xref: /openbmc/linux/mm/Kconfig (revision 206204a1)
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	boolean
133
134config HAVE_MEMBLOCK_NODE_MAP
135	boolean
136
137config HAVE_MEMBLOCK_PHYS_MAP
138	boolean
139
140config ARCH_DISCARD_MEMBLOCK
141	boolean
142
143config NO_BOOTMEM
144	boolean
145
146config MEMORY_ISOLATION
147	boolean
148
149config MOVABLE_NODE
150	boolean "Enable to assign a node which has only movable memory"
151	depends on HAVE_MEMBLOCK
152	depends on NO_BOOTMEM
153	depends on X86_64
154	depends on NUMA
155	default n
156	help
157	  Allow a node to have only movable memory.  Pages used by the kernel,
158	  such as direct mapping pages cannot be migrated.  So the corresponding
159	  memory device cannot be hotplugged.  This option allows the following
160	  two things:
161	  - When the system is booting, node full of hotpluggable memory can
162	  be arranged to have only movable memory so that the whole node can
163	  be hot-removed. (need movable_node boot option specified).
164	  - After the system is up, the option allows users to online all the
165	  memory of a node as movable memory so that the whole node can be
166	  hot-removed.
167
168	  Users who don't use the memory hotplug feature are fine with this
169	  option on since they don't specify movable_node boot option or they
170	  don't online memory as movable.
171
172	  Say Y here if you want to hotplug a whole node.
173	  Say N here if you want kernel to use memory on all nodes evenly.
174
175#
176# Only be set on architectures that have completely implemented memory hotplug
177# feature. If you are not sure, don't touch it.
178#
179config HAVE_BOOTMEM_INFO_NODE
180	def_bool n
181
182# eventually, we can have this option just 'select SPARSEMEM'
183config MEMORY_HOTPLUG
184	bool "Allow for memory hot-add"
185	depends on SPARSEMEM || X86_64_ACPI_NUMA
186	depends on ARCH_ENABLE_MEMORY_HOTPLUG
187	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
188
189config MEMORY_HOTPLUG_SPARSE
190	def_bool y
191	depends on SPARSEMEM && MEMORY_HOTPLUG
192
193config MEMORY_HOTREMOVE
194	bool "Allow for memory hot remove"
195	select MEMORY_ISOLATION
196	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
197	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
198	depends on MIGRATION
199
200#
201# If we have space for more page flags then we can enable additional
202# optimizations and functionality.
203#
204# Regular Sparsemem takes page flag bits for the sectionid if it does not
205# use a virtual memmap. Disable extended page flags for 32 bit platforms
206# that require the use of a sectionid in the page flags.
207#
208config PAGEFLAGS_EXTENDED
209	def_bool y
210	depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
211
212# Heavily threaded applications may benefit from splitting the mm-wide
213# page_table_lock, so that faults on different parts of the user address
214# space can be handled with less contention: split it at this NR_CPUS.
215# Default to 4 for wider testing, though 8 might be more appropriate.
216# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
217# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
218# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
219#
220config SPLIT_PTLOCK_CPUS
221	int
222	default "999999" if !MMU
223	default "999999" if ARM && !CPU_CACHE_VIPT
224	default "999999" if PARISC && !PA20
225	default "4"
226
227config ARCH_ENABLE_SPLIT_PMD_PTLOCK
228	boolean
229
230#
231# support for memory balloon compaction
232config BALLOON_COMPACTION
233	bool "Allow for balloon memory compaction/migration"
234	def_bool y
235	depends on COMPACTION && VIRTIO_BALLOON
236	help
237	  Memory fragmentation introduced by ballooning might reduce
238	  significantly the number of 2MB contiguous memory blocks that can be
239	  used within a guest, thus imposing performance penalties associated
240	  with the reduced number of transparent huge pages that could be used
241	  by the guest workload. Allowing the compaction & migration for memory
242	  pages enlisted as being part of memory balloon devices avoids the
243	  scenario aforementioned and helps improving memory defragmentation.
