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"
26 config BUILDTIME_EXTABLE_SORT
29 config THREAD_INFO_IN_TASK
32 Select this to move thread_info off the stack into task_struct. To
33 make this work, an arch will need to remove all thread_info fields
34 except flags and fix any runtime bugs.
36 One subtle change that will be needed is to use try_get_task_stack()
37 and put_task_stack() in save_thread_stack_tsk() and get_wchan().
46 depends on BROKEN || !SMP
49 config INIT_ENV_ARG_LIMIT
54 Maximum of each of the number of arguments and environment
55 variables passed to init from the kernel command line.
59 string "Cross-compiler tool prefix"
61 Same as running 'make CROSS_COMPILE=prefix-' but stored for
62 default make runs in this kernel build directory. You don't
63 need to set this unless you want the configured kernel build
64 directory to select the cross-compiler automatically.
67 bool "Compile also drivers which will not load"
70 Some drivers can be compiled on a different platform than they are
71 intended to be run on. Despite they cannot be loaded there (or even
72 when they load they cannot be used due to missing HW support),
73 developers still, opposing to distributors, might want to build such
74 drivers to compile-test them.
76 If you are a developer and want to build everything available, say Y
77 here. If you are a user/distributor, say N here to exclude useless
78 drivers to be distributed.
81 string "Local version - append to kernel release"
83 Append an extra string to the end of your kernel version.
84 This will show up when you type uname, for example.
85 The string you set here will be appended after the contents of
86 any files with a filename matching localversion* in your
87 object and source tree, in that order. Your total string can
88 be a maximum of 64 characters.
90 config LOCALVERSION_AUTO
91 bool "Automatically append version information to the version string"
94 This will try to automatically determine if the current tree is a
95 release tree by looking for git tags that belong to the current
98 A string of the format -gxxxxxxxx will be added to the localversion
99 if a git-based tree is found. The string generated by this will be
100 appended after any matching localversion* files, and after the value
101 set in CONFIG_LOCALVERSION.
103 (The actual string used here is the first eight characters produced
104 by running the command:
106 $ git rev-parse --verify HEAD
108 which is done within the script "scripts/setlocalversion".)
110 config HAVE_KERNEL_GZIP
113 config HAVE_KERNEL_BZIP2
116 config HAVE_KERNEL_LZMA
119 config HAVE_KERNEL_XZ
122 config HAVE_KERNEL_LZO
125 config HAVE_KERNEL_LZ4
129 prompt "Kernel compression mode"
131 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
133 The linux kernel is a kind of self-extracting executable.
134 Several compression algorithms are available, which differ
135 in efficiency, compression and decompression speed.
136 Compression speed is only relevant when building a kernel.
137 Decompression speed is relevant at each boot.
139 If you have any problems with bzip2 or lzma compressed
140 kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older
141 version of this functionality (bzip2 only), for 2.4, was
142 supplied by Christian Ludwig)
144 High compression options are mostly useful for users, who
145 are low on disk space (embedded systems), but for whom ram
148 If in doubt, select 'gzip'
152 depends on HAVE_KERNEL_GZIP
154 The old and tried gzip compression. It provides a good balance
155 between compression ratio and decompression speed.
159 depends on HAVE_KERNEL_BZIP2
161 Its compression ratio and speed is intermediate.
162 Decompression speed is slowest among the choices. The kernel
163 size is about 10% smaller with bzip2, in comparison to gzip.
164 Bzip2 uses a large amount of memory. For modern kernels you
165 will need at least 8MB RAM or more for booting.
169 depends on HAVE_KERNEL_LZMA
171 This compression algorithm's ratio is best. Decompression speed
172 is between gzip and bzip2. Compression is slowest.
173 The kernel size is about 33% smaller with LZMA in comparison to gzip.
177 depends on HAVE_KERNEL_XZ
179 XZ uses the LZMA2 algorithm and instruction set specific
180 BCJ filters which can improve compression ratio of executable
181 code. The size of the kernel is about 30% smaller with XZ in
182 comparison to gzip. On architectures for which there is a BCJ
183 filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
184 will create a few percent smaller kernel than plain LZMA.
186 The speed is about the same as with LZMA: The decompression
187 speed of XZ is better than that of bzip2 but worse than gzip
188 and LZO. Compression is slow.
192 depends on HAVE_KERNEL_LZO
194 Its compression ratio is the poorest among the choices. The kernel
195 size is about 10% bigger than gzip; however its speed
196 (both compression and decompression) is the fastest.
200 depends on HAVE_KERNEL_LZ4
202 LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
203 A preliminary version of LZ4 de/compression tool is available at
204 <https://code.google.com/p/lz4/>.
206 Its compression ratio is worse than LZO. The size of the kernel
207 is about 8% bigger than LZO. But the decompression speed is
212 config DEFAULT_HOSTNAME
213 string "Default hostname"
216 This option determines the default system hostname before userspace
217 calls sethostname(2). The kernel traditionally uses "(none)" here,
218 but you may wish to use a different default here to make a minimal
219 system more usable with less configuration.
222 bool "Support for paging of anonymous memory (swap)"
223 depends on MMU && BLOCK
226 This option allows you to choose whether you want to have support
227 for so called swap devices or swap files in your kernel that are
228 used to provide more virtual memory than the actual RAM present
229 in your computer. If unsure say Y.
234 Inter Process Communication is a suite of library functions and
235 system calls which let processes (running programs) synchronize and
236 exchange information. It is generally considered to be a good thing,
237 and some programs won't run unless you say Y here. In particular, if
238 you want to run the DOS emulator dosemu under Linux (read the
239 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
240 you'll need to say Y here.
242 You can find documentation about IPC with "info ipc" and also in
243 section 6.4 of the Linux Programmer's Guide, available from
244 <http://www.tldp.org/guides.html>.
246 config SYSVIPC_SYSCTL
253 bool "POSIX Message Queues"
256 POSIX variant of message queues is a part of IPC. In POSIX message
257 queues every message has a priority which decides about succession
258 of receiving it by a process. If you want to compile and run
259 programs written e.g. for Solaris with use of its POSIX message
260 queues (functions mq_*) say Y here.
262 POSIX message queues are visible as a filesystem called 'mqueue'
263 and can be mounted somewhere if you want to do filesystem
264 operations on message queues.
268 config POSIX_MQUEUE_SYSCTL
270 depends on POSIX_MQUEUE
274 config CROSS_MEMORY_ATTACH
275 bool "Enable process_vm_readv/writev syscalls"
279 Enabling this option adds the system calls process_vm_readv and
280 process_vm_writev which allow a process with the correct privileges
281 to directly read from or write to another process' address space.
282 See the man page for more details.
285 bool "open by fhandle syscalls"
288 If you say Y here, a user level program will be able to map
289 file names to handle and then later use the handle for
290 different file system operations. This is useful in implementing
291 userspace file servers, which now track files using handles instead
292 of names. The handle would remain the same even if file names
293 get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
297 bool "uselib syscall"
300 This option enables the uselib syscall, a system call used in the
301 dynamic linker from libc5 and earlier. glibc does not use this
302 system call. If you intend to run programs built on libc5 or
303 earlier, you may need to enable this syscall. Current systems
304 running glibc can safely disable this.
