1# SPDX-License-Identifier: GPL-2.0-only 2 3menu "Memory Management options" 4 5# 6# For some reason microblaze and nios2 hard code SWAP=n. Hopefully we can 7# add proper SWAP support to them, in which case this can be remove. 8# 9config ARCH_NO_SWAP 10 bool 11 12config ZPOOL 13 bool 14 15menuconfig SWAP 16 bool "Support for paging of anonymous memory (swap)" 17 depends on MMU && BLOCK && !ARCH_NO_SWAP 18 default y 19 help 20 This option allows you to choose whether you want to have support 21 for so called swap devices or swap files in your kernel that are 22 used to provide more virtual memory than the actual RAM present 23 in your computer. If unsure say Y. 24 25config ZSWAP 26 bool "Compressed cache for swap pages" 27 depends on SWAP 28 select CRYPTO 29 select ZPOOL 30 help 31 A lightweight compressed cache for swap pages. It takes 32 pages that are in the process of being swapped out and attempts to 33 compress them into a dynamically allocated RAM-based memory pool. 34 This can result in a significant I/O reduction on swap device and, 35 in the case where decompressing from RAM is faster than swap device 36 reads, can also improve workload performance. 37 38config ZSWAP_DEFAULT_ON 39 bool "Enable the compressed cache for swap pages by default" 40 depends on ZSWAP 41 help 42 If selected, the compressed cache for swap pages will be enabled 43 at boot, otherwise it will be disabled. 44 45 The selection made here can be overridden by using the kernel 46 command line 'zswap.enabled=' option. 47 48config ZSWAP_SHRINKER_DEFAULT_ON 49 bool "Shrink the zswap pool on memory pressure" 50 depends on ZSWAP 51 default n 52 help 53 If selected, the zswap shrinker will be enabled, and the pages 54 stored in the zswap pool will become available for reclaim (i.e 55 written back to the backing swap device) on memory pressure. 56 57 This means that zswap writeback could happen even if the pool is 58 not yet full, or the cgroup zswap limit has not been reached, 59 reducing the chance that cold pages will reside in the zswap pool 60 and consume memory indefinitely. 61 62choice 63 prompt "Default compressor" 64 depends on ZSWAP 65 default ZSWAP_COMPRESSOR_DEFAULT_LZO 66 help 67 Selects the default compression algorithm for the compressed cache 68 for swap pages. 69 70 For an overview what kind of performance can be expected from 71 a particular compression algorithm please refer to the benchmarks 72 available at the following LWN page: 73 https://lwn.net/Articles/751795/ 74 75 If in doubt, select 'LZO'. 76 77 The selection made here can be overridden by using the kernel 78 command line 'zswap.compressor=' option. 79 80config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE 81 bool "Deflate" 82 select CRYPTO_DEFLATE 83 help 84 Use the Deflate algorithm as the default compression algorithm. 85 86config ZSWAP_COMPRESSOR_DEFAULT_LZO 87 bool "LZO" 88 select CRYPTO_LZO 89 help 90 Use the LZO algorithm as the default compression algorithm. 91 92config ZSWAP_COMPRESSOR_DEFAULT_842 93 bool "842" 94 select CRYPTO_842 95 help 96 Use the 842 algorithm as the default compression algorithm. 97 98config ZSWAP_COMPRESSOR_DEFAULT_LZ4 99 bool "LZ4" 100 select CRYPTO_LZ4 101 help 102 Use the LZ4 algorithm as the default compression algorithm. 103 104config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC 105 bool "LZ4HC" 106 select CRYPTO_LZ4HC 107 help 108 Use the LZ4HC algorithm as the default compression algorithm. 109 110config ZSWAP_COMPRESSOR_DEFAULT_ZSTD 111 bool "zstd" 112 select CRYPTO_ZSTD 113 help 114 Use the zstd algorithm as the default compression algorithm. 115endchoice 116 117config ZSWAP_COMPRESSOR_DEFAULT 118 string 119 depends on ZSWAP 120 default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE 121 default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO 122 default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 123 default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 124 default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC 125 default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD 126 default "" 127 128choice 129 prompt "Default allocator" 130 depends on ZSWAP 131 default ZSWAP_ZPOOL_DEFAULT_ZSMALLOC if HAVE_ZSMALLOC 132 default ZSWAP_ZPOOL_DEFAULT_ZBUD 133 help 134 Selects the default allocator for the compressed cache for 135 swap pages. 136 The default is 'zbud' for compatibility, however please do 137 read the description of each of the allocators below before 138 making a right choice. 139 140 The selection made here can be overridden by using the kernel 141 command line 'zswap.zpool=' option. 142 143config ZSWAP_ZPOOL_DEFAULT_ZBUD 144 bool "zbud" 145 select ZBUD 146 help 147 Use the zbud allocator as the default allocator. 148 149config ZSWAP_ZPOOL_DEFAULT_Z3FOLD 150 bool "z3fold" 151 select Z3FOLD 152 help 153 Use the z3fold allocator as the default allocator. 154 155config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC 156 bool "zsmalloc" 157 depends on HAVE_ZSMALLOC 158 select ZSMALLOC 159 help 160 Use the zsmalloc allocator as the default allocator. 161endchoice 162 163config ZSWAP_ZPOOL_DEFAULT 164 string 165 depends on ZSWAP 166 default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD 167 default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD 168 default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC 169 default "" 170 171config ZBUD 172 tristate "2:1 compression allocator (zbud)" 173 depends on ZSWAP 174 help 175 A special purpose allocator for storing compressed pages. 