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 help 398 If you say Y here, a user level program will be able to instruct the 399 kernel (via a special system call) to write process accounting 400 information to a file: whenever a process exits, information about 401 that process will be appended to the file by the kernel. The 402 information includes things such as creation time, owning user, 403 command name, memory usage, controlling terminal etc. (the complete 404 list is in the struct acct in <file:include/linux/acct.h>). It is 405 up to the user level program to do useful things with this 406 information. This is generally a good idea, so say Y. 407 408config BSD_PROCESS_ACCT_V3 409 bool "BSD Process Accounting version 3 file format" 410 depends on BSD_PROCESS_ACCT 411 default n 412 help 413 If you say Y here, the process accounting information is written 414 in a new file format that also logs the process IDs of each 415 process and it's parent. Note that this file format is incompatible 416 with previous v0/v1/v2 file formats, so you will need updated tools 417 for processing it. A preliminary version of these tools is available 418 at <http://www.gnu.org/software/acct/>. 419 420config TASKSTATS 421 bool "Export task/process statistics through netlink" 422 depends on NET 423 default n 424 help 425 Export selected statistics for tasks/processes through the 426 generic netlink interface. Unlike BSD process accounting, the 427 statistics are available during the lifetime of tasks/processes as 428 responses to commands. Like BSD accounting, they are sent to user 429 space on task exit. 430 431 Say N if unsure. 432 433config TASK_DELAY_ACCT 434 bool "Enable per-task delay accounting" 435 depends on TASKSTATS 436 help 437 Collect information on time spent by a task waiting for system 438 resources like cpu, synchronous block I/O completion and swapping 439 in pages. Such statistics can help in setting a task's priorities 440 relative to other tasks for cpu, io, rss limits etc. 441 442 Say N if unsure. 443 444config TASK_XACCT 445 bool "Enable extended accounting over taskstats" 446 depends on TASKSTATS 447 help 448 Collect extended task accounting data and send the data 449 to userland for processing over the taskstats interface. 450 451 Say N if unsure. 452 453config TASK_IO_ACCOUNTING 454 bool "Enable per-task storage I/O accounting" 455 depends on TASK_XACCT 456 help 457 Collect information on the number of bytes of storage I/O which this 458 task has caused. 459 460 Say N if unsure. 461 462endmenu # "CPU/Task time and stats accounting" 463 464menu "RCU Subsystem" 465 466choice 467 prompt "RCU Implementation" 468 default TREE_RCU 469 470config TREE_RCU 471 bool "Tree-based hierarchical RCU" 472 depends on !PREEMPT && SMP 473 select IRQ_WORK 474 help 475 This option selects the RCU implementation that is 476 designed for very large SMP system with hundreds or 477 thousands of CPUs. It also scales down nicely to 478 smaller systems. 479 480config TREE_PREEMPT_RCU 481 bool "Preemptible tree-based hierarchical RCU" 482 depends on PREEMPT 483 select IRQ_WORK 484 help 485 This option selects the RCU implementation that is 486 designed for very large SMP systems with hundreds or 487 thousands of CPUs, but for which real-time response 488 is also required. It also scales down nicely to 489 smaller systems. 490 491 Select this option if you are unsure. 492 493config TINY_RCU 494 bool "UP-only small-memory-footprint RCU" 495 depends on !PREEMPT && !SMP 496 help 497 This option selects the RCU implementation that is 498 designed for UP systems from which real-time response 499 is not required. This option greatly reduces the 500 memory footprint of RCU. 501 502endchoice 503 504config PREEMPT_RCU 505 def_bool TREE_PREEMPT_RCU 506 help 507 This option enables preemptible-RCU code that is common between 508 TREE_PREEMPT_RCU and, in the old days, TINY_PREEMPT_RCU. 509 510config RCU_STALL_COMMON 511 def_bool ( TREE_RCU || TREE_PREEMPT_RCU || RCU_TRACE ) 512 help 513 This option enables RCU CPU stall code that is common between 514 the TINY and TREE variants of RCU. The purpose is to allow 515 the tiny variants to disable RCU CPU stall warnings, while 516 making these warnings mandatory for the tree variants. 517 518config CONTEXT_TRACKING 519 bool 520 521config RCU_USER_QS 522 bool "Consider userspace as in RCU extended quiescent state" 523 depends on HAVE_CONTEXT_TRACKING && SMP 524 select CONTEXT_TRACKING 525 help 526 This option sets hooks on kernel / userspace boundaries and 527 puts RCU in extended quiescent state when the CPU runs in 528 userspace. It means that when a CPU runs in userspace, it is 529 excluded from the global RCU state machine and thus doesn't 530 try to keep the timer tick on for RCU. 531 532 Unless you want to hack and help the development of the full 533 dynticks mode, you shouldn't enable this option. It also 534 adds unnecessary overhead. 535 536 If unsure say N 537 538config CONTEXT_TRACKING_FORCE 539 bool "Force context tracking" 540 depends on CONTEXT_TRACKING 541 default y if !NO_HZ_FULL 542 help 543 The major pre-requirement for full dynticks to work is to 544 support the context tracking subsystem. But there are also 545 other dependencies to provide in order to make the full 546 dynticks working. 547 548 This option stands for testing when an arch implements the 549 context tracking backend but doesn't yet fullfill all the 550 requirements to make the full dynticks feature working. 551 Without the full dynticks, there is no way to test the support 552 for context tracking and the subsystems that rely on it: RCU 553 userspace extended quiescent state and tickless cputime 554 accounting. This option copes with the absence of the full 555 dynticks subsystem by forcing the context tracking on all 556 CPUs in the system. 557 558 Say Y only if you're working on the development of an 559 architecture backend for the context tracking. 560 561 Say N otherwise, this option brings an overhead that you 562 don't want in production. 