307 bool "Auditing support"
310 Enable auditing infrastructure that can be used with another
311 kernel subsystem, such as SELinux (which requires this for
312 logging of avc messages output). Does not do system-call
313 auditing without CONFIG_AUDITSYSCALL.
315 config HAVE_ARCH_AUDITSYSCALL
319 bool "Enable system-call auditing support"
320 depends on AUDIT && HAVE_ARCH_AUDITSYSCALL
321 default y if SECURITY_SELINUX
323 Enable low-overhead system-call auditing infrastructure that
324 can be used independently or with another kernel subsystem,
329 depends on AUDITSYSCALL
334 depends on AUDITSYSCALL
337 source "kernel/irq/Kconfig"
338 source "kernel/time/Kconfig"
340 menu "CPU/Task time and stats accounting"
342 config VIRT_CPU_ACCOUNTING
346 prompt "Cputime accounting"
347 default TICK_CPU_ACCOUNTING if !PPC64
348 default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
350 # Kind of a stub config for the pure tick based cputime accounting
351 config TICK_CPU_ACCOUNTING
352 bool "Simple tick based cputime accounting"
353 depends on !S390 && !NO_HZ_FULL
355 This is the basic tick based cputime accounting that maintains
356 statistics about user, system and idle time spent on per jiffies
361 config VIRT_CPU_ACCOUNTING_NATIVE
362 bool "Deterministic task and CPU time accounting"
363 depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL
364 select VIRT_CPU_ACCOUNTING
366 Select this option to enable more accurate task and CPU time
367 accounting. This is done by reading a CPU counter on each
368 kernel entry and exit and on transitions within the kernel
369 between system, softirq and hardirq state, so there is a
370 small performance impact. In the case of s390 or IBM POWER > 5,
371 this also enables accounting of stolen time on logically-partitioned
374 config VIRT_CPU_ACCOUNTING_GEN
375 bool "Full dynticks CPU time accounting"
376 depends on HAVE_CONTEXT_TRACKING
377 depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
378 select VIRT_CPU_ACCOUNTING
379 select CONTEXT_TRACKING
381 Select this option to enable task and CPU time accounting on full
382 dynticks systems. This accounting is implemented by watching every
383 kernel-user boundaries using the context tracking subsystem.
384 The accounting is thus performed at the expense of some significant
387 For now this is only useful if you are working on the full
388 dynticks subsystem development.
392 config IRQ_TIME_ACCOUNTING
393 bool "Fine granularity task level IRQ time accounting"
394 depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL
396 Select this option to enable fine granularity task irq time
397 accounting. This is done by reading a timestamp on each
398 transitions between softirq and hardirq state, so there can be a
399 small performance impact.
401 If in doubt, say N here.
405 config BSD_PROCESS_ACCT
406 bool "BSD Process Accounting"
409 If you say Y here, a user level program will be able to instruct the
410 kernel (via a special system call) to write process accounting
411 information to a file: whenever a process exits, information about
412 that process will be appended to the file by the kernel. The
413 information includes things such as creation time, owning user,
414 command name, memory usage, controlling terminal etc. (the complete
415 list is in the struct acct in <file:include/linux/acct.h>). It is
416 up to the user level program to do useful things with this
417 information. This is generally a good idea, so say Y.
419 config BSD_PROCESS_ACCT_V3
420 bool "BSD Process Accounting version 3 file format"
421 depends on BSD_PROCESS_ACCT
424 If you say Y here, the process accounting information is written
425 in a new file format that also logs the process IDs of each
426 process and it's parent. Note that this file format is incompatible
427 with previous v0/v1/v2 file formats, so you will need updated tools
428 for processing it. A preliminary version of these tools is available
429 at <http://www.gnu.org/software/acct/>.
432 bool "Export task/process statistics through netlink"
437 Export selected statistics for tasks/processes through the
438 generic netlink interface. Unlike BSD process accounting, the
439 statistics are available during the lifetime of tasks/processes as
440 responses to commands. Like BSD accounting, they are sent to user
445 config TASK_DELAY_ACCT
446 bool "Enable per-task delay accounting"
450 Collect information on time spent by a task waiting for system
451 resources like cpu, synchronous block I/O completion and swapping
452 in pages. Such statistics can help in setting a task's priorities
453 relative to other tasks for cpu, io, rss limits etc.
458 bool "Enable extended accounting over taskstats"
461 Collect extended task accounting data and send the data
462 to userland for processing over the taskstats interface.
466 config TASK_IO_ACCOUNTING
467 bool "Enable per-task storage I/O accounting"
468 depends on TASK_XACCT
470 Collect information on the number of bytes of storage I/O which this
475 endmenu # "CPU/Task time and stats accounting"
481 default y if !PREEMPT && SMP
483 This option selects the RCU implementation that is
484 designed for very large SMP system with hundreds or
485 thousands of CPUs. It also scales down nicely to
492 This option selects the RCU implementation that is
493 designed for very large SMP systems with hundreds or
494 thousands of CPUs, but for which real-time response
495 is also required. It also scales down nicely to
498 Select this option if you are unsure.
502 default y if !PREEMPT && !SMP
504 This option selects the RCU implementation that is
505 designed for UP systems from which real-time response
506 is not required. This option greatly reduces the
507 memory footprint of RCU.
510 bool "Make expert-level adjustments to RCU configuration"
513 This option needs to be enabled if you wish to make
514 expert-level adjustments to RCU configuration. By default,
515 no such adjustments can be made, which has the often-beneficial
516 side-effect of preventing "make oldconfig" from asking you all
517 sorts of detailed questions about how you would like numerous
518 obscure RCU options to be set up.
520 Say Y if you need to make expert-level adjustments to RCU.
522 Say N if you are unsure.
527 This option selects the sleepable version of RCU. This version
528 permits arbitrary sleeping or blocking within RCU read-side critical
536 This option enables a task-based RCU implementation that uses
537 only voluntary context switch (not preemption!), idle, and
538 user-mode execution as quiescent states.
540 config RCU_STALL_COMMON
541 def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
543 This option enables RCU CPU stall code that is common between
544 the TINY and TREE variants of RCU. The purpose is to allow
545 the tiny variants to disable RCU CPU stall warnings, while
546 making these warnings mandatory for the tree variants.
548 config CONTEXT_TRACKING
551 config CONTEXT_TRACKING_FORCE
552 bool "Force context tracking"
553 depends on CONTEXT_TRACKING
554 default y if !NO_HZ_FULL
556 The major pre-requirement for full dynticks to work is to
557 support the context tracking subsystem. But there are also
558 other dependencies to provide in order to make the full
561 This option stands for testing when an arch implements the
562 context tracking backend but doesn't yet fullfill all the
563 requirements to make the full dynticks feature working.
564 Without the full dynticks, there is no way to test the support
565 for context tracking and the subsystems that rely on it: RCU
566 userspace extended quiescent state and tickless cputime
567 accounting. This option copes with the absence of the full
568 dynticks subsystem by forcing the context tracking on all
571 Say Y only if you're working on the development of an
572 architecture backend for the context tracking.
574 Say N otherwise, this option brings an overhead that you
575 don't want in production.
579 int "Tree-based hierarchical RCU fanout value"
582 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
586 This option controls the fanout of hierarchical implementations
587 of RCU, allowing RCU to work efficiently on machines with
588 large numbers of CPUs. This value must be at least the fourth
589 root of NR_CPUS, which allows NR_CPUS to be insanely large.
