2 # For a description of the syntax of this configuration file,
3 # see Documentation/kbuild/kconfig-language.txt.
6 mainmenu "IA-64 Linux Kernel Configuration"
10 menu "Processor type and features"
14 select PCI if (!IA64_HP_SIM)
15 select ACPI if (!IA64_HP_SIM)
18 The Itanium Processor Family is Intel's 64-bit successor to
19 the 32-bit X86 line. The IA-64 Linux project has a home
20 page at <http://www.linuxia64.org/> and a mailing list at
21 <linux-ia64@vger.kernel.org>.
34 config RWSEM_XCHGADD_ALGORITHM
38 config ARCH_HAS_ILOG2_U32
42 config ARCH_HAS_ILOG2_U64
46 config GENERIC_FIND_NEXT_BIT
50 config GENERIC_CALIBRATE_DELAY
54 config TIME_INTERPOLATION
70 config SCHED_NO_NO_OMIT_FRAME_POINTER
74 config IA64_UNCACHED_ALLOCATOR
76 select GENERIC_ALLOCATOR
92 This selects the system type of your hardware. A "generic" kernel
93 will run on any supported IA-64 system. However, if you configure
94 a kernel for your specific system, it will be faster and smaller.
96 generic For any supported IA-64 system
97 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
98 HP-zx1/sx1000 For HP systems
99 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
100 SGI-SN2 For SGI Altix systems
101 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
103 If you don't know what to do, choose "generic".
112 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
113 support for the HP I/O MMU.
115 config IA64_HP_ZX1_SWIOTLB
116 bool "HP-zx1/sx1000 with software I/O TLB"
119 Build a kernel that runs on HP zx1 and sx1000 systems even when they
120 have broken PCI devices which cannot DMA to full 32 bits. Apart
121 from support for the HP I/O MMU, this includes support for the software
122 I/O TLB, which allows supporting the broken devices at the expense of
123 wasting some kernel memory (about 2MB by default).
128 Selecting this option will optimize the kernel for use on sn2 based
129 systems, but the resulting kernel binary will not run on other
130 types of ia64 systems. If you have an SGI Altix system, it's safe
131 to select this option. If in doubt, select ia64 generic support
141 prompt "Processor type"
147 Select your IA-64 processor type. The default is Itanium.
148 This choice is safe for all IA-64 systems, but may not perform
149 optimally on systems with, say, Itanium 2 or newer processors.
154 Select this to configure for an Itanium 2 (McKinley) processor.
159 prompt "Kernel page size"
160 default IA64_PAGE_SIZE_16KB
162 config IA64_PAGE_SIZE_4KB
165 This lets you select the page size of the kernel. For best IA-64
166 performance, a page size of 8KB or 16KB is recommended. For best
167 IA-32 compatibility, a page size of 4KB should be selected (the vast
168 majority of IA-32 binaries work perfectly fine with a larger page
169 size). For Itanium 2 or newer systems, a page size of 64KB can also
172 4KB For best IA-32 compatibility
173 8KB For best IA-64 performance
174 16KB For best IA-64 performance
175 64KB Requires Itanium 2 or newer processor.
177 If you don't know what to do, choose 16KB.
179 config IA64_PAGE_SIZE_8KB
182 config IA64_PAGE_SIZE_16KB
185 config IA64_PAGE_SIZE_64KB
192 prompt "Page Table Levels"
199 depends on !IA64_PAGE_SIZE_64KB
204 source kernel/Kconfig.hz
211 # align cache-sensitive data to 128 bytes
212 config IA64_L1_CACHE_SHIFT
214 default "7" if MCKINLEY
215 default "6" if ITANIUM
218 bool "Cyclone (EXA) Time Source support"
220 Say Y here to enable support for IBM EXA Cyclone time source.
221 If you're unsure, answer N.
225 depends on !IA64_HP_SIM
228 config IA64_SGI_SN_XP
229 tristate "Support communication between SGI SSIs"
230 depends on IA64_GENERIC || IA64_SGI_SN2
231 select IA64_UNCACHED_ALLOCATOR
233 An SGI machine can be divided into multiple Single System
234 Images which act independently of each other and have
235 hardware based memory protection from the others. Enabling
236 this feature will allow for direct communication between SSIs
237 based on a network adapter and DMA messaging.
