Lines Matching +full:default +full:- +full:on
1 # SPDX-License-Identifier: GPL-2.0-only
17 depends on MMU && BLOCK && !ARCH_NO_SWAP
18 default y
27 depends on SWAP
33 compress them into a dynamically allocated RAM-based memory pool.
34 This can result in a significant I/O reduction on swap device and,
39 bool "Enable the compressed cache for swap pages by default"
40 depends on ZSWAP
50 depends on ZSWAP
62 swapped out again, it will be re-compressed.
65 prompt "Default compressor"
66 depends on ZSWAP
67 default ZSWAP_COMPRESSOR_DEFAULT_LZO
69 Selects the default compression algorithm for the compressed cache
86 Use the Deflate algorithm as the default compression algorithm.
92 Use the LZO algorithm as the default compression algorithm.
98 Use the 842 algorithm as the default compression algorithm.
104 Use the LZ4 algorithm as the default compression algorithm.
110 Use the LZ4HC algorithm as the default compression algorithm.
116 Use the zstd algorithm as the default compression algorithm.
121 depends on ZSWAP
122 default "deflate" if ZSWAP_COMPRESSOR_DEFAULT_DEFLATE
123 default "lzo" if ZSWAP_COMPRESSOR_DEFAULT_LZO
124 default "842" if ZSWAP_COMPRESSOR_DEFAULT_842
125 default "lz4" if ZSWAP_COMPRESSOR_DEFAULT_LZ4
126 default "lz4hc" if ZSWAP_COMPRESSOR_DEFAULT_LZ4HC
127 default "zstd" if ZSWAP_COMPRESSOR_DEFAULT_ZSTD
128 default ""
131 prompt "Default allocator"
132 depends on ZSWAP
133 default ZSWAP_ZPOOL_DEFAULT_ZBUD
135 Selects the default allocator for the compressed cache for
137 The default is 'zbud' for compatibility, however please do
148 Use the zbud allocator as the default allocator.
154 Use the z3fold allocator as the default allocator.
163 Use the zsmalloc allocator as the default allocator.
168 depends on ZSWAP
169 default "zbud" if ZSWAP_ZPOOL_DEFAULT_ZBUD
170 default "z3fold" if ZSWAP_ZPOOL_DEFAULT_Z3FOLD_DEPRECATED
171 default "zsmalloc" if ZSWAP_ZPOOL_DEFAULT_ZSMALLOC
172 default ""
176 depends on ZSWAP
186 depends on ZSWAP
190 linux-mm@kvack.org and the zswap maintainers.
199 default y if Z3FOLD_DEPRECATED=y
200 default m if Z3FOLD_DEPRECATED=m
201 depends on Z3FOLD_DEPRECATED
206 depends on MMU
208 zsmalloc is a slab-based memory allocator designed to store
214 depends on ZSMALLOC
223 int "Maximum number of physical pages per-zspage"
224 default 8
226 depends on ZSMALLOC
228 This option sets the upper limit on the number of physical pages
245 default SLUB
251 depends on !PREEMPT_RT
256 If you cannot migrate to SLUB, please contact linux-mm@kvack.org
271 and has enhanced diagnostics. SLUB is the default choice for
278 default y
279 depends on SLAB_DEPRECATED
283 depends on SLUB && EXPERT
296 default y
297 depends on SLAB || SLUB
306 merging at runtime, "slab_nomerge" can be passed on the kernel
311 depends on SLAB || (SLUB && !SLUB_TINY)
313 Randomizes the freelist order used on creating new pages. This
319 depends on SLAB || (SLUB && !SLUB_TINY)
325 sanity-checking than others. This option is most effective with
329 default n
331 depends on SLUB && SYSFS && !SLUB_TINY
339 Try running: slabinfo -DA
342 default y
343 depends on SLUB && SMP && !SLUB_TINY
348 in the latency of the free. On overflow these caches will be cleared
353 default n
354 depends on SLUB && !SLUB_TINY
359 on code address, which makes the attackers more difficult to spray
360 vulnerable memory objects on the heap for the purpose of exploiting
373 default SLAB_FREELIST_RANDOM && ACPI_NUMA
376 utilization of a direct-mapped memory-side-cache. See section
379 the presence of a memory-side-cache. There are also incidental
382 default granularity of shuffling on the MAX_ORDER i.e, 10th
383 order of pages is selected based on cache utilization benefits
384 on x86.
