xref: /linux/mm/Kconfig (revision 2ba9268dd603d23e17643437b2246acb6844953b)
1config SELECT_MEMORY_MODEL
2	def_bool y
3	depends on ARCH_SELECT_MEMORY_MODEL
4
5choice
6	prompt "Memory model"
7	depends on SELECT_MEMORY_MODEL
8	default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
9	default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
10	default FLATMEM_MANUAL
11
12config FLATMEM_MANUAL
13	bool "Flat Memory"
14	depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
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
21	  Some users of more advanced features like NUMA and
22	  memory hotplug may have different options here.
23	  DISCONTIGMEM is a 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.
30
31config DISCONTIGMEM_MANUAL
32	bool "Discontiguous Memory"
33	depends on ARCH_DISCONTIGMEM_ENABLE
34	help
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
40	  can have degraded performance from the extra overhead that
41	  this option imposes.
42
43	  Many NUMA configurations will have this as the only option.
44
45	  If unsure, choose "Flat Memory" over this option.
46
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
55	  "Discontiguous Memory".  This option provides some potential
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
62endchoice
63
64config DISCONTIGMEM
65	def_bool y
66	depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL
67
68config SPARSEMEM
69	def_bool y
70	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
71
72config FLATMEM
73	def_bool y
74	depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
75
76config FLAT_NODE_MEM_MAP
77	def_bool y
78	depends on !SPARSEMEM
79
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
88
89config HAVE_MEMORY_PRESENT
90	def_bool y
91	depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
92
93#
94# SPARSEMEM_EXTREME (which is the default) does some bootmem
95# allocations when memory_present() is called.  If this cannot
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
104	bool
105
106#
107# Architecture platforms which require a two level mem_section in SPARSEMEM
108# must select this option. This is usually for architecture platforms with
109# an extremely sparse physical address space.
110#
111config SPARSEMEM_EXTREME
112	def_bool y
113	depends on SPARSEMEM && !SPARSEMEM_STATIC
114
115config SPARSEMEM_VMEMMAP_ENABLE
116	bool
117
118config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
119	def_bool y
120	depends on SPARSEMEM && X86_64
121
122config SPARSEMEM_VMEMMAP
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.
130
131config HAVE_MEMBLOCK
132	bool
133
134config HAVE_MEMBLOCK_NODE_MAP
135	bool
136
137config HAVE_MEMBLOCK_PHYS_MAP
138	bool
139
140config HAVE_GENERIC_RCU_GUP
141	bool
142
143config ARCH_DISCARD_MEMBLOCK
144	bool
145
146config NO_BOOTMEM
147	bool
148
149config MEMORY_ISOLATION
150	bool
151
152config MOVABLE_NODE
153	bool "Enable to assign a node which has only movable memory"
154	depends on HAVE_MEMBLOCK
155	depends on NO_BOOTMEM
156	depends on X86_64
157	depends on NUMA
158	default n
159	help
160	  Allow a node to have only movable memory.  Pages used by the kernel,
161	  such as direct mapping pages cannot be migrated.  So the corresponding
162	  memory device cannot be hotplugged.  This option allows the following
163	  two things:
164	  - When the system is booting, node full of hotpluggable memory can
165	  be arranged to have only movable memory so that the whole node can
166	  be hot-removed. (need movable_node boot option specified).
167	  - After the system is up, the option allows users to online all the
168	  memory of a node as movable memory so that the whole node can be
169	  hot-removed.
170
171	  Users who don't use the memory hotplug feature are fine with this
172	  option on since they don't specify movable_node boot option or they
173	  don't online memory as movable.
174
175	  Say Y here if you want to hotplug a whole node.
176	  Say N here if you want kernel to use memory on all nodes evenly.
177
178#
179# Only be set on architectures that have completely implemented memory hotplug
180# feature. If you are not sure, don't touch it.
