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_CALIBRATE_DELAY
41 config TIME_INTERPOLATION
57 config SCHED_NO_NO_OMIT_FRAME_POINTER
61 config IA64_UNCACHED_ALLOCATOR
63 select GENERIC_ALLOCATOR
79 This selects the system type of your hardware. A "generic" kernel
80 will run on any supported IA-64 system. However, if you configure
81 a kernel for your specific system, it will be faster and smaller.
83 generic For any supported IA-64 system
84 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
85 HP-zx1/sx1000 For HP systems
86 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
87 SGI-SN2 For SGI Altix systems
88 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
90 If you don't know what to do, choose "generic".
98 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
99 support for the HP I/O MMU.
101 config IA64_HP_ZX1_SWIOTLB
102 bool "HP-zx1/sx1000 with software I/O TLB"
104 Build a kernel that runs on HP zx1 and sx1000 systems even when they
105 have broken PCI devices which cannot DMA to full 32 bits. Apart
106 from support for the HP I/O MMU, this includes support for the software
107 I/O TLB, which allows supporting the broken devices at the expense of
108 wasting some kernel memory (about 2MB by default).
113 Selecting this option will optimize the kernel for use on sn2 based
114 systems, but the resulting kernel binary will not run on other
115 types of ia64 systems. If you have an SGI Altix system, it's safe
116 to select this option. If in doubt, select ia64 generic support
125 prompt "Processor type"
131 Select your IA-64 processor type. The default is Itanium.
132 This choice is safe for all IA-64 systems, but may not perform
133 optimally on systems with, say, Itanium 2 or newer processors.
138 Select this to configure for an Itanium 2 (McKinley) processor.
143 prompt "Kernel page size"
144 default IA64_PAGE_SIZE_16KB
146 config IA64_PAGE_SIZE_4KB
149 This lets you select the page size of the kernel. For best IA-64
150 performance, a page size of 8KB or 16KB is recommended. For best
151 IA-32 compatibility, a page size of 4KB should be selected (the vast
152 majority of IA-32 binaries work perfectly fine with a larger page
153 size). For Itanium 2 or newer systems, a page size of 64KB can also
156 4KB For best IA-32 compatibility
157 8KB For best IA-64 performance
158 16KB For best IA-64 performance
159 64KB Requires Itanium 2 or newer processor.
161 If you don't know what to do, choose 16KB.
163 config IA64_PAGE_SIZE_8KB
166 config IA64_PAGE_SIZE_16KB
169 config IA64_PAGE_SIZE_64KB
176 prompt "Page Table Levels"
183 depends on !IA64_PAGE_SIZE_64KB
188 source kernel/Kconfig.hz
195 # align cache-sensitive data to 128 bytes
196 config IA64_L1_CACHE_SHIFT
198 default "7" if MCKINLEY
199 default "6" if ITANIUM
202 bool "Cyclone (EXA) Time Source support"
204 Say Y here to enable support for IBM EXA Cyclone time source.
205 If you're unsure, answer N.
209 depends on !IA64_HP_SIM
212 config IA64_SGI_SN_XP
213 tristate "Support communication between SGI SSIs"
214 depends on IA64_GENERIC || IA64_SGI_SN2
215 select IA64_UNCACHED_ALLOCATOR
217 An SGI machine can be divided into multiple Single System
218 Images which act independently of each other and have
219 hardware based memory protection from the others. Enabling
220 this feature will allow for direct communication between SSIs
221 based on a network adapter and DMA messaging.
223 config FORCE_MAX_ZONEORDER
224 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
225 range 11 17 if !HUGETLB_PAGE
226 default "17" if HUGETLB_PAGE
230 bool "Symmetric multi-processing support"
232 This enables support for systems with more than one CPU. If you have
233 a system with only one CPU, say N. If you have a system with more
236 If you say N here, the kernel will run on single and multiprocessor
237 systems, but will use only one CPU of a multiprocessor system. If
238 you say Y here, the kernel will run on many, but not all,
239 single processor systems. On a single processor system, the kernel
240 will run faster if you say N here.
242 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
243 available at <http://www.tldp.org/docs.html#howto>.
245 If you don't know what to do here, say N.
248 int "Maximum number of CPUs (2-1024)"
253 You should set this to the number of CPUs in your system, but
254 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
255 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
256 than 64 will cause the use of a CPU mask array, causing a small
260 int "Maximum number of NODEs (256-1024)" if (IA64_SGI_SN2 || IA64_GENERIC)
262 depends on IA64_SGI_SN2 || IA64_GENERIC
265 This option specifies the maximum number of nodes in your SSI system.
266 If in doubt, use the default.
269 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
270 depends on SMP && EXPERIMENTAL
274 Say Y here to experiment with turning CPUs off and on. CPUs
275 can be controlled through /sys/devices/system/cpu/cpu#.
276 Say N if you want to disable CPU hotplug.
279 bool "SMT scheduler support"
283 Improves the CPU scheduler's decision making when dealing with
284 Intel IA64 chips with MultiThreading at a cost of slightly increased
285 overhead in some places. If unsure say N here.
