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 HAVE_IRQ_WORK 24 bool 25 26config IRQ_WORK 27 bool 28 depends on HAVE_IRQ_WORK 29 30config BUILDTIME_EXTABLE_SORT 31 bool 32 33menu "General setup" 34 35config EXPERIMENTAL 36 bool "Prompt for development and/or incomplete code/drivers" 37 ---help--- 38 Some of the various things that Linux supports (such as network 39 drivers, file systems, network protocols, etc.) can be in a state 40 of development where the functionality, stability, or the level of 41 testing is not yet high enough for general use. This is usually 42 known as the "alpha-test" phase among developers. If a feature is 43 currently in alpha-test, then the developers usually discourage 44 uninformed widespread use of this feature by the general public to 45 avoid "Why doesn't this work?" type mail messages. However, active 46 testing and use of these systems is welcomed. Just be aware that it 47 may not meet the normal level of reliability or it may fail to work 48 in some special cases. Detailed bug reports from people familiar 49 with the kernel internals are usually welcomed by the developers 50 (before submitting bug reports, please read the documents 51 <file:README>, <file:MAINTAINERS>, <file:REPORTING-BUGS>, 52 <file:Documentation/BUG-HUNTING>, and 53 <file:Documentation/oops-tracing.txt> in the kernel source). 54 55 This option will also make obsoleted drivers available. These are 56 drivers that have been replaced by something else, and/or are 57 scheduled to be removed in a future kernel release. 58 59 Unless you intend to help test and develop a feature or driver that 60 falls into this category, or you have a situation that requires 61 using these features, you should probably say N here, which will 62 cause the configurator to present you with fewer choices. If 63 you say Y here, you will be offered the choice of using features or 64 drivers that are currently considered to be in the alpha-test phase. 65 66config BROKEN 67 bool 68 69config BROKEN_ON_SMP 70 bool 71 depends on BROKEN || !SMP 72 default y 73 74config INIT_ENV_ARG_LIMIT 75 int 76 default 32 if !UML 77 default 128 if UML 78 help 79 Maximum of each of the number of arguments and environment 80 variables passed to init from the kernel command line. 81 82 83config CROSS_COMPILE 84 string "Cross-compiler tool prefix" 85 help 86 Same as running 'make CROSS_COMPILE=prefix-' but stored for 87 default make runs in this kernel build directory. You don't 88 need to set this unless you want the configured kernel build 89 directory to select the cross-compiler automatically. 90 91config LOCALVERSION 92 string "Local version - append to kernel release" 93 help 94 Append an extra string to the end of your kernel version. 95 This will show up when you type uname, for example. 96 The string you set here will be appended after the contents of 97 any files with a filename matching localversion* in your 98 object and source tree, in that order. Your total string can 99 be a maximum of 64 characters. 100 101config LOCALVERSION_AUTO 102 bool "Automatically append version information to the version string" 103 default y 104 help 105 This will try to automatically determine if the current tree is a 106 release tree by looking for git tags that belong to the current 107 top of tree revision. 108 109 A string of the format -gxxxxxxxx will be added to the localversion 110 if a git-based tree is found. The string generated by this will be 111 appended after any matching localversion* files, and after the value 112 set in CONFIG_LOCALVERSION. 113 114 (The actual string used here is the first eight characters produced 115 by running the command: 116 117 $ git rev-parse --verify HEAD 118 119 which is done within the script "scripts/setlocalversion".) 120 121config HAVE_KERNEL_GZIP 122 bool 123 124config HAVE_KERNEL_BZIP2 125 bool 126 127config HAVE_KERNEL_LZMA 128 bool 129 130config HAVE_KERNEL_XZ 131 bool 132 133config HAVE_KERNEL_LZO 134 bool 135 136choice 137 prompt "Kernel compression mode" 138 default KERNEL_GZIP 139 depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO 140 help 141 The linux kernel is a kind of self-extracting executable. 142 Several compression algorithms are available, which differ 143 in efficiency, compression and decompression speed. 144 Compression speed is only relevant when building a kernel. 145 Decompression speed is relevant at each boot. 146 147 If you have any problems with bzip2 or lzma compressed 148 kernels, mail me (Alain Knaff) <alain@knaff.lu>. (An older 149 version of this functionality (bzip2 only), for 2.4, was 150 supplied by Christian Ludwig) 151 152 High compression options are mostly useful for users, who 153 are low on disk space (embedded systems), but for whom ram 154 size matters less. 155 156 If in doubt, select 'gzip' 157 158config KERNEL_GZIP 159 bool "Gzip" 160 depends on HAVE_KERNEL_GZIP 161 help 162 The old and tried gzip compression. It provides a good balance 163 between compression ratio and decompression speed. 164 165config KERNEL_BZIP2 166 bool "Bzip2" 167 depends on HAVE_KERNEL_BZIP2 168 help 169 Its compression ratio and speed is intermediate. 170 Decompression speed is slowest among the three. The kernel 171 size is about 10% smaller with bzip2, in comparison to gzip. 172 Bzip2 uses a large amount of memory. For modern kernels you 173 will need at least 8MB RAM or more for booting. 174 175config KERNEL_LZMA 176 bool "LZMA" 177 depends on HAVE_KERNEL_LZMA 178 help 179 The most recent compression algorithm. 180 Its ratio is best, decompression speed is between the other 181 two. Compression is slowest. The kernel size is about 33% 182 smaller with LZMA in comparison to gzip. 183 184config KERNEL_XZ 185 bool "XZ" 186 depends on HAVE_KERNEL_XZ 187 help 188 XZ uses the LZMA2 algorithm and instruction set specific 189 BCJ filters which can improve compression ratio of executable 190 code. The size of the kernel is about 30% smaller with XZ in 191 comparison to gzip. On architectures for which there is a BCJ 192 filter (i386, x86_64, ARM, IA-64, PowerPC, and SPARC), XZ 193 will create a few percent smaller kernel than plain LZMA. 194 195 The speed is about the same as with LZMA: The decompression 196 speed of XZ is better than that of bzip2 but worse than gzip 197 and LZO. Compression is slow. 198 199config KERNEL_LZO 200 bool "LZO" 201 depends on HAVE_KERNEL_LZO 202 help 203 Its compression ratio is the poorest among the 4. The kernel 204 size is about 10% bigger than gzip; however its speed 205 (both compression and decompression) is the fastest. 206 207endchoice 208 209config DEFAULT_HOSTNAME 210 string "Default hostname" 211 default "(none)" 212 help 213 This option determines the default system hostname before userspace 214 calls sethostname(2). The kernel traditionally uses "(none)" here, 215 but you may wish to use a different default here to make a minimal 216 system more usable with less configuration. 