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 FRONTSWAP 29 select CRYPTO 30 select ZPOOL 31 help 32 A lightweight compressed cache for swap pages. It takes 33 pages that are in the process of being swapped out and attempts to 34 compress them into a dynamically allocated RAM-based memory pool. 35 This can result in a significant I/O reduction on swap device and, 36 in the case where decompressing from RAM is faster than swap device 37 reads, can also improve workload performance. 38 39config ZSWAP_DEFAULT_ON 40 bool "Enable the compressed cache for swap pages by default" 41 depends on ZSWAP 42 help 43 If selected, the compressed cache for swap pages will be enabled 44 at boot, otherwise it will be disabled. 45 46 The selection made here can be overridden by using the kernel 47 command line 'zswap.enabled=' option. 48 49choice 50 prompt "Default compressor" 51 depends on ZSWAP 52 default ZSWAP_COMPRESSOR_DEFAULT_LZO 53 help 54 Selects the default compression algorithm for the compressed cache 55 for swap pages. 56 57 For an overview what kind of performance can be expected from 58 a particular compression algorithm please refer to the benchmarks 59 available at the following LWN page: 60 https://lwn.net/Articles/751795/ 61 62 If in doubt, select 'LZO'. 63 64 The selection made here can be overridden by using the kernel 65 command line 'zswap.compressor=' option. 66 67config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE 68 bool "Deflate" 69 select CRYPTO_DEFLATE 70 help 71 Use the Deflate algorithm as the default compression algorithm. 72 73config ZSWAP_COMPRESSOR_DEFAULT_LZO 74 bool "LZO" 75 select CRYPTO_LZO 76 help 77 Use the LZO algorithm as the default compression algorithm. 78 79config ZSWAP_COMPRESSOR_DEFAULT_842 80 bool "842" 81 select CRYPTO_842 82 help 83 Use the 842 algorithm as the default compression algorithm. 84 85config ZSWAP_COMPRESSOR_DEFAULT_LZ4 86 bool "LZ4" 87 select CRYPTO_LZ4 88 help 89 Use the LZ4 algorithm as the default compression algorithm. 90 91config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC 92 bool "LZ4HC" 93 select CRYPTO_LZ4HC 94 help 95 Use the LZ4HC algorithm as the default compression algorithm. 96 97config ZSWAP_COMPRESSOR_DEFAULT_ZSTD 98 bool "zstd" 99 select CRYPTO_ZSTD 100 help 101 Use the zstd algorithm as the default compression algorithm. 102endchoice 103 104config ZSWAP_COMPRESSOR_DEFAULT 105 string 106 depends on ZSWAP 107 default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE 108 default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO 109 default "842" if ZSWAP_COMPRESSOR_DEFAULT_842 110 default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4 111 default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC 112 default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD 113 default "" 114 115choice 116 prompt "Default allocator" 117 depends on ZSWAP 118 default ZSWAP_ZPOOL_DEFAULT_ZBUD 119 help 120 Selects the default allocator for the compressed cache for 121 swap pages. 122 The default is 'zbud' for compatibility, however please do 123 read the description of each of the allocators below before 124 making a right choice. 125 126 The selection made here can be overridden by using the kernel 127 command line 'zswap.zpool=' option. 128 129config ZSWAP_ZPOOL_DEFAULT_ZBUD 130 bool "zbud" 131 select ZBUD 132 help 133 Use the zbud allocator as the default allocator. 134 135config ZSWAP_ZPOOL_DEFAULT_Z3FOLD 136 bool "z3fold" 137 select Z3FOLD 138 help 139 Use the z3fold allocator as the default allocator. 140 141config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC 142 bool "zsmalloc" 143 select ZSMALLOC 144 help 145 Use the zsmalloc allocator as the default allocator. 146endchoice 147 148config ZSWAP_ZPOOL_DEFAULT 149 string 150 depends on ZSWAP 151 default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD 152 default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD 153 default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC 154 default "" 155 156config ZBUD 157 tristate "2:1 compression allocator (zbud)" 158 depends on ZSWAP 159 help 160 A special purpose allocator for storing compressed pages. 161 It is designed to store up to two compressed pages per physical 162 page. While this design limits storage density, it has simple and 163 deterministic reclaim properties that make it preferable to a higher 164 density approach when reclaim will be used. 165 166config Z3FOLD 167 tristate "3:1 compression allocator (z3fold)" 168 depends on ZSWAP 169 help 170 A special purpose allocator for storing compressed pages. 171 It is designed to store up to three compressed pages per physical 172 page. It is a ZBUD derivative so the simplicity and determinism are 173 still there. 