direct-io.hg

view linux-2.6-xen-sparse/arch/ia64/Kconfig @ 11443:af50fb41612c

[IA64] Expand memory_op for PV-on-HVM on IPF

Signed-off-by: Tsunehisa Doi <Doi.Tsunehisa@jp.fujitsu.com>
Signed-off-by: Tomonari Horikoshi <t.horikoshi@jp.fujitsu.com>
author awilliam@xenbuild.aw
date Fri Sep 01 08:46:02 2006 -0600 (2006-09-01)
parents c3e20511c745
children 2f3db1a38b11
line source
1 #
2 # For a description of the syntax of this configuration file,
3 # see Documentation/kbuild/kconfig-language.txt.
4 #
6 mainmenu "IA-64 Linux Kernel Configuration"
8 source "init/Kconfig"
10 menu "Processor type and features"
12 config IA64
13 bool
14 default y
15 help
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>.
21 config 64BIT
22 bool
23 default y
25 config MMU
26 bool
27 default y
29 config SWIOTLB
30 bool
31 default y
33 config RWSEM_XCHGADD_ALGORITHM
34 bool
35 default y
37 config GENERIC_CALIBRATE_DELAY
38 bool
39 default y
41 config TIME_INTERPOLATION
42 bool
43 default y
45 config EFI
46 bool
47 default y
49 config GENERIC_IOMAP
50 bool
51 default y
53 config XEN
54 bool "Xen hypervisor support"
55 default y
56 help
57 Enable Xen hypervisor support. Resulting kernel runs
58 both as a guest OS on Xen and natively on hardware.
60 config XEN_IA64_VDSO_PARAVIRT
61 bool
62 depends on XEN && !ITANIUM
63 default y
64 help
65 vDSO paravirtualization
67 config SCHED_NO_NO_OMIT_FRAME_POINTER
68 bool
69 default y
71 config IA64_UNCACHED_ALLOCATOR
72 bool
73 select GENERIC_ALLOCATOR
75 config DMA_IS_DMA32
76 bool
77 default y
79 choice
80 prompt "System type"
81 default IA64_GENERIC
83 config IA64_GENERIC
84 bool "generic"
85 select ACPI
86 select NUMA
87 select ACPI_NUMA
88 help
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".
102 config IA64_DIG
103 bool "DIG-compliant"
105 config IA64_HP_ZX1
106 bool "HP-zx1/sx1000"
107 help
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"
113 help
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).
120 config IA64_SGI_SN2
121 bool "SGI-SN2"
122 help
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
127 instead.
129 config IA64_HP_SIM
130 bool "Ski-simulator"
132 endchoice
134 choice
135 prompt "Processor type"
136 default ITANIUM
138 config ITANIUM
139 bool "Itanium"
140 help
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.
145 config MCKINLEY
146 bool "Itanium 2"
147 help
148 Select this to configure for an Itanium 2 (McKinley) processor.
150 endchoice
152 choice
153 prompt "Kernel page size"
154 default IA64_PAGE_SIZE_16KB
156 config IA64_PAGE_SIZE_4KB
157 bool "4KB"
158 help
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
164 be selected.
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
174 bool "8KB"
176 config IA64_PAGE_SIZE_16KB
177 bool "16KB"
179 config IA64_PAGE_SIZE_64KB
180 depends on !ITANIUM
181 bool "64KB"
183 endchoice
185 choice
186 prompt "Page Table Levels"
187 default PGTABLE_3
189 config PGTABLE_3
190 bool "3 Levels"
192 config PGTABLE_4
193 depends on !IA64_PAGE_SIZE_64KB
194 bool "4 Levels"
196 endchoice
198 source kernel/Kconfig.hz
200 config IA64_BRL_EMU
201 bool
202 depends on ITANIUM
203 default y
205 # align cache-sensitive data to 128 bytes
206 config IA64_L1_CACHE_SHIFT
207 int
208 default "7" if MCKINLEY
209 default "6" if ITANIUM
211 config IA64_CYCLONE
212 bool "Cyclone (EXA) Time Source support"
213 help
214 Say Y here to enable support for IBM EXA Cyclone time source.
215 If you're unsure, answer N.
217 config IOSAPIC
218 bool
219 depends on !IA64_HP_SIM
220 default y
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
226 help
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
237 default "11"
239 config SMP
240 bool "Symmetric multi-processing support"
241 help
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
244 than one CPU, say Y.
