Roman Zippel | 80daa56 | 2008-01-14 04:51:16 +0100 | [diff] [blame] | 1 | config ARCH |
| 2 | string |
| 3 | option env="ARCH" |
| 4 | |
| 5 | config KERNELVERSION |
| 6 | string |
| 7 | option env="KERNELVERSION" |
| 8 | |
Roman Zippel | face437 | 2006-06-08 22:12:45 -0700 | [diff] [blame] | 9 | config DEFCONFIG_LIST |
| 10 | string |
Paolo 'Blaisorblade' Giarrusso | b2670eac | 2006-10-19 23:28:23 -0700 | [diff] [blame] | 11 | depends on !UML |
Roman Zippel | face437 | 2006-06-08 22:12:45 -0700 | [diff] [blame] | 12 | option defconfig_list |
| 13 | default "/lib/modules/$UNAME_RELEASE/.config" |
| 14 | default "/etc/kernel-config" |
| 15 | default "/boot/config-$UNAME_RELEASE" |
Sam Ravnborg | 7353190 | 2008-05-25 23:03:18 +0200 | [diff] [blame] | 16 | default "$ARCH_DEFCONFIG" |
Roman Zippel | face437 | 2006-06-08 22:12:45 -0700 | [diff] [blame] | 17 | default "arch/$ARCH/defconfig" |
| 18 | |
Peter Oberparleiter | b99b87f | 2009-06-17 16:28:03 -0700 | [diff] [blame] | 19 | config CONSTRUCTORS |
| 20 | bool |
| 21 | depends on !UML |
Peter Oberparleiter | b99b87f | 2009-06-17 16:28:03 -0700 | [diff] [blame] | 22 | |
Peter Zijlstra | e360adb | 2010-10-14 14:01:34 +0800 | [diff] [blame] | 23 | config IRQ_WORK |
| 24 | bool |
Peter Zijlstra | e360adb | 2010-10-14 14:01:34 +0800 | [diff] [blame] | 25 | |
David Daney | 1dbdc6f | 2012-04-19 14:59:57 -0700 | [diff] [blame] | 26 | config BUILDTIME_EXTABLE_SORT |
| 27 | bool |
| 28 | |
Al Boldi | ff0cfc6 | 2007-07-31 00:39:23 -0700 | [diff] [blame] | 29 | menu "General setup" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 30 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 31 | config BROKEN |
| 32 | bool |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 33 | |
| 34 | config BROKEN_ON_SMP |
| 35 | bool |
| 36 | depends on BROKEN || !SMP |
| 37 | default y |
| 38 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 39 | config INIT_ENV_ARG_LIMIT |
| 40 | int |
Adrian Bunk | dd673bc | 2006-06-30 01:55:51 -0700 | [diff] [blame] | 41 | default 32 if !UML |
| 42 | default 128 if UML |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 43 | help |
Randy Dunlap | 34ad92c | 2005-10-30 15:01:46 -0800 | [diff] [blame] | 44 | Maximum of each of the number of arguments and environment |
| 45 | variables passed to init from the kernel command line. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 46 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 47 | |
Roland McGrath | 8433646 | 2009-12-21 16:24:06 -0800 | [diff] [blame] | 48 | config 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 Slaby | 4bb1667 | 2013-05-22 10:56:24 +0200 | [diff] [blame] | 56 | config COMPILE_TEST |
| 57 | bool "Compile also drivers which will not load" |
| 58 | default n |
| 59 | help |
| 60 | Some drivers can be compiled on a different platform than they are |
| 61 | intended to be run on. Despite they cannot be loaded there (or even |
| 62 | when they load they cannot be used due to missing HW support), |
| 63 | developers still, opposing to distributors, might want to build such |
| 64 | drivers to compile-test them. |
| 65 | |
| 66 | If you are a developer and want to build everything available, say Y |
| 67 | here. If you are a user/distributor, say N here to exclude useless |
| 68 | drivers to be distributed. |
| 69 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 70 | config LOCALVERSION |
| 71 | string "Local version - append to kernel release" |
| 72 | help |
| 73 | Append an extra string to the end of your kernel version. |
| 74 | This will show up when you type uname, for example. |
| 75 | The string you set here will be appended after the contents of |
| 76 | any files with a filename matching localversion* in your |
| 77 | object and source tree, in that order. Your total string can |
| 78 | be a maximum of 64 characters. |
| 79 | |
Ryan Anderson | aaebf43 | 2005-07-31 04:57:49 -0400 | [diff] [blame] | 80 | config LOCALVERSION_AUTO |
| 81 | bool "Automatically append version information to the version string" |
| 82 | default y |
| 83 | help |
| 84 | This will try to automatically determine if the current tree is a |
Robert P. J. Day | 6e5a542 | 2007-05-01 23:08:11 +0200 | [diff] [blame] | 85 | release tree by looking for git tags that belong to the current |
| 86 | top of tree revision. |
Ryan Anderson | aaebf43 | 2005-07-31 04:57:49 -0400 | [diff] [blame] | 87 | |
| 88 | A string of the format -gxxxxxxxx will be added to the localversion |
Robert P. J. Day | 6e5a542 | 2007-05-01 23:08:11 +0200 | [diff] [blame] | 89 | if a git-based tree is found. The string generated by this will be |
Ryan Anderson | aaebf43 | 2005-07-31 04:57:49 -0400 | [diff] [blame] | 90 | appended after any matching localversion* files, and after the value |
Robert P. J. Day | 6e5a542 | 2007-05-01 23:08:11 +0200 | [diff] [blame] | 91 | set in CONFIG_LOCALVERSION. |
Ryan Anderson | aaebf43 | 2005-07-31 04:57:49 -0400 | [diff] [blame] | 92 | |
Robert P. J. Day | 6e5a542 | 2007-05-01 23:08:11 +0200 | [diff] [blame] | 93 | (The actual string used here is the first eight characters produced |
| 94 | by running the command: |
| 95 | |
| 96 | $ git rev-parse --verify HEAD |
| 97 | |
| 98 | which is done within the script "scripts/setlocalversion".) |
Ryan Anderson | aaebf43 | 2005-07-31 04:57:49 -0400 | [diff] [blame] | 99 | |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 100 | config HAVE_KERNEL_GZIP |
| 101 | bool |
| 102 | |
| 103 | config HAVE_KERNEL_BZIP2 |
| 104 | bool |
| 105 | |
| 106 | config HAVE_KERNEL_LZMA |
| 107 | bool |
| 108 | |
Lasse Collin | 3ebe124 | 2011-01-12 17:01:23 -0800 | [diff] [blame] | 109 | config HAVE_KERNEL_XZ |
| 110 | bool |
| 111 | |
Albin Tonnerre | 7dd65fe | 2010-01-08 14:42:42 -0800 | [diff] [blame] | 112 | config HAVE_KERNEL_LZO |
| 113 | bool |
| 114 | |
Kyungsik Lee | e76e1fd | 2013-07-08 16:01:46 -0700 | [diff] [blame] | 115 | config HAVE_KERNEL_LZ4 |
| 116 | bool |
| 117 | |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 118 | choice |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 119 | prompt "Kernel compression mode" |
| 120 | default KERNEL_GZIP |
H. Peter Anvin | 2d3c627 | 2013-11-14 21:43:47 -0800 | [diff] [blame] | 121 | depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 122 | help |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 123 | The linux kernel is a kind of self-extracting executable. |
| 124 | Several compression algorithms are available, which differ |
| 125 | in efficiency, compression and decompression speed. |
| 126 | Compression speed is only relevant when building a kernel. |
| 127 | Decompression speed is relevant at each boot. |
| 128 | |
| 129 | If you have any problems with bzip2 or lzma compressed |
| 130 | kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older |
| 131 | version of this functionality (bzip2 only), for 2.4, was |
| 132 | supplied by Christian Ludwig) |
| 133 | |
| 134 | High compression options are mostly useful for users, who |
| 135 | are low on disk space (embedded systems), but for whom ram |
| 136 | size matters less. |
| 137 | |
| 138 | If in doubt, select 'gzip' |
| 139 | |
| 140 | config KERNEL_GZIP |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 141 | bool "Gzip" |
| 142 | depends on HAVE_KERNEL_GZIP |
| 143 | help |
Albin Tonnerre | 7dd65fe | 2010-01-08 14:42:42 -0800 | [diff] [blame] | 144 | The old and tried gzip compression. It provides a good balance |
| 145 | between compression ratio and decompression speed. |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 146 | |
| 147 | config KERNEL_BZIP2 |
| 148 | bool "Bzip2" |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 149 | depends on HAVE_KERNEL_BZIP2 |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 150 | help |
| 151 | Its compression ratio and speed is intermediate. |
Randy Dunlap | 0a4dd35 | 2012-05-31 16:26:46 -0700 | [diff] [blame] | 152 | Decompression speed is slowest among the choices. The kernel |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 153 | size is about 10% smaller with bzip2, in comparison to gzip. |
| 154 | Bzip2 uses a large amount of memory. For modern kernels you |
| 155 | will need at least 8MB RAM or more for booting. |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 156 | |
| 157 | config KERNEL_LZMA |
H. Peter Anvin | 2e9f3bd | 2009-01-04 15:41:25 -0800 | [diff] [blame] | 158 | bool "LZMA" |
| 159 | depends on HAVE_KERNEL_LZMA |
| 160 | help |
Randy Dunlap | 0a4dd35 | 2012-05-31 16:26:46 -0700 | [diff] [blame] | 161 | This compression algorithm's ratio is best. Decompression speed |
| 162 | is between gzip and bzip2. Compression is slowest. |
| 163 | The kernel size is about 33% smaller with LZMA in comparison to gzip. |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 164 | |
Lasse Collin | 3ebe124 | 2011-01-12 17:01:23 -0800 | [diff] [blame] | 165 | config KERNEL_XZ |
| 166 | bool "XZ" |
| 167 | depends on HAVE_KERNEL_XZ |
| 168 | help |
| 169 | XZ uses the LZMA2 algorithm and instruction set specific |
| 170 | BCJ filters which can improve compression ratio of executable |
| 171 | code. The size of the kernel is about 30% smaller with XZ in |
| 172 | comparison to gzip. On architectures for which there is a BCJ |
| 173 | filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ |
| 174 | will create a few percent smaller kernel than plain LZMA. |
| 175 | |
| 176 | The speed is about the same as with LZMA: The decompression |
| 177 | speed of XZ is better than that of bzip2 but worse than gzip |
| 178 | and LZO. Compression is slow. |
| 179 | |
Albin Tonnerre | 7dd65fe | 2010-01-08 14:42:42 -0800 | [diff] [blame] | 180 | config KERNEL_LZO |
| 181 | bool "LZO" |
| 182 | depends on HAVE_KERNEL_LZO |
| 183 | help |
Randy Dunlap | 0a4dd35 | 2012-05-31 16:26:46 -0700 | [diff] [blame] | 184 | Its compression ratio is the poorest among the choices. The kernel |
Stephan Sperber | 681b304 | 2010-07-14 11:23:08 +0200 | [diff] [blame] | 185 | size is about 10% bigger than gzip; however its speed |
Albin Tonnerre | 7dd65fe | 2010-01-08 14:42:42 -0800 | [diff] [blame] | 186 | (both compression and decompression) is the fastest. |
| 187 | |
Kyungsik Lee | e76e1fd | 2013-07-08 16:01:46 -0700 | [diff] [blame] | 188 | config KERNEL_LZ4 |
| 189 | bool "LZ4" |
| 190 | depends on HAVE_KERNEL_LZ4 |
| 191 | help |
| 192 | LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding. |
| 193 | A preliminary version of LZ4 de/compression tool is available at |
| 194 | <https://code.google.com/p/lz4/>. |
| 195 | |
| 196 | Its compression ratio is worse than LZO. The size of the kernel |
| 197 | is about 8% bigger than LZO. But the decompression speed is |
| 198 | faster than LZO. |
| 199 | |
Alain Knaff | 30d65db | 2009-01-04 22:46:17 +0100 | [diff] [blame] | 200 | endchoice |
| 201 | |
Josh Triplett | bd5dc17 | 2011-06-15 15:08:28 -0700 | [diff] [blame] | 202 | config DEFAULT_HOSTNAME |
| 203 | string "Default hostname" |
| 204 | default "(none)" |
| 205 | help |
| 206 | This option determines the default system hostname before userspace |
| 207 | calls sethostname(2). The kernel traditionally uses "(none)" here, |
| 208 | but you may wish to use a different default here to make a minimal |
| 209 | system more usable with less configuration. |
| 210 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 211 | config SWAP |
| 212 | bool "Support for paging of anonymous memory (swap)" |
David Howells | 9361401 | 2006-09-30 20:45:40 +0200 | [diff] [blame] | 213 | depends on MMU && BLOCK |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 214 | default y |
| 215 | help |
| 216 | This option allows you to choose whether you want to have support |
Jesper Juhl | 92c3504 | 2006-01-15 02:40:08 +0100 | [diff] [blame] | 217 | for so called swap devices or swap files in your kernel that are |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 218 | used to provide more virtual memory than the actual RAM present |
| 219 | in your computer. If unsure say Y. |
| 220 | |
| 221 | config SYSVIPC |
| 222 | bool "System V IPC" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 223 | ---help--- |
| 224 | Inter Process Communication is a suite of library functions and |
| 225 | system calls which let processes (running programs) synchronize and |
| 226 | exchange information. It is generally considered to be a good thing, |
| 227 | and some programs won't run unless you say Y here. In particular, if |
| 228 | you want to run the DOS emulator dosemu under Linux (read the |
| 229 | DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>), |
| 230 | you'll need to say Y here. |
| 231 | |
| 232 | You can find documentation about IPC with "info ipc" and also in |
| 233 | section 6.4 of the Linux Programmer's Guide, available from |
| 234 | <http://www.tldp.org/guides.html>. |
| 235 | |
Eric W. Biederman | a5494dc | 2007-02-14 00:34:06 -0800 | [diff] [blame] | 236 | config SYSVIPC_SYSCTL |
| 237 | bool |
| 238 | depends on SYSVIPC |
| 239 | depends on SYSCTL |
| 240 | default y |
| 241 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 242 | config POSIX_MQUEUE |
| 243 | bool "POSIX Message Queues" |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 244 | depends on NET |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 245 | ---help--- |
| 246 | POSIX variant of message queues is a part of IPC. In POSIX message |
| 247 | queues every message has a priority which decides about succession |
| 248 | of receiving it by a process. If you want to compile and run |
| 249 | programs written e.g. for Solaris with use of its POSIX message |
Robert P. J. Day | b0e3765 | 2007-05-09 07:25:13 +0200 | [diff] [blame] | 250 | queues (functions mq_*) say Y here. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 251 | |
| 252 | POSIX message queues are visible as a filesystem called 'mqueue' |
| 253 | and can be mounted somewhere if you want to do filesystem |
| 254 | operations on message queues. |
| 255 | |
| 256 | If unsure, say Y. |
| 257 | |
Serge E. Hallyn | bdc8e5f | 2009-04-06 19:01:11 -0700 | [diff] [blame] | 258 | config POSIX_MQUEUE_SYSCTL |
| 259 | bool |
