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
75 depends on IA64_SGI_SN2
89 This selects the system type of your hardware. A "generic" kernel
90 will run on any supported IA-64 system. However, if you configure
91 a kernel for your specific system, it will be faster and smaller.
93 generic For any supported IA-64 system
94 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
95 HP-zx1/sx1000 For HP systems
96 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
97 SGI-SN2 For SGI Altix systems
98 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
100 If you don't know what to do, choose "generic".
108 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
109 support for the HP I/O MMU.
111 config IA64_HP_ZX1_SWIOTLB
112 bool "HP-zx1/sx1000 with software I/O TLB"
114 Build a kernel that runs on HP zx1 and sx1000 systems even when they
115 have broken PCI devices which cannot DMA to full 32 bits. Apart
116 from support for the HP I/O MMU, this includes support for the software
117 I/O TLB, which allows supporting the broken devices at the expense of
118 wasting some kernel memory (about 2MB by default).
123 Selecting this option will optimize the kernel for use on sn2 based
124 systems, but the resulting kernel binary will not run on other
125 types of ia64 systems. If you have an SGI Altix system, it's safe
126 to select this option. If in doubt, select ia64 generic support
135 prompt "Processor type"
141 Select your IA-64 processor type. The default is Itanium.
142 This choice is safe for all IA-64 systems, but may not perform
143 optimally on systems with, say, Itanium 2 or newer processors.
148 Select this to configure for an Itanium 2 (McKinley) processor.
153 prompt "Kernel page size"
154 default IA64_PAGE_SIZE_16KB
156 config IA64_PAGE_SIZE_4KB
159 This lets you select the page size of the kernel. For best IA-64
160 performance, a page size of 8KB or 16KB is recommended. For best
161 IA-32 compatibility, a page size of 4KB should be selected (the vast
162 majority of IA-32 binaries work perfectly fine with a larger page
163 size). For Itanium 2 or newer systems, a page size of 64KB can also
166 4KB For best IA-32 compatibility
167 8KB For best IA-64 performance
168 16KB For best IA-64 performance
169 64KB Requires Itanium 2 or newer processor.
171 If you don't know what to do, choose 16KB.
173 config IA64_PAGE_SIZE_8KB
176 config IA64_PAGE_SIZE_16KB
179 config IA64_PAGE_SIZE_64KB
186 prompt "Page Table Levels"
193 depends on !IA64_PAGE_SIZE_64KB
198 source kernel/Kconfig.hz
205 # align cache-sensitive data to 128 bytes
206 config IA64_L1_CACHE_SHIFT
208 default "7" if MCKINLEY
209 default "6" if ITANIUM
212 bool "Cyclone (EXA) Time Source support"
214 Say Y here to enable support for IBM EXA Cyclone time source.
215 If you're unsure, answer N.
219 depends on !IA64_HP_SIM
222 config IA64_SGI_SN_XP
223 tristate "Support communication between SGI SSIs"
224 depends on IA64_GENERIC || IA64_SGI_SN2
225 select IA64_UNCACHED_ALLOCATOR
227 An SGI machine can be divided into multiple Single System
228 Images which act independently of each other and have
229 hardware based memory protection from the others. Enabling
230 this feature will allow for direct communication between SSIs
231 based on a network adapter and DMA messaging.
233 config FORCE_MAX_ZONEORDER
234 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
235 range 11 17 if !HUGETLB_PAGE
236 default "17" if HUGETLB_PAGE
240 bool "Symmetric multi-processing support"
242 This enables support for systems with more than one CPU. If you have
243 a system with only one CPU, say N. If you have a system with more
246 If you say N here, the kernel will run on single and multiprocessor
247 systems, but will use only one CPU of a multiprocessor system. If
248 you say Y here, the kernel will run on many, but not all,
249 single processor systems. On a single processor system, the kernel
250 will run faster if you say N here.
252 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
253 available at <http://www.tldp.org/docs.html#howto>.
255 If you don't know what to do here, say N.
258 int "Maximum number of CPUs (2-1024)"
263 You should set this to the number of CPUs in your system, but
264 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
265 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
266 than 64 will cause the use of a CPU mask array, causing a small
270 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
271 depends on SMP && EXPERIMENTAL
275 Say Y here to experiment with turning CPUs off and on. CPUs
276 can be controlled through /sys/devices/system/cpu/cpu#.
277 Say N if you want to disable CPU hotplug.
279 config ARCH_ENABLE_MEMORY_HOTPLUG
283 bool "SMT scheduler support"
286 Improves the CPU scheduler's decision making when dealing with
287 Intel IA64 chips with MultiThreading at a cost of slightly increased
288 overhead in some places. If unsure say N here.
290 config PERMIT_BSP_REMOVE
291 bool "Support removal of Bootstrap Processor"
292 depends on HOTPLUG_CPU
295 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
298 config FORCE_CPEI_RETARGET
299 bool "Force assumption that CPEI can be re-targetted"
300 depends on PERMIT_BSP_REMOVE
303 Say Y if you need to force the assumption that CPEI can be re-targetted to
304 any cpu in the system. This hint is available via ACPI 3.0 specifications.
