1 config SELECT_MEMORY_MODEL
3 depends on ARCH_SELECT_MEMORY_MODEL
7 depends on SELECT_MEMORY_MODEL
8 default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
9 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
10 default FLATMEM_MANUAL
14 depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
16 This option allows you to change some of the ways that
17 Linux manages its memory internally. Most users will
18 only have one option here: FLATMEM. This is normal
21 Some users of more advanced features like NUMA and
22 memory hotplug may have different options here.
23 DISCONTIGMEM is a more mature, better tested system,
24 but is incompatible with memory hotplug and may suffer
25 decreased performance over SPARSEMEM. If unsure between
26 "Sparse Memory" and "Discontiguous Memory", choose
27 "Discontiguous Memory".
29 If unsure, choose this option (Flat Memory) over any other.
31 config DISCONTIGMEM_MANUAL
32 bool "Discontiguous Memory"
33 depends on ARCH_DISCONTIGMEM_ENABLE
35 This option provides enhanced support for discontiguous
36 memory systems, over FLATMEM. These systems have holes
37 in their physical address spaces, and this option provides
38 more efficient handling of these holes. However, the vast
39 majority of hardware has quite flat address spaces, and
40 can have degraded performance from the extra overhead that
43 Many NUMA configurations will have this as the only option.
45 If unsure, choose "Flat Memory" over this option.
47 config SPARSEMEM_MANUAL
49 depends on ARCH_SPARSEMEM_ENABLE
51 This will be the only option for some systems, including
52 memory hotplug systems. This is normal.
54 For many other systems, this will be an alternative to
55 "Discontiguous Memory". This option provides some potential
56 performance benefits, along with decreased code complexity,
57 but it is newer, and more experimental.
59 If unsure, choose "Discontiguous Memory" or "Flat Memory"
66 depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL
70 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
74 depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL
76 config FLAT_NODE_MEM_MAP
81 # Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
82 # to represent different areas of memory. This variable allows
83 # those dependencies to exist individually.
85 config NEED_MULTIPLE_NODES
87 depends on DISCONTIGMEM || NUMA
89 config HAVE_MEMORY_PRESENT
91 depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
94 # SPARSEMEM_EXTREME (which is the default) does some bootmem
95 # allocations when memory_present() is called. If this cannot
96 # be done on your architecture, select this option. However,
97 # statically allocating the mem_section[] array can potentially
98 # consume vast quantities of .bss, so be careful.
100 # This option will also potentially produce smaller runtime code
101 # with gcc 3.4 and later.
103 config SPARSEMEM_STATIC
107 # Architecture platforms which require a two level mem_section in SPARSEMEM
108 # must select this option. This is usually for architecture platforms with
109 # an extremely sparse physical address space.
111 config SPARSEMEM_EXTREME
113 depends on SPARSEMEM && !SPARSEMEM_STATIC
115 config SPARSEMEM_VMEMMAP_ENABLE
118 config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
120 depends on SPARSEMEM && X86_64
122 config SPARSEMEM_VMEMMAP
123 bool "Sparse Memory virtual memmap"
124 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
127 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
128 pfn_to_page and page_to_pfn operations. This is the most
129 efficient option when sufficient kernel resources are available.
134 config HAVE_MEMBLOCK_NODE_MAP
137 config HAVE_MEMBLOCK_PHYS_MAP
140 config HAVE_GENERIC_GUP
143 config ARCH_DISCARD_MEMBLOCK
149 config MEMORY_ISOLATION
153 # Only be set on architectures that have completely implemented memory hotplug
154 # feature. If you are not sure, don't touch it.
156 config HAVE_BOOTMEM_INFO_NODE
159 # eventually, we can have this option just 'select SPARSEMEM'
160 config MEMORY_HOTPLUG
161 bool "Allow for memory hot-add"
162 depends on SPARSEMEM || X86_64_ACPI_NUMA
163 depends on ARCH_ENABLE_MEMORY_HOTPLUG
165 config MEMORY_HOTPLUG_SPARSE
167 depends on SPARSEMEM && MEMORY_HOTPLUG
169 config MEMORY_HOTPLUG_DEFAULT_ONLINE
170 bool "Online the newly added memory blocks by default"
172 depends on MEMORY_HOTPLUG
174 This option sets the default policy setting for memory hotplug
175 onlining policy (/sys/devices/system/memory/auto_online_blocks) which
176 determines what happens to newly added memory regions. Policy setting
177 can always be changed at runtime.
