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47 drivers that have been replaced by something else, and/or are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 || 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
334 is also required. It also scales down nicely to
340 bool "Enable tracing for RCU"
341 depends on TREE_RCU || TREE_PREEMPT_RCU
343 This option provides tracing in RCU which presents stats
344 in debugfs for debugging RCU implementation.
346 Say Y here if you want to enable RCU tracing
347 Say N if you are unsure.
350 int "Tree-based hierarchical RCU fanout value"
353 depends on TREE_RCU || TREE_PREEMPT_RCU
357 This option controls the fanout of hierarchical implementations
358 of RCU, allowing RCU to work efficiently on machines with
359 large numbers of CPUs. This value must be at least the cube
360 root of NR_CPUS, which allows NR_CPUS up to 32,768 for 32-bit
361 systems and up to 262,144 for 64-bit systems.
363 Select a specific number if testing RCU itself.
364 Take the default if unsure.
366 config RCU_FANOUT_EXACT
367 bool "Disable tree-based hierarchical RCU auto-balancing"
368 depends on TREE_RCU || TREE_PREEMPT_RCU
371 This option forces use of the exact RCU_FANOUT value specified,
372 regardless of imbalances in the hierarchy. This is useful for
373 testing RCU itself, and might one day be useful on systems with
374 strong NUMA behavior.
376 Without RCU_FANOUT_EXACT, the code will balance the hierarchy.
380 config TREE_RCU_TRACE
381 def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU )
384 This option provides tracing for the TREE_RCU and
385 TREE_PREEMPT_RCU implementations, permitting Makefile to
386 trivially select kernel/rcutree_trace.c.
388 endmenu # "RCU Subsystem"
391 tristate "Kernel .config support"
393 This option enables the complete Linux kernel ".config" file
394 contents to be saved in the kernel. It provides documentation
395 of which kernel options are used in a running kernel or in an
396 on-disk kernel. This information can be extracted from the kernel
397 image file with the script scripts/extract-ikconfig and used as
398 input to rebuild the current kernel or to build another kernel.
399 It can also be extracted from a running kernel by reading
400 /proc/config.gz if enabled (below).
403 bool "Enable access to .config through /proc/config.gz"
404 depends on IKCONFIG && PROC_FS
406 This option enables access to the kernel configuration file
407 through /proc/config.gz.
410 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
414 Select kernel log buffer size as a power of 2.
424 # Architectures with an unreliable sched_clock() should select this:
426 config HAVE_UNSTABLE_SCHED_CLOCK
430 bool "Group CPU scheduler"
431 depends on EXPERIMENTAL
434 This feature lets CPU scheduler recognize task groups and control CPU
435 bandwidth allocation to such task groups.
436 In order to create a group from arbitrary set of processes, use
437 CONFIG_CGROUPS. (See Control Group support.)
439 config FAIR_GROUP_SCHED
440 bool "Group scheduling for SCHED_OTHER"
441 depends on GROUP_SCHED
444 config RT_GROUP_SCHED
445 bool "Group scheduling for SCHED_RR/FIFO"
446 depends on EXPERIMENTAL
447 depends on GROUP_SCHED
450 This feature lets you explicitly allocate real CPU bandwidth
451 to users or control groups (depending on the "Basis for grouping tasks"
452 setting below. If enabled, it will also make it impossible to
453 schedule realtime tasks for non-root users until you allocate
454 realtime bandwidth for them.
455 See Documentation/scheduler/sched-rt-group.txt for more information.
458 depends on GROUP_SCHED
459 prompt "Basis for grouping tasks"
465 This option will choose userid as the basis for grouping
466 tasks, thus providing equal CPU bandwidth to each user.
469 bool "Control groups"
472 This option allows you to create arbitrary task groups
473 using the "cgroup" pseudo filesystem and control
474 the cpu bandwidth allocated to each such task group.
475 Refer to Documentation/cgroups/cgroups.txt for more
476 information on "cgroup" pseudo filesystem.
