blob: 8f08f49a7c3945f62054a6e21505bdd1ce82fc50 [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 Oberparleiterb99b87f72009-06-17 16:28:03 -070019config CONSTRUCTORS
20 bool
21 depends on !UML
Peter Oberparleiterb99b87f72009-06-17 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 Dunlap34ad92c22005-10-30 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"
Richard Weinbergerbc083a62016-08-02 14:03:27 -070058 depends on !UML
Jiri Slaby4bb16672013-05-22 10:56:24 +020059 default n
60 help
61 Some drivers can be compiled on a different platform than they are
62 intended to be run on. Despite they cannot be loaded there (or even
63 when they load they cannot be used due to missing HW support),
64 developers still, opposing to distributors, might want to build such
65 drivers to compile-test them.
66
67 If you are a developer and want to build everything available, say Y
68 here. If you are a user/distributor, say N here to exclude useless
69 drivers to be distributed.
70
Linus Torvalds1da177e2005-04-16 15:20:36 -070071config LOCALVERSION
72 string "Local version - append to kernel release"
73 help
74 Append an extra string to the end of your kernel version.
75 This will show up when you type uname, for example.
76 The string you set here will be appended after the contents of
77 any files with a filename matching localversion* in your
78 object and source tree, in that order. Your total string can
79 be a maximum of 64 characters.
80
Ryan Andersonaaebf432005-07-31 04:57:49 -040081config LOCALVERSION_AUTO
82 bool "Automatically append version information to the version string"
83 default y
84 help
85 This will try to automatically determine if the current tree is a
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020086 release tree by looking for git tags that belong to the current
87 top of tree revision.
Ryan Andersonaaebf432005-07-31 04:57:49 -040088
89 A string of the format -gxxxxxxxx will be added to the localversion
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020090 if a git-based tree is found. The string generated by this will be
Ryan Andersonaaebf432005-07-31 04:57:49 -040091 appended after any matching localversion* files, and after the value
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020092 set in CONFIG_LOCALVERSION.
Ryan Andersonaaebf432005-07-31 04:57:49 -040093
Robert P. J. Day6e5a5422007-05-01 23:08:11 +020094 (The actual string used here is the first eight characters produced
95 by running the command:
96
97 $ git rev-parse --verify HEAD
98
99 which is done within the script "scripts/setlocalversion".)
Ryan Andersonaaebf432005-07-31 04:57:49 -0400100
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800101config HAVE_KERNEL_GZIP
102 bool
103
104config HAVE_KERNEL_BZIP2
105 bool
106
107config HAVE_KERNEL_LZMA
108 bool
109
Lasse Collin3ebe1242011-01-12 17:01:23 -0800110config HAVE_KERNEL_XZ
111 bool
112
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800113config HAVE_KERNEL_LZO
114 bool
115
Kyungsik Leee76e1fd2013-07-08 16:01:46 -0700116config HAVE_KERNEL_LZ4
117 bool
118
Alain Knaff30d65db2009-01-04 22:46:17 +0100119choice
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800120 prompt "Kernel compression mode"
121 default KERNEL_GZIP
H. Peter Anvin2d3c6272013-11-14 21:43:47 -0800122 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 -0800123 help
Alain Knaff30d65db2009-01-04 22:46:17 +0100124 The linux kernel is a kind of self-extracting executable.
125 Several compression algorithms are available, which differ
126 in efficiency, compression and decompression speed.
127 Compression speed is only relevant when building a kernel.
128 Decompression speed is relevant at each boot.
129
130 If you have any problems with bzip2 or lzma compressed
131 kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older
132 version of this functionality (bzip2 only), for 2.4, was
133 supplied by Christian Ludwig)
134
135 High compression options are mostly useful for users, who
136 are low on disk space (embedded systems), but for whom ram
137 size matters less.
138
139 If in doubt, select 'gzip'
140
141config KERNEL_GZIP
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800142 bool "Gzip"
143 depends on HAVE_KERNEL_GZIP
144 help
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800145 The old and tried gzip compression. It provides a good balance
146 between compression ratio and decompression speed.
Alain Knaff30d65db2009-01-04 22:46:17 +0100147
148config KERNEL_BZIP2
149 bool "Bzip2"
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800150 depends on HAVE_KERNEL_BZIP2
Alain Knaff30d65db2009-01-04 22:46:17 +0100151 help
152 Its compression ratio and speed is intermediate.
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700153 Decompression speed is slowest among the choices. The kernel
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800154 size is about 10% smaller with bzip2, in comparison to gzip.
155 Bzip2 uses a large amount of memory. For modern kernels you
156 will need at least 8MB RAM or more for booting.
Alain Knaff30d65db2009-01-04 22:46:17 +0100157
158config KERNEL_LZMA
H. Peter Anvin2e9f3bd2009-01-04 15:41:25 -0800159 bool "LZMA"
160 depends on HAVE_KERNEL_LZMA
161 help
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700162 This compression algorithm's ratio is best. Decompression speed
163 is between gzip and bzip2. Compression is slowest.
164 The kernel size is about 33% smaller with LZMA in comparison to gzip.
Alain Knaff30d65db2009-01-04 22:46:17 +0100165
Lasse Collin3ebe1242011-01-12 17:01:23 -0800166config KERNEL_XZ
167 bool "XZ"
168 depends on HAVE_KERNEL_XZ
169 help
170 XZ uses the LZMA2 algorithm and instruction set specific
171 BCJ filters which can improve compression ratio of executable
172 code. The size of the kernel is about 30% smaller with XZ in
173 comparison to gzip. On architectures for which there is a BCJ
174 filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
175 will create a few percent smaller kernel than plain LZMA.
176
177 The speed is about the same as with LZMA: The decompression
178 speed of XZ is better than that of bzip2 but worse than gzip
179 and LZO. Compression is slow.
180
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800181config KERNEL_LZO
182 bool "LZO"
183 depends on HAVE_KERNEL_LZO
184 help
Randy Dunlap0a4dd352012-05-31 16:26:46 -0700185 Its compression ratio is the poorest among the choices. The kernel
Stephan Sperber681b3042010-07-14 11:23:08 +0200186 size is about 10% bigger than gzip; however its speed
Albin Tonnerre7dd65fe2010-01-08 14:42:42 -0800187 (both compression and decompression) is the fastest.
188
Kyungsik Leee76e1fd2013-07-08 16:01:46 -0700189config KERNEL_LZ4
190 bool "LZ4"
191 depends on HAVE_KERNEL_LZ4
192 help
193 LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
194 A preliminary version of LZ4 de/compression tool is available at
195 <https://code.google.com/p/lz4/>.
196
197 Its compression ratio is worse than LZO. The size of the kernel
198 is about 8% bigger than LZO. But the decompression speed is
199 faster than LZO.
200
Alain Knaff30d65db2009-01-04 22:46:17 +0100201endchoice
202
Josh Triplettbd5dc172011-06-15 15:08:28 -0700203config DEFAULT_HOSTNAME
204 string "Default hostname"
205 default "(none)"
206 help
207 This option determines the default system hostname before userspace
208 calls sethostname(2). The kernel traditionally uses "(none)" here,
209 but you may wish to use a different default here to make a minimal
210 system more usable with less configuration.
211
Linus Torvalds1da177e2005-04-16 15:20:36 -0700212config SWAP
213 bool "Support for paging of anonymous memory (swap)"
David Howells93614012006-09-30 20:45:40 +0200214 depends on MMU && BLOCK
Linus Torvalds1da177e2005-04-16 15:20:36 -0700215 default y
216 help
217 This option allows you to choose whether you want to have support
Jesper Juhl92c35042006-01-15 02:40:08 +0100218 for so called swap devices or swap files in your kernel that are
Linus Torvalds1da177e2005-04-16 15:20:36 -0700219 used to provide more virtual memory than the actual RAM present
220 in your computer. If unsure say Y.
221
222config SYSVIPC
223 bool "System V IPC"
Linus Torvalds1da177e2005-04-16 15:20:36 -0700224 ---help---
225 Inter Process Communication is a suite of library functions and
226 system calls which let processes (running programs) synchronize and
227 exchange information. It is generally considered to be a good thing,
228 and some programs won't run unless you say Y here. In particular, if
229 you want to run the DOS emulator dosemu under Linux (read the
230 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
231 you'll need to say Y here.
232
233 You can find documentation about IPC with "info ipc" and also in
234 section 6.4 of the Linux Programmer's Guide, available from
235 <http://www.tldp.org/guides.html>.
236
Eric W. Biedermana5494dc2007-02-14 00:34:06 -0800237config SYSVIPC_SYSCTL
238 bool
239 depends on SYSVIPC
240 depends on SYSCTL
241 default y
242
Linus Torvalds1da177e2005-04-16 15:20:36 -0700243config POSIX_MQUEUE
244 bool "POSIX Message Queues"
Kees Cook19c92392012-10-02 11:19:29 -0700245 depends on NET
Linus Torvalds1da177e2005-04-16 15:20:36 -0700246 ---help---
247 POSIX variant of message queues is a part of IPC. In POSIX message
248 queues every message has a priority which decides about succession
249 of receiving it by a process. If you want to compile and run
250 programs written e.g. for Solaris with use of its POSIX message
Robert P. J. Dayb0e37652007-05-09 07:25:13 +0200251 queues (functions mq_*) say Y here.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700252
253 POSIX message queues are visible as a filesystem called 'mqueue'
254 and can be mounted somewhere if you want to do filesystem
255 operations on message queues.
256
257 If unsure, say Y.
258
Serge E. Hallynbdc8e5f2009-04-06 19:01:11 -0700259config POSIX_MQUEUE_SYSCTL
260 bool
261 depends on POSIX_MQUEUE
262 depends on SYSCTL
263 default y
264
Konstantin Khlebnikov226b4cc2014-06-04 16:10:50 -0700265config CROSS_MEMORY_ATTACH
266 bool "Enable process_vm_readv/writev syscalls"
267 depends on MMU
268 default y
269 help
270 Enabling this option adds the system calls process_vm_readv and
271 process_vm_writev which allow a process with the correct privileges
Geert Uytterhoevena2a368d2014-08-12 13:46:11 -0700272 to directly read from or write to another process' address space.
Konstantin Khlebnikov226b4cc2014-06-04 16:10:50 -0700273 See the man page for more details.
274
Aneesh Kumar K.V990d6c22011-01-29 18:43:26 +0530275config FHANDLE
Andi Kleenf76be612016-04-01 14:31:40 -0700276 bool "open by fhandle syscalls" if EXPERT
Aneesh Kumar K.V990d6c22011-01-29 18:43:26 +0530277 select EXPORTFS
Andi Kleenf76be612016-04-01 14:31:40 -0700278 default y
Aneesh Kumar K.V990d6c22011-01-29 18:43:26 +0530279 help
280 If you say Y here, a user level program will be able to map
281 file names to handle and then later use the handle for
282 different file system operations. This is useful in implementing
283 userspace file servers, which now track files using handles instead
284 of names. The handle would remain the same even if file names
285 get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
286 syscalls.
287
Josh Triplett69369a72014-04-03 14:48:27 -0700288config USELIB
289 bool "uselib syscall"
Riku Voipiob2113a42016-01-15 16:58:13 -0800290 def_bool ALPHA || M68K || SPARC || X86_32 || IA32_EMULATION
Josh Triplett69369a72014-04-03 14:48:27 -0700291 help
292 This option enables the uselib syscall, a system call used in the
293 dynamic linker from libc5 and earlier. glibc does not use this
294 system call. If you intend to run programs built on libc5 or
295 earlier, you may need to enable this syscall. Current systems
296 running glibc can safely disable this.
297
Linus Torvalds1da177e2005-04-16 15:20:36 -0700298config AUDIT
299 bool "Auditing support"
Chris Wright804a6a492005-05-11 10:52:45 +0100300 depends on NET
Linus Torvalds1da177e2005-04-16 15:20:36 -0700301 help
302 Enable auditing infrastructure that can be used with another
303 kernel subsystem, such as SELinux (which requires this for
Paul Moorecb74ed22016-01-13 09:18:55 -0500304 logging of avc messages output). System call auditing is included
305 on architectures which support it.
