2 menu "Memory Management options"
4 config SELECT_MEMORY_MODEL
6 depends on ARCH_SELECT_MEMORY_MODEL
10 depends on SELECT_MEMORY_MODEL
11 default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
12 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
13 default FLATMEM_MANUAL
17 depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
19 This option allows you to change some of the ways that
20 Linux manages its memory internally. Most users will
21 only have one option here: FLATMEM. This is normal
24 Some users of more advanced features like NUMA and
25 memory hotplug may have different options here.
26 DISCONTIGMEM is a more mature, better tested system,
27 but is incompatible with memory hotplug and may suffer
28 decreased performance over SPARSEMEM. If unsure between
29 "Sparse Memory" and "Discontiguous Memory", choose
30 "Discontiguous Memory".
32 If unsure, choose this option (Flat Memory) over any other.
34 config DISCONTIGMEM_MANUAL
35 bool "Discontiguous Memory"
36 depends on ARCH_DISCONTIGMEM_ENABLE
38 This option provides enhanced support for discontiguous
39 memory systems, over FLATMEM. These systems have holes
40 in their physical address spaces, and this option provides
41 more efficient handling of these holes. However, the vast
42 majority of hardware has quite flat address spaces, and
43 can have degraded performance from the extra overhead that
46 Many NUMA configurations will have this as the only option.
48 If unsure, choose "Flat Memory" over this option.
50 config SPARSEMEM_MANUAL
52 depends on ARCH_SPARSEMEM_ENABLE
54 This will be the only option for some systems, including
55 memory hotplug systems. This is normal.
57 For many other systems, this will be an alternative to
58 "Discontiguous Memory". This option provides some potential
59 performance benefits, along with decreased code complexity,
60 but it is newer, and more experimental.
62 If unsure, choose "Discontiguous Memory" or "Flat Memory"
69 depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL
73 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
77 depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
79 config FLAT_NODE_MEM_MAP
84 # Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
85 # to represent different areas of memory. This variable allows
86 # those dependencies to exist individually.
88 config NEED_MULTIPLE_NODES
90 depends on DISCONTIGMEM || NUMA
92 config HAVE_MEMORY_PRESENT
94 depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
97 # SPARSEMEM_EXTREME (which is the default) does some bootmem
98 # allocations when memory_present() is called. If this cannot
99 # be done on your architecture, select this option. However,
100 # statically allocating the mem_section[] array can potentially
101 # consume vast quantities of .bss, so be careful.
103 # This option will also potentially produce smaller runtime code
104 # with gcc 3.4 and later.
106 config SPARSEMEM_STATIC
110 # Architecture platforms which require a two level mem_section in SPARSEMEM
111 # must select this option. This is usually for architecture platforms with
112 # an extremely sparse physical address space.
114 config SPARSEMEM_EXTREME
116 depends on SPARSEMEM && !SPARSEMEM_STATIC
118 config SPARSEMEM_VMEMMAP_ENABLE
121 config SPARSEMEM_VMEMMAP
122 bool "Sparse Memory virtual memmap"
123 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
126 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
127 pfn_to_page and page_to_pfn operations. This is the most
128 efficient option when sufficient kernel resources are available.
133 config HAVE_MEMBLOCK_NODE_MAP
136 config HAVE_MEMBLOCK_PHYS_MAP
139 config HAVE_GENERIC_GUP
142 config ARCH_DISCARD_MEMBLOCK
145 config MEMORY_ISOLATION
149 # Only be set on architectures that have completely implemented memory hotplug
150 # feature. If you are not sure, don't touch it.
152 config HAVE_BOOTMEM_INFO_NODE
155 # eventually, we can have this option just 'select SPARSEMEM'
156 config MEMORY_HOTPLUG
157 bool "Allow for memory hot-add"
158 depends on SPARSEMEM || X86_64_ACPI_NUMA
159 depends on ARCH_ENABLE_MEMORY_HOTPLUG
161 config MEMORY_HOTPLUG_SPARSE
163 depends on SPARSEMEM && MEMORY_HOTPLUG
165 config MEMORY_HOTPLUG_DEFAULT_ONLINE
166 bool "Online the newly added memory blocks by default"
168 depends on MEMORY_HOTPLUG
170 This option sets the default policy setting for memory hotplug
171 onlining policy (/sys/devices/system/memory/auto_online_blocks) which
172 determines what happens to newly added memory regions. Policy setting
173 can always be changed at runtime.