244
245#
246# support for memory compaction
247config COMPACTION
248	bool "Allow for memory compaction"
249	def_bool y
250	select MIGRATION
251	depends on MMU
252	help
253	  Allows the compaction of memory for the allocation of huge pages.
254
255#
256# support for page migration
257#
258config MIGRATION
259	bool "Page migration"
260	def_bool y
261	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
262	help
263	  Allows the migration of the physical location of pages of processes
264	  while the virtual addresses are not changed. This is useful in
265	  two situations. The first is on NUMA systems to put pages nearer
266	  to the processors accessing. The second is when allocating huge
267	  pages as migration can relocate pages to satisfy a huge page
268	  allocation instead of reclaiming.
269
270config ARCH_ENABLE_HUGEPAGE_MIGRATION
271	boolean
272
273config PHYS_ADDR_T_64BIT
274	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
275
276config ZONE_DMA_FLAG
277	int
278	default "0" if !ZONE_DMA
279	default "1"
280
281config BOUNCE
282	bool "Enable bounce buffers"
283	default y
284	depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
285	help
286	  Enable bounce buffers for devices that cannot access
287	  the full range of memory available to the CPU. Enabled
288	  by default when ZONE_DMA or HIGHMEM is selected, but you
289	  may say n to override this.
290
291# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
292# have more than 4GB of memory, but we don't currently use the IOTLB to present
293# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
294#
295# We also use the bounce pool to provide stable page writes for jbd.  jbd
296# initiates buffer writeback without locking the page or setting PG_writeback,
297# and fixing that behavior (a second time; jbd2 doesn't have this problem) is
298# a major rework effort.  Instead, use the bounce buffer to snapshot pages
299# (until jbd goes away).  The only jbd user is ext3.
300config NEED_BOUNCE_POOL
301	bool
302	default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD)
303
304config NR_QUICK
305	int
306	depends on QUICKLIST
307	default "2" if AVR32
308	default "1"
309
310config VIRT_TO_BUS
311	bool
312	help
313	  An architecture should select this if it implements the
314	  deprecated interface virt_to_bus().  All new architectures
315	  should probably not select this.
316
317
318config MMU_NOTIFIER
319	bool
320
321config KSM
322	bool "Enable KSM for page merging"
323	depends on MMU
324	help
325	  Enable Kernel Samepage Merging: KSM periodically scans those areas
326	  of an application's address space that an app has advised may be
327	  mergeable.  When it finds pages of identical content, it replaces
328	  the many instances by a single page with that content, so
329	  saving memory until one or another app needs to modify the content.
330	  Recommended for use with KVM, or with other duplicative applications.
331	  See Documentation/vm/ksm.txt for more information: KSM is inactive
332	  until a program has madvised that an area is MADV_MERGEABLE, and
333	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
334
335config DEFAULT_MMAP_MIN_ADDR
336        int "Low address space to protect from user allocation"
337	depends on MMU
338        default 4096
339        help
340	  This is the portion of low virtual memory which should be protected
341	  from userspace allocation.  Keeping a user from writing to low pages
342	  can help reduce the impact of kernel NULL pointer bugs.
343
344	  For most ia64, ppc64 and x86 users with lots of address space
345	  a value of 65536 is reasonable and should cause no problems.
346	  On arm and other archs it should not be higher than 32768.
347	  Programs which use vm86 functionality or have some need to map
348	  this low address space will need CAP_SYS_RAWIO or disable this
349	  protection by setting the value to 0.
350
351	  This value can be changed after boot using the
352	  /proc/sys/vm/mmap_min_addr tunable.
353
354config ARCH_SUPPORTS_MEMORY_FAILURE
355	bool
356
357config MEMORY_FAILURE
358	depends on MMU
359	depends on ARCH_SUPPORTS_MEMORY_FAILURE
360	bool "Enable recovery from hardware memory errors"
361	select MEMORY_ISOLATION
362	help
363	  Enables code to recover from some memory failures on systems
364	  with MCA recovery. This allows a system to continue running
365	  even when some of its memory has uncorrected errors. This requires
366	  special hardware support and typically ECC memory.
367
368config HWPOISON_INJECT
369	tristate "HWPoison pages injector"
370	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
371	select PROC_PAGE_MONITOR
372
373config NOMMU_INITIAL_TRIM_EXCESS
374	int "Turn on mmap() excess space trimming before booting"
375	depends on !MMU
376	default 1
377	help
378	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
379	  of memory on which to store mappings, but it can only ask the system
380	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
381	  more than it requires.  To deal with this, mmap() is able to trim off
382	  the excess and return it to the allocator.