Linus Torvalds1da177e2005-04-16 15:20:36 -0700306
AKASHI Takahiro7a017722014-02-25 18:16:24 +0900307config HAVE_ARCH_AUDITSYSCALL
308 bool
309
Linus Torvalds1da177e2005-04-16 15:20:36 -0700310config AUDITSYSCALL
Paul Moorecb74ed22016-01-13 09:18:55 -0500311 def_bool y
AKASHI Takahiro7a017722014-02-25 18:16:24 +0900312 depends on AUDIT && HAVE_ARCH_AUDITSYSCALL
Linus Torvalds1da177e2005-04-16 15:20:36 -0700313
Eric Paris939a67f2009-12-17 20:12:06 -0500314config AUDIT_WATCH
315 def_bool y
316 depends on AUDITSYSCALL
317 select FSNOTIFY
Linus Torvalds1da177e2005-04-16 15:20:36 -0700318
Al Viro74c3cbe2007-07-22 08:04:18 -0400319config AUDIT_TREE
320 def_bool y
Eric Paris63c882a2009-05-21 17:02:01 -0400321 depends on AUDITSYSCALL
Eric Paris28a3a7e2009-12-17 20:12:05 -0500322 select FSNOTIFY
Al Viro74c3cbe2007-07-22 08:04:18 -0400323
Thomas Gleixnerd9817eb2010-09-27 12:45:59 +0000324source "kernel/irq/Kconfig"
Thomas Gleixner764e0da2012-05-21 23:16:18 +0200325source "kernel/time/Kconfig"
Thomas Gleixnerd9817eb2010-09-27 12:45:59 +0000326
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200327menu "CPU/Task time and stats accounting"
328
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200329config VIRT_CPU_ACCOUNTING
330 bool
331
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200332choice
333 prompt "Cputime accounting"
334 default TICK_CPU_ACCOUNTING if !PPC64
Stephen Rothwell02fc8d32013-02-08 14:19:38 +1100335 default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200336
337# Kind of a stub config for the pure tick based cputime accounting
338config TICK_CPU_ACCOUNTING
339 bool "Simple tick based cputime accounting"
Frederic Weisbeckerc58b0df2013-04-26 15:16:31 +0200340 depends on !S390 && !NO_HZ_FULL
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200341 help
342 This is the basic tick based cputime accounting that maintains
343 statistics about user, system and idle time spent on per jiffies
344 granularity.
345
346 If unsure, say Y.
347
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200348config VIRT_CPU_ACCOUNTING_NATIVE
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200349 bool "Deterministic task and CPU time accounting"
Frederic Weisbeckerc58b0df2013-04-26 15:16:31 +0200350 depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200351 select VIRT_CPU_ACCOUNTING
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200352 help
353 Select this option to enable more accurate task and CPU time
354 accounting. This is done by reading a CPU counter on each
355 kernel entry and exit and on transitions within the kernel
356 between system, softirq and hardirq state, so there is a
357 small performance impact. In the case of s390 or IBM POWER > 5,
358 this also enables accounting of stolen time on logically-partitioned
359 systems.
360
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200361config VIRT_CPU_ACCOUNTING_GEN
362 bool "Full dynticks CPU time accounting"
Kevin Hilmanff3fb252013-09-16 15:28:19 -0700363 depends on HAVE_CONTEXT_TRACKING
Kevin Hilman554b0002013-09-16 15:28:21 -0700364 depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
Frederic Weisbeckerabf917c2012-07-25 07:56:04 +0200365 select VIRT_CPU_ACCOUNTING
366 select CONTEXT_TRACKING
367 help
368 Select this option to enable task and CPU time accounting on full
369 dynticks systems. This accounting is implemented by watching every
370 kernel-user boundaries using the context tracking subsystem.
371 The accounting is thus performed at the expense of some significant
372 overhead.
373
374 For now this is only useful if you are working on the full
375 dynticks subsystem development.
376
377 If unsure, say N.
378
Rik van Rielb58c3582016-07-13 16:50:02 +0200379endchoice
380
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200381config IRQ_TIME_ACCOUNTING
382 bool "Fine granularity task level IRQ time accounting"
Rik van Rielb58c3582016-07-13 16:50:02 +0200383 depends on HAVE_IRQ_TIME_ACCOUNTING && !VIRT_CPU_ACCOUNTING_NATIVE
Frederic Weisbeckerfdf9c352012-09-09 14:56:31 +0200384 help
385 Select this option to enable fine granularity task irq time
386 accounting. This is done by reading a timestamp on each
387 transitions between softirq and hardirq state, so there can be a
388 small performance impact.
389
390 If in doubt, say N here.
391
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200392config BSD_PROCESS_ACCT
393 bool "BSD Process Accounting"
Iulia Manda28138932015-04-15 16:16:41 -0700394 depends on MULTIUSER
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200395 help
396 If you say Y here, a user level program will be able to instruct the
397 kernel (via a special system call) to write process accounting
398 information to a file: whenever a process exits, information about
399 that process will be appended to the file by the kernel. The
400 information includes things such as creation time, owning user,
401 command name, memory usage, controlling terminal etc. (the complete
402 list is in the struct acct in <file:include/linux/acct.h>). It is
403 up to the user level program to do useful things with this
404 information. This is generally a good idea, so say Y.
405
406config BSD_PROCESS_ACCT_V3
407 bool "BSD Process Accounting version 3 file format"
408 depends on BSD_PROCESS_ACCT
409 default n
410 help
411 If you say Y here, the process accounting information is written
412 in a new file format that also logs the process IDs of each
413 process and it's parent. Note that this file format is incompatible
414 with previous v0/v1/v2 file formats, so you will need updated tools
415 for processing it. A preliminary version of these tools is available
416 at <http://www.gnu.org/software/acct/>.
417
418config TASKSTATS
Kees Cook19c92392012-10-02 11:19:29 -0700419 bool "Export task/process statistics through netlink"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200420 depends on NET
Iulia Manda28138932015-04-15 16:16:41 -0700421 depends on MULTIUSER
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200422 default n
423 help
424 Export selected statistics for tasks/processes through the
425 generic netlink interface. Unlike BSD process accounting, the
426 statistics are available during the lifetime of tasks/processes as
427 responses to commands. Like BSD accounting, they are sent to user
428 space on task exit.
429
430 Say N if unsure.
431
432config TASK_DELAY_ACCT
Kees Cook19c92392012-10-02 11:19:29 -0700433 bool "Enable per-task delay accounting"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200434 depends on TASKSTATS
Naveen N. Raof6db8342015-06-25 23:53:37 +0530435 select SCHED_INFO
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200436 help
437 Collect information on time spent by a task waiting for system
438 resources like cpu, synchronous block I/O completion and swapping
439 in pages. Such statistics can help in setting a task's priorities
440 relative to other tasks for cpu, io, rss limits etc.
441
442 Say N if unsure.
443
444config TASK_XACCT
Kees Cook19c92392012-10-02 11:19:29 -0700445 bool "Enable extended accounting over taskstats"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200446 depends on TASKSTATS
447 help
448 Collect extended task accounting data and send the data
449 to userland for processing over the taskstats interface.
450
451 Say N if unsure.
452
453config TASK_IO_ACCOUNTING
Kees Cook19c92392012-10-02 11:19:29 -0700454 bool "Enable per-task storage I/O accounting"
Frederic Weisbecker391dc692012-09-09 14:22:07 +0200455 depends on TASK_XACCT
456 help
457 Collect information on the number of bytes of storage I/O which this
458 task has caused.
459
460 Say N if unsure.
461
462endmenu # "CPU/Task time and stats accounting"
463
Mike Travisc903ff82009-01-15 12:28:29 -0800464menu "RCU Subsystem"
465
Mike Travisc903ff82009-01-15 12:28:29 -0800466config TREE_RCU
Pranith Kumare72aeaf2015-04-21 17:29:42 -0400467 bool
468 default y if !PREEMPT && SMP
Mike Travisc903ff82009-01-15 12:28:29 -0800469 help
470 This option selects the RCU implementation that is
471 designed for very large SMP system with hundreds or
Paul E. McKenneyc17ef452009-06-23 17:12:47 -0700472 thousands of CPUs. It also scales down nicely to
473 smaller systems.
Mike Travisc903ff82009-01-15 12:28:29 -0800474
Pranith Kumar28f65692014-09-22 14:00:48 -0400475config PREEMPT_RCU
Pranith Kumare72aeaf2015-04-21 17:29:42 -0400476 bool
477 default y if PREEMPT
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700478 help
479 This option selects the RCU implementation that is
480 designed for very large SMP systems with hundreds or
481 thousands of CPUs, but for which real-time response
Paul E. McKenneybbe3eae2009-09-13 09:15:08 -0700482 is also required. It also scales down nicely to
483 smaller systems.
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700484
Paul E. McKenney9fc52d82013-01-08 15:48:33 -0800485 Select this option if you are unsure.
486
Paul E. McKenney9b1d82f2009-10-25 19:03:50 -0700487config TINY_RCU
Pranith Kumare72aeaf2015-04-21 17:29:42 -0400488 bool
489 default y if !PREEMPT && !SMP
Paul E. McKenney9b1d82f2009-10-25 19:03:50 -0700490 help
491 This option selects the RCU implementation that is
492 designed for UP systems from which real-time response
493 is not required. This option greatly reduces the
494 memory footprint of RCU.
495
Paul E. McKenney78cae102015-04-20 12:19:45 -0700496config RCU_EXPERT
497 bool "Make expert-level adjustments to RCU configuration"
498 default n
499 help
500 This option needs to be enabled if you wish to make
501 expert-level adjustments to RCU configuration. By default,
502 no such adjustments can be made, which has the often-beneficial
503 side-effect of preventing "make oldconfig" from asking you all
504 sorts of detailed questions about how you would like numerous
505 obscure RCU options to be set up.
506
507 Say Y if you need to make expert-level adjustments to RCU.
508
509 Say N if you are unsure.
510
Pranith Kumar83fe27e2014-12-05 11:24:45 -0500511config SRCU
512 bool
513 help
514 This option selects the sleepable version of RCU. This version
515 permits arbitrary sleeping or blocking within RCU read-side critical
516 sections.
517
Paul E. McKenney8315f422014-06-27 13:42:20 -0700518config TASKS_RCU
Paul E. McKenney82d0f4c2015-04-20 05:42:50 -0700519 bool
Paul E. McKenney8315f422014-06-27 13:42:20 -0700520 default n
Paul E. McKenney570dd3c2016-06-15 08:56:53 -0700521 depends on !UML
Pranith Kumar83fe27e2014-12-05 11:24:45 -0500522 select SRCU
Paul E. McKenney8315f422014-06-27 13:42:20 -0700523 help
524 This option enables a task-based RCU implementation that uses
525 only voluntary context switch (not preemption!), idle, and
526 user-mode execution as quiescent states.
527
Paul E. McKenney6bfc09e2012-10-19 12:49:17 -0700528config RCU_STALL_COMMON
Pranith Kumar28f65692014-09-22 14:00:48 -0400529 def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
Paul E. McKenney6bfc09e2012-10-19 12:49:17 -0700530 help
531 This option enables RCU CPU stall code that is common between
532 the TINY and TREE variants of RCU. The purpose is to allow
533 the tiny variants to disable RCU CPU stall warnings, while
534 making these warnings mandatory for the tree variants.
535
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100536config CONTEXT_TRACKING
537 bool
538
Frederic Weisbecker91d1aa432012-11-27 19:33:25 +0100539config CONTEXT_TRACKING_FORCE
540 bool "Force context tracking"
541 depends on CONTEXT_TRACKING
Frederic Weisbeckerd84d27a2013-07-24 21:59:29 +0200542 default y if !NO_HZ_FULL
Frederic Weisbecker1fd2b442012-07-11 20:26:40 +0200543 help
Frederic Weisbeckerd84d27a2013-07-24 21:59:29 +0200544 The major pre-requirement for full dynticks to work is to
545 support the context tracking subsystem. But there are also
546 other dependencies to provide in order to make the full
547 dynticks working.
548
549 This option stands for testing when an arch implements the
550 context tracking backend but doesn't yet fullfill all the
551 requirements to make the full dynticks feature working.
552 Without the full dynticks, there is no way to test the support
553 for context tracking and the subsystems that rely on it: RCU
554 userspace extended quiescent state and tickless cputime
555 accounting. This option copes with the absence of the full
556 dynticks subsystem by forcing the context tracking on all
557 CPUs in the system.
558
Paul Gortmaker99c8b1e2013-10-24 10:07:47 -0400559 Say Y only if you're working on the development of an
Frederic Weisbeckerd84d27a2013-07-24 21:59:29 +0200560 architecture backend for the context tracking.
561
562 Say N otherwise, this option brings an overhead that you
563 don't want in production.
564
Frederic Weisbeckerd6771242012-10-11 01:48:28 +0200565
Mike Travisc903ff82009-01-15 12:28:29 -0800566config RCU_FANOUT
567 int "Tree-based hierarchical RCU fanout value"
568 range 2 64 if 64BIT
569 range 2 32 if !64BIT
Paul E. McKenney05c5df32015-04-20 14:27:43 -0700570 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
Mike Travisc903ff82009-01-15 12:28:29 -0800571 default 64 if 64BIT
572 default 32 if !64BIT
573 help
574 This option controls the fanout of hierarchical implementations
575 of RCU, allowing RCU to work efficiently on machines with
Paul E. McKenney4d87ffa2010-08-04 17:31:12 -0700576 large numbers of CPUs. This value must be at least the fourth
577 root of NR_CPUS, which allows NR_CPUS to be insanely large.
578 The default value of RCU_FANOUT should be used for production
579 systems, but if you are stress-testing the RCU implementation
580 itself, small RCU_FANOUT values allow you to test large-system
581 code paths on small(er) systems.