176 It is designed to store up to two compressed pages per physical 177 page. While this design limits storage density, it has simple and 178 deterministic reclaim properties that make it preferable to a higher 179 density approach when reclaim will be used. 180 181config Z3FOLD 182 tristate "3:1 compression allocator (z3fold)" 183 depends on ZSWAP 184 help 185 A special purpose allocator for storing compressed pages. 186 It is designed to store up to three compressed pages per physical 187 page. It is a ZBUD derivative so the simplicity and determinism are 188 still there. 189 190config HAVE_ZSMALLOC 191 def_bool y 192 depends on MMU 193 depends on PAGE_SIZE_LESS_THAN_256KB # we want <= 64 KiB 194 195config ZSMALLOC 196 tristate 197 prompt "N:1 compression allocator (zsmalloc)" if ZSWAP 198 depends on HAVE_ZSMALLOC 199 help 200 zsmalloc is a slab-based memory allocator designed to store 201 pages of various compression levels efficiently. It achieves 202 the highest storage density with the least amount of fragmentation. 203 204config ZSMALLOC_STAT 205 bool "Export zsmalloc statistics" 206 depends on ZSMALLOC 207 select DEBUG_FS 208 help 209 This option enables code in the zsmalloc to collect various 210 statistics about what's happening in zsmalloc and exports that 211 information to userspace via debugfs. 212 If unsure, say N. 213 214config ZSMALLOC_CHAIN_SIZE 215 int "Maximum number of physical pages per-zspage" 216 default 8 217 range 4 16 218 depends on ZSMALLOC 219 help 220 This option sets the upper limit on the number of physical pages 221 that a zmalloc page (zspage) can consist of. The optimal zspage 222 chain size is calculated for each size class during the 223 initialization of the pool. 224 225 Changing this option can alter the characteristics of size classes, 226 such as the number of pages per zspage and the number of objects 227 per zspage. This can also result in different configurations of 228 the pool, as zsmalloc merges size classes with similar 229 characteristics. 230 231 For more information, see zsmalloc documentation. 232 233menu "Slab allocator options" 234 235config SLUB 236 def_bool y 237 238config SLUB_TINY 239 bool "Configure for minimal memory footprint" 240 depends on EXPERT 241 select SLAB_MERGE_DEFAULT 242 help 243 Configures the slab allocator in a way to achieve minimal memory 244 footprint, sacrificing scalability, debugging and other features. 245 This is intended only for the smallest system that had used the 246 SLOB allocator and is not recommended for systems with more than 247 16MB RAM. 248 249 If unsure, say N. 250 251config SLAB_MERGE_DEFAULT 252 bool "Allow slab caches to be merged" 253 default y 254 help 255 For reduced kernel memory fragmentation, slab caches can be 256 merged when they share the same size and other characteristics. 257 This carries a risk of kernel heap overflows being able to 258 overwrite objects from merged caches (and more easily control 259 cache layout), which makes such heap attacks easier to exploit 260 by attackers. By keeping caches unmerged, these kinds of exploits 261 can usually only damage objects in the same cache. To disable 262 merging at runtime, "slab_nomerge" can be passed on the kernel 263 command line. 264 265config SLAB_FREELIST_RANDOM 266 bool "Randomize slab freelist" 267 depends on !SLUB_TINY 268 help 269 Randomizes the freelist order used on creating new pages. This 270 security feature reduces the predictability of the kernel slab 271 allocator against heap overflows. 272 273config SLAB_FREELIST_HARDENED 274 bool "Harden slab freelist metadata" 275 depends on !SLUB_TINY 276 help 277 Many kernel heap attacks try to target slab cache metadata and 278 other infrastructure. This options makes minor performance 279 sacrifices to harden the kernel slab allocator against common 280 freelist exploit methods. 281 282config SLAB_BUCKETS 283 bool "Support allocation from separate kmalloc buckets" 284 depends on !SLUB_TINY 285 default SLAB_FREELIST_HARDENED 286 help 287 Kernel heap attacks frequently depend on being able to create 288 specifically-sized allocations with user-controlled contents 289 that will be allocated into the same kmalloc bucket as a 290 target object. To avoid sharing these allocation buckets, 291 provide an explicitly separated set of buckets to be used for 292 user-controlled allocations. This may very slightly increase 293 memory fragmentation, though in practice it's only a handful 294 of extra pages since the bulk of user-controlled allocations 295 are relatively long-lived. 296 297 If unsure, say Y. 298 299config SLUB_STATS 300 default n 301 bool "Enable performance statistics" 302 depends on SYSFS && !SLUB_TINY 303 help 304 The statistics are useful to debug slab allocation behavior in 305 order find ways to optimize the allocator. This should never be 306 enabled for production use since keeping statistics slows down 307 the allocator by a few percentage points. The slabinfo command 308 supports the determination of the most active slabs to figure 309 out which slabs are relevant to a particular load. 310 Try running: slabinfo -DA 311 312config SLUB_CPU_PARTIAL 313 default y 314 depends on SMP && !SLUB_TINY 315 bool "Enable per cpu partial caches" 316 help 317 Per cpu partial caches accelerate objects allocation and freeing 318 that is local to a processor at the price of more indeterminism 319 in the latency of the free. On overflow these caches will be cleared 320 which requires the taking of locks that may cause latency spikes. 