590 The default value of RCU_FANOUT should be used for production
591 systems, but if you are stress-testing the RCU implementation
592 itself, small RCU_FANOUT values allow you to test large-system
593 code paths on small(er) systems.
595 Select a specific number if testing RCU itself.
596 Take the default if unsure.
598 config RCU_FANOUT_LEAF
599 int "Tree-based hierarchical RCU leaf-level fanout value"
602 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
605 This option controls the leaf-level fanout of hierarchical
606 implementations of RCU, and allows trading off cache misses
607 against lock contention. Systems that synchronize their
608 scheduling-clock interrupts for energy-efficiency reasons will
609 want the default because the smaller leaf-level fanout keeps
610 lock contention levels acceptably low. Very large systems
611 (hundreds or thousands of CPUs) will instead want to set this
612 value to the maximum value possible in order to reduce the
613 number of cache misses incurred during RCU's grace-period
614 initialization. These systems tend to run CPU-bound, and thus
615 are not helped by synchronized interrupts, and thus tend to
616 skew them, which reduces lock contention enough that large
617 leaf-level fanouts work well.
619 Select a specific number if testing RCU itself.
621 Select the maximum permissible value for large systems.
623 Take the default if unsure.
625 config RCU_FAST_NO_HZ
626 bool "Accelerate last non-dyntick-idle CPU's grace periods"
627 depends on NO_HZ_COMMON && SMP && RCU_EXPERT
630 This option permits CPUs to enter dynticks-idle state even if
631 they have RCU callbacks queued, and prevents RCU from waking
632 these CPUs up more than roughly once every four jiffies (by
633 default, you can adjust this using the rcutree.rcu_idle_gp_delay
634 parameter), thus improving energy efficiency. On the other
635 hand, this option increases the duration of RCU grace periods,
636 for example, slowing down synchronize_rcu().
638 Say Y if energy efficiency is critically important, and you
639 don't care about increased grace-period durations.
641 Say N if you are unsure.
643 config TREE_RCU_TRACE
644 def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU )
647 This option provides tracing for the TREE_RCU and
648 PREEMPT_RCU implementations, permitting Makefile to
649 trivially select kernel/rcutree_trace.c.
652 bool "Enable RCU priority boosting"
653 depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
656 This option boosts the priority of preempted RCU readers that
657 block the current preemptible RCU grace period for too long.
658 This option also prevents heavy loads from blocking RCU
659 callback invocation for all flavors of RCU.
661 Say Y here if you are working with real-time apps or heavy loads
662 Say N here if you are unsure.
664 config RCU_KTHREAD_PRIO
665 int "Real-time priority to use for RCU worker threads"
666 range 1 99 if RCU_BOOST
667 range 0 99 if !RCU_BOOST
668 default 1 if RCU_BOOST
669 default 0 if !RCU_BOOST
670 depends on RCU_EXPERT
672 This option specifies the SCHED_FIFO priority value that will be
673 assigned to the rcuc/n and rcub/n threads and is also the value
674 used for RCU_BOOST (if enabled). If you are working with a
675 real-time application that has one or more CPU-bound threads
676 running at a real-time priority level, you should set
677 RCU_KTHREAD_PRIO to a priority higher than the highest-priority
678 real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO
679 value of 1 is appropriate in the common case, which is real-time
680 applications that do not have any CPU-bound threads.
682 Some real-time applications might not have a single real-time
683 thread that saturates a given CPU, but instead might have
684 multiple real-time threads that, taken together, fully utilize
685 that CPU. In this case, you should set RCU_KTHREAD_PRIO to
686 a priority higher than the lowest-priority thread that is
687 conspiring to prevent the CPU from running any non-real-time
688 tasks. For example, if one thread at priority 10 and another
689 thread at priority 5 are between themselves fully consuming
690 the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be
691 set to priority 6 or higher.
693 Specify the real-time priority, or take the default if unsure.
695 config RCU_BOOST_DELAY
696 int "Milliseconds to delay boosting after RCU grace-period start"
701 This option specifies the time to wait after the beginning of
702 a given grace period before priority-boosting preempted RCU
703 readers blocking that grace period. Note that any RCU reader
704 blocking an expedited RCU grace period is boosted immediately.
706 Accept the default if unsure.
709 bool "Offload RCU callback processing from boot-selected CPUs"
710 depends on TREE_RCU || PREEMPT_RCU
711 depends on RCU_EXPERT || NO_HZ_FULL
714 Use this option to reduce OS jitter for aggressive HPC or
715 real-time workloads. It can also be used to offload RCU
716 callback invocation to energy-efficient CPUs in battery-powered
717 asymmetric multiprocessors.
719 This option offloads callback invocation from the set of
720 CPUs specified at boot time by the rcu_nocbs parameter.
721 For each such CPU, a kthread ("rcuox/N") will be created to
722 invoke callbacks, where the "N" is the CPU being offloaded,
723 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
724 "s" for RCU-sched. Nothing prevents this kthread from running
725 on the specified CPUs, but (1) the kthreads may be preempted
726 between each callback, and (2) affinity or cgroups can be used
727 to force the kthreads to run on whatever set of CPUs is desired.
729 Say Y here if you want to help to debug reduced OS jitter.
730 Say N here if you are unsure.
733 prompt "Build-forced no-CBs CPUs"
734 default RCU_NOCB_CPU_NONE
735 depends on RCU_NOCB_CPU
737 This option allows no-CBs CPUs (whose RCU callbacks are invoked
738 from kthreads rather than from softirq context) to be specified
739 at build time. Additional no-CBs CPUs may be specified by
740 the rcu_nocbs= boot parameter.
742 config RCU_NOCB_CPU_NONE
743 bool "No build_forced no-CBs CPUs"
745 This option does not force any of the CPUs to be no-CBs CPUs.
746 Only CPUs designated by the rcu_nocbs= boot parameter will be
747 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
748 kthreads whose names begin with "rcuo". All other CPUs will
749 invoke their own RCU callbacks in softirq context.
751 Select this option if you want to choose no-CBs CPUs at
752 boot time, for example, to allow testing of different no-CBs
753 configurations without having to rebuild the kernel each time.
755 config RCU_NOCB_CPU_ZERO
756 bool "CPU 0 is a build_forced no-CBs CPU"
758 This option forces CPU 0 to be a no-CBs CPU, so that its RCU
759 callbacks are invoked by a per-CPU kthread whose name begins
760 with "rcuo". Additional CPUs may be designated as no-CBs
761 CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
762 All other CPUs will invoke their own RCU callbacks in softirq
765 Select this if CPU 0 needs to be a no-CBs CPU for real-time
766 or energy-efficiency reasons, but the real reason it exists
767 is to ensure that randconfig testing covers mixed systems.
769 config RCU_NOCB_CPU_ALL
770 bool "All CPUs are build_forced no-CBs CPUs"
772 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs=
773 boot parameter will be ignored. All CPUs' RCU callbacks will
774 be executed in the context of per-CPU rcuo kthreads created for
775 this purpose. Assuming that the kthreads whose names start with
776 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
777 on the remaining CPUs, but might decrease memory locality during
778 RCU-callback invocation, thus potentially degrading throughput.
780 Select this if all CPUs need to be no-CBs CPUs for real-time
781 or energy-efficiency reasons.
