1config ARCH 2 string 3 option env="ARCH" 4 5config KERNELVERSION 6 string 7 option env="KERNELVERSION" 8 9config DEFCONFIG_LIST 10 string 11 depends on !UML 12 option defconfig_list 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" 18 19config CONSTRUCTORS 20 bool 21 depends on !UML 22 23config IRQ_WORK 24 bool 25 26config BUILDTIME_EXTABLE_SORT 27 bool 28 29menu "General setup" 30 31config BROKEN 32 bool 33 34config BROKEN_ON_SMP 35 bool 36 depends on BROKEN || !SMP 37 default y 38 39config INIT_ENV_ARG_LIMIT 40 int 41 default 32 if !UML 42 default 128 if UML 43 help 44 Maximum of each of the number of arguments and environment 45 variables passed to init from the kernel command line. 46 47 48config CROSS_COMPILE 49 string "Cross-compiler tool prefix" 50 help 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. 55 56config COMPILE_TEST 57 bool "Compile also drivers which will not load" 58 default n 59 help 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. 65 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. 69 70config LOCALVERSION 71 string "Local version - append to kernel release" 72 help 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. 79 80config LOCALVERSION_AUTO 81 bool "Automatically append version information to the version string" 82 default y 83 help 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 86 top of tree revision. 87 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. 92 93 (The actual string used here is the first eight characters produced 94 by running the command: 95 96 $ git rev-parse --verify HEAD 97 98 which is done within the script "scripts/setlocalversion".) 99 100config HAVE_KERNEL_GZIP 101 bool 102 103config HAVE_KERNEL_BZIP2 104 bool 105 106config HAVE_KERNEL_LZMA 107 bool 108 109config HAVE_KERNEL_XZ 110 bool 111 112config HAVE_KERNEL_LZO 113 bool 114 115config HAVE_KERNEL_LZ4 116 bool 117 118choice 119 prompt "Kernel compression mode" 120 default KERNEL_GZIP 121 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 122 help 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. 128 129 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) 133 134 High compression options are mostly useful for users, who 135 are low on disk space (embedded systems), but for whom ram 136 size matters less. 137 138 If in doubt, select 'gzip' 139 140config KERNEL_GZIP 141 bool "Gzip" 142 depends on HAVE_KERNEL_GZIP 143 help 144 The old and tried gzip compression. It provides a good balance 145 between compression ratio and decompression speed. 146 147config KERNEL_BZIP2 148 bool "Bzip2" 149 depends on HAVE_KERNEL_BZIP2 150 help 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. 156 157config KERNEL_LZMA 158 bool "LZMA" 159 depends on HAVE_KERNEL_LZMA 160 help 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. 164 165config KERNEL_XZ 166 bool "XZ" 167 depends on HAVE_KERNEL_XZ 168 help 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. 175 176 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. 179 180config KERNEL_LZO 181 bool "LZO" 182 depends on HAVE_KERNEL_LZO 183 help 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. 187 188config KERNEL_LZ4 189 bool "LZ4" 190 depends on HAVE_KERNEL_LZ4 191 help 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/>. 195 196 Its compression ratio is worse than LZO. The size of the kernel 197 is about 8% bigger than LZO. But the decompression speed is 198 faster than LZO. 199 200endchoice 201 202config DEFAULT_HOSTNAME 203 string "Default hostname" 204 default "(none)" 205 help 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. 210 211config SWAP 212 bool "Support for paging of anonymous memory (swap)" 213 depends on MMU && BLOCK 214 default y 215 help 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. 220 221config SYSVIPC 222 bool "System V IPC" 223 ---help--- 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. 231 232 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>. 235 236config SYSVIPC_SYSCTL 237 bool 238 depends on SYSVIPC 239 depends on SYSCTL 240 default y 241 242config POSIX_MQUEUE 243 bool "POSIX Message Queues" 244 depends on NET 245 ---help--- 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. 251 252 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. 255 256 If unsure, say Y. 257 258config POSIX_MQUEUE_SYSCTL 259 bool 260 depends on POSIX_MQUEUE 261 depends on SYSCTL 262 default y 263 264config CROSS_MEMORY_ATTACH 265 bool "Enable process_vm_readv/writev syscalls" 266 depends on MMU 267 default y 268 help 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. 273 274config FHANDLE 275 bool "open by fhandle syscalls" 276 select EXPORTFS 277 help 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) 284 syscalls. 285 286config USELIB 287 bool "uselib syscall" 288 default y 289 help 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. 295 296config AUDIT 297 bool "Auditing support" 298 depends on NET 299 help 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. 304 305config HAVE_ARCH_AUDITSYSCALL 306 bool 307 308config AUDITSYSCALL 309 bool "Enable system-call auditing support" 310 depends on AUDIT && HAVE_ARCH_AUDITSYSCALL 311 default y if SECURITY_SELINUX 312 help 313 Enable low-overhead system-call auditing infrastructure that 314 can be used independently or with another kernel subsystem, 315 such as SELinux. 316 317config AUDIT_WATCH 318 def_bool y 319 depends on AUDITSYSCALL 320 select FSNOTIFY 321 322config AUDIT_TREE 323 def_bool y 324 depends on AUDITSYSCALL 325 select FSNOTIFY 326 327source "kernel/irq/Kconfig" 328source "kernel/time/Kconfig" 329 330menu "CPU/Task time and stats accounting" 331 332config VIRT_CPU_ACCOUNTING 333 bool 334 335choice 336 prompt "Cputime accounting" 337 default TICK_CPU_ACCOUNTING if !PPC64 338 default VIRT_CPU_ACCOUNTING_NATIVE if PPC64 339 340# Kind of a stub config for the pure tick based cputime accounting 341config TICK_CPU_ACCOUNTING 342 bool "Simple tick based cputime accounting" 343 depends on !S390 && !NO_HZ_FULL 344 help 345 This is the basic tick based cputime accounting that maintains 346 statistics about user, system and idle time spent on per jiffies 347 granularity. 348 349 If unsure, say Y. 350 351config 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 355 help 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 362 systems. 363 364config 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 370 help 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 375 overhead. 376 377 For now this is only useful if you are working on the full 378 dynticks subsystem development. 379 380 If unsure, say N. 381 382config IRQ_TIME_ACCOUNTING 383 bool "Fine granularity task level IRQ time accounting" 384 depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL 385 help 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. 390 391 If in doubt, say N here. 392 393endchoice 394 395config BSD_PROCESS_ACCT 396 bool "BSD Process Accounting" 397 depends on MULTIUSER 398 help 399 If you say Y here, a user level program will be able to instruct the 400 kernel (via a special system call) to write process accounting 401 information to a file: whenever a process exits, information about 402 that process will be appended to the file by the kernel. The 403 information includes things such as creation time, owning user, 404 command name, memory usage, controlling terminal etc. (the complete 405 list is in the struct acct in <file:include/linux/acct.h>). It is 406 up to the user level program to do useful things with this 407 information. This is generally a good idea, so say Y. 408 409config BSD_PROCESS_ACCT_V3 410 bool "BSD Process Accounting version 3 file format" 411 depends on BSD_PROCESS_ACCT 412 default n 413 help 414 If you say Y here, the process accounting information is written 415 in a new file format that also logs the process IDs of each 416 process and it's parent. Note that this file format is incompatible 417 with previous v0/v1/v2 file formats, so you will need updated tools 418 for processing it. A preliminary version of these tools is available 419 at <http://www.gnu.org/software/acct/>. 