217 218config SWAP 219 bool "Support for paging of anonymous memory (swap)" 220 depends on MMU && BLOCK 221 default y 222 help 223 This option allows you to choose whether you want to have support 224 for so called swap devices or swap files in your kernel that are 225 used to provide more virtual memory than the actual RAM present 226 in your computer. If unsure say Y. 227 228config SYSVIPC 229 bool "System V IPC" 230 ---help--- 231 Inter Process Communication is a suite of library functions and 232 system calls which let processes (running programs) synchronize and 233 exchange information. It is generally considered to be a good thing, 234 and some programs won't run unless you say Y here. In particular, if 235 you want to run the DOS emulator dosemu under Linux (read the 236 DOSEMU-HOWTO, available from <http://www.tldp.org/docs.html#howto>), 237 you'll need to say Y here. 238 239 You can find documentation about IPC with "info ipc" and also in 240 section 6.4 of the Linux Programmer's Guide, available from 241 <http://www.tldp.org/guides.html>. 242 243config SYSVIPC_SYSCTL 244 bool 245 depends on SYSVIPC 246 depends on SYSCTL 247 default y 248 249config POSIX_MQUEUE 250 bool "POSIX Message Queues" 251 depends on NET && EXPERIMENTAL 252 ---help--- 253 POSIX variant of message queues is a part of IPC. In POSIX message 254 queues every message has a priority which decides about succession 255 of receiving it by a process. If you want to compile and run 256 programs written e.g. for Solaris with use of its POSIX message 257 queues (functions mq_*) say Y here. 258 259 POSIX message queues are visible as a filesystem called 'mqueue' 260 and can be mounted somewhere if you want to do filesystem 261 operations on message queues. 262 263 If unsure, say Y. 264 265config POSIX_MQUEUE_SYSCTL 266 bool 267 depends on POSIX_MQUEUE 268 depends on SYSCTL 269 default y 270 271config BSD_PROCESS_ACCT 272 bool "BSD Process Accounting" 273 help 274 If you say Y here, a user level program will be able to instruct the 275 kernel (via a special system call) to write process accounting 276 information to a file: whenever a process exits, information about 277 that process will be appended to the file by the kernel. The 278 information includes things such as creation time, owning user, 279 command name, memory usage, controlling terminal etc. (the complete 280 list is in the struct acct in <file:include/linux/acct.h>). It is 281 up to the user level program to do useful things with this 282 information. This is generally a good idea, so say Y. 283 284config BSD_PROCESS_ACCT_V3 285 bool "BSD Process Accounting version 3 file format" 286 depends on BSD_PROCESS_ACCT 287 default n 288 help 289 If you say Y here, the process accounting information is written 290 in a new file format that also logs the process IDs of each 291 process and it's parent. Note that this file format is incompatible 292 with previous v0/v1/v2 file formats, so you will need updated tools 293 for processing it. A preliminary version of these tools is available 294 at <http://www.gnu.org/software/acct/>. 295 296config FHANDLE 297 bool "open by fhandle syscalls" 298 select EXPORTFS 299 help 300 If you say Y here, a user level program will be able to map 301 file names to handle and then later use the handle for 302 different file system operations. This is useful in implementing 303 userspace file servers, which now track files using handles instead 304 of names. The handle would remain the same even if file names 305 get renamed. Enables open_by_handle_at(2) and name_to_handle_at(2) 306 syscalls. 307 308config TASKSTATS 309 bool "Export task/process statistics through netlink (EXPERIMENTAL)" 310 depends on NET 311 default n 312 help 313 Export selected statistics for tasks/processes through the 314 generic netlink interface. Unlike BSD process accounting, the 315 statistics are available during the lifetime of tasks/processes as 316 responses to commands. Like BSD accounting, they are sent to user 317 space on task exit. 318 319 Say N if unsure. 320 321config TASK_DELAY_ACCT 322 bool "Enable per-task delay accounting (EXPERIMENTAL)" 323 depends on TASKSTATS 324 help 325 Collect information on time spent by a task waiting for system 326 resources like cpu, synchronous block I/O completion and swapping 327 in pages. Such statistics can help in setting a task's priorities 328 relative to other tasks for cpu, io, rss limits etc. 329 330 Say N if unsure. 331 332config TASK_XACCT 333 bool "Enable extended accounting over taskstats (EXPERIMENTAL)" 334 depends on TASKSTATS 335 help 336 Collect extended task accounting data and send the data 337 to userland for processing over the taskstats interface. 338 339 Say N if unsure. 340 341config TASK_IO_ACCOUNTING 342 bool "Enable per-task storage I/O accounting (EXPERIMENTAL)" 343 depends on TASK_XACCT 344 help 345 Collect information on the number of bytes of storage I/O which this 346 task has caused. 347 348 Say N if unsure. 349 350config AUDIT 351 bool "Auditing support" 352 depends on NET 353 help 354 Enable auditing infrastructure that can be used with another 355 kernel subsystem, such as SELinux (which requires this for 356 logging of avc messages output). Does not do system-call 357 auditing without CONFIG_AUDITSYSCALL. 358 359config AUDITSYSCALL 360 bool "Enable system-call auditing support" 361 depends on AUDIT && (X86 || PPC || S390 || IA64 || UML || SPARC64 || SUPERH || ARM) 362 default y if SECURITY_SELINUX 363 help 364 Enable low-overhead system-call auditing infrastructure that 365 can be used independently or with another kernel subsystem, 366 such as SELinux. 367 368config AUDIT_WATCH 369 def_bool y 370 depends on AUDITSYSCALL 371 select FSNOTIFY 372 373config AUDIT_TREE 374 def_bool y 375 depends on AUDITSYSCALL 376 select FSNOTIFY 377 378config AUDIT_LOGINUID_IMMUTABLE 379 bool "Make audit loginuid immutable" 380 depends on AUDIT 381 help 382 The config option toggles if a task setting its loginuid requires 383 CAP_SYS_AUDITCONTROL or if that task should require no special permissions 384 but should instead only allow setting its loginuid if it was never 385 previously set. On systems which use systemd or a similar central 386 process to restart login services this should be set to true. On older 387 systems in which an admin would typically have to directly stop and 388 start processes this should be set to false. Setting this to true allows 389 one to drop potentially dangerous capabilites from the login tasks, 390 but may not be backwards compatible with older init systems. 391 392source "kernel/irq/Kconfig" 393source "kernel/time/Kconfig" 394 395menu "RCU Subsystem" 396 397choice 398 prompt "RCU Implementation" 399 default TREE_RCU 400 401config TREE_RCU 402 bool "Tree-based hierarchical RCU" 403 depends on !PREEMPT && SMP 404 help 405 This option selects the RCU implementation that is 406 designed for very large SMP system with hundreds or 407 thousands of CPUs. It also scales down nicely to 408 smaller systems. 