xref: /linux/mm/Kconfig (revision 345531df1cf864bbdba8d5a31c0b5519296c39cc)
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 CRYPTO
29	select ZPOOL
30	help
31	  A lightweight compressed cache for swap pages.  It takes
32	  pages that are in the process of being swapped out and attempts to
33	  compress them into a dynamically allocated RAM-based memory pool.
34	  This can result in a significant I/O reduction on swap device and,
35	  in the case where decompressing from RAM is faster than swap device
36	  reads, can also improve workload performance.
37
38config ZSWAP_DEFAULT_ON
39	bool "Enable the compressed cache for swap pages by default"
40	depends on ZSWAP
41	help
42	  If selected, the compressed cache for swap pages will be enabled
43	  at boot, otherwise it will be disabled.
44
45	  The selection made here can be overridden by using the kernel
46	  command line 'zswap.enabled=' option.
47
48config ZSWAP_SHRINKER_DEFAULT_ON
49	bool "Shrink the zswap pool on memory pressure"
50	depends on ZSWAP
51	default n
52	help
53	  If selected, the zswap shrinker will be enabled, and the pages
54	  stored in the zswap pool will become available for reclaim (i.e
55	  written back to the backing swap device) on memory pressure.
56
57	  This means that zswap writeback could happen even if the pool is
58	  not yet full, or the cgroup zswap limit has not been reached,
59	  reducing the chance that cold pages will reside in the zswap pool
60	  and consume memory indefinitely.
61
62choice
63	prompt "Default compressor"
64	depends on ZSWAP
65	default ZSWAP_COMPRESSOR_DEFAULT_LZO
66	help
67	  Selects the default compression algorithm for the compressed cache
68	  for swap pages.
69
70	  For an overview what kind of performance can be expected from
71	  a particular compression algorithm please refer to the benchmarks
72	  available at the following LWN page:
73	  https://lwn.net/Articles/751795/
74
75	  If in doubt, select 'LZO'.
76
77	  The selection made here can be overridden by using the kernel
78	  command line 'zswap.compressor=' option.
79
80config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
81	bool "Deflate"
82	select CRYPTO_DEFLATE
83	help
84	  Use the Deflate algorithm as the default compression algorithm.
85
86config ZSWAP_COMPRESSOR_DEFAULT_LZO
87	bool "LZO"
88	select CRYPTO_LZO
89	help
90	  Use the LZO algorithm as the default compression algorithm.
91
92config ZSWAP_COMPRESSOR_DEFAULT_842
93	bool "842"
94	select CRYPTO_842
95	help
96	  Use the 842 algorithm as the default compression algorithm.
97
98config ZSWAP_COMPRESSOR_DEFAULT_LZ4
99	bool "LZ4"
100	select CRYPTO_LZ4
101	help
102	  Use the LZ4 algorithm as the default compression algorithm.
103
104config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
105	bool "LZ4HC"
106	select CRYPTO_LZ4HC
107	help
108	  Use the LZ4HC algorithm as the default compression algorithm.
109
110config ZSWAP_COMPRESSOR_DEFAULT_ZSTD
111	bool "zstd"
112	select CRYPTO_ZSTD
113	help
114	  Use the zstd algorithm as the default compression algorithm.
115endchoice
116
117config ZSWAP_COMPRESSOR_DEFAULT
118       string
119       depends on ZSWAP
120       default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
121       default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO
122       default "842" if ZSWAP_COMPRESSOR_DEFAULT_842
123       default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4
124       default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
125       default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD
126       default ""
127
128choice
129	prompt "Default allocator"
130	depends on ZSWAP
131	default ZSWAP_ZPOOL_DEFAULT_ZSMALLOC if MMU
132	default ZSWAP_ZPOOL_DEFAULT_ZBUD
133	help
134	  Selects the default allocator for the compressed cache for
135	  swap pages.
136	  The default is 'zbud' for compatibility, however please do
137	  read the description of each of the allocators below before
138	  making a right choice.
139
140	  The selection made here can be overridden by using the kernel
141	  command line 'zswap.zpool=' option.
142
143config ZSWAP_ZPOOL_DEFAULT_ZBUD
144	bool "zbud"
145	select ZBUD
146	help
147	  Use the zbud allocator as the default allocator.
148
149config ZSWAP_ZPOOL_DEFAULT_Z3FOLD
150	bool "z3fold"
151	select Z3FOLD
152	help
153	  Use the z3fold allocator as the default allocator.
154
155config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
156	bool "zsmalloc"
157	select ZSMALLOC
158	help
159	  Use the zsmalloc allocator as the default allocator.
160endchoice
161
162config ZSWAP_ZPOOL_DEFAULT
163       string
164       depends on ZSWAP
165       default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD
166       default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD
167       default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
168       default ""
169
170config ZBUD
171	tristate "2:1 compression allocator (zbud)"
172	depends on ZSWAP
173	help
174	  A special purpose allocator for storing compressed pages.
175	  It is designed to store up to two compressed pages per physical
176	  page.  While this design limits storage density, it has simple and
177	  deterministic reclaim properties that make it preferable to a higher
178	  density approach when reclaim will be used.