785 config RCU_EXPEDITE_BOOT
789 This option enables expedited grace periods at boot time,
790 as if rcu_expedite_gp() had been invoked early in boot.
791 The corresponding rcu_unexpedite_gp() is invoked from
792 rcu_end_inkernel_boot(), which is intended to be invoked
793 at the end of the kernel-only boot sequence, just before
796 Accept the default if unsure.
798 endmenu # "RCU Subsystem"
805 tristate "Kernel .config support"
808 This option enables the complete Linux kernel ".config" file
809 contents to be saved in the kernel. It provides documentation
810 of which kernel options are used in a running kernel or in an
811 on-disk kernel. This information can be extracted from the kernel
812 image file with the script scripts/extract-ikconfig and used as
813 input to rebuild the current kernel or to build another kernel.
814 It can also be extracted from a running kernel by reading
815 /proc/config.gz if enabled (below).
818 bool "Enable access to .config through /proc/config.gz"
819 depends on IKCONFIG && PROC_FS
821 This option enables access to the kernel configuration file
822 through /proc/config.gz.
825 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
830 Select the minimal kernel log buffer size as a power of 2.
831 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config
832 parameter, see below. Any higher size also might be forced
833 by "log_buf_len" boot parameter.
843 config LOG_CPU_MAX_BUF_SHIFT
844 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
847 default 12 if !BASE_SMALL
848 default 0 if BASE_SMALL
851 This option allows to increase the default ring buffer size
852 according to the number of CPUs. The value defines the contribution
853 of each CPU as a power of 2. The used space is typically only few
854 lines however it might be much more when problems are reported,
857 The increased size means that a new buffer has to be allocated and
858 the original static one is unused. It makes sense only on systems
859 with more CPUs. Therefore this value is used only when the sum of
860 contributions is greater than the half of the default kernel ring
861 buffer as defined by LOG_BUF_SHIFT. The default values are set
862 so that more than 64 CPUs are needed to trigger the allocation.
864 Also this option is ignored when "log_buf_len" kernel parameter is
865 used as it forces an exact (power of two) size of the ring buffer.
867 The number of possible CPUs is used for this computation ignoring
868 hotplugging making the compuation optimal for the the worst case
869 scenerio while allowing a simple algorithm to be used from bootup.
871 Examples shift values and their meaning:
872 17 => 128 KB for each CPU
873 16 => 64 KB for each CPU
874 15 => 32 KB for each CPU
875 14 => 16 KB for each CPU
876 13 => 8 KB for each CPU
877 12 => 4 KB for each CPU
880 # Architectures with an unreliable sched_clock() should select this:
882 config HAVE_UNSTABLE_SCHED_CLOCK
885 config GENERIC_SCHED_CLOCK
889 # For architectures that want to enable the support for NUMA-affine scheduler
892 config ARCH_SUPPORTS_NUMA_BALANCING
896 # For architectures that prefer to flush all TLBs after a number of pages
897 # are unmapped instead of sending one IPI per page to flush. The architecture
898 # must provide guarantees on what happens if a clean TLB cache entry is
899 # written after the unmap. Details are in mm/rmap.c near the check for
900 # should_defer_flush. The architecture should also consider if the full flush
901 # and the refill costs are offset by the savings of sending fewer IPIs.
902 config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
906 # For architectures that know their GCC __int128 support is sound
908 config ARCH_SUPPORTS_INT128
911 # For architectures that (ab)use NUMA to represent different memory regions
912 # all cpu-local but of different latencies, such as SuperH.
914 config ARCH_WANT_NUMA_VARIABLE_LOCALITY
917 config NUMA_BALANCING
918 bool "Memory placement aware NUMA scheduler"
919 depends on ARCH_SUPPORTS_NUMA_BALANCING
920 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
921 depends on SMP && NUMA && MIGRATION
923 This option adds support for automatic NUMA aware memory/task placement.
924 The mechanism is quite primitive and is based on migrating memory when
925 it has references to the node the task is running on.
927 This system will be inactive on UMA systems.
929 config NUMA_BALANCING_DEFAULT_ENABLED
930 bool "Automatically enable NUMA aware memory/task placement"
932 depends on NUMA_BALANCING
934 If set, automatic NUMA balancing will be enabled if running on a NUMA
938 bool "Control Group support"
941 This option adds support for grouping sets of processes together, for
942 use with process control subsystems such as Cpusets, CFS, memory
943 controls or device isolation.
945 - Documentation/scheduler/sched-design-CFS.txt (CFS)
946 - Documentation/cgroups/ (features for grouping, isolation
947 and resource control)
954 bool "Example debug cgroup subsystem"
957 This option enables a simple cgroup subsystem that
958 exports useful debugging information about the cgroups
963 config CGROUP_FREEZER
964 bool "Freezer cgroup subsystem"
966 Provides a way to freeze and unfreeze all tasks in a
970 bool "PIDs cgroup subsystem"
972 Provides enforcement of process number limits in the scope of a
973 cgroup. Any attempt to fork more processes than is allowed in the
974 cgroup will fail. PIDs are fundamentally a global resource because it
975 is fairly trivial to reach PID exhaustion before you reach even a
976 conservative kmemcg limit. As a result, it is possible to grind a
977 system to halt without being limited by other cgroup policies. The
978 PIDs cgroup subsystem is designed to stop this from happening.
980 It should be noted that organisational operations (such as attaching
981 to a cgroup hierarchy will *not* be blocked by the PIDs subsystem),
982 since the PIDs limit only affects a process's ability to fork, not to
986 bool "Device controller for cgroups"
988 Provides a cgroup implementing whitelists for devices which
989 a process in the cgroup can mknod or open.
992 bool "Cpuset support"
994 This option will let you create and manage CPUSETs which
995 allow dynamically partitioning a system into sets of CPUs and
996 Memory Nodes and assigning tasks to run only within those sets.
997 This is primarily useful on large SMP or NUMA systems.
1001 config PROC_PID_CPUSET
1002 bool "Include legacy /proc/<pid>/cpuset file"
1006 config CGROUP_CPUACCT
1007 bool "Simple CPU accounting cgroup subsystem"
1009 Provides a simple Resource Controller for monitoring the
1010 total CPU consumed by the tasks in a cgroup.
1016 bool "Memory Resource Controller for Control Groups"
1020 Provides a memory resource controller that manages both anonymous
1021 memory and page cache. (See Documentation/cgroups/memory.txt)
1024 bool "Memory Resource Controller Swap Extension"
1025 depends on MEMCG && SWAP
1027 Add swap management feature to memory resource controller. When you
1028 enable this, you can limit mem+swap usage per cgroup. In other words,
1029 when you disable this, memory resource controller has no cares to
1030 usage of swap...a process can exhaust all of the swap. This extension
1031 is useful when you want to avoid exhaustion swap but this itself
1032 adds more overheads and consumes memory for remembering information.
1033 Especially if you use 32bit system or small memory system, please
1034 be careful about enabling this. When memory resource controller
1035 is disabled by boot option, this will be automatically disabled and
1036 there will be no overhead from this. Even when you set this config=y,
1037 if boot option "swapaccount=0" is set, swap will not be accounted.
1038 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
1039 size is 4096bytes, 512k per 1Gbytes of swap.