563 564 565config RCU_FANOUT 566 int "Tree-based hierarchical RCU fanout value" 567 range 2 64 if 64BIT 568 range 2 32 if !64BIT 569 depends on TREE_RCU || TREE_PREEMPT_RCU 570 default 64 if 64BIT 571 default 32 if !64BIT 572 help 573 This option controls the fanout of hierarchical implementations 574 of RCU, allowing RCU to work efficiently on machines with 575 large numbers of CPUs. This value must be at least the fourth 576 root of NR_CPUS, which allows NR_CPUS to be insanely large. 577 The default value of RCU_FANOUT should be used for production 578 systems, but if you are stress-testing the RCU implementation 579 itself, small RCU_FANOUT values allow you to test large-system 580 code paths on small(er) systems. 581 582 Select a specific number if testing RCU itself. 583 Take the default if unsure. 584 585config RCU_FANOUT_LEAF 586 int "Tree-based hierarchical RCU leaf-level fanout value" 587 range 2 RCU_FANOUT if 64BIT 588 range 2 RCU_FANOUT if !64BIT 589 depends on TREE_RCU || TREE_PREEMPT_RCU 590 default 16 591 help 592 This option controls the leaf-level fanout of hierarchical 593 implementations of RCU, and allows trading off cache misses 594 against lock contention. Systems that synchronize their 595 scheduling-clock interrupts for energy-efficiency reasons will 596 want the default because the smaller leaf-level fanout keeps 597 lock contention levels acceptably low. Very large systems 598 (hundreds or thousands of CPUs) will instead want to set this 599 value to the maximum value possible in order to reduce the 600 number of cache misses incurred during RCU's grace-period 601 initialization. These systems tend to run CPU-bound, and thus 602 are not helped by synchronized interrupts, and thus tend to 603 skew them, which reduces lock contention enough that large 604 leaf-level fanouts work well. 605 606 Select a specific number if testing RCU itself. 607 608 Select the maximum permissible value for large systems. 609 610 Take the default if unsure. 611 612config RCU_FANOUT_EXACT 613 bool "Disable tree-based hierarchical RCU auto-balancing" 614 depends on TREE_RCU || TREE_PREEMPT_RCU 615 default n 616 help 617 This option forces use of the exact RCU_FANOUT value specified, 618 regardless of imbalances in the hierarchy. This is useful for 619 testing RCU itself, and might one day be useful on systems with 620 strong NUMA behavior. 621 622 Without RCU_FANOUT_EXACT, the code will balance the hierarchy. 623 624 Say N if unsure. 625 626config RCU_FAST_NO_HZ 627 bool "Accelerate last non-dyntick-idle CPU's grace periods" 628 depends on NO_HZ_COMMON && SMP 629 default n 630 help 631 This option permits CPUs to enter dynticks-idle state even if 632 they have RCU callbacks queued, and prevents RCU from waking 633 these CPUs up more than roughly once every four jiffies (by 634 default, you can adjust this using the rcutree.rcu_idle_gp_delay 635 parameter), thus improving energy efficiency. On the other 636 hand, this option increases the duration of RCU grace periods, 637 for example, slowing down synchronize_rcu(). 638 639 Say Y if energy efficiency is critically important, and you 640 don't care about increased grace-period durations. 641 642 Say N if you are unsure. 643 644config TREE_RCU_TRACE 645 def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) 646 select DEBUG_FS 647 help 648 This option provides tracing for the TREE_RCU and 649 TREE_PREEMPT_RCU implementations, permitting Makefile to 650 trivially select kernel/rcutree_trace.c. 651 652config RCU_BOOST 653 bool "Enable RCU priority boosting" 654 depends on RT_MUTEXES && PREEMPT_RCU 655 default n 656 help 657 This option boosts the priority of preempted RCU readers that 658 block the current preemptible RCU grace period for too long. 659 This option also prevents heavy loads from blocking RCU 660 callback invocation for all flavors of RCU. 661 662 Say Y here if you are working with real-time apps or heavy loads 663 Say N here if you are unsure. 664 665config RCU_BOOST_PRIO 666 int "Real-time priority to boost RCU readers to" 667 range 1 99 668 depends on RCU_BOOST 669 default 1 670 help 671 This option specifies the real-time priority to which long-term 672 preempted RCU readers are to be boosted. If you are working 673 with a real-time application that has one or more CPU-bound 674 threads running at a real-time priority level, you should set 675 RCU_BOOST_PRIO to a priority higher then the highest-priority 676 real-time CPU-bound thread. The default RCU_BOOST_PRIO value 677 of 1 is appropriate in the common case, which is real-time 678 applications that do not have any CPU-bound threads. 679 680 Some real-time applications might not have a single real-time 681 thread that saturates a given CPU, but instead might have 682 multiple real-time threads that, taken together, fully utilize 683 that CPU. In this case, you should set RCU_BOOST_PRIO to 684 a priority higher than the lowest-priority thread that is 685 conspiring to prevent the CPU from running any non-real-time 686 tasks. For example, if one thread at priority 10 and another 687 thread at priority 5 are between themselves fully consuming 688 the CPU time on a given CPU, then RCU_BOOST_PRIO should be 689 set to priority 6 or higher. 690 691 Specify the real-time priority, or take the default if unsure. 692 693config RCU_BOOST_DELAY 694 int "Milliseconds to delay boosting after RCU grace-period start" 695 range 0 3000 696 depends on RCU_BOOST 697 default 500 698 help 699 This option specifies the time to wait after the beginning of 700 a given grace period before priority-boosting preempted RCU 701 readers blocking that grace period. Note that any RCU reader 702 blocking an expedited RCU grace period is boosted immediately. 703 704 Accept the default if unsure. 705 706config RCU_NOCB_CPU 707 bool "Offload RCU callback processing from boot-selected CPUs" 708 depends on TREE_RCU || TREE_PREEMPT_RCU 709 default n 710 help 711 Use this option to reduce OS jitter for aggressive HPC or 712 real-time workloads. It can also be used to offload RCU 713 callback invocation to energy-efficient CPUs in battery-powered 714 asymmetric multiprocessors. 715 716 This option offloads callback invocation from the set of 717 CPUs specified at boot time by the rcu_nocbs parameter. 