409 410config TREE_PREEMPT_RCU 411 bool "Preemptible tree-based hierarchical RCU" 412 depends on PREEMPT && SMP 413 help 414 This option selects the RCU implementation that is 415 designed for very large SMP systems with hundreds or 416 thousands of CPUs, but for which real-time response 417 is also required. It also scales down nicely to 418 smaller systems. 419 420config TINY_RCU 421 bool "UP-only small-memory-footprint RCU" 422 depends on !PREEMPT && !SMP 423 help 424 This option selects the RCU implementation that is 425 designed for UP systems from which real-time response 426 is not required. This option greatly reduces the 427 memory footprint of RCU. 428 429config TINY_PREEMPT_RCU 430 bool "Preemptible UP-only small-memory-footprint RCU" 431 depends on PREEMPT && !SMP 432 help 433 This option selects the RCU implementation that is designed 434 for real-time UP systems. This option greatly reduces the 435 memory footprint of RCU. 436 437endchoice 438 439config PREEMPT_RCU 440 def_bool ( TREE_PREEMPT_RCU || TINY_PREEMPT_RCU ) 441 help 442 This option enables preemptible-RCU code that is common between 443 the TREE_PREEMPT_RCU and TINY_PREEMPT_RCU implementations. 444 445config RCU_FANOUT 446 int "Tree-based hierarchical RCU fanout value" 447 range 2 64 if 64BIT 448 range 2 32 if !64BIT 449 depends on TREE_RCU || TREE_PREEMPT_RCU 450 default 64 if 64BIT 451 default 32 if !64BIT 452 help 453 This option controls the fanout of hierarchical implementations 454 of RCU, allowing RCU to work efficiently on machines with 455 large numbers of CPUs. This value must be at least the fourth 456 root of NR_CPUS, which allows NR_CPUS to be insanely large. 457 The default value of RCU_FANOUT should be used for production 458 systems, but if you are stress-testing the RCU implementation 459 itself, small RCU_FANOUT values allow you to test large-system 460 code paths on small(er) systems. 461 462 Select a specific number if testing RCU itself. 463 Take the default if unsure. 464 465config RCU_FANOUT_LEAF 466 int "Tree-based hierarchical RCU leaf-level fanout value" 467 range 2 RCU_FANOUT if 64BIT 468 range 2 RCU_FANOUT if !64BIT 469 depends on TREE_RCU || TREE_PREEMPT_RCU 470 default 16 471 help 472 This option controls the leaf-level fanout of hierarchical 473 implementations of RCU, and allows trading off cache misses 474 against lock contention. Systems that synchronize their 475 scheduling-clock interrupts for energy-efficiency reasons will 476 want the default because the smaller leaf-level fanout keeps 477 lock contention levels acceptably low. Very large systems 478 (hundreds or thousands of CPUs) will instead want to set this 479 value to the maximum value possible in order to reduce the 480 number of cache misses incurred during RCU's grace-period 481 initialization. These systems tend to run CPU-bound, and thus 482 are not helped by synchronized interrupts, and thus tend to 483 skew them, which reduces lock contention enough that large 484 leaf-level fanouts work well. 485 486 Select a specific number if testing RCU itself. 487 488 Select the maximum permissible value for large systems. 489 490 Take the default if unsure. 491 492config RCU_FANOUT_EXACT 493 bool "Disable tree-based hierarchical RCU auto-balancing" 494 depends on TREE_RCU || TREE_PREEMPT_RCU 495 default n 496 help 497 This option forces use of the exact RCU_FANOUT value specified, 498 regardless of imbalances in the hierarchy. This is useful for 499 testing RCU itself, and might one day be useful on systems with 500 strong NUMA behavior. 501 502 Without RCU_FANOUT_EXACT, the code will balance the hierarchy. 503 504 Say N if unsure. 505 506config RCU_FAST_NO_HZ 507 bool "Accelerate last non-dyntick-idle CPU's grace periods" 508 depends on NO_HZ && SMP 509 default n 510 help 511 This option causes RCU to attempt to accelerate grace periods 512 in order to allow CPUs to enter dynticks-idle state more 513 quickly. On the other hand, this option increases the overhead 514 of the dynticks-idle checking, particularly on systems with 515 large numbers of CPUs. 516 517 Say Y if energy efficiency is critically important, particularly 518 if you have relatively few CPUs. 519 520 Say N if you are unsure. 521 522config TREE_RCU_TRACE 523 def_bool RCU_TRACE && ( TREE_RCU || TREE_PREEMPT_RCU ) 524 select DEBUG_FS 525 help 526 This option provides tracing for the TREE_RCU and 527 TREE_PREEMPT_RCU implementations, permitting Makefile to 528 trivially select kernel/rcutree_trace.c. 529 530config RCU_BOOST 531 bool "Enable RCU priority boosting" 532 depends on RT_MUTEXES && PREEMPT_RCU 533 default n 534 help 535 This option boosts the priority of preempted RCU readers that 536 block the current preemptible RCU grace period for too long. 537 This option also prevents heavy loads from blocking RCU 538 callback invocation for all flavors of RCU. 539 540 Say Y here if you are working with real-time apps or heavy loads 541 Say N here if you are unsure. 542 543config RCU_BOOST_PRIO 544 int "Real-time priority to boost RCU readers to" 545 range 1 99 546 depends on RCU_BOOST 547 default 1 548 help 549 This option specifies the real-time priority to which long-term 550 preempted RCU readers are to be boosted. If you are working 551 with a real-time application that has one or more CPU-bound 552 threads running at a real-time priority level, you should set 553 RCU_BOOST_PRIO to a priority higher then the highest-priority 554 real-time CPU-bound thread. The default RCU_BOOST_PRIO value 555 of 1 is appropriate in the common case, which is real-time 556 applications that do not have any CPU-bound threads. 557 558 Some real-time applications might not have a single real-time 559 thread that saturates a given CPU, but instead might have 560 multiple real-time threads that, taken together, fully utilize 561 that CPU. In this case, you should set RCU_BOOST_PRIO to 562 a priority higher than the lowest-priority thread that is 563 conspiring to prevent the CPU from running any non-real-time 564 tasks. For example, if one thread at priority 10 and another 565 thread at priority 5 are between themselves fully consuming 566 the CPU time on a given CPU, then RCU_BOOST_PRIO should be 567 set to priority 6 or higher. 568 569 Specify the real-time priority, or take the default if unsure. 570 571config RCU_BOOST_DELAY 572 int "Milliseconds to delay boosting after RCU grace-period start" 573 range 0 3000 574 depends on RCU_BOOST 575 default 500 576 help 577 This option specifies the time to wait after the beginning of 578 a given grace period before priority-boosting preempted RCU 579 readers blocking that grace period. Note that any RCU reader 580 blocking an expedited RCU grace period is boosted immediately. 