174 See Documentation/memory-hotplug.txt for more information.
176 Say Y here if you want all hot-plugged memory blocks to appear in
177 'online' state by default.
178 Say N here if you want the default policy to keep all hot-plugged
179 memory blocks in 'offline' state.
181 config MEMORY_HOTREMOVE
182 bool "Allow for memory hot remove"
183 select MEMORY_ISOLATION
184 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
185 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
188 # Heavily threaded applications may benefit from splitting the mm-wide
189 # page_table_lock, so that faults on different parts of the user address
190 # space can be handled with less contention: split it at this NR_CPUS.
191 # Default to 4 for wider testing, though 8 might be more appropriate.
192 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
193 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
194 # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
196 config SPLIT_PTLOCK_CPUS
198 default "999999" if !MMU
199 default "999999" if ARM && !CPU_CACHE_VIPT
200 default "999999" if PARISC && !PA20
203 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
207 # support for memory balloon
208 config MEMORY_BALLOON
212 # support for memory balloon compaction
213 config BALLOON_COMPACTION
214 bool "Allow for balloon memory compaction/migration"
216 depends on COMPACTION && MEMORY_BALLOON
218 Memory fragmentation introduced by ballooning might reduce
219 significantly the number of 2MB contiguous memory blocks that can be
220 used within a guest, thus imposing performance penalties associated
221 with the reduced number of transparent huge pages that could be used
222 by the guest workload. Allowing the compaction & migration for memory
223 pages enlisted as being part of memory balloon devices avoids the
224 scenario aforementioned and helps improving memory defragmentation.
227 # support for memory compaction
229 bool "Allow for memory compaction"
234 Compaction is the only memory management component to form
235 high order (larger physically contiguous) memory blocks
236 reliably. The page allocator relies on compaction heavily and
237 the lack of the feature can lead to unexpected OOM killer
238 invocations for high order memory requests. You shouldn't
239 disable this option unless there really is a strong reason for
240 it and then we would be really interested to hear about that at
244 # support for page migration
247 bool "Page migration"
249 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
251 Allows the migration of the physical location of pages of processes
252 while the virtual addresses are not changed. This is useful in
253 two situations. The first is on NUMA systems to put pages nearer
254 to the processors accessing. The second is when allocating huge
255 pages as migration can relocate pages to satisfy a huge page
256 allocation instead of reclaiming.
258 config ARCH_ENABLE_HUGEPAGE_MIGRATION
261 config ARCH_ENABLE_THP_MIGRATION
264 config PHYS_ADDR_T_64BIT
268 bool "Enable bounce buffers"
270 depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
272 Enable bounce buffers for devices that cannot access
273 the full range of memory available to the CPU. Enabled
274 by default when ZONE_DMA or HIGHMEM is selected, but you
275 may say n to override this.
285 An architecture should select this if it implements the
286 deprecated interface virt_to_bus(). All new architectures
287 should probably not select this.
295 bool "Enable KSM for page merging"
298 Enable Kernel Samepage Merging: KSM periodically scans those areas
299 of an application's address space that an app has advised may be
300 mergeable. When it finds pages of identical content, it replaces
301 the many instances by a single page with that content, so
302 saving memory until one or another app needs to modify the content.
303 Recommended for use with KVM, or with other duplicative applications.
304 See Documentation/vm/ksm.rst for more information: KSM is inactive
305 until a program has madvised that an area is MADV_MERGEABLE, and
306 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
308 config DEFAULT_MMAP_MIN_ADDR
309 int "Low address space to protect from user allocation"
313 This is the portion of low virtual memory which should be protected
314 from userspace allocation. Keeping a user from writing to low pages
315 can help reduce the impact of kernel NULL pointer bugs.
317 For most ia64, ppc64 and x86 users with lots of address space
318 a value of 65536 is reasonable and should cause no problems.
319 On arm and other archs it should not be higher than 32768.
320 Programs which use vm86 functionality or have some need to map
321 this low address space will need CAP_SYS_RAWIO or disable this
322 protection by setting the value to 0.
324 This value can be changed after boot using the
325 /proc/sys/vm/mmap_min_addr tunable.
