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
53 config SCHED_NO_NO_OMIT_FRAME_POINTER
57 config IA64_UNCACHED_ALLOCATOR
59 select GENERIC_ALLOCATOR
75 This selects the system type of your hardware. A "generic" kernel
76 will run on any supported IA-64 system. However, if you configure
77 a kernel for your specific system, it will be faster and smaller.
79 generic For any supported IA-64 system
80 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
81 HP-zx1/sx1000 For HP systems
82 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
83 SGI-SN2 For SGI Altix systems
84 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
86 If you don't know what to do, choose "generic".
94 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
95 support for the HP I/O MMU.
97 config IA64_HP_ZX1_SWIOTLB
98 bool "HP-zx1/sx1000 with software I/O TLB"
100 Build a kernel that runs on HP zx1 and sx1000 systems even when they
101 have broken PCI devices which cannot DMA to full 32 bits. Apart
102 from support for the HP I/O MMU, this includes support for the software
103 I/O TLB, which allows supporting the broken devices at the expense of
104 wasting some kernel memory (about 2MB by default).
109 Selecting this option will optimize the kernel for use on sn2 based
110 systems, but the resulting kernel binary will not run on other
111 types of ia64 systems. If you have an SGI Altix system, it's safe
112 to select this option. If in doubt, select ia64 generic support
121 prompt "Processor type"
127 Select your IA-64 processor type. The default is Itanium.
128 This choice is safe for all IA-64 systems, but may not perform
129 optimally on systems with, say, Itanium 2 or newer processors.
134 Select this to configure for an Itanium 2 (McKinley) processor.
139 prompt "Kernel page size"
140 default IA64_PAGE_SIZE_16KB
142 config IA64_PAGE_SIZE_4KB
145 This lets you select the page size of the kernel. For best IA-64
146 performance, a page size of 8KB or 16KB is recommended. For best
147 IA-32 compatibility, a page size of 4KB should be selected (the vast
148 majority of IA-32 binaries work perfectly fine with a larger page
149 size). For Itanium 2 or newer systems, a page size of 64KB can also
152 4KB For best IA-32 compatibility
153 8KB For best IA-64 performance
154 16KB For best IA-64 performance
155 64KB Requires Itanium 2 or newer processor.
157 If you don't know what to do, choose 16KB.
159 config IA64_PAGE_SIZE_8KB
162 config IA64_PAGE_SIZE_16KB
165 config IA64_PAGE_SIZE_64KB
172 prompt "Page Table Levels"
179 depends on !IA64_PAGE_SIZE_64KB
184 source kernel/Kconfig.hz
191 # align cache-sensitive data to 128 bytes
192 config IA64_L1_CACHE_SHIFT
194 default "7" if MCKINLEY
195 default "6" if ITANIUM
198 bool "Cyclone (EXA) Time Source support"
200 Say Y here to enable support for IBM EXA Cyclone time source.
201 If you're unsure, answer N.
205 depends on !IA64_HP_SIM
208 config IA64_SGI_SN_XP
209 tristate "Support communication between SGI SSIs"
210 depends on IA64_GENERIC || IA64_SGI_SN2
211 select IA64_UNCACHED_ALLOCATOR
213 An SGI machine can be divided into multiple Single System
214 Images which act independently of each other and have
215 hardware based memory protection from the others. Enabling
216 this feature will allow for direct communication between SSIs
217 based on a network adapter and DMA messaging.
219 config FORCE_MAX_ZONEORDER
220 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
221 range 11 17 if !HUGETLB_PAGE
222 default "17" if HUGETLB_PAGE
226 bool "Symmetric multi-processing support"
228 This enables support for systems with more than one CPU. If you have
229 a system with only one CPU, say N. If you have a system with more
232 If you say N here, the kernel will run on single and multiprocessor
233 systems, but will use only one CPU of a multiprocessor system. If
234 you say Y here, the kernel will run on many, but not all,
235 single processor systems. On a single processor system, the kernel
236 will run faster if you say N here.
238 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
239 available at <http://www.tldp.org/docs.html#howto>.
241 If you don't know what to do here, say N.
244 int "Maximum number of CPUs (2-1024)"
249 You should set this to the number of CPUs in your system, but
250 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
251 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
252 than 64 will cause the use of a CPU mask array, causing a small
256 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
257 depends on SMP && EXPERIMENTAL
261 Say Y here to experiment with turning CPUs off and on. CPUs
262 can be controlled through /sys/devices/system/cpu/cpu#.
263 Say N if you want to disable CPU hotplug.
266 bool "SMT scheduler support"
270 Improves the CPU scheduler's decision making when dealing with
271 Intel IA64 chips with MultiThreading at a cost of slightly increased
272 overhead in some places. If unsure say N here.