174 175config ZSMALLOC 176 tristate 177 prompt "N:1 compression allocator (zsmalloc)" if ZSWAP 178 depends on MMU 179 help 180 zsmalloc is a slab-based memory allocator designed to store 181 pages of various compression levels efficiently. It achieves 182 the highest storage density with the least amount of fragmentation. 183 184config ZSMALLOC_STAT 185 bool "Export zsmalloc statistics" 186 depends on ZSMALLOC 187 select DEBUG_FS 188 help 189 This option enables code in the zsmalloc to collect various 190 statistics about what's happening in zsmalloc and exports that 191 information to userspace via debugfs. 192 If unsure, say N. 193 194menu "SLAB allocator options" 195 196choice 197 prompt "Choose SLAB allocator" 198 default SLUB 199 help 200 This option allows to select a slab allocator. 201 202config SLAB 203 bool "SLAB" 204 depends on !PREEMPT_RT 205 select HAVE_HARDENED_USERCOPY_ALLOCATOR 206 help 207 The regular slab allocator that is established and known to work 208 well in all environments. It organizes cache hot objects in 209 per cpu and per node queues. 210 211config SLUB 212 bool "SLUB (Unqueued Allocator)" 213 select HAVE_HARDENED_USERCOPY_ALLOCATOR 214 help 215 SLUB is a slab allocator that minimizes cache line usage 216 instead of managing queues of cached objects (SLAB approach). 217 Per cpu caching is realized using slabs of objects instead 218 of queues of objects. SLUB can use memory efficiently 219 and has enhanced diagnostics. SLUB is the default choice for 220 a slab allocator. 221 222config SLOB 223 depends on EXPERT 224 bool "SLOB (Simple Allocator)" 225 depends on !PREEMPT_RT 226 help 227 SLOB replaces the stock allocator with a drastically simpler 228 allocator. SLOB is generally more space efficient but 229 does not perform as well on large systems. 230 231endchoice 232 233config SLAB_MERGE_DEFAULT 234 bool "Allow slab caches to be merged" 235 default y 236 depends on SLAB || SLUB 237 help 238 For reduced kernel memory fragmentation, slab caches can be 239 merged when they share the same size and other characteristics. 240 This carries a risk of kernel heap overflows being able to 241 overwrite objects from merged caches (and more easily control 242 cache layout), which makes such heap attacks easier to exploit 243 by attackers. By keeping caches unmerged, these kinds of exploits 244 can usually only damage objects in the same cache. To disable 245 merging at runtime, "slab_nomerge" can be passed on the kernel 246 command line. 247 248config SLAB_FREELIST_RANDOM 249 bool "Randomize slab freelist" 250 depends on SLAB || SLUB 251 help 252 Randomizes the freelist order used on creating new pages. This 253 security feature reduces the predictability of the kernel slab 254 allocator against heap overflows. 255 256config SLAB_FREELIST_HARDENED 257 bool "Harden slab freelist metadata" 258 depends on SLAB || SLUB 259 help 260 Many kernel heap attacks try to target slab cache metadata and 261 other infrastructure. This options makes minor performance 262 sacrifices to harden the kernel slab allocator against common 263 freelist exploit methods. Some slab implementations have more 264 sanity-checking than others. This option is most effective with 265 CONFIG_SLUB. 266 267config SLUB_STATS 268 default n 269 bool "Enable SLUB performance statistics" 270 depends on SLUB && SYSFS 271 help 272 SLUB statistics are useful to debug SLUBs allocation behavior in 273 order find ways to optimize the allocator. This should never be 274 enabled for production use since keeping statistics slows down 275 the allocator by a few percentage points. The slabinfo command 276 supports the determination of the most active slabs to figure 277 out which slabs are relevant to a particular load. 278 Try running: slabinfo -DA 279 280config SLUB_CPU_PARTIAL 281 default y 282 depends on SLUB && SMP 283 bool "SLUB per cpu partial cache" 284 help 285 Per cpu partial caches accelerate objects allocation and freeing 286 that is local to a processor at the price of more indeterminism 287 in the latency of the free. On overflow these caches will be cleared 288 which requires the taking of locks that may cause latency spikes. 289 Typically one would choose no for a realtime system. 290 291endmenu # SLAB allocator options 292 293config SHUFFLE_PAGE_ALLOCATOR 294 bool "Page allocator randomization" 295 default SLAB_FREELIST_RANDOM && ACPI_NUMA 296 help 297 Randomization of the page allocator improves the average 298 utilization of a direct-mapped memory-side-cache. See section 299 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI 300 6.2a specification for an example of how a platform advertises 301 the presence of a memory-side-cache. There are also incidental 302 security benefits as it reduces the predictability of page 303 allocations to compliment SLAB_FREELIST_RANDOM, but the 304 default granularity of shuffling on the "MAX_ORDER - 1" i.e, 305 10th order of pages is selected based on cache utilization 306 benefits on x86. 