327 config ARCH_SUPPORTS_MEMORY_FAILURE
330 config MEMORY_FAILURE
332 depends on ARCH_SUPPORTS_MEMORY_FAILURE
333 bool "Enable recovery from hardware memory errors"
334 select MEMORY_ISOLATION
337 Enables code to recover from some memory failures on systems
338 with MCA recovery. This allows a system to continue running
339 even when some of its memory has uncorrected errors. This requires
340 special hardware support and typically ECC memory.
342 config HWPOISON_INJECT
343 tristate "HWPoison pages injector"
344 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
345 select PROC_PAGE_MONITOR
347 config NOMMU_INITIAL_TRIM_EXCESS
348 int "Turn on mmap() excess space trimming before booting"
352 The NOMMU mmap() frequently needs to allocate large contiguous chunks
353 of memory on which to store mappings, but it can only ask the system
354 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
355 more than it requires. To deal with this, mmap() is able to trim off
356 the excess and return it to the allocator.
358 If trimming is enabled, the excess is trimmed off and returned to the
359 system allocator, which can cause extra fragmentation, particularly
360 if there are a lot of transient processes.
362 If trimming is disabled, the excess is kept, but not used, which for
363 long-term mappings means that the space is wasted.
365 Trimming can be dynamically controlled through a sysctl option
366 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
367 excess pages there must be before trimming should occur, or zero if
368 no trimming is to occur.
370 This option specifies the initial value of this option. The default
371 of 1 says that all excess pages should be trimmed.
373 See Documentation/nommu-mmap.txt for more information.
375 config TRANSPARENT_HUGEPAGE
376 bool "Transparent Hugepage Support"
377 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
381 Transparent Hugepages allows the kernel to use huge pages and
382 huge tlb transparently to the applications whenever possible.
383 This feature can improve computing performance to certain
384 applications by speeding up page faults during memory
385 allocation, by reducing the number of tlb misses and by speeding
386 up the pagetable walking.
388 If memory constrained on embedded, you may want to say N.
391 prompt "Transparent Hugepage Support sysfs defaults"
392 depends on TRANSPARENT_HUGEPAGE
393 default TRANSPARENT_HUGEPAGE_ALWAYS
395 Selects the sysfs defaults for Transparent Hugepage Support.
397 config TRANSPARENT_HUGEPAGE_ALWAYS
400 Enabling Transparent Hugepage always, can increase the
401 memory footprint of applications without a guaranteed
402 benefit but it will work automatically for all applications.
404 config TRANSPARENT_HUGEPAGE_MADVISE
407 Enabling Transparent Hugepage madvise, will only provide a
408 performance improvement benefit to the applications using
409 madvise(MADV_HUGEPAGE) but it won't risk to increase the
410 memory footprint of applications without a guaranteed
414 config ARCH_WANTS_THP_SWAP
419 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP
421 Swap transparent huge pages in one piece, without splitting.
422 XXX: For now, swap cluster backing transparent huge page
423 will be split after swapout.
425 For selection by architectures with reasonable THP sizes.
427 config TRANSPARENT_HUGE_PAGECACHE
429 depends on TRANSPARENT_HUGEPAGE
432 # UP and nommu archs use km based percpu allocator
434 config NEED_PER_CPU_KM
440 bool "Enable cleancache driver to cache clean pages if tmem is present"
443 Cleancache can be thought of as a page-granularity victim cache
444 for clean pages that the kernel's pageframe replacement algorithm
445 (PFRA) would like to keep around, but can't since there isn't enough
446 memory. So when the PFRA "evicts" a page, it first attempts to use
447 cleancache code to put the data contained in that page into
448 "transcendent memory", memory that is not directly accessible or
449 addressable by the kernel and is of unknown and possibly
450 time-varying size. And when a cleancache-enabled
451 filesystem wishes to access a page in a file on disk, it first
452 checks cleancache to see if it already contains it; if it does,
453 the page is copied into the kernel and a disk access is avoided.
454 When a transcendent memory driver is available (such as zcache or
455 Xen transcendent memory), a significant I/O reduction
456 may be achieved. When none is available, all cleancache calls
457 are reduced to a single pointer-compare-against-NULL resulting
458 in a negligible performance hit.
460 If unsure, say Y to enable cleancache
463 bool "Enable frontswap to cache swap pages if tmem is present"
467 Frontswap is so named because it can be thought of as the opposite
468 of a "backing" store for a swap device. The data is stored into
469 "transcendent memory", memory that is not directly accessible or
470 addressable by the kernel and is of unknown and possibly
471 time-varying size. When space in transcendent memory is available,
472 a significant swap I/O reduction may be achieved. When none is
473 available, all frontswap calls are reduced to a single pointer-
474 compare-against-NULL resulting in a negligible performance hit
475 and swap data is stored as normal on the matching swap device.