274 config PERMIT_BSP_REMOVE
275 bool "Support removal of Bootstrap Processor"
276 depends on HOTPLUG_CPU
279 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
282 config FORCE_CPEI_RETARGET
283 bool "Force assumption that CPEI can be re-targetted"
284 depends on PERMIT_BSP_REMOVE
287 Say Y if you need to force the assumption that CPEI can be re-targetted to
288 any cpu in the system. This hint is available via ACPI 3.0 specifications.
289 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
290 This option it useful to enable this feature on older BIOS's as well.
291 You can also enable this by using boot command line option force_cpei=1.
294 bool "Preemptible Kernel"
296 This option reduces the latency of the kernel when reacting to
297 real-time or interactive events by allowing a low priority process to
298 be preempted even if it is in kernel mode executing a system call.
299 This allows applications to run more reliably even when the system is
302 Say Y here if you are building a kernel for a desktop, embedded
303 or real-time system. Say N if you are unsure.
307 config ARCH_SELECT_MEMORY_MODEL
310 config ARCH_DISCONTIGMEM_ENABLE
313 Say Y to support efficient handling of discontiguous physical memory,
314 for architectures which are either NUMA (Non-Uniform Memory Access)
315 or have huge holes in the physical address space for other reasons.
316 See <file:Documentation/vm/numa> for more.
318 config ARCH_FLATMEM_ENABLE
321 config ARCH_SPARSEMEM_ENABLE
323 depends on ARCH_DISCONTIGMEM_ENABLE
325 config ARCH_DISCONTIGMEM_DEFAULT
326 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
327 depends on ARCH_DISCONTIGMEM_ENABLE
331 depends on !IA64_HP_SIM && !FLATMEM
332 default y if IA64_SGI_SN2
334 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
335 Access). This option is for configuring high-end multiprocessor
336 server systems. If in doubt, say N.
338 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
339 # VIRTUAL_MEM_MAP has been retained for historical reasons.
340 config VIRTUAL_MEM_MAP
341 bool "Virtual mem map"
342 depends on !SPARSEMEM
343 default y if !IA64_HP_SIM
345 Say Y to compile the kernel with support for a virtual mem map.
346 This code also only takes effect if a memory hole of greater than
347 1 Gb is found during boot. You must turn this option on if you
348 require the DISCONTIGMEM option for your machine. If you are
353 default y if VIRTUAL_MEM_MAP
355 config HAVE_ARCH_EARLY_PFN_TO_NID
357 depends on NEED_MULTIPLE_NODES
360 bool "Support for Linux/x86 binaries"
362 IA-64 processors can execute IA-32 (X86) instructions. By
363 saying Y here, the kernel will include IA-32 system call
364 emulation support which makes it possible to transparently
365 run IA-32 Linux binaries on an IA-64 Linux system.
370 depends on IA32_SUPPORT
373 config IA64_MCA_RECOVERY
374 tristate "MCA recovery from errors other than TLB."
377 bool "Performance monitor support"
379 Selects whether support for the IA-64 performance monitor hardware
380 is included in the kernel. This makes some kernel data-structures a
381 little bigger and slows down execution a bit, but it is generally
382 a good idea to turn this on. If you're unsure, say Y.
385 tristate "/proc/pal support"
387 If you say Y here, you are able to get PAL (Processor Abstraction
388 Layer) information in /proc/pal. This contains useful information
389 about the processors in your systems, such as cache and TLB sizes
390 and the PAL firmware version in use.
392 To use this option, you have to ensure that the "/proc file system
393 support" (CONFIG_PROC_FS) is enabled, too.
396 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
398 source "drivers/firmware/Kconfig"
400 source "fs/Kconfig.binfmt"
404 menu "Power management and ACPI"
406 source "kernel/power/Kconfig"
408 source "drivers/acpi/Kconfig"
412 source "arch/ia64/kernel/cpufreq/Kconfig"
420 menu "Bus options (PCI, PCMCIA)"
425 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
426 here unless you are using a simulator without PCI support.
432 source "drivers/pci/Kconfig"
434 source "drivers/pci/hotplug/Kconfig"
436 source "drivers/pcmcia/Kconfig"
444 source "drivers/Kconfig"
451 # Use the generic interrupt handling code in kernel/irq/:
453 config GENERIC_HARDIRQS
457 config GENERIC_IRQ_PROBE
461 config GENERIC_PENDING_IRQ
463 depends on GENERIC_HARDIRQS && SMP
466 source "arch/ia64/hp/sim/Kconfig"
468 menu "Instrumentation Support"
469 depends on EXPERIMENTAL
471 source "arch/ia64/oprofile/Kconfig"
474 bool "Kprobes (EXPERIMENTAL)"
475 depends on EXPERIMENTAL && MODULES
477 Kprobes allows you to trap at almost any kernel address and
478 execute a callback function. register_kprobe() establishes
479 a probepoint and specifies the callback. Kprobes is useful
480 for kernel debugging, non-intrusive instrumentation and testing.
481 If in doubt, say "N".
484 source "arch/ia64/Kconfig.debug"
486 source "security/Kconfig"
488 source "crypto/Kconfig"