diff options
Diffstat (limited to 'mm/Kconfig')
| -rw-r--r-- | mm/Kconfig | 1130 |
1 files changed, 851 insertions, 279 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 3326ee3903f3..bd0ea5454af8 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -2,6 +2,338 @@ 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 + +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" + depends on SWAP + select CRYPTO + select ZSMALLOC + 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. + +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 ZSWAP_SHRINKER_DEFAULT_ON + bool "Shrink the zswap pool on memory pressure" + depends on ZSWAP + default n + help + If selected, the zswap shrinker will be enabled, and the pages + stored in the zswap pool will become available for reclaim (i.e + written back to the backing swap device) on memory pressure. + + This means that zswap writeback could happen even if the pool is + not yet full, or the cgroup zswap limit has not been reached, + reducing the chance that cold pages will reside in the zswap pool + and consume memory indefinitely. + +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 "" + +config ZSMALLOC + tristate + +if ZSMALLOC + +menu "Zsmalloc allocator options" + depends on ZSMALLOC + +comment "Zsmalloc is a common backend allocator for zswap & zram" + +config ZSMALLOC_STAT + bool "Export zsmalloc statistics" + 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. + +config ZSMALLOC_CHAIN_SIZE + int "Maximum number of physical pages per-zspage" + default 8 + range 4 16 + help + This option sets the upper limit on the number of physical pages + that a zmalloc page (zspage) can consist of. The optimal zspage + chain size is calculated for each size class during the + initialization of the pool. + + Changing this option can alter the characteristics of size classes, + such as the number of pages per zspage and the number of objects + per zspage. This can also result in different configurations of + the pool, as zsmalloc merges size classes with similar + characteristics. + + For more information, see zsmalloc documentation. + +endmenu + +endif + +menu "Slab allocator options" + +config SLUB + def_bool y + select IRQ_WORK + +config KVFREE_RCU_BATCHED + def_bool y + depends on !SLUB_TINY && !TINY_RCU + +config SLUB_TINY + bool "Configure for minimal memory footprint" + depends on EXPERT && !COMPILE_TEST + select SLAB_MERGE_DEFAULT + help + Configures the slab allocator in a way to achieve minimal memory + footprint, sacrificing scalability, debugging and other features. + This is intended only for the smallest system that had used the + SLOB allocator and is not recommended for systems with more than + 16MB RAM. + + If unsure, say N. + +config SLAB_MERGE_DEFAULT + bool "Allow slab caches to be merged" + default y + 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 !SLUB_TINY + 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 !SLUB_TINY + 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. + +config SLAB_BUCKETS + bool "Support allocation from separate kmalloc buckets" + depends on !SLUB_TINY + default SLAB_FREELIST_HARDENED + help + Kernel heap attacks frequently depend on being able to create + specifically-sized allocations with user-controlled contents + that will be allocated into the same kmalloc bucket as a + target object. To avoid sharing these allocation buckets, + provide an explicitly separated set of buckets to be used for + user-controlled allocations. This may very slightly increase + memory fragmentation, though in practice it's only a handful + of extra pages since the bulk of user-controlled allocations + are relatively long-lived. + + If unsure, say Y. + +config SLUB_STATS + default n + bool "Enable performance statistics" + depends on SYSFS && !SLUB_TINY + help + The statistics are useful to debug slab 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 SMP && !SLUB_TINY + bool "Enable per cpu partial caches" + 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. + +config RANDOM_KMALLOC_CACHES + default n + depends on !SLUB_TINY + bool "Randomize slab caches for normal kmalloc" + help + A hardening feature that creates multiple copies of slab caches for + normal kmalloc allocation and makes kmalloc randomly pick one based + on code address, which makes the attackers more difficult to spray + vulnerable memory objects on the heap for the purpose of exploiting + memory vulnerabilities. + + Currently the number of copies is set to 16, a reasonably large value + that effectively diverges the memory objects allocated for different + subsystems or modules into different caches, at the expense of a + limited degree of memory and CPU overhead that relates to hardware and + system workload. + +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_PAGE_ORDER 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 not enabled even + if SHUFFLE_PAGE_ALLOCATOR=y. 