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_EXCLUSIVE_LOADS_DEFAULT_ON 49 bool "Invalidate zswap entries when pages are loaded" 50 depends on ZSWAP 51 help 52 If selected, exclusive loads for zswap will be enabled at boot, 53 otherwise it will be disabled. 54 55 If exclusive loads are enabled, when a page is loaded from zswap, 56 the zswap entry is invalidated at once, as opposed to leaving it 57 in zswap until the swap entry is freed. 58 59 This avoids having two copies of the same page in memory 60 (compressed and uncompressed) after faulting in a page from zswap. 61 The cost is that if the page was never dirtied and needs to be 62 swapped out again, it will be re-compressed. 63 64choice 65 prompt "Default compressor" 66 depends on ZSWAP 67 default ZSWAP_COMPRESSOR_DEFAULT_LZO 68 help 69 Selects the default compression algorithm for the compressed cache 70 for swap pages. 71 72 For an overview what kind of performance can be expected from 73 a particular compression algorithm please refer to the benchmarks 74 available at the following LWN page: 75 https://lwn.net/Articles/751795/ 76 77 If in doubt, select 'LZO'. 78 79 The selection made here can be overridden by using the kernel 80 command line 'zswap.compressor=' option. 81 82config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE 83 bool "Deflate" 84 select CRYPTO_DEFLATE 85 help 86 Use the Deflate algorithm as the default compression algorithm. 87 88config ZSWAP_COMPRESSOR_DEFAULT_LZO 89 bool "LZO" 90 select CRYPTO_LZO 91 help 92 Use the LZO algorithm as the default compression algorithm. 93 94config ZSWAP_COMPRESSOR_DEFAULT_842 95 bool "842" 96 select CRYPTO_842 97 help 98 Use the 842 algorithm as the default compression algorithm. 99 100config ZSWAP_COMPRESSOR_DEFAULT_LZ4 101 bool "LZ4" 102 select CRYPTO_LZ4 103 help 104 Use the LZ4 algorithm as the default compression algorithm. 105 106config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC 107 bool "LZ4HC" 108 select CRYPTO_LZ4HC 109 help 110 Use the LZ4HC algorithm as the default compression algorithm. 111 112config ZSWAP_COMPRESSOR_DEFAULT_ZSTD 113 bool "zstd" 114 select CRYPTO_ZSTD 115 help 116 Use the zstd algorithm as the default compression algorithm. 117endchoice 118 119config ZSWAP_COMPRESSOR_DEFAULT 120 string 121 depends on ZSWAP 122 default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE 123 default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO 124 default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 125 default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 126 default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC 127 default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD 128 default "" 129 130choice 131 prompt "Default allocator" 132 depends on ZSWAP 133 default ZSWAP_ZPOOL_DEFAULT_ZSMALLOC if MMU 134 default ZSWAP_ZPOOL_DEFAULT_ZBUD 135 help 136 Selects the default allocator for the compressed cache for 137 swap pages. 138 The default is 'zbud' for compatibility, however please do 139 read the description of each of the allocators below before 140 making a right choice. 141 142 The selection made here can be overridden by using the kernel 143 command line 'zswap.zpool=' option. 144 145config ZSWAP_ZPOOL_DEFAULT_ZBUD 146 bool "zbud" 147 select ZBUD 148 help 149 Use the zbud allocator as the default allocator. 150 151config ZSWAP_ZPOOL_DEFAULT_Z3FOLD 152 bool "z3fold" 153 select Z3FOLD 154 help 155 Use the z3fold allocator as the default allocator. 156 157config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC 158 bool "zsmalloc" 159 select ZSMALLOC 160 help 161 Use the zsmalloc allocator as the default allocator. 162endchoice 163 164config ZSWAP_ZPOOL_DEFAULT 165 string 166 depends on ZSWAP 167 default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD 168 default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD 169 default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC 170 default "" 171 172config ZBUD 173 tristate "2:1 compression allocator (zbud)" 174 depends on ZSWAP 175 help 176 A special purpose allocator for storing compressed pages. 177 It is designed to store up to two compressed pages per physical 178 page. While this design limits storage density, it has simple and 179 deterministic reclaim properties that make it preferable to a higher 180 density approach when reclaim will be used. 181 182config Z3FOLD 183 tristate "3:1 compression allocator (z3fold)" 184 depends on ZSWAP 185 help 186 A special purpose allocator for storing compressed pages. 187 It is designed to store up to three compressed pages per physical 188 page. It is a ZBUD derivative so the simplicity and determinism are 189 still there. 190 191config ZSMALLOC 192 tristate 193 prompt "N:1 compression allocator (zsmalloc)" if ZSWAP 194 depends on MMU 195 help 196 zsmalloc is a slab-based memory allocator designed to store 197 pages of various compression levels efficiently. It achieves 198 the highest storage density with the least amount of fragmentation. 199 200config ZSMALLOC_STAT 201 bool "Export zsmalloc statistics" 202 depends on ZSMALLOC 203 select DEBUG_FS 204 help 205 This option enables code in the zsmalloc to collect various 206 statistics about what's happening in zsmalloc and exports that 207 information to userspace via debugfs. 