581 582 Accept the default if unsure. 583 584endmenu # "RCU Subsystem" 585 586config IKCONFIG 587 tristate "Kernel .config support" 588 ---help--- 589 This option enables the complete Linux kernel ".config" file 590 contents to be saved in the kernel. It provides documentation 591 of which kernel options are used in a running kernel or in an 592 on-disk kernel. This information can be extracted from the kernel 593 image file with the script scripts/extract-ikconfig and used as 594 input to rebuild the current kernel or to build another kernel. 595 It can also be extracted from a running kernel by reading 596 /proc/config.gz if enabled (below). 597 598config IKCONFIG_PROC 599 bool "Enable access to .config through /proc/config.gz" 600 depends on IKCONFIG && PROC_FS 601 ---help--- 602 This option enables access to the kernel configuration file 603 through /proc/config.gz. 604 605config LOG_BUF_SHIFT 606 int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" 607 range 12 21 608 default 17 609 help 610 Select kernel log buffer size as a power of 2. 611 Examples: 612 17 => 128 KB 613 16 => 64 KB 614 15 => 32 KB 615 14 => 16 KB 616 13 => 8 KB 617 12 => 4 KB 618 619# 620# Architectures with an unreliable sched_clock() should select this: 621# 622config HAVE_UNSTABLE_SCHED_CLOCK 623 bool 624 625menuconfig CGROUPS 626 boolean "Control Group support" 627 depends on EVENTFD 628 help 629 This option adds support for grouping sets of processes together, for 630 use with process control subsystems such as Cpusets, CFS, memory 631 controls or device isolation. 632 See 633 - Documentation/scheduler/sched-design-CFS.txt (CFS) 634 - Documentation/cgroups/ (features for grouping, isolation 635 and resource control) 636 637 Say N if unsure. 638 639if CGROUPS 640 641config CGROUP_DEBUG 642 bool "Example debug cgroup subsystem" 643 default n 644 help 645 This option enables a simple cgroup subsystem that 646 exports useful debugging information about the cgroups 647 framework. 648 649 Say N if unsure. 650 651config CGROUP_FREEZER 652 bool "Freezer cgroup subsystem" 653 help 654 Provides a way to freeze and unfreeze all tasks in a 655 cgroup. 656 657config CGROUP_DEVICE 658 bool "Device controller for cgroups" 659 help 660 Provides a cgroup implementing whitelists for devices which 661 a process in the cgroup can mknod or open. 662 663config CPUSETS 664 bool "Cpuset support" 665 help 666 This option will let you create and manage CPUSETs which 667 allow dynamically partitioning a system into sets of CPUs and 668 Memory Nodes and assigning tasks to run only within those sets. 669 This is primarily useful on large SMP or NUMA systems. 670 671 Say N if unsure. 672 673config PROC_PID_CPUSET 674 bool "Include legacy /proc/<pid>/cpuset file" 675 depends on CPUSETS 676 default y 677 678config CGROUP_CPUACCT 679 bool "Simple CPU accounting cgroup subsystem" 680 help 681 Provides a simple Resource Controller for monitoring the 682 total CPU consumed by the tasks in a cgroup. 683 684config RESOURCE_COUNTERS 685 bool "Resource counters" 686 help 687 This option enables controller independent resource accounting 688 infrastructure that works with cgroups. 689 690config CGROUP_MEM_RES_CTLR 691 bool "Memory Resource Controller for Control Groups" 692 depends on RESOURCE_COUNTERS 693 select MM_OWNER 694 help 695 Provides a memory resource controller that manages both anonymous 696 memory and page cache. (See Documentation/cgroups/memory.txt) 697 698 Note that setting this option increases fixed memory overhead 699 associated with each page of memory in the system. By this, 700 20(40)bytes/PAGE_SIZE on 32(64)bit system will be occupied by memory 701 usage tracking struct at boot. Total amount of this is printed out 702 at boot. 703 704 Only enable when you're ok with these trade offs and really 705 sure you need the memory resource controller. Even when you enable 706 this, you can set "cgroup_disable=memory" at your boot option to 707 disable memory resource controller and you can avoid overheads. 708 (and lose benefits of memory resource controller) 709 710 This config option also selects MM_OWNER config option, which 711 could in turn add some fork/exit overhead. 712 713config CGROUP_MEM_RES_CTLR_SWAP 714 bool "Memory Resource Controller Swap Extension" 715 depends on CGROUP_MEM_RES_CTLR && SWAP 716 help 717 Add swap management feature to memory resource controller. When you 718 enable this, you can limit mem+swap usage per cgroup. In other words, 719 when you disable this, memory resource controller has no cares to 720 usage of swap...a process can exhaust all of the swap. This extension 721 is useful when you want to avoid exhaustion swap but this itself 722 adds more overheads and consumes memory for remembering information. 723 Especially if you use 32bit system or small memory system, please 724 be careful about enabling this. When memory resource controller 725 is disabled by boot option, this will be automatically disabled and 726 there will be no overhead from this. Even when you set this config=y, 727 if boot option "swapaccount=0" is set, swap will not be accounted. 728 Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page 729 size is 4096bytes, 512k per 1Gbytes of swap. 730config CGROUP_MEM_RES_CTLR_SWAP_ENABLED 731 bool "Memory Resource Controller Swap Extension enabled by default" 732 depends on CGROUP_MEM_RES_CTLR_SWAP 733 default y 734 help 735 Memory Resource Controller Swap Extension comes with its price in 736 a bigger memory consumption. General purpose distribution kernels 737 which want to enable the feature but keep it disabled by default 738 and let the user enable it by swapaccount boot command line 739 parameter should have this option unselected. 740 For those who want to have the feature enabled by default should 741 select this option (if, for some reason, they need to disable it 742 then swapaccount=0 does the trick). 743config CGROUP_MEM_RES_CTLR_KMEM 744 bool "Memory Resource Controller Kernel Memory accounting (EXPERIMENTAL)" 745 depends on CGROUP_MEM_RES_CTLR && EXPERIMENTAL 746 default n 747 help 748 The Kernel Memory extension for Memory Resource Controller can limit 749 the amount of memory used by kernel objects in the system. Those are 750 fundamentally different from the entities handled by the standard 751 Memory Controller, which are page-based, and can be swapped. Users of 752 the kmem extension can use it to guarantee that no group of processes 753 will ever exhaust kernel resources alone. 754 755config CGROUP_PERF 756 bool "Enable perf_event per-cpu per-container group (cgroup) monitoring" 757 depends on PERF_EVENTS && CGROUPS 758 help 759 This option extends the per-cpu mode to restrict monitoring to 760 threads which belong to the cgroup specified and run on the 761 designated cpu. 762 763 Say N if unsure. 