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
36 depends on BROKEN || !SMP
39 config INIT_ENV_ARG_LIMIT
44 Maximum of each of the number of arguments and environment
45 variables passed to init from the kernel command line.
49 string "Cross-compiler tool prefix"
51 Same as running 'make CROSS_COMPILE=prefix-' but stored for
52 default make runs in this kernel build directory. You don't
53 need to set this unless you want the configured kernel build
54 directory to select the cross-compiler automatically.
57 bool "Compile also drivers which will not load"
60 Some drivers can be compiled on a different platform than they are
61 intended to be run on. Despite they cannot be loaded there (or even
62 when they load they cannot be used due to missing HW support),
63 developers still, opposing to distributors, might want to build such
64 drivers to compile-test them.
66 If you are a developer and want to build everything available, say Y
67 here. If you are a user/distributor, say N here to exclude useless
68 drivers to be distributed.
71 string "Local version - append to kernel release"
73 Append an extra string to the end of your kernel version.
74 This will show up when you type uname, for example.
75 The string you set here will be appended after the contents of
76 any files with a filename matching localversion* in your
77 object and source tree, in that order. Your total string can
78 be a maximum of 64 characters.
80 config LOCALVERSION_AUTO
81 bool "Automatically append version information to the version string"
84 This will try to automatically determine if the current tree is a
85 release tree by looking for git tags that belong to the current
88 A string of the format -gxxxxxxxx will be added to the localversion
89 if a git-based tree is found. The string generated by this will be
90 appended after any matching localversion* files, and after the value
91 set in CONFIG_LOCALVERSION.
93 (The actual string used here is the first eight characters produced
94 by running the command:
96 $ git rev-parse --verify HEAD
98 which is done within the script "scripts/setlocalversion".)
100 config HAVE_KERNEL_GZIP
103 config HAVE_KERNEL_BZIP2
106 config HAVE_KERNEL_LZMA
109 config HAVE_KERNEL_XZ
112 config HAVE_KERNEL_LZO
115 config HAVE_KERNEL_LZ4
119 prompt "Kernel compression mode"
121 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
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. It provides a good balance
145 between compression ratio and decompression speed.
149 depends on HAVE_KERNEL_BZIP2
151 Its compression ratio and speed is intermediate.
152 Decompression speed is slowest among the choices. The kernel
153 size is about 10% smaller with bzip2, in comparison to gzip.
154 Bzip2 uses a large amount of memory. For modern kernels you
155 will need at least 8MB RAM or more for booting.
159 depends on HAVE_KERNEL_LZMA
161 This compression algorithm's ratio is best. Decompression speed
162 is between gzip and bzip2. Compression is slowest.
163 The kernel size is about 33% smaller with LZMA in comparison to gzip.
167 depends on HAVE_KERNEL_XZ
169 XZ uses the LZMA2 algorithm and instruction set specific
170 BCJ filters which can improve compression ratio of executable
171 code. The size of the kernel is about 30% smaller with XZ in
172 comparison to gzip. On architectures for which there is a BCJ
173 filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ
174 will create a few percent smaller kernel than plain LZMA.
176 The speed is about the same as with LZMA: The decompression
177 speed of XZ is better than that of bzip2 but worse than gzip
178 and LZO. Compression is slow.
182 depends on HAVE_KERNEL_LZO
184 Its compression ratio is the poorest among the choices. The kernel
185 size is about 10% bigger than gzip; however its speed
186 (both compression and decompression) is the fastest.
190 depends on HAVE_KERNEL_LZ4
192 LZ4 is an LZ77-type compressor with a fixed, byte-oriented encoding.
193 A preliminary version of LZ4 de/compression tool is available at
194 <https://code.google.com/p/lz4/>.
196 Its compression ratio is worse than LZO. The size of the kernel
197 is about 8% bigger than LZO. But the decompression speed is
202 config DEFAULT_HOSTNAME
203 string "Default hostname"
206 This option determines the default system hostname before userspace
207 calls sethostname(2). The kernel traditionally uses "(none)" here,
208 but you may wish to use a different default here to make a minimal
209 system more usable with less configuration.
212 bool "Support for paging of anonymous memory (swap)"
213 depends on MMU && BLOCK
216 This option allows you to choose whether you want to have support
217 for so called swap devices or swap files in your kernel that are
218 used to provide more virtual memory than the actual RAM present
219 in your computer. If unsure say Y.
224 Inter Process Communication is a suite of library functions and
225 system calls which let processes (running programs) synchronize and
226 exchange information. It is generally considered to be a good thing,
227 and some programs won't run unless you say Y here. In particular, if
228 you want to run the DOS emulator dosemu under Linux (read the
229 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>),
230 you'll need to say Y here.
232 You can find documentation about IPC with "info ipc" and also in
233 section 6.4 of the Linux Programmer's Guide, available from
234 <http://www.tldp.org/guides.html>.
236 config SYSVIPC_SYSCTL
243 bool "POSIX Message Queues"
246 POSIX variant of message queues is a part of IPC. In POSIX message
247 queues every message has a priority which decides about succession
248 of receiving it by a process. If you want to compile and run
249 programs written e.g. for Solaris with use of its POSIX message
250 queues (functions mq_*) say Y here.
252 POSIX message queues are visible as a filesystem called 'mqueue'
253 and can be mounted somewhere if you want to do filesystem
254 operations on message queues.
258 config POSIX_MQUEUE_SYSCTL
260 depends on POSIX_MQUEUE
264 config CROSS_MEMORY_ATTACH
265 bool "Enable process_vm_readv/writev syscalls"
269 Enabling this option adds the system calls process_vm_readv and
270 process_vm_writev which allow a process with the correct privileges
271 to directly read from or write to another process' address space.
272 See the man page for more details.
275 bool "open by fhandle syscalls"
278 If you say Y here, a user level program will be able to map
279 file names to handle and then later use the handle for
280 different file system operations. This is useful in implementing
281 userspace file servers, which now track files using handles instead
282 of names. The handle would remain the same even if file names
283 get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2)
287 bool "uselib syscall"
290 This option enables the uselib syscall, a system call used in the
291 dynamic linker from libc5 and earlier. glibc does not use this
292 system call. If you intend to run programs built on libc5 or
293 earlier, you may need to enable this syscall. Current systems
294 running glibc can safely disable this.
297 bool "Auditing support"
300 Enable auditing infrastructure that can be used with another
301 kernel subsystem, such as SELinux (which requires this for
302 logging of avc messages output). Does not do system-call
303 auditing without CONFIG_AUDITSYSCALL.