420 421config TASKSTATS 422 bool "Export task/process statistics through netlink" 423 depends on NET 424 depends on MULTIUSER 425 default n 426 help 427 Export selected statistics for tasks/processes through the 428 generic netlink interface. Unlike BSD process accounting, the 429 statistics are available during the lifetime of tasks/processes as 430 responses to commands. Like BSD accounting, they are sent to user 431 space on task exit. 432 433 Say N if unsure. 434 435config TASK_DELAY_ACCT 436 bool "Enable per-task delay accounting" 437 depends on TASKSTATS 438 select SCHED_INFO 439 help 440 Collect information on time spent by a task waiting for system 441 resources like cpu, synchronous block I/O completion and swapping 442 in pages. Such statistics can help in setting a task's priorities 443 relative to other tasks for cpu, io, rss limits etc. 444 445 Say N if unsure. 446 447config TASK_XACCT 448 bool "Enable extended accounting over taskstats" 449 depends on TASKSTATS 450 help 451 Collect extended task accounting data and send the data 452 to userland for processing over the taskstats interface. 453 454 Say N if unsure. 455 456config TASK_IO_ACCOUNTING 457 bool "Enable per-task storage I/O accounting" 458 depends on TASK_XACCT 459 help 460 Collect information on the number of bytes of storage I/O which this 461 task has caused. 462 463 Say N if unsure. 464 465endmenu # "CPU/Task time and stats accounting" 466 467menu "RCU Subsystem" 468 469config TREE_RCU 470 bool 471 default y if !PREEMPT && SMP 472 help 473 This option selects the RCU implementation that is 474 designed for very large SMP system with hundreds or 475 thousands of CPUs. It also scales down nicely to 476 smaller systems. 477 478config PREEMPT_RCU 479 bool 480 default y if PREEMPT 481 help 482 This option selects the RCU implementation that is 483 designed for very large SMP systems with hundreds or 484 thousands of CPUs, but for which real-time response 485 is also required. It also scales down nicely to 486 smaller systems. 487 488 Select this option if you are unsure. 489 490config TINY_RCU 491 bool 492 default y if !PREEMPT && !SMP 493 help 494 This option selects the RCU implementation that is 495 designed for UP systems from which real-time response 496 is not required. This option greatly reduces the 497 memory footprint of RCU. 498 499config RCU_EXPERT 500 bool "Make expert-level adjustments to RCU configuration" 501 default n 502 help 503 This option needs to be enabled if you wish to make 504 expert-level adjustments to RCU configuration. By default, 505 no such adjustments can be made, which has the often-beneficial 506 side-effect of preventing "make oldconfig" from asking you all 507 sorts of detailed questions about how you would like numerous 508 obscure RCU options to be set up. 509 510 Say Y if you need to make expert-level adjustments to RCU. 511 512 Say N if you are unsure. 513 514config SRCU 515 bool 516 help 517 This option selects the sleepable version of RCU. This version 518 permits arbitrary sleeping or blocking within RCU read-side critical 519 sections. 520 521config TASKS_RCU 522 bool 523 default n 524 select SRCU 525 help 526 This option enables a task-based RCU implementation that uses 527 only voluntary context switch (not preemption!), idle, and 528 user-mode execution as quiescent states. 529 530config RCU_STALL_COMMON 531 def_bool ( TREE_RCU || PREEMPT_RCU || RCU_TRACE ) 532 help 533 This option enables RCU CPU stall code that is common between 534 the TINY and TREE variants of RCU. The purpose is to allow 535 the tiny variants to disable RCU CPU stall warnings, while 536 making these warnings mandatory for the tree variants. 537 538config CONTEXT_TRACKING 539 bool 540 541config CONTEXT_TRACKING_FORCE 542 bool "Force context tracking" 543 depends on CONTEXT_TRACKING 544 default y if !NO_HZ_FULL 545 help 546 The major pre-requirement for full dynticks to work is to 547 support the context tracking subsystem. But there are also 548 other dependencies to provide in order to make the full 549 dynticks working. 550 551 This option stands for testing when an arch implements the 552 context tracking backend but doesn't yet fullfill all the 553 requirements to make the full dynticks feature working. 554 Without the full dynticks, there is no way to test the support 555 for context tracking and the subsystems that rely on it: RCU 556 userspace extended quiescent state and tickless cputime 557 accounting. This option copes with the absence of the full 558 dynticks subsystem by forcing the context tracking on all 559 CPUs in the system. 560 561 Say Y only if you're working on the development of an 562 architecture backend for the context tracking. 563 564 Say N otherwise, this option brings an overhead that you 565 don't want in production. 566 567 568config RCU_FANOUT 569 int "Tree-based hierarchical RCU fanout value" 570 range 2 64 if 64BIT 571 range 2 32 if !64BIT 572 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT 573 default 64 if 64BIT 574 default 32 if !64BIT 575 help 576 This option controls the fanout of hierarchical implementations 577 of RCU, allowing RCU to work efficiently on machines with 578 large numbers of CPUs. This value must be at least the fourth 579 root of NR_CPUS, which allows NR_CPUS to be insanely large. 580 The default value of RCU_FANOUT should be used for production 581 systems, but if you are stress-testing the RCU implementation 582 itself, small RCU_FANOUT values allow you to test large-system 583 code paths on small(er) systems. 584 585 Select a specific number if testing RCU itself. 586 Take the default if unsure. 587 588config RCU_FANOUT_LEAF 589 int "Tree-based hierarchical RCU leaf-level fanout value" 590 range 2 64 if 64BIT 591 range 2 32 if !64BIT 592 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT 593 default 16 594 help 595 This option controls the leaf-level fanout of hierarchical 596 implementations of RCU, and allows trading off cache misses 597 against lock contention. Systems that synchronize their 598 scheduling-clock interrupts for energy-efficiency reasons will 599 want the default because the smaller leaf-level fanout keeps 600 lock contention levels acceptably low. Very large systems 601 (hundreds or thousands of CPUs) will instead want to set this 602 value to the maximum value possible in order to reduce the 603 number of cache misses incurred during RCU's grace-period 604 initialization. These systems tend to run CPU-bound, and thus 605 are not helped by synchronized interrupts, and thus tend to 606 skew them, which reduces lock contention enough that large 607 leaf-level fanouts work well. 608 609 Select a specific number if testing RCU itself. 610 611 Select the maximum permissible value for large systems. 612 613 Take the default if unsure. 614 615config RCU_FAST_NO_HZ 616 bool "Accelerate last non-dyntick-idle CPU's grace periods" 617 depends on NO_HZ_COMMON && SMP && RCU_EXPERT 618 default n 619 help 620 This option permits CPUs to enter dynticks-idle state even if 621 they have RCU callbacks queued, and prevents RCU from waking 622 these CPUs up more than roughly once every four jiffies (by 623 default, you can adjust this using the rcutree.rcu_idle_gp_delay 624 parameter), thus improving energy efficiency. On the other 625 hand, this option increases the duration of RCU grace periods, 626 for example, slowing down synchronize_rcu(). 627 628 Say Y if energy efficiency is critically important, and you 629 don't care about increased grace-period durations. 630 631 Say N if you are unsure. 632 633config TREE_RCU_TRACE 634 def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU ) 635 select DEBUG_FS 636 help 637 This option provides tracing for the TREE_RCU and 638 PREEMPT_RCU implementations, permitting Makefile to 639 trivially select kernel/rcutree_trace.c. 640 641config RCU_BOOST 642 bool "Enable RCU priority boosting" 643 depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT 644 default n 645 help 646 This option boosts the priority of preempted RCU readers that 647 block the current preemptible RCU grace period for too long. 648 This option also prevents heavy loads from blocking RCU 649 callback invocation for all flavors of RCU. 650 651 Say Y here if you are working with real-time apps or heavy loads 652 Say N here if you are unsure. 