1e1785e85SDave Hansenconfig SELECT_MEMORY_MODEL 2e1785e85SDave Hansen def_bool y 3a8826eebSKees Cook depends on ARCH_SELECT_MEMORY_MODEL 4e1785e85SDave Hansen 53a9da765SDave Hansenchoice 63a9da765SDave Hansen prompt "Memory model" 7e1785e85SDave Hansen depends on SELECT_MEMORY_MODEL 8e1785e85SDave Hansen default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT 9d41dee36SAndy Whitcroft default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT 10e1785e85SDave Hansen default FLATMEM_MANUAL 113a9da765SDave Hansen 12e1785e85SDave Hansenconfig FLATMEM_MANUAL 133a9da765SDave Hansen bool "Flat Memory" 14c898ec16SAnton Blanchard depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE 153a9da765SDave Hansen help 163a9da765SDave Hansen This option allows you to change some of the ways that 173a9da765SDave Hansen Linux manages its memory internally. Most users will 183a9da765SDave Hansen only have one option here: FLATMEM. This is normal 193a9da765SDave Hansen and a correct option. 203a9da765SDave Hansen 21d41dee36SAndy Whitcroft Some users of more advanced features like NUMA and 22d41dee36SAndy Whitcroft memory hotplug may have different options here. 2318f65332SGeert Uytterhoeven DISCONTIGMEM is a more mature, better tested system, 24d41dee36SAndy Whitcroft but is incompatible with memory hotplug and may suffer 25d41dee36SAndy Whitcroft decreased performance over SPARSEMEM. If unsure between 26d41dee36SAndy Whitcroft "Sparse Memory" and "Discontiguous Memory", choose 27d41dee36SAndy Whitcroft "Discontiguous Memory". 28d41dee36SAndy Whitcroft 29d41dee36SAndy Whitcroft If unsure, choose this option (Flat Memory) over any other. 303a9da765SDave Hansen 31e1785e85SDave Hansenconfig DISCONTIGMEM_MANUAL 32f3519f91SDave Hansen bool "Discontiguous Memory" 333a9da765SDave Hansen depends on ARCH_DISCONTIGMEM_ENABLE 343a9da765SDave Hansen help 35785dcd44SDave Hansen This option provides enhanced support for discontiguous 36785dcd44SDave Hansen memory systems, over FLATMEM. These systems have holes 37785dcd44SDave Hansen in their physical address spaces, and this option provides 38785dcd44SDave Hansen more efficient handling of these holes. However, the vast 39785dcd44SDave Hansen majority of hardware has quite flat address spaces, and 40ad3d0a38SPhilipp Marek can have degraded performance from the extra overhead that 41785dcd44SDave Hansen this option imposes. 42785dcd44SDave Hansen 43785dcd44SDave Hansen Many NUMA configurations will have this as the only option. 44785dcd44SDave Hansen 453a9da765SDave Hansen If unsure, choose "Flat Memory" over this option. 463a9da765SDave Hansen 47d41dee36SAndy Whitcroftconfig SPARSEMEM_MANUAL 48d41dee36SAndy Whitcroft bool "Sparse Memory" 49d41dee36SAndy Whitcroft depends on ARCH_SPARSEMEM_ENABLE 50d41dee36SAndy Whitcroft help 51d41dee36SAndy Whitcroft This will be the only option for some systems, including 52d41dee36SAndy Whitcroft memory hotplug systems. This is normal. 53d41dee36SAndy Whitcroft 54d41dee36SAndy Whitcroft For many other systems, this will be an alternative to 55f3519f91SDave Hansen "Discontiguous Memory". This option provides some potential 56d41dee36SAndy Whitcroft performance benefits, along with decreased code complexity, 57d41dee36SAndy Whitcroft but it is newer, and more experimental. 58d41dee36SAndy Whitcroft 59d41dee36SAndy Whitcroft If unsure, choose "Discontiguous Memory" or "Flat Memory" 60d41dee36SAndy Whitcroft over this option. 61d41dee36SAndy Whitcroft 623a9da765SDave Hansenendchoice 633a9da765SDave Hansen 64e1785e85SDave Hansenconfig DISCONTIGMEM 65e1785e85SDave Hansen def_bool y 66e1785e85SDave Hansen depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL 67e1785e85SDave Hansen 68d41dee36SAndy Whitcroftconfig SPARSEMEM 69d41dee36SAndy Whitcroft def_bool y 701a83e175SRussell King depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL 71d41dee36SAndy Whitcroft 72e1785e85SDave Hansenconfig FLATMEM 73e1785e85SDave Hansen def_bool y 74d41dee36SAndy Whitcroft depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL 75d41dee36SAndy Whitcroft 76d41dee36SAndy Whitcroftconfig FLAT_NODE_MEM_MAP 77d41dee36SAndy Whitcroft def_bool y 78d41dee36SAndy Whitcroft depends on !SPARSEMEM 79e1785e85SDave Hansen 8093b7504eSDave Hansen# 8193b7504eSDave Hansen# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's 8293b7504eSDave Hansen# to represent different areas of memory. This variable allows 8393b7504eSDave Hansen# those dependencies to exist individually. 8493b7504eSDave Hansen# 8593b7504eSDave Hansenconfig NEED_MULTIPLE_NODES 8693b7504eSDave Hansen def_bool y 8793b7504eSDave Hansen depends on DISCONTIGMEM || NUMA 88af705362SAndy Whitcroft 89af705362SAndy Whitcroftconfig HAVE_MEMORY_PRESENT 90af705362SAndy Whitcroft def_bool y 91d41dee36SAndy Whitcroft depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM 92802f192eSBob Picco 93802f192eSBob Picco# 943e347261SBob Picco# SPARSEMEM_EXTREME (which is the default) does some bootmem 953e347261SBob Picco# allocations when memory_present() is called. If this cannot 963e347261SBob Picco# be done on your architecture, select this option. However, 973e347261SBob Picco# statically allocating the mem_section[] array can potentially 983e347261SBob Picco# consume vast quantities of .bss, so be careful. 993e347261SBob Picco# 1003e347261SBob Picco# This option will also potentially produce smaller runtime code 1013e347261SBob Picco# with gcc 3.4 and later. 