xref: /linux/mm/Kconfig (revision 460ea8980511c01c1551012b9a6ec6a06d02da59)
1# SPDX-License-Identifier: GPL-2.0-only
2
3menu "Memory Management options"
4
5#
6# For some reason microblaze and nios2 hard code SWAP=n.  Hopefully we can
7# add proper SWAP support to them, in which case this can be remove.
8#
9config ARCH_NO_SWAP
10	bool
11
12config ZPOOL
13	bool
14
15menuconfig SWAP
16	bool "Support for paging of anonymous memory (swap)"
17	depends on MMU && BLOCK && !ARCH_NO_SWAP
18	default y
19	help
20	  This option allows you to choose whether you want to have support
21	  for so called swap devices or swap files in your kernel that are
22	  used to provide more virtual memory than the actual RAM present
23	  in your computer.  If unsure say Y.
24
25config ZSWAP
26	bool "Compressed cache for swap pages"
27	depends on SWAP
28	select FRONTSWAP
29	select CRYPTO
30	select ZPOOL
31	help
32	  A lightweight compressed cache for swap pages.  It takes
33	  pages that are in the process of being swapped out and attempts to
34	  compress them into a dynamically allocated RAM-based memory pool.
35	  This can result in a significant I/O reduction on swap device and,
36	  in the case where decompressing from RAM is faster than swap device
37	  reads, can also improve workload performance.
38
39config ZSWAP_DEFAULT_ON
40	bool "Enable the compressed cache for swap pages by default"
41	depends on ZSWAP
42	help
43	  If selected, the compressed cache for swap pages will be enabled
44	  at boot, otherwise it will be disabled.
45
46	  The selection made here can be overridden by using the kernel
47	  command line 'zswap.enabled=' option.
48
49config ZSWAP_EXCLUSIVE_LOADS_DEFAULT_ON
50	bool "Invalidate zswap entries when pages are loaded"
51	depends on ZSWAP
52	help
53	  If selected, exclusive loads for zswap will be enabled at boot,
54	  otherwise it will be disabled.
55
56	  If exclusive loads are enabled, when a page is loaded from zswap,
57	  the zswap entry is invalidated at once, as opposed to leaving it
58	  in zswap until the swap entry is freed.
59
60	  This avoids having two copies of the same page in memory
61	  (compressed and uncompressed) after faulting in a page from zswap.
62	  The cost is that if the page was never dirtied and needs to be
63	  swapped out again, it will be re-compressed.
64
65choice
66	prompt "Default compressor"
67	depends on ZSWAP
68	default ZSWAP_COMPRESSOR_DEFAULT_LZO
69	help
70	  Selects the default compression algorithm for the compressed cache
71	  for swap pages.
72
73	  For an overview what kind of performance can be expected from
74	  a particular compression algorithm please refer to the benchmarks
75	  available at the following LWN page:
76	  https://lwn.net/Articles/751795/
77
78	  If in doubt, select 'LZO'.
79
80	  The selection made here can be overridden by using the kernel
81	  command line 'zswap.compressor=' option.
82
83config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
84	bool "Deflate"
85	select CRYPTO_DEFLATE
86	help
87	  Use the Deflate algorithm as the default compression algorithm.
88
89config ZSWAP_COMPRESSOR_DEFAULT_LZO
90	bool "LZO"
91	select CRYPTO_LZO
92	help
93	  Use the LZO algorithm as the default compression algorithm.
94
95config ZSWAP_COMPRESSOR_DEFAULT_842
96	bool "842"
97	select CRYPTO_842
98	help
99	  Use the 842 algorithm as the default compression algorithm.
100
101config ZSWAP_COMPRESSOR_DEFAULT_LZ4
102	bool "LZ4"
103	select CRYPTO_LZ4
104	help
105	  Use the LZ4 algorithm as the default compression algorithm.
106
107config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
108	bool "LZ4HC"
109	select CRYPTO_LZ4HC
110	help
111	  Use the LZ4HC algorithm as the default compression algorithm.
112
113config ZSWAP_COMPRESSOR_DEFAULT_ZSTD
114	bool "zstd"
115	select CRYPTO_ZSTD
116	help
117	  Use the zstd algorithm as the default compression algorithm.
118endchoice
119
120config ZSWAP_COMPRESSOR_DEFAULT
121       string
122       depends on ZSWAP
123       default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
124       default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO
125       default "842" if ZSWAP_COMPRESSOR_DEFAULT_842
126       default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4
127       default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
128       default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD
129       default ""
130
131choice
132	prompt "Default allocator"
133	depends on ZSWAP
134	default ZSWAP_ZPOOL_DEFAULT_ZBUD
135	help
136	  Selects the default allocator for the compressed cache for
137	  swap pages.
138	  The default is 'zbud' for compatibility, however please do
139	  read the description of each of the allocators below before
140	  making a right choice.
141
142	  The selection made here can be overridden by using the kernel
143	  command line 'zswap.zpool=' option.
