xref: /openbmc/linux/mm/Kconfig (revision 5fc3037a)
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
49choice
50	prompt "Default compressor"
51	depends on ZSWAP
52	default ZSWAP_COMPRESSOR_DEFAULT_LZO
53	help
54	  Selects the default compression algorithm for the compressed cache
55	  for swap pages.
56
57	  For an overview what kind of performance can be expected from
58	  a particular compression algorithm please refer to the benchmarks
59	  available at the following LWN page:
60	  https://lwn.net/Articles/751795/
61
62	  If in doubt, select 'LZO'.
63
64	  The selection made here can be overridden by using the kernel
65	  command line 'zswap.compressor=' option.
66
67config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
68	bool "Deflate"
69	select CRYPTO_DEFLATE
70	help
71	  Use the Deflate algorithm as the default compression algorithm.
72
73config ZSWAP_COMPRESSOR_DEFAULT_LZO
74	bool "LZO"
75	select CRYPTO_LZO
76	help
77	  Use the LZO algorithm as the default compression algorithm.
78
79config ZSWAP_COMPRESSOR_DEFAULT_842
80	bool "842"
81	select CRYPTO_842
82	help
83	  Use the 842 algorithm as the default compression algorithm.
84
85config ZSWAP_COMPRESSOR_DEFAULT_LZ4
86	bool "LZ4"
87	select CRYPTO_LZ4
88	help
89	  Use the LZ4 algorithm as the default compression algorithm.
90
91config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
92	bool "LZ4HC"
93	select CRYPTO_LZ4HC
94	help
95	  Use the LZ4HC algorithm as the default compression algorithm.
96
97config ZSWAP_COMPRESSOR_DEFAULT_ZSTD
98	bool "zstd"
99	select CRYPTO_ZSTD
100	help
101	  Use the zstd algorithm as the default compression algorithm.
102endchoice
103
104config ZSWAP_COMPRESSOR_DEFAULT
105       string
106       depends on ZSWAP
107       default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
108       default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO
109       default "842" if ZSWAP_COMPRESSOR_DEFAULT_842
110       default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4
111       default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
112       default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD
113       default ""
114
115choice
116	prompt "Default allocator"
117	depends on ZSWAP
118	default ZSWAP_ZPOOL_DEFAULT_ZBUD
119	help
120	  Selects the default allocator for the compressed cache for
121	  swap pages.
122	  The default is 'zbud' for compatibility, however please do
123	  read the description of each of the allocators below before
124	  making a right choice.
125
126	  The selection made here can be overridden by using the kernel
127	  command line 'zswap.zpool=' option.
128
129config ZSWAP_ZPOOL_DEFAULT_ZBUD
130	bool "zbud"
131	select ZBUD
132	help
133	  Use the zbud allocator as the default allocator.
134
135config ZSWAP_ZPOOL_DEFAULT_Z3FOLD
136	bool "z3fold"
137	select Z3FOLD
138	help
139	  Use the z3fold allocator as the default allocator.
140
141config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
142	bool "zsmalloc"
143	select ZSMALLOC
144	help
145	  Use the zsmalloc allocator as the default allocator.
146endchoice
147
148config ZSWAP_ZPOOL_DEFAULT
149       string
150       depends on ZSWAP
151       default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD
152       default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD
153       default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
154       default ""
155
156config ZBUD
157	tristate "2:1 compression allocator (zbud)"
158	depends on ZSWAP
159	help
160	  A special purpose allocator for storing compressed pages.
161	  It is designed to store up to two compressed pages per physical
162	  page.  While this design limits storage density, it has simple and
163	  deterministic reclaim properties that make it preferable to a higher
164	  density approach when reclaim will be used.
165
166config Z3FOLD
167	tristate "3:1 compression allocator (z3fold)"
168	depends on ZSWAP
169	help
170	  A special purpose allocator for storing compressed pages.
171	  It is designed to store up to three compressed pages per physical
172	  page. It is a ZBUD derivative so the simplicity and determinism are
173	  still there.
174
175config ZSMALLOC
176	tristate
177	prompt "N:1 compression allocator (zsmalloc)" if ZSWAP
178	depends on MMU
179	help
180	  zsmalloc is a slab-based memory allocator designed to store
181	  pages of various compression levels efficiently. It achieves
182	  the highest storage density with the least amount of fragmentation.
183
184config ZSMALLOC_STAT
185	bool "Export zsmalloc statistics"
186	depends on ZSMALLOC
187	select DEBUG_FS
188	help
189	  This option enables code in the zsmalloc to collect various
190	  statistics about what's happening in zsmalloc and exports that
191	  information to userspace via debugfs.
192	  If unsure, say N.
193
194menu "SLAB allocator options"
195
196choice
197	prompt "Choose SLAB allocator"
198	default SLUB
199	help
200	   This option allows to select a slab allocator.
201
202config SLAB
203	bool "SLAB"
204	depends on !PREEMPT_RT
205	select HAVE_HARDENED_USERCOPY_ALLOCATOR
206	help
207	  The regular slab allocator that is established and known to work
208	  well in all environments. It organizes cache hot objects in
209	  per cpu and per node queues.