181#
182config HAVE_BOOTMEM_INFO_NODE
183	def_bool n
184
185# eventually, we can have this option just 'select SPARSEMEM'
186config MEMORY_HOTPLUG
187	bool "Allow for memory hot-add"
188	depends on SPARSEMEM || X86_64_ACPI_NUMA
189	depends on ARCH_ENABLE_MEMORY_HOTPLUG
190	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
191
192config MEMORY_HOTPLUG_SPARSE
193	def_bool y
194	depends on SPARSEMEM && MEMORY_HOTPLUG
195
196config MEMORY_HOTREMOVE
197	bool "Allow for memory hot remove"
198	select MEMORY_ISOLATION
199	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
200	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
201	depends on MIGRATION
202
203#
204# If we have space for more page flags then we can enable additional
205# optimizations and functionality.
206#
207# Regular Sparsemem takes page flag bits for the sectionid if it does not
208# use a virtual memmap. Disable extended page flags for 32 bit platforms
209# that require the use of a sectionid in the page flags.
210#
211config PAGEFLAGS_EXTENDED
212	def_bool y
213	depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
214
215# Heavily threaded applications may benefit from splitting the mm-wide
216# page_table_lock, so that faults on different parts of the user address
217# space can be handled with less contention: split it at this NR_CPUS.
218# Default to 4 for wider testing, though 8 might be more appropriate.
219# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
220# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
221# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
222#
223config SPLIT_PTLOCK_CPUS
224	int
225	default "999999" if !MMU
226	default "999999" if ARM && !CPU_CACHE_VIPT
227	default "999999" if PARISC && !PA20
228	default "4"
229
230config ARCH_ENABLE_SPLIT_PMD_PTLOCK
231	bool
232
233#
234# support for memory balloon
235config MEMORY_BALLOON
236	bool
237
238#
239# support for memory balloon compaction
240config BALLOON_COMPACTION
241	bool "Allow for balloon memory compaction/migration"
242	def_bool y
243	depends on COMPACTION && MEMORY_BALLOON
244	help
245	  Memory fragmentation introduced by ballooning might reduce
246	  significantly the number of 2MB contiguous memory blocks that can be
247	  used within a guest, thus imposing performance penalties associated
248	  with the reduced number of transparent huge pages that could be used
249	  by the guest workload. Allowing the compaction & migration for memory
250	  pages enlisted as being part of memory balloon devices avoids the
251	  scenario aforementioned and helps improving memory defragmentation.
252
253#
254# support for memory compaction
255config COMPACTION
256	bool "Allow for memory compaction"
257	def_bool y
258	select MIGRATION
259	depends on MMU
260	help
261	  Allows the compaction of memory for the allocation of huge pages.
262
263#
264# support for page migration
265#
266config MIGRATION
267	bool "Page migration"
268	def_bool y
269	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
270	help
271	  Allows the migration of the physical location of pages of processes
272	  while the virtual addresses are not changed. This is useful in
273	  two situations. The first is on NUMA systems to put pages nearer
274	  to the processors accessing. The second is when allocating huge
275	  pages as migration can relocate pages to satisfy a huge page
276	  allocation instead of reclaiming.
277
278config ARCH_ENABLE_HUGEPAGE_MIGRATION
279	bool
280
281config PHYS_ADDR_T_64BIT
282	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
283
284config ZONE_DMA_FLAG
285	int
286	default "0" if !ZONE_DMA
287	default "1"
288
289config BOUNCE
290	bool "Enable bounce buffers"
291	default y
292	depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
293	help
294	  Enable bounce buffers for devices that cannot access
295	  the full range of memory available to the CPU. Enabled
296	  by default when ZONE_DMA or HIGHMEM is selected, but you
297	  may say n to override this.
298
299# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
300# have more than 4GB of memory, but we don't currently use the IOTLB to present
301# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
302#
303# We also use the bounce pool to provide stable page writes for jbd.  jbd
304# initiates buffer writeback without locking the page or setting PG_writeback,
305# and fixing that behavior (a second time; jbd2 doesn't have this problem) is
306# a major rework effort.  Instead, use the bounce buffer to snapshot pages
307# (until jbd goes away).  The only jbd user is ext3.
