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_RCU_GUP
143 config ARCH_DISCARD_MEMBLOCK
149 config MEMORY_ISOLATION
153 bool "Enable to assign a node which has only movable memory"
154 depends on HAVE_MEMBLOCK
155 depends on NO_BOOTMEM
160 Allow a node to have only movable memory. Pages used by the kernel,
161 such as direct mapping pages cannot be migrated. So the corresponding
162 memory device cannot be hotplugged. This option allows the following
164 - When the system is booting, node full of hotpluggable memory can
165 be arranged to have only movable memory so that the whole node can
166 be hot-removed. (need movable_node boot option specified).
167 - After the system is up, the option allows users to online all the
168 memory of a node as movable memory so that the whole node can be
171 Users who don't use the memory hotplug feature are fine with this
172 option on since they don't specify movable_node boot option or they
173 don't online memory as movable.
175 Say Y here if you want to hotplug a whole node.
176 Say N here if you want kernel to use memory on all nodes evenly.
179 # Only be set on architectures that have completely implemented memory hotplug
180 # feature. If you are not sure, don't touch it.
182 config HAVE_BOOTMEM_INFO_NODE
185 # eventually, we can have this option just 'select SPARSEMEM'
186 config MEMORY_HOTPLUG
187 bool "Allow for memory hot-add"
188 depends on SPARSEMEM || X86_64_ACPI_NUMA
189 depends on ARCH_ENABLE_MEMORY_HOTPLUG
190 depends on COMPILE_TEST || !KASAN
192 config MEMORY_HOTPLUG_SPARSE
194 depends on SPARSEMEM && MEMORY_HOTPLUG
196 config MEMORY_HOTPLUG_DEFAULT_ONLINE
197 bool "Online the newly added memory blocks by default"
199 depends on MEMORY_HOTPLUG
201 This option sets the default policy setting for memory hotplug
202 onlining policy (/sys/devices/system/memory/auto_online_blocks) which
203 determines what happens to newly added memory regions. Policy setting
204 can always be changed at runtime.
205 See Documentation/memory-hotplug.txt for more information.
207 Say Y here if you want all hot-plugged memory blocks to appear in
208 'online' state by default.
209 Say N here if you want the default policy to keep all hot-plugged
210 memory blocks in 'offline' state.
212 config MEMORY_HOTREMOVE
213 bool "Allow for memory hot remove"
214 select MEMORY_ISOLATION
215 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
216 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
219 # Heavily threaded applications may benefit from splitting the mm-wide
220 # page_table_lock, so that faults on different parts of the user address
221 # space can be handled with less contention: split it at this NR_CPUS.
222 # Default to 4 for wider testing, though 8 might be more appropriate.
223 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
224 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
225 # DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
227 config SPLIT_PTLOCK_CPUS
229 default "999999" if !MMU
230 default "999999" if ARM && !CPU_CACHE_VIPT
231 default "999999" if PARISC && !PA20
234 config ARCH_ENABLE_SPLIT_PMD_PTLOCK
238 # support for memory balloon
239 config MEMORY_BALLOON
243 # support for memory balloon compaction
244 config BALLOON_COMPACTION
245 bool "Allow for balloon memory compaction/migration"
247 depends on COMPACTION && MEMORY_BALLOON
249 Memory fragmentation introduced by ballooning might reduce
250 significantly the number of 2MB contiguous memory blocks that can be
251 used within a guest, thus imposing performance penalties associated
252 with the reduced number of transparent huge pages that could be used
253 by the guest workload. Allowing the compaction & migration for memory
254 pages enlisted as being part of memory balloon devices avoids the
255 scenario aforementioned and helps improving memory defragmentation.
258 # support for memory compaction
260 bool "Allow for memory compaction"
265 Compaction is the only memory management component to form
266 high order (larger physically contiguous) memory blocks
267 reliably. The page allocator relies on compaction heavily and
268 the lack of the feature can lead to unexpected OOM killer
269 invocations for high order memory requests. You shouldn't
270 disable this option unless there really is a strong reason for
271 it and then we would be really interested to hear about that at
275 # support for page migration
278 bool "Page migration"
280 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
282 Allows the migration of the physical location of pages of processes
283 while the virtual addresses are not changed. This is useful in
284 two situations. The first is on NUMA systems to put pages nearer
285 to the processors accessing. The second is when allocating huge
286 pages as migration can relocate pages to satisfy a huge page
287 allocation instead of reclaiming.