383
384	  If trimming is enabled, the excess is trimmed off and returned to the
385	  system allocator, which can cause extra fragmentation, particularly
386	  if there are a lot of transient processes.
387
388	  If trimming is disabled, the excess is kept, but not used, which for
389	  long-term mappings means that the space is wasted.
390
391	  Trimming can be dynamically controlled through a sysctl option
392	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
393	  excess pages there must be before trimming should occur, or zero if
394	  no trimming is to occur.
395
396	  This option specifies the initial value of this option.  The default
397	  of 1 says that all excess pages should be trimmed.
398
399	  See Documentation/nommu-mmap.txt for more information.
400
401config TRANSPARENT_HUGEPAGE
402	bool "Transparent Hugepage Support"
403	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
404	select COMPACTION
405	help
406	  Transparent Hugepages allows the kernel to use huge pages and
407	  huge tlb transparently to the applications whenever possible.
408	  This feature can improve computing performance to certain
409	  applications by speeding up page faults during memory
410	  allocation, by reducing the number of tlb misses and by speeding
411	  up the pagetable walking.
412
413	  If memory constrained on embedded, you may want to say N.
414
415choice
416	prompt "Transparent Hugepage Support sysfs defaults"
417	depends on TRANSPARENT_HUGEPAGE
418	default TRANSPARENT_HUGEPAGE_ALWAYS
419	help
420	  Selects the sysfs defaults for Transparent Hugepage Support.
421
422	config TRANSPARENT_HUGEPAGE_ALWAYS
423		bool "always"
424	help
425	  Enabling Transparent Hugepage always, can increase the
426	  memory footprint of applications without a guaranteed
427	  benefit but it will work automatically for all applications.
428
429	config TRANSPARENT_HUGEPAGE_MADVISE
430		bool "madvise"
431	help
432	  Enabling Transparent Hugepage madvise, will only provide a
433	  performance improvement benefit to the applications using
434	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
435	  memory footprint of applications without a guaranteed
436	  benefit.
437endchoice
438
439#
440# UP and nommu archs use km based percpu allocator
441#
442config NEED_PER_CPU_KM
443	depends on !SMP
444	bool
445	default y
446
447config CLEANCACHE
448	bool "Enable cleancache driver to cache clean pages if tmem is present"
449	default n
450	help
451	  Cleancache can be thought of as a page-granularity victim cache
452	  for clean pages that the kernel's pageframe replacement algorithm
453	  (PFRA) would like to keep around, but can't since there isn't enough
454	  memory.  So when the PFRA "evicts" a page, it first attempts to use
455	  cleancache code to put the data contained in that page into
456	  "transcendent memory", memory that is not directly accessible or
457	  addressable by the kernel and is of unknown and possibly
458	  time-varying size.  And when a cleancache-enabled
459	  filesystem wishes to access a page in a file on disk, it first
460	  checks cleancache to see if it already contains it; if it does,
461	  the page is copied into the kernel and a disk access is avoided.
462	  When a transcendent memory driver is available (such as zcache or
463	  Xen transcendent memory), a significant I/O reduction
464	  may be achieved.  When none is available, all cleancache calls
465	  are reduced to a single pointer-compare-against-NULL resulting
466	  in a negligible performance hit.
467
468	  If unsure, say Y to enable cleancache
469
470config FRONTSWAP
471	bool "Enable frontswap to cache swap pages if tmem is present"
472	depends on SWAP
473	default n
474	help
475	  Frontswap is so named because it can be thought of as the opposite
476	  of a "backing" store for a swap device.  The data is stored into
477	  "transcendent memory", memory that is not directly accessible or
478	  addressable by the kernel and is of unknown and possibly
479	  time-varying size.  When space in transcendent memory is available,
480	  a significant swap I/O reduction may be achieved.  When none is
481	  available, all frontswap calls are reduced to a single pointer-
482	  compare-against-NULL resulting in a negligible performance hit
483	  and swap data is stored as normal on the matching swap device.
