xref: /openbmc/linux/mm/Kconfig (revision 1b39e7607144337d752f36c2068ed79447462f99)
1 # SPDX-License-Identifier: GPL-2.0-only
2 
3 menu "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 #
9 config ARCH_NO_SWAP
10 	bool
11 
12 config ZPOOL
13 	bool
14 
15 menuconfig 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 
25 config 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 
39 config 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 
49 choice
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 
67 config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
68 	bool "Deflate"
69 	select CRYPTO_DEFLATE
70 	help
71 	  Use the Deflate algorithm as the default compression algorithm.
72 
73 config ZSWAP_COMPRESSOR_DEFAULT_LZO
74 	bool "LZO"
75 	select CRYPTO_LZO
76 	help
77 	  Use the LZO algorithm as the default compression algorithm.
78 
79 config ZSWAP_COMPRESSOR_DEFAULT_842
80 	bool "842"
81 	select CRYPTO_842
82 	help
83 	  Use the 842 algorithm as the default compression algorithm.
84 
85 config ZSWAP_COMPRESSOR_DEFAULT_LZ4
86 	bool "LZ4"
87 	select CRYPTO_LZ4
88 	help
89 	  Use the LZ4 algorithm as the default compression algorithm.
90 
91 config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
92 	bool "LZ4HC"
93 	select CRYPTO_LZ4HC
94 	help
95 	  Use the LZ4HC algorithm as the default compression algorithm.
96 
97 config ZSWAP_COMPRESSOR_DEFAULT_ZSTD
98 	bool "zstd"
99 	select CRYPTO_ZSTD
100 	help
101 	  Use the zstd algorithm as the default compression algorithm.
102 endchoice
103 
104 config 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 
115 choice
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 
129 config ZSWAP_ZPOOL_DEFAULT_ZBUD
130 	bool "zbud"
131 	select ZBUD
132 	help
133 	  Use the zbud allocator as the default allocator.
134 
135 config ZSWAP_ZPOOL_DEFAULT_Z3FOLD
136 	bool "z3fold"
137 	select Z3FOLD
138 	help
139 	  Use the z3fold allocator as the default allocator.
140 
141 config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
142 	bool "zsmalloc"
143 	select ZSMALLOC
144 	help
145 	  Use the zsmalloc allocator as the default allocator.
146 endchoice
147 
148 config 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 
156 config 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 
166 config 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 
175 config 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 
184 config 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 
194 config ZSMALLOC_CHAIN_SIZE
195 	int "Maximum number of physical pages per-zspage"
196 	default 8
197 	range 4 16
198 	depends on ZSMALLOC
199 	help
200 	  This option sets the upper limit on the number of physical pages
201 	  that a zmalloc page (zspage) can consist of. The optimal zspage
202 	  chain size is calculated for each size class during the
203 	  initialization of the pool.
204 
205 	  Changing this option can alter the characteristics of size classes,
206 	  such as the number of pages per zspage and the number of objects
207 	  per zspage. This can also result in different configurations of
208 	  the pool, as zsmalloc merges size classes with similar
209 	  characteristics.
210 
211 	  For more information, see zsmalloc documentation.
212 
213 menu "SLAB allocator options"
214 
215 choice
216 	prompt "Choose SLAB allocator"
217 	default SLUB
218 	help
219 	   This option allows to select a slab allocator.
220 
221 config SLAB
222 	bool "SLAB"
223 	depends on !PREEMPT_RT
224 	select HAVE_HARDENED_USERCOPY_ALLOCATOR
225 	help
226 	  The regular slab allocator that is established and known to work
227 	  well in all environments. It organizes cache hot objects in
228 	  per cpu and per node queues.
229 
230 config SLUB
231 	bool "SLUB (Unqueued Allocator)"
232 	select HAVE_HARDENED_USERCOPY_ALLOCATOR
233 	help
234 	   SLUB is a slab allocator that minimizes cache line usage
235 	   instead of managing queues of cached objects (SLAB approach).
236 	   Per cpu caching is realized using slabs of objects instead
237 	   of queues of objects. SLUB can use memory efficiently
238 	   and has enhanced diagnostics. SLUB is the default choice for
239 	   a slab allocator.
240 
241 endchoice
242 
243 config SLUB_TINY
244 	bool "Configure SLUB for minimal memory footprint"
245 	depends on SLUB && EXPERT
246 	select SLAB_MERGE_DEFAULT
247 	help
248 	   Configures the SLUB allocator in a way to achieve minimal memory
249 	   footprint, sacrificing scalability, debugging and other features.
250 	   This is intended only for the smallest system that had used the
251 	   SLOB allocator and is not recommended for systems with more than
252 	   16MB RAM.
253 
254 	   If unsure, say N.
255 
256 config SLAB_MERGE_DEFAULT
257 	bool "Allow slab caches to be merged"
258 	default y
259 	depends on SLAB || SLUB
260 	help
261 	  For reduced kernel memory fragmentation, slab caches can be
262 	  merged when they share the same size and other characteristics.
