arch: fix has_transparent_hugepage()

[mirror_ubuntu-jammy-kernel.git] / mm / Kconfig

config SELECT_MEMORY_MODEL
	def_bool y
	depends on ARCH_SELECT_MEMORY_MODEL

choice
	prompt "Memory model"
	depends on SELECT_MEMORY_MODEL
	default DISCONTIGMEM_MANUAL if ARCH_DISCONTIGMEM_DEFAULT
	default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
	default FLATMEM_MANUAL

config FLATMEM_MANUAL
	bool "Flat Memory"
	depends on !(ARCH_DISCONTIGMEM_ENABLE || ARCH_SPARSEMEM_ENABLE) || ARCH_FLATMEM_ENABLE
	help
	  This option allows you to change some of the ways that
	  Linux manages its memory internally.  Most users will
	  only have one option here: FLATMEM.  This is normal
	  and a correct option.

	  Some users of more advanced features like NUMA and
	  memory hotplug may have different options here.
	  DISCONTIGMEM is a more mature, better tested system,
	  but is incompatible with memory hotplug and may suffer
	  decreased performance over SPARSEMEM.  If unsure between
	  "Sparse Memory" and "Discontiguous Memory", choose
	  "Discontiguous Memory".

	  If unsure, choose this option (Flat Memory) over any other.

config DISCONTIGMEM_MANUAL
	bool "Discontiguous Memory"
	depends on ARCH_DISCONTIGMEM_ENABLE
	help
	  This option provides enhanced support for discontiguous
	  memory systems, over FLATMEM.  These systems have holes
	  in their physical address spaces, and this option provides
	  more efficient handling of these holes.  However, the vast
	  majority of hardware has quite flat address spaces, and
	  can have degraded performance from the extra overhead that
	  this option imposes.

	  Many NUMA configurations will have this as the only option.

	  If unsure, choose "Flat Memory" over this option.

config SPARSEMEM_MANUAL
	bool "Sparse Memory"
	depends on ARCH_SPARSEMEM_ENABLE
	help
	  This will be the only option for some systems, including
	  memory hotplug systems.  This is normal.

	  For many other systems, this will be an alternative to
	  "Discontiguous Memory".  This option provides some potential
	  performance benefits, along with decreased code complexity,
	  but it is newer, and more experimental.

	  If unsure, choose "Discontiguous Memory" or "Flat Memory"
	  over this option.

endchoice

config DISCONTIGMEM
	def_bool y
	depends on (!SELECT_MEMORY_MODEL && ARCH_DISCONTIGMEM_ENABLE) || DISCONTIGMEM_MANUAL

config SPARSEMEM
	def_bool y
	depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL

config FLATMEM
	def_bool y
	depends on (!DISCONTIGMEM && !SPARSEMEM) || FLATMEM_MANUAL

config FLAT_NODE_MEM_MAP
	def_bool y
	depends on !SPARSEMEM

#
# Both the NUMA code and DISCONTIGMEM use arrays of pg_data_t's
# to represent different areas of memory.  This variable allows
# those dependencies to exist individually.
#
config NEED_MULTIPLE_NODES
	def_bool y
	depends on DISCONTIGMEM || NUMA

config HAVE_MEMORY_PRESENT
	def_bool y
	depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM

#
# SPARSEMEM_EXTREME (which is the default) does some bootmem
# allocations when memory_present() is called.  If this cannot
# be done on your architecture, select this option.  However,
# statically allocating the mem_section[] array can potentially
# consume vast quantities of .bss, so be careful.
#
# This option will also potentially produce smaller runtime code
# with gcc 3.4 and later.
#
config SPARSEMEM_STATIC
	bool

#
# Architecture platforms which require a two level mem_section in SPARSEMEM
# must select this option. This is usually for architecture platforms with
# an extremely sparse physical address space.
#
config SPARSEMEM_EXTREME
	def_bool y
	depends on SPARSEMEM && !SPARSEMEM_STATIC

config SPARSEMEM_VMEMMAP_ENABLE
	bool

config SPARSEMEM_ALLOC_MEM_MAP_TOGETHER
	def_bool y
	depends on SPARSEMEM && X86_64

config SPARSEMEM_VMEMMAP
	bool "Sparse Memory virtual memmap"
	depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
	default y
	help
	 SPARSEMEM_VMEMMAP uses a virtually mapped memmap to optimise
	 pfn_to_page and page_to_pfn operations.  This is the most
	 efficient option when sufficient kernel resources are available.