653 654config RCU_KTHREAD_PRIO 655 int "Real-time priority to use for RCU worker threads" 656 range 1 99 if RCU_BOOST 657 range 0 99 if !RCU_BOOST 658 default 1 if RCU_BOOST 659 default 0 if !RCU_BOOST 660 depends on RCU_EXPERT 661 help 662 This option specifies the SCHED_FIFO priority value that will be 663 assigned to the rcuc/n and rcub/n threads and is also the value 664 used for RCU_BOOST (if enabled). If you are working with a 665 real-time application that has one or more CPU-bound threads 666 running at a real-time priority level, you should set 667 RCU_KTHREAD_PRIO to a priority higher than the highest-priority 668 real-time CPU-bound application thread. The default RCU_KTHREAD_PRIO 669 value of 1 is appropriate in the common case, which is real-time 670 applications that do not have any CPU-bound threads. 671 672 Some real-time applications might not have a single real-time 673 thread that saturates a given CPU, but instead might have 674 multiple real-time threads that, taken together, fully utilize 675 that CPU. In this case, you should set RCU_KTHREAD_PRIO to 676 a priority higher than the lowest-priority thread that is 677 conspiring to prevent the CPU from running any non-real-time 678 tasks. For example, if one thread at priority 10 and another 679 thread at priority 5 are between themselves fully consuming 680 the CPU time on a given CPU, then RCU_KTHREAD_PRIO should be 681 set to priority 6 or higher. 682 683 Specify the real-time priority, or take the default if unsure. 684 685config RCU_BOOST_DELAY 686 int "Milliseconds to delay boosting after RCU grace-period start" 687 range 0 3000 688 depends on RCU_BOOST 689 default 500 690 help 691 This option specifies the time to wait after the beginning of 692 a given grace period before priority-boosting preempted RCU 693 readers blocking that grace period. Note that any RCU reader 694 blocking an expedited RCU grace period is boosted immediately. 695 696 Accept the default if unsure. 697 698config RCU_NOCB_CPU 699 bool "Offload RCU callback processing from boot-selected CPUs" 700 depends on TREE_RCU || PREEMPT_RCU 701 depends on RCU_EXPERT || NO_HZ_FULL 702 default n 703 help 704 Use this option to reduce OS jitter for aggressive HPC or 705 real-time workloads. It can also be used to offload RCU 706 callback invocation to energy-efficient CPUs in battery-powered 707 asymmetric multiprocessors. 708 709 This option offloads callback invocation from the set of 710 CPUs specified at boot time by the rcu_nocbs parameter. 711 For each such CPU, a kthread ("rcuox/N") will be created to 712 invoke callbacks, where the "N" is the CPU being offloaded, 713 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and 714 "s" for RCU-sched. Nothing prevents this kthread from running 715 on the specified CPUs, but (1) the kthreads may be preempted 716 between each callback, and (2) affinity or cgroups can be used 717 to force the kthreads to run on whatever set of CPUs is desired. 718 719 Say Y here if you want to help to debug reduced OS jitter. 720 Say N here if you are unsure. 721 722choice 723 prompt "Build-forced no-CBs CPUs" 724 default RCU_NOCB_CPU_NONE 725 depends on RCU_NOCB_CPU 726 help 727 This option allows no-CBs CPUs (whose RCU callbacks are invoked 728 from kthreads rather than from softirq context) to be specified 729 at build time. Additional no-CBs CPUs may be specified by 730 the rcu_nocbs= boot parameter. 731 732config RCU_NOCB_CPU_NONE 733 bool "No build_forced no-CBs CPUs" 734 help 735 This option does not force any of the CPUs to be no-CBs CPUs. 736 Only CPUs designated by the rcu_nocbs= boot parameter will be 737 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU 738 kthreads whose names begin with "rcuo". All other CPUs will 739 invoke their own RCU callbacks in softirq context. 740 741 Select this option if you want to choose no-CBs CPUs at 742 boot time, for example, to allow testing of different no-CBs 743 configurations without having to rebuild the kernel each time. 744 745config RCU_NOCB_CPU_ZERO 746 bool "CPU 0 is a build_forced no-CBs CPU" 747 help 748 This option forces CPU 0 to be a no-CBs CPU, so that its RCU 749 callbacks are invoked by a per-CPU kthread whose name begins 750 with "rcuo". Additional CPUs may be designated as no-CBs 751 CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs. 752 All other CPUs will invoke their own RCU callbacks in softirq 753 context. 754 755 Select this if CPU 0 needs to be a no-CBs CPU for real-time 756 or energy-efficiency reasons, but the real reason it exists 757 is to ensure that randconfig testing covers mixed systems. 758 759config RCU_NOCB_CPU_ALL 760 bool "All CPUs are build_forced no-CBs CPUs" 761 help 762 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= 763 boot parameter will be ignored. All CPUs' RCU callbacks will 764 be executed in the context of per-CPU rcuo kthreads created for 765 this purpose. Assuming that the kthreads whose names start with 766 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter 767 on the remaining CPUs, but might decrease memory locality during 768 RCU-callback invocation, thus potentially degrading throughput. 769 770 Select this if all CPUs need to be no-CBs CPUs for real-time 771 or energy-efficiency reasons. 772 773endchoice 774 775config RCU_EXPEDITE_BOOT 776 bool 777 default n 778 help 779 This option enables expedited grace periods at boot time, 780 as if rcu_expedite_gp() had been invoked early in boot. 781 The corresponding rcu_unexpedite_gp() is invoked from 782 rcu_end_inkernel_boot(), which is intended to be invoked 783 at the end of the kernel-only boot sequence, just before 784 init is exec'ed. 785 786 Accept the default if unsure. 787 788endmenu # "RCU Subsystem" 789 790config BUILD_BIN2C 791 bool 792 default n 793 794config IKCONFIG 795 tristate "Kernel .config support" 796 select BUILD_BIN2C 797 ---help--- 798 This option enables the complete Linux kernel ".config" file 799 contents to be saved in the kernel. It provides documentation 800 of which kernel options are used in a running kernel or in an 801 on-disk kernel. This information can be extracted from the kernel 802 image file with the script scripts/extract-ikconfig and used as 803 input to rebuild the current kernel or to build another kernel. 804 It can also be extracted from a running kernel by reading 805 /proc/config.gz if enabled (below). 806 807config IKCONFIG_PROC 808 bool "Enable access to .config through /proc/config.gz" 809 depends on IKCONFIG && PROC_FS 810 ---help--- 811 This option enables access to the kernel configuration file 812 through /proc/config.gz. 813 814config LOG_BUF_SHIFT 815 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" 816 range 12 25 817 default 17 818 depends on PRINTK 819 help 820 Select the minimal kernel log buffer size as a power of 2. 821 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config 822 parameter, see below. Any higher size also might be forced 823 by "log_buf_len" boot parameter. 824 825 Examples: 826 17 => 128 KB 827 16 => 64 KB 828 15 => 32 KB 829 14 => 16 KB 830 13 => 8 KB 831 12 => 4 KB 832 833config LOG_CPU_MAX_BUF_SHIFT 834 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)" 835 depends on SMP 836 range 0 21 837 default 12 if !BASE_SMALL 838 default 0 if BASE_SMALL 839 depends on PRINTK 840 help 841 This option allows to increase the default ring buffer size 842 according to the number of CPUs. The value defines the contribution 843 of each CPU as a power of 2. The used space is typically only few 844 lines however it might be much more when problems are reported, 845 e.g. backtraces. 846 847 The increased size means that a new buffer has to be allocated and 848 the original static one is unused. It makes sense only on systems 849 with more CPUs. Therefore this value is used only when the sum of 850 contributions is greater than the half of the default kernel ring 851 buffer as defined by LOG_BUF_SHIFT. The default values are set 852 so that more than 64 CPUs are needed to trigger the allocation. 