Mike Travisc903ff82009-01-15 12:28:29 -0800582
583 Select a specific number if testing RCU itself.
584 Take the default if unsure.
585
Paul E. McKenney8932a632012-04-19 12:20:14 -0700586config RCU_FANOUT_LEAF
587 int "Tree-based hierarchical RCU leaf-level fanout value"
Paul E. McKenney8739c5c2015-04-20 18:27:54 -0700588 range 2 64 if 64BIT
589 range 2 32 if !64BIT
Paul E. McKenney47d631a2015-04-21 09:12:13 -0700590 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
Paul E. McKenney8932a632012-04-19 12:20:14 -0700591 default 16
592 help
593 This option controls the leaf-level fanout of hierarchical
594 implementations of RCU, and allows trading off cache misses
595 against lock contention. Systems that synchronize their
596 scheduling-clock interrupts for energy-efficiency reasons will
597 want the default because the smaller leaf-level fanout keeps
598 lock contention levels acceptably low. Very large systems
599 (hundreds or thousands of CPUs) will instead want to set this
600 value to the maximum value possible in order to reduce the
601 number of cache misses incurred during RCU's grace-period
602 initialization. These systems tend to run CPU-bound, and thus
603 are not helped by synchronized interrupts, and thus tend to
604 skew them, which reduces lock contention enough that large
605 leaf-level fanouts work well.
606
607 Select a specific number if testing RCU itself.
608
609 Select the maximum permissible value for large systems.
610
611 Take the default if unsure.
612
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800613config RCU_FAST_NO_HZ
614 bool "Accelerate last non-dyntick-idle CPU's grace periods"
Paul E. McKenney78cae102015-04-20 12:19:45 -0700615 depends on NO_HZ_COMMON && SMP && RCU_EXPERT
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800616 default n
617 help
Paul E. McKenneyc0f4dfd2012-12-28 11:30:36 -0800618 This option permits CPUs to enter dynticks-idle state even if
619 they have RCU callbacks queued, and prevents RCU from waking
620 these CPUs up more than roughly once every four jiffies (by
621 default, you can adjust this using the rcutree.rcu_idle_gp_delay
622 parameter), thus improving energy efficiency. On the other
623 hand, this option increases the duration of RCU grace periods,
624 for example, slowing down synchronize_rcu().
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800625
Paul E. McKenneyc0f4dfd2012-12-28 11:30:36 -0800626 Say Y if energy efficiency is critically important, and you
627 don't care about increased grace-period durations.
Paul E. McKenney8bd93a22010-02-22 17:04:59 -0800628
629 Say N if you are unsure.
630
Mike Travisc903ff82009-01-15 12:28:29 -0800631config TREE_RCU_TRACE
Pranith Kumar28f65692014-09-22 14:00:48 -0400632 def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU )
Mike Travisc903ff82009-01-15 12:28:29 -0800633 select DEBUG_FS
634 help
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700635 This option provides tracing for the TREE_RCU and
Pranith Kumar28f65692014-09-22 14:00:48 -0400636 PREEMPT_RCU implementations, permitting Makefile to
Paul E. McKenneyf41d9112009-08-22 13:56:52 -0700637 trivially select kernel/rcutree_trace.c.
Mike Travisc903ff82009-01-15 12:28:29 -0800638
Paul E. McKenney24278d12010-09-27 17:25:23 -0700639config RCU_BOOST
640 bool "Enable RCU priority boosting"
Paul E. McKenney78cae102015-04-20 12:19:45 -0700641 depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
Paul E. McKenney24278d12010-09-27 17:25:23 -0700642 default n
643 help
644 This option boosts the priority of preempted RCU readers that
645 block the current preemptible RCU grace period for too long.
646 This option also prevents heavy loads from blocking RCU
647 callback invocation for all flavors of RCU.
648
649 Say Y here if you are working with real-time apps or heavy loads
650 Say N here if you are unsure.
651
Clark Williams21871d72014-09-12 21:21:09 -0500652config RCU_KTHREAD_PRIO
653 int "Real-time priority to use for RCU worker threads"
Paul E. McKenneya94844b2014-12-12 07:37:48 -0800654 range 1 99 if RCU_BOOST
655 range 0 99 if !RCU_BOOST
656 default 1 if RCU_BOOST
657 default 0 if !RCU_BOOST
Paul E. McKenney26730f52015-04-21 09:22:14 -0700658 depends on RCU_EXPERT
Paul E. McKenney24278d12010-09-27 17:25:23 -0700659 help
Clark Williams21871d72014-09-12 21:21:09 -0500660 This option specifies the SCHED_FIFO priority value that will be
661 assigned to the rcuc/n and rcub/n threads and is also the value
662 used for RCU_BOOST (if enabled). If you are working with a
663 real-time application that has one or more CPU-bound threads
664 running at a real-time priority level, you should set
665 RCU_KTHREAD_PRIO to a priority higher than the highest-priority
666 real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO
667 value of 1 is appropriate in the common case, which is real-time
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700668 applications that do not have any CPU-bound threads.
669
670 Some real-time applications might not have a single real-time
671 thread that saturates a given CPU, but instead might have
672 multiple real-time threads that, taken together, fully utilize
Clark Williams21871d72014-09-12 21:21:09 -0500673 that CPU. In this case, you should set RCU_KTHREAD_PRIO to
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700674 a priority higher than the lowest-priority thread that is
675 conspiring to prevent the CPU from running any non-real-time
676 tasks. For example, if one thread at priority 10 and another
677 thread at priority 5 are between themselves fully consuming
Clark Williams21871d72014-09-12 21:21:09 -0500678 the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be
Paul E. McKenneyc9336642012-04-18 16:20:18 -0700679 set to priority 6 or higher.
Paul E. McKenney24278d12010-09-27 17:25:23 -0700680
681 Specify the real-time priority, or take the default if unsure.
682
683config RCU_BOOST_DELAY
684 int "Milliseconds to delay boosting after RCU grace-period start"
685 range 0 3000
686 depends on RCU_BOOST
687 default 500
688 help
689 This option specifies the time to wait after the beginning of
690 a given grace period before priority-boosting preempted RCU
691 readers blocking that grace period. Note that any RCU reader
692 blocking an expedited RCU grace period is boosted immediately.
693
694 Accept the default if unsure.
695
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700696config RCU_NOCB_CPU
Paul E. McKenney9a5739d2013-03-28 20:48:36 -0700697 bool "Offload RCU callback processing from boot-selected CPUs"
Pranith Kumar28f65692014-09-22 14:00:48 -0400698 depends on TREE_RCU || PREEMPT_RCU
Paul E. McKenneybe55fa22015-06-02 05:29:18 -0700699 depends on RCU_EXPERT || NO_HZ_FULL
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700700 default n
701 help
702 Use this option to reduce OS jitter for aggressive HPC or
703 real-time workloads. It can also be used to offload RCU
704 callback invocation to energy-efficient CPUs in battery-powered
705 asymmetric multiprocessors.
706
707 This option offloads callback invocation from the set of
708 CPUs specified at boot time by the rcu_nocbs parameter.
Paul E. McKenneya4889852012-12-03 08:16:28 -0800709 For each such CPU, a kthread ("rcuox/N") will be created to
710 invoke callbacks, where the "N" is the CPU being offloaded,
711 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
712 "s" for RCU-sched. Nothing prevents this kthread from running
713 on the specified CPUs, but (1) the kthreads may be preempted
714 between each callback, and (2) affinity or cgroups can be used
715 to force the kthreads to run on whatever set of CPUs is desired.
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700716
Paul E. McKenney34ed62462013-01-07 13:37:42 -0800717 Say Y here if you want to help to debug reduced OS jitter.
Paul E. McKenney3fbfbf72012-08-19 21:35:53 -0700718 Say N here if you are unsure.
719
Paul E. McKenney911af502013-02-11 10:23:27 -0800720choice
721 prompt "Build-forced no-CBs CPUs"
722 default RCU_NOCB_CPU_NONE
Stefan Hengelein45687792014-09-02 19:55:11 +0200723 depends on RCU_NOCB_CPU
Paul E. McKenney911af502013-02-11 10:23:27 -0800724 help
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700725 This option allows no-CBs CPUs (whose RCU callbacks are invoked
726 from kthreads rather than from softirq context) to be specified
727 at build time. Additional no-CBs CPUs may be specified by
728 the rcu_nocbs= boot parameter.
Paul E. McKenney911af502013-02-11 10:23:27 -0800729
730config RCU_NOCB_CPU_NONE
731 bool "No build_forced no-CBs CPUs"
Paul E. McKenney911af502013-02-11 10:23:27 -0800732 help
733 This option does not force any of the CPUs to be no-CBs CPUs.
734 Only CPUs designated by the rcu_nocbs= boot parameter will be
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700735 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
736 kthreads whose names begin with "rcuo". All other CPUs will
737 invoke their own RCU callbacks in softirq context.
738
739 Select this option if you want to choose no-CBs CPUs at
740 boot time, for example, to allow testing of different no-CBs
741 configurations without having to rebuild the kernel each time.
Paul E. McKenney911af502013-02-11 10:23:27 -0800742
743config RCU_NOCB_CPU_ZERO
744 bool "CPU 0 is a build_forced no-CBs CPU"
Paul E. McKenney911af502013-02-11 10:23:27 -0800745 help
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700746 This option forces CPU 0 to be a no-CBs CPU, so that its RCU
747 callbacks are invoked by a per-CPU kthread whose name begins
748 with "rcuo". Additional CPUs may be designated as no-CBs
749 CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
750 All other CPUs will invoke their own RCU callbacks in softirq
751 context.
Paul E. McKenney911af502013-02-11 10:23:27 -0800752
753 Select this if CPU 0 needs to be a no-CBs CPU for real-time
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700754 or energy-efficiency reasons, but the real reason it exists
755 is to ensure that randconfig testing covers mixed systems.
Paul E. McKenney911af502013-02-11 10:23:27 -0800756
757config RCU_NOCB_CPU_ALL
758 bool "All CPUs are build_forced no-CBs CPUs"
Paul E. McKenney911af502013-02-11 10:23:27 -0800759 help
760 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs=
Paul E. McKenney676c3dc2013-04-30 14:49:42 -0700761 boot parameter will be ignored. All CPUs' RCU callbacks will
762 be executed in the context of per-CPU rcuo kthreads created for
763 this purpose. Assuming that the kthreads whose names start with
764 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
765 on the remaining CPUs, but might decrease memory locality during
766 RCU-callback invocation, thus potentially degrading throughput.
Paul E. McKenney911af502013-02-11 10:23:27 -0800767
768 Select this if all CPUs need to be no-CBs CPUs for real-time
769 or energy-efficiency reasons.
770
771endchoice
772
Paul E. McKenneyee425712015-02-19 10:51:32 -0800773config RCU_EXPEDITE_BOOT
774 bool
775 default n
776 help
777 This option enables expedited grace periods at boot time,
778 as if rcu_expedite_gp() had been invoked early in boot.
779 The corresponding rcu_unexpedite_gp() is invoked from
780 rcu_end_inkernel_boot(), which is intended to be invoked
781 at the end of the kernel-only boot sequence, just before
782 init is exec'ed.
783
784 Accept the default if unsure.
785
Mike Travisc903ff82009-01-15 12:28:29 -0800786endmenu # "RCU Subsystem"
787
Vivek Goyalde5b56b2014-08-08 14:25:41 -0700788config BUILD_BIN2C
789 bool
790 default n
791
Linus Torvalds1da177e2005-04-16 15:20:36 -0700792config IKCONFIG
Ross Birof2443ab2006-09-30 23:27:25 -0700793 tristate "Kernel .config support"
Vivek Goyalde5b56b2014-08-08 14:25:41 -0700794 select BUILD_BIN2C
Linus Torvalds1da177e2005-04-16 15:20:36 -0700795 ---help---
796 This option enables the complete Linux kernel ".config" file
797 contents to be saved in the kernel. It provides documentation
798 of which kernel options are used in a running kernel or in an
799 on-disk kernel. This information can be extracted from the kernel
800 image file with the script scripts/extract-ikconfig and used as
801 input to rebuild the current kernel or to build another kernel.
802 It can also be extracted from a running kernel by reading
803 /proc/config.gz if enabled (below).
804
805config IKCONFIG_PROC
806 bool "Enable access to .config through /proc/config.gz"
807 depends on IKCONFIG && PROC_FS
808 ---help---
809 This option enables access to the kernel configuration file
810 through /proc/config.gz.
811
Alistair John Strachan794543a2007-05-08 00:31:15 -0700812config LOG_BUF_SHIFT
813 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
Ingo Molnarfb39f982015-07-01 10:19:11 +0200814 range 12 25
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700815 default 17
Josh Triplett361e9df2014-10-03 16:00:54 -0700816 depends on PRINTK
Alistair John Strachan794543a2007-05-08 00:31:15 -0700817 help
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700818 Select the minimal kernel log buffer size as a power of 2.
819 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config
820 parameter, see below. Any higher size also might be forced
821 by "log_buf_len" boot parameter.