308config NEED_BOUNCE_POOL
309	bool
310	default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD)
311
312config NR_QUICK
313	int
314	depends on QUICKLIST
315	default "2" if AVR32
316	default "1"
317
318config VIRT_TO_BUS
319	bool
320	help
321	  An architecture should select this if it implements the
322	  deprecated interface virt_to_bus().  All new architectures
323	  should probably not select this.
324
325
326config MMU_NOTIFIER
327	bool
328	select SRCU
329
330config KSM
331	bool "Enable KSM for page merging"
332	depends on MMU
333	help
334	  Enable Kernel Samepage Merging: KSM periodically scans those areas
335	  of an application's address space that an app has advised may be
336	  mergeable.  When it finds pages of identical content, it replaces
337	  the many instances by a single page with that content, so
338	  saving memory until one or another app needs to modify the content.
339	  Recommended for use with KVM, or with other duplicative applications.
340	  See Documentation/vm/ksm.txt for more information: KSM is inactive
341	  until a program has madvised that an area is MADV_MERGEABLE, and
342	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
343
344config DEFAULT_MMAP_MIN_ADDR
345        int "Low address space to protect from user allocation"
346	depends on MMU
347        default 4096
348        help
349	  This is the portion of low virtual memory which should be protected
350	  from userspace allocation.  Keeping a user from writing to low pages
351	  can help reduce the impact of kernel NULL pointer bugs.
352
353	  For most ia64, ppc64 and x86 users with lots of address space
354	  a value of 65536 is reasonable and should cause no problems.
355	  On arm and other archs it should not be higher than 32768.
356	  Programs which use vm86 functionality or have some need to map
357	  this low address space will need CAP_SYS_RAWIO or disable this
358	  protection by setting the value to 0.
359
360	  This value can be changed after boot using the
361	  /proc/sys/vm/mmap_min_addr tunable.
362
363config ARCH_SUPPORTS_MEMORY_FAILURE
364	bool
365
366config MEMORY_FAILURE
367	depends on MMU
368	depends on ARCH_SUPPORTS_MEMORY_FAILURE
369	bool "Enable recovery from hardware memory errors"
370	select MEMORY_ISOLATION
371	help
372	  Enables code to recover from some memory failures on systems
373	  with MCA recovery. This allows a system to continue running
374	  even when some of its memory has uncorrected errors. This requires
375	  special hardware support and typically ECC memory.
376
377config HWPOISON_INJECT
378	tristate "HWPoison pages injector"
379	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
380	select PROC_PAGE_MONITOR
381
382config NOMMU_INITIAL_TRIM_EXCESS
383	int "Turn on mmap() excess space trimming before booting"
384	depends on !MMU
385	default 1
386	help
387	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
388	  of memory on which to store mappings, but it can only ask the system
389	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
390	  more than it requires.  To deal with this, mmap() is able to trim off
391	  the excess and return it to the allocator.
392
393	  If trimming is enabled, the excess is trimmed off and returned to the
394	  system allocator, which can cause extra fragmentation, particularly
395	  if there are a lot of transient processes.
396
397	  If trimming is disabled, the excess is kept, but not used, which for
398	  long-term mappings means that the space is wasted.
399
400	  Trimming can be dynamically controlled through a sysctl option
401	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
402	  excess pages there must be before trimming should occur, or zero if
403	  no trimming is to occur.
404
405	  This option specifies the initial value of this option.  The default
406	  of 1 says that all excess pages should be trimmed.
407
408	  See Documentation/nommu-mmap.txt for more information.
409
410config TRANSPARENT_HUGEPAGE
411	bool "Transparent Hugepage Support"
412	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
413	select COMPACTION
414	help
415	  Transparent Hugepages allows the kernel to use huge pages and
416	  huge tlb transparently to the applications whenever possible.
417	  This feature can improve computing performance to certain
418	  applications by speeding up page faults during memory
419	  allocation, by reducing the number of tlb misses and by speeding
420	  up the pagetable walking.
