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 RCU_USER_QS 542 bool 543 help 544 This option sets hooks on kernel / userspace boundaries and 545 puts RCU in extended quiescent state when the CPU runs in 546 userspace. It means that when a CPU runs in userspace, it is 547 excluded from the global RCU state machine and thus doesn't 548 try to keep the timer tick on for RCU. 549 550config CONTEXT_TRACKING_FORCE 551 bool "Force context tracking" 552 depends on CONTEXT_TRACKING 553 default y if !NO_HZ_FULL 554 help 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 558 dynticks working. 559 560 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 568 CPUs in the system. 569 570 Say Y only if you're working on the development of an 571 architecture backend for the context tracking. 572 573 Say N otherwise, this option brings an overhead that you 574 don't want in production. 575 576 577config RCU_FANOUT 578 int "Tree-based hierarchical RCU fanout value" 579 range 2 64 if 64BIT 580 range 2 32 if !64BIT 581 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT 582 default 64 if 64BIT 583 default 32 if !64BIT 584 help 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. 593 594 Select a specific number if testing RCU itself. 595 Take the default if unsure. 596 597config RCU_FANOUT_LEAF 598 int "Tree-based hierarchical RCU leaf-level fanout value" 599 range 2 64 if 64BIT 600 range 2 32 if !64BIT 601 depends on (TREE_RCU || PREEMPT_RCU) && RCU_EXPERT 602 default 16 603 help 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. 617 618 Select a specific number if testing RCU itself. 619 620 Select the maximum permissible value for large systems. 621 622 Take the default if unsure. 623 624config RCU_FAST_NO_HZ 625 bool "Accelerate last non-dyntick-idle CPU's grace periods" 626 depends on NO_HZ_COMMON && SMP && RCU_EXPERT 627 default n 628 help 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(). 636 637 Say Y if energy efficiency is critically important, and you 638 don't care about increased grace-period durations. 639 640 Say N if you are unsure. 641 642config TREE_RCU_TRACE 643 def_bool RCU_TRACE && ( TREE_RCU || PREEMPT_RCU ) 644 select DEBUG_FS 645 help 646 This option provides tracing for the TREE_RCU and 647 PREEMPT_RCU implementations, permitting Makefile to 648 trivially select kernel/rcutree_trace.c. 649 650config RCU_BOOST 651 bool "Enable RCU priority boosting" 652 depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT 653 default n 654 help 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. 659 660 Say Y here if you are working with real-time apps or heavy loads 661 Say N here if you are unsure. 662 663config 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 670 help 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. 680 681 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. 691 692 Specify the real-time priority, or take the default if unsure. 693 694config RCU_BOOST_DELAY 695 int "Milliseconds to delay boosting after RCU grace-period start" 696 range 0 3000 697 depends on RCU_BOOST 698 default 500 699 help 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. 704 705 Accept the default if unsure. 706 707config RCU_NOCB_CPU 708 bool "Offload RCU callback processing from boot-selected CPUs" 709 depends on TREE_RCU || PREEMPT_RCU 710 default n 711 help 712 Use this option to reduce OS jitter for aggressive HPC or 713 real-time workloads. It can also be used to offload RCU 714 callback invocation to energy-efficient CPUs in battery-powered 715 asymmetric multiprocessors. 716 717 This option offloads callback invocation from the set of 718 CPUs specified at boot time by the rcu_nocbs parameter. 719 For each such CPU, a kthread ("rcuox/N") will be created to 720 invoke callbacks, where the "N" is the CPU being offloaded, 721 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and 722 "s" for RCU-sched. Nothing prevents this kthread from running 723 on the specified CPUs, but (1) the kthreads may be preempted 724 between each callback, and (2) affinity or cgroups can be used 725 to force the kthreads to run on whatever set of CPUs is desired. 726 727 Say Y here if you want to help to debug reduced OS jitter. 728 Say N here if you are unsure. 729 730choice 731 prompt "Build-forced no-CBs CPUs" 732 default RCU_NOCB_CPU_NONE 733 depends on RCU_NOCB_CPU 734 help 735 This option allows no-CBs CPUs (whose RCU callbacks are invoked 736 from kthreads rather than from softirq context) to be specified 737 at build time. Additional no-CBs CPUs may be specified by 738 the rcu_nocbs= boot parameter. 739 740config RCU_NOCB_CPU_NONE 741 bool "No build_forced no-CBs CPUs" 742 help 743 This option does not force any of the CPUs to be no-CBs CPUs. 744 Only CPUs designated by the rcu_nocbs= boot parameter will be 745 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU 746 kthreads whose names begin with "rcuo". All other CPUs will 747 invoke their own RCU callbacks in softirq context. 748 749 Select this option if you want to choose no-CBs CPUs at 750 boot time, for example, to allow testing of different no-CBs 751 configurations without having to rebuild the kernel each time. 752 753config RCU_NOCB_CPU_ZERO 754 bool "CPU 0 is a build_forced no-CBs CPU" 755 help 756 This option forces CPU 0 to be a no-CBs CPU, so that its RCU 757 callbacks are invoked by a per-CPU kthread whose name begins 758 with "rcuo". Additional CPUs may be designated as no-CBs 759 CPUs using the rcu_nocbs= boot parameter will be no-CBs CPUs. 760 All other CPUs will invoke their own RCU callbacks in softirq 761 context. 762 763 Select this if CPU 0 needs to be a no-CBs CPU for real-time 764 or energy-efficiency reasons, but the real reason it exists 765 is to ensure that randconfig testing covers mixed systems. 766 767config RCU_NOCB_CPU_ALL 768 bool "All CPUs are build_forced no-CBs CPUs" 769 help 770 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= 771 boot parameter will be ignored. All CPUs' RCU callbacks will 772 be executed in the context of per-CPU rcuo kthreads created for 773 this purpose. Assuming that the kthreads whose names start with 774 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter 775 on the remaining CPUs, but might decrease memory locality during 776 RCU-callback invocation, thus potentially degrading throughput. 