179
180config Z3FOLD
181	tristate "3:1 compression allocator (z3fold)"
182	depends on ZSWAP
183	help
184	  A special purpose allocator for storing compressed pages.
185	  It is designed to store up to three compressed pages per physical
186	  page. It is a ZBUD derivative so the simplicity and determinism are
187	  still there.
188
189config ZSMALLOC
190	tristate
191	prompt "N:1 compression allocator (zsmalloc)" if ZSWAP
192	depends on MMU
193	help
194	  zsmalloc is a slab-based memory allocator designed to store
195	  pages of various compression levels efficiently. It achieves
196	  the highest storage density with the least amount of fragmentation.
197
198config ZSMALLOC_STAT
199	bool "Export zsmalloc statistics"
200	depends on ZSMALLOC
201	select DEBUG_FS
202	help
203	  This option enables code in the zsmalloc to collect various
204	  statistics about what's happening in zsmalloc and exports that
205	  information to userspace via debugfs.
206	  If unsure, say N.
207
208config ZSMALLOC_CHAIN_SIZE
209	int "Maximum number of physical pages per-zspage"
210	default 8
211	range 4 16
212	depends on ZSMALLOC
213	help
214	  This option sets the upper limit on the number of physical pages
215	  that a zmalloc page (zspage) can consist of. The optimal zspage
216	  chain size is calculated for each size class during the
217	  initialization of the pool.
218
219	  Changing this option can alter the characteristics of size classes,
220	  such as the number of pages per zspage and the number of objects
221	  per zspage. This can also result in different configurations of
222	  the pool, as zsmalloc merges size classes with similar
223	  characteristics.
224
225	  For more information, see zsmalloc documentation.
226
227menu "Slab allocator options"
228
229config SLUB
230	def_bool y
231
232config SLUB_TINY
233	bool "Configure for minimal memory footprint"
234	depends on EXPERT
235	select SLAB_MERGE_DEFAULT
236	help
237	   Configures the slab allocator in a way to achieve minimal memory
238	   footprint, sacrificing scalability, debugging and other features.
239	   This is intended only for the smallest system that had used the
240	   SLOB allocator and is not recommended for systems with more than
241	   16MB RAM.
242
243	   If unsure, say N.
244
245config SLAB_MERGE_DEFAULT
246	bool "Allow slab caches to be merged"
247	default y
248	help
249	  For reduced kernel memory fragmentation, slab caches can be
250	  merged when they share the same size and other characteristics.
251	  This carries a risk of kernel heap overflows being able to
252	  overwrite objects from merged caches (and more easily control
253	  cache layout), which makes such heap attacks easier to exploit
254	  by attackers. By keeping caches unmerged, these kinds of exploits
255	  can usually only damage objects in the same cache. To disable
256	  merging at runtime, "slab_nomerge" can be passed on the kernel
257	  command line.
258
259config SLAB_FREELIST_RANDOM
260	bool "Randomize slab freelist"
261	depends on !SLUB_TINY
262	help
263	  Randomizes the freelist order used on creating new pages. This
264	  security feature reduces the predictability of the kernel slab
265	  allocator against heap overflows.
266
267config SLAB_FREELIST_HARDENED
268	bool "Harden slab freelist metadata"
269	depends on !SLUB_TINY
270	help
271	  Many kernel heap attacks try to target slab cache metadata and
272	  other infrastructure. This options makes minor performance
273	  sacrifices to harden the kernel slab allocator against common
274	  freelist exploit methods.
275
276config SLUB_STATS
277	default n
278	bool "Enable performance statistics"
279	depends on SYSFS && !SLUB_TINY
280	help
281	  The statistics are useful to debug slab allocation behavior in
282	  order find ways to optimize the allocator. This should never be
283	  enabled for production use since keeping statistics slows down
284	  the allocator by a few percentage points. The slabinfo command
285	  supports the determination of the most active slabs to figure
286	  out which slabs are relevant to a particular load.
287	  Try running: slabinfo -DA
288
289config SLUB_CPU_PARTIAL
290	default y
291	depends on SMP && !SLUB_TINY
292	bool "Enable per cpu partial caches"
293	help
294	  Per cpu partial caches accelerate objects allocation and freeing
295	  that is local to a processor at the price of more indeterminism
296	  in the latency of the free. On overflow these caches will be cleared
297	  which requires the taking of locks that may cause latency spikes.
