as they are in different
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -0800936 pid namespaces. This is a building block of containers.
937
Matt Helsleyd6eb6332009-01-26 12:25:55 -0800938config NET_NS
939 bool "Network namespace"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -0700940 depends on NET
Daniel Lezcano17a6d442010-10-27 15:34:37 -0700941 default y
Matt Helsleyd6eb6332009-01-26 12:25:55 -0800942 help
943 Allow user space to create what appear to be multiple instances
944 of the network stack.
945
Daniel Lezcano8dd2a822010-10-27 15:34:38 -0700946endif # NAMESPACES
947
Eric W. Biedermane1c972b2012-04-21 04:09:01 -0700948config UIDGID_CONVERTED
949 # True if all of the selected software conmponents are known
950 # to have uid_t and gid_t converted to kuid_t and kgid_t
951 # where appropriate and are otherwise safe to use with
952 # the user namespace.
953 bool
954 default y
955
956 # List of kernel pieces that need user namespace work
957 # Features
Eric W. Biedermane1c972b2012-04-21 04:09:01 -0700958 depends on SYSVIPC = n
959 depends on IMA = n
960 depends on EVM = n
961 depends on KEYS = n
962 depends on AUDIT = n
963 depends on AUDITSYSCALL = n
964 depends on TASKSTATS = n
965 depends on TRACING = n
966 depends on FS_POSIX_ACL = n
967 depends on QUOTA = n
968 depends on QUOTACTL = n
969 depends on DEBUG_CREDENTIALS = n
970 depends on BSD_PROCESS_ACCT = n
971 depends on DRM = n
972 depends on PROC_EVENTS = n
973
974 # Networking
975 depends on NET = n
976 depends on NET_9P = n
977 depends on IPX = n
978 depends on PHONET = n
979 depends on NET_CLS_FLOW = n
980 depends on NETFILTER_XT_MATCH_OWNER = n
981 depends on NETFILTER_XT_MATCH_RECENT = n
982 depends on NETFILTER_XT_TARGET_LOG = n
983 depends on NETFILTER_NETLINK_LOG = n
984 depends on INET = n
985 depends on IPV6 = n
986 depends on IP_SCTP = n
987 depends on AF_RXRPC = n
988 depends on LLC2 = n
989 depends on NET_KEY = n
990 depends on INET_DIAG = n
991 depends on DNS_RESOLVER = n
992 depends on AX25 = n
993 depends on ATALK = n
994
995 # Filesystems
996 depends on USB_DEVICEFS = n
997 depends on USB_GADGETFS = n
998 depends on USB_FUNCTIONFS = n
999 depends on DEVTMPFS = n
1000 depends on XENFS = n
1001
1002 depends on 9P_FS = n
1003 depends on ADFS_FS = n
1004 depends on AFFS_FS = n
1005 depends on AFS_FS = n
1006 depends on AUTOFS4_FS = n
1007 depends on BEFS_FS = n
1008 depends on BFS_FS = n
1009 depends on BTRFS_FS = n
1010 depends on CEPH_FS = n
1011 depends on CIFS = n
1012 depends on CODA_FS = n
1013 depends on CONFIGFS_FS = n
1014 depends on CRAMFS = n
1015 depends on DEBUG_FS = n
1016 depends on ECRYPT_FS = n
1017 depends on EFS_FS = n
1018 depends on EXOFS_FS = n
Eric W. Biedermane1c972b2012-04-21 04:09:01 -07001019 depends on FAT_FS = n
1020 depends on FUSE_FS = n
1021 depends on GFS2_FS = n
1022 depends on HFS_FS = n
1023 depends on HFSPLUS_FS = n
1024 depends on HPFS_FS = n
1025 depends on HUGETLBFS = n
1026 depends on ISO9660_FS = n
1027 depends on JFFS2_FS = n
1028 depends on JFS_FS = n
1029 depends on LOGFS = n
1030 depends on MINIX_FS = n
1031 depends on NCP_FS = n
1032 depends on NFSD = n
1033 depends on NFS_FS = n
1034 depends on NILFS2_FS = n
1035 depends on NTFS_FS = n
1036 depends on OCFS2_FS = n
1037 depends on OMFS_FS = n
Eric W. Biedermane1c972b2012-04-21 04:09:01 -07001038 depends on QNX4FS_FS = n
1039 depends on QNX6FS_FS = n
1040 depends on REISERFS_FS = n
1041 depends on SQUASHFS = n
Eric W. Biedermane1c972b2012-04-21 04:09:01 -07001042 depends on SYSV_FS = n
Eric W. Biedermane1c972b2012-04-21 04:09:01 -07001043 depends on UBIFS_FS = n
1044 depends on UDF_FS = n
1045 depends on UFS_FS = n
1046 depends on VXFS_FS = n
1047 depends on XFS_FS = n
1048
1049 depends on !UML || HOSTFS = n
1050
1051 # The rare drivers that won't build
1052 depends on AIRO = n
1053 depends on AIRO_CS = n
1054 depends on TUN = n
1055 depends on INFINIBAND_QIB = n