321 Typically one would choose no for a realtime system. 322 323config RANDOM_KMALLOC_CACHES 324 default n 325 depends on !SLUB_TINY 326 bool "Randomize slab caches for normal kmalloc" 327 help 328 A hardening feature that creates multiple copies of slab caches for 329 normal kmalloc allocation and makes kmalloc randomly pick one based 330 on code address, which makes the attackers more difficult to spray 331 vulnerable memory objects on the heap for the purpose of exploiting 332 memory vulnerabilities. 333 334 Currently the number of copies is set to 16, a reasonably large value 335 that effectively diverges the memory objects allocated for different 336 subsystems or modules into different caches, at the expense of a 337 limited degree of memory and CPU overhead that relates to hardware and 338 system workload. 339 340endmenu # Slab allocator options 341 342config SHUFFLE_PAGE_ALLOCATOR 343 bool "Page allocator randomization" 344 default SLAB_FREELIST_RANDOM && ACPI_NUMA 345 help 346 Randomization of the page allocator improves the average 347 utilization of a direct-mapped memory-side-cache. See section 348 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI 349 6.2a specification for an example of how a platform advertises 350 the presence of a memory-side-cache. There are also incidental 351 security benefits as it reduces the predictability of page 352 allocations to compliment SLAB_FREELIST_RANDOM, but the 353 default granularity of shuffling on the MAX_PAGE_ORDER i.e, 10th 354 order of pages is selected based on cache utilization benefits 355 on x86. 356 357 While the randomization improves cache utilization it may 358 negatively impact workloads on platforms without a cache. For 359 this reason, by default, the randomization is not enabled even 360 if SHUFFLE_PAGE_ALLOCATOR=y. The randomization may be force enabled 361 with the 'page_alloc.shuffle' kernel command line parameter. 362 363 Say Y if unsure. 364 365config COMPAT_BRK 366 bool "Disable heap randomization" 367 default y 368 help 369 Randomizing heap placement makes heap exploits harder, but it 370 also breaks ancient binaries (including anything libc5 based). 371 This option changes the bootup default to heap randomization 372 disabled, and can be overridden at runtime by setting 373 /proc/sys/kernel/randomize_va_space to 2. 374 375 On non-ancient distros (post-2000 ones) N is usually a safe choice. 376 377config MMAP_ALLOW_UNINITIALIZED 378 bool "Allow mmapped anonymous memory to be uninitialized" 379 depends on EXPERT && !MMU 380 default n 381 help 382 Normally, and according to the Linux spec, anonymous memory obtained 383 from mmap() has its contents cleared before it is passed to 384 userspace. Enabling this config option allows you to request that 385 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 386 providing a huge performance boost. If this option is not enabled, 387 then the flag will be ignored. 388 389 This is taken advantage of by uClibc's malloc(), and also by 390 ELF-FDPIC binfmt's brk and stack allocator. 391 392 Because of the obvious security issues, this option should only be 393 enabled on embedded devices where you control what is run in 394 userspace. Since that isn't generally a problem on no-MMU systems, 395 it is normally safe to say Y here. 396 397 See Documentation/admin-guide/mm/nommu-mmap.rst for more information. 398 399config SELECT_MEMORY_MODEL 400 def_bool y 401 depends on ARCH_SELECT_MEMORY_MODEL 402 403choice 404 prompt "Memory model" 405 depends on SELECT_MEMORY_MODEL 406 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT 407 default FLATMEM_MANUAL 408 help 409 This option allows you to change some of the ways that 410 Linux manages its memory internally. Most users will 411 only have one option here selected by the architecture 412 configuration. This is normal. 413 414config FLATMEM_MANUAL 415 bool "Flat Memory" 416 depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE 417 help 418 This option is best suited for non-NUMA systems with 419 flat address space. The FLATMEM is the most efficient 420 system in terms of performance and resource consumption 421 and it is the best option for smaller systems. 422 423 For systems that have holes in their physical address 424 spaces and for features like NUMA and memory hotplug, 425 choose "Sparse Memory". 426 427 If unsure, choose this option (Flat Memory) over any other. 428 429config SPARSEMEM_MANUAL 430 bool "Sparse Memory" 431 depends on ARCH_SPARSEMEM_ENABLE 432 help 433 This will be the only option for some systems, including 434 memory hot-plug systems. This is normal. 435 436 This option provides efficient support for systems with 437 holes is their physical address space and allows memory 438 hot-plug and hot-remove. 439 440 If unsure, choose "Flat Memory" over this option. 441 442endchoice 443 444config SPARSEMEM 445 def_bool y 446 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL 447 448config FLATMEM 449 def_bool y 450 depends on !SPARSEMEM || FLATMEM_MANUAL 451 452# 453# SPARSEMEM_EXTREME (which is the default) does some bootmem 454# allocations when sparse_init() is called. If this cannot 455# be done on your architecture, select this option. However, 456# statically allocating the mem_section[] array can potentially 457# consume vast quantities of .bss, so be careful. 