481 boolean "Control Group support"
483 This option adds support for grouping sets of processes together, for
484 use with process control subsystems such as Cpusets, CFS, memory
485 controls or device isolation.
487 - Documentation/scheduler/sched-design-CFS.txt (CFS)
488 - Documentation/cgroups/ (features for grouping, isolation
489 and resource control)
496 bool "Example debug cgroup subsystem"
500 This option enables a simple cgroup subsystem that
501 exports useful debugging information about the cgroups
507 bool "Namespace cgroup subsystem"
510 Provides a simple namespace cgroup subsystem to
511 provide hierarchical naming of sets of namespaces,
512 for instance virtual servers and checkpoint/restart
515 config CGROUP_FREEZER
516 bool "Freezer cgroup subsystem"
519 Provides a way to freeze and unfreeze all tasks in a
523 bool "Device controller for cgroups"
524 depends on CGROUPS && EXPERIMENTAL
526 Provides a cgroup implementing whitelists for devices which
527 a process in the cgroup can mknod or open.
530 bool "Cpuset support"
533 This option will let you create and manage CPUSETs which
534 allow dynamically partitioning a system into sets of CPUs and
535 Memory Nodes and assigning tasks to run only within those sets.
536 This is primarily useful on large SMP or NUMA systems.
540 config PROC_PID_CPUSET
541 bool "Include legacy /proc/<pid>/cpuset file"
545 config CGROUP_CPUACCT
546 bool "Simple CPU accounting cgroup subsystem"
549 Provides a simple Resource Controller for monitoring the
550 total CPU consumed by the tasks in a cgroup.
552 config RESOURCE_COUNTERS
553 bool "Resource counters"
555 This option enables controller independent resource accounting
556 infrastructure that works with cgroups.
559 config CGROUP_MEM_RES_CTLR
560 bool "Memory Resource Controller for Control Groups"
561 depends on CGROUPS && RESOURCE_COUNTERS
564 Provides a memory resource controller that manages both anonymous
565 memory and page cache. (See Documentation/cgroups/memory.txt)
567 Note that setting this option increases fixed memory overhead
568 associated with each page of memory in the system. By this,
569 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory
570 usage tracking struct at boot. Total amount of this is printed out
573 Only enable when you're ok with these trade offs and really
574 sure you need the memory resource controller. Even when you enable
575 this, you can set "cgroup_disable=memory" at your boot option to
576 disable memory resource controller and you can avoid overheads.
577 (and lose benefits of memory resource controller)
579 This config option also selects MM_OWNER config option, which
580 could in turn add some fork/exit overhead.
582 config CGROUP_MEM_RES_CTLR_SWAP
583 bool "Memory Resource Controller Swap Extension(EXPERIMENTAL)"
584 depends on CGROUP_MEM_RES_CTLR && SWAP && EXPERIMENTAL
586 Add swap management feature to memory resource controller. When you
587 enable this, you can limit mem+swap usage per cgroup. In other words,
588 when you disable this, memory resource controller has no cares to
589 usage of swap...a process can exhaust all of the swap. This extension
590 is useful when you want to avoid exhaustion swap but this itself
591 adds more overheads and consumes memory for remembering information.
592 Especially if you use 32bit system or small memory system, please
593 be careful about enabling this. When memory resource controller
594 is disabled by boot option, this will be automatically disabled and
595 there will be no overhead from this. Even when you set this config=y,
596 if boot option "noswapaccount" is set, swap will not be accounted.
597 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
598 size is 4096bytes, 512k per 1Gbytes of swap.
605 config SYSFS_DEPRECATED
608 config SYSFS_DEPRECATED_V2
609 bool "enable deprecated sysfs features which may confuse old userspace tools"
612 select SYSFS_DEPRECATED
614 This option switches the layout of sysfs to the deprecated
615 version. Do not use it on recent distributions.
