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
65 config TIME_INTERPOLATION
81 config SCHED_NO_NO_OMIT_FRAME_POINTER
85 config IA64_UNCACHED_ALLOCATOR
87 select GENERIC_ALLOCATOR
103 This selects the system type of your hardware. A "generic" kernel
104 will run on any supported IA-64 system. However, if you configure
105 a kernel for your specific system, it will be faster and smaller.
107 generic For any supported IA-64 system
108 DIG-compliant For DIG ("Developer's Interface Guide") compliant systems
109 HP-zx1/sx1000 For HP systems
110 HP-zx1/sx1000+swiotlb For HP systems with (broken) DMA-constrained devices.
111 SGI-SN2 For SGI Altix systems
112 Ski-simulator For the HP simulator <http://www.hpl.hp.com/research/linux/ski/>
114 If you don't know what to do, choose "generic".
123 Build a kernel that runs on HP zx1 and sx1000 systems. This adds
124 support for the HP I/O MMU.
126 config IA64_HP_ZX1_SWIOTLB
127 bool "HP-zx1/sx1000 with software I/O TLB"
130 Build a kernel that runs on HP zx1 and sx1000 systems even when they
131 have broken PCI devices which cannot DMA to full 32 bits. Apart
132 from support for the HP I/O MMU, this includes support for the software
133 I/O TLB, which allows supporting the broken devices at the expense of
134 wasting some kernel memory (about 2MB by default).
139 Selecting this option will optimize the kernel for use on sn2 based
140 systems, but the resulting kernel binary will not run on other
141 types of ia64 systems. If you have an SGI Altix system, it's safe
142 to select this option. If in doubt, select ia64 generic support
152 prompt "Processor type"
158 Select your IA-64 processor type. The default is Itanium.
159 This choice is safe for all IA-64 systems, but may not perform
160 optimally on systems with, say, Itanium 2 or newer processors.
165 Select this to configure for an Itanium 2 (McKinley) processor.
170 prompt "Kernel page size"
171 default IA64_PAGE_SIZE_16KB
173 config IA64_PAGE_SIZE_4KB
176 This lets you select the page size of the kernel. For best IA-64
177 performance, a page size of 8KB or 16KB is recommended. For best
178 IA-32 compatibility, a page size of 4KB should be selected (the vast
179 majority of IA-32 binaries work perfectly fine with a larger page
180 size). For Itanium 2 or newer systems, a page size of 64KB can also
183 4KB For best IA-32 compatibility
184 8KB For best IA-64 performance
185 16KB For best IA-64 performance
186 64KB Requires Itanium 2 or newer processor.
188 If you don't know what to do, choose 16KB.
190 config IA64_PAGE_SIZE_8KB
193 config IA64_PAGE_SIZE_16KB
196 config IA64_PAGE_SIZE_64KB
203 prompt "Page Table Levels"
210 depends on !IA64_PAGE_SIZE_64KB
215 source kernel/Kconfig.hz
222 # align cache-sensitive data to 128 bytes
223 config IA64_L1_CACHE_SHIFT
225 default "7" if MCKINLEY
226 default "6" if ITANIUM
229 bool "Cyclone (EXA) Time Source support"
231 Say Y here to enable support for IBM EXA Cyclone time source.
232 If you're unsure, answer N.
236 depends on !IA64_HP_SIM
239 config IA64_SGI_SN_XP
240 tristate "Support communication between SGI SSIs"
241 depends on IA64_GENERIC || IA64_SGI_SN2
242 select IA64_UNCACHED_ALLOCATOR
244 An SGI machine can be divided into multiple Single System
245 Images which act independently of each other and have
246 hardware based memory protection from the others. Enabling
247 this feature will allow for direct communication between SSIs
248 based on a network adapter and DMA messaging.
250 config FORCE_MAX_ZONEORDER
251 int "MAX_ORDER (11 - 17)" if !HUGETLB_PAGE
252 range 11 17 if !HUGETLB_PAGE
253 default "17" if HUGETLB_PAGE
257 bool "Symmetric multi-processing support"
259 This enables support for systems with more than one CPU. If you have
260 a system with only one CPU, say N. If you have a system with more
263 If you say N here, the kernel will run on single and multiprocessor
264 systems, but will use only one CPU of a multiprocessor system. If
265 you say Y here, the kernel will run on many, but not all,
266 single processor systems. On a single processor system, the kernel
267 will run faster if you say N here.
