Commit | Line | Data |
---|---|---|
80daa560 RZ |
1 | config ARCH |
2 | string | |
3 | option env="ARCH" | |
4 | ||
5 | config KERNELVERSION | |
6 | string | |
7 | option env="KERNELVERSION" | |
8 | ||
face4374 RZ |
9 | config DEFCONFIG_LIST |
10 | string | |
b2670eac | 11 | depends on !UML |
face4374 RZ |
12 | option defconfig_list |
13 | default "/lib/modules/$UNAME_RELEASE/.config" | |
14 | default "/etc/kernel-config" | |
15 | default "/boot/config-$UNAME_RELEASE" | |
73531905 | 16 | default "$ARCH_DEFCONFIG" |
face4374 RZ |
17 | default "arch/$ARCH/defconfig" |
18 | ||
b99b87f7 PO |
19 | config CONSTRUCTORS |
20 | bool | |
21 | depends on !UML | |
22 | default y | |
23 | ||
ff0cfc66 | 24 | menu "General setup" |
1da177e4 LT |
25 | |
26 | config EXPERIMENTAL | |
27 | bool "Prompt for development and/or incomplete code/drivers" | |
28 | ---help--- | |
29 | Some of the various things that Linux supports (such as network | |
30 | drivers, file systems, network protocols, etc.) can be in a state | |
31 | of development where the functionality, stability, or the level of | |
32 | testing is not yet high enough for general use. This is usually | |
33 | known as the "alpha-test" phase among developers. If a feature is | |
34 | currently in alpha-test, then the developers usually discourage | |
35 | uninformed widespread use of this feature by the general public to | |
36 | avoid "Why doesn't this work?" type mail messages. However, active | |
37 | testing and use of these systems is welcomed. Just be aware that it | |
38 | may not meet the normal level of reliability or it may fail to work | |
39 | in some special cases. Detailed bug reports from people familiar | |
40 | with the kernel internals are usually welcomed by the developers | |
41 | (before submitting bug reports, please read the documents | |
42 | <file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>, | |
43 | <file:Documentation/BUG-HUNTING>, and | |
44 | <file:Documentation/oops-tracing.txt> in the kernel source). | |
45 | ||
46 | This option will also make obsoleted drivers available. These are | |
47 | drivers that have been replaced by something else, and/or are | |
48 | scheduled to be removed in a future kernel release. | |
49 | ||
50 | Unless you intend to help test and develop a feature or driver that | |
51 | falls into this category, or you have a situation that requires | |
52 | using these features, you should probably say N here, which will | |
53 | cause the configurator to present you with fewer choices. If | |
54 | you say Y here, you will be offered the choice of using features or | |
55 | drivers that are currently considered to be in the alpha-test phase. | |
56 | ||
1da177e4 LT |
57 | config BROKEN |
58 | bool | |
1da177e4 LT |
59 | |
60 | config BROKEN_ON_SMP | |
61 | bool | |
62 | depends on BROKEN || !SMP | |
63 | default y | |
64 | ||
65 | config LOCK_KERNEL | |
66 | bool | |
67 | depends on SMP || PREEMPT | |
68 | default y | |
69 | ||
70 | config INIT_ENV_ARG_LIMIT | |
71 | int | |
dd673bca AB |
72 | default 32 if !UML |
73 | default 128 if UML | |
1da177e4 | 74 | help |
34ad92c2 RD |
75 | Maximum of each of the number of arguments and environment |
76 | variables passed to init from the kernel command line. | |
1da177e4 | 77 | |
1da177e4 | 78 | |
84336466 RM |
79 | config CROSS_COMPILE |
80 | string "Cross-compiler tool prefix" | |
81 | help | |
82 | Same as running 'make CROSS_COMPILE=prefix-' but stored for | |
83 | default make runs in this kernel build directory. You don't | |
84 | need to set this unless you want the configured kernel build | |
85 | directory to select the cross-compiler automatically. | |
86 | ||
1da177e4 LT |
87 | config LOCALVERSION |
88 | string "Local version - append to kernel release" | |
89 | help | |
90 | Append an extra string to the end of your kernel version. | |
91 | This will show up when you type uname, for example. | |
92 | The string you set here will be appended after the contents of | |
93 | any files with a filename matching localversion* in your | |
94 | object and source tree, in that order. Your total string can | |
95 | be a maximum of 64 characters. | |
96 | ||
aaebf433 RA |
97 | config LOCALVERSION_AUTO |
98 | bool "Automatically append version information to the version string" | |
99 | default y | |
100 | help | |
101 | This will try to automatically determine if the current tree is a | |
6e5a5420 RD |
102 | release tree by looking for git tags that belong to the current |
103 | top of tree revision. | |
aaebf433 RA |
104 | |
105 | A string of the format -gxxxxxxxx will be added to the localversion | |
6e5a5420 | 106 | if a git-based tree is found. The string generated by this will be |
aaebf433 | 107 | appended after any matching localversion* files, and after the value |
6e5a5420 | 108 | set in CONFIG_LOCALVERSION. |
aaebf433 | 109 | |
6e5a5420 RD |
110 | (The actual string used here is the first eight characters produced |
111 | by running the command: | |
112 | ||
113 | $ git rev-parse --verify HEAD | |
114 | ||
115 | which is done within the script "scripts/setlocalversion".) | |
aaebf433 | 116 | |
2e9f3bdd PA |
117 | config HAVE_KERNEL_GZIP |
118 | bool | |
119 | ||
120 | config HAVE_KERNEL_BZIP2 | |
121 | bool | |
122 | ||
123 | config HAVE_KERNEL_LZMA | |
124 | bool | |
125 | ||
7dd65feb AT |
126 | config HAVE_KERNEL_LZO |
127 | bool | |
128 | ||
30d65dbf | 129 | choice |
2e9f3bdd PA |
130 | prompt "Kernel compression mode" |
131 | default KERNEL_GZIP | |
7dd65feb | 132 | depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_LZO |
2e9f3bdd | 133 | help |
30d65dbf AK |
134 | The linux kernel is a kind of self-extracting executable. |
135 | Several compression algorithms are available, which differ | |
136 | in efficiency, compression and decompression speed. | |
137 | Compression speed is only relevant when building a kernel. | |
138 | Decompression speed is relevant at each boot. | |
139 | ||
140 | If you have any problems with bzip2 or lzma compressed | |
141 | kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older | |
142 | version of this functionality (bzip2 only), for 2.4, was | |
143 | supplied by Christian Ludwig) | |
144 | ||
145 | High compression options are mostly useful for users, who | |
146 | are low on disk space (embedded systems), but for whom ram | |
147 | size matters less. | |
148 | ||
149 | If in doubt, select 'gzip' | |
150 | ||
151 | config KERNEL_GZIP | |
2e9f3bdd PA |
152 | bool "Gzip" |
153 | depends on HAVE_KERNEL_GZIP | |
154 | help | |
7dd65feb AT |
155 | The old and tried gzip compression. It provides a good balance |
156 | between compression ratio and decompression speed. | |
30d65dbf AK |
157 | |
158 | config KERNEL_BZIP2 | |
159 | bool "Bzip2" | |
2e9f3bdd | 160 | depends on HAVE_KERNEL_BZIP2 |
30d65dbf AK |
161 | help |
162 | Its compression ratio and speed is intermediate. | |
2e9f3bdd PA |
163 | Decompression speed is slowest among the three. The kernel |
164 | size is about 10% smaller with bzip2, in comparison to gzip. | |
165 | Bzip2 uses a large amount of memory. For modern kernels you | |