144
145config ZSWAP_ZPOOL_DEFAULT_ZBUD
146	bool "zbud"
147	select ZBUD
148	help
149	  Use the zbud allocator as the default allocator.
150
151config ZSWAP_ZPOOL_DEFAULT_Z3FOLD
152	bool "z3fold"
153	select Z3FOLD
154	help
155	  Use the z3fold allocator as the default allocator.
156
157config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
158	bool "zsmalloc"
159	select ZSMALLOC
160	help
161	  Use the zsmalloc allocator as the default allocator.
162endchoice
163
164config ZSWAP_ZPOOL_DEFAULT
165       string
166       depends on ZSWAP
167       default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD
168       default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD
169       default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
170       default ""
171
172config ZBUD
173	tristate "2:1 compression allocator (zbud)"
174	depends on ZSWAP
175	help
176	  A special purpose allocator for storing compressed pages.
177	  It is designed to store up to two compressed pages per physical
178	  page.  While this design limits storage density, it has simple and
179	  deterministic reclaim properties that make it preferable to a higher
180	  density approach when reclaim will be used.
181
182config Z3FOLD
183	tristate "3:1 compression allocator (z3fold)"
184	depends on ZSWAP
185	help
186	  A special purpose allocator for storing compressed pages.
187	  It is designed to store up to three compressed pages per physical
188	  page. It is a ZBUD derivative so the simplicity and determinism are
189	  still there.
190
191config ZSMALLOC
192	tristate
193	prompt "N:1 compression allocator (zsmalloc)" if ZSWAP
194	depends on MMU
195	help
196	  zsmalloc is a slab-based memory allocator designed to store
197	  pages of various compression levels efficiently. It achieves
198	  the highest storage density with the least amount of fragmentation.
199
200config ZSMALLOC_STAT
201	bool "Export zsmalloc statistics"
202	depends on ZSMALLOC
203	select DEBUG_FS
204	help
205	  This option enables code in the zsmalloc to collect various
206	  statistics about what's happening in zsmalloc and exports that
207	  information to userspace via debugfs.
208	  If unsure, say N.
209
210config ZSMALLOC_CHAIN_SIZE
211	int "Maximum number of physical pages per-zspage"
212	default 8
213	range 4 16
214	depends on ZSMALLOC
215	help
216	  This option sets the upper limit on the number of physical pages
217	  that a zmalloc page (zspage) can consist of. The optimal zspage
218	  chain size is calculated for each size class during the
219	  initialization of the pool.
220
221	  Changing this option can alter the characteristics of size classes,
222	  such as the number of pages per zspage and the number of objects
223	  per zspage. This can also result in different configurations of
224	  the pool, as zsmalloc merges size classes with similar
225	  characteristics.
226
227	  For more information, see zsmalloc documentation.
228
229menu "SLAB allocator options"
230
231choice
232	prompt "Choose SLAB allocator"
233	default SLUB
234	help
235	   This option allows to select a slab allocator.
236
237config SLAB_DEPRECATED
238	bool "SLAB (DEPRECATED)"
239	depends on !PREEMPT_RT
240	help
241	  Deprecated and scheduled for removal in a few cycles. Replaced by
242	  SLUB.
243
244	  If you cannot migrate to SLUB, please contact linux-mm@kvack.org
245	  and the people listed in the SLAB ALLOCATOR section of MAINTAINERS
246	  file, explaining why.
247
248	  The regular slab allocator that is established and known to work
249	  well in all environments. It organizes cache hot objects in
250	  per cpu and per node queues.
251
252config SLUB
253	bool "SLUB (Unqueued Allocator)"
254	help
255	   SLUB is a slab allocator that minimizes cache line usage
256	   instead of managing queues of cached objects (SLAB approach).
257	   Per cpu caching is realized using slabs of objects instead
258	   of queues of objects. SLUB can use memory efficiently
259	   and has enhanced diagnostics. SLUB is the default choice for
260	   a slab allocator.
261
262endchoice
263
264config SLAB
265	bool
266	default y
267	depends on SLAB_DEPRECATED
268
269config SLUB_TINY
270	bool "Configure SLUB for minimal memory footprint"
271	depends on SLUB && EXPERT
272	select SLAB_MERGE_DEFAULT
273	help
274	   Configures the SLUB allocator in a way to achieve minimal memory
275	   footprint, sacrificing scalability, debugging and other features.
276	   This is intended only for the smallest system that had used the
277	   SLOB allocator and is not recommended for systems with more than
278	   16MB RAM.
279
280	   If unsure, say N.
281
282config SLAB_MERGE_DEFAULT
283	bool "Allow slab caches to be merged"
284	default y
285	depends on SLAB || SLUB
286	help
287	  For reduced kernel memory fragmentation, slab caches can be
288	  merged when they share the same size and other characteristics.
289	  This carries a risk of kernel heap overflows being able to
290	  overwrite objects from merged caches (and more easily control
291	  cache layout), which makes such heap attacks easier to exploit
292	  by attackers. By keeping caches unmerged, these kinds of exploits
293	  can usually only damage objects in the same cache. To disable
294	  merging at runtime, "slab_nomerge" can be passed on the kernel
295	  command line.
296
297config SLAB_FREELIST_RANDOM
298	bool "Randomize slab freelist"
299	depends on SLAB || (SLUB && !SLUB_TINY)
300	help
301	  Randomizes the freelist order used on creating new pages. This
302	  security feature reduces the predictability of the kernel slab
303	  allocator against heap overflows.