| 260 | depends on POSIX_MQUEUE |
| 261 | depends on SYSCTL |
| 262 | default y |
| 263 | |
Aneesh Kumar K.V | 990d6c2 | 2011-01-29 18:43:26 +0530 | [diff] [blame] | 264 | config FHANDLE |
| 265 | bool "open by fhandle syscalls" |
| 266 | select EXPORTFS |
| 267 | help |
| 268 | If you say Y here, a user level program will be able to map |
| 269 | file names to handle and then later use the handle for |
| 270 | different file system operations. This is useful in implementing |
| 271 | userspace file servers, which now track files using handles instead |
| 272 | of names. The handle would remain the same even if file names |
| 273 | get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2) |
| 274 | syscalls. |
| 275 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 276 | config AUDIT |
| 277 | bool "Auditing support" |
Chris Wright | 804a6a49 | 2005-05-11 10:52:45 +0100 | [diff] [blame] | 278 | depends on NET |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 279 | help |
| 280 | Enable auditing infrastructure that can be used with another |
| 281 | kernel subsystem, such as SELinux (which requires this for |
| 282 | logging of avc messages output). Does not do system-call |
| 283 | auditing without CONFIG_AUDITSYSCALL. |
| 284 | |
| 285 | config AUDITSYSCALL |
| 286 | bool "Enable system-call auditing support" |
蔡æ£é¾™ | a9302e8 | 2013-12-20 10:04:10 +0800 | [diff] [blame] | 287 | depends on AUDIT && (X86 || PARISC || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || (ARM && AEABI && !OABI_COMPAT) || ALPHA) |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 288 | default y if SECURITY_SELINUX |
| 289 | help |
| 290 | Enable low-overhead system-call auditing infrastructure that |
| 291 | can be used independently or with another kernel subsystem, |
Eric Paris | 67640b6 | 2009-12-17 20:12:06 -0500 | [diff] [blame] | 292 | such as SELinux. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 293 | |
Eric Paris | 939a67f | 2009-12-17 20:12:06 -0500 | [diff] [blame] | 294 | config AUDIT_WATCH |
| 295 | def_bool y |
| 296 | depends on AUDITSYSCALL |
| 297 | select FSNOTIFY |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 298 | |
Al Viro | 74c3cbe | 2007-07-22 08:04:18 -0400 | [diff] [blame] | 299 | config AUDIT_TREE |
| 300 | def_bool y |
Eric Paris | 63c882a | 2009-05-21 17:02:01 -0400 | [diff] [blame] | 301 | depends on AUDITSYSCALL |
Eric Paris | 28a3a7e | 2009-12-17 20:12:05 -0500 | [diff] [blame] | 302 | select FSNOTIFY |
Al Viro | 74c3cbe | 2007-07-22 08:04:18 -0400 | [diff] [blame] | 303 | |
Thomas Gleixner | d9817eb | 2010-09-27 12:45:59 +0000 | [diff] [blame] | 304 | source "kernel/irq/Kconfig" |
Thomas Gleixner | 764e0da | 2012-05-21 23:16:18 +0200 | [diff] [blame] | 305 | source "kernel/time/Kconfig" |
Thomas Gleixner | d9817eb | 2010-09-27 12:45:59 +0000 | [diff] [blame] | 306 | |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 307 | menu "CPU/Task time and stats accounting" |
| 308 | |
Frederic Weisbecker | abf917c | 2012-07-25 07:56:04 +0200 | [diff] [blame] | 309 | config VIRT_CPU_ACCOUNTING |
| 310 | bool |
| 311 | |
Frederic Weisbecker | fdf9c35 | 2012-09-09 14:56:31 +0200 | [diff] [blame] | 312 | choice |
| 313 | prompt "Cputime accounting" |
| 314 | default TICK_CPU_ACCOUNTING if !PPC64 |
Stephen Rothwell | 02fc8d3 | 2013-02-08 14:19:38 +1100 | [diff] [blame] | 315 | default VIRT_CPU_ACCOUNTING_NATIVE if PPC64 |
Frederic Weisbecker | fdf9c35 | 2012-09-09 14:56:31 +0200 | [diff] [blame] | 316 | |
| 317 | # Kind of a stub config for the pure tick based cputime accounting |
| 318 | config TICK_CPU_ACCOUNTING |
| 319 | bool "Simple tick based cputime accounting" |
Frederic Weisbecker | c58b0df | 2013-04-26 15:16:31 +0200 | [diff] [blame] | 320 | depends on !S390 && !NO_HZ_FULL |
Frederic Weisbecker | fdf9c35 | 2012-09-09 14:56:31 +0200 | [diff] [blame] | 321 | help |
| 322 | This is the basic tick based cputime accounting that maintains |
| 323 | statistics about user, system and idle time spent on per jiffies |
| 324 | granularity. |
| 325 | |
| 326 | If unsure, say Y. |
| 327 | |
Frederic Weisbecker | abf917c | 2012-07-25 07:56:04 +0200 | [diff] [blame] | 328 | config VIRT_CPU_ACCOUNTING_NATIVE |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 329 | bool "Deterministic task and CPU time accounting" |
Frederic Weisbecker | c58b0df | 2013-04-26 15:16:31 +0200 | [diff] [blame] | 330 | depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL |
Frederic Weisbecker | abf917c | 2012-07-25 07:56:04 +0200 | [diff] [blame] | 331 | select VIRT_CPU_ACCOUNTING |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 332 | help |
| 333 | Select this option to enable more accurate task and CPU time |
| 334 | accounting. This is done by reading a CPU counter on each |
| 335 | kernel entry and exit and on transitions within the kernel |
| 336 | between system, softirq and hardirq state, so there is a |
| 337 | small performance impact. In the case of s390 or IBM POWER > 5, |
| 338 | this also enables accounting of stolen time on logically-partitioned |
| 339 | systems. |
| 340 | |
Frederic Weisbecker | abf917c | 2012-07-25 07:56:04 +0200 | [diff] [blame] | 341 | config VIRT_CPU_ACCOUNTING_GEN |
| 342 | bool "Full dynticks CPU time accounting" |
Kevin Hilman | ff3fb25 | 2013-09-16 15:28:19 -0700 | [diff] [blame] | 343 | depends on HAVE_CONTEXT_TRACKING |
Kevin Hilman | 554b000 | 2013-09-16 15:28:21 -0700 | [diff] [blame] | 344 | depends on HAVE_VIRT_CPU_ACCOUNTING_GEN |
Frederic Weisbecker | abf917c | 2012-07-25 07:56:04 +0200 | [diff] [blame] | 345 | select VIRT_CPU_ACCOUNTING |
| 346 | select CONTEXT_TRACKING |
| 347 | help |
| 348 | Select this option to enable task and CPU time accounting on full |
| 349 | dynticks systems. This accounting is implemented by watching every |
| 350 | kernel-user boundaries using the context tracking subsystem. |
| 351 | The accounting is thus performed at the expense of some significant |
| 352 | overhead. |
| 353 | |
| 354 | For now this is only useful if you are working on the full |
| 355 | dynticks subsystem development. |
| 356 | |
| 357 | If unsure, say N. |
| 358 | |
Frederic Weisbecker | fdf9c35 | 2012-09-09 14:56:31 +0200 | [diff] [blame] | 359 | config IRQ_TIME_ACCOUNTING |
| 360 | bool "Fine granularity task level IRQ time accounting" |
Frederic Weisbecker | c58b0df | 2013-04-26 15:16:31 +0200 | [diff] [blame] | 361 | depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL |
Frederic Weisbecker | fdf9c35 | 2012-09-09 14:56:31 +0200 | [diff] [blame] | 362 | help |
| 363 | Select this option to enable fine granularity task irq time |
| 364 | accounting. This is done by reading a timestamp on each |
| 365 | transitions between softirq and hardirq state, so there can be a |
| 366 | small performance impact. |
| 367 | |
| 368 | If in doubt, say N here. |
| 369 | |
| 370 | endchoice |
| 371 | |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 372 | config BSD_PROCESS_ACCT |
| 373 | bool "BSD Process Accounting" |
| 374 | help |
| 375 | If you say Y here, a user level program will be able to instruct the |
| 376 | kernel (via a special system call) to write process accounting |
| 377 | information to a file: whenever a process exits, information about |
| 378 | that process will be appended to the file by the kernel. The |
| 379 | information includes things such as creation time, owning user, |
| 380 | command name, memory usage, controlling terminal etc. (the complete |
| 381 | list is in the struct acct in <file:include/linux/acct.h>). It is |
| 382 | up to the user level program to do useful things with this |
| 383 | information. This is generally a good idea, so say Y. |
| 384 | |
| 385 | config BSD_PROCESS_ACCT_V3 |
| 386 | bool "BSD Process Accounting version 3 file format" |
| 387 | depends on BSD_PROCESS_ACCT |
| 388 | default n |
| 389 | help |
| 390 | If you say Y here, the process accounting information is written |
| 391 | in a new file format that also logs the process IDs of each |
| 392 | process and it's parent. Note that this file format is incompatible |
| 393 | with previous v0/v1/v2 file formats, so you will need updated tools |
| 394 | for processing it. A preliminary version of these tools is available |
| 395 | at <http://www.gnu.org/software/acct/>. |
| 396 | |
| 397 | config TASKSTATS |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 398 | bool "Export task/process statistics through netlink" |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 399 | depends on NET |
| 400 | default n |
| 401 | help |
| 402 | Export selected statistics for tasks/processes through the |
| 403 | generic netlink interface. Unlike BSD process accounting, the |
| 404 | statistics are available during the lifetime of tasks/processes as |
| 405 | responses to commands. Like BSD accounting, they are sent to user |
| 406 | space on task exit. |
| 407 | |
| 408 | Say N if unsure. |
| 409 | |
| 410 | config TASK_DELAY_ACCT |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 411 | bool "Enable per-task delay accounting" |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 412 | depends on TASKSTATS |
| 413 | help |
| 414 | Collect information on time spent by a task waiting for system |
| 415 | resources like cpu, synchronous block I/O completion and swapping |
| 416 | in pages. Such statistics can help in setting a task's priorities |
| 417 | relative to other tasks for cpu, io, rss limits etc. |
| 418 | |
| 419 | Say N if unsure. |
| 420 | |
| 421 | config TASK_XACCT |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 422 | bool "Enable extended accounting over taskstats" |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 423 | depends on TASKSTATS |
| 424 | help |
| 425 | Collect extended task accounting data and send the data |
| 426 | to userland for processing over the taskstats interface. |
| 427 | |
| 428 | Say N if unsure. |
| 429 | |
| 430 | config TASK_IO_ACCOUNTING |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 431 | bool "Enable per-task storage I/O accounting" |
Frederic Weisbecker | 391dc69 | 2012-09-09 14:22:07 +0200 | [diff] [blame] | 432 | depends on TASK_XACCT |
| 433 | help |
| 434 | Collect information on the number of bytes of storage I/O which this |
| 435 | task has caused. |
| 436 | |
| 437 | Say N if unsure. |
| 438 | |
| 439 | endmenu # "CPU/Task time and stats accounting" |
| 440 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 441 | menu "RCU Subsystem" |
| 442 | |
| 443 | choice |
| 444 | prompt "RCU Implementation" |
Paul E. McKenney | 31c9a24 | 2009-04-02 21:06:25 -0700 | [diff] [blame] | 445 | default TREE_RCU |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 446 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 447 | config TREE_RCU |
| 448 | bool "Tree-based hierarchical RCU" |
Paul E. McKenney | 687d7a9 | 2010-07-21 06:52:40 -0700 | [diff] [blame] | 449 | depends on !PREEMPT && SMP |
Steven Rostedt | 016a8d5 | 2013-05-28 17:32:53 -0400 | [diff] [blame] | 450 | select IRQ_WORK |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 451 | help |
| 452 | This option selects the RCU implementation that is |
| 453 | designed for very large SMP system with hundreds or |
Paul E. McKenney | c17ef45 | 2009-06-23 17:12:47 -0700 | [diff] [blame] | 454 | thousands of CPUs. It also scales down nicely to |
| 455 | smaller systems. |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 456 | |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 457 | config TREE_PREEMPT_RCU |
Paul E. McKenney | a57eb94 | 2010-06-29 16:49:16 -0700 | [diff] [blame] | 458 | bool "Preemptible tree-based hierarchical RCU" |
Paul E. McKenney | 9fc52d8 | 2013-01-08 15:48:33 -0800 | [diff] [blame] | 459 | depends on PREEMPT |
James Hogan | 5361471 | 2013-07-25 15:34:25 +0100 | [diff] [blame] | 460 | select IRQ_WORK |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 461 | help |
| 462 | This option selects the RCU implementation that is |
| 463 | designed for very large SMP systems with hundreds or |
| 464 | thousands of CPUs, but for which real-time response |
Paul E. McKenney | bbe3eae | 2009-09-13 09:15:08 -0700 | [diff] [blame] | 465 | is also required. It also scales down nicely to |
| 466 | smaller systems. |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 467 | |
Paul E. McKenney | 9fc52d8 | 2013-01-08 15:48:33 -0800 | [diff] [blame] | 468 | Select this option if you are unsure. |
| 469 | |
Paul E. McKenney | 9b1d82f | 2009-10-25 19:03:50 -0700 | [diff] [blame] | 470 | config TINY_RCU |
| 471 | bool "UP-only small-memory-footprint RCU" |
Paul E. McKenney | 8008e12 | 2011-06-08 16:31:33 -0700 | [diff] [blame] | 472 | depends on !PREEMPT && !SMP |
Paul E. McKenney | 9b1d82f | 2009-10-25 19:03:50 -0700 | [diff] [blame] | 473 | help |
| 474 | This option selects the RCU implementation that is |
| 475 | designed for UP systems from which real-time response |
| 476 | is not required. This option greatly reduces the |
| 477 | memory footprint of RCU. |
| 478 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 479 | endchoice |
| 480 | |
Paul E. McKenney | a57eb94 | 2010-06-29 16:49:16 -0700 | [diff] [blame] | 481 | config PREEMPT_RCU |
Paul E. McKenney | 127781d | 2013-03-27 08:44:00 -0700 | [diff] [blame] | 482 | def_bool TREE_PREEMPT_RCU |
Paul E. McKenney | a57eb94 | 2010-06-29 16:49:16 -0700 | [diff] [blame] | 483 | help |
| 484 | This option enables preemptible-RCU code that is common between |
| 485 | the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. |
| 486 | |
Paul E. McKenney | 6bfc09e | 2012-10-19 12:49:17 -0700 | [diff] [blame] | 487 | config RCU_STALL_COMMON |
| 488 | def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) |
| 489 | help |
| 490 | This option enables RCU CPU stall code that is common between |
| 491 | the TINY and TREE variants of RCU. The purpose is to allow |
| 492 | the tiny variants to disable RCU CPU stall warnings, while |
| 493 | making these warnings mandatory for the tree variants. |
| 494 | |
Frederic Weisbecker | 91d1aa43 | 2012-11-27 19:33:25 +0100 | [diff] [blame] | 495 | config CONTEXT_TRACKING |
| 496 | bool |