289 config ARCH_ENABLE_HUGEPAGE_MIGRATION
292 config PHYS_ADDR_T_64BIT
293 def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
296 bool "Enable bounce buffers"
298 depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
300 Enable bounce buffers for devices that cannot access
301 the full range of memory available to the CPU. Enabled
302 by default when ZONE_DMA or HIGHMEM is selected, but you
303 may say n to override this.
305 # On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
306 # have more than 4GB of memory, but we don't currently use the IOTLB to present
307 # a 32-bit address to OHCI. So we need to use a bounce pool instead.
308 config NEED_BOUNCE_POOL
310 default y if TILE && USB_OHCI_HCD
321 An architecture should select this if it implements the
322 deprecated interface virt_to_bus(). All new architectures
323 should probably not select this.
331 bool "Enable KSM for page merging"
334 Enable Kernel Samepage Merging: KSM periodically scans those areas
335 of an application's address space that an app has advised may be
336 mergeable. When it finds pages of identical content, it replaces
337 the many instances by a single page with that content, so
338 saving memory until one or another app needs to modify the content.
339 Recommended for use with KVM, or with other duplicative applications.
340 See Documentation/vm/ksm.txt for more information: KSM is inactive
341 until a program has madvised that an area is MADV_MERGEABLE, and
342 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).
344 config DEFAULT_MMAP_MIN_ADDR
345 int "Low address space to protect from user allocation"
349 This is the portion of low virtual memory which should be protected
350 from userspace allocation. Keeping a user from writing to low pages
351 can help reduce the impact of kernel NULL pointer bugs.
353 For most ia64, ppc64 and x86 users with lots of address space
354 a value of 65536 is reasonable and should cause no problems.
355 On arm and other archs it should not be higher than 32768.
356 Programs which use vm86 functionality or have some need to map
357 this low address space will need CAP_SYS_RAWIO or disable this
358 protection by setting the value to 0.
360 This value can be changed after boot using the
361 /proc/sys/vm/mmap_min_addr tunable.
363 config ARCH_SUPPORTS_MEMORY_FAILURE
366 config MEMORY_FAILURE
368 depends on ARCH_SUPPORTS_MEMORY_FAILURE
369 bool "Enable recovery from hardware memory errors"
370 select MEMORY_ISOLATION
373 Enables code to recover from some memory failures on systems
374 with MCA recovery. This allows a system to continue running
375 even when some of its memory has uncorrected errors. This requires
376 special hardware support and typically ECC memory.
378 config HWPOISON_INJECT
379 tristate "HWPoison pages injector"
380 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
381 select PROC_PAGE_MONITOR
383 config NOMMU_INITIAL_TRIM_EXCESS
384 int "Turn on mmap() excess space trimming before booting"
388 The NOMMU mmap() frequently needs to allocate large contiguous chunks
389 of memory on which to store mappings, but it can only ask the system
390 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
391 more than it requires. To deal with this, mmap() is able to trim off
392 the excess and return it to the allocator.
394 If trimming is enabled, the excess is trimmed off and returned to the
395 system allocator, which can cause extra fragmentation, particularly
396 if there are a lot of transient processes.
398 If trimming is disabled, the excess is kept, but not used, which for
399 long-term mappings means that the space is wasted.
401 Trimming can be dynamically controlled through a sysctl option
402 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
403 excess pages there must be before trimming should occur, or zero if
404 no trimming is to occur.
406 This option specifies the initial value of this option. The default
407 of 1 says that all excess pages should be trimmed.
409 See Documentation/nommu-mmap.txt for more information.
411 config TRANSPARENT_HUGEPAGE
412 bool "Transparent Hugepage Support"
413 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
415 select RADIX_TREE_MULTIORDER
417 Transparent Hugepages allows the kernel to use huge pages and
418 huge tlb transparently to the applications whenever possible.
419 This feature can improve computing performance to certain
420 applications by speeding up page faults during memory
421 allocation, by reducing the number of tlb misses and by speeding
422 up the pagetable walking.
424 If memory constrained on embedded, you may want to say N.
427 prompt "Transparent Hugepage Support sysfs defaults"
428 depends on TRANSPARENT_HUGEPAGE
429 default TRANSPARENT_HUGEPAGE_ALWAYS
431 Selects the sysfs defaults for Transparent Hugepage Support.
433 config TRANSPARENT_HUGEPAGE_ALWAYS
436 Enabling Transparent Hugepage always, can increase the
437 memory footprint of applications without a guaranteed
438 benefit but it will work automatically for all applications.