777 778 Select this if all CPUs need to be no-CBs CPUs for real-time 779 or energy-efficiency reasons. 780 781endchoice 782 783config RCU_EXPEDITE_BOOT 784 bool 785 default n 786 help 787 This option enables expedited grace periods at boot time, 788 as if rcu_expedite_gp() had been invoked early in boot. 789 The corresponding rcu_unexpedite_gp() is invoked from 790 rcu_end_inkernel_boot(), which is intended to be invoked 791 at the end of the kernel-only boot sequence, just before 792 init is exec'ed. 793 794 Accept the default if unsure. 795 796endmenu # "RCU Subsystem" 797 798config BUILD_BIN2C 799 bool 800 default n 801 802config IKCONFIG 803 tristate "Kernel .config support" 804 select BUILD_BIN2C 805 ---help--- 806 This option enables the complete Linux kernel ".config" file 807 contents to be saved in the kernel. It provides documentation 808 of which kernel options are used in a running kernel or in an 809 on-disk kernel. This information can be extracted from the kernel 810 image file with the script scripts/extract-ikconfig and used as 811 input to rebuild the current kernel or to build another kernel. 812 It can also be extracted from a running kernel by reading 813 /proc/config.gz if enabled (below). 814 815config IKCONFIG_PROC 816 bool "Enable access to .config through /proc/config.gz" 817 depends on IKCONFIG && PROC_FS 818 ---help--- 819 This option enables access to the kernel configuration file 820 through /proc/config.gz. 821 822config LOG_BUF_SHIFT 823 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" 824 range 12 25 825 default 17 826 depends on PRINTK 827 help 828 Select the minimal kernel log buffer size as a power of 2. 829 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config 830 parameter, see below. Any higher size also might be forced 831 by "log_buf_len" boot parameter. 832 833 Examples: 834 17 => 128 KB 835 16 => 64 KB 836 15 => 32 KB 837 14 => 16 KB 838 13 => 8 KB 839 12 => 4 KB 840 841config LOG_CPU_MAX_BUF_SHIFT 842 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)" 843 depends on SMP 844 range 0 21 845 default 12 if !BASE_SMALL 846 default 0 if BASE_SMALL 847 depends on PRINTK 848 help 849 This option allows to increase the default ring buffer size 850 according to the number of CPUs. The value defines the contribution 851 of each CPU as a power of 2. The used space is typically only few 852 lines however it might be much more when problems are reported, 853 e.g. backtraces. 854 855 The increased size means that a new buffer has to be allocated and 856 the original static one is unused. It makes sense only on systems 857 with more CPUs. Therefore this value is used only when the sum of 858 contributions is greater than the half of the default kernel ring 859 buffer as defined by LOG_BUF_SHIFT. The default values are set 860 so that more than 64 CPUs are needed to trigger the allocation. 861 862 Also this option is ignored when "log_buf_len" kernel parameter is 863 used as it forces an exact (power of two) size of the ring buffer. 864 865 The number of possible CPUs is used for this computation ignoring 866 hotplugging making the compuation optimal for the the worst case 867 scenerio while allowing a simple algorithm to be used from bootup. 868 869 Examples shift values and their meaning: 870 17 => 128 KB for each CPU 871 16 => 64 KB for each CPU 872 15 => 32 KB for each CPU 873 14 => 16 KB for each CPU 874 13 => 8 KB for each CPU 875 12 => 4 KB for each CPU 876 877# 878# Architectures with an unreliable sched_clock() should select this: 879# 880config HAVE_UNSTABLE_SCHED_CLOCK 881 bool 882 883config GENERIC_SCHED_CLOCK 884 bool 885 886# 887# For architectures that want to enable the support for NUMA-affine scheduler 888# balancing logic: 889# 890config ARCH_SUPPORTS_NUMA_BALANCING 891 bool 892 893# 894# For architectures that know their GCC __int128 support is sound 895# 896config ARCH_SUPPORTS_INT128 897 bool 898 899# For architectures that (ab)use NUMA to represent different memory regions 900# all cpu-local but of different latencies, such as SuperH. 901# 902config ARCH_WANT_NUMA_VARIABLE_LOCALITY 903 bool 904 905config NUMA_BALANCING 906 bool "Memory placement aware NUMA scheduler" 907 depends on ARCH_SUPPORTS_NUMA_BALANCING 908 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY 909 depends on SMP && NUMA && MIGRATION 910 help 911 This option adds support for automatic NUMA aware memory/task placement. 912 The mechanism is quite primitive and is based on migrating memory when 913 it has references to the node the task is running on. 914 915 This system will be inactive on UMA systems. 916 917config NUMA_BALANCING_DEFAULT_ENABLED 918 bool "Automatically enable NUMA aware memory/task placement" 919 default y 920 depends on NUMA_BALANCING 921 help 922 If set, automatic NUMA balancing will be enabled if running on a NUMA 923 machine. 924 925menuconfig CGROUPS 926 bool "Control Group support" 927 select KERNFS 928 select PERCPU_RWSEM 929 help 930 This option adds support for grouping sets of processes together, for 931 use with process control subsystems such as Cpusets, CFS, memory 932 controls or device isolation. 933 See 934 - Documentation/scheduler/sched-design-CFS.txt (CFS) 935 - Documentation/cgroups/ (features for grouping, isolation 936 and resource control) 937 938 Say N if unsure. 939 940if CGROUPS 941 942config CGROUP_DEBUG 943 bool "Example debug cgroup subsystem" 944 default n 945 help 946 This option enables a simple cgroup subsystem that 947 exports useful debugging information about the cgroups 948 framework. 949 950 Say N if unsure. 951 952config CGROUP_FREEZER 953 bool "Freezer cgroup subsystem" 954 help 955 Provides a way to freeze and unfreeze all tasks in a 956 cgroup. 