1config SELECT_MEMORY_MODEL 2 def_bool y 3 depends on ARCH_SELECT_MEMORY_MODEL 4 5choice 6 prompt "Memory model" 7 depends on SELECT_MEMORY_MODEL 8 default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT 9 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT 10 default FLATMEM_MANUAL 11 12config FLATMEM_MANUAL 13 bool "Flat Memory" 14 depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE 15 help 16 This option allows you to change some of the ways that 17 Linux manages its memory internally. Most users will 18 only have one option here: FLATMEM. This is normal 19 and a correct option. 20 21 Some users of more advanced features like NUMA and 22 memory hotplug may have different options here. 23 DISCONTIGMEM is a more mature, better tested system, 24 but is incompatible with memory hotplug and may suffer 25 decreased performance over SPARSEMEM. If unsure between 26 "Sparse Memory" and "Discontiguous Memory", choose 27 "Discontiguous Memory". 28 29 If unsure, choose this option (Flat Memory) over any other. 30 31config DISCONTIGMEM_MANUAL 32 bool "Discontiguous Memory" 33 depends on ARCH_DISCONTIGMEM_ENABLE 34 help 35 This option provides enhanced support for discontiguous 36 memory systems, over FLATMEM. These systems have holes 37 in their physical address spaces, and this option provides 38 more efficient handling of these holes. However, the vast 39 majority of hardware has quite flat address spaces, and 40 can have degraded performance from the extra overhead that 41 this option imposes. 42 43 Many NUMA configurations will have this as the only option. 44 45 If unsure, choose "Flat Memory" over this option. 46 47config SPARSEMEM_MANUAL 48 bool "Sparse Memory" 49 depends on ARCH_SPARSEMEM_ENABLE 50 help 51 This will be the only option for some systems, including 52 memory hotplug systems. This is normal. 53 54 For many other systems, this will be an alternative to 55 "Discontiguous Memory". This option provides some potential 56 performance benefits, along with decreased code complexity, 57 but it is newer, and more experimental. 58 59 If unsure, choose "Discontiguous Memory" or "Flat Memory" 60 over this option. 61 62endchoice 63 64config DISCONTIGMEM 65 def_bool y 66 depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL 67 68config SPARSEMEM 69 def_bool y 70 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL 71 72config FLATMEM 73 def_bool y 74 depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL 75 76config FLAT_NODE_MEM_MAP 77 def_bool y 78 depends on !SPARSEMEM 79 80# 81# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's 82# to represent different areas of memory. This variable allows 83# those dependencies to exist individually. 84# 85config NEED_MULTIPLE_NODES 86 def_bool y 87 depends on DISCONTIGMEM || NUMA 88 89config HAVE_MEMORY_PRESENT 90 def_bool y 91 depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM 92 93# 94# SPARSEMEM_EXTREME (which is the default) does some bootmem 95# allocations when memory_present() is called. If this cannot 96# be done on your architecture, select this option. However, 97# statically allocating the mem_section[] array can potentially 98# consume vast quantities of .bss, so be careful. 99# 100# This option will also potentially produce smaller runtime code 101# with gcc 3.4 and later. 102# 103config SPARSEMEM_STATIC 104 bool 105 106# 107# Architecture platforms which require a two level mem_section in SPARSEMEM 108# must select this option. This is usually for architecture platforms with 109# an extremely sparse physical address space. 110# 111config SPARSEMEM_EXTREME 112 def_bool y 113 depends on SPARSEMEM && !SPARSEMEM_STATIC 114 115config SPARSEMEM_VMEMMAP_ENABLE 116 bool 117 118config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER 119 def_bool y 120 depends on SPARSEMEM && X86_64 121 122config SPARSEMEM_VMEMMAP 123 bool "Sparse Memory virtual memmap" 124 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE 125 default y 126 help 127 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise 128 pfn_to_page and page_to_pfn operations. This is the most 129 efficient option when sufficient kernel resources are available. 