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.
257 config NR_CPUS
258 int "Maximum number of CPUs (2-1024)"
259 range 2 1024
260 depends on SMP
261 default "64"
262 help
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
267 performance hit.
269 config HOTPLUG_CPU
270 bool "Support for hot-pluggable CPUs (EXPERIMENTAL)"
271 depends on SMP && EXPERIMENTAL
272 select HOTPLUG
273 default n
274 ---help---
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 SCHED_SMT
280 bool "SMT scheduler support"
281 depends on SMP
282 default off
283 help
284 Improves the CPU scheduler's decision making when dealing with
285 Intel IA64 chips with MultiThreading at a cost of slightly increased
286 overhead in some places. If unsure say N here.
288 config PREEMPT
289 bool "Preemptible Kernel"
290 help
291 This option reduces the latency of the kernel when reacting to
292 real-time or interactive events by allowing a low priority process to
293 be preempted even if it is in kernel mode executing a system call.
294 This allows applications to run more reliably even when the system is
295 under load.
297 Say Y here if you are building a kernel for a desktop, embedded
298 or real-time system. Say N if you are unsure.
300 source "mm/Kconfig"
302 config ARCH_SELECT_MEMORY_MODEL
303 def_bool y
305 config ARCH_DISCONTIGMEM_ENABLE
306 def_bool y
307 help
308 Say Y to support efficient handling of discontiguous physical memory,
309 for architectures which are either NUMA (Non-Uniform Memory Access)
310 or have huge holes in the physical address space for other reasons.
311 See <file:Documentation/vm/numa> for more.
313 config ARCH_FLATMEM_ENABLE
314 def_bool y
316 config ARCH_SPARSEMEM_ENABLE
317 def_bool y
318 depends on ARCH_DISCONTIGMEM_ENABLE
320 config ARCH_DISCONTIGMEM_DEFAULT
321 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC || IA64_HP_ZX1 || IA64_HP_ZX1_SWIOTLB)
322 depends on ARCH_DISCONTIGMEM_ENABLE
324 config NUMA
325 bool "NUMA support"
326 depends on !IA64_HP_SIM && !FLATMEM
327 default y if IA64_SGI_SN2
328 help
329 Say Y to compile the kernel to support NUMA (Non-Uniform Memory
330 Access). This option is for configuring high-end multiprocessor
331 server systems. If in doubt, say N.
333 # VIRTUAL_MEM_MAP and FLAT_NODE_MEM_MAP are functionally equivalent.
334 # VIRTUAL_MEM_MAP has been retained for historical reasons.
335 config VIRTUAL_MEM_MAP
336 bool "Virtual mem map"
337 depends on !SPARSEMEM
338 default y if !IA64_HP_SIM
339 help
340 Say Y to compile the kernel with support for a virtual mem map.
341 This code also only takes effect if a memory hole of greater than
342 1 Gb is found during boot. You must turn this option on if you
343 require the DISCONTIGMEM option for your machine. If you are
344 unsure, say Y.
346 config HOLES_IN_ZONE
347 bool
348 default y if VIRTUAL_MEM_MAP
350 config HAVE_ARCH_EARLY_PFN_TO_NID
351 def_bool y
352 depends on NEED_MULTIPLE_NODES
354 config IA32_SUPPORT
355 bool "Support for Linux/x86 binaries"
356 help
357 IA-64 processors can execute IA-32 (X86) instructions. By
358 saying Y here, the kernel will include IA-32 system call
359 emulation support which makes it possible to transparently
360 run IA-32 Linux binaries on an IA-64 Linux system.
361 If in doubt, say Y.
363 config COMPAT
364 bool
365 depends on IA32_SUPPORT
366 default y
368 config IA64_MCA_RECOVERY
369 tristate "MCA recovery from errors other than TLB."