210
211config SLUB
212	bool "SLUB (Unqueued Allocator)"
213	select HAVE_HARDENED_USERCOPY_ALLOCATOR
214	help
215	   SLUB is a slab allocator that minimizes cache line usage
216	   instead of managing queues of cached objects (SLAB approach).
217	   Per cpu caching is realized using slabs of objects instead
218	   of queues of objects. SLUB can use memory efficiently
219	   and has enhanced diagnostics. SLUB is the default choice for
220	   a slab allocator.
221
222config SLOB_DEPRECATED
223	depends on EXPERT
224	bool "SLOB (Simple Allocator - DEPRECATED)"
225	depends on !PREEMPT_RT
226	help
227	   Deprecated and scheduled for removal in a few cycles. SLUB
228	   recommended as replacement. CONFIG_SLUB_TINY can be considered
229	   on systems with 16MB or less RAM.
230
231	   If you need SLOB to stay, please contact linux-mm@kvack.org and
232	   people listed in the SLAB ALLOCATOR section of MAINTAINERS file,
233	   with your use case.
234
235	   SLOB replaces the stock allocator with a drastically simpler
236	   allocator. SLOB is generally more space efficient but
237	   does not perform as well on large systems.
238
239endchoice
240
241config SLOB
242	bool
243	default y
244	depends on SLOB_DEPRECATED
245
246config SLUB_TINY
247	bool "Configure SLUB for minimal memory footprint"
248	depends on SLUB && EXPERT
249	select SLAB_MERGE_DEFAULT
250	help
251	   Configures the SLUB allocator in a way to achieve minimal memory
252	   footprint, sacrificing scalability, debugging and other features.
253	   This is intended only for the smallest system that had used the
254	   SLOB allocator and is not recommended for systems with more than
255	   16MB RAM.
256
257	   If unsure, say N.
258
259config SLAB_MERGE_DEFAULT
260	bool "Allow slab caches to be merged"
261	default y
262	depends on SLAB || SLUB
263	help
264	  For reduced kernel memory fragmentation, slab caches can be
265	  merged when they share the same size and other characteristics.
266	  This carries a risk of kernel heap overflows being able to
267	  overwrite objects from merged caches (and more easily control
268	  cache layout), which makes such heap attacks easier to exploit
269	  by attackers. By keeping caches unmerged, these kinds of exploits
270	  can usually only damage objects in the same cache. To disable
271	  merging at runtime, "slab_nomerge" can be passed on the kernel
272	  command line.
273
274config SLAB_FREELIST_RANDOM
275	bool "Randomize slab freelist"
276	depends on SLAB || (SLUB && !SLUB_TINY)
277	help
278	  Randomizes the freelist order used on creating new pages. This
279	  security feature reduces the predictability of the kernel slab
280	  allocator against heap overflows.
281
282config SLAB_FREELIST_HARDENED
283	bool "Harden slab freelist metadata"
284	depends on SLAB || (SLUB && !SLUB_TINY)
285	help
286	  Many kernel heap attacks try to target slab cache metadata and
287	  other infrastructure. This options makes minor performance
288	  sacrifices to harden the kernel slab allocator against common
289	  freelist exploit methods. Some slab implementations have more
290	  sanity-checking than others. This option is most effective with
291	  CONFIG_SLUB.
292
293config SLUB_STATS
294	default n
295	bool "Enable SLUB performance statistics"
296	depends on SLUB && SYSFS && !SLUB_TINY
297	help
298	  SLUB statistics are useful to debug SLUBs allocation behavior in
299	  order find ways to optimize the allocator. This should never be
300	  enabled for production use since keeping statistics slows down
301	  the allocator by a few percentage points. The slabinfo command
302	  supports the determination of the most active slabs to figure
303	  out which slabs are relevant to a particular load.
304	  Try running: slabinfo -DA
305
306config SLUB_CPU_PARTIAL
307	default y
308	depends on SLUB && SMP && !SLUB_TINY
309	bool "SLUB per cpu partial cache"
310	help
311	  Per cpu partial caches accelerate objects allocation and freeing
312	  that is local to a processor at the price of more indeterminism
313	  in the latency of the free. On overflow these caches will be cleared
314	  which requires the taking of locks that may cause latency spikes.
315	  Typically one would choose no for a realtime system.
316
317endmenu # SLAB allocator options
318
319config SHUFFLE_PAGE_ALLOCATOR
320	bool "Page allocator randomization"
321	default SLAB_FREELIST_RANDOM && ACPI_NUMA
322	help
323	  Randomization of the page allocator improves the average
324	  utilization of a direct-mapped memory-side-cache. See section
325	  5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI
326	  6.2a specification for an example of how a platform advertises
327	  the presence of a memory-side-cache. There are also incidental
328	  security benefits as it reduces the predictability of page
329	  allocations to compliment SLAB_FREELIST_RANDOM, but the
330	  default granularity of shuffling on the "MAX_ORDER - 1" i.e,
331	  10th order of pages is selected based on cache utilization
332	  benefits on x86.