617 The current sysfs layout features a unified device tree at
618 /sys/devices/, which is able to express a hierarchy between
619 class devices. If the deprecated option is set to Y, the
620 unified device tree is split into a bus device tree at
621 /sys/devices/ and several individual class device trees at
622 /sys/class/. The class and bus devices will be connected by
623 "<subsystem>:<name>" and the "device" links. The "block"
624 class devices, will not show up in /sys/class/block/. Some
625 subsystems will suppress the creation of some devices which
626 depend on the unified device tree.
628 This option is not a pure compatibility option that can
629 be safely enabled on newer distributions. It will change the
630 layout of sysfs to the non-extensible deprecated version,
631 and disable some features, which can not be exported without
632 confusing older userspace tools. Since 2007/2008 all major
633 distributions do not enable this option, and ship no tools which
634 depend on the deprecated layout or this option.
636 If you are using a new kernel on an older distribution, or use
637 older userspace tools, you might need to say Y here. Do not say Y,
638 if the original kernel, that came with your distribution, has
639 this option set to N.
642 bool "Kernel->user space relay support (formerly relayfs)"
644 This option enables support for relay interface support in
645 certain file systems (such as debugfs).
646 It is designed to provide an efficient mechanism for tools and
647 facilities to relay large amounts of data from kernel space to
653 bool "Namespaces support" if EMBEDDED
656 Provides the way to make tasks work with different objects using
657 the same id. For example same IPC id may refer to different objects
658 or same user id or pid may refer to different tasks when used in
659 different namespaces.
663 depends on NAMESPACES
665 In this namespace tasks see different info provided with the
670 depends on NAMESPACES && (SYSVIPC || POSIX_MQUEUE)
672 In this namespace tasks work with IPC ids which correspond to
673 different IPC objects in different namespaces.
676 bool "User namespace (EXPERIMENTAL)"
677 depends on NAMESPACES && EXPERIMENTAL
679 This allows containers, i.e. vservers, to use user namespaces
680 to provide different user info for different servers.
684 bool "PID Namespaces (EXPERIMENTAL)"
686 depends on NAMESPACES && EXPERIMENTAL
688 Support process id namespaces. This allows having multiple
689 processes with the same pid as long as they are in different
690 pid namespaces. This is a building block of containers.
692 Unless you want to work with an experimental feature
696 bool "Network namespace"
698 depends on NAMESPACES && EXPERIMENTAL && NET
700 Allow user space to create what appear to be multiple instances
701 of the network stack.
703 config BLK_DEV_INITRD
704 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
705 depends on BROKEN || !FRV
707 The initial RAM filesystem is a ramfs which is loaded by the
708 boot loader (loadlin or lilo) and that is mounted as root
709 before the normal boot procedure. It is typically used to
710 load modules needed to mount the "real" root file system,
711 etc. See <file:Documentation/initrd.txt> for details.
713 If RAM disk support (BLK_DEV_RAM) is also included, this
714 also enables initial RAM disk (initrd) support and adds
715 15 Kbytes (more on some other architectures) to the kernel size.
725 config CC_OPTIMIZE_FOR_SIZE
726 bool "Optimize for size"
729 Enabling this option will pass "-Os" instead of "-O2" to gcc
730 resulting in a smaller kernel.
741 bool "Configure standard kernel features (for small systems)"
743 This option allows certain base kernel options and settings
744 to be disabled or tweaked. This is for specialized
745 environments which can tolerate a "non-standard" kernel.
746 Only use this if you really know what you are doing.
749 bool "Enable 16-bit UID system calls" if EMBEDDED
750 depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION)
753 This enables the legacy 16-bit UID syscall wrappers.
755 config SYSCTL_SYSCALL
756 bool "Sysctl syscall support" if EMBEDDED
760 sys_sysctl uses binary paths that have been found challenging
761 to properly maintain and use. The interface in /proc/sys
762 using paths with ascii names is now the primary path to this
765 Almost nothing using the binary sysctl interface so if you are
766 trying to save some space it is probably safe to disable this,
767 making your kernel marginally smaller.
769 If unsure say Y here.
772 bool "Load all symbols for debugging/ksymoops" if EMBEDDED
775 Say Y here to let the kernel print out symbolic crash information and
776 symbolic stack backtraces. This increases the size of the kernel
777 somewhat, as all symbols have to be loaded into the kernel image.