371 config PERFMON
372 bool "Performance monitor support"
373 help
374 Selects whether support for the IA-64 performance monitor hardware
375 is included in the kernel. This makes some kernel data-structures a
376 little bigger and slows down execution a bit, but it is generally
377 a good idea to turn this on. If you're unsure, say Y.
379 config IA64_PALINFO
380 tristate "/proc/pal support"
381 help
382 If you say Y here, you are able to get PAL (Processor Abstraction
383 Layer) information in /proc/pal. This contains useful information
384 about the processors in your systems, such as cache and TLB sizes
385 and the PAL firmware version in use.
387 To use this option, you have to ensure that the "/proc file system
388 support" (CONFIG_PROC_FS) is enabled, too.
390 config SGI_SN
391 def_bool y if (IA64_SGI_SN2 || IA64_GENERIC)
393 source "drivers/firmware/Kconfig"
395 source "fs/Kconfig.binfmt"
397 endmenu
399 menu "Power management and ACPI"
401 source "kernel/power/Kconfig"
403 source "drivers/acpi/Kconfig"
405 if PM
407 source "arch/ia64/kernel/cpufreq/Kconfig"
409 endif
411 endmenu
413 if !IA64_HP_SIM
415 menu "Bus options (PCI, PCMCIA)"
417 config PCI
418 bool "PCI support"
419 help
420 Real IA-64 machines all have PCI/PCI-X/PCI Express busses. Say Y
421 here unless you are using a simulator without PCI support.
423 config PCI_DOMAINS
424 bool
425 default PCI
427 config XEN_PCIDEV_FRONTEND
428 bool "Xen PCI Frontend"
429 depends on PCI && XEN
430 default y
431 help
432 The PCI device frontend driver allows the kernel to import arbitrary
433 PCI devices from a PCI backend to support PCI driver domains.
435 config XEN_PCIDEV_FE_DEBUG
436 bool "Xen PCI Frontend Debugging"
437 depends on XEN_PCIDEV_FRONTEND
438 default n
439 help
440 Enables some debug statements within the PCI Frontend.
442 source "drivers/pci/Kconfig"
444 source "drivers/pci/hotplug/Kconfig"
446 source "drivers/pcmcia/Kconfig"
448 endmenu
450 endif
452 source "net/Kconfig"
454 source "drivers/Kconfig"
456 source "fs/Kconfig"
458 source "lib/Kconfig"
460 #
461 # Use the generic interrupt handling code in kernel/irq/:
462 #
463 config GENERIC_HARDIRQS
464 bool
465 default y
467 config GENERIC_IRQ_PROBE
468 bool
469 default y
471 config GENERIC_PENDING_IRQ
472 bool
473 depends on GENERIC_HARDIRQS && SMP
474 default y
476 source "arch/ia64/hp/sim/Kconfig"
478 menu "Instrumentation Support"
479 depends on EXPERIMENTAL
481 source "arch/ia64/oprofile/Kconfig"
483 config KPROBES
484 bool "Kprobes (EXPERIMENTAL)"
485 depends on EXPERIMENTAL && MODULES
486 help
487 Kprobes allows you to trap at almost any kernel address and
488 execute a callback function. register_kprobe() establishes
489 a probepoint and specifies the callback. Kprobes is useful
490 for kernel debugging, non-intrusive instrumentation and testing.
491 If in doubt, say "N".
492 endmenu
494 source "arch/ia64/Kconfig.debug"
496 source "security/Kconfig"
498 source "crypto/Kconfig"
500 #
501 # override default values of drivers/xen/Kconfig
502 #
503 if XEN
504 config XEN_UTIL
505 default n
507 config HAVE_ARCH_ALLOC_SKB
508 default y
510 config HAVE_ARCH_DEV_ALLOC_SKB
511 default y
513 config XEN_BALLOON
514 default y
516 config XEN_SKBUFF
517 default y
519 config XEN_NETDEV_BACKEND
520 default y
522 config XEN_NETDEV_FRONTEND
523 default y
525 config XEN_DEVMEM
526 default n
528 config XEN_REBOOT
529 default y
531 config XEN_SMPBOOT
532 default n
533 endif
535 source "drivers/xen/Kconfig"