1023e347261SBob Picco# 1033e347261SBob Piccoconfig SPARSEMEM_STATIC 1049ba16087SJan Beulich bool 1053e347261SBob Picco 1063e347261SBob Picco# 10744c09201SMatt LaPlante# Architecture platforms which require a two level mem_section in SPARSEMEM 108802f192eSBob Picco# must select this option. This is usually for architecture platforms with 109802f192eSBob Picco# an extremely sparse physical address space. 110802f192eSBob Picco# 1113e347261SBob Piccoconfig SPARSEMEM_EXTREME 1123e347261SBob Picco def_bool y 1133e347261SBob Picco depends on SPARSEMEM && !SPARSEMEM_STATIC 1144c21e2f2SHugh Dickins 11529c71111SAndy Whitcroftconfig SPARSEMEM_VMEMMAP_ENABLE 1169ba16087SJan Beulich bool 11729c71111SAndy Whitcroft 1189bdac914SYinghai Luconfig SPARSEMEM_ALLOC_MEM_MAP_TOGETHER 1199bdac914SYinghai Lu def_bool y 1209bdac914SYinghai Lu depends on SPARSEMEM && X86_64 1219bdac914SYinghai Lu 12229c71111SAndy Whitcroftconfig SPARSEMEM_VMEMMAP 123a5ee6daaSGeoff Levand bool "Sparse Memory virtual memmap" 124a5ee6daaSGeoff Levand depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE 125a5ee6daaSGeoff Levand default y 126a5ee6daaSGeoff Levand help 127a5ee6daaSGeoff Levand SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise 128a5ee6daaSGeoff Levand pfn_to_page and page_to_pfn operations. This is the most 129a5ee6daaSGeoff Levand efficient option when sufficient kernel resources are available. 13029c71111SAndy Whitcroft 13195f72d1eSYinghai Luconfig HAVE_MEMBLOCK 1326341e62bSChristoph Jaeger bool 13395f72d1eSYinghai Lu 1347c0caeb8STejun Heoconfig HAVE_MEMBLOCK_NODE_MAP 1356341e62bSChristoph Jaeger bool 1367c0caeb8STejun Heo 13770210ed9SPhilipp Hachtmannconfig HAVE_MEMBLOCK_PHYS_MAP 1386341e62bSChristoph Jaeger bool 13970210ed9SPhilipp Hachtmann 140e585513bSKirill A. Shutemovconfig HAVE_GENERIC_GUP 1416341e62bSChristoph Jaeger bool 1422667f50eSSteve Capper 143c378ddd5STejun Heoconfig ARCH_DISCARD_MEMBLOCK 1446341e62bSChristoph Jaeger bool 145c378ddd5STejun Heo 14666616720SSam Ravnborgconfig NO_BOOTMEM 1476341e62bSChristoph Jaeger bool 14866616720SSam Ravnborg 149ee6f509cSMinchan Kimconfig MEMORY_ISOLATION 1506341e62bSChristoph Jaeger bool 151ee6f509cSMinchan Kim 15246723bfaSYasuaki Ishimatsu# 15346723bfaSYasuaki Ishimatsu# Only be set on architectures that have completely implemented memory hotplug 15446723bfaSYasuaki Ishimatsu# feature. If you are not sure, don't touch it. 15546723bfaSYasuaki Ishimatsu# 15646723bfaSYasuaki Ishimatsuconfig HAVE_BOOTMEM_INFO_NODE 15746723bfaSYasuaki Ishimatsu def_bool n 15846723bfaSYasuaki Ishimatsu 1593947be19SDave Hansen# eventually, we can have this option just 'select SPARSEMEM' 1603947be19SDave Hansenconfig MEMORY_HOTPLUG 1613947be19SDave Hansen bool "Allow for memory hot-add" 162ec69acbbSKeith Mannthey depends on SPARSEMEM || X86_64_ACPI_NUMA 16340b31360SStephen Rothwell depends on ARCH_ENABLE_MEMORY_HOTPLUG 1643947be19SDave Hansen 165ec69acbbSKeith Manntheyconfig MEMORY_HOTPLUG_SPARSE 166ec69acbbSKeith Mannthey def_bool y 167ec69acbbSKeith Mannthey depends on SPARSEMEM && MEMORY_HOTPLUG 168ec69acbbSKeith Mannthey 1698604d9e5SVitaly Kuznetsovconfig MEMORY_HOTPLUG_DEFAULT_ONLINE 1708604d9e5SVitaly Kuznetsov bool "Online the newly added memory blocks by default" 1718604d9e5SVitaly Kuznetsov default n 1728604d9e5SVitaly Kuznetsov depends on MEMORY_HOTPLUG 1738604d9e5SVitaly Kuznetsov help 1748604d9e5SVitaly Kuznetsov This option sets the default policy setting for memory hotplug 1758604d9e5SVitaly Kuznetsov onlining policy (/sys/devices/system/memory/auto_online_blocks) which 1768604d9e5SVitaly Kuznetsov determines what happens to newly added memory regions. Policy setting 1778604d9e5SVitaly Kuznetsov can always be changed at runtime. 1788604d9e5SVitaly Kuznetsov See Documentation/memory-hotplug.txt for more information. 1798604d9e5SVitaly Kuznetsov 1808604d9e5SVitaly Kuznetsov Say Y here if you want all hot-plugged memory blocks to appear in 1818604d9e5SVitaly Kuznetsov 'online' state by default. 1828604d9e5SVitaly Kuznetsov Say N here if you want the default policy to keep all hot-plugged 1838604d9e5SVitaly Kuznetsov memory blocks in 'offline' state. 1848604d9e5SVitaly Kuznetsov 1850c0e6195SKAMEZAWA Hiroyukiconfig MEMORY_HOTREMOVE 1860c0e6195SKAMEZAWA Hiroyuki bool "Allow for memory hot remove" 18746723bfaSYasuaki Ishimatsu select MEMORY_ISOLATION 188f7e3334aSNathan Fontenot select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64) 1890c0e6195SKAMEZAWA Hiroyuki depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE 1900c0e6195SKAMEZAWA Hiroyuki depends on MIGRATION 1910c0e6195SKAMEZAWA Hiroyuki 1924c21e2f2SHugh Dickins# Heavily threaded applications may benefit from splitting the mm-wide 1934c21e2f2SHugh Dickins# page_table_lock, so that faults on different parts of the user address 1944c21e2f2SHugh Dickins# space can be handled with less contention: split it at this NR_CPUS. 1954c21e2f2SHugh Dickins# Default to 4 for wider testing, though 8 might be more appropriate. 