304
305config SLAB_FREELIST_HARDENED
306	bool "Harden slab freelist metadata"
307	depends on SLAB || (SLUB && !SLUB_TINY)
308	help
309	  Many kernel heap attacks try to target slab cache metadata and
310	  other infrastructure. This options makes minor performance
311	  sacrifices to harden the kernel slab allocator against common
312	  freelist exploit methods. Some slab implementations have more
313	  sanity-checking than others. This option is most effective with
314	  CONFIG_SLUB.
315
316config SLUB_STATS
317	default n
318	bool "Enable SLUB performance statistics"
319	depends on SLUB && SYSFS && !SLUB_TINY
320	help
321	  SLUB statistics are useful to debug SLUBs allocation behavior in
322	  order find ways to optimize the allocator. This should never be
323	  enabled for production use since keeping statistics slows down
324	  the allocator by a few percentage points. The slabinfo command
325	  supports the determination of the most active slabs to figure
326	  out which slabs are relevant to a particular load.
327	  Try running: slabinfo -DA
328
329config SLUB_CPU_PARTIAL
330	default y
331	depends on SLUB && SMP && !SLUB_TINY
332	bool "SLUB per cpu partial cache"
333	help
334	  Per cpu partial caches accelerate objects allocation and freeing
335	  that is local to a processor at the price of more indeterminism
336	  in the latency of the free. On overflow these caches will be cleared
337	  which requires the taking of locks that may cause latency spikes.
338	  Typically one would choose no for a realtime system.
339
340endmenu # SLAB allocator options
341
342config SHUFFLE_PAGE_ALLOCATOR
343	bool "Page allocator randomization"
344	default SLAB_FREELIST_RANDOM && ACPI_NUMA
345	help
346	  Randomization of the page allocator improves the average
347	  utilization of a direct-mapped memory-side-cache. See section
348	  5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI
349	  6.2a specification for an example of how a platform advertises
350	  the presence of a memory-side-cache. There are also incidental
351	  security benefits as it reduces the predictability of page
352	  allocations to compliment SLAB_FREELIST_RANDOM, but the
353	  default granularity of shuffling on the MAX_ORDER i.e, 10th
354	  order of pages is selected based on cache utilization benefits
355	  on x86.
356
357	  While the randomization improves cache utilization it may
358	  negatively impact workloads on platforms without a cache. For
359	  this reason, by default, the randomization is enabled only
360	  after runtime detection of a direct-mapped memory-side-cache.
361	  Otherwise, the randomization may be force enabled with the
362	  'page_alloc.shuffle' kernel command line parameter.
363
364	  Say Y if unsure.
365
366config COMPAT_BRK
367	bool "Disable heap randomization"
368	default y
369	help
370	  Randomizing heap placement makes heap exploits harder, but it
371	  also breaks ancient binaries (including anything libc5 based).
372	  This option changes the bootup default to heap randomization
373	  disabled, and can be overridden at runtime by setting
374	  /proc/sys/kernel/randomize_va_space to 2.
375
376	  On non-ancient distros (post-2000 ones) N is usually a safe choice.
377
378config MMAP_ALLOW_UNINITIALIZED
379	bool "Allow mmapped anonymous memory to be uninitialized"
380	depends on EXPERT && !MMU
381	default n
382	help
383	  Normally, and according to the Linux spec, anonymous memory obtained
384	  from mmap() has its contents cleared before it is passed to
385	  userspace.  Enabling this config option allows you to request that
386	  mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
387	  providing a huge performance boost.  If this option is not enabled,
388	  then the flag will be ignored.
389
390	  This is taken advantage of by uClibc's malloc(), and also by
391	  ELF-FDPIC binfmt's brk and stack allocator.
392
393	  Because of the obvious security issues, this option should only be
394	  enabled on embedded devices where you control what is run in
395	  userspace.  Since that isn't generally a problem on no-MMU systems,
396	  it is normally safe to say Y here.
397
398	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
399
400config SELECT_MEMORY_MODEL
401	def_bool y
402	depends on ARCH_SELECT_MEMORY_MODEL
403
404choice
405	prompt "Memory model"
406	depends on SELECT_MEMORY_MODEL
407	default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
408	default FLATMEM_MANUAL
409	help
410	  This option allows you to change some of the ways that
411	  Linux manages its memory internally. Most users will
412	  only have one option here selected by the architecture
413	  configuration. This is normal.
414
415config FLATMEM_MANUAL
416	bool "Flat Memory"
417	depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE
418	help
419	  This option is best suited for non-NUMA systems with
420	  flat address space. The FLATMEM is the most efficient
421	  system in terms of performance and resource consumption
422	  and it is the best option for smaller systems.
423
424	  For systems that have holes in their physical address
425	  spaces and for features like NUMA and memory hotplug,
426	  choose "Sparse Memory".
427
428	  If unsure, choose this option (Flat Memory) over any other.
429
430config SPARSEMEM_MANUAL
431	bool "Sparse Memory"
432	depends on ARCH_SPARSEMEM_ENABLE
433	help
434	  This will be the only option for some systems, including
435	  memory hot-plug systems.  This is normal.
436
437	  This option provides efficient support for systems with
438	  holes is their physical address space and allows memory
439	  hot-plug and hot-remove.
440
441	  If unsure, choose "Flat Memory" over this option.
442
443endchoice
444
445config SPARSEMEM
446	def_bool y
447	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
448
449config FLATMEM
450	def_bool y
451	depends on !SPARSEMEM || FLATMEM_MANUAL
452
453#
454# SPARSEMEM_EXTREME (which is the default) does some bootmem
455# allocations when sparse_init() is called.  If this cannot
456# be done on your architecture, select this option.  However,
457# statically allocating the mem_section[] array can potentially
458# consume vast quantities of .bss, so be careful.
