mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-12-05 10:04:12 +08:00
c235698355
- Introduce a 'struct cxl_region' object with support for provisioning and assembling persistent memory regions. - Introduce alloc_free_mem_region() to accompany the existing request_free_mem_region() as a method to allocate physical memory capacity out of an existing resource. - Export insert_resource_expand_to_fit() for the CXL subsystem to late-publish CXL platform windows in iomem_resource. - Add a polled mode PCI DOE (Data Object Exchange) driver service and use it in cxl_pci to retrieve the CDAT (Coherent Device Attribute Table). -----BEGIN PGP SIGNATURE----- iHUEABYKAB0WIQSbo+XnGs+rwLz9XGXfioYZHlFsZwUCYvLYmAAKCRDfioYZHlFs Z0pbAQC/3j+WriWpU7CdhrnZI1Wqn+x5IIklF0Lc4/f6LwGZtAEAsSbLpItzvwqx M/rcLaeLpwYlgvS1JjdsuQ2VQ7KOtAs= =ehNT -----END PGP SIGNATURE----- Merge tag 'cxl-for-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl Pull cxl updates from Dan Williams: "Compute Express Link (CXL) updates for 6.0: - Introduce a 'struct cxl_region' object with support for provisioning and assembling persistent memory regions. - Introduce alloc_free_mem_region() to accompany the existing request_free_mem_region() as a method to allocate physical memory capacity out of an existing resource. - Export insert_resource_expand_to_fit() for the CXL subsystem to late-publish CXL platform windows in iomem_resource. - Add a polled mode PCI DOE (Data Object Exchange) driver service and use it in cxl_pci to retrieve the CDAT (Coherent Device Attribute Table)" * tag 'cxl-for-6.0' of git://git.kernel.org/pub/scm/linux/kernel/git/cxl/cxl: (74 commits) cxl/hdm: Fix skip allocations vs multiple pmem allocations cxl/region: Disallow region granularity != window granularity cxl/region: Fix x1 interleave to greater than x1 interleave routing cxl/region: Move HPA setup to cxl_region_attach() cxl/region: Fix decoder interleave programming Documentation: cxl: remove dangling kernel-doc reference cxl/region: describe targets and nr_targets members of cxl_region_params cxl/regions: add padding for cxl_rr_ep_add nested lists cxl/region: Fix IS_ERR() vs NULL check cxl/region: Fix region reference target accounting cxl/region: Fix region commit uninitialized variable warning cxl/region: Fix port setup uninitialized variable warnings cxl/region: Stop initializing interleave granularity cxl/hdm: Fix DPA reservation vs cxl_endpoint_decoder lifetime cxl/acpi: Minimize granularity for x1 interleaves cxl/region: Delete 'region' attribute from root decoders cxl/acpi: Autoload driver for 'cxl_acpi' test devices cxl/region: decrement ->nr_targets on error in cxl_region_attach() cxl/region: prevent underflow in ways_to_cxl() cxl/region: uninitialized variable in alloc_hpa() ...
1130 lines
35 KiB
Plaintext
1130 lines
35 KiB
Plaintext
# SPDX-License-Identifier: GPL-2.0-only
|
|
|
|
menu "Memory Management options"
|
|
|
|
#
|
|
# For some reason microblaze and nios2 hard code SWAP=n. Hopefully we can
|
|
# add proper SWAP support to them, in which case this can be remove.
|
|
#
|
|
config ARCH_NO_SWAP
|
|
bool
|
|
|
|
config ZPOOL
|
|
bool
|
|
|
|
menuconfig SWAP
|
|
bool "Support for paging of anonymous memory (swap)"
|
|
depends on MMU && BLOCK && !ARCH_NO_SWAP
|
|
default y
|
|
help
|
|
This option allows you to choose whether you want to have support
|
|
for so called swap devices or swap files in your kernel that are
|
|
used to provide more virtual memory than the actual RAM present
|
|
in your computer. If unsure say Y.
|
|
|
|
config ZSWAP
|
|
bool "Compressed cache for swap pages (EXPERIMENTAL)"
|
|
depends on SWAP
|
|
select FRONTSWAP
|
|
select CRYPTO
|
|
select ZPOOL
|
|
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 than 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 ZSWAP_DEFAULT_ON
|
|
bool "Enable the compressed cache for swap pages by default"
|
|
depends on ZSWAP
|
|
help
|
|
If selected, the compressed cache for swap pages will be enabled
|
|
at boot, otherwise it will be disabled.