208 If unsure, say N. 209 210config ZSMALLOC_CHAIN_SIZE 211 int "Maximum number of physical pages per-zspage" 212 default 8 213 range 4 16 214 depends on ZSMALLOC 215 help 216 This option sets the upper limit on the number of physical pages 217 that a zmalloc page (zspage) can consist of. The optimal zspage 218 chain size is calculated for each size class during the 219 initialization of the pool. 220 221 Changing this option can alter the characteristics of size classes, 222 such as the number of pages per zspage and the number of objects 223 per zspage. This can also result in different configurations of 224 the pool, as zsmalloc merges size classes with similar 225 characteristics. 226 227 For more information, see zsmalloc documentation. 228 229menu "SLAB allocator options" 230 231choice 232 prompt "Choose SLAB allocator" 233 default SLUB 234 help 235 This option allows to select a slab allocator. 236 237config SLAB_DEPRECATED 238 bool "SLAB (DEPRECATED)" 239 depends on !PREEMPT_RT 240 help 241 Deprecated and scheduled for removal in a few cycles. Replaced by 242 SLUB. 243 244 If you cannot migrate to SLUB, please contact linux-mm@kvack.org 245 and the people listed in the SLAB ALLOCATOR section of MAINTAINERS 246 file, explaining why. 247 248 The regular slab allocator that is established and known to work 249 well in all environments. It organizes cache hot objects in 250 per cpu and per node queues. 251 252config SLUB 253 bool "SLUB (Unqueued Allocator)" 254 help 255 SLUB is a slab allocator that minimizes cache line usage 256 instead of managing queues of cached objects (SLAB approach). 257 Per cpu caching is realized using slabs of objects instead 258 of queues of objects. SLUB can use memory efficiently 259 and has enhanced diagnostics. SLUB is the default choice for 260 a slab allocator. 261 262endchoice 263 264config SLAB 265 bool 266 default y 267 depends on SLAB_DEPRECATED 268 269config SLUB_TINY 270 bool "Configure SLUB for minimal memory footprint" 271 depends on SLUB && EXPERT 272 select SLAB_MERGE_DEFAULT 273 help 274 Configures the SLUB allocator in a way to achieve minimal memory 275 footprint, sacrificing scalability, debugging and other features. 276 This is intended only for the smallest system that had used the 277 SLOB allocator and is not recommended for systems with more than 278 16MB RAM. 279 280 If unsure, say N. 281 282config SLAB_MERGE_DEFAULT 283 bool "Allow slab caches to be merged" 284 default y 285 depends on SLAB || SLUB 286 help 287 For reduced kernel memory fragmentation, slab caches can be 288 merged when they share the same size and other characteristics. 289 This carries a risk of kernel heap overflows being able to 290 overwrite objects from merged caches (and more easily control 291 cache layout), which makes such heap attacks easier to exploit 292 by attackers. By keeping caches unmerged, these kinds of exploits 293 can usually only damage objects in the same cache. To disable 294 merging at runtime, "slab_nomerge" can be passed on the kernel 295 command line. 296 297config SLAB_FREELIST_RANDOM 298 bool "Randomize slab freelist" 299 depends on SLAB || (SLUB && !SLUB_TINY) 300 help 301 Randomizes the freelist order used on creating new pages. This 302 security feature reduces the predictability of the kernel slab 303 allocator against heap overflows. 304 305config SLAB_FREELIST_HARDENED 306 bool "Harden slab freelist metadata" 307 depends on SLAB || (SLUB && !SLUB_TINY) 308 help 309 Many kernel heap attacks try to target slab cache metadata and 310 other infrastructure. This options makes minor performance 311 sacrifices to harden the kernel slab allocator against common 312 freelist exploit methods. Some slab implementations have more 313 sanity-checking than others. This option is most effective with 314 CONFIG_SLUB. 315 316config SLUB_STATS 317 default n 318 bool "Enable SLUB performance statistics" 319 depends on SLUB && SYSFS && !SLUB_TINY 320 help 321 SLUB statistics are useful to debug SLUBs allocation behavior in 322 order find ways to optimize the allocator. This should never be 323 enabled for production use since keeping statistics slows down 324 the allocator by a few percentage points. The slabinfo command 325 supports the determination of the most active slabs to figure 326 out which slabs are relevant to a particular load. 327 Try running: slabinfo -DA 328 329config SLUB_CPU_PARTIAL 330 default y 331 depends on SLUB && SMP && !SLUB_TINY 332 bool "SLUB per cpu partial cache" 333 help 334 Per cpu partial caches accelerate objects allocation and freeing 335 that is local to a processor at the price of more indeterminism 336 in the latency of the free. On overflow these caches will be cleared 337 which requires the taking of locks that may cause latency spikes. 338 Typically one would choose no for a realtime system. 339 340config RANDOM_KMALLOC_CACHES 341 default n 342 depends on SLUB && !SLUB_TINY 343 bool "Randomize slab caches for normal kmalloc" 344 help 345 A hardening feature that creates multiple copies of slab caches for 346 normal kmalloc allocation and makes kmalloc randomly pick one based 347 on code address, which makes the attackers more difficult to spray 348 vulnerable memory objects on the heap for the purpose of exploiting 349 memory vulnerabilities. 