459#
460# This option will also potentially produce smaller runtime code
461# with gcc 3.4 and later.
462#
463config SPARSEMEM_STATIC
464	bool
465
466#
467# Architecture platforms which require a two level mem_section in SPARSEMEM
468# must select this option. This is usually for architecture platforms with
469# an extremely sparse physical address space.
470#
471config SPARSEMEM_EXTREME
472	def_bool y
473	depends on SPARSEMEM && !SPARSEMEM_STATIC
474
475config SPARSEMEM_VMEMMAP_ENABLE
476	bool
477
478config SPARSEMEM_VMEMMAP
479	bool "Sparse Memory virtual memmap"
480	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
481	default y
482	help
483	  SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
484	  pfn_to_page and page_to_pfn operations.  This is the most
485	  efficient option when sufficient kernel resources are available.
486#
487# Select this config option from the architecture Kconfig, if it is preferred
488# to enable the feature of HugeTLB/dev_dax vmemmap optimization.
489#
490config ARCH_WANT_OPTIMIZE_VMEMMAP
491	bool
492
493config HAVE_MEMBLOCK_PHYS_MAP
494	bool
495
496config HAVE_FAST_GUP
497	depends on MMU
498	bool
499
500# Don't discard allocated memory used to track "memory" and "reserved" memblocks
501# after early boot, so it can still be used to test for validity of memory.
502# Also, memblocks are updated with memory hot(un)plug.
503config ARCH_KEEP_MEMBLOCK
504	bool
505
506# Keep arch NUMA mapping infrastructure post-init.
507config NUMA_KEEP_MEMINFO
508	bool
509
510config MEMORY_ISOLATION
511	bool
512
513# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked
514# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via
515# /dev/mem.
516config EXCLUSIVE_SYSTEM_RAM
517	def_bool y
518	depends on !DEVMEM || STRICT_DEVMEM
519
520#
521# Only be set on architectures that have completely implemented memory hotplug
522# feature. If you are not sure, don't touch it.
523#
524config HAVE_BOOTMEM_INFO_NODE
525	def_bool n
526
527config ARCH_ENABLE_MEMORY_HOTPLUG
528	bool
529
530config ARCH_ENABLE_MEMORY_HOTREMOVE
531	bool
532
533# eventually, we can have this option just 'select SPARSEMEM'
534menuconfig MEMORY_HOTPLUG
535	bool "Memory hotplug"
536	select MEMORY_ISOLATION
537	depends on SPARSEMEM
538	depends on ARCH_ENABLE_MEMORY_HOTPLUG
539	depends on 64BIT
540	select NUMA_KEEP_MEMINFO if NUMA
541
542if MEMORY_HOTPLUG
543
544config MEMORY_HOTPLUG_DEFAULT_ONLINE
545	bool "Online the newly added memory blocks by default"
546	depends on MEMORY_HOTPLUG
547	help
548	  This option sets the default policy setting for memory hotplug
549	  onlining policy (/sys/devices/system/memory/auto_online_blocks) which
550	  determines what happens to newly added memory regions. Policy setting
551	  can always be changed at runtime.
552	  See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
553
554	  Say Y here if you want all hot-plugged memory blocks to appear in
555	  'online' state by default.
556	  Say N here if you want the default policy to keep all hot-plugged
557	  memory blocks in 'offline' state.
558
559config MEMORY_HOTREMOVE
560	bool "Allow for memory hot remove"
561	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
562	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
563	depends on MIGRATION
564
565config MHP_MEMMAP_ON_MEMORY
566	def_bool y
567	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
568	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
569
570endif # MEMORY_HOTPLUG
571
572# Heavily threaded applications may benefit from splitting the mm-wide
573# page_table_lock, so that faults on different parts of the user address
574# space can be handled with less contention: split it at this NR_CPUS.
575# Default to 4 for wider testing, though 8 might be more appropriate.
576# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
577# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
578# SPARC32 allocates multiple pte tables within a single page, and therefore
579# a per-page lock leads to problems when multiple tables need to be locked
580# at the same time (e.g. copy_page_range()).
581# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
582#
583config SPLIT_PTLOCK_CPUS
584	int
585	default "999999" if !MMU
586	default "999999" if ARM && !CPU_CACHE_VIPT
587	default "999999" if PARISC && !PA20
588	default "999999" if SPARC32
589	default "4"
590
591config ARCH_ENABLE_SPLIT_PMD_PTLOCK
592	bool
593
594#
595# support for memory balloon
596config MEMORY_BALLOON
597	bool
598
599#
600# support for memory balloon compaction
601config BALLOON_COMPACTION
602	bool "Allow for balloon memory compaction/migration"
603	def_bool y
604	depends on COMPACTION && MEMORY_BALLOON
605	help
606	  Memory fragmentation introduced by ballooning might reduce
607	  significantly the number of 2MB contiguous memory blocks that can be
608	  used within a guest, thus imposing performance penalties associated
609	  with the reduced number of transparent huge pages that could be used
610	  by the guest workload. Allowing the compaction & migration for memory
611	  pages enlisted as being part of memory balloon devices avoids the
612	  scenario aforementioned and helps improving memory defragmentation.