440 config TRANSPARENT_HUGEPAGE_MADVISE
443 Enabling Transparent Hugepage madvise, will only provide a
444 performance improvement benefit to the applications using
445 madvise(MADV_HUGEPAGE) but it won't risk to increase the
446 memory footprint of applications without a guaranteed
451 # We don't deposit page tables on file THP mapping,
452 # but Power makes use of them to address MMU quirk.
454 config TRANSPARENT_HUGE_PAGECACHE
456 depends on TRANSPARENT_HUGEPAGE && !PPC
459 # UP and nommu archs use km based percpu allocator
461 config NEED_PER_CPU_KM
467 bool "Enable cleancache driver to cache clean pages if tmem is present"
470 Cleancache can be thought of as a page-granularity victim cache
471 for clean pages that the kernel's pageframe replacement algorithm
472 (PFRA) would like to keep around, but can't since there isn't enough
473 memory. So when the PFRA "evicts" a page, it first attempts to use
474 cleancache code to put the data contained in that page into
475 "transcendent memory", memory that is not directly accessible or
476 addressable by the kernel and is of unknown and possibly
477 time-varying size. And when a cleancache-enabled
478 filesystem wishes to access a page in a file on disk, it first
479 checks cleancache to see if it already contains it; if it does,
480 the page is copied into the kernel and a disk access is avoided.
481 When a transcendent memory driver is available (such as zcache or
482 Xen transcendent memory), a significant I/O reduction
483 may be achieved. When none is available, all cleancache calls
484 are reduced to a single pointer-compare-against-NULL resulting
485 in a negligible performance hit.
487 If unsure, say Y to enable cleancache
490 bool "Enable frontswap to cache swap pages if tmem is present"
494 Frontswap is so named because it can be thought of as the opposite
495 of a "backing" store for a swap device. The data is stored into
496 "transcendent memory", memory that is not directly accessible or
497 addressable by the kernel and is of unknown and possibly
498 time-varying size. When space in transcendent memory is available,
499 a significant swap I/O reduction may be achieved. When none is
500 available, all frontswap calls are reduced to a single pointer-
501 compare-against-NULL resulting in a negligible performance hit
502 and swap data is stored as normal on the matching swap device.
504 If unsure, say Y to enable frontswap.
507 bool "Contiguous Memory Allocator"
508 depends on HAVE_MEMBLOCK && MMU
510 select MEMORY_ISOLATION
512 This enables the Contiguous Memory Allocator which allows other
513 subsystems to allocate big physically-contiguous blocks of memory.
514 CMA reserves a region of memory and allows only movable pages to
515 be allocated from it. This way, the kernel can use the memory for
516 pagecache and when a subsystem requests for contiguous area, the
517 allocated pages are migrated away to serve the contiguous request.
522 bool "CMA debug messages (DEVELOPMENT)"
523 depends on DEBUG_KERNEL && CMA
525 Turns on debug messages in CMA. This produces KERN_DEBUG
526 messages for every CMA call as well as various messages while
527 processing calls such as dma_alloc_from_contiguous().
528 This option does not affect warning and error messages.
531 bool "CMA debugfs interface"
532 depends on CMA && DEBUG_FS
534 Turns on the DebugFS interface for CMA.
537 int "Maximum count of the CMA areas"
541 CMA allows to create CMA areas for particular purpose, mainly,
542 used as device private area. This parameter sets the maximum
543 number of CMA area in the system.
545 If unsure, leave the default value "7".
547 config MEM_SOFT_DIRTY
548 bool "Track memory changes"
549 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
550 select PROC_PAGE_MONITOR
552 This option enables memory changes tracking by introducing a
553 soft-dirty bit on pte-s. This bit it set when someone writes
554 into a page just as regular dirty bit, but unlike the latter
555 it can be cleared by hands.
557 See Documentation/vm/soft-dirty.txt for more details.
560 bool "Compressed cache for swap pages (EXPERIMENTAL)"
561 depends on FRONTSWAP && CRYPTO=y
566 A lightweight compressed cache for swap pages. It takes
567 pages that are in the process of being swapped out and attempts to
568 compress them into a dynamically allocated RAM-based memory pool.
569 This can result in a significant I/O reduction on swap device and,
570 in the case where decompressing from RAM is faster that swap device
571 reads, can also improve workload performance.