178 See Documentation/memory-hotplug.txt for more information.
180 Say Y here if you want all hot-plugged memory blocks to appear in
181 'online' state by default.
182 Say N here if you want the default policy to keep all hot-plugged
183 memory blocks in 'offline' state.
185 config MEMORY_HOTREMOVE
186 bool "Allow for memory hot remove"
187 select MEMORY_ISOLATION
188 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
189 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
192 # Heavily threaded applications may benefit from splitting the mm-wide
193 # page_table_lock, so that faults on different parts of the user address
194 # space can be handled with less contention: split it at this NR_CPUS.
195 # Default to 4 for wider testing, though 8 might be more appropriate.
196 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
197 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
198 # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
200 config SPLIT_PTLOCK_CPUS
202 default "999999" if !MMU
203 default "999999" if ARM && !CPU_CACHE_VIPT
204 default "999999" if PARISC && !PA20
207 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
211 # support for memory balloon
212 config MEMORY_BALLOON
216 # support for memory balloon compaction
217 config BALLOON_COMPACTION
218 bool "Allow for balloon memory compaction/migration"
220 depends on COMPACTION && MEMORY_BALLOON
222 Memory fragmentation introduced by ballooning might reduce
223 significantly the number of 2MB contiguous memory blocks that can be
224 used within a guest, thus imposing performance penalties associated
225 with the reduced number of transparent huge pages that could be used
226 by the guest workload. Allowing the compaction & migration for memory
227 pages enlisted as being part of memory balloon devices avoids the
228 scenario aforementioned and helps improving memory defragmentation.
231 # support for memory compaction
233 bool "Allow for memory compaction"
238 Compaction is the only memory management component to form
239 high order (larger physically contiguous) memory blocks
240 reliably. The page allocator relies on compaction heavily and
241 the lack of the feature can lead to unexpected OOM killer
242 invocations for high order memory requests. You shouldn't
243 disable this option unless there really is a strong reason for
244 it and then we would be really interested to hear about that at
248 # support for page migration
251 bool "Page migration"
253 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
255 Allows the migration of the physical location of pages of processes
256 while the virtual addresses are not changed. This is useful in
257 two situations. The first is on NUMA systems to put pages nearer
258 to the processors accessing. The second is when allocating huge
259 pages as migration can relocate pages to satisfy a huge page
260 allocation instead of reclaiming.
262 config ARCH_ENABLE_HUGEPAGE_MIGRATION
265 config PHYS_ADDR_T_64BIT
266 def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
269 bool "Enable bounce buffers"
271 depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
273 Enable bounce buffers for devices that cannot access
274 the full range of memory available to the CPU. Enabled
275 by default when ZONE_DMA or HIGHMEM is selected, but you
276 may say n to override this.
278 # On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
279 # have more than 4GB of memory, but we don't currently use the IOTLB to present
280 # a 32-bit address to OHCI. So we need to use a bounce pool instead.
281 config NEED_BOUNCE_POOL
283 default y if TILE && USB_OHCI_HCD
293 An architecture should select this if it implements the
294 deprecated interface virt_to_bus(). All new architectures
295 should probably not select this.
303 bool "Enable KSM for page merging"
306 Enable Kernel Samepage Merging: KSM periodically scans those areas
307 of an application's address space that an app has advised may be
308 mergeable. When it finds pages of identical content, it replaces
309 the many instances by a single page with that content, so
310 saving memory until one or another app needs to modify the content.
311 Recommended for use with KVM, or with other duplicative applications.
312 See Documentation/vm/ksm.txt for more information: KSM is inactive
313 until a program has madvised that an area is MADV_MERGEABLE, and
314 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
316 config DEFAULT_MMAP_MIN_ADDR
317 int "Low address space to protect from user allocation"
321 This is the portion of low virtual memory which should be protected
322 from userspace allocation. Keeping a user from writing to low pages
323 can help reduce the impact of kernel NULL pointer bugs.