853 854 Also this option is ignored when "log_buf_len" kernel parameter is 855 used as it forces an exact (power of two) size of the ring buffer. 856 857 The number of possible CPUs is used for this computation ignoring 858 hotplugging making the compuation optimal for the the worst case 859 scenerio while allowing a simple algorithm to be used from bootup. 860 861 Examples shift values and their meaning: 862 17 => 128 KB for each CPU 863 16 => 64 KB for each CPU 864 15 => 32 KB for each CPU 865 14 => 16 KB for each CPU 866 13 => 8 KB for each CPU 867 12 => 4 KB for each CPU 868 869# 870# Architectures with an unreliable sched_clock() should select this: 871# 872config HAVE_UNSTABLE_SCHED_CLOCK 873 bool 874 875config GENERIC_SCHED_CLOCK 876 bool 877 878# 879# For architectures that want to enable the support for NUMA-affine scheduler 880# balancing logic: 881# 882config ARCH_SUPPORTS_NUMA_BALANCING 883 bool 884 885# 886# For architectures that know their GCC __int128 support is sound 887# 888config ARCH_SUPPORTS_INT128 889 bool 890 891# For architectures that (ab)use NUMA to represent different memory regions 892# all cpu-local but of different latencies, such as SuperH. 893# 894config ARCH_WANT_NUMA_VARIABLE_LOCALITY 895 bool 896 897config NUMA_BALANCING 898 bool "Memory placement aware NUMA scheduler" 899 depends on ARCH_SUPPORTS_NUMA_BALANCING 900 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY 901 depends on SMP && NUMA && MIGRATION 902 help 903 This option adds support for automatic NUMA aware memory/task placement. 904 The mechanism is quite primitive and is based on migrating memory when 905 it has references to the node the task is running on. 906 907 This system will be inactive on UMA systems. 908 909config NUMA_BALANCING_DEFAULT_ENABLED 910 bool "Automatically enable NUMA aware memory/task placement" 911 default y 912 depends on NUMA_BALANCING 913 help 914 If set, automatic NUMA balancing will be enabled if running on a NUMA 915 machine. 916 917menuconfig CGROUPS 918 bool "Control Group support" 919 select KERNFS 920 select PERCPU_RWSEM 921 help 922 This option adds support for grouping sets of processes together, for 923 use with process control subsystems such as Cpusets, CFS, memory 924 controls or device isolation. 925 See 926 - Documentation/scheduler/sched-design-CFS.txt (CFS) 927 - Documentation/cgroups/ (features for grouping, isolation 928 and resource control) 929 930 Say N if unsure. 931 932if CGROUPS 933 934config CGROUP_DEBUG 935 bool "Example debug cgroup subsystem" 936 default n 937 help 938 This option enables a simple cgroup subsystem that 939 exports useful debugging information about the cgroups 940 framework. 941 942 Say N if unsure. 943 944config CGROUP_FREEZER 945 bool "Freezer cgroup subsystem" 946 help 947 Provides a way to freeze and unfreeze all tasks in a 948 cgroup. 949 950config CGROUP_PIDS 951 bool "PIDs cgroup subsystem" 952 help 953 Provides enforcement of process number limits in the scope of a 954 cgroup. Any attempt to fork more processes than is allowed in the 955 cgroup will fail. PIDs are fundamentally a global resource because it 956 is fairly trivial to reach PID exhaustion before you reach even a 957 conservative kmemcg limit. As a result, it is possible to grind a 958 system to halt without being limited by other cgroup policies. The 959 PIDs cgroup subsystem is designed to stop this from happening. 960 961 It should be noted that organisational operations (such as attaching 962 to a cgroup hierarchy will *not* be blocked by the PIDs subsystem), 963 since the PIDs limit only affects a process's ability to fork, not to 964 attach to a cgroup. 965 966config CGROUP_DEVICE 967 bool "Device controller for cgroups" 968 help 969 Provides a cgroup implementing whitelists for devices which 970 a process in the cgroup can mknod or open. 971 972config CPUSETS 973 bool "Cpuset support" 974 help 975 This option will let you create and manage CPUSETs which 976 allow dynamically partitioning a system into sets of CPUs and 977 Memory Nodes and assigning tasks to run only within those sets. 978 This is primarily useful on large SMP or NUMA systems. 979 980 Say N if unsure. 981 982config PROC_PID_CPUSET 983 bool "Include legacy /proc/<pid>/cpuset file" 984 depends on CPUSETS 985 default y 986 987config CGROUP_CPUACCT 988 bool "Simple CPU accounting cgroup subsystem" 989 help 990 Provides a simple Resource Controller for monitoring the 991 total CPU consumed by the tasks in a cgroup. 992 993config PAGE_COUNTER 994 bool 995 996config MEMCG 997 bool "Memory Resource Controller for Control Groups" 998 select PAGE_COUNTER 999 select EVENTFD 1000 help 1001 Provides a memory resource controller that manages both anonymous 1002 memory and page cache. (See Documentation/cgroups/memory.txt) 1003 1004config MEMCG_SWAP 1005 bool "Memory Resource Controller Swap Extension" 1006 depends on MEMCG && SWAP 1007 help 1008 Add swap management feature to memory resource controller. When you 1009 enable this, you can limit mem+swap usage per cgroup. In other words, 1010 when you disable this, memory resource controller has no cares to 1011 usage of swap...a process can exhaust all of the swap. This extension 1012 is useful when you want to avoid exhaustion swap but this itself 1013 adds more overheads and consumes memory for remembering information. 1014 Especially if you use 32bit system or small memory system, please 1015 be careful about enabling this. When memory resource controller 1016 is disabled by boot option, this will be automatically disabled and 1017 there will be no overhead from this. Even when you set this config=y, 1018 if boot option "swapaccount=0" is set, swap will not be accounted. 1019 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page 1020 size is 4096bytes, 512k per 1Gbytes of swap. 1021config MEMCG_SWAP_ENABLED 1022 bool "Memory Resource Controller Swap Extension enabled by default" 1023 depends on MEMCG_SWAP 1024 default y 1025 help 1026 Memory Resource Controller Swap Extension comes with its price in 1027 a bigger memory consumption. General purpose distribution kernels 1028 which want to enable the feature but keep it disabled by default 1029 and let the user enable it by swapaccount=1 boot command line 1030 parameter should have this option unselected. 1031 For those who want to have the feature enabled by default should 1032 select this option (if, for some reason, they need to disable it 1033 then swapaccount=0 does the trick). 1034config MEMCG_KMEM 1035 bool "Memory Resource Controller Kernel Memory accounting" 1036 depends on MEMCG 1037 depends on SLUB || SLAB 1038 help 1039 The Kernel Memory extension for Memory Resource Controller can limit 1040 the amount of memory used by kernel objects in the system. Those are 1041 fundamentally different from the entities handled by the standard 1042 Memory Controller, which are page-based, and can be swapped. Users of 1043 the kmem extension can use it to guarantee that no group of processes 1044 will ever exhaust kernel resources alone. 1045 1046config CGROUP_HUGETLB 1047 bool "HugeTLB Resource Controller for Control Groups" 1048 depends on HUGETLB_PAGE 1049 select PAGE_COUNTER 1050 default n 1051 help 1052 Provides a cgroup Resource Controller for HugeTLB pages. 1053 When you enable this, you can put a per cgroup limit on HugeTLB usage. 1054 The limit is enforced during page fault. Since HugeTLB doesn't 1055 support page reclaim, enforcing the limit at page fault time implies 1056 that, the application will get SIGBUS signal if it tries to access 1057 HugeTLB pages beyond its limit. This requires the application to know 1058 beforehand how much HugeTLB pages it would require for its use. The 1059 control group is tracked in the third page lru pointer. This means 1060 that we cannot use the controller with huge page less than 3 pages. 