718 For each such CPU, a kthread ("rcuox/N") will be created to 719 invoke callbacks, where the "N" is the CPU being offloaded, 720 and where the "x" is "b" for RCU-bh, "p" for RCU-preempt, and 721 "s" for RCU-sched. Nothing prevents this kthread from running 722 on the specified CPUs, but (1) the kthreads may be preempted 723 between each callback, and (2) affinity or cgroups can be used 724 to force the kthreads to run on whatever set of CPUs is desired. 725 726 Say Y here if you want to help to debug reduced OS jitter. 727 Say N here if you are unsure. 728 729choice 730 prompt "Build-forced no-CBs CPUs" 731 default RCU_NOCB_CPU_NONE 732 help 733 This option allows no-CBs CPUs (whose RCU callbacks are invoked 734 from kthreads rather than from softirq context) to be specified 735 at build time. Additional no-CBs CPUs may be specified by 736 the rcu_nocbs= boot parameter. 737 738config RCU_NOCB_CPU_NONE 739 bool "No build_forced no-CBs CPUs" 740 depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL 741 help 742 This option does not force any of the CPUs to be no-CBs CPUs. 743 Only CPUs designated by the rcu_nocbs= boot parameter will be 744 no-CBs CPUs, whose RCU callbacks will be invoked by per-CPU 745 kthreads whose names begin with "rcuo". All other CPUs will 746 invoke their own RCU callbacks in softirq context. 747 748 Select this option if you want to choose no-CBs CPUs at 749 boot time, for example, to allow testing of different no-CBs 750 configurations without having to rebuild the kernel each time. 751 752config RCU_NOCB_CPU_ZERO 753 bool "CPU 0 is a build_forced no-CBs CPU" 754 depends on RCU_NOCB_CPU && !NO_HZ_FULL_ALL 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 depends on RCU_NOCB_CPU 770 help 771 This option forces all CPUs to be no-CBs CPUs. The rcu_nocbs= 772 boot parameter will be ignored. All CPUs' RCU callbacks will 773 be executed in the context of per-CPU rcuo kthreads created for 774 this purpose. Assuming that the kthreads whose names start with 775 "rcuo" are bound to "housekeeping" CPUs, this reduces OS jitter 776 on the remaining CPUs, but might decrease memory locality during 777 RCU-callback invocation, thus potentially degrading throughput. 778 779 Select this if all CPUs need to be no-CBs CPUs for real-time 780 or energy-efficiency reasons. 781 782endchoice 783 784endmenu # "RCU Subsystem" 785 786config BUILD_BIN2C 787 bool 788 default n 789 790config IKCONFIG 791 tristate "Kernel .config support" 792 select BUILD_BIN2C 793 ---help--- 794 This option enables the complete Linux kernel ".config" file 795 contents to be saved in the kernel. It provides documentation 796 of which kernel options are used in a running kernel or in an 797 on-disk kernel. This information can be extracted from the kernel 798 image file with the script scripts/extract-ikconfig and used as 799 input to rebuild the current kernel or to build another kernel. 800 It can also be extracted from a running kernel by reading 801 /proc/config.gz if enabled (below). 802 803config IKCONFIG_PROC 804 bool "Enable access to .config through /proc/config.gz" 805 depends on IKCONFIG && PROC_FS 806 ---help--- 807 This option enables access to the kernel configuration file 808 through /proc/config.gz. 809 810config LOG_BUF_SHIFT 811 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" 812 range 12 21 813 default 17 814 help 815 Select the minimal kernel log buffer size as a power of 2. 816 The final size is affected by LOG_CPU_MAX_BUF_SHIFT config 817 parameter, see below. Any higher size also might be forced 818 by "log_buf_len" boot parameter. 819 820 Examples: 821 17 => 128 KB 822 16 => 64 KB 823 15 => 32 KB 824 14 => 16 KB 825 13 => 8 KB 826 12 => 4 KB 827 828config LOG_CPU_MAX_BUF_SHIFT 829 int "CPU kernel log buffer size contribution (13 => 8 KB, 17 => 128KB)" 830 range 0 21 831 default 12 if !BASE_SMALL 832 default 0 if BASE_SMALL 833 help 834 This option allows to increase the default ring buffer size 835 according to the number of CPUs. The value defines the contribution 836 of each CPU as a power of 2. The used space is typically only few 837 lines however it might be much more when problems are reported, 838 e.g. backtraces. 839 840 The increased size means that a new buffer has to be allocated and 841 the original static one is unused. It makes sense only on systems 842 with more CPUs. Therefore this value is used only when the sum of 843 contributions is greater than the half of the default kernel ring 844 buffer as defined by LOG_BUF_SHIFT. The default values are set 845 so that more than 64 CPUs are needed to trigger the allocation. 846 847 Also this option is ignored when "log_buf_len" kernel parameter is 848 used as it forces an exact (power of two) size of the ring buffer. 849 850 The number of possible CPUs is used for this computation ignoring 851 hotplugging making the compuation optimal for the the worst case 852 scenerio while allowing a simple algorithm to be used from bootup. 853 854 Examples shift values and their meaning: 855 17 => 128 KB for each CPU 856 16 => 64 KB for each CPU 857 15 => 32 KB for each CPU 858 14 => 16 KB for each CPU 859 13 => 8 KB for each CPU 860 12 => 4 KB for each CPU 861 862# 863# Architectures with an unreliable sched_clock() should select this: 864# 865config HAVE_UNSTABLE_SCHED_CLOCK 866 bool 867 868config GENERIC_SCHED_CLOCK 869 bool 870 871# 872# For architectures that want to enable the support for NUMA-affine scheduler 873# balancing logic: 874# 875config ARCH_SUPPORTS_NUMA_BALANCING 876 bool 877 878# 879# For architectures that know their GCC __int128 support is sound 880# 881config ARCH_SUPPORTS_INT128 882 bool 883 884# For architectures that (ab)use NUMA to represent different memory regions 885# all cpu-local but of different latencies, such as SuperH. 886# 887config ARCH_WANT_NUMA_VARIABLE_LOCALITY 888 bool 889 890# 891# For architectures that are willing to define _PAGE_NUMA as _PAGE_PROTNONE 892config ARCH_WANTS_PROT_NUMA_PROT_NONE 893 bool 894 895config ARCH_USES_NUMA_PROT_NONE 896 bool 897 default y 898 depends on ARCH_WANTS_PROT_NUMA_PROT_NONE 899 depends on NUMA_BALANCING 900 901config NUMA_BALANCING_DEFAULT_ENABLED 902 bool "Automatically enable NUMA aware memory/task placement" 903 default y 904 depends on NUMA_BALANCING 905 help 906 If set, automatic NUMA balancing will be enabled if running on a NUMA 907 machine. 