130 131config HAVE_MEMBLOCK 132 bool 133 134config HAVE_MEMBLOCK_NODE_MAP 135 bool 136 137config HAVE_MEMBLOCK_PHYS_MAP 138 bool 139 140config HAVE_GENERIC_RCU_GUP 141 bool 142 143config ARCH_DISCARD_MEMBLOCK 144 bool 145 146config NO_BOOTMEM 147 bool 148 149config MEMORY_ISOLATION 150 bool 151 152config MOVABLE_NODE 153 bool "Enable to assign a node which has only movable memory" 154 depends on HAVE_MEMBLOCK 155 depends on NO_BOOTMEM 156 depends on X86_64 157 depends on NUMA 158 default n 159 help 160 Allow a node to have only movable memory. Pages used by the kernel, 161 such as direct mapping pages cannot be migrated. So the corresponding 162 memory device cannot be hotplugged. This option allows the following 163 two things: 164 - When the system is booting, node full of hotpluggable memory can 165 be arranged to have only movable memory so that the whole node can 166 be hot-removed. (need movable_node boot option specified). 167 - After the system is up, the option allows users to online all the 168 memory of a node as movable memory so that the whole node can be 169 hot-removed. 170 171 Users who don't use the memory hotplug feature are fine with this 172 option on since they don't specify movable_node boot option or they 173 don't online memory as movable. 174 175 Say Y here if you want to hotplug a whole node. 176 Say N here if you want kernel to use memory on all nodes evenly. 177 178# 179# Only be set on architectures that have completely implemented memory hotplug 180# feature. If you are not sure, don't touch it. 181# 182config HAVE_BOOTMEM_INFO_NODE 183 def_bool n 184 185# eventually, we can have this option just 'select SPARSEMEM' 186config MEMORY_HOTPLUG 187 bool "Allow for memory hot-add" 188 depends on SPARSEMEM || X86_64_ACPI_NUMA 189 depends on ARCH_ENABLE_MEMORY_HOTPLUG 190 depends on !KASAN 191 192config MEMORY_HOTPLUG_SPARSE 193 def_bool y 194 depends on SPARSEMEM && MEMORY_HOTPLUG 195 196config MEMORY_HOTPLUG_DEFAULT_ONLINE 197 bool "Online the newly added memory blocks by default" 198 default n 199 depends on MEMORY_HOTPLUG 200 help 201 This option sets the default policy setting for memory hotplug 202 onlining policy (/sys/devices/system/memory/auto_online_blocks) which 203 determines what happens to newly added memory regions. Policy setting 204 can always be changed at runtime. 205 See Documentation/memory-hotplug.txt for more information. 206 207 Say Y here if you want all hot-plugged memory blocks to appear in 208 'online' state by default. 209 Say N here if you want the default policy to keep all hot-plugged 210 memory blocks in 'offline' state. 211 212config MEMORY_HOTREMOVE 213 bool "Allow for memory hot remove" 214 select MEMORY_ISOLATION 215 select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) 216 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE 217 depends on MIGRATION 218 219# Heavily threaded applications may benefit from splitting the mm-wide 220# page_table_lock, so that faults on different parts of the user address 221# space can be handled with less contention: split it at this NR_CPUS. 222# Default to 4 for wider testing, though 8 might be more appropriate. 223# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. 224# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. 225# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. 226# 227config SPLIT_PTLOCK_CPUS 228 int 229 default "999999" if !MMU 230 default "999999" if ARM && !CPU_CACHE_VIPT 231 default "999999" if PARISC && !PA20 232 default "4" 233 234config ARCH_ENABLE_SPLIT_PMD_PTLOCK 235 bool 236 237# 238# support for memory balloon 239config MEMORY_BALLOON 240 bool 241 242# 243# support for memory balloon compaction 244config BALLOON_COMPACTION 245 bool "Allow for balloon memory compaction/migration" 246 def_bool y 247 depends on COMPACTION && MEMORY_BALLOON 248 help 249 Memory fragmentation introduced by ballooning might reduce 250 significantly the number of 2MB contiguous memory blocks that can be 251 used within a guest, thus imposing performance penalties associated 252 with the reduced number of transparent huge pages that could be used 253 by the guest workload. Allowing the compaction & migration for memory 254 pages enlisted as being part of memory balloon devices avoids the 255 scenario aforementioned and helps improving memory defragmentation. 