263 	  This carries a risk of kernel heap overflows being able to
264 	  overwrite objects from merged caches (and more easily control
265 	  cache layout), which makes such heap attacks easier to exploit
266 	  by attackers. By keeping caches unmerged, these kinds of exploits
267 	  can usually only damage objects in the same cache. To disable
268 	  merging at runtime, "slab_nomerge" can be passed on the kernel
269 	  command line.
270 
271 config SLAB_FREELIST_RANDOM
272 	bool "Randomize slab freelist"
273 	depends on SLAB || (SLUB && !SLUB_TINY)
274 	help
275 	  Randomizes the freelist order used on creating new pages. This
276 	  security feature reduces the predictability of the kernel slab
277 	  allocator against heap overflows.
278 
279 config SLAB_FREELIST_HARDENED
280 	bool "Harden slab freelist metadata"
281 	depends on SLAB || (SLUB && !SLUB_TINY)
282 	help
283 	  Many kernel heap attacks try to target slab cache metadata and
284 	  other infrastructure. This options makes minor performance
285 	  sacrifices to harden the kernel slab allocator against common
286 	  freelist exploit methods. Some slab implementations have more
287 	  sanity-checking than others. This option is most effective with
288 	  CONFIG_SLUB.
289 
290 config SLUB_STATS
291 	default n
292 	bool "Enable SLUB performance statistics"
293 	depends on SLUB && SYSFS && !SLUB_TINY
294 	help
295 	  SLUB statistics are useful to debug SLUBs allocation behavior in
296 	  order find ways to optimize the allocator. This should never be
297 	  enabled for production use since keeping statistics slows down
298 	  the allocator by a few percentage points. The slabinfo command
299 	  supports the determination of the most active slabs to figure
300 	  out which slabs are relevant to a particular load.
301 	  Try running: slabinfo -DA
302 
303 config SLUB_CPU_PARTIAL
304 	default y
305 	depends on SLUB && SMP && !SLUB_TINY
306 	bool "SLUB per cpu partial cache"
307 	help
308 	  Per cpu partial caches accelerate objects allocation and freeing
309 	  that is local to a processor at the price of more indeterminism
310 	  in the latency of the free. On overflow these caches will be cleared
311 	  which requires the taking of locks that may cause latency spikes.
312 	  Typically one would choose no for a realtime system.
313 
314 endmenu # SLAB allocator options
315 
316 config SHUFFLE_PAGE_ALLOCATOR
317 	bool "Page allocator randomization"
318 	default SLAB_FREELIST_RANDOM && ACPI_NUMA
319 	help
320 	  Randomization of the page allocator improves the average
321 	  utilization of a direct-mapped memory-side-cache. See section
322 	  5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI
323 	  6.2a specification for an example of how a platform advertises
324 	  the presence of a memory-side-cache. There are also incidental
325 	  security benefits as it reduces the predictability of page
326 	  allocations to compliment SLAB_FREELIST_RANDOM, but the
327 	  default granularity of shuffling on the MAX_ORDER i.e, 10th
328 	  order of pages is selected based on cache utilization benefits
329 	  on x86.
330 
331 	  While the randomization improves cache utilization it may
332 	  negatively impact workloads on platforms without a cache. For
333 	  this reason, by default, the randomization is enabled only
334 	  after runtime detection of a direct-mapped memory-side-cache.
335 	  Otherwise, the randomization may be force enabled with the
336 	  'page_alloc.shuffle' kernel command line parameter.
337 
338 	  Say Y if unsure.
339 
340 config COMPAT_BRK
341 	bool "Disable heap randomization"
342 	default y
343 	help
344 	  Randomizing heap placement makes heap exploits harder, but it
345 	  also breaks ancient binaries (including anything libc5 based).
346 	  This option changes the bootup default to heap randomization
347 	  disabled, and can be overridden at runtime by setting
348 	  /proc/sys/kernel/randomize_va_space to 2.
349 
350 	  On non-ancient distros (post-2000 ones) N is usually a safe choice.
351 
352 config MMAP_ALLOW_UNINITIALIZED
353 	bool "Allow mmapped anonymous memory to be uninitialized"
354 	depends on EXPERT && !MMU
355 	default n
356 	help
357 	  Normally, and according to the Linux spec, anonymous memory obtained
358 	  from mmap() has its contents cleared before it is passed to
359 	  userspace.  Enabling this config option allows you to request that
360 	  mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
361 	  providing a huge performance boost.  If this option is not enabled,
362 	  then the flag will be ignored.
363 
364 	  This is taken advantage of by uClibc's malloc(), and also by
365 	  ELF-FDPIC binfmt's brk and stack allocator.
366 
367 	  Because of the obvious security issues, this option should only be
368 	  enabled on embedded devices where you control what is run in
369 	  userspace.  Since that isn't generally a problem on no-MMU systems,
370 	  it is normally safe to say Y here.