1964c21e2f2SHugh Dickins# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock. 1977b6ac9dfSHugh Dickins# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes. 198a70caa8bSHugh Dickins# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page. 1994c21e2f2SHugh Dickins# 2004c21e2f2SHugh Dickinsconfig SPLIT_PTLOCK_CPUS 2014c21e2f2SHugh Dickins int 2029164550eSKirill A. Shutemov default "999999" if !MMU 203a70caa8bSHugh Dickins default "999999" if ARM && !CPU_CACHE_VIPT 204a70caa8bSHugh Dickins default "999999" if PARISC && !PA20 2054c21e2f2SHugh Dickins default "4" 2067cbe34cfSChristoph Lameter 207e009bb30SKirill A. Shutemovconfig ARCH_ENABLE_SPLIT_PMD_PTLOCK 2086341e62bSChristoph Jaeger bool 209e009bb30SKirill A. Shutemov 2107cbe34cfSChristoph Lameter# 21109316c09SKonstantin Khlebnikov# support for memory balloon 21209316c09SKonstantin Khlebnikovconfig MEMORY_BALLOON 2136341e62bSChristoph Jaeger bool 21409316c09SKonstantin Khlebnikov 21509316c09SKonstantin Khlebnikov# 21618468d93SRafael Aquini# support for memory balloon compaction 21718468d93SRafael Aquiniconfig BALLOON_COMPACTION 21818468d93SRafael Aquini bool "Allow for balloon memory compaction/migration" 21918468d93SRafael Aquini def_bool y 22009316c09SKonstantin Khlebnikov depends on COMPACTION && MEMORY_BALLOON 22118468d93SRafael Aquini help 22218468d93SRafael Aquini Memory fragmentation introduced by ballooning might reduce 22318468d93SRafael Aquini significantly the number of 2MB contiguous memory blocks that can be 22418468d93SRafael Aquini used within a guest, thus imposing performance penalties associated 22518468d93SRafael Aquini with the reduced number of transparent huge pages that could be used 22618468d93SRafael Aquini by the guest workload. Allowing the compaction & migration for memory 22718468d93SRafael Aquini pages enlisted as being part of memory balloon devices avoids the 22818468d93SRafael Aquini scenario aforementioned and helps improving memory defragmentation. 22918468d93SRafael Aquini 23018468d93SRafael Aquini# 231e9e96b39SMel Gorman# support for memory compaction 232e9e96b39SMel Gormanconfig COMPACTION 233e9e96b39SMel Gorman bool "Allow for memory compaction" 23405106e6aSRik van Riel def_bool y 235e9e96b39SMel Gorman select MIGRATION 23633a93877SAndrea Arcangeli depends on MMU 237e9e96b39SMel Gorman help 238b32eaf71SMichal Hocko Compaction is the only memory management component to form 239b32eaf71SMichal Hocko high order (larger physically contiguous) memory blocks 240b32eaf71SMichal Hocko reliably. The page allocator relies on compaction heavily and 241b32eaf71SMichal Hocko the lack of the feature can lead to unexpected OOM killer 242b32eaf71SMichal Hocko invocations for high order memory requests. You shouldn't 243b32eaf71SMichal Hocko disable this option unless there really is a strong reason for 244b32eaf71SMichal Hocko it and then we would be really interested to hear about that at 245b32eaf71SMichal Hocko linux-mm@kvack.org. 246e9e96b39SMel Gorman 247e9e96b39SMel Gorman# 2487cbe34cfSChristoph Lameter# support for page migration 2497cbe34cfSChristoph Lameter# 2507cbe34cfSChristoph Lameterconfig MIGRATION 251b20a3503SChristoph Lameter bool "Page migration" 2526c5240aeSChristoph Lameter def_bool y 253de32a817SChen Gang depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU 254b20a3503SChristoph Lameter help 255b20a3503SChristoph Lameter Allows the migration of the physical location of pages of processes 256e9e96b39SMel Gorman while the virtual addresses are not changed. This is useful in 257e9e96b39SMel Gorman two situations. The first is on NUMA systems to put pages nearer 258e9e96b39SMel Gorman to the processors accessing. The second is when allocating huge 259e9e96b39SMel Gorman pages as migration can relocate pages to satisfy a huge page 260e9e96b39SMel Gorman allocation instead of reclaiming. 2616550e07fSGreg Kroah-Hartman 262c177c81eSNaoya Horiguchiconfig ARCH_ENABLE_HUGEPAGE_MIGRATION 2636341e62bSChristoph Jaeger bool 264c177c81eSNaoya Horiguchi 2659c670ea3SNaoya Horiguchiconfig ARCH_ENABLE_THP_MIGRATION 2669c670ea3SNaoya Horiguchi bool 2679c670ea3SNaoya Horiguchi 268600715dcSJeremy Fitzhardingeconfig PHYS_ADDR_T_64BIT 269600715dcSJeremy Fitzhardinge def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT 270600715dcSJeremy Fitzhardinge 2712a7326b5SChristoph Lameterconfig BOUNCE 2729ca24e2eSVinayak Menon bool "Enable bounce buffers" 2739ca24e2eSVinayak Menon default y 2742a7326b5SChristoph Lameter depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) 2759ca24e2eSVinayak Menon help 2769ca24e2eSVinayak Menon Enable bounce buffers for devices that cannot access 2779ca24e2eSVinayak Menon the full range of memory available to the CPU. Enabled 2789ca24e2eSVinayak Menon by default when ZONE_DMA or HIGHMEM is selected, but you 2799ca24e2eSVinayak Menon may say n to override this. 2802a7326b5SChristoph Lameter 2816225e937SChristoph Lameterconfig NR_QUICK 2826225e937SChristoph Lameter int 2836225e937SChristoph Lameter depends on QUICKLIST 2846225e937SChristoph Lameter default "1" 285f057eac0SStephen Rothwell 286f057eac0SStephen Rothwellconfig VIRT_TO_BUS 2874febd95aSStephen Rothwell bool 2884febd95aSStephen Rothwell help 2894febd95aSStephen Rothwell An architecture should select this if it implements the 2904febd95aSStephen Rothwell deprecated interface virt_to_bus(). All new architectures 2914febd95aSStephen Rothwell should probably not select this. 2924febd95aSStephen Rothwell 293cddb8a5cSAndrea Arcangeli 294cddb8a5cSAndrea Arcangeliconfig MMU_NOTIFIER 295cddb8a5cSAndrea Arcangeli bool 29683fe27eaSPranith Kumar select SRCU 297fc4d5c29SDavid Howells 298f8af4da3SHugh Dickinsconfig KSM 299f8af4da3SHugh Dickins bool "Enable KSM for page merging" 300f8af4da3SHugh Dickins depends on MMU 301f8af4da3SHugh Dickins help 302f8af4da3SHugh Dickins Enable Kernel Samepage Merging: KSM periodically scans those areas 303f8af4da3SHugh Dickins of an application's address space that an app has advised may be 304f8af4da3SHugh Dickins mergeable. When it finds pages of identical content, it replaces 305d0f209f6SHugh Dickins the many instances by a single page with that content, so 306f8af4da3SHugh Dickins saving memory until one or another app needs to modify the content. 