387 negatively impact workloads on platforms without a cache. For
388 this reason, by default, the randomization is enabled only
389 after runtime detection of a direct-mapped memory-side-cache.
397 default y
401 This option changes the bootup default to heap randomization
405 On non-ancient distros (post-2000 ones) N is usually a safe choice.
409 depends on EXPERT && !MMU
410 default n
420 ELF-FDPIC binfmt's brk and stack allocator.
423 enabled on embedded devices where you control what is run in
424 userspace. Since that isn't generally a problem on no-MMU systems,
427 See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
431 depends on ARCH_SELECT_MEMORY_MODEL
435 depends on SELECT_MEMORY_MODEL
436 default SPARSEMEM_MANUAL if ARCH_SPARSEMEM_DEFAULT
437 default FLATMEM_MANUAL
446 depends on !ARCH_SPARSEMEM_ENABLE || ARCH_FLATMEM_ENABLE
448 This option is best suited for non-NUMA systems with
461 depends on ARCH_SPARSEMEM_ENABLE
464 memory hot-plug systems. This is normal.
468 hot-plug and hot-remove.
476 depends on (!SELECT_MEMORY_MODEL && ARCH_SPARSEMEM_ENABLE) || SPARSEMEM_MANUAL
480 depends on !SPARSEMEM || FLATMEM_MANUAL
483 # SPARSEMEM_EXTREME (which is the default) does some bootmem
485 # be done on your architecture, select this option. However,
502 depends on SPARSEMEM && !SPARSEMEM_STATIC
509 depends on SPARSEMEM && SPARSEMEM_VMEMMAP_ENABLE
510 default y
529 depends on MMU
538 # Keep arch NUMA mapping infrastructure post-init.
550 depends on !DEVMEM || STRICT_DEVMEM
553 # Only be set on architectures that have completely implemented memory hotplug
569 depends on SPARSEMEM
570 depends on ARCH_ENABLE_MEMORY_HOTPLUG
571 depends on 64BIT
577 bool "Online the newly added memory blocks by default"
578 depends on MEMORY_HOTPLUG
580 This option sets the default policy setting for memory hotplug
584 See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
586 Say Y here if you want all hot-plugged memory blocks to appear in
587 'online' state by default.
588 Say N here if you want the default policy to keep all hot-plugged
594 depends on MEMORY_HOTPLUG && ARCH_ENABLE_MEMORY_HOTREMOVE
595 depends on MIGRATION
599 depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP
600 depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
607 # Heavily threaded applications may benefit from splitting the mm-wide
608 # page_table_lock, so that faults on different parts of the user address
610 # Default to 4 for wider testing, though 8 might be more appropriate.
611 # ARM's adjust_pte (unused if VIPT) depends on mm-wide page_table_lock.
612 # PA-RISC 7xxx's spinlock_t would enlarge struct page from 32 to 44 bytes.
614 # a per-page lock leads to problems when multiple tables need to be locked
620 default "999999" if !MMU
621 default "999999" if ARM && !CPU_CACHE_VIPT
622 default "999999" if PARISC && !PA20
623 default "999999" if SPARC32
624 default "4"
639 depends on COMPACTION && MEMORY_BALLOON
655 depends on MMU
659 reliably. The page allocator relies on compaction heavily and
664 linux-mm@kvack.org.
668 depends on COMPACTION
669 default 0 if PREEMPT_RT
670 default 1
689 depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU
693 two situations. The first is on NUMA systems to put pages nearer
712 on a platform.
721 int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free"
722 default 5
725 In page allocator, PCP (Per-CPU pageset) is refilled and drained in
736 default y
737 depends on BLOCK && MMU && HIGHMEM
740 memory available to the CPU. Enabled by default when HIGHMEM is
749 depends on MMU
764 depends on MMU
765 default 4096
773 On arm and other archs it should not be higher than 32768.
785 depends on MMU
786 depends on ARCH_SUPPORTS_MEMORY_FAILURE
791 Enables code to recover from some memory failures on systems
798 depends on MEMORY_FAILURE && DEBUG_KERNEL && PROC_FS
802 int "Turn on mmap() excess space trimming before booting"
803 depends on !MMU
804 default 1
807 of memory on which to store mappings, but it can only ask the system
808 allocator for chunks in 2^N*PAGE_SIZE amounts - which is frequently
817 long-term mappings means that the space is wasted.