|
|
|
|
The selection made here can be overridden by using the kernel
|
|
command line 'zswap.enabled=' option.
|
|
|
|
choice
|
|
prompt "Default compressor"
|
|
depends on ZSWAP
|
|
default ZSWAP_COMPRESSOR_DEFAULT_LZO
|
|
help
|
|
Selects the default compression algorithm for the compressed cache
|
|
for swap pages.
|
|
|
|
For an overview what kind of performance can be expected from
|
|
a particular compression algorithm please refer to the benchmarks
|
|
available at the following LWN page:
|
|
https://lwn.net/Articles/751795/
|
|
|
|
If in doubt, select 'LZO'.
|
|
|
|
The selection made here can be overridden by using the kernel
|
|
command line 'zswap.compressor=' option.
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
|
|
bool "Deflate"
|
|
select CRYPTO_DEFLATE
|
|
help
|
|
Use the Deflate algorithm as the default compression algorithm.
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT_LZO
|
|
bool "LZO"
|
|
select CRYPTO_LZO
|
|
help
|
|
Use the LZO algorithm as the default compression algorithm.
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT_842
|
|
bool "842"
|
|
select CRYPTO_842
|
|
help
|
|
Use the 842 algorithm as the default compression algorithm.
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT_LZ4
|
|
bool "LZ4"
|
|
select CRYPTO_LZ4
|
|
help
|
|
Use the LZ4 algorithm as the default compression algorithm.
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
|
|
bool "LZ4HC"
|
|
select CRYPTO_LZ4HC
|
|
help
|
|
Use the LZ4HC algorithm as the default compression algorithm.
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT_ZSTD
|
|
bool "zstd"
|
|
select CRYPTO_ZSTD
|
|
help
|
|
Use the zstd algorithm as the default compression algorithm.
|
|
endchoice
|
|
|
|
config ZSWAP_COMPRESSOR_DEFAULT
|
|
string
|
|
depends on ZSWAP
|
|
default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
|
|
default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO
|
|
default "842" if ZSWAP_COMPRESSOR_DEFAULT_842
|
|
default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4
|
|
default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
|
|
default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD
|
|
default ""
|
|
|
|
choice
|
|
prompt "Default allocator"
|
|
depends on ZSWAP
|
|
default ZSWAP_ZPOOL_DEFAULT_ZBUD
|
|
help
|
|
Selects the default allocator for the compressed cache for
|
|
swap pages.
|
|
The default is 'zbud' for compatibility, however please do
|
|
read the description of each of the allocators below before
|
|
making a right choice.
|
|
|
|
The selection made here can be overridden by using the kernel
|
|
command line 'zswap.zpool=' option.
|
|
|
|
config ZSWAP_ZPOOL_DEFAULT_ZBUD
|
|
bool "zbud"
|
|
select ZBUD
|
|
help
|
|
Use the zbud allocator as the default allocator.
|
|
|
|
config ZSWAP_ZPOOL_DEFAULT_Z3FOLD
|
|
bool "z3fold"
|
|
select Z3FOLD
|
|
help
|
|
Use the z3fold allocator as the default allocator.
|
|
|
|
config ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
|
|
bool "zsmalloc"
|
|
select ZSMALLOC
|
|
help
|
|
Use the zsmalloc allocator as the default allocator.
|
|
endchoice
|
|
|
|
config ZSWAP_ZPOOL_DEFAULT
|
|
string
|
|
depends on ZSWAP
|
|
default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD
|
|
default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD
|
|
default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
|
|
default ""
|
|
|
|
config ZBUD
|
|
tristate "2:1 compression allocator (zbud)"
|
|
depends on ZSWAP
|
|
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 Z3FOLD
|
|
tristate "3:1 compression allocator (z3fold)"
|
|
depends on ZSWAP
|
|
help
|
|
A special purpose allocator for storing compressed pages.
|
|
It is designed to store up to three compressed pages per physical
|
|
page. It is a ZBUD derivative so the simplicity and determinism are
|
|
still there.
|
|
|
|
config ZSMALLOC
|
|
tristate
|
|
prompt "N:1 compression allocator (zsmalloc)" if ZSWAP
|
|
depends on MMU
|
|
help
|
|
zsmalloc is a slab-based memory allocator designed to store
|
|
pages of various compression levels efficiently. It achieves
|
|
the highest storage density with the least amount of fragmentation.
