xref: /openbmc/linux/mm/Kconfig (revision cd5d5810)
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 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.
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 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.
164
165#
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
172# eventually, we can have this option just 'select SPARSEMEM'
173config MEMORY_HOTPLUG
174	bool "Allow for memory hot-add"
175	depends on SPARSEMEM || X86_64_ACPI_NUMA
176	depends on ARCH_ENABLE_MEMORY_HOTPLUG
177	depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390)
178
179config MEMORY_HOTPLUG_SPARSE
180	def_bool y
181	depends on SPARSEMEM && MEMORY_HOTPLUG
182
183config MEMORY_HOTREMOVE
184	bool "Allow for memory hot remove"
185	select MEMORY_ISOLATION
186	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
187	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
188	depends on MIGRATION
189
190#
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
200	depends on 64BIT || SPARSEMEM_VMEMMAP || !SPARSEMEM
201
202# 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.
207# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
208# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
209#
210config SPLIT_PTLOCK_CPUS
211	int
212	default "999999" if ARM && !CPU_CACHE_VIPT
213	default "999999" if PARISC && !PA20
214	default "999999" if DEBUG_SPINLOCK || DEBUG_LOCK_ALLOC
215	default "4"
216
217#
218# 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#
233# support for memory compaction
234config COMPACTION
235	bool "Allow for memory compaction"
236	def_bool y
237	select MIGRATION
238	depends on MMU
239	help
240	  Allows the compaction of memory for the allocation of huge pages.
241
242#
243# support for page migration
244#
245config MIGRATION
246	bool "Page migration"
247	def_bool y
248	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
249	help
250	  Allows the migration of the physical location of pages of processes
251	  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.
256
257config PHYS_ADDR_T_64BIT
258	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
259
260config ZONE_DMA_FLAG
261	int
262	default "0" if !ZONE_DMA
263	default "1"
264
265config BOUNCE
266	bool "Enable bounce buffers"
267	default y
268	depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
269	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.
274
275# 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
288config NR_QUICK
289	int
290	depends on QUICKLIST
291	default "2" if AVR32
292	default "1"
293
294config VIRT_TO_BUS
295	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
301
302config MMU_NOTIFIER
303	bool
304
305config 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
312	  the many instances by a single page with that content, so
313	  saving memory until one or another app needs to modify the content.
314	  Recommended for use with KVM, or with other duplicative applications.
315	  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).
318
319config DEFAULT_MMAP_MIN_ADDR
320        int "Low address space to protect from user allocation"
321	depends on MMU
322        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.
331	  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.
334
335	  This value can be changed after boot using the
336	  /proc/sys/vm/mmap_min_addr tunable.
337
338config ARCH_SUPPORTS_MEMORY_FAILURE
339	bool
340
341config MEMORY_FAILURE
342	depends on MMU
343	depends on ARCH_SUPPORTS_MEMORY_FAILURE
344	bool "Enable recovery from hardware memory errors"
345	select MEMORY_ISOLATION
346	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
352config HWPOISON_INJECT
353	tristate "HWPoison pages injector"
354	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
355	select PROC_PAGE_MONITOR
356
357config 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.
384
385config TRANSPARENT_HUGEPAGE
386	bool "Transparent Hugepage Support"
387	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
388	select COMPACTION
389	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
399choice
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
423config 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
433#
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
440
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
449	  cleancache code to put the data contained in that page into
450	  "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
463
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.
480
481config CMA
482	bool "Contiguous Memory Allocator"
483	depends on HAVE_MEMBLOCK && MMU
484	select MIGRATION
485	select MEMORY_ISOLATION
486	help
487	  This enables the Contiguous Memory Allocator which allows other
488	  subsystems to allocate big physically-contiguous blocks of memory.
489	  CMA reserves a region of memory and allows only movable pages to
490	  be allocated from it. This way, the kernel can use the memory for
491	  pagecache and when a subsystem requests for contiguous area, the
492	  allocated pages are migrated away to serve the contiguous request.
493
494	  If unsure, say "n".
495
496config CMA_DEBUG
497	bool "CMA debug messages (DEVELOPMENT)"
498	depends on DEBUG_KERNEL && CMA
499	help
500	  Turns on debug messages in CMA.  This produces KERN_DEBUG
501	  messages for every CMA call as well as various messages while
502	  processing calls such as dma_alloc_from_contiguous().
503	  This option does not affect warning and error messages.
504
505config ZBUD
506	tristate
507	default n
508	help
509	  A special purpose allocator for storing compressed pages.
510	  It is designed to store up to two compressed pages per physical
511	  page.  While this design limits storage density, it has simple and
512	  deterministic reclaim properties that make it preferable to a higher
513	  density approach when reclaim will be used.
514
515config ZSWAP
516	bool "Compressed cache for swap pages (EXPERIMENTAL)"
517	depends on FRONTSWAP && CRYPTO=y
518	select CRYPTO_LZO
519	select ZBUD
520	default n
521	help
522	  A lightweight compressed cache for swap pages.  It takes
523	  pages that are in the process of being swapped out and attempts to
524	  compress them into a dynamically allocated RAM-based memory pool.
525	  This can result in a significant I/O reduction on swap device and,
526	  in the case where decompressing from RAM is faster that swap device
527	  reads, can also improve workload performance.
528
529	  This is marked experimental because it is a new feature (as of
530	  v3.11) that interacts heavily with memory reclaim.  While these
531	  interactions don't cause any known issues on simple memory setups,
532	  they have not be fully explored on the large set of potential
533	  configurations and workloads that exist.
534
535config MEM_SOFT_DIRTY
536	bool "Track memory changes"
537	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
538	select PROC_PAGE_MONITOR
539	help
540	  This option enables memory changes tracking by introducing a
541	  soft-dirty bit on pte-s. This bit it set when someone writes
542	  into a page just as regular dirty bit, but unlike the latter
543	  it can be cleared by hands.
544
545	  See Documentation/vm/soft-dirty.txt for more details.
546