613
614#
615# support for memory compaction
616config COMPACTION
617	bool "Allow for memory compaction"
618	def_bool y
619	select MIGRATION
620	depends on MMU
621	help
622	  Compaction is the only memory management component to form
623	  high order (larger physically contiguous) memory blocks
624	  reliably. The page allocator relies on compaction heavily and
625	  the lack of the feature can lead to unexpected OOM killer
626	  invocations for high order memory requests. You shouldn't
627	  disable this option unless there really is a strong reason for
628	  it and then we would be really interested to hear about that at
629	  linux-mm@kvack.org.
630
631config COMPACT_UNEVICTABLE_DEFAULT
632	int
633	depends on COMPACTION
634	default 0 if PREEMPT_RT
635	default 1
636
637#
638# support for free page reporting
639config PAGE_REPORTING
640	bool "Free page reporting"
641	def_bool n
642	help
643	  Free page reporting allows for the incremental acquisition of
644	  free pages from the buddy allocator for the purpose of reporting
645	  those pages to another entity, such as a hypervisor, so that the
646	  memory can be freed within the host for other uses.
647
648#
649# support for page migration
650#
651config MIGRATION
652	bool "Page migration"
653	def_bool y
654	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
655	help
656	  Allows the migration of the physical location of pages of processes
657	  while the virtual addresses are not changed. This is useful in
658	  two situations. The first is on NUMA systems to put pages nearer
659	  to the processors accessing. The second is when allocating huge
660	  pages as migration can relocate pages to satisfy a huge page
661	  allocation instead of reclaiming.
662
663config DEVICE_MIGRATION
664	def_bool MIGRATION && ZONE_DEVICE
665
666config ARCH_ENABLE_HUGEPAGE_MIGRATION
667	bool
668
669config ARCH_ENABLE_THP_MIGRATION
670	bool
671
672config HUGETLB_PAGE_SIZE_VARIABLE
673	def_bool n
674	help
675	  Allows the pageblock_order value to be dynamic instead of just standard
676	  HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
677	  on a platform.
678
679	  Note that the pageblock_order cannot exceed MAX_ORDER and will be
680	  clamped down to MAX_ORDER.
681
682config CONTIG_ALLOC
683	def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
684
685config PHYS_ADDR_T_64BIT
686	def_bool 64BIT
687
688config BOUNCE
689	bool "Enable bounce buffers"
690	default y
691	depends on BLOCK && MMU && HIGHMEM
692	help
693	  Enable bounce buffers for devices that cannot access the full range of
694	  memory available to the CPU. Enabled by default when HIGHMEM is
695	  selected, but you may say n to override this.
696
697config MMU_NOTIFIER
698	bool
699	select INTERVAL_TREE
700
701config KSM
702	bool "Enable KSM for page merging"
703	depends on MMU
704	select XXHASH
705	help
706	  Enable Kernel Samepage Merging: KSM periodically scans those areas
707	  of an application's address space that an app has advised may be
708	  mergeable.  When it finds pages of identical content, it replaces
709	  the many instances by a single page with that content, so
710	  saving memory until one or another app needs to modify the content.
711	  Recommended for use with KVM, or with other duplicative applications.
712	  See Documentation/mm/ksm.rst for more information: KSM is inactive
713	  until a program has madvised that an area is MADV_MERGEABLE, and
714	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
715
716config DEFAULT_MMAP_MIN_ADDR
717	int "Low address space to protect from user allocation"
718	depends on MMU
719	default 4096
720	help
721	  This is the portion of low virtual memory which should be protected
722	  from userspace allocation.  Keeping a user from writing to low pages
723	  can help reduce the impact of kernel NULL pointer bugs.
724
725	  For most ia64, ppc64 and x86 users with lots of address space
726	  a value of 65536 is reasonable and should cause no problems.
727	  On arm and other archs it should not be higher than 32768.
728	  Programs which use vm86 functionality or have some need to map
729	  this low address space will need CAP_SYS_RAWIO or disable this
730	  protection by setting the value to 0.
731
732	  This value can be changed after boot using the
733	  /proc/sys/vm/mmap_min_addr tunable.
734
735config ARCH_SUPPORTS_MEMORY_FAILURE
736	bool
737
738config MEMORY_FAILURE
739	depends on MMU
740	depends on ARCH_SUPPORTS_MEMORY_FAILURE
741	bool "Enable recovery from hardware memory errors"
742	select MEMORY_ISOLATION
743	select RAS
744	help
745	  Enables code to recover from some memory failures on systems
746	  with MCA recovery. This allows a system to continue running
747	  even when some of its memory has uncorrected errors. This requires
748	  special hardware support and typically ECC memory.
749
750config HWPOISON_INJECT
751	tristate "HWPoison pages injector"
752	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
753	select PROC_PAGE_MONITOR
754
755config NOMMU_INITIAL_TRIM_EXCESS
756	int "Turn on mmap() excess space trimming before booting"
757	depends on !MMU
758	default 1
759	help
760	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
761	  of memory on which to store mappings, but it can only ask the system
762	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
763	  more than it requires.  To deal with this, mmap() is able to trim off
764	  the excess and return it to the allocator.
765
766	  If trimming is enabled, the excess is trimmed off and returned to the
767	  system allocator, which can cause extra fragmentation, particularly
768	  if there are a lot of transient processes.
769
770	  If trimming is disabled, the excess is kept, but not used, which for
771	  long-term mappings means that the space is wasted.
772
773	  Trimming can be dynamically controlled through a sysctl option
774	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
775	  excess pages there must be before trimming should occur, or zero if
776	  no trimming is to occur.