307 308 While the randomization improves cache utilization it may 309 negatively impact workloads on platforms without a cache. For 310 this reason, by default, the randomization is enabled only 311 after runtime detection of a direct-mapped memory-side-cache. 312 Otherwise, the randomization may be force enabled with the 313 'page_alloc.shuffle' kernel command line parameter. 314 315 Say Y if unsure. 316 317config COMPAT_BRK 318 bool "Disable heap randomization" 319 default y 320 help 321 Randomizing heap placement makes heap exploits harder, but it 322 also breaks ancient binaries (including anything libc5 based). 323 This option changes the bootup default to heap randomization 324 disabled, and can be overridden at runtime by setting 325 /proc/sys/kernel/randomize_va_space to 2. 326 327 On non-ancient distros (post-2000 ones) N is usually a safe choice. 328 329config MMAP_ALLOW_UNINITIALIZED 330 bool "Allow mmapped anonymous memory to be uninitialized" 331 depends on EXPERT && !MMU 332 default n 333 help 334 Normally, and according to the Linux spec, anonymous memory obtained 335 from mmap() has its contents cleared before it is passed to 336 userspace. Enabling this config option allows you to request that 337 mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus 338 providing a huge performance boost. If this option is not enabled, 339 then the flag will be ignored. 340 341 This is taken advantage of by uClibc's malloc(), and also by 342 ELF-FDPIC binfmt's brk and stack allocator. 343 344 Because of the obvious security issues, this option should only be 345 enabled on embedded devices where you control what is run in 346 userspace. Since that isn't generally a problem on no-MMU systems, 347 it is normally safe to say Y here. 348 349 See Documentation/admin-guide/mm/nommu-mmap.rst for more information. 350 351config SELECT_MEMORY_MODEL 352 def_bool y 353 depends on ARCH_SELECT_MEMORY_MODEL 354 355choice 356 prompt "Memory model" 357 depends on SELECT_MEMORY_MODEL 358 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT 359 default FLATMEM_MANUAL 360 help 361 This option allows you to change some of the ways that 362 Linux manages its memory internally. Most users will 363 only have one option here selected by the architecture 364 configuration. This is normal. 365 366config FLATMEM_MANUAL 367 bool "Flat Memory" 368 depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE 369 help 370 This option is best suited for non-NUMA systems with 371 flat address space. The FLATMEM is the most efficient 372 system in terms of performance and resource consumption 373 and it is the best option for smaller systems. 374 375 For systems that have holes in their physical address 376 spaces and for features like NUMA and memory hotplug, 377 choose "Sparse Memory". 378 379 If unsure, choose this option (Flat Memory) over any other. 380 381config SPARSEMEM_MANUAL 382 bool "Sparse Memory" 383 depends on ARCH_SPARSEMEM_ENABLE 384 help 385 This will be the only option for some systems, including 386 memory hot-plug systems. This is normal. 387 388 This option provides efficient support for systems with 389 holes is their physical address space and allows memory 390 hot-plug and hot-remove. 391 392 If unsure, choose "Flat Memory" over this option. 393 394endchoice 395 396config SPARSEMEM 397 def_bool y 398 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL 399 400config FLATMEM 401 def_bool y 402 depends on !SPARSEMEM || FLATMEM_MANUAL 403 404# 405# SPARSEMEM_EXTREME (which is the default) does some bootmem 406# allocations when sparse_init() is called. If this cannot 407# be done on your architecture, select this option. However, 408# statically allocating the mem_section[] array can potentially 409# consume vast quantities of .bss, so be careful. 410# 411# This option will also potentially produce smaller runtime code 412# with gcc 3.4 and later. 413# 414config SPARSEMEM_STATIC 415 bool 416 417# 418# Architecture platforms which require a two level mem_section in SPARSEMEM 419# must select this option. This is usually for architecture platforms with 420# an extremely sparse physical address space. 421# 422config SPARSEMEM_EXTREME 423 def_bool y 424 depends on SPARSEMEM && !SPARSEMEM_STATIC 425 426config SPARSEMEM_VMEMMAP_ENABLE 427 bool 428 429config SPARSEMEM_VMEMMAP 430 bool "Sparse Memory virtual memmap" 431 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE 432 default y 433 help 434 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise 435 pfn_to_page and page_to_pfn operations. This is the most 436 efficient option when sufficient kernel resources are available. 