333
334	  While the randomization improves cache utilization it may
335	  negatively impact workloads on platforms without a cache. For
336	  this reason, by default, the randomization is enabled only
337	  after runtime detection of a direct-mapped memory-side-cache.
338	  Otherwise, the randomization may be force enabled with the
339	  'page_alloc.shuffle' kernel command line parameter.
340
341	  Say Y if unsure.
342
343config COMPAT_BRK
344	bool "Disable heap randomization"
345	default y
346	help
347	  Randomizing heap placement makes heap exploits harder, but it
348	  also breaks ancient binaries (including anything libc5 based).
349	  This option changes the bootup default to heap randomization
350	  disabled, and can be overridden at runtime by setting
351	  /proc/sys/kernel/randomize_va_space to 2.
352
353	  On non-ancient distros (post-2000 ones) N is usually a safe choice.
354
355config MMAP_ALLOW_UNINITIALIZED
356	bool "Allow mmapped anonymous memory to be uninitialized"
357	depends on EXPERT && !MMU
358	default n
359	help
360	  Normally, and according to the Linux spec, anonymous memory obtained
361	  from mmap() has its contents cleared before it is passed to
362	  userspace.  Enabling this config option allows you to request that
363	  mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
364	  providing a huge performance boost.  If this option is not enabled,
365	  then the flag will be ignored.
366
367	  This is taken advantage of by uClibc's malloc(), and also by
368	  ELF-FDPIC binfmt's brk and stack allocator.
369
370	  Because of the obvious security issues, this option should only be
371	  enabled on embedded devices where you control what is run in
372	  userspace.  Since that isn't generally a problem on no-MMU systems,
373	  it is normally safe to say Y here.
374
375	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
376
377config SELECT_MEMORY_MODEL
378	def_bool y
379	depends on ARCH_SELECT_MEMORY_MODEL
380
381choice
382	prompt "Memory model"
383	depends on SELECT_MEMORY_MODEL
384	default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
385	default FLATMEM_MANUAL
386	help
387	  This option allows you to change some of the ways that
388	  Linux manages its memory internally. Most users will
389	  only have one option here selected by the architecture
390	  configuration. This is normal.
391
392config FLATMEM_MANUAL
393	bool "Flat Memory"
394	depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE
395	help
396	  This option is best suited for non-NUMA systems with
397	  flat address space. The FLATMEM is the most efficient
398	  system in terms of performance and resource consumption
399	  and it is the best option for smaller systems.
400
401	  For systems that have holes in their physical address
402	  spaces and for features like NUMA and memory hotplug,
403	  choose "Sparse Memory".
404
405	  If unsure, choose this option (Flat Memory) over any other.
406
407config SPARSEMEM_MANUAL
408	bool "Sparse Memory"
409	depends on ARCH_SPARSEMEM_ENABLE
410	help
411	  This will be the only option for some systems, including
412	  memory hot-plug systems.  This is normal.
413
414	  This option provides efficient support for systems with
415	  holes is their physical address space and allows memory
416	  hot-plug and hot-remove.
417
418	  If unsure, choose "Flat Memory" over this option.
419
420endchoice
421
422config SPARSEMEM
423	def_bool y
424	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
425
426config FLATMEM
427	def_bool y
428	depends on !SPARSEMEM || FLATMEM_MANUAL
429
430#
431# SPARSEMEM_EXTREME (which is the default) does some bootmem
432# allocations when sparse_init() is called.  If this cannot
433# be done on your architecture, select this option.  However,
434# statically allocating the mem_section[] array can potentially
435# consume vast quantities of .bss, so be careful.
436#
437# This option will also potentially produce smaller runtime code
438# with gcc 3.4 and later.
439#
440config SPARSEMEM_STATIC
441	bool
442
443#
444# Architecture platforms which require a two level mem_section in SPARSEMEM
445# must select this option. This is usually for architecture platforms with
446# an extremely sparse physical address space.
447#
448config SPARSEMEM_EXTREME
449	def_bool y
450	depends on SPARSEMEM && !SPARSEMEM_STATIC
451
452config SPARSEMEM_VMEMMAP_ENABLE
453	bool
454
455config SPARSEMEM_VMEMMAP
456	bool "Sparse Memory virtual memmap"
457	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
458	default y
459	help
460	  SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
461	  pfn_to_page and page_to_pfn operations.  This is the most
462	  efficient option when sufficient kernel resources are available.
463
464config HAVE_MEMBLOCK_PHYS_MAP
465	bool
466
467config HAVE_FAST_GUP
468	depends on MMU
469	bool
470
471# Don't discard allocated memory used to track "memory" and "reserved" memblocks
472# after early boot, so it can still be used to test for validity of memory.
