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)
19 The Itanium Processor Family is Intel's 64-bit successor to
20 the 32-bit X86 line. The IA-64 Linux project has a home
21 page at <http://www.linuxia64.org/> and a mailing list at
22 <linux-ia64@vger.kernel.org>.
26 select ATA_NONSTANDARD if ATA
31 depends on !IA64_SGI_SN2
40 config RWSEM_XCHGADD_ALGORITHM
44 config ARCH_HAS_ILOG2_U32
48 config ARCH_HAS_ILOG2_U64
52 config GENERIC_FIND_NEXT_BIT
56 config GENERIC_CALIBRATE_DELAY
60 config TIME_INTERPOLATION
76 config SCHED_NO_NO_OMIT_FRAME_POINTER
80 config IA64_UNCACHED_ALLOCATOR
82 select GENERIC_ALLOCATOR
98 This selects the system type of your hardware. A "generic" kernel
99 will run on any supported IA-64 system. However, if you configure
100 a kernel for your specific system, it will be faster and smaller.
102 generic For any supported IA-64 system
103 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
104 HP-zx1/sx1000 For HP systems
105 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
106 SGI-SN2 For SGI Altix systems
107 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
109 If you don't know what to do, choose "generic".
118 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
119 support for the HP I/O MMU.
121 config IA64_HP_ZX1_SWIOTLB
122 bool "HP-zx1/sx1000 with software I/O TLB"
125 Build a kernel that runs on HP zx1 and sx1000 systems even when they
126 have broken PCI devices which cannot DMA to full 32 bits. Apart
127 from support for the HP I/O MMU, this includes support for the software
128 I/O TLB, which allows supporting the broken devices at the expense of
129 wasting some kernel memory (about 2MB by default).
134 Selecting this option will optimize the kernel for use on sn2 based
135 systems, but the resulting kernel binary will not run on other
136 types of ia64 systems. If you have an SGI Altix system, it's safe
137 to select this option. If in doubt, select ia64 generic support
147 prompt "Processor type"
153 Select your IA-64 processor type. The default is Itanium.
154 This choice is safe for all IA-64 systems, but may not perform
155 optimally on systems with, say, Itanium 2 or newer processors.
160 Select this to configure for an Itanium 2 (McKinley) processor.
165 prompt "Kernel page size"
166 default IA64_PAGE_SIZE_16KB
168 config IA64_PAGE_SIZE_4KB
171 This lets you select the page size of the kernel. For best IA-64
172 performance, a page size of 8KB or 16KB is recommended. For best
173 IA-32 compatibility, a page size of 4KB should be selected (the vast
174 majority of IA-32 binaries work perfectly fine with a larger page
175 size). For Itanium 2 or newer systems, a page size of 64KB can also
178 4KB For best IA-32 compatibility
179 8KB For best IA-64 performance
180 16KB For best IA-64 performance
181 64KB Requires Itanium 2 or newer processor.
183 If you don't know what to do, choose 16KB.
185 config IA64_PAGE_SIZE_8KB
188 config IA64_PAGE_SIZE_16KB
191 config IA64_PAGE_SIZE_64KB
198 prompt "Page Table Levels"
205 depends on !IA64_PAGE_SIZE_64KB
210 source kernel/Kconfig.hz
217 # align cache-sensitive data to 128 bytes
218 config IA64_L1_CACHE_SHIFT
220 default "7" if MCKINLEY
221 default "6" if ITANIUM
224 bool "Cyclone (EXA) Time Source support"
226 Say Y here to enable support for IBM EXA Cyclone time source.
227 If you're unsure, answer N.
231 depends on !IA64_HP_SIM
234 config IA64_SGI_SN_XP
235 tristate "Support communication between SGI SSIs"
236 depends on IA64_GENERIC || IA64_SGI_SN2
237 select IA64_UNCACHED_ALLOCATOR
239 An SGI machine can be divided into multiple Single System
240 Images which act independently of each other and have
241 hardware based memory protection from the others. Enabling
242 this feature will allow for direct communication between SSIs
243 based on a network adapter and DMA messaging.