824 This option specifies the initial value of this option. The default
827 See Documentation/admin-guide/mm/nommu-mmap.rst for more information.
837 depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT
848 If memory constrained on embedded, you may want to say N.
854 depends on TRANSPARENT_HUGEPAGE
855 default TRANSPARENT_HUGEPAGE_ALWAYS
878 depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT
887 bool "Read-only THP for filesystems (EXPERIMENTAL)"
888 depends on TRANSPARENT_HUGEPAGE && SHMEM
891 Allow khugepaged to put read-only file-backed pages in THP.
903 depends on !SMP || !MMU
905 default y
921 depends on MMU
926 subsystems to allocate big physically-contiguous blocks of memory.
936 depends on DEBUG_KERNEL && CMA
938 Turns on debug messages in CMA. This produces KERN_DEBUG
945 depends on CMA && DEBUG_FS
947 Turns on the DebugFS interface for CMA.
951 depends on CMA && SYSFS
958 depends on CMA
959 default 19 if NUMA
960 default 7
966 If unsure, leave the default value "7" in UMA and "19" in NUMA.
970 depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
974 soft-dirty bit on pte-s. This bit it set when someone writes
978 See Documentation/admin-guide/mm/soft-dirty.rst for more details.
984 int "Default maximum user stack size for 32-bit processes (MB)"
985 default 100
987 depends on STACK_GROWSUP && (!64BIT || COMPAT)
989 This is the maximum stack size in Megabytes in the VM layout of 32-bit
990 user processes when the stack grows upwards (currently only on parisc
997 depends on SPARSEMEM
998 depends on !NEED_PER_CPU_KM
999 depends on 64BIT
1003 single thread. On very large machines this can take a considerable
1006 This has a potential performance impact on tasks running early in the
1020 depends on SYSFS && MMU
1028 See Documentation/admin-guide/mm/idle_page_tracking.rst for
1038 checking, an architecture-agnostic way to find the stack pointer
1051 default y if ARM64 || X86
1055 depends on !X86_32
1056 default y if ARM64
1060 depends on MEMORY_HOTPLUG
1061 depends on MEMORY_HOTREMOVE
1062 depends on SPARSEMEM_VMEMMAP
1063 depends on ARCH_HAS_PTE_DEVMAP
1070 "device-physical" addresses which is needed for using a DAX
1081 depends on MMU
1084 depends on SPARSEMEM
1089 depends on ZONE_DEVICE
1109 suitable for 64-bit architectures with CONFIG_FLATMEM or
1111 enough room for additional bits in page->flags.
1114 default y
1119 on EXPERT systems. /proc/vmstat will only show page counts
1130 bool "Enable infrastructure for get_user_pages()-related unit tests"
1131 depends on DEBUG_FS
1134 to make ioctl calls that can launch kernel-based unit tests for
1139 the non-_fast variants.
1141 There is also a sub-test that allows running dump_page() on any
1143 range of user-space addresses. These pages are either pinned via
1150 depends on !GUP_TEST && !DEBUG_FS
1156 tristate "Enable a module to run time tests on dma_pool"
1157 depends on HAS_DMA
1171 # introduced it on powerpc. This allows for a more flexible hugepage
1194 default y
1196 depends on ARCH_HAS_SET_DIRECT_MAP
1204 depends on PROC_FS && ADVISE_SYSCALLS && MMU
1218 depends on MMU
1235 default y
1236 depends on HAVE_ARCH_USERFAULTFD_WP
1240 purposes. It is required to enable userfaultfd write protection on
1241 file-backed memory types like shmem and hugetlbfs.
1243 # multi-gen LRU {
1245 bool "Multi-Gen LRU"
1246 depends on MMU
1247 # make sure folio->flags has enough spare bits
1248 depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP
1251 Documentation/admin-guide/mm/multigen_lru.rst for details.
1254 bool "Enable by default"
1255 depends on LRU_GEN
1257 This option enables the multi-gen LRU by default.
1261 depends on LRU_GEN
1266 This option has a per-memcg and per-node memory overhead.
1274 depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP
1276 Allow per-vma locking during page fault handling.
1283 depends on !STACK_GROWSUP