305 config HAVE_ARCH_AUDITSYSCALL
309 bool "Enable system-call auditing support"
310 depends on AUDIT && HAVE_ARCH_AUDITSYSCALL
311 default y if SECURITY_SELINUX
313 Enable low-overhead system-call auditing infrastructure that
314 can be used independently or with another kernel subsystem,
319 depends on AUDITSYSCALL
324 depends on AUDITSYSCALL
327 source "kernel/irq/Kconfig"
328 source "kernel/time/Kconfig"
330 menu "CPU/Task time and stats accounting"
332 config VIRT_CPU_ACCOUNTING
336 prompt "Cputime accounting"
337 default TICK_CPU_ACCOUNTING if !PPC64
338 default VIRT_CPU_ACCOUNTING_NATIVE if PPC64
340 # Kind of a stub config for the pure tick based cputime accounting
341 config TICK_CPU_ACCOUNTING
342 bool "Simple tick based cputime accounting"
343 depends on !S390 && !NO_HZ_FULL
345 This is the basic tick based cputime accounting that maintains
346 statistics about user, system and idle time spent on per jiffies
351 config VIRT_CPU_ACCOUNTING_NATIVE
352 bool "Deterministic task and CPU time accounting"
353 depends on HAVE_VIRT_CPU_ACCOUNTING && !NO_HZ_FULL
354 select VIRT_CPU_ACCOUNTING
356 Select this option to enable more accurate task and CPU time
357 accounting. This is done by reading a CPU counter on each
358 kernel entry and exit and on transitions within the kernel
359 between system, softirq and hardirq state, so there is a
360 small performance impact. In the case of s390 or IBM POWER > 5,
361 this also enables accounting of stolen time on logically-partitioned
364 config VIRT_CPU_ACCOUNTING_GEN
365 bool "Full dynticks CPU time accounting"
366 depends on HAVE_CONTEXT_TRACKING
367 depends on HAVE_VIRT_CPU_ACCOUNTING_GEN
368 select VIRT_CPU_ACCOUNTING
369 select CONTEXT_TRACKING
371 Select this option to enable task and CPU time accounting on full
372 dynticks systems. This accounting is implemented by watching every
373 kernel-user boundaries using the context tracking subsystem.
374 The accounting is thus performed at the expense of some significant
377 For now this is only useful if you are working on the full
378 dynticks subsystem development.
382 config IRQ_TIME_ACCOUNTING
383 bool "Fine granularity task level IRQ time accounting"
384 depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL
386 Select this option to enable fine granularity task irq time
387 accounting. This is done by reading a timestamp on each
388 transitions between softirq and hardirq state, so there can be a
389 small performance impact.
391 If in doubt, say N here.
396 bool "Support window based load tracking"
399 This feature will allow the scheduler to maintain a tunable window
400 based set of metrics for tasks and runqueues. These metrics can be
401 used to guide task placement as well as task frequency requirements
402 for cpufreq governors.
404 config BSD_PROCESS_ACCT
405 bool "BSD Process Accounting"
408 If you say Y here, a user level program will be able to instruct the
409 kernel (via a special system call) to write process accounting
410 information to a file: whenever a process exits, information about
411 that process will be appended to the file by the kernel. The
412 information includes things such as creation time, owning user,
413 command name, memory usage, controlling terminal etc. (the complete
414 list is in the struct acct in <file:include/linux/acct.h>). It is
415 up to the user level program to do useful things with this
416 information. This is generally a good idea, so say Y.
418 config BSD_PROCESS_ACCT_V3
419 bool "BSD Process Accounting version 3 file format"
420 depends on BSD_PROCESS_ACCT
423 If you say Y here, the process accounting information is written
424 in a new file format that also logs the process IDs of each
425 process and it's parent. Note that this file format is incompatible
426 with previous v0/v1/v2 file formats, so you will need updated tools
427 for processing it. A preliminary version of these tools is available
428 at <http://www.gnu.org/software/acct/>.
431 bool "Export task/process statistics through netlink"
436 Export selected statistics for tasks/processes through the
437 generic netlink interface. Unlike BSD process accounting, the
438 statistics are available during the lifetime of tasks/processes as
439 responses to commands. Like BSD accounting, they are sent to user
444 config TASK_DELAY_ACCT
445 bool "Enable per-task delay accounting"
449 Collect information on time spent by a task waiting for system
450 resources like cpu, synchronous block I/O completion and swapping
451 in pages. Such statistics can help in setting a task's priorities
452 relative to other tasks for cpu, io, rss limits etc.
457 bool "Enable extended accounting over taskstats"
460 Collect extended task accounting data and send the data
461 to userland for processing over the taskstats interface.
465 config TASK_IO_ACCOUNTING
466 bool "Enable per-task storage I/O accounting"
467 depends on TASK_XACCT
469 Collect information on the number of bytes of storage I/O which this
474 endmenu # "CPU/Task time and stats accounting"
480 default y if !PREEMPT && SMP
482 This option selects the RCU implementation that is
483 designed for very large SMP system with hundreds or
484 thousands of CPUs. It also scales down nicely to
491 This option selects the RCU implementation that is
492 designed for very large SMP systems with hundreds or
493 thousands of CPUs, but for which real-time response
494 is also required. It also scales down nicely to
497 Select this option if you are unsure.
501 default y if !PREEMPT && !SMP
503 This option selects the RCU implementation that is
504 designed for UP systems from which real-time response
505 is not required. This option greatly reduces the
506 memory footprint of RCU.
509 bool "Make expert-level adjustments to RCU configuration"
512 This option needs to be enabled if you wish to make
513 expert-level adjustments to RCU configuration. By default,
514 no such adjustments can be made, which has the often-beneficial
515 side-effect of preventing "make oldconfig" from asking you all
516 sorts of detailed questions about how you would like numerous
517 obscure RCU options to be set up.
519 Say Y if you need to make expert-level adjustments to RCU.
521 Say N if you are unsure.
526 This option selects the sleepable version of RCU. This version
527 permits arbitrary sleeping or blocking within RCU read-side critical
535 This option enables a task-based RCU implementation that uses
536 only voluntary context switch (not preemption!), idle, and
537 user-mode execution as quiescent states.
539 config RCU_STALL_COMMON
540 def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE )
542 This option enables RCU CPU stall code that is common between
543 the TINY and TREE variants of RCU. The purpose is to allow
544 the tiny variants to disable RCU CPU stall warnings, while
545 making these warnings mandatory for the tree variants.
547 config CONTEXT_TRACKING
550 config CONTEXT_TRACKING_FORCE
551 bool "Force context tracking"
552 depends on CONTEXT_TRACKING
553 default y if !NO_HZ_FULL
555 The major pre-requirement for full dynticks to work is to
556 support the context tracking subsystem. But there are also
557 other dependencies to provide in order to make the full
560 This option stands for testing when an arch implements the
561 context tracking backend but doesn't yet fullfill all the
562 requirements to make the full dynticks feature working.
563 Without the full dynticks, there is no way to test the support
564 for context tracking and the subsystems that rely on it: RCU
565 userspace extended quiescent state and tickless cputime
566 accounting. This option copes with the absence of the full
567 dynticks subsystem by forcing the context tracking on all
570 Say Y only if you're working on the development of an
571 architecture backend for the context tracking.
573 Say N otherwise, this option brings an overhead that you
574 don't want in production.
578 int "Tree-based hierarchical RCU fanout value"
581 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
585 This option controls the fanout of hierarchical implementations
586 of RCU, allowing RCU to work efficiently on machines with
587 large numbers of CPUs. This value must be at least the fourth
588 root of NR_CPUS, which allows NR_CPUS to be insanely large.
589 The default value of RCU_FANOUT should be used for production
590 systems, but if you are stress-testing the RCU implementation
591 itself, small RCU_FANOUT values allow you to test large-system
592 code paths on small(er) systems.
594 Select a specific number if testing RCU itself.
595 Take the default if unsure.
597 config RCU_FANOUT_LEAF
598 int "Tree-based hierarchical RCU leaf-level fanout value"
601 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT
604 This option controls the leaf-level fanout of hierarchical
605 implementations of RCU, and allows trading off cache misses
606 against lock contention. Systems that synchronize their
607 scheduling-clock interrupts for energy-efficiency reasons will
608 want the default because the smaller leaf-level fanout keeps
609 lock contention levels acceptably low. Very large systems
610 (hundreds or thousands of CPUs) will instead want to set this
611 value to the maximum value possible in order to reduce the
612 number of cache misses incurred during RCU's grace-period
613 initialization. These systems tend to run CPU-bound, and thus
614 are not helped by synchronized interrupts, and thus tend to
615 skew them, which reduces lock contention enough that large
616 leaf-level fanouts work well.