822
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700823 Examples:
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700824 17 => 128 KB
Adrian Bunkf17a32e2008-04-29 00:58:58 -0700825 16 => 64 KB
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700826 15 => 32 KB
827 14 => 16 KB
Alistair John Strachan794543a2007-05-08 00:31:15 -0700828 13 => 8 KB
829 12 => 4 KB
830
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700831config LOG_CPU_MAX_BUF_SHIFT
832 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
Geert Uytterhoeven2240a312014-10-13 15:51:11 -0700833 depends on SMP
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700834 range 0 21
835 default 12 if !BASE_SMALL
836 default 0 if BASE_SMALL
Josh Triplett361e9df2014-10-03 16:00:54 -0700837 depends on PRINTK
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700838 help
839 This option allows to increase the default ring buffer size
840 according to the number of CPUs. The value defines the contribution
841 of each CPU as a power of 2. The used space is typically only few
842 lines however it might be much more when problems are reported,
843 e.g. backtraces.
844
845 The increased size means that a new buffer has to be allocated and
846 the original static one is unused. It makes sense only on systems
847 with more CPUs. Therefore this value is used only when the sum of
848 contributions is greater than the half of the default kernel ring
849 buffer as defined by LOG_BUF_SHIFT. The default values are set
850 so that more than 64 CPUs are needed to trigger the allocation.
851
852 Also this option is ignored when "log_buf_len" kernel parameter is
853 used as it forces an exact (power of two) size of the ring buffer.
854
855 The number of possible CPUs is used for this computation ignoring
Geert Uytterhoeven5e0d8d52016-06-05 10:47:02 +0200856 hotplugging making the computation optimal for the worst case
857 scenario while allowing a simple algorithm to be used from bootup.
Luis R. Rodriguez23b28992014-08-06 16:08:56 -0700858
859 Examples shift values and their meaning:
860 17 => 128 KB for each CPU
861 16 => 64 KB for each CPU
862 15 => 32 KB for each CPU
863 14 => 16 KB for each CPU
864 13 => 8 KB for each CPU
865 12 => 4 KB for each CPU
866
Petr Mladek427934b2016-05-20 17:00:39 -0700867config NMI_LOG_BUF_SHIFT
868 int "Temporary per-CPU NMI log buffer size (12 => 4KB, 13 => 8KB)"
869 range 10 21
870 default 13
871 depends on PRINTK_NMI
872 help
873 Select the size of a per-CPU buffer where NMI messages are temporary
874 stored. They are copied to the main log buffer in a safe context
875 to avoid a deadlock. The value defines the size as a power of 2.
876
877 NMI messages are rare and limited. The largest one is when
878 a backtrace is printed. It usually fits into 4KB. Select
879 8KB if you want to be on the safe side.
880
881 Examples:
882 17 => 128 KB for each CPU
883 16 => 64 KB for each CPU
884 15 => 32 KB for each CPU
885 14 => 16 KB for each CPU
886 13 => 8 KB for each CPU
887 12 => 4 KB for each CPU
888
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800889#
890# Architectures with an unreliable sched_clock() should select this:
891#
892config HAVE_UNSTABLE_SCHED_CLOCK
893 bool
894
Stephen Boyd38ff87f2013-06-01 23:39:40 -0700895config GENERIC_SCHED_CLOCK
896 bool
897
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200898#
899# For architectures that want to enable the support for NUMA-affine scheduler
900# balancing logic:
901#
902config ARCH_SUPPORTS_NUMA_BALANCING
903 bool
904
Peter Zijlstrabe5e6102013-11-18 18:27:06 +0100905#
Mel Gorman72b252a2015-09-04 15:47:32 -0700906# For architectures that prefer to flush all TLBs after a number of pages
907# are unmapped instead of sending one IPI per page to flush. The architecture
908# must provide guarantees on what happens if a clean TLB cache entry is
909# written after the unmap. Details are in mm/rmap.c near the check for
910# should_defer_flush. The architecture should also consider if the full flush
911# and the refill costs are offset by the savings of sending fewer IPIs.
912config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
913 bool
914
915#
Peter Zijlstrabe5e6102013-11-18 18:27:06 +0100916# For architectures that know their GCC __int128 support is sound
917#
918config ARCH_SUPPORTS_INT128
919 bool
920
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200921# For architectures that (ab)use NUMA to represent different memory regions
922# all cpu-local but of different latencies, such as SuperH.
923#
924config ARCH_WANT_NUMA_VARIABLE_LOCALITY
925 bool
926
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200927config NUMA_BALANCING
928 bool "Memory placement aware NUMA scheduler"
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200929 depends on ARCH_SUPPORTS_NUMA_BALANCING
930 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
931 depends on SMP && NUMA && MIGRATION
932 help
933 This option adds support for automatic NUMA aware memory/task placement.
934 The mechanism is quite primitive and is based on migrating memory when
Paul Gortmaker6d56a412013-08-13 11:06:50 -0400935 it has references to the node the task is running on.
Andrea Arcangelibe3a7282012-10-04 01:50:47 +0200936
937 This system will be inactive on UMA systems.
938
Aneesh Kumar K.V6f7c97e2014-12-10 15:43:37 -0800939config NUMA_BALANCING_DEFAULT_ENABLED
940 bool "Automatically enable NUMA aware memory/task placement"
941 default y
942 depends on NUMA_BALANCING
943 help
944 If set, automatic NUMA balancing will be enabled if running on a NUMA
945 machine.
946
Li Zefan23964d22009-01-15 13:50:58 -0800947menuconfig CGROUPS
Christoph Jaeger6341e622014-12-20 15:41:11 -0500948 bool "Control Group support"
Tejun Heo2bd59d42014-02-11 11:52:49 -0500949 select KERNFS
Paul Menageddbcc7e2007-10-18 23:39:30 -0700950 help
Li Zefan23964d22009-01-15 13:50:58 -0800951 This option adds support for grouping sets of processes together, for
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800952 use with process control subsystems such as Cpusets, CFS, memory
953 controls or device isolation.
954 See
KAMEZAWA Hiroyuki5cdc38f2009-01-07 18:07:30 -0800955 - Documentation/scheduler/sched-design-CFS.txt (CFS)
seokhoon.yoon9991a9c2016-08-02 14:03:13 -0700956 - Documentation/cgroup-v1/ (features for grouping, isolation
Li Zefan45ce80f2009-01-15 13:50:59 -0800957 and resource control)
Paul Menageddbcc7e2007-10-18 23:39:30 -0700958
959 Say N if unsure.
960
Li Zefan23964d22009-01-15 13:50:58 -0800961if CGROUPS
962
Johannes Weiner3e32cb22014-12-10 15:42:31 -0800963config PAGE_COUNTER
964 bool
965
Andrew Mortonc255a452012-07-31 16:43:02 -0700966config MEMCG
Johannes Weinera0166ec2015-12-17 17:19:56 -0500967 bool "Memory controller"
Johannes Weiner3e32cb22014-12-10 15:42:31 -0800968 select PAGE_COUNTER
Tejun Heo79bd9812013-11-22 18:20:42 -0500969 select EVENTFD
Balbir Singh00f0b822008-03-04 14:28:39 -0800970 help
Johannes Weinera0166ec2015-12-17 17:19:56 -0500971 Provides control over the memory footprint of tasks in a cgroup.
Balbir Singh00f0b822008-03-04 14:28:39 -0800972
Andrew Mortonc255a452012-07-31 16:43:02 -0700973config MEMCG_SWAP
Johannes Weinera0166ec2015-12-17 17:19:56 -0500974 bool "Swap controller"
Andrew Mortonc255a452012-07-31 16:43:02 -0700975 depends on MEMCG && SWAP
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -0800976 help
Johannes Weinera0166ec2015-12-17 17:19:56 -0500977 Provides control over the swap space consumed by tasks in a cgroup.
978
Andrew Mortonc255a452012-07-31 16:43:02 -0700979config MEMCG_SWAP_ENABLED
Johannes Weinera0166ec2015-12-17 17:19:56 -0500980 bool "Swap controller enabled by default"
Andrew Mortonc255a452012-07-31 16:43:02 -0700981 depends on MEMCG_SWAP
Michal Hockoa42c3902010-11-24 12:57:08 -0800982 default y
983 help
984 Memory Resource Controller Swap Extension comes with its price in
985 a bigger memory consumption. General purpose distribution kernels
Jim Cromie43d547f2010-12-17 14:32:36 -0700986 which want to enable the feature but keep it disabled by default
Michal Hocko07555ac2013-08-22 16:35:46 -0700987 and let the user enable it by swapaccount=1 boot command line
Michal Hockoa42c3902010-11-24 12:57:08 -0800988 parameter should have this option unselected.
989 For those who want to have the feature enabled by default should
990 select this option (if, for some reason, they need to disable it
WANG Cong00a66d22011-07-25 17:12:12 -0700991 then swapaccount=0 does the trick).
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -0800992
Johannes Weiner6bf024e2015-12-17 17:19:57 -0500993config BLK_CGROUP
994 bool "IO controller"
995 depends on BLOCK
Aneesh Kumar K.V2bc64a22012-07-31 16:42:12 -0700996 default n
Johannes Weiner6bf024e2015-12-17 17:19:57 -0500997 ---help---
998 Generic block IO controller cgroup interface. This is the common
999 cgroup interface which should be used by various IO controlling
1000 policies.
Aneesh Kumar K.V2bc64a22012-07-31 16:42:12 -07001001
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001002 Currently, CFQ IO scheduler uses it to recognize task groups and
1003 control disk bandwidth allocation (proportional time slice allocation)
1004 to such task groups. It is also used by bio throttling logic in
1005 block layer to implement upper limit in IO rates on a device.
Stephane Eraniane5d13672011-02-14 11:20:01 +02001006
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001007 This option only enables generic Block IO controller infrastructure.
1008 One needs to also enable actual IO controlling logic/policy. For
1009 enabling proportional weight division of disk bandwidth in CFQ, set
1010 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
1011 CONFIG_BLK_DEV_THROTTLING=y.
1012
seokhoon.yoon9991a9c2016-08-02 14:03:13 -07001013 See Documentation/cgroup-v1/blkio-controller.txt for more information.
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001014
1015config DEBUG_BLK_CGROUP
1016 bool "IO controller debugging"
1017 depends on BLK_CGROUP
1018 default n
1019 ---help---
1020 Enable some debugging help. Currently it exports additional stat
1021 files in a cgroup which can be useful for debugging.
1022
1023config CGROUP_WRITEBACK
1024 bool
1025 depends on MEMCG && BLK_CGROUP
1026 default y
Stephane Eraniane5d13672011-02-14 11:20:01 +02001027
Dhaval Giani7c941432010-01-20 13:26:18 +01001028menuconfig CGROUP_SCHED
Johannes Weinera0166ec2015-12-17 17:19:56 -05001029 bool "CPU controller"
Dhaval Giani7c941432010-01-20 13:26:18 +01001030 default n
1031 help
1032 This feature lets CPU scheduler recognize task groups and control CPU
1033 bandwidth allocation to such task groups. It uses cgroups to group
1034 tasks.
1035
1036if CGROUP_SCHED
1037config FAIR_GROUP_SCHED
1038 bool "Group scheduling for SCHED_OTHER"
1039 depends on CGROUP_SCHED
1040 default CGROUP_SCHED
1041
Paul Turnerab84d312011-07-21 09:43:28 -07001042config CFS_BANDWIDTH
1043 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
Paul Turnerab84d312011-07-21 09:43:28 -07001044 depends on FAIR_GROUP_SCHED
1045 default n
1046 help
1047 This option allows users to define CPU bandwidth rates (limits) for
1048 tasks running within the fair group scheduler. Groups with no limit
1049 set are considered to be unconstrained and will run with no
1050 restriction.
1051 See tip/Documentation/scheduler/sched-bwc.txt for more information.
1052
Dhaval Giani7c941432010-01-20 13:26:18 +01001053config RT_GROUP_SCHED
1054 bool "Group scheduling for SCHED_RR/FIFO"
Dhaval Giani7c941432010-01-20 13:26:18 +01001055 depends on CGROUP_SCHED
1056 default n
1057 help
1058 This feature lets you explicitly allocate real CPU bandwidth
Li Zefan32bd7eb2010-03-24 13:17:19 +08001059 to task groups. If enabled, it will also make it impossible to
Dhaval Giani7c941432010-01-20 13:26:18 +01001060 schedule realtime tasks for non-root users until you allocate
1061 realtime bandwidth for them.
1062 See Documentation/scheduler/sched-rt-group.txt for more information.
1063
1064endif #CGROUP_SCHED
1065
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001066config CGROUP_PIDS
1067 bool "PIDs controller"
1068 help
1069 Provides enforcement of process number limits in the scope of a
1070 cgroup. Any attempt to fork more processes than is allowed in the
1071 cgroup will fail. PIDs are fundamentally a global resource because it
1072 is fairly trivial to reach PID exhaustion before you reach even a
1073 conservative kmemcg limit. As a result, it is possible to grind a
1074 system to halt without being limited by other cgroup policies. The
Parav Pandit6cc578d2016-03-05 11:30:56 +05301075 PIDs controller is designed to stop this from happening.
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001076
1077 It should be noted that organisational operations (such as attaching
Parav Pandit6cc578d2016-03-05 11:30:56 +05301078 to a cgroup hierarchy will *not* be blocked by the PIDs controller),
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001079 since the PIDs limit only affects a process's ability to fork, not to
1080 attach to a cgroup.
1081
1082config CGROUP_FREEZER
1083 bool "Freezer controller"
1084 help
1085 Provides a way to freeze and unfreeze all tasks in a
1086 cgroup.