269 See also the <file:Documentation/smp.txt> and the SMP-HOWTO
270 available at <http://www.tldp.org/docs.html#howto>.
272 If you don't know what to do here, say N.
275 int "Maximum number of CPUs (2-1024)"
280 You should set this to the number of CPUs in your system, but
281 keep in mind that a kernel compiled for, e.g., 2 CPUs will boot but
282 only use 2 CPUs on a >2 CPU system. Setting this to a value larger
283 than 64 will cause the use of a CPU mask array, causing a small
287 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
288 depends on SMP && EXPERIMENTAL
292 Say Y here to experiment with turning CPUs off and on. CPUs
293 can be controlled through /sys/devices/system/cpu/cpu#.
294 Say N if you want to disable CPU hotplug.
296 config ARCH_ENABLE_MEMORY_HOTPLUG
300 bool "SMT scheduler support"
303 Improves the CPU scheduler's decision making when dealing with
304 Intel IA64 chips with MultiThreading at a cost of slightly increased
305 overhead in some places. If unsure say N here.
307 config PERMIT_BSP_REMOVE
308 bool "Support removal of Bootstrap Processor"
309 depends on HOTPLUG_CPU
312 Say Y here if your platform SAL will support removal of BSP with HOTPLUG_CPU
315 config FORCE_CPEI_RETARGET
316 bool "Force assumption that CPEI can be re-targetted"
317 depends on PERMIT_BSP_REMOVE
320 Say Y if you need to force the assumption that CPEI can be re-targetted to
321 any cpu in the system. This hint is available via ACPI 3.0 specifications.
322 Tiger4 systems are capable of re-directing CPEI to any CPU other than BSP.
323 This option it useful to enable this feature on older BIOS's as well.
324 You can also enable this by using boot command line option force_cpei=1.
327 bool "Preemptible Kernel"
329 This option reduces the latency of the kernel when reacting to
330 real-time or interactive events by allowing a low priority process to
331 be preempted even if it is in kernel mode executing a system call.
332 This allows applications to run more reliably even when the system is
335 Say Y here if you are building a kernel for a desktop, embedded
336 or real-time system. Say N if you are unsure.
340 config ARCH_SELECT_MEMORY_MODEL
343 config ARCH_DISCONTIGMEM_ENABLE
346 Say Y to support efficient handling of discontiguous physical memory,
347 for architectures which are either NUMA (Non-Uniform Memory Access)
348 or have huge holes in the physical address space for other reasons.
349 See <file:Documentation/vm/numa> for more.
351 config ARCH_FLATMEM_ENABLE
354 config ARCH_SPARSEMEM_ENABLE
356 depends on ARCH_DISCONTIGMEM_ENABLE
358 config ARCH_DISCONTIGMEM_DEFAULT
359 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
360 depends on ARCH_DISCONTIGMEM_ENABLE
364 depends on !IA64_HP_SIM && !FLATMEM
365 default y if IA64_SGI_SN2
366 select ACPI_NUMA if ACPI
368 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
369 Access). This option is for configuring high-end multiprocessor
370 server systems. If in doubt, say N.
373 int "Max num nodes shift(3-10)"
376 depends on NEED_MULTIPLE_NODES
378 This option specifies the maximum number of nodes in your SSI system.
379 MAX_NUMNODES will be 2^(This value).
380 If in doubt, use the default.
382 config ARCH_POPULATES_NODE_MAP
385 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
386 # VIRTUAL_MEM_MAP has been retained for historical reasons.
387 config VIRTUAL_MEM_MAP
388 bool "Virtual mem map"
389 depends on !SPARSEMEM
390 default y if !IA64_HP_SIM
392 Say Y to compile the kernel with support for a virtual mem map.
393 This code also only takes effect if a memory hole of greater than
394 1 Gb is found during boot. You must turn this option on if you
395 require the DISCONTIGMEM option for your machine. If you are
400 default y if VIRTUAL_MEM_MAP
402 config HAVE_ARCH_EARLY_PFN_TO_NID
404 depends on NEED_MULTIPLE_NODES
406 config HAVE_ARCH_NODEDATA_EXTENSION
411 bool "Support for Linux/x86 binaries"
413 IA-64 processors can execute IA-32 (X86) instructions. By
414 saying Y here, the kernel will include IA-32 system call
415 emulation support which makes it possible to transparently
416 run IA-32 Linux binaries on an IA-64 Linux system.