| 497 | |
Frederic Weisbecker | 2b1d502 | 2012-07-11 20:26:30 +0200 | [diff] [blame] | 498 | config RCU_USER_QS |
| 499 | bool "Consider userspace as in RCU extended quiescent state" |
Frederic Weisbecker | 91d1aa43 | 2012-11-27 19:33:25 +0100 | [diff] [blame] | 500 | depends on HAVE_CONTEXT_TRACKING && SMP |
| 501 | select CONTEXT_TRACKING |
Frederic Weisbecker | 2b1d502 | 2012-07-11 20:26:30 +0200 | [diff] [blame] | 502 | help |
| 503 | This option sets hooks on kernel / userspace boundaries and |
| 504 | puts RCU in extended quiescent state when the CPU runs in |
| 505 | userspace. It means that when a CPU runs in userspace, it is |
| 506 | excluded from the global RCU state machine and thus doesn't |
Paul Gortmaker | af71bef | 2012-10-24 11:07:09 -0700 | [diff] [blame] | 507 | try to keep the timer tick on for RCU. |
Frederic Weisbecker | 2b1d502 | 2012-07-11 20:26:30 +0200 | [diff] [blame] | 508 | |
Frederic Weisbecker | d677124 | 2012-10-11 01:48:28 +0200 | [diff] [blame] | 509 | Unless you want to hack and help the development of the full |
Frederic Weisbecker | 91d1aa43 | 2012-11-27 19:33:25 +0100 | [diff] [blame] | 510 | dynticks mode, you shouldn't enable this option. It also |
Paul Gortmaker | af71bef | 2012-10-24 11:07:09 -0700 | [diff] [blame] | 511 | adds unnecessary overhead. |
Frederic Weisbecker | d677124 | 2012-10-11 01:48:28 +0200 | [diff] [blame] | 512 | |
| 513 | If unsure say N |
| 514 | |
Frederic Weisbecker | 91d1aa43 | 2012-11-27 19:33:25 +0100 | [diff] [blame] | 515 | config CONTEXT_TRACKING_FORCE |
| 516 | bool "Force context tracking" |
| 517 | depends on CONTEXT_TRACKING |
Frederic Weisbecker | d84d27a | 2013-07-24 21:59:29 +0200 | [diff] [blame] | 518 | default y if !NO_HZ_FULL |
Frederic Weisbecker | 1fd2b44 | 2012-07-11 20:26:40 +0200 | [diff] [blame] | 519 | help |
Frederic Weisbecker | d84d27a | 2013-07-24 21:59:29 +0200 | [diff] [blame] | 520 | The major pre-requirement for full dynticks to work is to |
| 521 | support the context tracking subsystem. But there are also |
| 522 | other dependencies to provide in order to make the full |
| 523 | dynticks working. |
| 524 | |
| 525 | This option stands for testing when an arch implements the |
| 526 | context tracking backend but doesn't yet fullfill all the |
| 527 | requirements to make the full dynticks feature working. |
| 528 | Without the full dynticks, there is no way to test the support |
| 529 | for context tracking and the subsystems that rely on it: RCU |
| 530 | userspace extended quiescent state and tickless cputime |
| 531 | accounting. This option copes with the absence of the full |
| 532 | dynticks subsystem by forcing the context tracking on all |
| 533 | CPUs in the system. |
| 534 | |
Paul Gortmaker | 99c8b1e | 2013-10-24 10:07:47 -0400 | [diff] [blame] | 535 | Say Y only if you're working on the development of an |
Frederic Weisbecker | d84d27a | 2013-07-24 21:59:29 +0200 | [diff] [blame] | 536 | architecture backend for the context tracking. |
| 537 | |
| 538 | Say N otherwise, this option brings an overhead that you |
| 539 | don't want in production. |
| 540 | |
Frederic Weisbecker | d677124 | 2012-10-11 01:48:28 +0200 | [diff] [blame] | 541 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 542 | config RCU_FANOUT |
| 543 | int "Tree-based hierarchical RCU fanout value" |
| 544 | range 2 64 if 64BIT |
| 545 | range 2 32 if !64BIT |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 546 | depends on TREE_RCU || TREE_PREEMPT_RCU |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 547 | default 64 if 64BIT |
| 548 | default 32 if !64BIT |
| 549 | help |
| 550 | This option controls the fanout of hierarchical implementations |
| 551 | of RCU, allowing RCU to work efficiently on machines with |
Paul E. McKenney | 4d87ffa | 2010-08-04 17:31:12 -0700 | [diff] [blame] | 552 | large numbers of CPUs. This value must be at least the fourth |
| 553 | root of NR_CPUS, which allows NR_CPUS to be insanely large. |
| 554 | The default value of RCU_FANOUT should be used for production |
| 555 | systems, but if you are stress-testing the RCU implementation |
| 556 | itself, small RCU_FANOUT values allow you to test large-system |
| 557 | code paths on small(er) systems. |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 558 | |
| 559 | Select a specific number if testing RCU itself. |
| 560 | Take the default if unsure. |
| 561 | |
Paul E. McKenney | 8932a63 | 2012-04-19 12:20:14 -0700 | [diff] [blame] | 562 | config RCU_FANOUT_LEAF |
| 563 | int "Tree-based hierarchical RCU leaf-level fanout value" |
| 564 | range 2 RCU_FANOUT if 64BIT |
| 565 | range 2 RCU_FANOUT if !64BIT |
| 566 | depends on TREE_RCU || TREE_PREEMPT_RCU |
| 567 | default 16 |
| 568 | help |
| 569 | This option controls the leaf-level fanout of hierarchical |
| 570 | implementations of RCU, and allows trading off cache misses |
| 571 | against lock contention. Systems that synchronize their |
| 572 | scheduling-clock interrupts for energy-efficiency reasons will |
| 573 | want the default because the smaller leaf-level fanout keeps |
| 574 | lock contention levels acceptably low. Very large systems |
| 575 | (hundreds or thousands of CPUs) will instead want to set this |
| 576 | value to the maximum value possible in order to reduce the |
| 577 | number of cache misses incurred during RCU's grace-period |
| 578 | initialization. These systems tend to run CPU-bound, and thus |
| 579 | are not helped by synchronized interrupts, and thus tend to |
| 580 | skew them, which reduces lock contention enough that large |
| 581 | leaf-level fanouts work well. |
| 582 | |
| 583 | Select a specific number if testing RCU itself. |
| 584 | |
| 585 | Select the maximum permissible value for large systems. |
| 586 | |
| 587 | Take the default if unsure. |
| 588 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 589 | config RCU_FANOUT_EXACT |
| 590 | bool "Disable tree-based hierarchical RCU auto-balancing" |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 591 | depends on TREE_RCU || TREE_PREEMPT_RCU |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 592 | default n |
| 593 | help |
| 594 | This option forces use of the exact RCU_FANOUT value specified, |
| 595 | regardless of imbalances in the hierarchy. This is useful for |
| 596 | testing RCU itself, and might one day be useful on systems with |
| 597 | strong NUMA behavior. |
| 598 | |
| 599 | Without RCU_FANOUT_EXACT, the code will balance the hierarchy. |
| 600 | |
| 601 | Say N if unsure. |
| 602 | |
Paul E. McKenney | 8bd93a2 | 2010-02-22 17:04:59 -0800 | [diff] [blame] | 603 | config RCU_FAST_NO_HZ |
| 604 | bool "Accelerate last non-dyntick-idle CPU's grace periods" |
Frederic Weisbecker | 3451d02 | 2011-08-10 23:21:01 +0200 | [diff] [blame] | 605 | depends on NO_HZ_COMMON && SMP |
Paul E. McKenney | 8bd93a2 | 2010-02-22 17:04:59 -0800 | [diff] [blame] | 606 | default n |
| 607 | help |
Paul E. McKenney | c0f4dfd | 2012-12-28 11:30:36 -0800 | [diff] [blame] | 608 | This option permits CPUs to enter dynticks-idle state even if |
| 609 | they have RCU callbacks queued, and prevents RCU from waking |
| 610 | these CPUs up more than roughly once every four jiffies (by |
| 611 | default, you can adjust this using the rcutree.rcu_idle_gp_delay |
| 612 | parameter), thus improving energy efficiency. On the other |
| 613 | hand, this option increases the duration of RCU grace periods, |
| 614 | for example, slowing down synchronize_rcu(). |
Paul E. McKenney | 8bd93a2 | 2010-02-22 17:04:59 -0800 | [diff] [blame] | 615 | |
Paul E. McKenney | c0f4dfd | 2012-12-28 11:30:36 -0800 | [diff] [blame] | 616 | Say Y if energy efficiency is critically important, and you |
| 617 | don't care about increased grace-period durations. |
Paul E. McKenney | 8bd93a2 | 2010-02-22 17:04:59 -0800 | [diff] [blame] | 618 | |
| 619 | Say N if you are unsure. |
| 620 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 621 | config TREE_RCU_TRACE |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 622 | def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 623 | select DEBUG_FS |
| 624 | help |
Paul E. McKenney | f41d911 | 2009-08-22 13:56:52 -0700 | [diff] [blame] | 625 | This option provides tracing for the TREE_RCU and |
| 626 | TREE_PREEMPT_RCU implementations, permitting Makefile to |
| 627 | trivially select kernel/rcutree_trace.c. |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 628 | |
Paul E. McKenney | 24278d1 | 2010-09-27 17:25:23 -0700 | [diff] [blame] | 629 | config RCU_BOOST |
| 630 | bool "Enable RCU priority boosting" |
Paul E. McKenney | 27f4d28 | 2011-02-07 12:47:15 -0800 | [diff] [blame] | 631 | depends on RT_MUTEXES && PREEMPT_RCU |
Paul E. McKenney | 24278d1 | 2010-09-27 17:25:23 -0700 | [diff] [blame] | 632 | default n |
| 633 | help |
| 634 | This option boosts the priority of preempted RCU readers that |
| 635 | block the current preemptible RCU grace period for too long. |
| 636 | This option also prevents heavy loads from blocking RCU |
| 637 | callback invocation for all flavors of RCU. |
| 638 | |
| 639 | Say Y here if you are working with real-time apps or heavy loads |
| 640 | Say N here if you are unsure. |
| 641 | |
| 642 | config RCU_BOOST_PRIO |
| 643 | int "Real-time priority to boost RCU readers to" |
| 644 | range 1 99 |
| 645 | depends on RCU_BOOST |
| 646 | default 1 |
| 647 | help |
Paul E. McKenney | c933664 | 2012-04-18 16:20:18 -0700 | [diff] [blame] | 648 | This option specifies the real-time priority to which long-term |
| 649 | preempted RCU readers are to be boosted. If you are working |
| 650 | with a real-time application that has one or more CPU-bound |
| 651 | threads running at a real-time priority level, you should set |
| 652 | RCU_BOOST_PRIO to a priority higher then the highest-priority |
| 653 | real-time CPU-bound thread. The default RCU_BOOST_PRIO value |
| 654 | of 1 is appropriate in the common case, which is real-time |
| 655 | applications that do not have any CPU-bound threads. |
| 656 | |
| 657 | Some real-time applications might not have a single real-time |
| 658 | thread that saturates a given CPU, but instead might have |
| 659 | multiple real-time threads that, taken together, fully utilize |
| 660 | that CPU. In this case, you should set RCU_BOOST_PRIO to |
| 661 | a priority higher than the lowest-priority thread that is |
| 662 | conspiring to prevent the CPU from running any non-real-time |
| 663 | tasks. For example, if one thread at priority 10 and another |
| 664 | thread at priority 5 are between themselves fully consuming |
| 665 | the CPU time on a given CPU, then RCU_BOOST_PRIO should be |
| 666 | set to priority 6 or higher. |
Paul E. McKenney | 24278d1 | 2010-09-27 17:25:23 -0700 | [diff] [blame] | 667 | |
| 668 | Specify the real-time priority, or take the default if unsure. |
| 669 | |
| 670 | config RCU_BOOST_DELAY |
| 671 | int "Milliseconds to delay boosting after RCU grace-period start" |
| 672 | range 0 3000 |
| 673 | depends on RCU_BOOST |
| 674 | default 500 |
| 675 | help |
| 676 | This option specifies the time to wait after the beginning of |
| 677 | a given grace period before priority-boosting preempted RCU |
| 678 | readers blocking that grace period. Note that any RCU reader |
| 679 | blocking an expedited RCU grace period is boosted immediately. |
| 680 | |
| 681 | Accept the default if unsure. |
| 682 | |
Paul E. McKenney | 3fbfbf7 | 2012-08-19 21:35:53 -0700 | [diff] [blame] | 683 | config RCU_NOCB_CPU |
Paul E. McKenney | 9a5739d | 2013-03-28 20:48:36 -0700 | [diff] [blame] | 684 | bool "Offload RCU callback processing from boot-selected CPUs" |
Paul E. McKenney | 3fbfbf7 | 2012-08-19 21:35:53 -0700 | [diff] [blame] | 685 | depends on TREE_RCU || TREE_PREEMPT_RCU |
| 686 | default n |
| 687 | help |
| 688 | Use this option to reduce OS jitter for aggressive HPC or |
| 689 | real-time workloads. It can also be used to offload RCU |
| 690 | callback invocation to energy-efficient CPUs in battery-powered |
| 691 | asymmetric multiprocessors. |
| 692 | |
| 693 | This option offloads callback invocation from the set of |
| 694 | CPUs specified at boot time by the rcu_nocbs parameter. |
Paul E. McKenney | a488985 | 2012-12-03 08:16:28 -0800 | [diff] [blame] | 695 | For each such CPU, a kthread ("rcuox/N") will be created to |
| 696 | invoke callbacks, where the "N" is the CPU being offloaded, |
| 697 | and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and |
| 698 | "s" for RCU-sched. Nothing prevents this kthread from running |
| 699 | on the specified CPUs, but (1) the kthreads may be preempted |
| 700 | between each callback, and (2) affinity or cgroups can be used |
| 701 | to force the kthreads to run on whatever set of CPUs is desired. |
Paul E. McKenney | 3fbfbf7 | 2012-08-19 21:35:53 -0700 | [diff] [blame] | 702 | |
Paul E. McKenney | 34ed6246 | 2013-01-07 13:37:42 -0800 | [diff] [blame] | 703 | Say Y here if you want to help to debug reduced OS jitter. |
Paul E. McKenney | 3fbfbf7 | 2012-08-19 21:35:53 -0700 | [diff] [blame] | 704 | Say N here if you are unsure. |
| 705 | |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 706 | choice |
| 707 | prompt "Build-forced no-CBs CPUs" |
| 708 | default RCU_NOCB_CPU_NONE |
| 709 | help |
Paul E. McKenney | 676c3dc | 2013-04-30 14:49:42 -0700 | [diff] [blame] | 710 | This option allows no-CBs CPUs (whose RCU callbacks are invoked |
| 711 | from kthreads rather than from softirq context) to be specified |
| 712 | at build time. Additional no-CBs CPUs may be specified by |
| 713 | the rcu_nocbs= boot parameter. |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 714 | |
| 715 | config RCU_NOCB_CPU_NONE |
| 716 | bool "No build_forced no-CBs CPUs" |
Frederic Weisbecker | 73c3082 | 2013-05-03 01:28:12 +0200 | [diff] [blame] | 717 | depends on RCU_NOCB_CPU && !NO_HZ_FULL |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 718 | help |
| 719 | This option does not force any of the CPUs to be no-CBs CPUs. |
| 720 | Only CPUs designated by the rcu_nocbs= boot parameter will be |