437 438config HAVE_MEMBLOCK_PHYS_MAP 439 bool 440 441config HAVE_FAST_GUP 442 depends on MMU 443 bool 444 445# Don't discard allocated memory used to track "memory" and "reserved" memblocks 446# after early boot, so it can still be used to test for validity of memory. 447# Also, memblocks are updated with memory hot(un)plug. 448config ARCH_KEEP_MEMBLOCK 449 bool 450 451# Keep arch NUMA mapping infrastructure post-init. 452config NUMA_KEEP_MEMINFO 453 bool 454 455config MEMORY_ISOLATION 456 bool 457 458# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked 459# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via 460# /dev/mem. 461config EXCLUSIVE_SYSTEM_RAM 462 def_bool y 463 depends on !DEVMEM || STRICT_DEVMEM 464 465# 466# Only be set on architectures that have completely implemented memory hotplug 467# feature. If you are not sure, don't touch it. 468# 469config HAVE_BOOTMEM_INFO_NODE 470 def_bool n 471 472config ARCH_ENABLE_MEMORY_HOTPLUG 473 bool 474 475config ARCH_ENABLE_MEMORY_HOTREMOVE 476 bool 477 478# eventually, we can have this option just 'select SPARSEMEM' 479menuconfig MEMORY_HOTPLUG 480 bool "Memory hotplug" 481 select MEMORY_ISOLATION 482 depends on SPARSEMEM 483 depends on ARCH_ENABLE_MEMORY_HOTPLUG 484 depends on 64BIT 485 select NUMA_KEEP_MEMINFO if NUMA 486 487if MEMORY_HOTPLUG 488 489config MEMORY_HOTPLUG_DEFAULT_ONLINE 490 bool "Online the newly added memory blocks by default" 491 depends on MEMORY_HOTPLUG 492 help 493 This option sets the default policy setting for memory hotplug 494 onlining policy (/sys/devices/system/memory/auto_online_blocks) which 495 determines what happens to newly added memory regions. Policy setting 496 can always be changed at runtime. 497 See Documentation/admin-guide/mm/memory-hotplug.rst for more information. 498 499 Say Y here if you want all hot-plugged memory blocks to appear in 500 'online' state by default. 501 Say N here if you want the default policy to keep all hot-plugged 502 memory blocks in 'offline' state. 503 504config MEMORY_HOTREMOVE 505 bool "Allow for memory hot remove" 506 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) 507 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE 508 depends on MIGRATION 509 510config MHP_MEMMAP_ON_MEMORY 511 def_bool y 512 depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP 513 depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE 514 515endif # MEMORY_HOTPLUG 516 517# Heavily threaded applications may benefit from splitting the mm-wide 518# page_table_lock, so that faults on different parts of the user address 519# space can be handled with less contention: split it at this NR_CPUS. 520# Default to 4 for wider testing, though 8 might be more appropriate. 521# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. 522# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. 523# SPARC32 allocates multiple pte tables within a single page, and therefore 524# a per-page lock leads to problems when multiple tables need to be locked 525# at the same time (e.g. copy_page_range()). 526# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. 527# 528config SPLIT_PTLOCK_CPUS 529 int 530 default "999999" if !MMU 531 default "999999" if ARM && !CPU_CACHE_VIPT 532 default "999999" if PARISC && !PA20 533 default "999999" if SPARC32 534 default "4" 535 536config ARCH_ENABLE_SPLIT_PMD_PTLOCK 537 bool 538 539# 540# support for memory balloon 541config MEMORY_BALLOON 542 bool 543 544# 545# support for memory balloon compaction 546config BALLOON_COMPACTION 547 bool "Allow for balloon memory compaction/migration" 548 def_bool y 549 depends on COMPACTION && MEMORY_BALLOON 550 help 551 Memory fragmentation introduced by ballooning might reduce 552 significantly the number of 2MB contiguous memory blocks that can be 553 used within a guest, thus imposing performance penalties associated 554 with the reduced number of transparent huge pages that could be used 555 by the guest workload. Allowing the compaction & migration for memory 556 pages enlisted as being part of memory balloon devices avoids the 557 scenario aforementioned and helps improving memory defragmentation. 