421 depends on IA32_SUPPORT
424 config IA64_MCA_RECOVERY
425 tristate "MCA recovery from errors other than TLB."
428 bool "Performance monitor support"
430 Selects whether support for the IA-64 performance monitor hardware
431 is included in the kernel. This makes some kernel data-structures a
432 little bigger and slows down execution a bit, but it is generally
433 a good idea to turn this on. If you're unsure, say Y.
436 tristate "/proc/pal support"
438 If you say Y here, you are able to get PAL (Processor Abstraction
439 Layer) information in /proc/pal. This contains useful information
440 about the processors in your systems, such as cache and TLB sizes
441 and the PAL firmware version in use.
443 To use this option, you have to ensure that the "/proc file system
444 support" (CONFIG_PROC_FS) is enabled, too.
446 config IA64_MC_ERR_INJECT
447 tristate "MC error injection support"
449 Selets whether support for MC error injection. By enabling the
450 support, kernel provide sysfs interface for user application to
451 call MC error injection PAL procedure to inject various errors.
452 This is a useful tool for MCA testing.
454 If you're unsure, do not select this option.
457 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
460 bool "ESI (Extensible SAL Interface) support"
462 If you say Y here, support is built into the kernel to
463 make ESI calls. ESI calls are used to support vendor-specific
464 firmware extensions, such as the ability to inject memory-errors
465 for test-purposes. If you're unsure, say N.
467 source "drivers/sn/Kconfig"
470 bool "kexec system call (EXPERIMENTAL)"
471 depends on EXPERIMENTAL && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
473 kexec is a system call that implements the ability to shutdown your
474 current kernel, and to start another kernel. It is like a reboot
475 but it is independent of the system firmware. And like a reboot
476 you can start any kernel with it, not just Linux.
478 The name comes from the similiarity to the exec system call.
480 It is an ongoing process to be certain the hardware in a machine
481 is properly shutdown, so do not be surprised if this code does not
482 initially work for you. It may help to enable device hotplugging
483 support. As of this writing the exact hardware interface is
484 strongly in flux, so no good recommendation can be made.
487 bool "kernel crash dumps (EXPERIMENTAL)"
488 depends on EXPERIMENTAL && IA64_MCA_RECOVERY && !IA64_HP_SIM && (!SMP || HOTPLUG_CPU)
490 Generate crash dump after being started by kexec.
492 source "drivers/firmware/Kconfig"
494 source "fs/Kconfig.binfmt"
498 menu "Power management and ACPI"
500 source "kernel/power/Kconfig"
502 source "drivers/acpi/Kconfig"
506 source "arch/ia64/kernel/cpufreq/Kconfig"
514 menu "Bus options (PCI, PCMCIA)"
519 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
520 here unless you are using a simulator without PCI support.
528 source "drivers/pci/pcie/Kconfig"
530 source "drivers/pci/Kconfig"
532 source "drivers/pci/hotplug/Kconfig"
534 source "drivers/pcmcia/Kconfig"
542 source "drivers/Kconfig"
545 tristate "Memory special operations driver"
547 select IA64_UNCACHED_ALLOCATOR
549 If you have an ia64 and you want to enable memory special
550 operations support (formerly known as fetchop), say Y here,
558 # Use the generic interrupt handling code in kernel/irq/:
560 config GENERIC_HARDIRQS
564 config GENERIC_IRQ_PROBE
568 config GENERIC_PENDING_IRQ
570 depends on GENERIC_HARDIRQS && SMP
577 source "arch/ia64/hp/sim/Kconfig"
579 menu "Instrumentation Support"
580 depends on EXPERIMENTAL
582 source "arch/ia64/oprofile/Kconfig"
585 bool "Kprobes (EXPERIMENTAL)"
586 depends on KALLSYMS && EXPERIMENTAL && MODULES
588 Kprobes allows you to trap at almost any kernel address and
589 execute a callback function. register_kprobe() establishes
590 a probepoint and specifies the callback. Kprobes is useful
591 for kernel debugging, non-intrusive instrumentation and testing.
592 If in doubt, say "N".
595 source "arch/ia64/Kconfig.debug"
597 source "security/Kconfig"
599 source "crypto/Kconfig"