618 Select a specific number if testing RCU itself.
620 Select the maximum permissible value for large systems.
622 Take the default if unsure.
624 config RCU_FAST_NO_HZ
625 bool "Accelerate last non-dyntick-idle CPU's grace periods"
626 depends on NO_HZ_COMMON && SMP && RCU_EXPERT
629 This option permits CPUs to enter dynticks-idle state even if
630 they have RCU callbacks queued, and prevents RCU from waking
631 these CPUs up more than roughly once every four jiffies (by
632 default, you can adjust this using the rcutree.rcu_idle_gp_delay
633 parameter), thus improving energy efficiency. On the other
634 hand, this option increases the duration of RCU grace periods,
635 for example, slowing down synchronize_rcu().
637 Say Y if energy efficiency is critically important, and you
638 don't care about increased grace-period durations.
640 Say N if you are unsure.
642 config TREE_RCU_TRACE
643 def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU )
646 This option provides tracing for the TREE_RCU and
647 PREEMPT_RCU implementations, permitting Makefile to
648 trivially select kernel/rcutree_trace.c.
651 bool "Enable RCU priority boosting"
652 depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT
655 This option boosts the priority of preempted RCU readers that
656 block the current preemptible RCU grace period for too long.
657 This option also prevents heavy loads from blocking RCU
658 callback invocation for all flavors of RCU.
660 Say Y here if you are working with real-time apps or heavy loads
661 Say N here if you are unsure.
663 config RCU_KTHREAD_PRIO
664 int "Real-time priority to use for RCU worker threads"
665 range 1 99 if RCU_BOOST
666 range 0 99 if !RCU_BOOST
667 default 1 if RCU_BOOST
668 default 0 if !RCU_BOOST
669 depends on RCU_EXPERT
671 This option specifies the SCHED_FIFO priority value that will be
672 assigned to the rcuc/n and rcub/n threads and is also the value
673 used for RCU_BOOST (if enabled). If you are working with a
674 real-time application that has one or more CPU-bound threads
675 running at a real-time priority level, you should set
676 RCU_KTHREAD_PRIO to a priority higher than the highest-priority
677 real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO
678 value of 1 is appropriate in the common case, which is real-time
679 applications that do not have any CPU-bound threads.
681 Some real-time applications might not have a single real-time
682 thread that saturates a given CPU, but instead might have
683 multiple real-time threads that, taken together, fully utilize
684 that CPU. In this case, you should set RCU_KTHREAD_PRIO to
685 a priority higher than the lowest-priority thread that is
686 conspiring to prevent the CPU from running any non-real-time
687 tasks. For example, if one thread at priority 10 and another
688 thread at priority 5 are between themselves fully consuming
689 the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be
690 set to priority 6 or higher.
692 Specify the real-time priority, or take the default if unsure.
694 config RCU_BOOST_DELAY
695 int "Milliseconds to delay boosting after RCU grace-period start"
700 This option specifies the time to wait after the beginning of
701 a given grace period before priority-boosting preempted RCU
702 readers blocking that grace period. Note that any RCU reader
703 blocking an expedited RCU grace period is boosted immediately.
705 Accept the default if unsure.
708 bool "Offload RCU callback processing from boot-selected CPUs"
709 depends on TREE_RCU || PREEMPT_RCU
710 depends on RCU_EXPERT || NO_HZ_FULL
713 Use this option to reduce OS jitter for aggressive HPC or
714 real-time workloads. It can also be used to offload RCU
715 callback invocation to energy-efficient CPUs in battery-powered
716 asymmetric multiprocessors.
718 This option offloads callback invocation from the set of
719 CPUs specified at boot time by the rcu_nocbs parameter.
720 For each such CPU, a kthread ("rcuox/N") will be created to
721 invoke callbacks, where the "N" is the CPU being offloaded,
722 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and
723 "s" for RCU-sched. Nothing prevents this kthread from running
724 on the specified CPUs, but (1) the kthreads may be preempted
725 between each callback, and (2) affinity or cgroups can be used
726 to force the kthreads to run on whatever set of CPUs is desired.
728 Say Y here if you want to help to debug reduced OS jitter.
729 Say N here if you are unsure.
732 prompt "Build-forced no-CBs CPUs"
733 default RCU_NOCB_CPU_NONE
734 depends on RCU_NOCB_CPU
736 This option allows no-CBs CPUs (whose RCU callbacks are invoked
737 from kthreads rather than from softirq context) to be specified
738 at build time. Additional no-CBs CPUs may be specified by
739 the rcu_nocbs= boot parameter.
741 config RCU_NOCB_CPU_NONE
742 bool "No build_forced no-CBs CPUs"
744 This option does not force any of the CPUs to be no-CBs CPUs.
745 Only CPUs designated by the rcu_nocbs= boot parameter will be
746 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU
747 kthreads whose names begin with "rcuo". All other CPUs will
748 invoke their own RCU callbacks in softirq context.
750 Select this option if you want to choose no-CBs CPUs at
751 boot time, for example, to allow testing of different no-CBs
752 configurations without having to rebuild the kernel each time.
754 config RCU_NOCB_CPU_ZERO
755 bool "CPU 0 is a build_forced no-CBs CPU"
757 This option forces CPU 0 to be a no-CBs CPU, so that its RCU
758 callbacks are invoked by a per-CPU kthread whose name begins
759 with "rcuo". Additional CPUs may be designated as no-CBs
760 CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs.
761 All other CPUs will invoke their own RCU callbacks in softirq
764 Select this if CPU 0 needs to be a no-CBs CPU for real-time
765 or energy-efficiency reasons, but the real reason it exists
766 is to ensure that randconfig testing covers mixed systems.
768 config RCU_NOCB_CPU_ALL
769 bool "All CPUs are build_forced no-CBs CPUs"
771 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs=
772 boot parameter will be ignored. All CPUs' RCU callbacks will
773 be executed in the context of per-CPU rcuo kthreads created for
774 this purpose. Assuming that the kthreads whose names start with
775 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter
776 on the remaining CPUs, but might decrease memory locality during
777 RCU-callback invocation, thus potentially degrading throughput.
779 Select this if all CPUs need to be no-CBs CPUs for real-time
780 or energy-efficiency reasons.
784 config RCU_EXPEDITE_BOOT
788 This option enables expedited grace periods at boot time,
789 as if rcu_expedite_gp() had been invoked early in boot.
790 The corresponding rcu_unexpedite_gp() is invoked from
791 rcu_end_inkernel_boot(), which is intended to be invoked
792 at the end of the kernel-only boot sequence, just before
795 Accept the default if unsure.
797 endmenu # "RCU Subsystem"
804 tristate "Kernel .config support"
807 This option enables the complete Linux kernel ".config" file
808 contents to be saved in the kernel. It provides documentation
809 of which kernel options are used in a running kernel or in an
810 on-disk kernel. This information can be extracted from the kernel
811 image file with the script scripts/extract-ikconfig and used as
812 input to rebuild the current kernel or to build another kernel.
