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"
14 select PCI if (!IA64_HP_SIM)
15 select ACPI if (!IA64_HP_SIM)
16 select PM if (!IA64_HP_SIM)
17 select ARCH_SUPPORTS_MSI
20 The Itanium Processor Family is Intel's 64-bit successor to
21 the 32-bit X86 line. The IA-64 Linux project has a home
22 page at <http://www.linuxia64.org/> and a mailing list at
23 <linux-ia64@vger.kernel.org>.
27 select ATA_NONSTANDARD if ATA
32 depends on !IA64_SGI_SN2
45 config RWSEM_XCHGADD_ALGORITHM
49 config ARCH_HAS_ILOG2_U32
53 config ARCH_HAS_ILOG2_U64
57 config GENERIC_FIND_NEXT_BIT
61 config GENERIC_CALIBRATE_DELAY
69 config GENERIC_TIME_VSYSCALL
85 config SCHED_NO_NO_OMIT_FRAME_POINTER
89 config IA64_UNCACHED_ALLOCATOR
91 select GENERIC_ALLOCATOR
107 This selects the system type of your hardware. A "generic" kernel
108 will run on any supported IA-64 system. However, if you configure
109 a kernel for your specific system, it will be faster and smaller.
111 generic For any supported IA-64 system
112 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
113 HP-zx1/sx1000 For HP systems
114 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
115 SGI-SN2 For SGI Altix systems
116 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
118 If you don't know what to do, choose "generic".
127 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
128 support for the HP I/O MMU.
130 config IA64_HP_ZX1_SWIOTLB
131 bool "HP-zx1/sx1000 with software I/O TLB"
134 Build a kernel that runs on HP zx1 and sx1000 systems even when they
135 have broken PCI devices which cannot DMA to full 32 bits. Apart
136 from support for the HP I/O MMU, this includes support for the software
137 I/O TLB, which allows supporting the broken devices at the expense of
138 wasting some kernel memory (about 2MB by default).
143 Selecting this option will optimize the kernel for use on sn2 based
144 systems, but the resulting kernel binary will not run on other
145 types of ia64 systems. If you have an SGI Altix system, it's safe
146 to select this option. If in doubt, select ia64 generic support
156 prompt "Processor type"
162 Select your IA-64 processor type. The default is Itanium.
163 This choice is safe for all IA-64 systems, but may not perform
164 optimally on systems with, say, Itanium 2 or newer processors.
169 Select this to configure for an Itanium 2 (McKinley) processor.
174 prompt "Kernel page size"
175 default IA64_PAGE_SIZE_16KB
177 config IA64_PAGE_SIZE_4KB
180 This lets you select the page size of the kernel. For best IA-64
181 performance, a page size of 8KB or 16KB is recommended. For best
182 IA-32 compatibility, a page size of 4KB should be selected (the vast
183 majority of IA-32 binaries work perfectly fine with a larger page
184 size). For Itanium 2 or newer systems, a page size of 64KB can also
187 4KB For best IA-32 compatibility
188 8KB For best IA-64 performance
189 16KB For best IA-64 performance
190 64KB Requires Itanium 2 or newer processor.
192 If you don't know what to do, choose 16KB.
194 config IA64_PAGE_SIZE_8KB
197 config IA64_PAGE_SIZE_16KB
200 config IA64_PAGE_SIZE_64KB
207 prompt "Page Table Levels"
214 depends on !IA64_PAGE_SIZE_64KB
219 source kernel/Kconfig.hz
226 # align cache-sensitive data to 128 bytes
227 config IA64_L1_CACHE_SHIFT
229 default "7" if MCKINLEY
230 default "6" if ITANIUM
233 bool "Cyclone (EXA) Time Source support"
235 Say Y here to enable support for IBM EXA Cyclone time source.
236 If you're unsure, answer N.
240 depends on !IA64_HP_SIM
243 config IA64_SGI_SN_XP
244 tristate "Support communication between SGI SSIs"
245 depends on IA64_GENERIC || IA64_SGI_SN2
246 select IA64_UNCACHED_ALLOCATOR
248 An SGI machine can be divided into multiple Single System
249 Images which act independently of each other and have
250 hardware based memory protection from the others. Enabling
251 this feature will allow for direct communication between SSIs
252 based on a network adapter and DMA messaging.