764 765menuconfig CGROUP_SCHED 766 bool "Group CPU scheduler" 767 default n 768 help 769 This feature lets CPU scheduler recognize task groups and control CPU 770 bandwidth allocation to such task groups. It uses cgroups to group 771 tasks. 772 773if CGROUP_SCHED 774config FAIR_GROUP_SCHED 775 bool "Group scheduling for SCHED_OTHER" 776 depends on CGROUP_SCHED 777 default CGROUP_SCHED 778 779config CFS_BANDWIDTH 780 bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED" 781 depends on EXPERIMENTAL 782 depends on FAIR_GROUP_SCHED 783 default n 784 help 785 This option allows users to define CPU bandwidth rates (limits) for 786 tasks running within the fair group scheduler. Groups with no limit 787 set are considered to be unconstrained and will run with no 788 restriction. 789 See tip/Documentation/scheduler/sched-bwc.txt for more information. 790 791config RT_GROUP_SCHED 792 bool "Group scheduling for SCHED_RR/FIFO" 793 depends on EXPERIMENTAL 794 depends on CGROUP_SCHED 795 default n 796 help 797 This feature lets you explicitly allocate real CPU bandwidth 798 to task groups. If enabled, it will also make it impossible to 799 schedule realtime tasks for non-root users until you allocate 800 realtime bandwidth for them. 801 See Documentation/scheduler/sched-rt-group.txt for more information. 802 803endif #CGROUP_SCHED 804 805config BLK_CGROUP 806 tristate "Block IO controller" 807 depends on BLOCK 808 default n 809 ---help--- 810 Generic block IO controller cgroup interface. This is the common 811 cgroup interface which should be used by various IO controlling 812 policies. 813 814 Currently, CFQ IO scheduler uses it to recognize task groups and 815 control disk bandwidth allocation (proportional time slice allocation) 816 to such task groups. It is also used by bio throttling logic in 817 block layer to implement upper limit in IO rates on a device. 818 819 This option only enables generic Block IO controller infrastructure. 820 One needs to also enable actual IO controlling logic/policy. For 821 enabling proportional weight division of disk bandwidth in CFQ, set 822 CONFIG_CFQ_GROUP_IOSCHED=y; for enabling throttling policy, set 823 CONFIG_BLK_DEV_THROTTLING=y. 824 825 See Documentation/cgroups/blkio-controller.txt for more information. 826 827config DEBUG_BLK_CGROUP 828 bool "Enable Block IO controller debugging" 829 depends on BLK_CGROUP 830 default n 831 ---help--- 832 Enable some debugging help. Currently it exports additional stat 833 files in a cgroup which can be useful for debugging. 834 835endif # CGROUPS 836 837config CHECKPOINT_RESTORE 838 bool "Checkpoint/restore support" if EXPERT 839 default n 840 help 841 Enables additional kernel features in a sake of checkpoint/restore. 842 In particular it adds auxiliary prctl codes to setup process text, 843 data and heap segment sizes, and a few additional /proc filesystem 844 entries. 845 846 If unsure, say N here. 847 848menuconfig NAMESPACES 849 bool "Namespaces support" if EXPERT 850 default !EXPERT 851 help 852 Provides the way to make tasks work with different objects using 853 the same id. For example same IPC id may refer to different objects 854 or same user id or pid may refer to different tasks when used in 855 different namespaces. 856 857if NAMESPACES 858 859config UTS_NS 860 bool "UTS namespace" 861 default y 862 help 863 In this namespace tasks see different info provided with the 864 uname() system call 865 866config IPC_NS 867 bool "IPC namespace" 868 depends on (SYSVIPC || POSIX_MQUEUE) 869 default y 870 help 871 In this namespace tasks work with IPC ids which correspond to 872 different IPC objects in different namespaces. 873 874config USER_NS 875 bool "User namespace (EXPERIMENTAL)" 876 depends on EXPERIMENTAL 877 depends on UIDGID_CONVERTED 878 select UIDGID_STRICT_TYPE_CHECKS 879 880 default n 881 help 882 This allows containers, i.e. vservers, to use user namespaces 883 to provide different user info for different servers. 884 If unsure, say N. 885 886config PID_NS 887 bool "PID Namespaces" 888 default y 889 help 890 Support process id namespaces. This allows having multiple 891 processes with the same pid as long as they are in different 892 pid namespaces. This is a building block of containers. 893 894config NET_NS 895 bool "Network namespace" 896 depends on NET 897 default y 898 help 899 Allow user space to create what appear to be multiple instances 900 of the network stack. 901 902endif # NAMESPACES 903 904config UIDGID_CONVERTED 905 # True if all of the selected software conmponents are known 906 # to have uid_t and gid_t converted to kuid_t and kgid_t 907 # where appropriate and are otherwise safe to use with 908 # the user namespace. 909 bool 910 default y 911 912 # List of kernel pieces that need user namespace work 913 # Features 914 depends on SYSVIPC = n 915 depends on IMA = n 916 depends on EVM = n 917 depends on KEYS = n 918 depends on AUDIT = n 919 depends on AUDITSYSCALL = n 920 depends on TASKSTATS = n 921 depends on TRACING = n 922 depends on FS_POSIX_ACL = n 923 depends on QUOTA = n 924 depends on QUOTACTL = n 925 depends on DEBUG_CREDENTIALS = n 926 depends on BSD_PROCESS_ACCT = n 927 depends on DRM = n 928 depends on PROC_EVENTS = n 929 930 # Networking 931 depends on NET = n 932 depends on NET_9P = n 933 depends on IPX = n 934 depends on PHONET = n 935 depends on NET_CLS_FLOW = n 936 depends on NETFILTER_XT_MATCH_OWNER = n 937 depends on NETFILTER_XT_MATCH_RECENT = n 938 depends on NETFILTER_XT_TARGET_LOG = n 939 depends on NETFILTER_NETLINK_LOG = n 940 depends on INET = n 941 depends on IPV6 = n 942 depends on IP_SCTP = n 943 depends on AF_RXRPC = n 944 depends on LLC2 = n 945 depends on NET_KEY = n 946 depends on INET_DIAG = n 947 depends on DNS_RESOLVER = n 948 depends on AX25 = n 949 depends on ATALK = n 950 951 # Filesystems 952 depends on USB_DEVICEFS = n 953 depends on USB_GADGETFS = n 954 depends on USB_FUNCTIONFS = n 955 depends on DEVTMPFS = n 956 depends on XENFS = n 957 958 depends on 9P_FS = n 959 depends on ADFS_FS = n 960 depends on AFFS_FS = n 961 depends on AFS_FS = n 962 depends on AUTOFS4_FS = n 963 depends on BEFS_FS = n 964 depends on BFS_FS = n 965 depends on BTRFS_FS = n 966 depends on CEPH_FS = n 967 depends on CIFS = n 968 depends on CODA_FS = n 969 depends on CONFIGFS_FS = n 970 depends on CRAMFS = n 971 depends on DEBUG_FS = n 972 depends on ECRYPT_FS = n 973 depends on EFS_FS = n 974 depends on EXOFS_FS = n 975 depends on FAT_FS = n 976 depends on FUSE_FS = n 977 depends on GFS2_FS = n 978 depends on HFS_FS = n 979 depends on HFSPLUS_FS = n 980 depends on HPFS_FS = n 981 depends on HUGETLBFS = n 982 depends on ISO9660_FS = n 983 depends on JFFS2_FS = n 984 depends on JFS_FS = n 985 depends on LOGFS = n 986 depends on MINIX_FS = n 987 depends on NCP_FS = n 988 depends on NFSD = n 989 depends on NFS_FS = n 990 depends on NILFS2_FS = n 991 depends on NTFS_FS = n 992 depends on OCFS2_FS = n 993 depends on OMFS_FS = n 994 depends on QNX4FS_FS = n 995 depends on QNX6FS_FS = n 996 depends on REISERFS_FS = n 997 depends on SQUASHFS = n 998 depends on SYSV_FS = n 999 depends on UBIFS_FS = n 1000 depends on UDF_FS = n 1001 depends on UFS_FS = n 1002 depends on VXFS_FS = n 1003 depends on XFS_FS = n 1004 1005 depends on !UML || HOSTFS = n 1006 1007 # The rare drivers that won't build 1008 depends on AIRO = n 1009 depends on AIRO_CS = n 1010 depends on TUN = n 1011 depends on INFINIBAND_QIB = n 1012 depends on BLK_DEV_LOOP = n 1013 depends on ANDROID_BINDER_IPC = n 1014 1015 # Security modules 1016 depends on SECURITY_TOMOYO = n 1017 depends on SECURITY_APPARMOR = n 1018 1019config UIDGID_STRICT_TYPE_CHECKS 1020 bool "Require conversions between uid/gids and their internal representation" 1021 depends on UIDGID_CONVERTED 1022 default n 1023 help 1024 While the nececessary conversions are being added to all subsystems this option allows 1025 the code to continue to build for unconverted subsystems. 