813 It can also be extracted from a running kernel by reading
814 /proc/config.gz if enabled (below).
817 bool "Enable access to .config through /proc/config.gz"
818 depends on IKCONFIG && PROC_FS
820 This option enables access to the kernel configuration file
821 through /proc/config.gz.
824 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)"
829 Select the minimal kernel log buffer size as a power of 2.
830 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config
831 parameter, see below. Any higher size also might be forced
832 by "log_buf_len" boot parameter.
842 config LOG_CPU_MAX_BUF_SHIFT
843 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)"
846 default 12 if !BASE_SMALL
847 default 0 if BASE_SMALL
850 This option allows to increase the default ring buffer size
851 according to the number of CPUs. The value defines the contribution
852 of each CPU as a power of 2. The used space is typically only few
853 lines however it might be much more when problems are reported,
856 The increased size means that a new buffer has to be allocated and
857 the original static one is unused. It makes sense only on systems
858 with more CPUs. Therefore this value is used only when the sum of
859 contributions is greater than the half of the default kernel ring
860 buffer as defined by LOG_BUF_SHIFT. The default values are set
861 so that more than 64 CPUs are needed to trigger the allocation.
863 Also this option is ignored when "log_buf_len" kernel parameter is
864 used as it forces an exact (power of two) size of the ring buffer.
866 The number of possible CPUs is used for this computation ignoring
867 hotplugging making the compuation optimal for the the worst case
868 scenerio while allowing a simple algorithm to be used from bootup.
870 Examples shift values and their meaning:
871 17 => 128 KB for each CPU
872 16 => 64 KB for each CPU
873 15 => 32 KB for each CPU
874 14 => 16 KB for each CPU
875 13 => 8 KB for each CPU
876 12 => 4 KB for each CPU
879 # Architectures with an unreliable sched_clock() should select this:
881 config HAVE_UNSTABLE_SCHED_CLOCK
884 config GENERIC_SCHED_CLOCK
888 # For architectures that want to enable the support for NUMA-affine scheduler
891 config ARCH_SUPPORTS_NUMA_BALANCING
895 # For architectures that prefer to flush all TLBs after a number of pages
896 # are unmapped instead of sending one IPI per page to flush. The architecture
897 # must provide guarantees on what happens if a clean TLB cache entry is
898 # written after the unmap. Details are in mm/rmap.c near the check for
899 # should_defer_flush. The architecture should also consider if the full flush
900 # and the refill costs are offset by the savings of sending fewer IPIs.
901 config ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
905 # For architectures that know their GCC __int128 support is sound
907 config ARCH_SUPPORTS_INT128
910 # For architectures that (ab)use NUMA to represent different memory regions
911 # all cpu-local but of different latencies, such as SuperH.
913 config ARCH_WANT_NUMA_VARIABLE_LOCALITY
916 config NUMA_BALANCING
917 bool "Memory placement aware NUMA scheduler"
918 depends on ARCH_SUPPORTS_NUMA_BALANCING
919 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
920 depends on SMP && NUMA && MIGRATION
922 This option adds support for automatic NUMA aware memory/task placement.
923 The mechanism is quite primitive and is based on migrating memory when
924 it has references to the node the task is running on.
926 This system will be inactive on UMA systems.
928 config NUMA_BALANCING_DEFAULT_ENABLED
929 bool "Automatically enable NUMA aware memory/task placement"
931 depends on NUMA_BALANCING
933 If set, automatic NUMA balancing will be enabled if running on a NUMA
937 bool "Control Group support"
940 This option adds support for grouping sets of processes together, for
941 use with process control subsystems such as Cpusets, CFS, memory
942 controls or device isolation.
944 - Documentation/scheduler/sched-design-CFS.txt (CFS)
945 - Documentation/cgroups/ (features for grouping, isolation
946 and resource control)
953 bool "Example debug cgroup subsystem"
956 This option enables a simple cgroup subsystem that
957 exports useful debugging information about the cgroups
962 config CGROUP_FREEZER
963 bool "Freezer cgroup subsystem"
965 Provides a way to freeze and unfreeze all tasks in a
969 bool "PIDs cgroup subsystem"
971 Provides enforcement of process number limits in the scope of a
972 cgroup. Any attempt to fork more processes than is allowed in the
973 cgroup will fail. PIDs are fundamentally a global resource because it
974 is fairly trivial to reach PID exhaustion before you reach even a
975 conservative kmemcg limit. As a result, it is possible to grind a
976 system to halt without being limited by other cgroup policies. The
977 PIDs cgroup subsystem is designed to stop this from happening.
979 It should be noted that organisational operations (such as attaching
980 to a cgroup hierarchy will *not* be blocked by the PIDs subsystem),
981 since the PIDs limit only affects a process's ability to fork, not to
985 bool "Device controller for cgroups"
987 Provides a cgroup implementing whitelists for devices which
988 a process in the cgroup can mknod or open.
991 bool "Cpuset support"
993 This option will let you create and manage CPUSETs which
994 allow dynamically partitioning a system into sets of CPUs and
995 Memory Nodes and assigning tasks to run only within those sets.
996 This is primarily useful on large SMP or NUMA systems.
1000 config PROC_PID_CPUSET
1001 bool "Include legacy /proc/<pid>/cpuset file"
1005 config CGROUP_CPUACCT
1006 bool "Simple CPU accounting cgroup subsystem"
1008 Provides a simple Resource Controller for monitoring the
1009 total CPU consumed by the tasks in a cgroup.
1011 config CGROUP_SCHEDTUNE
1012 bool "CFS tasks boosting cgroup subsystem (EXPERIMENTAL)"
1013 depends on SCHED_TUNE
1015 This option provides the "schedtune" controller which improves the
1016 flexibility of the task boosting mechanism by introducing the support
1017 to define "per task" boost values.
1019 This new controller:
1020 1. allows only a two layers hierarchy, where the root defines the
1021 system-wide boost value and its direct childrens define each one a
1022 different "class of tasks" to be boosted with a different value
1023 2. supports up to 16 different task classes, each one which could be
1024 configured with a different boost value
1032 bool "Memory Resource Controller for Control Groups"
1036 Provides a memory resource controller that manages both anonymous
1037 memory and page cache. (See Documentation/cgroups/memory.txt)
1040 bool "Memory Resource Controller Swap Extension"
1041 depends on MEMCG && SWAP
1043 Add swap management feature to memory resource controller. When you
1044 enable this, you can limit mem+swap usage per cgroup. In other words,
1045 when you disable this, memory resource controller has no cares to
1046 usage of swap...a process can exhaust all of the swap. This extension
1047 is useful when you want to avoid exhaustion swap but this itself
1048 adds more overheads and consumes memory for remembering information.
1049 Especially if you use 32bit system or small memory system, please
1050 be careful about enabling this. When memory resource controller
1051 is disabled by boot option, this will be automatically disabled and
1052 there will be no overhead from this. Even when you set this config=y,
1053 if boot option "swapaccount=0" is set, swap will not be accounted.
1054 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
1055 size is 4096bytes, 512k per 1Gbytes of swap.
1056 config MEMCG_SWAP_ENABLED
1057 bool "Memory Resource Controller Swap Extension enabled by default"
1058 depends on MEMCG_SWAP
1061 Memory Resource Controller Swap Extension comes with its price in
1062 a bigger memory consumption. General purpose distribution kernels
1063 which want to enable the feature but keep it disabled by default
1064 and let the user enable it by swapaccount=1 boot command line
1065 parameter should have this option unselected.
