7 option env="KERNELVERSION"
13 default "/lib/modules/$UNAME_RELEASE/.config"
14 default "/etc/kernel-config"
15 default "/boot/config-$UNAME_RELEASE"
16 default "$ARCH_DEFCONFIG"
17 default "arch/$ARCH/defconfig"
27 bool "Prompt for development and/or incomplete code/drivers"
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).
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47 drivers that have been replaced by something else, and/or are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.
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.
62 depends on BROKEN || !SMP
67 depends on SMP || PREEMPT
70 config INIT_ENV_ARG_LIMIT
75 Maximum of each of the number of arguments and environment
76 variables passed to init from the kernel command line.
80 string "Local version - append to kernel release"
82 Append an extra string to the end of your kernel version.
83 This will show up when you type uname, for example.
84 The string you set here will be appended after the contents of
85 any files with a filename matching localversion* in your
86 object and source tree, in that order. Your total string can
87 be a maximum of 64 characters.
89 config LOCALVERSION_AUTO
90 bool "Automatically append version information to the version string"
93 This will try to automatically determine if the current tree is a
94 release tree by looking for git tags that belong to the current
97 A string of the format -gxxxxxxxx will be added to the localversion
98 if a git-based tree is found. The string generated by this will be
99 appended after any matching localversion* files, and after the value
100 set in CONFIG_LOCALVERSION.
102 (The actual string used here is the first eight characters produced
103 by running the command:
105 $ git rev-parse --verify HEAD
107 which is done within the script "scripts/setlocalversion".)
109 config HAVE_KERNEL_GZIP
112 config HAVE_KERNEL_BZIP2
115 config HAVE_KERNEL_LZMA
119 prompt "Kernel compression mode"
121 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA
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.
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)
134 High compression options are mostly useful for users, who
135 are low on disk space (embedded systems), but for whom ram
138 If in doubt, select 'gzip'
142 depends on HAVE_KERNEL_GZIP
144 The old and tried gzip compression. Its compression ratio is
145 the poorest among the 3 choices; however its speed (both
146 compression and decompression) is the fastest.
150 depends on HAVE_KERNEL_BZIP2
152 Its compression ratio and speed is intermediate.
153 Decompression speed is slowest among the three. The kernel
154 size is about 10% smaller with bzip2, in comparison to gzip.
155 Bzip2 uses a large amount of memory. For modern kernels you
156 will need at least 8MB RAM or more for booting.
160 depends on HAVE_KERNEL_LZMA
162 The most recent compression algorithm.
163 Its ratio is best, decompression speed is between the other
164 two. Compression is slowest. The kernel size is about 33%
165 smaller with LZMA in comparison to gzip.
170 bool "Support for paging of anonymous memory (swap)"
171 depends on MMU && BLOCK
174 This option allows you to choose whether you want to have support
175 for so called swap devices or swap files in your kernel that are
176 used to provide more virtual memory than the actual RAM present
177 in your computer. If unsure say Y.
182 Inter Process Communication is a suite of library functions and
183 system calls which let processes (running programs) synchronize and
184 exchange information. It is generally considered to be a good thing,
185 and some programs won't run unless you say Y here. In particular, if
186 you want to run the DOS emulator dosemu under Linux (read the
187 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
188 you'll need to say Y here.
190 You can find documentation about IPC with "info ipc" and also in
191 section 6.4 of the Linux Programmer's Guide, available from
192 <http://www.tldp.org/guides.html>.
194 config SYSVIPC_SYSCTL
201 bool "POSIX Message Queues"
202 depends on NET && EXPERIMENTAL
204 POSIX variant of message queues is a part of IPC. In POSIX message
205 queues every message has a priority which decides about succession
206 of receiving it by a process. If you want to compile and run
207 programs written e.g. for Solaris with use of its POSIX message
208 queues (functions mq_*) say Y here.
210 POSIX message queues are visible as a filesystem called 'mqueue'
211 and can be mounted somewhere if you want to do filesystem
212 operations on message queues.