1087
Johannes Weiner489c2a22016-01-20 15:02:41 -08001088 This option affects the ORIGINAL cgroup interface. The cgroup2 memory
1089 controller includes important in-kernel memory consumers per default.
1090
1091 If you're using cgroup2, say N.
1092
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001093config CGROUP_HUGETLB
1094 bool "HugeTLB controller"
1095 depends on HUGETLB_PAGE
1096 select PAGE_COUNTER
Vivek Goyalafc24d42010-04-26 19:27:56 +02001097 default n
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001098 help
1099 Provides a cgroup controller for HugeTLB pages.
1100 When you enable this, you can put a per cgroup limit on HugeTLB usage.
1101 The limit is enforced during page fault. Since HugeTLB doesn't
1102 support page reclaim, enforcing the limit at page fault time implies
1103 that, the application will get SIGBUS signal if it tries to access
1104 HugeTLB pages beyond its limit. This requires the application to know
1105 beforehand how much HugeTLB pages it would require for its use. The
1106 control group is tracked in the third page lru pointer. This means
1107 that we cannot use the controller with huge page less than 3 pages.
Vivek Goyalafc24d42010-04-26 19:27:56 +02001108
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001109config CPUSETS
1110 bool "Cpuset controller"
1111 help
1112 This option will let you create and manage CPUSETs which
1113 allow dynamically partitioning a system into sets of CPUs and
1114 Memory Nodes and assigning tasks to run only within those sets.
1115 This is primarily useful on large SMP or NUMA systems.
Vivek Goyalafc24d42010-04-26 19:27:56 +02001116
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001117 Say N if unsure.
Vivek Goyalafc24d42010-04-26 19:27:56 +02001118
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001119config PROC_PID_CPUSET
1120 bool "Include legacy /proc/<pid>/cpuset file"
1121 depends on CPUSETS
Tejun Heo89e9b9e2015-05-22 17:13:36 -04001122 default y
1123
Johannes Weiner6bf024e2015-12-17 17:19:57 -05001124config CGROUP_DEVICE
1125 bool "Device controller"
1126 help
1127 Provides a cgroup controller implementing whitelists for
1128 devices which a process in the cgroup can mknod or open.
1129
1130config CGROUP_CPUACCT
1131 bool "Simple CPU accounting controller"
1132 help
1133 Provides a simple controller for monitoring the
1134 total CPU consumed by the tasks in a cgroup.
1135
1136config CGROUP_PERF
1137 bool "Perf controller"
1138 depends on PERF_EVENTS
1139 help
1140 This option extends the perf per-cpu mode to restrict monitoring
1141 to threads which belong to the cgroup specified and run on the
1142 designated cpu.
1143
1144 Say N if unsure.
1145
1146config CGROUP_DEBUG
1147 bool "Example controller"
1148 default n
1149 help
1150 This option enables a simple controller that exports
1151 debugging information about the cgroups framework.
1152
1153 Say N.
1154
Li Zefan23964d22009-01-15 13:50:58 -08001155endif # CGROUPS
KAMEZAWA Hiroyukic0777192009-01-07 18:07:57 -08001156
Cyrill Gorcunov067bce12012-01-12 17:20:49 -08001157config CHECKPOINT_RESTORE
1158 bool "Checkpoint/restore support" if EXPERT
Iago López Galeiras2e13ba52015-06-25 15:00:57 -07001159 select PROC_CHILDREN
Cyrill Gorcunov067bce12012-01-12 17:20:49 -08001160 default n
1161 help
1162 Enables additional kernel features in a sake of checkpoint/restore.
1163 In particular it adds auxiliary prctl codes to setup process text,
1164 data and heap segment sizes, and a few additional /proc filesystem
1165 entries.
1166
1167 If unsure, say N here.
1168
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001169menuconfig NAMESPACES
David Rientjes6a108a12011-01-20 14:44:16 -08001170 bool "Namespaces support" if EXPERT
Iulia Manda28138932015-04-15 16:16:41 -07001171 depends on MULTIUSER
David Rientjes6a108a12011-01-20 14:44:16 -08001172 default !EXPERT
Pavel Emelyanovc5289a692008-02-08 04:18:19 -08001173 help
1174 Provides the way to make tasks work with different objects using
1175 the same id. For example same IPC id may refer to different objects
1176 or same user id or pid may refer to different tasks when used in
1177 different namespaces.
1178
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001179if NAMESPACES
1180
Pavel Emelyanov58bfdd6d2008-02-08 04:18:21 -08001181config UTS_NS
1182 bool "UTS namespace"
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001183 default y
Pavel Emelyanov58bfdd6d2008-02-08 04:18:21 -08001184 help
1185 In this namespace tasks see different info provided with the
1186 uname() system call
1187
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -08001188config IPC_NS
1189 bool "IPC namespace"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001190 depends on (SYSVIPC || POSIX_MQUEUE)
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001191 default y
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -08001192 help
1193 In this namespace tasks work with IPC ids which correspond to
Serge E. Hallyn614b84c2009-04-06 19:01:08 -07001194 different IPC objects in different namespaces.
Pavel Emelyanovae5e1b22008-02-08 04:18:22 -08001195
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -08001196config USER_NS
Kees Cook19c92392012-10-02 11:19:29 -07001197 bool "User namespace"
Eric W. Biederman5673a942011-11-17 10:23:55 -08001198 default n
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -08001199 help
1200 This allows containers, i.e. vservers, to use user namespaces
1201 to provide different user info for different servers.
Eric W. Biedermane11f0ae2013-01-25 16:48:31 -08001202
1203 When user namespaces are enabled in the kernel it is
Johannes Weinerd886f4e2016-01-20 15:02:47 -08001204 recommended that the MEMCG option also be enabled and that
1205 user-space use the memory control groups to limit the amount
1206 of memory a memory unprivileged users can use.
Eric W. Biedermane11f0ae2013-01-25 16:48:31 -08001207
Pavel Emelyanovaee16ce2008-02-08 04:18:23 -08001208 If unsure, say N.
1209
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -08001210config PID_NS
Daniel Lezcano9bd38c22010-10-27 15:34:37 -07001211 bool "PID Namespaces"
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001212 default y
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -08001213 help
Heikki Orsila12d2b8f2008-07-06 15:48:02 +03001214 Support process id namespaces. This allows having multiple
Matt LaPlante692105b2009-01-26 11:12:25 +01001215 processes with the same pid as long as they are in different
Pavel Emelyanov74bd59b2008-02-08 04:18:24 -08001216 pid namespaces. This is a building block of containers.
1217
Matt Helsleyd6eb6332009-01-26 12:25:55 -08001218config NET_NS
1219 bool "Network namespace"
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001220 depends on NET
Daniel Lezcano17a6d442010-10-27 15:34:37 -07001221 default y
Matt Helsleyd6eb6332009-01-26 12:25:55 -08001222 help
1223 Allow user space to create what appear to be multiple instances
1224 of the network stack.
1225
Daniel Lezcano8dd2a822010-10-27 15:34:38 -07001226endif # NAMESPACES
1227
Mike Galbraith5091faa2010-11-30 14:18:03 +01001228config SCHED_AUTOGROUP
1229 bool "Automatic process group scheduling"
Mike Galbraith5091faa2010-11-30 14:18:03 +01001230 select CGROUPS
1231 select CGROUP_SCHED
1232 select FAIR_GROUP_SCHED
1233 help
1234 This option optimizes the scheduler for common desktop workloads by
1235 automatically creating and populating task groups. This separation
1236 of workloads isolates aggressive CPU burners (like build jobs) from
1237 desktop applications. Task group autogeneration is currently based
1238 upon task session.
1239
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001240config SYSFS_DEPRECATED
Ferenc Wagner5d6a4ea2011-01-10 19:04:22 +01001241 bool "Enable deprecated sysfs features to support old userspace tools"
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001242 depends on SYSFS
1243 default n
1244 help
1245 This option adds code that switches the layout of the "block" class
1246 devices, to not show up in /sys/class/block/, but only in
1247 /sys/block/.
1248
1249 This switch is only active when the sysfs.deprecated=1 boot option is
1250 passed or the SYSFS_DEPRECATED_V2 option is set.
1251
1252 This option allows new kernels to run on old distributions and tools,
1253 which might get confused by /sys/class/block/. Since 2007/2008 all
1254 major distributions and tools handle this just fine.
1255
1256 Recent distributions and userspace tools after 2009/2010 depend on
1257 the existence of /sys/class/block/, and will not work with this
1258 option enabled.
1259
1260 Only if you are using a new kernel on an old distribution, you might
1261 need to say Y here.
1262
1263config SYSFS_DEPRECATED_V2
Ferenc Wagner5d6a4ea2011-01-10 19:04:22 +01001264 bool "Enable deprecated sysfs features by default"
Daniel Lezcano7af37be2010-10-27 15:34:41 -07001265 default n
1266 depends on SYSFS
1267 depends on SYSFS_DEPRECATED
1268 help
1269 Enable deprecated sysfs by default.
1270
1271 See the CONFIG_SYSFS_DEPRECATED option for more details about this
1272 option.
1273
1274 Only if you are using a new kernel on an old distribution, you might
1275 need to say Y here. Even then, odds are you would not need it
1276 enabled, you can always pass the boot option if absolutely necessary.
1277
1278config RELAY
1279 bool "Kernel->user space relay support (formerly relayfs)"
1280 help
1281 This option enables support for relay interface support in
1282 certain file systems (such as debugfs).
1283 It is designed to provide an efficient mechanism for tools and
1284 facilities to relay large amounts of data from kernel space to
1285 user space.
1286
1287 If unsure, say N.
1288
Dimitri Gorokhovikf9916332007-03-06 01:42:17 -08001289config BLK_DEV_INITRD
1290 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
1291 depends on BROKEN || !FRV
1292 help
1293 The initial RAM filesystem is a ramfs which is loaded by the
1294 boot loader (loadlin or lilo) and that is mounted as root
1295 before the normal boot procedure. It is typically used to
1296 load modules needed to mount the "real" root file system,
1297 etc. See <file:Documentation/initrd.txt> for details.
1298
1299 If RAM disk support (BLK_DEV_RAM) is also included, this
1300 also enables initial RAM disk (initrd) support and adds
1301 15 Kbytes (more on some other architectures) to the kernel size.
1302
1303 If unsure say Y.
1304
Jean-Paul Samanc33df4e2007-02-10 01:44:43 -08001305if BLK_DEV_INITRD
1306
Sam Ravnborgdbec4862005-08-10 20:44:50 +02001307source "usr/Kconfig"
1308
Jean-Paul Samanc33df4e2007-02-10 01:44:43 -08001309endif
1310
Arnd Bergmann877417e2016-04-25 17:35:27 +02001311choice
1312 prompt "Compiler optimization level"
1313 default CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
1314
1315config CC_OPTIMIZE_FOR_PERFORMANCE
1316 bool "Optimize for performance"
1317 help
1318 This is the default optimization level for the kernel, building
1319 with the "-O2" compiler flag for best performance and most
1320 helpful compile-time warnings.
1321
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001322config CC_OPTIMIZE_FOR_SIZE
Ingo Molnar96fffeb2008-04-28 01:39:43 +02001323 bool "Optimize for size"
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001324 help
Masahiro Yamada31a4af72014-08-05 14:43:07 +09001325 Enabling this option will pass "-Os" instead of "-O2" to
1326 your compiler resulting in a smaller kernel.
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001327
Kirill Smelkov3a55fb02012-11-02 15:41:01 +04001328 If unsure, say N.
Linus Torvaldsc45b4f12005-12-14 18:52:21 -08001329
Arnd Bergmann877417e2016-04-25 17:35:27 +02001330endchoice
1331
Randy Dunlap08470622006-09-30 23:28:13 -07001332config SYSCTL
1333 bool
1334
Randy Dunlapb943c462009-03-10 12:55:46 -07001335config ANON_INODES
1336 bool
1337
Mike Frysinger657a5202013-04-30 15:28:45 -07001338config HAVE_UID16
1339 bool
1340
1341config SYSCTL_EXCEPTION_TRACE
1342 bool
1343 help
1344 Enable support for /proc/sys/debug/exception-trace.
1345
1346config SYSCTL_ARCH_UNALIGN_NO_WARN
1347 bool
1348 help
1349 Enable support for /proc/sys/kernel/ignore-unaligned-usertrap
1350 Allows arch to define/use @no_unaligned_warning to possibly warn
1351 about unaligned access emulation going on under the hood.
1352
1353config SYSCTL_ARCH_UNALIGN_ALLOW
1354 bool
1355 help
1356 Enable support for /proc/sys/kernel/unaligned-trap
1357 Allows arches to define/use @unaligned_enabled to runtime toggle
1358 the unaligned access emulation.