957 958config CGROUP_DEVICE 959 bool "Device controller for cgroups" 960 help 961 Provides a cgroup implementing whitelists for devices which 962 a process in the cgroup can mknod or open. 963 964config CPUSETS 965 bool "Cpuset support" 966 help 967 This option will let you create and manage CPUSETs which 968 allow dynamically partitioning a system into sets of CPUs and 969 Memory Nodes and assigning tasks to run only within those sets. 970 This is primarily useful on large SMP or NUMA systems. 971 972 Say N if unsure. 973 974config PROC_PID_CPUSET 975 bool "Include legacy /proc/<pid>/cpuset file" 976 depends on CPUSETS 977 default y 978 979config CGROUP_CPUACCT 980 bool "Simple CPU accounting cgroup subsystem" 981 help 982 Provides a simple Resource Controller for monitoring the 983 total CPU consumed by the tasks in a cgroup. 984 985config PAGE_COUNTER 986 bool 987 988config MEMCG 989 bool "Memory Resource Controller for Control Groups" 990 select PAGE_COUNTER 991 select EVENTFD 992 help 993 Provides a memory resource controller that manages both anonymous 994 memory and page cache. (See Documentation/cgroups/memory.txt) 995 996config MEMCG_SWAP 997 bool "Memory Resource Controller Swap Extension" 998 depends on MEMCG && SWAP 999 help 1000 Add swap management feature to memory resource controller. When you 1001 enable this, you can limit mem+swap usage per cgroup. In other words, 1002 when you disable this, memory resource controller has no cares to 1003 usage of swap...a process can exhaust all of the swap. This extension 1004 is useful when you want to avoid exhaustion swap but this itself 1005 adds more overheads and consumes memory for remembering information. 1006 Especially if you use 32bit system or small memory system, please 1007 be careful about enabling this. When memory resource controller 1008 is disabled by boot option, this will be automatically disabled and 1009 there will be no overhead from this. Even when you set this config=y, 1010 if boot option "swapaccount=0" is set, swap will not be accounted. 1011 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page 1012 size is 4096bytes, 512k per 1Gbytes of swap. 1013config MEMCG_SWAP_ENABLED 1014 bool "Memory Resource Controller Swap Extension enabled by default" 1015 depends on MEMCG_SWAP 1016 default y 1017 help 1018 Memory Resource Controller Swap Extension comes with its price in 1019 a bigger memory consumption. General purpose distribution kernels 1020 which want to enable the feature but keep it disabled by default 1021 and let the user enable it by swapaccount=1 boot command line 1022 parameter should have this option unselected. 1023 For those who want to have the feature enabled by default should 1024 select this option (if, for some reason, they need to disable it 1025 then swapaccount=0 does the trick). 1026config MEMCG_KMEM 1027 bool "Memory Resource Controller Kernel Memory accounting" 1028 depends on MEMCG 1029 depends on SLUB || SLAB 1030 help 1031 The Kernel Memory extension for Memory Resource Controller can limit 1032 the amount of memory used by kernel objects in the system. Those are 1033 fundamentally different from the entities handled by the standard 1034 Memory Controller, which are page-based, and can be swapped. Users of 1035 the kmem extension can use it to guarantee that no group of processes 1036 will ever exhaust kernel resources alone. 1037 1038config CGROUP_HUGETLB 1039 bool "HugeTLB Resource Controller for Control Groups" 1040 depends on HUGETLB_PAGE 1041 select PAGE_COUNTER 1042 default n 1043 help 1044 Provides a cgroup Resource Controller for HugeTLB pages. 1045 When you enable this, you can put a per cgroup limit on HugeTLB usage. 1046 The limit is enforced during page fault. Since HugeTLB doesn't 1047 support page reclaim, enforcing the limit at page fault time implies 1048 that, the application will get SIGBUS signal if it tries to access 1049 HugeTLB pages beyond its limit. This requires the application to know 1050 beforehand how much HugeTLB pages it would require for its use. The 1051 control group is tracked in the third page lru pointer. This means 1052 that we cannot use the controller with huge page less than 3 pages. 1053 1054config CGROUP_PERF 1055 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" 1056 depends on PERF_EVENTS && CGROUPS 1057 help 1058 This option extends the per-cpu mode to restrict monitoring to 1059 threads which belong to the cgroup specified and run on the 1060 designated cpu. 1061 1062 Say N if unsure. 1063 1064menuconfig CGROUP_SCHED 1065 bool "Group CPU scheduler" 1066 default n 1067 help 1068 This feature lets CPU scheduler recognize task groups and control CPU 1069 bandwidth allocation to such task groups. It uses cgroups to group 1070 tasks. 1071 1072if CGROUP_SCHED 1073config FAIR_GROUP_SCHED 1074 bool "Group scheduling for SCHED_OTHER" 1075 depends on CGROUP_SCHED 1076 default CGROUP_SCHED 1077 1078config CFS_BANDWIDTH 1079 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" 1080 depends on FAIR_GROUP_SCHED 1081 default n 1082 help 1083 This option allows users to define CPU bandwidth rates (limits) for 1084 tasks running within the fair group scheduler. Groups with no limit 1085 set are considered to be unconstrained and will run with no 1086 restriction. 1087 See tip/Documentation/scheduler/sched-bwc.txt for more information. 1088 1089config RT_GROUP_SCHED 1090 bool "Group scheduling for SCHED_RR/FIFO" 1091 depends on CGROUP_SCHED 1092 default n 1093 help 1094 This feature lets you explicitly allocate real CPU bandwidth 1095 to task groups. If enabled, it will also make it impossible to 1096 schedule realtime tasks for non-root users until you allocate 1097 realtime bandwidth for them. 1098 See Documentation/scheduler/sched-rt-group.txt for more information. 1099 1100endif #CGROUP_SCHED 1101 1102config BLK_CGROUP 1103 bool "Block IO controller" 1104 depends on BLOCK 1105 default n 1106 ---help--- 1107 Generic block IO controller cgroup interface. This is the common 1108 cgroup interface which should be used by various IO controlling 1109 policies. 