1040 config MEMCG_SWAP_ENABLED
1041 bool "Memory Resource Controller Swap Extension enabled by default"
1042 depends on MEMCG_SWAP
1045 Memory Resource Controller Swap Extension comes with its price in
1046 a bigger memory consumption. General purpose distribution kernels
1047 which want to enable the feature but keep it disabled by default
1048 and let the user enable it by swapaccount=1 boot command line
1049 parameter should have this option unselected.
1050 For those who want to have the feature enabled by default should
1051 select this option (if, for some reason, they need to disable it
1052 then swapaccount=0 does the trick).
1054 bool "Memory Resource Controller Kernel Memory accounting"
1056 depends on SLUB || SLAB
1058 The Kernel Memory extension for Memory Resource Controller can limit
1059 the amount of memory used by kernel objects in the system. Those are
1060 fundamentally different from the entities handled by the standard
1061 Memory Controller, which are page-based, and can be swapped. Users of
1062 the kmem extension can use it to guarantee that no group of processes
1063 will ever exhaust kernel resources alone.
1065 config CGROUP_HUGETLB
1066 bool "HugeTLB Resource Controller for Control Groups"
1067 depends on HUGETLB_PAGE
1071 Provides a cgroup Resource Controller for HugeTLB pages.
1072 When you enable this, you can put a per cgroup limit on HugeTLB usage.
1073 The limit is enforced during page fault. Since HugeTLB doesn't
1074 support page reclaim, enforcing the limit at page fault time implies
1075 that, the application will get SIGBUS signal if it tries to access
1076 HugeTLB pages beyond its limit. This requires the application to know
1077 beforehand how much HugeTLB pages it would require for its use. The
1078 control group is tracked in the third page lru pointer. This means
1079 that we cannot use the controller with huge page less than 3 pages.
1082 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
1083 depends on PERF_EVENTS && CGROUPS
1085 This option extends the per-cpu mode to restrict monitoring to
1086 threads which belong to the cgroup specified and run on the
1091 menuconfig CGROUP_SCHED
1092 bool "Group CPU scheduler"
1095 This feature lets CPU scheduler recognize task groups and control CPU
1096 bandwidth allocation to such task groups. It uses cgroups to group
1100 config FAIR_GROUP_SCHED
1101 bool "Group scheduling for SCHED_OTHER"
1102 depends on CGROUP_SCHED
1103 default CGROUP_SCHED
1105 config CFS_BANDWIDTH
1106 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
1107 depends on FAIR_GROUP_SCHED
1110 This option allows users to define CPU bandwidth rates (limits) for
1111 tasks running within the fair group scheduler. Groups with no limit
1112 set are considered to be unconstrained and will run with no
1114 See tip/Documentation/scheduler/sched-bwc.txt for more information.
1116 config RT_GROUP_SCHED
1117 bool "Group scheduling for SCHED_RR/FIFO"
1118 depends on CGROUP_SCHED
1121 This feature lets you explicitly allocate real CPU bandwidth
1122 to task groups. If enabled, it will also make it impossible to
1123 schedule realtime tasks for non-root users until you allocate
1124 realtime bandwidth for them.
1125 See Documentation/scheduler/sched-rt-group.txt for more information.
1130 bool "Block IO controller"
1134 Generic block IO controller cgroup interface. This is the common
1135 cgroup interface which should be used by various IO controlling
1138 Currently, CFQ IO scheduler uses it to recognize task groups and
1139 control disk bandwidth allocation (proportional time slice allocation)
1140 to such task groups. It is also used by bio throttling logic in
1141 block layer to implement upper limit in IO rates on a device.
1143 This option only enables generic Block IO controller infrastructure.
1144 One needs to also enable actual IO controlling logic/policy. For
1145 enabling proportional weight division of disk bandwidth in CFQ, set
1146 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
1147 CONFIG_BLK_DEV_THROTTLING=y.
1149 See Documentation/cgroups/blkio-controller.txt for more information.
1151 config DEBUG_BLK_CGROUP
1152 bool "Enable Block IO controller debugging"
1153 depends on BLK_CGROUP
1156 Enable some debugging help. Currently it exports additional stat
1157 files in a cgroup which can be useful for debugging.
1159 config CGROUP_WRITEBACK
1161 depends on MEMCG && BLK_CGROUP
1166 config CHECKPOINT_RESTORE
1167 bool "Checkpoint/restore support" if EXPERT
1168 select PROC_CHILDREN
1171 Enables additional kernel features in a sake of checkpoint/restore.
1172 In particular it adds auxiliary prctl codes to setup process text,
1173 data and heap segment sizes, and a few additional /proc filesystem
1176 If unsure, say N here.
1178 menuconfig NAMESPACES
1179 bool "Namespaces support" if EXPERT
1180 depends on MULTIUSER
1183 Provides the way to make tasks work with different objects using
1184 the same id. For example same IPC id may refer to different objects
1185 or same user id or pid may refer to different tasks when used in
1186 different namespaces.
1191 bool "UTS namespace"
1194 In this namespace tasks see different info provided with the
1198 bool "IPC namespace"
1199 depends on (SYSVIPC || POSIX_MQUEUE)
1202 In this namespace tasks work with IPC ids which correspond to
1203 different IPC objects in different namespaces.
1206 bool "User namespace"
1209 This allows containers, i.e. vservers, to use user namespaces
1210 to provide different user info for different servers.
1212 When user namespaces are enabled in the kernel it is
1213 recommended that the MEMCG and MEMCG_KMEM options also be
1214 enabled and that user-space use the memory control groups to
1215 limit the amount of memory a memory unprivileged users can
1221 bool "PID Namespaces"
1224 Support process id namespaces. This allows having multiple
1225 processes with the same pid as long as they are in different
1226 pid namespaces. This is a building block of containers.
1229 bool "Network namespace"
1233 Allow user space to create what appear to be multiple instances
1234 of the network stack.
1238 config SCHED_AUTOGROUP
1239 bool "Automatic process group scheduling"
1242 select FAIR_GROUP_SCHED
1244 This option optimizes the scheduler for common desktop workloads by
1245 automatically creating and populating task groups. This separation
1246 of workloads isolates aggressive CPU burners (like build jobs) from
1247 desktop applications. Task group autogeneration is currently based
1250 config SYSFS_DEPRECATED
1251 bool "Enable deprecated sysfs features to support old userspace tools"
1255 This option adds code that switches the layout of the "block" class
1256 devices, to not show up in /sys/class/block/, but only in
1259 This switch is only active when the sysfs.deprecated=1 boot option is
1260 passed or the SYSFS_DEPRECATED_V2 option is set.
1262 This option allows new kernels to run on old distributions and tools,
1263 which might get confused by /sys/class/block/. Since 2007/2008 all
1264 major distributions and tools handle this just fine.
1266 Recent distributions and userspace tools after 2009/2010 depend on
1267 the existence of /sys/class/block/, and will not work with this
1270 Only if you are using a new kernel on an old distribution, you might
1273 config SYSFS_DEPRECATED_V2
1274 bool "Enable deprecated sysfs features by default"
1277 depends on SYSFS_DEPRECATED
1279 Enable deprecated sysfs by default.
1281 See the CONFIG_SYSFS_DEPRECATED option for more details about this
1284 Only if you are using a new kernel on an old distribution, you might
1285 need to say Y here. Even then, odds are you would not need it
1286 enabled, you can always pass the boot option if absolutely necessary.
