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"
16 The Itanium Processor Family is Intel's 64-bit successor to
17 the 32-bit X86 line. The IA-64 Linux project has a home
18 page at <http://www.linuxia64.org/> and a mailing list at
19 <linux-ia64@vger.kernel.org>.
33 config RWSEM_XCHGADD_ALGORITHM
37 config GENERIC_FIND_NEXT_BIT
41 config GENERIC_CALIBRATE_DELAY
45 config TIME_INTERPOLATION
61 config SCHED_NO_NO_OMIT_FRAME_POINTER
65 config IA64_UNCACHED_ALLOCATOR
67 select GENERIC_ALLOCATOR
83 This selects the system type of your hardware. A "generic" kernel
84 will run on any supported IA-64 system. However, if you configure
85 a kernel for your specific system, it will be faster and smaller.
87 generic For any supported IA-64 system
88 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
89 HP-zx1/sx1000 For HP systems
90 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
91 SGI-SN2 For SGI Altix systems
92 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
94 If you don't know what to do, choose "generic".
102 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
103 support for the HP I/O MMU.
105 config IA64_HP_ZX1_SWIOTLB
106 bool "HP-zx1/sx1000 with software I/O TLB"
108 Build a kernel that runs on HP zx1 and sx1000 systems even when they
109 have broken PCI devices which cannot DMA to full 32 bits. Apart
110 from support for the HP I/O MMU, this includes support for the software
111 I/O TLB, which allows supporting the broken devices at the expense of
112 wasting some kernel memory (about 2MB by default).
117 Selecting this option will optimize the kernel for use on sn2 based
118 systems, but the resulting kernel binary will not run on other
119 types of ia64 systems. If you have an SGI Altix system, it's safe
120 to select this option. If in doubt, select ia64 generic support
129 prompt "Processor type"
135 Select your IA-64 processor type. The default is Itanium.
136 This choice is safe for all IA-64 systems, but may not perform
137 optimally on systems with, say, Itanium 2 or newer processors.
142 Select this to configure for an Itanium 2 (McKinley) processor.
147 prompt "Kernel page size"
148 default IA64_PAGE_SIZE_16KB
150 config IA64_PAGE_SIZE_4KB
153 This lets you select the page size of the kernel. For best IA-64
154 performance, a page size of 8KB or 16KB is recommended. For best
155 IA-32 compatibility, a page size of 4KB should be selected (the vast
156 majority of IA-32 binaries work perfectly fine with a larger page
157 size). For Itanium 2 or newer systems, a page size of 64KB can also
160 4KB For best IA-32 compatibility
161 8KB For best IA-64 performance
162 16KB For best IA-64 performance
163 64KB Requires Itanium 2 or newer processor.
165 If you don't know what to do, choose 16KB.
167 config IA64_PAGE_SIZE_8KB
170 config IA64_PAGE_SIZE_16KB
173 config IA64_PAGE_SIZE_64KB
180 prompt "Page Table Levels"
187 depends on !IA64_PAGE_SIZE_64KB
192 source kernel/Kconfig.hz
199 # align cache-sensitive data to 128 bytes
200 config IA64_L1_CACHE_SHIFT
202 default "7" if MCKINLEY
203 default "6" if ITANIUM
206 bool "Cyclone (EXA) Time Source support"
208 Say Y here to enable support for IBM EXA Cyclone time source.
209 If you're unsure, answer N.
213 depends on !IA64_HP_SIM
216 config IA64_SGI_SN_XP
217 tristate "Support communication between SGI SSIs"
218 depends on IA64_GENERIC || IA64_SGI_SN2
219 select IA64_UNCACHED_ALLOCATOR
221 An SGI machine can be divided into multiple Single System
222 Images which act independently of each other and have
223 hardware based memory protection from the others. Enabling
224 this feature will allow for direct communication between SSIs
225 based on a network adapter and DMA messaging.
227 config FORCE_MAX_ZONEORDER
228 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
229 range 11 17 if !HUGETLB_PAGE
230 default "17" if HUGETLB_PAGE
234 bool "Symmetric multi-processing support"
236 This enables support for systems with more than one CPU. If you have
237 a system with only one CPU, say N. If you have a system with more
240 If you say N here, the kernel will run on single and multiprocessor
241 systems, but will use only one CPU of a multiprocessor system. If
242 you say Y here, the kernel will run on many, but not all,
243 single processor systems. On a single processor system, the kernel
244 will run faster if you say N here.
246 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
247 available at <http://www.tldp.org/docs.html#howto>.
249 If you don't know what to do here, say N.
252 int "Maximum number of CPUs (2-1024)"
257 You should set this to the number of CPUs in your system, but
258 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
259 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
260 than 64 will cause the use of a CPU mask array, causing a small
264 int "Maximum number of NODEs (256-1024)" if (IA64_SGI_SN2 || IA64_GENERIC)
266 depends on IA64_SGI_SN2 || IA64_GENERIC
269 This option specifies the maximum number of nodes in your SSI system.
270 If in doubt, use the default.
273 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
274 depends on SMP && EXPERIMENTAL
278 Say Y here to experiment with turning CPUs off and on. CPUs
279 can be controlled through /sys/devices/system/cpu/cpu#.