908 909config NUMA_BALANCING 910 bool "Memory placement aware NUMA scheduler" 911 depends on ARCH_SUPPORTS_NUMA_BALANCING 912 depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY 913 depends on SMP && NUMA && MIGRATION 914 help 915 This option adds support for automatic NUMA aware memory/task placement. 916 The mechanism is quite primitive and is based on migrating memory when 917 it has references to the node the task is running on. 918 919 This system will be inactive on UMA systems. 920 921menuconfig CGROUPS 922 boolean "Control Group support" 923 select KERNFS 924 help 925 This option adds support for grouping sets of processes together, for 926 use with process control subsystems such as Cpusets, CFS, memory 927 controls or device isolation. 928 See 929 - Documentation/scheduler/sched-design-CFS.txt (CFS) 930 - Documentation/cgroups/ (features for grouping, isolation 931 and resource control) 932 933 Say N if unsure. 934 935if CGROUPS 936 937config CGROUP_DEBUG 938 bool "Example debug cgroup subsystem" 939 default n 940 help 941 This option enables a simple cgroup subsystem that 942 exports useful debugging information about the cgroups 943 framework. 944 945 Say N if unsure. 946 947config CGROUP_FREEZER 948 bool "Freezer cgroup subsystem" 949 help 950 Provides a way to freeze and unfreeze all tasks in a 951 cgroup. 952 953config CGROUP_DEVICE 954 bool "Device controller for cgroups" 955 help 956 Provides a cgroup implementing whitelists for devices which 957 a process in the cgroup can mknod or open. 958 959config CPUSETS 960 bool "Cpuset support" 961 help 962 This option will let you create and manage CPUSETs which 963 allow dynamically partitioning a system into sets of CPUs and 964 Memory Nodes and assigning tasks to run only within those sets. 965 This is primarily useful on large SMP or NUMA systems. 966 967 Say N if unsure. 968 969config PROC_PID_CPUSET 970 bool "Include legacy /proc/<pid>/cpuset file" 971 depends on CPUSETS 972 default y 973 974config CGROUP_CPUACCT 975 bool "Simple CPU accounting cgroup subsystem" 976 help 977 Provides a simple Resource Controller for monitoring the 978 total CPU consumed by the tasks in a cgroup. 979 980config RESOURCE_COUNTERS 981 bool "Resource counters" 982 help 983 This option enables controller independent resource accounting 984 infrastructure that works with cgroups. 985 986config MEMCG 987 bool "Memory Resource Controller for Control Groups" 988 depends on RESOURCE_COUNTERS 989 select EVENTFD 990 help 991 Provides a memory resource controller that manages both anonymous 992 memory and page cache. (See Documentation/cgroups/memory.txt) 993 994 Note that setting this option increases fixed memory overhead 995 associated with each page of memory in the system. By this, 996 8(16)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory 997 usage tracking struct at boot. Total amount of this is printed out 998 at boot. 999 1000 Only enable when you're ok with these trade offs and really 1001 sure you need the memory resource controller. Even when you enable 1002 this, you can set "cgroup_disable=memory" at your boot option to 1003 disable memory resource controller and you can avoid overheads. 1004 (and lose benefits of memory resource controller) 1005 1006config MEMCG_SWAP 1007 bool "Memory Resource Controller Swap Extension" 1008 depends on MEMCG && SWAP 1009 help 1010 Add swap management feature to memory resource controller. When you 1011 enable this, you can limit mem+swap usage per cgroup. In other words, 1012 when you disable this, memory resource controller has no cares to 1013 usage of swap...a process can exhaust all of the swap. This extension 1014 is useful when you want to avoid exhaustion swap but this itself 1015 adds more overheads and consumes memory for remembering information. 1016 Especially if you use 32bit system or small memory system, please 1017 be careful about enabling this. When memory resource controller 1018 is disabled by boot option, this will be automatically disabled and 1019 there will be no overhead from this. Even when you set this config=y, 1020 if boot option "swapaccount=0" is set, swap will not be accounted. 1021 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page 1022 size is 4096bytes, 512k per 1Gbytes of swap. 1023config MEMCG_SWAP_ENABLED 1024 bool "Memory Resource Controller Swap Extension enabled by default" 1025 depends on MEMCG_SWAP 1026 default y 1027 help 1028 Memory Resource Controller Swap Extension comes with its price in 1029 a bigger memory consumption. General purpose distribution kernels 1030 which want to enable the feature but keep it disabled by default 1031 and let the user enable it by swapaccount=1 boot command line 1032 parameter should have this option unselected. 1033 For those who want to have the feature enabled by default should 1034 select this option (if, for some reason, they need to disable it 1035 then swapaccount=0 does the trick). 1036config MEMCG_KMEM 1037 bool "Memory Resource Controller Kernel Memory accounting" 1038 depends on MEMCG 1039 depends on SLUB || SLAB 1040 help 1041 The Kernel Memory extension for Memory Resource Controller can limit 1042 the amount of memory used by kernel objects in the system. Those are 1043 fundamentally different from the entities handled by the standard 1044 Memory Controller, which are page-based, and can be swapped. Users of 1045 the kmem extension can use it to guarantee that no group of processes 1046 will ever exhaust kernel resources alone. 1047 1048 WARNING: Current implementation lacks reclaim support. That means 1049 allocation attempts will fail when close to the limit even if there 1050 are plenty of kmem available for reclaim. That makes this option 1051 unusable in real life so DO NOT SELECT IT unless for development 1052 purposes. 1053 1054config CGROUP_HUGETLB 1055 bool "HugeTLB Resource Controller for Control Groups" 1056 depends on RESOURCE_COUNTERS && HUGETLB_PAGE 1057 default n 1058 help 1059 Provides a cgroup Resource Controller for HugeTLB pages. 