1056 depends on BLK_DEV_LOOP = n
1057 depends on ANDROID_BINDER_IPC = n
1058
1059 # Security modules
1060 depends on SECURITY_TOMOYO = n
1061 depends on SECURITY_APPARMOR = n
1062
Eric W. Biederman5673a942011-11-17 10:23:55 -08001063config UIDGID_STRICT_TYPE_CHECKS
1064 bool "Require conversions between uid/gids and their internal representation"
Eric W. Biedermane1c972b2012-04-21 04:09:01 -07001065 depends on UIDGID_CONVERTED
Eric W. Biederman5673a942011-11-17 10:23:55 -08001066 default n
1067 help
1068 While the nececessary conversions are being added to all subsystems this option allows
1069 the code to continue to build for unconverted subsystems.
1070
1071 Say Y here if you want the strict type checking enabled
1072
Mike Galbraith5091faa2010-11-30 14:18:03 +01001073config SCHED_AUTOGROUP
1074 bool "Automatic process group scheduling"
1075 select EVENTFD
1076 select CGROUPS
1077 select CGROUP_SCHED
1078 select FAIR_GROUP_SCHED
1079 help
1080 This option optimizes the scheduler for common desktop workloads by
1081 automatically creating and populating task groups. This separation
1082 of workloads isolates aggressive CPU burners (like build jobs) from
1083 desktop applications. Task group autogeneration is currently based
1084 upon task session.
1085
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001086config MM_OWNER
1087 bool
1088
1089config SYSFS_DEPRECATED
Ferenc Wagner5d6a4ea2011-01-10 19:04:22 +01001090 bool "Enable deprecated sysfs features to support old userspace tools"
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001091 depends on SYSFS
1092 default n
1093 help
1094 This option adds code that switches the layout of the "block" class
1095 devices, to not show up in /sys/class/block/, but only in
1096 /sys/block/.
1097
1098 This switch is only active when the sysfs.deprecated=1 boot option is
1099 passed or the SYSFS_DEPRECATED_V2 option is set.
1100
1101 This option allows new kernels to run on old distributions and tools,
1102 which might get confused by /sys/class/block/. Since 2007/2008 all
1103 major distributions and tools handle this just fine.
1104
1105 Recent distributions and userspace tools after 2009/2010 depend on
1106 the existence of /sys/class/block/, and will not work with this
1107 option enabled.
1108
1109 Only if you are using a new kernel on an old distribution, you might
1110 need to say Y here.
1111
1112config SYSFS_DEPRECATED_V2
Ferenc Wagner5d6a4ea2011-01-10 19:04:22 +01001113 bool "Enable deprecated sysfs features by default"
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001114 default n
1115 depends on SYSFS
1116 depends on SYSFS_DEPRECATED
1117 help
1118 Enable deprecated sysfs by default.
1119
1120 See the CONFIG_SYSFS_DEPRECATED option for more details about this
1121 option.
1122
1123 Only if you are using a new kernel on an old distribution, you might
1124 need to say Y here. Even then, odds are you would not need it
1125 enabled, you can always pass the boot option if absolutely necessary.
1126
1127config RELAY
1128 bool "Kernel->user space relay support (formerly relayfs)"
1129 help
1130 This option enables support for relay interface support in
1131 certain file systems (such as debugfs).
1132 It is designed to provide an efficient mechanism for tools and
1133 facilities to relay large amounts of data from kernel space to
1134 user space.
1135
1136 If unsure, say N.
1137
Dimitri Gorokhovikf9916332007-03-06 01:42:17 -08001138config BLK_DEV_INITRD
1139 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
1140 depends on BROKEN || !FRV
1141 help
1142 The initial RAM filesystem is a ramfs which is loaded by the
1143 boot loader (loadlin or lilo) and that is mounted as root
1144 before the normal boot procedure. It is typically used to
1145 load modules needed to mount the "real" root file system,
1146 etc. See <file:Documentation/initrd.txt> for details.