780 bool "Include all symbols in kallsyms"
781 depends on DEBUG_KERNEL && KALLSYMS
783 Normally kallsyms only contains the symbols of functions, for nicer
784 OOPS messages. Some debuggers can use kallsyms for other
785 symbols too: say Y here to include all symbols, if you need them
786 and you don't care about adding 300k to the size of your kernel.
790 config KALLSYMS_EXTRA_PASS
791 bool "Do an extra kallsyms pass"
794 If kallsyms is not working correctly, the build will fail with
795 inconsistent kallsyms data. If that occurs, log a bug report and
796 turn on KALLSYMS_EXTRA_PASS which should result in a stable build.
797 Always say N here unless you find a bug in kallsyms, which must be
798 reported. KALLSYMS_EXTRA_PASS is only a temporary workaround while
799 you wait for kallsyms to be fixed.
803 bool "Support for hot-pluggable devices" if EMBEDDED
806 This option is provided for the case where no hotplug or uevent
807 capabilities is wanted by the kernel. You should only consider
808 disabling this option for embedded systems that do not use modules, a
809 dynamic /dev tree, or dynamic device discovery. Just say Y.
813 bool "Enable support for printk" if EMBEDDED
815 This option enables normal printk support. Removing it
816 eliminates most of the message strings from the kernel image
817 and makes the kernel more or less silent. As this makes it
818 very difficult to diagnose system problems, saying N here is
819 strongly discouraged.
822 bool "BUG() support" if EMBEDDED
825 Disabling this option eliminates support for BUG and WARN, reducing
826 the size of your kernel image and potentially quietly ignoring
827 numerous fatal conditions. You should only consider disabling this
828 option for embedded systems with no facilities for reporting errors.
833 bool "Enable ELF core dumps" if EMBEDDED
835 Enable support for generating core dumps. Disabling saves about 4k.
837 config PCSPKR_PLATFORM
838 bool "Enable PC-Speaker support" if EMBEDDED
839 depends on ALPHA || X86 || MIPS || PPC_PREP || PPC_CHRP || PPC_PSERIES
842 This option allows to disable the internal PC-Speaker
843 support, saving some memory.
847 bool "Enable full-sized data structures for core" if EMBEDDED
849 Disabling this option reduces the size of miscellaneous core
850 kernel data structures. This saves memory on small machines,
851 but may reduce performance.
854 bool "Enable futex support" if EMBEDDED
858 Disabling this option will cause the kernel to be built without
859 support for "fast userspace mutexes". The resulting kernel may not
860 run glibc-based applications correctly.
863 bool "Enable eventpoll support" if EMBEDDED
867 Disabling this option will cause the kernel to be built without
868 support for epoll family of system calls.
871 bool "Enable signalfd() system call" if EMBEDDED
875 Enable the signalfd() system call that allows to receive signals
876 on a file descriptor.
881 bool "Enable timerfd() system call" if EMBEDDED
885 Enable the timerfd() system call that allows to receive timer
886 events on a file descriptor.
891 bool "Enable eventfd() system call" if EMBEDDED
895 Enable the eventfd() system call that allows to receive both
896 kernel notification (ie. KAIO) or userspace notifications.
901 bool "Use full shmem filesystem" if EMBEDDED
905 The shmem is an internal filesystem used to manage shared memory.
906 It is backed by swap and manages resource limits. It is also exported
907 to userspace as tmpfs if TMPFS is enabled. Disabling this
908 option replaces shmem and tmpfs with the much simpler ramfs code,
909 which may be appropriate on small systems without swap.
912 bool "Enable AIO support" if EMBEDDED
915 This option enables POSIX asynchronous I/O which may by used
916 by some high performance threaded applications. Disabling
917 this option saves about 7k.