1060 When you enable this, you can put a per cgroup limit on HugeTLB usage. 1061 The limit is enforced during page fault. Since HugeTLB doesn't 1062 support page reclaim, enforcing the limit at page fault time implies 1063 that, the application will get SIGBUS signal if it tries to access 1064 HugeTLB pages beyond its limit. This requires the application to know 1065 beforehand how much HugeTLB pages it would require for its use. The 1066 control group is tracked in the third page lru pointer. This means 1067 that we cannot use the controller with huge page less than 3 pages. 1068 1069config CGROUP_PERF 1070 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" 1071 depends on PERF_EVENTS && CGROUPS 1072 help 1073 This option extends the per-cpu mode to restrict monitoring to 1074 threads which belong to the cgroup specified and run on the 1075 designated cpu. 1076 1077 Say N if unsure. 1078 1079menuconfig CGROUP_SCHED 1080 bool "Group CPU scheduler" 1081 default n 1082 help 1083 This feature lets CPU scheduler recognize task groups and control CPU 1084 bandwidth allocation to such task groups. It uses cgroups to group 1085 tasks. 1086 1087if CGROUP_SCHED 1088config FAIR_GROUP_SCHED 1089 bool "Group scheduling for SCHED_OTHER" 1090 depends on CGROUP_SCHED 1091 default CGROUP_SCHED 1092 1093config CFS_BANDWIDTH 1094 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" 1095 depends on FAIR_GROUP_SCHED 1096 default n 1097 help 1098 This option allows users to define CPU bandwidth rates (limits) for 1099 tasks running within the fair group scheduler. Groups with no limit 1100 set are considered to be unconstrained and will run with no 1101 restriction. 1102 See tip/Documentation/scheduler/sched-bwc.txt for more information. 1103 1104config RT_GROUP_SCHED 1105 bool "Group scheduling for SCHED_RR/FIFO" 1106 depends on CGROUP_SCHED 1107 default n 1108 help 1109 This feature lets you explicitly allocate real CPU bandwidth 1110 to task groups. If enabled, it will also make it impossible to 1111 schedule realtime tasks for non-root users until you allocate 1112 realtime bandwidth for them. 1113 See Documentation/scheduler/sched-rt-group.txt for more information. 1114 1115endif #CGROUP_SCHED 1116 1117config BLK_CGROUP 1118 bool "Block IO controller" 1119 depends on BLOCK 1120 default n 1121 ---help--- 1122 Generic block IO controller cgroup interface. This is the common 1123 cgroup interface which should be used by various IO controlling 1124 policies. 1125 1126 Currently, CFQ IO scheduler uses it to recognize task groups and 1127 control disk bandwidth allocation (proportional time slice allocation) 1128 to such task groups. It is also used by bio throttling logic in 1129 block layer to implement upper limit in IO rates on a device. 1130 1131 This option only enables generic Block IO controller infrastructure. 1132 One needs to also enable actual IO controlling logic/policy. For 1133 enabling proportional weight division of disk bandwidth in CFQ, set 1134 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set 1135 CONFIG_BLK_DEV_THROTTLING=y. 1136 1137 See Documentation/cgroups/blkio-controller.txt for more information. 1138 1139config DEBUG_BLK_CGROUP 1140 bool "Enable Block IO controller debugging" 1141 depends on BLK_CGROUP 1142 default n 1143 ---help--- 1144 Enable some debugging help. Currently it exports additional stat 1145 files in a cgroup which can be useful for debugging. 1146 1147endif # CGROUPS 1148 1149config CHECKPOINT_RESTORE 1150 bool "Checkpoint/restore support" if EXPERT 1151 default n 1152 help 1153 Enables additional kernel features in a sake of checkpoint/restore. 1154 In particular it adds auxiliary prctl codes to setup process text, 1155 data and heap segment sizes, and a few additional /proc filesystem 1156 entries. 1157 1158 If unsure, say N here. 1159 1160menuconfig NAMESPACES 1161 bool "Namespaces support" if EXPERT 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 gcc 1306 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 1342menuconfig EXPERT 1343 bool "Configure standard kernel features (expert users)" 1344 # Unhide debug options, to make the on-by-default options visible 1345 select DEBUG_KERNEL 1346 help 1347 This option allows certain base kernel options and settings 1348 to be disabled or tweaked. This is for specialized 1349 environments which can tolerate a "non-standard" kernel. 1350 Only use this if you really know what you are doing. 1351 1352config UID16 1353 bool "Enable 16-bit UID system calls" if EXPERT 1354 depends on HAVE_UID16 1355 default y 1356 help 1357 This enables the legacy 16-bit UID syscall wrappers. 1358 1359config SGETMASK_SYSCALL 1360 bool "sgetmask/ssetmask syscalls support" if EXPERT 1361 def_bool PARISC || MN10300 || BLACKFIN || M68K || PPC || MIPS || X86 || SPARC || CRIS || MICROBLAZE || SUPERH 1362 ---help--- 1363 sys_sgetmask and sys_ssetmask are obsolete system calls 1364 no longer supported in libc but still enabled by default in some 1365 architectures. 1366 1367 If unsure, leave the default option here. 1368 1369config SYSFS_SYSCALL 1370 bool "Sysfs syscall support" if EXPERT 1371 default y 1372 ---help--- 1373 sys_sysfs is an obsolete system call no longer supported in libc. 1374 Note that disabling this option is more secure but might break 1375 compatibility with some systems. 1376 1377 If unsure say Y here. 1378 1379config SYSCTL_SYSCALL 1380 bool "Sysctl syscall support" if EXPERT 1381 depends on PROC_SYSCTL 1382 default n 1383 select SYSCTL 1384 ---help--- 1385 sys_sysctl uses binary paths that have been found challenging 1386 to properly maintain and use. The interface in /proc/sys 1387 using paths with ascii names is now the primary path to this 1388 information. 1389 1390 Almost nothing using the binary sysctl interface so if you are 1391 trying to save some space it is probably safe to disable this, 1392 making your kernel marginally smaller. 1393 1394 If unsure say N here. 1395 1396config KALLSYMS 1397 bool "Load all symbols for debugging/ksymoops" if EXPERT 1398 default y 1399 help 1400 Say Y here to let the kernel print out symbolic crash information and 1401 symbolic stack backtraces. This increases the size of the kernel 1402 somewhat, as all symbols have to be loaded into the kernel image. 