558 559# 560# support for memory compaction 561config COMPACTION 562 bool "Allow for memory compaction" 563 def_bool y 564 select MIGRATION 565 depends on MMU 566 help 567 Compaction is the only memory management component to form 568 high order (larger physically contiguous) memory blocks 569 reliably. The page allocator relies on compaction heavily and 570 the lack of the feature can lead to unexpected OOM killer 571 invocations for high order memory requests. You shouldn't 572 disable this option unless there really is a strong reason for 573 it and then we would be really interested to hear about that at 574 linux-mm@kvack.org. 575 576# 577# support for free page reporting 578config PAGE_REPORTING 579 bool "Free page reporting" 580 def_bool n 581 help 582 Free page reporting allows for the incremental acquisition of 583 free pages from the buddy allocator for the purpose of reporting 584 those pages to another entity, such as a hypervisor, so that the 585 memory can be freed within the host for other uses. 586 587# 588# support for page migration 589# 590config MIGRATION 591 bool "Page migration" 592 def_bool y 593 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU 594 help 595 Allows the migration of the physical location of pages of processes 596 while the virtual addresses are not changed. This is useful in 597 two situations. The first is on NUMA systems to put pages nearer 598 to the processors accessing. The second is when allocating huge 599 pages as migration can relocate pages to satisfy a huge page 600 allocation instead of reclaiming. 601 602config DEVICE_MIGRATION 603 def_bool MIGRATION && ZONE_DEVICE 604 605config ARCH_ENABLE_HUGEPAGE_MIGRATION 606 bool 607 608config ARCH_ENABLE_THP_MIGRATION 609 bool 610 611config HUGETLB_PAGE_SIZE_VARIABLE 612 def_bool n 613 help 614 Allows the pageblock_order value to be dynamic instead of just standard 615 HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available 616 on a platform. 617 618 Note that the pageblock_order cannot exceed MAX_ORDER - 1 and will be 619 clamped down to MAX_ORDER - 1. 620 621config CONTIG_ALLOC 622 def_bool (MEMORY_ISOLATION && COMPACTION) || CMA 623 624config PHYS_ADDR_T_64BIT 625 def_bool 64BIT 626 627config BOUNCE 628 bool "Enable bounce buffers" 629 default y 630 depends on BLOCK && MMU && HIGHMEM 631 help 632 Enable bounce buffers for devices that cannot access the full range of 633 memory available to the CPU. Enabled by default when HIGHMEM is 634 selected, but you may say n to override this. 635 636config MMU_NOTIFIER 637 bool 638 select SRCU 639 select INTERVAL_TREE 640 641config KSM 642 bool "Enable KSM for page merging" 643 depends on MMU 644 select XXHASH 645 help 646 Enable Kernel Samepage Merging: KSM periodically scans those areas 647 of an application's address space that an app has advised may be 648 mergeable. When it finds pages of identical content, it replaces 649 the many instances by a single page with that content, so 650 saving memory until one or another app needs to modify the content. 651 Recommended for use with KVM, or with other duplicative applications. 652 See Documentation/mm/ksm.rst for more information: KSM is inactive 653 until a program has madvised that an area is MADV_MERGEABLE, and 654 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). 655 656config DEFAULT_MMAP_MIN_ADDR 657 int "Low address space to protect from user allocation" 658 depends on MMU 659 default 4096 660 help 661 This is the portion of low virtual memory which should be protected 662 from userspace allocation. Keeping a user from writing to low pages 663 can help reduce the impact of kernel NULL pointer bugs. 664 665 For most ia64, ppc64 and x86 users with lots of address space 666 a value of 65536 is reasonable and should cause no problems. 667 On arm and other archs it should not be higher than 32768. 668 Programs which use vm86 functionality or have some need to map 669 this low address space will need CAP_SYS_RAWIO or disable this 670 protection by setting the value to 0. 671 672 This value can be changed after boot using the 673 /proc/sys/vm/mmap_min_addr tunable. 674 675config ARCH_SUPPORTS_MEMORY_FAILURE 676 bool 677 678config MEMORY_FAILURE 679 depends on MMU 680 depends on ARCH_SUPPORTS_MEMORY_FAILURE 681 bool "Enable recovery from hardware memory errors" 682 select MEMORY_ISOLATION 683 select RAS 684 help 685 Enables code to recover from some memory failures on systems 686 with MCA recovery. This allows a system to continue running 687 even when some of its memory has uncorrected errors. This requires 688 special hardware support and typically ECC memory. 689 690config HWPOISON_INJECT 691 tristate "HWPoison pages injector" 692 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS 693 select PROC_PAGE_MONITOR 694 695config NOMMU_INITIAL_TRIM_EXCESS 696 int "Turn on mmap() excess space trimming before booting" 697 depends on !MMU 698 default 1 699 help 700 The NOMMU mmap() frequently needs to allocate large contiguous chunks 701 of memory on which to store mappings, but it can only ask the system 702 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently 703 more than it requires. To deal with this, mmap() is able to trim off 704 the excess and return it to the allocator. 