1110 1111 Currently, CFQ IO scheduler uses it to recognize task groups and 1112 control disk bandwidth allocation (proportional time slice allocation) 1113 to such task groups. It is also used by bio throttling logic in 1114 block layer to implement upper limit in IO rates on a device. 1115 1116 This option only enables generic Block IO controller infrastructure. 1117 One needs to also enable actual IO controlling logic/policy. For 1118 enabling proportional weight division of disk bandwidth in CFQ, set 1119 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set 1120 CONFIG_BLK_DEV_THROTTLING=y. 1121 1122 See Documentation/cgroups/blkio-controller.txt for more information. 1123 1124config DEBUG_BLK_CGROUP 1125 bool "Enable Block IO controller debugging" 1126 depends on BLK_CGROUP 1127 default n 1128 ---help--- 1129 Enable some debugging help. Currently it exports additional stat 1130 files in a cgroup which can be useful for debugging. 1131 1132config CGROUP_WRITEBACK 1133 bool 1134 depends on MEMCG && BLK_CGROUP 1135 default y 1136 1137endif # CGROUPS 1138 1139config CHECKPOINT_RESTORE 1140 bool "Checkpoint/restore support" if EXPERT 1141 select PROC_CHILDREN 1142 default n 1143 help 1144 Enables additional kernel features in a sake of checkpoint/restore. 1145 In particular it adds auxiliary prctl codes to setup process text, 1146 data and heap segment sizes, and a few additional /proc filesystem 1147 entries. 1148 1149 If unsure, say N here. 1150 1151menuconfig NAMESPACES 1152 bool "Namespaces support" if EXPERT 1153 depends on MULTIUSER 1154 default !EXPERT 1155 help 1156 Provides the way to make tasks work with different objects using 1157 the same id. For example same IPC id may refer to different objects 1158 or same user id or pid may refer to different tasks when used in 1159 different namespaces. 1160 1161if NAMESPACES 1162 1163config UTS_NS 1164 bool "UTS namespace" 1165 default y 1166 help 1167 In this namespace tasks see different info provided with the 1168 uname() system call 1169 1170config IPC_NS 1171 bool "IPC namespace" 1172 depends on (SYSVIPC || POSIX_MQUEUE) 1173 default y 1174 help 1175 In this namespace tasks work with IPC ids which correspond to 1176 different IPC objects in different namespaces. 1177 1178config USER_NS 1179 bool "User namespace" 1180 default n 1181 help 1182 This allows containers, i.e. vservers, to use user namespaces 1183 to provide different user info for different servers. 1184 1185 When user namespaces are enabled in the kernel it is 1186 recommended that the MEMCG and MEMCG_KMEM options also be 1187 enabled and that user-space use the memory control groups to 1188 limit the amount of memory a memory unprivileged users can 1189 use. 1190 1191 If unsure, say N. 1192 1193config PID_NS 1194 bool "PID Namespaces" 1195 default y 1196 help 1197 Support process id namespaces. This allows having multiple 1198 processes with the same pid as long as they are in different 1199 pid namespaces. This is a building block of containers. 1200 1201config NET_NS 1202 bool "Network namespace" 1203 depends on NET 1204 default y 1205 help 1206 Allow user space to create what appear to be multiple instances 1207 of the network stack. 1208 1209endif # NAMESPACES 1210 1211config SCHED_AUTOGROUP 1212 bool "Automatic process group scheduling" 1213 select CGROUPS 1214 select CGROUP_SCHED 1215 select FAIR_GROUP_SCHED 1216 help 1217 This option optimizes the scheduler for common desktop workloads by 1218 automatically creating and populating task groups. This separation 1219 of workloads isolates aggressive CPU burners (like build jobs) from 1220 desktop applications. Task group autogeneration is currently based 1221 upon task session. 1222 1223config SYSFS_DEPRECATED 1224 bool "Enable deprecated sysfs features to support old userspace tools" 1225 depends on SYSFS 1226 default n 1227 help 1228 This option adds code that switches the layout of the "block" class 1229 devices, to not show up in /sys/class/block/, but only in 1230 /sys/block/. 1231 1232 This switch is only active when the sysfs.deprecated=1 boot option is 1233 passed or the SYSFS_DEPRECATED_V2 option is set. 1234 1235 This option allows new kernels to run on old distributions and tools, 1236 which might get confused by /sys/class/block/. Since 2007/2008 all 1237 major distributions and tools handle this just fine. 1238 1239 Recent distributions and userspace tools after 2009/2010 depend on 1240 the existence of /sys/class/block/, and will not work with this 1241 option enabled. 1242 1243 Only if you are using a new kernel on an old distribution, you might 1244 need to say Y here. 1245 1246config SYSFS_DEPRECATED_V2 1247 bool "Enable deprecated sysfs features by default" 1248 default n 1249 depends on SYSFS 1250 depends on SYSFS_DEPRECATED 1251 help 1252 Enable deprecated sysfs by default. 1253 1254 See the CONFIG_SYSFS_DEPRECATED option for more details about this 1255 option. 1256 1257 Only if you are using a new kernel on an old distribution, you might 1258 need to say Y here. Even then, odds are you would not need it 1259 enabled, you can always pass the boot option if absolutely necessary. 1260 1261config RELAY 1262 bool "Kernel->user space relay support (formerly relayfs)" 1263 help 1264 This option enables support for relay interface support in 1265 certain file systems (such as debugfs). 1266 It is designed to provide an efficient mechanism for tools and 1267 facilities to relay large amounts of data from kernel space to 1268 user space. 1269 1270 If unsure, say N. 1271 1272config BLK_DEV_INITRD 1273 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" 1274 depends on BROKEN || !FRV 1275 help 1276 The initial RAM filesystem is a ramfs which is loaded by the 1277 boot loader (loadlin or lilo) and that is mounted as root 1278 before the normal boot procedure. It is typically used to 1279 load modules needed to mount the "real" root file system, 1280 etc. See <file:Documentation/initrd.txt> for details. 