166 | will need at least 8MB RAM or more for booting. | |
30d65dbf AK |
167 | |
168 | config KERNEL_LZMA | |
2e9f3bdd PA |
169 | bool "LZMA" |
170 | depends on HAVE_KERNEL_LZMA | |
171 | help | |
172 | The most recent compression algorithm. | |
173 | Its ratio is best, decompression speed is between the other | |
174 | two. Compression is slowest. The kernel size is about 33% | |
175 | smaller with LZMA in comparison to gzip. | |
30d65dbf | 176 | |
7dd65feb AT |
177 | config KERNEL_LZO |
178 | bool "LZO" | |
179 | depends on HAVE_KERNEL_LZO | |
180 | help | |
181 | Its compression ratio is the poorest among the 4. The kernel | |
182 | size is about about 10% bigger than gzip; however its speed | |
183 | (both compression and decompression) is the fastest. | |
184 | ||
30d65dbf AK |
185 | endchoice |
186 | ||
1da177e4 LT |
187 | config SWAP |
188 | bool "Support for paging of anonymous memory (swap)" | |
9361401e | 189 | depends on MMU && BLOCK |
1da177e4 LT |
190 | default y |
191 | help | |
192 | This option allows you to choose whether you want to have support | |
92c3504e | 193 | for so called swap devices or swap files in your kernel that are |
1da177e4 LT |
194 | used to provide more virtual memory than the actual RAM present |
195 | in your computer. If unsure say Y. | |
196 | ||
197 | config SYSVIPC | |
198 | bool "System V IPC" | |
1da177e4 LT |
199 | ---help--- |
200 | Inter Process Communication is a suite of library functions and | |
201 | system calls which let processes (running programs) synchronize and | |
202 | exchange information. It is generally considered to be a good thing, | |
203 | and some programs won't run unless you say Y here. In particular, if | |
204 | you want to run the DOS emulator dosemu under Linux (read the | |
205 | DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>), | |
206 | you'll need to say Y here. | |
207 | ||
208 | You can find documentation about IPC with "info ipc" and also in | |
209 | section 6.4 of the Linux Programmer's Guide, available from | |
210 | <http://www.tldp.org/guides.html>. | |
211 | ||
a5494dcd EB |
212 | config SYSVIPC_SYSCTL |
213 | bool | |
214 | depends on SYSVIPC | |
215 | depends on SYSCTL | |
216 | default y | |
217 | ||
1da177e4 LT |
218 | config POSIX_MQUEUE |
219 | bool "POSIX Message Queues" | |
220 | depends on NET && EXPERIMENTAL | |
221 | ---help--- | |
222 | POSIX variant of message queues is a part of IPC. In POSIX message | |
223 | queues every message has a priority which decides about succession | |
224 | of receiving it by a process. If you want to compile and run | |
225 | programs written e.g. for Solaris with use of its POSIX message | |
b0e37650 | 226 | queues (functions mq_*) say Y here. |
1da177e4 LT |
227 | |
228 | POSIX message queues are visible as a filesystem called 'mqueue' | |
229 | and can be mounted somewhere if you want to do filesystem | |
230 | operations on message queues. | |
231 | ||
232 | If unsure, say Y. | |
233 | ||
bdc8e5f8 SH |
234 | config POSIX_MQUEUE_SYSCTL |
235 | bool | |
236 | depends on POSIX_MQUEUE | |
237 | depends on SYSCTL | |
238 | default y | |
239 | ||
1da177e4 LT |
240 | config BSD_PROCESS_ACCT |
241 | bool "BSD Process Accounting" | |
242 | help | |
243 | If you say Y here, a user level program will be able to instruct the | |
244 | kernel (via a special system call) to write process accounting | |
245 | information to a file: whenever a process exits, information about | |
246 | that process will be appended to the file by the kernel. The | |
247 | information includes things such as creation time, owning user, | |
248 | command name, memory usage, controlling terminal etc. (the complete | |
249 | list is in the struct acct in <file:include/linux/acct.h>). It is | |
250 | up to the user level program to do useful things with this | |
251 | information. This is generally a good idea, so say Y. | |
252 | ||
253 | config BSD_PROCESS_ACCT_V3 | |
254 | bool "BSD Process Accounting version 3 file format" | |
255 | depends on BSD_PROCESS_ACCT | |
256 | default n | |
257 | help | |
258 | If you say Y here, the process accounting information is written | |
259 | in a new file format that also logs the process IDs of each | |
260 | process and it's parent. Note that this file format is incompatible | |
261 | with previous v0/v1/v2 file formats, so you will need updated tools | |
262 | for processing it. A preliminary version of these tools is available | |
37a4c940 | 263 | at <http://www.gnu.org/software/acct/>. |
1da177e4 | 264 | |
c757249a SN |
265 | config TASKSTATS |
266 | bool "Export task/process statistics through netlink (EXPERIMENTAL)" | |
267 | depends on NET | |
268 | default n | |
269 | help | |
270 | Export selected statistics for tasks/processes through the | |
271 | generic netlink interface. Unlike BSD process accounting, the | |
272 | statistics are available during the lifetime of tasks/processes as | |
273 | responses to commands. Like BSD accounting, they are sent to user | |
274 | space on task exit. | |
275 | ||
276 | Say N if unsure. | |
277 | ||
ca74e92b SN |
278 | config TASK_DELAY_ACCT |
279 | bool "Enable per-task delay accounting (EXPERIMENTAL)" | |
6f44993f | 280 | depends on TASKSTATS |
ca74e92b SN |
281 | help |
282 | Collect information on time spent by a task waiting for system | |
283 | resources like cpu, synchronous block I/O completion and swapping | |
284 | in pages. Such statistics can help in setting a task's priorities | |
285 | relative to other tasks for cpu, io, rss limits etc. | |
286 | ||
287 | Say N if unsure. | |
288 | ||
18f705f4 AD |
289 | config TASK_XACCT |
290 | bool "Enable extended accounting over taskstats (EXPERIMENTAL)" | |
291 | depends on TASKSTATS | |
292 | help | |
293 | Collect extended task accounting data and send the data | |
294 | to userland for processing over the taskstats interface. | |
295 | ||
296 | Say N if unsure. | |
297 | ||
298 | config TASK_IO_ACCOUNTING | |
299 | bool "Enable per-task storage I/O accounting (EXPERIMENTAL)" | |
300 | depends on TASK_XACCT | |
301 | help | |
302 | Collect information on the number of bytes of storage I/O which this | |
303 | task has caused. | |
304 | ||
305 | Say N if unsure. | |
306 | ||
1da177e4 LT |
307 | config AUDIT |
308 | bool "Auditing support" | |
804a6a49 | 309 | depends on NET |
1da177e4 LT |
310 | help |
311 | Enable auditing infrastructure that can be used with another | |
312 | kernel subsystem, such as SELinux (which requires this for | |
313 | logging of avc messages output). Does not do system-call | |
314 | auditing without CONFIG_AUDITSYSCALL. | |
315 | ||
316 | config AUDITSYSCALL | |
317 | bool "Enable system-call auditing support" | |
022382a5 | 318 | depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH) |
1da177e4 LT |
319 | default y if SECURITY_SELINUX |
320 | help | |
321 | Enable low-overhead system-call auditing infrastructure that | |
322 | can be used independently or with another kernel subsystem, | |
67640b60 | 323 | such as SELinux. |
1da177e4 | 324 | |
939a67fc EP |
325 | config AUDIT_WATCH |
326 | def_bool y | |
327 | depends on AUDITSYSCALL | |