705 706 If trimming is enabled, the excess is trimmed off and returned to the 707 system allocator, which can cause extra fragmentation, particularly 708 if there are a lot of transient processes. 709 710 If trimming is disabled, the excess is kept, but not used, which for 711 long-term mappings means that the space is wasted. 712 713 Trimming can be dynamically controlled through a sysctl option 714 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of 715 excess pages there must be before trimming should occur, or zero if 716 no trimming is to occur. 717 718 This option specifies the initial value of this option. The default 719 of 1 says that all excess pages should be trimmed. 720 721 See Documentation/admin-guide/mm/nommu-mmap.rst for more information. 722 723config ARCH_WANT_GENERAL_HUGETLB 724 bool 725 726config ARCH_WANTS_THP_SWAP 727 def_bool n 728 729menuconfig TRANSPARENT_HUGEPAGE 730 bool "Transparent Hugepage Support" 731 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT 732 select COMPACTION 733 select XARRAY_MULTI 734 help 735 Transparent Hugepages allows the kernel to use huge pages and 736 huge tlb transparently to the applications whenever possible. 737 This feature can improve computing performance to certain 738 applications by speeding up page faults during memory 739 allocation, by reducing the number of tlb misses and by speeding 740 up the pagetable walking. 741 742 If memory constrained on embedded, you may want to say N. 743 744if TRANSPARENT_HUGEPAGE 745 746choice 747 prompt "Transparent Hugepage Support sysfs defaults" 748 depends on TRANSPARENT_HUGEPAGE 749 default TRANSPARENT_HUGEPAGE_ALWAYS 750 help 751 Selects the sysfs defaults for Transparent Hugepage Support. 752 753 config TRANSPARENT_HUGEPAGE_ALWAYS 754 bool "always" 755 help 756 Enabling Transparent Hugepage always, can increase the 757 memory footprint of applications without a guaranteed 758 benefit but it will work automatically for all applications. 759 760 config TRANSPARENT_HUGEPAGE_MADVISE 761 bool "madvise" 762 help 763 Enabling Transparent Hugepage madvise, will only provide a 764 performance improvement benefit to the applications using 765 madvise(MADV_HUGEPAGE) but it won't risk to increase the 766 memory footprint of applications without a guaranteed 767 benefit. 768endchoice 769 770config THP_SWAP 771 def_bool y 772 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP 773 help 774 Swap transparent huge pages in one piece, without splitting. 775 XXX: For now, swap cluster backing transparent huge page 776 will be split after swapout. 777 778 For selection by architectures with reasonable THP sizes. 779 780config READ_ONLY_THP_FOR_FS 781 bool "Read-only THP for filesystems (EXPERIMENTAL)" 782 depends on TRANSPARENT_HUGEPAGE && SHMEM 783 784 help 785 Allow khugepaged to put read-only file-backed pages in THP. 786 787 This is marked experimental because it is a new feature. Write 788 support of file THPs will be developed in the next few release 789 cycles. 790 791endif # TRANSPARENT_HUGEPAGE 792 793# 794# UP and nommu archs use km based percpu allocator 795# 796config NEED_PER_CPU_KM 797 depends on !SMP || !MMU 798 bool 799 default y 800 801config NEED_PER_CPU_EMBED_FIRST_CHUNK 802 bool 803 804config NEED_PER_CPU_PAGE_FIRST_CHUNK 805 bool 806 807config USE_PERCPU_NUMA_NODE_ID 808 bool 809 810config HAVE_SETUP_PER_CPU_AREA 811 bool 812 813config FRONTSWAP 814 bool 815 816config CMA 817 bool "Contiguous Memory Allocator" 818 depends on MMU 819 select MIGRATION 820 select MEMORY_ISOLATION 821 help 822 This enables the Contiguous Memory Allocator which allows other 823 subsystems to allocate big physically-contiguous blocks of memory. 824 CMA reserves a region of memory and allows only movable pages to 825 be allocated from it. This way, the kernel can use the memory for 826 pagecache and when a subsystem requests for contiguous area, the 827 allocated pages are migrated away to serve the contiguous request. 828 829 If unsure, say "n". 830 831config CMA_DEBUG 832 bool "CMA debug messages (DEVELOPMENT)" 833 depends on DEBUG_KERNEL && CMA 834 help 835 Turns on debug messages in CMA. This produces KERN_DEBUG 836 messages for every CMA call as well as various messages while 837 processing calls such as dma_alloc_from_contiguous(). 838 This option does not affect warning and error messages. 839 840config CMA_DEBUGFS 841 bool "CMA debugfs interface" 842 depends on CMA && DEBUG_FS 843 help 844 Turns on the DebugFS interface for CMA. 845 846config CMA_SYSFS 847 bool "CMA information through sysfs interface" 848 depends on CMA && SYSFS 849 help 850 This option exposes some sysfs attributes to get information 851 from CMA. 852 853config CMA_AREAS 854 int "Maximum count of the CMA areas" 855 depends on CMA 856 default 19 if NUMA 857 default 7 858 help 859 CMA allows to create CMA areas for particular purpose, mainly, 860 used as device private area. This parameter sets the maximum 861 number of CMA area in the system. 