350 351 Currently the number of copies is set to 16, a reasonably large value 352 that effectively diverges the memory objects allocated for different 353 subsystems or modules into different caches, at the expense of a 354 limited degree of memory and CPU overhead that relates to hardware and 355 system workload. 356 357endmenu # SLAB allocator options 358 359config SHUFFLE_PAGE_ALLOCATOR 360 bool "Page allocator randomization" 361 default SLAB_FREELIST_RANDOM && ACPI_NUMA 362 help 363 Randomization of the page allocator improves the average 364 utilization of a direct-mapped memory-side-cache. See section 365 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI 366 6.2a specification for an example of how a platform advertises 367 the presence of a memory-side-cache. There are also incidental 368 security benefits as it reduces the predictability of page 369 allocations to compliment SLAB_FREELIST_RANDOM, but the 370 default granularity of shuffling on the MAX_ORDER i.e, 10th 371 order of pages is selected based on cache utilization benefits 372 on x86. 373 374 While the randomization improves cache utilization it may 375 negatively impact workloads on platforms without a cache. For 376 this reason, by default, the randomization is enabled only 377 after runtime detection of a direct-mapped memory-side-cache. 378 Otherwise, the randomization may be force enabled with the 379 'page_alloc.shuffle' kernel command line parameter. 380 381 Say Y if unsure. 382 383config COMPAT_BRK 384 bool "Disable heap randomization" 385 default y 386 help 387 Randomizing heap placement makes heap exploits harder, but it 388 also breaks ancient binaries (including anything libc5 based). 389 This option changes the bootup default to heap randomization 390 disabled, and can be overridden at runtime by setting 391 /proc/sys/kernel/randomize_va_space to 2. 392 393 On non-ancient distros (post-2000 ones) N is usually a safe choice. 394 395config MMAP_ALLOW_UNINITIALIZED 396 bool "Allow mmapped anonymous memory to be uninitialized" 397 depends on EXPERT && !MMU 398 default n 399 help 400 Normally, and according to the Linux spec, anonymous memory obtained 401 from mmap() has its contents cleared before it is passed to 402 userspace. Enabling this config option allows you to request that 403 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 404 providing a huge performance boost. If this option is not enabled, 405 then the flag will be ignored. 406 407 This is taken advantage of by uClibc's malloc(), and also by 408 ELF-FDPIC binfmt's brk and stack allocator. 409 410 Because of the obvious security issues, this option should only be 411 enabled on embedded devices where you control what is run in 412 userspace. Since that isn't generally a problem on no-MMU systems, 413 it is normally safe to say Y here. 414 415 See Documentation/admin-guide/mm/nommu-mmap.rst for more information. 416 417config SELECT_MEMORY_MODEL 418 def_bool y 419 depends on ARCH_SELECT_MEMORY_MODEL 420 421choice 422 prompt "Memory model" 423 depends on SELECT_MEMORY_MODEL 424 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT 425 default FLATMEM_MANUAL 426 help 427 This option allows you to change some of the ways that 428 Linux manages its memory internally. Most users will 429 only have one option here selected by the architecture 430 configuration. This is normal. 431 432config FLATMEM_MANUAL 433 bool "Flat Memory" 434 depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE 435 help 436 This option is best suited for non-NUMA systems with 437 flat address space. The FLATMEM is the most efficient 438 system in terms of performance and resource consumption 439 and it is the best option for smaller systems. 440 441 For systems that have holes in their physical address 442 spaces and for features like NUMA and memory hotplug, 443 choose "Sparse Memory". 444 445 If unsure, choose this option (Flat Memory) over any other. 446 447config SPARSEMEM_MANUAL 448 bool "Sparse Memory" 449 depends on ARCH_SPARSEMEM_ENABLE 450 help 451 This will be the only option for some systems, including 452 memory hot-plug systems. This is normal. 453 454 This option provides efficient support for systems with 455 holes is their physical address space and allows memory 456 hot-plug and hot-remove. 457 458 If unsure, choose "Flat Memory" over this option. 459 460endchoice 461 462config SPARSEMEM 463 def_bool y 464 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL 465 466config FLATMEM 467 def_bool y 468 depends on !SPARSEMEM || FLATMEM_MANUAL 469 470# 471# SPARSEMEM_EXTREME (which is the default) does some bootmem 472# allocations when sparse_init() is called. If this cannot 473# be done on your architecture, select this option. However, 474# statically allocating the mem_section[] array can potentially 475# consume vast quantities of .bss, so be careful. 476# 477# This option will also potentially produce smaller runtime code 478# with gcc 3.4 and later. 479# 480config SPARSEMEM_STATIC 481 bool 482 483# 484# Architecture platforms which require a two level mem_section in SPARSEMEM 485# must select this option. This is usually for architecture platforms with 486# an extremely sparse physical address space. 