config HAVE_MEMBLOCK
	bool

config HAVE_MEMBLOCK_NODE_MAP
	bool

config HAVE_MEMBLOCK_PHYS_MAP
	bool

config HAVE_GENERIC_RCU_GUP
	bool

config ARCH_DISCARD_MEMBLOCK
	bool

config NO_BOOTMEM
	bool

config MEMORY_ISOLATION
	bool

config MOVABLE_NODE
	bool "Enable to assign a node which has only movable memory"
	depends on HAVE_MEMBLOCK
	depends on NO_BOOTMEM
	depends on X86_64
	depends on NUMA
	default n
	help
	  Allow a node to have only movable memory.  Pages used by the kernel,
	  such as direct mapping pages cannot be migrated.  So the corresponding
	  memory device cannot be hotplugged.  This option allows the following
	  two things:
	  - When the system is booting, node full of hotpluggable memory can
	  be arranged to have only movable memory so that the whole node can
	  be hot-removed. (need movable_node boot option specified).
	  - After the system is up, the option allows users to online all the
	  memory of a node as movable memory so that the whole node can be
	  hot-removed.

	  Users who don't use the memory hotplug feature are fine with this
	  option on since they don't specify movable_node boot option or they
	  don't online memory as movable.

	  Say Y here if you want to hotplug a whole node.
	  Say N here if you want kernel to use memory on all nodes evenly.

#
# Only be set on architectures that have completely implemented memory hotplug
# feature. If you are not sure, don't touch it.
#
config HAVE_BOOTMEM_INFO_NODE
	def_bool n

# eventually, we can have this option just 'select SPARSEMEM'
config MEMORY_HOTPLUG
	bool "Allow for memory hot-add"
	depends on SPARSEMEM || X86_64_ACPI_NUMA
	depends on ARCH_ENABLE_MEMORY_HOTPLUG

config MEMORY_HOTPLUG_SPARSE
	def_bool y
	depends on SPARSEMEM && MEMORY_HOTPLUG

config MEMORY_HOTREMOVE
	bool "Allow for memory hot remove"
	select MEMORY_ISOLATION
	select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
	depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
	depends on MIGRATION

# Heavily threaded applications may benefit from splitting the mm-wide
# page_table_lock, so that faults on different parts of the user address
# space can be handled with less contention: split it at this NR_CPUS.
# Default to 4 for wider testing, though 8 might be more appropriate.
# ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
# PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
# DEBUG_SPINLOCK and DEBUG_LOCK_ALLOC spinlock_t also enlarge struct page.
#
config SPLIT_PTLOCK_CPUS
	int
	default "999999" if !MMU
	default "999999" if ARM && !CPU_CACHE_VIPT
	default "999999" if PARISC && !PA20
	default "4"

config ARCH_ENABLE_SPLIT_PMD_PTLOCK
	bool

#
# support for memory balloon
config MEMORY_BALLOON
	bool

#
# support for memory balloon compaction
config BALLOON_COMPACTION
	bool "Allow for balloon memory compaction/migration"
	def_bool y
	depends on COMPACTION && MEMORY_BALLOON
	help
	  Memory fragmentation introduced by ballooning might reduce
	  significantly the number of 2MB contiguous memory blocks that can be
	  used within a guest, thus imposing performance penalties associated
	  with the reduced number of transparent huge pages that could be used
	  by the guest workload. Allowing the compaction & migration for memory
	  pages enlisted as being part of memory balloon devices avoids the
	  scenario aforementioned and helps improving memory defragmentation.

#
# support for memory compaction
config COMPACTION
	bool "Allow for memory compaction"
	def_bool y
	select MIGRATION
	depends on MMU
	help
	  Allows the compaction of memory for the allocation of huge pages.

#
# support for page migration
#
config MIGRATION
	bool "Page migration"
	def_bool y
	depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
	help
	  Allows the migration of the physical location of pages of processes
	  while the virtual addresses are not changed. This is useful in
	  two situations. The first is on NUMA systems to put pages nearer
	  to the processors accessing. The second is when allocating huge
	  pages as migration can relocate pages to satisfy a huge page
	  allocation instead of reclaiming.

config ARCH_ENABLE_HUGEPAGE_MIGRATION
	bool

config PHYS_ADDR_T_64BIT
	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT

config BOUNCE
	bool "Enable bounce buffers"
	default y
	depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM)
	help
	  Enable bounce buffers for devices that cannot access
	  the full range of memory available to the CPU. Enabled
	  by default when ZONE_DMA or HIGHMEM is selected, but you
	  may say n to override this.