473# Also, memblocks are updated with memory hot(un)plug.
474config ARCH_KEEP_MEMBLOCK
475	bool
476
477# Keep arch NUMA mapping infrastructure post-init.
478config NUMA_KEEP_MEMINFO
479	bool
480
481config MEMORY_ISOLATION
482	bool
483
484# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked
485# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via
486# /dev/mem.
487config EXCLUSIVE_SYSTEM_RAM
488	def_bool y
489	depends on !DEVMEM || STRICT_DEVMEM
490
491#
492# Only be set on architectures that have completely implemented memory hotplug
493# feature. If you are not sure, don't touch it.
494#
495config HAVE_BOOTMEM_INFO_NODE
496	def_bool n
497
498config ARCH_ENABLE_MEMORY_HOTPLUG
499	bool
500
501config ARCH_ENABLE_MEMORY_HOTREMOVE
502	bool
503
504# eventually, we can have this option just 'select SPARSEMEM'
505menuconfig MEMORY_HOTPLUG
506	bool "Memory hotplug"
507	select MEMORY_ISOLATION
508	depends on SPARSEMEM
509	depends on ARCH_ENABLE_MEMORY_HOTPLUG
510	depends on 64BIT
511	select NUMA_KEEP_MEMINFO if NUMA
512
513if MEMORY_HOTPLUG
514
515config MEMORY_HOTPLUG_DEFAULT_ONLINE
516	bool "Online the newly added memory blocks by default"
517	depends on MEMORY_HOTPLUG
518	help
519	  This option sets the default policy setting for memory hotplug
520	  onlining policy (/sys/devices/system/memory/auto_online_blocks) which
521	  determines what happens to newly added memory regions. Policy setting
522	  can always be changed at runtime.
523	  See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
524
525	  Say Y here if you want all hot-plugged memory blocks to appear in
526	  'online' state by default.
527	  Say N here if you want the default policy to keep all hot-plugged
528	  memory blocks in 'offline' state.
529
530config MEMORY_HOTREMOVE
531	bool "Allow for memory hot remove"
532	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
533	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
534	depends on MIGRATION
535
536config MHP_MEMMAP_ON_MEMORY
537	def_bool y
538	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
539	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
540
541endif # MEMORY_HOTPLUG
542
543# Heavily threaded applications may benefit from splitting the mm-wide
544# page_table_lock, so that faults on different parts of the user address
545# space can be handled with less contention: split it at this NR_CPUS.
546# Default to 4 for wider testing, though 8 might be more appropriate.
547# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
548# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
549# SPARC32 allocates multiple pte tables within a single page, and therefore
550# a per-page lock leads to problems when multiple tables need to be locked
551# at the same time (e.g. copy_page_range()).
552# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
553#
554config SPLIT_PTLOCK_CPUS
555	int
556	default "999999" if !MMU
557	default "999999" if ARM && !CPU_CACHE_VIPT
558	default "999999" if PARISC && !PA20
559	default "999999" if SPARC32
560	default "4"
561
562config ARCH_ENABLE_SPLIT_PMD_PTLOCK
563	bool
564
565#
566# support for memory balloon
567config MEMORY_BALLOON
568	bool
569
570#
571# support for memory balloon compaction
572config BALLOON_COMPACTION
573	bool "Allow for balloon memory compaction/migration"
574	def_bool y
575	depends on COMPACTION && MEMORY_BALLOON
576	help
577	  Memory fragmentation introduced by ballooning might reduce
578	  significantly the number of 2MB contiguous memory blocks that can be
579	  used within a guest, thus imposing performance penalties associated
580	  with the reduced number of transparent huge pages that could be used
581	  by the guest workload. Allowing the compaction & migration for memory
582	  pages enlisted as being part of memory balloon devices avoids the
583	  scenario aforementioned and helps improving memory defragmentation.
584
585#
586# support for memory compaction
587config COMPACTION
588	bool "Allow for memory compaction"
589	def_bool y
590	select MIGRATION
591	depends on MMU
592	help
593	  Compaction is the only memory management component to form
594	  high order (larger physically contiguous) memory blocks
595	  reliably. The page allocator relies on compaction heavily and
596	  the lack of the feature can lead to unexpected OOM killer
597	  invocations for high order memory requests. You shouldn't
598	  disable this option unless there really is a strong reason for
599	  it and then we would be really interested to hear about that at
600	  linux-mm@kvack.org.
601
602config COMPACT_UNEVICTABLE_DEFAULT
603	int
604	depends on COMPACTION
605	default 0 if PREEMPT_RT
606	default 1
607
608#
609# support for free page reporting
610config PAGE_REPORTING
611	bool "Free page reporting"
612	def_bool n
613	help
614	  Free page reporting allows for the incremental acquisition of
615	  free pages from the buddy allocator for the purpose of reporting
616	  those pages to another entity, such as a hypervisor, so that the
617	  memory can be freed within the host for other uses.