239 config FORCE_MAX_ZONEORDER
240 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
241 range 11 17 if !HUGETLB_PAGE
242 default "17" if HUGETLB_PAGE
246 bool "Symmetric multi-processing support"
248 This enables support for systems with more than one CPU. If you have
249 a system with only one CPU, say N. If you have a system with more
252 If you say N here, the kernel will run on single and multiprocessor
253 systems, but will use only one CPU of a multiprocessor system. If
254 you say Y here, the kernel will run on many, but not all,
255 single processor systems. On a single processor system, the kernel
256 will run faster if you say N here.
258 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
259 available at <http://www.tldp.org/docs.html#howto>.
261 If you don't know what to do here, say N.
264 int "Maximum number of CPUs (2-1024)"
269 You should set this to the number of CPUs in your system, but
270 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
271 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
272 than 64 will cause the use of a CPU mask array, causing a small
276 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
277 depends on SMP && EXPERIMENTAL
281 Say Y here to experiment with turning CPUs off and on. CPUs
282 can be controlled through /sys/devices/system/cpu/cpu#.
283 Say N if you want to disable CPU hotplug.
285 config ARCH_ENABLE_MEMORY_HOTPLUG
289 bool "SMT scheduler support"
292 Improves the CPU scheduler's decision making when dealing with
293 Intel IA64 chips with MultiThreading at a cost of slightly increased
294 overhead in some places. If unsure say N here.
296 config PERMIT_BSP_REMOVE
297 bool "Support removal of Bootstrap Processor"
298 depends on HOTPLUG_CPU
301 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
304 config FORCE_CPEI_RETARGET
305 bool "Force assumption that CPEI can be re-targetted"
306 depends on PERMIT_BSP_REMOVE
309 Say Y if you need to force the assumption that CPEI can be re-targetted to
310 any cpu in the system. This hint is available via ACPI 3.0 specifications.
311 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
312 This option it useful to enable this feature on older BIOS's as well.
313 You can also enable this by using boot command line option force_cpei=1.
316 bool "Preemptible Kernel"
318 This option reduces the latency of the kernel when reacting to
319 real-time or interactive events by allowing a low priority process to
320 be preempted even if it is in kernel mode executing a system call.
321 This allows applications to run more reliably even when the system is
324 Say Y here if you are building a kernel for a desktop, embedded
325 or real-time system. Say N if you are unsure.
329 config ARCH_SELECT_MEMORY_MODEL
332 config ARCH_DISCONTIGMEM_ENABLE
335 Say Y to support efficient handling of discontiguous physical memory,
336 for architectures which are either NUMA (Non-Uniform Memory Access)
337 or have huge holes in the physical address space for other reasons.
338 See <file:Documentation/vm/numa> for more.
340 config ARCH_FLATMEM_ENABLE
343 config ARCH_SPARSEMEM_ENABLE
345 depends on ARCH_DISCONTIGMEM_ENABLE
347 config ARCH_DISCONTIGMEM_DEFAULT
348 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
349 depends on ARCH_DISCONTIGMEM_ENABLE
353 depends on !IA64_HP_SIM && !FLATMEM
354 default y if IA64_SGI_SN2
355 select ACPI_NUMA if ACPI
357 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
358 Access). This option is for configuring high-end multiprocessor
359 server systems. If in doubt, say N.
362 int "Max num nodes shift(3-10)"
365 depends on NEED_MULTIPLE_NODES
367 This option specifies the maximum number of nodes in your SSI system.
368 MAX_NUMNODES will be 2^(This value).
369 If in doubt, use the default.
371 config ARCH_POPULATES_NODE_MAP
374 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
375 # VIRTUAL_MEM_MAP has been retained for historical reasons.
376 config VIRTUAL_MEM_MAP
377 bool "Virtual mem map"
378 depends on !SPARSEMEM
379 default y if !IA64_HP_SIM
381 Say Y to compile the kernel with support for a virtual mem map.
382 This code also only takes effect if a memory hole of greater than
383 1 Gb is found during boot. You must turn this option on if you
384 require the DISCONTIGMEM option for your machine. If you are
389 default y if VIRTUAL_MEM_MAP
391 config HAVE_ARCH_EARLY_PFN_TO_NID
393 depends on NEED_MULTIPLE_NODES
395 config HAVE_ARCH_NODEDATA_EXTENSION
400 bool "Support for Linux/x86 binaries"
402 IA-64 processors can execute IA-32 (X86) instructions. By
403 saying Y here, the kernel will include IA-32 system call
404 emulation support which makes it possible to transparently
405 run IA-32 Linux binaries on an IA-64 Linux system.