325 For most ia64, ppc64 and x86 users with lots of address space
326 a value of 65536 is reasonable and should cause no problems.
327 On arm and other archs it should not be higher than 32768.
328 Programs which use vm86 functionality or have some need to map
329 this low address space will need CAP_SYS_RAWIO or disable this
330 protection by setting the value to 0.
332 This value can be changed after boot using the
333 /proc/sys/vm/mmap_min_addr tunable.
335 config ARCH_SUPPORTS_MEMORY_FAILURE
338 config MEMORY_FAILURE
340 depends on ARCH_SUPPORTS_MEMORY_FAILURE
341 bool "Enable recovery from hardware memory errors"
342 select MEMORY_ISOLATION
345 Enables code to recover from some memory failures on systems
346 with MCA recovery. This allows a system to continue running
347 even when some of its memory has uncorrected errors. This requires
348 special hardware support and typically ECC memory.
350 config HWPOISON_INJECT
351 tristate "HWPoison pages injector"
352 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
353 select PROC_PAGE_MONITOR
355 config NOMMU_INITIAL_TRIM_EXCESS
356 int "Turn on mmap() excess space trimming before booting"
360 The NOMMU mmap() frequently needs to allocate large contiguous chunks
361 of memory on which to store mappings, but it can only ask the system
362 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
363 more than it requires. To deal with this, mmap() is able to trim off
364 the excess and return it to the allocator.
366 If trimming is enabled, the excess is trimmed off and returned to the
367 system allocator, which can cause extra fragmentation, particularly
368 if there are a lot of transient processes.
370 If trimming is disabled, the excess is kept, but not used, which for
371 long-term mappings means that the space is wasted.
373 Trimming can be dynamically controlled through a sysctl option
374 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
375 excess pages there must be before trimming should occur, or zero if
376 no trimming is to occur.
378 This option specifies the initial value of this option. The default
379 of 1 says that all excess pages should be trimmed.
381 See Documentation/nommu-mmap.txt for more information.
383 config TRANSPARENT_HUGEPAGE
384 bool "Transparent Hugepage Support"
385 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
387 select RADIX_TREE_MULTIORDER
389 Transparent Hugepages allows the kernel to use huge pages and
390 huge tlb transparently to the applications whenever possible.
391 This feature can improve computing performance to certain
392 applications by speeding up page faults during memory
393 allocation, by reducing the number of tlb misses and by speeding
394 up the pagetable walking.
396 If memory constrained on embedded, you may want to say N.
399 prompt "Transparent Hugepage Support sysfs defaults"
400 depends on TRANSPARENT_HUGEPAGE
401 default TRANSPARENT_HUGEPAGE_ALWAYS
403 Selects the sysfs defaults for Transparent Hugepage Support.
405 config TRANSPARENT_HUGEPAGE_ALWAYS
408 Enabling Transparent Hugepage always, can increase the
409 memory footprint of applications without a guaranteed
410 benefit but it will work automatically for all applications.
412 config TRANSPARENT_HUGEPAGE_MADVISE
415 Enabling Transparent Hugepage madvise, will only provide a
416 performance improvement benefit to the applications using
417 madvise(MADV_HUGEPAGE) but it won't risk to increase the
418 memory footprint of applications without a guaranteed
422 config ARCH_WANTS_THP_SWAP
427 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP
429 Swap transparent huge pages in one piece, without splitting.
430 XXX: For now this only does clustered swap space allocation.
432 For selection by architectures with reasonable THP sizes.
434 config TRANSPARENT_HUGE_PAGECACHE
436 depends on TRANSPARENT_HUGEPAGE
439 # UP and nommu archs use km based percpu allocator
441 config NEED_PER_CPU_KM
447 bool "Enable cleancache driver to cache clean pages if tmem is present"
450 Cleancache can be thought of as a page-granularity victim cache
451 for clean pages that the kernel's pageframe replacement algorithm
452 (PFRA) would like to keep around, but can't since there isn't enough
453 memory. So when the PFRA "evicts" a page, it first attempts to use
454 cleancache code to put the data contained in that page into
455 "transcendent memory", memory that is not directly accessible or
456 addressable by the kernel and is of unknown and possibly
457 time-varying size. And when a cleancache-enabled
458 filesystem wishes to access a page in a file on disk, it first
459 checks cleancache to see if it already contains it; if it does,
460 the page is copied into the kernel and a disk access is avoided.
