blob: 8028dcc6615c6bbd533adf060ea3d9db36b9a48c [file] [log] [blame]
Dave Hansene1785e82005-06-23 00:07:49 -07001config SELECT_MEMORY_MODEL
2 def_bool y
Kees Cooka8826ee2013-01-16 18:54:17 -08003 depends on ARCH_SELECT_MEMORY_MODEL
Dave Hansene1785e82005-06-23 00:07:49 -07004
Dave Hansen3a9da762005-06-23 00:07:42 -07005choice
6 prompt "Memory model"
Dave Hansene1785e82005-06-23 00:07:49 -07007 depends on SELECT_MEMORY_MODEL
8 default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
Andy Whitcroftd41dee32005-06-23 00:07:54 -07009 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
Dave Hansene1785e82005-06-23 00:07:49 -070010 default FLATMEM_MANUAL
Dave Hansen3a9da762005-06-23 00:07:42 -070011
Dave Hansene1785e82005-06-23 00:07:49 -070012config FLATMEM_MANUAL
Dave Hansen3a9da762005-06-23 00:07:42 -070013 bool "Flat Memory"
Anton Blanchardc898ec12006-01-06 00:12:07 -080014 depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
Dave Hansen3a9da762005-06-23 00:07:42 -070015 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
Andy Whitcroftd41dee32005-06-23 00:07:54 -070021 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.
Dave Hansen3a9da762005-06-23 00:07:42 -070030
Dave Hansene1785e82005-06-23 00:07:49 -070031config DISCONTIGMEM_MANUAL
Dave Hansenf3519f92005-09-16 19:27:54 -070032 bool "Discontiguous Memory"
Dave Hansen3a9da762005-06-23 00:07:42 -070033 depends on ARCH_DISCONTIGMEM_ENABLE
34 help
Dave Hansen785dcd42005-06-23 00:07:50 -070035 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
Philipp Marekad3d0a32007-10-20 02:46:58 +020040 can have degraded performance from the extra overhead that
Dave Hansen785dcd42005-06-23 00:07:50 -070041 this option imposes.
42
43 Many NUMA configurations will have this as the only option.
44
Dave Hansen3a9da762005-06-23 00:07:42 -070045 If unsure, choose "Flat Memory" over this option.
46
Andy Whitcroftd41dee32005-06-23 00:07:54 -070047config 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
Dave Hansenf3519f92005-09-16 19:27:54 -070055 "Discontiguous Memory". This option provides some potential
Andy Whitcroftd41dee32005-06-23 00:07:54 -070056 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
Dave Hansen3a9da762005-06-23 00:07:42 -070062endchoice
63
Dave Hansene1785e82005-06-23 00:07:49 -070064config DISCONTIGMEM
65 def_bool y
66 depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL
67
Andy Whitcroftd41dee32005-06-23 00:07:54 -070068config SPARSEMEM
69 def_bool y
Russell King1a83e172009-10-26 16:50:12 -070070 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
Andy Whitcroftd41dee32005-06-23 00:07:54 -070071
Dave Hansene1785e82005-06-23 00:07:49 -070072config FLATMEM
73 def_bool y
Andy Whitcroftd41dee32005-06-23 00:07:54 -070074 depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
75
76config FLAT_NODE_MEM_MAP
77 def_bool y
78 depends on !SPARSEMEM
Dave Hansene1785e82005-06-23 00:07:49 -070079
Dave Hansen93b75042005-06-23 00:07:47 -070080#
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
Andy Whitcroftaf705362005-06-23 00:07:53 -070088
89config HAVE_MEMORY_PRESENT
90 def_bool y
Andy Whitcroftd41dee32005-06-23 00:07:54 -070091 depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
Bob Picco802f1922005-09-03 15:54:26 -070092
93#
Bob Picco3e347262005-09-03 15:54:28 -070094# SPARSEMEM_EXTREME (which is the default) does some bootmem
Matt LaPlante84eb8d02006-10-03 22:53:09 +020095# allocations when memory_present() is called. If this cannot
Bob Picco3e347262005-09-03 15:54:28 -070096# 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
Jan Beulich9ba16082008-10-15 22:01:38 -0700104 bool
Bob Picco3e347262005-09-03 15:54:28 -0700105
106#
Matt LaPlante44c09202006-10-03 22:34:14 +0200107# Architecture platforms which require a two level mem_section in SPARSEMEM
Bob Picco802f1922005-09-03 15:54:26 -0700108# must select this option. This is usually for architecture platforms with
109# an extremely sparse physical address space.