487# 488config SPARSEMEM_EXTREME 489 def_bool y 490 depends on SPARSEMEM && !SPARSEMEM_STATIC 491 492config SPARSEMEM_VMEMMAP_ENABLE 493 bool 494 495config SPARSEMEM_VMEMMAP 496 bool "Sparse Memory virtual memmap" 497 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE 498 default y 499 help 500 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise 501 pfn_to_page and page_to_pfn operations. This is the most 502 efficient option when sufficient kernel resources are available. 503# 504# Select this config option from the architecture Kconfig, if it is preferred 505# to enable the feature of HugeTLB/dev_dax vmemmap optimization. 506# 507config ARCH_WANT_OPTIMIZE_DAX_VMEMMAP 508 bool 509 510config ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP 511 bool 512 513config HAVE_MEMBLOCK_PHYS_MAP 514 bool 515 516config HAVE_FAST_GUP 517 depends on MMU 518 bool 519 520# Don't discard allocated memory used to track "memory" and "reserved" memblocks 521# after early boot, so it can still be used to test for validity of memory. 522# Also, memblocks are updated with memory hot(un)plug. 523config ARCH_KEEP_MEMBLOCK 524 bool 525 526# Keep arch NUMA mapping infrastructure post-init. 527config NUMA_KEEP_MEMINFO 528 bool 529 530config MEMORY_ISOLATION 531 bool 532 533# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked 534# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via 535# /dev/mem. 536config EXCLUSIVE_SYSTEM_RAM 537 def_bool y 538 depends on !DEVMEM || STRICT_DEVMEM 539 540# 541# Only be set on architectures that have completely implemented memory hotplug 542# feature. If you are not sure, don't touch it. 543# 544config HAVE_BOOTMEM_INFO_NODE 545 def_bool n 546 547config ARCH_ENABLE_MEMORY_HOTPLUG 548 bool 549 550config ARCH_ENABLE_MEMORY_HOTREMOVE 551 bool 552 553# eventually, we can have this option just 'select SPARSEMEM' 554menuconfig MEMORY_HOTPLUG 555 bool "Memory hotplug" 556 select MEMORY_ISOLATION 557 depends on SPARSEMEM 558 depends on ARCH_ENABLE_MEMORY_HOTPLUG 559 depends on 64BIT 560 select NUMA_KEEP_MEMINFO if NUMA 561 562if MEMORY_HOTPLUG 563 564config MEMORY_HOTPLUG_DEFAULT_ONLINE 565 bool "Online the newly added memory blocks by default" 566 depends on MEMORY_HOTPLUG 567 help 568 This option sets the default policy setting for memory hotplug 569 onlining policy (/sys/devices/system/memory/auto_online_blocks) which 570 determines what happens to newly added memory regions. Policy setting 571 can always be changed at runtime. 572 See Documentation/admin-guide/mm/memory-hotplug.rst for more information. 573 574 Say Y here if you want all hot-plugged memory blocks to appear in 575 'online' state by default. 576 Say N here if you want the default policy to keep all hot-plugged 577 memory blocks in 'offline' state. 578 579config MEMORY_HOTREMOVE 580 bool "Allow for memory hot remove" 581 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) 582 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE 583 depends on MIGRATION 584 585config MHP_MEMMAP_ON_MEMORY 586 def_bool y 587 depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP 588 depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE 589 590endif # MEMORY_HOTPLUG 591 592config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE 593 bool 594 595# Heavily threaded applications may benefit from splitting the mm-wide 596# page_table_lock, so that faults on different parts of the user address 597# space can be handled with less contention: split it at this NR_CPUS. 598# Default to 4 for wider testing, though 8 might be more appropriate. 599# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. 600# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. 601# SPARC32 allocates multiple pte tables within a single page, and therefore 602# a per-page lock leads to problems when multiple tables need to be locked 603# at the same time (e.g. copy_page_range()). 604# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. 605# 606config SPLIT_PTLOCK_CPUS 607 int 608 default "999999" if !MMU 609 default "999999" if ARM && !CPU_CACHE_VIPT 610 default "999999" if PARISC && !PA20 611 default "999999" if SPARC32 612 default "4" 613 614config ARCH_ENABLE_SPLIT_PMD_PTLOCK 615 bool 616 617# 618# support for memory balloon 619config MEMORY_BALLOON 620 bool 621 622# 623# support for memory balloon compaction 624config BALLOON_COMPACTION 625 bool "Allow for balloon memory compaction/migration" 626 def_bool y 627 depends on COMPACTION && MEMORY_BALLOON 628 help 629 Memory fragmentation introduced by ballooning might reduce 630 significantly the number of 2MB contiguous memory blocks that can be 631 used within a guest, thus imposing performance penalties associated 632 with the reduced number of transparent huge pages that could be used 633 by the guest workload. Allowing the compaction & migration for memory 634 pages enlisted as being part of memory balloon devices avoids the 635 scenario aforementioned and helps improving memory defragmentation. 