1066 For those who want to have the feature enabled by default should
1067 select this option (if, for some reason, they need to disable it
1068 then swapaccount=0 does the trick).
1070 bool "Memory Resource Controller Kernel Memory accounting"
1072 depends on SLUB || SLAB
1074 The Kernel Memory extension for Memory Resource Controller can limit
1075 the amount of memory used by kernel objects in the system. Those are
1076 fundamentally different from the entities handled by the standard
1077 Memory Controller, which are page-based, and can be swapped. Users of
1078 the kmem extension can use it to guarantee that no group of processes
1079 will ever exhaust kernel resources alone.
1081 config CGROUP_HUGETLB
1082 bool "HugeTLB Resource Controller for Control Groups"
1083 depends on HUGETLB_PAGE
1087 Provides a cgroup Resource Controller for HugeTLB pages.
1088 When you enable this, you can put a per cgroup limit on HugeTLB usage.
1089 The limit is enforced during page fault. Since HugeTLB doesn't
1090 support page reclaim, enforcing the limit at page fault time implies
1091 that, the application will get SIGBUS signal if it tries to access
1092 HugeTLB pages beyond its limit. This requires the application to know
1093 beforehand how much HugeTLB pages it would require for its use. The
1094 control group is tracked in the third page lru pointer. This means
1095 that we cannot use the controller with huge page less than 3 pages.
1098 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring"
1099 depends on PERF_EVENTS && CGROUPS
1101 This option extends the per-cpu mode to restrict monitoring to
1102 threads which belong to the cgroup specified and run on the
1107 menuconfig CGROUP_SCHED
1108 bool "Group CPU scheduler"
1111 This feature lets CPU scheduler recognize task groups and control CPU
1112 bandwidth allocation to such task groups. It uses cgroups to group
1116 config FAIR_GROUP_SCHED
1117 bool "Group scheduling for SCHED_OTHER"
1118 depends on CGROUP_SCHED
1119 default CGROUP_SCHED
1121 config CFS_BANDWIDTH
1122 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
1123 depends on FAIR_GROUP_SCHED
1126 This option allows users to define CPU bandwidth rates (limits) for
1127 tasks running within the fair group scheduler. Groups with no limit
1128 set are considered to be unconstrained and will run with no
1130 See tip/Documentation/scheduler/sched-bwc.txt for more information.
1132 config RT_GROUP_SCHED
1133 bool "Group scheduling for SCHED_RR/FIFO"
1134 depends on CGROUP_SCHED
1137 This feature lets you explicitly allocate real CPU bandwidth
1138 to task groups. If enabled, it will also make it impossible to
1139 schedule realtime tasks for non-root users until you allocate
1140 realtime bandwidth for them.
1141 See Documentation/scheduler/sched-rt-group.txt for more information.
1146 bool "Block IO controller"
1150 Generic block IO controller cgroup interface. This is the common
1151 cgroup interface which should be used by various IO controlling
1154 Currently, CFQ IO scheduler uses it to recognize task groups and
1155 control disk bandwidth allocation (proportional time slice allocation)
1156 to such task groups. It is also used by bio throttling logic in
1157 block layer to implement upper limit in IO rates on a device.
1159 This option only enables generic Block IO controller infrastructure.
1160 One needs to also enable actual IO controlling logic/policy. For
1161 enabling proportional weight division of disk bandwidth in CFQ, set
1162 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set
1163 CONFIG_BLK_DEV_THROTTLING=y.
1165 See Documentation/cgroups/blkio-controller.txt for more information.
1167 config DEBUG_BLK_CGROUP
1168 bool "Enable Block IO controller debugging"
1169 depends on BLK_CGROUP
1172 Enable some debugging help. Currently it exports additional stat
1173 files in a cgroup which can be useful for debugging.
1175 config CGROUP_WRITEBACK
1177 depends on MEMCG && BLK_CGROUP
1182 config CHECKPOINT_RESTORE
1183 bool "Checkpoint/restore support" if EXPERT
1184 select PROC_CHILDREN
1187 Enables additional kernel features in a sake of checkpoint/restore.
1188 In particular it adds auxiliary prctl codes to setup process text,
1189 data and heap segment sizes, and a few additional /proc filesystem
1192 If unsure, say N here.
1194 menuconfig NAMESPACES
1195 bool "Namespaces support" if EXPERT
1196 depends on MULTIUSER
1199 Provides the way to make tasks work with different objects using
1200 the same id. For example same IPC id may refer to different objects
1201 or same user id or pid may refer to different tasks when used in
1202 different namespaces.
1207 bool "UTS namespace"
1210 In this namespace tasks see different info provided with the
1214 bool "IPC namespace"
1215 depends on (SYSVIPC || POSIX_MQUEUE)
1218 In this namespace tasks work with IPC ids which correspond to
1219 different IPC objects in different namespaces.
1222 bool "User namespace"
1225 This allows containers, i.e. vservers, to use user namespaces
1226 to provide different user info for different servers.
1228 When user namespaces are enabled in the kernel it is
1229 recommended that the MEMCG and MEMCG_KMEM options also be
1230 enabled and that user-space use the memory control groups to
1231 limit the amount of memory a memory unprivileged users can
1237 bool "PID Namespaces"
1240 Support process id namespaces. This allows having multiple
1241 processes with the same pid as long as they are in different
1242 pid namespaces. This is a building block of containers.
1245 bool "Network namespace"
1249 Allow user space to create what appear to be multiple instances
1250 of the network stack.
1254 config SCHED_AUTOGROUP
1255 bool "Automatic process group scheduling"
1258 select FAIR_GROUP_SCHED
1260 This option optimizes the scheduler for common desktop workloads by
1261 automatically creating and populating task groups. This separation
1262 of workloads isolates aggressive CPU burners (like build jobs) from
1263 desktop applications. Task group autogeneration is currently based
1267 bool "Boosting for CFS tasks (EXPERIMENTAL)"
1270 This option enables the system-wide support for task boosting.
1271 When this support is enabled a new sysctl interface is exposed to
1273 /proc/sys/kernel/sched_cfs_boost
1274 which allows to set a system-wide boost value in range [0..100].
1276 The currently boosting strategy is implemented in such a way that:
1277 - a 0% boost value requires to operate in "standard" mode by
1278 scheduling all tasks at the minimum capacities required by their
1280 - a 100% boost value requires to push at maximum the task
1281 performances, "regardless" of the incurred energy consumption
1283 A boost value in between these two boundaries is used to bias the
1284 power/performance trade-off, the higher the boost value the more the
1285 scheduler is biased toward performance boosting instead of energy
1288 Since this support exposes a single system-wide knob, the specified
1289 boost value is applied to all (CFS) tasks in the system.
1293 config DEFAULT_USE_ENERGY_AWARE
1294 bool "Default to enabling the Energy Aware Scheduler feature"
1297 This option defaults the ENERGY_AWARE scheduling feature to true,
1298 as without SCHED_DEBUG set this feature can't be enabled or disabled
1303 config SYSFS_DEPRECATED
1304 bool "Enable deprecated sysfs features to support old userspace tools"
1308 This option adds code that switches the layout of the "block" class
1309 devices, to not show up in /sys/class/block/, but only in
1312 This switch is only active when the sysfs.deprecated=1 boot option is
1313 passed or the SYSFS_DEPRECATED_V2 option is set.