110#
Bob Picco3e347262005-09-03 15:54:28 -0700111config SPARSEMEM_EXTREME
112 def_bool y
113 depends on SPARSEMEM && !SPARSEMEM_STATIC
Hugh Dickins4c21e2f2005-10-29 18:16:40 -0700114
Andy Whitcroft29c71112007-10-16 01:24:14 -0700115config SPARSEMEM_VMEMMAP_ENABLE
Jan Beulich9ba16082008-10-15 22:01:38 -0700116 bool
Andy Whitcroft29c71112007-10-16 01:24:14 -0700117
Yinghai Lu9bdac912010-02-10 01:20:22 -0800118config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
119 def_bool y
120 depends on SPARSEMEM && X86_64
121
Andy Whitcroft29c71112007-10-16 01:24:14 -0700122config SPARSEMEM_VMEMMAP
Geoff Levanda5ee6da2007-12-17 16:19:53 -0800123 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.
Andy Whitcroft29c71112007-10-16 01:24:14 -0700130
Yinghai Lu95f72d12010-07-12 14:36:09 +1000131config HAVE_MEMBLOCK
132 boolean
133
Tejun Heo7c0caeb2011-07-14 11:43:42 +0200134config HAVE_MEMBLOCK_NODE_MAP
135 boolean
136
Tejun Heoc378ddd2011-07-14 11:46:03 +0200137config ARCH_DISCARD_MEMBLOCK
138 boolean
139
Sam Ravnborg66616722011-10-31 17:08:20 -0700140config NO_BOOTMEM
141 boolean
142
Minchan Kimee6f5092012-07-31 16:43:50 -0700143config MEMORY_ISOLATION
144 boolean
145
Lai Jiangshan20b2f522012-12-12 13:52:00 -0800146config MOVABLE_NODE
147 boolean "Enable to assign a node which has only movable memory"
148 depends on HAVE_MEMBLOCK
149 depends on NO_BOOTMEM
150 depends on X86_64
151 depends on NUMA
Tang Chenc2974052012-12-18 14:21:33 -0800152 default n
153 help
154 Allow a node to have only movable memory. Pages used by the kernel,
155 such as direct mapping pages cannot be migrated. So the corresponding
156 memory device cannot be hotplugged. This option allows users to
157 online all the memory of a node as movable memory so that the whole
158 node can be hotplugged. Users who don't use the memory hotplug
159 feature are fine with this option on since they don't online memory
160 as movable.
161
162 Say Y here if you want to hotplug a whole node.
163 Say N here if you want kernel to use memory on all nodes evenly.
Lai Jiangshan20b2f522012-12-12 13:52:00 -0800164
Yasuaki Ishimatsu46723bf2013-02-22 16:33:00 -0800165#
166# Only be set on architectures that have completely implemented memory hotplug
167# feature. If you are not sure, don't touch it.
168#
169config HAVE_BOOTMEM_INFO_NODE
170 def_bool n
171
Dave Hansen3947be12005-10-29 18:16:54 -0700172# eventually, we can have this option just 'select SPARSEMEM'
173config MEMORY_HOTPLUG
174 bool "Allow for memory hot-add"
Keith Manntheyec69acb2006-09-30 23:27:05 -0700175 depends on SPARSEMEM || X86_64_ACPI_NUMA
Stephen Rothwell40b31362013-05-21 13:49:35 +1000176 depends on ARCH_ENABLE_MEMORY_HOTPLUG
Kumar Galaed84a072009-10-16 07:21:36 +0000177 depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
Dave Hansen3947be12005-10-29 18:16:54 -0700178
Keith Manntheyec69acb2006-09-30 23:27:05 -0700179config MEMORY_HOTPLUG_SPARSE
180 def_bool y
181 depends on SPARSEMEM && MEMORY_HOTPLUG
182
KAMEZAWA Hiroyuki0c0e6192007-10-16 01:26:12 -0700183config MEMORY_HOTREMOVE
184 bool "Allow for memory hot remove"
Yasuaki Ishimatsu46723bf2013-02-22 16:33:00 -0800185 select MEMORY_ISOLATION
186 select HAVE_BOOTMEM_INFO_NODE if X86_64
KAMEZAWA Hiroyuki0c0e6192007-10-16 01:26:12 -0700187 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
188 depends on MIGRATION
189
Christoph Lametere20b8cc2008-04-28 02:12:55 -0700190#
191# If we have space for more page flags then we can enable additional
192# optimizations and functionality.