328 | select FSNOTIFY | |
1da177e4 | 329 | |
74c3cbe3 AV |
330 | config AUDIT_TREE |
331 | def_bool y | |
63c882a0 | 332 | depends on AUDITSYSCALL |
28a3a7eb | 333 | select FSNOTIFY |
74c3cbe3 | 334 | |
c903ff83 MT |
335 | menu "RCU Subsystem" |
336 | ||
337 | choice | |
338 | prompt "RCU Implementation" | |
31c9a24e | 339 | default TREE_RCU |
c903ff83 | 340 | |
c903ff83 MT |
341 | config TREE_RCU |
342 | bool "Tree-based hierarchical RCU" | |
687d7a96 | 343 | depends on !PREEMPT && SMP |
c903ff83 MT |
344 | help |
345 | This option selects the RCU implementation that is | |
346 | designed for very large SMP system with hundreds or | |
c17ef453 PM |
347 | thousands of CPUs. It also scales down nicely to |
348 | smaller systems. | |
c903ff83 | 349 | |
f41d911f | 350 | config TREE_PREEMPT_RCU |
a57eb940 | 351 | bool "Preemptible tree-based hierarchical RCU" |
f41d911f PM |
352 | depends on PREEMPT |
353 | help | |
354 | This option selects the RCU implementation that is | |
355 | designed for very large SMP systems with hundreds or | |
356 | thousands of CPUs, but for which real-time response | |
bbe3eae8 PM |
357 | is also required. It also scales down nicely to |
358 | smaller systems. | |
f41d911f | 359 | |
9b1d82fa PM |
360 | config TINY_RCU |
361 | bool "UP-only small-memory-footprint RCU" | |
362 | depends on !SMP | |
363 | help | |
364 | This option selects the RCU implementation that is | |
365 | designed for UP systems from which real-time response | |
366 | is not required. This option greatly reduces the | |
367 | memory footprint of RCU. | |
368 | ||
a57eb940 PM |
369 | config TINY_PREEMPT_RCU |
370 | bool "Preemptible UP-only small-memory-footprint RCU" | |
371 | depends on !SMP && PREEMPT | |
372 | help | |
373 | This option selects the RCU implementation that is designed | |
374 | for real-time UP systems. This option greatly reduces the | |
375 | memory footprint of RCU. | |
376 | ||
c903ff83 MT |
377 | endchoice |
378 | ||
a57eb940 PM |
379 | config PREEMPT_RCU |
380 | def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU ) | |
381 | help | |
382 | This option enables preemptible-RCU code that is common between | |
383 | the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. | |
384 | ||
c903ff83 MT |
385 | config RCU_TRACE |
386 | bool "Enable tracing for RCU" | |
c903ff83 MT |
387 | help |
388 | This option provides tracing in RCU which presents stats | |
389 | in debugfs for debugging RCU implementation. | |
390 | ||
391 | Say Y here if you want to enable RCU tracing | |
392 | Say N if you are unsure. | |
393 | ||
394 | config RCU_FANOUT | |
395 | int "Tree-based hierarchical RCU fanout value" | |
396 | range 2 64 if 64BIT | |
397 | range 2 32 if !64BIT | |
f41d911f | 398 | depends on TREE_RCU || TREE_PREEMPT_RCU |
c903ff83 MT |
399 | default 64 if 64BIT |
400 | default 32 if !64BIT | |
401 | help | |
402 | This option controls the fanout of hierarchical implementations | |
403 | of RCU, allowing RCU to work efficiently on machines with | |
4d87ffad PM |
404 | large numbers of CPUs. This value must be at least the fourth |
405 | root of NR_CPUS, which allows NR_CPUS to be insanely large. | |
406 | The default value of RCU_FANOUT should be used for production | |
407 | systems, but if you are stress-testing the RCU implementation | |
408 | itself, small RCU_FANOUT values allow you to test large-system | |
409 | code paths on small(er) systems. | |
c903ff83 MT |
410 | |
411 | Select a specific number if testing RCU itself. | |
412 | Take the default if unsure. | |
413 | ||
414 | config RCU_FANOUT_EXACT | |
415 | bool "Disable tree-based hierarchical RCU auto-balancing" | |
f41d911f | 416 | depends on TREE_RCU || TREE_PREEMPT_RCU |
c903ff83 MT |
417 | default n |
418 | help | |
419 | This option forces use of the exact RCU_FANOUT value specified, | |
420 | regardless of imbalances in the hierarchy. This is useful for | |
421 | testing RCU itself, and might one day be useful on systems with | |
422 | strong NUMA behavior. | |
423 | ||
424 | Without RCU_FANOUT_EXACT, the code will balance the hierarchy. | |
425 | ||
426 | Say N if unsure. | |
427 | ||
8bd93a2c PM |
428 | config RCU_FAST_NO_HZ |
429 | bool "Accelerate last non-dyntick-idle CPU's grace periods" | |
430 | depends on TREE_RCU && NO_HZ && SMP | |
431 | default n | |
432 | help | |
433 | This option causes RCU to attempt to accelerate grace periods | |
434 | in order to allow the final CPU to enter dynticks-idle state | |
435 | more quickly. On the other hand, this option increases the | |
436 | overhead of the dynticks-idle checking, particularly on systems | |
437 | with large numbers of CPUs. | |
438 | ||
439 | Say Y if energy efficiency is critically important, particularly | |
440 | if you have relatively few CPUs. | |
441 | ||
442 | Say N if you are unsure. | |
443 | ||
c903ff83 | 444 | config TREE_RCU_TRACE |
f41d911f | 445 | def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) |
c903ff83 MT |
446 | select DEBUG_FS |
447 | help | |
f41d911f PM |
448 | This option provides tracing for the TREE_RCU and |
449 | TREE_PREEMPT_RCU implementations, permitting Makefile to | |
450 | trivially select kernel/rcutree_trace.c. | |
c903ff83 | 451 | |
24278d14 PM |
452 | config RCU_BOOST |
453 | bool "Enable RCU priority boosting" | |
454 | depends on RT_MUTEXES && TINY_PREEMPT_RCU | |
455 | default n | |
456 | help | |
457 | This option boosts the priority of preempted RCU readers that | |
458 | block the current preemptible RCU grace period for too long. | |
459 | This option also prevents heavy loads from blocking RCU | |
460 | callback invocation for all flavors of RCU. | |
461 | ||
462 | Say Y here if you are working with real-time apps or heavy loads | |
463 | Say N here if you are unsure. | |
464 | ||
465 | config RCU_BOOST_PRIO | |
466 | int "Real-time priority to boost RCU readers to" | |
467 | range 1 99 | |
468 | depends on RCU_BOOST | |
469 | default 1 | |
470 | help | |
471 | This option specifies the real-time priority to which preempted | |
472 | RCU readers are to be boosted. If you are working with CPU-bound | |
473 | real-time applications, you should specify a priority higher then | |
474 | the highest-priority CPU-bound application. | |
475 | ||
476 | Specify the real-time priority, or take the default if unsure. | |
477 | ||
478 | config RCU_BOOST_DELAY | |
479 | int "Milliseconds to delay boosting after RCU grace-period start" | |
480 | range 0 3000 | |
481 | depends on RCU_BOOST | |
482 | default 500 | |
483 | help | |
484 | This option specifies the time to wait after the beginning of | |
485 | a given grace period before priority-boosting preempted RCU | |
486 | readers blocking that grace period. Note that any RCU reader | |
487 | blocking an expedited RCU grace period is boosted immediately. | |
488 | ||
489 | Accept the default if unsure. | |
490 | ||
c903ff83 MT |
491 | endmenu # "RCU Subsystem" |
492 | ||
1da177e4 | 493 | config IKCONFIG |
f2443ab6 | 494 | tristate "Kernel .config support" |
1da177e4 LT |
495 | ---help--- |
496 | This option enables the complete Linux kernel ".config" file | |