371 
372 	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
373 
374 config SELECT_MEMORY_MODEL
375 	def_bool y
376 	depends on ARCH_SELECT_MEMORY_MODEL
377 
378 choice
379 	prompt "Memory model"
380 	depends on SELECT_MEMORY_MODEL
381 	default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
382 	default FLATMEM_MANUAL
383 	help
384 	  This option allows you to change some of the ways that
385 	  Linux manages its memory internally. Most users will
386 	  only have one option here selected by the architecture
387 	  configuration. This is normal.
388 
389 config FLATMEM_MANUAL
390 	bool "Flat Memory"
391 	depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE
392 	help
393 	  This option is best suited for non-NUMA systems with
394 	  flat address space. The FLATMEM is the most efficient
395 	  system in terms of performance and resource consumption
396 	  and it is the best option for smaller systems.
397 
398 	  For systems that have holes in their physical address
399 	  spaces and for features like NUMA and memory hotplug,
400 	  choose "Sparse Memory".
401 
402 	  If unsure, choose this option (Flat Memory) over any other.
403 
404 config SPARSEMEM_MANUAL
405 	bool "Sparse Memory"
406 	depends on ARCH_SPARSEMEM_ENABLE
407 	help
408 	  This will be the only option for some systems, including
409 	  memory hot-plug systems.  This is normal.
410 
411 	  This option provides efficient support for systems with
412 	  holes is their physical address space and allows memory
413 	  hot-plug and hot-remove.
414 
415 	  If unsure, choose "Flat Memory" over this option.
416 
417 endchoice
418 
419 config SPARSEMEM
420 	def_bool y
421 	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
422 
423 config FLATMEM
424 	def_bool y
425 	depends on !SPARSEMEM || FLATMEM_MANUAL
426 
427 #
428 # SPARSEMEM_EXTREME (which is the default) does some bootmem
429 # allocations when sparse_init() is called.  If this cannot
430 # be done on your architecture, select this option.  However,
431 # statically allocating the mem_section[] array can potentially
432 # consume vast quantities of .bss, so be careful.
433 #
434 # This option will also potentially produce smaller runtime code
435 # with gcc 3.4 and later.
436 #
437 config SPARSEMEM_STATIC
438 	bool
439 
440 #
441 # Architecture platforms which require a two level mem_section in SPARSEMEM
442 # must select this option. This is usually for architecture platforms with
443 # an extremely sparse physical address space.
444 #
445 config SPARSEMEM_EXTREME
446 	def_bool y
447 	depends on SPARSEMEM && !SPARSEMEM_STATIC
448 
449 config SPARSEMEM_VMEMMAP_ENABLE
450 	bool
451 
452 config SPARSEMEM_VMEMMAP
453 	bool "Sparse Memory virtual memmap"
454 	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
455 	default y
456 	help
457 	  SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
458 	  pfn_to_page and page_to_pfn operations.  This is the most
459 	  efficient option when sufficient kernel resources are available.
460 #
461 # Select this config option from the architecture Kconfig, if it is preferred
462 # to enable the feature of HugeTLB/dev_dax vmemmap optimization.
463 #
464 config ARCH_WANT_OPTIMIZE_VMEMMAP
465 	bool
466 
467 config HAVE_MEMBLOCK_PHYS_MAP
468 	bool
469 
470 config HAVE_FAST_GUP
471 	depends on MMU
472 	bool
473 
474 # Don't discard allocated memory used to track "memory" and "reserved" memblocks
475 # after early boot, so it can still be used to test for validity of memory.
476 # Also, memblocks are updated with memory hot(un)plug.
477 config ARCH_KEEP_MEMBLOCK
478 	bool
479 
480 # Keep arch NUMA mapping infrastructure post-init.
481 config NUMA_KEEP_MEMINFO
482 	bool
483 
484 config MEMORY_ISOLATION
485 	bool
486 
487 # IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked
488 # IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via
489 # /dev/mem.
490 config EXCLUSIVE_SYSTEM_RAM
491 	def_bool y
492 	depends on !DEVMEM || STRICT_DEVMEM
493 
494 #
495 # Only be set on architectures that have completely implemented memory hotplug
496 # feature. If you are not sure, don't touch it.
497 #
498 config HAVE_BOOTMEM_INFO_NODE
499 	def_bool n
500 
501 config ARCH_ENABLE_MEMORY_HOTPLUG
502 	bool
503 
504 config ARCH_ENABLE_MEMORY_HOTREMOVE
505 	bool
506 
507 # eventually, we can have this option just 'select SPARSEMEM'
508 menuconfig MEMORY_HOTPLUG
509 	bool "Memory hotplug"
510 	select MEMORY_ISOLATION
511 	depends on SPARSEMEM
512 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
513 	depends on 64BIT
514 	select NUMA_KEEP_MEMINFO if NUMA
515 
516 if MEMORY_HOTPLUG
517 
518 config MEMORY_HOTPLUG_DEFAULT_ONLINE
519 	bool "Online the newly added memory blocks by default"
520 	depends on MEMORY_HOTPLUG
521 	help
522 	  This option sets the default policy setting for memory hotplug
523 	  onlining policy (/sys/devices/system/memory/auto_online_blocks) which
524 	  determines what happens to newly added memory regions. Policy setting
525 	  can always be changed at runtime.