1026 1027 Say Y here if you want the strict type checking enabled 1028 1029config SCHED_AUTOGROUP 1030 bool "Automatic process group scheduling" 1031 select EVENTFD 1032 select CGROUPS 1033 select CGROUP_SCHED 1034 select FAIR_GROUP_SCHED 1035 help 1036 This option optimizes the scheduler for common desktop workloads by 1037 automatically creating and populating task groups. This separation 1038 of workloads isolates aggressive CPU burners (like build jobs) from 1039 desktop applications. Task group autogeneration is currently based 1040 upon task session. 1041 1042config MM_OWNER 1043 bool 1044 1045config SYSFS_DEPRECATED 1046 bool "Enable deprecated sysfs features to support old userspace tools" 1047 depends on SYSFS 1048 default n 1049 help 1050 This option adds code that switches the layout of the "block" class 1051 devices, to not show up in /sys/class/block/, but only in 1052 /sys/block/. 1053 1054 This switch is only active when the sysfs.deprecated=1 boot option is 1055 passed or the SYSFS_DEPRECATED_V2 option is set. 1056 1057 This option allows new kernels to run on old distributions and tools, 1058 which might get confused by /sys/class/block/. Since 2007/2008 all 1059 major distributions and tools handle this just fine. 1060 1061 Recent distributions and userspace tools after 2009/2010 depend on 1062 the existence of /sys/class/block/, and will not work with this 1063 option enabled. 1064 1065 Only if you are using a new kernel on an old distribution, you might 1066 need to say Y here. 1067 1068config SYSFS_DEPRECATED_V2 1069 bool "Enable deprecated sysfs features by default" 1070 default n 1071 depends on SYSFS 1072 depends on SYSFS_DEPRECATED 1073 help 1074 Enable deprecated sysfs by default. 1075 1076 See the CONFIG_SYSFS_DEPRECATED option for more details about this 1077 option. 1078 1079 Only if you are using a new kernel on an old distribution, you might 1080 need to say Y here. Even then, odds are you would not need it 1081 enabled, you can always pass the boot option if absolutely necessary. 1082 1083config RELAY 1084 bool "Kernel->user space relay support (formerly relayfs)" 1085 help 1086 This option enables support for relay interface support in 1087 certain file systems (such as debugfs). 1088 It is designed to provide an efficient mechanism for tools and 1089 facilities to relay large amounts of data from kernel space to 1090 user space. 1091 1092 If unsure, say N. 1093 1094config BLK_DEV_INITRD 1095 bool "Initial RAM filesystem and RAM disk (initramfs/initrd) support" 1096 depends on BROKEN || !FRV 1097 help 1098 The initial RAM filesystem is a ramfs which is loaded by the 1099 boot loader (loadlin or lilo) and that is mounted as root 1100 before the normal boot procedure. It is typically used to 1101 load modules needed to mount the "real" root file system, 1102 etc. See <file:Documentation/initrd.txt> for details. 1103 1104 If RAM disk support (BLK_DEV_RAM) is also included, this 1105 also enables initial RAM disk (initrd) support and adds 1106 15 Kbytes (more on some other architectures) to the kernel size. 1107 1108 If unsure say Y. 1109 1110if BLK_DEV_INITRD 1111 1112source "usr/Kconfig" 1113 1114endif 1115 1116config CC_OPTIMIZE_FOR_SIZE 1117 bool "Optimize for size" 1118 help 1119 Enabling this option will pass "-Os" instead of "-O2" to gcc 1120 resulting in a smaller kernel. 1121 1122 If unsure, say Y. 1123 1124config SYSCTL 1125 bool 1126 1127config ANON_INODES 1128 bool 1129 1130menuconfig EXPERT 1131 bool "Configure standard kernel features (expert users)" 1132 # Unhide debug options, to make the on-by-default options visible 1133 select DEBUG_KERNEL 1134 help 1135 This option allows certain base kernel options and settings 1136 to be disabled or tweaked. This is for specialized 1137 environments which can tolerate a "non-standard" kernel. 1138 Only use this if you really know what you are doing. 1139 1140config UID16 1141 bool "Enable 16-bit UID system calls" if EXPERT 1142 depends on ARM || BLACKFIN || CRIS || FRV || H8300 || X86_32 || M68K || (S390 && !64BIT) || SUPERH || SPARC32 || (SPARC64 && COMPAT) || UML || (X86_64 && IA32_EMULATION) 1143 default y 1144 help 1145 This enables the legacy 16-bit UID syscall wrappers. 1146 1147config SYSCTL_SYSCALL 1148 bool "Sysctl syscall support" if EXPERT 1149 depends on PROC_SYSCTL 1150 default n 1151 select SYSCTL 1152 ---help--- 1153 sys_sysctl uses binary paths that have been found challenging 1154 to properly maintain and use. The interface in /proc/sys 1155 using paths with ascii names is now the primary path to this 1156 information. 1157 1158 Almost nothing using the binary sysctl interface so if you are 1159 trying to save some space it is probably safe to disable this, 1160 making your kernel marginally smaller. 1161 1162 If unsure say N here. 1163 1164config KALLSYMS 1165 bool "Load all symbols for debugging/ksymoops" if EXPERT 1166 default y 1167 help 1168 Say Y here to let the kernel print out symbolic crash information and 1169 symbolic stack backtraces. This increases the size of the kernel 1170 somewhat, as all symbols have to be loaded into the kernel image. 1171 1172config KALLSYMS_ALL 1173 bool "Include all symbols in kallsyms" 1174 depends on DEBUG_KERNEL && KALLSYMS 1175 help 1176 Normally kallsyms only contains the symbols of functions for nicer 1177 OOPS messages and backtraces (i.e., symbols from the text and inittext 1178 sections). This is sufficient for most cases. And only in very rare 1179 cases (e.g., when a debugger is used) all symbols are required (e.g., 1180 names of variables from the data sections, etc). 1181 1182 This option makes sure that all symbols are loaded into the kernel 1183 image (i.e., symbols from all sections) in cost of increased kernel 1184 size (depending on the kernel configuration, it may be 300KiB or 1185 something like this). 