1147
1148 If RAM disk support (BLK_DEV_RAM) is also included, this
1149 also enables initial RAM disk (initrd) support and adds
1150 15 Kbytes (more on some other architectures) to the kernel size.
1151
1152 If unsure say Y.
1153
Jean-Paul Samanc33df4e2007-02-10 01:44:43 -08001154if BLK_DEV_INITRD
1155
Sam Ravnborgdbec4862005-08-10 20:44:50 +02001156source "usr/Kconfig"
1157
Jean-Paul Samanc33df4e2007-02-10 01:44:43 -08001158endif
1159
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001160config CC_OPTIMIZE_FOR_SIZE
Ingo Molnar96fffeb2008-04-28 01:39:43 +02001161 bool "Optimize for size"
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001162 help
1163 Enabling this option will pass "-Os" instead of "-O2" to gcc
1164 resulting in a smaller kernel.
1165
jkacur775a7222008-07-16 00:31:16 +02001166 If unsure, say Y.
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001167
Randy Dunlap08470622006-09-30 23:28:13 -07001168config SYSCTL
1169 bool
1170
Randy Dunlapb943c462009-03-10 12:55:46 -07001171config ANON_INODES
1172 bool
1173
David Rientjes6a108a12011-01-20 14:44:16 -08001174menuconfig EXPERT
1175 bool "Configure standard kernel features (expert users)"
Josh Triplettf505c552011-06-05 18:23:58 -07001176 # Unhide debug options, to make the on-by-default options visible
1177 select DEBUG_KERNEL
Linus Torvalds1da177e2005-04-16 15:20:36 -07001178 help
1179 This option allows certain base kernel options and settings
1180 to be disabled or tweaked. This is for specialized
1181 environments which can tolerate a "non-standard" kernel.
1182 Only use this if you really know what you are doing.
1183
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001184config UID16
David Rientjes6a108a12011-01-20 14:44:16 -08001185 bool "Enable 16-bit UID system calls" if EXPERT
David S. Miller09337f52008-04-26 03:17:12 -07001186 depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION)
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001187 default y
1188 help
1189 This enables the legacy 16-bit UID syscall wrappers.
1190
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001191config SYSCTL_SYSCALL
David Rientjes6a108a12011-01-20 14:44:16 -08001192 bool "Sysctl syscall support" if EXPERT
Eric W. Biederman26a70342009-11-05 05:26:41 -08001193 depends on PROC_SYSCTL
WANG Congc736de62011-11-02 13:39:25 -07001194 default n
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001195 select SYSCTL
1196 ---help---
Eric W. Biederman13bb7e32006-11-08 17:44:51 -08001197 sys_sysctl uses binary paths that have been found challenging
1198 to properly maintain and use. The interface in /proc/sys
1199 using paths with ascii names is now the primary path to this
1200 information.
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001201
Eric W. Biederman13bb7e32006-11-08 17:44:51 -08001202 Almost nothing using the binary sysctl interface so if you are
1203 trying to save some space it is probably safe to disable this,
1204 making your kernel marginally smaller.
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001205
WANG Congc736de62011-11-02 13:39:25 -07001206 If unsure say N here.
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001207
Linus Torvalds1da177e2005-04-16 15:20:36 -07001208config KALLSYMS
David Rientjes6a108a12011-01-20 14:44:16 -08001209 bool "Load all symbols for debugging/ksymoops" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001210 default y
1211 help
1212 Say Y here to let the kernel print out symbolic crash information and
1213 symbolic stack backtraces. This increases the size of the kernel
1214 somewhat, as all symbols have to be loaded into the kernel image.
1215
1216config KALLSYMS_ALL
1217 bool "Include all symbols in kallsyms"
1218 depends on DEBUG_KERNEL && KALLSYMS
1219 help
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001220 Normally kallsyms only contains the symbols of functions for nicer
1221 OOPS messages and backtraces (i.e., symbols from the text and inittext
1222 sections). This is sufficient for most cases. And only in very rare
1223 cases (e.g., when a debugger is used) all symbols are required (e.g.,
1224 names of variables from the data sections, etc).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001225
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001226 This option makes sure that all symbols are loaded into the kernel
1227 image (i.e., symbols from all sections) in cost of increased kernel
1228 size (depending on the kernel configuration, it may be 300KiB or
1229 something like this).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001230
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001231 Say N unless you really need all symbols.