1061 1062config CGROUP_PERF 1063 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" 1064 depends on PERF_EVENTS && CGROUPS 1065 help 1066 This option extends the per-cpu mode to restrict monitoring to 1067 threads which belong to the cgroup specified and run on the 1068 designated cpu. 1069 1070 Say N if unsure. 1071 1072menuconfig CGROUP_SCHED 1073 bool "Group CPU scheduler" 1074 default n 1075 help 1076 This feature lets CPU scheduler recognize task groups and control CPU 1077 bandwidth allocation to such task groups. It uses cgroups to group 1078 tasks. 1079 1080if CGROUP_SCHED 1081config FAIR_GROUP_SCHED 1082 bool "Group scheduling for SCHED_OTHER" 1083 depends on CGROUP_SCHED 1084 default CGROUP_SCHED 1085 1086config CFS_BANDWIDTH 1087 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" 1088 depends on FAIR_GROUP_SCHED 1089 default n 1090 help 1091 This option allows users to define CPU bandwidth rates (limits) for 1092 tasks running within the fair group scheduler. Groups with no limit 1093 set are considered to be unconstrained and will run with no 1094 restriction. 1095 See tip/Documentation/scheduler/sched-bwc.txt for more information. 1096 1097config RT_GROUP_SCHED 1098 bool "Group scheduling for SCHED_RR/FIFO" 1099 depends on CGROUP_SCHED 1100 default n 1101 help 1102 This feature lets you explicitly allocate real CPU bandwidth 1103 to task groups. If enabled, it will also make it impossible to 1104 schedule realtime tasks for non-root users until you allocate 1105 realtime bandwidth for them. 1106 See Documentation/scheduler/sched-rt-group.txt for more information. 1107 1108endif #CGROUP_SCHED 1109 1110config BLK_CGROUP 1111 bool "Block IO controller" 1112 depends on BLOCK 1113 default n 1114 ---help--- 1115 Generic block IO controller cgroup interface. This is the common 1116 cgroup interface which should be used by various IO controlling 1117 policies. 1118 1119 Currently, CFQ IO scheduler uses it to recognize task groups and 1120 control disk bandwidth allocation (proportional time slice allocation) 1121 to such task groups. It is also used by bio throttling logic in 1122 block layer to implement upper limit in IO rates on a device. 1123 1124 This option only enables generic Block IO controller infrastructure. 1125 One needs to also enable actual IO controlling logic/policy. For 1126 enabling proportional weight division of disk bandwidth in CFQ, set 1127 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set 1128 CONFIG_BLK_DEV_THROTTLING=y. 1129 1130 See Documentation/cgroups/blkio-controller.txt for more information. 1131 1132config DEBUG_BLK_CGROUP 1133 bool "Enable Block IO controller debugging" 1134 depends on BLK_CGROUP 1135 default n 1136 ---help--- 1137 Enable some debugging help. Currently it exports additional stat 1138 files in a cgroup which can be useful for debugging. 1139 1140config CGROUP_WRITEBACK 1141 bool 1142 depends on MEMCG && BLK_CGROUP 1143 default y 1144 1145endif # CGROUPS 1146 1147config CHECKPOINT_RESTORE 1148 bool "Checkpoint/restore support" if EXPERT 1149 select PROC_CHILDREN 1150 default n 1151 help 1152 Enables additional kernel features in a sake of checkpoint/restore. 1153 In particular it adds auxiliary prctl codes to setup process text, 1154 data and heap segment sizes, and a few additional /proc filesystem 1155 entries. 1156 1157 If unsure, say N here. 1158 1159menuconfig NAMESPACES 1160 bool "Namespaces support" if EXPERT 1161 depends on MULTIUSER 1162 default !EXPERT 1163 help 1164 Provides the way to make tasks work with different objects using 1165 the same id. For example same IPC id may refer to different objects 1166 or same user id or pid may refer to different tasks when used in 1167 different namespaces. 1168 1169if NAMESPACES 1170 1171config UTS_NS 1172 bool "UTS namespace" 1173 default y 1174 help 1175 In this namespace tasks see different info provided with the 1176 uname() system call 1177 1178config IPC_NS 1179 bool "IPC namespace" 1180 depends on (SYSVIPC || POSIX_MQUEUE) 1181 default y 1182 help 1183 In this namespace tasks work with IPC ids which correspond to 1184 different IPC objects in different namespaces. 1185 1186config USER_NS 1187 bool "User namespace" 1188 default n 1189 help 1190 This allows containers, i.e. vservers, to use user namespaces 1191 to provide different user info for different servers. 1192 1193 When user namespaces are enabled in the kernel it is 1194 recommended that the MEMCG and MEMCG_KMEM options also be 1195 enabled and that user-space use the memory control groups to 1196 limit the amount of memory a memory unprivileged users can 1197 use. 1198 1199 If unsure, say N. 1200 1201config PID_NS 1202 bool "PID Namespaces" 1203 default y 1204 help 1205 Support process id namespaces. This allows having multiple 1206 processes with the same pid as long as they are in different 1207 pid namespaces. This is a building block of containers. 1208 1209config NET_NS 1210 bool "Network namespace" 1211 depends on NET 1212 default y 1213 help 1214 Allow user space to create what appear to be multiple instances 1215 of the network stack. 1216 1217endif # NAMESPACES 1218 1219config SCHED_AUTOGROUP 1220 bool "Automatic process group scheduling" 1221 select CGROUPS 1222 select CGROUP_SCHED 1223 select FAIR_GROUP_SCHED 1224 help 1225 This option optimizes the scheduler for common desktop workloads by 1226 automatically creating and populating task groups. This separation 1227 of workloads isolates aggressive CPU burners (like build jobs) from 1228 desktop applications. Task group autogeneration is currently based 1229 upon task session. 1230 1231config SYSFS_DEPRECATED 1232 bool "Enable deprecated sysfs features to support old userspace tools" 1233 depends on SYSFS 1234 default n 1235 help 1236 This option adds code that switches the layout of the "block" class 1237 devices, to not show up in /sys/class/block/, but only in 1238 /sys/block/. 1239 1240 This switch is only active when the sysfs.deprecated=1 boot option is 1241 passed or the SYSFS_DEPRECATED_V2 option is set. 1242 1243 This option allows new kernels to run on old distributions and tools, 1244 which might get confused by /sys/class/block/. Since 2007/2008 all 1245 major distributions and tools handle this just fine. 1246 1247 Recent distributions and userspace tools after 2009/2010 depend on 1248 the existence of /sys/class/block/, and will not work with this 1249 option enabled. 1250 1251 Only if you are using a new kernel on an old distribution, you might 1252 need to say Y here. 1253 1254config SYSFS_DEPRECATED_V2 1255 bool "Enable deprecated sysfs features by default" 1256 default n 1257 depends on SYSFS 1258 depends on SYSFS_DEPRECATED 1259 help 1260 Enable deprecated sysfs by default. 1261 1262 See the CONFIG_SYSFS_DEPRECATED option for more details about this 1263 option. 1264 1265 Only if you are using a new kernel on an old distribution, you might 1266 need to say Y here. Even then, odds are you would not need it 1267 enabled, you can always pass the boot option if absolutely necessary. 1268 1269config RELAY 1270 bool "Kernel->user space relay support (formerly relayfs)" 1271 help 1272 This option enables support for relay interface support in 1273 certain file systems (such as debugfs). 1274 It is designed to provide an efficient mechanism for tools and 1275 facilities to relay large amounts of data from kernel space to 1276 user space. 1277 1278 If unsure, say N. 1279 1280config BLK_DEV_INITRD 1281 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" 1282 depends on BROKEN || !FRV 1283 help 1284 The initial RAM filesystem is a ramfs which is loaded by the 1285 boot loader (loadlin or lilo) and that is mounted as root 1286 before the normal boot procedure. It is typically used to 1287 load modules needed to mount the "real" root file system, 1288 etc. See <file:Documentation/initrd.txt> for details. 