298	  Typically one would choose no for a realtime system.
299
300config RANDOM_KMALLOC_CACHES
301	default n
302	depends on !SLUB_TINY
303	bool "Randomize slab caches for normal kmalloc"
304	help
305	  A hardening feature that creates multiple copies of slab caches for
306	  normal kmalloc allocation and makes kmalloc randomly pick one based
307	  on code address, which makes the attackers more difficult to spray
308	  vulnerable memory objects on the heap for the purpose of exploiting
309	  memory vulnerabilities.
310
311	  Currently the number of copies is set to 16, a reasonably large value
312	  that effectively diverges the memory objects allocated for different
313	  subsystems or modules into different caches, at the expense of a
314	  limited degree of memory and CPU overhead that relates to hardware and
315	  system workload.
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_PAGE_ORDER i.e, 10th
331	  order of pages is selected based on cache utilization benefits
332	  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#
464# Select this config option from the architecture Kconfig, if it is preferred
465# to enable the feature of HugeTLB/dev_dax vmemmap optimization.
466#
467config ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
468	bool
469
470config ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP
471	bool
472
473config HAVE_MEMBLOCK_PHYS_MAP
474	bool
475
476config HAVE_FAST_GUP
477	depends on MMU
478	bool
479
480# Don't discard allocated memory used to track "memory" and "reserved" memblocks
481# after early boot, so it can still be used to test for validity of memory.
482# Also, memblocks are updated with memory hot(un)plug.
483config ARCH_KEEP_MEMBLOCK
484	bool
485
486# Keep arch NUMA mapping infrastructure post-init.
487config NUMA_KEEP_MEMINFO
488	bool
489
490config MEMORY_ISOLATION
491	bool
492
493# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked
494# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via
495# /dev/mem.
496config EXCLUSIVE_SYSTEM_RAM
497	def_bool y
498	depends on !DEVMEM || STRICT_DEVMEM
499
500#
501# Only be set on architectures that have completely implemented memory hotplug
502# feature. If you are not sure, don't touch it.
503#
504config HAVE_BOOTMEM_INFO_NODE
505	def_bool n
506
507config ARCH_ENABLE_MEMORY_HOTPLUG
508	bool
509
510config ARCH_ENABLE_MEMORY_HOTREMOVE
511	bool
512
513# eventually, we can have this option just 'select SPARSEMEM'
514menuconfig MEMORY_HOTPLUG
515	bool "Memory hotplug"
516	select MEMORY_ISOLATION
517	depends on SPARSEMEM
518	depends on ARCH_ENABLE_MEMORY_HOTPLUG
519	depends on 64BIT
520	select NUMA_KEEP_MEMINFO if NUMA
521
522if MEMORY_HOTPLUG
523
524config MEMORY_HOTPLUG_DEFAULT_ONLINE
525	bool "Online the newly added memory blocks by default"
526	depends on MEMORY_HOTPLUG
527	help
528	  This option sets the default policy setting for memory hotplug
529	  onlining policy (/sys/devices/system/memory/auto_online_blocks) which
530	  determines what happens to newly added memory regions. Policy setting
531	  can always be changed at runtime.
532	  See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
533
534	  Say Y here if you want all hot-plugged memory blocks to appear in
535	  'online' state by default.
536	  Say N here if you want the default policy to keep all hot-plugged
537	  memory blocks in 'offline' state.
538
539config MEMORY_HOTREMOVE
540	bool "Allow for memory hot remove"
541	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
542	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
543	depends on MIGRATION
544
545config MHP_MEMMAP_ON_MEMORY
546	def_bool y
547	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
548	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
549
550endif # MEMORY_HOTPLUG
551
552config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
553       bool
554
555# Heavily threaded applications may benefit from splitting the mm-wide
556# page_table_lock, so that faults on different parts of the user address
557# space can be handled with less contention: split it at this NR_CPUS.
558# Default to 4 for wider testing, though 8 might be more appropriate.
559# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
560# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
561# SPARC32 allocates multiple pte tables within a single page, and therefore
562# a per-page lock leads to problems when multiple tables need to be locked
563# at the same time (e.g. copy_page_range()).
564# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
565#
566config SPLIT_PTLOCK_CPUS
567	int
568	default "999999" if !MMU
569	default "999999" if ARM && !CPU_CACHE_VIPT
570	default "999999" if PARISC && !PA20
571	default "999999" if SPARC32
572	default "4"
573
574config ARCH_ENABLE_SPLIT_PMD_PTLOCK
575	bool
576
577#
578# support for memory balloon
579config MEMORY_BALLOON
580	bool
581
582#
583# support for memory balloon compaction
584config BALLOON_COMPACTION
585	bool "Allow for balloon memory compaction/migration"
586	default y
587	depends on COMPACTION && MEMORY_BALLOON
588	help
589	  Memory fragmentation introduced by ballooning might reduce
590	  significantly the number of 2MB contiguous memory blocks that can be
591	  used within a guest, thus imposing performance penalties associated
592	  with the reduced number of transparent huge pages that could be used
593	  by the guest workload. Allowing the compaction & migration for memory
594	  pages enlisted as being part of memory balloon devices avoids the
595	  scenario aforementioned and helps improving memory defragmentation.
596
597#
598# support for memory compaction
599config COMPACTION
600	bool "Allow for memory compaction"
601	default y
602	select MIGRATION
603	depends on MMU
604	help
605	  Compaction is the only memory management component to form
606	  high order (larger physically contiguous) memory blocks
607	  reliably. The page allocator relies on compaction heavily and
608	  the lack of the feature can lead to unexpected OOM killer
609	  invocations for high order memory requests. You shouldn't
610	  disable this option unless there really is a strong reason for
611	  it and then we would be really interested to hear about that at
612	  linux-mm@kvack.org.
613
614config COMPACT_UNEVICTABLE_DEFAULT
615	int
616	depends on COMPACTION
617	default 0 if PREEMPT_RT
618	default 1
619
620#
621# support for free page reporting
622config PAGE_REPORTING
623	bool "Free page reporting"
624	help
625	  Free page reporting allows for the incremental acquisition of
626	  free pages from the buddy allocator for the purpose of reporting
627	  those pages to another entity, such as a hypervisor, so that the
628	  memory can be freed within the host for other uses.
629
630#
631# support for page migration
632#
633config MIGRATION
634	bool "Page migration"
635	default y
636	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
637	help
638	  Allows the migration of the physical location of pages of processes
639	  while the virtual addresses are not changed. This is useful in
640	  two situations. The first is on NUMA systems to put pages nearer
641	  to the processors accessing. The second is when allocating huge
642	  pages as migration can relocate pages to satisfy a huge page
643	  allocation instead of reclaiming.
644
645config DEVICE_MIGRATION
646	def_bool MIGRATION && ZONE_DEVICE
647
648config ARCH_ENABLE_HUGEPAGE_MIGRATION
649	bool
650
651config ARCH_ENABLE_THP_MIGRATION
652	bool
653
654config HUGETLB_PAGE_SIZE_VARIABLE
655	def_bool n
656	help
657	  Allows the pageblock_order value to be dynamic instead of just standard
658	  HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
659	  on a platform.
660
661	  Note that the pageblock_order cannot exceed MAX_PAGE_ORDER and will be
662	  clamped down to MAX_PAGE_ORDER.
663
664config CONTIG_ALLOC
665	def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
666
667config PCP_BATCH_SCALE_MAX
668	int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free"
669	default 5
670	range 0 6
671	help
672	  In page allocator, PCP (Per-CPU pageset) is refilled and drained in
673	  batches.  The batch number is scaled automatically to improve page
674	  allocation/free throughput.  But too large scale factor may hurt
675	  latency.  This option sets the upper limit of scale factor to limit
676	  the maximum latency.
677
678config PHYS_ADDR_T_64BIT
679	def_bool 64BIT
680
681config BOUNCE
682	bool "Enable bounce buffers"
683	default y
684	depends on BLOCK && MMU && HIGHMEM
685	help
686	  Enable bounce buffers for devices that cannot access the full range of
687	  memory available to the CPU. Enabled by default when HIGHMEM is
688	  selected, but you may say n to override this.
689
690config MMU_NOTIFIER
691	bool
692	select INTERVAL_TREE
693
694config KSM
695	bool "Enable KSM for page merging"
696	depends on MMU
697	select XXHASH
698	help
699	  Enable Kernel Samepage Merging: KSM periodically scans those areas
700	  of an application's address space that an app has advised may be
701	  mergeable.  When it finds pages of identical content, it replaces
702	  the many instances by a single page with that content, so
703	  saving memory until one or another app needs to modify the content.
704	  Recommended for use with KVM, or with other duplicative applications.
705	  See Documentation/mm/ksm.rst for more information: KSM is inactive
706	  until a program has madvised that an area is MADV_MERGEABLE, and
707	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
708
709config DEFAULT_MMAP_MIN_ADDR
710	int "Low address space to protect from user allocation"
711	depends on MMU
712	default 4096
713	help
714	  This is the portion of low virtual memory which should be protected
715	  from userspace allocation.  Keeping a user from writing to low pages
716	  can help reduce the impact of kernel NULL pointer bugs.