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 @@ -81,21 +413,39 @@ config SPARSEMEM_VMEMMAP_ENABLE bool config SPARSEMEM_VMEMMAP - bool "Sparse Memory virtual memmap" + def_bool y 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 SPARSEMEM_VMEMMAP_PREINIT + bool +# +# Select this config option from the architecture Kconfig, if it is preferred +# to enable the feature of HugeTLB/dev_dax vmemmap optimization. +# +config ARCH_WANT_OPTIMIZE_DAX_VMEMMAP + bool + +config ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP + bool + +config ARCH_WANT_HUGETLB_VMEMMAP_PREINIT + bool + config HAVE_MEMBLOCK_PHYS_MAP bool -config HAVE_FAST_GUP +config HAVE_GUP_FAST depends on MMU bool +# Enable memblock support for scratch memory which is needed for kexec handover +config MEMBLOCK_KHO_SCRATCH + 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. @@ -126,32 +476,77 @@ config HAVE_BOOTMEM_INFO_NODE config ARCH_ENABLE_MEMORY_HOTPLUG bool +config ARCH_ENABLE_MEMORY_HOTREMOVE + bool + # eventually, we can have this option just 'select SPARSEMEM' -config MEMORY_HOTPLUG - bool "Allow for memory hot-add" +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 -config MEMORY_HOTPLUG_DEFAULT_ONLINE - bool "Online the newly added memory blocks by default" - depends on MEMORY_HOTPLUG +if MEMORY_HOTPLUG + +choice + prompt "Memory Hotplug Default Online Type" + default MHP_DEFAULT_ONLINE_TYPE_OFFLINE help + Default memory type for hotplugged memory. + 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. + + The default is 'offline'. + + Select offline to defer onlining to drivers and user policy. + Select auto to let the kernel choose what zones to utilize. + Select online_kernel to generally allow kernel usage of this memory. + Select online_movable to generally disallow kernel usage of this memory. + + Example kernel usage would be page structs and page tables. + 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 MHP_DEFAULT_ONLINE_TYPE_OFFLINE + bool "offline" + help + Hotplugged memory will not be onlined by default. + Choose this for systems with drivers and user policy that + handle onlining of hotplug memory policy. -config ARCH_ENABLE_MEMORY_HOTREMOVE - bool +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_AUTO + bool "auto" + help + Select this if you want the kernel to automatically online + hotplugged memory into the zone it thinks is reasonable. + This memory may be utilized for kernel data. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_KERNEL + bool "kernel" + help + Select this if you want the kernel to automatically online + hotplugged memory into a zone capable of being used for kernel + data. This typically means ZONE_NORMAL. + +config MHP_DEFAULT_ONLINE_TYPE_ONLINE_MOVABLE + bool "movable" + help + Select this if you want the kernel to automatically online + hotplug memory into ZONE_MOVABLE. This memory will generally + not be utilized for kernel data. + + This should only be used when the admin knows sufficient + ZONE_NORMAL memory is available to describe hotplug memory, + otherwise hotplug memory may fail to online. For example, + sufficient kernel-capable memory (ZONE_NORMAL) must be + available to allocate page structs to describe ZONE_MOVABLE. + +endchoice config MEMORY_HOTREMOVE bool "Allow for memory hot remove" @@ -164,6 +559,11 @@ config MHP_MEMMAP_ON_MEMORY depends on MEMORY_HOTPLUG && SPARSEMEM_VMEMMAP depends on ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE +endif # MEMORY_HOTPLUG + +config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE + bool + # 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. @@ -175,17 +575,22 @@ config MHP_MEMMAP_ON_MEMORY # 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 SPLIT_PTE_PTLOCKS + def_bool