256 257# 258# support for memory compaction 259config COMPACTION 260 bool "Allow for memory compaction" 261 def_bool y 262 select MIGRATION 263 depends on MMU 264 help 265 Allows the compaction of memory for the allocation of huge pages. 266 267# 268# support for page migration 269# 270config MIGRATION 271 bool "Page migration" 272 def_bool y 273 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU 274 help 275 Allows the migration of the physical location of pages of processes 276 while the virtual addresses are not changed. This is useful in 277 two situations. The first is on NUMA systems to put pages nearer 278 to the processors accessing. The second is when allocating huge 279 pages as migration can relocate pages to satisfy a huge page 280 allocation instead of reclaiming. 281 282config ARCH_ENABLE_HUGEPAGE_MIGRATION 283 bool 284 285config PHYS_ADDR_T_64BIT 286 def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT 287 288config BOUNCE 289 bool "Enable bounce buffers" 290 default y 291 depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) 292 help 293 Enable bounce buffers for devices that cannot access 294 the full range of memory available to the CPU. Enabled 295 by default when ZONE_DMA or HIGHMEM is selected, but you 296 may say n to override this. 297 298# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often 299# have more than 4GB of memory, but we don't currently use the IOTLB to present 300# a 32-bit address to OHCI. So we need to use a bounce pool instead. 301config NEED_BOUNCE_POOL 302 bool 303 default y if TILE && USB_OHCI_HCD 304 305config NR_QUICK 306 int 307 depends on QUICKLIST 308 default "2" if AVR32 309 default "1" 310 311config VIRT_TO_BUS 312 bool 313 help 314 An architecture should select this if it implements the 315 deprecated interface virt_to_bus(). All new architectures 316 should probably not select this. 317 318 319config MMU_NOTIFIER 320 bool 321 select SRCU 322 323config KSM 324 bool "Enable KSM for page merging" 325 depends on MMU 326 help 327 Enable Kernel Samepage Merging: KSM periodically scans those areas 328 of an application's address space that an app has advised may be 329 mergeable. When it finds pages of identical content, it replaces 330 the many instances by a single page with that content, so 331 saving memory until one or another app needs to modify the content. 332 Recommended for use with KVM, or with other duplicative applications. 333 See Documentation/vm/ksm.txt for more information: KSM is inactive 334 until a program has madvised that an area is MADV_MERGEABLE, and 335 root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). 336 337config DEFAULT_MMAP_MIN_ADDR 338 int "Low address space to protect from user allocation" 339 depends on MMU 340 default 4096 341 help 342 This is the portion of low virtual memory which should be protected 343 from userspace allocation. Keeping a user from writing to low pages 344 can help reduce the impact of kernel NULL pointer bugs. 345 346 For most ia64, ppc64 and x86 users with lots of address space 347 a value of 65536 is reasonable and should cause no problems. 348 On arm and other archs it should not be higher than 32768. 349 Programs which use vm86 functionality or have some need to map 350 this low address space will need CAP_SYS_RAWIO or disable this 351 protection by setting the value to 0. 352 353 This value can be changed after boot using the 354 /proc/sys/vm/mmap_min_addr tunable. 355 356config ARCH_SUPPORTS_MEMORY_FAILURE 357 bool 358 359config MEMORY_FAILURE 360 depends on MMU 361 depends on ARCH_SUPPORTS_MEMORY_FAILURE 362 bool "Enable recovery from hardware memory errors" 363 select MEMORY_ISOLATION 364 select RAS 365 help 366 Enables code to recover from some memory failures on systems 367 with MCA recovery. This allows a system to continue running 368 even when some of its memory has uncorrected errors. This requires 369 special hardware support and typically ECC memory. 