497 | contents to be saved in the kernel. It provides documentation | |
498 | of which kernel options are used in a running kernel or in an | |
499 | on-disk kernel. This information can be extracted from the kernel | |
500 | image file with the script scripts/extract-ikconfig and used as | |
501 | input to rebuild the current kernel or to build another kernel. | |
502 | It can also be extracted from a running kernel by reading | |
503 | /proc/config.gz if enabled (below). | |
504 | ||
505 | config IKCONFIG_PROC | |
506 | bool "Enable access to .config through /proc/config.gz" | |
507 | depends on IKCONFIG && PROC_FS | |
508 | ---help--- | |
509 | This option enables access to the kernel configuration file | |
510 | through /proc/config.gz. | |
511 | ||
794543a2 AJS |
512 | config LOG_BUF_SHIFT |
513 | int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" | |
514 | range 12 21 | |
f17a32e9 | 515 | default 17 |
794543a2 AJS |
516 | help |
517 | Select kernel log buffer size as a power of 2. | |
f17a32e9 AB |
518 | Examples: |
519 | 17 => 128 KB | |
520 | 16 => 64 KB | |
521 | 15 => 32 KB | |
522 | 14 => 16 KB | |
794543a2 AJS |
523 | 13 => 8 KB |
524 | 12 => 4 KB | |
525 | ||
a5574cf6 IM |
526 | # |
527 | # Architectures with an unreliable sched_clock() should select this: | |
528 | # | |
529 | config HAVE_UNSTABLE_SCHED_CLOCK | |
530 | bool | |
531 | ||
23964d2d LZ |
532 | menuconfig CGROUPS |
533 | boolean "Control Group support" | |
0dea1168 | 534 | depends on EVENTFD |
5cdc38f9 | 535 | help |
23964d2d | 536 | This option adds support for grouping sets of processes together, for |
5cdc38f9 KH |
537 | use with process control subsystems such as Cpusets, CFS, memory |
538 | controls or device isolation. | |
539 | See | |
5cdc38f9 | 540 | - Documentation/scheduler/sched-design-CFS.txt (CFS) |
45ce80fb LZ |
541 | - Documentation/cgroups/ (features for grouping, isolation |
542 | and resource control) | |
5cdc38f9 KH |
543 | |
544 | Say N if unsure. | |
545 | ||
23964d2d LZ |
546 | if CGROUPS |
547 | ||
5cdc38f9 KH |
548 | config CGROUP_DEBUG |
549 | bool "Example debug cgroup subsystem" | |
550 | depends on CGROUPS | |
551 | default n | |
552 | help | |
553 | This option enables a simple cgroup subsystem that | |
554 | exports useful debugging information about the cgroups | |
23964d2d | 555 | framework. |
5cdc38f9 | 556 | |
23964d2d | 557 | Say N if unsure. |
5cdc38f9 KH |
558 | |
559 | config CGROUP_NS | |
23964d2d LZ |
560 | bool "Namespace cgroup subsystem" |
561 | depends on CGROUPS | |
562 | help | |
563 | Provides a simple namespace cgroup subsystem to | |
564 | provide hierarchical naming of sets of namespaces, | |
565 | for instance virtual servers and checkpoint/restart | |
566 | jobs. | |
5cdc38f9 KH |
567 | |
568 | config CGROUP_FREEZER | |
23964d2d LZ |
569 | bool "Freezer cgroup subsystem" |
570 | depends on CGROUPS | |
571 | help | |
572 | Provides a way to freeze and unfreeze all tasks in a | |
5cdc38f9 KH |
573 | cgroup. |
574 | ||
575 | config CGROUP_DEVICE | |
576 | bool "Device controller for cgroups" | |
577 | depends on CGROUPS && EXPERIMENTAL | |
578 | help | |
579 | Provides a cgroup implementing whitelists for devices which | |
580 | a process in the cgroup can mknod or open. | |
581 | ||
582 | config CPUSETS | |
583 | bool "Cpuset support" | |
db7f47cf | 584 | depends on CGROUPS |
5cdc38f9 KH |
585 | help |
586 | This option will let you create and manage CPUSETs which | |
587 | allow dynamically partitioning a system into sets of CPUs and | |
588 | Memory Nodes and assigning tasks to run only within those sets. | |
589 | This is primarily useful on large SMP or NUMA systems. | |
590 | ||
591 | Say N if unsure. | |
592 | ||
23964d2d LZ |
593 | config PROC_PID_CPUSET |
594 | bool "Include legacy /proc/<pid>/cpuset file" | |
595 | depends on CPUSETS | |
596 | default y | |
597 | ||
d842de87 SV |
598 | config CGROUP_CPUACCT |
599 | bool "Simple CPU accounting cgroup subsystem" | |
600 | depends on CGROUPS | |
601 | help | |
602 | Provides a simple Resource Controller for monitoring the | |
23964d2d | 603 | total CPU consumed by the tasks in a cgroup. |
d842de87 | 604 | |
e552b661 PE |
605 | config RESOURCE_COUNTERS |
606 | bool "Resource counters" | |
607 | help | |
608 | This option enables controller independent resource accounting | |
23964d2d | 609 | infrastructure that works with cgroups. |
e552b661 PE |
610 | depends on CGROUPS |
611 | ||
00f0b825 BS |
612 | config CGROUP_MEM_RES_CTLR |
613 | bool "Memory Resource Controller for Control Groups" | |
614 | depends on CGROUPS && RESOURCE_COUNTERS | |
cf475ad2 | 615 | select MM_OWNER |
00f0b825 | 616 | help |
84ad6d70 | 617 | Provides a memory resource controller that manages both anonymous |
21acb9ca | 618 | memory and page cache. (See Documentation/cgroups/memory.txt) |
00f0b825 BS |
619 | |
620 | Note that setting this option increases fixed memory overhead | |
84ad6d70 KH |
621 | associated with each page of memory in the system. By this, |
622 | 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory | |
623 | usage tracking struct at boot. Total amount of this is printed out | |
624 | at boot. | |
00f0b825 BS |
625 | |
626 | Only enable when you're ok with these trade offs and really | |
84ad6d70 KH |
627 | sure you need the memory resource controller. Even when you enable |
628 | this, you can set "cgroup_disable=memory" at your boot option to | |
629 | disable memory resource controller and you can avoid overheads. | |
c9d5409f | 630 | (and lose benefits of memory resource controller) |
00f0b825 | 631 | |
cf475ad2 BS |
632 | This config option also selects MM_OWNER config option, which |
633 | could in turn add some fork/exit overhead. | |
634 | ||
c077719b | 635 | config CGROUP_MEM_RES_CTLR_SWAP |
65e0e811 KH |
636 | bool "Memory Resource Controller Swap Extension" |
637 | depends on CGROUP_MEM_RES_CTLR && SWAP | |
c077719b KH |
638 | help |
639 | Add swap management feature to memory resource controller. When you | |
640 | enable this, you can limit mem+swap usage per cgroup. In other words, | |
641 | when you disable this, memory resource controller has no cares to | |
642 | usage of swap...a process can exhaust all of the swap. This extension | |
643 | is useful when you want to avoid exhaustion swap but this itself | |
644 | adds more overheads and consumes memory for remembering information. | |
645 | Especially if you use 32bit system or small memory system, please | |
646 | be careful about enabling this. When memory resource controller | |
647 | is disabled by boot option, this will be automatically disabled and | |
648 | there will be no overhead from this. Even when you set this config=y, | |
649 | if boot option "noswapaccount" is set, swap will not be accounted. | |
627991a2 KH |
650 | Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page |
651 | size is 4096bytes, 512k per 1Gbytes of swap. | |
c077719b | 652 | |
7c941438 DG |
653 | menuconfig CGROUP_SCHED |
654 | bool "Group CPU scheduler" | |
655 | depends on EXPERIMENTAL && CGROUPS | |
656 | default n | |
657 | help | |