421
422	  If memory constrained on embedded, you may want to say N.
423
424choice
425	prompt "Transparent Hugepage Support sysfs defaults"
426	depends on TRANSPARENT_HUGEPAGE
427	default TRANSPARENT_HUGEPAGE_ALWAYS
428	help
429	  Selects the sysfs defaults for Transparent Hugepage Support.
430
431	config TRANSPARENT_HUGEPAGE_ALWAYS
432		bool "always"
433	help
434	  Enabling Transparent Hugepage always, can increase the
435	  memory footprint of applications without a guaranteed
436	  benefit but it will work automatically for all applications.
437
438	config TRANSPARENT_HUGEPAGE_MADVISE
439		bool "madvise"
440	help
441	  Enabling Transparent Hugepage madvise, will only provide a
442	  performance improvement benefit to the applications using
443	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
444	  memory footprint of applications without a guaranteed
445	  benefit.
446endchoice
447
448#
449# UP and nommu archs use km based percpu allocator
450#
451config NEED_PER_CPU_KM
452	depends on !SMP
453	bool
454	default y
455
456config CLEANCACHE
457	bool "Enable cleancache driver to cache clean pages if tmem is present"
458	default n
459	help
460	  Cleancache can be thought of as a page-granularity victim cache
461	  for clean pages that the kernel's pageframe replacement algorithm
462	  (PFRA) would like to keep around, but can't since there isn't enough
463	  memory.  So when the PFRA "evicts" a page, it first attempts to use
464	  cleancache code to put the data contained in that page into
465	  "transcendent memory", memory that is not directly accessible or
466	  addressable by the kernel and is of unknown and possibly
467	  time-varying size.  And when a cleancache-enabled
468	  filesystem wishes to access a page in a file on disk, it first
469	  checks cleancache to see if it already contains it; if it does,
470	  the page is copied into the kernel and a disk access is avoided.
471	  When a transcendent memory driver is available (such as zcache or
472	  Xen transcendent memory), a significant I/O reduction
473	  may be achieved.  When none is available, all cleancache calls
474	  are reduced to a single pointer-compare-against-NULL resulting
475	  in a negligible performance hit.
476
477	  If unsure, say Y to enable cleancache
478
479config FRONTSWAP
480	bool "Enable frontswap to cache swap pages if tmem is present"
481	depends on SWAP
482	default n
483	help
484	  Frontswap is so named because it can be thought of as the opposite
485	  of a "backing" store for a swap device.  The data is stored into
486	  "transcendent memory", memory that is not directly accessible or
487	  addressable by the kernel and is of unknown and possibly
488	  time-varying size.  When space in transcendent memory is available,
489	  a significant swap I/O reduction may be achieved.  When none is
490	  available, all frontswap calls are reduced to a single pointer-
491	  compare-against-NULL resulting in a negligible performance hit
492	  and swap data is stored as normal on the matching swap device.
493
494	  If unsure, say Y to enable frontswap.
495
496config CMA
497	bool "Contiguous Memory Allocator"
498	depends on HAVE_MEMBLOCK && MMU
499	select MIGRATION
500	select MEMORY_ISOLATION
501	help
502	  This enables the Contiguous Memory Allocator which allows other
503	  subsystems to allocate big physically-contiguous blocks of memory.
504	  CMA reserves a region of memory and allows only movable pages to
505	  be allocated from it. This way, the kernel can use the memory for
506	  pagecache and when a subsystem requests for contiguous area, the
507	  allocated pages are migrated away to serve the contiguous request.
508
509	  If unsure, say "n".
510
511config CMA_DEBUG
512	bool "CMA debug messages (DEVELOPMENT)"
513	depends on DEBUG_KERNEL && CMA
514	help
515	  Turns on debug messages in CMA.  This produces KERN_DEBUG
516	  messages for every CMA call as well as various messages while
517	  processing calls such as dma_alloc_from_contiguous().
518	  This option does not affect warning and error messages.
519
520config CMA_AREAS
521	int "Maximum count of the CMA areas"
522	depends on CMA
523	default 7
524	help
525	  CMA allows to create CMA areas for particular purpose, mainly,
526	  used as device private area. This parameter sets the maximum
527	  number of CMA area in the system.