Matt Mackalld59745c2005-05-01 08:59:02 -07001232
Greg Kroah-Hartman712f47c2005-11-16 11:27:07 -08001233config HOTPLUG
David Rientjes6a108a12011-01-20 14:44:16 -08001234 bool "Support for hot-pluggable devices" if EXPERT
Greg Kroah-Hartman712f47c2005-11-16 11:27:07 -08001235 default y
1236 help
1237 This option is provided for the case where no hotplug or uevent
1238 capabilities is wanted by the kernel. You should only consider
1239 disabling this option for embedded systems that do not use modules, a
1240 dynamic /dev tree, or dynamic device discovery. Just say Y.
1241
Matt Mackalld59745c2005-05-01 08:59:02 -07001242config PRINTK
1243 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001244 bool "Enable support for printk" if EXPERT
Matt Mackalld59745c2005-05-01 08:59:02 -07001245 help
1246 This option enables normal printk support. Removing it
1247 eliminates most of the message strings from the kernel image
1248 and makes the kernel more or less silent. As this makes it
1249 very difficult to diagnose system problems, saying N here is
1250 strongly discouraged.
1251
Matt Mackallc8538a72005-05-01 08:59:01 -07001252config BUG
David Rientjes6a108a12011-01-20 14:44:16 -08001253 bool "BUG() support" if EXPERT
Matt Mackallc8538a72005-05-01 08:59:01 -07001254 default y
1255 help
1256 Disabling this option eliminates support for BUG and WARN, reducing
1257 the size of your kernel image and potentially quietly ignoring
1258 numerous fatal conditions. You should only consider disabling this
1259 option for embedded systems with no facilities for reporting errors.
1260 Just say Y.
1261
Matt Mackall708e9a72006-01-08 01:05:25 -08001262config ELF_CORE
1263 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001264 bool "Enable ELF core dumps" if EXPERT
Matt Mackall708e9a72006-01-08 01:05:25 -08001265 help
1266 Enable support for generating core dumps. Disabling saves about 4k.
1267
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001268
Stas Sergeeve5e1d3c2008-05-07 12:39:56 +02001269config PCSPKR_PLATFORM
David Rientjes6a108a12011-01-20 14:44:16 -08001270 bool "Enable PC-Speaker support" if EXPERT
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001271 depends on HAVE_PCSPKR_PLATFORM
Ralf Baechle15f304b2011-06-01 19:04:59 +01001272 select I8253_LOCK
Stas Sergeeve5e1d3c2008-05-07 12:39:56 +02001273 default y
1274 help
1275 This option allows to disable the internal PC-Speaker
1276 support, saving some memory.
1277
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001278config HAVE_PCSPKR_PLATFORM
1279 bool
1280
Linus Torvalds1da177e2005-04-16 15:20:36 -07001281config BASE_FULL
1282 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001283 bool "Enable full-sized data structures for core" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001284 help
1285 Disabling this option reduces the size of miscellaneous core
1286 kernel data structures. This saves memory on small machines,
1287 but may reduce performance.
1288
1289config FUTEX
David Rientjes6a108a12011-01-20 14:44:16 -08001290 bool "Enable futex support" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001291 default y
Ingo Molnar23f78d4a2006-06-27 02:54:53 -07001292 select RT_MUTEXES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001293 help
1294 Disabling this option will cause the kernel to be built without
1295 support for "fast userspace mutexes". The resulting kernel may not
1296 run glibc-based applications correctly.
1297
1298config EPOLL
David Rientjes6a108a12011-01-20 14:44:16 -08001299 bool "Enable eventpoll support" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001300 default y
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001301 select ANON_INODES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001302 help
1303 Disabling this option will cause the kernel to be built without
1304 support for epoll family of system calls.
1305
Davide Libenzifba2afa2007-05-10 22:23:13 -07001306config SIGNALFD
David Rientjes6a108a12011-01-20 14:44:16 -08001307 bool "Enable signalfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001308 select ANON_INODES
Davide Libenzifba2afa2007-05-10 22:23:13 -07001309 default y
1310 help
1311 Enable the signalfd() system call that allows to receive signals
1312 on a file descriptor.