216 config POSIX_MQUEUE_SYSCTL
218 depends on POSIX_MQUEUE
222 config BSD_PROCESS_ACCT
223 bool "BSD Process Accounting"
225 If you say Y here, a user level program will be able to instruct the
226 kernel (via a special system call) to write process accounting
227 information to a file: whenever a process exits, information about
228 that process will be appended to the file by the kernel. The
229 information includes things such as creation time, owning user,
230 command name, memory usage, controlling terminal etc. (the complete
231 list is in the struct acct in <file:include/linux/acct.h>). It is
232 up to the user level program to do useful things with this
233 information. This is generally a good idea, so say Y.
235 config BSD_PROCESS_ACCT_V3
236 bool "BSD Process Accounting version 3 file format"
237 depends on BSD_PROCESS_ACCT
240 If you say Y here, the process accounting information is written
241 in a new file format that also logs the process IDs of each
242 process and it's parent. Note that this file format is incompatible
243 with previous v0/v1/v2 file formats, so you will need updated tools
244 for processing it. A preliminary version of these tools is available
245 at <http://www.gnu.org/software/acct/>.
248 bool "Export task/process statistics through netlink (EXPERIMENTAL)"
252 Export selected statistics for tasks/processes through the
253 generic netlink interface. Unlike BSD process accounting, the
254 statistics are available during the lifetime of tasks/processes as
255 responses to commands. Like BSD accounting, they are sent to user
260 config TASK_DELAY_ACCT
261 bool "Enable per-task delay accounting (EXPERIMENTAL)"
264 Collect information on time spent by a task waiting for system
265 resources like cpu, synchronous block I/O completion and swapping
266 in pages. Such statistics can help in setting a task's priorities
267 relative to other tasks for cpu, io, rss limits etc.
272 bool "Enable extended accounting over taskstats (EXPERIMENTAL)"
275 Collect extended task accounting data and send the data
276 to userland for processing over the taskstats interface.
280 config TASK_IO_ACCOUNTING
281 bool "Enable per-task storage I/O accounting (EXPERIMENTAL)"
282 depends on TASK_XACCT
284 Collect information on the number of bytes of storage I/O which this
290 bool "Auditing support"
293 Enable auditing infrastructure that can be used with another
294 kernel subsystem, such as SELinux (which requires this for
295 logging of avc messages output). Does not do system-call
296 auditing without CONFIG_AUDITSYSCALL.
299 bool "Enable system-call auditing support"
300 depends on AUDIT && (X86 || PPC || PPC64 || S390 || IA64 || UML || SPARC64|| SUPERH)
301 default y if SECURITY_SELINUX
303 Enable low-overhead system-call auditing infrastructure that
304 can be used independently or with another kernel subsystem,
305 such as SELinux. To use audit's filesystem watch feature, please
306 ensure that INOTIFY is configured.
310 depends on AUDITSYSCALL
316 prompt "RCU Implementation"
320 bool "Tree-based hierarchical RCU"
322 This option selects the RCU implementation that is
323 designed for very large SMP system with hundreds or
324 thousands of CPUs. It also scales down nicely to
327 config TREE_PREEMPT_RCU
328 bool "Preemptable tree-based hierarchical RCU"
331 This option selects the RCU implementation that is
332 designed for very large SMP systems with hundreds or
333 thousands of CPUs, but for which real-time response
339 bool "Enable tracing for RCU"
340 depends on TREE_RCU || TREE_PREEMPT_RCU
342 This option provides tracing in RCU which presents stats
343 in debugfs for debugging RCU implementation.
345 Say Y here if you want to enable RCU tracing
346 Say N if you are unsure.
349 int "Tree-based hierarchical RCU fanout value"
352 depends on TREE_RCU || TREE_PREEMPT_RCU
356 This option controls the fanout of hierarchical implementations
357 of RCU, allowing RCU to work efficiently on machines with
358 large numbers of CPUs. This value must be at least the cube
359 root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
360 systems and up to 262,144 for 64-bit systems.
362 Select a specific number if testing RCU itself.
363 Take the default if unsure.
365 config RCU_FANOUT_EXACT
366 bool "Disable tree-based hierarchical RCU auto-balancing"
367 depends on TREE_RCU || TREE_PREEMPT_RCU
370 This option forces use of the exact RCU_FANOUT value specified,
371 regardless of imbalances in the hierarchy. This is useful for
372 testing RCU itself, and might one day be useful on systems with
373 strong NUMA behavior.
375 Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
379 config TREE_RCU_TRACE
380 def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
383 This option provides tracing for the TREE_RCU and
384 TREE_PREEMPT_RCU implementations, permitting Makefile to
385 trivially select kernel/rcutree_trace.c.