458# 459# This option will also potentially produce smaller runtime code 460# with gcc 3.4 and later. 461# 462config SPARSEMEM_STATIC 463 bool 464 465# 466# Architecture platforms which require a two level mem_section in SPARSEMEM 467# must select this option. This is usually for architecture platforms with 468# an extremely sparse physical address space. 469# 470config SPARSEMEM_EXTREME 471 def_bool y 472 depends on SPARSEMEM && !SPARSEMEM_STATIC 473 474config SPARSEMEM_VMEMMAP_ENABLE 475 bool 476 477config SPARSEMEM_VMEMMAP 478 bool "Sparse Memory virtual memmap" 479 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE 480 default y 481 help 482 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise 483 pfn_to_page and page_to_pfn operations. This is the most 484 efficient option when sufficient kernel resources are available. 485# 486# Select this config option from the architecture Kconfig, if it is preferred 487# to enable the feature of HugeTLB/dev_dax vmemmap optimization. 488# 489config ARCH_WANT_OPTIMIZE_DAX_VMEMMAP 490 bool 491 492config ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP 493 bool 494 495config HAVE_MEMBLOCK_PHYS_MAP 496 bool 497 498config HAVE_GUP_FAST 499 depends on MMU 500 bool 501 502# Don't discard allocated memory used to track "memory" and "reserved" memblocks 503# after early boot, so it can still be used to test for validity of memory. 504# Also, memblocks are updated with memory hot(un)plug. 505config ARCH_KEEP_MEMBLOCK 506 bool 507 508# Keep arch NUMA mapping infrastructure post-init. 509config NUMA_KEEP_MEMINFO 510 bool 511 512config MEMORY_ISOLATION 513 bool 514 515# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked 516# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via 517# /dev/mem. 518config EXCLUSIVE_SYSTEM_RAM 519 def_bool y 520 depends on !DEVMEM || STRICT_DEVMEM 521 522# 523# Only be set on architectures that have completely implemented memory hotplug 524# feature. If you are not sure, don't touch it. 525# 526config HAVE_BOOTMEM_INFO_NODE 527 def_bool n 528 529config ARCH_ENABLE_MEMORY_HOTPLUG 530 bool 531 532config ARCH_ENABLE_MEMORY_HOTREMOVE 533 bool 534 535# eventually, we can have this option just 'select SPARSEMEM' 536menuconfig MEMORY_HOTPLUG 537 bool "Memory hotplug" 538 select MEMORY_ISOLATION 539 depends on SPARSEMEM 540 depends on ARCH_ENABLE_MEMORY_HOTPLUG 541 depends on 64BIT 542 select NUMA_KEEP_MEMINFO if NUMA 543 544if MEMORY_HOTPLUG 545 546config MEMORY_HOTPLUG_DEFAULT_ONLINE 547 bool "Online the newly added memory blocks by default" 548 depends on MEMORY_HOTPLUG 549 help 550 This option sets the default policy setting for memory hotplug 551 onlining policy (/sys/devices/system/memory/auto_online_blocks) which 552 determines what happens to newly added memory regions. Policy setting 553 can always be changed at runtime. 554 See Documentation/admin-guide/mm/memory-hotplug.rst for more information. 555 556 Say Y here if you want all hot-plugged memory blocks to appear in 557 'online' state by default. 558 Say N here if you want the default policy to keep all hot-plugged 559 memory blocks in 'offline' state. 560 561config MEMORY_HOTREMOVE 562 bool "Allow for memory hot remove" 563 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) 564 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE 565 depends on MIGRATION 566 567config MHP_MEMMAP_ON_MEMORY 568 def_bool y 569 depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP 570 depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE 571 572endif # MEMORY_HOTPLUG 573 574config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE 575 bool 576 577# Heavily threaded applications may benefit from splitting the mm-wide 578# page_table_lock, so that faults on different parts of the user address 579# space can be handled with less contention: split it at this NR_CPUS. 580# Default to 4 for wider testing, though 8 might be more appropriate. 581# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. 582# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. 583# SPARC32 allocates multiple pte tables within a single page, and therefore 584# a per-page lock leads to problems when multiple tables need to be locked 585# at the same time (e.g. copy_page_range()). 586# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. 587# 588config SPLIT_PTLOCK_CPUS 589 int 590 default "999999" if !MMU 591 default "999999" if ARM && !CPU_CACHE_VIPT 592 default "999999" if PARISC && !PA20 593 default "999999" if SPARC32 594 default "4" 595 596config ARCH_ENABLE_SPLIT_PMD_PTLOCK 597 bool 598 599# 600# support for memory balloon 601config MEMORY_BALLOON 602 bool 603 604# 605# support for memory balloon compaction 606config BALLOON_COMPACTION 607 bool "Allow for balloon memory compaction/migration" 608 default y 609 depends on COMPACTION && MEMORY_BALLOON 610 help 611 Memory fragmentation introduced by ballooning might reduce 612 significantly the number of 2MB contiguous memory blocks that can be 613 used within a guest, thus imposing performance penalties associated 614 with the reduced number of transparent huge pages that could be used 615 by the guest workload. Allowing the compaction & migration for memory 616 pages enlisted as being part of memory balloon devices avoids the 617 scenario aforementioned and helps improving memory defragmentation. 