1313
1314 If unsure, say Y.
1315
Davide Libenzib215e282007-05-10 22:23:16 -07001316config TIMERFD
David Rientjes6a108a12011-01-20 14:44:16 -08001317 bool "Enable timerfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001318 select ANON_INODES
Davide Libenzib215e282007-05-10 22:23:16 -07001319 default y
1320 help
1321 Enable the timerfd() system call that allows to receive timer
1322 events on a file descriptor.
1323
1324 If unsure, say Y.
1325
Davide Libenzie1ad7462007-05-10 22:23:19 -07001326config EVENTFD
David Rientjes6a108a12011-01-20 14:44:16 -08001327 bool "Enable eventfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001328 select ANON_INODES
Davide Libenzie1ad7462007-05-10 22:23:19 -07001329 default y
1330 help
1331 Enable the eventfd() system call that allows to receive both
1332 kernel notification (ie. KAIO) or userspace notifications.
1333
1334 If unsure, say Y.
1335
Linus Torvalds1da177e2005-04-16 15:20:36 -07001336config SHMEM
David Rientjes6a108a12011-01-20 14:44:16 -08001337 bool "Use full shmem filesystem" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001338 default y
1339 depends on MMU
1340 help
1341 The shmem is an internal filesystem used to manage shared memory.
1342 It is backed by swap and manages resource limits. It is also exported
1343 to userspace as tmpfs if TMPFS is enabled. Disabling this
1344 option replaces shmem and tmpfs with the much simpler ramfs code,
1345 which may be appropriate on small systems without swap.
1346
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001347config AIO
David Rientjes6a108a12011-01-20 14:44:16 -08001348 bool "Enable AIO support" if EXPERT
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001349 default y
1350 help
1351 This option enables POSIX asynchronous I/O which may by used
1352 by some high performance threaded applications. Disabling
1353 this option saves about 7k.
1354
Randy Dunlap6befe5f2011-04-26 12:33:21 -07001355config EMBEDDED
1356 bool "Embedded system"
1357 select EXPERT
1358 help
1359 This option should be enabled if compiling the kernel for
1360 an embedded system so certain expert options are available
1361 for configuration.
1362
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001363config HAVE_PERF_EVENTS
Thomas Gleixner0793a612008-12-04 20:12:29 +01001364 bool
Mike Frysinger018df722009-06-12 13:17:43 -04001365 help
1366 See tools/perf/design.txt for details.
Thomas Gleixner0793a612008-12-04 20:12:29 +01001367
Peter Zijlstra906010b2009-09-21 16:08:49 +02001368config PERF_USE_VMALLOC
1369 bool
1370 help
1371 See tools/perf/design.txt for details
1372
Ingo Molnar57c0c152009-09-21 12:20:38 +02001373menu "Kernel Performance Events And Counters"
Thomas Gleixner0793a612008-12-04 20:12:29 +01001374
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001375config PERF_EVENTS
Ingo Molnar57c0c152009-09-21 12:20:38 +02001376 bool "Kernel performance events and counters"
Robert Richter392d65a2012-04-05 18:24:44 +02001377 default y if PROFILING
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001378 depends on HAVE_PERF_EVENTS
Ingo Molnar4c59e462008-12-08 19:38:33 +01001379 select ANON_INODES
Peter Zijlstrae360adb2010-10-14 14:01:34 +08001380 select IRQ_WORK
Thomas Gleixner0793a612008-12-04 20:12:29 +01001381 help
Ingo Molnar57c0c152009-09-21 12:20:38 +02001382 Enable kernel support for various performance events provided
1383 by software and hardware.
Thomas Gleixner0793a612008-12-04 20:12:29 +01001384
Thadeu Lima de Souza Cascardodd770382009-10-30 19:32:25 -02001385 Software events are supported either built-in or via the
Ingo Molnar57c0c152009-09-21 12:20:38 +02001386 use of generic tracepoints.
1387
1388 Most modern CPUs support performance events via performance
1389 counter registers. These registers count the number of certain
Thomas Gleixner0793a612008-12-04 20:12:29 +01001390 types of hw events: such as instructions executed, cachemisses
1391 suffered, or branches mis-predicted - without slowing down the
1392 kernel or applications. These registers can also trigger interrupts
1393 when a threshold number of events have passed - and can thus be
1394 used to profile the code that runs on that CPU.