245 config FORCE_MAX_ZONEORDER
246 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
247 range 11 17 if !HUGETLB_PAGE
248 default "17" if HUGETLB_PAGE
252 bool "Symmetric multi-processing support"
254 This enables support for systems with more than one CPU. If you have
255 a system with only one CPU, say N. If you have a system with more
258 If you say N here, the kernel will run on single and multiprocessor
259 systems, but will use only one CPU of a multiprocessor system. If
260 you say Y here, the kernel will run on many, but not all,
261 single processor systems. On a single processor system, the kernel
262 will run faster if you say N here.
264 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
265 available at <http://www.tldp.org/docs.html#howto>.
267 If you don't know what to do here, say N.
270 int "Maximum number of CPUs (2-1024)"
275 You should set this to the number of CPUs in your system, but
276 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
277 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
278 than 64 will cause the use of a CPU mask array, causing a small
282 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
283 depends on SMP && EXPERIMENTAL
287 Say Y here to experiment with turning CPUs off and on. CPUs
288 can be controlled through /sys/devices/system/cpu/cpu#.
289 Say N if you want to disable CPU hotplug.
291 config ARCH_ENABLE_MEMORY_HOTPLUG
295 bool "SMT scheduler support"
298 Improves the CPU scheduler's decision making when dealing with
299 Intel IA64 chips with MultiThreading at a cost of slightly increased
300 overhead in some places. If unsure say N here.
302 config PERMIT_BSP_REMOVE
303 bool "Support removal of Bootstrap Processor"
304 depends on HOTPLUG_CPU
307 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
310 config FORCE_CPEI_RETARGET
311 bool "Force assumption that CPEI can be re-targetted"
312 depends on PERMIT_BSP_REMOVE
315 Say Y if you need to force the assumption that CPEI can be re-targetted to
316 any cpu in the system. This hint is available via ACPI 3.0 specifications.
317 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
318 This option it useful to enable this feature on older BIOS's as well.
319 You can also enable this by using boot command line option force_cpei=1.
322 bool "Preemptible Kernel"
324 This option reduces the latency of the kernel when reacting to
325 real-time or interactive events by allowing a low priority process to
326 be preempted even if it is in kernel mode executing a system call.
327 This allows applications to run more reliably even when the system is
330 Say Y here if you are building a kernel for a desktop, embedded
331 or real-time system. Say N if you are unsure.
335 config ARCH_SELECT_MEMORY_MODEL
338 config ARCH_DISCONTIGMEM_ENABLE
341 Say Y to support efficient handling of discontiguous physical memory,
342 for architectures which are either NUMA (Non-Uniform Memory Access)
343 or have huge holes in the physical address space for other reasons.
344 See <file:Documentation/vm/numa> for more.
346 config ARCH_FLATMEM_ENABLE
349 config ARCH_SPARSEMEM_ENABLE
351 depends on ARCH_DISCONTIGMEM_ENABLE
353 config ARCH_DISCONTIGMEM_DEFAULT
354 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
355 depends on ARCH_DISCONTIGMEM_ENABLE
359 depends on !IA64_HP_SIM && !FLATMEM
360 default y if IA64_SGI_SN2
361 select ACPI_NUMA if ACPI
363 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
364 Access). This option is for configuring high-end multiprocessor
365 server systems. If in doubt, say N.
368 int "Max num nodes shift(3-10)"
371 depends on NEED_MULTIPLE_NODES
373 This option specifies the maximum number of nodes in your SSI system.
374 MAX_NUMNODES will be 2^(This value).
375 If in doubt, use the default.
377 config ARCH_POPULATES_NODE_MAP
380 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
381 # VIRTUAL_MEM_MAP has been retained for historical reasons.
382 config VIRTUAL_MEM_MAP
383 bool "Virtual mem map"
384 depends on !SPARSEMEM
385 default y if !IA64_HP_SIM
387 Say Y to compile the kernel with support for a virtual mem map.
388 This code also only takes effect if a memory hole of greater than
389 1 Gb is found during boot. You must turn this option on if you
390 require the DISCONTIGMEM option for your machine. If you are
395 default y if VIRTUAL_MEM_MAP
397 config HAVE_ARCH_EARLY_PFN_TO_NID
399 depends on NEED_MULTIPLE_NODES
401 config HAVE_ARCH_NODEDATA_EXTENSION
406 bool "Support for Linux/x86 binaries"
408 IA-64 processors can execute IA-32 (X86) instructions. By
409 saying Y here, the kernel will include IA-32 system call
410 emulation support which makes it possible to transparently
411 run IA-32 Linux binaries on an IA-64 Linux system.