717
718	  For most ppc64 and x86 users with lots of address space
719	  a value of 65536 is reasonable and should cause no problems.
720	  On arm and other archs it should not be higher than 32768.
721	  Programs which use vm86 functionality or have some need to map
722	  this low address space will need CAP_SYS_RAWIO or disable this
723	  protection by setting the value to 0.
724
725	  This value can be changed after boot using the
726	  /proc/sys/vm/mmap_min_addr tunable.
727
728config ARCH_SUPPORTS_MEMORY_FAILURE
729	bool
730
731config MEMORY_FAILURE
732	depends on MMU
733	depends on ARCH_SUPPORTS_MEMORY_FAILURE
734	bool "Enable recovery from hardware memory errors"
735	select MEMORY_ISOLATION
736	select RAS
737	help
738	  Enables code to recover from some memory failures on systems
739	  with MCA recovery. This allows a system to continue running
740	  even when some of its memory has uncorrected errors. This requires
741	  special hardware support and typically ECC memory.
742
743config HWPOISON_INJECT
744	tristate "HWPoison pages injector"
745	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
746	select PROC_PAGE_MONITOR
747
748config NOMMU_INITIAL_TRIM_EXCESS
749	int "Turn on mmap() excess space trimming before booting"
750	depends on !MMU
751	default 1
752	help
753	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
754	  of memory on which to store mappings, but it can only ask the system
755	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
756	  more than it requires.  To deal with this, mmap() is able to trim off
757	  the excess and return it to the allocator.
758
759	  If trimming is enabled, the excess is trimmed off and returned to the
760	  system allocator, which can cause extra fragmentation, particularly
761	  if there are a lot of transient processes.
762
763	  If trimming is disabled, the excess is kept, but not used, which for
764	  long-term mappings means that the space is wasted.
765
766	  Trimming can be dynamically controlled through a sysctl option
767	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
768	  excess pages there must be before trimming should occur, or zero if
769	  no trimming is to occur.
770
771	  This option specifies the initial value of this option.  The default
772	  of 1 says that all excess pages should be trimmed.
773
774	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
775
776config ARCH_WANT_GENERAL_HUGETLB
777	bool
778
779config ARCH_WANTS_THP_SWAP
780	def_bool n
781
782menuconfig TRANSPARENT_HUGEPAGE
783	bool "Transparent Hugepage Support"
784	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT
785	select COMPACTION
786	select XARRAY_MULTI
787	help
788	  Transparent Hugepages allows the kernel to use huge pages and
789	  huge tlb transparently to the applications whenever possible.
790	  This feature can improve computing performance to certain
791	  applications by speeding up page faults during memory
792	  allocation, by reducing the number of tlb misses and by speeding
793	  up the pagetable walking.
794
795	  If memory constrained on embedded, you may want to say N.
796
797if TRANSPARENT_HUGEPAGE
798
799choice
800	prompt "Transparent Hugepage Support sysfs defaults"
801	depends on TRANSPARENT_HUGEPAGE
802	default TRANSPARENT_HUGEPAGE_ALWAYS
803	help
804	  Selects the sysfs defaults for Transparent Hugepage Support.
805
806	config TRANSPARENT_HUGEPAGE_ALWAYS
807		bool "always"
808	help
809	  Enabling Transparent Hugepage always, can increase the
810	  memory footprint of applications without a guaranteed
811	  benefit but it will work automatically for all applications.
812
813	config TRANSPARENT_HUGEPAGE_MADVISE
814		bool "madvise"
815	help
816	  Enabling Transparent Hugepage madvise, will only provide a
817	  performance improvement benefit to the applications using
818	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
819	  memory footprint of applications without a guaranteed
820	  benefit.
821
822	config TRANSPARENT_HUGEPAGE_NEVER
823		bool "never"
824	help
825	  Disable Transparent Hugepage by default. It can still be
826	  enabled at runtime via sysfs.
827endchoice
828
829config THP_SWAP
830	def_bool y
831	depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT
832	help
833	  Swap transparent huge pages in one piece, without splitting.
834	  XXX: For now, swap cluster backing transparent huge page
835	  will be split after swapout.
836
837	  For selection by architectures with reasonable THP sizes.
838
839config READ_ONLY_THP_FOR_FS
840	bool "Read-only THP for filesystems (EXPERIMENTAL)"
841	depends on TRANSPARENT_HUGEPAGE && SHMEM
842
843	help
844	  Allow khugepaged to put read-only file-backed pages in THP.
845
846	  This is marked experimental because it is a new feature. Write
847	  support of file THPs will be developed in the next few release
848	  cycles.