1289 1290 If RAM disk support (BLK_DEV_RAM) is also included, this 1291 also enables initial RAM disk (initrd) support and adds 1292 15 Kbytes (more on some other architectures) to the kernel size. 1293 1294 If unsure say Y. 1295 1296if BLK_DEV_INITRD 1297 1298source "usr/Kconfig" 1299 1300endif 1301 1302config CC_OPTIMIZE_FOR_SIZE 1303 bool "Optimize for size" 1304 help 1305 Enabling this option will pass "-Os" instead of "-O2" to 1306 your compiler resulting in a smaller kernel. 1307 1308 If unsure, say N. 1309 1310config SYSCTL 1311 bool 1312 1313config ANON_INODES 1314 bool 1315 1316config HAVE_UID16 1317 bool 1318 1319config SYSCTL_EXCEPTION_TRACE 1320 bool 1321 help 1322 Enable support for /proc/sys/debug/exception-trace. 1323 1324config SYSCTL_ARCH_UNALIGN_NO_WARN 1325 bool 1326 help 1327 Enable support for /proc/sys/kernel/ignore-unaligned-usertrap 1328 Allows arch to define/use @no_unaligned_warning to possibly warn 1329 about unaligned access emulation going on under the hood. 1330 1331config SYSCTL_ARCH_UNALIGN_ALLOW 1332 bool 1333 help 1334 Enable support for /proc/sys/kernel/unaligned-trap 1335 Allows arches to define/use @unaligned_enabled to runtime toggle 1336 the unaligned access emulation. 1337 see arch/parisc/kernel/unaligned.c for reference 1338 1339config HAVE_PCSPKR_PLATFORM 1340 bool 1341 1342# interpreter that classic socket filters depend on 1343config BPF 1344 bool 1345 1346menuconfig EXPERT 1347 bool "Configure standard kernel features (expert users)" 1348 # Unhide debug options, to make the on-by-default options visible 1349 select DEBUG_KERNEL 1350 help 1351 This option allows certain base kernel options and settings 1352 to be disabled or tweaked. This is for specialized 1353 environments which can tolerate a "non-standard" kernel. 1354 Only use this if you really know what you are doing. 1355 1356config UID16 1357 bool "Enable 16-bit UID system calls" if EXPERT 1358 depends on HAVE_UID16 && MULTIUSER 1359 default y 1360 help 1361 This enables the legacy 16-bit UID syscall wrappers. 1362 1363config MULTIUSER 1364 bool "Multiple users, groups and capabilities support" if EXPERT 1365 default y 1366 help 1367 This option enables support for non-root users, groups and 1368 capabilities. 1369 1370 If you say N here, all processes will run with UID 0, GID 0, and all 1371 possible capabilities. Saying N here also compiles out support for 1372 system calls related to UIDs, GIDs, and capabilities, such as setuid, 1373 setgid, and capset. 1374 1375 If unsure, say Y here. 1376 1377config SGETMASK_SYSCALL 1378 bool "sgetmask/ssetmask syscalls support" if EXPERT 1379 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH 1380 ---help--- 1381 sys_sgetmask and sys_ssetmask are obsolete system calls 1382 no longer supported in libc but still enabled by default in some 1383 architectures. 1384 1385 If unsure, leave the default option here. 1386 1387config SYSFS_SYSCALL 1388 bool "Sysfs syscall support" if EXPERT 1389 default y 1390 ---help--- 1391 sys_sysfs is an obsolete system call no longer supported in libc. 1392 Note that disabling this option is more secure but might break 1393 compatibility with some systems. 1394 1395 If unsure say Y here. 1396 1397config SYSCTL_SYSCALL 1398 bool "Sysctl syscall support" if EXPERT 1399 depends on PROC_SYSCTL 1400 default n 1401 select SYSCTL 1402 ---help--- 1403 sys_sysctl uses binary paths that have been found challenging 1404 to properly maintain and use. The interface in /proc/sys 1405 using paths with ascii names is now the primary path to this 1406 information. 1407 1408 Almost nothing using the binary sysctl interface so if you are 1409 trying to save some space it is probably safe to disable this, 1410 making your kernel marginally smaller. 1411 1412 If unsure say N here. 1413 1414config KALLSYMS 1415 bool "Load all symbols for debugging/ksymoops" if EXPERT 1416 default y 1417 help 1418 Say Y here to let the kernel print out symbolic crash information and 1419 symbolic stack backtraces. This increases the size of the kernel 1420 somewhat, as all symbols have to be loaded into the kernel image. 1421 1422config KALLSYMS_ALL 1423 bool "Include all symbols in kallsyms" 1424 depends on DEBUG_KERNEL && KALLSYMS 1425 help 1426 Normally kallsyms only contains the symbols of functions for nicer 1427 OOPS messages and backtraces (i.e., symbols from the text and inittext 1428 sections). This is sufficient for most cases. And only in very rare 1429 cases (e.g., when a debugger is used) all symbols are required (e.g., 1430 names of variables from the data sections, etc). 1431 1432 This option makes sure that all symbols are loaded into the kernel 1433 image (i.e., symbols from all sections) in cost of increased kernel 1434 size (depending on the kernel configuration, it may be 300KiB or 1435 something like this). 1436 1437 Say N unless you really need all symbols. 1438 1439config PRINTK 1440 default y 1441 bool "Enable support for printk" if EXPERT 1442 select IRQ_WORK 1443 help 1444 This option enables normal printk support. Removing it 1445 eliminates most of the message strings from the kernel image 1446 and makes the kernel more or less silent. As this makes it 1447 very difficult to diagnose system problems, saying N here is 1448 strongly discouraged. 1449 1450config BUG 1451 bool "BUG() support" if EXPERT 1452 default y 1453 help 1454 Disabling this option eliminates support for BUG and WARN, reducing 1455 the size of your kernel image and potentially quietly ignoring 1456 numerous fatal conditions. You should only consider disabling this 1457 option for embedded systems with no facilities for reporting errors. 1458 Just say Y. 1459 1460config ELF_CORE 1461 depends on COREDUMP 1462 default y 1463 bool "Enable ELF core dumps" if EXPERT 1464 help 1465 Enable support for generating core dumps. Disabling saves about 4k. 1466 1467 1468config PCSPKR_PLATFORM 1469 bool "Enable PC-Speaker support" if EXPERT 1470 depends on HAVE_PCSPKR_PLATFORM 1471 select I8253_LOCK 1472 default y 1473 help 1474 This option allows to disable the internal PC-Speaker 1475 support, saving some memory. 1476 1477config BASE_FULL 1478 default y 1479 bool "Enable full-sized data structures for core" if EXPERT 1480 help 1481 Disabling this option reduces the size of miscellaneous core 1482 kernel data structures. This saves memory on small machines, 1483 but may reduce performance. 1484 1485config FUTEX 1486 bool "Enable futex support" if EXPERT 1487 default y 1488 select RT_MUTEXES 1489 help 1490 Disabling this option will cause the kernel to be built without 1491 support for "fast userspace mutexes". The resulting kernel may not 1492 run glibc-based applications correctly. 1493 1494config HAVE_FUTEX_CMPXCHG 1495 bool 1496 depends on FUTEX 1497 help 1498 Architectures should select this if futex_atomic_cmpxchg_inatomic() 1499 is implemented and always working. This removes a couple of runtime 1500 checks. 1501 1502config EPOLL 1503 bool "Enable eventpoll support" if EXPERT 1504 default y 1505 select ANON_INODES 1506 help 1507 Disabling this option will cause the kernel to be built without 1508 support for epoll family of system calls. 1509 1510config SIGNALFD 1511 bool "Enable signalfd() system call" if EXPERT 1512 select ANON_INODES 1513 default y 1514 help 1515 Enable the signalfd() system call that allows to receive signals 1516 on a file descriptor. 1517 1518 If unsure, say Y. 1519 1520config TIMERFD 1521 bool "Enable timerfd() system call" if EXPERT 1522 select ANON_INODES 1523 default y 1524 help 1525 Enable the timerfd() system call that allows to receive timer 1526 events on a file descriptor. 1527 1528 If unsure, say Y. 1529 1530config EVENTFD 1531 bool "Enable eventfd() system call" if EXPERT 1532 select ANON_INODES 1533 default y 1534 help 1535 Enable the eventfd() system call that allows to receive both 1536 kernel notification (ie. KAIO) or userspace notifications. 1537 1538 If unsure, say Y. 1539 1540# syscall, maps, verifier 1541config BPF_SYSCALL 1542 bool "Enable bpf() system call" 1543 select ANON_INODES 1544 select BPF 1545 default n 1546 help 1547 Enable the bpf() system call that allows to manipulate eBPF 1548 programs and maps via file descriptors. 1549 1550config SHMEM 1551 bool "Use full shmem filesystem" if EXPERT 1552 default y 1553 depends on MMU 1554 help 1555 The shmem is an internal filesystem used to manage shared memory. 