|
|
|
|
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 what's happening in zsmalloc and exports that
|
|
information to userspace via debugfs.
|
|
If unsure, say N.
|
|
|
|
menu "SLAB allocator options"
|
|
|
|
choice
|
|
prompt "Choose SLAB allocator"
|
|
default SLUB
|
|
help
|
|
This option allows to select a slab allocator.
|
|
|
|
config SLAB
|
|
bool "SLAB"
|
|
depends on !PREEMPT_RT
|
|
select HAVE_HARDENED_USERCOPY_ALLOCATOR
|
|
help
|
|
The regular slab allocator that is established and known to work
|
|
well in all environments. It organizes cache hot objects in
|
|
per cpu and per node queues.
|
|
|
|
config SLUB
|
|
bool "SLUB (Unqueued Allocator)"
|
|
select HAVE_HARDENED_USERCOPY_ALLOCATOR
|
|
help
|
|
SLUB is a slab allocator that minimizes cache line usage
|
|
instead of managing queues of cached objects (SLAB approach).
|
|
Per cpu caching is realized using slabs of objects instead
|
|
of queues of objects. SLUB can use memory efficiently
|
|
and has enhanced diagnostics. SLUB is the default choice for
|
|
a slab allocator.
|
|
|
|
config SLOB
|
|
depends on EXPERT
|
|
bool "SLOB (Simple Allocator)"
|
|
depends on !PREEMPT_RT
|
|
help
|
|
SLOB replaces the stock allocator with a drastically simpler
|
|
allocator. SLOB is generally more space efficient but
|
|
does not perform as well on large systems.
|
|
|
|
endchoice
|
|
|
|
config SLAB_MERGE_DEFAULT
|
|
bool "Allow slab caches to be merged"
|
|
default y
|
|
depends on SLAB || SLUB
|
|
help
|
|
For reduced kernel memory fragmentation, slab caches can be
|
|
merged when they share the same size and other characteristics.
|
|
This carries a risk of kernel heap overflows being able to
|
|
overwrite objects from merged caches (and more easily control
|
|
cache layout), which makes such heap attacks easier to exploit
|
|
by attackers. By keeping caches unmerged, these kinds of exploits
|
|
can usually only damage objects in the same cache. To disable
|
|
merging at runtime, "slab_nomerge" can be passed on the kernel
|
|
command line.
|
|
|
|
config SLAB_FREELIST_RANDOM
|
|
bool "Randomize slab freelist"
|
|
depends on SLAB || SLUB
|
|
help
|
|
Randomizes the freelist order used on creating new pages. This
|
|
security feature reduces the predictability of the kernel slab
|
|
allocator against heap overflows.
|
|
|
|
config SLAB_FREELIST_HARDENED
|
|
bool "Harden slab freelist metadata"
|
|
depends on SLAB || SLUB
|
|
help
|
|
Many kernel heap attacks try to target slab cache metadata and
|
|
other infrastructure. This options makes minor performance
|
|
sacrifices to harden the kernel slab allocator against common
|
|
freelist exploit methods. Some slab implementations have more
|
|
sanity-checking than others. This option is most effective with
|
|
CONFIG_SLUB.
|
|
|
|
config SLUB_STATS
|
|
default n
|
|
bool "Enable SLUB performance statistics"
|
|
depends on SLUB && SYSFS
|
|
help
|
|
SLUB statistics are useful to debug SLUBs allocation behavior in
|
|
order find ways to optimize the allocator. This should never be
|
|
enabled for production use since keeping statistics slows down
|
|
the allocator by a few percentage points. The slabinfo command
|
|
supports the determination of the most active slabs to figure
|
|
out which slabs are relevant to a particular load.
|
|
Try running: slabinfo -DA
|
|
|
|
config SLUB_CPU_PARTIAL
|
|
default y
|
|
depends on SLUB && SMP
|
|
bool "SLUB per cpu partial cache"
|
|
help
|
|
Per cpu partial caches accelerate objects allocation and freeing
|
|
that is local to a processor at the price of more indeterminism
|
|
in the latency of the free. On overflow these caches will be cleared
|
|
which requires the taking of locks that may cause latency spikes.
|
|
Typically one would choose no for a realtime system.