307f8af4da3SHugh Dickins Recommended for use with KVM, or with other duplicative applications. 308c73602adSHugh Dickins See Documentation/vm/ksm.txt for more information: KSM is inactive 309c73602adSHugh Dickins until a program has madvised that an area is MADV_MERGEABLE, and 310c73602adSHugh Dickins root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). 311f8af4da3SHugh Dickins 312e0a94c2aSChristoph Lameterconfig DEFAULT_MMAP_MIN_ADDR 313e0a94c2aSChristoph Lameter int "Low address space to protect from user allocation" 3146e141546SDavid Howells depends on MMU 315e0a94c2aSChristoph Lameter default 4096 316e0a94c2aSChristoph Lameter help 317e0a94c2aSChristoph Lameter This is the portion of low virtual memory which should be protected 318e0a94c2aSChristoph Lameter from userspace allocation. Keeping a user from writing to low pages 319e0a94c2aSChristoph Lameter can help reduce the impact of kernel NULL pointer bugs. 320e0a94c2aSChristoph Lameter 321e0a94c2aSChristoph Lameter For most ia64, ppc64 and x86 users with lots of address space 322e0a94c2aSChristoph Lameter a value of 65536 is reasonable and should cause no problems. 323e0a94c2aSChristoph Lameter On arm and other archs it should not be higher than 32768. 324788084abSEric Paris Programs which use vm86 functionality or have some need to map 325788084abSEric Paris this low address space will need CAP_SYS_RAWIO or disable this 326788084abSEric Paris protection by setting the value to 0. 327e0a94c2aSChristoph Lameter 328e0a94c2aSChristoph Lameter This value can be changed after boot using the 329e0a94c2aSChristoph Lameter /proc/sys/vm/mmap_min_addr tunable. 330e0a94c2aSChristoph Lameter 331d949f36fSLinus Torvaldsconfig ARCH_SUPPORTS_MEMORY_FAILURE 332d949f36fSLinus Torvalds bool 333e0a94c2aSChristoph Lameter 3346a46079cSAndi Kleenconfig MEMORY_FAILURE 3356a46079cSAndi Kleen depends on MMU 336d949f36fSLinus Torvalds depends on ARCH_SUPPORTS_MEMORY_FAILURE 3376a46079cSAndi Kleen bool "Enable recovery from hardware memory errors" 338ee6f509cSMinchan Kim select MEMORY_ISOLATION 33997f0b134SXie XiuQi select RAS 3406a46079cSAndi Kleen help 3416a46079cSAndi Kleen Enables code to recover from some memory failures on systems 3426a46079cSAndi Kleen with MCA recovery. This allows a system to continue running 3436a46079cSAndi Kleen even when some of its memory has uncorrected errors. This requires 3446a46079cSAndi Kleen special hardware support and typically ECC memory. 3456a46079cSAndi Kleen 346cae681fcSAndi Kleenconfig HWPOISON_INJECT 347413f9efbSAndi Kleen tristate "HWPoison pages injector" 34827df5068SAndi Kleen depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS 349478c5ffcSWu Fengguang select PROC_PAGE_MONITOR 350cae681fcSAndi Kleen 351fc4d5c29SDavid Howellsconfig NOMMU_INITIAL_TRIM_EXCESS 352fc4d5c29SDavid Howells int "Turn on mmap() excess space trimming before booting" 353fc4d5c29SDavid Howells depends on !MMU 354fc4d5c29SDavid Howells default 1 355fc4d5c29SDavid Howells help 356fc4d5c29SDavid Howells The NOMMU mmap() frequently needs to allocate large contiguous chunks 357fc4d5c29SDavid Howells of memory on which to store mappings, but it can only ask the system 358fc4d5c29SDavid Howells allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently 359fc4d5c29SDavid Howells more than it requires. To deal with this, mmap() is able to trim off 360fc4d5c29SDavid Howells the excess and return it to the allocator. 361fc4d5c29SDavid Howells 362fc4d5c29SDavid Howells If trimming is enabled, the excess is trimmed off and returned to the 363fc4d5c29SDavid Howells system allocator, which can cause extra fragmentation, particularly 364fc4d5c29SDavid Howells if there are a lot of transient processes. 365fc4d5c29SDavid Howells 366fc4d5c29SDavid Howells If trimming is disabled, the excess is kept, but not used, which for 367fc4d5c29SDavid Howells long-term mappings means that the space is wasted. 368fc4d5c29SDavid Howells 369fc4d5c29SDavid Howells Trimming can be dynamically controlled through a sysctl option 370fc4d5c29SDavid Howells (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of 371fc4d5c29SDavid Howells excess pages there must be before trimming should occur, or zero if 372fc4d5c29SDavid Howells no trimming is to occur. 373fc4d5c29SDavid Howells 374fc4d5c29SDavid Howells This option specifies the initial value of this option. The default 375fc4d5c29SDavid Howells of 1 says that all excess pages should be trimmed. 376fc4d5c29SDavid Howells 377fc4d5c29SDavid Howells See Documentation/nommu-mmap.txt for more information. 378bbddff05STejun Heo 3794c76d9d1SAndrea Arcangeliconfig TRANSPARENT_HUGEPAGE 38013ece886SAndrea Arcangeli bool "Transparent Hugepage Support" 38115626062SGerald Schaefer depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE 3825d689240SAndrea Arcangeli select COMPACTION 38357578c2eSMatthew Wilcox select RADIX_TREE_MULTIORDER 3844c76d9d1SAndrea Arcangeli help 3854c76d9d1SAndrea Arcangeli Transparent Hugepages allows the kernel to use huge pages and 3864c76d9d1SAndrea Arcangeli huge tlb transparently to the applications whenever possible. 