1403 1404config KALLSYMS_ALL 1405 bool "Include all symbols in kallsyms" 1406 depends on DEBUG_KERNEL && KALLSYMS 1407 help 1408 Normally kallsyms only contains the symbols of functions for nicer 1409 OOPS messages and backtraces (i.e., symbols from the text and inittext 1410 sections). This is sufficient for most cases. And only in very rare 1411 cases (e.g., when a debugger is used) all symbols are required (e.g., 1412 names of variables from the data sections, etc). 1413 1414 This option makes sure that all symbols are loaded into the kernel 1415 image (i.e., symbols from all sections) in cost of increased kernel 1416 size (depending on the kernel configuration, it may be 300KiB or 1417 something like this). 1418 1419 Say N unless you really need all symbols. 1420 1421config PRINTK 1422 default y 1423 bool "Enable support for printk" if EXPERT 1424 select IRQ_WORK 1425 help 1426 This option enables normal printk support. Removing it 1427 eliminates most of the message strings from the kernel image 1428 and makes the kernel more or less silent. As this makes it 1429 very difficult to diagnose system problems, saying N here is 1430 strongly discouraged. 1431 1432config BUG 1433 bool "BUG() support" if EXPERT 1434 default y 1435 help 1436 Disabling this option eliminates support for BUG and WARN, reducing 1437 the size of your kernel image and potentially quietly ignoring 1438 numerous fatal conditions. You should only consider disabling this 1439 option for embedded systems with no facilities for reporting errors. 1440 Just say Y. 1441 1442config ELF_CORE 1443 depends on COREDUMP 1444 default y 1445 bool "Enable ELF core dumps" if EXPERT 1446 help 1447 Enable support for generating core dumps. Disabling saves about 4k. 1448 1449 1450config PCSPKR_PLATFORM 1451 bool "Enable PC-Speaker support" if EXPERT 1452 depends on HAVE_PCSPKR_PLATFORM 1453 select I8253_LOCK 1454 default y 1455 help 1456 This option allows to disable the internal PC-Speaker 1457 support, saving some memory. 1458 1459config BASE_FULL 1460 default y 1461 bool "Enable full-sized data structures for core" if EXPERT 1462 help 1463 Disabling this option reduces the size of miscellaneous core 1464 kernel data structures. This saves memory on small machines, 1465 but may reduce performance. 1466 1467config FUTEX 1468 bool "Enable futex support" if EXPERT 1469 default y 1470 select RT_MUTEXES 1471 help 1472 Disabling this option will cause the kernel to be built without 1473 support for "fast userspace mutexes". The resulting kernel may not 1474 run glibc-based applications correctly. 1475 1476config HAVE_FUTEX_CMPXCHG 1477 bool 1478 help 1479 Architectures should select this if futex_atomic_cmpxchg_inatomic() 1480 is implemented and always working. This removes a couple of runtime 1481 checks. 1482 1483config EPOLL 1484 bool "Enable eventpoll support" if EXPERT 1485 default y 1486 select ANON_INODES 1487 help 1488 Disabling this option will cause the kernel to be built without 1489 support for epoll family of system calls. 1490 1491config SIGNALFD 1492 bool "Enable signalfd() system call" if EXPERT 1493 select ANON_INODES 1494 default y 1495 help 1496 Enable the signalfd() system call that allows to receive signals 1497 on a file descriptor. 1498 1499 If unsure, say Y. 1500 1501config TIMERFD 1502 bool "Enable timerfd() system call" if EXPERT 1503 select ANON_INODES 1504 default y 1505 help 1506 Enable the timerfd() system call that allows to receive timer 1507 events on a file descriptor. 1508 1509 If unsure, say Y. 1510 1511config EVENTFD 1512 bool "Enable eventfd() system call" if EXPERT 1513 select ANON_INODES 1514 default y 1515 help 1516 Enable the eventfd() system call that allows to receive both 1517 kernel notification (ie. KAIO) or userspace notifications. 1518 1519 If unsure, say Y. 1520 1521config SHMEM 1522 bool "Use full shmem filesystem" if EXPERT 1523 default y 1524 depends on MMU 1525 help 1526 The shmem is an internal filesystem used to manage shared memory. 1527 It is backed by swap and manages resource limits. It is also exported 1528 to userspace as tmpfs if TMPFS is enabled. Disabling this 1529 option replaces shmem and tmpfs with the much simpler ramfs code, 1530 which may be appropriate on small systems without swap. 1531 1532config AIO 1533 bool "Enable AIO support" if EXPERT 1534 default y 1535 help 1536 This option enables POSIX asynchronous I/O which may by used 1537 by some high performance threaded applications. Disabling 1538 this option saves about 7k. 1539 1540config PCI_QUIRKS 1541 default y 1542 bool "Enable PCI quirk workarounds" if EXPERT 1543 depends on PCI 1544 help 1545 This enables workarounds for various PCI chipset 1546 bugs/quirks. Disable this only if your target machine is 1547 unaffected by PCI quirks. 1548 1549config EMBEDDED 1550 bool "Embedded system" 1551 option allnoconfig_y 1552 select EXPERT 1553 help 1554 This option should be enabled if compiling the kernel for 1555 an embedded system so certain expert options are available 1556 for configuration. 1557 1558config HAVE_PERF_EVENTS 1559 bool 1560 help 1561 See tools/perf/design.txt for details. 1562 1563config PERF_USE_VMALLOC 1564 bool 1565 help 1566 See tools/perf/design.txt for details 1567 1568menu "Kernel Performance Events And Counters" 1569 1570config PERF_EVENTS 1571 bool "Kernel performance events and counters" 1572 default y if PROFILING 1573 depends on HAVE_PERF_EVENTS 1574 select ANON_INODES 1575 select IRQ_WORK 1576 help 1577 Enable kernel support for various performance events provided 1578 by software and hardware. 1579 1580 Software events are supported either built-in or via the 1581 use of generic tracepoints. 1582 1583 Most modern CPUs support performance events via performance 1584 counter registers. These registers count the number of certain 1585 types of hw events: such as instructions executed, cachemisses 1586 suffered, or branches mis-predicted - without slowing down the 1587 kernel or applications. These registers can also trigger interrupts 1588 when a threshold number of events have passed - and can thus be 1589 used to profile the code that runs on that CPU. 1590 1591 The Linux Performance Event subsystem provides an abstraction of 1592 these software and hardware event capabilities, available via a 1593 system call and used by the "perf" utility in tools/perf/. It 1594 provides per task and per CPU counters, and it provides event 1595 capabilities on top of those. 