287 config PERMIT_BSP_REMOVE
288 bool "Support removal of Bootstrap Processor"
289 depends on HOTPLUG_CPU
292 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
295 config FORCE_CPEI_RETARGET
296 bool "Force assumption that CPEI can be re-targetted"
297 depends on PERMIT_BSP_REMOVE
300 Say Y if you need to force the assumption that CPEI can be re-targetted to
301 any cpu in the system. This hint is available via ACPI 3.0 specifications.
302 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
303 This option it useful to enable this feature on older BIOS's as well.
304 You can also enable this by using boot command line option force_cpei=1.
307 bool "Preemptible Kernel"
309 This option reduces the latency of the kernel when reacting to
310 real-time or interactive events by allowing a low priority process to
311 be preempted even if it is in kernel mode executing a system call.
312 This allows applications to run more reliably even when the system is
315 Say Y here if you are building a kernel for a desktop, embedded
316 or real-time system. Say N if you are unsure.
320 config ARCH_SELECT_MEMORY_MODEL
323 config ARCH_DISCONTIGMEM_ENABLE
326 Say Y to support efficient handling of discontiguous physical memory,
327 for architectures which are either NUMA (Non-Uniform Memory Access)
328 or have huge holes in the physical address space for other reasons.
329 See <file:Documentation/vm/numa> for more.
331 config ARCH_FLATMEM_ENABLE
334 config ARCH_SPARSEMEM_ENABLE
336 depends on ARCH_DISCONTIGMEM_ENABLE
338 config ARCH_DISCONTIGMEM_DEFAULT
339 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
340 depends on ARCH_DISCONTIGMEM_ENABLE
344 depends on !IA64_HP_SIM && !FLATMEM
345 default y if IA64_SGI_SN2
347 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
348 Access). This option is for configuring high-end multiprocessor
349 server systems. If in doubt, say N.
351 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
352 # VIRTUAL_MEM_MAP has been retained for historical reasons.
353 config VIRTUAL_MEM_MAP
354 bool "Virtual mem map"
355 depends on !SPARSEMEM
356 default y if !IA64_HP_SIM
358 Say Y to compile the kernel with support for a virtual mem map.
359 This code also only takes effect if a memory hole of greater than
360 1 Gb is found during boot. You must turn this option on if you
361 require the DISCONTIGMEM option for your machine. If you are
366 default y if VIRTUAL_MEM_MAP
368 config HAVE_ARCH_EARLY_PFN_TO_NID
370 depends on NEED_MULTIPLE_NODES
373 bool "Support for Linux/x86 binaries"
375 IA-64 processors can execute IA-32 (X86) instructions. By
376 saying Y here, the kernel will include IA-32 system call
377 emulation support which makes it possible to transparently
378 run IA-32 Linux binaries on an IA-64 Linux system.
383 depends on IA32_SUPPORT
386 config IA64_MCA_RECOVERY
387 tristate "MCA recovery from errors other than TLB."
390 bool "Performance monitor support"
392 Selects whether support for the IA-64 performance monitor hardware
393 is included in the kernel. This makes some kernel data-structures a
394 little bigger and slows down execution a bit, but it is generally
395 a good idea to turn this on. If you're unsure, say Y.
398 tristate "/proc/pal support"
400 If you say Y here, you are able to get PAL (Processor Abstraction
401 Layer) information in /proc/pal. This contains useful information
402 about the processors in your systems, such as cache and TLB sizes
403 and the PAL firmware version in use.
405 To use this option, you have to ensure that the "/proc file system
406 support" (CONFIG_PROC_FS) is enabled, too.
409 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
411 source "drivers/firmware/Kconfig"
413 source "fs/Kconfig.binfmt"
417 menu "Power management and ACPI"
419 source "kernel/power/Kconfig"
421 source "drivers/acpi/Kconfig"
425 source "arch/ia64/kernel/cpufreq/Kconfig"
433 menu "Bus options (PCI, PCMCIA)"
438 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
439 here unless you are using a simulator without PCI support.
445 source "drivers/pci/Kconfig"
447 source "drivers/pci/hotplug/Kconfig"
449 source "drivers/pcmcia/Kconfig"
457 source "drivers/Kconfig"
464 # Use the generic interrupt handling code in kernel/irq/:
466 config GENERIC_HARDIRQS
470 config GENERIC_IRQ_PROBE
474 config GENERIC_PENDING_IRQ
476 depends on GENERIC_HARDIRQS && SMP
479 source "arch/ia64/hp/sim/Kconfig"
481 menu "Instrumentation Support"
482 depends on EXPERIMENTAL
484 source "arch/ia64/oprofile/Kconfig"
487 bool "Kprobes (EXPERIMENTAL)"
488 depends on EXPERIMENTAL && MODULES
490 Kprobes allows you to trap at almost any kernel address and
491 execute a callback function. register_kprobe() establishes
492 a probepoint and specifies the callback. Kprobes is useful
493 for kernel debugging, non-intrusive instrumentation and testing.
494 If in doubt, say "N".
497 source "arch/ia64/Kconfig.debug"
499 source "security/Kconfig"
501 source "crypto/Kconfig"