1395
Ingo Molnar57c0c152009-09-21 12:20:38 +02001396 The Linux Performance Event subsystem provides an abstraction of
Thadeu Lima de Souza Cascardodd770382009-10-30 19:32:25 -02001397 these software and hardware event capabilities, available via a
Ingo Molnar57c0c152009-09-21 12:20:38 +02001398 system call and used by the "perf" utility in tools/perf/. It
Thomas Gleixner0793a612008-12-04 20:12:29 +01001399 provides per task and per CPU counters, and it provides event
1400 capabilities on top of those.
1401
1402 Say Y if unsure.
1403
Peter Zijlstra906010b2009-09-21 16:08:49 +02001404config DEBUG_PERF_USE_VMALLOC
1405 default n
1406 bool "Debug: use vmalloc to back perf mmap() buffers"
1407 depends on PERF_EVENTS && DEBUG_KERNEL
1408 select PERF_USE_VMALLOC
1409 help
1410 Use vmalloc memory to back perf mmap() buffers.
1411
1412 Mostly useful for debugging the vmalloc code on platforms
1413 that don't require it.
1414
1415 Say N if unsure.
1416
Thomas Gleixner0793a612008-12-04 20:12:29 +01001417endmenu
1418
Christoph Lameterf8891e52006-06-30 01:55:45 -07001419config VM_EVENT_COUNTERS
1420 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001421 bool "Enable VM event counters for /proc/vmstat" if EXPERT
Christoph Lameterf8891e52006-06-30 01:55:45 -07001422 help
Paul Jackson2aea4fb2006-12-22 01:06:10 -08001423 VM event counters are needed for event counts to be shown.
1424 This option allows the disabling of the VM event counters
David Rientjes6a108a12011-01-20 14:44:16 -08001425 on EXPERT systems. /proc/vmstat will only show page counts
Paul Jackson2aea4fb2006-12-22 01:06:10 -08001426 if VM event counters are disabled.
Christoph Lameterf8891e52006-06-30 01:55:45 -07001427
Thomas Petazzoni3d137312008-08-19 10:28:24 +02001428config PCI_QUIRKS
1429 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001430 bool "Enable PCI quirk workarounds" if EXPERT
Geert Uytterhoeven61cfc7e2008-10-22 08:53:25 +02001431 depends on PCI
Thomas Petazzoni3d137312008-08-19 10:28:24 +02001432 help
1433 This enables workarounds for various PCI chipset
1434 bugs/quirks. Disable this only if your target machine is
1435 unaffected by PCI quirks.
1436
Christoph Lameter41ecc552007-05-09 02:32:44 -07001437config SLUB_DEBUG
1438 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001439 bool "Enable SLUB debugging support" if EXPERT
Christoph Lameterf6acb632008-04-29 16:16:06 -07001440 depends on SLUB && SYSFS
Christoph Lameter41ecc552007-05-09 02:32:44 -07001441 help
1442 SLUB has extensive debug support features. Disabling these can
1443 result in significant savings in code size. This also disables
1444 SLUB sysfs support. /sys/slab will not exist and there will be
1445 no support for cache validation etc.
1446
Randy Dunlapb943c462009-03-10 12:55:46 -07001447config COMPAT_BRK
1448 bool "Disable heap randomization"
1449 default y
1450 help
1451 Randomizing heap placement makes heap exploits harder, but it
1452 also breaks ancient binaries (including anything libc5 based).
1453 This option changes the bootup default to heap randomization
Matt LaPlante692105b2009-01-26 11:12:25 +01001454 disabled, and can be overridden at runtime by setting
Randy Dunlapb943c462009-03-10 12:55:46 -07001455 /proc/sys/kernel/randomize_va_space to 2.
1456
1457 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1458
Christoph Lameter81819f02007-05-06 14:49:36 -07001459choice
1460 prompt "Choose SLAB allocator"
Christoph Lametera0acd822007-07-17 04:03:32 -07001461 default SLUB
Christoph Lameter81819f02007-05-06 14:49:36 -07001462 help
1463 This option allows to select a slab allocator.
1464
1465config SLAB
1466 bool "SLAB"
1467 help
1468 The regular slab allocator that is established and known to work
Christoph Lameter34013882007-05-09 02:32:47 -07001469 well in all environments. It organizes cache hot objects in
Simon Arlott02f56212008-11-05 22:18:19 +00001470 per cpu and per node queues.
Christoph Lameter81819f02007-05-06 14:49:36 -07001471
1472config SLUB
Christoph Lameter81819f02007-05-06 14:49:36 -07001473 bool "SLUB (Unqueued Allocator)"
1474 help
1475 SLUB is a slab allocator that minimizes cache line usage
1476 instead of managing queues of cached objects (SLAB approach).