1315 This option allows new kernels to run on old distributions and tools,
1316 which might get confused by /sys/class/block/. Since 2007/2008 all
1317 major distributions and tools handle this just fine.
1319 Recent distributions and userspace tools after 2009/2010 depend on
1320 the existence of /sys/class/block/, and will not work with this
1323 Only if you are using a new kernel on an old distribution, you might
1326 config SYSFS_DEPRECATED_V2
1327 bool "Enable deprecated sysfs features by default"
1330 depends on SYSFS_DEPRECATED
1332 Enable deprecated sysfs by default.
1334 See the CONFIG_SYSFS_DEPRECATED option for more details about this
1337 Only if you are using a new kernel on an old distribution, you might
1338 need to say Y here. Even then, odds are you would not need it
1339 enabled, you can always pass the boot option if absolutely necessary.
1342 bool "Kernel->user space relay support (formerly relayfs)"
1344 This option enables support for relay interface support in
1345 certain file systems (such as debugfs).
1346 It is designed to provide an efficient mechanism for tools and
1347 facilities to relay large amounts of data from kernel space to
1352 config BLK_DEV_INITRD
1353 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support"
1354 depends on BROKEN || !FRV
1356 The initial RAM filesystem is a ramfs which is loaded by the
1357 boot loader (loadlin or lilo) and that is mounted as root
1358 before the normal boot procedure. It is typically used to
1359 load modules needed to mount the "real" root file system,
1360 etc. See <file:Documentation/initrd.txt> for details.
1362 If RAM disk support (BLK_DEV_RAM) is also included, this
1363 also enables initial RAM disk (initrd) support and adds
1364 15 Kbytes (more on some other architectures) to the kernel size.
1370 source "usr/Kconfig"
1374 config CC_OPTIMIZE_FOR_SIZE
1375 bool "Optimize for size"
1377 Enabling this option will pass "-Os" instead of "-O2" to
1378 your compiler resulting in a smaller kernel.
1391 config SYSCTL_EXCEPTION_TRACE
1394 Enable support for /proc/sys/debug/exception-trace.
1396 config SYSCTL_ARCH_UNALIGN_NO_WARN
1399 Enable support for /proc/sys/kernel/ignore-unaligned-usertrap
1400 Allows arch to define/use @no_unaligned_warning to possibly warn
1401 about unaligned access emulation going on under the hood.
1403 config SYSCTL_ARCH_UNALIGN_ALLOW
1406 Enable support for /proc/sys/kernel/unaligned-trap
1407 Allows arches to define/use @unaligned_enabled to runtime toggle
1408 the unaligned access emulation.
1409 see arch/parisc/kernel/unaligned.c for reference
1411 config HAVE_PCSPKR_PLATFORM
1414 # interpreter that classic socket filters depend on
1419 bool "Configure standard kernel features (expert users)"
1420 # Unhide debug options, to make the on-by-default options visible
1423 This option allows certain base kernel options and settings
1424 to be disabled or tweaked. This is for specialized
1425 environments which can tolerate a "non-standard" kernel.
1426 Only use this if you really know what you are doing.
1429 bool "Enable 16-bit UID system calls" if EXPERT
1430 depends on HAVE_UID16 && MULTIUSER
1433 This enables the legacy 16-bit UID syscall wrappers.
1436 bool "Multiple users, groups and capabilities support" if EXPERT
1439 This option enables support for non-root users, groups and
1442 If you say N here, all processes will run with UID 0, GID 0, and all
1443 possible capabilities. Saying N here also compiles out support for
1444 system calls related to UIDs, GIDs, and capabilities, such as setuid,
1447 If unsure, say Y here.
1449 config SGETMASK_SYSCALL
1450 bool "sgetmask/ssetmask syscalls support" if EXPERT
1451 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH
1453 sys_sgetmask and sys_ssetmask are obsolete system calls
1454 no longer supported in libc but still enabled by default in some
1457 If unsure, leave the default option here.
1459 config SYSFS_SYSCALL
1460 bool "Sysfs syscall support" if EXPERT
1463 sys_sysfs is an obsolete system call no longer supported in libc.
1464 Note that disabling this option is more secure but might break
1465 compatibility with some systems.
1467 If unsure say Y here.
1469 config SYSCTL_SYSCALL
1470 bool "Sysctl syscall support" if EXPERT
1471 depends on PROC_SYSCTL
1475 sys_sysctl uses binary paths that have been found challenging
1476 to properly maintain and use. The interface in /proc/sys
1477 using paths with ascii names is now the primary path to this
1480 Almost nothing using the binary sysctl interface so if you are
1481 trying to save some space it is probably safe to disable this,
1482 making your kernel marginally smaller.
1484 If unsure say N here.
1487 bool "Load all symbols for debugging/ksymoops" if EXPERT
1490 Say Y here to let the kernel print out symbolic crash information and
1491 symbolic stack backtraces. This increases the size of the kernel
1492 somewhat, as all symbols have to be loaded into the kernel image.
1495 bool "Include all symbols in kallsyms"
1496 depends on DEBUG_KERNEL && KALLSYMS
1498 Normally kallsyms only contains the symbols of functions for nicer
1499 OOPS messages and backtraces (i.e., symbols from the text and inittext
1500 sections). This is sufficient for most cases. And only in very rare
1501 cases (e.g., when a debugger is used) all symbols are required (e.g.,
1502 names of variables from the data sections, etc).
1504 This option makes sure that all symbols are loaded into the kernel
1505 image (i.e., symbols from all sections) in cost of increased kernel
1506 size (depending on the kernel configuration, it may be 300KiB or
1507 something like this).
1509 Say N unless you really need all symbols.
1513 bool "Enable support for printk" if EXPERT
1516 This option enables normal printk support. Removing it
1517 eliminates most of the message strings from the kernel image
1518 and makes the kernel more or less silent. As this makes it
1519 very difficult to diagnose system problems, saying N here is
1520 strongly discouraged.
1523 bool "BUG() support" if EXPERT
1526 Disabling this option eliminates support for BUG and WARN, reducing
1527 the size of your kernel image and potentially quietly ignoring
1528 numerous fatal conditions. You should only consider disabling this
1529 option for embedded systems with no facilities for reporting errors.
1535 bool "Enable ELF core dumps" if EXPERT
1537 Enable support for generating core dumps. Disabling saves about 4k.
1540 config PCSPKR_PLATFORM
1541 bool "Enable PC-Speaker support" if EXPERT
1542 depends on HAVE_PCSPKR_PLATFORM
1546 This option allows to disable the internal PC-Speaker
1547 support, saving some memory.
1551 bool "Enable full-sized data structures for core" if EXPERT
1553 Disabling this option reduces the size of miscellaneous core
1554 kernel data structures. This saves memory on small machines,
1555 but may reduce performance.
1558 bool "Enable futex support" if EXPERT
1562 Disabling this option will cause the kernel to be built without
1563 support for "fast userspace mutexes". The resulting kernel may not
1564 run glibc-based applications correctly.
1566 config HAVE_FUTEX_CMPXCHG
1570 Architectures should select this if futex_atomic_cmpxchg_inatomic()
1571 is implemented and always working. This removes a couple of runtime
1575 bool "Enable eventpoll support" if EXPERT
1579 Disabling this option will cause the kernel to be built without
1580 support for epoll family of system calls.
1583 bool "Enable signalfd() system call" if EXPERT
1587 Enable the signalfd() system call that allows to receive signals
1588 on a file descriptor.