|
|
|
|
endmenu # SLAB allocator options
|
|
|
|
config SHUFFLE_PAGE_ALLOCATOR
|
|
bool "Page allocator randomization"
|
|
default SLAB_FREELIST_RANDOM && ACPI_NUMA
|
|
help
|
|
Randomization of the page allocator improves the average
|
|
utilization of a direct-mapped memory-side-cache. See section
|
|
5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI
|
|
6.2a specification for an example of how a platform advertises
|
|
the presence of a memory-side-cache. There are also incidental
|
|
security benefits as it reduces the predictability of page
|
|
allocations to compliment SLAB_FREELIST_RANDOM, but the
|
|
default granularity of shuffling on the "MAX_ORDER - 1" i.e,
|
|
10th order of pages is selected based on cache utilization
|
|
benefits on x86.
|
|
|
|
While the randomization improves cache utilization it may
|
|
negatively impact workloads on platforms without a cache. For
|
|
this reason, by default, the randomization is enabled only
|
|
after runtime detection of a direct-mapped memory-side-cache.
|
|
Otherwise, the randomization may be force enabled with the
|
|
'page_alloc.shuffle' kernel command line parameter.
|
|
|
|
Say Y if unsure.
|
|
|
|
config COMPAT_BRK
|
|
bool "Disable heap randomization"
|
|
default y
|
|
help
|
|
Randomizing heap placement makes heap exploits harder, but it
|
|
also breaks ancient binaries (including anything libc5 based).
|
|
This option changes the bootup default to heap randomization
|
|
disabled, and can be overridden at runtime by setting
|
|
/proc/sys/kernel/randomize_va_space to 2.
|
|
|
|
On non-ancient distros (post-2000 ones) N is usually a safe choice.
|
|
|
|
config MMAP_ALLOW_UNINITIALIZED
|
|
bool "Allow mmapped anonymous memory to be uninitialized"
|
|
depends on EXPERT && !MMU
|
|
default n
|
|
help
|
|
Normally, and according to the Linux spec, anonymous memory obtained
|
|
from mmap() has its contents cleared before it is passed to
|
|
userspace. Enabling this config option allows you to request that
|
|
mmap() skip that if it is given an MAP_UNINITIALIZED flag, thus
|
|
providing a huge performance boost. If this option is not enabled,
|
|
then the flag will be ignored.
|
|
|
|
This is taken advantage of by uClibc's malloc(), and also by
|
|
ELF-FDPIC binfmt's brk and stack allocator.
|
|
|
|
Because of the obvious security issues, this option should only be
|
|
enabled on embedded devices where you control what is run in
|
|
userspace. Since that isn't generally a problem on no-MMU systems,
|
|
it is normally safe to say Y here.
|
|
|
|
See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
|
|
|
|
config SELECT_MEMORY_MODEL
|
|
def_bool y
|
|
depends on ARCH_SELECT_MEMORY_MODEL
|
|
|
|
choice
|
|
prompt "Memory model"
|
|
depends on SELECT_MEMORY_MODEL
|
|
default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
|
|
default FLATMEM_MANUAL
|
|
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 selected by the architecture
|
|
configuration. This is normal.
|
|
|
|
config FLATMEM_MANUAL
|
|
bool "Flat Memory"
|
|
depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE
|
|
help
|
|
This option is best suited for non-NUMA systems with
|
|
flat address space. The FLATMEM is the most efficient
|
|
system in terms of performance and resource consumption
|
|
and it is the best option for smaller systems.
|
|
|
|
For systems that have holes in their physical address
|
|
spaces and for features like NUMA and memory hotplug,
|
|
choose "Sparse Memory".
|
|
|
|
If unsure, choose this option (Flat Memory) over any other.
|
|
|
|
config SPARSEMEM_MANUAL
|
|
bool "Sparse Memory"
|
|
depends on ARCH_SPARSEMEM_ENABLE
|
|
help
|
|
This will be the only option for some systems, including
|
|
memory hot-plug systems. This is normal.
|
|
|
|
This option provides efficient support for systems with
|
|
holes is their physical address space and allows memory
|
|
hot-plug and hot-remove.
|
|
|
|
If unsure, choose "Flat Memory" over this option.