526 	  See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
527 
528 	  Say Y here if you want all hot-plugged memory blocks to appear in
529 	  'online' state by default.
530 	  Say N here if you want the default policy to keep all hot-plugged
531 	  memory blocks in 'offline' state.
532 
533 config MEMORY_HOTREMOVE
534 	bool "Allow for memory hot remove"
535 	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
536 	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
537 	depends on MIGRATION
538 
539 config MHP_MEMMAP_ON_MEMORY
540 	def_bool y
541 	depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
542 	depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
543 
544 endif # MEMORY_HOTPLUG
545 
546 # Heavily threaded applications may benefit from splitting the mm-wide
547 # page_table_lock, so that faults on different parts of the user address
548 # space can be handled with less contention: split it at this NR_CPUS.
549 # Default to 4 for wider testing, though 8 might be more appropriate.
550 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
551 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
552 # SPARC32 allocates multiple pte tables within a single page, and therefore
553 # a per-page lock leads to problems when multiple tables need to be locked
554 # at the same time (e.g. copy_page_range()).
555 # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
556 #
557 config SPLIT_PTLOCK_CPUS
558 	int
559 	default "999999" if !MMU
560 	default "999999" if ARM && !CPU_CACHE_VIPT
561 	default "999999" if PARISC && !PA20
562 	default "999999" if SPARC32
563 	default "4"
564 
565 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
566 	bool
567 
568 #
569 # support for memory balloon
570 config MEMORY_BALLOON
571 	bool
572 
573 #
574 # support for memory balloon compaction
575 config BALLOON_COMPACTION
576 	bool "Allow for balloon memory compaction/migration"
577 	def_bool y
578 	depends on COMPACTION && MEMORY_BALLOON
579 	help
580 	  Memory fragmentation introduced by ballooning might reduce
581 	  significantly the number of 2MB contiguous memory blocks that can be
582 	  used within a guest, thus imposing performance penalties associated
583 	  with the reduced number of transparent huge pages that could be used
584 	  by the guest workload. Allowing the compaction & migration for memory
585 	  pages enlisted as being part of memory balloon devices avoids the
586 	  scenario aforementioned and helps improving memory defragmentation.
587 
588 #
589 # support for memory compaction
590 config COMPACTION
591 	bool "Allow for memory compaction"
592 	def_bool y
593 	select MIGRATION
594 	depends on MMU
595 	help
596 	  Compaction is the only memory management component to form
597 	  high order (larger physically contiguous) memory blocks
598 	  reliably. The page allocator relies on compaction heavily and
599 	  the lack of the feature can lead to unexpected OOM killer
600 	  invocations for high order memory requests. You shouldn't
601 	  disable this option unless there really is a strong reason for
602 	  it and then we would be really interested to hear about that at
603 	  linux-mm@kvack.org.
604 
605 config COMPACT_UNEVICTABLE_DEFAULT
606 	int
607 	depends on COMPACTION
608 	default 0 if PREEMPT_RT
609 	default 1
610 
611 #
612 # support for free page reporting
613 config PAGE_REPORTING
614 	bool "Free page reporting"
615 	def_bool n
616 	help
617 	  Free page reporting allows for the incremental acquisition of
618 	  free pages from the buddy allocator for the purpose of reporting
619 	  those pages to another entity, such as a hypervisor, so that the
620 	  memory can be freed within the host for other uses.
621 
622 #
623 # support for page migration
624 #
625 config MIGRATION
626 	bool "Page migration"
627 	def_bool y
628 	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
629 	help
630 	  Allows the migration of the physical location of pages of processes
631 	  while the virtual addresses are not changed. This is useful in
632 	  two situations. The first is on NUMA systems to put pages nearer
633 	  to the processors accessing. The second is when allocating huge
634 	  pages as migration can relocate pages to satisfy a huge page
635 	  allocation instead of reclaiming.
636 
637 config DEVICE_MIGRATION
638 	def_bool MIGRATION && ZONE_DEVICE
639 
640 config ARCH_ENABLE_HUGEPAGE_MIGRATION
641 	bool
642 
643 config ARCH_ENABLE_THP_MIGRATION
644 	bool
645 
646 config HUGETLB_PAGE_SIZE_VARIABLE
647 	def_bool n
648 	help
649 	  Allows the pageblock_order value to be dynamic instead of just standard
650 	  HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
651 	  on a platform.
652 
653 	  Note that the pageblock_order cannot exceed MAX_ORDER and will be
654 	  clamped down to MAX_ORDER.
655 
656 config CONTIG_ALLOC
657 	def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
658 
659 config PHYS_ADDR_T_64BIT
660 	def_bool 64BIT
661 
662 config BOUNCE
663 	bool "Enable bounce buffers"
664 	default y
665 	depends on BLOCK && MMU && HIGHMEM
666 	help
667 	  Enable bounce buffers for devices that cannot access the full range of
668 	  memory available to the CPU. Enabled by default when HIGHMEM is
669 	  selected, but you may say n to override this.