919 config HAVE_PERF_EVENTS
922 See tools/perf/design.txt for details.
924 config PERF_USE_VMALLOC
927 See tools/perf/design.txt for details
929 menu "Kernel Performance Events And Counters"
932 bool "Kernel performance events and counters"
933 default y if (PROFILING || PERF_COUNTERS)
934 depends on HAVE_PERF_EVENTS
937 Enable kernel support for various performance events provided
938 by software and hardware.
940 Software events are supported either built-in or via the
941 use of generic tracepoints.
943 Most modern CPUs support performance events via performance
944 counter registers. These registers count the number of certain
945 types of hw events: such as instructions executed, cachemisses
946 suffered, or branches mis-predicted - without slowing down the
947 kernel or applications. These registers can also trigger interrupts
948 when a threshold number of events have passed - and can thus be
949 used to profile the code that runs on that CPU.
951 The Linux Performance Event subsystem provides an abstraction of
952 these software and hardware event capabilities, available via a
953 system call and used by the "perf" utility in tools/perf/. It
954 provides per task and per CPU counters, and it provides event
955 capabilities on top of those.
960 bool "Tracepoint profiling sources"
961 depends on PERF_EVENTS && EVENT_TRACING
964 Allow the use of tracepoints as software performance events.
966 When this is enabled, you can create perf events based on
967 tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID
968 found in debugfs://tracing/events/*/*/id. (The -e/--events
969 option to the perf tool can parse and interpret symbolic
970 tracepoints, in the subsystem:tracepoint_name format.)
973 bool "Kernel performance counters (old config option)"
974 depends on HAVE_PERF_EVENTS
976 This config has been obsoleted by the PERF_EVENTS
977 config option - please see that one for details.
979 It has no effect on the kernel whether you enable
980 it or not, it is a compatibility placeholder.
984 config DEBUG_PERF_USE_VMALLOC
986 bool "Debug: use vmalloc to back perf mmap() buffers"
987 depends on PERF_EVENTS && DEBUG_KERNEL
988 select PERF_USE_VMALLOC
990 Use vmalloc memory to back perf mmap() buffers.
992 Mostly useful for debugging the vmalloc code on platforms
993 that don't require it.
999 config VM_EVENT_COUNTERS
1001 bool "Enable VM event counters for /proc/vmstat" if EMBEDDED
1003 VM event counters are needed for event counts to be shown.
1004 This option allows the disabling of the VM event counters
1005 on EMBEDDED systems. /proc/vmstat will only show page counts
1006 if VM event counters are disabled.
1010 bool "Enable PCI quirk workarounds" if EMBEDDED
1013 This enables workarounds for various PCI chipset
1014 bugs/quirks. Disable this only if your target machine is
1015 unaffected by PCI quirks.
1019 bool "Enable SLUB debugging support" if EMBEDDED
1020 depends on SLUB && SYSFS
1022 SLUB has extensive debug support features. Disabling these can
1023 result in significant savings in code size. This also disables
1024 SLUB sysfs support. /sys/slab will not exist and there will be
1025 no support for cache validation etc.
1028 bool "Disable heap randomization"
1031 Randomizing heap placement makes heap exploits harder, but it
1032 also breaks ancient binaries (including anything libc5 based).
1033 This option changes the bootup default to heap randomization
1034 disabled, and can be overridden at runtime by setting
1035 /proc/sys/kernel/randomize_va_space to 2.
1037 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1040 prompt "Choose SLAB allocator"
1043 This option allows to select a slab allocator.
1048 The regular slab allocator that is established and known to work
1049 well in all environments. It organizes cache hot objects in
1050 per cpu and per node queues.
1053 bool "SLUB (Unqueued Allocator)"
1055 SLUB is a slab allocator that minimizes cache line usage
1056 instead of managing queues of cached objects (SLAB approach).
1057 Per cpu caching is realized using slabs of objects instead
1058 of queues of objects. SLUB can use memory efficiently
1059 and has enhanced diagnostics. SLUB is the default choice for
1064 bool "SLOB (Simple Allocator)"
1066 SLOB replaces the stock allocator with a drastically simpler
1067 allocator. SLOB is generally more space efficient but
1068 does not perform as well on large systems.
