xref: /openbmc/linux/mm/Kconfig (revision 930beb5a)
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 ARCH_DISCARD_MEMBLOCK
138	boolean
139
140config NO_BOOTMEM
141	boolean
142
143config MEMORY_ISOLATION
144	boolean
145
146config 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
152	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 the following
157	  two things:
158	  - When the system is booting, node full of hotpluggable memory can
159	  be arranged to have only movable memory so that the whole node can
160	  be hot-removed. (need movable_node boot option specified).
161	  - After the system is up, the option allows users to online all the
162	  memory of a node as movable memory so that the whole node can be
163	  hot-removed.
164
165	  Users who don't use the memory hotplug feature are fine with this
166	  option on since they don't specify movable_node boot option or they
167	  don't online memory as movable.
168
169	  Say Y here if you want to hotplug a whole node.
170	  Say N here if you want kernel to use memory on all nodes evenly.
171
172#
173# Only be set on architectures that have completely implemented memory hotplug
174# feature. If you are not sure, don't touch it.
175#
176config HAVE_BOOTMEM_INFO_NODE
177	def_bool n
178
179# eventually, we can have this option just 'select SPARSEMEM'
180config MEMORY_HOTPLUG
181	bool "Allow for memory hot-add"
182	depends on SPARSEMEM || X86_64_ACPI_NUMA
183	depends on ARCH_ENABLE_MEMORY_HOTPLUG
184	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
185
186config MEMORY_HOTPLUG_SPARSE
187	def_bool y
188	depends on SPARSEMEM && MEMORY_HOTPLUG
189
190config MEMORY_HOTREMOVE
191	bool "Allow for memory hot remove"
192	select MEMORY_ISOLATION
193	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
194	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
195	depends on MIGRATION
196
197#
198# If we have space for more page flags then we can enable additional
199# optimizations and functionality.
200#
201# Regular Sparsemem takes page flag bits for the sectionid if it does not
202# use a virtual memmap. Disable extended page flags for 32 bit platforms
203# that require the use of a sectionid in the page flags.
204#
205config PAGEFLAGS_EXTENDED
206	def_bool y
207	depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
208
209# Heavily threaded applications may benefit from splitting the mm-wide
210# page_table_lock, so that faults on different parts of the user address
211# space can be handled with less contention: split it at this NR_CPUS.
212# Default to 4 for wider testing, though 8 might be more appropriate.
213# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
214# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
215# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
216#
217config SPLIT_PTLOCK_CPUS
218	int
219	default "999999" if ARM && !CPU_CACHE_VIPT
220	default "999999" if PARISC && !PA20
221	default "4"
222
223config ARCH_ENABLE_SPLIT_PMD_PTLOCK
224	boolean
225
226#
227# support for memory balloon compaction
228config BALLOON_COMPACTION
229	bool "Allow for balloon memory compaction/migration"
230	def_bool y
231	depends on COMPACTION && VIRTIO_BALLOON
232	help
233	  Memory fragmentation introduced by ballooning might reduce
234	  significantly the number of 2MB contiguous memory blocks that can be
235	  used within a guest, thus imposing performance penalties associated
236	  with the reduced number of transparent huge pages that could be used
237	  by the guest workload. Allowing the compaction & migration for memory
238	  pages enlisted as being part of memory balloon devices avoids the
239	  scenario aforementioned and helps improving memory defragmentation.
240
241#
242# support for memory compaction
243config COMPACTION
244	bool "Allow for memory compaction"
245	def_bool y
246	select MIGRATION
247	depends on MMU
248	help
249	  Allows the compaction of memory for the allocation of huge pages.
250
251#
252# support for page migration
253#
254config MIGRATION
255	bool "Page migration"
256	def_bool y
257	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
258	help
259	  Allows the migration of the physical location of pages of processes
260	  while the virtual addresses are not changed. This is useful in
261	  two situations. The first is on NUMA systems to put pages nearer
262	  to the processors accessing. The second is when allocating huge
263	  pages as migration can relocate pages to satisfy a huge page
264	  allocation instead of reclaiming.
265
266config PHYS_ADDR_T_64BIT
267	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
268
269config ZONE_DMA_FLAG
270	int
271	default "0" if !ZONE_DMA
272	default "1"
273
274config BOUNCE
275	bool "Enable bounce buffers"
276	default y
277	depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
278	help
279	  Enable bounce buffers for devices that cannot access
280	  the full range of memory available to the CPU. Enabled
281	  by default when ZONE_DMA or HIGHMEM is selected, but you
282	  may say n to override this.
283
284# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
285# have more than 4GB of memory, but we don't currently use the IOTLB to present
286# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
287#
288# We also use the bounce pool to provide stable page writes for jbd.  jbd
289# initiates buffer writeback without locking the page or setting PG_writeback,
290# and fixing that behavior (a second time; jbd2 doesn't have this problem) is
291# a major rework effort.  Instead, use the bounce buffer to snapshot pages
292# (until jbd goes away).  The only jbd user is ext3.
