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
84 This selects the system type of your hardware. A "generic" kernel
85 will run on any supported IA-64 system. However, if you configure
86 a kernel for your specific system, it will be faster and smaller.
88 generic For any supported IA-64 system
89 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
90 HP-zx1/sx1000 For HP systems
91 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
92 SGI-SN2 For SGI Altix systems
93 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
95 If you don't know what to do, choose "generic".
103 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
104 support for the HP I/O MMU.
106 config IA64_HP_ZX1_SWIOTLB
107 bool "HP-zx1/sx1000 with software I/O TLB"
109 Build a kernel that runs on HP zx1 and sx1000 systems even when they
110 have broken PCI devices which cannot DMA to full 32 bits. Apart
111 from support for the HP I/O MMU, this includes support for the software
112 I/O TLB, which allows supporting the broken devices at the expense of
113 wasting some kernel memory (about 2MB by default).
118 Selecting this option will optimize the kernel for use on sn2 based
119 systems, but the resulting kernel binary will not run on other
120 types of ia64 systems. If you have an SGI Altix system, it's safe
121 to select this option. If in doubt, select ia64 generic support
130 prompt "Processor type"
136 Select your IA-64 processor type. The default is Itanium.
137 This choice is safe for all IA-64 systems, but may not perform
138 optimally on systems with, say, Itanium 2 or newer processors.
143 Select this to configure for an Itanium 2 (McKinley) processor.
148 prompt "Kernel page size"
149 default IA64_PAGE_SIZE_16KB
151 config IA64_PAGE_SIZE_4KB
154 This lets you select the page size of the kernel. For best IA-64
155 performance, a page size of 8KB or 16KB is recommended. For best
156 IA-32 compatibility, a page size of 4KB should be selected (the vast
157 majority of IA-32 binaries work perfectly fine with a larger page
158 size). For Itanium 2 or newer systems, a page size of 64KB can also
161 4KB For best IA-32 compatibility
162 8KB For best IA-64 performance
163 16KB For best IA-64 performance
164 64KB Requires Itanium 2 or newer processor.
166 If you don't know what to do, choose 16KB.
168 config IA64_PAGE_SIZE_8KB
171 config IA64_PAGE_SIZE_16KB
174 config IA64_PAGE_SIZE_64KB
181 prompt "Page Table Levels"
188 depends on !IA64_PAGE_SIZE_64KB
193 source kernel/Kconfig.hz
200 # align cache-sensitive data to 128 bytes
201 config IA64_L1_CACHE_SHIFT
203 default "7" if MCKINLEY
204 default "6" if ITANIUM
207 bool "Cyclone (EXA) Time Source support"
209 Say Y here to enable support for IBM EXA Cyclone time source.
210 If you're unsure, answer N.
214 depends on !IA64_HP_SIM
217 config IA64_SGI_SN_XP
218 tristate "Support communication between SGI SSIs"
219 depends on IA64_GENERIC || IA64_SGI_SN2
220 select IA64_UNCACHED_ALLOCATOR
222 An SGI machine can be divided into multiple Single System
223 Images which act independently of each other and have
224 hardware based memory protection from the others. Enabling
225 this feature will allow for direct communication between SSIs
226 based on a network adapter and DMA messaging.
228 config FORCE_MAX_ZONEORDER
229 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
230 range 11 17 if !HUGETLB_PAGE
231 default "17" if HUGETLB_PAGE
235 bool "Symmetric multi-processing support"
237 This enables support for systems with more than one CPU. If you have
238 a system with only one CPU, say N. If you have a system with more
241 If you say N here, the kernel will run on single and multiprocessor
242 systems, but will use only one CPU of a multiprocessor system. If
243 you say Y here, the kernel will run on many, but not all,
244 single processor systems. On a single processor system, the kernel
245 will run faster if you say N here.
247 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
248 available at <http://www.tldp.org/docs.html#howto>.
250 If you don't know what to do here, say N.
253 int "Maximum number of CPUs (2-1024)"
258 You should set this to the number of CPUs in your system, but
259 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
260 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
261 than 64 will cause the use of a CPU mask array, causing a small
265 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
266 depends on SMP && EXPERIMENTAL
270 Say Y here to experiment with turning CPUs off and on. CPUs
271 can be controlled through /sys/devices/system/cpu/cpu#.
272 Say N if you want to disable CPU hotplug.
274 config ARCH_ENABLE_MEMORY_HOTPLUG
278 bool "SMT scheduler support"
281 Improves the CPU scheduler's decision making when dealing with
282 Intel IA64 chips with MultiThreading at a cost of slightly increased
283 overhead in some places. If unsure say N here.
285 config PERMIT_BSP_REMOVE
286 bool "Support removal of Bootstrap Processor"
287 depends on HOTPLUG_CPU
290 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
293 config FORCE_CPEI_RETARGET
294 bool "Force assumption that CPEI can be re-targetted"
295 depends on PERMIT_BSP_REMOVE
298 Say Y if you need to force the assumption that CPEI can be re-targetted to
299 any cpu in the system. This hint is available via ACPI 3.0 specifications.
300 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
301 This option it useful to enable this feature on older BIOS's as well.
302 You can also enable this by using boot command line option force_cpei=1.
305 bool "Preemptible Kernel"
307 This option reduces the latency of the kernel when reacting to
308 real-time or interactive events by allowing a low priority process to
309 be preempted even if it is in kernel mode executing a system call.