193#
194# Regular Sparsemem takes page flag bits for the sectionid if it does not
195# use a virtual memmap. Disable extended page flags for 32 bit platforms
196# that require the use of a sectionid in the page flags.
197#
198config PAGEFLAGS_EXTENDED
199 def_bool y
H. Peter Anvina269cca2009-08-31 11:17:44 -0700200 depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
Christoph Lametere20b8cc2008-04-28 02:12:55 -0700201
Hugh Dickins4c21e2f2005-10-29 18:16:40 -0700202# Heavily threaded applications may benefit from splitting the mm-wide
203# page_table_lock, so that faults on different parts of the user address
204# space can be handled with less contention: split it at this NR_CPUS.
205# Default to 4 for wider testing, though 8 might be more appropriate.
206# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
Hugh Dickins7b6ac9d2005-11-23 13:37:37 -0800207# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
Hugh Dickinsa70caa82009-12-14 17:59:02 -0800208# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
Hugh Dickins4c21e2f2005-10-29 18:16:40 -0700209#
210config SPLIT_PTLOCK_CPUS
211 int
Hugh Dickinsa70caa82009-12-14 17:59:02 -0800212 default "999999" if ARM && !CPU_CACHE_VIPT
213 default "999999" if PARISC && !PA20
214 default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
Hugh Dickins4c21e2f2005-10-29 18:16:40 -0700215 default "4"
Christoph Lameter7cbe34c2006-01-08 01:00:49 -0800216
217#
Rafael Aquini18468d92012-12-11 16:02:38 -0800218# support for memory balloon compaction
219config BALLOON_COMPACTION
220 bool "Allow for balloon memory compaction/migration"
221 def_bool y
222 depends on COMPACTION && VIRTIO_BALLOON
223 help
224 Memory fragmentation introduced by ballooning might reduce
225 significantly the number of 2MB contiguous memory blocks that can be
226 used within a guest, thus imposing performance penalties associated
227 with the reduced number of transparent huge pages that could be used
228 by the guest workload. Allowing the compaction & migration for memory
229 pages enlisted as being part of memory balloon devices avoids the
230 scenario aforementioned and helps improving memory defragmentation.
231
232#
Mel Gormane9e96b32010-05-24 14:32:21 -0700233# support for memory compaction
234config COMPACTION
235 bool "Allow for memory compaction"
Rik van Riel05106e62012-10-08 16:33:03 -0700236 def_bool y
Mel Gormane9e96b32010-05-24 14:32:21 -0700237 select MIGRATION
Andrea Arcangeli33a93872011-01-25 15:07:25 -0800238 depends on MMU
Mel Gormane9e96b32010-05-24 14:32:21 -0700239 help
240 Allows the compaction of memory for the allocation of huge pages.
241
242#
Christoph Lameter7cbe34c2006-01-08 01:00:49 -0800243# support for page migration
244#
245config MIGRATION
Christoph Lameterb20a3502006-03-22 00:09:12 -0800246 bool "Page migration"
Christoph Lameter6c5240a2006-06-23 02:03:37 -0700247 def_bool y
Michal Nazarewicz47118af2011-12-29 13:09:50 +0100248 depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA
Christoph Lameterb20a3502006-03-22 00:09:12 -0800249 help
250 Allows the migration of the physical location of pages of processes
Mel Gormane9e96b32010-05-24 14:32:21 -0700251 while the virtual addresses are not changed. This is useful in
252 two situations. The first is on NUMA systems to put pages nearer
253 to the processors accessing. The second is when allocating huge
254 pages as migration can relocate pages to satisfy a huge page
255 allocation instead of reclaiming.