387 endmenu # "RCU Subsystem"
390 tristate "Kernel .config support"
392 This option enables the complete Linux kernel ".config" file
393 contents to be saved in the kernel. It provides documentation
394 of which kernel options are used in a running kernel or in an
395 on-disk kernel. This information can be extracted from the kernel
396 image file with the script scripts/extract-ikconfig and used as
397 input to rebuild the current kernel or to build another kernel.
398 It can also be extracted from a running kernel by reading
399 /proc/config.gz if enabled (below).
402 bool "Enable access to .config through /proc/config.gz"
403 depends on IKCONFIG && PROC_FS
405 This option enables access to the kernel configuration file
406 through /proc/config.gz.
409 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
413 Select kernel log buffer size as a power of 2.
423 # Architectures with an unreliable sched_clock() should select this:
425 config HAVE_UNSTABLE_SCHED_CLOCK
429 bool "Group CPU scheduler"
430 depends on EXPERIMENTAL
433 This feature lets CPU scheduler recognize task groups and control CPU
434 bandwidth allocation to such task groups.
435 In order to create a group from arbitrary set of processes, use
436 CONFIG_CGROUPS. (See Control Group support.)
438 config FAIR_GROUP_SCHED
439 bool "Group scheduling for SCHED_OTHER"
440 depends on GROUP_SCHED
443 config RT_GROUP_SCHED
444 bool "Group scheduling for SCHED_RR/FIFO"
445 depends on EXPERIMENTAL
446 depends on GROUP_SCHED
449 This feature lets you explicitly allocate real CPU bandwidth
450 to users or control groups (depending on the "Basis for grouping tasks"
451 setting below. If enabled, it will also make it impossible to
452 schedule realtime tasks for non-root users until you allocate
453 realtime bandwidth for them.
454 See Documentation/scheduler/sched-rt-group.txt for more information.
457 depends on GROUP_SCHED
458 prompt "Basis for grouping tasks"
464 This option will choose userid as the basis for grouping
465 tasks, thus providing equal CPU bandwidth to each user.
468 bool "Control groups"
471 This option allows you to create arbitrary task groups
472 using the "cgroup" pseudo filesystem and control
473 the cpu bandwidth allocated to each such task group.
474 Refer to Documentation/cgroups/cgroups.txt for more
475 information on "cgroup" pseudo filesystem.
480 boolean "Control Group support"
482 This option adds support for grouping sets of processes together, for
483 use with process control subsystems such as Cpusets, CFS, memory
484 controls or device isolation.
486 - Documentation/scheduler/sched-design-CFS.txt (CFS)
487 - Documentation/cgroups/ (features for grouping, isolation
488 and resource control)
495 bool "Example debug cgroup subsystem"
499 This option enables a simple cgroup subsystem that
500 exports useful debugging information about the cgroups
506 bool "Namespace cgroup subsystem"
509 Provides a simple namespace cgroup subsystem to
510 provide hierarchical naming of sets of namespaces,
511 for instance virtual servers and checkpoint/restart
514 config CGROUP_FREEZER
515 bool "Freezer cgroup subsystem"
518 Provides a way to freeze and unfreeze all tasks in a
522 bool "Device controller for cgroups"
523 depends on CGROUPS && EXPERIMENTAL
525 Provides a cgroup implementing whitelists for devices which
526 a process in the cgroup can mknod or open.
529 bool "Cpuset support"
532 This option will let you create and manage CPUSETs which
533 allow dynamically partitioning a system into sets of CPUs and
534 Memory Nodes and assigning tasks to run only within those sets.
535 This is primarily useful on large SMP or NUMA systems.
539 config PROC_PID_CPUSET
540 bool "Include legacy /proc/<pid>/cpuset file"
544 config CGROUP_CPUACCT
545 bool "Simple CPU accounting cgroup subsystem"
548 Provides a simple Resource Controller for monitoring the
549 total CPU consumed by the tasks in a cgroup.
551 config RESOURCE_COUNTERS
552 bool "Resource counters"
554 This option enables controller independent resource accounting
555 infrastructure that works with cgroups.