1359 see arch/parisc/kernel/unaligned.c for reference
1360
Mike Frysinger657a5202013-04-30 15:28:45 -07001361config HAVE_PCSPKR_PLATFORM
1362 bool
1363
Alexei Starovoitovf89b7752014-10-23 18:41:08 -07001364# interpreter that classic socket filters depend on
1365config BPF
1366 bool
1367
David Rientjes6a108a12011-01-20 14:44:16 -08001368menuconfig EXPERT
1369 bool "Configure standard kernel features (expert users)"
Josh Triplettf505c552011-06-05 18:23:58 -07001370 # Unhide debug options, to make the on-by-default options visible
1371 select DEBUG_KERNEL
Linus Torvalds1da177e2005-04-16 15:20:36 -07001372 help
1373 This option allows certain base kernel options and settings
1374 to be disabled or tweaked. This is for specialized
1375 environments which can tolerate a "non-standard" kernel.
1376 Only use this if you really know what you are doing.
1377
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001378config UID16
David Rientjes6a108a12011-01-20 14:44:16 -08001379 bool "Enable 16-bit UID system calls" if EXPERT
Iulia Manda28138932015-04-15 16:16:41 -07001380 depends on HAVE_UID16 && MULTIUSER
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001381 default y
1382 help
1383 This enables the legacy 16-bit UID syscall wrappers.
1384
Iulia Manda28138932015-04-15 16:16:41 -07001385config MULTIUSER
1386 bool "Multiple users, groups and capabilities support" if EXPERT
1387 default y
1388 help
1389 This option enables support for non-root users, groups and
1390 capabilities.
1391
1392 If you say N here, all processes will run with UID 0, GID 0, and all
1393 possible capabilities. Saying N here also compiles out support for
1394 system calls related to UIDs, GIDs, and capabilities, such as setuid,
1395 setgid, and capset.
1396
1397 If unsure, say Y here.
1398
Fabian Frederickf6187762014-06-04 16:11:12 -07001399config SGETMASK_SYSCALL
1400 bool "sgetmask/ssetmask syscalls support" if EXPERT
1401 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH
1402 ---help---
1403 sys_sgetmask and sys_ssetmask are obsolete system calls
1404 no longer supported in libc but still enabled by default in some
1405 architectures.
1406
1407 If unsure, leave the default option here.
1408
Fabian Frederick6af9f7b2014-04-03 14:48:25 -07001409config SYSFS_SYSCALL
1410 bool "Sysfs syscall support" if EXPERT
1411 default y
1412 ---help---
1413 sys_sysfs is an obsolete system call no longer supported in libc.
1414 Note that disabling this option is more secure but might break
1415 compatibility with some systems.
1416
1417 If unsure say Y here.
1418
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001419config SYSCTL_SYSCALL
David Rientjes6a108a12011-01-20 14:44:16 -08001420 bool "Sysctl syscall support" if EXPERT
Eric W. Biederman26a70342009-11-05 05:26:41 -08001421 depends on PROC_SYSCTL
WANG Congc736de62011-11-02 13:39:25 -07001422 default n
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001423 select SYSCTL
1424 ---help---
Eric W. Biederman13bb7e32006-11-08 17:44:51 -08001425 sys_sysctl uses binary paths that have been found challenging
1426 to properly maintain and use. The interface in /proc/sys
1427 using paths with ascii names is now the primary path to this
1428 information.
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001429
Eric W. Biederman13bb7e32006-11-08 17:44:51 -08001430 Almost nothing using the binary sysctl interface so if you are
1431 trying to save some space it is probably safe to disable this,
1432 making your kernel marginally smaller.
Eric W. Biedermanb89a8172006-09-27 01:51:04 -07001433
WANG Congc736de62011-11-02 13:39:25 -07001434 If unsure say N here.
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001435
Linus Torvalds1da177e2005-04-16 15:20:36 -07001436config KALLSYMS
David Rientjes6a108a12011-01-20 14:44:16 -08001437 bool "Load all symbols for debugging/ksymoops" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001438 default y
1439 help
1440 Say Y here to let the kernel print out symbolic crash information and
1441 symbolic stack backtraces. This increases the size of the kernel
1442 somewhat, as all symbols have to be loaded into the kernel image.
1443
1444config KALLSYMS_ALL
1445 bool "Include all symbols in kallsyms"
1446 depends on DEBUG_KERNEL && KALLSYMS
1447 help
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001448 Normally kallsyms only contains the symbols of functions for nicer
1449 OOPS messages and backtraces (i.e., symbols from the text and inittext
1450 sections). This is sufficient for most cases. And only in very rare
1451 cases (e.g., when a debugger is used) all symbols are required (e.g.,
1452 names of variables from the data sections, etc).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001453
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001454 This option makes sure that all symbols are loaded into the kernel
1455 image (i.e., symbols from all sections) in cost of increased kernel
1456 size (depending on the kernel configuration, it may be 300KiB or
1457 something like this).
Linus Torvalds1da177e2005-04-16 15:20:36 -07001458
Artem Bityutskiy71a83ec2011-04-05 13:24:57 +03001459 Say N unless you really need all symbols.
Matt Mackalld59745c2005-05-01 08:59:02 -07001460
Ard Biesheuvel4d5d5662016-03-15 14:58:12 -07001461config KALLSYMS_ABSOLUTE_PERCPU
1462 bool
Randy Dunlap076501f2016-07-06 16:06:53 -07001463 depends on KALLSYMS
Ard Biesheuvel4d5d5662016-03-15 14:58:12 -07001464 default X86_64 && SMP
1465
Ard Biesheuvel2213e9a2016-03-15 14:58:19 -07001466config KALLSYMS_BASE_RELATIVE
1467 bool
1468 depends on KALLSYMS
1469 default !IA64 && !(TILE && 64BIT)
1470 help
1471 Instead of emitting them as absolute values in the native word size,
1472 emit the symbol references in the kallsyms table as 32-bit entries,
1473 each containing a relative value in the range [base, base + U32_MAX]
1474 or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either
1475 an absolute value in the range [0, S32_MAX] or a relative value in the
1476 range [base, base + S32_MAX], where base is the lowest relative symbol
1477 address encountered in the image.
1478
1479 On 64-bit builds, this reduces the size of the address table by 50%,
1480 but more importantly, it results in entries whose values are build
1481 time constants, and no relocation pass is required at runtime to fix
1482 up the entries based on the runtime load address of the kernel.
1483
Matt Mackalld59745c2005-05-01 08:59:02 -07001484config PRINTK
1485 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001486 bool "Enable support for printk" if EXPERT
Frederic Weisbecker74876a92012-10-12 18:00:23 +02001487 select IRQ_WORK
Matt Mackalld59745c2005-05-01 08:59:02 -07001488 help
1489 This option enables normal printk support. Removing it
1490 eliminates most of the message strings from the kernel image
1491 and makes the kernel more or less silent. As this makes it
1492 very difficult to diagnose system problems, saying N here is
1493 strongly discouraged.
1494
Petr Mladek42a0bb32016-05-20 17:00:33 -07001495config PRINTK_NMI
1496 def_bool y
1497 depends on PRINTK
1498 depends on HAVE_NMI
1499
Matt Mackallc8538a72005-05-01 08:59:01 -07001500config BUG
David Rientjes6a108a12011-01-20 14:44:16 -08001501 bool "BUG() support" if EXPERT
Matt Mackallc8538a72005-05-01 08:59:01 -07001502 default y
1503 help
1504 Disabling this option eliminates support for BUG and WARN, reducing
1505 the size of your kernel image and potentially quietly ignoring
1506 numerous fatal conditions. You should only consider disabling this
1507 option for embedded systems with no facilities for reporting errors.
1508 Just say Y.
1509
Matt Mackall708e9a72006-01-08 01:05:25 -08001510config ELF_CORE
Alex Kelly046d6622012-10-04 17:15:23 -07001511 depends on COREDUMP
Matt Mackall708e9a72006-01-08 01:05:25 -08001512 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001513 bool "Enable ELF core dumps" if EXPERT
Matt Mackall708e9a72006-01-08 01:05:25 -08001514 help
1515 Enable support for generating core dumps. Disabling saves about 4k.
1516
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001517
Stas Sergeeve5e1d3c2008-05-07 12:39:56 +02001518config PCSPKR_PLATFORM
David Rientjes6a108a12011-01-20 14:44:16 -08001519 bool "Enable PC-Speaker support" if EXPERT
Ralf Baechle8761f1a2011-06-01 19:05:09 +01001520 depends on HAVE_PCSPKR_PLATFORM
Ralf Baechle15f304b2011-06-01 19:04:59 +01001521 select I8253_LOCK
Stas Sergeeve5e1d3c2008-05-07 12:39:56 +02001522 default y
1523 help
1524 This option allows to disable the internal PC-Speaker
1525 support, saving some memory.
1526
Linus Torvalds1da177e2005-04-16 15:20:36 -07001527config BASE_FULL
1528 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001529 bool "Enable full-sized data structures for core" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001530 help
1531 Disabling this option reduces the size of miscellaneous core
1532 kernel data structures. This saves memory on small machines,
1533 but may reduce performance.
1534
1535config FUTEX
David Rientjes6a108a12011-01-20 14:44:16 -08001536 bool "Enable futex support" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001537 default y
Ingo Molnar23f78d4a2006-06-27 02:54:53 -07001538 select RT_MUTEXES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001539 help
1540 Disabling this option will cause the kernel to be built without
1541 support for "fast userspace mutexes". The resulting kernel may not
1542 run glibc-based applications correctly.
1543
Heiko Carstens03b8c7b2014-03-02 13:09:47 +01001544config HAVE_FUTEX_CMPXCHG
1545 bool
Josh Triplett62b4d202014-10-03 16:19:24 -07001546 depends on FUTEX
Heiko Carstens03b8c7b2014-03-02 13:09:47 +01001547 help
1548 Architectures should select this if futex_atomic_cmpxchg_inatomic()
1549 is implemented and always working. This removes a couple of runtime
1550 checks.
1551
Linus Torvalds1da177e2005-04-16 15:20:36 -07001552config EPOLL
David Rientjes6a108a12011-01-20 14:44:16 -08001553 bool "Enable eventpoll support" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001554 default y
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001555 select ANON_INODES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001556 help
1557 Disabling this option will cause the kernel to be built without
1558 support for epoll family of system calls.
1559
Davide Libenzifba2afa2007-05-10 22:23:13 -07001560config SIGNALFD
David Rientjes6a108a12011-01-20 14:44:16 -08001561 bool "Enable signalfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001562 select ANON_INODES
Davide Libenzifba2afa2007-05-10 22:23:13 -07001563 default y
1564 help
1565 Enable the signalfd() system call that allows to receive signals
1566 on a file descriptor.
1567
1568 If unsure, say Y.
1569
Davide Libenzib215e282007-05-10 22:23:16 -07001570config TIMERFD
David Rientjes6a108a12011-01-20 14:44:16 -08001571 bool "Enable timerfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001572 select ANON_INODES
Davide Libenzib215e282007-05-10 22:23:16 -07001573 default y
1574 help
1575 Enable the timerfd() system call that allows to receive timer
1576 events on a file descriptor.
1577
1578 If unsure, say Y.
1579
Davide Libenzie1ad7462007-05-10 22:23:19 -07001580config EVENTFD
David Rientjes6a108a12011-01-20 14:44:16 -08001581 bool "Enable eventfd() system call" if EXPERT
Adrian Bunk448e3ce2007-07-31 00:39:10 -07001582 select ANON_INODES
Davide Libenzie1ad7462007-05-10 22:23:19 -07001583 default y
1584 help
1585 Enable the eventfd() system call that allows to receive both
1586 kernel notification (ie. KAIO) or userspace notifications.
1587
1588 If unsure, say Y.
1589
Alexei Starovoitovf89b7752014-10-23 18:41:08 -07001590# syscall, maps, verifier
1591config BPF_SYSCALL
Ingo Molnare1abf2c2015-04-02 15:51:39 +02001592 bool "Enable bpf() system call"
Alexei Starovoitovf89b7752014-10-23 18:41:08 -07001593 select ANON_INODES
1594 select BPF
1595 default n
1596 help
1597 Enable the bpf() system call that allows to manipulate eBPF
1598 programs and maps via file descriptors.
1599
Linus Torvalds1da177e2005-04-16 15:20:36 -07001600config SHMEM
David Rientjes6a108a12011-01-20 14:44:16 -08001601 bool "Use full shmem filesystem" if EXPERT
Linus Torvalds1da177e2005-04-16 15:20:36 -07001602 default y
1603 depends on MMU
1604 help
1605 The shmem is an internal filesystem used to manage shared memory.
1606 It is backed by swap and manages resource limits. It is also exported
1607 to userspace as tmpfs if TMPFS is enabled. Disabling this
1608 option replaces shmem and tmpfs with the much simpler ramfs code,
1609 which may be appropriate on small systems without swap.
1610
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001611config AIO
David Rientjes6a108a12011-01-20 14:44:16 -08001612 bool "Enable AIO support" if EXPERT
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001613 default y
1614 help
1615 This option enables POSIX asynchronous I/O which may by used
Mike Frysinger657a5202013-04-30 15:28:45 -07001616 by some high performance threaded applications. Disabling
1617 this option saves about 7k.
1618
Josh Triplettd3ac21c2014-08-17 19:41:09 -05001619config ADVISE_SYSCALLS
1620 bool "Enable madvise/fadvise syscalls" if EXPERT
1621 default y
1622 help
1623 This option enables the madvise and fadvise syscalls, used by
1624 applications to advise the kernel about their future memory or file
1625 usage, improving performance. If building an embedded system where no
1626 applications use these syscalls, you can disable this option to save
1627 space.