Paul E. McKenney | 676c3dc | 2013-04-30 14:49:42 -0700 | [diff] [blame] | 721 | no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU |
| 722 | kthreads whose names begin with "rcuo". All other CPUs will |
| 723 | invoke their own RCU callbacks in softirq context. |
| 724 | |
| 725 | Select this option if you want to choose no-CBs CPUs at |
| 726 | boot time, for example, to allow testing of different no-CBs |
| 727 | configurations without having to rebuild the kernel each time. |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 728 | |
| 729 | config RCU_NOCB_CPU_ZERO |
| 730 | bool "CPU 0 is a build_forced no-CBs CPU" |
Frederic Weisbecker | 73c3082 | 2013-05-03 01:28:12 +0200 | [diff] [blame] | 731 | depends on RCU_NOCB_CPU && !NO_HZ_FULL |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 732 | help |
Paul E. McKenney | 676c3dc | 2013-04-30 14:49:42 -0700 | [diff] [blame] | 733 | This option forces CPU 0 to be a no-CBs CPU, so that its RCU |
| 734 | callbacks are invoked by a per-CPU kthread whose name begins |
| 735 | with "rcuo". Additional CPUs may be designated as no-CBs |
| 736 | CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs. |
| 737 | All other CPUs will invoke their own RCU callbacks in softirq |
| 738 | context. |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 739 | |
| 740 | Select this if CPU 0 needs to be a no-CBs CPU for real-time |
Paul E. McKenney | 676c3dc | 2013-04-30 14:49:42 -0700 | [diff] [blame] | 741 | or energy-efficiency reasons, but the real reason it exists |
| 742 | is to ensure that randconfig testing covers mixed systems. |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 743 | |
| 744 | config RCU_NOCB_CPU_ALL |
| 745 | bool "All CPUs are build_forced no-CBs CPUs" |
| 746 | depends on RCU_NOCB_CPU |
| 747 | help |
| 748 | This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= |
Paul E. McKenney | 676c3dc | 2013-04-30 14:49:42 -0700 | [diff] [blame] | 749 | boot parameter will be ignored. All CPUs' RCU callbacks will |
| 750 | be executed in the context of per-CPU rcuo kthreads created for |
| 751 | this purpose. Assuming that the kthreads whose names start with |
| 752 | "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter |
| 753 | on the remaining CPUs, but might decrease memory locality during |
| 754 | RCU-callback invocation, thus potentially degrading throughput. |
Paul E. McKenney | 911af50 | 2013-02-11 10:23:27 -0800 | [diff] [blame] | 755 | |
| 756 | Select this if all CPUs need to be no-CBs CPUs for real-time |
| 757 | or energy-efficiency reasons. |
| 758 | |
| 759 | endchoice |
| 760 | |
Mike Travis | c903ff8 | 2009-01-15 12:28:29 -0800 | [diff] [blame] | 761 | endmenu # "RCU Subsystem" |
| 762 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 763 | config IKCONFIG |
Ross Biro | f2443ab | 2006-09-30 23:27:25 -0700 | [diff] [blame] | 764 | tristate "Kernel .config support" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 765 | ---help--- |
| 766 | This option enables the complete Linux kernel ".config" file |
| 767 | contents to be saved in the kernel. It provides documentation |
| 768 | of which kernel options are used in a running kernel or in an |
| 769 | on-disk kernel. This information can be extracted from the kernel |
| 770 | image file with the script scripts/extract-ikconfig and used as |
| 771 | input to rebuild the current kernel or to build another kernel. |
| 772 | It can also be extracted from a running kernel by reading |
| 773 | /proc/config.gz if enabled (below). |
| 774 | |
| 775 | config IKCONFIG_PROC |
| 776 | bool "Enable access to .config through /proc/config.gz" |
| 777 | depends on IKCONFIG && PROC_FS |
| 778 | ---help--- |
| 779 | This option enables access to the kernel configuration file |
| 780 | through /proc/config.gz. |
| 781 | |
Alistair John Strachan | 794543a | 2007-05-08 00:31:15 -0700 | [diff] [blame] | 782 | config LOG_BUF_SHIFT |
| 783 | int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" |
| 784 | range 12 21 |
Adrian Bunk | f17a32e | 2008-04-29 00:58:58 -0700 | [diff] [blame] | 785 | default 17 |
Alistair John Strachan | 794543a | 2007-05-08 00:31:15 -0700 | [diff] [blame] | 786 | help |
| 787 | Select kernel log buffer size as a power of 2. |
Adrian Bunk | f17a32e | 2008-04-29 00:58:58 -0700 | [diff] [blame] | 788 | Examples: |
| 789 | 17 => 128 KB |
| 790 | 16 => 64 KB |
| 791 | 15 => 32 KB |
| 792 | 14 => 16 KB |
Alistair John Strachan | 794543a | 2007-05-08 00:31:15 -0700 | [diff] [blame] | 793 | 13 => 8 KB |
| 794 | 12 => 4 KB |
| 795 | |
KAMEZAWA Hiroyuki | 5cdc38f | 2009-01-07 18:07:30 -0800 | [diff] [blame] | 796 | # |
| 797 | # Architectures with an unreliable sched_clock() should select this: |
| 798 | # |
| 799 | config HAVE_UNSTABLE_SCHED_CLOCK |
| 800 | bool |
| 801 | |
Stephen Boyd | 38ff87f | 2013-06-01 23:39:40 -0700 | [diff] [blame] | 802 | config GENERIC_SCHED_CLOCK |
| 803 | bool |
| 804 | |
Andrea Arcangeli | be3a728 | 2012-10-04 01:50:47 +0200 | [diff] [blame] | 805 | # |
| 806 | # For architectures that want to enable the support for NUMA-affine scheduler |
| 807 | # balancing logic: |
| 808 | # |
| 809 | config ARCH_SUPPORTS_NUMA_BALANCING |
| 810 | bool |
| 811 | |
Peter Zijlstra | be5e610 | 2013-11-18 18:27:06 +0100 | [diff] [blame] | 812 | # |
| 813 | # For architectures that know their GCC __int128 support is sound |
| 814 | # |
| 815 | config ARCH_SUPPORTS_INT128 |
| 816 | bool |
| 817 | |
Andrea Arcangeli | be3a728 | 2012-10-04 01:50:47 +0200 | [diff] [blame] | 818 | # For architectures that (ab)use NUMA to represent different memory regions |
| 819 | # all cpu-local but of different latencies, such as SuperH. |
| 820 | # |
| 821 | config ARCH_WANT_NUMA_VARIABLE_LOCALITY |
| 822 | bool |
| 823 | |
| 824 | # |
| 825 | # For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE |
| 826 | config ARCH_WANTS_PROT_NUMA_PROT_NONE |
| 827 | bool |
| 828 | |
| 829 | config ARCH_USES_NUMA_PROT_NONE |
| 830 | bool |
| 831 | default y |
| 832 | depends on ARCH_WANTS_PROT_NUMA_PROT_NONE |
| 833 | depends on NUMA_BALANCING |
| 834 | |
Mel Gorman | 1a687c2 | 2012-11-22 11:16:36 +0000 | [diff] [blame] | 835 | config NUMA_BALANCING_DEFAULT_ENABLED |
| 836 | bool "Automatically enable NUMA aware memory/task placement" |
| 837 | default y |
| 838 | depends on NUMA_BALANCING |
| 839 | help |
Paul Gortmaker | 6d56a41 | 2013-08-13 11:06:50 -0400 | [diff] [blame] | 840 | If set, automatic NUMA balancing will be enabled if running on a NUMA |
Mel Gorman | 1a687c2 | 2012-11-22 11:16:36 +0000 | [diff] [blame] | 841 | machine. |
| 842 | |
Andrea Arcangeli | be3a728 | 2012-10-04 01:50:47 +0200 | [diff] [blame] | 843 | config NUMA_BALANCING |
| 844 | bool "Memory placement aware NUMA scheduler" |
Andrea Arcangeli | be3a728 | 2012-10-04 01:50:47 +0200 | [diff] [blame] | 845 | depends on ARCH_SUPPORTS_NUMA_BALANCING |
| 846 | depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY |
| 847 | depends on SMP && NUMA && MIGRATION |
| 848 | help |
| 849 | This option adds support for automatic NUMA aware memory/task placement. |
| 850 | The mechanism is quite primitive and is based on migrating memory when |
Paul Gortmaker | 6d56a41 | 2013-08-13 11:06:50 -0400 | [diff] [blame] | 851 | it has references to the node the task is running on. |
Andrea Arcangeli | be3a728 | 2012-10-04 01:50:47 +0200 | [diff] [blame] | 852 | |
| 853 | This system will be inactive on UMA systems. |
| 854 | |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 855 | menuconfig CGROUPS |
| 856 | boolean "Control Group support" |
Paul Menage | ddbcc7e | 2007-10-18 23:39:30 -0700 | [diff] [blame] | 857 | help |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 858 | This option adds support for grouping sets of processes together, for |
KAMEZAWA Hiroyuki | 5cdc38f | 2009-01-07 18:07:30 -0800 | [diff] [blame] | 859 | use with process control subsystems such as Cpusets, CFS, memory |
| 860 | controls or device isolation. |
| 861 | See |
KAMEZAWA Hiroyuki | 5cdc38f | 2009-01-07 18:07:30 -0800 | [diff] [blame] | 862 | - Documentation/scheduler/sched-design-CFS.txt (CFS) |
Li Zefan | 45ce80f | 2009-01-15 13:50:59 -0800 | [diff] [blame] | 863 | - Documentation/cgroups/ (features for grouping, isolation |
| 864 | and resource control) |
Paul Menage | ddbcc7e | 2007-10-18 23:39:30 -0700 | [diff] [blame] | 865 | |
| 866 | Say N if unsure. |
| 867 | |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 868 | if CGROUPS |
| 869 | |
Paul Menage | 006cb99 | 2007-10-18 23:39:43 -0700 | [diff] [blame] | 870 | config CGROUP_DEBUG |
| 871 | bool "Example debug cgroup subsystem" |
Paul Menage | 418d7d8 | 2008-04-29 01:00:05 -0700 | [diff] [blame] | 872 | default n |
Paul Menage | 006cb99 | 2007-10-18 23:39:43 -0700 | [diff] [blame] | 873 | help |
| 874 | This option enables a simple cgroup subsystem that |
| 875 | exports useful debugging information about the cgroups |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 876 | framework. |
Paul Menage | 006cb99 | 2007-10-18 23:39:43 -0700 | [diff] [blame] | 877 | |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 878 | Say N if unsure. |
Paul Menage | 006cb99 | 2007-10-18 23:39:43 -0700 | [diff] [blame] | 879 | |
Matt Helsley | dc52ddc | 2008-10-18 20:27:21 -0700 | [diff] [blame] | 880 | config CGROUP_FREEZER |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 881 | bool "Freezer cgroup subsystem" |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 882 | help |
| 883 | Provides a way to freeze and unfreeze all tasks in a |
Matt Helsley | dc52ddc | 2008-10-18 20:27:21 -0700 | [diff] [blame] | 884 | cgroup. |
| 885 | |
Serge E. Hallyn | 08ce5f1 | 2008-04-29 01:00:10 -0700 | [diff] [blame] | 886 | config CGROUP_DEVICE |
| 887 | bool "Device controller for cgroups" |
Serge E. Hallyn | 08ce5f1 | 2008-04-29 01:00:10 -0700 | [diff] [blame] | 888 | help |
| 889 | Provides a cgroup implementing whitelists for devices which |
| 890 | a process in the cgroup can mknod or open. |
| 891 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 892 | config CPUSETS |
| 893 | bool "Cpuset support" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 894 | help |
Randy Dunlap | d9fd8a6 | 2005-07-27 11:45:11 -0700 | [diff] [blame] | 895 | This option will let you create and manage CPUSETs which |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 896 | allow dynamically partitioning a system into sets of CPUs and |
| 897 | Memory Nodes and assigning tasks to run only within those sets. |
| 898 | This is primarily useful on large SMP or NUMA systems. |
| 899 | |
| 900 | Say N if unsure. |
| 901 | |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 902 | config PROC_PID_CPUSET |
| 903 | bool "Include legacy /proc/<pid>/cpuset file" |
| 904 | depends on CPUSETS |
| 905 | default y |
| 906 | |
Srivatsa Vaddagiri | d842de8 | 2007-12-02 20:04:49 +0100 | [diff] [blame] | 907 | config CGROUP_CPUACCT |
| 908 | bool "Simple CPU accounting cgroup subsystem" |
Srivatsa Vaddagiri | d842de8 | 2007-12-02 20:04:49 +0100 | [diff] [blame] | 909 | help |
| 910 | Provides a simple Resource Controller for monitoring the |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 911 | total CPU consumed by the tasks in a cgroup. |
Srivatsa Vaddagiri | d842de8 | 2007-12-02 20:04:49 +0100 | [diff] [blame] | 912 | |
Pavel Emelianov | e552b66 | 2008-02-07 00:13:49 -0800 | [diff] [blame] | 913 | config RESOURCE_COUNTERS |
| 914 | bool "Resource counters" |
| 915 | help |
| 916 | This option enables controller independent resource accounting |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 917 | infrastructure that works with cgroups. |
Pavel Emelianov | e552b66 | 2008-02-07 00:13:49 -0800 | [diff] [blame] | 918 | |
Andrew Morton | c255a45 | 2012-07-31 16:43:02 -0700 | [diff] [blame] | 919 | config MEMCG |
Balbir Singh | 00f0b82 | 2008-03-04 14:28:39 -0800 | [diff] [blame] | 920 | bool "Memory Resource Controller for Control Groups" |
Daniel Lezcano | 79ae9c2 | 2010-10-27 15:34:39 -0700 | [diff] [blame] | 921 | depends on RESOURCE_COUNTERS |
Balbir Singh | cf475ad | 2008-04-29 01:00:16 -0700 | [diff] [blame] | 922 | select MM_OWNER |
Tejun Heo | 79bd981 | 2013-11-22 18:20:42 -0500 | [diff] [blame] | 923 | select EVENTFD |
Balbir Singh | 00f0b82 | 2008-03-04 14:28:39 -0800 | [diff] [blame] | 924 | help |
KAMEZAWA Hiroyuki | 84ad6d7 | 2008-10-29 14:01:06 -0700 | [diff] [blame] | 925 | Provides a memory resource controller that manages both anonymous |
Thadeu Lima de Souza Cascardo | 21acb9c | 2009-02-04 10:12:08 +0100 | [diff] [blame] | 926 | memory and page cache. (See Documentation/cgroups/memory.txt) |
Balbir Singh | 00f0b82 | 2008-03-04 14:28:39 -0800 | [diff] [blame] | 927 | |
| 928 | Note that setting this option increases fixed memory overhead |
KAMEZAWA Hiroyuki | 84ad6d7 | 2008-10-29 14:01:06 -0700 | [diff] [blame] | 929 | associated with each page of memory in the system. By this, |
Sergey Dyasly | f60e2a9 | 2013-07-03 15:03:30 -0700 | [diff] [blame] | 930 | 8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory |
KAMEZAWA Hiroyuki | 84ad6d7 | 2008-10-29 14:01:06 -0700 | [diff] [blame] | 931 | usage tracking struct at boot. Total amount of this is printed out |
| 932 | at boot. |
Balbir Singh | 00f0b82 | 2008-03-04 14:28:39 -0800 | [diff] [blame] | 933 | |
| 934 | Only enable when you're ok with these trade offs and really |
KAMEZAWA Hiroyuki | 84ad6d7 | 2008-10-29 14:01:06 -0700 | [diff] [blame] | 935 | sure you need the memory resource controller. Even when you enable |
| 936 | this, you can set "cgroup_disable=memory" at your boot option to |
| 937 | disable memory resource controller and you can avoid overheads. |
Li Zefan | c9d5409 | 2009-01-07 18:07:35 -0800 | [diff] [blame] | 938 | (and lose benefits of memory resource controller) |
Balbir Singh | 00f0b82 | 2008-03-04 14:28:39 -0800 | [diff] [blame] | 939 | |
Balbir Singh | cf475ad | 2008-04-29 01:00:16 -0700 | [diff] [blame] | 940 | This config option also selects MM_OWNER config option, which |
| 941 | could in turn add some fork/exit overhead. |
| 942 | |
Andrew Morton | c255a45 | 2012-07-31 16:43:02 -0700 | [diff] [blame] | 943 | config MEMCG_SWAP |