558 config CGROUP_MEM_RES_CTLR
559 bool "Memory Resource Controller for Control Groups"
560 depends on CGROUPS && RESOURCE_COUNTERS
563 Provides a memory resource controller that manages both anonymous
564 memory and page cache. (See Documentation/cgroups/memory.txt)
566 Note that setting this option increases fixed memory overhead
567 associated with each page of memory in the system. By this,
568 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
569 usage tracking struct at boot. Total amount of this is printed out
572 Only enable when you're ok with these trade offs and really
573 sure you need the memory resource controller. Even when you enable
574 this, you can set "cgroup_disable=memory" at your boot option to
575 disable memory resource controller and you can avoid overheads.
576 (and lose benefits of memory resource controller)
578 This config option also selects MM_OWNER config option, which
579 could in turn add some fork/exit overhead.
581 config CGROUP_MEM_RES_CTLR_SWAP
582 bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)"
583 depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL
585 Add swap management feature to memory resource controller. When you
586 enable this, you can limit mem+swap usage per cgroup. In other words,
587 when you disable this, memory resource controller has no cares to
588 usage of swap...a process can exhaust all of the swap. This extension
589 is useful when you want to avoid exhaustion swap but this itself
590 adds more overheads and consumes memory for remembering information.
591 Especially if you use 32bit system or small memory system, please
592 be careful about enabling this. When memory resource controller
593 is disabled by boot option, this will be automatically disabled and
594 there will be no overhead from this. Even when you set this config=y,
595 if boot option "noswapaccount" is set, swap will not be accounted.
596 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
597 size is 4096bytes, 512k per 1Gbytes of swap.
604 config SYSFS_DEPRECATED
607 config SYSFS_DEPRECATED_V2
608 bool "remove sysfs features which may confuse old userspace tools"
611 select SYSFS_DEPRECATED
613 This option switches the layout of sysfs to the deprecated
614 version. Do not use it on recent distributions.
616 The current sysfs layout features a unified device tree at
617 /sys/devices/, which is able to express a hierarchy between
618 class devices. If the deprecated option is set to Y, the
619 unified device tree is split into a bus device tree at
620 /sys/devices/ and several individual class device trees at
621 /sys/class/. The class and bus devices will be connected by
622 "<subsystem>:<name>" and the "device" links. The "block"
623 class devices, will not show up in /sys/class/block/. Some
624 subsystems will suppress the creation of some devices which
625 depend on the unified device tree.
627 This option is not a pure compatibility option that can
628 be safely enabled on newer distributions. It will change the
629 layout of sysfs to the non-extensible deprecated version,
630 and disable some features, which can not be exported without
631 confusing older userspace tools. Since 2007/2008 all major
632 distributions do not enable this option, and ship no tools which
633 depend on the deprecated layout or this option.
635 If you are using a new kernel on an older distribution, or use
636 older userspace tools, you might need to say Y here. Do not say Y,
637 if the original kernel, that came with your distribution, has
638 this option set to N.
641 bool "Kernel->user space relay support (formerly relayfs)"
643 This option enables support for relay interface support in
644 certain file systems (such as debugfs).
645 It is designed to provide an efficient mechanism for tools and
646 facilities to relay large amounts of data from kernel space to
652 bool "Namespaces support" if EMBEDDED
655 Provides the way to make tasks work with different objects using
656 the same id. For example same IPC id may refer to different objects
657 or same user id or pid may refer to different tasks when used in
658 different namespaces.
662 depends on NAMESPACES
664 In this namespace tasks see different info provided with the
669 depends on NAMESPACES && (SYSVIPC || POSIX_MQUEUE)
671 In this namespace tasks work with IPC ids which correspond to
672 different IPC objects in different namespaces.
675 bool "User namespace (EXPERIMENTAL)"
676 depends on NAMESPACES && EXPERIMENTAL
678 This allows containers, i.e. vservers, to use user namespaces
679 to provide different user info for different servers.
683 bool "PID Namespaces (EXPERIMENTAL)"
685 depends on NAMESPACES && EXPERIMENTAL
687 Support process id namespaces. This allows having multiple
688 processes with the same pid as long as they are in different
689 pid namespaces. This is a building block of containers.
691 Unless you want to work with an experimental feature
695 bool "Network namespace"
697 depends on NAMESPACES && EXPERIMENTAL && NET
699 Allow user space to create what appear to be multiple instances
700 of the network stack.