1289 bool "Kernel->user space relay support (formerly relayfs)"
1291 This option enables support for relay interface support in
1292 certain file systems (such as debugfs).
1293 It is designed to provide an efficient mechanism for tools and
1294 facilities to relay large amounts of data from kernel space to
1299 config BLK_DEV_INITRD
1300 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
1301 depends on BROKEN || !FRV
1303 The initial RAM filesystem is a ramfs which is loaded by the
1304 boot loader (loadlin or lilo) and that is mounted as root
1305 before the normal boot procedure. It is typically used to
1306 load modules needed to mount the "real" root file system,
1307 etc. See <file:Documentation/initrd.txt> for details.
1309 If RAM disk support (BLK_DEV_RAM) is also included, this
1310 also enables initial RAM disk (initrd) support and adds
1311 15 Kbytes (more on some other architectures) to the kernel size.
1317 source "usr/Kconfig"
1322 prompt "Compiler optimization level"
1323 default CONFIG_CC_OPTIMIZE_FOR_PERFORMANCE
1325 config CC_OPTIMIZE_FOR_PERFORMANCE
1326 bool "Optimize for performance"
1328 This is the default optimization level for the kernel, building
1329 with the "-O2" compiler flag for best performance and most
1330 helpful compile-time warnings.
1332 config CC_OPTIMIZE_FOR_SIZE
1333 bool "Optimize for size"
1335 Enabling this option will pass "-Os" instead of "-O2" to
1336 your compiler resulting in a smaller kernel.
1351 config SYSCTL_EXCEPTION_TRACE
1354 Enable support for /proc/sys/debug/exception-trace.
1356 config SYSCTL_ARCH_UNALIGN_NO_WARN
1359 Enable support for /proc/sys/kernel/ignore-unaligned-usertrap
1360 Allows arch to define/use @no_unaligned_warning to possibly warn
1361 about unaligned access emulation going on under the hood.
1363 config SYSCTL_ARCH_UNALIGN_ALLOW
1366 Enable support for /proc/sys/kernel/unaligned-trap
1367 Allows arches to define/use @unaligned_enabled to runtime toggle
1368 the unaligned access emulation.
1369 see arch/parisc/kernel/unaligned.c for reference
1371 config HAVE_PCSPKR_PLATFORM
1374 # interpreter that classic socket filters depend on
1379 bool "Configure standard kernel features (expert users)"
1380 # Unhide debug options, to make the on-by-default options visible
1383 This option allows certain base kernel options and settings
1384 to be disabled or tweaked. This is for specialized
1385 environments which can tolerate a "non-standard" kernel.
1386 Only use this if you really know what you are doing.
1389 bool "Enable 16-bit UID system calls" if EXPERT
1390 depends on HAVE_UID16 && MULTIUSER
1393 This enables the legacy 16-bit UID syscall wrappers.
1396 bool "Multiple users, groups and capabilities support" if EXPERT
1399 This option enables support for non-root users, groups and
1402 If you say N here, all processes will run with UID 0, GID 0, and all
1403 possible capabilities. Saying N here also compiles out support for
1404 system calls related to UIDs, GIDs, and capabilities, such as setuid,
1407 If unsure, say Y here.
1409 config SGETMASK_SYSCALL
1410 bool "sgetmask/ssetmask syscalls support" if EXPERT
1411 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH
1413 sys_sgetmask and sys_ssetmask are obsolete system calls
1414 no longer supported in libc but still enabled by default in some
1417 If unsure, leave the default option here.
1419 config SYSFS_SYSCALL
1420 bool "Sysfs syscall support" if EXPERT
1423 sys_sysfs is an obsolete system call no longer supported in libc.
1424 Note that disabling this option is more secure but might break
1425 compatibility with some systems.
1427 If unsure say Y here.
1429 config SYSCTL_SYSCALL
1430 bool "Sysctl syscall support" if EXPERT
1431 depends on PROC_SYSCTL
1435 sys_sysctl uses binary paths that have been found challenging
1436 to properly maintain and use. The interface in /proc/sys
1437 using paths with ascii names is now the primary path to this
1440 Almost nothing using the binary sysctl interface so if you are
1441 trying to save some space it is probably safe to disable this,
1442 making your kernel marginally smaller.
1444 If unsure say N here.
1447 bool "Load all symbols for debugging/ksymoops" if EXPERT
1450 Say Y here to let the kernel print out symbolic crash information and
1451 symbolic stack backtraces. This increases the size of the kernel
1452 somewhat, as all symbols have to be loaded into the kernel image.
1455 bool "Include all symbols in kallsyms"
1456 depends on DEBUG_KERNEL && KALLSYMS
1458 Normally kallsyms only contains the symbols of functions for nicer
1459 OOPS messages and backtraces (i.e., symbols from the text and inittext
1460 sections). This is sufficient for most cases. And only in very rare
1461 cases (e.g., when a debugger is used) all symbols are required (e.g.,
1462 names of variables from the data sections, etc).
1464 This option makes sure that all symbols are loaded into the kernel
1465 image (i.e., symbols from all sections) in cost of increased kernel
1466 size (depending on the kernel configuration, it may be 300KiB or
1467 something like this).
1469 Say N unless you really need all symbols.
1473 bool "Enable support for printk" if EXPERT
1476 This option enables normal printk support. Removing it
1477 eliminates most of the message strings from the kernel image
1478 and makes the kernel more or less silent. As this makes it
1479 very difficult to diagnose system problems, saying N here is
1480 strongly discouraged.
1483 bool "BUG() support" if EXPERT
1486 Disabling this option eliminates support for BUG and WARN, reducing
1487 the size of your kernel image and potentially quietly ignoring
1488 numerous fatal conditions. You should only consider disabling this
1489 option for embedded systems with no facilities for reporting errors.
1495 bool "Enable ELF core dumps" if EXPERT
1497 Enable support for generating core dumps. Disabling saves about 4k.
1500 config PCSPKR_PLATFORM
1501 bool "Enable PC-Speaker support" if EXPERT
1502 depends on HAVE_PCSPKR_PLATFORM
1506 This option allows to disable the internal PC-Speaker
1507 support, saving some memory.
1511 bool "Enable full-sized data structures for core" if EXPERT
1513 Disabling this option reduces the size of miscellaneous core
1514 kernel data structures. This saves memory on small machines,
1515 but may reduce performance.
1518 bool "Enable futex support" if EXPERT
1522 Disabling this option will cause the kernel to be built without
1523 support for "fast userspace mutexes". The resulting kernel may not
1524 run glibc-based applications correctly.
1526 config HAVE_FUTEX_CMPXCHG
1530 Architectures should select this if futex_atomic_cmpxchg_inatomic()
1531 is implemented and always working. This removes a couple of runtime
1535 bool "Enable eventpoll support" if EXPERT
1539 Disabling this option will cause the kernel to be built without
1540 support for epoll family of system calls.
1543 bool "Enable signalfd() system call" if EXPERT
1547 Enable the signalfd() system call that allows to receive signals
1548 on a file descriptor.
1553 bool "Enable timerfd() system call" if EXPERT
1557 Enable the timerfd() system call that allows to receive timer
1558 events on a file descriptor.