658 | This feature lets CPU scheduler recognize task groups and control CPU | |
659 | bandwidth allocation to such task groups. It uses cgroups to group | |
660 | tasks. | |
661 | ||
662 | if CGROUP_SCHED | |
663 | config FAIR_GROUP_SCHED | |
664 | bool "Group scheduling for SCHED_OTHER" | |
665 | depends on CGROUP_SCHED | |
666 | default CGROUP_SCHED | |
667 | ||
668 | config RT_GROUP_SCHED | |
669 | bool "Group scheduling for SCHED_RR/FIFO" | |
670 | depends on EXPERIMENTAL | |
671 | depends on CGROUP_SCHED | |
672 | default n | |
673 | help | |
674 | This feature lets you explicitly allocate real CPU bandwidth | |
32bd7eb5 | 675 | to task groups. If enabled, it will also make it impossible to |
7c941438 DG |
676 | schedule realtime tasks for non-root users until you allocate |
677 | realtime bandwidth for them. | |
678 | See Documentation/scheduler/sched-rt-group.txt for more information. | |
679 | ||
680 | endif #CGROUP_SCHED | |
681 | ||
afc24d49 VG |
682 | config BLK_CGROUP |
683 | tristate "Block IO controller" | |
684 | depends on CGROUPS && BLOCK | |
685 | default n | |
686 | ---help--- | |
687 | Generic block IO controller cgroup interface. This is the common | |
688 | cgroup interface which should be used by various IO controlling | |
689 | policies. | |
690 | ||
691 | Currently, CFQ IO scheduler uses it to recognize task groups and | |
692 | control disk bandwidth allocation (proportional time slice allocation) | |
693 | to such task groups. | |
694 | ||
695 | This option only enables generic Block IO controller infrastructure. | |
696 | One needs to also enable actual IO controlling logic in CFQ for it | |
697 | to take effect. (CONFIG_CFQ_GROUP_IOSCHED=y). | |
698 | ||
699 | See Documentation/cgroups/blkio-controller.txt for more information. | |
700 | ||
701 | config DEBUG_BLK_CGROUP | |
702 | bool "Enable Block IO controller debugging" | |
703 | depends on BLK_CGROUP | |
704 | default n | |
705 | ---help--- | |
706 | Enable some debugging help. Currently it exports additional stat | |
707 | files in a cgroup which can be useful for debugging. | |
708 | ||
23964d2d | 709 | endif # CGROUPS |
c077719b | 710 | |
23964d2d LZ |
711 | config MM_OWNER |
712 | bool | |
5cdc38f9 | 713 | |
88a22c98 | 714 | config SYSFS_DEPRECATED |
d47846c5 IM |
715 | bool |
716 | ||
717 | config SYSFS_DEPRECATED_V2 | |
9e9868a7 | 718 | bool "enable deprecated sysfs features to support old userspace tools" |
9148fe87 | 719 | depends on SYSFS |
f6ee649f | 720 | default n |
d47846c5 | 721 | select SYSFS_DEPRECATED |
88a22c98 | 722 | help |
fce3e804 | 723 | This option switches the layout of sysfs to the deprecated |
f6ee649f | 724 | version. Do not use it on recent distributions. |
fce3e804 KS |
725 | |
726 | The current sysfs layout features a unified device tree at | |
727 | /sys/devices/, which is able to express a hierarchy between | |
728 | class devices. If the deprecated option is set to Y, the | |
729 | unified device tree is split into a bus device tree at | |
730 | /sys/devices/ and several individual class device trees at | |
731 | /sys/class/. The class and bus devices will be connected by | |
732 | "<subsystem>:<name>" and the "device" links. The "block" | |
733 | class devices, will not show up in /sys/class/block/. Some | |
734 | subsystems will suppress the creation of some devices which | |
735 | depend on the unified device tree. | |
736 | ||
737 | This option is not a pure compatibility option that can | |
738 | be safely enabled on newer distributions. It will change the | |
739 | layout of sysfs to the non-extensible deprecated version, | |
740 | and disable some features, which can not be exported without | |
741 | confusing older userspace tools. Since 2007/2008 all major | |
742 | distributions do not enable this option, and ship no tools which | |
743 | depend on the deprecated layout or this option. | |
744 | ||
745 | If you are using a new kernel on an older distribution, or use | |
746 | older userspace tools, you might need to say Y here. Do not say Y, | |
747 | if the original kernel, that came with your distribution, has | |
748 | this option set to N. | |
88a22c98 | 749 | |
b86ff981 JA |
750 | config RELAY |
751 | bool "Kernel->user space relay support (formerly relayfs)" | |
752 | help | |
753 | This option enables support for relay interface support in | |
754 | certain file systems (such as debugfs). | |
755 | It is designed to provide an efficient mechanism for tools and | |
756 | facilities to relay large amounts of data from kernel space to | |
757 | user space. | |
758 | ||
759 | If unsure, say N. | |
760 | ||
c5289a69 PE |
761 | config NAMESPACES |
762 | bool "Namespaces support" if EMBEDDED | |
763 | default !EMBEDDED | |
764 | help | |
765 | Provides the way to make tasks work with different objects using | |
766 | the same id. For example same IPC id may refer to different objects | |
767 | or same user id or pid may refer to different tasks when used in | |
768 | different namespaces. | |
769 | ||
58bfdd6d PE |
770 | config UTS_NS |
771 | bool "UTS namespace" | |
772 | depends on NAMESPACES | |
773 | help | |
774 | In this namespace tasks see different info provided with the | |
775 | uname() system call | |
776 | ||
ae5e1b22 PE |
777 | config IPC_NS |
778 | bool "IPC namespace" | |
614b84cf | 779 | depends on NAMESPACES && (SYSVIPC || POSIX_MQUEUE) |
ae5e1b22 PE |
780 | help |
781 | In this namespace tasks work with IPC ids which correspond to | |
614b84cf | 782 | different IPC objects in different namespaces. |
ae5e1b22 | 783 | |
aee16ce7 PE |
784 | config USER_NS |
785 | bool "User namespace (EXPERIMENTAL)" | |
786 | depends on NAMESPACES && EXPERIMENTAL | |
787 | help | |
788 | This allows containers, i.e. vservers, to use user namespaces | |
789 | to provide different user info for different servers. | |
790 | If unsure, say N. | |
791 | ||
74bd59bb PE |
792 | config PID_NS |
793 | bool "PID Namespaces (EXPERIMENTAL)" | |
794 | default n | |
795 | depends on NAMESPACES && EXPERIMENTAL | |
796 | help | |
12d2b8f9 | 797 | Support process id namespaces. This allows having multiple |
692105b8 | 798 | processes with the same pid as long as they are in different |
74bd59bb PE |
799 | pid namespaces. This is a building block of containers. |
800 | ||
801 | Unless you want to work with an experimental feature | |
802 | say N here. | |
803 | ||
d6eb633f MH |
804 | config NET_NS |
805 | bool "Network namespace" | |
806 | default n | |
807 | depends on NAMESPACES && EXPERIMENTAL && NET | |
808 | help | |
809 | Allow user space to create what appear to be multiple instances | |
810 | of the network stack. | |
811 | ||
f991633d DG |
812 | config BLK_DEV_INITRD |
813 | bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" | |
814 | depends on BROKEN || !FRV | |
815 | help | |
816 | The initial RAM filesystem is a ramfs which is loaded by the | |
817 | boot loader (loadlin or lilo) and that is mounted as root | |
818 | before the normal boot procedure. It is typically used to | |
819 | load modules needed to mount the "real" root file system, | |