636 637# 638# support for memory compaction 639config COMPACTION 640 bool "Allow for memory compaction" 641 def_bool y 642 select MIGRATION 643 depends on MMU 644 help 645 Compaction is the only memory management component to form 646 high order (larger physically contiguous) memory blocks 647 reliably. The page allocator relies on compaction heavily and 648 the lack of the feature can lead to unexpected OOM killer 649 invocations for high order memory requests. You shouldn't 650 disable this option unless there really is a strong reason for 651 it and then we would be really interested to hear about that at 652 linux-mm@kvack.org. 653 654config COMPACT_UNEVICTABLE_DEFAULT 655 int 656 depends on COMPACTION 657 default 0 if PREEMPT_RT 658 default 1 659 660# 661# support for free page reporting 662config PAGE_REPORTING 663 bool "Free page reporting" 664 def_bool n 665 help 666 Free page reporting allows for the incremental acquisition of 667 free pages from the buddy allocator for the purpose of reporting 668 those pages to another entity, such as a hypervisor, so that the 669 memory can be freed within the host for other uses. 670 671# 672# support for page migration 673# 674config MIGRATION 675 bool "Page migration" 676 def_bool y 677 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU 678 help 679 Allows the migration of the physical location of pages of processes 680 while the virtual addresses are not changed. This is useful in 681 two situations. The first is on NUMA systems to put pages nearer 682 to the processors accessing. The second is when allocating huge 683 pages as migration can relocate pages to satisfy a huge page 684 allocation instead of reclaiming. 685 686config DEVICE_MIGRATION 687 def_bool MIGRATION && ZONE_DEVICE 688 689config ARCH_ENABLE_HUGEPAGE_MIGRATION 690 bool 691 692config ARCH_ENABLE_THP_MIGRATION 693 bool 694 695config HUGETLB_PAGE_SIZE_VARIABLE 696 def_bool n 697 help 698 Allows the pageblock_order value to be dynamic instead of just standard 699 HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available 700 on a platform. 701 702 Note that the pageblock_order cannot exceed MAX_ORDER and will be 703 clamped down to MAX_ORDER. 704 705config CONTIG_ALLOC 706 def_bool (MEMORY_ISOLATION && COMPACTION) || CMA 707 708config PCP_BATCH_SCALE_MAX 709 int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" 710 default 5 711 range 0 6 712 help 713 In page allocator, PCP (Per-CPU pageset) is refilled and drained in 714 batches. The batch number is scaled automatically to improve page 715 allocation/free throughput. But too large scale factor may hurt 716 latency. This option sets the upper limit of scale factor to limit 717 the maximum latency. 718 719config PHYS_ADDR_T_64BIT 720 def_bool 64BIT 721 722config BOUNCE 723 bool "Enable bounce buffers" 724 default y 725 depends on BLOCK && MMU && HIGHMEM 726 help 727 Enable bounce buffers for devices that cannot access the full range of 728 memory available to the CPU. Enabled by default when HIGHMEM is 729 selected, but you may say n to override this. 730 731config MMU_NOTIFIER 732 bool 733 select INTERVAL_TREE 734 735config KSM 736 bool "Enable KSM for page merging" 737 depends on MMU 738 select XXHASH 739 help 740 Enable Kernel Samepage Merging: KSM periodically scans those areas 741 of an application's address space that an app has advised may be 742 mergeable. When it finds pages of identical content, it replaces 743 the many instances by a single page with that content, so 744 saving memory until one or another app needs to modify the content. 745 Recommended for use with KVM, or with other duplicative applications. 746 See Documentation/mm/ksm.rst for more information: KSM is inactive 747 until a program has madvised that an area is MADV_MERGEABLE, and 748 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). 749 750config DEFAULT_MMAP_MIN_ADDR 751 int "Low address space to protect from user allocation" 752 depends on MMU 753 default 4096 754 help 755 This is the portion of low virtual memory which should be protected 756 from userspace allocation. Keeping a user from writing to low pages 757 can help reduce the impact of kernel NULL pointer bugs. 758 759 For most ia64, ppc64 and x86 users with lots of address space 760 a value of 65536 is reasonable and should cause no problems. 761 On arm and other archs it should not be higher than 32768. 762 Programs which use vm86 functionality or have some need to map 763 this low address space will need CAP_SYS_RAWIO or disable this 764 protection by setting the value to 0. 765 766 This value can be changed after boot using the 767 /proc/sys/vm/mmap_min_addr tunable. 768 769config ARCH_SUPPORTS_MEMORY_FAILURE 770 bool 771 772config MEMORY_FAILURE 773 depends on MMU 774 depends on ARCH_SUPPORTS_MEMORY_FAILURE 775 bool "Enable recovery from hardware memory errors" 776 select MEMORY_ISOLATION 777 select RAS 778 help 779 Enables code to recover from some memory failures on systems 780 with MCA recovery. This allows a system to continue running 781 even when some of its memory has uncorrected errors. This requires 782 special hardware support and typically ECC memory. 783 784config HWPOISON_INJECT 785 tristate "HWPoison pages injector" 786 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS 787 select PROC_PAGE_MONITOR 788 789config NOMMU_INITIAL_TRIM_EXCESS 790 int "Turn on mmap() excess space trimming before booting" 791 depends on !MMU 792 default 1 793 help 794 The NOMMU mmap() frequently needs to allocate large contiguous chunks 795 of memory on which to store mappings, but it can only ask the system 796 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently 797 more than it requires. To deal with this, mmap() is able to trim off 798 the excess and return it to the allocator. 