1596 1597 Say Y if unsure. 1598 1599config DEBUG_PERF_USE_VMALLOC 1600 default n 1601 bool "Debug: use vmalloc to back perf mmap() buffers" 1602 depends on PERF_EVENTS && DEBUG_KERNEL 1603 select PERF_USE_VMALLOC 1604 help 1605 Use vmalloc memory to back perf mmap() buffers. 1606 1607 Mostly useful for debugging the vmalloc code on platforms 1608 that don't require it. 1609 1610 Say N if unsure. 1611 1612endmenu 1613 1614config VM_EVENT_COUNTERS 1615 default y 1616 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1617 help 1618 VM event counters are needed for event counts to be shown. 1619 This option allows the disabling of the VM event counters 1620 on EXPERT systems. /proc/vmstat will only show page counts 1621 if VM event counters are disabled. 1622 1623config SLUB_DEBUG 1624 default y 1625 bool "Enable SLUB debugging support" if EXPERT 1626 depends on SLUB && SYSFS 1627 help 1628 SLUB has extensive debug support features. Disabling these can 1629 result in significant savings in code size. This also disables 1630 SLUB sysfs support. /sys/slab will not exist and there will be 1631 no support for cache validation etc. 1632 1633config COMPAT_BRK 1634 bool "Disable heap randomization" 1635 default y 1636 help 1637 Randomizing heap placement makes heap exploits harder, but it 1638 also breaks ancient binaries (including anything libc5 based). 1639 This option changes the bootup default to heap randomization 1640 disabled, and can be overridden at runtime by setting 1641 /proc/sys/kernel/randomize_va_space to 2. 1642 1643 On non-ancient distros (post-2000 ones) N is usually a safe choice. 1644 1645choice 1646 prompt "Choose SLAB allocator" 1647 default SLUB 1648 help 1649 This option allows to select a slab allocator. 1650 1651config SLAB 1652 bool "SLAB" 1653 help 1654 The regular slab allocator that is established and known to work 1655 well in all environments. It organizes cache hot objects in 1656 per cpu and per node queues. 1657 1658config SLUB 1659 bool "SLUB (Unqueued Allocator)" 1660 help 1661 SLUB is a slab allocator that minimizes cache line usage 1662 instead of managing queues of cached objects (SLAB approach). 1663 Per cpu caching is realized using slabs of objects instead 1664 of queues of objects. SLUB can use memory efficiently 1665 and has enhanced diagnostics. SLUB is the default choice for 1666 a slab allocator. 1667 1668config SLOB 1669 depends on EXPERT 1670 bool "SLOB (Simple Allocator)" 1671 help 1672 SLOB replaces the stock allocator with a drastically simpler 1673 allocator. SLOB is generally more space efficient but 1674 does not perform as well on large systems. 1675 1676endchoice 1677 1678config SLUB_CPU_PARTIAL 1679 default y 1680 depends on SLUB && SMP 1681 bool "SLUB per cpu partial cache" 1682 help 1683 Per cpu partial caches accellerate objects allocation and freeing 1684 that is local to a processor at the price of more indeterminism 1685 in the latency of the free. On overflow these caches will be cleared 1686 which requires the taking of locks that may cause latency spikes. 1687 Typically one would choose no for a realtime system. 1688 1689config MMAP_ALLOW_UNINITIALIZED 1690 bool "Allow mmapped anonymous memory to be uninitialized" 1691 depends on EXPERT && !MMU 1692 default n 1693 help 1694 Normally, and according to the Linux spec, anonymous memory obtained 1695 from mmap() has it's contents cleared before it is passed to 1696 userspace. Enabling this config option allows you to request that 1697 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 1698 providing a huge performance boost. If this option is not enabled, 1699 then the flag will be ignored. 1700 1701 This is taken advantage of by uClibc's malloc(), and also by 1702 ELF-FDPIC binfmt's brk and stack allocator. 1703 1704 Because of the obvious security issues, this option should only be 1705 enabled on embedded devices where you control what is run in 1706 userspace. Since that isn't generally a problem on no-MMU systems, 1707 it is normally safe to say Y here. 1708 1709 See Documentation/nommu-mmap.txt for more information. 1710 1711config SYSTEM_TRUSTED_KEYRING 1712 bool "Provide system-wide ring of trusted keys" 1713 depends on KEYS 1714 help 1715 Provide a system keyring to which trusted keys can be added. Keys in 1716 the keyring are considered to be trusted. Keys may be added at will 1717 by the kernel from compiled-in data and from hardware key stores, but 1718 userspace may only add extra keys if those keys can be verified by 1719 keys already in the keyring. 1720 1721 Keys in this keyring are used by module signature checking. 1722 1723config PROFILING 1724 bool "Profiling support" 1725 help 1726 Say Y here to enable the extended profiling support mechanisms used 1727 by profilers such as OProfile. 1728 1729# 1730# Place an empty function call at each tracepoint site. Can be 1731# dynamically changed for a probe function. 1732# 1733config TRACEPOINTS 1734 bool 1735 1736source "arch/Kconfig" 1737 1738endmenu # General setup 1739 1740config HAVE_GENERIC_DMA_COHERENT 1741 bool 1742 default n 1743 1744config SLABINFO 1745 bool 1746 depends on PROC_FS 1747 depends on SLAB || SLUB_DEBUG 1748 default y 1749 1750config RT_MUTEXES 1751 boolean 1752 1753config BASE_SMALL 1754 int 1755 default 0 if BASE_FULL 1756 default 1 if !BASE_FULL 1757 1758menuconfig MODULES 1759 bool "Enable loadable module support" 1760 option modules 1761 help 1762 Kernel modules are small pieces of compiled code which can 1763 be inserted in the running kernel, rather than being 1764 permanently built into the kernel. You use the "modprobe" 1765 tool to add (and sometimes remove) them. If you say Y here, 1766 many parts of the kernel can be built as modules (by 1767 answering M instead of Y where indicated): this is most 1768 useful for infrequently used options which are not required 1769 for booting. For more information, see the man pages for 1770 modprobe, lsmod, modinfo, insmod and rmmod. 