KAMEZAWA Hiroyuki | 65e0e81 | 2010-08-10 18:02:56 -0700 | [diff] [blame] | 944 | bool "Memory Resource Controller Swap Extension" |
Andrew Morton | c255a45 | 2012-07-31 16:43:02 -0700 | [diff] [blame] | 945 | depends on MEMCG && SWAP |
KAMEZAWA Hiroyuki | c077719 | 2009-01-07 18:07:57 -0800 | [diff] [blame] | 946 | help |
| 947 | Add swap management feature to memory resource controller. When you |
| 948 | enable this, you can limit mem+swap usage per cgroup. In other words, |
| 949 | when you disable this, memory resource controller has no cares to |
| 950 | usage of swap...a process can exhaust all of the swap. This extension |
| 951 | is useful when you want to avoid exhaustion swap but this itself |
| 952 | adds more overheads and consumes memory for remembering information. |
| 953 | Especially if you use 32bit system or small memory system, please |
| 954 | be careful about enabling this. When memory resource controller |
| 955 | is disabled by boot option, this will be automatically disabled and |
| 956 | there will be no overhead from this. Even when you set this config=y, |
WANG Cong | 00a66d2 | 2011-07-25 17:12:12 -0700 | [diff] [blame] | 957 | if boot option "swapaccount=0" is set, swap will not be accounted. |
KAMEZAWA Hiroyuki | 627991a | 2009-04-02 16:57:47 -0700 | [diff] [blame] | 958 | Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page |
| 959 | size is 4096bytes, 512k per 1Gbytes of swap. |
Andrew Morton | c255a45 | 2012-07-31 16:43:02 -0700 | [diff] [blame] | 960 | config MEMCG_SWAP_ENABLED |
Michal Hocko | a42c390 | 2010-11-24 12:57:08 -0800 | [diff] [blame] | 961 | bool "Memory Resource Controller Swap Extension enabled by default" |
Andrew Morton | c255a45 | 2012-07-31 16:43:02 -0700 | [diff] [blame] | 962 | depends on MEMCG_SWAP |
Michal Hocko | a42c390 | 2010-11-24 12:57:08 -0800 | [diff] [blame] | 963 | default y |
| 964 | help |
| 965 | Memory Resource Controller Swap Extension comes with its price in |
| 966 | a bigger memory consumption. General purpose distribution kernels |
Jim Cromie | 43d547f | 2010-12-17 14:32:36 -0700 | [diff] [blame] | 967 | which want to enable the feature but keep it disabled by default |
Michal Hocko | 07555ac | 2013-08-22 16:35:46 -0700 | [diff] [blame] | 968 | and let the user enable it by swapaccount=1 boot command line |
Michal Hocko | a42c390 | 2010-11-24 12:57:08 -0800 | [diff] [blame] | 969 | parameter should have this option unselected. |
| 970 | For those who want to have the feature enabled by default should |
| 971 | select this option (if, for some reason, they need to disable it |
WANG Cong | 00a66d2 | 2011-07-25 17:12:12 -0700 | [diff] [blame] | 972 | then swapaccount=0 does the trick). |
Andrew Morton | c255a45 | 2012-07-31 16:43:02 -0700 | [diff] [blame] | 973 | config MEMCG_KMEM |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 974 | bool "Memory Resource Controller Kernel Memory accounting" |
| 975 | depends on MEMCG |
Glauber Costa | 510fc4e | 2012-12-18 14:21:47 -0800 | [diff] [blame] | 976 | depends on SLUB || SLAB |
Glauber Costa | e5671df | 2011-12-11 21:47:01 +0000 | [diff] [blame] | 977 | help |
| 978 | The Kernel Memory extension for Memory Resource Controller can limit |
| 979 | the amount of memory used by kernel objects in the system. Those are |
| 980 | fundamentally different from the entities handled by the standard |
| 981 | Memory Controller, which are page-based, and can be swapped. Users of |
| 982 | the kmem extension can use it to guarantee that no group of processes |
| 983 | will ever exhaust kernel resources alone. |
KAMEZAWA Hiroyuki | c077719 | 2009-01-07 18:07:57 -0800 | [diff] [blame] | 984 | |
Aneesh Kumar K.V | 2bc64a2 | 2012-07-31 16:42:12 -0700 | [diff] [blame] | 985 | config CGROUP_HUGETLB |
| 986 | bool "HugeTLB Resource Controller for Control Groups" |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 987 | depends on RESOURCE_COUNTERS && HUGETLB_PAGE |
Aneesh Kumar K.V | 2bc64a2 | 2012-07-31 16:42:12 -0700 | [diff] [blame] | 988 | default n |
| 989 | help |
| 990 | Provides a cgroup Resource Controller for HugeTLB pages. |
| 991 | When you enable this, you can put a per cgroup limit on HugeTLB usage. |
| 992 | The limit is enforced during page fault. Since HugeTLB doesn't |
| 993 | support page reclaim, enforcing the limit at page fault time implies |
| 994 | that, the application will get SIGBUS signal if it tries to access |
| 995 | HugeTLB pages beyond its limit. This requires the application to know |
| 996 | beforehand how much HugeTLB pages it would require for its use. The |
| 997 | control group is tracked in the third page lru pointer. This means |
| 998 | that we cannot use the controller with huge page less than 3 pages. |
| 999 | |
Stephane Eranian | e5d1367 | 2011-02-14 11:20:01 +0200 | [diff] [blame] | 1000 | config CGROUP_PERF |
| 1001 | bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" |
| 1002 | depends on PERF_EVENTS && CGROUPS |
| 1003 | help |
| 1004 | This option extends the per-cpu mode to restrict monitoring to |
Li Zefan | 2d0f252 | 2011-03-03 14:26:20 +0800 | [diff] [blame] | 1005 | threads which belong to the cgroup specified and run on the |
Stephane Eranian | e5d1367 | 2011-02-14 11:20:01 +0200 | [diff] [blame] | 1006 | designated cpu. |
| 1007 | |
| 1008 | Say N if unsure. |
| 1009 | |
Dhaval Giani | 7c94143 | 2010-01-20 13:26:18 +0100 | [diff] [blame] | 1010 | menuconfig CGROUP_SCHED |
| 1011 | bool "Group CPU scheduler" |
Dhaval Giani | 7c94143 | 2010-01-20 13:26:18 +0100 | [diff] [blame] | 1012 | default n |
| 1013 | help |
| 1014 | This feature lets CPU scheduler recognize task groups and control CPU |
| 1015 | bandwidth allocation to such task groups. It uses cgroups to group |
| 1016 | tasks. |
| 1017 | |
| 1018 | if CGROUP_SCHED |
| 1019 | config FAIR_GROUP_SCHED |
| 1020 | bool "Group scheduling for SCHED_OTHER" |
| 1021 | depends on CGROUP_SCHED |
| 1022 | default CGROUP_SCHED |
| 1023 | |
Paul Turner | ab84d31 | 2011-07-21 09:43:28 -0700 | [diff] [blame] | 1024 | config CFS_BANDWIDTH |
| 1025 | bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" |
Paul Turner | ab84d31 | 2011-07-21 09:43:28 -0700 | [diff] [blame] | 1026 | depends on FAIR_GROUP_SCHED |
| 1027 | default n |
| 1028 | help |
| 1029 | This option allows users to define CPU bandwidth rates (limits) for |
| 1030 | tasks running within the fair group scheduler. Groups with no limit |
| 1031 | set are considered to be unconstrained and will run with no |
| 1032 | restriction. |
| 1033 | See tip/Documentation/scheduler/sched-bwc.txt for more information. |
| 1034 | |
Dhaval Giani | 7c94143 | 2010-01-20 13:26:18 +0100 | [diff] [blame] | 1035 | config RT_GROUP_SCHED |
| 1036 | bool "Group scheduling for SCHED_RR/FIFO" |
Dhaval Giani | 7c94143 | 2010-01-20 13:26:18 +0100 | [diff] [blame] | 1037 | depends on CGROUP_SCHED |
| 1038 | default n |
| 1039 | help |
| 1040 | This feature lets you explicitly allocate real CPU bandwidth |
Li Zefan | 32bd7eb | 2010-03-24 13:17:19 +0800 | [diff] [blame] | 1041 | to task groups. If enabled, it will also make it impossible to |
Dhaval Giani | 7c94143 | 2010-01-20 13:26:18 +0100 | [diff] [blame] | 1042 | schedule realtime tasks for non-root users until you allocate |
| 1043 | realtime bandwidth for them. |
| 1044 | See Documentation/scheduler/sched-rt-group.txt for more information. |
| 1045 | |
| 1046 | endif #CGROUP_SCHED |
| 1047 | |
Vivek Goyal | afc24d4 | 2010-04-26 19:27:56 +0200 | [diff] [blame] | 1048 | config BLK_CGROUP |
Tejun Heo | 32e380a | 2012-03-05 13:14:54 -0800 | [diff] [blame] | 1049 | bool "Block IO controller" |
Daniel Lezcano | 79ae9c2 | 2010-10-27 15:34:39 -0700 | [diff] [blame] | 1050 | depends on BLOCK |
Vivek Goyal | afc24d4 | 2010-04-26 19:27:56 +0200 | [diff] [blame] | 1051 | default n |
| 1052 | ---help--- |
| 1053 | Generic block IO controller cgroup interface. This is the common |
| 1054 | cgroup interface which should be used by various IO controlling |
| 1055 | policies. |
| 1056 | |
| 1057 | Currently, CFQ IO scheduler uses it to recognize task groups and |
| 1058 | control disk bandwidth allocation (proportional time slice allocation) |
Vivek Goyal | e43473b | 2010-09-15 17:06:35 -0400 | [diff] [blame] | 1059 | to such task groups. It is also used by bio throttling logic in |
| 1060 | block layer to implement upper limit in IO rates on a device. |
Vivek Goyal | afc24d4 | 2010-04-26 19:27:56 +0200 | [diff] [blame] | 1061 | |
| 1062 | This option only enables generic Block IO controller infrastructure. |
Vivek Goyal | e43473b | 2010-09-15 17:06:35 -0400 | [diff] [blame] | 1063 | One needs to also enable actual IO controlling logic/policy. For |
Michael Witten | 79e2e75 | 2011-01-16 21:43:10 +0000 | [diff] [blame] | 1064 | enabling proportional weight division of disk bandwidth in CFQ, set |
| 1065 | CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set |
Michael Witten | c5e0591 | 2011-01-17 00:08:41 +0000 | [diff] [blame] | 1066 | CONFIG_BLK_DEV_THROTTLING=y. |
Vivek Goyal | afc24d4 | 2010-04-26 19:27:56 +0200 | [diff] [blame] | 1067 | |
| 1068 | See Documentation/cgroups/blkio-controller.txt for more information. |
| 1069 | |
| 1070 | config DEBUG_BLK_CGROUP |
| 1071 | bool "Enable Block IO controller debugging" |
| 1072 | depends on BLK_CGROUP |
| 1073 | default n |
| 1074 | ---help--- |
| 1075 | Enable some debugging help. Currently it exports additional stat |
| 1076 | files in a cgroup which can be useful for debugging. |
| 1077 | |
Li Zefan | 23964d2 | 2009-01-15 13:50:58 -0800 | [diff] [blame] | 1078 | endif # CGROUPS |
KAMEZAWA Hiroyuki | c077719 | 2009-01-07 18:07:57 -0800 | [diff] [blame] | 1079 | |
Cyrill Gorcunov | 067bce1 | 2012-01-12 17:20:49 -0800 | [diff] [blame] | 1080 | config CHECKPOINT_RESTORE |
| 1081 | bool "Checkpoint/restore support" if EXPERT |
| 1082 | default n |
| 1083 | help |
| 1084 | Enables additional kernel features in a sake of checkpoint/restore. |
| 1085 | In particular it adds auxiliary prctl codes to setup process text, |
| 1086 | data and heap segment sizes, and a few additional /proc filesystem |
| 1087 | entries. |
| 1088 | |
| 1089 | If unsure, say N here. |
| 1090 | |
Daniel Lezcano | 8dd2a82 | 2010-10-27 15:34:38 -0700 | [diff] [blame] | 1091 | menuconfig NAMESPACES |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1092 | bool "Namespaces support" if EXPERT |
| 1093 | default !EXPERT |
Pavel Emelyanov | c5289a6 | 2008-02-08 04:18:19 -0800 | [diff] [blame] | 1094 | help |
| 1095 | Provides the way to make tasks work with different objects using |
| 1096 | the same id. For example same IPC id may refer to different objects |
| 1097 | or same user id or pid may refer to different tasks when used in |
| 1098 | different namespaces. |
| 1099 | |
Daniel Lezcano | 8dd2a82 | 2010-10-27 15:34:38 -0700 | [diff] [blame] | 1100 | if NAMESPACES |
| 1101 | |
Pavel Emelyanov | 58bfdd6d | 2008-02-08 04:18:21 -0800 | [diff] [blame] | 1102 | config UTS_NS |
| 1103 | bool "UTS namespace" |
Daniel Lezcano | 17a6d44 | 2010-10-27 15:34:37 -0700 | [diff] [blame] | 1104 | default y |
Pavel Emelyanov | 58bfdd6d | 2008-02-08 04:18:21 -0800 | [diff] [blame] | 1105 | help |
| 1106 | In this namespace tasks see different info provided with the |
| 1107 | uname() system call |
| 1108 | |
Pavel Emelyanov | ae5e1b2 | 2008-02-08 04:18:22 -0800 | [diff] [blame] | 1109 | config IPC_NS |
| 1110 | bool "IPC namespace" |
Daniel Lezcano | 8dd2a82 | 2010-10-27 15:34:38 -0700 | [diff] [blame] | 1111 | depends on (SYSVIPC || POSIX_MQUEUE) |
Daniel Lezcano | 17a6d44 | 2010-10-27 15:34:37 -0700 | [diff] [blame] | 1112 | default y |
Pavel Emelyanov | ae5e1b2 | 2008-02-08 04:18:22 -0800 | [diff] [blame] | 1113 | help |
| 1114 | In this namespace tasks work with IPC ids which correspond to |
Serge E. Hallyn | 614b84c | 2009-04-06 19:01:08 -0700 | [diff] [blame] | 1115 | different IPC objects in different namespaces. |
Pavel Emelyanov | ae5e1b2 | 2008-02-08 04:18:22 -0800 | [diff] [blame] | 1116 | |
Pavel Emelyanov | aee16ce | 2008-02-08 04:18:23 -0800 | [diff] [blame] | 1117 | config USER_NS |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 1118 | bool "User namespace" |
Eric W. Biederman | 5673a94 | 2011-11-17 10:23:55 -0800 | [diff] [blame] | 1119 | default n |
Pavel Emelyanov | aee16ce | 2008-02-08 04:18:23 -0800 | [diff] [blame] | 1120 | help |
| 1121 | This allows containers, i.e. vservers, to use user namespaces |
| 1122 | to provide different user info for different servers. |
Eric W. Biederman | e11f0ae | 2013-01-25 16:48:31 -0800 | [diff] [blame] | 1123 | |
| 1124 | When user namespaces are enabled in the kernel it is |
| 1125 | recommended that the MEMCG and MEMCG_KMEM options also be |
| 1126 | enabled and that user-space use the memory control groups to |
| 1127 | limit the amount of memory a memory unprivileged users can |
| 1128 | use. |
| 1129 | |
Pavel Emelyanov | aee16ce | 2008-02-08 04:18:23 -0800 | [diff] [blame] | 1130 | If unsure, say N. |
| 1131 | |
Pavel Emelyanov | 74bd59b | 2008-02-08 04:18:24 -0800 | [diff] [blame] | 1132 | config PID_NS |
Daniel Lezcano | 9bd38c2 | 2010-10-27 15:34:37 -0700 | [diff] [blame] | 1133 | bool "PID Namespaces" |
Daniel Lezcano | 17a6d44 | 2010-10-27 15:34:37 -0700 | [diff] [blame] | 1134 | default y |
Pavel Emelyanov | 74bd59b | 2008-02-08 04:18:24 -0800 | [diff] [blame] | 1135 | help |
Heikki Orsila | 12d2b8f | 2008-07-06 15:48:02 +0300 | [diff] [blame] | 1136 | Support process id namespaces. This allows having multiple |
Matt LaPlante | 692105b | 2009-01-26 11:12:25 +0100 | [diff] [blame] | 1137 | processes with the same pid as long as they are in different |
Pavel Emelyanov | 74bd59b | 2008-02-08 04:18:24 -0800 | [diff] [blame] | 1138 | pid namespaces. This is a building block of containers. |
| 1139 | |
Matt Helsley | d6eb633 | 2009-01-26 12:25:55 -0800 | [diff] [blame] | 1140 | config NET_NS |
| 1141 | bool "Network namespace" |
Daniel Lezcano | 8dd2a82 | 2010-10-27 15:34:38 -0700 | [diff] [blame] | 1142 | depends on NET |
Daniel Lezcano | 17a6d44 | 2010-10-27 15:34:37 -0700 | [diff] [blame] | 1143 | default y |