849
850endif # TRANSPARENT_HUGEPAGE
851
852#
853# UP and nommu archs use km based percpu allocator
854#
855config NEED_PER_CPU_KM
856	depends on !SMP || !MMU
857	bool
858	default y
859
860config NEED_PER_CPU_EMBED_FIRST_CHUNK
861	bool
862
863config NEED_PER_CPU_PAGE_FIRST_CHUNK
864	bool
865
866config USE_PERCPU_NUMA_NODE_ID
867	bool
868
869config HAVE_SETUP_PER_CPU_AREA
870	bool
871
872config CMA
873	bool "Contiguous Memory Allocator"
874	depends on MMU
875	select MIGRATION
876	select MEMORY_ISOLATION
877	help
878	  This enables the Contiguous Memory Allocator which allows other
879	  subsystems to allocate big physically-contiguous blocks of memory.
880	  CMA reserves a region of memory and allows only movable pages to
881	  be allocated from it. This way, the kernel can use the memory for
882	  pagecache and when a subsystem requests for contiguous area, the
883	  allocated pages are migrated away to serve the contiguous request.
884
885	  If unsure, say "n".
886
887config CMA_DEBUGFS
888	bool "CMA debugfs interface"
889	depends on CMA && DEBUG_FS
890	help
891	  Turns on the DebugFS interface for CMA.
892
893config CMA_SYSFS
894	bool "CMA information through sysfs interface"
895	depends on CMA && SYSFS
896	help
897	  This option exposes some sysfs attributes to get information
898	  from CMA.
899
900config CMA_AREAS
901	int "Maximum count of the CMA areas"
902	depends on CMA
903	default 20 if NUMA
904	default 8
905	help
906	  CMA allows to create CMA areas for particular purpose, mainly,
907	  used as device private area. This parameter sets the maximum
908	  number of CMA area in the system.
909
910	  If unsure, leave the default value "8" in UMA and "20" in NUMA.
911
912config MEM_SOFT_DIRTY
913	bool "Track memory changes"
914	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
915	select PROC_PAGE_MONITOR
916	help
917	  This option enables memory changes tracking by introducing a
918	  soft-dirty bit on pte-s. This bit it set when someone writes
919	  into a page just as regular dirty bit, but unlike the latter
920	  it can be cleared by hands.
921
922	  See Documentation/admin-guide/mm/soft-dirty.rst for more details.
923
924config GENERIC_EARLY_IOREMAP
925	bool
926
927config STACK_MAX_DEFAULT_SIZE_MB
928	int "Default maximum user stack size for 32-bit processes (MB)"
929	default 100
930	range 8 2048
931	depends on STACK_GROWSUP && (!64BIT || COMPAT)
932	help
933	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
934	  user processes when the stack grows upwards (currently only on parisc
935	  arch) when the RLIMIT_STACK hard limit is unlimited.
936
937	  A sane initial value is 100 MB.
938
939config DEFERRED_STRUCT_PAGE_INIT
940	bool "Defer initialisation of struct pages to kthreads"
941	depends on SPARSEMEM
942	depends on !NEED_PER_CPU_KM
943	depends on 64BIT
944	select PADATA
945	help
946	  Ordinarily all struct pages are initialised during early boot in a
947	  single thread. On very large machines this can take a considerable
948	  amount of time. If this option is set, large machines will bring up
949	  a subset of memmap at boot and then initialise the rest in parallel.
950	  This has a potential performance impact on tasks running early in the
951	  lifetime of the system until these kthreads finish the
952	  initialisation.
953
954config PAGE_IDLE_FLAG
955	bool
956	select PAGE_EXTENSION if !64BIT
957	help
958	  This adds PG_idle and PG_young flags to 'struct page'.  PTE Accessed
959	  bit writers can set the state of the bit in the flags so that PTE
960	  Accessed bit readers may avoid disturbance.
961
962config IDLE_PAGE_TRACKING
963	bool "Enable idle page tracking"
964	depends on SYSFS && MMU
965	select PAGE_IDLE_FLAG
966	help
967	  This feature allows to estimate the amount of user pages that have
968	  not been touched during a given period of time. This information can
969	  be useful to tune memory cgroup limits and/or for job placement
970	  within a compute cluster.
971
972	  See Documentation/admin-guide/mm/idle_page_tracking.rst for
973	  more details.
974
975# Architectures which implement cpu_dcache_is_aliasing() to query
976# whether the data caches are aliased (VIVT or VIPT with dcache
977# aliasing) need to select this.