670 
671 config MMU_NOTIFIER
672 	bool
673 	select INTERVAL_TREE
674 
675 config KSM
676 	bool "Enable KSM for page merging"
677 	depends on MMU
678 	select XXHASH
679 	help
680 	  Enable Kernel Samepage Merging: KSM periodically scans those areas
681 	  of an application's address space that an app has advised may be
682 	  mergeable.  When it finds pages of identical content, it replaces
683 	  the many instances by a single page with that content, so
684 	  saving memory until one or another app needs to modify the content.
685 	  Recommended for use with KVM, or with other duplicative applications.
686 	  See Documentation/mm/ksm.rst for more information: KSM is inactive
687 	  until a program has madvised that an area is MADV_MERGEABLE, and
688 	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
689 
690 config DEFAULT_MMAP_MIN_ADDR
691 	int "Low address space to protect from user allocation"
692 	depends on MMU
693 	default 4096
694 	help
695 	  This is the portion of low virtual memory which should be protected
696 	  from userspace allocation.  Keeping a user from writing to low pages
697 	  can help reduce the impact of kernel NULL pointer bugs.
698 
699 	  For most ia64, ppc64 and x86 users with lots of address space
700 	  a value of 65536 is reasonable and should cause no problems.
701 	  On arm and other archs it should not be higher than 32768.
702 	  Programs which use vm86 functionality or have some need to map
703 	  this low address space will need CAP_SYS_RAWIO or disable this
704 	  protection by setting the value to 0.
705 
706 	  This value can be changed after boot using the
707 	  /proc/sys/vm/mmap_min_addr tunable.
708 
709 config ARCH_SUPPORTS_MEMORY_FAILURE
710 	bool
711 
712 config MEMORY_FAILURE
713 	depends on MMU
714 	depends on ARCH_SUPPORTS_MEMORY_FAILURE
715 	bool "Enable recovery from hardware memory errors"
716 	select MEMORY_ISOLATION
717 	select RAS
718 	help
719 	  Enables code to recover from some memory failures on systems
720 	  with MCA recovery. This allows a system to continue running
721 	  even when some of its memory has uncorrected errors. This requires
722 	  special hardware support and typically ECC memory.
723 
724 config HWPOISON_INJECT
725 	tristate "HWPoison pages injector"
726 	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
727 	select PROC_PAGE_MONITOR
728 
729 config NOMMU_INITIAL_TRIM_EXCESS
730 	int "Turn on mmap() excess space trimming before booting"
731 	depends on !MMU
732 	default 1
733 	help
734 	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
735 	  of memory on which to store mappings, but it can only ask the system
736 	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
737 	  more than it requires.  To deal with this, mmap() is able to trim off
738 	  the excess and return it to the allocator.
739 
740 	  If trimming is enabled, the excess is trimmed off and returned to the
741 	  system allocator, which can cause extra fragmentation, particularly
742 	  if there are a lot of transient processes.
743 
744 	  If trimming is disabled, the excess is kept, but not used, which for
745 	  long-term mappings means that the space is wasted.
746 
747 	  Trimming can be dynamically controlled through a sysctl option
748 	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
749 	  excess pages there must be before trimming should occur, or zero if
750 	  no trimming is to occur.
751 
752 	  This option specifies the initial value of this option.  The default
753 	  of 1 says that all excess pages should be trimmed.
754 
755 	  See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
756 
757 config ARCH_WANT_GENERAL_HUGETLB
758 	bool
759 
760 config ARCH_WANTS_THP_SWAP
761 	def_bool n
762 
763 menuconfig TRANSPARENT_HUGEPAGE
764 	bool "Transparent Hugepage Support"
765 	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT
766 	select COMPACTION
767 	select XARRAY_MULTI
768 	help
769 	  Transparent Hugepages allows the kernel to use huge pages and
770 	  huge tlb transparently to the applications whenever possible.
771 	  This feature can improve computing performance to certain
772 	  applications by speeding up page faults during memory
773 	  allocation, by reducing the number of tlb misses and by speeding
774 	  up the pagetable walking.
775 
776 	  If memory constrained on embedded, you may want to say N.
777 
778 if TRANSPARENT_HUGEPAGE
779 
780 choice
781 	prompt "Transparent Hugepage Support sysfs defaults"
782 	depends on TRANSPARENT_HUGEPAGE
783 	default TRANSPARENT_HUGEPAGE_ALWAYS
784 	help
785 	  Selects the sysfs defaults for Transparent Hugepage Support.
786 
787 	config TRANSPARENT_HUGEPAGE_ALWAYS
788 		bool "always"
789 	help
790 	  Enabling Transparent Hugepage always, can increase the
791 	  memory footprint of applications without a guaranteed
792 	  benefit but it will work automatically for all applications.
793 
794 	config TRANSPARENT_HUGEPAGE_MADVISE
795 		bool "madvise"
796 	help
797 	  Enabling Transparent Hugepage madvise, will only provide a
798 	  performance improvement benefit to the applications using
799 	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
800 	  memory footprint of applications without a guaranteed
801 	  benefit.