410 depends on IA32_SUPPORT
413 config IA64_MCA_RECOVERY
414 tristate "MCA recovery from errors other than TLB."
417 bool "Performance monitor support"
419 Selects whether support for the IA-64 performance monitor hardware
420 is included in the kernel. This makes some kernel data-structures a
421 little bigger and slows down execution a bit, but it is generally
422 a good idea to turn this on. If you're unsure, say Y.
425 tristate "/proc/pal support"
427 If you say Y here, you are able to get PAL (Processor Abstraction
428 Layer) information in /proc/pal. This contains useful information
429 about the processors in your systems, such as cache and TLB sizes
430 and the PAL firmware version in use.
432 To use this option, you have to ensure that the "/proc file system
433 support" (CONFIG_PROC_FS) is enabled, too.
436 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
439 bool "ESI (Extensible SAL Interface) support"
441 If you say Y here, support is built into the kernel to
442 make ESI calls. ESI calls are used to support vendor-specific
443 firmware extensions, such as the ability to inject memory-errors
444 for test-purposes. If you're unsure, say N.
446 source "drivers/sn/Kconfig"
449 bool "kexec system call (EXPERIMENTAL)"
450 depends on EXPERIMENTAL && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
452 kexec is a system call that implements the ability to shutdown your
453 current kernel, and to start another kernel. It is like a reboot
454 but it is indepedent of the system firmware. And like a reboot
455 you can start any kernel with it, not just Linux.
457 The name comes from the similiarity to the exec system call.
459 It is an ongoing process to be certain the hardware in a machine
460 is properly shutdown, so do not be surprised if this code does not
461 initially work for you. It may help to enable device hotplugging
462 support. As of this writing the exact hardware interface is
463 strongly in flux, so no good recommendation can be made.
466 bool "kernel crash dumps (EXPERIMENTAL)"
467 depends on EXPERIMENTAL && IA64_MCA_RECOVERY && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
469 Generate crash dump after being started by kexec.
471 source "drivers/firmware/Kconfig"
473 source "fs/Kconfig.binfmt"
477 menu "Power management and ACPI"
479 source "kernel/power/Kconfig"
481 source "drivers/acpi/Kconfig"
485 source "arch/ia64/kernel/cpufreq/Kconfig"
493 menu "Bus options (PCI, PCMCIA)"
498 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
499 here unless you are using a simulator without PCI support.
505 source "drivers/pci/pcie/Kconfig"
507 source "drivers/pci/Kconfig"
509 source "drivers/pci/hotplug/Kconfig"
511 source "drivers/pcmcia/Kconfig"
519 source "drivers/Kconfig"
522 tristate "Memory special operations driver"
524 select IA64_UNCACHED_ALLOCATOR
526 If you have an ia64 and you want to enable memory special
527 operations support (formerly known as fetchop), say Y here,
535 # Use the generic interrupt handling code in kernel/irq/:
537 config GENERIC_HARDIRQS
541 config GENERIC_IRQ_PROBE
545 config GENERIC_PENDING_IRQ
547 depends on GENERIC_HARDIRQS && SMP
554 source "arch/ia64/hp/sim/Kconfig"
556 menu "Instrumentation Support"
557 depends on EXPERIMENTAL
559 source "arch/ia64/oprofile/Kconfig"
562 bool "Kprobes (EXPERIMENTAL)"
563 depends on KALLSYMS && EXPERIMENTAL && MODULES
565 Kprobes allows you to trap at almost any kernel address and
566 execute a callback function. register_kprobe() establishes
567 a probepoint and specifies the callback. Kprobes is useful
568 for kernel debugging, non-intrusive instrumentation and testing.
569 If in doubt, say "N".
572 source "arch/ia64/Kconfig.debug"
574 source "security/Kconfig"
576 source "crypto/Kconfig"