799 800 If trimming is enabled, the excess is trimmed off and returned to the 801 system allocator, which can cause extra fragmentation, particularly 802 if there are a lot of transient processes. 803 804 If trimming is disabled, the excess is kept, but not used, which for 805 long-term mappings means that the space is wasted. 806 807 Trimming can be dynamically controlled through a sysctl option 808 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of 809 excess pages there must be before trimming should occur, or zero if 810 no trimming is to occur. 811 812 This option specifies the initial value of this option. The default 813 of 1 says that all excess pages should be trimmed. 814 815 See Documentation/admin-guide/mm/nommu-mmap.rst for more information. 816 817config ARCH_WANT_GENERAL_HUGETLB 818 bool 819 820config ARCH_WANTS_THP_SWAP 821 def_bool n 822 823menuconfig TRANSPARENT_HUGEPAGE 824 bool "Transparent Hugepage Support" 825 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT 826 select COMPACTION 827 select XARRAY_MULTI 828 help 829 Transparent Hugepages allows the kernel to use huge pages and 830 huge tlb transparently to the applications whenever possible. 831 This feature can improve computing performance to certain 832 applications by speeding up page faults during memory 833 allocation, by reducing the number of tlb misses and by speeding 834 up the pagetable walking. 835 836 If memory constrained on embedded, you may want to say N. 837 838if TRANSPARENT_HUGEPAGE 839 840choice 841 prompt "Transparent Hugepage Support sysfs defaults" 842 depends on TRANSPARENT_HUGEPAGE 843 default TRANSPARENT_HUGEPAGE_ALWAYS 844 help 845 Selects the sysfs defaults for Transparent Hugepage Support. 846 847 config TRANSPARENT_HUGEPAGE_ALWAYS 848 bool "always" 849 help 850 Enabling Transparent Hugepage always, can increase the 851 memory footprint of applications without a guaranteed 852 benefit but it will work automatically for all applications. 853 854 config TRANSPARENT_HUGEPAGE_MADVISE 855 bool "madvise" 856 help 857 Enabling Transparent Hugepage madvise, will only provide a 858 performance improvement benefit to the applications using 859 madvise(MADV_HUGEPAGE) but it won't risk to increase the 860 memory footprint of applications without a guaranteed 861 benefit. 862endchoice 863 864config THP_SWAP 865 def_bool y 866 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT 867 help 868 Swap transparent huge pages in one piece, without splitting. 869 XXX: For now, swap cluster backing transparent huge page 870 will be split after swapout. 871 872 For selection by architectures with reasonable THP sizes. 873 874config READ_ONLY_THP_FOR_FS 875 bool "Read-only THP for filesystems (EXPERIMENTAL)" 876 depends on TRANSPARENT_HUGEPAGE && SHMEM 877 878 help 879 Allow khugepaged to put read-only file-backed pages in THP. 880 881 This is marked experimental because it is a new feature. Write 882 support of file THPs will be developed in the next few release 883 cycles. 884 885endif # TRANSPARENT_HUGEPAGE 886 887# 888# UP and nommu archs use km based percpu allocator 889# 890config NEED_PER_CPU_KM 891 depends on !SMP || !MMU 892 bool 893 default y 894 895config NEED_PER_CPU_EMBED_FIRST_CHUNK 896 bool 897 898config NEED_PER_CPU_PAGE_FIRST_CHUNK 899 bool 900 901config USE_PERCPU_NUMA_NODE_ID 902 bool 903 904config HAVE_SETUP_PER_CPU_AREA 905 bool 906 907config CMA 908 bool "Contiguous Memory Allocator" 909 depends on MMU 910 select MIGRATION 911 select MEMORY_ISOLATION 912 help 913 This enables the Contiguous Memory Allocator which allows other 914 subsystems to allocate big physically-contiguous blocks of memory. 915 CMA reserves a region of memory and allows only movable pages to 916 be allocated from it. This way, the kernel can use the memory for 917 pagecache and when a subsystem requests for contiguous area, the 918 allocated pages are migrated away to serve the contiguous request. 919 920 If unsure, say "n". 921 922config CMA_DEBUG 923 bool "CMA debug messages (DEVELOPMENT)" 924 depends on DEBUG_KERNEL && CMA 925 help 926 Turns on debug messages in CMA. This produces KERN_DEBUG 927 messages for every CMA call as well as various messages while 928 processing calls such as dma_alloc_from_contiguous(). 929 This option does not affect warning and error messages. 930 931config CMA_DEBUGFS 932 bool "CMA debugfs interface" 933 depends on CMA && DEBUG_FS 934 help 935 Turns on the DebugFS interface for CMA. 936 937config CMA_SYSFS 938 bool "CMA information through sysfs interface" 939 depends on CMA && SYSFS 940 help 941 This option exposes some sysfs attributes to get information 942 from CMA. 943 944config CMA_AREAS 945 int "Maximum count of the CMA areas" 946 depends on CMA 947 default 19 if NUMA 948 default 7 949 help 950 CMA allows to create CMA areas for particular purpose, mainly, 951 used as device private area. This parameter sets the maximum 952 number of CMA area in the system. 