618
619#
620# support for page migration
621#
622config MIGRATION
623	bool "Page migration"
624	def_bool y
625	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
626	help
627	  Allows the migration of the physical location of pages of processes
628	  while the virtual addresses are not changed. This is useful in
629	  two situations. The first is on NUMA systems to put pages nearer
630	  to the processors accessing. The second is when allocating huge
631	  pages as migration can relocate pages to satisfy a huge page
632	  allocation instead of reclaiming.
633
634config DEVICE_MIGRATION
635	def_bool MIGRATION && ZONE_DEVICE
636
637config ARCH_ENABLE_HUGEPAGE_MIGRATION
638	bool
639
640config ARCH_ENABLE_THP_MIGRATION
641	bool
642
643config HUGETLB_PAGE_SIZE_VARIABLE
644	def_bool n
645	help
646	  Allows the pageblock_order value to be dynamic instead of just standard
647	  HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
648	  on a platform.
649
650	  Note that the pageblock_order cannot exceed MAX_ORDER - 1 and will be
651	  clamped down to MAX_ORDER - 1.
652
653config CONTIG_ALLOC
654	def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
655
656config PHYS_ADDR_T_64BIT
657	def_bool 64BIT
658
659config BOUNCE
660	bool "Enable bounce buffers"
661	default y
662	depends on BLOCK && MMU && HIGHMEM
663	help
664	  Enable bounce buffers for devices that cannot access the full range of
665	  memory available to the CPU. Enabled by default when HIGHMEM is
666	  selected, but you may say n to override this.
667
668config MMU_NOTIFIER
669	bool
670	select SRCU
671	select INTERVAL_TREE
672
673config KSM
674	bool "Enable KSM for page merging"
675	depends on MMU
676	select XXHASH
677	help
678	  Enable Kernel Samepage Merging: KSM periodically scans those areas
679	  of an application's address space that an app has advised may be
680	  mergeable.  When it finds pages of identical content, it replaces
681	  the many instances by a single page with that content, so
682	  saving memory until one or another app needs to modify the content.
683	  Recommended for use with KVM, or with other duplicative applications.
684	  See Documentation/mm/ksm.rst for more information: KSM is inactive
685	  until a program has madvised that an area is MADV_MERGEABLE, and
686	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
687
688config DEFAULT_MMAP_MIN_ADDR
689	int "Low address space to protect from user allocation"
690	depends on MMU
691	default 4096
692	help
693	  This is the portion of low virtual memory which should be protected
694	  from userspace allocation.  Keeping a user from writing to low pages
695	  can help reduce the impact of kernel NULL pointer bugs.
696
697	  For most ia64, ppc64 and x86 users with lots of address space
698	  a value of 65536 is reasonable and should cause no problems.
699	  On arm and other archs it should not be higher than 32768.
700	  Programs which use vm86 functionality or have some need to map
701	  this low address space will need CAP_SYS_RAWIO or disable this
702	  protection by setting the value to 0.
703
704	  This value can be changed after boot using the
705	  /proc/sys/vm/mmap_min_addr tunable.
706
707config ARCH_SUPPORTS_MEMORY_FAILURE
708	bool
709
710config MEMORY_FAILURE
711	depends on MMU
712	depends on ARCH_SUPPORTS_MEMORY_FAILURE
713	bool "Enable recovery from hardware memory errors"
714	select MEMORY_ISOLATION
715	select RAS
716	help
717	  Enables code to recover from some memory failures on systems
718	  with MCA recovery. This allows a system to continue running
719	  even when some of its memory has uncorrected errors. This requires
720	  special hardware support and typically ECC memory.
721
722config HWPOISON_INJECT
723	tristate "HWPoison pages injector"
724	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
725	select PROC_PAGE_MONITOR
726
727config NOMMU_INITIAL_TRIM_EXCESS
728	int "Turn on mmap() excess space trimming before booting"
729	depends on !MMU
730	default 1
731	help
732	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
733	  of memory on which to store mappings, but it can only ask the system
734	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
735	  more than it requires.  To deal with this, mmap() is able to trim off
736	  the excess and return it to the allocator.
737
738	  If trimming is enabled, the excess is trimmed off and returned to the
739	  system allocator, which can cause extra fragmentation, particularly
740	  if there are a lot of transient processes.
741
742	  If trimming is disabled, the excess is kept, but not used, which for
743	  long-term mappings means that the space is wasted.
744
745	  Trimming can be dynamically controlled through a sysctl option
746	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
747	  excess pages there must be before trimming should occur, or zero if
748	  no trimming is to occur.
749
750	  This option specifies the initial value of this option.  The default
751	  of 1 says that all excess pages should be trimmed.
752
753	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
754
755config ARCH_WANT_GENERAL_HUGETLB
756	bool
757
758config ARCH_WANTS_THP_SWAP
759	def_bool n
760
761menuconfig TRANSPARENT_HUGEPAGE
762	bool "Transparent Hugepage Support"
763	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT
764	select COMPACTION
765	select XARRAY_MULTI
766	help
767	  Transparent Hugepages allows the kernel to use huge pages and
768	  huge tlb transparently to the applications whenever possible.