1556 It is backed by swap and manages resource limits. It is also exported 1557 to userspace as tmpfs if TMPFS is enabled. Disabling this 1558 option replaces shmem and tmpfs with the much simpler ramfs code, 1559 which may be appropriate on small systems without swap. 1560 1561config AIO 1562 bool "Enable AIO support" if EXPERT 1563 default y 1564 help 1565 This option enables POSIX asynchronous I/O which may by used 1566 by some high performance threaded applications. Disabling 1567 this option saves about 7k. 1568 1569config ADVISE_SYSCALLS 1570 bool "Enable madvise/fadvise syscalls" if EXPERT 1571 default y 1572 help 1573 This option enables the madvise and fadvise syscalls, used by 1574 applications to advise the kernel about their future memory or file 1575 usage, improving performance. If building an embedded system where no 1576 applications use these syscalls, you can disable this option to save 1577 space. 1578 1579config PCI_QUIRKS 1580 default y 1581 bool "Enable PCI quirk workarounds" if EXPERT 1582 depends on PCI 1583 help 1584 This enables workarounds for various PCI chipset 1585 bugs/quirks. Disable this only if your target machine is 1586 unaffected by PCI quirks. 1587 1588config EMBEDDED 1589 bool "Embedded system" 1590 option allnoconfig_y 1591 select EXPERT 1592 help 1593 This option should be enabled if compiling the kernel for 1594 an embedded system so certain expert options are available 1595 for configuration. 1596 1597config HAVE_PERF_EVENTS 1598 bool 1599 help 1600 See tools/perf/design.txt for details. 1601 1602config PERF_USE_VMALLOC 1603 bool 1604 help 1605 See tools/perf/design.txt for details 1606 1607menu "Kernel Performance Events And Counters" 1608 1609config PERF_EVENTS 1610 bool "Kernel performance events and counters" 1611 default y if PROFILING 1612 depends on HAVE_PERF_EVENTS 1613 select ANON_INODES 1614 select IRQ_WORK 1615 select SRCU 1616 help 1617 Enable kernel support for various performance events provided 1618 by software and hardware. 1619 1620 Software events are supported either built-in or via the 1621 use of generic tracepoints. 1622 1623 Most modern CPUs support performance events via performance 1624 counter registers. These registers count the number of certain 1625 types of hw events: such as instructions executed, cachemisses 1626 suffered, or branches mis-predicted - without slowing down the 1627 kernel or applications. These registers can also trigger interrupts 1628 when a threshold number of events have passed - and can thus be 1629 used to profile the code that runs on that CPU. 1630 1631 The Linux Performance Event subsystem provides an abstraction of 1632 these software and hardware event capabilities, available via a 1633 system call and used by the "perf" utility in tools/perf/. It 1634 provides per task and per CPU counters, and it provides event 1635 capabilities on top of those. 1636 1637 Say Y if unsure. 1638 1639config DEBUG_PERF_USE_VMALLOC 1640 default n 1641 bool "Debug: use vmalloc to back perf mmap() buffers" 1642 depends on PERF_EVENTS && DEBUG_KERNEL && !PPC 1643 select PERF_USE_VMALLOC 1644 help 1645 Use vmalloc memory to back perf mmap() buffers. 1646 1647 Mostly useful for debugging the vmalloc code on platforms 1648 that don't require it. 1649 1650 Say N if unsure. 1651 1652endmenu 1653 1654config VM_EVENT_COUNTERS 1655 default y 1656 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1657 help 1658 VM event counters are needed for event counts to be shown. 1659 This option allows the disabling of the VM event counters 1660 on EXPERT systems. /proc/vmstat will only show page counts 1661 if VM event counters are disabled. 1662 1663config SLUB_DEBUG 1664 default y 1665 bool "Enable SLUB debugging support" if EXPERT 1666 depends on SLUB && SYSFS 1667 help 1668 SLUB has extensive debug support features. Disabling these can 1669 result in significant savings in code size. This also disables 1670 SLUB sysfs support. /sys/slab will not exist and there will be 1671 no support for cache validation etc. 1672 1673config COMPAT_BRK 1674 bool "Disable heap randomization" 1675 default y 1676 help 1677 Randomizing heap placement makes heap exploits harder, but it 1678 also breaks ancient binaries (including anything libc5 based). 1679 This option changes the bootup default to heap randomization 1680 disabled, and can be overridden at runtime by setting 1681 /proc/sys/kernel/randomize_va_space to 2. 1682 1683 On non-ancient distros (post-2000 ones) N is usually a safe choice. 1684 1685choice 1686 prompt "Choose SLAB allocator" 1687 default SLUB 1688 help 1689 This option allows to select a slab allocator. 1690 1691config SLAB 1692 bool "SLAB" 1693 help 1694 The regular slab allocator that is established and known to work 1695 well in all environments. It organizes cache hot objects in 1696 per cpu and per node queues. 1697 1698config SLUB 1699 bool "SLUB (Unqueued Allocator)" 1700 help 1701 SLUB is a slab allocator that minimizes cache line usage 1702 instead of managing queues of cached objects (SLAB approach). 1703 Per cpu caching is realized using slabs of objects instead 1704 of queues of objects. SLUB can use memory efficiently 1705 and has enhanced diagnostics. SLUB is the default choice for 1706 a slab allocator. 1707 1708config SLOB 1709 depends on EXPERT 1710 bool "SLOB (Simple Allocator)" 1711 help 1712 SLOB replaces the stock allocator with a drastically simpler 1713 allocator. SLOB is generally more space efficient but 1714 does not perform as well on large systems. 1715 1716endchoice 1717 1718config SLUB_CPU_PARTIAL 1719 default y 1720 depends on SLUB && SMP 1721 bool "SLUB per cpu partial cache" 1722 help 1723 Per cpu partial caches accellerate objects allocation and freeing 1724 that is local to a processor at the price of more indeterminism 1725 in the latency of the free. On overflow these caches will be cleared 1726 which requires the taking of locks that may cause latency spikes. 1727 Typically one would choose no for a realtime system. 1728 1729config MMAP_ALLOW_UNINITIALIZED 1730 bool "Allow mmapped anonymous memory to be uninitialized" 1731 depends on EXPERT && !MMU 1732 default n 1733 help 1734 Normally, and according to the Linux spec, anonymous memory obtained 1735 from mmap() has it's contents cleared before it is passed to 1736 userspace. Enabling this config option allows you to request that 1737 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 1738 providing a huge performance boost. If this option is not enabled, 1739 then the flag will be ignored. 1740 1741 This is taken advantage of by uClibc's malloc(), and also by 1742 ELF-FDPIC binfmt's brk and stack allocator. 1743 1744 Because of the obvious security issues, this option should only be 1745 enabled on embedded devices where you control what is run in 1746 userspace. Since that isn't generally a problem on no-MMU systems, 1747 it is normally safe to say Y here. 1748 1749 See Documentation/nommu-mmap.txt for more information. 1750 1751config SYSTEM_TRUSTED_KEYRING 1752 bool "Provide system-wide ring of trusted keys" 1753 depends on KEYS 1754 help 1755 Provide a system keyring to which trusted keys can be added. Keys in 1756 the keyring are considered to be trusted. Keys may be added at will 1757 by the kernel from compiled-in data and from hardware key stores, but 1758 userspace may only add extra keys if those keys can be verified by 1759 keys already in the keyring. 1760 1761 Keys in this keyring are used by module signature checking. 1762 1763config PROFILING 1764 bool "Profiling support" 1765 help 1766 Say Y here to enable the extended profiling support mechanisms used 1767 by profilers such as OProfile. 1768 1769# 1770# Place an empty function call at each tracepoint site. Can be 1771# dynamically changed for a probe function. 