1593 bool "Enable timerfd() system call" if EXPERT
1597 Enable the timerfd() system call that allows to receive timer
1598 events on a file descriptor.
1603 bool "Enable eventfd() system call" if EXPERT
1607 Enable the eventfd() system call that allows to receive both
1608 kernel notification (ie. KAIO) or userspace notifications.
1612 # syscall, maps, verifier
1614 bool "Enable bpf() system call"
1619 Enable the bpf() system call that allows to manipulate eBPF
1620 programs and maps via file descriptors.
1623 bool "Use full shmem filesystem" if EXPERT
1627 The shmem is an internal filesystem used to manage shared memory.
1628 It is backed by swap and manages resource limits. It is also exported
1629 to userspace as tmpfs if TMPFS is enabled. Disabling this
1630 option replaces shmem and tmpfs with the much simpler ramfs code,
1631 which may be appropriate on small systems without swap.
1634 bool "Enable AIO support" if EXPERT
1637 This option enables POSIX asynchronous I/O which may by used
1638 by some high performance threaded applications. Disabling
1639 this option saves about 7k.
1641 config ADVISE_SYSCALLS
1642 bool "Enable madvise/fadvise syscalls" if EXPERT
1645 This option enables the madvise and fadvise syscalls, used by
1646 applications to advise the kernel about their future memory or file
1647 usage, improving performance. If building an embedded system where no
1648 applications use these syscalls, you can disable this option to save
1652 bool "Enable userfaultfd() system call"
1656 Enable the userfaultfd() system call that allows to intercept and
1657 handle page faults in userland.
1661 bool "Enable PCI quirk workarounds" if EXPERT
1664 This enables workarounds for various PCI chipset
1665 bugs/quirks. Disable this only if your target machine is
1666 unaffected by PCI quirks.
1669 bool "Enable membarrier() system call" if EXPERT
1672 Enable the membarrier() system call that allows issuing memory
1673 barriers across all running threads, which can be used to distribute
1674 the cost of user-space memory barriers asymmetrically by transforming
1675 pairs of memory barriers into pairs consisting of membarrier() and a
1681 bool "Embedded system"
1682 option allnoconfig_y
1685 This option should be enabled if compiling the kernel for
1686 an embedded system so certain expert options are available
1689 config HAVE_PERF_EVENTS
1692 See tools/perf/design.txt for details.
1694 config PERF_USE_VMALLOC
1697 See tools/perf/design.txt for details
1699 menu "Kernel Performance Events And Counters"
1702 bool "Kernel performance events and counters"
1703 default y if PROFILING
1704 depends on HAVE_PERF_EVENTS
1709 Enable kernel support for various performance events provided
1710 by software and hardware.
1712 Software events are supported either built-in or via the
1713 use of generic tracepoints.
1715 Most modern CPUs support performance events via performance
1716 counter registers. These registers count the number of certain
1717 types of hw events: such as instructions executed, cachemisses
1718 suffered, or branches mis-predicted - without slowing down the
1719 kernel or applications. These registers can also trigger interrupts
1720 when a threshold number of events have passed - and can thus be
1721 used to profile the code that runs on that CPU.
1723 The Linux Performance Event subsystem provides an abstraction of
1724 these software and hardware event capabilities, available via a
1725 system call and used by the "perf" utility in tools/perf/. It
1726 provides per task and per CPU counters, and it provides event
1727 capabilities on top of those.
1731 config DEBUG_PERF_USE_VMALLOC
1733 bool "Debug: use vmalloc to back perf mmap() buffers"
1734 depends on PERF_EVENTS && DEBUG_KERNEL && !PPC
1735 select PERF_USE_VMALLOC
1737 Use vmalloc memory to back perf mmap() buffers.
1739 Mostly useful for debugging the vmalloc code on platforms
1740 that don't require it.
1746 config VM_EVENT_COUNTERS
1748 bool "Enable VM event counters for /proc/vmstat" if EXPERT
1750 VM event counters are needed for event counts to be shown.
1751 This option allows the disabling of the VM event counters
1752 on EXPERT systems. /proc/vmstat will only show page counts
1753 if VM event counters are disabled.
1757 bool "Enable SLUB debugging support" if EXPERT
1758 depends on SLUB && SYSFS
1760 SLUB has extensive debug support features. Disabling these can
1761 result in significant savings in code size. This also disables
1762 SLUB sysfs support. /sys/slab will not exist and there will be
1763 no support for cache validation etc.
1766 bool "Disable heap randomization"
1769 Randomizing heap placement makes heap exploits harder, but it
1770 also breaks ancient binaries (including anything libc5 based).
1771 This option changes the bootup default to heap randomization
1772 disabled, and can be overridden at runtime by setting
1773 /proc/sys/kernel/randomize_va_space to 2.
1775 On non-ancient distros (post-2000 ones) N is usually a safe choice.
1778 prompt "Choose SLAB allocator"
1781 This option allows to select a slab allocator.
1785 select HAVE_HARDENED_USERCOPY_ALLOCATOR
1787 The regular slab allocator that is established and known to work
1788 well in all environments. It organizes cache hot objects in
1789 per cpu and per node queues.
1792 bool "SLUB (Unqueued Allocator)"
1793 select HAVE_HARDENED_USERCOPY_ALLOCATOR
1795 SLUB is a slab allocator that minimizes cache line usage
1796 instead of managing queues of cached objects (SLAB approach).
1797 Per cpu caching is realized using slabs of objects instead
1798 of queues of objects. SLUB can use memory efficiently
1799 and has enhanced diagnostics. SLUB is the default choice for
1804 bool "SLOB (Simple Allocator)"
1806 SLOB replaces the stock allocator with a drastically simpler
1807 allocator. SLOB is generally more space efficient but
1808 does not perform as well on large systems.
1812 config SLUB_CPU_PARTIAL
1814 depends on SLUB && SMP
1815 bool "SLUB per cpu partial cache"
1817 Per cpu partial caches accellerate objects allocation and freeing
1818 that is local to a processor at the price of more indeterminism
1819 in the latency of the free. On overflow these caches will be cleared
1820 which requires the taking of locks that may cause latency spikes.
1821 Typically one would choose no for a realtime system.
1823 config MMAP_ALLOW_UNINITIALIZED
1824 bool "Allow mmapped anonymous memory to be uninitialized"
1825 depends on EXPERT && !MMU
1828 Normally, and according to the Linux spec, anonymous memory obtained
1829 from mmap() has it's contents cleared before it is passed to
1830 userspace. Enabling this config option allows you to request that
1831 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
1832 providing a huge performance boost. If this option is not enabled,
1833 then the flag will be ignored.
1835 This is taken advantage of by uClibc's malloc(), and also by
1836 ELF-FDPIC binfmt's brk and stack allocator.
1838 Because of the obvious security issues, this option should only be
1839 enabled on embedded devices where you control what is run in
1840 userspace. Since that isn't generally a problem on no-MMU systems,
1841 it is normally safe to say Y here.
1843 See Documentation/nommu-mmap.txt for more information.
1845 config SYSTEM_DATA_VERIFICATION
1847 select SYSTEM_TRUSTED_KEYRING
1850 select ASYMMETRIC_KEY_TYPE
1851 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE
1852 select PUBLIC_KEY_ALGO_RSA
1855 select X509_CERTIFICATE_PARSER
1856 select PKCS7_MESSAGE_PARSER
1858 Provide PKCS#7 message verification using the contents of the system
1859 trusted keyring to provide public keys. This then can be used for
1860 module verification, kexec image verification and firmware blob
1864 bool "Profiling support"
1866 Say Y here to enable the extended profiling support mechanisms used
1867 by profilers such as OProfile.