769	  This feature can improve computing performance to certain
770	  applications by speeding up page faults during memory
771	  allocation, by reducing the number of tlb misses and by speeding
772	  up the pagetable walking.
773
774	  If memory constrained on embedded, you may want to say N.
775
776if TRANSPARENT_HUGEPAGE
777
778choice
779	prompt "Transparent Hugepage Support sysfs defaults"
780	depends on TRANSPARENT_HUGEPAGE
781	default TRANSPARENT_HUGEPAGE_ALWAYS
782	help
783	  Selects the sysfs defaults for Transparent Hugepage Support.
784
785	config TRANSPARENT_HUGEPAGE_ALWAYS
786		bool "always"
787	help
788	  Enabling Transparent Hugepage always, can increase the
789	  memory footprint of applications without a guaranteed
790	  benefit but it will work automatically for all applications.
791
792	config TRANSPARENT_HUGEPAGE_MADVISE
793		bool "madvise"
794	help
795	  Enabling Transparent Hugepage madvise, will only provide a
796	  performance improvement benefit to the applications using
797	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
798	  memory footprint of applications without a guaranteed
799	  benefit.
800endchoice
801
802config THP_SWAP
803	def_bool y
804	depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT
805	help
806	  Swap transparent huge pages in one piece, without splitting.
807	  XXX: For now, swap cluster backing transparent huge page
808	  will be split after swapout.
809
810	  For selection by architectures with reasonable THP sizes.
811
812config READ_ONLY_THP_FOR_FS
813	bool "Read-only THP for filesystems (EXPERIMENTAL)"
814	depends on TRANSPARENT_HUGEPAGE && SHMEM
815
816	help
817	  Allow khugepaged to put read-only file-backed pages in THP.
818
819	  This is marked experimental because it is a new feature. Write
820	  support of file THPs will be developed in the next few release
821	  cycles.
822
823endif # TRANSPARENT_HUGEPAGE
824
825#
826# UP and nommu archs use km based percpu allocator
827#
828config NEED_PER_CPU_KM
829	depends on !SMP || !MMU
830	bool
831	default y
832
833config NEED_PER_CPU_EMBED_FIRST_CHUNK
834	bool
835
836config NEED_PER_CPU_PAGE_FIRST_CHUNK
837	bool
838
839config USE_PERCPU_NUMA_NODE_ID
840	bool
841
842config HAVE_SETUP_PER_CPU_AREA
843	bool
844
845config FRONTSWAP
846	bool
847
848config CMA
849	bool "Contiguous Memory Allocator"
850	depends on MMU
851	select MIGRATION
852	select MEMORY_ISOLATION
853	help
854	  This enables the Contiguous Memory Allocator which allows other
855	  subsystems to allocate big physically-contiguous blocks of memory.
856	  CMA reserves a region of memory and allows only movable pages to
857	  be allocated from it. This way, the kernel can use the memory for
858	  pagecache and when a subsystem requests for contiguous area, the
859	  allocated pages are migrated away to serve the contiguous request.
860
861	  If unsure, say "n".
862
863config CMA_DEBUG
864	bool "CMA debug messages (DEVELOPMENT)"
865	depends on DEBUG_KERNEL && CMA
866	help
867	  Turns on debug messages in CMA.  This produces KERN_DEBUG
868	  messages for every CMA call as well as various messages while
869	  processing calls such as dma_alloc_from_contiguous().
870	  This option does not affect warning and error messages.
871
872config CMA_DEBUGFS
873	bool "CMA debugfs interface"
874	depends on CMA && DEBUG_FS
875	help
876	  Turns on the DebugFS interface for CMA.
877
878config CMA_SYSFS
879	bool "CMA information through sysfs interface"
880	depends on CMA && SYSFS
881	help
882	  This option exposes some sysfs attributes to get information
883	  from CMA.
884
885config CMA_AREAS
886	int "Maximum count of the CMA areas"
887	depends on CMA
888	default 19 if NUMA
889	default 7
890	help
891	  CMA allows to create CMA areas for particular purpose, mainly,
892	  used as device private area. This parameter sets the maximum
893	  number of CMA area in the system.
894
895	  If unsure, leave the default value "7" in UMA and "19" in NUMA.
896
897config MEM_SOFT_DIRTY
898	bool "Track memory changes"
899	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
900	select PROC_PAGE_MONITOR
901	help
902	  This option enables memory changes tracking by introducing a
903	  soft-dirty bit on pte-s. This bit it set when someone writes
904	  into a page just as regular dirty bit, but unlike the latter
905	  it can be cleared by hands.