Greg Kroah-Hartman6550e072006-06-12 17:11:31 -0700256
Jeremy Fitzhardinge600715d2008-09-11 01:31:45 -0700257config PHYS_ADDR_T_64BIT
258 def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
259
Christoph Lameter4b51d662007-02-10 01:43:10 -0800260config ZONE_DMA_FLAG
261 int
262 default "0" if !ZONE_DMA
263 default "1"
264
Christoph Lameter2a7326b2007-07-17 04:03:37 -0700265config BOUNCE
Vinayak Menon9ca24e22013-04-29 15:08:55 -0700266 bool "Enable bounce buffers"
267 default y
Christoph Lameter2a7326b2007-07-17 04:03:37 -0700268 depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
Vinayak Menon9ca24e22013-04-29 15:08:55 -0700269 help
270 Enable bounce buffers for devices that cannot access
271 the full range of memory available to the CPU. Enabled
272 by default when ZONE_DMA or HIGHMEM is selected, but you
273 may say n to override this.
Christoph Lameter2a7326b2007-07-17 04:03:37 -0700274
Darrick J. Wongffecfd12013-02-21 16:42:55 -0800275# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
276# have more than 4GB of memory, but we don't currently use the IOTLB to present
277# a 32-bit address to OHCI. So we need to use a bounce pool instead.
278#
279# We also use the bounce pool to provide stable page writes for jbd. jbd
280# initiates buffer writeback without locking the page or setting PG_writeback,
281# and fixing that behavior (a second time; jbd2 doesn't have this problem) is
282# a major rework effort. Instead, use the bounce buffer to snapshot pages
283# (until jbd goes away). The only jbd user is ext3.
284config NEED_BOUNCE_POOL
285 bool
286 default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD)
287
Christoph Lameter6225e932007-05-06 14:49:50 -0700288config NR_QUICK
289 int
290 depends on QUICKLIST
Paul Mundt0176bd32010-01-05 12:35:00 +0900291 default "2" if AVR32
Christoph Lameter6225e932007-05-06 14:49:50 -0700292 default "1"
Stephen Rothwellf057eac2007-07-15 23:40:05 -0700293
294config VIRT_TO_BUS
Stephen Rothwell4febd952013-03-07 15:48:16 +1100295 bool
296 help
297 An architecture should select this if it implements the
298 deprecated interface virt_to_bus(). All new architectures
299 should probably not select this.
300
Andrea Arcangelicddb8a52008-07-28 15:46:29 -0700301
302config MMU_NOTIFIER
303 bool
David Howellsfc4d5c22009-05-06 16:03:05 -0700304
Hugh Dickinsf8af4da2009-09-21 17:01:57 -0700305config KSM
306 bool "Enable KSM for page merging"
307 depends on MMU
308 help
309 Enable Kernel Samepage Merging: KSM periodically scans those areas
310 of an application's address space that an app has advised may be
311 mergeable. When it finds pages of identical content, it replaces
Hugh Dickinsd0f209f2009-12-14 17:59:34 -0800312 the many instances by a single page with that content, so
Hugh Dickinsf8af4da2009-09-21 17:01:57 -0700313 saving memory until one or another app needs to modify the content.
314 Recommended for use with KVM, or with other duplicative applications.
Hugh Dickinsc73602a2009-10-07 16:32:22 -0700315 See Documentation/vm/ksm.txt for more information: KSM is inactive
316 until a program has madvised that an area is MADV_MERGEABLE, and
317 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
Hugh Dickinsf8af4da2009-09-21 17:01:57 -0700318
Christoph Lametere0a94c22009-06-03 16:04:31 -0400319config DEFAULT_MMAP_MIN_ADDR
320 int "Low address space to protect from user allocation"
David Howells6e141542009-12-15 19:27:45 +0000321 depends on MMU
Christoph Lametere0a94c22009-06-03 16:04:31 -0400322 default 4096
323 help
324 This is the portion of low virtual memory which should be protected
325 from userspace allocation. Keeping a user from writing to low pages
326 can help reduce the impact of kernel NULL pointer bugs.
327
328 For most ia64, ppc64 and x86 users with lots of address space
329 a value of 65536 is reasonable and should cause no problems.
330 On arm and other archs it should not be higher than 32768.
Eric Paris788084a2009-07-31 12:54:11 -0400331 Programs which use vm86 functionality or have some need to map
332 this low address space will need CAP_SYS_RAWIO or disable this
333 protection by setting the value to 0.
Christoph Lametere0a94c22009-06-03 16:04:31 -0400334
335 This value can be changed after boot using the
336 /proc/sys/vm/mmap_min_addr tunable.