1186 1187 Say N unless you really need all symbols. 1188 1189config HOTPLUG 1190 bool "Support for hot-pluggable devices" if EXPERT 1191 default y 1192 help 1193 This option is provided for the case where no hotplug or uevent 1194 capabilities is wanted by the kernel. You should only consider 1195 disabling this option for embedded systems that do not use modules, a 1196 dynamic /dev tree, or dynamic device discovery. Just say Y. 1197 1198config PRINTK 1199 default y 1200 bool "Enable support for printk" if EXPERT 1201 help 1202 This option enables normal printk support. Removing it 1203 eliminates most of the message strings from the kernel image 1204 and makes the kernel more or less silent. As this makes it 1205 very difficult to diagnose system problems, saying N here is 1206 strongly discouraged. 1207 1208config BUG 1209 bool "BUG() support" if EXPERT 1210 default y 1211 help 1212 Disabling this option eliminates support for BUG and WARN, reducing 1213 the size of your kernel image and potentially quietly ignoring 1214 numerous fatal conditions. You should only consider disabling this 1215 option for embedded systems with no facilities for reporting errors. 1216 Just say Y. 1217 1218config ELF_CORE 1219 default y 1220 bool "Enable ELF core dumps" if EXPERT 1221 help 1222 Enable support for generating core dumps. Disabling saves about 4k. 1223 1224 1225config PCSPKR_PLATFORM 1226 bool "Enable PC-Speaker support" if EXPERT 1227 depends on HAVE_PCSPKR_PLATFORM 1228 select I8253_LOCK 1229 default y 1230 help 1231 This option allows to disable the internal PC-Speaker 1232 support, saving some memory. 1233 1234config HAVE_PCSPKR_PLATFORM 1235 bool 1236 1237config BASE_FULL 1238 default y 1239 bool "Enable full-sized data structures for core" if EXPERT 1240 help 1241 Disabling this option reduces the size of miscellaneous core 1242 kernel data structures. This saves memory on small machines, 1243 but may reduce performance. 1244 1245config FUTEX 1246 bool "Enable futex support" if EXPERT 1247 default y 1248 select RT_MUTEXES 1249 help 1250 Disabling this option will cause the kernel to be built without 1251 support for "fast userspace mutexes". The resulting kernel may not 1252 run glibc-based applications correctly. 1253 1254config EPOLL 1255 bool "Enable eventpoll support" if EXPERT 1256 default y 1257 select ANON_INODES 1258 help 1259 Disabling this option will cause the kernel to be built without 1260 support for epoll family of system calls. 1261 1262config SIGNALFD 1263 bool "Enable signalfd() system call" if EXPERT 1264 select ANON_INODES 1265 default y 1266 help 1267 Enable the signalfd() system call that allows to receive signals 1268 on a file descriptor. 1269 1270 If unsure, say Y. 1271 1272config TIMERFD 1273 bool "Enable timerfd() system call" if EXPERT 1274 select ANON_INODES 1275 default y 1276 help 1277 Enable the timerfd() system call that allows to receive timer 1278 events on a file descriptor. 1279 1280 If unsure, say Y. 1281 1282config EVENTFD 1283 bool "Enable eventfd() system call" if EXPERT 1284 select ANON_INODES 1285 default y 1286 help 1287 Enable the eventfd() system call that allows to receive both 1288 kernel notification (ie. KAIO) or userspace notifications. 1289 1290 If unsure, say Y. 1291 1292config SHMEM 1293 bool "Use full shmem filesystem" if EXPERT 1294 default y 1295 depends on MMU 1296 help 1297 The shmem is an internal filesystem used to manage shared memory. 1298 It is backed by swap and manages resource limits. It is also exported 1299 to userspace as tmpfs if TMPFS is enabled. Disabling this 1300 option replaces shmem and tmpfs with the much simpler ramfs code, 1301 which may be appropriate on small systems without swap. 1302 1303config AIO 1304 bool "Enable AIO support" if EXPERT 1305 default y 1306 help 1307 This option enables POSIX asynchronous I/O which may by used 1308 by some high performance threaded applications. Disabling 1309 this option saves about 7k. 1310 1311config EMBEDDED 1312 bool "Embedded system" 1313 select EXPERT 1314 help 1315 This option should be enabled if compiling the kernel for 1316 an embedded system so certain expert options are available 1317 for configuration. 1318 1319config HAVE_PERF_EVENTS 1320 bool 1321 help 1322 See tools/perf/design.txt for details. 1323 1324config PERF_USE_VMALLOC 1325 bool 1326 help 1327 See tools/perf/design.txt for details 1328 1329menu "Kernel Performance Events And Counters" 1330 1331config PERF_EVENTS 1332 bool "Kernel performance events and counters" 1333 default y if PROFILING 1334 depends on HAVE_PERF_EVENTS 1335 select ANON_INODES 1336 select IRQ_WORK 1337 help 1338 Enable kernel support for various performance events provided 1339 by software and hardware. 1340 1341 Software events are supported either built-in or via the 1342 use of generic tracepoints. 1343 1344 Most modern CPUs support performance events via performance 1345 counter registers. These registers count the number of certain 1346 types of hw events: such as instructions executed, cachemisses 1347 suffered, or branches mis-predicted - without slowing down the 1348 kernel or applications. These registers can also trigger interrupts 1349 when a threshold number of events have passed - and can thus be 1350 used to profile the code that runs on that CPU. 1351 1352 The Linux Performance Event subsystem provides an abstraction of 1353 these software and hardware event capabilities, available via a 1354 system call and used by the "perf" utility in tools/perf/. It 1355 provides per task and per CPU counters, and it provides event 1356 capabilities on top of those. 1357 1358 Say Y if unsure. 1359 1360config DEBUG_PERF_USE_VMALLOC 1361 default n 1362 bool "Debug: use vmalloc to back perf mmap() buffers" 1363 depends on PERF_EVENTS && DEBUG_KERNEL 1364 select PERF_USE_VMALLOC 1365 help 1366 Use vmalloc memory to back perf mmap() buffers. 1367 1368 Mostly useful for debugging the vmalloc code on platforms 1369 that don't require it. 1370 1371 Say N if unsure. 1372 1373endmenu 1374 1375config VM_EVENT_COUNTERS 1376 default y 1377 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1378 help 1379 VM event counters are needed for event counts to be shown. 1380 This option allows the disabling of the VM event counters 1381 on EXPERT systems. /proc/vmstat will only show page counts 1382 if VM event counters are disabled. 1383 1384config PCI_QUIRKS 1385 default y 1386 bool "Enable PCI quirk workarounds" if EXPERT 1387 depends on PCI 1388 help 1389 This enables workarounds for various PCI chipset 1390 bugs/quirks. Disable this only if your target machine is 1391 unaffected by PCI quirks. 