|
|
|
|
endchoice
|
|
|
|
config SPARSEMEM
|
|
def_bool y
|
|
depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
|
|
|
|
config FLATMEM
|
|
def_bool y
|
|
depends on !SPARSEMEM || FLATMEM_MANUAL
|
|
|
|
#
|
|
# SPARSEMEM_EXTREME (which is the default) does some bootmem
|
|
# allocations when sparse_init() 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_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_PHYS_MAP
|
|
bool
|
|
|
|
config HAVE_FAST_GUP
|
|
depends on MMU
|
|
bool
|
|
|
|
# Don't discard allocated memory used to track "memory" and "reserved" memblocks
|
|
# after early boot, so it can still be used to test for validity of memory.
|
|
# Also, memblocks are updated with memory hot(un)plug.
|
|
config ARCH_KEEP_MEMBLOCK
|
|
bool
|
|
|
|
# Keep arch NUMA mapping infrastructure post-init.
|
|
config NUMA_KEEP_MEMINFO
|
|
bool
|
|
|
|
config MEMORY_ISOLATION
|
|
bool
|
|
|
|
# IORESOURCE_SYSTEM_RAM regions in the kernel resource tree that are marked
|
|
# IORESOURCE_EXCLUSIVE cannot be mapped to user space, for example, via
|
|
# /dev/mem.
|
|
config EXCLUSIVE_SYSTEM_RAM
|
|
def_bool y
|
|
depends on !DEVMEM || STRICT_DEVMEM
|
|
|
|
#
|
|
# 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
|
|
|
|
config ARCH_ENABLE_MEMORY_HOTPLUG
|
|
bool
|
|
|
|
config ARCH_ENABLE_MEMORY_HOTREMOVE
|
|
bool
|
|
|
|
# eventually, we can have this option just 'select SPARSEMEM'
|
|
menuconfig MEMORY_HOTPLUG
|
|
bool "Memory hotplug"
|
|
select MEMORY_ISOLATION
|
|
depends on SPARSEMEM
|
|
depends on ARCH_ENABLE_MEMORY_HOTPLUG
|
|
depends on 64BIT
|
|
select NUMA_KEEP_MEMINFO if NUMA
|
|
|
|
if MEMORY_HOTPLUG
|
|
|
|
config MEMORY_HOTPLUG_DEFAULT_ONLINE
|
|
bool "Online the newly added memory blocks by default"
|
|
depends on MEMORY_HOTPLUG
|
|
help
|
|
This option sets the default policy setting for memory hotplug
|
|
onlining policy (/sys/devices/system/memory/auto_online_blocks) which
|
|
determines what happens to newly added memory regions. Policy setting
|
|
can always be changed at runtime.
|
|
See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
|
|
|
|
Say Y here if you want all hot-plugged memory blocks to appear in
|
|
'online' state by default.
|
|
Say N here if you want the default policy to keep all hot-plugged
|
|
memory blocks in 'offline' state.
|
|
|
|
config MEMORY_HOTREMOVE
|
|
bool "Allow for memory hot remove"
|
|
select HAVE_BOOTMEM_INFO_NODE if (X86_64 || PPC64)
|
|
depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
|
|
depends on MIGRATION
|
|
|
|
config MHP_MEMMAP_ON_MEMORY
|
|
def_bool y
|
|
depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
|
|
depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
|
|
|
|
endif # MEMORY_HOTPLUG
|
|
|
|
# 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.
|
|
# SPARC32 allocates multiple pte tables within a single page, and therefore
|
|
# a per-page lock leads to problems when multiple tables need to be locked
|
|
# at the same time (e.g. copy_page_range()).
|
|
# 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 "999999" if SPARC32
|
|
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
|
|
Compaction is the only memory management component to form
|
|
high order (larger physically contiguous) memory blocks
|
|
reliably. The page allocator relies on compaction heavily and
|
|
the lack of the feature can lead to unexpected OOM killer
|
|
invocations for high order memory requests. You shouldn't
|
|
disable this option unless there really is a strong reason for
|
|
it and then we would be really interested to hear about that at
|
|
linux-mm@kvack.org.
|
|
|
|
#
|
|
# support for free page reporting
|
|
config PAGE_REPORTING
|
|
bool "Free page reporting"
|
|
def_bool n
|
|
help
|
|
Free page reporting allows for the incremental acquisition of
|
|
free pages from the buddy allocator for the purpose of reporting
|
|
those pages to another entity, such as a hypervisor, so that the
|
|
memory can be freed within the host for other uses.