802 endchoice
803 
804 config THP_SWAP
805 	def_bool y
806 	depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT
807 	help
808 	  Swap transparent huge pages in one piece, without splitting.
809 	  XXX: For now, swap cluster backing transparent huge page
810 	  will be split after swapout.
811 
812 	  For selection by architectures with reasonable THP sizes.
813 
814 config READ_ONLY_THP_FOR_FS
815 	bool "Read-only THP for filesystems (EXPERIMENTAL)"
816 	depends on TRANSPARENT_HUGEPAGE && SHMEM
817 
818 	help
819 	  Allow khugepaged to put read-only file-backed pages in THP.
820 
821 	  This is marked experimental because it is a new feature. Write
822 	  support of file THPs will be developed in the next few release
823 	  cycles.
824 
825 endif # TRANSPARENT_HUGEPAGE
826 
827 #
828 # UP and nommu archs use km based percpu allocator
829 #
830 config NEED_PER_CPU_KM
831 	depends on !SMP || !MMU
832 	bool
833 	default y
834 
835 config NEED_PER_CPU_EMBED_FIRST_CHUNK
836 	bool
837 
838 config NEED_PER_CPU_PAGE_FIRST_CHUNK
839 	bool
840 
841 config USE_PERCPU_NUMA_NODE_ID
842 	bool
843 
844 config HAVE_SETUP_PER_CPU_AREA
845 	bool
846 
847 config FRONTSWAP
848 	bool
849 
850 config CMA
851 	bool "Contiguous Memory Allocator"
852 	depends on MMU
853 	select MIGRATION
854 	select MEMORY_ISOLATION
855 	help
856 	  This enables the Contiguous Memory Allocator which allows other
857 	  subsystems to allocate big physically-contiguous blocks of memory.
858 	  CMA reserves a region of memory and allows only movable pages to
859 	  be allocated from it. This way, the kernel can use the memory for
860 	  pagecache and when a subsystem requests for contiguous area, the
861 	  allocated pages are migrated away to serve the contiguous request.
862 
863 	  If unsure, say "n".
864 
865 config CMA_DEBUG
866 	bool "CMA debug messages (DEVELOPMENT)"
867 	depends on DEBUG_KERNEL && CMA
868 	help
869 	  Turns on debug messages in CMA.  This produces KERN_DEBUG
870 	  messages for every CMA call as well as various messages while
871 	  processing calls such as dma_alloc_from_contiguous().
872 	  This option does not affect warning and error messages.
873 
874 config CMA_DEBUGFS
875 	bool "CMA debugfs interface"
876 	depends on CMA && DEBUG_FS
877 	help
878 	  Turns on the DebugFS interface for CMA.
879 
880 config CMA_SYSFS
881 	bool "CMA information through sysfs interface"
882 	depends on CMA && SYSFS
883 	help
884 	  This option exposes some sysfs attributes to get information
885 	  from CMA.
886 
887 config CMA_AREAS
888 	int "Maximum count of the CMA areas"
889 	depends on CMA
890 	default 19 if NUMA
891 	default 7
892 	help
893 	  CMA allows to create CMA areas for particular purpose, mainly,
894 	  used as device private area. This parameter sets the maximum
895 	  number of CMA area in the system.
896 
897 	  If unsure, leave the default value "7" in UMA and "19" in NUMA.
898 
899 config MEM_SOFT_DIRTY
900 	bool "Track memory changes"
901 	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
902 	select PROC_PAGE_MONITOR
903 	help
904 	  This option enables memory changes tracking by introducing a
905 	  soft-dirty bit on pte-s. This bit it set when someone writes
906 	  into a page just as regular dirty bit, but unlike the latter
907 	  it can be cleared by hands.
908 
909 	  See Documentation/admin-guide/mm/soft-dirty.rst for more details.
910 
911 config GENERIC_EARLY_IOREMAP
912 	bool
913 
914 config STACK_MAX_DEFAULT_SIZE_MB
915 	int "Default maximum user stack size for 32-bit processes (MB)"
916 	default 100
917 	range 8 2048
918 	depends on STACK_GROWSUP && (!64BIT || COMPAT)
919 	help
920 	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
921 	  user processes when the stack grows upwards (currently only on parisc
922 	  arch) when the RLIMIT_STACK hard limit is unlimited.
923 
924 	  A sane initial value is 100 MB.
925 
926 config DEFERRED_STRUCT_PAGE_INIT
927 	bool "Defer initialisation of struct pages to kthreads"
928 	depends on SPARSEMEM
929 	depends on !NEED_PER_CPU_KM
930 	depends on 64BIT
931 	select PADATA
932 	help
933 	  Ordinarily all struct pages are initialised during early boot in a
934 	  single thread. On very large machines this can take a considerable
935 	  amount of time. If this option is set, large machines will bring up
936 	  a subset of memmap at boot and then initialise the rest in parallel.
937 	  This has a potential performance impact on tasks running early in the
938 	  lifetime of the system until these kthreads finish the
939 	  initialisation.