293config NEED_BOUNCE_POOL
294	bool
295	default y if (TILE && USB_OHCI_HCD) || (BLK_DEV_INTEGRITY && JBD)
296
297config NR_QUICK
298	int
299	depends on QUICKLIST
300	default "2" if AVR32
301	default "1"
302
303config VIRT_TO_BUS
304	bool
305	help
306	  An architecture should select this if it implements the
307	  deprecated interface virt_to_bus().  All new architectures
308	  should probably not select this.
309
310
311config MMU_NOTIFIER
312	bool
313
314config KSM
315	bool "Enable KSM for page merging"
316	depends on MMU
317	help
318	  Enable Kernel Samepage Merging: KSM periodically scans those areas
319	  of an application's address space that an app has advised may be
320	  mergeable.  When it finds pages of identical content, it replaces
321	  the many instances by a single page with that content, so
322	  saving memory until one or another app needs to modify the content.
323	  Recommended for use with KVM, or with other duplicative applications.
324	  See Documentation/vm/ksm.txt for more information: KSM is inactive
325	  until a program has madvised that an area is MADV_MERGEABLE, and
326	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
327
328config DEFAULT_MMAP_MIN_ADDR
329        int "Low address space to protect from user allocation"
330	depends on MMU
331        default 4096
332        help
333	  This is the portion of low virtual memory which should be protected
334	  from userspace allocation.  Keeping a user from writing to low pages
335	  can help reduce the impact of kernel NULL pointer bugs.
336
337	  For most ia64, ppc64 and x86 users with lots of address space
338	  a value of 65536 is reasonable and should cause no problems.
339	  On arm and other archs it should not be higher than 32768.
340	  Programs which use vm86 functionality or have some need to map
341	  this low address space will need CAP_SYS_RAWIO or disable this
342	  protection by setting the value to 0.
343
344	  This value can be changed after boot using the
345	  /proc/sys/vm/mmap_min_addr tunable.
346
347config ARCH_SUPPORTS_MEMORY_FAILURE
348	bool
349
350config MEMORY_FAILURE
351	depends on MMU
352	depends on ARCH_SUPPORTS_MEMORY_FAILURE
353	bool "Enable recovery from hardware memory errors"
354	select MEMORY_ISOLATION
355	help
356	  Enables code to recover from some memory failures on systems
357	  with MCA recovery. This allows a system to continue running
358	  even when some of its memory has uncorrected errors. This requires
359	  special hardware support and typically ECC memory.
360
361config HWPOISON_INJECT
362	tristate "HWPoison pages injector"
363	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
364	select PROC_PAGE_MONITOR
365
366config NOMMU_INITIAL_TRIM_EXCESS
367	int "Turn on mmap() excess space trimming before booting"
368	depends on !MMU
369	default 1
370	help
371	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
372	  of memory on which to store mappings, but it can only ask the system
373	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
374	  more than it requires.  To deal with this, mmap() is able to trim off
375	  the excess and return it to the allocator.
376
377	  If trimming is enabled, the excess is trimmed off and returned to the
378	  system allocator, which can cause extra fragmentation, particularly
379	  if there are a lot of transient processes.
380
381	  If trimming is disabled, the excess is kept, but not used, which for
382	  long-term mappings means that the space is wasted.
383
384	  Trimming can be dynamically controlled through a sysctl option
385	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
386	  excess pages there must be before trimming should occur, or zero if
387	  no trimming is to occur.
388
389	  This option specifies the initial value of this option.  The default
390	  of 1 says that all excess pages should be trimmed.
391
392	  See Documentation/nommu-mmap.txt for more information.
393
394config TRANSPARENT_HUGEPAGE
395	bool "Transparent Hugepage Support"
396	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
397	select COMPACTION
398	help
399	  Transparent Hugepages allows the kernel to use huge pages and
400	  huge tlb transparently to the applications whenever possible.
401	  This feature can improve computing performance to certain
402	  applications by speeding up page faults during memory
403	  allocation, by reducing the number of tlb misses and by speeding
404	  up the pagetable walking.
405
406	  If memory constrained on embedded, you may want to say N.
407
408choice
409	prompt "Transparent Hugepage Support sysfs defaults"
410	depends on TRANSPARENT_HUGEPAGE
411	default TRANSPARENT_HUGEPAGE_ALWAYS
412	help
413	  Selects the sysfs defaults for Transparent Hugepage Support.
414
415	config TRANSPARENT_HUGEPAGE_ALWAYS
416		bool "always"
417	help
418	  Enabling Transparent Hugepage always, can increase the
419	  memory footprint of applications without a guaranteed
420	  benefit but it will work automatically for all applications.
421
422	config TRANSPARENT_HUGEPAGE_MADVISE
423		bool "madvise"
424	help
425	  Enabling Transparent Hugepage madvise, will only provide a
426	  performance improvement benefit to the applications using
427	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
428	  memory footprint of applications without a guaranteed
429	  benefit.