Matt Helsley | d6eb633 | 2009-01-26 12:25:55 -0800 | [diff] [blame] | 1144 | help |
| 1145 | Allow user space to create what appear to be multiple instances |
| 1146 | of the network stack. |
| 1147 | |
Daniel Lezcano | 8dd2a82 | 2010-10-27 15:34:38 -0700 | [diff] [blame] | 1148 | endif # NAMESPACES |
| 1149 | |
Mike Galbraith | 5091faa | 2010-11-30 14:18:03 +0100 | [diff] [blame] | 1150 | config SCHED_AUTOGROUP |
| 1151 | bool "Automatic process group scheduling" |
Mike Galbraith | 5091faa | 2010-11-30 14:18:03 +0100 | [diff] [blame] | 1152 | select CGROUPS |
| 1153 | select CGROUP_SCHED |
| 1154 | select FAIR_GROUP_SCHED |
| 1155 | help |
| 1156 | This option optimizes the scheduler for common desktop workloads by |
| 1157 | automatically creating and populating task groups. This separation |
| 1158 | of workloads isolates aggressive CPU burners (like build jobs) from |
| 1159 | desktop applications. Task group autogeneration is currently based |
| 1160 | upon task session. |
| 1161 | |
Daniel Lezcano | 7af37be | 2010-10-27 15:34:41 -0700 | [diff] [blame] | 1162 | config MM_OWNER |
| 1163 | bool |
| 1164 | |
| 1165 | config SYSFS_DEPRECATED |
Ferenc Wagner | 5d6a4ea | 2011-01-10 19:04:22 +0100 | [diff] [blame] | 1166 | bool "Enable deprecated sysfs features to support old userspace tools" |
Daniel Lezcano | 7af37be | 2010-10-27 15:34:41 -0700 | [diff] [blame] | 1167 | depends on SYSFS |
| 1168 | default n |
| 1169 | help |
| 1170 | This option adds code that switches the layout of the "block" class |
| 1171 | devices, to not show up in /sys/class/block/, but only in |
| 1172 | /sys/block/. |
| 1173 | |
| 1174 | This switch is only active when the sysfs.deprecated=1 boot option is |
| 1175 | passed or the SYSFS_DEPRECATED_V2 option is set. |
| 1176 | |
| 1177 | This option allows new kernels to run on old distributions and tools, |
| 1178 | which might get confused by /sys/class/block/. Since 2007/2008 all |
| 1179 | major distributions and tools handle this just fine. |
| 1180 | |
| 1181 | Recent distributions and userspace tools after 2009/2010 depend on |
| 1182 | the existence of /sys/class/block/, and will not work with this |
| 1183 | option enabled. |
| 1184 | |
| 1185 | Only if you are using a new kernel on an old distribution, you might |
| 1186 | need to say Y here. |
| 1187 | |
| 1188 | config SYSFS_DEPRECATED_V2 |
Ferenc Wagner | 5d6a4ea | 2011-01-10 19:04:22 +0100 | [diff] [blame] | 1189 | bool "Enable deprecated sysfs features by default" |
Daniel Lezcano | 7af37be | 2010-10-27 15:34:41 -0700 | [diff] [blame] | 1190 | default n |
| 1191 | depends on SYSFS |
| 1192 | depends on SYSFS_DEPRECATED |
| 1193 | help |
| 1194 | Enable deprecated sysfs by default. |
| 1195 | |
| 1196 | See the CONFIG_SYSFS_DEPRECATED option for more details about this |
| 1197 | option. |
| 1198 | |
| 1199 | Only if you are using a new kernel on an old distribution, you might |
| 1200 | need to say Y here. Even then, odds are you would not need it |
| 1201 | enabled, you can always pass the boot option if absolutely necessary. |
| 1202 | |
| 1203 | config RELAY |
| 1204 | bool "Kernel->user space relay support (formerly relayfs)" |
| 1205 | help |
| 1206 | This option enables support for relay interface support in |
| 1207 | certain file systems (such as debugfs). |
| 1208 | It is designed to provide an efficient mechanism for tools and |
| 1209 | facilities to relay large amounts of data from kernel space to |
| 1210 | user space. |
| 1211 | |
| 1212 | If unsure, say N. |
| 1213 | |
Dimitri Gorokhovik | f991633 | 2007-03-06 01:42:17 -0800 | [diff] [blame] | 1214 | config BLK_DEV_INITRD |
| 1215 | bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" |
| 1216 | depends on BROKEN || !FRV |
| 1217 | help |
| 1218 | The initial RAM filesystem is a ramfs which is loaded by the |
| 1219 | boot loader (loadlin or lilo) and that is mounted as root |
| 1220 | before the normal boot procedure. It is typically used to |
| 1221 | load modules needed to mount the "real" root file system, |
| 1222 | etc. See <file:Documentation/initrd.txt> for details. |
| 1223 | |
| 1224 | If RAM disk support (BLK_DEV_RAM) is also included, this |
| 1225 | also enables initial RAM disk (initrd) support and adds |
| 1226 | 15 Kbytes (more on some other architectures) to the kernel size. |
| 1227 | |
| 1228 | If unsure say Y. |
| 1229 | |
Jean-Paul Saman | c33df4e | 2007-02-10 01:44:43 -0800 | [diff] [blame] | 1230 | if BLK_DEV_INITRD |
| 1231 | |
Sam Ravnborg | dbec486 | 2005-08-10 20:44:50 +0200 | [diff] [blame] | 1232 | source "usr/Kconfig" |
| 1233 | |
Jean-Paul Saman | c33df4e | 2007-02-10 01:44:43 -0800 | [diff] [blame] | 1234 | endif |
| 1235 | |
Linus Torvalds | c45b4f1 | 2005-12-14 18:52:21 -0800 | [diff] [blame] | 1236 | config CC_OPTIMIZE_FOR_SIZE |
Ingo Molnar | 96fffeb | 2008-04-28 01:39:43 +0200 | [diff] [blame] | 1237 | bool "Optimize for size" |
Linus Torvalds | c45b4f1 | 2005-12-14 18:52:21 -0800 | [diff] [blame] | 1238 | help |
| 1239 | Enabling this option will pass "-Os" instead of "-O2" to gcc |
| 1240 | resulting in a smaller kernel. |
| 1241 | |
Kirill Smelkov | 3a55fb0 | 2012-11-02 15:41:01 +0400 | [diff] [blame] | 1242 | If unsure, say N. |
Linus Torvalds | c45b4f1 | 2005-12-14 18:52:21 -0800 | [diff] [blame] | 1243 | |
Randy Dunlap | 0847062 | 2006-09-30 23:28:13 -0700 | [diff] [blame] | 1244 | config SYSCTL |
| 1245 | bool |
| 1246 | |
Randy Dunlap | b943c46 | 2009-03-10 12:55:46 -0700 | [diff] [blame] | 1247 | config ANON_INODES |
| 1248 | bool |
| 1249 | |
Mike Frysinger | 657a520 | 2013-04-30 15:28:45 -0700 | [diff] [blame] | 1250 | config HAVE_UID16 |
| 1251 | bool |
| 1252 | |
| 1253 | config SYSCTL_EXCEPTION_TRACE |
| 1254 | bool |
| 1255 | help |
| 1256 | Enable support for /proc/sys/debug/exception-trace. |
| 1257 | |
| 1258 | config SYSCTL_ARCH_UNALIGN_NO_WARN |
| 1259 | bool |
| 1260 | help |
| 1261 | Enable support for /proc/sys/kernel/ignore-unaligned-usertrap |
| 1262 | Allows arch to define/use @no_unaligned_warning to possibly warn |
| 1263 | about unaligned access emulation going on under the hood. |
| 1264 | |
| 1265 | config SYSCTL_ARCH_UNALIGN_ALLOW |
| 1266 | bool |
| 1267 | help |
| 1268 | Enable support for /proc/sys/kernel/unaligned-trap |
| 1269 | Allows arches to define/use @unaligned_enabled to runtime toggle |
| 1270 | the unaligned access emulation. |
| 1271 | see arch/parisc/kernel/unaligned.c for reference |
| 1272 | |
Mike Frysinger | 657a520 | 2013-04-30 15:28:45 -0700 | [diff] [blame] | 1273 | config HAVE_PCSPKR_PLATFORM |
| 1274 | bool |
| 1275 | |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1276 | menuconfig EXPERT |
| 1277 | bool "Configure standard kernel features (expert users)" |
Josh Triplett | f505c55 | 2011-06-05 18:23:58 -0700 | [diff] [blame] | 1278 | # Unhide debug options, to make the on-by-default options visible |
| 1279 | select DEBUG_KERNEL |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1280 | help |
| 1281 | This option allows certain base kernel options and settings |
| 1282 | to be disabled or tweaked. This is for specialized |
| 1283 | environments which can tolerate a "non-standard" kernel. |
| 1284 | Only use this if you really know what you are doing. |
| 1285 | |
Chuck Ebbert | ae81f9e | 2006-09-16 12:15:53 -0700 | [diff] [blame] | 1286 | config UID16 |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1287 | bool "Enable 16-bit UID system calls" if EXPERT |
Catalin Marinas | af1839e | 2012-10-08 16:28:08 -0700 | [diff] [blame] | 1288 | depends on HAVE_UID16 |
Chuck Ebbert | ae81f9e | 2006-09-16 12:15:53 -0700 | [diff] [blame] | 1289 | default y |
| 1290 | help |
| 1291 | This enables the legacy 16-bit UID syscall wrappers. |
| 1292 | |
Eric W. Biederman | b89a817 | 2006-09-27 01:51:04 -0700 | [diff] [blame] | 1293 | config SYSCTL_SYSCALL |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1294 | bool "Sysctl syscall support" if EXPERT |
Eric W. Biederman | 26a7034 | 2009-11-05 05:26:41 -0800 | [diff] [blame] | 1295 | depends on PROC_SYSCTL |
WANG Cong | c736de6 | 2011-11-02 13:39:25 -0700 | [diff] [blame] | 1296 | default n |
Eric W. Biederman | b89a817 | 2006-09-27 01:51:04 -0700 | [diff] [blame] | 1297 | select SYSCTL |
| 1298 | ---help--- |
Eric W. Biederman | 13bb7e3 | 2006-11-08 17:44:51 -0800 | [diff] [blame] | 1299 | sys_sysctl uses binary paths that have been found challenging |
| 1300 | to properly maintain and use. The interface in /proc/sys |
| 1301 | using paths with ascii names is now the primary path to this |
| 1302 | information. |
Eric W. Biederman | b89a817 | 2006-09-27 01:51:04 -0700 | [diff] [blame] | 1303 | |
Eric W. Biederman | 13bb7e3 | 2006-11-08 17:44:51 -0800 | [diff] [blame] | 1304 | Almost nothing using the binary sysctl interface so if you are |
| 1305 | trying to save some space it is probably safe to disable this, |
| 1306 | making your kernel marginally smaller. |
Eric W. Biederman | b89a817 | 2006-09-27 01:51:04 -0700 | [diff] [blame] | 1307 | |
WANG Cong | c736de6 | 2011-11-02 13:39:25 -0700 | [diff] [blame] | 1308 | If unsure say N here. |
Chuck Ebbert | ae81f9e | 2006-09-16 12:15:53 -0700 | [diff] [blame] | 1309 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1310 | config KALLSYMS |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1311 | bool "Load all symbols for debugging/ksymoops" if EXPERT |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1312 | default y |
| 1313 | help |
| 1314 | Say Y here to let the kernel print out symbolic crash information and |
| 1315 | symbolic stack backtraces. This increases the size of the kernel |
| 1316 | somewhat, as all symbols have to be loaded into the kernel image. |
| 1317 | |
| 1318 | config KALLSYMS_ALL |
| 1319 | bool "Include all symbols in kallsyms" |
| 1320 | depends on DEBUG_KERNEL && KALLSYMS |
| 1321 | help |
Artem Bityutskiy | 71a83ec | 2011-04-05 13:24:57 +0300 | [diff] [blame] | 1322 | Normally kallsyms only contains the symbols of functions for nicer |
| 1323 | OOPS messages and backtraces (i.e., symbols from the text and inittext |
| 1324 | sections). This is sufficient for most cases. And only in very rare |
| 1325 | cases (e.g., when a debugger is used) all symbols are required (e.g., |
| 1326 | names of variables from the data sections, etc). |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1327 | |
Artem Bityutskiy | 71a83ec | 2011-04-05 13:24:57 +0300 | [diff] [blame] | 1328 | This option makes sure that all symbols are loaded into the kernel |
| 1329 | image (i.e., symbols from all sections) in cost of increased kernel |
| 1330 | size (depending on the kernel configuration, it may be 300KiB or |
| 1331 | something like this). |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1332 | |
Artem Bityutskiy | 71a83ec | 2011-04-05 13:24:57 +0300 | [diff] [blame] | 1333 | Say N unless you really need all symbols. |
Matt Mackall | d59745c | 2005-05-01 08:59:02 -0700 | [diff] [blame] | 1334 | |
| 1335 | config PRINTK |
| 1336 | default y |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1337 | bool "Enable support for printk" if EXPERT |
Frederic Weisbecker | 74876a9 | 2012-10-12 18:00:23 +0200 | [diff] [blame] | 1338 | select IRQ_WORK |
Matt Mackall | d59745c | 2005-05-01 08:59:02 -0700 | [diff] [blame] | 1339 | help |
| 1340 | This option enables normal printk support. Removing it |
| 1341 | eliminates most of the message strings from the kernel image |
| 1342 | and makes the kernel more or less silent. As this makes it |
| 1343 | very difficult to diagnose system problems, saying N here is |
| 1344 | strongly discouraged. |
| 1345 | |
Matt Mackall | c8538a7 | 2005-05-01 08:59:01 -0700 | [diff] [blame] | 1346 | config BUG |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1347 | bool "BUG() support" if EXPERT |
Matt Mackall | c8538a7 | 2005-05-01 08:59:01 -0700 | [diff] [blame] | 1348 | default y |
| 1349 | help |
| 1350 | Disabling this option eliminates support for BUG and WARN, reducing |
| 1351 | the size of your kernel image and potentially quietly ignoring |
| 1352 | numerous fatal conditions. You should only consider disabling this |
| 1353 | option for embedded systems with no facilities for reporting errors. |
| 1354 | Just say Y. |
| 1355 | |
Matt Mackall | 708e9a7 | 2006-01-08 01:05:25 -0800 | [diff] [blame] | 1356 | config ELF_CORE |
Alex Kelly | 046d662 | 2012-10-04 17:15:23 -0700 | [diff] [blame] | 1357 | depends on COREDUMP |
Matt Mackall | 708e9a7 | 2006-01-08 01:05:25 -0800 | [diff] [blame] | 1358 | default y |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1359 | bool "Enable ELF core dumps" if EXPERT |
Matt Mackall | 708e9a7 | 2006-01-08 01:05:25 -0800 | [diff] [blame] | 1360 | help |
| 1361 | Enable support for generating core dumps. Disabling saves about 4k. |
| 1362 | |
Ralf Baechle | 8761f1a | 2011-06-01 19:05:09 +0100 | [diff] [blame] | 1363 | |
Stas Sergeev | e5e1d3c | 2008-05-07 12:39:56 +0200 | [diff] [blame] | 1364 | config PCSPKR_PLATFORM |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1365 | bool "Enable PC-Speaker support" if EXPERT |
Ralf Baechle | 8761f1a | 2011-06-01 19:05:09 +0100 | [diff] [blame] | 1366 | depends on HAVE_PCSPKR_PLATFORM |
Ralf Baechle | 15f304b | 2011-06-01 19:04:59 +0100 | [diff] [blame] | 1367 | select I8253_LOCK |
Stas Sergeev | e5e1d3c | 2008-05-07 12:39:56 +0200 | [diff] [blame] | 1368 | default y |
| 1369 | help |
| 1370 | This option allows to disable the internal PC-Speaker |
| 1371 | support, saving some memory. |
| 1372 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1373 | config BASE_FULL |
| 1374 | default y |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1375 | bool "Enable full-sized data structures for core" if EXPERT |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1376 | help |
| 1377 | Disabling this option reduces the size of miscellaneous core |
| 1378 | kernel data structures. This saves memory on small machines, |
| 1379 | but may reduce performance. |
| 1380 | |
| 1381 | config FUTEX |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1382 | bool "Enable futex support" if EXPERT |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1383 | default y |