3874c76d9d1SAndrea Arcangeli This feature can improve computing performance to certain 3884c76d9d1SAndrea Arcangeli applications by speeding up page faults during memory 3894c76d9d1SAndrea Arcangeli allocation, by reducing the number of tlb misses and by speeding 3904c76d9d1SAndrea Arcangeli up the pagetable walking. 3914c76d9d1SAndrea Arcangeli 3924c76d9d1SAndrea Arcangeli If memory constrained on embedded, you may want to say N. 3934c76d9d1SAndrea Arcangeli 39413ece886SAndrea Arcangelichoice 39513ece886SAndrea Arcangeli prompt "Transparent Hugepage Support sysfs defaults" 39613ece886SAndrea Arcangeli depends on TRANSPARENT_HUGEPAGE 39713ece886SAndrea Arcangeli default TRANSPARENT_HUGEPAGE_ALWAYS 39813ece886SAndrea Arcangeli help 39913ece886SAndrea Arcangeli Selects the sysfs defaults for Transparent Hugepage Support. 40013ece886SAndrea Arcangeli 40113ece886SAndrea Arcangeli config TRANSPARENT_HUGEPAGE_ALWAYS 40213ece886SAndrea Arcangeli bool "always" 40313ece886SAndrea Arcangeli help 40413ece886SAndrea Arcangeli Enabling Transparent Hugepage always, can increase the 40513ece886SAndrea Arcangeli memory footprint of applications without a guaranteed 40613ece886SAndrea Arcangeli benefit but it will work automatically for all applications. 40713ece886SAndrea Arcangeli 40813ece886SAndrea Arcangeli config TRANSPARENT_HUGEPAGE_MADVISE 40913ece886SAndrea Arcangeli bool "madvise" 41013ece886SAndrea Arcangeli help 41113ece886SAndrea Arcangeli Enabling Transparent Hugepage madvise, will only provide a 41213ece886SAndrea Arcangeli performance improvement benefit to the applications using 41313ece886SAndrea Arcangeli madvise(MADV_HUGEPAGE) but it won't risk to increase the 41413ece886SAndrea Arcangeli memory footprint of applications without a guaranteed 41513ece886SAndrea Arcangeli benefit. 41613ece886SAndrea Arcangeliendchoice 41713ece886SAndrea Arcangeli 41838d8b4e6SHuang Yingconfig ARCH_WANTS_THP_SWAP 41938d8b4e6SHuang Ying def_bool n 42038d8b4e6SHuang Ying 42138d8b4e6SHuang Yingconfig THP_SWAP 42238d8b4e6SHuang Ying def_bool y 42338d8b4e6SHuang Ying depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP 42438d8b4e6SHuang Ying help 42538d8b4e6SHuang Ying Swap transparent huge pages in one piece, without splitting. 42638d8b4e6SHuang Ying XXX: For now this only does clustered swap space allocation. 42738d8b4e6SHuang Ying 42838d8b4e6SHuang Ying For selection by architectures with reasonable THP sizes. 42938d8b4e6SHuang Ying 430e496cf3dSKirill A. Shutemovconfig TRANSPARENT_HUGE_PAGECACHE 431e496cf3dSKirill A. Shutemov def_bool y 432953c66c2SAneesh Kumar K.V depends on TRANSPARENT_HUGEPAGE 433e496cf3dSKirill A. Shutemov 434e496cf3dSKirill A. Shutemov# 435bbddff05STejun Heo# UP and nommu archs use km based percpu allocator 436bbddff05STejun Heo# 437bbddff05STejun Heoconfig NEED_PER_CPU_KM 438bbddff05STejun Heo depends on !SMP 439bbddff05STejun Heo bool 440bbddff05STejun Heo default y 441077b1f83SDan Magenheimer 442077b1f83SDan Magenheimerconfig CLEANCACHE 443077b1f83SDan Magenheimer bool "Enable cleancache driver to cache clean pages if tmem is present" 444077b1f83SDan Magenheimer default n 445077b1f83SDan Magenheimer help 446077b1f83SDan Magenheimer Cleancache can be thought of as a page-granularity victim cache 447077b1f83SDan Magenheimer for clean pages that the kernel's pageframe replacement algorithm 448077b1f83SDan Magenheimer (PFRA) would like to keep around, but can't since there isn't enough 449077b1f83SDan Magenheimer memory. So when the PFRA "evicts" a page, it first attempts to use 450140a1ef2SMichael Witten cleancache code to put the data contained in that page into 451077b1f83SDan Magenheimer "transcendent memory", memory that is not directly accessible or 452077b1f83SDan Magenheimer addressable by the kernel and is of unknown and possibly 453077b1f83SDan Magenheimer time-varying size. And when a cleancache-enabled 454077b1f83SDan Magenheimer filesystem wishes to access a page in a file on disk, it first 455077b1f83SDan Magenheimer checks cleancache to see if it already contains it; if it does, 456077b1f83SDan Magenheimer the page is copied into the kernel and a disk access is avoided. 457077b1f83SDan Magenheimer When a transcendent memory driver is available (such as zcache or 458077b1f83SDan Magenheimer Xen transcendent memory), a significant I/O reduction 459077b1f83SDan Magenheimer may be achieved. When none is available, all cleancache calls 460077b1f83SDan Magenheimer are reduced to a single pointer-compare-against-NULL resulting 461077b1f83SDan Magenheimer in a negligible performance hit. 462077b1f83SDan Magenheimer 463077b1f83SDan Magenheimer If unsure, say Y to enable cleancache 46427c6aec2SDan Magenheimer 46527c6aec2SDan Magenheimerconfig FRONTSWAP 46627c6aec2SDan Magenheimer bool "Enable frontswap to cache swap pages if tmem is present" 46727c6aec2SDan Magenheimer depends on SWAP 46827c6aec2SDan Magenheimer default n 46927c6aec2SDan Magenheimer help 47027c6aec2SDan Magenheimer Frontswap is so named because it can be thought of as the opposite 47127c6aec2SDan Magenheimer of a "backing" store for a swap device. The data is stored into 47227c6aec2SDan Magenheimer "transcendent memory", memory that is not directly accessible or 47327c6aec2SDan Magenheimer addressable by the kernel and is of unknown and possibly 47427c6aec2SDan Magenheimer time-varying size. When space in transcendent memory is available, 47527c6aec2SDan Magenheimer a significant swap I/O reduction may be achieved. When none is 47627c6aec2SDan Magenheimer available, all frontswap calls are reduced to a single pointer- 47727c6aec2SDan Magenheimer compare-against-NULL resulting in a negligible performance hit 47827c6aec2SDan Magenheimer and swap data is stored as normal on the matching swap device. 