254 config FORCE_MAX_ZONEORDER
255 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
256 range 11 17 if !HUGETLB_PAGE
257 default "17" if HUGETLB_PAGE
261 bool "Symmetric multi-processing support"
263 This enables support for systems with more than one CPU. If you have
264 a system with only one CPU, say N. If you have a system with more
267 If you say N here, the kernel will run on single and multiprocessor
268 systems, but will use only one CPU of a multiprocessor system. If
269 you say Y here, the kernel will run on many, but not all,
270 single processor systems. On a single processor system, the kernel
271 will run faster if you say N here.
273 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
274 available at <http://www.tldp.org/docs.html#howto>.
276 If you don't know what to do here, say N.
279 int "Maximum number of CPUs (2-1024)"
284 You should set this to the number of CPUs in your system, but
285 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
286 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
287 than 64 will cause the use of a CPU mask array, causing a small
291 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
292 depends on SMP && EXPERIMENTAL
296 Say Y here to experiment with turning CPUs off and on. CPUs
297 can be controlled through /sys/devices/system/cpu/cpu#.
298 Say N if you want to disable CPU hotplug.
300 config ARCH_ENABLE_MEMORY_HOTPLUG
304 bool "SMT scheduler support"
307 Improves the CPU scheduler's decision making when dealing with
308 Intel IA64 chips with MultiThreading at a cost of slightly increased
309 overhead in some places. If unsure say N here.
311 config PERMIT_BSP_REMOVE
312 bool "Support removal of Bootstrap Processor"
313 depends on HOTPLUG_CPU
316 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
319 config FORCE_CPEI_RETARGET
320 bool "Force assumption that CPEI can be re-targetted"
321 depends on PERMIT_BSP_REMOVE
324 Say Y if you need to force the assumption that CPEI can be re-targetted to
325 any cpu in the system. This hint is available via ACPI 3.0 specifications.
326 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
327 This option it useful to enable this feature on older BIOS's as well.
328 You can also enable this by using boot command line option force_cpei=1.
330 source "kernel/Kconfig.preempt"
334 config ARCH_SELECT_MEMORY_MODEL
337 config ARCH_DISCONTIGMEM_ENABLE
340 Say Y to support efficient handling of discontiguous physical memory,
341 for architectures which are either NUMA (Non-Uniform Memory Access)
342 or have huge holes in the physical address space for other reasons.
343 See <file:Documentation/vm/numa> for more.
345 config ARCH_FLATMEM_ENABLE
348 config ARCH_SPARSEMEM_ENABLE
350 depends on ARCH_DISCONTIGMEM_ENABLE
352 config ARCH_DISCONTIGMEM_DEFAULT
353 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
354 depends on ARCH_DISCONTIGMEM_ENABLE
358 depends on !IA64_HP_SIM && !FLATMEM
359 default y if IA64_SGI_SN2
360 select ACPI_NUMA if ACPI
362 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
363 Access). This option is for configuring high-end multiprocessor
364 server systems. If in doubt, say N.
367 int "Max num nodes shift(3-10)"
370 depends on NEED_MULTIPLE_NODES
372 This option specifies the maximum number of nodes in your SSI system.
373 MAX_NUMNODES will be 2^(This value).
374 If in doubt, use the default.
376 config ARCH_POPULATES_NODE_MAP
379 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
380 # VIRTUAL_MEM_MAP has been retained for historical reasons.
381 config VIRTUAL_MEM_MAP
382 bool "Virtual mem map"
383 depends on !SPARSEMEM
384 default y if !IA64_HP_SIM
386 Say Y to compile the kernel with support for a virtual mem map.
387 This code also only takes effect if a memory hole of greater than
388 1 Gb is found during boot. You must turn this option on if you
389 require the DISCONTIGMEM option for your machine. If you are
394 default y if VIRTUAL_MEM_MAP
396 config HAVE_ARCH_EARLY_PFN_TO_NID
398 depends on NEED_MULTIPLE_NODES
400 config HAVE_ARCH_NODEDATA_EXTENSION
405 bool "Support for Linux/x86 binaries"
407 IA-64 processors can execute IA-32 (X86) instructions. By
408 saying Y here, the kernel will include IA-32 system call
409 emulation support which makes it possible to transparently
410 run IA-32 Linux binaries on an IA-64 Linux system.
