mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 23:01:04 +07:00
e91d8d7823
While I was doing zram testing, I found sometimes decompression failed
since the compression buffer was corrupted. With investigation, I found
below commit calls cond_resched unconditionally so it could make a
problem in atomic context if the task is reschedule.
BUG: sleeping function called from invalid context at mm/vmalloc.c:108
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 946, name: memhog
3 locks held by memhog/946:
#0: ffff9d01d4b193e8 (&mm->mmap_lock#2){++++}-{4:4}, at: __mm_populate+0x103/0x160
#1: ffffffffa3d53de0 (fs_reclaim){+.+.}-{0:0}, at: __alloc_pages_slowpath.constprop.0+0xa98/0x1160
#2: ffff9d01d56b8110 (&zspage->lock){.+.+}-{3:3}, at: zs_map_object+0x8e/0x1f0
CPU: 0 PID: 946 Comm: memhog Not tainted 5.9.3-00011-gc5bfc0287345-dirty #316
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1 04/01/2014
Call Trace:
unmap_kernel_range_noflush+0x2eb/0x350
unmap_kernel_range+0x14/0x30
zs_unmap_object+0xd5/0xe0
zram_bvec_rw.isra.0+0x38c/0x8e0
zram_rw_page+0x90/0x101
bdev_write_page+0x92/0xe0
__swap_writepage+0x94/0x4a0
pageout+0xe3/0x3a0
shrink_page_list+0xb94/0xd60
shrink_inactive_list+0x158/0x460
We can fix this by removing the ZSMALLOC_PGTABLE_MAPPING feature (which
contains the offending calling code) from zsmalloc.
Even though this option showed some amount improvement(e.g., 30%) in
some arm32 platforms, it has been headache to maintain since it have
abused APIs[1](e.g., unmap_kernel_range in atomic context).
Since we are approaching to deprecate 32bit machines and already made
the config option available for only builtin build since v5.8, lastly it
has been not default option in zsmalloc, it's time to drop the option
for better maintenance.
[1] http://lore.kernel.org/linux-mm/20201105170249.387069-1-minchan@kernel.org
Fixes: e47110e905 ("mm/vunmap: add cond_resched() in vunmap_pmd_range")
Signed-off-by: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Tony Lindgren <tony@atomide.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Harish Sriram <harish@linux.ibm.com>
Cc: Uladzislau Rezki <urezki@gmail.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20201117202916.GA3856507@google.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
863 lines
28 KiB
Plaintext
863 lines
28 KiB
Plaintext
# SPDX-License-Identifier: GPL-2.0-only
|
|
|
|
menu "Memory Management options"
|
|
|
|
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
|
|
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_DISCONTIGMEM_ENABLE || 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 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.
|
|
|
|
Although "Discontiguous Memory" is still used by several
|
|
architectures, it is considered deprecated in favor of
|
|
"Sparse Memory".
|
|
|
|
If unsure, choose "Sparse 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 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 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
|
|
|
|
#
|
|
# 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
|
|
|
|
#
|
|
# 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"
|
|
select MEMORY_ISOLATION
|
|
depends on SPARSEMEM || X86_64_ACPI_NUMA
|
|
depends on ARCH_ENABLE_MEMORY_HOTPLUG
|
|
depends on 64BIT || BROKEN
|
|
select NUMA_KEEP_MEMINFO if NUMA
|
|
|
|
config MEMORY_HOTPLUG_SPARSE
|
|
def_bool y
|
|
depends on SPARSEMEM && 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
|
|
|
|
# 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 ARCH_ENABLE_HUGEPAGE_MIGRATION
|
|
bool
|
|
|
|
config ARCH_ENABLE_THP_MIGRATION
|
|
bool
|
|
|
|
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 && (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.
|
|
|
|
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
|
|
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/vm/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 TRANSPARENT_HUGEPAGE
|
|
bool "Transparent Hugepage Support"
|
|
depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE
|
|
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.
|
|
|
|
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 ARCH_WANTS_THP_SWAP
|
|
def_bool n
|
|
|
|
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.
|
|
|
|
#
|
|
# 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"
|
|
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
|
|
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 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 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 ZSWAP
|
|
bool "Compressed cache for swap pages (EXPERIMENTAL)"
|
|
depends on FRONTSWAP && CRYPTO=y
|
|
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 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.
|
|
|
|
choice
|
|
prompt "Compressed cache for swap pages 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 "Compressed cache for swap pages 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 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.
|
|
|
|
config ZPOOL
|
|
tristate "Common API for compressed memory storage"
|
|
help
|
|
Compressed memory storage API. This allows using either zbud or
|
|
zsmalloc.
|
|
|
|
config ZBUD
|
|
tristate "Low (Up to 2x) density storage for compressed pages"
|
|
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 "Up to 3x density storage for compressed pages"
|
|
depends on ZPOOL
|
|
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 "Memory allocator for compressed pages"
|
|
depends on MMU
|
|
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 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 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). 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.
|
|
|
|
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 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/admin-guide/mm/idle_page_tracking.rst for
|
|
more details.
|
|
|
|
config ARCH_HAS_PTE_DEVMAP
|
|
bool
|
|
|
|
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.
|
|
|
|
config DEV_PAGEMAP_OPS
|
|
bool
|
|
|
|
#
|
|
# Helpers to mirror range of the CPU page tables of a process into device page
|
|
# tables.
|
|
#
|
|
config HMM_MIRROR
|
|
bool
|
|
depends on MMU
|
|
|
|
config DEVICE_PRIVATE
|
|
bool "Unaddressable device memory (GPU memory, ...)"
|
|
depends on ZONE_DEVICE
|
|
select DEV_PAGEMAP_OPS
|
|
|
|
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 FRAME_VECTOR
|
|
bool
|
|
|
|
config ARCH_USES_HIGH_VMA_FLAGS
|
|
bool
|
|
config ARCH_HAS_PKEYS
|
|
bool
|
|
|
|
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_BENCHMARK
|
|
bool "Enable infrastructure for get_user_pages() and related calls benchmarking"
|
|
help
|
|
Provides /sys/kernel/debug/gup_benchmark that helps with testing
|
|
performance of get_user_pages() and related calls.
|
|
|
|
See tools/testing/selftests/vm/gup_benchmark.c
|
|
|
|
config GUP_GET_PTE_LOW_HIGH
|
|
bool
|
|
|
|
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.
|
|
|
|
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
|
|
|
|
endmenu
|