# On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often
# have more than 4GB of memory, but we don't currently use the IOTLB to present
# a 32-bit address to OHCI.  So we need to use a bounce pool instead.
config NEED_BOUNCE_POOL
	bool
	default y if TILE && USB_OHCI_HCD

config NR_QUICK
	int
	depends on QUICKLIST
	default "2" if AVR32
	default "1"

config VIRT_TO_BUS
	bool
	help
	  An architecture should select this if it implements the
	  deprecated interface virt_to_bus().  All new architectures
	  should probably not select this.


config MMU_NOTIFIER
	bool
	select SRCU

config KSM
	bool "Enable KSM for page merging"
	depends on MMU
	help
	  Enable Kernel Samepage Merging: KSM periodically scans those areas
	  of an application's address space that an app has advised may be
	  mergeable.  When it finds pages of identical content, it replaces
	  the many instances by a single page with that content, so
	  saving memory until one or another app needs to modify the content.
	  Recommended for use with KVM, or with other duplicative applications.
	  See Documentation/vm/ksm.txt for more information: KSM is inactive
	  until a program has madvised that an area is MADV_MERGEABLE, and
	  root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set).

config DEFAULT_MMAP_MIN_ADDR
        int "Low address space to protect from user allocation"
	depends on MMU
        default 4096
        help
	  This is the portion of low virtual memory which should be protected
	  from userspace allocation.  Keeping a user from writing to low pages
	  can help reduce the impact of kernel NULL pointer bugs.

	  For most ia64, ppc64 and x86 users with lots of address space
	  a value of 65536 is reasonable and should cause no problems.
	  On arm and other archs it should not be higher than 32768.
	  Programs which use vm86 functionality or have some need to map
	  this low address space will need CAP_SYS_RAWIO or disable this
	  protection by setting the value to 0.

	  This value can be changed after boot using the
	  /proc/sys/vm/mmap_min_addr tunable.

config ARCH_SUPPORTS_MEMORY_FAILURE
	bool

config MEMORY_FAILURE
	depends on MMU
	depends on ARCH_SUPPORTS_MEMORY_FAILURE
	bool "Enable recovery from hardware memory errors"
	select MEMORY_ISOLATION
	select RAS
	help
	  Enables code to recover from some memory failures on systems
	  with MCA recovery. This allows a system to continue running
	  even when some of its memory has uncorrected errors. This requires
	  special hardware support and typically ECC memory.

config HWPOISON_INJECT
	tristate "HWPoison pages injector"
	depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
	select PROC_PAGE_MONITOR

config NOMMU_INITIAL_TRIM_EXCESS
	int "Turn on mmap() excess space trimming before booting"
	depends on !MMU
	default 1
	help
	  The NOMMU mmap() frequently needs to allocate large contiguous chunks
	  of memory on which to store mappings, but it can only ask the system
	  allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
	  more than it requires.  To deal with this, mmap() is able to trim off
	  the excess and return it to the allocator.

	  If trimming is enabled, the excess is trimmed off and returned to the
	  system allocator, which can cause extra fragmentation, particularly
	  if there are a lot of transient processes.

	  If trimming is disabled, the excess is kept, but not used, which for
	  long-term mappings means that the space is wasted.

	  Trimming can be dynamically controlled through a sysctl option
	  (/proc/sys/vm/nr_trim_pages) which specifies the minimum number of
	  excess pages there must be before trimming should occur, or zero if
	  no trimming is to occur.

	  This option specifies the initial value of this option.  The default
	  of 1 says that all excess pages should be trimmed.

	  See Documentation/nommu-mmap.txt for more information.

config TRANSPARENT_HUGEPAGE
	bool "Transparent Hugepage Support"
	depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
	select COMPACTION
	help
	  Transparent Hugepages allows the kernel to use huge pages and
	  huge tlb transparently to the applications whenever possible.
	  This feature can improve computing performance to certain
	  applications by speeding up page faults during memory
	  allocation, by reducing the number of tlb misses and by speeding
	  up the pagetable walking.