310 This allows applications to run more reliably even when the system is
313 Say Y here if you are building a kernel for a desktop, embedded
314 or real-time system. Say N if you are unsure.
318 config ARCH_SELECT_MEMORY_MODEL
321 config ARCH_DISCONTIGMEM_ENABLE
324 Say Y to support efficient handling of discontiguous physical memory,
325 for architectures which are either NUMA (Non-Uniform Memory Access)
326 or have huge holes in the physical address space for other reasons.
327 See <file:Documentation/vm/numa> for more.
329 config ARCH_FLATMEM_ENABLE
332 config ARCH_SPARSEMEM_ENABLE
334 depends on ARCH_DISCONTIGMEM_ENABLE
336 config ARCH_DISCONTIGMEM_DEFAULT
337 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
338 depends on ARCH_DISCONTIGMEM_ENABLE
342 depends on !IA64_HP_SIM && !FLATMEM
343 default y if IA64_SGI_SN2
345 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
346 Access). This option is for configuring high-end multiprocessor
347 server systems. If in doubt, say N.
350 int "Max num nodes shift(3-10)"
353 depends on NEED_MULTIPLE_NODES
355 This option specifies the maximum number of nodes in your SSI system.
356 MAX_NUMNODES will be 2^(This value).
357 If in doubt, use the default.
359 config ARCH_POPULATES_NODE_MAP
362 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
363 # VIRTUAL_MEM_MAP has been retained for historical reasons.
364 config VIRTUAL_MEM_MAP
365 bool "Virtual mem map"
366 depends on !SPARSEMEM
367 default y if !IA64_HP_SIM
369 Say Y to compile the kernel with support for a virtual mem map.
370 This code also only takes effect if a memory hole of greater than
371 1 Gb is found during boot. You must turn this option on if you
372 require the DISCONTIGMEM option for your machine. If you are
377 default y if VIRTUAL_MEM_MAP
379 config HAVE_ARCH_EARLY_PFN_TO_NID
381 depends on NEED_MULTIPLE_NODES
383 config HAVE_ARCH_NODEDATA_EXTENSION
388 bool "Support for Linux/x86 binaries"
390 IA-64 processors can execute IA-32 (X86) instructions. By
391 saying Y here, the kernel will include IA-32 system call
392 emulation support which makes it possible to transparently
393 run IA-32 Linux binaries on an IA-64 Linux system.
398 depends on IA32_SUPPORT
401 config IA64_MCA_RECOVERY
402 tristate "MCA recovery from errors other than TLB."
405 bool "Performance monitor support"
407 Selects whether support for the IA-64 performance monitor hardware
408 is included in the kernel. This makes some kernel data-structures a
409 little bigger and slows down execution a bit, but it is generally
410 a good idea to turn this on. If you're unsure, say Y.
413 tristate "/proc/pal support"
415 If you say Y here, you are able to get PAL (Processor Abstraction
416 Layer) information in /proc/pal. This contains useful information
417 about the processors in your systems, such as cache and TLB sizes
418 and the PAL firmware version in use.
420 To use this option, you have to ensure that the "/proc file system
421 support" (CONFIG_PROC_FS) is enabled, too.
424 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
427 bool "ESI (Extensible SAL Interface) support"
429 If you say Y here, support is built into the kernel to
430 make ESI calls. ESI calls are used to support vendor-specific
431 firmware extensions, such as the ability to inject memory-errors
432 for test-purposes. If you're unsure, say N.
434 source "drivers/sn/Kconfig"
436 source "drivers/firmware/Kconfig"
438 source "fs/Kconfig.binfmt"
442 menu "Power management and ACPI"
444 source "kernel/power/Kconfig"
446 source "drivers/acpi/Kconfig"
450 source "arch/ia64/kernel/cpufreq/Kconfig"
458 menu "Bus options (PCI, PCMCIA)"
463 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
464 here unless you are using a simulator without PCI support.
470 source "drivers/pci/pcie/Kconfig"
472 source "drivers/pci/Kconfig"
474 source "drivers/pci/hotplug/Kconfig"
476 source "drivers/pcmcia/Kconfig"
484 source "drivers/Kconfig"
491 # Use the generic interrupt handling code in kernel/irq/:
493 config GENERIC_HARDIRQS
497 config GENERIC_IRQ_PROBE
501 config GENERIC_PENDING_IRQ
503 depends on GENERIC_HARDIRQS && SMP
510 source "arch/ia64/hp/sim/Kconfig"
512 menu "Instrumentation Support"
513 depends on EXPERIMENTAL
515 source "arch/ia64/oprofile/Kconfig"
518 bool "Kprobes (EXPERIMENTAL)"
519 depends on EXPERIMENTAL && MODULES
521 Kprobes allows you to trap at almost any kernel address and
522 execute a callback function. register_kprobe() establishes
523 a probepoint and specifies the callback. Kprobes is useful
524 for kernel debugging, non-intrusive instrumentation and testing.
525 If in doubt, say "N".
528 source "arch/ia64/Kconfig.debug"
530 source "security/Kconfig"
532 source "crypto/Kconfig"