573 This is marked experimental because it is a new feature (as of
574 v3.11) that interacts heavily with memory reclaim. While these
575 interactions don't cause any known issues on simple memory setups,
576 they have not be fully explored on the large set of potential
577 configurations and workloads that exist.
580 tristate "Common API for compressed memory storage"
583 Compressed memory storage API. This allows using either zbud or
587 tristate "Low (Up to 2x) density storage for compressed pages"
590 A special purpose allocator for storing compressed pages.
591 It is designed to store up to two compressed pages per physical
592 page. While this design limits storage density, it has simple and
593 deterministic reclaim properties that make it preferable to a higher
594 density approach when reclaim will be used.
597 tristate "Up to 3x density storage for compressed pages"
601 A special purpose allocator for storing compressed pages.
602 It is designed to store up to three compressed pages per physical
603 page. It is a ZBUD derivative so the simplicity and determinism are
607 tristate "Memory allocator for compressed pages"
611 zsmalloc is a slab-based memory allocator designed to store
612 compressed RAM pages. zsmalloc uses virtual memory mapping
613 in order to reduce fragmentation. However, this results in a
614 non-standard allocator interface where a handle, not a pointer, is
615 returned by an alloc(). This handle must be mapped in order to
616 access the allocated space.
618 config PGTABLE_MAPPING
619 bool "Use page table mapping to access object in zsmalloc"
622 By default, zsmalloc uses a copy-based object mapping method to
623 access allocations that span two pages. However, if a particular
624 architecture (ex, ARM) performs VM mapping faster than copying,
625 then you should select this. This causes zsmalloc to use page table
626 mapping rather than copying for object mapping.
628 You can check speed with zsmalloc benchmark:
629 https://github.com/spartacus06/zsmapbench
632 bool "Export zsmalloc statistics"
636 This option enables code in the zsmalloc to collect various
637 statistics about whats happening in zsmalloc and exports that
638 information to userspace via debugfs.
641 config GENERIC_EARLY_IOREMAP
644 config MAX_STACK_SIZE_MB
645 int "Maximum user stack size for 32-bit processes (MB)"
649 depends on STACK_GROWSUP && (!64BIT || COMPAT)
651 This is the maximum stack size in Megabytes in the VM layout of 32-bit
652 user processes when the stack grows upwards (currently only on parisc
653 and metag arch). The stack will be located at the highest memory
654 address minus the given value, unless the RLIMIT_STACK hard limit is
655 changed to a smaller value in which case that is used.
657 A sane initial value is 80 MB.
659 # For architectures that support deferred memory initialisation
660 config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
663 config DEFERRED_STRUCT_PAGE_INIT
664 bool "Defer initialisation of struct pages to kthreads"
666 depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
667 depends on NO_BOOTMEM && MEMORY_HOTPLUG
670 Ordinarily all struct pages are initialised during early boot in a
671 single thread. On very large machines this can take a considerable
672 amount of time. If this option is set, large machines will bring up
673 a subset of memmap at boot and then initialise the rest in parallel
674 by starting one-off "pgdatinitX" kernel thread for each node X. This
675 has a potential performance impact on processes running early in the
676 lifetime of the system until these kthreads finish the
679 config IDLE_PAGE_TRACKING
680 bool "Enable idle page tracking"
681 depends on SYSFS && MMU
682 select PAGE_EXTENSION if !64BIT
684 This feature allows to estimate the amount of user pages that have
685 not been touched during a given period of time. This information can
686 be useful to tune memory cgroup limits and/or for job placement
687 within a compute cluster.
689 See Documentation/vm/idle_page_tracking.txt for more details.
692 bool "Device memory (pmem, etc...) hotplug support"
693 depends on MEMORY_HOTPLUG
694 depends on MEMORY_HOTREMOVE
695 depends on SPARSEMEM_VMEMMAP
696 depends on X86_64 #arch_add_memory() comprehends device memory
699 Device memory hotplug support allows for establishing pmem,
700 or other device driver discovered memory regions, in the
701 memmap. This allows pfn_to_page() lookups of otherwise
702 "device-physical" addresses which is needed for using a DAX
703 mapping in an O_DIRECT operation, among other things.
705 If FS_DAX is enabled, then say Y.
710 config ARCH_USES_HIGH_VMA_FLAGS
712 config ARCH_HAS_PKEYS