702 config BLK_DEV_INITRD
703 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
704 depends on BROKEN || !FRV
706 The initial RAM filesystem is a ramfs which is loaded by the
707 boot loader (loadlin or lilo) and that is mounted as root
708 before the normal boot procedure. It is typically used to
709 load modules needed to mount the "real" root file system,
710 etc. See <file:Documentation/initrd.txt> for details.
712 If RAM disk support (BLK_DEV_RAM) is also included, this
713 also enables initial RAM disk (initrd) support and adds
714 15 Kbytes (more on some other architectures) to the kernel size.
724 config CC_OPTIMIZE_FOR_SIZE
725 bool "Optimize for size"
728 Enabling this option will pass "-Os" instead of "-O2" to gcc
729 resulting in a smaller kernel.
740 bool "Configure standard kernel features (for small systems)"
742 This option allows certain base kernel options and settings
743 to be disabled or tweaked. This is for specialized
744 environments which can tolerate a "non-standard" kernel.
745 Only use this if you really know what you are doing.
748 bool "Enable 16-bit UID system calls" if EMBEDDED
749 depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION)
752 This enables the legacy 16-bit UID syscall wrappers.
754 config SYSCTL_SYSCALL
755 bool "Sysctl syscall support" if EMBEDDED
759 sys_sysctl uses binary paths that have been found challenging
760 to properly maintain and use. The interface in /proc/sys
761 using paths with ascii names is now the primary path to this
764 Almost nothing using the binary sysctl interface so if you are
765 trying to save some space it is probably safe to disable this,
766 making your kernel marginally smaller.
768 If unsure say Y here.
771 bool "Load all symbols for debugging/ksymoops" if EMBEDDED
774 Say Y here to let the kernel print out symbolic crash information and
775 symbolic stack backtraces. This increases the size of the kernel
776 somewhat, as all symbols have to be loaded into the kernel image.
779 bool "Include all symbols in kallsyms"
780 depends on DEBUG_KERNEL && KALLSYMS
782 Normally kallsyms only contains the symbols of functions, for nicer
783 OOPS messages. Some debuggers can use kallsyms for other
784 symbols too: say Y here to include all symbols, if you need them
785 and you don't care about adding 300k to the size of your kernel.
789 config KALLSYMS_EXTRA_PASS
790 bool "Do an extra kallsyms pass"
793 If kallsyms is not working correctly, the build will fail with
794 inconsistent kallsyms data. If that occurs, log a bug report and
795 turn on KALLSYMS_EXTRA_PASS which should result in a stable build.
796 Always say N here unless you find a bug in kallsyms, which must be
797 reported. KALLSYMS_EXTRA_PASS is only a temporary workaround while
798 you wait for kallsyms to be fixed.
802 bool "Support for hot-pluggable devices" if EMBEDDED
805 This option is provided for the case where no hotplug or uevent
806 capabilities is wanted by the kernel. You should only consider
807 disabling this option for embedded systems that do not use modules, a
808 dynamic /dev tree, or dynamic device discovery. Just say Y.
812 bool "Enable support for printk" if EMBEDDED
814 This option enables normal printk support. Removing it
815 eliminates most of the message strings from the kernel image
816 and makes the kernel more or less silent. As this makes it
817 very difficult to diagnose system problems, saying N here is
818 strongly discouraged.
821 bool "BUG() support" if EMBEDDED
824 Disabling this option eliminates support for BUG and WARN, reducing
825 the size of your kernel image and potentially quietly ignoring
826 numerous fatal conditions. You should only consider disabling this
827 option for embedded systems with no facilities for reporting errors.
832 bool "Enable ELF core dumps" if EMBEDDED
834 Enable support for generating core dumps. Disabling saves about 4k.
836 config PCSPKR_PLATFORM
837 bool "Enable PC-Speaker support" if EMBEDDED
838 depends on ALPHA || X86 || MIPS || PPC_PREP || PPC_CHRP || PPC_PSERIES
841 This option allows to disable the internal PC-Speaker
842 support, saving some memory.
846 bool "Enable full-sized data structures for core" if EMBEDDED
848 Disabling this option reduces the size of miscellaneous core
849 kernel data structures. This saves memory on small machines,
850 but may reduce performance.