618 619# 620# support for memory compaction 621config COMPACTION 622 bool "Allow for memory compaction" 623 default y 624 select MIGRATION 625 depends on MMU 626 help 627 Compaction is the only memory management component to form 628 high order (larger physically contiguous) memory blocks 629 reliably. The page allocator relies on compaction heavily and 630 the lack of the feature can lead to unexpected OOM killer 631 invocations for high order memory requests. You shouldn't 632 disable this option unless there really is a strong reason for 633 it and then we would be really interested to hear about that at 634 linux-mm@kvack.org. 635 636config COMPACT_UNEVICTABLE_DEFAULT 637 int 638 depends on COMPACTION 639 default 0 if PREEMPT_RT 640 default 1 641 642# 643# support for free page reporting 644config PAGE_REPORTING 645 bool "Free page reporting" 646 help 647 Free page reporting allows for the incremental acquisition of 648 free pages from the buddy allocator for the purpose of reporting 649 those pages to another entity, such as a hypervisor, so that the 650 memory can be freed within the host for other uses. 651 652# 653# support for page migration 654# 655config MIGRATION 656 bool "Page migration" 657 default y 658 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU 659 help 660 Allows the migration of the physical location of pages of processes 661 while the virtual addresses are not changed. This is useful in 662 two situations. The first is on NUMA systems to put pages nearer 663 to the processors accessing. The second is when allocating huge 664 pages as migration can relocate pages to satisfy a huge page 665 allocation instead of reclaiming. 666 667config DEVICE_MIGRATION 668 def_bool MIGRATION && ZONE_DEVICE 669 670config ARCH_ENABLE_HUGEPAGE_MIGRATION 671 bool 672 673config ARCH_ENABLE_THP_MIGRATION 674 bool 675 676config HUGETLB_PAGE_SIZE_VARIABLE 677 def_bool n 678 help 679 Allows the pageblock_order value to be dynamic instead of just standard 680 HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available 681 on a platform. 682 683 Note that the pageblock_order cannot exceed MAX_PAGE_ORDER and will be 684 clamped down to MAX_PAGE_ORDER. 685 686config CONTIG_ALLOC 687 def_bool (MEMORY_ISOLATION && COMPACTION) || CMA 688 689config PCP_BATCH_SCALE_MAX 690 int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" 691 default 5 692 range 0 6 693 help 694 In page allocator, PCP (Per-CPU pageset) is refilled and drained in 695 batches. The batch number is scaled automatically to improve page 696 allocation/free throughput. But too large scale factor may hurt 697 latency. This option sets the upper limit of scale factor to limit 698 the maximum latency. 699 700config PHYS_ADDR_T_64BIT 701 def_bool 64BIT 702 703config BOUNCE 704 bool "Enable bounce buffers" 705 default y 706 depends on BLOCK && MMU && HIGHMEM 707 help 708 Enable bounce buffers for devices that cannot access the full range of 709 memory available to the CPU. Enabled by default when HIGHMEM is 710 selected, but you may say n to override this. 711 712config MMU_NOTIFIER 713 bool 714 select INTERVAL_TREE 715 716config KSM 717 bool "Enable KSM for page merging" 718 depends on MMU 719 select XXHASH 720 help 721 Enable Kernel Samepage Merging: KSM periodically scans those areas 722 of an application's address space that an app has advised may be 723 mergeable. When it finds pages of identical content, it replaces 724 the many instances by a single page with that content, so 725 saving memory until one or another app needs to modify the content. 726 Recommended for use with KVM, or with other duplicative applications. 727 See Documentation/mm/ksm.rst for more information: KSM is inactive 728 until a program has madvised that an area is MADV_MERGEABLE, and 729 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). 730 731config DEFAULT_MMAP_MIN_ADDR 732 int "Low address space to protect from user allocation" 733 depends on MMU 734 default 4096 735 help 736 This is the portion of low virtual memory which should be protected 737 from userspace allocation. Keeping a user from writing to low pages 738 can help reduce the impact of kernel NULL pointer bugs. 739 740 For most arm64, ppc64 and x86 users with lots of address space 741 a value of 65536 is reasonable and should cause no problems. 742 On arm and other archs it should not be higher than 32768. 743 Programs which use vm86 functionality or have some need to map 744 this low address space will need CAP_SYS_RAWIO or disable this 745 protection by setting the value to 0. 746 747 This value can be changed after boot using the 748 /proc/sys/vm/mmap_min_addr tunable. 749 750config ARCH_SUPPORTS_MEMORY_FAILURE 751 bool 752 753config MEMORY_FAILURE 754 depends on MMU 755 depends on ARCH_SUPPORTS_MEMORY_FAILURE 756 bool "Enable recovery from hardware memory errors" 757 select MEMORY_ISOLATION 758 select RAS 759 help 760 Enables code to recover from some memory failures on systems 761 with MCA recovery. This allows a system to continue running 762 even when some of its memory has uncorrected errors. This requires 763 special hardware support and typically ECC memory. 