305 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
306 This option it useful to enable this feature on older BIOS's as well.
307 You can also enable this by using boot command line option force_cpei=1.
310 bool "Preemptible Kernel"
312 This option reduces the latency of the kernel when reacting to
313 real-time or interactive events by allowing a low priority process to
314 be preempted even if it is in kernel mode executing a system call.
315 This allows applications to run more reliably even when the system is
318 Say Y here if you are building a kernel for a desktop, embedded
319 or real-time system. Say N if you are unsure.
323 config ARCH_SELECT_MEMORY_MODEL
326 config ARCH_DISCONTIGMEM_ENABLE
329 Say Y to support efficient handling of discontiguous physical memory,
330 for architectures which are either NUMA (Non-Uniform Memory Access)
331 or have huge holes in the physical address space for other reasons.
332 See <file:Documentation/vm/numa> for more.
334 config ARCH_FLATMEM_ENABLE
337 config ARCH_SPARSEMEM_ENABLE
339 depends on ARCH_DISCONTIGMEM_ENABLE
341 config ARCH_DISCONTIGMEM_DEFAULT
342 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
343 depends on ARCH_DISCONTIGMEM_ENABLE
347 depends on !IA64_HP_SIM && !FLATMEM
348 default y if IA64_SGI_SN2
350 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
351 Access). This option is for configuring high-end multiprocessor
352 server systems. If in doubt, say N.
355 int "Max num nodes shift(3-10)"
358 depends on NEED_MULTIPLE_NODES
360 This option specifies the maximum number of nodes in your SSI system.
361 MAX_NUMNODES will be 2^(This value).
362 If in doubt, use the default.
364 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
365 # VIRTUAL_MEM_MAP has been retained for historical reasons.
366 config VIRTUAL_MEM_MAP
367 bool "Virtual mem map"
368 depends on !SPARSEMEM
369 default y if !IA64_HP_SIM
371 Say Y to compile the kernel with support for a virtual mem map.
372 This code also only takes effect if a memory hole of greater than
373 1 Gb is found during boot. You must turn this option on if you
374 require the DISCONTIGMEM option for your machine. If you are
379 default y if VIRTUAL_MEM_MAP
381 config HAVE_ARCH_EARLY_PFN_TO_NID
383 depends on NEED_MULTIPLE_NODES
385 config HAVE_ARCH_NODEDATA_EXTENSION
390 bool "Support for Linux/x86 binaries"
392 IA-64 processors can execute IA-32 (X86) instructions. By
393 saying Y here, the kernel will include IA-32 system call
394 emulation support which makes it possible to transparently
395 run IA-32 Linux binaries on an IA-64 Linux system.
400 depends on IA32_SUPPORT
403 config IA64_MCA_RECOVERY
404 tristate "MCA recovery from errors other than TLB."
407 bool "Performance monitor support"
409 Selects whether support for the IA-64 performance monitor hardware
410 is included in the kernel. This makes some kernel data-structures a
411 little bigger and slows down execution a bit, but it is generally
412 a good idea to turn this on. If you're unsure, say Y.
415 tristate "/proc/pal support"
417 If you say Y here, you are able to get PAL (Processor Abstraction
418 Layer) information in /proc/pal. This contains useful information
419 about the processors in your systems, such as cache and TLB sizes
420 and the PAL firmware version in use.
422 To use this option, you have to ensure that the "/proc file system
423 support" (CONFIG_PROC_FS) is enabled, too.
426 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
428 source "drivers/sn/Kconfig"
430 source "drivers/firmware/Kconfig"
432 source "fs/Kconfig.binfmt"
436 menu "Power management and ACPI"
438 source "kernel/power/Kconfig"
440 source "drivers/acpi/Kconfig"
444 source "arch/ia64/kernel/cpufreq/Kconfig"
452 menu "Bus options (PCI, PCMCIA)"
457 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
458 here unless you are using a simulator without PCI support.
464 source "drivers/pci/pcie/Kconfig"
466 source "drivers/pci/Kconfig"
468 source "drivers/pci/hotplug/Kconfig"
470 source "drivers/pcmcia/Kconfig"
478 source "drivers/Kconfig"
485 # Use the generic interrupt handling code in kernel/irq/:
487 config GENERIC_HARDIRQS
491 config GENERIC_IRQ_PROBE
495 config GENERIC_PENDING_IRQ
497 depends on GENERIC_HARDIRQS && SMP
504 source "arch/ia64/hp/sim/Kconfig"
506 menu "Instrumentation Support"
507 depends on EXPERIMENTAL
509 source "arch/ia64/oprofile/Kconfig"
512 bool "Kprobes (EXPERIMENTAL)"
513 depends on EXPERIMENTAL && MODULES
515 Kprobes allows you to trap at almost any kernel address and
516 execute a callback function. register_kprobe() establishes
517 a probepoint and specifies the callback. Kprobes is useful
518 for kernel debugging, non-intrusive instrumentation and testing.
519 If in doubt, say "N".
522 source "arch/ia64/Kconfig.debug"
524 source "security/Kconfig"
526 source "crypto/Kconfig"