1563 bool "Enable eventfd() system call" if EXPERT
1567 Enable the eventfd() system call that allows to receive both
1568 kernel notification (ie. KAIO) or userspace notifications.
1572 # syscall, maps, verifier
1574 bool "Enable bpf() system call"
1579 Enable the bpf() system call that allows to manipulate eBPF
1580 programs and maps via file descriptors.
1582 config BPF_JIT_ALWAYS_ON
1583 bool "Permanently enable BPF JIT and remove BPF interpreter"
1584 depends on BPF_SYSCALL && HAVE_EBPF_JIT && BPF_JIT
1586 Enables BPF JIT and removes BPF interpreter to avoid
1587 speculative execution of BPF instructions by the interpreter
1590 bool "Use full shmem filesystem" if EXPERT
1594 The shmem is an internal filesystem used to manage shared memory.
1595 It is backed by swap and manages resource limits. It is also exported
1596 to userspace as tmpfs if TMPFS is enabled. Disabling this
1597 option replaces shmem and tmpfs with the much simpler ramfs code,
1598 which may be appropriate on small systems without swap.
1601 bool "Enable AIO support" if EXPERT
1604 This option enables POSIX asynchronous I/O which may by used
1605 by some high performance threaded applications. Disabling
1606 this option saves about 7k.
1608 config ADVISE_SYSCALLS
1609 bool "Enable madvise/fadvise syscalls" if EXPERT
1612 This option enables the madvise and fadvise syscalls, used by
1613 applications to advise the kernel about their future memory or file
1614 usage, improving performance. If building an embedded system where no
1615 applications use these syscalls, you can disable this option to save
1619 bool "Enable userfaultfd() system call"
1623 Enable the userfaultfd() system call that allows to intercept and
1624 handle page faults in userland.
1628 bool "Enable PCI quirk workarounds" if EXPERT
1631 This enables workarounds for various PCI chipset
1632 bugs/quirks. Disable this only if your target machine is
1633 unaffected by PCI quirks.
1636 bool "Enable membarrier() system call" if EXPERT
1639 Enable the membarrier() system call that allows issuing memory
1640 barriers across all running threads, which can be used to distribute
1641 the cost of user-space memory barriers asymmetrically by transforming
1642 pairs of memory barriers into pairs consisting of membarrier() and a
1648 bool "Embedded system"
1649 option allnoconfig_y
1652 This option should be enabled if compiling the kernel for
1653 an embedded system so certain expert options are available
1656 config HAVE_PERF_EVENTS
1659 See tools/perf/design.txt for details.
1661 config PERF_USE_VMALLOC
1664 See tools/perf/design.txt for details
1666 menu "Kernel Performance Events And Counters"
1669 bool "Kernel performance events and counters"
1670 default y if PROFILING
1671 depends on HAVE_PERF_EVENTS
1676 Enable kernel support for various performance events provided
1677 by software and hardware.
1679 Software events are supported either built-in or via the
1680 use of generic tracepoints.
1682 Most modern CPUs support performance events via performance
1683 counter registers. These registers count the number of certain
1684 types of hw events: such as instructions executed, cachemisses
1685 suffered, or branches mis-predicted - without slowing down the
1686 kernel or applications. These registers can also trigger interrupts
1687 when a threshold number of events have passed - and can thus be
1688 used to profile the code that runs on that CPU.
1690 The Linux Performance Event subsystem provides an abstraction of
1691 these software and hardware event capabilities, available via a
1692 system call and used by the "perf" utility in tools/perf/. It
1693 provides per task and per CPU counters, and it provides event
1694 capabilities on top of those.
1698 config DEBUG_PERF_USE_VMALLOC
1700 bool "Debug: use vmalloc to back perf mmap() buffers"
1701 depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
1702 select PERF_USE_VMALLOC
1704 Use vmalloc memory to back perf mmap() buffers.
1706 Mostly useful for debugging the vmalloc code on platforms
1707 that don't require it.
1713 config VM_EVENT_COUNTERS
1715 bool "Enable VM event counters for /proc/vmstat" if EXPERT
1717 VM event counters are needed for event counts to be shown.
1718 This option allows the disabling of the VM event counters
1719 on EXPERT systems. /proc/vmstat will only show page counts
1720 if VM event counters are disabled.
1724 bool "Enable SLUB debugging support" if EXPERT
1725 depends on SLUB && SYSFS
1727 SLUB has extensive debug support features. Disabling these can
1728 result in significant savings in code size. This also disables
1729 SLUB sysfs support. /sys/slab will not exist and there will be
1730 no support for cache validation etc.
1733 bool "Disable heap randomization"
1736 Randomizing heap placement makes heap exploits harder, but it
1737 also breaks ancient binaries (including anything libc5 based).
1738 This option changes the bootup default to heap randomization
1739 disabled, and can be overridden at runtime by setting
1740 /proc/sys/kernel/randomize_va_space to 2.
1742 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1745 prompt "Choose SLAB allocator"
1748 This option allows to select a slab allocator.
1753 The regular slab allocator that is established and known to work
1754 well in all environments. It organizes cache hot objects in
1755 per cpu and per node queues.
1758 bool "SLUB (Unqueued Allocator)"
1760 SLUB is a slab allocator that minimizes cache line usage
1761 instead of managing queues of cached objects (SLAB approach).
1762 Per cpu caching is realized using slabs of objects instead
1763 of queues of objects. SLUB can use memory efficiently
1764 and has enhanced diagnostics. SLUB is the default choice for
1769 bool "SLOB (Simple Allocator)"
1771 SLOB replaces the stock allocator with a drastically simpler
1772 allocator. SLOB is generally more space efficient but
1773 does not perform as well on large systems.
1777 config SLUB_CPU_PARTIAL
1779 depends on SLUB && SMP
1780 bool "SLUB per cpu partial cache"
1782 Per cpu partial caches accellerate objects allocation and freeing
1783 that is local to a processor at the price of more indeterminism
1784 in the latency of the free. On overflow these caches will be cleared
1785 which requires the taking of locks that may cause latency spikes.
1786 Typically one would choose no for a realtime system.
1788 config MMAP_ALLOW_UNINITIALIZED
1789 bool "Allow mmapped anonymous memory to be uninitialized"
1790 depends on EXPERT && !MMU
1793 Normally, and according to the Linux spec, anonymous memory obtained
1794 from mmap() has it's contents cleared before it is passed to
1795 userspace. Enabling this config option allows you to request that
1796 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
1797 providing a huge performance boost. If this option is not enabled,
1798 then the flag will be ignored.
1800 This is taken advantage of by uClibc's malloc(), and also by
1801 ELF-FDPIC binfmt's brk and stack allocator.
1803 Because of the obvious security issues, this option should only be
1804 enabled on embedded devices where you control what is run in
1805 userspace. Since that isn't generally a problem on no-MMU systems,
1806 it is normally safe to say Y here.
1808 See Documentation/nommu-mmap.txt for more information.
1810 config SYSTEM_DATA_VERIFICATION
1812 select SYSTEM_TRUSTED_KEYRING
1815 select ASYMMETRIC_KEY_TYPE
1816 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
1817 select PUBLIC_KEY_ALGO_RSA
1820 select X509_CERTIFICATE_PARSER
1821 select PKCS7_MESSAGE_PARSER
1823 Provide PKCS#7 message verification using the contents of the system
1824 trusted keyring to provide public keys. This then can be used for
1825 module verification, kexec image verification and firmware blob
1829 bool "Profiling support"
1831 Say Y here to enable the extended profiling support mechanisms used
1832 by profilers such as OProfile.