461 When a transcendent memory driver is available (such as zcache or
462 Xen transcendent memory), a significant I/O reduction
463 may be achieved. When none is available, all cleancache calls
464 are reduced to a single pointer-compare-against-NULL resulting
465 in a negligible performance hit.
467 If unsure, say Y to enable cleancache
470 bool "Enable frontswap to cache swap pages if tmem is present"
474 Frontswap is so named because it can be thought of as the opposite
475 of a "backing" store for a swap device. The data is stored into
476 "transcendent memory", memory that is not directly accessible or
477 addressable by the kernel and is of unknown and possibly
478 time-varying size. When space in transcendent memory is available,
479 a significant swap I/O reduction may be achieved. When none is
480 available, all frontswap calls are reduced to a single pointer-
481 compare-against-NULL resulting in a negligible performance hit
482 and swap data is stored as normal on the matching swap device.
484 If unsure, say Y to enable frontswap.
487 bool "Contiguous Memory Allocator"
488 depends on HAVE_MEMBLOCK && MMU
490 select MEMORY_ISOLATION
492 This enables the Contiguous Memory Allocator which allows other
493 subsystems to allocate big physically-contiguous blocks of memory.
494 CMA reserves a region of memory and allows only movable pages to
495 be allocated from it. This way, the kernel can use the memory for
496 pagecache and when a subsystem requests for contiguous area, the
497 allocated pages are migrated away to serve the contiguous request.
502 bool "CMA debug messages (DEVELOPMENT)"
503 depends on DEBUG_KERNEL && CMA
505 Turns on debug messages in CMA. This produces KERN_DEBUG
506 messages for every CMA call as well as various messages while
507 processing calls such as dma_alloc_from_contiguous().
508 This option does not affect warning and error messages.
511 bool "CMA debugfs interface"
512 depends on CMA && DEBUG_FS
514 Turns on the DebugFS interface for CMA.
517 int "Maximum count of the CMA areas"
521 CMA allows to create CMA areas for particular purpose, mainly,
522 used as device private area. This parameter sets the maximum
523 number of CMA area in the system.
525 If unsure, leave the default value "7".
527 config MEM_SOFT_DIRTY
528 bool "Track memory changes"
529 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
530 select PROC_PAGE_MONITOR
532 This option enables memory changes tracking by introducing a
533 soft-dirty bit on pte-s. This bit it set when someone writes
534 into a page just as regular dirty bit, but unlike the latter
535 it can be cleared by hands.
537 See Documentation/vm/soft-dirty.txt for more details.
540 bool "Compressed cache for swap pages (EXPERIMENTAL)"
541 depends on FRONTSWAP && CRYPTO=y
546 A lightweight compressed cache for swap pages. It takes
547 pages that are in the process of being swapped out and attempts to
548 compress them into a dynamically allocated RAM-based memory pool.
549 This can result in a significant I/O reduction on swap device and,
550 in the case where decompressing from RAM is faster that swap device
551 reads, can also improve workload performance.
553 This is marked experimental because it is a new feature (as of
554 v3.11) that interacts heavily with memory reclaim. While these
555 interactions don't cause any known issues on simple memory setups,
556 they have not be fully explored on the large set of potential
557 configurations and workloads that exist.
560 tristate "Common API for compressed memory storage"
563 Compressed memory storage API. This allows using either zbud or
567 tristate "Low (Up to 2x) density storage for compressed pages"
570 A special purpose allocator for storing compressed pages.
571 It is designed to store up to two compressed pages per physical
572 page. While this design limits storage density, it has simple and
573 deterministic reclaim properties that make it preferable to a higher
574 density approach when reclaim will be used.