47927c6aec2SDan Magenheimer 48027c6aec2SDan Magenheimer If unsure, say Y to enable frontswap. 481f825c736SAneesh Kumar K.V 482f825c736SAneesh Kumar K.Vconfig CMA 483f825c736SAneesh Kumar K.V bool "Contiguous Memory Allocator" 484de32a817SChen Gang depends on HAVE_MEMBLOCK && MMU 485f825c736SAneesh Kumar K.V select MIGRATION 486f825c736SAneesh Kumar K.V select MEMORY_ISOLATION 487f825c736SAneesh Kumar K.V help 488f825c736SAneesh Kumar K.V This enables the Contiguous Memory Allocator which allows other 489f825c736SAneesh Kumar K.V subsystems to allocate big physically-contiguous blocks of memory. 490f825c736SAneesh Kumar K.V CMA reserves a region of memory and allows only movable pages to 491f825c736SAneesh Kumar K.V be allocated from it. This way, the kernel can use the memory for 492f825c736SAneesh Kumar K.V pagecache and when a subsystem requests for contiguous area, the 493f825c736SAneesh Kumar K.V allocated pages are migrated away to serve the contiguous request. 494f825c736SAneesh Kumar K.V 495f825c736SAneesh Kumar K.V If unsure, say "n". 496f825c736SAneesh Kumar K.V 497f825c736SAneesh Kumar K.Vconfig CMA_DEBUG 498f825c736SAneesh Kumar K.V bool "CMA debug messages (DEVELOPMENT)" 499f825c736SAneesh Kumar K.V depends on DEBUG_KERNEL && CMA 500f825c736SAneesh Kumar K.V help 501f825c736SAneesh Kumar K.V Turns on debug messages in CMA. This produces KERN_DEBUG 502f825c736SAneesh Kumar K.V messages for every CMA call as well as various messages while 503f825c736SAneesh Kumar K.V processing calls such as dma_alloc_from_contiguous(). 504f825c736SAneesh Kumar K.V This option does not affect warning and error messages. 505bf550fc9SAlexander Graf 50628b24c1fSSasha Levinconfig CMA_DEBUGFS 50728b24c1fSSasha Levin bool "CMA debugfs interface" 50828b24c1fSSasha Levin depends on CMA && DEBUG_FS 50928b24c1fSSasha Levin help 51028b24c1fSSasha Levin Turns on the DebugFS interface for CMA. 51128b24c1fSSasha Levin 512a254129eSJoonsoo Kimconfig CMA_AREAS 513a254129eSJoonsoo Kim int "Maximum count of the CMA areas" 514a254129eSJoonsoo Kim depends on CMA 515a254129eSJoonsoo Kim default 7 516a254129eSJoonsoo Kim help 517a254129eSJoonsoo Kim CMA allows to create CMA areas for particular purpose, mainly, 518a254129eSJoonsoo Kim used as device private area. This parameter sets the maximum 519a254129eSJoonsoo Kim number of CMA area in the system. 520a254129eSJoonsoo Kim 521a254129eSJoonsoo Kim If unsure, leave the default value "7". 522a254129eSJoonsoo Kim 523af8d417aSDan Streetmanconfig MEM_SOFT_DIRTY 524af8d417aSDan Streetman bool "Track memory changes" 525af8d417aSDan Streetman depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS 526af8d417aSDan Streetman select PROC_PAGE_MONITOR 5274e2e2770SSeth Jennings help 528af8d417aSDan Streetman This option enables memory changes tracking by introducing a 529af8d417aSDan Streetman soft-dirty bit on pte-s. This bit it set when someone writes 530af8d417aSDan Streetman into a page just as regular dirty bit, but unlike the latter 531af8d417aSDan Streetman it can be cleared by hands. 532af8d417aSDan Streetman 533af8d417aSDan Streetman See Documentation/vm/soft-dirty.txt for more details. 5344e2e2770SSeth Jennings 5352b281117SSeth Jenningsconfig ZSWAP 5362b281117SSeth Jennings bool "Compressed cache for swap pages (EXPERIMENTAL)" 5372b281117SSeth Jennings depends on FRONTSWAP && CRYPTO=y 5382b281117SSeth Jennings select CRYPTO_LZO 53912d79d64SDan Streetman select ZPOOL 5402b281117SSeth Jennings default n 5412b281117SSeth Jennings help 5422b281117SSeth Jennings A lightweight compressed cache for swap pages. It takes 5432b281117SSeth Jennings pages that are in the process of being swapped out and attempts to 5442b281117SSeth Jennings compress them into a dynamically allocated RAM-based memory pool. 5452b281117SSeth Jennings This can result in a significant I/O reduction on swap device and, 5462b281117SSeth Jennings in the case where decompressing from RAM is faster that swap device 5472b281117SSeth Jennings reads, can also improve workload performance. 5482b281117SSeth Jennings 5492b281117SSeth Jennings This is marked experimental because it is a new feature (as of 5502b281117SSeth Jennings v3.11) that interacts heavily with memory reclaim. While these 5512b281117SSeth Jennings interactions don't cause any known issues on simple memory setups, 5522b281117SSeth Jennings they have not be fully explored on the large set of potential 5532b281117SSeth Jennings configurations and workloads that exist. 5542b281117SSeth Jennings 555af8d417aSDan Streetmanconfig ZPOOL 556af8d417aSDan Streetman tristate "Common API for compressed memory storage" 557af8d417aSDan Streetman default n 5580f8975ecSPavel Emelyanov help 559af8d417aSDan Streetman Compressed memory storage API. This allows using either zbud or 560af8d417aSDan Streetman zsmalloc. 5610f8975ecSPavel Emelyanov 562af8d417aSDan Streetmanconfig ZBUD 5639a001fc1SVitaly Wool tristate "Low (Up to 2x) density storage for compressed pages" 564af8d417aSDan Streetman default n 565af8d417aSDan Streetman help 566af8d417aSDan Streetman A special purpose allocator for storing compressed pages. 