y + depends on MMU + depends on SMP + depends on NR_CPUS >= 4 + depends on !ARM || CPU_CACHE_VIPT + depends on !PARISC || PA20 + depends on !SPARC32 config ARCH_ENABLE_SPLIT_PMD_PTLOCK bool +config SPLIT_PMD_PTLOCKS + def_bool y + depends on SPLIT_PTE_PTLOCKS && ARCH_ENABLE_SPLIT_PMD_PTLOCK + # # support for memory balloon config MEMORY_BALLOON @@ -195,7 +600,7 @@ config MEMORY_BALLOON # support for memory balloon compaction config BALLOON_COMPACTION bool "Allow for balloon memory compaction/migration" - def_bool y + default y depends on COMPACTION && MEMORY_BALLOON help Memory fragmentation introduced by ballooning might reduce @@ -210,7 +615,7 @@ config BALLOON_COMPACTION # support for memory compaction config COMPACTION bool "Allow for memory compaction" - def_bool y + default y select MIGRATION depends on MMU help @@ -223,11 +628,16 @@ config COMPACTION it and then we would be really interested to hear about that at linux-mm@kvack.org. +config COMPACT_UNEVICTABLE_DEFAULT + int + depends on COMPACTION + default 0 if PREEMPT_RT + default 1 + # # 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 @@ -239,7 +649,7 @@ config PAGE_REPORTING # config MIGRATION bool "Page migration" - def_bool y + default y depends on (NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA) && MMU help Allows the migration of the physical location of pages of processes @@ -249,6 +659,9 @@ config MIGRATION 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 @@ -262,32 +675,28 @@ config HUGETLB_PAGE_SIZE_VARIABLE HUGETLB_PAGE_ORDER when there are multiple HugeTLB page sizes available on a platform. + Note that the pageblock_order cannot exceed MAX_PAGE_ORDER and will be + clamped down to MAX_PAGE_ORDER. + 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 VIRT_TO_BUS - bool +config PCP_BATCH_SCALE_MAX + int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" + default 5 + range 0 6 help - An architecture should select this if it implements the - deprecated interface virt_to_bus(). All new architectures - should probably not select this. + In page allocator, PCP (Per-CPU pageset) is refilled and drained in + batches. The batch number is scaled automatically to improve page + allocation/free throughput. But too large scale factor may hurt + latency. This option sets the upper limit of scale factor to limit + the maximum latency. +config PHYS_ADDR_T_64BIT + def_bool 64BIT config MMU_NOTIFIER bool - select SRCU select INTERVAL_TREE config KSM @@ -301,7 +710,7 @@ config KSM 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 + 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). @@ -314,7 +723,7 @@ config DEFAULT_MMAP_MIN_ADDR 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 + For most arm64, 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 @@ -331,8 +740,7 @@ config MEMORY_FAILURE depends on MMU depends on ARCH_SUPPORTS_MEMORY_FAILURE bool "Enable recovery from hardware memory errors" - select MEMORY_ISOLATION - select RAS + select INTERVAL_TREE help Enables code to recover from some memory failures on systems with MCA recovery. This allows a system to continue running @@ -372,11 +780,37 @@ config NOMMU_INITIAL_TRIM_EXCESS See Documentation/admin-guide/mm/nommu-mmap.rst for more information. -config TRANSPARENT_HUGEPAGE +config ARCH_WANT_GENERAL_HUGETLB + bool + +config ARCH_WANTS_THP_SWAP + def_bool n + +config PERSISTENT_HUGE_ZERO_FOLIO + bool "Allocate a PMD sized folio for zeroing" + depends on TRANSPARENT_HUGEPAGE + help + Enable this option to reduce the runtime refcounting overhead + of the huge zero folio and expand the places in the kernel + that can use huge zero folios. For instance, block I/O benefits + from access to large folios for zeroing memory. + + With this option enabled, the huge zero folio is allocated + once and never freed. One full huge page's worth of memory shall + be used. + + Say Y if your system has lots of memory. Say N if you are + memory constrained. + +config MM_ID + def_bool n + +menuconfig TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT select COMPACTION select XARRAY_MULTI + select MM_ID help Transparent Hugepages allows the kernel to use huge pages and huge tlb transparently to the applications whenever possible. @@ -387,6 +821,8 @@ config TRANSPARENT_HUGEPAGE 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 @@ -409,14 +845,108 @@ choice madvise(MADV_HUGEPAGE) but it won't risk to increase the memory footprint of applications without a guaranteed benefit. + + config TRANSPARENT_HUGEPAGE_NEVER + bool "never" + help + Disable Transparent Hugepage by default. It can still be + enabled at runtime via sysfs. endchoice -config ARCH_WANTS_THP_SWAP - def_bool n +choice + prompt "Shmem hugepage allocation defaults" + depends on TRANSPARENT_HUGEPAGE + default TRANSPARENT_HUGEPAGE_SHMEM_HUGE_NEVER + help + Selects the hugepage allocation policy defaults for + the internal shmem mount. + + The selection made here can be overridden by using the kernel + command line 'transparent_hugepage_shmem=' option. + + config TRANSPARENT_HUGEPAGE_SHMEM_HUGE_NEVER + bool "never" + help + Disable hugepage allocation for shmem mount by default. It can + still be enabled with the kernel command line + 'transparent_hugepage_shmem=' option or at runtime via sysfs + knob. Note that madvise(MADV_COLLAPSE) can still cause + transparent huge pages to be obtained even if this mode is + specified. + + config TRANSPARENT_HUGEPAGE_SHMEM_HUGE_ALWAYS + bool "always" + help + Always attempt to allocate hugepage for shmem mount, can + increase the memory footprint of applications without a + guaranteed benefit but it will work automatically for all + applications. + + config TRANSPARENT_HUGEPAGE_SHMEM_HUGE_WITHIN_SIZE + bool "within_size" + help + Enable hugepage allocation for shmem mount if the allocation + will be fully within the i_size. This configuration also takes + into account any madvise(MADV_HUGEPAGE) hints that may be + provided by the applications. + + config TRANSPARENT_HUGEPAGE_SHMEM_HUGE_ADVISE + bool "advise" + help + Enable hugepage allocation for the shmem mount exclusively when + applications supply the madvise(MADV_HUGEPAGE) hint. + This ensures that hugepages are used only in response to explicit + requests from applications. +endchoice + +choice + prompt "Tmpfs hugepage allocation defaults" + depends on TRANSPARENT_HUGEPAGE + default TRANSPARENT_HUGEPAGE_TMPFS_HUGE_NEVER + help + Selects the hugepage allocation policy defaults for + the tmpfs mount. + + The selection made here can be overridden by using the kernel + command line 'transparent_hugepage_tmpfs=' option. + + config TRANSPARENT_HUGEPAGE_TMPFS_HUGE_NEVER + bool "never" + help + Disable hugepage allocation for tmpfs mount by default. It can + still be enabled with the kernel command line + 'transparent_hugepage_tmpfs=' option. Note that + madvise(MADV_COLLAPSE) can still cause transparent huge pages + to be obtained even if this mode is specified. + + config TRANSPARENT_HUGEPAGE_TMPFS_HUGE_ALWAYS + bool "always" + help + Always attempt to allocate hugepage for tmpfs mount, can + increase the memory footprint of applications without a + guaranteed benefit but it will work automatically for all + applications. + + config TRANSPARENT_HUGEPAGE_TMPFS_HUGE_WITHIN_SIZE + bool "within_size" + help + Enable hugepage allocation for tmpfs mount if the allocation + will be fully within the i_size. This configuration also takes + into account any madvise(MADV_HUGEPAGE) hints that may be + provided by the applications. + + config TRANSPARENT_HUGEPAGE_TMPFS_HUGE_ADVISE + bool "advise" + help + Enable hugepage allocation for the tmpfs mount exclusively when + applications supply the madvise(MADV_HUGEPAGE) hint. + This ensures that hugepages are used only in response to explicit + requests from applications. +endchoice config THP_SWAP def_bool y - depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP + depends on TRANSPARENT_HUGEPAGE && ARCH_WANTS_THP_SWAP && SWAP && 64BIT help Swap transparent huge pages in one piece, without splitting. XXX: For now, swap cluster backing transparent huge page @@ -424,6 +954,72 @@ config THP_SWAP 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 + + 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 NO_PAGE_MAPCOUNT + bool "No per-page mapcount (EXPERIMENTAL)" + help + Do not maintain per-page mapcounts for pages part of larger + allocations, such as transparent huge pages. + + When this config option is enabled, some interfaces that relied on + this information will rely on less-precise per-allocation information + instead: for example, using the average per-page mapcount in such + a large