1477 Per cpu caching is realized using slabs of objects instead
1478 of queues of objects. SLUB can use memory efficiently
Simon Arlott02f56212008-11-05 22:18:19 +00001479 and has enhanced diagnostics. SLUB is the default choice for
1480 a slab allocator.
Christoph Lameter81819f02007-05-06 14:49:36 -07001481
1482config SLOB
David Rientjes6a108a12011-01-20 14:44:16 -08001483 depends on EXPERT
Christoph Lameter81819f02007-05-06 14:49:36 -07001484 bool "SLOB (Simple Allocator)"
1485 help
Matt Mackall37291452008-02-04 22:29:38 -08001486 SLOB replaces the stock allocator with a drastically simpler
1487 allocator. SLOB is generally more space efficient but
1488 does not perform as well on large systems.
Christoph Lameter81819f02007-05-06 14:49:36 -07001489
1490endchoice
1491
Jie Zhangea637632009-12-14 18:00:02 -08001492config MMAP_ALLOW_UNINITIALIZED
1493 bool "Allow mmapped anonymous memory to be uninitialized"
David Rientjes6a108a12011-01-20 14:44:16 -08001494 depends on EXPERT && !MMU
Jie Zhangea637632009-12-14 18:00:02 -08001495 default n
1496 help
1497 Normally, and according to the Linux spec, anonymous memory obtained
1498 from mmap() has it's contents cleared before it is passed to
1499 userspace. Enabling this config option allows you to request that
1500 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
1501 providing a huge performance boost. If this option is not enabled,
1502 then the flag will be ignored.
1503
1504 This is taken advantage of by uClibc's malloc(), and also by
1505 ELF-FDPIC binfmt's brk and stack allocator.
1506
1507 Because of the obvious security issues, this option should only be
1508 enabled on embedded devices where you control what is run in
1509 userspace. Since that isn't generally a problem on no-MMU systems,
1510 it is normally safe to say Y here.
1511
1512 See Documentation/nommu-mmap.txt for more information.
1513
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05001514config PROFILING
Robert Richterb309a292010-02-26 15:01:23 +01001515 bool "Profiling support"
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05001516 help
1517 Say Y here to enable the extended profiling support mechanisms used
1518 by profilers such as OProfile.
1519
Ingo Molnar5f87f112008-07-23 14:15:22 +02001520#
1521# Place an empty function call at each tracepoint site. Can be
1522# dynamically changed for a probe function.
1523#
Mathieu Desnoyers97e1c182008-07-18 12:16:16 -04001524config TRACEPOINTS
Ingo Molnar5f87f112008-07-23 14:15:22 +02001525 bool
Mathieu Desnoyers97e1c182008-07-18 12:16:16 -04001526
Mathieu Desnoyersfb32e032008-02-02 15:10:33 -05001527source "arch/Kconfig"
1528
Linus Torvalds1da177e2005-04-16 15:20:36 -07001529endmenu # General setup
1530
Dmitry Baryshkovee7e5512008-06-29 14:18:46 +04001531config HAVE_GENERIC_DMA_COHERENT
1532 bool
1533 default n
1534
Linus Torvalds158a9622008-01-02 13:04:48 -08001535config SLABINFO
1536 bool
1537 depends on PROC_FS
Christoph Lameter0f389ec2008-04-14 18:53:02 +03001538 depends on SLAB || SLUB_DEBUG
Linus Torvalds158a9622008-01-02 13:04:48 -08001539 default y
1540
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001541config RT_MUTEXES
1542 boolean
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001543
Linus Torvalds1da177e2005-04-16 15:20:36 -07001544config BASE_SMALL
1545 int
1546 default 0 if BASE_FULL
1547 default 1 if !BASE_FULL
1548
Jan Engelhardt66da5732007-07-15 23:39:29 -07001549menuconfig MODULES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001550 bool "Enable loadable module support"
1551 help
1552 Kernel modules are small pieces of compiled code which can
1553 be inserted in the running kernel, rather than being
1554 permanently built into the kernel. You use the "modprobe"
1555 tool to add (and sometimes remove) them. If you say Y here,
1556 many parts of the kernel can be built as modules (by
1557 answering M instead of Y where indicated): this is most
1558 useful for infrequently used options which are not required
1559 for booting. For more information, see the man pages for
1560 modprobe, lsmod, modinfo, insmod and rmmod.