906
907	  See Documentation/admin-guide/mm/soft-dirty.rst for more details.
908
909config GENERIC_EARLY_IOREMAP
910	bool
911
912config STACK_MAX_DEFAULT_SIZE_MB
913	int "Default maximum user stack size for 32-bit processes (MB)"
914	default 100
915	range 8 2048
916	depends on STACK_GROWSUP && (!64BIT || COMPAT)
917	help
918	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
919	  user processes when the stack grows upwards (currently only on parisc
920	  arch) when the RLIMIT_STACK hard limit is unlimited.
921
922	  A sane initial value is 100 MB.
923
924config DEFERRED_STRUCT_PAGE_INIT
925	bool "Defer initialisation of struct pages to kthreads"
926	depends on SPARSEMEM
927	depends on !NEED_PER_CPU_KM
928	depends on 64BIT
929	select PADATA
930	help
931	  Ordinarily all struct pages are initialised during early boot in a
932	  single thread. On very large machines this can take a considerable
933	  amount of time. If this option is set, large machines will bring up
934	  a subset of memmap at boot and then initialise the rest in parallel.
935	  This has a potential performance impact on tasks running early in the
936	  lifetime of the system until these kthreads finish the
937	  initialisation.
938
939config PAGE_IDLE_FLAG
940	bool
941	select PAGE_EXTENSION if !64BIT
942	help
943	  This adds PG_idle and PG_young flags to 'struct page'.  PTE Accessed
944	  bit writers can set the state of the bit in the flags so that PTE
945	  Accessed bit readers may avoid disturbance.
946
947config IDLE_PAGE_TRACKING
948	bool "Enable idle page tracking"
949	depends on SYSFS && MMU
950	select PAGE_IDLE_FLAG
951	help
952	  This feature allows to estimate the amount of user pages that have
953	  not been touched during a given period of time. This information can
954	  be useful to tune memory cgroup limits and/or for job placement
955	  within a compute cluster.
956
957	  See Documentation/admin-guide/mm/idle_page_tracking.rst for
958	  more details.
959
960config ARCH_HAS_CACHE_LINE_SIZE
961	bool
962
963config ARCH_HAS_CURRENT_STACK_POINTER
964	bool
965	help
966	  In support of HARDENED_USERCOPY performing stack variable lifetime
967	  checking, an architecture-agnostic way to find the stack pointer
968	  is needed. Once an architecture defines an unsigned long global
969	  register alias named "current_stack_pointer", this config can be
970	  selected.
971
972config ARCH_HAS_PTE_DEVMAP
973	bool
974
975config ARCH_HAS_ZONE_DMA_SET
976	bool
977
978config ZONE_DMA
979	bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET
980	default y if ARM64 || X86
981
982config ZONE_DMA32
983	bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET
984	depends on !X86_32
985	default y if ARM64
986
987config ZONE_DEVICE
988	bool "Device memory (pmem, HMM, etc...) hotplug support"
989	depends on MEMORY_HOTPLUG
990	depends on MEMORY_HOTREMOVE
991	depends on SPARSEMEM_VMEMMAP
992	depends on ARCH_HAS_PTE_DEVMAP
993	select XARRAY_MULTI
994
995	help
996	  Device memory hotplug support allows for establishing pmem,
997	  or other device driver discovered memory regions, in the
998	  memmap. This allows pfn_to_page() lookups of otherwise
999	  "device-physical" addresses which is needed for using a DAX
1000	  mapping in an O_DIRECT operation, among other things.
1001
1002	  If FS_DAX is enabled, then say Y.
1003
1004#
1005# Helpers to mirror range of the CPU page tables of a process into device page
1006# tables.
1007#
1008config HMM_MIRROR
1009	bool
1010	depends on MMU
1011
1012config GET_FREE_REGION
1013	depends on SPARSEMEM
1014	bool
1015
1016config DEVICE_PRIVATE
1017	bool "Unaddressable device memory (GPU memory, ...)"
1018	depends on ZONE_DEVICE
1019	select GET_FREE_REGION
1020
1021	help
1022	  Allows creation of struct pages to represent unaddressable device
1023	  memory; i.e., memory that is only accessible from the device (or
1024	  group of devices). You likely also want to select HMM_MIRROR.
1025
1026config VMAP_PFN
1027	bool
1028
1029config ARCH_USES_HIGH_VMA_FLAGS
1030	bool
1031config ARCH_HAS_PKEYS
1032	bool
1033
1034config ARCH_USES_PG_ARCH_X
1035	bool
1036	help
1037	  Enable the definition of PG_arch_x page flags with x > 1. Only
1038	  suitable for 64-bit architectures with CONFIG_FLATMEM or
1039	  CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be
1040	  enough room for additional bits in page->flags.
1041
1042config VM_EVENT_COUNTERS
1043	default y
1044	bool "Enable VM event counters for /proc/vmstat" if EXPERT
1045	help
1046	  VM event counters are needed for event counts to be shown.
1047	  This option allows the disabling of the VM event counters
1048	  on EXPERT systems.  /proc/vmstat will only show page counts
1049	  if VM event counters are disabled.