528
529	  If unsure, leave the default value "7".
530
531config MEM_SOFT_DIRTY
532	bool "Track memory changes"
533	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
534	select PROC_PAGE_MONITOR
535	help
536	  This option enables memory changes tracking by introducing a
537	  soft-dirty bit on pte-s. This bit it set when someone writes
538	  into a page just as regular dirty bit, but unlike the latter
539	  it can be cleared by hands.
540
541	  See Documentation/vm/soft-dirty.txt for more details.
542
543config ZSWAP
544	bool "Compressed cache for swap pages (EXPERIMENTAL)"
545	depends on FRONTSWAP && CRYPTO=y
546	select CRYPTO_LZO
547	select ZPOOL
548	default n
549	help
550	  A lightweight compressed cache for swap pages.  It takes
551	  pages that are in the process of being swapped out and attempts to
552	  compress them into a dynamically allocated RAM-based memory pool.
553	  This can result in a significant I/O reduction on swap device and,
554	  in the case where decompressing from RAM is faster that swap device
555	  reads, can also improve workload performance.
556
557	  This is marked experimental because it is a new feature (as of
558	  v3.11) that interacts heavily with memory reclaim.  While these
559	  interactions don't cause any known issues on simple memory setups,
560	  they have not be fully explored on the large set of potential
561	  configurations and workloads that exist.
562
563config ZPOOL
564	tristate "Common API for compressed memory storage"
565	default n
566	help
567	  Compressed memory storage API.  This allows using either zbud or
568	  zsmalloc.
569
570config ZBUD
571	tristate "Low density storage for compressed pages"
572	default n
573	help
574	  A special purpose allocator for storing compressed pages.
575	  It is designed to store up to two compressed pages per physical
576	  page.  While this design limits storage density, it has simple and
577	  deterministic reclaim properties that make it preferable to a higher
578	  density approach when reclaim will be used.
579
580config ZSMALLOC
581	tristate "Memory allocator for compressed pages"
582	depends on MMU
583	default n
584	help
585	  zsmalloc is a slab-based memory allocator designed to store
586	  compressed RAM pages.  zsmalloc uses virtual memory mapping
587	  in order to reduce fragmentation.  However, this results in a
588	  non-standard allocator interface where a handle, not a pointer, is
589	  returned by an alloc().  This handle must be mapped in order to
590	  access the allocated space.
591
592config PGTABLE_MAPPING
593	bool "Use page table mapping to access object in zsmalloc"
594	depends on ZSMALLOC
595	help
596	  By default, zsmalloc uses a copy-based object mapping method to
597	  access allocations that span two pages. However, if a particular
598	  architecture (ex, ARM) performs VM mapping faster than copying,
599	  then you should select this. This causes zsmalloc to use page table
600	  mapping rather than copying for object mapping.
601
602	  You can check speed with zsmalloc benchmark:
603	  https://github.com/spartacus06/zsmapbench
604
605config ZSMALLOC_STAT
606	bool "Export zsmalloc statistics"
607	depends on ZSMALLOC
608	select DEBUG_FS
609	help
610	  This option enables code in the zsmalloc to collect various
611	  statistics about whats happening in zsmalloc and exports that
612	  information to userspace via debugfs.
613	  If unsure, say N.
614
615config GENERIC_EARLY_IOREMAP
616	bool
617
618config MAX_STACK_SIZE_MB
619	int "Maximum user stack size for 32-bit processes (MB)"
620	default 80
621	range 8 256 if METAG
622	range 8 2048
623	depends on STACK_GROWSUP && (!64BIT || COMPAT)
624	help
625	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
626	  user processes when the stack grows upwards (currently only on parisc
627	  and metag arch). The stack will be located at the highest memory
628	  address minus the given value, unless the RLIMIT_STACK hard limit is
629	  changed to a smaller value in which case that is used.
630
631	  A sane initial value is 80 MB.
632