280 Say N if you want to disable CPU hotplug.
283 bool "SMT scheduler support"
287 Improves the CPU scheduler's decision making when dealing with
288 Intel IA64 chips with MultiThreading at a cost of slightly increased
289 overhead in some places. If unsure say N here.
291 config PERMIT_BSP_REMOVE
292 bool "Support removal of Bootstrap Processor"
293 depends on HOTPLUG_CPU
296 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
299 config FORCE_CPEI_RETARGET
300 bool "Force assumption that CPEI can be re-targetted"
301 depends on PERMIT_BSP_REMOVE
304 Say Y if you need to force the assumption that CPEI can be re-targetted to
305 any cpu in the system. This hint is available via ACPI 3.0 specifications.
306 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
307 This option it useful to enable this feature on older BIOS's as well.
308 You can also enable this by using boot command line option force_cpei=1.
311 bool "Preemptible Kernel"
313 This option reduces the latency of the kernel when reacting to
314 real-time or interactive events by allowing a low priority process to
315 be preempted even if it is in kernel mode executing a system call.
316 This allows applications to run more reliably even when the system is
319 Say Y here if you are building a kernel for a desktop, embedded
320 or real-time system. Say N if you are unsure.
324 config ARCH_SELECT_MEMORY_MODEL
327 config ARCH_DISCONTIGMEM_ENABLE
330 Say Y to support efficient handling of discontiguous physical memory,
331 for architectures which are either NUMA (Non-Uniform Memory Access)
332 or have huge holes in the physical address space for other reasons.
333 See <file:Documentation/vm/numa> for more.
335 config ARCH_FLATMEM_ENABLE
338 config ARCH_SPARSEMEM_ENABLE
340 depends on ARCH_DISCONTIGMEM_ENABLE
342 config ARCH_DISCONTIGMEM_DEFAULT
343 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
344 depends on ARCH_DISCONTIGMEM_ENABLE
348 depends on !IA64_HP_SIM && !FLATMEM
349 default y if IA64_SGI_SN2
351 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
352 Access). This option is for configuring high-end multiprocessor
353 server systems. If in doubt, say N.
355 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
356 # VIRTUAL_MEM_MAP has been retained for historical reasons.
357 config VIRTUAL_MEM_MAP
358 bool "Virtual mem map"
359 depends on !SPARSEMEM
360 default y if !IA64_HP_SIM
362 Say Y to compile the kernel with support for a virtual mem map.
363 This code also only takes effect if a memory hole of greater than
364 1 Gb is found during boot. You must turn this option on if you
365 require the DISCONTIGMEM option for your machine. If you are
370 default y if VIRTUAL_MEM_MAP
372 config HAVE_ARCH_EARLY_PFN_TO_NID
374 depends on NEED_MULTIPLE_NODES
377 bool "Support for Linux/x86 binaries"
379 IA-64 processors can execute IA-32 (X86) instructions. By
380 saying Y here, the kernel will include IA-32 system call
381 emulation support which makes it possible to transparently
382 run IA-32 Linux binaries on an IA-64 Linux system.
387 depends on IA32_SUPPORT
390 config IA64_MCA_RECOVERY
391 tristate "MCA recovery from errors other than TLB."
394 bool "Performance monitor support"
396 Selects whether support for the IA-64 performance monitor hardware
397 is included in the kernel. This makes some kernel data-structures a
398 little bigger and slows down execution a bit, but it is generally
399 a good idea to turn this on. If you're unsure, say Y.
402 tristate "/proc/pal support"
404 If you say Y here, you are able to get PAL (Processor Abstraction
405 Layer) information in /proc/pal. This contains useful information
406 about the processors in your systems, such as cache and TLB sizes
407 and the PAL firmware version in use.
409 To use this option, you have to ensure that the "/proc file system
410 support" (CONFIG_PROC_FS) is enabled, too.
413 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
415 source "drivers/firmware/Kconfig"
417 source "fs/Kconfig.binfmt"
421 menu "Power management and ACPI"
423 source "kernel/power/Kconfig"
425 source "drivers/acpi/Kconfig"
429 source "arch/ia64/kernel/cpufreq/Kconfig"
437 menu "Bus options (PCI, PCMCIA)"
442 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
443 here unless you are using a simulator without PCI support.
449 source "drivers/pci/Kconfig"
451 source "drivers/pci/hotplug/Kconfig"
453 source "drivers/pcmcia/Kconfig"
461 source "drivers/Kconfig"
468 # Use the generic interrupt handling code in kernel/irq/:
470 config GENERIC_HARDIRQS
474 config GENERIC_IRQ_PROBE
478 config GENERIC_PENDING_IRQ
480 depends on GENERIC_HARDIRQS && SMP
483 source "arch/ia64/hp/sim/Kconfig"
485 menu "Instrumentation Support"
486 depends on EXPERIMENTAL
488 source "arch/ia64/oprofile/Kconfig"
491 bool "Kprobes (EXPERIMENTAL)"
492 depends on EXPERIMENTAL && MODULES
494 Kprobes allows you to trap at almost any kernel address and
495 execute a callback function. register_kprobe() establishes
496 a probepoint and specifies the callback. Kprobes is useful
497 for kernel debugging, non-intrusive instrumentation and testing.
498 If in doubt, say "N".
501 source "arch/ia64/Kconfig.debug"
503 source "security/Kconfig"
505 source "crypto/Kconfig"