862 863 If unsure, leave the default value "7" in UMA and "19" in NUMA. 864 865config MEM_SOFT_DIRTY 866 bool "Track memory changes" 867 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS 868 select PROC_PAGE_MONITOR 869 help 870 This option enables memory changes tracking by introducing a 871 soft-dirty bit on pte-s. This bit it set when someone writes 872 into a page just as regular dirty bit, but unlike the latter 873 it can be cleared by hands. 874 875 See Documentation/admin-guide/mm/soft-dirty.rst for more details. 876 877config GENERIC_EARLY_IOREMAP 878 bool 879 880config STACK_MAX_DEFAULT_SIZE_MB 881 int "Default maximum user stack size for 32-bit processes (MB)" 882 default 100 883 range 8 2048 884 depends on STACK_GROWSUP && (!64BIT || COMPAT) 885 help 886 This is the maximum stack size in Megabytes in the VM layout of 32-bit 887 user processes when the stack grows upwards (currently only on parisc 888 arch) when the RLIMIT_STACK hard limit is unlimited. 889 890 A sane initial value is 100 MB. 891 892config DEFERRED_STRUCT_PAGE_INIT 893 bool "Defer initialisation of struct pages to kthreads" 894 depends on SPARSEMEM 895 depends on !NEED_PER_CPU_KM 896 depends on 64BIT 897 select PADATA 898 help 899 Ordinarily all struct pages are initialised during early boot in a 900 single thread. On very large machines this can take a considerable 901 amount of time. If this option is set, large machines will bring up 902 a subset of memmap at boot and then initialise the rest in parallel. 903 This has a potential performance impact on tasks running early in the 904 lifetime of the system until these kthreads finish the 905 initialisation. 906 907config PAGE_IDLE_FLAG 908 bool 909 select PAGE_EXTENSION if !64BIT 910 help 911 This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed 912 bit writers can set the state of the bit in the flags so that PTE 913 Accessed bit readers may avoid disturbance. 914 915config IDLE_PAGE_TRACKING 916 bool "Enable idle page tracking" 917 depends on SYSFS && MMU 918 select PAGE_IDLE_FLAG 919 help 920 This feature allows to estimate the amount of user pages that have 921 not been touched during a given period of time. This information can 922 be useful to tune memory cgroup limits and/or for job placement 923 within a compute cluster. 924 925 See Documentation/admin-guide/mm/idle_page_tracking.rst for 926 more details. 927 928config ARCH_HAS_CACHE_LINE_SIZE 929 bool 930 931config ARCH_HAS_CURRENT_STACK_POINTER 932 bool 933 help 934 In support of HARDENED_USERCOPY performing stack variable lifetime 935 checking, an architecture-agnostic way to find the stack pointer 936 is needed. Once an architecture defines an unsigned long global 937 register alias named "current_stack_pointer", this config can be 938 selected. 939 940config ARCH_HAS_PTE_DEVMAP 941 bool 942 943config ARCH_HAS_ZONE_DMA_SET 944 bool 945 946config ZONE_DMA 947 bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET 948 default y if ARM64 || X86 949 950config ZONE_DMA32 951 bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET 952 depends on !X86_32 953 default y if ARM64 954 955config ZONE_DEVICE 956 bool "Device memory (pmem, HMM, etc...) hotplug support" 957 depends on MEMORY_HOTPLUG 958 depends on MEMORY_HOTREMOVE 959 depends on SPARSEMEM_VMEMMAP 960 depends on ARCH_HAS_PTE_DEVMAP 961 select XARRAY_MULTI 962 963 help 964 Device memory hotplug support allows for establishing pmem, 965 or other device driver discovered memory regions, in the 966 memmap. This allows pfn_to_page() lookups of otherwise 967 "device-physical" addresses which is needed for using a DAX 968 mapping in an O_DIRECT operation, among other things. 969 970 If FS_DAX is enabled, then say Y. 971 972# 973# Helpers to mirror range of the CPU page tables of a process into device page 974# tables. 975# 976config HMM_MIRROR 977 bool 978 depends on MMU 979 980config GET_FREE_REGION 981 depends on SPARSEMEM 982 bool 983 984config DEVICE_PRIVATE 985 bool "Unaddressable device memory (GPU memory, ...)" 986 depends on ZONE_DEVICE 987 select GET_FREE_REGION 988 989 help 990 Allows creation of struct pages to represent unaddressable device 991 memory; i.e., memory that is only accessible from the device (or 992 group of devices). You likely also want to select HMM_MIRROR. 993 994config VMAP_PFN 995 bool 996 997config ARCH_USES_HIGH_VMA_FLAGS 998 bool 999config ARCH_HAS_PKEYS 1000 bool 1001 1002config VM_EVENT_COUNTERS 1003 default y 1004 bool "Enable VM event counters for /proc/vmstat" if EXPERT 1005 help 1006 VM event counters are needed for event counts to be shown. 