370 371config HWPOISON_INJECT 372 tristate "HWPoison pages injector" 373 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS 374 select PROC_PAGE_MONITOR 375 376config NOMMU_INITIAL_TRIM_EXCESS 377 int "Turn on mmap() excess space trimming before booting" 378 depends on !MMU 379 default 1 380 help 381 The NOMMU mmap() frequently needs to allocate large contiguous chunks 382 of memory on which to store mappings, but it can only ask the system 383 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently 384 more than it requires. To deal with this, mmap() is able to trim off 385 the excess and return it to the allocator. 386 387 If trimming is enabled, the excess is trimmed off and returned to the 388 system allocator, which can cause extra fragmentation, particularly 389 if there are a lot of transient processes. 390 391 If trimming is disabled, the excess is kept, but not used, which for 392 long-term mappings means that the space is wasted. 393 394 Trimming can be dynamically controlled through a sysctl option 395 (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of 396 excess pages there must be before trimming should occur, or zero if 397 no trimming is to occur. 398 399 This option specifies the initial value of this option. The default 400 of 1 says that all excess pages should be trimmed. 401 402 See Documentation/nommu-mmap.txt for more information. 403 404config TRANSPARENT_HUGEPAGE 405 bool "Transparent Hugepage Support" 406 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE 407 select COMPACTION 408 select RADIX_TREE_MULTIORDER 409 help 410 Transparent Hugepages allows the kernel to use huge pages and 411 huge tlb transparently to the applications whenever possible. 412 This feature can improve computing performance to certain 413 applications by speeding up page faults during memory 414 allocation, by reducing the number of tlb misses and by speeding 415 up the pagetable walking. 416 417 If memory constrained on embedded, you may want to say N. 418 419choice 420 prompt "Transparent Hugepage Support sysfs defaults" 421 depends on TRANSPARENT_HUGEPAGE 422 default TRANSPARENT_HUGEPAGE_ALWAYS 423 help 424 Selects the sysfs defaults for Transparent Hugepage Support. 425 426 config TRANSPARENT_HUGEPAGE_ALWAYS 427 bool "always" 428 help 429 Enabling Transparent Hugepage always, can increase the 430 memory footprint of applications without a guaranteed 431 benefit but it will work automatically for all applications. 432 433 config TRANSPARENT_HUGEPAGE_MADVISE 434 bool "madvise" 435 help 436 Enabling Transparent Hugepage madvise, will only provide a 437 performance improvement benefit to the applications using 438 madvise(MADV_HUGEPAGE) but it won't risk to increase the 439 memory footprint of applications without a guaranteed 440 benefit. 441endchoice 442 443# 444# We don't deposit page tables on file THP mapping, 445# but Power makes use of them to address MMU quirk. 446# 447config TRANSPARENT_HUGE_PAGECACHE 448 def_bool y 449 depends on TRANSPARENT_HUGEPAGE && !PPC 450 451# 452# UP and nommu archs use km based percpu allocator 453# 454config NEED_PER_CPU_KM 455 depends on !SMP 456 bool 457 default y 458 459config CLEANCACHE 460 bool "Enable cleancache driver to cache clean pages if tmem is present" 461 default n 462 help 463 Cleancache can be thought of as a page-granularity victim cache 464 for clean pages that the kernel's pageframe replacement algorithm 465 (PFRA) would like to keep around, but can't since there isn't enough 466 memory. So when the PFRA "evicts" a page, it first attempts to use 467 cleancache code to put the data contained in that page into 468 "transcendent memory", memory that is not directly accessible or 469 addressable by the kernel and is of unknown and possibly 470 time-varying size. And when a cleancache-enabled 471 filesystem wishes to access a page in a file on disk, it first 472 checks cleancache to see if it already contains it; if it does, 473 the page is copied into the kernel and a disk access is avoided. 