1835 # Place an empty function call at each tracepoint site. Can be
1836 # dynamically changed for a probe function.
1841 source "arch/Kconfig"
1843 endmenu # General setup
1845 config HAVE_GENERIC_DMA_COHERENT
1852 depends on SLAB || SLUB_DEBUG
1860 default 0 if BASE_FULL
1861 default 1 if !BASE_FULL
1864 bool "Enable loadable module support"
1867 Kernel modules are small pieces of compiled code which can
1868 be inserted in the running kernel, rather than being
1869 permanently built into the kernel. You use the "modprobe"
1870 tool to add (and sometimes remove) them. If you say Y here,
1871 many parts of the kernel can be built as modules (by
1872 answering M instead of Y where indicated): this is most
1873 useful for infrequently used options which are not required
1874 for booting. For more information, see the man pages for
1875 modprobe, lsmod, modinfo, insmod and rmmod.
1877 If you say Y here, you will need to run "make
1878 modules_install" to put the modules under /lib/modules/
1879 where modprobe can find them (you may need to be root to do
1886 config MODULE_FORCE_LOAD
1887 bool "Forced module loading"
1890 Allow loading of modules without version information (ie. modprobe
1891 --force). Forced module loading sets the 'F' (forced) taint flag and
1892 is usually a really bad idea.
1894 config MODULE_UNLOAD
1895 bool "Module unloading"
1897 Without this option you will not be able to unload any
1898 modules (note that some modules may not be unloadable
1899 anyway), which makes your kernel smaller, faster
1900 and simpler. If unsure, say Y.
1902 config MODULE_FORCE_UNLOAD
1903 bool "Forced module unloading"
1904 depends on MODULE_UNLOAD
1906 This option allows you to force a module to unload, even if the
1907 kernel believes it is unsafe: the kernel will remove the module
1908 without waiting for anyone to stop using it (using the -f option to
1909 rmmod). This is mainly for kernel developers and desperate users.
1913 bool "Module versioning support"
1915 Usually, you have to use modules compiled with your kernel.
1916 Saying Y here makes it sometimes possible to use modules
1917 compiled for different kernels, by adding enough information
1918 to the modules to (hopefully) spot any changes which would
1919 make them incompatible with the kernel you are running. If
1922 config MODULE_SRCVERSION_ALL
1923 bool "Source checksum for all modules"
1925 Modules which contain a MODULE_VERSION get an extra "srcversion"
1926 field inserted into their modinfo section, which contains a
1927 sum of the source files which made it. This helps maintainers
1928 see exactly which source was used to build a module (since
1929 others sometimes change the module source without updating
1930 the version). With this option, such a "srcversion" field
1931 will be created for all modules. If unsure, say N.
1934 bool "Module signature verification"
1936 select SYSTEM_DATA_VERIFICATION
1938 Check modules for valid signatures upon load: the signature
1939 is simply appended to the module. For more information see
1940 Documentation/module-signing.txt.
1942 Note that this option adds the OpenSSL development packages as a
1943 kernel build dependency so that the signing tool can use its crypto
1946 !!!WARNING!!! If you enable this option, you MUST make sure that the
1947 module DOES NOT get stripped after being signed. This includes the
1948 debuginfo strip done by some packagers (such as rpmbuild) and
1949 inclusion into an initramfs that wants the module size reduced.
1951 config MODULE_SIG_FORCE
1952 bool "Require modules to be validly signed"
1953 depends on MODULE_SIG
1955 Reject unsigned modules or signed modules for which we don't have a
1956 key. Without this, such modules will simply taint the kernel.
1958 config MODULE_SIG_ALL
1959 bool "Automatically sign all modules"
1961 depends on MODULE_SIG
1963 Sign all modules during make modules_install. Without this option,
1964 modules must be signed manually, using the scripts/sign-file tool.
1966 comment "Do not forget to sign required modules with scripts/sign-file"
1967 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
1970 prompt "Which hash algorithm should modules be signed with?"
1971 depends on MODULE_SIG
1973 This determines which sort of hashing algorithm will be used during
1974 signature generation. This algorithm _must_ be built into the kernel
1975 directly so that signature verification can take place. It is not
1976 possible to load a signed module containing the algorithm to check
1977 the signature on that module.
1979 config MODULE_SIG_SHA1
1980 bool "Sign modules with SHA-1"
1983 config MODULE_SIG_SHA224
1984 bool "Sign modules with SHA-224"
1985 select CRYPTO_SHA256
1987 config MODULE_SIG_SHA256
1988 bool "Sign modules with SHA-256"
1989 select CRYPTO_SHA256
1991 config MODULE_SIG_SHA384
1992 bool "Sign modules with SHA-384"
1993 select CRYPTO_SHA512
1995 config MODULE_SIG_SHA512
1996 bool "Sign modules with SHA-512"
1997 select CRYPTO_SHA512
2001 config MODULE_SIG_HASH
2003 depends on MODULE_SIG
2004 default "sha1" if MODULE_SIG_SHA1
2005 default "sha224" if MODULE_SIG_SHA224
2006 default "sha256" if MODULE_SIG_SHA256
2007 default "sha384" if MODULE_SIG_SHA384
2008 default "sha512" if MODULE_SIG_SHA512
2010 config MODULE_COMPRESS
2011 bool "Compress modules on installation"
2015 Compresses kernel modules when 'make modules_install' is run; gzip or
2016 xz depending on "Compression algorithm" below.
2018 module-init-tools MAY support gzip, and kmod MAY support gzip and xz.
2020 Out-of-tree kernel modules installed using Kbuild will also be
2021 compressed upon installation.
2023 Note: for modules inside an initrd or initramfs, it's more efficient
2024 to compress the whole initrd or initramfs instead.
2026 Note: This is fully compatible with signed modules.
2031 prompt "Compression algorithm"
2032 depends on MODULE_COMPRESS
2033 default MODULE_COMPRESS_GZIP
2035 This determines which sort of compression will be used during
2036 'make modules_install'.
2038 GZIP (default) and XZ are supported.
2040 config MODULE_COMPRESS_GZIP
2043 config MODULE_COMPRESS_XZ
2050 config MODULES_TREE_LOOKUP
2052 depends on PERF_EVENTS || TRACING
2054 config INIT_ALL_POSSIBLE
2057 Back when each arch used to define their own cpu_online_mask and
2058 cpu_possible_mask, some of them chose to initialize cpu_possible_mask
2059 with all 1s, and others with all 0s. When they were centralised,
2060 it was better to provide this option than to break all the archs
2061 and have several arch maintainers pursuing me down dark alleys.
2063 source "block/Kconfig"
2065 config PREEMPT_NOTIFIERS
2072 # Can be selected by architectures with broken toolchains
2073 # that get confused by correct const<->read_only section
2075 config BROKEN_RODATA
2081 Build a simple ASN.1 grammar compiler that produces a bytecode output
2082 that can be interpreted by the ASN.1 stream decoder and used to
2083 inform it as to what tags are to be expected in a stream and what
2084 functions to call on what tags.
2086 source "kernel/Kconfig.locks"