Ingo Molnar | 23f78d4a | 2006-06-27 02:54:53 -0700 | [diff] [blame] | 1384 | select RT_MUTEXES |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1385 | help |
| 1386 | Disabling this option will cause the kernel to be built without |
| 1387 | support for "fast userspace mutexes". The resulting kernel may not |
| 1388 | run glibc-based applications correctly. |
| 1389 | |
| 1390 | config EPOLL |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1391 | bool "Enable eventpoll support" if EXPERT |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1392 | default y |
Adrian Bunk | 448e3ce | 2007-07-31 00:39:10 -0700 | [diff] [blame] | 1393 | select ANON_INODES |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1394 | help |
| 1395 | Disabling this option will cause the kernel to be built without |
| 1396 | support for epoll family of system calls. |
| 1397 | |
Davide Libenzi | fba2afa | 2007-05-10 22:23:13 -0700 | [diff] [blame] | 1398 | config SIGNALFD |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1399 | bool "Enable signalfd() system call" if EXPERT |
Adrian Bunk | 448e3ce | 2007-07-31 00:39:10 -0700 | [diff] [blame] | 1400 | select ANON_INODES |
Davide Libenzi | fba2afa | 2007-05-10 22:23:13 -0700 | [diff] [blame] | 1401 | default y |
| 1402 | help |
| 1403 | Enable the signalfd() system call that allows to receive signals |
| 1404 | on a file descriptor. |
| 1405 | |
| 1406 | If unsure, say Y. |
| 1407 | |
Davide Libenzi | b215e28 | 2007-05-10 22:23:16 -0700 | [diff] [blame] | 1408 | config TIMERFD |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1409 | bool "Enable timerfd() system call" if EXPERT |
Adrian Bunk | 448e3ce | 2007-07-31 00:39:10 -0700 | [diff] [blame] | 1410 | select ANON_INODES |
Davide Libenzi | b215e28 | 2007-05-10 22:23:16 -0700 | [diff] [blame] | 1411 | default y |
| 1412 | help |
| 1413 | Enable the timerfd() system call that allows to receive timer |
| 1414 | events on a file descriptor. |
| 1415 | |
| 1416 | If unsure, say Y. |
| 1417 | |
Davide Libenzi | e1ad746 | 2007-05-10 22:23:19 -0700 | [diff] [blame] | 1418 | config EVENTFD |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1419 | bool "Enable eventfd() system call" if EXPERT |
Adrian Bunk | 448e3ce | 2007-07-31 00:39:10 -0700 | [diff] [blame] | 1420 | select ANON_INODES |
Davide Libenzi | e1ad746 | 2007-05-10 22:23:19 -0700 | [diff] [blame] | 1421 | default y |
| 1422 | help |
| 1423 | Enable the eventfd() system call that allows to receive both |
| 1424 | kernel notification (ie. KAIO) or userspace notifications. |
| 1425 | |
| 1426 | If unsure, say Y. |
| 1427 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1428 | config SHMEM |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1429 | bool "Use full shmem filesystem" if EXPERT |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1430 | default y |
| 1431 | depends on MMU |
| 1432 | help |
| 1433 | The shmem is an internal filesystem used to manage shared memory. |
| 1434 | It is backed by swap and manages resource limits. It is also exported |
| 1435 | to userspace as tmpfs if TMPFS is enabled. Disabling this |
| 1436 | option replaces shmem and tmpfs with the much simpler ramfs code, |
| 1437 | which may be appropriate on small systems without swap. |
| 1438 | |
Thomas Petazzoni | ebf3f09 | 2008-10-15 22:05:12 -0700 | [diff] [blame] | 1439 | config AIO |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1440 | bool "Enable AIO support" if EXPERT |
Thomas Petazzoni | ebf3f09 | 2008-10-15 22:05:12 -0700 | [diff] [blame] | 1441 | default y |
| 1442 | help |
| 1443 | This option enables POSIX asynchronous I/O which may by used |
Mike Frysinger | 657a520 | 2013-04-30 15:28:45 -0700 | [diff] [blame] | 1444 | by some high performance threaded applications. Disabling |
| 1445 | this option saves about 7k. |
| 1446 | |
| 1447 | config PCI_QUIRKS |
| 1448 | default y |
| 1449 | bool "Enable PCI quirk workarounds" if EXPERT |
| 1450 | depends on PCI |
| 1451 | help |
| 1452 | This enables workarounds for various PCI chipset |
| 1453 | bugs/quirks. Disable this only if your target machine is |
| 1454 | unaffected by PCI quirks. |
Thomas Petazzoni | ebf3f09 | 2008-10-15 22:05:12 -0700 | [diff] [blame] | 1455 | |
Randy Dunlap | 6befe5f | 2011-04-26 12:33:21 -0700 | [diff] [blame] | 1456 | config EMBEDDED |
| 1457 | bool "Embedded system" |
| 1458 | select EXPERT |
| 1459 | help |
| 1460 | This option should be enabled if compiling the kernel for |
| 1461 | an embedded system so certain expert options are available |
| 1462 | for configuration. |
| 1463 | |
Ingo Molnar | cdd6c48 | 2009-09-21 12:02:48 +0200 | [diff] [blame] | 1464 | config HAVE_PERF_EVENTS |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1465 | bool |
Mike Frysinger | 018df72 | 2009-06-12 13:17:43 -0400 | [diff] [blame] | 1466 | help |
| 1467 | See tools/perf/design.txt for details. |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1468 | |
Peter Zijlstra | 906010b | 2009-09-21 16:08:49 +0200 | [diff] [blame] | 1469 | config PERF_USE_VMALLOC |
| 1470 | bool |
| 1471 | help |
| 1472 | See tools/perf/design.txt for details |
| 1473 | |
Ingo Molnar | 57c0c15 | 2009-09-21 12:20:38 +0200 | [diff] [blame] | 1474 | menu "Kernel Performance Events And Counters" |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1475 | |
Ingo Molnar | cdd6c48 | 2009-09-21 12:02:48 +0200 | [diff] [blame] | 1476 | config PERF_EVENTS |
Ingo Molnar | 57c0c15 | 2009-09-21 12:20:38 +0200 | [diff] [blame] | 1477 | bool "Kernel performance events and counters" |
Robert Richter | 392d65a | 2012-04-05 18:24:44 +0200 | [diff] [blame] | 1478 | default y if PROFILING |
Ingo Molnar | cdd6c48 | 2009-09-21 12:02:48 +0200 | [diff] [blame] | 1479 | depends on HAVE_PERF_EVENTS |
Ingo Molnar | 4c59e46 | 2008-12-08 19:38:33 +0100 | [diff] [blame] | 1480 | select ANON_INODES |
Peter Zijlstra | e360adb | 2010-10-14 14:01:34 +0800 | [diff] [blame] | 1481 | select IRQ_WORK |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1482 | help |
Ingo Molnar | 57c0c15 | 2009-09-21 12:20:38 +0200 | [diff] [blame] | 1483 | Enable kernel support for various performance events provided |
| 1484 | by software and hardware. |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1485 | |
Thadeu Lima de Souza Cascardo | dd77038 | 2009-10-30 19:32:25 -0200 | [diff] [blame] | 1486 | Software events are supported either built-in or via the |
Ingo Molnar | 57c0c15 | 2009-09-21 12:20:38 +0200 | [diff] [blame] | 1487 | use of generic tracepoints. |
| 1488 | |
| 1489 | Most modern CPUs support performance events via performance |
| 1490 | counter registers. These registers count the number of certain |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1491 | types of hw events: such as instructions executed, cachemisses |
| 1492 | suffered, or branches mis-predicted - without slowing down the |
| 1493 | kernel or applications. These registers can also trigger interrupts |
| 1494 | when a threshold number of events have passed - and can thus be |
| 1495 | used to profile the code that runs on that CPU. |
| 1496 | |
Ingo Molnar | 57c0c15 | 2009-09-21 12:20:38 +0200 | [diff] [blame] | 1497 | The Linux Performance Event subsystem provides an abstraction of |
Thadeu Lima de Souza Cascardo | dd77038 | 2009-10-30 19:32:25 -0200 | [diff] [blame] | 1498 | these software and hardware event capabilities, available via a |
Ingo Molnar | 57c0c15 | 2009-09-21 12:20:38 +0200 | [diff] [blame] | 1499 | system call and used by the "perf" utility in tools/perf/. It |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1500 | provides per task and per CPU counters, and it provides event |
| 1501 | capabilities on top of those. |
| 1502 | |
| 1503 | Say Y if unsure. |
| 1504 | |
Peter Zijlstra | 906010b | 2009-09-21 16:08:49 +0200 | [diff] [blame] | 1505 | config DEBUG_PERF_USE_VMALLOC |
| 1506 | default n |
| 1507 | bool "Debug: use vmalloc to back perf mmap() buffers" |
| 1508 | depends on PERF_EVENTS && DEBUG_KERNEL |
| 1509 | select PERF_USE_VMALLOC |
| 1510 | help |
| 1511 | Use vmalloc memory to back perf mmap() buffers. |
| 1512 | |
| 1513 | Mostly useful for debugging the vmalloc code on platforms |
| 1514 | that don't require it. |
| 1515 | |
| 1516 | Say N if unsure. |
| 1517 | |
Thomas Gleixner | 0793a61 | 2008-12-04 20:12:29 +0100 | [diff] [blame] | 1518 | endmenu |
| 1519 | |
Christoph Lameter | f8891e5 | 2006-06-30 01:55:45 -0700 | [diff] [blame] | 1520 | config VM_EVENT_COUNTERS |
| 1521 | default y |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1522 | bool "Enable VM event counters for /proc/vmstat" if EXPERT |
Christoph Lameter | f8891e5 | 2006-06-30 01:55:45 -0700 | [diff] [blame] | 1523 | help |
Paul Jackson | 2aea4fb | 2006-12-22 01:06:10 -0800 | [diff] [blame] | 1524 | VM event counters are needed for event counts to be shown. |
| 1525 | This option allows the disabling of the VM event counters |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1526 | on EXPERT systems. /proc/vmstat will only show page counts |
Paul Jackson | 2aea4fb | 2006-12-22 01:06:10 -0800 | [diff] [blame] | 1527 | if VM event counters are disabled. |
Christoph Lameter | f8891e5 | 2006-06-30 01:55:45 -0700 | [diff] [blame] | 1528 | |
Christoph Lameter | 41ecc55 | 2007-05-09 02:32:44 -0700 | [diff] [blame] | 1529 | config SLUB_DEBUG |
| 1530 | default y |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1531 | bool "Enable SLUB debugging support" if EXPERT |
Christoph Lameter | f6acb63 | 2008-04-29 16:16:06 -0700 | [diff] [blame] | 1532 | depends on SLUB && SYSFS |
Christoph Lameter | 41ecc55 | 2007-05-09 02:32:44 -0700 | [diff] [blame] | 1533 | help |
| 1534 | SLUB has extensive debug support features. Disabling these can |
| 1535 | result in significant savings in code size. This also disables |
| 1536 | SLUB sysfs support. /sys/slab will not exist and there will be |
| 1537 | no support for cache validation etc. |
| 1538 | |
Randy Dunlap | b943c46 | 2009-03-10 12:55:46 -0700 | [diff] [blame] | 1539 | config COMPAT_BRK |
| 1540 | bool "Disable heap randomization" |
| 1541 | default y |
| 1542 | help |
| 1543 | Randomizing heap placement makes heap exploits harder, but it |
| 1544 | also breaks ancient binaries (including anything libc5 based). |
| 1545 | This option changes the bootup default to heap randomization |
Matt LaPlante | 692105b | 2009-01-26 11:12:25 +0100 | [diff] [blame] | 1546 | disabled, and can be overridden at runtime by setting |
Randy Dunlap | b943c46 | 2009-03-10 12:55:46 -0700 | [diff] [blame] | 1547 | /proc/sys/kernel/randomize_va_space to 2. |
| 1548 | |
| 1549 | On non-ancient distros (post-2000 ones) N is usually a safe choice. |
| 1550 | |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1551 | choice |
| 1552 | prompt "Choose SLAB allocator" |
Christoph Lameter | a0acd82 | 2007-07-17 04:03:32 -0700 | [diff] [blame] | 1553 | default SLUB |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1554 | help |
| 1555 | This option allows to select a slab allocator. |
| 1556 | |
| 1557 | config SLAB |
| 1558 | bool "SLAB" |
| 1559 | help |
| 1560 | The regular slab allocator that is established and known to work |
Christoph Lameter | 3401388 | 2007-05-09 02:32:47 -0700 | [diff] [blame] | 1561 | well in all environments. It organizes cache hot objects in |
Simon Arlott | 02f5621 | 2008-11-05 22:18:19 +0000 | [diff] [blame] | 1562 | per cpu and per node queues. |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1563 | |
| 1564 | config SLUB |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1565 | bool "SLUB (Unqueued Allocator)" |
| 1566 | help |
| 1567 | SLUB is a slab allocator that minimizes cache line usage |
| 1568 | instead of managing queues of cached objects (SLAB approach). |
| 1569 | Per cpu caching is realized using slabs of objects instead |
| 1570 | of queues of objects. SLUB can use memory efficiently |
Simon Arlott | 02f5621 | 2008-11-05 22:18:19 +0000 | [diff] [blame] | 1571 | and has enhanced diagnostics. SLUB is the default choice for |
| 1572 | a slab allocator. |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1573 | |
| 1574 | config SLOB |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1575 | depends on EXPERT |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1576 | bool "SLOB (Simple Allocator)" |
| 1577 | help |
Matt Mackall | 3729145 | 2008-02-04 22:29:38 -0800 | [diff] [blame] | 1578 | SLOB replaces the stock allocator with a drastically simpler |
| 1579 | allocator. SLOB is generally more space efficient but |
| 1580 | does not perform as well on large systems. |
Christoph Lameter | 81819f0 | 2007-05-06 14:49:36 -0700 | [diff] [blame] | 1581 | |
| 1582 | endchoice |
| 1583 | |
Joonsoo Kim | 345c905 | 2013-06-19 14:05:52 +0900 | [diff] [blame] | 1584 | config SLUB_CPU_PARTIAL |
| 1585 | default y |
Uwe Kleine-König | b39ffbf | 2013-07-17 16:54:59 +0200 | [diff] [blame] | 1586 | depends on SLUB && SMP |
Joonsoo Kim | 345c905 | 2013-06-19 14:05:52 +0900 | [diff] [blame] | 1587 | bool "SLUB per cpu partial cache" |
| 1588 | help |
| 1589 | Per cpu partial caches accellerate objects allocation and freeing |
| 1590 | that is local to a processor at the price of more indeterminism |
| 1591 | in the latency of the free. On overflow these caches will be cleared |
| 1592 | which requires the taking of locks that may cause latency spikes. |
| 1593 | Typically one would choose no for a realtime system. |
| 1594 | |
Jie Zhang | ea63763 | 2009-12-14 18:00:02 -0800 | [diff] [blame] | 1595 | config MMAP_ALLOW_UNINITIALIZED |
| 1596 | bool "Allow mmapped anonymous memory to be uninitialized" |
David Rientjes | 6a108a1 | 2011-01-20 14:44:16 -0800 | [diff] [blame] | 1597 | depends on EXPERT && !MMU |
Jie Zhang | ea63763 | 2009-12-14 18:00:02 -0800 | [diff] [blame] | 1598 | default n |
| 1599 | help |
| 1600 | Normally, and according to the Linux spec, anonymous memory obtained |
| 1601 | from mmap() has it's contents cleared before it is passed to |
| 1602 | userspace. Enabling this config option allows you to request that |