567af8d417aSDan Streetman It is designed to store up to two compressed pages per physical 568af8d417aSDan Streetman page. While this design limits storage density, it has simple and 569af8d417aSDan Streetman deterministic reclaim properties that make it preferable to a higher 570af8d417aSDan Streetman density approach when reclaim will be used. 571bcf1647dSMinchan Kim 5729a001fc1SVitaly Woolconfig Z3FOLD 5739a001fc1SVitaly Wool tristate "Up to 3x density storage for compressed pages" 5749a001fc1SVitaly Wool depends on ZPOOL 5759a001fc1SVitaly Wool default n 5769a001fc1SVitaly Wool help 5779a001fc1SVitaly Wool A special purpose allocator for storing compressed pages. 5789a001fc1SVitaly Wool It is designed to store up to three compressed pages per physical 5799a001fc1SVitaly Wool page. It is a ZBUD derivative so the simplicity and determinism are 5809a001fc1SVitaly Wool still there. 5819a001fc1SVitaly Wool 582bcf1647dSMinchan Kimconfig ZSMALLOC 583d867f203SMinchan Kim tristate "Memory allocator for compressed pages" 584bcf1647dSMinchan Kim depends on MMU 585bcf1647dSMinchan Kim default n 586bcf1647dSMinchan Kim help 587bcf1647dSMinchan Kim zsmalloc is a slab-based memory allocator designed to store 588bcf1647dSMinchan Kim compressed RAM pages. zsmalloc uses virtual memory mapping 589bcf1647dSMinchan Kim in order to reduce fragmentation. However, this results in a 590bcf1647dSMinchan Kim non-standard allocator interface where a handle, not a pointer, is 591bcf1647dSMinchan Kim returned by an alloc(). This handle must be mapped in order to 592bcf1647dSMinchan Kim access the allocated space. 593bcf1647dSMinchan Kim 594bcf1647dSMinchan Kimconfig PGTABLE_MAPPING 595bcf1647dSMinchan Kim bool "Use page table mapping to access object in zsmalloc" 596bcf1647dSMinchan Kim depends on ZSMALLOC 597bcf1647dSMinchan Kim help 598bcf1647dSMinchan Kim By default, zsmalloc uses a copy-based object mapping method to 599bcf1647dSMinchan Kim access allocations that span two pages. However, if a particular 600bcf1647dSMinchan Kim architecture (ex, ARM) performs VM mapping faster than copying, 601bcf1647dSMinchan Kim then you should select this. This causes zsmalloc to use page table 602bcf1647dSMinchan Kim mapping rather than copying for object mapping. 603bcf1647dSMinchan Kim 6042216ee85SBen Hutchings You can check speed with zsmalloc benchmark: 6052216ee85SBen Hutchings https://github.com/spartacus06/zsmapbench 6069e5c33d7SMark Salter 6070f050d99SGanesh Mahendranconfig ZSMALLOC_STAT 6080f050d99SGanesh Mahendran bool "Export zsmalloc statistics" 6090f050d99SGanesh Mahendran depends on ZSMALLOC 6100f050d99SGanesh Mahendran select DEBUG_FS 6110f050d99SGanesh Mahendran help 6120f050d99SGanesh Mahendran This option enables code in the zsmalloc to collect various 6130f050d99SGanesh Mahendran statistics about whats happening in zsmalloc and exports that 6140f050d99SGanesh Mahendran information to userspace via debugfs. 6150f050d99SGanesh Mahendran If unsure, say N. 6160f050d99SGanesh Mahendran 6179e5c33d7SMark Salterconfig GENERIC_EARLY_IOREMAP 6189e5c33d7SMark Salter bool 619042d27acSHelge Deller 620042d27acSHelge Dellerconfig MAX_STACK_SIZE_MB 621042d27acSHelge Deller int "Maximum user stack size for 32-bit processes (MB)" 622042d27acSHelge Deller default 80 623042d27acSHelge Deller range 8 2048 624042d27acSHelge Deller depends on STACK_GROWSUP && (!64BIT || COMPAT) 625042d27acSHelge Deller help 626042d27acSHelge Deller This is the maximum stack size in Megabytes in the VM layout of 32-bit 627042d27acSHelge Deller user processes when the stack grows upwards (currently only on parisc 6285f171577SJames Hogan arch). The stack will be located at the highest memory address minus 6295f171577SJames Hogan the given value, unless the RLIMIT_STACK hard limit is changed to a 6305f171577SJames Hogan smaller value in which case that is used. 631042d27acSHelge Deller 632042d27acSHelge Deller A sane initial value is 80 MB. 6333a80a7faSMel Gorman 6343a80a7faSMel Gormanconfig DEFERRED_STRUCT_PAGE_INIT 6351ce22103SVlastimil Babka bool "Defer initialisation of struct pages to kthreads" 6363a80a7faSMel Gorman default n 6372e3ca40fSPavel Tatashin depends on NO_BOOTMEM 63895794924SYang Shi depends on !FLATMEM 6393a80a7faSMel Gorman help 6403a80a7faSMel Gorman Ordinarily all struct pages are initialised during early boot in a 6413a80a7faSMel Gorman single thread. On very large machines this can take a considerable 6423a80a7faSMel Gorman amount of time. If this option is set, large machines will bring up 6433a80a7faSMel Gorman a subset of memmap at boot and then initialise the rest in parallel 6441ce22103SVlastimil Babka by starting one-off "pgdatinitX" kernel thread for each node X. This 6451ce22103SVlastimil Babka has a potential performance impact on processes running early in the 6461ce22103SVlastimil Babka lifetime of the system until these kthreads finish the 6471ce22103SVlastimil Babka initialisation. 648033fbae9SDan Williams 64933c3fc71SVladimir Davydovconfig IDLE_PAGE_TRACKING 65033c3fc71SVladimir Davydov bool "Enable idle page tracking" 65133c3fc71SVladimir Davydov depends on SYSFS && MMU 65233c3fc71SVladimir Davydov select PAGE_EXTENSION if !64BIT 65333c3fc71SVladimir Davydov help 65433c3fc71SVladimir Davydov This feature allows to estimate the amount of user pages that have 65533c3fc71SVladimir Davydov not been touched during a given period of time. This information can 65633c3fc71SVladimir Davydov be useful to tune memory cgroup limits and/or for job placement 65733c3fc71SVladimir Davydov within a compute cluster. 