1007 This option allows the disabling of the VM event counters 1008 on EXPERT systems. /proc/vmstat will only show page counts 1009 if VM event counters are disabled. 1010 1011config PERCPU_STATS 1012 bool "Collect percpu memory statistics" 1013 help 1014 This feature collects and exposes statistics via debugfs. The 1015 information includes global and per chunk statistics, which can 1016 be used to help understand percpu memory usage. 1017 1018config GUP_TEST 1019 bool "Enable infrastructure for get_user_pages()-related unit tests" 1020 depends on DEBUG_FS 1021 help 1022 Provides /sys/kernel/debug/gup_test, which in turn provides a way 1023 to make ioctl calls that can launch kernel-based unit tests for 1024 the get_user_pages*() and pin_user_pages*() family of API calls. 1025 1026 These tests include benchmark testing of the _fast variants of 1027 get_user_pages*() and pin_user_pages*(), as well as smoke tests of 1028 the non-_fast variants. 1029 1030 There is also a sub-test that allows running dump_page() on any 1031 of up to eight pages (selected by command line args) within the 1032 range of user-space addresses. These pages are either pinned via 1033 pin_user_pages*(), or pinned via get_user_pages*(), as specified 1034 by other command line arguments. 1035 1036 See tools/testing/selftests/vm/gup_test.c 1037 1038comment "GUP_TEST needs to have DEBUG_FS enabled" 1039 depends on !GUP_TEST && !DEBUG_FS 1040 1041config GUP_GET_PTE_LOW_HIGH 1042 bool 1043 1044config ARCH_HAS_PTE_SPECIAL 1045 bool 1046 1047# 1048# Some architectures require a special hugepage directory format that is 1049# required to support multiple hugepage sizes. For example a4fe3ce76 1050# "powerpc/mm: Allow more flexible layouts for hugepage pagetables" 1051# introduced it on powerpc. This allows for a more flexible hugepage 1052# pagetable layouts. 1053# 1054config ARCH_HAS_HUGEPD 1055 bool 1056 1057config MAPPING_DIRTY_HELPERS 1058 bool 1059 1060config KMAP_LOCAL 1061 bool 1062 1063config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY 1064 bool 1065 1066# struct io_mapping based helper. Selected by drivers that need them 1067config IO_MAPPING 1068 bool 1069 1070config SECRETMEM 1071 def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED 1072 1073config ANON_VMA_NAME 1074 bool "Anonymous VMA name support" 1075 depends on PROC_FS && ADVISE_SYSCALLS && MMU 1076 1077 help 1078 Allow naming anonymous virtual memory areas. 1079 1080 This feature allows assigning names to virtual memory areas. Assigned 1081 names can be later retrieved from /proc/pid/maps and /proc/pid/smaps 1082 and help identifying individual anonymous memory areas. 1083 Assigning a name to anonymous virtual memory area might prevent that 1084 area from being merged with adjacent virtual memory areas due to the 1085 difference in their name. 1086 1087config USERFAULTFD 1088 bool "Enable userfaultfd() system call" 1089 depends on MMU 1090 help 1091 Enable the userfaultfd() system call that allows to intercept and 1092 handle page faults in userland. 1093 1094config HAVE_ARCH_USERFAULTFD_WP 1095 bool 1096 help 1097 Arch has userfaultfd write protection support 1098 1099config HAVE_ARCH_USERFAULTFD_MINOR 1100 bool 1101 help 1102 Arch has userfaultfd minor fault support 1103 1104config PTE_MARKER 1105 bool 1106 1107 help 1108 Allows to create marker PTEs for file-backed memory. 1109 1110config PTE_MARKER_UFFD_WP 1111 bool "Userfaultfd write protection support for shmem/hugetlbfs" 1112 default y 1113 depends on HAVE_ARCH_USERFAULTFD_WP 1114 select PTE_MARKER 1115 1116 help 1117 Allows to create marker PTEs for userfaultfd write protection 1118 purposes. It is required to enable userfaultfd write protection on 1119 file-backed memory types like shmem and hugetlbfs. 1120 1121# multi-gen LRU { 1122config LRU_GEN 1123 bool "Multi-Gen LRU" 1124 depends on MMU 1125 # make sure folio->flags has enough spare bits 1126 depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP 1127 help 1128 A high performance LRU implementation to overcommit memory. See 1129 Documentation/admin-guide/mm/multigen_lru.rst for details. 1130 1131config LRU_GEN_ENABLED 1132 bool "Enable by default" 1133 depends on LRU_GEN 1134 help 1135 This option enables the multi-gen LRU by default. 1136 1137config LRU_GEN_STATS 1138 bool "Full stats for debugging" 1139 depends on LRU_GEN 1140 help 1141 Do not enable this option unless you plan to look at historical stats 1142 from evicted generations for debugging purpose. 1143 1144 This option has a per-memcg and per-node memory overhead. 1145# } 1146 1147source "mm/damon/Kconfig" 1148 1149endmenu 1150