net: ipv6 bind to device issue
[linux-2.6-block.git] / mm / Kconfig
CommitLineData
e1785e85
DH
1config SELECT_MEMORY_MODEL
2 def_bool y
3 depends on EXPERIMENTAL || ARCH_SELECT_MEMORY_MODEL
4
3a9da765
DH
5choice
6 prompt "Memory model"
e1785e85
DH
7 depends on SELECT_MEMORY_MODEL
8 default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
d41dee36 9 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
e1785e85 10 default FLATMEM_MANUAL
3a9da765 11
e1785e85 12config FLATMEM_MANUAL
3a9da765 13 bool "Flat Memory"
c898ec16 14 depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
3a9da765
DH
15 help
16 This option allows you to change some of the ways that
17 Linux manages its memory internally. Most users will
18 only have one option here: FLATMEM. This is normal
19 and a correct option.
20
d41dee36
AW
21 Some users of more advanced features like NUMA and
22 memory hotplug may have different options here.
23 DISCONTIGMEM is an more mature, better tested system,
24 but is incompatible with memory hotplug and may suffer
25 decreased performance over SPARSEMEM. If unsure between
26 "Sparse Memory" and "Discontiguous Memory", choose
27 "Discontiguous Memory".
28
29 If unsure, choose this option (Flat Memory) over any other.
3a9da765 30
e1785e85 31config DISCONTIGMEM_MANUAL
f3519f91 32 bool "Discontiguous Memory"
3a9da765
DH
33 depends on ARCH_DISCONTIGMEM_ENABLE
34 help
785dcd44
DH
35 This option provides enhanced support for discontiguous
36 memory systems, over FLATMEM. These systems have holes
37 in their physical address spaces, and this option provides
38 more efficient handling of these holes. However, the vast
39 majority of hardware has quite flat address spaces, and
ad3d0a38 40 can have degraded performance from the extra overhead that
785dcd44
DH
41 this option imposes.
42
43 Many NUMA configurations will have this as the only option.
44
3a9da765
DH
45 If unsure, choose "Flat Memory" over this option.
46
d41dee36
AW
47config SPARSEMEM_MANUAL
48 bool "Sparse Memory"
49 depends on ARCH_SPARSEMEM_ENABLE
50 help
51 This will be the only option for some systems, including
52 memory hotplug systems. This is normal.
53
54 For many other systems, this will be an alternative to
f3519f91 55 "Discontiguous Memory". This option provides some potential
d41dee36
AW
56 performance benefits, along with decreased code complexity,
57 but it is newer, and more experimental.
58
59 If unsure, choose "Discontiguous Memory" or "Flat Memory"
60 over this option.
61
3a9da765
DH
62endchoice
63
e1785e85
DH
64config DISCONTIGMEM
65 def_bool y
66 depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL
67
d41dee36
AW
68config SPARSEMEM
69 def_bool y
1a83e175 70 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
d41dee36 71
e1785e85
DH
72config FLATMEM
73 def_bool y
d41dee36
AW
74 depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
75
76config FLAT_NODE_MEM_MAP
77 def_bool y
78 depends on !SPARSEMEM
e1785e85 79
93b7504e
DH
80#
81# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
82# to represent different areas of memory. This variable allows
83# those dependencies to exist individually.
84#
85config NEED_MULTIPLE_NODES
86 def_bool y
87 depends on DISCONTIGMEM || NUMA
af705362
AW
88
89config HAVE_MEMORY_PRESENT
90 def_bool y
d41dee36 91 depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
802f192e 92
3e347261
BP
93#
94# SPARSEMEM_EXTREME (which is the default) does some bootmem
84eb8d06 95# allocations when memory_present() is called. If this cannot
3e347261
BP
96# be done on your architecture, select this option. However,
97# statically allocating the mem_section[] array can potentially
98# consume vast quantities of .bss, so be careful.
99#
100# This option will also potentially produce smaller runtime code
101# with gcc 3.4 and later.
102#
103config SPARSEMEM_STATIC
9ba16087 104 bool
3e347261 105
802f192e 106#
44c09201 107# Architecture platforms which require a two level mem_section in SPARSEMEM
802f192e
BP
108# must select this option. This is usually for architecture platforms with
109# an extremely sparse physical address space.
110#
3e347261
BP
111config SPARSEMEM_EXTREME
112 def_bool y
113 depends on SPARSEMEM && !SPARSEMEM_STATIC
4c21e2f2 114
29c71111 115config SPARSEMEM_VMEMMAP_ENABLE
9ba16087 116 bool
29c71111 117
9bdac914
YL
118config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
119 def_bool y
120 depends on SPARSEMEM && X86_64
121
29c71111 122config SPARSEMEM_VMEMMAP
a5ee6daa
GL
123 bool "Sparse Memory virtual memmap"
124 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
125 default y
126 help
127 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
128 pfn_to_page and page_to_pfn operations. This is the most
129 efficient option when sufficient kernel resources are available.
29c71111 130
3947be19
DH
131# eventually, we can have this option just 'select SPARSEMEM'
132config MEMORY_HOTPLUG
133 bool "Allow for memory hot-add"
ec69acbb 134 depends on SPARSEMEM || X86_64_ACPI_NUMA
6ad696d2 135 depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG
ed84a07a 136 depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
3947be19 137
ec69acbb
KM
138config MEMORY_HOTPLUG_SPARSE
139 def_bool y
140 depends on SPARSEMEM && MEMORY_HOTPLUG
141
0c0e6195
KH
142config MEMORY_HOTREMOVE
143 bool "Allow for memory hot remove"
144 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
145 depends on MIGRATION
146
e20b8cca
CL
147#
148# If we have space for more page flags then we can enable additional
149# optimizations and functionality.