415 depends on IA32_SUPPORT
418 config COMPAT_FOR_U64_ALIGNMENT
421 config IA64_MCA_RECOVERY
422 tristate "MCA recovery from errors other than TLB."
425 bool "Performance monitor support"
427 Selects whether support for the IA-64 performance monitor hardware
428 is included in the kernel. This makes some kernel data-structures a
429 little bigger and slows down execution a bit, but it is generally
430 a good idea to turn this on. If you're unsure, say Y.
433 tristate "/proc/pal support"
435 If you say Y here, you are able to get PAL (Processor Abstraction
436 Layer) information in /proc/pal. This contains useful information
437 about the processors in your systems, such as cache and TLB sizes
438 and the PAL firmware version in use.
440 To use this option, you have to ensure that the "/proc file system
441 support" (CONFIG_PROC_FS) is enabled, too.
443 config IA64_MC_ERR_INJECT
444 tristate "MC error injection support"
446 Selets whether support for MC error injection. By enabling the
447 support, kernel provide sysfs interface for user application to
448 call MC error injection PAL procedure to inject various errors.
449 This is a useful tool for MCA testing.
451 If you're unsure, do not select this option.
454 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
457 bool "ESI (Extensible SAL Interface) support"
459 If you say Y here, support is built into the kernel to
460 make ESI calls. ESI calls are used to support vendor-specific
461 firmware extensions, such as the ability to inject memory-errors
462 for test-purposes. If you're unsure, say N.
464 source "drivers/sn/Kconfig"
467 bool "kexec system call (EXPERIMENTAL)"
468 depends on EXPERIMENTAL && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
470 kexec is a system call that implements the ability to shutdown your
471 current kernel, and to start another kernel. It is like a reboot
472 but it is independent of the system firmware. And like a reboot
473 you can start any kernel with it, not just Linux.
475 The name comes from the similiarity to the exec system call.
477 It is an ongoing process to be certain the hardware in a machine
478 is properly shutdown, so do not be surprised if this code does not
479 initially work for you. It may help to enable device hotplugging
480 support. As of this writing the exact hardware interface is
481 strongly in flux, so no good recommendation can be made.
484 bool "kernel crash dumps (EXPERIMENTAL)"
485 depends on EXPERIMENTAL && IA64_MCA_RECOVERY && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
487 Generate crash dump after being started by kexec.
489 source "drivers/firmware/Kconfig"
491 source "fs/Kconfig.binfmt"
495 menu "Power management and ACPI"
497 source "kernel/power/Kconfig"
499 source "drivers/acpi/Kconfig"
503 source "arch/ia64/kernel/cpufreq/Kconfig"
511 menu "Bus options (PCI, PCMCIA)"
516 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
517 here unless you are using a simulator without PCI support.
525 source "drivers/pci/pcie/Kconfig"
527 source "drivers/pci/Kconfig"
529 source "drivers/pci/hotplug/Kconfig"
531 source "drivers/pcmcia/Kconfig"
539 source "drivers/Kconfig"
542 tristate "Memory special operations driver"
544 select IA64_UNCACHED_ALLOCATOR
546 If you have an ia64 and you want to enable memory special
547 operations support (formerly known as fetchop), say Y here,
555 # Use the generic interrupt handling code in kernel/irq/:
557 config GENERIC_HARDIRQS
561 config GENERIC_IRQ_PROBE
565 config GENERIC_PENDING_IRQ
567 depends on GENERIC_HARDIRQS && SMP
574 source "arch/ia64/hp/sim/Kconfig"
576 menu "Instrumentation Support"
577 depends on EXPERIMENTAL
579 source "arch/ia64/oprofile/Kconfig"
583 depends on KALLSYMS && MODULES
585 Kprobes allows you to trap at almost any kernel address and
586 execute a callback function. register_kprobe() establishes
587 a probepoint and specifies the callback. Kprobes is useful
588 for kernel debugging, non-intrusive instrumentation and testing.
589 If in doubt, say "N".
592 source "arch/ia64/Kconfig.debug"
594 source "security/Kconfig"
596 source "crypto/Kconfig"