1281 1282 If RAM disk support (BLK_DEV_RAM) is also included, this 1283 also enables initial RAM disk (initrd) support and adds 1284 15 Kbytes (more on some other architectures) to the kernel size. 1285 1286 If unsure say Y. 1287 1288if BLK_DEV_INITRD 1289 1290source "usr/Kconfig" 1291 1292endif 1293 1294config CC_OPTIMIZE_FOR_SIZE 1295 bool "Optimize for size" 1296 help 1297 Enabling this option will pass "-Os" instead of "-O2" to 1298 your compiler resulting in a smaller kernel. 1299 1300 If unsure, say N. 1301 1302config SYSCTL 1303 bool 1304 1305config ANON_INODES 1306 bool 1307 1308config HAVE_UID16 1309 bool 1310 1311config SYSCTL_EXCEPTION_TRACE 1312 bool 1313 help 1314 Enable support for /proc/sys/debug/exception-trace. 1315 1316config SYSCTL_ARCH_UNALIGN_NO_WARN 1317 bool 1318 help 1319 Enable support for /proc/sys/kernel/ignore-unaligned-usertrap 1320 Allows arch to define/use @no_unaligned_warning to possibly warn 1321 about unaligned access emulation going on under the hood. 1322 1323config SYSCTL_ARCH_UNALIGN_ALLOW 1324 bool 1325 help 1326 Enable support for /proc/sys/kernel/unaligned-trap 1327 Allows arches to define/use @unaligned_enabled to runtime toggle 1328 the unaligned access emulation. 1329 see arch/parisc/kernel/unaligned.c for reference 1330 1331config HAVE_PCSPKR_PLATFORM 1332 bool 1333 1334# interpreter that classic socket filters depend on 1335config BPF 1336 bool 1337 1338menuconfig EXPERT 1339 bool "Configure standard kernel features (expert users)" 1340 # Unhide debug options, to make the on-by-default options visible 1341 select DEBUG_KERNEL 1342 help 1343 This option allows certain base kernel options and settings 1344 to be disabled or tweaked. This is for specialized 1345 environments which can tolerate a "non-standard" kernel. 1346 Only use this if you really know what you are doing. 1347 1348config UID16 1349 bool "Enable 16-bit UID system calls" if EXPERT 1350 depends on HAVE_UID16 && MULTIUSER 1351 default y 1352 help 1353 This enables the legacy 16-bit UID syscall wrappers. 1354 1355config MULTIUSER 1356 bool "Multiple users, groups and capabilities support" if EXPERT 1357 default y 1358 help 1359 This option enables support for non-root users, groups and 1360 capabilities. 1361 1362 If you say N here, all processes will run with UID 0, GID 0, and all 1363 possible capabilities. Saying N here also compiles out support for 1364 system calls related to UIDs, GIDs, and capabilities, such as setuid, 1365 setgid, and capset. 1366 1367 If unsure, say Y here. 1368 1369config SGETMASK_SYSCALL 1370 bool "sgetmask/ssetmask syscalls support" if EXPERT 1371 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH 1372 ---help--- 1373 sys_sgetmask and sys_ssetmask are obsolete system calls 1374 no longer supported in libc but still enabled by default in some 1375 architectures. 1376 1377 If unsure, leave the default option here. 1378 1379config SYSFS_SYSCALL 1380 bool "Sysfs syscall support" if EXPERT 1381 default y 1382 ---help--- 1383 sys_sysfs is an obsolete system call no longer supported in libc. 1384 Note that disabling this option is more secure but might break 1385 compatibility with some systems. 1386 1387 If unsure say Y here. 1388 1389config SYSCTL_SYSCALL 1390 bool "Sysctl syscall support" if EXPERT 1391 depends on PROC_SYSCTL 1392 default n 1393 select SYSCTL 1394 ---help--- 1395 sys_sysctl uses binary paths that have been found challenging 1396 to properly maintain and use. The interface in /proc/sys 1397 using paths with ascii names is now the primary path to this 1398 information. 1399 1400 Almost nothing using the binary sysctl interface so if you are 1401 trying to save some space it is probably safe to disable this, 1402 making your kernel marginally smaller. 1403 1404 If unsure say N here. 1405 1406config KALLSYMS 1407 bool "Load all symbols for debugging/ksymoops" if EXPERT 1408 default y 1409 help 1410 Say Y here to let the kernel print out symbolic crash information and 1411 symbolic stack backtraces. This increases the size of the kernel 1412 somewhat, as all symbols have to be loaded into the kernel image. 1413 1414config KALLSYMS_ALL 1415 bool "Include all symbols in kallsyms" 1416 depends on DEBUG_KERNEL && KALLSYMS 1417 help 1418 Normally kallsyms only contains the symbols of functions for nicer 1419 OOPS messages and backtraces (i.e., symbols from the text and inittext 1420 sections). This is sufficient for most cases. And only in very rare 1421 cases (e.g., when a debugger is used) all symbols are required (e.g., 1422 names of variables from the data sections, etc). 1423 1424 This option makes sure that all symbols are loaded into the kernel 1425 image (i.e., symbols from all sections) in cost of increased kernel 1426 size (depending on the kernel configuration, it may be 300KiB or 1427 something like this). 1428 1429 Say N unless you really need all symbols. 1430 1431config PRINTK 1432 default y 1433 bool "Enable support for printk" if EXPERT 1434 select IRQ_WORK 1435 help 1436 This option enables normal printk support. Removing it 1437 eliminates most of the message strings from the kernel image 1438 and makes the kernel more or less silent. As this makes it 1439 very difficult to diagnose system problems, saying N here is 1440 strongly discouraged. 1441 1442config BUG 1443 bool "BUG() support" if EXPERT 1444 default y 1445 help 1446 Disabling this option eliminates support for BUG and WARN, reducing 1447 the size of your kernel image and potentially quietly ignoring 1448 numerous fatal conditions. You should only consider disabling this 1449 option for embedded systems with no facilities for reporting errors. 1450 Just say Y. 1451 1452config ELF_CORE 1453 depends on COREDUMP 1454 default y 1455 bool "Enable ELF core dumps" if EXPERT 1456 help 1457 Enable support for generating core dumps. Disabling saves about 4k. 1458 1459 1460config PCSPKR_PLATFORM 1461 bool "Enable PC-Speaker support" if EXPERT 1462 depends on HAVE_PCSPKR_PLATFORM 1463 select I8253_LOCK 1464 default y 1465 help 1466 This option allows to disable the internal PC-Speaker 1467 support, saving some memory. 1468 1469config BASE_FULL 1470 default y 1471 bool "Enable full-sized data structures for core" if EXPERT 1472 help 1473 Disabling this option reduces the size of miscellaneous core 1474 kernel data structures. This saves memory on small machines, 1475 but may reduce performance. 