1628
Andrea Arcangelia14c1512015-09-04 15:46:54 -07001629config USERFAULTFD
1630 bool "Enable userfaultfd() system call"
1631 select ANON_INODES
Andrea Arcangelia14c1512015-09-04 15:46:54 -07001632 depends on MMU
1633 help
1634 Enable the userfaultfd() system call that allows to intercept and
1635 handle page faults in userland.
1636
Mike Frysinger657a5202013-04-30 15:28:45 -07001637config PCI_QUIRKS
1638 default y
1639 bool "Enable PCI quirk workarounds" if EXPERT
1640 depends on PCI
1641 help
1642 This enables workarounds for various PCI chipset
1643 bugs/quirks. Disable this only if your target machine is
1644 unaffected by PCI quirks.
Thomas Petazzoniebf3f092008-10-15 22:05:12 -07001645
Mathieu Desnoyers5b25b132015-09-11 13:07:39 -07001646config MEMBARRIER
1647 bool "Enable membarrier() system call" if EXPERT
1648 default y
1649 help
1650 Enable the membarrier() system call that allows issuing memory
1651 barriers across all running threads, which can be used to distribute
1652 the cost of user-space memory barriers asymmetrically by transforming
1653 pairs of memory barriers into pairs consisting of membarrier() and a
1654 compiler barrier.
1655
1656 If unsure, say Y.
1657
Randy Dunlap6befe5f2011-04-26 12:33:21 -07001658config EMBEDDED
1659 bool "Embedded system"
Josh Triplett5d2acfc2014-04-07 15:39:09 -07001660 option allnoconfig_y
Randy Dunlap6befe5f2011-04-26 12:33:21 -07001661 select EXPERT
1662 help
1663 This option should be enabled if compiling the kernel for
1664 an embedded system so certain expert options are available
1665 for configuration.
1666
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001667config HAVE_PERF_EVENTS
Thomas Gleixner0793a612008-12-04 20:12:29 +01001668 bool
Mike Frysinger018df722009-06-12 13:17:43 -04001669 help
1670 See tools/perf/design.txt for details.
Thomas Gleixner0793a612008-12-04 20:12:29 +01001671
Peter Zijlstra906010b2009-09-21 16:08:49 +02001672config PERF_USE_VMALLOC
1673 bool
1674 help
1675 See tools/perf/design.txt for details
1676
Ingo Molnar57c0c152009-09-21 12:20:38 +02001677menu "Kernel Performance Events And Counters"
Thomas Gleixner0793a612008-12-04 20:12:29 +01001678
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001679config PERF_EVENTS
Ingo Molnar57c0c152009-09-21 12:20:38 +02001680 bool "Kernel performance events and counters"
Robert Richter392d65a2012-04-05 18:24:44 +02001681 default y if PROFILING
Ingo Molnarcdd6c482009-09-21 12:02:48 +02001682 depends on HAVE_PERF_EVENTS
Ingo Molnar4c59e462008-12-08 19:38:33 +01001683 select ANON_INODES
Peter Zijlstrae360adb2010-10-14 14:01:34 +08001684 select IRQ_WORK
Pranith Kumar83fe27e2014-12-05 11:24:45 -05001685 select SRCU
Thomas Gleixner0793a612008-12-04 20:12:29 +01001686 help
Ingo Molnar57c0c152009-09-21 12:20:38 +02001687 Enable kernel support for various performance events provided
1688 by software and hardware.
Thomas Gleixner0793a612008-12-04 20:12:29 +01001689
Thadeu Lima de Souza Cascardodd770382009-10-30 19:32:25 -02001690 Software events are supported either built-in or via the
Ingo Molnar57c0c152009-09-21 12:20:38 +02001691 use of generic tracepoints.
1692
1693 Most modern CPUs support performance events via performance
1694 counter registers. These registers count the number of certain
Thomas Gleixner0793a612008-12-04 20:12:29 +01001695 types of hw events: such as instructions executed, cachemisses
1696 suffered, or branches mis-predicted - without slowing down the
1697 kernel or applications. These registers can also trigger interrupts
1698 when a threshold number of events have passed - and can thus be
1699 used to profile the code that runs on that CPU.
1700
Ingo Molnar57c0c152009-09-21 12:20:38 +02001701 The Linux Performance Event subsystem provides an abstraction of
Thadeu Lima de Souza Cascardodd770382009-10-30 19:32:25 -02001702 these software and hardware event capabilities, available via a
Ingo Molnar57c0c152009-09-21 12:20:38 +02001703 system call and used by the "perf" utility in tools/perf/. It
Thomas Gleixner0793a612008-12-04 20:12:29 +01001704 provides per task and per CPU counters, and it provides event
1705 capabilities on top of those.
1706
1707 Say Y if unsure.
1708
Peter Zijlstra906010b2009-09-21 16:08:49 +02001709config DEBUG_PERF_USE_VMALLOC
1710 default n
1711 bool "Debug: use vmalloc to back perf mmap() buffers"
Michael Ellermancb3071132015-05-04 16:26:39 +10001712 depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
Peter Zijlstra906010b2009-09-21 16:08:49 +02001713 select PERF_USE_VMALLOC
1714 help
1715 Use vmalloc memory to back perf mmap() buffers.
1716
1717 Mostly useful for debugging the vmalloc code on platforms
1718 that don't require it.
1719
1720 Say N if unsure.
1721
Thomas Gleixner0793a612008-12-04 20:12:29 +01001722endmenu
1723
Christoph Lameterf8891e52006-06-30 01:55:45 -07001724config VM_EVENT_COUNTERS
1725 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001726 bool "Enable VM event counters for /proc/vmstat" if EXPERT
Christoph Lameterf8891e52006-06-30 01:55:45 -07001727 help
Paul Jackson2aea4fb2006-12-22 01:06:10 -08001728 VM event counters are needed for event counts to be shown.
1729 This option allows the disabling of the VM event counters
David Rientjes6a108a12011-01-20 14:44:16 -08001730 on EXPERT systems. /proc/vmstat will only show page counts
Paul Jackson2aea4fb2006-12-22 01:06:10 -08001731 if VM event counters are disabled.
Christoph Lameterf8891e52006-06-30 01:55:45 -07001732
Christoph Lameter41ecc552007-05-09 02:32:44 -07001733config SLUB_DEBUG
1734 default y
David Rientjes6a108a12011-01-20 14:44:16 -08001735 bool "Enable SLUB debugging support" if EXPERT
Christoph Lameterf6acb632008-04-29 16:16:06 -07001736 depends on SLUB && SYSFS
Christoph Lameter41ecc552007-05-09 02:32:44 -07001737 help
1738 SLUB has extensive debug support features. Disabling these can
1739 result in significant savings in code size. This also disables
1740 SLUB sysfs support. /sys/slab will not exist and there will be
1741 no support for cache validation etc.
1742
Randy Dunlapb943c462009-03-10 12:55:46 -07001743config COMPAT_BRK
1744 bool "Disable heap randomization"
1745 default y
1746 help
1747 Randomizing heap placement makes heap exploits harder, but it
1748 also breaks ancient binaries (including anything libc5 based).
1749 This option changes the bootup default to heap randomization
Matt LaPlante692105b2009-01-26 11:12:25 +01001750 disabled, and can be overridden at runtime by setting
Randy Dunlapb943c462009-03-10 12:55:46 -07001751 /proc/sys/kernel/randomize_va_space to 2.
1752
1753 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1754
Christoph Lameter81819f02007-05-06 14:49:36 -07001755choice
1756 prompt "Choose SLAB allocator"
Christoph Lametera0acd822007-07-17 04:03:32 -07001757 default SLUB
Christoph Lameter81819f02007-05-06 14:49:36 -07001758 help
1759 This option allows to select a slab allocator.
1760
1761config SLAB
1762 bool "SLAB"
1763 help
1764 The regular slab allocator that is established and known to work
Christoph Lameter34013882007-05-09 02:32:47 -07001765 well in all environments. It organizes cache hot objects in
Simon Arlott02f56212008-11-05 22:18:19 +00001766 per cpu and per node queues.
Christoph Lameter81819f02007-05-06 14:49:36 -07001767
1768config SLUB
Christoph Lameter81819f02007-05-06 14:49:36 -07001769 bool "SLUB (Unqueued Allocator)"
1770 help
1771 SLUB is a slab allocator that minimizes cache line usage
1772 instead of managing queues of cached objects (SLAB approach).
1773 Per cpu caching is realized using slabs of objects instead
1774 of queues of objects. SLUB can use memory efficiently
Simon Arlott02f56212008-11-05 22:18:19 +00001775 and has enhanced diagnostics. SLUB is the default choice for
1776 a slab allocator.
Christoph Lameter81819f02007-05-06 14:49:36 -07001777
1778config SLOB
David Rientjes6a108a12011-01-20 14:44:16 -08001779 depends on EXPERT
Christoph Lameter81819f02007-05-06 14:49:36 -07001780 bool "SLOB (Simple Allocator)"
1781 help
Matt Mackall37291452008-02-04 22:29:38 -08001782 SLOB replaces the stock allocator with a drastically simpler
1783 allocator. SLOB is generally more space efficient but
1784 does not perform as well on large systems.
Christoph Lameter81819f02007-05-06 14:49:36 -07001785
1786endchoice
1787
Thomas Garnierc7ce4f602016-05-19 17:10:37 -07001788config SLAB_FREELIST_RANDOM
1789 default n
Thomas Garnier210e7a42016-07-26 15:21:59 -07001790 depends on SLAB || SLUB
Thomas Garnierc7ce4f602016-05-19 17:10:37 -07001791 bool "SLAB freelist randomization"
1792 help
Thomas Garnier210e7a42016-07-26 15:21:59 -07001793 Randomizes the freelist order used on creating new pages. This
Thomas Garnierc7ce4f602016-05-19 17:10:37 -07001794 security feature reduces the predictability of the kernel slab
1795 allocator against heap overflows.
1796
Joonsoo Kim345c9052013-06-19 14:05:52 +09001797config SLUB_CPU_PARTIAL
1798 default y
Uwe Kleine-Königb39ffbf2013-07-17 16:54:59 +02001799 depends on SLUB && SMP
Joonsoo Kim345c9052013-06-19 14:05:52 +09001800 bool "SLUB per cpu partial cache"
1801 help
1802 Per cpu partial caches accellerate objects allocation and freeing
1803 that is local to a processor at the price of more indeterminism
1804 in the latency of the free. On overflow these caches will be cleared
1805 which requires the taking of locks that may cause latency spikes.
1806 Typically one would choose no for a realtime system.
1807
Jie Zhangea637632009-12-14 18:00:02 -08001808config MMAP_ALLOW_UNINITIALIZED
1809 bool "Allow mmapped anonymous memory to be uninitialized"
David Rientjes6a108a12011-01-20 14:44:16 -08001810 depends on EXPERT && !MMU
Jie Zhangea637632009-12-14 18:00:02 -08001811 default n
1812 help
1813 Normally, and according to the Linux spec, anonymous memory obtained
1814 from mmap() has it's contents cleared before it is passed to
1815 userspace. Enabling this config option allows you to request that
1816 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
1817 providing a huge performance boost. If this option is not enabled,
1818 then the flag will be ignored.
1819
1820 This is taken advantage of by uClibc's malloc(), and also by
1821 ELF-FDPIC binfmt's brk and stack allocator.
1822
1823 Because of the obvious security issues, this option should only be
1824 enabled on embedded devices where you control what is run in
1825 userspace. Since that isn't generally a problem on no-MMU systems,
1826 it is normally safe to say Y here.
1827
1828 See Documentation/nommu-mmap.txt for more information.
1829
David Howells091f6e22015-07-20 21:16:28 +01001830config SYSTEM_DATA_VERIFICATION
1831 def_bool n
1832 select SYSTEM_TRUSTED_KEYRING
1833 select KEYS
1834 select CRYPTO
David Howellsd43de6c2016-03-03 21:49:27 +00001835 select CRYPTO_RSA
David Howells091f6e22015-07-20 21:16:28 +01001836 select ASYMMETRIC_KEY_TYPE
1837 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
David Howells091f6e22015-07-20 21:16:28 +01001838 select ASN1
1839 select OID_REGISTRY
1840 select X509_CERTIFICATE_PARSER
1841 select PKCS7_MESSAGE_PARSER
Peter Foley82c04ff2014-04-18 15:07:11 -07001842 help
David Howells091f6e22015-07-20 21:16:28 +01001843 Provide PKCS#7 message verification using the contents of the system
1844 trusted keyring to provide public keys. This then can be used for
1845 module verification, kexec image verification and firmware blob
1846 verification.
Peter Foley82c04ff2014-04-18 15:07:11 -07001847
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05001848config PROFILING
Robert Richterb309a292010-02-26 15:01:23 +01001849 bool "Profiling support"
Mathieu Desnoyers125e5642008-02-02 15:10:36 -05001850 help
1851 Say Y here to enable the extended profiling support mechanisms used
1852 by profilers such as OProfile.