1870 # Place an empty function call at each tracepoint site. Can be
1871 # dynamically changed for a probe function.
1876 source "arch/Kconfig"
1878 endmenu # General setup
1880 config HAVE_GENERIC_DMA_COHERENT
1887 depends on SLAB || SLUB_DEBUG
1895 default 0 if BASE_FULL
1896 default 1 if !BASE_FULL
1899 bool "Enable loadable module support"
1902 Kernel modules are small pieces of compiled code which can
1903 be inserted in the running kernel, rather than being
1904 permanently built into the kernel. You use the "modprobe"
1905 tool to add (and sometimes remove) them. If you say Y here,
1906 many parts of the kernel can be built as modules (by
1907 answering M instead of Y where indicated): this is most
1908 useful for infrequently used options which are not required
1909 for booting. For more information, see the man pages for
1910 modprobe, lsmod, modinfo, insmod and rmmod.
1912 If you say Y here, you will need to run "make
1913 modules_install" to put the modules under /lib/modules/
1914 where modprobe can find them (you may need to be root to do
1921 config MODULE_FORCE_LOAD
1922 bool "Forced module loading"
1925 Allow loading of modules without version information (ie. modprobe
1926 --force). Forced module loading sets the 'F' (forced) taint flag and
1927 is usually a really bad idea.
1929 config MODULE_UNLOAD
1930 bool "Module unloading"
1932 Without this option you will not be able to unload any
1933 modules (note that some modules may not be unloadable
1934 anyway), which makes your kernel smaller, faster
1935 and simpler. If unsure, say Y.
1937 config MODULE_FORCE_UNLOAD
1938 bool "Forced module unloading"
1939 depends on MODULE_UNLOAD
1941 This option allows you to force a module to unload, even if the
1942 kernel believes it is unsafe: the kernel will remove the module
1943 without waiting for anyone to stop using it (using the -f option to
1944 rmmod). This is mainly for kernel developers and desperate users.
1948 bool "Module versioning support"
1950 Usually, you have to use modules compiled with your kernel.
1951 Saying Y here makes it sometimes possible to use modules
1952 compiled for different kernels, by adding enough information
1953 to the modules to (hopefully) spot any changes which would
1954 make them incompatible with the kernel you are running. If
1957 config MODULE_SRCVERSION_ALL
1958 bool "Source checksum for all modules"
1960 Modules which contain a MODULE_VERSION get an extra "srcversion"
1961 field inserted into their modinfo section, which contains a
1962 sum of the source files which made it. This helps maintainers
1963 see exactly which source was used to build a module (since
1964 others sometimes change the module source without updating
1965 the version). With this option, such a "srcversion" field
1966 will be created for all modules. If unsure, say N.
1969 bool "Module signature verification"
1971 select SYSTEM_DATA_VERIFICATION
1973 Check modules for valid signatures upon load: the signature
1974 is simply appended to the module. For more information see
1975 Documentation/module-signing.txt.
1977 Note that this option adds the OpenSSL development packages as a
1978 kernel build dependency so that the signing tool can use its crypto
1981 !!!WARNING!!! If you enable this option, you MUST make sure that the
1982 module DOES NOT get stripped after being signed. This includes the
1983 debuginfo strip done by some packagers (such as rpmbuild) and
1984 inclusion into an initramfs that wants the module size reduced.
1986 config MODULE_SIG_FORCE
1987 bool "Require modules to be validly signed"
1988 depends on MODULE_SIG
1990 Reject unsigned modules or signed modules for which we don't have a
1991 key. Without this, such modules will simply taint the kernel.
1993 config MODULE_SIG_ALL
1994 bool "Automatically sign all modules"
1996 depends on MODULE_SIG
1998 Sign all modules during make modules_install. Without this option,
1999 modules must be signed manually, using the scripts/sign-file tool.
2001 comment "Do not forget to sign required modules with scripts/sign-file"
2002 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL
2005 prompt "Which hash algorithm should modules be signed with?"
2006 depends on MODULE_SIG
2008 This determines which sort of hashing algorithm will be used during
2009 signature generation. This algorithm _must_ be built into the kernel
2010 directly so that signature verification can take place. It is not
2011 possible to load a signed module containing the algorithm to check
2012 the signature on that module.
2014 config MODULE_SIG_SHA1
2015 bool "Sign modules with SHA-1"
2018 config MODULE_SIG_SHA224
2019 bool "Sign modules with SHA-224"
2020 select CRYPTO_SHA256
2022 config MODULE_SIG_SHA256
2023 bool "Sign modules with SHA-256"
2024 select CRYPTO_SHA256
2026 config MODULE_SIG_SHA384
2027 bool "Sign modules with SHA-384"
2028 select CRYPTO_SHA512
2030 config MODULE_SIG_SHA512
2031 bool "Sign modules with SHA-512"
2032 select CRYPTO_SHA512
2036 config MODULE_SIG_HASH
2038 depends on MODULE_SIG
2039 default "sha1" if MODULE_SIG_SHA1
2040 default "sha224" if MODULE_SIG_SHA224
2041 default "sha256" if MODULE_SIG_SHA256
2042 default "sha384" if MODULE_SIG_SHA384
2043 default "sha512" if MODULE_SIG_SHA512
2045 config MODULE_COMPRESS
2046 bool "Compress modules on installation"
2050 Compresses kernel modules when 'make modules_install' is run; gzip or
2051 xz depending on "Compression algorithm" below.
2053 module-init-tools MAY support gzip, and kmod MAY support gzip and xz.
2055 Out-of-tree kernel modules installed using Kbuild will also be
2056 compressed upon installation.
2058 Note: for modules inside an initrd or initramfs, it's more efficient
2059 to compress the whole initrd or initramfs instead.
2061 Note: This is fully compatible with signed modules.
2066 prompt "Compression algorithm"
2067 depends on MODULE_COMPRESS
2068 default MODULE_COMPRESS_GZIP
2070 This determines which sort of compression will be used during
2071 'make modules_install'.
2073 GZIP (default) and XZ are supported.
2075 config MODULE_COMPRESS_GZIP
2078 config MODULE_COMPRESS_XZ
2085 config MODULES_TREE_LOOKUP
2087 depends on PERF_EVENTS || TRACING
2089 config INIT_ALL_POSSIBLE
2092 Back when each arch used to define their own cpu_online_mask and
2093 cpu_possible_mask, some of them chose to initialize cpu_possible_mask
2094 with all 1s, and others with all 0s. When they were centralised,
2095 it was better to provide this option than to break all the archs
2096 and have several arch maintainers pursuing me down dark alleys.
2098 source "block/Kconfig"
2100 config PREEMPT_NOTIFIERS
2107 # Can be selected by architectures with broken toolchains
2108 # that get confused by correct const<->read_only section
2110 config BROKEN_RODATA
2116 Build a simple ASN.1 grammar compiler that produces a bytecode output
2117 that can be interpreted by the ASN.1 stream decoder and used to
2118 inform it as to what tags are to be expected in a stream and what
2119 functions to call on what tags.
2121 source "kernel/Kconfig.locks"
projects / firefly-linux-kernel-4.4.55.git / blob