|
|
|
|
#
|
|
# 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 DEVICE_MIGRATION
|
|
def_bool MIGRATION && ZONE_DEVICE
|
|
|
|
config ARCH_ENABLE_HUGEPAGE_MIGRATION
|
|
bool
|
|
|
|
config ARCH_ENABLE_THP_MIGRATION
|
|
bool
|
|
|
|
config HUGETLB_PAGE_SIZE_VARIABLE
|
|
def_bool n
|
|
help
|
|
Allows the pageblock_order value to be dynamic instead of just standard
|
|
HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available
|
|
on a platform.
|
|
|
|
Note that the pageblock_order cannot exceed MAX_ORDER - 1 and will be
|
|
clamped down to MAX_ORDER - 1.
|
|
|
|
config CONTIG_ALLOC
|
|
def_bool (MEMORY_ISOLATION && COMPACTION) || CMA
|
|
|
|
config PHYS_ADDR_T_64BIT
|
|
def_bool 64BIT
|
|
|
|
config BOUNCE
|
|
bool "Enable bounce buffers"
|
|
default y
|
|
depends on BLOCK && MMU && HIGHMEM
|
|
help
|
|
Enable bounce buffers for devices that cannot access the full range of
|
|
memory available to the CPU. Enabled by default when HIGHMEM is
|
|
selected, but you may say n to override this.
|
|
|
|
config MMU_NOTIFIER
|
|
bool
|
|
select SRCU
|
|
select INTERVAL_TREE
|
|
|
|
config KSM
|
|
bool "Enable KSM for page merging"
|
|
depends on MMU
|
|
select XXHASH
|
|
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/mm/ksm.rst 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/admin-guide/mm/nommu-mmap.rst for more information.
|
|
|
|
config ARCH_WANT_GENERAL_HUGETLB
|
|
bool
|
|
|
|
config ARCH_WANTS_THP_SWAP
|
|
def_bool n
|
|
|
|
menuconfig TRANSPARENT_HUGEPAGE
|
|
bool "Transparent Hugepage Support"
|
|
depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT
|
|
select COMPACTION
|
|
select XARRAY_MULTI
|
|
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.
|
|
|
|
if TRANSPARENT_HUGEPAGE
|
|
|
|
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
|
|
|
|
config THP_SWAP
|
|
def_bool y
|
|
depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP
|
|
help
|
|
Swap transparent huge pages in one piece, without splitting.
|
|
XXX: For now, swap cluster backing transparent huge page
|
|
will be split after swapout.
|
|
|
|
For selection by architectures with reasonable THP sizes.
|
|
|
|
config READ_ONLY_THP_FOR_FS
|
|
bool "Read-only THP for filesystems (EXPERIMENTAL)"
|
|
depends on TRANSPARENT_HUGEPAGE && SHMEM
|
|
|
|
help
|
|
Allow khugepaged to put read-only file-backed pages in THP.
|
|
|
|
This is marked experimental because it is a new feature. Write
|
|
support of file THPs will be developed in the next few release
|
|
cycles.
|
|
|
|
endif # TRANSPARENT_HUGEPAGE
|
|
|
|
#
|
|
# UP and nommu archs use km based percpu allocator
|
|
#
|
|
config NEED_PER_CPU_KM
|
|
depends on !SMP || !MMU
|
|
bool
|
|
default y
|
|
|
|
config NEED_PER_CPU_EMBED_FIRST_CHUNK
|
|
bool
|
|
|
|
config NEED_PER_CPU_PAGE_FIRST_CHUNK
|
|
bool
|
|
|
|
config USE_PERCPU_NUMA_NODE_ID
|
|
bool
|
|
|
|
config HAVE_SETUP_PER_CPU_AREA
|
|
bool
|
|
|
|
config FRONTSWAP
|
|
bool
|
|
|
|
config CMA
|
|
bool "Contiguous Memory Allocator"
|
|
depends on 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_SYSFS
|
|
bool "CMA information through sysfs interface"
|
|
depends on CMA && SYSFS
|
|
help
|
|
This option exposes some sysfs attributes to get information
|
|
from CMA.
|
|
|
|
config CMA_AREAS
|
|
int "Maximum count of the CMA areas"
|
|
depends on CMA
|
|
default 19 if NUMA
|
|
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" in UMA and "19" in NUMA.