577 tristate "Up to 3x density storage for compressed pages"
581 A special purpose allocator for storing compressed pages.
582 It is designed to store up to three compressed pages per physical
583 page. It is a ZBUD derivative so the simplicity and determinism are
587 tristate "Memory allocator for compressed pages"
591 zsmalloc is a slab-based memory allocator designed to store
592 compressed RAM pages. zsmalloc uses virtual memory mapping
593 in order to reduce fragmentation. However, this results in a
594 non-standard allocator interface where a handle, not a pointer, is
595 returned by an alloc(). This handle must be mapped in order to
596 access the allocated space.
598 config PGTABLE_MAPPING
599 bool "Use page table mapping to access object in zsmalloc"
602 By default, zsmalloc uses a copy-based object mapping method to
603 access allocations that span two pages. However, if a particular
604 architecture (ex, ARM) performs VM mapping faster than copying,
605 then you should select this. This causes zsmalloc to use page table
606 mapping rather than copying for object mapping.
608 You can check speed with zsmalloc benchmark:
609 https://github.com/spartacus06/zsmapbench
612 bool "Export zsmalloc statistics"
616 This option enables code in the zsmalloc to collect various
617 statistics about whats happening in zsmalloc and exports that
618 information to userspace via debugfs.
621 config GENERIC_EARLY_IOREMAP
624 config MAX_STACK_SIZE_MB
625 int "Maximum user stack size for 32-bit processes (MB)"
629 depends on STACK_GROWSUP && (!64BIT || COMPAT)
631 This is the maximum stack size in Megabytes in the VM layout of 32-bit
632 user processes when the stack grows upwards (currently only on parisc
633 and metag arch). The stack will be located at the highest memory
634 address minus the given value, unless the RLIMIT_STACK hard limit is
635 changed to a smaller value in which case that is used.
637 A sane initial value is 80 MB.
639 # For architectures that support deferred memory initialisation
640 config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
643 config DEFERRED_STRUCT_PAGE_INIT
644 bool "Defer initialisation of struct pages to kthreads"
646 depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
647 depends on NO_BOOTMEM && MEMORY_HOTPLUG
650 Ordinarily all struct pages are initialised during early boot in a
651 single thread. On very large machines this can take a considerable
652 amount of time. If this option is set, large machines will bring up
653 a subset of memmap at boot and then initialise the rest in parallel
654 by starting one-off "pgdatinitX" kernel thread for each node X. This
655 has a potential performance impact on processes running early in the
656 lifetime of the system until these kthreads finish the
659 config IDLE_PAGE_TRACKING
660 bool "Enable idle page tracking"
661 depends on SYSFS && MMU
662 select PAGE_EXTENSION if !64BIT
664 This feature allows to estimate the amount of user pages that have
665 not been touched during a given period of time. This information can
666 be useful to tune memory cgroup limits and/or for job placement
667 within a compute cluster.
669 See Documentation/vm/idle_page_tracking.txt for more details.
671 # arch_add_memory() comprehends device memory
672 config ARCH_HAS_ZONE_DEVICE
676 bool "Device memory (pmem, etc...) hotplug support"
677 depends on MEMORY_HOTPLUG
678 depends on MEMORY_HOTREMOVE
679 depends on SPARSEMEM_VMEMMAP
680 depends on ARCH_HAS_ZONE_DEVICE
683 Device memory hotplug support allows for establishing pmem,
684 or other device driver discovered memory regions, in the
685 memmap. This allows pfn_to_page() lookups of otherwise
686 "device-physical" addresses which is needed for using a DAX
687 mapping in an O_DIRECT operation, among other things.
689 If FS_DAX is enabled, then say Y.
694 config ARCH_USES_HIGH_VMA_FLAGS
696 config ARCH_HAS_PKEYS
700 bool "Collect percpu memory statistics"
703 This feature collects and exposes statistics via debugfs. The
704 information includes global and per chunk statistics, which can
705 be used to help understand percpu memory usage.