820 | etc. See <file:Documentation/initrd.txt> for details. | |
821 | ||
822 | If RAM disk support (BLK_DEV_RAM) is also included, this | |
823 | also enables initial RAM disk (initrd) support and adds | |
824 | 15 Kbytes (more on some other architectures) to the kernel size. | |
825 | ||
826 | If unsure say Y. | |
827 | ||
c33df4ea JPS |
828 | if BLK_DEV_INITRD |
829 | ||
dbec4866 SR |
830 | source "usr/Kconfig" |
831 | ||
c33df4ea JPS |
832 | endif |
833 | ||
c45b4f1f | 834 | config CC_OPTIMIZE_FOR_SIZE |
96fffeb4 | 835 | bool "Optimize for size" |
c45b4f1f | 836 | default y |
c45b4f1f LT |
837 | help |
838 | Enabling this option will pass "-Os" instead of "-O2" to gcc | |
839 | resulting in a smaller kernel. | |
840 | ||
775a7229 | 841 | If unsure, say Y. |
c45b4f1f | 842 | |
0847062a RD |
843 | config SYSCTL |
844 | bool | |
845 | ||
b943c460 RD |
846 | config ANON_INODES |
847 | bool | |
848 | ||
1da177e4 LT |
849 | menuconfig EMBEDDED |
850 | bool "Configure standard kernel features (for small systems)" | |
851 | help | |
852 | This option allows certain base kernel options and settings | |
853 | to be disabled or tweaked. This is for specialized | |
854 | environments which can tolerate a "non-standard" kernel. | |
855 | Only use this if you really know what you are doing. | |
856 | ||
ae81f9e3 CE |
857 | config UID16 |
858 | bool "Enable 16-bit UID system calls" if EMBEDDED | |
09337f50 | 859 | depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION) |
ae81f9e3 CE |
860 | default y |
861 | help | |
862 | This enables the legacy 16-bit UID syscall wrappers. | |
863 | ||
b89a8171 | 864 | config SYSCTL_SYSCALL |
0847062a | 865 | bool "Sysctl syscall support" if EMBEDDED |
26a7034b | 866 | depends on PROC_SYSCTL |
13bb7e37 | 867 | default y |
b89a8171 | 868 | select SYSCTL |
ae81f9e3 | 869 | ---help--- |
13bb7e37 EB |
870 | sys_sysctl uses binary paths that have been found challenging |
871 | to properly maintain and use. The interface in /proc/sys | |
872 | using paths with ascii names is now the primary path to this | |
873 | information. | |
b89a8171 | 874 | |
13bb7e37 EB |
875 | Almost nothing using the binary sysctl interface so if you are |
876 | trying to save some space it is probably safe to disable this, | |
877 | making your kernel marginally smaller. | |
b89a8171 | 878 | |
13bb7e37 | 879 | If unsure say Y here. |
ae81f9e3 | 880 | |
1da177e4 | 881 | config KALLSYMS |
979c6a1e | 882 | bool "Load all symbols for debugging/ksymoops" if EMBEDDED |
1da177e4 LT |
883 | default y |
884 | help | |
885 | Say Y here to let the kernel print out symbolic crash information and | |
886 | symbolic stack backtraces. This increases the size of the kernel | |
887 | somewhat, as all symbols have to be loaded into the kernel image. | |
888 | ||
889 | config KALLSYMS_ALL | |
890 | bool "Include all symbols in kallsyms" | |
891 | depends on DEBUG_KERNEL && KALLSYMS | |
892 | help | |
893 | Normally kallsyms only contains the symbols of functions, for nicer | |
894 | OOPS messages. Some debuggers can use kallsyms for other | |
f9f97bc0 JJ |
895 | symbols too: say Y here to include all symbols, if you need them |
896 | and you don't care about adding 300k to the size of your kernel. | |
1da177e4 LT |
897 | |
898 | Say N. | |
899 | ||
900 | config KALLSYMS_EXTRA_PASS | |
901 | bool "Do an extra kallsyms pass" | |
902 | depends on KALLSYMS | |
903 | help | |
904 | If kallsyms is not working correctly, the build will fail with | |
905 | inconsistent kallsyms data. If that occurs, log a bug report and | |
906 | turn on KALLSYMS_EXTRA_PASS which should result in a stable build. | |
907 | Always say N here unless you find a bug in kallsyms, which must be | |
908 | reported. KALLSYMS_EXTRA_PASS is only a temporary workaround while | |
909 | you wait for kallsyms to be fixed. | |
910 | ||
d59745ce | 911 | |
712f47ce GKH |
912 | config HOTPLUG |
913 | bool "Support for hot-pluggable devices" if EMBEDDED | |
914 | default y | |
915 | help | |
916 | This option is provided for the case where no hotplug or uevent | |
917 | capabilities is wanted by the kernel. You should only consider | |
918 | disabling this option for embedded systems that do not use modules, a | |
919 | dynamic /dev tree, or dynamic device discovery. Just say Y. | |
920 | ||
d59745ce MM |
921 | config PRINTK |
922 | default y | |
923 | bool "Enable support for printk" if EMBEDDED | |
924 | help | |
925 | This option enables normal printk support. Removing it | |
926 | eliminates most of the message strings from the kernel image | |
927 | and makes the kernel more or less silent. As this makes it | |
928 | very difficult to diagnose system problems, saying N here is | |
929 | strongly discouraged. | |
930 | ||
c8538a7a MM |
931 | config BUG |
932 | bool "BUG() support" if EMBEDDED | |
933 | default y | |
934 | help | |
935 | Disabling this option eliminates support for BUG and WARN, reducing | |
936 | the size of your kernel image and potentially quietly ignoring | |
937 | numerous fatal conditions. You should only consider disabling this | |
938 | option for embedded systems with no facilities for reporting errors. | |
939 | Just say Y. | |
940 | ||
708e9a79 MM |
941 | config ELF_CORE |
942 | default y | |
943 | bool "Enable ELF core dumps" if EMBEDDED | |
944 | help | |
945 | Enable support for generating core dumps. Disabling saves about 4k. | |
946 | ||
e5e1d3cb SS |
947 | config PCSPKR_PLATFORM |
948 | bool "Enable PC-Speaker support" if EMBEDDED | |
949 | depends on ALPHA || X86 || MIPS || PPC_PREP || PPC_CHRP || PPC_PSERIES | |
950 | default y | |
951 | help | |
952 | This option allows to disable the internal PC-Speaker | |
953 | support, saving some memory. | |
954 | ||
1da177e4 LT |
955 | config BASE_FULL |
956 | default y | |
957 | bool "Enable full-sized data structures for core" if EMBEDDED | |
958 | help | |
959 | Disabling this option reduces the size of miscellaneous core | |
960 | kernel data structures. This saves memory on small machines, | |
961 | but may reduce performance. | |
962 | ||
963 | config FUTEX | |
964 | bool "Enable futex support" if EMBEDDED | |
965 | default y | |
23f78d4a | 966 | select RT_MUTEXES |
1da177e4 LT |
967 | help |
968 | Disabling this option will cause the kernel to be built without | |
969 | support for "fast userspace mutexes". The resulting kernel may not | |
970 | run glibc-based applications correctly. | |
971 | ||
972 | config EPOLL | |
973 | bool "Enable eventpoll support" if EMBEDDED | |
974 | default y | |
448e3cee | 975 | select ANON_INODES |
1da177e4 LT |
976 | help |
977 | Disabling this option will cause the kernel to be built without | |
978 | support for epoll family of system calls. | |
979 | ||
fba2afaa DL |
980 | config SIGNALFD |
981 | bool "Enable signalfd() system call" if EMBEDDED | |
448e3cee | 982 | select ANON_INODES |
fba2afaa DL |
983 | default y |
984 | help | |
985 | Enable the signalfd() system call that allows to receive signals | |
986 | on a file descriptor. | |
987 | ||
988 | If unsure, say Y. | |
989 | ||
b215e283 DL |
990 | config TIMERFD |
991 | bool "Enable timerfd() system call" if EMBEDDED | |