|
|
|
|
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/admin-guide/mm/soft-dirty.rst for more details.
|
|
|
|
config GENERIC_EARLY_IOREMAP
|
|
bool
|
|
|
|
config STACK_MAX_DEFAULT_SIZE_MB
|
|
int "Default maximum user stack size for 32-bit processes (MB)"
|
|
default 100
|
|
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
|
|
arch) when the RLIMIT_STACK hard limit is unlimited.
|
|
|
|
A sane initial value is 100 MB.
|
|
|
|
config DEFERRED_STRUCT_PAGE_INIT
|
|
bool "Defer initialisation of struct pages to kthreads"
|
|
depends on SPARSEMEM
|
|
depends on !NEED_PER_CPU_KM
|
|
depends on 64BIT
|
|
select PADATA
|
|
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.
|
|
This has a potential performance impact on tasks running early in the
|
|
lifetime of the system until these kthreads finish the
|
|
initialisation.
|
|
|
|
config PAGE_IDLE_FLAG
|
|
bool
|
|
select PAGE_EXTENSION if !64BIT
|
|
help
|
|
This adds PG_idle and PG_young flags to 'struct page'. PTE Accessed
|
|
bit writers can set the state of the bit in the flags so that PTE
|
|
Accessed bit readers may avoid disturbance.
|
|
|
|
config IDLE_PAGE_TRACKING
|
|
bool "Enable idle page tracking"
|
|
depends on SYSFS && MMU
|
|
select PAGE_IDLE_FLAG
|
|
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/admin-guide/mm/idle_page_tracking.rst for
|
|
more details.
|
|
|
|
config ARCH_HAS_CACHE_LINE_SIZE
|
|
bool
|
|
|
|
config ARCH_HAS_CURRENT_STACK_POINTER
|
|
bool
|
|
help
|
|
In support of HARDENED_USERCOPY performing stack variable lifetime
|
|
checking, an architecture-agnostic way to find the stack pointer
|
|
is needed. Once an architecture defines an unsigned long global
|
|
register alias named "current_stack_pointer", this config can be
|
|
selected.
|
|
|
|
config ARCH_HAS_PTE_DEVMAP
|
|
bool
|
|
|
|
config ARCH_HAS_ZONE_DMA_SET
|
|
bool
|
|
|
|
config ZONE_DMA
|
|
bool "Support DMA zone" if ARCH_HAS_ZONE_DMA_SET
|
|
default y if ARM64 || X86
|
|
|
|
config ZONE_DMA32
|
|
bool "Support DMA32 zone" if ARCH_HAS_ZONE_DMA_SET
|
|
depends on !X86_32
|
|
default y if ARM64
|
|
|
|
config ZONE_DEVICE
|
|
bool "Device memory (pmem, HMM, etc...) hotplug support"
|
|
depends on MEMORY_HOTPLUG
|
|
depends on MEMORY_HOTREMOVE
|
|
depends on SPARSEMEM_VMEMMAP
|
|
depends on ARCH_HAS_PTE_DEVMAP
|
|
select XARRAY_MULTI
|
|
|
|
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.
|
|
|
|
#
|
|
# Helpers to mirror range of the CPU page tables of a process into device page
|
|
# tables.
|
|
#
|
|
config HMM_MIRROR
|
|
bool
|
|
depends on MMU
|
|
|
|
config GET_FREE_REGION
|
|
depends on SPARSEMEM
|
|
bool
|
|
|
|
config DEVICE_PRIVATE
|
|
bool "Unaddressable device memory (GPU memory, ...)"
|
|
depends on ZONE_DEVICE
|
|
select GET_FREE_REGION
|
|
|
|
help
|
|
Allows creation of struct pages to represent unaddressable device
|
|
memory; i.e., memory that is only accessible from the device (or
|
|
group of devices). You likely also want to select HMM_MIRROR.
|
|
|
|
config VMAP_PFN
|
|
bool
|
|
|
|
config ARCH_USES_HIGH_VMA_FLAGS
|
|
bool
|
|
config ARCH_HAS_PKEYS
|
|
bool
|
|
|
|
config VM_EVENT_COUNTERS
|
|
default y
|
|
bool "Enable VM event counters for /proc/vmstat" if EXPERT
|
|
help
|
|
VM event counters are needed for event counts to be shown.