1476 1477config FUTEX 1478 bool "Enable futex support" if EXPERT 1479 default y 1480 select RT_MUTEXES 1481 help 1482 Disabling this option will cause the kernel to be built without 1483 support for "fast userspace mutexes". The resulting kernel may not 1484 run glibc-based applications correctly. 1485 1486config HAVE_FUTEX_CMPXCHG 1487 bool 1488 depends on FUTEX 1489 help 1490 Architectures should select this if futex_atomic_cmpxchg_inatomic() 1491 is implemented and always working. This removes a couple of runtime 1492 checks. 1493 1494config EPOLL 1495 bool "Enable eventpoll support" if EXPERT 1496 default y 1497 select ANON_INODES 1498 help 1499 Disabling this option will cause the kernel to be built without 1500 support for epoll family of system calls. 1501 1502config SIGNALFD 1503 bool "Enable signalfd() system call" if EXPERT 1504 select ANON_INODES 1505 default y 1506 help 1507 Enable the signalfd() system call that allows to receive signals 1508 on a file descriptor. 1509 1510 If unsure, say Y. 1511 1512config TIMERFD 1513 bool "Enable timerfd() system call" if EXPERT 1514 select ANON_INODES 1515 default y 1516 help 1517 Enable the timerfd() system call that allows to receive timer 1518 events on a file descriptor. 1519 1520 If unsure, say Y. 1521 1522config EVENTFD 1523 bool "Enable eventfd() system call" if EXPERT 1524 select ANON_INODES 1525 default y 1526 help 1527 Enable the eventfd() system call that allows to receive both 1528 kernel notification (ie. KAIO) or userspace notifications. 1529 1530 If unsure, say Y. 1531 1532# syscall, maps, verifier 1533config BPF_SYSCALL 1534 bool "Enable bpf() system call" 1535 select ANON_INODES 1536 select BPF 1537 default n 1538 help 1539 Enable the bpf() system call that allows to manipulate eBPF 1540 programs and maps via file descriptors. 1541 1542config SHMEM 1543 bool "Use full shmem filesystem" if EXPERT 1544 default y 1545 depends on MMU 1546 help 1547 The shmem is an internal filesystem used to manage shared memory. 1548 It is backed by swap and manages resource limits. It is also exported 1549 to userspace as tmpfs if TMPFS is enabled. Disabling this 1550 option replaces shmem and tmpfs with the much simpler ramfs code, 1551 which may be appropriate on small systems without swap. 1552 1553config AIO 1554 bool "Enable AIO support" if EXPERT 1555 default y 1556 help 1557 This option enables POSIX asynchronous I/O which may by used 1558 by some high performance threaded applications. Disabling 1559 this option saves about 7k. 1560 1561config ADVISE_SYSCALLS 1562 bool "Enable madvise/fadvise syscalls" if EXPERT 1563 default y 1564 help 1565 This option enables the madvise and fadvise syscalls, used by 1566 applications to advise the kernel about their future memory or file 1567 usage, improving performance. If building an embedded system where no 1568 applications use these syscalls, you can disable this option to save 1569 space. 1570 1571config PCI_QUIRKS 1572 default y 1573 bool "Enable PCI quirk workarounds" if EXPERT 1574 depends on PCI 1575 help 1576 This enables workarounds for various PCI chipset 1577 bugs/quirks. Disable this only if your target machine is 1578 unaffected by PCI quirks. 1579 1580config EMBEDDED 1581 bool "Embedded system" 1582 option allnoconfig_y 1583 select EXPERT 1584 help 1585 This option should be enabled if compiling the kernel for 1586 an embedded system so certain expert options are available 1587 for configuration. 1588 1589config HAVE_PERF_EVENTS 1590 bool 1591 help 1592 See tools/perf/design.txt for details. 1593 1594config PERF_USE_VMALLOC 1595 bool 1596 help 1597 See tools/perf/design.txt for details 1598 1599menu "Kernel Performance Events And Counters" 1600 1601config PERF_EVENTS 1602 bool "Kernel performance events and counters" 1603 default y if PROFILING 1604 depends on HAVE_PERF_EVENTS 1605 select ANON_INODES 1606 select IRQ_WORK 1607 select SRCU 1608 help 1609 Enable kernel support for various performance events provided 1610 by software and hardware. 1611 1612 Software events are supported either built-in or via the 1613 use of generic tracepoints. 1614 1615 Most modern CPUs support performance events via performance 1616 counter registers. These registers count the number of certain 1617 types of hw events: such as instructions executed, cachemisses 1618 suffered, or branches mis-predicted - without slowing down the 1619 kernel or applications. These registers can also trigger interrupts 1620 when a threshold number of events have passed - and can thus be 1621 used to profile the code that runs on that CPU. 1622 1623 The Linux Performance Event subsystem provides an abstraction of 1624 these software and hardware event capabilities, available via a 1625 system call and used by the "perf" utility in tools/perf/. It 1626 provides per task and per CPU counters, and it provides event 1627 capabilities on top of those. 1628 1629 Say Y if unsure. 1630 1631config DEBUG_PERF_USE_VMALLOC 1632 default n 1633 bool "Debug: use vmalloc to back perf mmap() buffers" 1634 depends on PERF_EVENTS && DEBUG_KERNEL && !PPC 1635 select PERF_USE_VMALLOC 1636 help 1637 Use vmalloc memory to back perf mmap() buffers. 1638 1639 Mostly useful for debugging the vmalloc code on platforms 1640 that don't require it. 1641 1642 Say N if unsure. 1643 1644endmenu 1645 1646config VM_EVENT_COUNTERS 1647 default y 1648 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1649 help 1650 VM event counters are needed for event counts to be shown. 1651 This option allows the disabling of the VM event counters 1652 on EXPERT systems. /proc/vmstat will only show page counts 1653 if VM event counters are disabled. 