1771 1772 If you say Y here, you will need to run "make 1773 modules_install" to put the modules under /lib/modules/ 1774 where modprobe can find them (you may need to be root to do 1775 this). 1776 1777 If unsure, say Y. 1778 1779if MODULES 1780 1781config MODULE_FORCE_LOAD 1782 bool "Forced module loading" 1783 default n 1784 help 1785 Allow loading of modules without version information (ie. modprobe 1786 --force). Forced module loading sets the 'F' (forced) taint flag and 1787 is usually a really bad idea. 1788 1789config MODULE_UNLOAD 1790 bool "Module unloading" 1791 help 1792 Without this option you will not be able to unload any 1793 modules (note that some modules may not be unloadable 1794 anyway), which makes your kernel smaller, faster 1795 and simpler. If unsure, say Y. 1796 1797config MODULE_FORCE_UNLOAD 1798 bool "Forced module unloading" 1799 depends on MODULE_UNLOAD 1800 help 1801 This option allows you to force a module to unload, even if the 1802 kernel believes it is unsafe: the kernel will remove the module 1803 without waiting for anyone to stop using it (using the -f option to 1804 rmmod). This is mainly for kernel developers and desperate users. 1805 If unsure, say N. 1806 1807config MODVERSIONS 1808 bool "Module versioning support" 1809 help 1810 Usually, you have to use modules compiled with your kernel. 1811 Saying Y here makes it sometimes possible to use modules 1812 compiled for different kernels, by adding enough information 1813 to the modules to (hopefully) spot any changes which would 1814 make them incompatible with the kernel you are running. If 1815 unsure, say N. 1816 1817config MODULE_SRCVERSION_ALL 1818 bool "Source checksum for all modules" 1819 help 1820 Modules which contain a MODULE_VERSION get an extra "srcversion" 1821 field inserted into their modinfo section, which contains a 1822 sum of the source files which made it. This helps maintainers 1823 see exactly which source was used to build a module (since 1824 others sometimes change the module source without updating 1825 the version). With this option, such a "srcversion" field 1826 will be created for all modules. If unsure, say N. 1827 1828config MODULE_SIG 1829 bool "Module signature verification" 1830 depends on MODULES 1831 select SYSTEM_TRUSTED_KEYRING 1832 select KEYS 1833 select CRYPTO 1834 select ASYMMETRIC_KEY_TYPE 1835 select ASYMMETRIC_PUBLIC_KEY_SUBTYPE 1836 select PUBLIC_KEY_ALGO_RSA 1837 select ASN1 1838 select OID_REGISTRY 1839 select X509_CERTIFICATE_PARSER 1840 help 1841 Check modules for valid signatures upon load: the signature 1842 is simply appended to the module. For more information see 1843 Documentation/module-signing.txt. 1844 1845 !!!WARNING!!! If you enable this option, you MUST make sure that the 1846 module DOES NOT get stripped after being signed. This includes the 1847 debuginfo strip done by some packagers (such as rpmbuild) and 1848 inclusion into an initramfs that wants the module size reduced. 1849 1850config MODULE_SIG_FORCE 1851 bool "Require modules to be validly signed" 1852 depends on MODULE_SIG 1853 help 1854 Reject unsigned modules or signed modules for which we don't have a 1855 key. Without this, such modules will simply taint the kernel. 1856 1857config MODULE_SIG_ALL 1858 bool "Automatically sign all modules" 1859 default y 1860 depends on MODULE_SIG 1861 help 1862 Sign all modules during make modules_install. Without this option, 1863 modules must be signed manually, using the scripts/sign-file tool. 1864 1865comment "Do not forget to sign required modules with scripts/sign-file" 1866 depends on MODULE_SIG_FORCE && !MODULE_SIG_ALL 1867 1868choice 1869 prompt "Which hash algorithm should modules be signed with?" 1870 depends on MODULE_SIG 1871 help 1872 This determines which sort of hashing algorithm will be used during 1873 signature generation. This algorithm _must_ be built into the kernel 1874 directly so that signature verification can take place. It is not 1875 possible to load a signed module containing the algorithm to check 1876 the signature on that module. 1877 1878config MODULE_SIG_SHA1 1879 bool "Sign modules with SHA-1" 1880 select CRYPTO_SHA1 1881 1882config MODULE_SIG_SHA224 1883 bool "Sign modules with SHA-224" 1884 select CRYPTO_SHA256 1885 1886config MODULE_SIG_SHA256 1887 bool "Sign modules with SHA-256" 1888 select CRYPTO_SHA256 1889 1890config MODULE_SIG_SHA384 1891 bool "Sign modules with SHA-384" 1892 select CRYPTO_SHA512 1893 1894config MODULE_SIG_SHA512 1895 bool "Sign modules with SHA-512" 1896 select CRYPTO_SHA512 1897 1898endchoice 1899 1900config MODULE_SIG_HASH 1901 string 1902 depends on MODULE_SIG 1903 default "sha1" if MODULE_SIG_SHA1 1904 default "sha224" if MODULE_SIG_SHA224 1905 default "sha256" if MODULE_SIG_SHA256 1906 default "sha384" if MODULE_SIG_SHA384 1907 default "sha512" if MODULE_SIG_SHA512 1908 1909endif # MODULES 1910 1911config INIT_ALL_POSSIBLE 1912 bool 1913 help 1914 Back when each arch used to define their own cpu_online_mask and 1915 cpu_possible_mask, some of them chose to initialize cpu_possible_mask 1916 with all 1s, and others with all 0s. When they were centralised, 1917 it was better to provide this option than to break all the archs 1918 and have several arch maintainers pursuing me down dark alleys. 1919 1920config STOP_MACHINE 1921 bool 1922 default y 1923 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU 1924 help 1925 Need stop_machine() primitive. 1926 1927source "block/Kconfig" 1928 1929config PREEMPT_NOTIFIERS 1930 bool 1931 1932config PADATA 1933 depends on SMP 1934 bool 1935 1936# Can be selected by architectures with broken toolchains 1937# that get confused by correct const<->read_only section 1938# mappings 1939config BROKEN_RODATA 1940 bool 1941 1942config ASN1 1943 tristate 1944 help 1945 Build a simple ASN.1 grammar compiler that produces a bytecode output 1946 that can be interpreted by the ASN.1 stream decoder and used to 1947 inform it as to what tags are to be expected in a stream and what 1948 functions to call on what tags. 1949 1950source "kernel/Kconfig.locks" 1951