853 bool "Enable futex support" if EMBEDDED
857 Disabling this option will cause the kernel to be built without
858 support for "fast userspace mutexes". The resulting kernel may not
859 run glibc-based applications correctly.
862 bool "Enable eventpoll support" if EMBEDDED
866 Disabling this option will cause the kernel to be built without
867 support for epoll family of system calls.
870 bool "Enable signalfd() system call" if EMBEDDED
874 Enable the signalfd() system call that allows to receive signals
875 on a file descriptor.
880 bool "Enable timerfd() system call" if EMBEDDED
884 Enable the timerfd() system call that allows to receive timer
885 events on a file descriptor.
890 bool "Enable eventfd() system call" if EMBEDDED
894 Enable the eventfd() system call that allows to receive both
895 kernel notification (ie. KAIO) or userspace notifications.
900 bool "Use full shmem filesystem" if EMBEDDED
904 The shmem is an internal filesystem used to manage shared memory.
905 It is backed by swap and manages resource limits. It is also exported
906 to userspace as tmpfs if TMPFS is enabled. Disabling this
907 option replaces shmem and tmpfs with the much simpler ramfs code,
908 which may be appropriate on small systems without swap.
911 bool "Enable AIO support" if EMBEDDED
914 This option enables POSIX asynchronous I/O which may by used
915 by some high performance threaded applications. Disabling
916 this option saves about 7k.
918 config HAVE_PERF_COUNTERS
921 See tools/perf/design.txt for details.
923 menu "Performance Counters"
926 bool "Kernel Performance Counters"
927 default y if PROFILING
928 depends on HAVE_PERF_COUNTERS
931 Enable kernel support for performance counter hardware.
933 Performance counters are special hardware registers available
934 on most modern CPUs. These registers count the number of certain
935 types of hw events: such as instructions executed, cachemisses
936 suffered, or branches mis-predicted - without slowing down the
937 kernel or applications. These registers can also trigger interrupts
938 when a threshold number of events have passed - and can thus be
939 used to profile the code that runs on that CPU.
941 The Linux Performance Counter subsystem provides an abstraction of
942 these hardware capabilities, available via a system call. It
943 provides per task and per CPU counters, and it provides event
944 capabilities on top of those.
949 bool "Tracepoint profiling sources"
950 depends on PERF_COUNTERS && EVENT_TRACING
953 Allow the use of tracepoints as software performance counters.
955 When this is enabled, you can create perf counters based on
956 tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
957 found in debugfs://tracing/events/*/*/id. (The -e/--events
958 option to the perf tool can parse and interpret symbolic
959 tracepoints, in the subsystem:tracepoint_name format.)
963 config VM_EVENT_COUNTERS
965 bool "Enable VM event counters for /proc/vmstat" if EMBEDDED
967 VM event counters are needed for event counts to be shown.
968 This option allows the disabling of the VM event counters
969 on EMBEDDED systems. /proc/vmstat will only show page counts
970 if VM event counters are disabled.
974 bool "Enable PCI quirk workarounds" if EMBEDDED
977 This enables workarounds for various PCI chipset
978 bugs/quirks. Disable this only if your target machine is
979 unaffected by PCI quirks.
983 bool "Enable SLUB debugging support" if EMBEDDED
984 depends on SLUB && SYSFS
986 SLUB has extensive debug support features. Disabling these can
987 result in significant savings in code size. This also disables
988 SLUB sysfs support. /sys/slab will not exist and there will be
989 no support for cache validation etc.
991 config STRIP_ASM_SYMS
992 bool "Strip assembler-generated symbols during link"
995 Strip internal assembler-generated symbols during a link (symbols
996 that look like '.Lxxx') so they don't pollute the output of
997 get_wchan() and suchlike.
1000 bool "Disable heap randomization"
1003 Randomizing heap placement makes heap exploits harder, but it
1004 also breaks ancient binaries (including anything libc5 based).
1005 This option changes the bootup default to heap randomization
1006 disabled, and can be overridden at runtime by setting
1007 /proc/sys/kernel/randomize_va_space to 2.
1009 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1012 prompt "Choose SLAB allocator"
1015 This option allows to select a slab allocator.
1020 The regular slab allocator that is established and known to work
1021 well in all environments. It organizes cache hot objects in
1022 per cpu and per node queues.
1025 bool "SLUB (Unqueued Allocator)"
1027 SLUB is a slab allocator that minimizes cache line usage
1028 instead of managing queues of cached objects (SLAB approach).