953 954 If unsure, leave the default value "7" in UMA and "19" in NUMA. 955 956config MEM_SOFT_DIRTY 957 bool "Track memory changes" 958 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS 959 select PROC_PAGE_MONITOR 960 help 961 This option enables memory changes tracking by introducing a 962 soft-dirty bit on pte-s. This bit it set when someone writes 963 into a page just as regular dirty bit, but unlike the latter 964 it can be cleared by hands. 965 966 See Documentation/admin-guide/mm/soft-dirty.rst for more details. 967 968config GENERIC_EARLY_IOREMAP 969 bool 970 971config STACK_MAX_DEFAULT_SIZE_MB 972 int "Default maximum user stack size for 32-bit processes (MB)" 973 default 100 974 range 8 2048 975 depends on STACK_GROWSUP && (!64BIT || COMPAT) 976 help 977 This is the maximum stack size in Megabytes in the VM layout of 32-bit 978 user processes when the stack grows upwards (currently only on parisc 979 arch) when the RLIMIT_STACK hard limit is unlimited. 980 981 A sane initial value is 100 MB. 982 983config DEFERRED_STRUCT_PAGE_INIT 984 bool "Defer initialisation of struct pages to kthreads" 985 depends on SPARSEMEM 986 depends on !NEED_PER_CPU_KM 987 depends on 64BIT 988 select PADATA 989 help 990 Ordinarily all struct pages are initialised during early boot in a 991 single thread. On very large machines this can take a considerable 992 amount of time. If this option is set, large machines will bring up 993 a subset of memmap at boot and then initialise the rest in parallel. 994 This has a potential performance impact on tasks running early in the 995 lifetime of the system until these kthreads finish the 996 initialisation. 997 998config PAGE_IDLE_FLAG 999 bool 1000 select PAGE_EXTENSION if !64BIT 1001 help 1002 This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed 1003 bit writers can set the state of the bit in the flags so that PTE 1004 Accessed bit readers may avoid disturbance. 1005 1006config IDLE_PAGE_TRACKING 1007 bool "Enable idle page tracking" 1008 depends on SYSFS && MMU 1009 select PAGE_IDLE_FLAG 1010 help 1011 This feature allows to estimate the amount of user pages that have 1012 not been touched during a given period of time. This information can 1013 be useful to tune memory cgroup limits and/or for job placement 1014 within a compute cluster. 1015 1016 See Documentation/admin-guide/mm/idle_page_tracking.rst for 1017 more details. 1018 1019config ARCH_HAS_CACHE_LINE_SIZE 1020 bool 1021 1022config ARCH_HAS_CURRENT_STACK_POINTER 1023 bool 1024 help 1025 In support of HARDENED_USERCOPY performing stack variable lifetime 1026 checking, an architecture-agnostic way to find the stack pointer 1027 is needed. Once an architecture defines an unsigned long global 1028 register alias named "current_stack_pointer", this config can be 1029 selected. 1030 1031config ARCH_HAS_PTE_DEVMAP 1032 bool 1033 1034config ARCH_HAS_ZONE_DMA_SET 1035 bool 1036 1037config ZONE_DMA 1038 bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET 1039 default y if ARM64 || X86 1040 1041config ZONE_DMA32 1042 bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET 1043 depends on !X86_32 1044 default y if ARM64 1045 1046config ZONE_DEVICE 1047 bool "Device memory (pmem, HMM, etc...) hotplug support" 1048 depends on MEMORY_HOTPLUG 1049 depends on MEMORY_HOTREMOVE 1050 depends on SPARSEMEM_VMEMMAP 1051 depends on ARCH_HAS_PTE_DEVMAP 1052 select XARRAY_MULTI 1053 1054 help 1055 Device memory hotplug support allows for establishing pmem, 1056 or other device driver discovered memory regions, in the 1057 memmap. This allows pfn_to_page() lookups of otherwise 1058 "device-physical" addresses which is needed for using a DAX 1059 mapping in an O_DIRECT operation, among other things. 1060 1061 If FS_DAX is enabled, then say Y. 1062 1063# 1064# Helpers to mirror range of the CPU page tables of a process into device page 1065# tables. 1066# 1067config HMM_MIRROR 1068 bool 1069 depends on MMU 1070 1071config GET_FREE_REGION 1072 depends on SPARSEMEM 1073 bool 1074 1075config DEVICE_PRIVATE 1076 bool "Unaddressable device memory (GPU memory, ...)" 1077 depends on ZONE_DEVICE 1078 select GET_FREE_REGION 1079 1080 help 1081 Allows creation of struct pages to represent unaddressable device 1082 memory; i.e., memory that is only accessible from the device (or 1083 group of devices). You likely also want to select HMM_MIRROR. 1084 1085config VMAP_PFN 1086 bool 1087 1088config ARCH_USES_HIGH_VMA_FLAGS 1089 bool 1090config ARCH_HAS_PKEYS 1091 bool 1092 1093config ARCH_USES_PG_ARCH_X 1094 bool 1095 help 1096 Enable the definition of PG_arch_x page flags with x > 1. Only 1097 suitable for 64-bit architectures with CONFIG_FLATMEM or 1098 CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be 1099 enough room for additional bits in page->flags. 1100 1101config VM_EVENT_COUNTERS 1102 default y 1103 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1104 help 1105 VM event counters are needed for event counts to be shown. 1106 This option allows the disabling of the VM event counters 1107 on EXPERT systems. /proc/vmstat will only show page counts 1108 if VM event counters are disabled. 1109 1110config PERCPU_STATS 1111 bool "Collect percpu memory statistics" 1112 help 1113 This feature collects and exposes statistics via debugfs. The 1114 information includes global and per chunk statistics, which can 1115 be used to help understand percpu memory usage. 