764 765config HWPOISON_INJECT 766 tristate "HWPoison pages injector" 767 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS 768 select PROC_PAGE_MONITOR 769 770config NOMMU_INITIAL_TRIM_EXCESS 771 int "Turn on mmap() excess space trimming before booting" 772 depends on !MMU 773 default 1 774 help 775 The NOMMU mmap() frequently needs to allocate large contiguous chunks 776 of memory on which to store mappings, but it can only ask the system 777 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently 778 more than it requires. To deal with this, mmap() is able to trim off 779 the excess and return it to the allocator. 780 781 If trimming is enabled, the excess is trimmed off and returned to the 782 system allocator, which can cause extra fragmentation, particularly 783 if there are a lot of transient processes. 784 785 If trimming is disabled, the excess is kept, but not used, which for 786 long-term mappings means that the space is wasted. 787 788 Trimming can be dynamically controlled through a sysctl option 789 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of 790 excess pages there must be before trimming should occur, or zero if 791 no trimming is to occur. 792 793 This option specifies the initial value of this option. The default 794 of 1 says that all excess pages should be trimmed. 795 796 See Documentation/admin-guide/mm/nommu-mmap.rst for more information. 797 798config ARCH_WANT_GENERAL_HUGETLB 799 bool 800 801config ARCH_WANTS_THP_SWAP 802 def_bool n 803 804menuconfig TRANSPARENT_HUGEPAGE 805 bool "Transparent Hugepage Support" 806 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT 807 select COMPACTION 808 select XARRAY_MULTI 809 help 810 Transparent Hugepages allows the kernel to use huge pages and 811 huge tlb transparently to the applications whenever possible. 812 This feature can improve computing performance to certain 813 applications by speeding up page faults during memory 814 allocation, by reducing the number of tlb misses and by speeding 815 up the pagetable walking. 816 817 If memory constrained on embedded, you may want to say N. 818 819if TRANSPARENT_HUGEPAGE 820 821choice 822 prompt "Transparent Hugepage Support sysfs defaults" 823 depends on TRANSPARENT_HUGEPAGE 824 default TRANSPARENT_HUGEPAGE_ALWAYS 825 help 826 Selects the sysfs defaults for Transparent Hugepage Support. 827 828 config TRANSPARENT_HUGEPAGE_ALWAYS 829 bool "always" 830 help 831 Enabling Transparent Hugepage always, can increase the 832 memory footprint of applications without a guaranteed 833 benefit but it will work automatically for all applications. 834 835 config TRANSPARENT_HUGEPAGE_MADVISE 836 bool "madvise" 837 help 838 Enabling Transparent Hugepage madvise, will only provide a 839 performance improvement benefit to the applications using 840 madvise(MADV_HUGEPAGE) but it won't risk to increase the 841 memory footprint of applications without a guaranteed 842 benefit. 843 844 config TRANSPARENT_HUGEPAGE_NEVER 845 bool "never" 846 help 847 Disable Transparent Hugepage by default. It can still be 848 enabled at runtime via sysfs. 849endchoice 850 851config THP_SWAP 852 def_bool y 853 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT 854 help 855 Swap transparent huge pages in one piece, without splitting. 856 XXX: For now, swap cluster backing transparent huge page 857 will be split after swapout. 858 859 For selection by architectures with reasonable THP sizes. 860 861config READ_ONLY_THP_FOR_FS 862 bool "Read-only THP for filesystems (EXPERIMENTAL)" 863 depends on TRANSPARENT_HUGEPAGE && SHMEM 864 865 help 866 Allow khugepaged to put read-only file-backed pages in THP. 867 868 This is marked experimental because it is a new feature. Write 869 support of file THPs will be developed in the next few release 870 cycles. 871 872endif # TRANSPARENT_HUGEPAGE 873 874# 875# The architecture supports pgtable leaves that is larger than PAGE_SIZE 876# 877config PGTABLE_HAS_HUGE_LEAVES 878 def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE 879 880# 881# UP and nommu archs use km based percpu allocator 882# 883config NEED_PER_CPU_KM 884 depends on !SMP || !MMU 885 bool 886 default y 887 888config NEED_PER_CPU_EMBED_FIRST_CHUNK 889 bool 890 891config NEED_PER_CPU_PAGE_FIRST_CHUNK 892 bool 893 894config USE_PERCPU_NUMA_NODE_ID 895 bool 896 897config HAVE_SETUP_PER_CPU_AREA 898 bool 899 900config CMA 901 bool "Contiguous Memory Allocator" 902 depends on MMU 903 select MIGRATION 904 select MEMORY_ISOLATION 905 help 906 This enables the Contiguous Memory Allocator which allows other 907 subsystems to allocate big physically-contiguous blocks of memory. 908 CMA reserves a region of memory and allows only movable pages to 909 be allocated from it. This way, the kernel can use the memory for 910 pagecache and when a subsystem requests for contiguous area, the 911 allocated pages are migrated away to serve the contiguous request. 912 913 If unsure, say "n". 914 915config CMA_DEBUGFS 916 bool "CMA debugfs interface" 917 depends on CMA && DEBUG_FS 918 help 919 Turns on the DebugFS interface for CMA. 920 921config CMA_SYSFS 922 bool "CMA information through sysfs interface" 923 depends on CMA && SYSFS 924 help 925 This option exposes some sysfs attributes to get information 926 from CMA. 927 928config CMA_AREAS 929 int "Maximum count of the CMA areas" 930 depends on CMA 931 default 20 if NUMA 932 default 8 933 help 934 CMA allows to create CMA areas for particular purpose, mainly, 935 used as device private area. This parameter sets the maximum 936 number of CMA area in the system. 