1654 1655config SLUB_DEBUG 1656 default y 1657 bool "Enable SLUB debugging support" if EXPERT 1658 depends on SLUB && SYSFS 1659 help 1660 SLUB has extensive debug support features. Disabling these can 1661 result in significant savings in code size. This also disables 1662 SLUB sysfs support. /sys/slab will not exist and there will be 1663 no support for cache validation etc. 1664 1665config COMPAT_BRK 1666 bool "Disable heap randomization" 1667 default y 1668 help 1669 Randomizing heap placement makes heap exploits harder, but it 1670 also breaks ancient binaries (including anything libc5 based). 1671 This option changes the bootup default to heap randomization 1672 disabled, and can be overridden at runtime by setting 1673 /proc/sys/kernel/randomize_va_space to 2. 1674 1675 On non-ancient distros (post-2000 ones) N is usually a safe choice. 1676 1677choice 1678 prompt "Choose SLAB allocator" 1679 default SLUB 1680 help 1681 This option allows to select a slab allocator. 1682 1683config SLAB 1684 bool "SLAB" 1685 help 1686 The regular slab allocator that is established and known to work 1687 well in all environments. It organizes cache hot objects in 1688 per cpu and per node queues. 1689 1690config SLUB 1691 bool "SLUB (Unqueued Allocator)" 1692 help 1693 SLUB is a slab allocator that minimizes cache line usage 1694 instead of managing queues of cached objects (SLAB approach). 1695 Per cpu caching is realized using slabs of objects instead 1696 of queues of objects. SLUB can use memory efficiently 1697 and has enhanced diagnostics. SLUB is the default choice for 1698 a slab allocator. 1699 1700config SLOB 1701 depends on EXPERT 1702 bool "SLOB (Simple Allocator)" 1703 help 1704 SLOB replaces the stock allocator with a drastically simpler 1705 allocator. SLOB is generally more space efficient but 1706 does not perform as well on large systems. 1707 1708endchoice 1709 1710config SLUB_CPU_PARTIAL 1711 default y 1712 depends on SLUB && SMP 1713 bool "SLUB per cpu partial cache" 1714 help 1715 Per cpu partial caches accellerate objects allocation and freeing 1716 that is local to a processor at the price of more indeterminism 1717 in the latency of the free. On overflow these caches will be cleared 1718 which requires the taking of locks that may cause latency spikes. 1719 Typically one would choose no for a realtime system. 1720 1721config MMAP_ALLOW_UNINITIALIZED 1722 bool "Allow mmapped anonymous memory to be uninitialized" 1723 depends on EXPERT && !MMU 1724 default n 1725 help 1726 Normally, and according to the Linux spec, anonymous memory obtained 1727 from mmap() has it's contents cleared before it is passed to 1728 userspace. Enabling this config option allows you to request that 1729 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 1730 providing a huge performance boost. If this option is not enabled, 1731 then the flag will be ignored. 1732 1733 This is taken advantage of by uClibc's malloc(), and also by 1734 ELF-FDPIC binfmt's brk and stack allocator. 1735 1736 Because of the obvious security issues, this option should only be 1737 enabled on embedded devices where you control what is run in 1738 userspace. Since that isn't generally a problem on no-MMU systems, 1739 it is normally safe to say Y here. 1740 1741 See Documentation/nommu-mmap.txt for more information. 1742 1743config SYSTEM_TRUSTED_KEYRING 1744 bool "Provide system-wide ring of trusted keys" 1745 depends on KEYS 1746 help 1747 Provide a system keyring to which trusted keys can be added. Keys in 1748 the keyring are considered to be trusted. Keys may be added at will 1749 by the kernel from compiled-in data and from hardware key stores, but 1750 userspace may only add extra keys if those keys can be verified by 1751 keys already in the keyring. 1752 1753 Keys in this keyring are used by module signature checking. 1754 1755config PROFILING 1756 bool "Profiling support" 1757 help 1758 Say Y here to enable the extended profiling support mechanisms used 1759 by profilers such as OProfile. 1760 1761# 1762# Place an empty function call at each tracepoint site. Can be 1763# dynamically changed for a probe function. 1764# 1765config TRACEPOINTS 1766 bool 1767 1768source "arch/Kconfig" 1769 1770endmenu # General setup 1771 1772config HAVE_GENERIC_DMA_COHERENT 1773 bool 1774 default n 1775 1776config SLABINFO 1777 bool 1778 depends on PROC_FS 1779 depends on SLAB || SLUB_DEBUG 1780 default y 1781 1782config RT_MUTEXES 1783 bool 1784 1785config BASE_SMALL 1786 int 1787 default 0 if BASE_FULL 1788 default 1 if !BASE_FULL 1789 1790menuconfig MODULES 1791 bool "Enable loadable module support" 1792 option modules 1793 help 1794 Kernel modules are small pieces of compiled code which can 1795 be inserted in the running kernel, rather than being 1796 permanently built into the kernel. You use the "modprobe" 1797 tool to add (and sometimes remove) them. If you say Y here, 1798 many parts of the kernel can be built as modules (by 1799 answering M instead of Y where indicated): this is most 1800 useful for infrequently used options which are not required 1801 for booting. For more information, see the man pages for 1802 modprobe, lsmod, modinfo, insmod and rmmod. 1803 1804 If you say Y here, you will need to run "make 1805 modules_install" to put the modules under /lib/modules/ 1806 where modprobe can find them (you may need to be root to do 1807 this). 1808 1809 If unsure, say Y. 1810 1811if MODULES 1812 1813config MODULE_FORCE_LOAD 1814 bool "Forced module loading" 1815 default n 1816 help 1817 Allow loading of modules without version information (ie. modprobe 1818 --force). Forced module loading sets the 'F' (forced) taint flag and 1819 is usually a really bad idea. 1820 1821config MODULE_UNLOAD 1822 bool "Module unloading" 1823 help 1824 Without this option you will not be able to unload any 1825 modules (note that some modules may not be unloadable 1826 anyway), which makes your kernel smaller, faster 1827 and simpler. If unsure, say Y. 1828 1829config MODULE_FORCE_UNLOAD 1830 bool "Forced module unloading" 1831 depends on MODULE_UNLOAD 1832 help 1833 This option allows you to force a module to unload, even if the 1834 kernel believes it is unsafe: the kernel will remove the module 1835 without waiting for anyone to stop using it (using the -f option to 1836 rmmod). This is mainly for kernel developers and desperate users. 