978config ARCH_HAS_CPU_CACHE_ALIASING
979	bool
980
981config ARCH_HAS_CACHE_LINE_SIZE
982	bool
983
984config ARCH_HAS_CURRENT_STACK_POINTER
985	bool
986	help
987	  In support of HARDENED_USERCOPY performing stack variable lifetime
988	  checking, an architecture-agnostic way to find the stack pointer
989	  is needed. Once an architecture defines an unsigned long global
990	  register alias named "current_stack_pointer", this config can be
991	  selected.
992
993config ARCH_HAS_PTE_DEVMAP
994	bool
995
996config ARCH_HAS_ZONE_DMA_SET
997	bool
998
999config ZONE_DMA
1000	bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET
1001	default y if ARM64 || X86
1002
1003config ZONE_DMA32
1004	bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET
1005	depends on !X86_32
1006	default y if ARM64
1007
1008config ZONE_DEVICE
1009	bool "Device memory (pmem, HMM, etc...) hotplug support"
1010	depends on MEMORY_HOTPLUG
1011	depends on MEMORY_HOTREMOVE
1012	depends on SPARSEMEM_VMEMMAP
1013	depends on ARCH_HAS_PTE_DEVMAP
1014	select XARRAY_MULTI
1015
1016	help
1017	  Device memory hotplug support allows for establishing pmem,
1018	  or other device driver discovered memory regions, in the
1019	  memmap. This allows pfn_to_page() lookups of otherwise
1020	  "device-physical" addresses which is needed for using a DAX
1021	  mapping in an O_DIRECT operation, among other things.
1022
1023	  If FS_DAX is enabled, then say Y.
1024
1025#
1026# Helpers to mirror range of the CPU page tables of a process into device page
1027# tables.
1028#
1029config HMM_MIRROR
1030	bool
1031	depends on MMU
1032
1033config GET_FREE_REGION
1034	depends on SPARSEMEM
1035	bool
1036
1037config DEVICE_PRIVATE
1038	bool "Unaddressable device memory (GPU memory, ...)"
1039	depends on ZONE_DEVICE
1040	select GET_FREE_REGION
1041
1042	help
1043	  Allows creation of struct pages to represent unaddressable device
1044	  memory; i.e., memory that is only accessible from the device (or
1045	  group of devices). You likely also want to select HMM_MIRROR.
1046
1047config VMAP_PFN
1048	bool
1049
1050config ARCH_USES_HIGH_VMA_FLAGS
1051	bool
1052config ARCH_HAS_PKEYS
1053	bool
1054
1055config ARCH_USES_PG_ARCH_X
1056	bool
1057	help
1058	  Enable the definition of PG_arch_x page flags with x > 1. Only
1059	  suitable for 64-bit architectures with CONFIG_FLATMEM or
1060	  CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be
1061	  enough room for additional bits in page->flags.
1062
1063config VM_EVENT_COUNTERS
1064	default y
1065	bool "Enable VM event counters for /proc/vmstat" if EXPERT
1066	help
1067	  VM event counters are needed for event counts to be shown.
1068	  This option allows the disabling of the VM event counters
1069	  on EXPERT systems.  /proc/vmstat will only show page counts
1070	  if VM event counters are disabled.
1071
1072config PERCPU_STATS
1073	bool "Collect percpu memory statistics"
1074	help
1075	  This feature collects and exposes statistics via debugfs. The
1076	  information includes global and per chunk statistics, which can
1077	  be used to help understand percpu memory usage.
1078
1079config GUP_TEST
1080	bool "Enable infrastructure for get_user_pages()-related unit tests"
1081	depends on DEBUG_FS
1082	help
1083	  Provides /sys/kernel/debug/gup_test, which in turn provides a way
1084	  to make ioctl calls that can launch kernel-based unit tests for
1085	  the get_user_pages*() and pin_user_pages*() family of API calls.
1086
1087	  These tests include benchmark testing of the _fast variants of
1088	  get_user_pages*() and pin_user_pages*(), as well as smoke tests of
1089	  the non-_fast variants.
1090
1091	  There is also a sub-test that allows running dump_page() on any
1092	  of up to eight pages (selected by command line args) within the
1093	  range of user-space addresses. These pages are either pinned via
1094	  pin_user_pages*(), or pinned via get_user_pages*(), as specified
1095	  by other command line arguments.
1096
1097	  See tools/testing/selftests/mm/gup_test.c
1098
1099comment "GUP_TEST needs to have DEBUG_FS enabled"
1100	depends on !GUP_TEST && !DEBUG_FS
1101
1102config GUP_GET_PXX_LOW_HIGH
1103	bool
1104
1105config DMAPOOL_TEST
1106	tristate "Enable a module to run time tests on dma_pool"
1107	depends on HAS_DMA
1108	help
1109	  Provides a test module that will allocate and free many blocks of
1110	  various sizes and report how long it takes. This is intended to
1111	  provide a consistent way to measure how changes to the
1112	  dma_pool_alloc/free routines affect performance.