937 938 If unsure, leave the default value "8" in UMA and "20" in NUMA. 939 940config MEM_SOFT_DIRTY 941 bool "Track memory changes" 942 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS 943 select PROC_PAGE_MONITOR 944 help 945 This option enables memory changes tracking by introducing a 946 soft-dirty bit on pte-s. This bit it set when someone writes 947 into a page just as regular dirty bit, but unlike the latter 948 it can be cleared by hands. 949 950 See Documentation/admin-guide/mm/soft-dirty.rst for more details. 951 952config GENERIC_EARLY_IOREMAP 953 bool 954 955config STACK_MAX_DEFAULT_SIZE_MB 956 int "Default maximum user stack size for 32-bit processes (MB)" 957 default 100 958 range 8 2048 959 depends on STACK_GROWSUP && (!64BIT || COMPAT) 960 help 961 This is the maximum stack size in Megabytes in the VM layout of 32-bit 962 user processes when the stack grows upwards (currently only on parisc 963 arch) when the RLIMIT_STACK hard limit is unlimited. 964 965 A sane initial value is 100 MB. 966 967config DEFERRED_STRUCT_PAGE_INIT 968 bool "Defer initialisation of struct pages to kthreads" 969 depends on SPARSEMEM 970 depends on !NEED_PER_CPU_KM 971 depends on 64BIT 972 depends on !KMSAN 973 select PADATA 974 help 975 Ordinarily all struct pages are initialised during early boot in a 976 single thread. On very large machines this can take a considerable 977 amount of time. If this option is set, large machines will bring up 978 a subset of memmap at boot and then initialise the rest in parallel. 979 This has a potential performance impact on tasks running early in the 980 lifetime of the system until these kthreads finish the 981 initialisation. 982 983config PAGE_IDLE_FLAG 984 bool 985 select PAGE_EXTENSION if !64BIT 986 help 987 This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed 988 bit writers can set the state of the bit in the flags so that PTE 989 Accessed bit readers may avoid disturbance. 990 991config IDLE_PAGE_TRACKING 992 bool "Enable idle page tracking" 993 depends on SYSFS && MMU 994 select PAGE_IDLE_FLAG 995 help 996 This feature allows to estimate the amount of user pages that have 997 not been touched during a given period of time. This information can 998 be useful to tune memory cgroup limits and/or for job placement 999 within a compute cluster. 1000 1001 See Documentation/admin-guide/mm/idle_page_tracking.rst for 1002 more details. 1003 1004# Architectures which implement cpu_dcache_is_aliasing() to query 1005# whether the data caches are aliased (VIVT or VIPT with dcache 1006# aliasing) need to select this. 1007config ARCH_HAS_CPU_CACHE_ALIASING 1008 bool 1009 1010config ARCH_HAS_CACHE_LINE_SIZE 1011 bool 1012 1013config ARCH_HAS_CURRENT_STACK_POINTER 1014 bool 1015 help 1016 In support of HARDENED_USERCOPY performing stack variable lifetime 1017 checking, an architecture-agnostic way to find the stack pointer 1018 is needed. Once an architecture defines an unsigned long global 1019 register alias named "current_stack_pointer", this config can be 1020 selected. 1021 1022config ARCH_HAS_PTE_DEVMAP 1023 bool 1024 1025config ARCH_HAS_ZONE_DMA_SET 1026 bool 1027 1028config ZONE_DMA 1029 bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET 1030 default y if ARM64 || X86 1031 1032config ZONE_DMA32 1033 bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET 1034 depends on !X86_32 1035 default y if ARM64 1036 1037config ZONE_DEVICE 1038 bool "Device memory (pmem, HMM, etc...) hotplug support" 1039 depends on MEMORY_HOTPLUG 1040 depends on MEMORY_HOTREMOVE 1041 depends on SPARSEMEM_VMEMMAP 1042 depends on ARCH_HAS_PTE_DEVMAP 1043 select XARRAY_MULTI 1044 1045 help 1046 Device memory hotplug support allows for establishing pmem, 1047 or other device driver discovered memory regions, in the 1048 memmap. This allows pfn_to_page() lookups of otherwise 1049 "device-physical" addresses which is needed for using a DAX 1050 mapping in an O_DIRECT operation, among other things. 1051 1052 If FS_DAX is enabled, then say Y. 1053 1054# 1055# Helpers to mirror range of the CPU page tables of a process into device page 1056# tables. 1057# 1058config HMM_MIRROR 1059 bool 1060 depends on MMU 1061 1062config GET_FREE_REGION 1063 depends on SPARSEMEM 1064 bool 1065 1066config DEVICE_PRIVATE 1067 bool "Unaddressable device memory (GPU memory, ...)" 1068 depends on ZONE_DEVICE 1069 select GET_FREE_REGION 1070 1071 help 1072 Allows creation of struct pages to represent unaddressable device 1073 memory; i.e., memory that is only accessible from the device (or 1074 group of devices). You likely also want to select HMM_MIRROR. 1075 1076config VMAP_PFN 1077 bool 1078 1079config ARCH_USES_HIGH_VMA_FLAGS 1080 bool 1081config ARCH_HAS_PKEYS 1082 bool 1083 1084config ARCH_USES_PG_ARCH_X 1085 bool 1086 help 1087 Enable the definition of PG_arch_x page flags with x > 1. Only 1088 suitable for 64-bit architectures with CONFIG_FLATMEM or 1089 CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be 1090 enough room for additional bits in page->flags. 1091 1092config VM_EVENT_COUNTERS 1093 default y 1094 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1095 help 1096 VM event counters are needed for event counts to be shown. 1097 This option allows the disabling of the VM event counters 1098 on EXPERT systems. /proc/vmstat will only show page counts 1099 if VM event counters are disabled. 