940 
941 config PAGE_IDLE_FLAG
942 	bool
943 	select PAGE_EXTENSION if !64BIT
944 	help
945 	  This adds PG_idle and PG_young flags to 'struct page'.  PTE Accessed
946 	  bit writers can set the state of the bit in the flags so that PTE
947 	  Accessed bit readers may avoid disturbance.
948 
949 config IDLE_PAGE_TRACKING
950 	bool "Enable idle page tracking"
951 	depends on SYSFS && MMU
952 	select PAGE_IDLE_FLAG
953 	help
954 	  This feature allows to estimate the amount of user pages that have
955 	  not been touched during a given period of time. This information can
956 	  be useful to tune memory cgroup limits and/or for job placement
957 	  within a compute cluster.
958 
959 	  See Documentation/admin-guide/mm/idle_page_tracking.rst for
960 	  more details.
961 
962 config ARCH_HAS_CACHE_LINE_SIZE
963 	bool
964 
965 config ARCH_HAS_CURRENT_STACK_POINTER
966 	bool
967 	help
968 	  In support of HARDENED_USERCOPY performing stack variable lifetime
969 	  checking, an architecture-agnostic way to find the stack pointer
970 	  is needed. Once an architecture defines an unsigned long global
971 	  register alias named "current_stack_pointer", this config can be
972 	  selected.
973 
974 config ARCH_HAS_PTE_DEVMAP
975 	bool
976 
977 config ARCH_HAS_ZONE_DMA_SET
978 	bool
979 
980 config ZONE_DMA
981 	bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET
982 	default y if ARM64 || X86
983 
984 config ZONE_DMA32
985 	bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET
986 	depends on !X86_32
987 	default y if ARM64
988 
989 config ZONE_DEVICE
990 	bool "Device memory (pmem, HMM, etc...) hotplug support"
991 	depends on MEMORY_HOTPLUG
992 	depends on MEMORY_HOTREMOVE
993 	depends on SPARSEMEM_VMEMMAP
994 	depends on ARCH_HAS_PTE_DEVMAP
995 	select XARRAY_MULTI
996 
997 	help
998 	  Device memory hotplug support allows for establishing pmem,
999 	  or other device driver discovered memory regions, in the
1000 	  memmap. This allows pfn_to_page() lookups of otherwise
1001 	  "device-physical" addresses which is needed for using a DAX
1002 	  mapping in an O_DIRECT operation, among other things.
1003 
1004 	  If FS_DAX is enabled, then say Y.
1005 
1006 #
1007 # Helpers to mirror range of the CPU page tables of a process into device page
1008 # tables.
1009 #
1010 config HMM_MIRROR
1011 	bool
1012 	depends on MMU
1013 
1014 config GET_FREE_REGION
1015 	depends on SPARSEMEM
1016 	bool
1017 
1018 config DEVICE_PRIVATE
1019 	bool "Unaddressable device memory (GPU memory, ...)"
1020 	depends on ZONE_DEVICE
1021 	select GET_FREE_REGION
1022 
1023 	help
1024 	  Allows creation of struct pages to represent unaddressable device
1025 	  memory; i.e., memory that is only accessible from the device (or
1026 	  group of devices). You likely also want to select HMM_MIRROR.
1027 
1028 config VMAP_PFN
1029 	bool
1030 
1031 config ARCH_USES_HIGH_VMA_FLAGS
1032 	bool
1033 config ARCH_HAS_PKEYS
1034 	bool
1035 
1036 config ARCH_USES_PG_ARCH_X
1037 	bool
1038 	help
1039 	  Enable the definition of PG_arch_x page flags with x > 1. Only
1040 	  suitable for 64-bit architectures with CONFIG_FLATMEM or
1041 	  CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be
1042 	  enough room for additional bits in page->flags.
1043 
1044 config VM_EVENT_COUNTERS
1045 	default y
1046 	bool "Enable VM event counters for /proc/vmstat" if EXPERT
1047 	help
1048 	  VM event counters are needed for event counts to be shown.
1049 	  This option allows the disabling of the VM event counters
1050 	  on EXPERT systems.  /proc/vmstat will only show page counts
1051 	  if VM event counters are disabled.
1052 
1053 config PERCPU_STATS
1054 	bool "Collect percpu memory statistics"
1055 	help
1056 	  This feature collects and exposes statistics via debugfs. The
1057 	  information includes global and per chunk statistics, which can
1058 	  be used to help understand percpu memory usage.
1059 
1060 config GUP_TEST
1061 	bool "Enable infrastructure for get_user_pages()-related unit tests"
1062 	depends on DEBUG_FS
1063 	help
1064 	  Provides /sys/kernel/debug/gup_test, which in turn provides a way
1065 	  to make ioctl calls that can launch kernel-based unit tests for
1066 	  the get_user_pages*() and pin_user_pages*() family of API calls.
1067 
1068 	  These tests include benchmark testing of the _fast variants of
1069 	  get_user_pages*() and pin_user_pages*(), as well as smoke tests of
1070 	  the non-_fast variants.
1071 
1072 	  There is also a sub-test that allows running dump_page() on any
1073 	  of up to eight pages (selected by command line args) within the
1074 	  range of user-space addresses. These pages are either pinned via
1075 	  pin_user_pages*(), or pinned via get_user_pages*(), as specified
1076 	  by other command line arguments.