150#
151# Regular Sparsemem takes page flag bits for the sectionid if it does not
152# use a virtual memmap. Disable extended page flags for 32 bit platforms
153# that require the use of a sectionid in the page flags.
154#
155config PAGEFLAGS_EXTENDED
156 def_bool y
a269cca9 157 depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
e20b8cca 158
4c21e2f2
HD
159# Heavily threaded applications may benefit from splitting the mm-wide
160# page_table_lock, so that faults on different parts of the user address
161# space can be handled with less contention: split it at this NR_CPUS.
162# Default to 4 for wider testing, though 8 might be more appropriate.
163# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
7b6ac9df 164# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
a70caa8b 165# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
4c21e2f2
HD
166#
167config SPLIT_PTLOCK_CPUS
168 int
a70caa8b
HD
169 default "999999" if ARM && !CPU_CACHE_VIPT
170 default "999999" if PARISC && !PA20
171 default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
4c21e2f2 172 default "4"
7cbe34cf
CL
173
174#
175# support for page migration
176#
177config MIGRATION
b20a3503 178 bool "Page migration"
6c5240ae 179 def_bool y
83d1674a 180 depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE
b20a3503
CL
181 help
182 Allows the migration of the physical location of pages of processes
183 while the virtual addresses are not changed. This is useful for
184 example on NUMA systems to put pages nearer to the processors accessing
185 the page.
6550e07f 186
600715dc
JF
187config PHYS_ADDR_T_64BIT
188 def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
189
4b51d669
CL
190config ZONE_DMA_FLAG
191 int
192 default "0" if !ZONE_DMA
193 default "1"
194
2a7326b5
CL
195config BOUNCE
196 def_bool y
197 depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
198
6225e937
CL
199config NR_QUICK
200 int
201 depends on QUICKLIST
0176bd3d 202 default "2" if AVR32
6225e937 203 default "1"
f057eac0
SR
204
205config VIRT_TO_BUS
206 def_bool y
207 depends on !ARCH_NO_VIRT_TO_BUS
cddb8a5c
AA
208
209config MMU_NOTIFIER
210 bool
fc4d5c29 211
f8af4da3
HD
212config KSM
213 bool "Enable KSM for page merging"
214 depends on MMU
215 help
216 Enable Kernel Samepage Merging: KSM periodically scans those areas
217 of an application's address space that an app has advised may be
218 mergeable. When it finds pages of identical content, it replaces
d0f209f6 219 the many instances by a single page with that content, so
f8af4da3
HD
220 saving memory until one or another app needs to modify the content.
221 Recommended for use with KVM, or with other duplicative applications.
c73602ad
HD
222 See Documentation/vm/ksm.txt for more information: KSM is inactive
223 until a program has madvised that an area is MADV_MERGEABLE, and
224 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
f8af4da3 225
e0a94c2a
CL
226config DEFAULT_MMAP_MIN_ADDR
227 int "Low address space to protect from user allocation"
6e141546 228 depends on MMU
e0a94c2a
CL
229 default 4096
230 help
231 This is the portion of low virtual memory which should be protected
232 from userspace allocation. Keeping a user from writing to low pages
233 can help reduce the impact of kernel NULL pointer bugs.
234
235 For most ia64, ppc64 and x86 users with lots of address space
236 a value of 65536 is reasonable and should cause no problems.
237 On arm and other archs it should not be higher than 32768.
788084ab
EP
238 Programs which use vm86 functionality or have some need to map
239 this low address space will need CAP_SYS_RAWIO or disable this
240 protection by setting the value to 0.
e0a94c2a
CL
241
242 This value can be changed after boot using the
243 /proc/sys/vm/mmap_min_addr tunable.
244
d949f36f
LT
245config ARCH_SUPPORTS_MEMORY_FAILURE
246 bool
e0a94c2a 247
6a46079c
AK
248config MEMORY_FAILURE
249 depends on MMU
d949f36f 250 depends on ARCH_SUPPORTS_MEMORY_FAILURE
6a46079c
AK
251 bool "Enable recovery from hardware memory errors"
252 help
253 Enables code to recover from some memory failures on systems
254 with MCA recovery. This allows a system to continue running
255 even when some of its memory has uncorrected errors. This requires
256 special hardware support and typically ECC memory.
257
cae681fc 258config HWPOISON_INJECT
413f9efb 259 tristate "HWPoison pages injector"
27df5068 260 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
478c5ffc 261 select PROC_PAGE_MONITOR
cae681fc 262
fc4d5c29
DH
263config NOMMU_INITIAL_TRIM_EXCESS
264 int "Turn on mmap() excess space trimming before booting"
265 depends on !MMU
266 default 1
267 help
268 The NOMMU mmap() frequently needs to allocate large contiguous chunks
269 of memory on which to store mappings, but it can only ask the system
270 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
271 more than it requires. To deal with this, mmap() is able to trim off
272 the excess and return it to the allocator.
273
274 If trimming is enabled, the excess is trimmed off and returned to the
275 system allocator, which can cause extra fragmentation, particularly
276 if there are a lot of transient processes.
277
278 If trimming is disabled, the excess is kept, but not used, which for
279 long-term mappings means that the space is wasted.
280
281 Trimming can be dynamically controlled through a sysctl option
282 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
283 excess pages there must be before trimming should occur, or zero if
284 no trimming is to occur.
285
286 This option specifies the initial value of this option. The default
287 of 1 says that all excess pages should be trimmed.
288
289 See Documentation/nommu-mmap.txt for more information.