777
778	  This option specifies the initial value of this option.  The default
779	  of 1 says that all excess pages should be trimmed.
780
781	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
782
783config ARCH_WANT_GENERAL_HUGETLB
784	bool
785
786config ARCH_WANTS_THP_SWAP
787	def_bool n
788
789menuconfig TRANSPARENT_HUGEPAGE
790	bool "Transparent Hugepage Support"
791	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT
792	select COMPACTION
793	select XARRAY_MULTI
794	help
795	  Transparent Hugepages allows the kernel to use huge pages and
796	  huge tlb transparently to the applications whenever possible.
797	  This feature can improve computing performance to certain
798	  applications by speeding up page faults during memory
799	  allocation, by reducing the number of tlb misses and by speeding
800	  up the pagetable walking.
801
802	  If memory constrained on embedded, you may want to say N.
803
804if TRANSPARENT_HUGEPAGE
805
806choice
807	prompt "Transparent Hugepage Support sysfs defaults"
808	depends on TRANSPARENT_HUGEPAGE
809	default TRANSPARENT_HUGEPAGE_ALWAYS
810	help
811	  Selects the sysfs defaults for Transparent Hugepage Support.
812
813	config TRANSPARENT_HUGEPAGE_ALWAYS
814		bool "always"
815	help
816	  Enabling Transparent Hugepage always, can increase the
817	  memory footprint of applications without a guaranteed
818	  benefit but it will work automatically for all applications.
819
820	config TRANSPARENT_HUGEPAGE_MADVISE
821		bool "madvise"
822	help
823	  Enabling Transparent Hugepage madvise, will only provide a
824	  performance improvement benefit to the applications using
825	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
826	  memory footprint of applications without a guaranteed
827	  benefit.
828endchoice
829
830config THP_SWAP
831	def_bool y
832	depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT
833	help
834	  Swap transparent huge pages in one piece, without splitting.
835	  XXX: For now, swap cluster backing transparent huge page
836	  will be split after swapout.
837
838	  For selection by architectures with reasonable THP sizes.
839
840config READ_ONLY_THP_FOR_FS
841	bool "Read-only THP for filesystems (EXPERIMENTAL)"
842	depends on TRANSPARENT_HUGEPAGE && SHMEM
843
844	help
845	  Allow khugepaged to put read-only file-backed pages in THP.
846
847	  This is marked experimental because it is a new feature. Write
848	  support of file THPs will be developed in the next few release
849	  cycles.
850
851endif # TRANSPARENT_HUGEPAGE
852
853#
854# UP and nommu archs use km based percpu allocator
855#
856config NEED_PER_CPU_KM
857	depends on !SMP || !MMU
858	bool
859	default y
860
861config NEED_PER_CPU_EMBED_FIRST_CHUNK
862	bool
863
864config NEED_PER_CPU_PAGE_FIRST_CHUNK
865	bool
866
867config USE_PERCPU_NUMA_NODE_ID
868	bool
869
870config HAVE_SETUP_PER_CPU_AREA
871	bool
872
873config FRONTSWAP
874	bool
875
876config CMA
877	bool "Contiguous Memory Allocator"
878	depends on MMU
879	select MIGRATION
880	select MEMORY_ISOLATION
881	help
882	  This enables the Contiguous Memory Allocator which allows other
883	  subsystems to allocate big physically-contiguous blocks of memory.
884	  CMA reserves a region of memory and allows only movable pages to
885	  be allocated from it. This way, the kernel can use the memory for
886	  pagecache and when a subsystem requests for contiguous area, the
887	  allocated pages are migrated away to serve the contiguous request.
888
889	  If unsure, say "n".
890
891config CMA_DEBUG
892	bool "CMA debug messages (DEVELOPMENT)"
893	depends on DEBUG_KERNEL && CMA
894	help
895	  Turns on debug messages in CMA.  This produces KERN_DEBUG
896	  messages for every CMA call as well as various messages while
897	  processing calls such as dma_alloc_from_contiguous().
898	  This option does not affect warning and error messages.
899
900config CMA_DEBUGFS
901	bool "CMA debugfs interface"
902	depends on CMA && DEBUG_FS
903	help
904	  Turns on the DebugFS interface for CMA.
905
906config CMA_SYSFS
907	bool "CMA information through sysfs interface"
908	depends on CMA && SYSFS
909	help
910	  This option exposes some sysfs attributes to get information
911	  from CMA.
912
913config CMA_AREAS
914	int "Maximum count of the CMA areas"
915	depends on CMA
916	default 19 if NUMA
917	default 7
918	help
919	  CMA allows to create CMA areas for particular purpose, mainly,
920	  used as device private area. This parameter sets the maximum
921	  number of CMA area in the system.
922
923	  If unsure, leave the default value "7" in UMA and "19" in NUMA.
924
925config MEM_SOFT_DIRTY
926	bool "Track memory changes"
927	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
928	select PROC_PAGE_MONITOR
929	help
930	  This option enables memory changes tracking by introducing a
931	  soft-dirty bit on pte-s. This bit it set when someone writes
932	  into a page just as regular dirty bit, but unlike the latter
933	  it can be cleared by hands.