1077 
1078 	  See tools/testing/selftests/mm/gup_test.c
1079 
1080 comment "GUP_TEST needs to have DEBUG_FS enabled"
1081 	depends on !GUP_TEST && !DEBUG_FS
1082 
1083 config GUP_GET_PXX_LOW_HIGH
1084 	bool
1085 
1086 config DMAPOOL_TEST
1087 	tristate "Enable a module to run time tests on dma_pool"
1088 	depends on HAS_DMA
1089 	help
1090 	  Provides a test module that will allocate and free many blocks of
1091 	  various sizes and report how long it takes. This is intended to
1092 	  provide a consistent way to measure how changes to the
1093 	  dma_pool_alloc/free routines affect performance.
1094 
1095 config ARCH_HAS_PTE_SPECIAL
1096 	bool
1097 
1098 #
1099 # Some architectures require a special hugepage directory format that is
1100 # required to support multiple hugepage sizes. For example a4fe3ce76
1101 # "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
1102 # introduced it on powerpc.  This allows for a more flexible hugepage
1103 # pagetable layouts.
1104 #
1105 config ARCH_HAS_HUGEPD
1106 	bool
1107 
1108 config MAPPING_DIRTY_HELPERS
1109         bool
1110 
1111 config KMAP_LOCAL
1112 	bool
1113 
1114 config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
1115 	bool
1116 
1117 # struct io_mapping based helper.  Selected by drivers that need them
1118 config IO_MAPPING
1119 	bool
1120 
1121 config SECRETMEM
1122 	default y
1123 	bool "Enable memfd_secret() system call" if EXPERT
1124 	depends on ARCH_HAS_SET_DIRECT_MAP
1125 	help
1126 	  Enable the memfd_secret() system call with the ability to create
1127 	  memory areas visible only in the context of the owning process and
1128 	  not mapped to other processes and other kernel page tables.
1129 
1130 config ANON_VMA_NAME
1131 	bool "Anonymous VMA name support"
1132 	depends on PROC_FS && ADVISE_SYSCALLS && MMU
1133 
1134 	help
1135 	  Allow naming anonymous virtual memory areas.
1136 
1137 	  This feature allows assigning names to virtual memory areas. Assigned
1138 	  names can be later retrieved from /proc/pid/maps and /proc/pid/smaps
1139 	  and help identifying individual anonymous memory areas.
1140 	  Assigning a name to anonymous virtual memory area might prevent that
1141 	  area from being merged with adjacent virtual memory areas due to the
1142 	  difference in their name.
1143 
1144 config USERFAULTFD
1145 	bool "Enable userfaultfd() system call"
1146 	depends on MMU
1147 	help
1148 	  Enable the userfaultfd() system call that allows to intercept and
1149 	  handle page faults in userland.
1150 
1151 config HAVE_ARCH_USERFAULTFD_WP
1152 	bool
1153 	help
1154 	  Arch has userfaultfd write protection support
1155 
1156 config HAVE_ARCH_USERFAULTFD_MINOR
1157 	bool
1158 	help
1159 	  Arch has userfaultfd minor fault support
1160 
1161 config PTE_MARKER_UFFD_WP
1162 	bool "Userfaultfd write protection support for shmem/hugetlbfs"
1163 	default y
1164 	depends on HAVE_ARCH_USERFAULTFD_WP
1165 
1166 	help
1167 	  Allows to create marker PTEs for userfaultfd write protection
1168 	  purposes.  It is required to enable userfaultfd write protection on
1169 	  file-backed memory types like shmem and hugetlbfs.
1170 
1171 # multi-gen LRU {
1172 config LRU_GEN
1173 	bool "Multi-Gen LRU"
1174 	depends on MMU
1175 	# make sure folio->flags has enough spare bits
1176 	depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP
1177 	help
1178 	  A high performance LRU implementation to overcommit memory. See
1179 	  Documentation/admin-guide/mm/multigen_lru.rst for details.
1180 
1181 config LRU_GEN_ENABLED
1182 	bool "Enable by default"
1183 	depends on LRU_GEN
1184 	help
1185 	  This option enables the multi-gen LRU by default.
1186 
1187 config LRU_GEN_STATS
1188 	bool "Full stats for debugging"
1189 	depends on LRU_GEN
1190 	help
1191 	  Do not enable this option unless you plan to look at historical stats
1192 	  from evicted generations for debugging purpose.
1193 
1194 	  This option has a per-memcg and per-node memory overhead.
1195 # }
1196 
1197 config ARCH_SUPPORTS_PER_VMA_LOCK
1198        def_bool n
1199 
1200 config PER_VMA_LOCK
1201 	def_bool y
1202 	depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP
1203 	help
1204 	  Allow per-vma locking during page fault handling.
1205 
1206 	  This feature allows locking each virtual memory area separately when
1207 	  handling page faults instead of taking mmap_lock.
1208 
1209 source "mm/damon/Kconfig"
1210 
1211 endmenu
1212