	  If memory constrained on embedded, you may want to say N.

choice
	prompt "Transparent Hugepage Support sysfs defaults"
	depends on TRANSPARENT_HUGEPAGE
	default TRANSPARENT_HUGEPAGE_ALWAYS
	help
	  Selects the sysfs defaults for Transparent Hugepage Support.

	config TRANSPARENT_HUGEPAGE_ALWAYS
		bool "always"
	help
	  Enabling Transparent Hugepage always, can increase the
	  memory footprint of applications without a guaranteed
	  benefit but it will work automatically for all applications.

	config TRANSPARENT_HUGEPAGE_MADVISE
		bool "madvise"
	help
	  Enabling Transparent Hugepage madvise, will only provide a
	  performance improvement benefit to the applications using
	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
	  memory footprint of applications without a guaranteed
	  benefit.
endchoice

#
# UP and nommu archs use km based percpu allocator
#
config NEED_PER_CPU_KM
	depends on !SMP
	bool
	default y

config CLEANCACHE
	bool "Enable cleancache driver to cache clean pages if tmem is present"
	default n
	help
	  Cleancache can be thought of as a page-granularity victim cache
	  for clean pages that the kernel's pageframe replacement algorithm
	  (PFRA) would like to keep around, but can't since there isn't enough
	  memory.  So when the PFRA "evicts" a page, it first attempts to use
	  cleancache code to put the data contained in that page into
	  "transcendent memory", memory that is not directly accessible or
	  addressable by the kernel and is of unknown and possibly
	  time-varying size.  And when a cleancache-enabled
	  filesystem wishes to access a page in a file on disk, it first
	  checks cleancache to see if it already contains it; if it does,
	  the page is copied into the kernel and a disk access is avoided.
	  When a transcendent memory driver is available (such as zcache or
	  Xen transcendent memory), a significant I/O reduction
	  may be achieved.  When none is available, all cleancache calls
	  are reduced to a single pointer-compare-against-NULL resulting
	  in a negligible performance hit.

	  If unsure, say Y to enable cleancache

config FRONTSWAP
	bool "Enable frontswap to cache swap pages if tmem is present"
	depends on SWAP
	default n
	help
	  Frontswap is so named because it can be thought of as the opposite
	  of a "backing" store for a swap device.  The data is stored into
	  "transcendent memory", memory that is not directly accessible or
	  addressable by the kernel and is of unknown and possibly
	  time-varying size.  When space in transcendent memory is available,
	  a significant swap I/O reduction may be achieved.  When none is
	  available, all frontswap calls are reduced to a single pointer-
	  compare-against-NULL resulting in a negligible performance hit
	  and swap data is stored as normal on the matching swap device.

	  If unsure, say Y to enable frontswap.

config CMA
	bool "Contiguous Memory Allocator"
	depends on HAVE_MEMBLOCK && MMU
	select MIGRATION
	select MEMORY_ISOLATION
	help
	  This enables the Contiguous Memory Allocator which allows other
	  subsystems to allocate big physically-contiguous blocks of memory.
	  CMA reserves a region of memory and allows only movable pages to
	  be allocated from it. This way, the kernel can use the memory for
	  pagecache and when a subsystem requests for contiguous area, the
	  allocated pages are migrated away to serve the contiguous request.

	  If unsure, say "n".

config CMA_DEBUG
	bool "CMA debug messages (DEVELOPMENT)"
	depends on DEBUG_KERNEL && CMA
	help
	  Turns on debug messages in CMA.  This produces KERN_DEBUG
	  messages for every CMA call as well as various messages while
	  processing calls such as dma_alloc_from_contiguous().
	  This option does not affect warning and error messages.

config CMA_DEBUGFS
	bool "CMA debugfs interface"
	depends on CMA && DEBUG_FS
	help
	  Turns on the DebugFS interface for CMA.

config CMA_AREAS
	int "Maximum count of the CMA areas"
	depends on CMA
	default 7
	help
	  CMA allows to create CMA areas for particular purpose, mainly,
	  used as device private area. This parameter sets the maximum
	  number of CMA area in the system.

	  If unsure, leave the default value "7".

config MEM_SOFT_DIRTY
	bool "Track memory changes"
	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
	select PROC_PAGE_MONITOR
	help
	  This option enables memory changes tracking by introducing a
	  soft-dirty bit on pte-s. This bit it set when someone writes
	  into a page just as regular dirty bit, but unlike the latter
	  it can be cleared by hands.

	  See Documentation/vm/soft-dirty.txt for more details.

config ZSWAP
	bool "Compressed cache for swap pages (EXPERIMENTAL)"
	depends on FRONTSWAP && CRYPTO=y
	select CRYPTO_LZO
	select ZPOOL
	default n
	help
	  A lightweight compressed cache for swap pages.  It takes
	  pages that are in the process of being swapped out and attempts to
	  compress them into a dynamically allocated RAM-based memory pool.
	  This can result in a significant I/O reduction on swap device and,
	  in the case where decompressing from RAM is faster that swap device
	  reads, can also improve workload performance.