934
935	  See Documentation/admin-guide/mm/soft-dirty.rst for more details.
936
937config GENERIC_EARLY_IOREMAP
938	bool
939
940config STACK_MAX_DEFAULT_SIZE_MB
941	int "Default maximum user stack size for 32-bit processes (MB)"
942	default 100
943	range 8 2048
944	depends on STACK_GROWSUP && (!64BIT || COMPAT)
945	help
946	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
947	  user processes when the stack grows upwards (currently only on parisc
948	  arch) when the RLIMIT_STACK hard limit is unlimited.
949
950	  A sane initial value is 100 MB.
951
952config DEFERRED_STRUCT_PAGE_INIT
953	bool "Defer initialisation of struct pages to kthreads"
954	depends on SPARSEMEM
955	depends on !NEED_PER_CPU_KM
956	depends on 64BIT
957	select PADATA
958	help
959	  Ordinarily all struct pages are initialised during early boot in a
960	  single thread. On very large machines this can take a considerable
961	  amount of time. If this option is set, large machines will bring up
962	  a subset of memmap at boot and then initialise the rest in parallel.
963	  This has a potential performance impact on tasks running early in the
964	  lifetime of the system until these kthreads finish the
965	  initialisation.
966
967config PAGE_IDLE_FLAG
968	bool
969	select PAGE_EXTENSION if !64BIT
970	help
971	  This adds PG_idle and PG_young flags to 'struct page'.  PTE Accessed
972	  bit writers can set the state of the bit in the flags so that PTE
973	  Accessed bit readers may avoid disturbance.
974
975config IDLE_PAGE_TRACKING
976	bool "Enable idle page tracking"
977	depends on SYSFS && MMU
978	select PAGE_IDLE_FLAG
979	help
980	  This feature allows to estimate the amount of user pages that have
981	  not been touched during a given period of time. This information can
982	  be useful to tune memory cgroup limits and/or for job placement
983	  within a compute cluster.
984
985	  See Documentation/admin-guide/mm/idle_page_tracking.rst for
986	  more details.
987
988config ARCH_HAS_CACHE_LINE_SIZE
989	bool
990
991config ARCH_HAS_CURRENT_STACK_POINTER
992	bool
993	help
994	  In support of HARDENED_USERCOPY performing stack variable lifetime
995	  checking, an architecture-agnostic way to find the stack pointer
996	  is needed. Once an architecture defines an unsigned long global
997	  register alias named "current_stack_pointer", this config can be
998	  selected.
999
1000config ARCH_HAS_PTE_DEVMAP
1001	bool
1002
1003config ARCH_HAS_ZONE_DMA_SET
1004	bool
1005
1006config ZONE_DMA
1007	bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET
1008	default y if ARM64 || X86
1009
1010config ZONE_DMA32
1011	bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET
1012	depends on !X86_32
1013	default y if ARM64
1014
1015config ZONE_DEVICE
1016	bool "Device memory (pmem, HMM, etc...) hotplug support"
1017	depends on MEMORY_HOTPLUG
1018	depends on MEMORY_HOTREMOVE
1019	depends on SPARSEMEM_VMEMMAP
1020	depends on ARCH_HAS_PTE_DEVMAP
1021	select XARRAY_MULTI
1022
1023	help
1024	  Device memory hotplug support allows for establishing pmem,
1025	  or other device driver discovered memory regions, in the
1026	  memmap. This allows pfn_to_page() lookups of otherwise
1027	  "device-physical" addresses which is needed for using a DAX
1028	  mapping in an O_DIRECT operation, among other things.
1029
1030	  If FS_DAX is enabled, then say Y.
1031
1032#
1033# Helpers to mirror range of the CPU page tables of a process into device page
1034# tables.
1035#
1036config HMM_MIRROR
1037	bool
1038	depends on MMU
1039
1040config GET_FREE_REGION
1041	depends on SPARSEMEM
1042	bool
1043
1044config DEVICE_PRIVATE
1045	bool "Unaddressable device memory (GPU memory, ...)"
1046	depends on ZONE_DEVICE
1047	select GET_FREE_REGION
1048
1049	help
1050	  Allows creation of struct pages to represent unaddressable device
1051	  memory; i.e., memory that is only accessible from the device (or
1052	  group of devices). You likely also want to select HMM_MIRROR.
1053
1054config VMAP_PFN
1055	bool
1056
1057config ARCH_USES_HIGH_VMA_FLAGS
1058	bool
1059config ARCH_HAS_PKEYS
1060	bool
1061
1062config ARCH_USES_PG_ARCH_X
1063	bool
1064	help
1065	  Enable the definition of PG_arch_x page flags with x > 1. Only
1066	  suitable for 64-bit architectures with CONFIG_FLATMEM or
1067	  CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be
1068	  enough room for additional bits in page->flags.
1069
1070config VM_EVENT_COUNTERS
1071	default y
1072	bool "Enable VM event counters for /proc/vmstat" if EXPERT
1073	help
1074	  VM event counters are needed for event counts to be shown.
1075	  This option allows the disabling of the VM event counters
1076	  on EXPERT systems.  /proc/vmstat will only show page counts
1077	  if VM event counters are disabled.
1078
1079config PERCPU_STATS
1080	bool "Collect percpu memory statistics"
1081	help
1082	  This feature collects and exposes statistics via debugfs. The
1083	  information includes global and per chunk statistics, which can
1084	  be used to help understand percpu memory usage.
1085
1086config GUP_TEST
1087	bool "Enable infrastructure for get_user_pages()-related unit tests"
1088	depends on DEBUG_FS
1089	help
1090	  Provides /sys/kernel/debug/gup_test, which in turn provides a way
1091	  to make ioctl calls that can launch kernel-based unit tests for
1092	  the get_user_pages*() and pin_user_pages*() family of API calls.