1113
1114config ARCH_HAS_PTE_SPECIAL
1115	bool
1116
1117#
1118# Some architectures require a special hugepage directory format that is
1119# required to support multiple hugepage sizes. For example a4fe3ce76
1120# "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
1121# introduced it on powerpc.  This allows for a more flexible hugepage
1122# pagetable layouts.
1123#
1124config ARCH_HAS_HUGEPD
1125	bool
1126
1127config MAPPING_DIRTY_HELPERS
1128        bool
1129
1130config KMAP_LOCAL
1131	bool
1132
1133config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
1134	bool
1135
1136# struct io_mapping based helper.  Selected by drivers that need them
1137config IO_MAPPING
1138	bool
1139
1140config MEMFD_CREATE
1141	bool "Enable memfd_create() system call" if EXPERT
1142
1143config SECRETMEM
1144	default y
1145	bool "Enable memfd_secret() system call" if EXPERT
1146	depends on ARCH_HAS_SET_DIRECT_MAP
1147	help
1148	  Enable the memfd_secret() system call with the ability to create
1149	  memory areas visible only in the context of the owning process and
1150	  not mapped to other processes and other kernel page tables.
1151
1152config ANON_VMA_NAME
1153	bool "Anonymous VMA name support"
1154	depends on PROC_FS && ADVISE_SYSCALLS && MMU
1155
1156	help
1157	  Allow naming anonymous virtual memory areas.
1158
1159	  This feature allows assigning names to virtual memory areas. Assigned
1160	  names can be later retrieved from /proc/pid/maps and /proc/pid/smaps
1161	  and help identifying individual anonymous memory areas.
1162	  Assigning a name to anonymous virtual memory area might prevent that
1163	  area from being merged with adjacent virtual memory areas due to the
1164	  difference in their name.
1165
1166config HAVE_ARCH_USERFAULTFD_WP
1167	bool
1168	help
1169	  Arch has userfaultfd write protection support
1170
1171config HAVE_ARCH_USERFAULTFD_MINOR
1172	bool
1173	help
1174	  Arch has userfaultfd minor fault support
1175
1176menuconfig USERFAULTFD
1177	bool "Enable userfaultfd() system call"
1178	depends on MMU
1179	help
1180	  Enable the userfaultfd() system call that allows to intercept and
1181	  handle page faults in userland.
1182
1183if USERFAULTFD
1184config PTE_MARKER_UFFD_WP
1185	bool "Userfaultfd write protection support for shmem/hugetlbfs"
1186	default y
1187	depends on HAVE_ARCH_USERFAULTFD_WP
1188
1189	help
1190	  Allows to create marker PTEs for userfaultfd write protection
1191	  purposes.  It is required to enable userfaultfd write protection on
1192	  file-backed memory types like shmem and hugetlbfs.
1193endif # USERFAULTFD
1194
1195# multi-gen LRU {
1196config LRU_GEN
1197	bool "Multi-Gen LRU"
1198	depends on MMU
1199	# make sure folio->flags has enough spare bits
1200	depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP
1201	help
1202	  A high performance LRU implementation to overcommit memory. See
1203	  Documentation/admin-guide/mm/multigen_lru.rst for details.
1204
1205config LRU_GEN_ENABLED
1206	bool "Enable by default"
1207	depends on LRU_GEN
1208	help
1209	  This option enables the multi-gen LRU by default.
1210
1211config LRU_GEN_STATS
1212	bool "Full stats for debugging"
1213	depends on LRU_GEN
1214	help
1215	  Do not enable this option unless you plan to look at historical stats
1216	  from evicted generations for debugging purpose.
1217
1218	  This option has a per-memcg and per-node memory overhead.
1219
1220config LRU_GEN_WALKS_MMU
1221	def_bool y
1222	depends on LRU_GEN && ARCH_HAS_HW_PTE_YOUNG
1223# }
1224
1225config ARCH_SUPPORTS_PER_VMA_LOCK
1226       def_bool n
1227
1228config PER_VMA_LOCK
1229	def_bool y
1230	depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP
1231	help
1232	  Allow per-vma locking during page fault handling.
1233
1234	  This feature allows locking each virtual memory area separately when
1235	  handling page faults instead of taking mmap_lock.
1236
1237config LOCK_MM_AND_FIND_VMA
1238	bool
1239	depends on !STACK_GROWSUP
1240
1241config IOMMU_MM_DATA
1242	bool
1243
1244source "mm/damon/Kconfig"
1245
1246endmenu
1247