1772# 1773config TRACEPOINTS 1774 bool 1775 1776source "arch/Kconfig" 1777 1778endmenu # General setup 1779 1780config HAVE_GENERIC_DMA_COHERENT 1781 bool 1782 default n 1783 1784config SLABINFO 1785 bool 1786 depends on PROC_FS 1787 depends on SLAB || SLUB_DEBUG 1788 default y 1789 1790config RT_MUTEXES 1791 bool 1792 1793config BASE_SMALL 1794 int 1795 default 0 if BASE_FULL 1796 default 1 if !BASE_FULL 1797 1798menuconfig MODULES 1799 bool "Enable loadable module support" 1800 option modules 1801 help 1802 Kernel modules are small pieces of compiled code which can 1803 be inserted in the running kernel, rather than being 1804 permanently built into the kernel. You use the "modprobe" 1805 tool to add (and sometimes remove) them. If you say Y here, 1806 many parts of the kernel can be built as modules (by 1807 answering M instead of Y where indicated): this is most 1808 useful for infrequently used options which are not required 1809 for booting. For more information, see the man pages for 1810 modprobe, lsmod, modinfo, insmod and rmmod. 1811 1812 If you say Y here, you will need to run "make 1813 modules_install" to put the modules under /lib/modules/ 1814 where modprobe can find them (you may need to be root to do 1815 this). 1816 1817 If unsure, say Y. 1818 1819if MODULES 1820 1821config MODULE_FORCE_LOAD 1822 bool "Forced module loading" 1823 default n 1824 help 1825 Allow loading of modules without version information (ie. modprobe 1826 --force). Forced module loading sets the 'F' (forced) taint flag and 1827 is usually a really bad idea. 1828 1829config MODULE_UNLOAD 1830 bool "Module unloading" 1831 help 1832 Without this option you will not be able to unload any 1833 modules (note that some modules may not be unloadable 1834 anyway), which makes your kernel smaller, faster 1835 and simpler. If unsure, say Y. 1836 1837config MODULE_FORCE_UNLOAD 1838 bool "Forced module unloading" 1839 depends on MODULE_UNLOAD 1840 help 1841 This option allows you to force a module to unload, even if the 1842 kernel believes it is unsafe: the kernel will remove the module 1843 without waiting for anyone to stop using it (using the -f option to 1844 rmmod). This is mainly for kernel developers and desperate users. 1845 If unsure, say N. 1846 1847config MODVERSIONS 1848 bool "Module versioning support" 1849 help 1850 Usually, you have to use modules compiled with your kernel. 1851 Saying Y here makes it sometimes possible to use modules 1852 compiled for different kernels, by adding enough information 1853 to the modules to (hopefully) spot any changes which would 1854 make them incompatible with the kernel you are running. If 1855 unsure, say N. 1856 1857config MODULE_SRCVERSION_ALL 1858 bool "Source checksum for all modules" 1859 help 1860 Modules which contain a MODULE_VERSION get an extra "srcversion" 1861 field inserted into their modinfo section, which contains a 1862 sum of the source files which made it. This helps maintainers 1863 see exactly which source was used to build a module (since 1864 others sometimes change the module source without updating 1865 the version). With this option, such a "srcversion" field 1866 will be created for all modules. If unsure, say N. 1867 1868config MODULE_SIG 1869 bool "Module signature verification" 1870 depends on MODULES 1871 select SYSTEM_TRUSTED_KEYRING 1872 select KEYS 1873 select CRYPTO 1874 select ASYMMETRIC_KEY_TYPE 1875 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE 1876 select PUBLIC_KEY_ALGO_RSA 1877 select ASN1 1878 select OID_REGISTRY 1879 select X509_CERTIFICATE_PARSER 1880 help 1881 Check modules for valid signatures upon load: the signature 1882 is simply appended to the module. For more information see 1883 Documentation/module-signing.txt. 1884 1885 !!!WARNING!!! If you enable this option, you MUST make sure that the 1886 module DOES NOT get stripped after being signed. This includes the 1887 debuginfo strip done by some packagers (such as rpmbuild) and 1888 inclusion into an initramfs that wants the module size reduced. 1889 1890config MODULE_SIG_FORCE 1891 bool "Require modules to be validly signed" 1892 depends on MODULE_SIG 1893 help 1894 Reject unsigned modules or signed modules for which we don't have a 1895 key. Without this, such modules will simply taint the kernel. 1896 1897config MODULE_SIG_ALL 1898 bool "Automatically sign all modules" 1899 default y 1900 depends on MODULE_SIG 1901 help 1902 Sign all modules during make modules_install. Without this option, 1903 modules must be signed manually, using the scripts/sign-file tool. 1904 1905comment "Do not forget to sign required modules with scripts/sign-file" 1906 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL 1907 1908choice 1909 prompt "Which hash algorithm should modules be signed with?" 1910 depends on MODULE_SIG 1911 help 1912 This determines which sort of hashing algorithm will be used during 1913 signature generation. This algorithm _must_ be built into the kernel 1914 directly so that signature verification can take place. It is not 1915 possible to load a signed module containing the algorithm to check 1916 the signature on that module. 1917 1918config MODULE_SIG_SHA1 1919 bool "Sign modules with SHA-1" 1920 select CRYPTO_SHA1 1921 1922config MODULE_SIG_SHA224 1923 bool "Sign modules with SHA-224" 1924 select CRYPTO_SHA256 1925 1926config MODULE_SIG_SHA256 1927 bool "Sign modules with SHA-256" 1928 select CRYPTO_SHA256 1929 1930config MODULE_SIG_SHA384 1931 bool "Sign modules with SHA-384" 1932 select CRYPTO_SHA512 1933 1934config MODULE_SIG_SHA512 1935 bool "Sign modules with SHA-512" 1936 select CRYPTO_SHA512 1937 1938endchoice 1939 1940config MODULE_SIG_HASH 1941 string 1942 depends on MODULE_SIG 1943 default "sha1" if MODULE_SIG_SHA1 1944 default "sha224" if MODULE_SIG_SHA224 1945 default "sha256" if MODULE_SIG_SHA256 1946 default "sha384" if MODULE_SIG_SHA384 1947 default "sha512" if MODULE_SIG_SHA512 1948 1949config MODULE_COMPRESS 1950 bool "Compress modules on installation" 1951 depends on MODULES 1952 help 1953 1954 Compresses kernel modules when 'make modules_install' is run; gzip or 1955 xz depending on "Compression algorithm" below. 1956 1957 module-init-tools MAY support gzip, and kmod MAY support gzip and xz. 1958 1959 Out-of-tree kernel modules installed using Kbuild will also be 1960 compressed upon installation. 1961 1962 Note: for modules inside an initrd or initramfs, it's more efficient 1963 to compress the whole initrd or initramfs instead. 1964 1965 Note: This is fully compatible with signed modules. 1966 1967 If in doubt, say N. 1968 1969choice 1970 prompt "Compression algorithm" 1971 depends on MODULE_COMPRESS 1972 default MODULE_COMPRESS_GZIP 1973 help 1974 This determines which sort of compression will be used during 1975 'make modules_install'. 1976 1977 GZIP (default) and XZ are supported. 1978 1979config MODULE_COMPRESS_GZIP 1980 bool "GZIP" 1981 1982config MODULE_COMPRESS_XZ 1983 bool "XZ" 1984 1985endchoice 1986 1987endif # MODULES 1988 1989config MODULES_TREE_LOOKUP 1990 def_bool y 1991 depends on PERF_EVENTS || TRACING 1992 1993config INIT_ALL_POSSIBLE 1994 bool 1995 help 1996 Back when each arch used to define their own cpu_online_mask and 1997 cpu_possible_mask, some of them chose to initialize cpu_possible_mask 1998 with all 1s, and others with all 0s. When they were centralised, 1999 it was better to provide this option than to break all the archs 2000 and have several arch maintainers pursuing me down dark alleys. 2001 2002config STOP_MACHINE 2003 bool 2004 default y 2005 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU 2006 help 2007 Need stop_machine() primitive. 2008 2009source "block/Kconfig" 2010 2011config PREEMPT_NOTIFIERS 2012 bool 2013 2014config PADATA 2015 depends on SMP 2016 bool 2017 2018# Can be selected by architectures with broken toolchains 2019# that get confused by correct const<->read_only section 2020# mappings 2021config BROKEN_RODATA 2022 bool 2023 2024config ASN1 2025 tristate 2026 help 2027 Build a simple ASN.1 grammar compiler that produces a bytecode output 2028 that can be interpreted by the ASN.1 stream decoder and used to 2029 inform it as to what tags are to be expected in a stream and what 2030 functions to call on what tags. 2031 2032source "kernel/Kconfig.locks" 2033