474 When a transcendent memory driver is available (such as zcache or 475 Xen transcendent memory), a significant I/O reduction 476 may be achieved. When none is available, all cleancache calls 477 are reduced to a single pointer-compare-against-NULL resulting 478 in a negligible performance hit. 479 480 If unsure, say Y to enable cleancache 481 482config FRONTSWAP 483 bool "Enable frontswap to cache swap pages if tmem is present" 484 depends on SWAP 485 default n 486 help 487 Frontswap is so named because it can be thought of as the opposite 488 of a "backing" store for a swap device. The data is stored into 489 "transcendent memory", memory that is not directly accessible or 490 addressable by the kernel and is of unknown and possibly 491 time-varying size. When space in transcendent memory is available, 492 a significant swap I/O reduction may be achieved. When none is 493 available, all frontswap calls are reduced to a single pointer- 494 compare-against-NULL resulting in a negligible performance hit 495 and swap data is stored as normal on the matching swap device. 496 497 If unsure, say Y to enable frontswap. 498 499config CMA 500 bool "Contiguous Memory Allocator" 501 depends on HAVE_MEMBLOCK && MMU 502 select MIGRATION 503 select MEMORY_ISOLATION 504 help 505 This enables the Contiguous Memory Allocator which allows other 506 subsystems to allocate big physically-contiguous blocks of memory. 507 CMA reserves a region of memory and allows only movable pages to 508 be allocated from it. This way, the kernel can use the memory for 509 pagecache and when a subsystem requests for contiguous area, the 510 allocated pages are migrated away to serve the contiguous request. 511 512 If unsure, say "n". 513 514config CMA_DEBUG 515 bool "CMA debug messages (DEVELOPMENT)" 516 depends on DEBUG_KERNEL && CMA 517 help 518 Turns on debug messages in CMA. This produces KERN_DEBUG 519 messages for every CMA call as well as various messages while 520 processing calls such as dma_alloc_from_contiguous(). 521 This option does not affect warning and error messages. 522 523config CMA_DEBUGFS 524 bool "CMA debugfs interface" 525 depends on CMA && DEBUG_FS 526 help 527 Turns on the DebugFS interface for CMA. 528 529config CMA_AREAS 530 int "Maximum count of the CMA areas" 531 depends on CMA 532 default 7 533 help 534 CMA allows to create CMA areas for particular purpose, mainly, 535 used as device private area. This parameter sets the maximum 536 number of CMA area in the system. 537 538 If unsure, leave the default value "7". 539 540config MEM_SOFT_DIRTY 541 bool "Track memory changes" 542 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS 543 select PROC_PAGE_MONITOR 544 help 545 This option enables memory changes tracking by introducing a 546 soft-dirty bit on pte-s. This bit it set when someone writes 547 into a page just as regular dirty bit, but unlike the latter 548 it can be cleared by hands. 549 550 See Documentation/vm/soft-dirty.txt for more details. 551 552config ZSWAP 553 bool "Compressed cache for swap pages (EXPERIMENTAL)" 554 depends on FRONTSWAP && CRYPTO=y 555 select CRYPTO_LZO 556 select ZPOOL 557 default n 558 help 559 A lightweight compressed cache for swap pages. It takes 560 pages that are in the process of being swapped out and attempts to 561 compress them into a dynamically allocated RAM-based memory pool. 562 This can result in a significant I/O reduction on swap device and, 563 in the case where decompressing from RAM is faster that swap device 564 reads, can also improve workload performance. 565 566 This is marked experimental because it is a new feature (as of 567 v3.11) that interacts heavily with memory reclaim. While these 568 interactions don't cause any known issues on simple memory setups, 569 they have not be fully explored on the large set of potential 570 configurations and workloads that exist. 571 572config ZPOOL 573 tristate "Common API for compressed memory storage" 574 default n 575 help 576 Compressed memory storage API. This allows using either zbud or 577 zsmalloc. 578 579config ZBUD 580 tristate "Low (Up to 2x) density storage for compressed pages" 581 default n 582 help 583 A special purpose allocator for storing compressed pages. 584 It is designed to store up to two compressed pages per physical 585 page. While this design limits storage density, it has simple and 586 deterministic reclaim properties that make it preferable to a higher 587 density approach when reclaim will be used. 588 589config Z3FOLD 590 tristate "Up to 3x density storage for compressed pages" 591 depends on ZPOOL 592 default n 593 help 594 A special purpose allocator for storing compressed pages. 