| 1603 | mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus |
| 1604 | providing a huge performance boost. If this option is not enabled, |
| 1605 | then the flag will be ignored. |
| 1606 | |
| 1607 | This is taken advantage of by uClibc's malloc(), and also by |
| 1608 | ELF-FDPIC binfmt's brk and stack allocator. |
| 1609 | |
| 1610 | Because of the obvious security issues, this option should only be |
| 1611 | enabled on embedded devices where you control what is run in |
| 1612 | userspace. Since that isn't generally a problem on no-MMU systems, |
| 1613 | it is normally safe to say Y here. |
| 1614 | |
| 1615 | See Documentation/nommu-mmap.txt for more information. |
| 1616 | |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 1617 | config PROFILING |
Robert Richter | b309a29 | 2010-02-26 15:01:23 +0100 | [diff] [blame] | 1618 | bool "Profiling support" |
Mathieu Desnoyers | 125e564 | 2008-02-02 15:10:36 -0500 | [diff] [blame] | 1619 | help |
| 1620 | Say Y here to enable the extended profiling support mechanisms used |
| 1621 | by profilers such as OProfile. |
| 1622 | |
Ingo Molnar | 5f87f11 | 2008-07-23 14:15:22 +0200 | [diff] [blame] | 1623 | # |
| 1624 | # Place an empty function call at each tracepoint site. Can be |
| 1625 | # dynamically changed for a probe function. |
| 1626 | # |
Mathieu Desnoyers | 97e1c18 | 2008-07-18 12:16:16 -0400 | [diff] [blame] | 1627 | config TRACEPOINTS |
Ingo Molnar | 5f87f11 | 2008-07-23 14:15:22 +0200 | [diff] [blame] | 1628 | bool |
Mathieu Desnoyers | 97e1c18 | 2008-07-18 12:16:16 -0400 | [diff] [blame] | 1629 | |
Mathieu Desnoyers | fb32e03 | 2008-02-02 15:10:33 -0500 | [diff] [blame] | 1630 | source "arch/Kconfig" |
| 1631 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1632 | endmenu # General setup |
| 1633 | |
Dmitry Baryshkov | ee7e551 | 2008-06-29 14:18:46 +0400 | [diff] [blame] | 1634 | config HAVE_GENERIC_DMA_COHERENT |
| 1635 | bool |
| 1636 | default n |
| 1637 | |
Linus Torvalds | 158a962 | 2008-01-02 13:04:48 -0800 | [diff] [blame] | 1638 | config SLABINFO |
| 1639 | bool |
| 1640 | depends on PROC_FS |
Christoph Lameter | 0f389ec | 2008-04-14 18:53:02 +0300 | [diff] [blame] | 1641 | depends on SLAB || SLUB_DEBUG |
Linus Torvalds | 158a962 | 2008-01-02 13:04:48 -0800 | [diff] [blame] | 1642 | default y |
| 1643 | |
Chuck Ebbert | ae81f9e | 2006-09-16 12:15:53 -0700 | [diff] [blame] | 1644 | config RT_MUTEXES |
| 1645 | boolean |
Chuck Ebbert | ae81f9e | 2006-09-16 12:15:53 -0700 | [diff] [blame] | 1646 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1647 | config BASE_SMALL |
| 1648 | int |
| 1649 | default 0 if BASE_FULL |
| 1650 | default 1 if !BASE_FULL |
| 1651 | |
David Howells | b56e5a1 | 2013-08-30 16:07:30 +0100 | [diff] [blame] | 1652 | config SYSTEM_TRUSTED_KEYRING |
| 1653 | bool "Provide system-wide ring of trusted keys" |
| 1654 | depends on KEYS |
| 1655 | help |
| 1656 | Provide a system keyring to which trusted keys can be added. Keys in |
| 1657 | the keyring are considered to be trusted. Keys may be added at will |
| 1658 | by the kernel from compiled-in data and from hardware key stores, but |
| 1659 | userspace may only add extra keys if those keys can be verified by |
| 1660 | keys already in the keyring. |
| 1661 | |
| 1662 | Keys in this keyring are used by module signature checking. |
| 1663 | |
Jan Engelhardt | 66da573 | 2007-07-15 23:39:29 -0700 | [diff] [blame] | 1664 | menuconfig MODULES |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1665 | bool "Enable loadable module support" |
Yann E. MORIN | 11097a0 | 2013-08-11 16:07:50 +0200 | [diff] [blame] | 1666 | option modules |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1667 | help |
| 1668 | Kernel modules are small pieces of compiled code which can |
| 1669 | be inserted in the running kernel, rather than being |
| 1670 | permanently built into the kernel. You use the "modprobe" |
| 1671 | tool to add (and sometimes remove) them. If you say Y here, |
| 1672 | many parts of the kernel can be built as modules (by |
| 1673 | answering M instead of Y where indicated): this is most |
| 1674 | useful for infrequently used options which are not required |
| 1675 | for booting. For more information, see the man pages for |
| 1676 | modprobe, lsmod, modinfo, insmod and rmmod. |
| 1677 | |
| 1678 | If you say Y here, you will need to run "make |
| 1679 | modules_install" to put the modules under /lib/modules/ |
| 1680 | where modprobe can find them (you may need to be root to do |
| 1681 | this). |
| 1682 | |
| 1683 | If unsure, say Y. |
| 1684 | |
Robert P. J. Day | 0b0de14 | 2008-08-04 13:31:32 -0400 | [diff] [blame] | 1685 | if MODULES |
| 1686 | |
Linus Torvalds | 826e450 | 2008-05-04 17:04:16 -0700 | [diff] [blame] | 1687 | config MODULE_FORCE_LOAD |
| 1688 | bool "Forced module loading" |
Linus Torvalds | 826e450 | 2008-05-04 17:04:16 -0700 | [diff] [blame] | 1689 | default n |
| 1690 | help |
Rusty Russell | 91e37a7 | 2008-05-09 16:25:28 +1000 | [diff] [blame] | 1691 | Allow loading of modules without version information (ie. modprobe |
| 1692 | --force). Forced module loading sets the 'F' (forced) taint flag and |
| 1693 | is usually a really bad idea. |
Linus Torvalds | 826e450 | 2008-05-04 17:04:16 -0700 | [diff] [blame] | 1694 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1695 | config MODULE_UNLOAD |
| 1696 | bool "Module unloading" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1697 | help |
| 1698 | Without this option you will not be able to unload any |
| 1699 | modules (note that some modules may not be unloadable |
Denys Vlasenko | f7f5b67 | 2008-07-22 19:24:26 -0500 | [diff] [blame] | 1700 | anyway), which makes your kernel smaller, faster |
| 1701 | and simpler. If unsure, say Y. |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1702 | |
| 1703 | config MODULE_FORCE_UNLOAD |
| 1704 | bool "Forced module unloading" |
Kees Cook | 19c9239 | 2012-10-02 11:19:29 -0700 | [diff] [blame] | 1705 | depends on MODULE_UNLOAD |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1706 | help |
| 1707 | This option allows you to force a module to unload, even if the |
| 1708 | kernel believes it is unsafe: the kernel will remove the module |
| 1709 | without waiting for anyone to stop using it (using the -f option to |
| 1710 | rmmod). This is mainly for kernel developers and desperate users. |
| 1711 | If unsure, say N. |
| 1712 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1713 | config MODVERSIONS |
Sam Ravnborg | 0d54164 | 2005-12-26 23:04:02 +0100 | [diff] [blame] | 1714 | bool "Module versioning support" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1715 | help |
| 1716 | Usually, you have to use modules compiled with your kernel. |
| 1717 | Saying Y here makes it sometimes possible to use modules |
| 1718 | compiled for different kernels, by adding enough information |
| 1719 | to the modules to (hopefully) spot any changes which would |
| 1720 | make them incompatible with the kernel you are running. If |
| 1721 | unsure, say N. |
| 1722 | |
| 1723 | config MODULE_SRCVERSION_ALL |
| 1724 | bool "Source checksum for all modules" |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1725 | help |
| 1726 | Modules which contain a MODULE_VERSION get an extra "srcversion" |
| 1727 | field inserted into their modinfo section, which contains a |
| 1728 | sum of the source files which made it. This helps maintainers |
| 1729 | see exactly which source was used to build a module (since |
| 1730 | others sometimes change the module source without updating |
| 1731 | the version). With this option, such a "srcversion" field |
| 1732 | will be created for all modules. If unsure, say N. |
| 1733 | |
Rusty Russell | 106a4ee | 2012-09-26 10:09:40 +0100 | [diff] [blame] | 1734 | config MODULE_SIG |
| 1735 | bool "Module signature verification" |
| 1736 | depends on MODULES |
David Howells | b56e5a1 | 2013-08-30 16:07:30 +0100 | [diff] [blame] | 1737 | select SYSTEM_TRUSTED_KEYRING |
David Howells | 48ba246 | 2012-09-26 10:11:03 +0100 | [diff] [blame] | 1738 | select KEYS |
| 1739 | select CRYPTO |
| 1740 | select ASYMMETRIC_KEY_TYPE |
| 1741 | select ASYMMETRIC_PUBLIC_KEY_SUBTYPE |
| 1742 | select PUBLIC_KEY_ALGO_RSA |
| 1743 | select ASN1 |
| 1744 | select OID_REGISTRY |
| 1745 | select X509_CERTIFICATE_PARSER |
Rusty Russell | 106a4ee | 2012-09-26 10:09:40 +0100 | [diff] [blame] | 1746 | help |
| 1747 | Check modules for valid signatures upon load: the signature |
| 1748 | is simply appended to the module. For more information see |
| 1749 | Documentation/module-signing.txt. |
| 1750 | |
David Howells | ea0b6dc | 2012-09-26 10:09:50 +0100 | [diff] [blame] | 1751 | !!!WARNING!!! If you enable this option, you MUST make sure that the |
| 1752 | module DOES NOT get stripped after being signed. This includes the |
| 1753 | debuginfo strip done by some packagers (such as rpmbuild) and |
| 1754 | inclusion into an initramfs that wants the module size reduced. |
| 1755 | |
Rusty Russell | 106a4ee | 2012-09-26 10:09:40 +0100 | [diff] [blame] | 1756 | config MODULE_SIG_FORCE |
| 1757 | bool "Require modules to be validly signed" |
| 1758 | depends on MODULE_SIG |
| 1759 | help |
| 1760 | Reject unsigned modules or signed modules for which we don't have a |
| 1761 | key. Without this, such modules will simply taint the kernel. |
David Howells | ea0b6dc | 2012-09-26 10:09:50 +0100 | [diff] [blame] | 1762 | |
Michal Marek | d9d8d7e | 2013-01-25 13:41:31 +1030 | [diff] [blame] | 1763 | config MODULE_SIG_ALL |
| 1764 | bool "Automatically sign all modules" |
| 1765 | default y |
| 1766 | depends on MODULE_SIG |
| 1767 | help |
| 1768 | Sign all modules during make modules_install. Without this option, |
| 1769 | modules must be signed manually, using the scripts/sign-file tool. |
| 1770 | |
| 1771 | comment "Do not forget to sign required modules with scripts/sign-file" |
| 1772 | depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL |
| 1773 | |
David Howells | ea0b6dc | 2012-09-26 10:09:50 +0100 | [diff] [blame] | 1774 | choice |
| 1775 | prompt "Which hash algorithm should modules be signed with?" |
| 1776 | depends on MODULE_SIG |
| 1777 | help |
| 1778 | This determines which sort of hashing algorithm will be used during |
| 1779 | signature generation. This algorithm _must_ be built into the kernel |
| 1780 | directly so that signature verification can take place. It is not |
| 1781 | possible to load a signed module containing the algorithm to check |
| 1782 | the signature on that module. |
| 1783 | |
| 1784 | config MODULE_SIG_SHA1 |
| 1785 | bool "Sign modules with SHA-1" |
| 1786 | select CRYPTO_SHA1 |
| 1787 | |
| 1788 | config MODULE_SIG_SHA224 |
| 1789 | bool "Sign modules with SHA-224" |
| 1790 | select CRYPTO_SHA256 |
| 1791 | |
| 1792 | config MODULE_SIG_SHA256 |
| 1793 | bool "Sign modules with SHA-256" |
| 1794 | select CRYPTO_SHA256 |
| 1795 | |
| 1796 | config MODULE_SIG_SHA384 |
| 1797 | bool "Sign modules with SHA-384" |
| 1798 | select CRYPTO_SHA512 |
| 1799 | |
| 1800 | config MODULE_SIG_SHA512 |
| 1801 | bool "Sign modules with SHA-512" |
| 1802 | select CRYPTO_SHA512 |
| 1803 | |
| 1804 | endchoice |
| 1805 | |
Michal Marek | 2275367 | 2013-01-25 13:41:00 +1030 | [diff] [blame] | 1806 | config MODULE_SIG_HASH |
| 1807 | string |
| 1808 | depends on MODULE_SIG |
| 1809 | default "sha1" if MODULE_SIG_SHA1 |
| 1810 | default "sha224" if MODULE_SIG_SHA224 |
| 1811 | default "sha256" if MODULE_SIG_SHA256 |
| 1812 | default "sha384" if MODULE_SIG_SHA384 |
| 1813 | default "sha512" if MODULE_SIG_SHA512 |
| 1814 | |
Robert P. J. Day | 0b0de14 | 2008-08-04 13:31:32 -0400 | [diff] [blame] | 1815 | endif # MODULES |
| 1816 | |
Rusty Russell | 98a79d6 | 2008-12-13 21:19:41 +1030 | [diff] [blame] | 1817 | config INIT_ALL_POSSIBLE |
| 1818 | bool |
| 1819 | help |
Rusty Russell | 5f054e3 | 2012-03-29 15:38:31 +1030 | [diff] [blame] | 1820 | Back when each arch used to define their own cpu_online_mask and |
| 1821 | cpu_possible_mask, some of them chose to initialize cpu_possible_mask |
Rusty Russell | 98a79d6 | 2008-12-13 21:19:41 +1030 | [diff] [blame] | 1822 | with all 1s, and others with all 0s. When they were centralised, |
| 1823 | it was better to provide this option than to break all the archs |
Matt LaPlante | 692105b | 2009-01-26 11:12:25 +0100 | [diff] [blame] | 1824 | and have several arch maintainers pursuing me down dark alleys. |
Rusty Russell | 98a79d6 | 2008-12-13 21:19:41 +1030 | [diff] [blame] | 1825 | |
Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame] | 1826 | config STOP_MACHINE |
| 1827 | bool |
| 1828 | default y |
| 1829 | depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU |
| 1830 | help |
| 1831 | Need stop_machine() primitive. |
Jens Axboe | 3a65dfe | 2005-11-04 08:43:35 +0100 | [diff] [blame] | 1832 | |
Jens Axboe | 3a65dfe | 2005-11-04 08:43:35 +0100 | [diff] [blame] | 1833 | source "block/Kconfig" |
Avi Kivity | e98c320 | 2007-10-16 23:27:31 -0700 | [diff] [blame] | 1834 | |
| 1835 | config PREEMPT_NOTIFIERS |
| 1836 | bool |
Paul E. McKenney | e260be6 | 2008-01-25 21:08:24 +0100 | [diff] [blame] | 1837 | |
Steffen Klassert | 16295be | 2010-01-06 19:47:10 +1100 | [diff] [blame] | 1838 | config PADATA |
| 1839 | depends on SMP |
| 1840 | bool |
| 1841 | |
Andi Kleen | 754b7b6 | 2012-10-04 17:11:27 -0700 | [diff] [blame] | 1842 | # Can be selected by architectures with broken toolchains |
| 1843 | # that get confused by correct const<->read_only section |
| 1844 | # mappings |
| 1845 | config BROKEN_RODATA |
| 1846 | bool |
| 1847 | |
David Howells | 4520c6a | 2012-09-21 23:31:13 +0100 | [diff] [blame] | 1848 | config ASN1 |
| 1849 | tristate |
| 1850 | help |
| 1851 | Build a simple ASN.1 grammar compiler that produces a bytecode output |
| 1852 | that can be interpreted by the ASN.1 stream decoder and used to |
| 1853 | inform it as to what tags are to be expected in a stream and what |
| 1854 | functions to call on what tags. |
| 1855 | |
Thomas Gleixner | 6beb000 | 2009-11-09 15:21:34 +0000 | [diff] [blame] | 1856 | source "kernel/Kconfig.locks" |