1561
1562 If you say Y here, you will need to run "make
1563 modules_install" to put the modules under /lib/modules/
1564 where modprobe can find them (you may need to be root to do
1565 this).
1566
1567 If unsure, say Y.
1568
Robert P. J. Day0b0de142008-08-04 13:31:32 -04001569if MODULES
1570
Linus Torvalds826e4502008-05-04 17:04:16 -07001571config MODULE_FORCE_LOAD
1572 bool "Forced module loading"
Linus Torvalds826e4502008-05-04 17:04:16 -07001573 default n
1574 help
Rusty Russell91e37a72008-05-09 16:25:28 +10001575 Allow loading of modules without version information (ie. modprobe
1576 --force). Forced module loading sets the 'F' (forced) taint flag and
1577 is usually a really bad idea.
Linus Torvalds826e4502008-05-04 17:04:16 -07001578
Linus Torvalds1da177e2005-04-16 15:20:36 -07001579config MODULE_UNLOAD
1580 bool "Module unloading"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001581 help
1582 Without this option you will not be able to unload any
1583 modules (note that some modules may not be unloadable
Denys Vlasenkof7f5b672008-07-22 19:24:26 -05001584 anyway), which makes your kernel smaller, faster
1585 and simpler. If unsure, say Y.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001586
1587config MODULE_FORCE_UNLOAD
1588 bool "Forced module unloading"
1589 depends on MODULE_UNLOAD && EXPERIMENTAL
1590 help
1591 This option allows you to force a module to unload, even if the
1592 kernel believes it is unsafe: the kernel will remove the module
1593 without waiting for anyone to stop using it (using the -f option to
1594 rmmod). This is mainly for kernel developers and desperate users.
1595 If unsure, say N.
1596
Linus Torvalds1da177e2005-04-16 15:20:36 -07001597config MODVERSIONS
Sam Ravnborg0d541642005-12-26 23:04:02 +01001598 bool "Module versioning support"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001599 help
1600 Usually, you have to use modules compiled with your kernel.
1601 Saying Y here makes it sometimes possible to use modules
1602 compiled for different kernels, by adding enough information
1603 to the modules to (hopefully) spot any changes which would
1604 make them incompatible with the kernel you are running. If
1605 unsure, say N.
1606
1607config MODULE_SRCVERSION_ALL
1608 bool "Source checksum for all modules"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001609 help
1610 Modules which contain a MODULE_VERSION get an extra "srcversion"
1611 field inserted into their modinfo section, which contains a
1612 sum of the source files which made it. This helps maintainers
1613 see exactly which source was used to build a module (since
1614 others sometimes change the module source without updating
1615 the version). With this option, such a "srcversion" field
1616 will be created for all modules. If unsure, say N.
1617
Robert P. J. Day0b0de142008-08-04 13:31:32 -04001618endif # MODULES
1619
Rusty Russell98a79d62008-12-13 21:19:41 +10301620config INIT_ALL_POSSIBLE
1621 bool
1622 help
Rusty Russell5f054e32012-03-29 15:38:31 +10301623 Back when each arch used to define their own cpu_online_mask and
1624 cpu_possible_mask, some of them chose to initialize cpu_possible_mask
Rusty Russell98a79d62008-12-13 21:19:41 +10301625 with all 1s, and others with all 0s. When they were centralised,
1626 it was better to provide this option than to break all the archs
Matt LaPlante692105b2009-01-26 11:12:25 +01001627 and have several arch maintainers pursuing me down dark alleys.
Rusty Russell98a79d62008-12-13 21:19:41 +10301628
Linus Torvalds1da177e2005-04-16 15:20:36 -07001629config STOP_MACHINE
1630 bool
1631 default y
1632 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
1633 help
1634 Need stop_machine() primitive.
Jens Axboe3a65dfe2005-11-04 08:43:35 +01001635
Jens Axboe3a65dfe2005-11-04 08:43:35 +01001636source "block/Kconfig"
Avi Kivitye98c3202007-10-16 23:27:31 -07001637
1638config PREEMPT_NOTIFIERS
1639 bool
Paul E. McKenneye260be62008-01-25 21:08:24 +01001640
Steffen Klassert16295be2010-01-06 19:47:10 +11001641config PADATA
1642 depends on SMP
1643 bool
1644
Thomas Gleixner6beb0002009-11-09 15:21:34 +00001645source "kernel/Kconfig.locks"