477 If unsure, say Y to enable frontswap.
480 bool "Contiguous Memory Allocator"
481 depends on HAVE_MEMBLOCK && MMU
483 select MEMORY_ISOLATION
485 This enables the Contiguous Memory Allocator which allows other
486 subsystems to allocate big physically-contiguous blocks of memory.
487 CMA reserves a region of memory and allows only movable pages to
488 be allocated from it. This way, the kernel can use the memory for
489 pagecache and when a subsystem requests for contiguous area, the
490 allocated pages are migrated away to serve the contiguous request.
495 bool "CMA debug messages (DEVELOPMENT)"
496 depends on DEBUG_KERNEL && CMA
498 Turns on debug messages in CMA. This produces KERN_DEBUG
499 messages for every CMA call as well as various messages while
500 processing calls such as dma_alloc_from_contiguous().
501 This option does not affect warning and error messages.
504 bool "CMA debugfs interface"
505 depends on CMA && DEBUG_FS
507 Turns on the DebugFS interface for CMA.
510 int "Maximum count of the CMA areas"
514 CMA allows to create CMA areas for particular purpose, mainly,
515 used as device private area. This parameter sets the maximum
516 number of CMA area in the system.
518 If unsure, leave the default value "7".
520 config MEM_SOFT_DIRTY
521 bool "Track memory changes"
522 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
523 select PROC_PAGE_MONITOR
525 This option enables memory changes tracking by introducing a
526 soft-dirty bit on pte-s. This bit it set when someone writes
527 into a page just as regular dirty bit, but unlike the latter
528 it can be cleared by hands.
530 See Documentation/admin-guide/mm/soft-dirty.rst for more details.
533 bool "Compressed cache for swap pages (EXPERIMENTAL)"
534 depends on FRONTSWAP && CRYPTO=y
539 A lightweight compressed cache for swap pages. It takes
540 pages that are in the process of being swapped out and attempts to
541 compress them into a dynamically allocated RAM-based memory pool.
542 This can result in a significant I/O reduction on swap device and,
543 in the case where decompressing from RAM is faster that swap device
544 reads, can also improve workload performance.
546 This is marked experimental because it is a new feature (as of
547 v3.11) that interacts heavily with memory reclaim. While these
548 interactions don't cause any known issues on simple memory setups,
549 they have not be fully explored on the large set of potential
550 configurations and workloads that exist.
553 tristate "Common API for compressed memory storage"
556 Compressed memory storage API. This allows using either zbud or
560 tristate "Low (Up to 2x) density storage for compressed pages"
563 A special purpose allocator for storing compressed pages.
564 It is designed to store up to two compressed pages per physical
565 page. While this design limits storage density, it has simple and
566 deterministic reclaim properties that make it preferable to a higher
567 density approach when reclaim will be used.
570 tristate "Up to 3x density storage for compressed pages"
574 A special purpose allocator for storing compressed pages.
575 It is designed to store up to three compressed pages per physical
576 page. It is a ZBUD derivative so the simplicity and determinism are
580 tristate "Memory allocator for compressed pages"
584 zsmalloc is a slab-based memory allocator designed to store
585 compressed RAM pages. zsmalloc uses virtual memory mapping
586 in order to reduce fragmentation. However, this results in a
587 non-standard allocator interface where a handle, not a pointer, is
588 returned by an alloc(). This handle must be mapped in order to
589 access the allocated space.
591 config PGTABLE_MAPPING
592 bool "Use page table mapping to access object in zsmalloc"
595 By default, zsmalloc uses a copy-based object mapping method to
596 access allocations that span two pages. However, if a particular
597 architecture (ex, ARM) performs VM mapping faster than copying,
598 then you should select this. This causes zsmalloc to use page table
599 mapping rather than copying for object mapping.
601 You can check speed with zsmalloc benchmark:
602 https://github.com/spartacus06/zsmapbench
605 bool "Export zsmalloc statistics"
609 This option enables code in the zsmalloc to collect various
610 statistics about whats happening in zsmalloc and exports that
611 information to userspace via debugfs.