337
Linus Torvaldsd949f362009-09-26 09:35:07 -0700338config ARCH_SUPPORTS_MEMORY_FAILURE
339 bool
Christoph Lametere0a94c22009-06-03 16:04:31 -0400340
Andi Kleen6a460792009-09-16 11:50:15 +0200341config MEMORY_FAILURE
342 depends on MMU
Linus Torvaldsd949f362009-09-26 09:35:07 -0700343 depends on ARCH_SUPPORTS_MEMORY_FAILURE
Andi Kleen6a460792009-09-16 11:50:15 +0200344 bool "Enable recovery from hardware memory errors"
Minchan Kimee6f5092012-07-31 16:43:50 -0700345 select MEMORY_ISOLATION
Andi Kleen6a460792009-09-16 11:50:15 +0200346 help
347 Enables code to recover from some memory failures on systems
348 with MCA recovery. This allows a system to continue running
349 even when some of its memory has uncorrected errors. This requires
350 special hardware support and typically ECC memory.
351
Andi Kleencae681f2009-09-16 11:50:17 +0200352config HWPOISON_INJECT
Andi Kleen413f9ef2009-12-16 12:20:00 +0100353 tristate "HWPoison pages injector"
Andi Kleen27df5062009-12-21 19:56:42 +0100354 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
Wu Fengguang478c5ff2009-12-16 12:19:59 +0100355 select PROC_PAGE_MONITOR
Andi Kleencae681f2009-09-16 11:50:17 +0200356
David Howellsfc4d5c22009-05-06 16:03:05 -0700357config NOMMU_INITIAL_TRIM_EXCESS
358 int "Turn on mmap() excess space trimming before booting"
359 depends on !MMU
360 default 1
361 help
362 The NOMMU mmap() frequently needs to allocate large contiguous chunks
363 of memory on which to store mappings, but it can only ask the system
364 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
365 more than it requires. To deal with this, mmap() is able to trim off
366 the excess and return it to the allocator.
367
368 If trimming is enabled, the excess is trimmed off and returned to the
369 system allocator, which can cause extra fragmentation, particularly
370 if there are a lot of transient processes.
371
372 If trimming is disabled, the excess is kept, but not used, which for
373 long-term mappings means that the space is wasted.
374
375 Trimming can be dynamically controlled through a sysctl option
376 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
377 excess pages there must be before trimming should occur, or zero if
378 no trimming is to occur.
379
380 This option specifies the initial value of this option. The default
381 of 1 says that all excess pages should be trimmed.
382
383 See Documentation/nommu-mmap.txt for more information.
Tejun Heobbddff02010-09-03 18:22:48 +0200384
Andrea Arcangeli4c76d9d2011-01-13 15:46:39 -0800385config TRANSPARENT_HUGEPAGE
Andrea Arcangeli13ece882011-01-13 15:47:07 -0800386 bool "Transparent Hugepage Support"
Gerald Schaefer15626062012-10-08 16:30:04 -0700387 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
Andrea Arcangeli5d689242011-01-13 15:47:07 -0800388 select COMPACTION
Andrea Arcangeli4c76d9d2011-01-13 15:46:39 -0800389 help
390 Transparent Hugepages allows the kernel to use huge pages and
391 huge tlb transparently to the applications whenever possible.
392 This feature can improve computing performance to certain
393 applications by speeding up page faults during memory
394 allocation, by reducing the number of tlb misses and by speeding
395 up the pagetable walking.
396
397 If memory constrained on embedded, you may want to say N.
398
Andrea Arcangeli13ece882011-01-13 15:47:07 -0800399choice
400 prompt "Transparent Hugepage Support sysfs defaults"
401 depends on TRANSPARENT_HUGEPAGE
402 default TRANSPARENT_HUGEPAGE_ALWAYS
403 help
404 Selects the sysfs defaults for Transparent Hugepage Support.
405
406 config TRANSPARENT_HUGEPAGE_ALWAYS
407 bool "always"
408 help
409 Enabling Transparent Hugepage always, can increase the
410 memory footprint of applications without a guaranteed
411 benefit but it will work automatically for all applications.
412
413 config TRANSPARENT_HUGEPAGE_MADVISE
414 bool "madvise"
415 help
416 Enabling Transparent Hugepage madvise, will only provide a
417 performance improvement benefit to the applications using
418 madvise(MADV_HUGEPAGE) but it won't risk to increase the
419 memory footprint of applications without a guaranteed
420 benefit.