1050
1051config PERCPU_STATS
1052	bool "Collect percpu memory statistics"
1053	help
1054	  This feature collects and exposes statistics via debugfs. The
1055	  information includes global and per chunk statistics, which can
1056	  be used to help understand percpu memory usage.
1057
1058config GUP_TEST
1059	bool "Enable infrastructure for get_user_pages()-related unit tests"
1060	depends on DEBUG_FS
1061	help
1062	  Provides /sys/kernel/debug/gup_test, which in turn provides a way
1063	  to make ioctl calls that can launch kernel-based unit tests for
1064	  the get_user_pages*() and pin_user_pages*() family of API calls.
1065
1066	  These tests include benchmark testing of the _fast variants of
1067	  get_user_pages*() and pin_user_pages*(), as well as smoke tests of
1068	  the non-_fast variants.
1069
1070	  There is also a sub-test that allows running dump_page() on any
1071	  of up to eight pages (selected by command line args) within the
1072	  range of user-space addresses. These pages are either pinned via
1073	  pin_user_pages*(), or pinned via get_user_pages*(), as specified
1074	  by other command line arguments.
1075
1076	  See tools/testing/selftests/vm/gup_test.c
1077
1078comment "GUP_TEST needs to have DEBUG_FS enabled"
1079	depends on !GUP_TEST && !DEBUG_FS
1080
1081config GUP_GET_PXX_LOW_HIGH
1082	bool
1083
1084config ARCH_HAS_PTE_SPECIAL
1085	bool
1086
1087#
1088# Some architectures require a special hugepage directory format that is
1089# required to support multiple hugepage sizes. For example a4fe3ce76
1090# "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
1091# introduced it on powerpc.  This allows for a more flexible hugepage
1092# pagetable layouts.
1093#
1094config ARCH_HAS_HUGEPD
1095	bool
1096
1097config MAPPING_DIRTY_HELPERS
1098        bool
1099
1100config KMAP_LOCAL
1101	bool
1102
1103config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
1104	bool
1105
1106# struct io_mapping based helper.  Selected by drivers that need them
1107config IO_MAPPING
1108	bool
1109
1110config SECRETMEM
1111	default y
1112	bool "Enable memfd_secret() system call" if EXPERT
1113	depends on ARCH_HAS_SET_DIRECT_MAP
1114	help
1115	  Enable the memfd_secret() system call with the ability to create
1116	  memory areas visible only in the context of the owning process and
1117	  not mapped to other processes and other kernel page tables.
1118
1119config ANON_VMA_NAME
1120	bool "Anonymous VMA name support"
1121	depends on PROC_FS && ADVISE_SYSCALLS && MMU
1122
1123	help
1124	  Allow naming anonymous virtual memory areas.
1125
1126	  This feature allows assigning names to virtual memory areas. Assigned
1127	  names can be later retrieved from /proc/pid/maps and /proc/pid/smaps
1128	  and help identifying individual anonymous memory areas.
1129	  Assigning a name to anonymous virtual memory area might prevent that
1130	  area from being merged with adjacent virtual memory areas due to the
1131	  difference in their name.
1132
1133config USERFAULTFD
1134	bool "Enable userfaultfd() system call"
1135	depends on MMU
1136	help
1137	  Enable the userfaultfd() system call that allows to intercept and
1138	  handle page faults in userland.
1139
1140config HAVE_ARCH_USERFAULTFD_WP
1141	bool
1142	help
1143	  Arch has userfaultfd write protection support
1144
1145config HAVE_ARCH_USERFAULTFD_MINOR
1146	bool
1147	help
1148	  Arch has userfaultfd minor fault support
1149
1150config PTE_MARKER_UFFD_WP
1151	bool "Userfaultfd write protection support for shmem/hugetlbfs"
1152	default y
1153	depends on HAVE_ARCH_USERFAULTFD_WP
1154
1155	help
1156	  Allows to create marker PTEs for userfaultfd write protection
1157	  purposes.  It is required to enable userfaultfd write protection on
1158	  file-backed memory types like shmem and hugetlbfs.
1159
1160# multi-gen LRU {
1161config LRU_GEN
1162	bool "Multi-Gen LRU"
1163	depends on MMU
1164	# make sure folio->flags has enough spare bits
1165	depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP
1166	help
1167	  A high performance LRU implementation to overcommit memory. See
1168	  Documentation/admin-guide/mm/multigen_lru.rst for details.
1169
1170config LRU_GEN_ENABLED
1171	bool "Enable by default"
1172	depends on LRU_GEN
1173	help
1174	  This option enables the multi-gen LRU by default.
1175
1176config LRU_GEN_STATS
1177	bool "Full stats for debugging"
1178	depends on LRU_GEN
1179	help
1180	  Do not enable this option unless you plan to look at historical stats
1181	  from evicted generations for debugging purpose.
1182
1183	  This option has a per-memcg and per-node memory overhead.
1184# }
1185
1186source "mm/damon/Kconfig"
1187
1188endmenu
1189