1073 bool "Profiling support (EXPERIMENTAL)"
1075 Say Y here to enable the extended profiling support mechanisms used
1076 by profilers such as OProfile.
1079 # Place an empty function call at each tracepoint site. Can be
1080 # dynamically changed for a probe function.
1085 source "arch/Kconfig"
1091 The slow work thread pool provides a number of dynamically allocated
1092 threads that can be used by the kernel to perform operations that
1093 take a relatively long time.
1095 An example of this would be CacheFiles doing a path lookup followed
1096 by a series of mkdirs and a create call, all of which have to touch
1099 See Documentation/slow-work.txt.
1101 config SLOW_WORK_DEBUG
1102 bool "Slow work debugging through debugfs"
1104 depends on SLOW_WORK && DEBUG_FS
1106 Display the contents of the slow work run queue through debugfs,
1107 including items currently executing.
1109 See Documentation/slow-work.txt.
1111 endmenu # General setup
1113 config HAVE_GENERIC_DMA_COHERENT
1120 depends on SLAB || SLUB_DEBUG
1128 default 0 if BASE_FULL
1129 default 1 if !BASE_FULL
1132 bool "Enable loadable module support"
1134 Kernel modules are small pieces of compiled code which can
1135 be inserted in the running kernel, rather than being
1136 permanently built into the kernel. You use the "modprobe"
1137 tool to add (and sometimes remove) them. If you say Y here,
1138 many parts of the kernel can be built as modules (by
1139 answering M instead of Y where indicated): this is most
1140 useful for infrequently used options which are not required
1141 for booting. For more information, see the man pages for
1142 modprobe, lsmod, modinfo, insmod and rmmod.
1144 If you say Y here, you will need to run "make
1145 modules_install" to put the modules under /lib/modules/
1146 where modprobe can find them (you may need to be root to do
1153 config MODULE_FORCE_LOAD
1154 bool "Forced module loading"
1157 Allow loading of modules without version information (ie. modprobe
1158 --force). Forced module loading sets the 'F' (forced) taint flag and
1159 is usually a really bad idea.
1161 config MODULE_UNLOAD
1162 bool "Module unloading"
1164 Without this option you will not be able to unload any
1165 modules (note that some modules may not be unloadable
1166 anyway), which makes your kernel smaller, faster
1167 and simpler. If unsure, say Y.
1169 config MODULE_FORCE_UNLOAD
1170 bool "Forced module unloading"
1171 depends on MODULE_UNLOAD && EXPERIMENTAL
1173 This option allows you to force a module to unload, even if the
1174 kernel believes it is unsafe: the kernel will remove the module
1175 without waiting for anyone to stop using it (using the -f option to
1176 rmmod). This is mainly for kernel developers and desperate users.
1180 bool "Module versioning support"
1182 Usually, you have to use modules compiled with your kernel.
1183 Saying Y here makes it sometimes possible to use modules
1184 compiled for different kernels, by adding enough information
1185 to the modules to (hopefully) spot any changes which would
1186 make them incompatible with the kernel you are running. If
1189 config MODULE_SRCVERSION_ALL
1190 bool "Source checksum for all modules"
1192 Modules which contain a MODULE_VERSION get an extra "srcversion"
1193 field inserted into their modinfo section, which contains a
1194 sum of the source files which made it. This helps maintainers
1195 see exactly which source was used to build a module (since
1196 others sometimes change the module source without updating
1197 the version). With this option, such a "srcversion" field
1198 will be created for all modules. If unsure, say N.
1202 config INIT_ALL_POSSIBLE
1205 Back when each arch used to define their own cpu_online_map and
1206 cpu_possible_map, some of them chose to initialize cpu_possible_map
1207 with all 1s, and others with all 0s. When they were centralised,
1208 it was better to provide this option than to break all the archs
1209 and have several arch maintainers pursuing me down dark alleys.
1214 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
1216 Need stop_machine() primitive.
1218 source "block/Kconfig"
1220 config PREEMPT_NOTIFIERS