484
485	  If unsure, say Y to enable frontswap.
486
487config CMA
488	bool "Contiguous Memory Allocator"
489	depends on HAVE_MEMBLOCK && MMU
490	select MIGRATION
491	select MEMORY_ISOLATION
492	help
493	  This enables the Contiguous Memory Allocator which allows other
494	  subsystems to allocate big physically-contiguous blocks of memory.
495	  CMA reserves a region of memory and allows only movable pages to
496	  be allocated from it. This way, the kernel can use the memory for
497	  pagecache and when a subsystem requests for contiguous area, the
498	  allocated pages are migrated away to serve the contiguous request.
499
500	  If unsure, say "n".
501
502config CMA_DEBUG
503	bool "CMA debug messages (DEVELOPMENT)"
504	depends on DEBUG_KERNEL && CMA
505	help
506	  Turns on debug messages in CMA.  This produces KERN_DEBUG
507	  messages for every CMA call as well as various messages while
508	  processing calls such as dma_alloc_from_contiguous().
509	  This option does not affect warning and error messages.
510
511config ZBUD
512	tristate
513	default n
514	help
515	  A special purpose allocator for storing compressed pages.
516	  It is designed to store up to two compressed pages per physical
517	  page.  While this design limits storage density, it has simple and
518	  deterministic reclaim properties that make it preferable to a higher
519	  density approach when reclaim will be used.
520
521config ZSWAP
522	bool "Compressed cache for swap pages (EXPERIMENTAL)"
523	depends on FRONTSWAP && CRYPTO=y
524	select CRYPTO_LZO
525	select ZBUD
526	default n
527	help
528	  A lightweight compressed cache for swap pages.  It takes
529	  pages that are in the process of being swapped out and attempts to
530	  compress them into a dynamically allocated RAM-based memory pool.
531	  This can result in a significant I/O reduction on swap device and,
532	  in the case where decompressing from RAM is faster that swap device
533	  reads, can also improve workload performance.
534
535	  This is marked experimental because it is a new feature (as of
536	  v3.11) that interacts heavily with memory reclaim.  While these
537	  interactions don't cause any known issues on simple memory setups,
538	  they have not be fully explored on the large set of potential
539	  configurations and workloads that exist.
540
541config MEM_SOFT_DIRTY
542	bool "Track memory changes"
543	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
544	select PROC_PAGE_MONITOR
545	help
546	  This option enables memory changes tracking by introducing a
547	  soft-dirty bit on pte-s. This bit it set when someone writes
548	  into a page just as regular dirty bit, but unlike the latter
549	  it can be cleared by hands.
550
551	  See Documentation/vm/soft-dirty.txt for more details.
552
553config ZSMALLOC
554	tristate "Memory allocator for compressed pages"
555	depends on MMU
556	default n
557	help
558	  zsmalloc is a slab-based memory allocator designed to store
559	  compressed RAM pages.  zsmalloc uses virtual memory mapping
560	  in order to reduce fragmentation.  However, this results in a
561	  non-standard allocator interface where a handle, not a pointer, is
562	  returned by an alloc().  This handle must be mapped in order to
563	  access the allocated space.
564
565config PGTABLE_MAPPING
566	bool "Use page table mapping to access object in zsmalloc"
567	depends on ZSMALLOC
568	help
569	  By default, zsmalloc uses a copy-based object mapping method to
570	  access allocations that span two pages. However, if a particular
571	  architecture (ex, ARM) performs VM mapping faster than copying,
572	  then you should select this. This causes zsmalloc to use page table
573	  mapping rather than copying for object mapping.
574
575	  You can check speed with zsmalloc benchmark:
576	  https://github.com/spartacus06/zsmapbench
577
578config GENERIC_EARLY_IOREMAP
579	bool
580
581config MAX_STACK_SIZE_MB
582	int "Maximum user stack size for 32-bit processes (MB)"
583	default 80
584	range 8 256 if METAG
585	range 8 2048
586	depends on STACK_GROWSUP && (!64BIT || COMPAT)
587	help
588	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
589	  user processes when the stack grows upwards (currently only on parisc
590	  and metag arch). The stack will be located at the highest memory
591	  address minus the given value, unless the RLIMIT_STACK hard limit is
592	  changed to a smaller value in which case that is used.
593
594	  A sane initial value is 80 MB.
595