1116 1117config GUP_TEST 1118 bool "Enable infrastructure for get_user_pages()-related unit tests" 1119 depends on DEBUG_FS 1120 help 1121 Provides /sys/kernel/debug/gup_test, which in turn provides a way 1122 to make ioctl calls that can launch kernel-based unit tests for 1123 the get_user_pages*() and pin_user_pages*() family of API calls. 1124 1125 These tests include benchmark testing of the _fast variants of 1126 get_user_pages*() and pin_user_pages*(), as well as smoke tests of 1127 the non-_fast variants. 1128 1129 There is also a sub-test that allows running dump_page() on any 1130 of up to eight pages (selected by command line args) within the 1131 range of user-space addresses. These pages are either pinned via 1132 pin_user_pages*(), or pinned via get_user_pages*(), as specified 1133 by other command line arguments. 1134 1135 See tools/testing/selftests/mm/gup_test.c 1136 1137comment "GUP_TEST needs to have DEBUG_FS enabled" 1138 depends on !GUP_TEST && !DEBUG_FS 1139 1140config GUP_GET_PXX_LOW_HIGH 1141 bool 1142 1143config DMAPOOL_TEST 1144 tristate "Enable a module to run time tests on dma_pool" 1145 depends on HAS_DMA 1146 help 1147 Provides a test module that will allocate and free many blocks of 1148 various sizes and report how long it takes. This is intended to 1149 provide a consistent way to measure how changes to the 1150 dma_pool_alloc/free routines affect performance. 1151 1152config ARCH_HAS_PTE_SPECIAL 1153 bool 1154 1155# 1156# Some architectures require a special hugepage directory format that is 1157# required to support multiple hugepage sizes. For example a4fe3ce76 1158# "powerpc/mm: Allow more flexible layouts for hugepage pagetables" 1159# introduced it on powerpc. This allows for a more flexible hugepage 1160# pagetable layouts. 1161# 1162config ARCH_HAS_HUGEPD 1163 bool 1164 1165config MAPPING_DIRTY_HELPERS 1166 bool 1167 1168config KMAP_LOCAL 1169 bool 1170 1171config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY 1172 bool 1173 1174# struct io_mapping based helper. Selected by drivers that need them 1175config IO_MAPPING 1176 bool 1177 1178config MEMFD_CREATE 1179 bool "Enable memfd_create() system call" if EXPERT 1180 1181config SECRETMEM 1182 default y 1183 bool "Enable memfd_secret() system call" if EXPERT 1184 depends on ARCH_HAS_SET_DIRECT_MAP 1185 help 1186 Enable the memfd_secret() system call with the ability to create 1187 memory areas visible only in the context of the owning process and 1188 not mapped to other processes and other kernel page tables. 1189 1190config ANON_VMA_NAME 1191 bool "Anonymous VMA name support" 1192 depends on PROC_FS && ADVISE_SYSCALLS && MMU 1193 1194 help 1195 Allow naming anonymous virtual memory areas. 1196 1197 This feature allows assigning names to virtual memory areas. Assigned 1198 names can be later retrieved from /proc/pid/maps and /proc/pid/smaps 1199 and help identifying individual anonymous memory areas. 1200 Assigning a name to anonymous virtual memory area might prevent that 1201 area from being merged with adjacent virtual memory areas due to the 1202 difference in their name. 1203 1204config HAVE_ARCH_USERFAULTFD_WP 1205 bool 1206 help 1207 Arch has userfaultfd write protection support 1208 1209config HAVE_ARCH_USERFAULTFD_MINOR 1210 bool 1211 help 1212 Arch has userfaultfd minor fault support 1213 1214menuconfig USERFAULTFD 1215 bool "Enable userfaultfd() system call" 1216 depends on MMU 1217 help 1218 Enable the userfaultfd() system call that allows to intercept and 1219 handle page faults in userland. 1220 1221if USERFAULTFD 1222config PTE_MARKER_UFFD_WP 1223 bool "Userfaultfd write protection support for shmem/hugetlbfs" 1224 default y 1225 depends on HAVE_ARCH_USERFAULTFD_WP 1226 1227 help 1228 Allows to create marker PTEs for userfaultfd write protection 1229 purposes. It is required to enable userfaultfd write protection on 1230 file-backed memory types like shmem and hugetlbfs. 1231endif # USERFAULTFD 1232 1233# multi-gen LRU { 1234config LRU_GEN 1235 bool "Multi-Gen LRU" 1236 depends on MMU 1237 # make sure folio->flags has enough spare bits 1238 depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP 1239 help 1240 A high performance LRU implementation to overcommit memory. See 1241 Documentation/admin-guide/mm/multigen_lru.rst for details. 1242 1243config LRU_GEN_ENABLED 1244 bool "Enable by default" 1245 depends on LRU_GEN 1246 help 1247 This option enables the multi-gen LRU by default. 1248 1249config LRU_GEN_STATS 1250 bool "Full stats for debugging" 1251 depends on LRU_GEN 1252 help 1253 Do not enable this option unless you plan to look at historical stats 1254 from evicted generations for debugging purpose. 1255 1256 This option has a per-memcg and per-node memory overhead. 1257# } 1258 1259config ARCH_SUPPORTS_PER_VMA_LOCK 1260 def_bool n 1261 1262config PER_VMA_LOCK 1263 def_bool y 1264 depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP 1265 help 1266 Allow per-vma locking during page fault handling. 1267 1268 This feature allows locking each virtual memory area separately when 1269 handling page faults instead of taking mmap_lock. 1270 1271config LOCK_MM_AND_FIND_VMA 1272 bool 1273 depends on !STACK_GROWSUP 1274 1275source "mm/damon/Kconfig" 1276 1277endmenu 1278