1100 1101config PERCPU_STATS 1102 bool "Collect percpu memory statistics" 1103 help 1104 This feature collects and exposes statistics via debugfs. The 1105 information includes global and per chunk statistics, which can 1106 be used to help understand percpu memory usage. 1107 1108config GUP_TEST 1109 bool "Enable infrastructure for get_user_pages()-related unit tests" 1110 depends on DEBUG_FS 1111 help 1112 Provides /sys/kernel/debug/gup_test, which in turn provides a way 1113 to make ioctl calls that can launch kernel-based unit tests for 1114 the get_user_pages*() and pin_user_pages*() family of API calls. 1115 1116 These tests include benchmark testing of the _fast variants of 1117 get_user_pages*() and pin_user_pages*(), as well as smoke tests of 1118 the non-_fast variants. 1119 1120 There is also a sub-test that allows running dump_page() on any 1121 of up to eight pages (selected by command line args) within the 1122 range of user-space addresses. These pages are either pinned via 1123 pin_user_pages*(), or pinned via get_user_pages*(), as specified 1124 by other command line arguments. 1125 1126 See tools/testing/selftests/mm/gup_test.c 1127 1128comment "GUP_TEST needs to have DEBUG_FS enabled" 1129 depends on !GUP_TEST && !DEBUG_FS 1130 1131config GUP_GET_PXX_LOW_HIGH 1132 bool 1133 1134config DMAPOOL_TEST 1135 tristate "Enable a module to run time tests on dma_pool" 1136 depends on HAS_DMA 1137 help 1138 Provides a test module that will allocate and free many blocks of 1139 various sizes and report how long it takes. This is intended to 1140 provide a consistent way to measure how changes to the 1141 dma_pool_alloc/free routines affect performance. 1142 1143config ARCH_HAS_PTE_SPECIAL 1144 bool 1145 1146config MAPPING_DIRTY_HELPERS 1147 bool 1148 1149config KMAP_LOCAL 1150 bool 1151 1152config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY 1153 bool 1154 1155# struct io_mapping based helper. Selected by drivers that need them 1156config IO_MAPPING 1157 bool 1158 1159config MEMFD_CREATE 1160 bool "Enable memfd_create() system call" if EXPERT 1161 1162config SECRETMEM 1163 default y 1164 bool "Enable memfd_secret() system call" if EXPERT 1165 depends on ARCH_HAS_SET_DIRECT_MAP 1166 help 1167 Enable the memfd_secret() system call with the ability to create 1168 memory areas visible only in the context of the owning process and 1169 not mapped to other processes and other kernel page tables. 1170 1171config ANON_VMA_NAME 1172 bool "Anonymous VMA name support" 1173 depends on PROC_FS && ADVISE_SYSCALLS && MMU 1174 1175 help 1176 Allow naming anonymous virtual memory areas. 1177 1178 This feature allows assigning names to virtual memory areas. Assigned 1179 names can be later retrieved from /proc/pid/maps and /proc/pid/smaps 1180 and help identifying individual anonymous memory areas. 1181 Assigning a name to anonymous virtual memory area might prevent that 1182 area from being merged with adjacent virtual memory areas due to the 1183 difference in their name. 1184 1185config HAVE_ARCH_USERFAULTFD_WP 1186 bool 1187 help 1188 Arch has userfaultfd write protection support 1189 1190config HAVE_ARCH_USERFAULTFD_MINOR 1191 bool 1192 help 1193 Arch has userfaultfd minor fault support 1194 1195menuconfig USERFAULTFD 1196 bool "Enable userfaultfd() system call" 1197 depends on MMU 1198 help 1199 Enable the userfaultfd() system call that allows to intercept and 1200 handle page faults in userland. 1201 1202if USERFAULTFD 1203config PTE_MARKER_UFFD_WP 1204 bool "Userfaultfd write protection support for shmem/hugetlbfs" 1205 default y 1206 depends on HAVE_ARCH_USERFAULTFD_WP 1207 1208 help 1209 Allows to create marker PTEs for userfaultfd write protection 1210 purposes. It is required to enable userfaultfd write protection on 1211 file-backed memory types like shmem and hugetlbfs. 1212endif # USERFAULTFD 1213 1214# multi-gen LRU { 1215config LRU_GEN 1216 bool "Multi-Gen LRU" 1217 depends on MMU 1218 # make sure folio->flags has enough spare bits 1219 depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP 1220 help 1221 A high performance LRU implementation to overcommit memory. See 1222 Documentation/admin-guide/mm/multigen_lru.rst for details. 1223 1224config LRU_GEN_ENABLED 1225 bool "Enable by default" 1226 depends on LRU_GEN 1227 help 1228 This option enables the multi-gen LRU by default. 1229 1230config LRU_GEN_STATS 1231 bool "Full stats for debugging" 1232 depends on LRU_GEN 1233 help 1234 Do not enable this option unless you plan to look at historical stats 1235 from evicted generations for debugging purpose. 1236 1237 This option has a per-memcg and per-node memory overhead. 1238 1239config LRU_GEN_WALKS_MMU 1240 def_bool y 1241 depends on LRU_GEN && ARCH_HAS_HW_PTE_YOUNG 1242# } 1243 1244config ARCH_SUPPORTS_PER_VMA_LOCK 1245 def_bool n 1246 1247config PER_VMA_LOCK 1248 def_bool y 1249 depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP 1250 help 1251 Allow per-vma locking during page fault handling. 1252 1253 This feature allows locking each virtual memory area separately when 1254 handling page faults instead of taking mmap_lock. 1255 1256config LOCK_MM_AND_FIND_VMA 1257 bool 1258 depends on !STACK_GROWSUP 1259 1260config IOMMU_MM_DATA 1261 bool 1262 1263config EXECMEM 1264 bool 1265 1266source "mm/damon/Kconfig" 1267 1268endmenu 1269