416 depends on IA32_SUPPORT
419 config IA64_MCA_RECOVERY
420 tristate "MCA recovery from errors other than TLB."
423 bool "Performance monitor support"
425 Selects whether support for the IA-64 performance monitor hardware
426 is included in the kernel. This makes some kernel data-structures a
427 little bigger and slows down execution a bit, but it is generally
428 a good idea to turn this on. If you're unsure, say Y.
431 tristate "/proc/pal support"
433 If you say Y here, you are able to get PAL (Processor Abstraction
434 Layer) information in /proc/pal. This contains useful information
435 about the processors in your systems, such as cache and TLB sizes
436 and the PAL firmware version in use.
438 To use this option, you have to ensure that the "/proc file system
439 support" (CONFIG_PROC_FS) is enabled, too.
442 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
445 bool "ESI (Extensible SAL Interface) support"
447 If you say Y here, support is built into the kernel to
448 make ESI calls. ESI calls are used to support vendor-specific
449 firmware extensions, such as the ability to inject memory-errors
450 for test-purposes. If you're unsure, say N.
452 source "drivers/sn/Kconfig"
455 bool "kexec system call (EXPERIMENTAL)"
456 depends on EXPERIMENTAL && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
458 kexec is a system call that implements the ability to shutdown your
459 current kernel, and to start another kernel. It is like a reboot
460 but it is indepedent of the system firmware. And like a reboot
461 you can start any kernel with it, not just Linux.
463 The name comes from the similiarity to the exec system call.
465 It is an ongoing process to be certain the hardware in a machine
466 is properly shutdown, so do not be surprised if this code does not
467 initially work for you. It may help to enable device hotplugging
468 support. As of this writing the exact hardware interface is
469 strongly in flux, so no good recommendation can be made.
472 bool "kernel crash dumps (EXPERIMENTAL)"
473 depends on EXPERIMENTAL && IA64_MCA_RECOVERY && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
475 Generate crash dump after being started by kexec.
477 source "drivers/firmware/Kconfig"
479 source "fs/Kconfig.binfmt"
483 menu "Power management and ACPI"
485 source "kernel/power/Kconfig"
487 source "drivers/acpi/Kconfig"
491 source "arch/ia64/kernel/cpufreq/Kconfig"
499 menu "Bus options (PCI, PCMCIA)"
504 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
505 here unless you are using a simulator without PCI support.
511 source "drivers/pci/pcie/Kconfig"
513 source "drivers/pci/Kconfig"
515 source "drivers/pci/hotplug/Kconfig"
517 source "drivers/pcmcia/Kconfig"
525 source "drivers/Kconfig"
528 tristate "Memory special operations driver"
530 select IA64_UNCACHED_ALLOCATOR
532 If you have an ia64 and you want to enable memory special
533 operations support (formerly known as fetchop), say Y here,
541 # Use the generic interrupt handling code in kernel/irq/:
543 config GENERIC_HARDIRQS
547 config GENERIC_IRQ_PROBE
551 config GENERIC_PENDING_IRQ
553 depends on GENERIC_HARDIRQS && SMP
560 source "arch/ia64/hp/sim/Kconfig"
562 menu "Instrumentation Support"
563 depends on EXPERIMENTAL
565 source "arch/ia64/oprofile/Kconfig"
568 bool "Kprobes (EXPERIMENTAL)"
569 depends on KALLSYMS && EXPERIMENTAL && MODULES
571 Kprobes allows you to trap at almost any kernel address and
572 execute a callback function. register_kprobe() establishes
573 a probepoint and specifies the callback. Kprobes is useful
574 for kernel debugging, non-intrusive instrumentation and testing.
575 If in doubt, say "N".
578 source "arch/ia64/Kconfig.debug"
580 source "security/Kconfig"
582 source "crypto/Kconfig"