1853
Ingo Molnar5f87f112008-07-23 14:15:22 +02001854#
1855# Place an empty function call at each tracepoint site. Can be
1856# dynamically changed for a probe function.
1857#
Mathieu Desnoyers97e1c182008-07-18 12:16:16 -04001858config TRACEPOINTS
Ingo Molnar5f87f112008-07-23 14:15:22 +02001859 bool
Mathieu Desnoyers97e1c182008-07-18 12:16:16 -04001860
Mathieu Desnoyersfb32e032008-02-02 15:10:33 -05001861source "arch/Kconfig"
1862
Linus Torvalds1da177e2005-04-16 15:20:36 -07001863endmenu # General setup
1864
Dmitry Baryshkovee7e5512008-06-29 14:18:46 +04001865config HAVE_GENERIC_DMA_COHERENT
1866 bool
1867 default n
1868
Linus Torvalds158a9622008-01-02 13:04:48 -08001869config SLABINFO
1870 bool
1871 depends on PROC_FS
Christoph Lameter0f389ec2008-04-14 18:53:02 +03001872 depends on SLAB || SLUB_DEBUG
Linus Torvalds158a9622008-01-02 13:04:48 -08001873 default y
1874
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001875config RT_MUTEXES
Christoph Jaeger6341e622014-12-20 15:41:11 -05001876 bool
Chuck Ebbertae81f9e2006-09-16 12:15:53 -07001877
Linus Torvalds1da177e2005-04-16 15:20:36 -07001878config BASE_SMALL
1879 int
1880 default 0 if BASE_FULL
1881 default 1 if !BASE_FULL
1882
Jan Engelhardt66da5732007-07-15 23:39:29 -07001883menuconfig MODULES
Linus Torvalds1da177e2005-04-16 15:20:36 -07001884 bool "Enable loadable module support"
Yann E. MORIN11097a02013-08-11 16:07:50 +02001885 option modules
Linus Torvalds1da177e2005-04-16 15:20:36 -07001886 help
1887 Kernel modules are small pieces of compiled code which can
1888 be inserted in the running kernel, rather than being
1889 permanently built into the kernel. You use the "modprobe"
1890 tool to add (and sometimes remove) them. If you say Y here,
1891 many parts of the kernel can be built as modules (by
1892 answering M instead of Y where indicated): this is most
1893 useful for infrequently used options which are not required
1894 for booting. For more information, see the man pages for
1895 modprobe, lsmod, modinfo, insmod and rmmod.
1896
1897 If you say Y here, you will need to run "make
1898 modules_install" to put the modules under /lib/modules/
1899 where modprobe can find them (you may need to be root to do
1900 this).
1901
1902 If unsure, say Y.
1903
Robert P. J. Day0b0de142008-08-04 13:31:32 -04001904if MODULES
1905
Linus Torvalds826e4502008-05-04 17:04:16 -07001906config MODULE_FORCE_LOAD
1907 bool "Forced module loading"
Linus Torvalds826e4502008-05-04 17:04:16 -07001908 default n
1909 help
Rusty Russell91e37a72008-05-09 16:25:28 +10001910 Allow loading of modules without version information (ie. modprobe
1911 --force). Forced module loading sets the 'F' (forced) taint flag and
1912 is usually a really bad idea.
Linus Torvalds826e4502008-05-04 17:04:16 -07001913
Linus Torvalds1da177e2005-04-16 15:20:36 -07001914config MODULE_UNLOAD
1915 bool "Module unloading"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001916 help
1917 Without this option you will not be able to unload any
1918 modules (note that some modules may not be unloadable
Denys Vlasenkof7f5b672008-07-22 19:24:26 -05001919 anyway), which makes your kernel smaller, faster
1920 and simpler. If unsure, say Y.
Linus Torvalds1da177e2005-04-16 15:20:36 -07001921
1922config MODULE_FORCE_UNLOAD
1923 bool "Forced module unloading"
Kees Cook19c92392012-10-02 11:19:29 -07001924 depends on MODULE_UNLOAD
Linus Torvalds1da177e2005-04-16 15:20:36 -07001925 help
1926 This option allows you to force a module to unload, even if the
1927 kernel believes it is unsafe: the kernel will remove the module
1928 without waiting for anyone to stop using it (using the -f option to
1929 rmmod). This is mainly for kernel developers and desperate users.
1930 If unsure, say N.
1931
Linus Torvalds1da177e2005-04-16 15:20:36 -07001932config MODVERSIONS
Sam Ravnborg0d541642005-12-26 23:04:02 +01001933 bool "Module versioning support"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001934 help
1935 Usually, you have to use modules compiled with your kernel.
1936 Saying Y here makes it sometimes possible to use modules
1937 compiled for different kernels, by adding enough information
1938 to the modules to (hopefully) spot any changes which would
1939 make them incompatible with the kernel you are running. If
1940 unsure, say N.
1941
1942config MODULE_SRCVERSION_ALL
1943 bool "Source checksum for all modules"
Linus Torvalds1da177e2005-04-16 15:20:36 -07001944 help
1945 Modules which contain a MODULE_VERSION get an extra "srcversion"
1946 field inserted into their modinfo section, which contains a
1947 sum of the source files which made it. This helps maintainers
1948 see exactly which source was used to build a module (since
1949 others sometimes change the module source without updating
1950 the version). With this option, such a "srcversion" field
1951 will be created for all modules. If unsure, say N.
1952
Rusty Russell106a4ee2012-09-26 10:09:40 +01001953config MODULE_SIG
1954 bool "Module signature verification"
1955 depends on MODULES
David Howells091f6e22015-07-20 21:16:28 +01001956 select SYSTEM_DATA_VERIFICATION
Rusty Russell106a4ee2012-09-26 10:09:40 +01001957 help
1958 Check modules for valid signatures upon load: the signature
1959 is simply appended to the module. For more information see
1960 Documentation/module-signing.txt.
1961
David Howells228c37f2015-08-11 12:38:54 +01001962 Note that this option adds the OpenSSL development packages as a
1963 kernel build dependency so that the signing tool can use its crypto
1964 library.
1965
David Howellsea0b6dc2012-09-26 10:09:50 +01001966 !!!WARNING!!! If you enable this option, you MUST make sure that the
1967 module DOES NOT get stripped after being signed. This includes the
1968 debuginfo strip done by some packagers (such as rpmbuild) and
1969 inclusion into an initramfs that wants the module size reduced.
1970
Rusty Russell106a4ee2012-09-26 10:09:40 +01001971config MODULE_SIG_FORCE
1972 bool "Require modules to be validly signed"
1973 depends on MODULE_SIG
1974 help
1975 Reject unsigned modules or signed modules for which we don't have a
1976 key. Without this, such modules will simply taint the kernel.
David Howellsea0b6dc2012-09-26 10:09:50 +01001977
Michal Marekd9d8d7e2013-01-25 13:41:31 +10301978config MODULE_SIG_ALL
1979 bool "Automatically sign all modules"
1980 default y
1981 depends on MODULE_SIG
1982 help
1983 Sign all modules during make modules_install. Without this option,
1984 modules must be signed manually, using the scripts/sign-file tool.
1985
1986comment "Do not forget to sign required modules with scripts/sign-file"
1987 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
1988
David Howellsea0b6dc2012-09-26 10:09:50 +01001989choice
1990 prompt "Which hash algorithm should modules be signed with?"
1991 depends on MODULE_SIG
1992 help
1993 This determines which sort of hashing algorithm will be used during
1994 signature generation. This algorithm _must_ be built into the kernel
1995 directly so that signature verification can take place. It is not
1996 possible to load a signed module containing the algorithm to check
1997 the signature on that module.
1998
1999config MODULE_SIG_SHA1
2000 bool "Sign modules with SHA-1"
2001 select CRYPTO_SHA1
2002
2003config MODULE_SIG_SHA224
2004 bool "Sign modules with SHA-224"
2005 select CRYPTO_SHA256
2006
2007config MODULE_SIG_SHA256
2008 bool "Sign modules with SHA-256"
2009 select CRYPTO_SHA256
2010
2011config MODULE_SIG_SHA384
2012 bool "Sign modules with SHA-384"
2013 select CRYPTO_SHA512
2014
2015config MODULE_SIG_SHA512
2016 bool "Sign modules with SHA-512"
2017 select CRYPTO_SHA512
2018
2019endchoice
2020
Michal Marek22753672013-01-25 13:41:00 +10302021config MODULE_SIG_HASH
2022 string
2023 depends on MODULE_SIG
2024 default "sha1" if MODULE_SIG_SHA1
2025 default "sha224" if MODULE_SIG_SHA224
2026 default "sha256" if MODULE_SIG_SHA256
2027 default "sha384" if MODULE_SIG_SHA384
2028 default "sha512" if MODULE_SIG_SHA512
2029
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302030config MODULE_COMPRESS
2031 bool "Compress modules on installation"
2032 depends on MODULES
2033 help
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302034
Rusty Russellb6c09b52015-06-16 12:16:22 +09302035 Compresses kernel modules when 'make modules_install' is run; gzip or
2036 xz depending on "Compression algorithm" below.
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302037
Rusty Russellb6c09b52015-06-16 12:16:22 +09302038 module-init-tools MAY support gzip, and kmod MAY support gzip and xz.
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302039
Rusty Russellb6c09b52015-06-16 12:16:22 +09302040 Out-of-tree kernel modules installed using Kbuild will also be
2041 compressed upon installation.
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302042
Rusty Russellb6c09b52015-06-16 12:16:22 +09302043 Note: for modules inside an initrd or initramfs, it's more efficient
2044 to compress the whole initrd or initramfs instead.
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302045
Rusty Russellb6c09b52015-06-16 12:16:22 +09302046 Note: This is fully compatible with signed modules.
2047
2048 If in doubt, say N.
Bertrand Jacquinbeb50df2014-08-27 20:31:56 +09302049
2050choice
2051 prompt "Compression algorithm"
2052 depends on MODULE_COMPRESS
2053 default MODULE_COMPRESS_GZIP
2054 help
2055 This determines which sort of compression will be used during
2056 'make modules_install'.
2057
2058 GZIP (default) and XZ are supported.
2059
2060config MODULE_COMPRESS_GZIP
2061 bool "GZIP"
2062
2063config MODULE_COMPRESS_XZ
2064 bool "XZ"
2065
2066endchoice
2067
Nicolas Pitredbacb0e2016-01-26 21:51:05 -05002068config TRIM_UNUSED_KSYMS
2069 bool "Trim unused exported kernel symbols"
2070 depends on MODULES && !UNUSED_SYMBOLS
2071 help
2072 The kernel and some modules make many symbols available for
2073 other modules to use via EXPORT_SYMBOL() and variants. Depending
2074 on the set of modules being selected in your kernel configuration,
2075 many of those exported symbols might never be used.
2076
2077 This option allows for unused exported symbols to be dropped from
2078 the build. In turn, this provides the compiler more opportunities
2079 (especially when using LTO) for optimizing the code and reducing
2080 binary size. This might have some security advantages as well.
2081
2082 If unsure say N.
2083
Robert P. J. Day0b0de142008-08-04 13:31:32 -04002084endif # MODULES
2085
Peter Zijlstra6c9692e2015-05-27 11:09:37 +09302086config MODULES_TREE_LOOKUP
2087 def_bool y
2088 depends on PERF_EVENTS || TRACING
2089
Rusty Russell98a79d62008-12-13 21:19:41 +10302090config INIT_ALL_POSSIBLE
2091 bool
2092 help
Rusty Russell5f054e32012-03-29 15:38:31 +10302093 Back when each arch used to define their own cpu_online_mask and
2094 cpu_possible_mask, some of them chose to initialize cpu_possible_mask
Rusty Russell98a79d62008-12-13 21:19:41 +10302095 with all 1s, and others with all 0s. When they were centralised,
2096 it was better to provide this option than to break all the archs
Matt LaPlante692105b2009-01-26 11:12:25 +01002097 and have several arch maintainers pursuing me down dark alleys.
Rusty Russell98a79d62008-12-13 21:19:41 +10302098
Jens Axboe3a65dfe2005-11-04 08:43:35 +01002099source "block/Kconfig"
Avi Kivitye98c3202007-10-16 23:27:31 -07002100
2101config PREEMPT_NOTIFIERS
2102 bool
Paul E. McKenneye260be62008-01-25 21:08:24 +01002103
Steffen Klassert16295be2010-01-06 19:47:10 +11002104config PADATA
2105 depends on SMP
2106 bool
2107
Andi Kleen754b7b62012-10-04 17:11:27 -07002108# Can be selected by architectures with broken toolchains
2109# that get confused by correct const<->read_only section
2110# mappings
2111config BROKEN_RODATA
2112 bool
2113
David Howells4520c6a2012-09-21 23:31:13 +01002114config ASN1
2115 tristate
2116 help
2117 Build a simple ASN.1 grammar compiler that produces a bytecode output
2118 that can be interpreted by the ASN.1 stream decoder and used to
2119 inform it as to what tags are to be expected in a stream and what
2120 functions to call on what tags.
2121
Thomas Gleixner6beb0002009-11-09 15:21:34 +00002122source "kernel/Kconfig.locks"