595 It is designed to store up to three compressed pages per physical 596 page. It is a ZBUD derivative so the simplicity and determinism are 597 still there. 598 599config ZSMALLOC 600 tristate "Memory allocator for compressed pages" 601 depends on MMU 602 default n 603 help 604 zsmalloc is a slab-based memory allocator designed to store 605 compressed RAM pages. zsmalloc uses virtual memory mapping 606 in order to reduce fragmentation. However, this results in a 607 non-standard allocator interface where a handle, not a pointer, is 608 returned by an alloc(). This handle must be mapped in order to 609 access the allocated space. 610 611config PGTABLE_MAPPING 612 bool "Use page table mapping to access object in zsmalloc" 613 depends on ZSMALLOC 614 help 615 By default, zsmalloc uses a copy-based object mapping method to 616 access allocations that span two pages. However, if a particular 617 architecture (ex, ARM) performs VM mapping faster than copying, 618 then you should select this. This causes zsmalloc to use page table 619 mapping rather than copying for object mapping. 620 621 You can check speed with zsmalloc benchmark: 622 https://github.com/spartacus06/zsmapbench 623 624config ZSMALLOC_STAT 625 bool "Export zsmalloc statistics" 626 depends on ZSMALLOC 627 select DEBUG_FS 628 help 629 This option enables code in the zsmalloc to collect various 630 statistics about whats happening in zsmalloc and exports that 631 information to userspace via debugfs. 632 If unsure, say N. 633 634config GENERIC_EARLY_IOREMAP 635 bool 636 637config MAX_STACK_SIZE_MB 638 int "Maximum user stack size for 32-bit processes (MB)" 639 default 80 640 range 8 256 if METAG 641 range 8 2048 642 depends on STACK_GROWSUP && (!64BIT || COMPAT) 643 help 644 This is the maximum stack size in Megabytes in the VM layout of 32-bit 645 user processes when the stack grows upwards (currently only on parisc 646 and metag arch). The stack will be located at the highest memory 647 address minus the given value, unless the RLIMIT_STACK hard limit is 648 changed to a smaller value in which case that is used. 649 650 A sane initial value is 80 MB. 651 652# For architectures that support deferred memory initialisation 653config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT 654 bool 655 656config DEFERRED_STRUCT_PAGE_INIT 657 bool "Defer initialisation of struct pages to kthreads" 658 default n 659 depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT 660 depends on NO_BOOTMEM && MEMORY_HOTPLUG 661 depends on !FLATMEM 662 help 663 Ordinarily all struct pages are initialised during early boot in a 664 single thread. On very large machines this can take a considerable 665 amount of time. If this option is set, large machines will bring up 666 a subset of memmap at boot and then initialise the rest in parallel 667 by starting one-off "pgdatinitX" kernel thread for each node X. This 668 has a potential performance impact on processes running early in the 669 lifetime of the system until these kthreads finish the 670 initialisation. 671 672config IDLE_PAGE_TRACKING 673 bool "Enable idle page tracking" 674 depends on SYSFS && MMU 675 select PAGE_EXTENSION if !64BIT 676 help 677 This feature allows to estimate the amount of user pages that have 678 not been touched during a given period of time. This information can 679 be useful to tune memory cgroup limits and/or for job placement 680 within a compute cluster. 681 682 See Documentation/vm/idle_page_tracking.txt for more details. 683 684config ZONE_DEVICE 685 bool "Device memory (pmem, etc...) hotplug support" 686 depends on MEMORY_HOTPLUG 687 depends on MEMORY_HOTREMOVE 688 depends on SPARSEMEM_VMEMMAP 689 depends on X86_64 #arch_add_memory() comprehends device memory 690 691 help 692 Device memory hotplug support allows for establishing pmem, 693 or other device driver discovered memory regions, in the 694 memmap. This allows pfn_to_page() lookups of otherwise 695 "device-physical" addresses which is needed for using a DAX 696 mapping in an O_DIRECT operation, among other things. 697 698 If FS_DAX is enabled, then say Y. 699 700config FRAME_VECTOR 701 bool 702 703config ARCH_USES_HIGH_VMA_FLAGS 704 bool 705config ARCH_HAS_PKEYS 706 bool 707