614 config GENERIC_EARLY_IOREMAP
617 config MAX_STACK_SIZE_MB
618 int "Maximum user stack size for 32-bit processes (MB)"
621 depends on STACK_GROWSUP && (!64BIT || COMPAT)
623 This is the maximum stack size in Megabytes in the VM layout of 32-bit
624 user processes when the stack grows upwards (currently only on parisc
625 arch). The stack will be located at the highest memory address minus
626 the given value, unless the RLIMIT_STACK hard limit is changed to a
627 smaller value in which case that is used.
629 A sane initial value is 80 MB.
631 config DEFERRED_STRUCT_PAGE_INIT
632 bool "Defer initialisation of struct pages to kthreads"
635 depends on !NEED_PER_CPU_KM
638 Ordinarily all struct pages are initialised during early boot in a
639 single thread. On very large machines this can take a considerable
640 amount of time. If this option is set, large machines will bring up
641 a subset of memmap at boot and then initialise the rest in parallel
642 by starting one-off "pgdatinitX" kernel thread for each node X. This
643 has a potential performance impact on processes running early in the
644 lifetime of the system until these kthreads finish the
647 config IDLE_PAGE_TRACKING
648 bool "Enable idle page tracking"
649 depends on SYSFS && MMU
650 select PAGE_EXTENSION if !64BIT
652 This feature allows to estimate the amount of user pages that have
653 not been touched during a given period of time. This information can
654 be useful to tune memory cgroup limits and/or for job placement
655 within a compute cluster.
657 See Documentation/admin-guide/mm/idle_page_tracking.rst for
660 # arch_add_memory() comprehends device memory
661 config ARCH_HAS_ZONE_DEVICE
665 bool "Device memory (pmem, HMM, etc...) hotplug support"
666 depends on MEMORY_HOTPLUG
667 depends on MEMORY_HOTREMOVE
668 depends on SPARSEMEM_VMEMMAP
669 depends on ARCH_HAS_ZONE_DEVICE
673 Device memory hotplug support allows for establishing pmem,
674 or other device driver discovered memory regions, in the
675 memmap. This allows pfn_to_page() lookups of otherwise
676 "device-physical" addresses which is needed for using a DAX
677 mapping in an O_DIRECT operation, among other things.
679 If FS_DAX is enabled, then say Y.
684 depends on (X86_64 || PPC64)
685 depends on ZONE_DEVICE
686 depends on MMU && 64BIT
687 depends on MEMORY_HOTPLUG
688 depends on MEMORY_HOTREMOVE
689 depends on SPARSEMEM_VMEMMAP
691 config MIGRATE_VMA_HELPER
694 config DEV_PAGEMAP_OPS
699 select MIGRATE_VMA_HELPER
702 bool "HMM mirror CPU page table into a device page table"
703 depends on ARCH_HAS_HMM
707 Select HMM_MIRROR if you want to mirror range of the CPU page table of a
708 process into a device page table. Here, mirror means "keep synchronized".
709 Prerequisites: the device must provide the ability to write-protect its
710 page tables (at PAGE_SIZE granularity), and must be able to recover from
711 the resulting potential page faults.
713 config DEVICE_PRIVATE
714 bool "Unaddressable device memory (GPU memory, ...)"
715 depends on ARCH_HAS_HMM
717 select DEV_PAGEMAP_OPS
720 Allows creation of struct pages to represent unaddressable device
721 memory; i.e., memory that is only accessible from the device (or
722 group of devices). You likely also want to select HMM_MIRROR.
725 bool "Addressable device memory (like GPU memory)"
726 depends on ARCH_HAS_HMM
728 select DEV_PAGEMAP_OPS
731 Allows creation of struct pages to represent addressable device
732 memory; i.e., memory that is accessible from both the device and
738 config ARCH_USES_HIGH_VMA_FLAGS
740 config ARCH_HAS_PKEYS
744 bool "Collect percpu memory statistics"
747 This feature collects and exposes statistics via debugfs. The
748 information includes global and per chunk statistics, which can
749 be used to help understand percpu memory usage.
752 bool "Enable infrastructure for get_user_pages_fast() benchmarking"
755 Provides /sys/kernel/debug/gup_benchmark that helps with testing
756 performance of get_user_pages_fast().
758 See tools/testing/selftests/vm/gup_benchmark.c
760 config ARCH_HAS_PTE_SPECIAL