1093
1094	  These tests include benchmark testing of the _fast variants of
1095	  get_user_pages*() and pin_user_pages*(), as well as smoke tests of
1096	  the non-_fast variants.
1097
1098	  There is also a sub-test that allows running dump_page() on any
1099	  of up to eight pages (selected by command line args) within the
1100	  range of user-space addresses. These pages are either pinned via
1101	  pin_user_pages*(), or pinned via get_user_pages*(), as specified
1102	  by other command line arguments.
1103
1104	  See tools/testing/selftests/mm/gup_test.c
1105
1106comment "GUP_TEST needs to have DEBUG_FS enabled"
1107	depends on !GUP_TEST && !DEBUG_FS
1108
1109config GUP_GET_PXX_LOW_HIGH
1110	bool
1111
1112config DMAPOOL_TEST
1113	tristate "Enable a module to run time tests on dma_pool"
1114	depends on HAS_DMA
1115	help
1116	  Provides a test module that will allocate and free many blocks of
1117	  various sizes and report how long it takes. This is intended to
1118	  provide a consistent way to measure how changes to the
1119	  dma_pool_alloc/free routines affect performance.
1120
1121config ARCH_HAS_PTE_SPECIAL
1122	bool
1123
1124#
1125# Some architectures require a special hugepage directory format that is
1126# required to support multiple hugepage sizes. For example a4fe3ce76
1127# "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
1128# introduced it on powerpc.  This allows for a more flexible hugepage
1129# pagetable layouts.
1130#
1131config ARCH_HAS_HUGEPD
1132	bool
1133
1134config MAPPING_DIRTY_HELPERS
1135        bool
1136
1137config KMAP_LOCAL
1138	bool
1139
1140config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
1141	bool
1142
1143# struct io_mapping based helper.  Selected by drivers that need them
1144config IO_MAPPING
1145	bool
1146
1147config SECRETMEM
1148	default y
1149	bool "Enable memfd_secret() system call" if EXPERT
1150	depends on ARCH_HAS_SET_DIRECT_MAP
1151	help
1152	  Enable the memfd_secret() system call with the ability to create
1153	  memory areas visible only in the context of the owning process and
1154	  not mapped to other processes and other kernel page tables.
1155
1156config ANON_VMA_NAME
1157	bool "Anonymous VMA name support"
1158	depends on PROC_FS && ADVISE_SYSCALLS && MMU
1159
1160	help
1161	  Allow naming anonymous virtual memory areas.
1162
1163	  This feature allows assigning names to virtual memory areas. Assigned
1164	  names can be later retrieved from /proc/pid/maps and /proc/pid/smaps
1165	  and help identifying individual anonymous memory areas.
1166	  Assigning a name to anonymous virtual memory area might prevent that
1167	  area from being merged with adjacent virtual memory areas due to the
1168	  difference in their name.
1169
1170config USERFAULTFD
1171	bool "Enable userfaultfd() system call"
1172	depends on MMU
1173	help
1174	  Enable the userfaultfd() system call that allows to intercept and
1175	  handle page faults in userland.
1176
1177config HAVE_ARCH_USERFAULTFD_WP
1178	bool
1179	help
1180	  Arch has userfaultfd write protection support
1181
1182config HAVE_ARCH_USERFAULTFD_MINOR
1183	bool
1184	help
1185	  Arch has userfaultfd minor fault support
1186
1187config PTE_MARKER_UFFD_WP
1188	bool "Userfaultfd write protection support for shmem/hugetlbfs"
1189	default y
1190	depends on HAVE_ARCH_USERFAULTFD_WP
1191
1192	help
1193	  Allows to create marker PTEs for userfaultfd write protection
1194	  purposes.  It is required to enable userfaultfd write protection on
1195	  file-backed memory types like shmem and hugetlbfs.
1196
1197# multi-gen LRU {
1198config LRU_GEN
1199	bool "Multi-Gen LRU"
1200	depends on MMU
1201	# make sure folio->flags has enough spare bits
1202	depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP
1203	help
1204	  A high performance LRU implementation to overcommit memory. See
1205	  Documentation/admin-guide/mm/multigen_lru.rst for details.
1206
1207config LRU_GEN_ENABLED
1208	bool "Enable by default"
1209	depends on LRU_GEN
1210	help
1211	  This option enables the multi-gen LRU by default.
1212
1213config LRU_GEN_STATS
1214	bool "Full stats for debugging"
1215	depends on LRU_GEN
1216	help
1217	  Do not enable this option unless you plan to look at historical stats
1218	  from evicted generations for debugging purpose.
1219
1220	  This option has a per-memcg and per-node memory overhead.
1221# }
1222
1223config ARCH_SUPPORTS_PER_VMA_LOCK
1224       def_bool n
1225
1226config PER_VMA_LOCK
1227	def_bool y
1228	depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP
1229	help
1230	  Allow per-vma locking during page fault handling.
1231
1232	  This feature allows locking each virtual memory area separately when
1233	  handling page faults instead of taking mmap_lock.
1234
1235config LOCK_MM_AND_FIND_VMA
1236	bool
1237	depends on !STACK_GROWSUP
1238
1239source "mm/damon/Kconfig"
1240
1241endmenu
1242