65833c3fc71SVladimir Davydov 65933c3fc71SVladimir Davydov See Documentation/vm/idle_page_tracking.txt for more details. 66033c3fc71SVladimir Davydov 66165f7d049SOliver O'Halloran# arch_add_memory() comprehends device memory 66265f7d049SOliver O'Halloranconfig ARCH_HAS_ZONE_DEVICE 66365f7d049SOliver O'Halloran bool 66465f7d049SOliver O'Halloran 665033fbae9SDan Williamsconfig ZONE_DEVICE 6665042db43SJérôme Glisse bool "Device memory (pmem, HMM, etc...) hotplug support" 667033fbae9SDan Williams depends on MEMORY_HOTPLUG 668033fbae9SDan Williams depends on MEMORY_HOTREMOVE 66999490f16SDan Williams depends on SPARSEMEM_VMEMMAP 67065f7d049SOliver O'Halloran depends on ARCH_HAS_ZONE_DEVICE 671ab1b597eSDan Williams select RADIX_TREE_MULTIORDER 672033fbae9SDan Williams 673033fbae9SDan Williams help 674033fbae9SDan Williams Device memory hotplug support allows for establishing pmem, 675033fbae9SDan Williams or other device driver discovered memory regions, in the 676033fbae9SDan Williams memmap. This allows pfn_to_page() lookups of otherwise 677033fbae9SDan Williams "device-physical" addresses which is needed for using a DAX 678033fbae9SDan Williams mapping in an O_DIRECT operation, among other things. 679033fbae9SDan Williams 680033fbae9SDan Williams If FS_DAX is enabled, then say Y. 68106a660adSLinus Torvalds 682133ff0eaSJérôme Glisseconfig ARCH_HAS_HMM 683133ff0eaSJérôme Glisse bool 684133ff0eaSJérôme Glisse default y 685133ff0eaSJérôme Glisse depends on (X86_64 || PPC64) 686133ff0eaSJérôme Glisse depends on ZONE_DEVICE 687133ff0eaSJérôme Glisse depends on MMU && 64BIT 688133ff0eaSJérôme Glisse depends on MEMORY_HOTPLUG 689133ff0eaSJérôme Glisse depends on MEMORY_HOTREMOVE 690133ff0eaSJérôme Glisse depends on SPARSEMEM_VMEMMAP 691133ff0eaSJérôme Glisse 6926b368cd4SJérôme Glisseconfig MIGRATE_VMA_HELPER 6936b368cd4SJérôme Glisse bool 6946b368cd4SJérôme Glisse 695e7638488SDan Williamsconfig DEV_PAGEMAP_OPS 696e7638488SDan Williams bool 697e7638488SDan Williams 698133ff0eaSJérôme Glisseconfig HMM 699133ff0eaSJérôme Glisse bool 7006b368cd4SJérôme Glisse select MIGRATE_VMA_HELPER 701133ff0eaSJérôme Glisse 702c0b12405SJérôme Glisseconfig HMM_MIRROR 703c0b12405SJérôme Glisse bool "HMM mirror CPU page table into a device page table" 704c0b12405SJérôme Glisse depends on ARCH_HAS_HMM 705c0b12405SJérôme Glisse select MMU_NOTIFIER 706c0b12405SJérôme Glisse select HMM 707c0b12405SJérôme Glisse help 708c0b12405SJérôme Glisse Select HMM_MIRROR if you want to mirror range of the CPU page table of a 709c0b12405SJérôme Glisse process into a device page table. Here, mirror means "keep synchronized". 710c0b12405SJérôme Glisse Prerequisites: the device must provide the ability to write-protect its 711c0b12405SJérôme Glisse page tables (at PAGE_SIZE granularity), and must be able to recover from 712c0b12405SJérôme Glisse the resulting potential page faults. 713c0b12405SJérôme Glisse 7145042db43SJérôme Glisseconfig DEVICE_PRIVATE 7155042db43SJérôme Glisse bool "Unaddressable device memory (GPU memory, ...)" 7165042db43SJérôme Glisse depends on ARCH_HAS_HMM 717df6ad698SJérôme Glisse select HMM 718e7638488SDan Williams select DEV_PAGEMAP_OPS 7195042db43SJérôme Glisse 7205042db43SJérôme Glisse help 7215042db43SJérôme Glisse Allows creation of struct pages to represent unaddressable device 7225042db43SJérôme Glisse memory; i.e., memory that is only accessible from the device (or 7235042db43SJérôme Glisse group of devices). You likely also want to select HMM_MIRROR. 7245042db43SJérôme Glisse 725df6ad698SJérôme Glisseconfig DEVICE_PUBLIC 726df6ad698SJérôme Glisse bool "Addressable device memory (like GPU memory)" 727df6ad698SJérôme Glisse depends on ARCH_HAS_HMM 728df6ad698SJérôme Glisse select HMM 729e7638488SDan Williams select DEV_PAGEMAP_OPS 730df6ad698SJérôme Glisse 731df6ad698SJérôme Glisse help 732df6ad698SJérôme Glisse Allows creation of struct pages to represent addressable device 733df6ad698SJérôme Glisse memory; i.e., memory that is accessible from both the device and 734df6ad698SJérôme Glisse the CPU 735df6ad698SJérôme Glisse 7368025e5ddSJan Karaconfig FRAME_VECTOR 7378025e5ddSJan Kara bool 73863c17fb8SDave Hansen 73963c17fb8SDave Hansenconfig ARCH_USES_HIGH_VMA_FLAGS 74063c17fb8SDave Hansen bool 74166d37570SDave Hansenconfig ARCH_HAS_PKEYS 74266d37570SDave Hansen bool 74330a5b536SDennis Zhou 74430a5b536SDennis Zhouconfig PERCPU_STATS 74530a5b536SDennis Zhou bool "Collect percpu memory statistics" 74630a5b536SDennis Zhou default n 74730a5b536SDennis Zhou help 74830a5b536SDennis Zhou This feature collects and exposes statistics via debugfs. The 74930a5b536SDennis Zhou information includes global and per chunk statistics, which can 75030a5b536SDennis Zhou be used to help understand percpu memory usage. 75164c349f4SKirill A. Shutemov 75264c349f4SKirill A. Shutemovconfig GUP_BENCHMARK 75364c349f4SKirill A. Shutemov bool "Enable infrastructure for get_user_pages_fast() benchmarking" 75464c349f4SKirill A. Shutemov default n 75564c349f4SKirill A. Shutemov help 75664c349f4SKirill A. Shutemov Provides /sys/kernel/debug/gup_benchmark that helps with testing 75764c349f4SKirill A. Shutemov performance of get_user_pages_fast(). 75864c349f4SKirill A. Shutemov 75964c349f4SKirill A. Shutemov See tools/testing/selftests/vm/gup_benchmark.c 760