	  This is marked experimental because it is a new feature (as of
	  v3.11) that interacts heavily with memory reclaim.  While these
	  interactions don't cause any known issues on simple memory setups,
	  they have not be fully explored on the large set of potential
	  configurations and workloads that exist.

config ZPOOL
	tristate "Common API for compressed memory storage"
	default n
	help
	  Compressed memory storage API.  This allows using either zbud or
	  zsmalloc.

config ZBUD
	tristate "Low density storage for compressed pages"
	default n
	help
	  A special purpose allocator for storing compressed pages.
	  It is designed to store up to two compressed pages per physical
	  page.  While this design limits storage density, it has simple and
	  deterministic reclaim properties that make it preferable to a higher
	  density approach when reclaim will be used.

config ZSMALLOC
	tristate "Memory allocator for compressed pages"
	depends on MMU
	default n
	help
	  zsmalloc is a slab-based memory allocator designed to store
	  compressed RAM pages.  zsmalloc uses virtual memory mapping
	  in order to reduce fragmentation.  However, this results in a
	  non-standard allocator interface where a handle, not a pointer, is
	  returned by an alloc().  This handle must be mapped in order to
	  access the allocated space.

config PGTABLE_MAPPING
	bool "Use page table mapping to access object in zsmalloc"
	depends on ZSMALLOC
	help
	  By default, zsmalloc uses a copy-based object mapping method to
	  access allocations that span two pages. However, if a particular
	  architecture (ex, ARM) performs VM mapping faster than copying,
	  then you should select this. This causes zsmalloc to use page table
	  mapping rather than copying for object mapping.

	  You can check speed with zsmalloc benchmark:
	  https://github.com/spartacus06/zsmapbench

config ZSMALLOC_STAT
	bool "Export zsmalloc statistics"
	depends on ZSMALLOC
	select DEBUG_FS
	help
	  This option enables code in the zsmalloc to collect various
	  statistics about whats happening in zsmalloc and exports that
	  information to userspace via debugfs.
	  If unsure, say N.

config GENERIC_EARLY_IOREMAP
	bool

config MAX_STACK_SIZE_MB
	int "Maximum user stack size for 32-bit processes (MB)"
	default 80
	range 8 256 if METAG
	range 8 2048
	depends on STACK_GROWSUP && (!64BIT || COMPAT)
	help
	  This is the maximum stack size in Megabytes in the VM layout of 32-bit
	  user processes when the stack grows upwards (currently only on parisc
	  and metag arch). The stack will be located at the highest memory
	  address minus the given value, unless the RLIMIT_STACK hard limit is
	  changed to a smaller value in which case that is used.

	  A sane initial value is 80 MB.

# For architectures that support deferred memory initialisation
config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
	bool

config DEFERRED_STRUCT_PAGE_INIT
	bool "Defer initialisation of struct pages to kthreads"
	default n
	depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
	depends on MEMORY_HOTPLUG
	help
	  Ordinarily all struct pages are initialised during early boot in a
	  single thread. On very large machines this can take a considerable
	  amount of time. If this option is set, large machines will bring up
	  a subset of memmap at boot and then initialise the rest in parallel
	  by starting one-off "pgdatinitX" kernel thread for each node X. This
	  has a potential performance impact on processes running early in the
	  lifetime of the system until these kthreads finish the
	  initialisation.

config IDLE_PAGE_TRACKING
	bool "Enable idle page tracking"
	depends on SYSFS && MMU
	select PAGE_EXTENSION if !64BIT
	help
	  This feature allows to estimate the amount of user pages that have
	  not been touched during a given period of time. This information can
	  be useful to tune memory cgroup limits and/or for job placement
	  within a compute cluster.

	  See Documentation/vm/idle_page_tracking.txt for more details.

config ZONE_DEVICE
	bool "Device memory (pmem, etc...) hotplug support" if EXPERT
	depends on MEMORY_HOTPLUG
	depends on MEMORY_HOTREMOVE
	depends on SPARSEMEM_VMEMMAP
	depends on X86_64 #arch_add_memory() comprehends device memory

	help
	  Device memory hotplug support allows for establishing pmem,
	  or other device driver discovered memory regions, in the
	  memmap. This allows pfn_to_page() lookups of otherwise
	  "device-physical" addresses which is needed for using a DAX
	  mapping in an O_DIRECT operation, among other things.

	  If FS_DAX is enabled, then say Y.

config FRAME_VECTOR
	bool

config ARCH_USES_HIGH_VMA_FLAGS
	bool
config ARCH_HAS_PKEYS
	bool