421endchoice
422
Christopher Yeoh5febcbe2012-05-29 15:06:27 -0700423config CROSS_MEMORY_ATTACH
424 bool "Cross Memory Support"
425 depends on MMU
426 default y
427 help
428 Enabling this option adds the system calls process_vm_readv and
429 process_vm_writev which allow a process with the correct privileges
430 to directly read from or write to to another process's address space.
431 See the man page for more details.
432
Tejun Heobbddff02010-09-03 18:22:48 +0200433#
434# UP and nommu archs use km based percpu allocator
435#
436config NEED_PER_CPU_KM
437 depends on !SMP
438 bool
439 default y
Dan Magenheimer077b1f82011-05-26 10:01:36 -0600440
441config CLEANCACHE
442 bool "Enable cleancache driver to cache clean pages if tmem is present"
443 default n
444 help
445 Cleancache can be thought of as a page-granularity victim cache
446 for clean pages that the kernel's pageframe replacement algorithm
447 (PFRA) would like to keep around, but can't since there isn't enough
448 memory. So when the PFRA "evicts" a page, it first attempts to use
Michael Witten140a1ef2011-06-10 03:57:26 +0000449 cleancache code to put the data contained in that page into
Dan Magenheimer077b1f82011-05-26 10:01:36 -0600450 "transcendent memory", memory that is not directly accessible or
451 addressable by the kernel and is of unknown and possibly
452 time-varying size. And when a cleancache-enabled
453 filesystem wishes to access a page in a file on disk, it first
454 checks cleancache to see if it already contains it; if it does,
455 the page is copied into the kernel and a disk access is avoided.
456 When a transcendent memory driver is available (such as zcache or
457 Xen transcendent memory), a significant I/O reduction
458 may be achieved. When none is available, all cleancache calls
459 are reduced to a single pointer-compare-against-NULL resulting
460 in a negligible performance hit.
461
462 If unsure, say Y to enable cleancache
Dan Magenheimer27c6aec2012-04-09 17:10:34 -0600463
464config FRONTSWAP
465 bool "Enable frontswap to cache swap pages if tmem is present"
466 depends on SWAP
467 default n
468 help
469 Frontswap is so named because it can be thought of as the opposite
470 of a "backing" store for a swap device. The data is stored into
471 "transcendent memory", memory that is not directly accessible or
472 addressable by the kernel and is of unknown and possibly
473 time-varying size. When space in transcendent memory is available,
474 a significant swap I/O reduction may be achieved. When none is
475 available, all frontswap calls are reduced to a single pointer-
476 compare-against-NULL resulting in a negligible performance hit
477 and swap data is stored as normal on the matching swap device.
478
479 If unsure, say Y to enable frontswap.
Pavel Emelyanov0f8975e2013-07-03 15:01:20 -0700480
Seth Jennings4e2e2772013-07-10 16:04:55 -0700481config ZBUD
482 tristate
483 default n
484 help
485 A special purpose allocator for storing compressed pages.
486 It is designed to store up to two compressed pages per physical
487 page. While this design limits storage density, it has simple and
488 deterministic reclaim properties that make it preferable to a higher
489 density approach when reclaim will be used.
490
Seth Jennings2b281112013-07-10 16:05:03 -0700491config ZSWAP
492 bool "Compressed cache for swap pages (EXPERIMENTAL)"
493 depends on FRONTSWAP && CRYPTO=y
494 select CRYPTO_LZO
495 select ZBUD
496 default n
497 help
498 A lightweight compressed cache for swap pages. It takes
499 pages that are in the process of being swapped out and attempts to
500 compress them into a dynamically allocated RAM-based memory pool.
501 This can result in a significant I/O reduction on swap device and,
502 in the case where decompressing from RAM is faster that swap device
503 reads, can also improve workload performance.
504
505 This is marked experimental because it is a new feature (as of
506 v3.11) that interacts heavily with memory reclaim. While these
507 interactions don't cause any known issues on simple memory setups,
508 they have not be fully explored on the large set of potential
509 configurations and workloads that exist.
510
Pavel Emelyanov0f8975e2013-07-03 15:01:20 -0700511config MEM_SOFT_DIRTY
512 bool "Track memory changes"
513 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
514 select PROC_PAGE_MONITOR
515 help
516 This option enables memory changes tracking by introducing a
517 soft-dirty bit on pte-s. This bit it set when someone writes
518 into a page just as regular dirty bit, but unlike the latter
519 it can be cleared by hands.
520
521 See Documentation/vm/soft-dirty.txt for more details.