1837 If unsure, say N. 1838 1839config MODVERSIONS 1840 bool "Module versioning support" 1841 help 1842 Usually, you have to use modules compiled with your kernel. 1843 Saying Y here makes it sometimes possible to use modules 1844 compiled for different kernels, by adding enough information 1845 to the modules to (hopefully) spot any changes which would 1846 make them incompatible with the kernel you are running. If 1847 unsure, say N. 1848 1849config MODULE_SRCVERSION_ALL 1850 bool "Source checksum for all modules" 1851 help 1852 Modules which contain a MODULE_VERSION get an extra "srcversion" 1853 field inserted into their modinfo section, which contains a 1854 sum of the source files which made it. This helps maintainers 1855 see exactly which source was used to build a module (since 1856 others sometimes change the module source without updating 1857 the version). With this option, such a "srcversion" field 1858 will be created for all modules. If unsure, say N. 1859 1860config MODULE_SIG 1861 bool "Module signature verification" 1862 depends on MODULES 1863 select SYSTEM_TRUSTED_KEYRING 1864 select KEYS 1865 select CRYPTO 1866 select ASYMMETRIC_KEY_TYPE 1867 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE 1868 select PUBLIC_KEY_ALGO_RSA 1869 select ASN1 1870 select OID_REGISTRY 1871 select X509_CERTIFICATE_PARSER 1872 help 1873 Check modules for valid signatures upon load: the signature 1874 is simply appended to the module. For more information see 1875 Documentation/module-signing.txt. 1876 1877 !!!WARNING!!! If you enable this option, you MUST make sure that the 1878 module DOES NOT get stripped after being signed. This includes the 1879 debuginfo strip done by some packagers (such as rpmbuild) and 1880 inclusion into an initramfs that wants the module size reduced. 1881 1882config MODULE_SIG_FORCE 1883 bool "Require modules to be validly signed" 1884 depends on MODULE_SIG 1885 help 1886 Reject unsigned modules or signed modules for which we don't have a 1887 key. Without this, such modules will simply taint the kernel. 1888 1889config MODULE_SIG_ALL 1890 bool "Automatically sign all modules" 1891 default y 1892 depends on MODULE_SIG 1893 help 1894 Sign all modules during make modules_install. Without this option, 1895 modules must be signed manually, using the scripts/sign-file tool. 1896 1897comment "Do not forget to sign required modules with scripts/sign-file" 1898 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL 1899 1900choice 1901 prompt "Which hash algorithm should modules be signed with?" 1902 depends on MODULE_SIG 1903 help 1904 This determines which sort of hashing algorithm will be used during 1905 signature generation. This algorithm _must_ be built into the kernel 1906 directly so that signature verification can take place. It is not 1907 possible to load a signed module containing the algorithm to check 1908 the signature on that module. 1909 1910config MODULE_SIG_SHA1 1911 bool "Sign modules with SHA-1" 1912 select CRYPTO_SHA1 1913 1914config MODULE_SIG_SHA224 1915 bool "Sign modules with SHA-224" 1916 select CRYPTO_SHA256 1917 1918config MODULE_SIG_SHA256 1919 bool "Sign modules with SHA-256" 1920 select CRYPTO_SHA256 1921 1922config MODULE_SIG_SHA384 1923 bool "Sign modules with SHA-384" 1924 select CRYPTO_SHA512 1925 1926config MODULE_SIG_SHA512 1927 bool "Sign modules with SHA-512" 1928 select CRYPTO_SHA512 1929 1930endchoice 1931 1932config MODULE_SIG_HASH 1933 string 1934 depends on MODULE_SIG 1935 default "sha1" if MODULE_SIG_SHA1 1936 default "sha224" if MODULE_SIG_SHA224 1937 default "sha256" if MODULE_SIG_SHA256 1938 default "sha384" if MODULE_SIG_SHA384 1939 default "sha512" if MODULE_SIG_SHA512 1940 1941config MODULE_COMPRESS 1942 bool "Compress modules on installation" 1943 depends on MODULES 1944 help 1945 1946 Compresses kernel modules when 'make modules_install' is run; gzip or 1947 xz depending on "Compression algorithm" below. 1948 1949 module-init-tools MAY support gzip, and kmod MAY support gzip and xz. 1950 1951 Out-of-tree kernel modules installed using Kbuild will also be 1952 compressed upon installation. 1953 1954 Note: for modules inside an initrd or initramfs, it's more efficient 1955 to compress the whole initrd or initramfs instead. 1956 1957 Note: This is fully compatible with signed modules. 1958 1959 If in doubt, say N. 1960 1961choice 1962 prompt "Compression algorithm" 1963 depends on MODULE_COMPRESS 1964 default MODULE_COMPRESS_GZIP 1965 help 1966 This determines which sort of compression will be used during 1967 'make modules_install'. 1968 1969 GZIP (default) and XZ are supported. 1970 1971config MODULE_COMPRESS_GZIP 1972 bool "GZIP" 1973 1974config MODULE_COMPRESS_XZ 1975 bool "XZ" 1976 1977endchoice 1978 1979endif # MODULES 1980 1981config MODULES_TREE_LOOKUP 1982 def_bool y 1983 depends on PERF_EVENTS || TRACING 1984 1985config INIT_ALL_POSSIBLE 1986 bool 1987 help 1988 Back when each arch used to define their own cpu_online_mask and 1989 cpu_possible_mask, some of them chose to initialize cpu_possible_mask 1990 with all 1s, and others with all 0s. When they were centralised, 1991 it was better to provide this option than to break all the archs 1992 and have several arch maintainers pursuing me down dark alleys. 1993 1994config STOP_MACHINE 1995 bool 1996 default y 1997 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU 1998 help 1999 Need stop_machine() primitive. 2000 2001source "block/Kconfig" 2002 2003config PREEMPT_NOTIFIERS 2004 bool 2005 2006config PADATA 2007 depends on SMP 2008 bool 2009 2010# Can be selected by architectures with broken toolchains 2011# that get confused by correct const<->read_only section 2012# mappings 2013config BROKEN_RODATA 2014 bool 2015 2016config ASN1 2017 tristate 2018 help 2019 Build a simple ASN.1 grammar compiler that produces a bytecode output 2020 that can be interpreted by the ASN.1 stream decoder and used to 2021 inform it as to what tags are to be expected in a stream and what 2022 functions to call on what tags. 2023 2024source "kernel/Kconfig.locks" 2025