448e3cee | 992 | select ANON_INODES |
b215e283 DL |
993 | default y |
994 | help | |
995 | Enable the timerfd() system call that allows to receive timer | |
996 | events on a file descriptor. | |
997 | ||
998 | If unsure, say Y. | |
999 | ||
e1ad7468 DL |
1000 | config EVENTFD |
1001 | bool "Enable eventfd() system call" if EMBEDDED | |
448e3cee | 1002 | select ANON_INODES |
e1ad7468 DL |
1003 | default y |
1004 | help | |
1005 | Enable the eventfd() system call that allows to receive both | |
1006 | kernel notification (ie. KAIO) or userspace notifications. | |
1007 | ||
1008 | If unsure, say Y. | |
1009 | ||
1da177e4 LT |
1010 | config SHMEM |
1011 | bool "Use full shmem filesystem" if EMBEDDED | |
1012 | default y | |
1013 | depends on MMU | |
1014 | help | |
1015 | The shmem is an internal filesystem used to manage shared memory. | |
1016 | It is backed by swap and manages resource limits. It is also exported | |
1017 | to userspace as tmpfs if TMPFS is enabled. Disabling this | |
1018 | option replaces shmem and tmpfs with the much simpler ramfs code, | |
1019 | which may be appropriate on small systems without swap. | |
1020 | ||
ebf3f09c TP |
1021 | config AIO |
1022 | bool "Enable AIO support" if EMBEDDED | |
1023 | default y | |
1024 | help | |
1025 | This option enables POSIX asynchronous I/O which may by used | |
1026 | by some high performance threaded applications. Disabling | |
1027 | this option saves about 7k. | |
1028 | ||
cdd6c482 | 1029 | config HAVE_PERF_EVENTS |
0793a61d | 1030 | bool |
018df72d MF |
1031 | help |
1032 | See tools/perf/design.txt for details. | |
0793a61d | 1033 | |
906010b2 PZ |
1034 | config PERF_USE_VMALLOC |
1035 | bool | |
1036 | help | |
1037 | See tools/perf/design.txt for details | |
1038 | ||
57c0c15b | 1039 | menu "Kernel Performance Events And Counters" |
0793a61d | 1040 | |
cdd6c482 | 1041 | config PERF_EVENTS |
57c0c15b IM |
1042 | bool "Kernel performance events and counters" |
1043 | default y if (PROFILING || PERF_COUNTERS) | |
cdd6c482 | 1044 | depends on HAVE_PERF_EVENTS |
4c59e467 | 1045 | select ANON_INODES |
0793a61d | 1046 | help |
57c0c15b IM |
1047 | Enable kernel support for various performance events provided |
1048 | by software and hardware. | |
0793a61d | 1049 | |
dd77038d | 1050 | Software events are supported either built-in or via the |
57c0c15b | 1051 | use of generic tracepoints. |
0793a61d | 1052 | |
57c0c15b IM |
1053 | Most modern CPUs support performance events via performance |
1054 | counter registers. These registers count the number of certain | |
0793a61d TG |
1055 | types of hw events: such as instructions executed, cachemisses |
1056 | suffered, or branches mis-predicted - without slowing down the | |
1057 | kernel or applications. These registers can also trigger interrupts | |
1058 | when a threshold number of events have passed - and can thus be | |
1059 | used to profile the code that runs on that CPU. | |
1060 | ||
57c0c15b | 1061 | The Linux Performance Event subsystem provides an abstraction of |
dd77038d | 1062 | these software and hardware event capabilities, available via a |
57c0c15b | 1063 | system call and used by the "perf" utility in tools/perf/. It |
0793a61d TG |
1064 | provides per task and per CPU counters, and it provides event |
1065 | capabilities on top of those. | |
1066 | ||
1067 | Say Y if unsure. | |
1068 | ||
57c0c15b IM |
1069 | config PERF_COUNTERS |
1070 | bool "Kernel performance counters (old config option)" | |
1071 | depends on HAVE_PERF_EVENTS | |
1072 | help | |
1073 | This config has been obsoleted by the PERF_EVENTS | |
1074 | config option - please see that one for details. | |
1075 | ||
1076 | It has no effect on the kernel whether you enable | |
1077 | it or not, it is a compatibility placeholder. | |
1078 | ||
1079 | Say N if unsure. | |
1080 | ||
906010b2 PZ |
1081 | config DEBUG_PERF_USE_VMALLOC |
1082 | default n | |
1083 | bool "Debug: use vmalloc to back perf mmap() buffers" | |
1084 | depends on PERF_EVENTS && DEBUG_KERNEL | |
1085 | select PERF_USE_VMALLOC | |
1086 | help | |
1087 | Use vmalloc memory to back perf mmap() buffers. | |
1088 | ||
1089 | Mostly useful for debugging the vmalloc code on platforms | |
1090 | that don't require it. | |
1091 | ||
1092 | Say N if unsure. | |
1093 | ||
0793a61d TG |
1094 | endmenu |
1095 | ||
f8891e5e CL |
1096 | config VM_EVENT_COUNTERS |
1097 | default y | |
1098 | bool "Enable VM event counters for /proc/vmstat" if EMBEDDED | |
1099 | help | |
2aea4fb6 PJ |
1100 | VM event counters are needed for event counts to be shown. |
1101 | This option allows the disabling of the VM event counters | |
1102 | on EMBEDDED systems. /proc/vmstat will only show page counts | |
1103 | if VM event counters are disabled. | |
f8891e5e | 1104 | |
3d137310 TP |
1105 | config PCI_QUIRKS |
1106 | default y | |
61cfc7e4 GU |
1107 | bool "Enable PCI quirk workarounds" if EMBEDDED |
1108 | depends on PCI | |
3d137310 TP |
1109 | help |
1110 | This enables workarounds for various PCI chipset | |
1111 | bugs/quirks. Disable this only if your target machine is | |
1112 | unaffected by PCI quirks. | |
1113 | ||
41ecc55b CL |
1114 | config SLUB_DEBUG |
1115 | default y | |
1116 | bool "Enable SLUB debugging support" if EMBEDDED | |
f6acb635 | 1117 | depends on SLUB && SYSFS |
41ecc55b CL |
1118 | help |
1119 | SLUB has extensive debug support features. Disabling these can | |
1120 | result in significant savings in code size. This also disables | |
1121 | SLUB sysfs support. /sys/slab will not exist and there will be | |
1122 | no support for cache validation etc. | |
1123 | ||
b943c460 RD |
1124 | config COMPAT_BRK |
1125 | bool "Disable heap randomization" | |
1126 | default y | |
1127 | help | |
1128 | Randomizing heap placement makes heap exploits harder, but it | |
1129 | also breaks ancient binaries (including anything libc5 based). | |
1130 | This option changes the bootup default to heap randomization | |
692105b8 | 1131 | disabled, and can be overridden at runtime by setting |
b943c460 RD |
1132 | /proc/sys/kernel/randomize_va_space to 2. |
1133 | ||
1134 | On non-ancient distros (post-2000 ones) N is usually a safe choice. | |
1135 | ||
81819f0f CL |
1136 | choice |
1137 | prompt "Choose SLAB allocator" | |
a0acd820 | 1138 | default SLUB |
81819f0f CL |
1139 | help |
1140 | This option allows to select a slab allocator. | |
1141 | ||
1142 | config SLAB | |
1143 | bool "SLAB" | |
1144 | help | |
1145 | The regular slab allocator that is established and known to work | |
34013886 | 1146 | well in all environments. It organizes cache hot objects in |
02f56210 | 1147 | per cpu and per node queues. |
81819f0f CL |
1148 | |
1149 | config SLUB | |
81819f0f CL |
1150 | bool "SLUB (Unqueued Allocator)" |
1151 | help | |
1152 | SLUB is a slab allocator that minimizes cache line usage | |
1153 | instead of managing queues of cached objects (SLAB approach). | |
1154 | Per cpu caching is realized using slabs of objects instead | |
1155 | of queues of objects. SLUB can use memory efficiently | |
02f56210 SA |
1156 | and has enhanced diagnostics. SLUB is the default choice for |