1029 Per cpu caching is realized using slabs of objects instead
1030 of queues of objects. SLUB can use memory efficiently
1031 and has enhanced diagnostics. SLUB is the default choice for
1036 bool "SLOB (Simple Allocator)"
1038 SLOB replaces the stock allocator with a drastically simpler
1039 allocator. SLOB is generally more space efficient but
1040 does not perform as well on large systems.
1045 bool "Profiling support (EXPERIMENTAL)"
1047 Say Y here to enable the extended profiling support mechanisms used
1048 by profilers such as OProfile.
1051 # Place an empty function call at each tracepoint site. Can be
1052 # dynamically changed for a probe function.
1058 bool "Activate markers"
1061 Place an empty function call at each marker site. Can be
1062 dynamically changed for a probe function.
1064 source "arch/Kconfig"
1070 The slow work thread pool provides a number of dynamically allocated
1071 threads that can be used by the kernel to perform operations that
1072 take a relatively long time.
1074 An example of this would be CacheFiles doing a path lookup followed
1075 by a series of mkdirs and a create call, all of which have to touch
1078 See Documentation/slow-work.txt.
1080 endmenu # General setup
1082 config HAVE_GENERIC_DMA_COHERENT
1089 depends on SLAB || SLUB_DEBUG
1097 default 0 if BASE_FULL
1098 default 1 if !BASE_FULL
1101 bool "Enable loadable module support"
1103 Kernel modules are small pieces of compiled code which can
1104 be inserted in the running kernel, rather than being
1105 permanently built into the kernel. You use the "modprobe"
1106 tool to add (and sometimes remove) them. If you say Y here,
1107 many parts of the kernel can be built as modules (by
1108 answering M instead of Y where indicated): this is most
1109 useful for infrequently used options which are not required
1110 for booting. For more information, see the man pages for
1111 modprobe, lsmod, modinfo, insmod and rmmod.
1113 If you say Y here, you will need to run "make
1114 modules_install" to put the modules under /lib/modules/
1115 where modprobe can find them (you may need to be root to do
1122 config MODULE_FORCE_LOAD
1123 bool "Forced module loading"
1126 Allow loading of modules without version information (ie. modprobe
1127 --force). Forced module loading sets the 'F' (forced) taint flag and
1128 is usually a really bad idea.
1130 config MODULE_UNLOAD
1131 bool "Module unloading"
1133 Without this option you will not be able to unload any
1134 modules (note that some modules may not be unloadable
1135 anyway), which makes your kernel smaller, faster
1136 and simpler. If unsure, say Y.
1138 config MODULE_FORCE_UNLOAD
1139 bool "Forced module unloading"
1140 depends on MODULE_UNLOAD && EXPERIMENTAL
1142 This option allows you to force a module to unload, even if the
1143 kernel believes it is unsafe: the kernel will remove the module
1144 without waiting for anyone to stop using it (using the -f option to
1145 rmmod). This is mainly for kernel developers and desperate users.
1149 bool "Module versioning support"
1151 Usually, you have to use modules compiled with your kernel.
1152 Saying Y here makes it sometimes possible to use modules
1153 compiled for different kernels, by adding enough information
1154 to the modules to (hopefully) spot any changes which would
1155 make them incompatible with the kernel you are running. If
1158 config MODULE_SRCVERSION_ALL
1159 bool "Source checksum for all modules"
1161 Modules which contain a MODULE_VERSION get an extra "srcversion"
1162 field inserted into their modinfo section, which contains a
1163 sum of the source files which made it. This helps maintainers
1164 see exactly which source was used to build a module (since
1165 others sometimes change the module source without updating
1166 the version). With this option, such a "srcversion" field
1167 will be created for all modules. If unsure, say N.
1171 config INIT_ALL_POSSIBLE
1174 Back when each arch used to define their own cpu_online_map and
1175 cpu_possible_map, some of them chose to initialize cpu_possible_map
1176 with all 1s, and others with all 0s. When they were centralised,
1177 it was better to provide this option than to break all the archs
1178 and have several arch maintainers pursuing me down dark alleys.
1183 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
1185 Need stop_machine() primitive.
1187 source "block/Kconfig"
1189 config PREEMPT_NOTIFIERS