430endchoice
431
432config CROSS_MEMORY_ATTACH
433	bool "Cross Memory Support"
434	depends on MMU
435	default y
436	help
437	  Enabling this option adds the system calls process_vm_readv and
438	  process_vm_writev which allow a process with the correct privileges
439	  to directly read from or write to to another process's address space.
440	  See the man page for more details.
441
442#
443# UP and nommu archs use km based percpu allocator
444#
445config NEED_PER_CPU_KM
446	depends on !SMP
447	bool
448	default y
449
450config CLEANCACHE
451	bool "Enable cleancache driver to cache clean pages if tmem is present"
452	default n
453	help
454	  Cleancache can be thought of as a page-granularity victim cache
455	  for clean pages that the kernel's pageframe replacement algorithm
456	  (PFRA) would like to keep around, but can't since there isn't enough
457	  memory.  So when the PFRA "evicts" a page, it first attempts to use
458	  cleancache code to put the data contained in that page into
459	  "transcendent memory", memory that is not directly accessible or
460	  addressable by the kernel and is of unknown and possibly
461	  time-varying size.  And when a cleancache-enabled
462	  filesystem wishes to access a page in a file on disk, it first
463	  checks cleancache to see if it already contains it; if it does,
464	  the page is copied into the kernel and a disk access is avoided.
465	  When a transcendent memory driver is available (such as zcache or
466	  Xen transcendent memory), a significant I/O reduction
467	  may be achieved.  When none is available, all cleancache calls
468	  are reduced to a single pointer-compare-against-NULL resulting
469	  in a negligible performance hit.
470
471	  If unsure, say Y to enable cleancache
472
473config FRONTSWAP
474	bool "Enable frontswap to cache swap pages if tmem is present"
475	depends on SWAP
476	default n
477	help
478	  Frontswap is so named because it can be thought of as the opposite
479	  of a "backing" store for a swap device.  The data is stored into
480	  "transcendent memory", memory that is not directly accessible or
481	  addressable by the kernel and is of unknown and possibly
482	  time-varying size.  When space in transcendent memory is available,
483	  a significant swap I/O reduction may be achieved.  When none is
484	  available, all frontswap calls are reduced to a single pointer-
485	  compare-against-NULL resulting in a negligible performance hit
486	  and swap data is stored as normal on the matching swap device.
487
488	  If unsure, say Y to enable frontswap.
489
490config CMA
491	bool "Contiguous Memory Allocator"
492	depends on HAVE_MEMBLOCK && MMU
493	select MIGRATION
494	select MEMORY_ISOLATION
495	help
496	  This enables the Contiguous Memory Allocator which allows other
497	  subsystems to allocate big physically-contiguous blocks of memory.
498	  CMA reserves a region of memory and allows only movable pages to
499	  be allocated from it. This way, the kernel can use the memory for
500	  pagecache and when a subsystem requests for contiguous area, the
501	  allocated pages are migrated away to serve the contiguous request.
502
503	  If unsure, say "n".
504
505config CMA_DEBUG
506	bool "CMA debug messages (DEVELOPMENT)"
507	depends on DEBUG_KERNEL && CMA
508	help
509	  Turns on debug messages in CMA.  This produces KERN_DEBUG
510	  messages for every CMA call as well as various messages while
511	  processing calls such as dma_alloc_from_contiguous().
512	  This option does not affect warning and error messages.
513
514config ZBUD
515	tristate
516	default n
517	help
518	  A special purpose allocator for storing compressed pages.
519	  It is designed to store up to two compressed pages per physical
520	  page.  While this design limits storage density, it has simple and
521	  deterministic reclaim properties that make it preferable to a higher
522	  density approach when reclaim will be used.
523
524config ZSWAP
525	bool "Compressed cache for swap pages (EXPERIMENTAL)"
526	depends on FRONTSWAP && CRYPTO=y
527	select CRYPTO_LZO
528	select ZBUD
529	default n
530	help
531	  A lightweight compressed cache for swap pages.  It takes
532	  pages that are in the process of being swapped out and attempts to
533	  compress them into a dynamically allocated RAM-based memory pool.
534	  This can result in a significant I/O reduction on swap device and,
535	  in the case where decompressing from RAM is faster that swap device
536	  reads, can also improve workload performance.
537
538	  This is marked experimental because it is a new feature (as of
539	  v3.11) that interacts heavily with memory reclaim.  While these
540	  interactions don't cause any known issues on simple memory setups,
541	  they have not be fully explored on the large set of potential
542	  configurations and workloads that exist.
543
544config MEM_SOFT_DIRTY
545	bool "Track memory changes"
546	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
547	select PROC_PAGE_MONITOR
548	help
549	  This option enables memory changes tracking by introducing a
550	  soft-dirty bit on pte-s. This bit it set when someone writes
551	  into a page just as regular dirty bit, but unlike the latter
552	  it can be cleared by hands.
553
554	  See Documentation/vm/soft-dirty.txt for more details.
555