|
|
This option allows the disabling of the VM event counters
|
|
on EXPERT systems. /proc/vmstat will only show page counts
|
|
if VM event counters are disabled.
|
|
|
|
config PERCPU_STATS
|
|
bool "Collect percpu memory statistics"
|
|
help
|
|
This feature collects and exposes statistics via debugfs. The
|
|
information includes global and per chunk statistics, which can
|
|
be used to help understand percpu memory usage.
|
|
|
|
config GUP_TEST
|
|
bool "Enable infrastructure for get_user_pages()-related unit tests"
|
|
depends on DEBUG_FS
|
|
help
|
|
Provides /sys/kernel/debug/gup_test, which in turn provides a way
|
|
to make ioctl calls that can launch kernel-based unit tests for
|
|
the get_user_pages*() and pin_user_pages*() family of API calls.
|
|
|
|
These tests include benchmark testing of the _fast variants of
|
|
get_user_pages*() and pin_user_pages*(), as well as smoke tests of
|
|
the non-_fast variants.
|
|
|
|
There is also a sub-test that allows running dump_page() on any
|
|
of up to eight pages (selected by command line args) within the
|
|
range of user-space addresses. These pages are either pinned via
|
|
pin_user_pages*(), or pinned via get_user_pages*(), as specified
|
|
by other command line arguments.
|
|
|
|
See tools/testing/selftests/vm/gup_test.c
|
|
|
|
comment "GUP_TEST needs to have DEBUG_FS enabled"
|
|
depends on !GUP_TEST && !DEBUG_FS
|
|
|
|
config GUP_GET_PTE_LOW_HIGH
|
|
bool
|
|
|
|
config ARCH_HAS_PTE_SPECIAL
|
|
bool
|
|
|
|
#
|
|
# Some architectures require a special hugepage directory format that is
|
|
# required to support multiple hugepage sizes. For example a4fe3ce76
|
|
# "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
|
|
# introduced it on powerpc. This allows for a more flexible hugepage
|
|
# pagetable layouts.
|
|
#
|
|
config ARCH_HAS_HUGEPD
|
|
bool
|
|
|
|
config MAPPING_DIRTY_HELPERS
|
|
bool
|
|
|
|
config KMAP_LOCAL
|
|
bool
|
|
|
|
config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
|
|
bool
|
|
|
|
# struct io_mapping based helper. Selected by drivers that need them
|
|
config IO_MAPPING
|
|
bool
|
|
|
|
config SECRETMEM
|
|
def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
|
|
|
|
config ANON_VMA_NAME
|
|
bool "Anonymous VMA name support"
|
|
depends on PROC_FS && ADVISE_SYSCALLS && MMU
|
|
|
|
help
|
|
Allow naming anonymous virtual memory areas.
|
|
|
|
This feature allows assigning names to virtual memory areas. Assigned
|
|
names can be later retrieved from /proc/pid/maps and /proc/pid/smaps
|
|
and help identifying individual anonymous memory areas.
|
|
Assigning a name to anonymous virtual memory area might prevent that
|
|
area from being merged with adjacent virtual memory areas due to the
|
|
difference in their name.
|
|
|
|
config USERFAULTFD
|
|
bool "Enable userfaultfd() system call"
|
|
depends on MMU
|
|
help
|
|
Enable the userfaultfd() system call that allows to intercept and
|
|
handle page faults in userland.
|
|
|
|
config HAVE_ARCH_USERFAULTFD_WP
|
|
bool
|
|
help
|
|
Arch has userfaultfd write protection support
|
|
|
|
config HAVE_ARCH_USERFAULTFD_MINOR
|
|
bool
|
|
help
|
|
Arch has userfaultfd minor fault support
|
|
|
|
config PTE_MARKER
|
|
bool
|
|
|
|
help
|
|
Allows to create marker PTEs for file-backed memory.
|
|
|
|
config PTE_MARKER_UFFD_WP
|
|
bool "Userfaultfd write protection support for shmem/hugetlbfs"
|
|
default y
|
|
depends on HAVE_ARCH_USERFAULTFD_WP
|
|
select PTE_MARKER
|
|
|
|
help
|
|
Allows to create marker PTEs for userfaultfd write protection
|
|
purposes. It is required to enable userfaultfd write protection on
|
|
file-backed memory types like shmem and hugetlbfs.
|
|
|
|
source "mm/damon/Kconfig"
|
|
|
|
endmenu
|