1392 1393config SLUB_DEBUG 1394 default y 1395 bool "Enable SLUB debugging support" if EXPERT 1396 depends on SLUB && SYSFS 1397 help 1398 SLUB has extensive debug support features. Disabling these can 1399 result in significant savings in code size. This also disables 1400 SLUB sysfs support. /sys/slab will not exist and there will be 1401 no support for cache validation etc. 1402 1403config COMPAT_BRK 1404 bool "Disable heap randomization" 1405 default y 1406 help 1407 Randomizing heap placement makes heap exploits harder, but it 1408 also breaks ancient binaries (including anything libc5 based). 1409 This option changes the bootup default to heap randomization 1410 disabled, and can be overridden at runtime by setting 1411 /proc/sys/kernel/randomize_va_space to 2. 1412 1413 On non-ancient distros (post-2000 ones) N is usually a safe choice. 1414 1415choice 1416 prompt "Choose SLAB allocator" 1417 default SLUB 1418 help 1419 This option allows to select a slab allocator. 1420 1421config SLAB 1422 bool "SLAB" 1423 help 1424 The regular slab allocator that is established and known to work 1425 well in all environments. It organizes cache hot objects in 1426 per cpu and per node queues. 1427 1428config SLUB 1429 bool "SLUB (Unqueued Allocator)" 1430 help 1431 SLUB is a slab allocator that minimizes cache line usage 1432 instead of managing queues of cached objects (SLAB approach). 1433 Per cpu caching is realized using slabs of objects instead 1434 of queues of objects. SLUB can use memory efficiently 1435 and has enhanced diagnostics. SLUB is the default choice for 1436 a slab allocator. 1437 1438config SLOB 1439 depends on EXPERT 1440 bool "SLOB (Simple Allocator)" 1441 help 1442 SLOB replaces the stock allocator with a drastically simpler 1443 allocator. SLOB is generally more space efficient but 1444 does not perform as well on large systems. 1445 1446endchoice 1447 1448config MMAP_ALLOW_UNINITIALIZED 1449 bool "Allow mmapped anonymous memory to be uninitialized" 1450 depends on EXPERT && !MMU 1451 default n 1452 help 1453 Normally, and according to the Linux spec, anonymous memory obtained 1454 from mmap() has it's contents cleared before it is passed to 1455 userspace. Enabling this config option allows you to request that 1456 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 1457 providing a huge performance boost. If this option is not enabled, 1458 then the flag will be ignored. 1459 1460 This is taken advantage of by uClibc's malloc(), and also by 1461 ELF-FDPIC binfmt's brk and stack allocator. 1462 1463 Because of the obvious security issues, this option should only be 1464 enabled on embedded devices where you control what is run in 1465 userspace. Since that isn't generally a problem on no-MMU systems, 1466 it is normally safe to say Y here. 1467 1468 See Documentation/nommu-mmap.txt for more information. 1469 1470config PROFILING 1471 bool "Profiling support" 1472 help 1473 Say Y here to enable the extended profiling support mechanisms used 1474 by profilers such as OProfile. 1475 1476# 1477# Place an empty function call at each tracepoint site. Can be 1478# dynamically changed for a probe function. 1479# 1480config TRACEPOINTS 1481 bool 1482 1483source "arch/Kconfig" 1484 1485endmenu # General setup 1486 1487config HAVE_GENERIC_DMA_COHERENT 1488 bool 1489 default n 1490 1491config SLABINFO 1492 bool 1493 depends on PROC_FS 1494 depends on SLAB || SLUB_DEBUG 1495 default y 1496 1497config RT_MUTEXES 1498 boolean 1499 1500config BASE_SMALL 1501 int 1502 default 0 if BASE_FULL 1503 default 1 if !BASE_FULL 1504 1505menuconfig MODULES 1506 bool "Enable loadable module support" 1507 help 1508 Kernel modules are small pieces of compiled code which can 1509 be inserted in the running kernel, rather than being 1510 permanently built into the kernel. You use the "modprobe" 1511 tool to add (and sometimes remove) them. If you say Y here, 1512 many parts of the kernel can be built as modules (by 1513 answering M instead of Y where indicated): this is most 1514 useful for infrequently used options which are not required 1515 for booting. For more information, see the man pages for 1516 modprobe, lsmod, modinfo, insmod and rmmod. 1517 1518 If you say Y here, you will need to run "make 1519 modules_install" to put the modules under /lib/modules/ 1520 where modprobe can find them (you may need to be root to do 1521 this). 1522 1523 If unsure, say Y. 1524 1525if MODULES 1526 1527config MODULE_FORCE_LOAD 1528 bool "Forced module loading" 1529 default n 1530 help 1531 Allow loading of modules without version information (ie. modprobe 1532 --force). Forced module loading sets the 'F' (forced) taint flag and 1533 is usually a really bad idea. 1534 1535config MODULE_UNLOAD 1536 bool "Module unloading" 1537 help 1538 Without this option you will not be able to unload any 1539 modules (note that some modules may not be unloadable 1540 anyway), which makes your kernel smaller, faster 1541 and simpler. If unsure, say Y. 1542 1543config MODULE_FORCE_UNLOAD 1544 bool "Forced module unloading" 1545 depends on MODULE_UNLOAD && EXPERIMENTAL 1546 help 1547 This option allows you to force a module to unload, even if the 1548 kernel believes it is unsafe: the kernel will remove the module 1549 without waiting for anyone to stop using it (using the -f option to 1550 rmmod). This is mainly for kernel developers and desperate users. 1551 If unsure, say N. 1552 1553config MODVERSIONS 1554 bool "Module versioning support" 1555 help 1556 Usually, you have to use modules compiled with your kernel. 1557 Saying Y here makes it sometimes possible to use modules 1558 compiled for different kernels, by adding enough information 1559 to the modules to (hopefully) spot any changes which would 1560 make them incompatible with the kernel you are running. If 1561 unsure, say N. 1562 1563config MODULE_SRCVERSION_ALL 1564 bool "Source checksum for all modules" 1565 help 1566 Modules which contain a MODULE_VERSION get an extra "srcversion" 1567 field inserted into their modinfo section, which contains a 1568 sum of the source files which made it. This helps maintainers 1569 see exactly which source was used to build a module (since 1570 others sometimes change the module source without updating 1571 the version). With this option, such a "srcversion" field 1572 will be created for all modules. If unsure, say N. 1573 1574endif # MODULES 1575 1576config INIT_ALL_POSSIBLE 1577 bool 1578 help 1579 Back when each arch used to define their own cpu_online_mask and 1580 cpu_possible_mask, some of them chose to initialize cpu_possible_mask 1581 with all 1s, and others with all 0s. When they were centralised, 1582 it was better to provide this option than to break all the archs 1583 and have several arch maintainers pursuing me down dark alleys. 1584 1585config STOP_MACHINE 1586 bool 1587 default y 1588 depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU 1589 help 1590 Need stop_machine() primitive. 1591 1592source "block/Kconfig" 1593 1594config PREEMPT_NOTIFIERS 1595 bool 1596 1597config PADATA 1598 depends on SMP 1599 bool 1600 1601source "kernel/Kconfig.locks" 1602