1157 | a slab allocator. | |
81819f0f CL |
1158 | |
1159 | config SLOB | |
84a01c2f | 1160 | depends on EMBEDDED |
81819f0f CL |
1161 | bool "SLOB (Simple Allocator)" |
1162 | help | |
37291458 MM |
1163 | SLOB replaces the stock allocator with a drastically simpler |
1164 | allocator. SLOB is generally more space efficient but | |
1165 | does not perform as well on large systems. | |
81819f0f CL |
1166 | |
1167 | endchoice | |
1168 | ||
ea637639 JZ |
1169 | config MMAP_ALLOW_UNINITIALIZED |
1170 | bool "Allow mmapped anonymous memory to be uninitialized" | |
1171 | depends on EMBEDDED && !MMU | |
1172 | default n | |
1173 | help | |
1174 | Normally, and according to the Linux spec, anonymous memory obtained | |
1175 | from mmap() has it's contents cleared before it is passed to | |
1176 | userspace. Enabling this config option allows you to request that | |
1177 | mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus | |
1178 | providing a huge performance boost. If this option is not enabled, | |
1179 | then the flag will be ignored. | |
1180 | ||
1181 | This is taken advantage of by uClibc's malloc(), and also by | |
1182 | ELF-FDPIC binfmt's brk and stack allocator. | |
1183 | ||
1184 | Because of the obvious security issues, this option should only be | |
1185 | enabled on embedded devices where you control what is run in | |
1186 | userspace. Since that isn't generally a problem on no-MMU systems, | |
1187 | it is normally safe to say Y here. | |
1188 | ||
1189 | See Documentation/nommu-mmap.txt for more information. | |
1190 | ||
125e5645 | 1191 | config PROFILING |
b309a294 | 1192 | bool "Profiling support" |
125e5645 MD |
1193 | help |
1194 | Say Y here to enable the extended profiling support mechanisms used | |
1195 | by profilers such as OProfile. | |
1196 | ||
5f87f112 IM |
1197 | # |
1198 | # Place an empty function call at each tracepoint site. Can be | |
1199 | # dynamically changed for a probe function. | |
1200 | # | |
97e1c18e | 1201 | config TRACEPOINTS |
5f87f112 | 1202 | bool |
97e1c18e | 1203 | |
fb32e03f MD |
1204 | source "arch/Kconfig" |
1205 | ||
1da177e4 LT |
1206 | endmenu # General setup |
1207 | ||
ee7e5516 DB |
1208 | config HAVE_GENERIC_DMA_COHERENT |
1209 | bool | |
1210 | default n | |
1211 | ||
158a9624 LT |
1212 | config SLABINFO |
1213 | bool | |
1214 | depends on PROC_FS | |
0f389ec6 | 1215 | depends on SLAB || SLUB_DEBUG |
158a9624 LT |
1216 | default y |
1217 | ||
ae81f9e3 CE |
1218 | config RT_MUTEXES |
1219 | boolean | |
ae81f9e3 | 1220 | |
1da177e4 LT |
1221 | config BASE_SMALL |
1222 | int | |
1223 | default 0 if BASE_FULL | |
1224 | default 1 if !BASE_FULL | |
1225 | ||
66da5733 | 1226 | menuconfig MODULES |
1da177e4 LT |
1227 | bool "Enable loadable module support" |
1228 | help | |
1229 | Kernel modules are small pieces of compiled code which can | |
1230 | be inserted in the running kernel, rather than being | |
1231 | permanently built into the kernel. You use the "modprobe" | |
1232 | tool to add (and sometimes remove) them. If you say Y here, | |
1233 | many parts of the kernel can be built as modules (by | |
1234 | answering M instead of Y where indicated): this is most | |
1235 | useful for infrequently used options which are not required | |
1236 | for booting. For more information, see the man pages for | |
1237 | modprobe, lsmod, modinfo, insmod and rmmod. | |
1238 | ||
1239 | If you say Y here, you will need to run "make | |
1240 | modules_install" to put the modules under /lib/modules/ | |
1241 | where modprobe can find them (you may need to be root to do | |
1242 | this). | |
1243 | ||
1244 | If unsure, say Y. | |
1245 | ||
0b0de144 RD |
1246 | if MODULES |
1247 | ||
826e4506 LT |
1248 | config MODULE_FORCE_LOAD |
1249 | bool "Forced module loading" | |
826e4506 LT |
1250 | default n |
1251 | help | |
91e37a79 RR |
1252 | Allow loading of modules without version information (ie. modprobe |
1253 | --force). Forced module loading sets the 'F' (forced) taint flag and | |
1254 | is usually a really bad idea. | |
826e4506 | 1255 | |
1da177e4 LT |
1256 | config MODULE_UNLOAD |
1257 | bool "Module unloading" | |
1da177e4 LT |
1258 | help |
1259 | Without this option you will not be able to unload any | |
1260 | modules (note that some modules may not be unloadable | |
f7f5b675 DV |
1261 | anyway), which makes your kernel smaller, faster |
1262 | and simpler. If unsure, say Y. | |
1da177e4 LT |
1263 | |
1264 | config MODULE_FORCE_UNLOAD | |
1265 | bool "Forced module unloading" | |
1266 | depends on MODULE_UNLOAD && EXPERIMENTAL | |
1267 | help | |
1268 | This option allows you to force a module to unload, even if the | |
1269 | kernel believes it is unsafe: the kernel will remove the module | |
1270 | without waiting for anyone to stop using it (using the -f option to | |
1271 | rmmod). This is mainly for kernel developers and desperate users. | |
1272 | If unsure, say N. | |
1273 | ||
1da177e4 | 1274 | config MODVERSIONS |
0d541643 | 1275 | bool "Module versioning support" |
1da177e4 LT |
1276 | help |
1277 | Usually, you have to use modules compiled with your kernel. | |
1278 | Saying Y here makes it sometimes possible to use modules | |
1279 | compiled for different kernels, by adding enough information | |
1280 | to the modules to (hopefully) spot any changes which would | |
1281 | make them incompatible with the kernel you are running. If | |
1282 | unsure, say N. | |
1283 | ||
1284 | config MODULE_SRCVERSION_ALL | |
1285 | bool "Source checksum for all modules" | |
1da177e4 LT |
1286 | help |
1287 | Modules which contain a MODULE_VERSION get an extra "srcversion" | |
1288 | field inserted into their modinfo section, which contains a | |
1289 | sum of the source files which made it. This helps maintainers | |
1290 | see exactly which source was used to build a module (since | |
1291 | others sometimes change the module source without updating | |
1292 | the version). With this option, such a "srcversion" field | |
1293 | will be created for all modules. If unsure, say N. | |
1294 | ||
0b0de144 RD |
1295 | endif # MODULES |
1296 | ||
98a79d6a RR |
1297 | config INIT_ALL_POSSIBLE |
1298 | bool | |
1299 | help | |
1300 | Back when each arch used to define their own cpu_online_map and | |
1301 | cpu_possible_map, some of them chose to initialize cpu_possible_map | |
1302 | with all 1s, and others with all 0s. When they were centralised, | |
1303 | it was better to provide this option than to break all the archs | |
692105b8 | 1304 | and have several arch maintainers pursuing me down dark alleys. |
98a79d6a | 1305 | |
1da177e4 LT |
1306 | config STOP_MACHINE |
1307 | bool | |
1308 | default y | |
1309 | depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU | |
1310 | help | |
1311 | Need stop_machine() primitive. | |
3a65dfe8 | 1312 | |
3a65dfe8 | 1313 | source "block/Kconfig" |
e98c3202 AK |
1314 | |
1315 | config PREEMPT_NOTIFIERS | |
1316 | bool | |
e260be67 | 1317 | |
16295bec SK |
1318 | config PADATA |
1319 | depends on SMP | |
1320 | bool | |
1321 | ||
6beb0009 | 1322 | source "kernel/Kconfig.locks" |