allocation instead of the per-page mapcount. + + EXPERIMENTAL because the impact of some changes is still unclear. + +endif # TRANSPARENT_HUGEPAGE + +# simple helper to make the code a bit easier to read +config PAGE_MAPCOUNT + def_bool !NO_PAGE_MAPCOUNT + +# +# The architecture supports pgtable leaves that is larger than PAGE_SIZE +# +config PGTABLE_HAS_HUGE_LEAVES + def_bool TRANSPARENT_HUGEPAGE || HUGETLB_PAGE + +# +# We can end up creating gigantic folio. +# +config HAVE_GIGANTIC_FOLIOS + def_bool (HUGETLB_PAGE && ARCH_HAS_GIGANTIC_PAGE) || \ + (ZONE_DEVICE && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) + +config ASYNC_KERNEL_PGTABLE_FREE + def_bool n + +# TODO: Allow to be enabled without THP +config ARCH_SUPPORTS_HUGE_PFNMAP + def_bool n + depends on TRANSPARENT_HUGEPAGE + +config ARCH_SUPPORTS_PMD_PFNMAP + def_bool y + depends on ARCH_SUPPORTS_HUGE_PFNMAP && HAVE_ARCH_TRANSPARENT_HUGEPAGE + +config ARCH_SUPPORTS_PUD_PFNMAP + def_bool y + depends on ARCH_SUPPORTS_HUGE_PFNMAP && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD + +# +# Architectures that always use weak definitions for percpu +# variables in modules should set this. +# +config ARCH_MODULE_NEEDS_WEAK_PER_CPU + bool + # # UP and nommu archs use km based percpu allocator # @@ -444,9 +1040,6 @@ config USE_PERCPU_NUMA_NODE_ID config HAVE_SETUP_PER_CPU_AREA bool -config FRONTSWAP - bool - config CMA bool "Contiguous Memory Allocator" depends on MMU @@ -462,15 +1055,6 @@ config CMA 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 @@ -487,14 +1071,49 @@ config CMA_SYSFS config CMA_AREAS int "Maximum count of the CMA areas" depends on CMA - default 19 if NUMA - default 7 + default 20 if NUMA + default 8 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. + If unsure, leave the default value "8" in UMA and "20" in NUMA. + +# +# Select this config option from the architecture Kconfig, if available, to set +# the max page order for physically contiguous allocations. +# +config ARCH_FORCE_MAX_ORDER + int + +# +# When ARCH_FORCE_MAX_ORDER is not defined, +# the default page block order is MAX_PAGE_ORDER (10) as per +# include/linux/mmzone.h. +# +config PAGE_BLOCK_MAX_ORDER + int "Page Block Order Upper Limit" + range 1 10 if ARCH_FORCE_MAX_ORDER = 0 + default 10 if ARCH_FORCE_MAX_ORDER = 0 + range 1 ARCH_FORCE_MAX_ORDER if ARCH_FORCE_MAX_ORDER != 0 + default ARCH_FORCE_MAX_ORDER if ARCH_FORCE_MAX_ORDER != 0 + help + The page block order refers to the power of two number of pages that + are physically contiguous and can have a migrate type associated to + them. The maximum size of the page block order is at least limited by + ARCH_FORCE_MAX_ORDER/MAX_PAGE_ORDER. + + This config adds a new upper limit of default page block + order when the page block order is required to be smaller than + ARCH_FORCE_MAX_ORDER/MAX_PAGE_ORDER or other limits + (see include/linux/pageblock-flags.h for details). + + Reducing pageblock order can negatively impact THP generation + success rate. If your workloads use THP heavily, please use this + option with caution. + + Don't change if unsure. config MEM_SOFT_DIRTY bool "Track memory changes" @@ -508,188 +1127,6 @@ config MEM_SOFT_DIRTY See Documentation/admin-guide/mm/soft-dirty.rst for more details. -config ZSWAP - bool "Compressed cache for swap pages (EXPERIMENTAL)" - depends on SWAP && CRYPTO=y - select FRONTSWAP - 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" - depends on ZPOOL - 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 what's happening in zsmalloc and exports that - information to userspace via debugfs. - If unsure, say N. - config GENERIC_EARLY_IOREMAP bool @@ -710,6 +1147,7 @@ config DEFERRED_STRUCT_PAGE_INIT depends on SPARSEMEM depends on !NEED_PER_CPU_KM depends on 64BIT + depends on !KMSAN select PADATA help Ordinarily all struct pages are initialised during early boot in a @@ -741,11 +1179,23 @@ config IDLE_PAGE_TRACKING See Documentation/admin-guide/mm/idle_page_tracking.rst for more details. +# Architectures which implement cpu_dcache_is_aliasing() to query +# whether the data caches are aliased (VIVT or VIPT with dcache +# aliasing) need to select this. +config ARCH_HAS_CPU_CACHE_ALIASING + bool + config ARCH_HAS_CACHE_LINE_SIZE bool -config ARCH_HAS_PTE_DEVMAP +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_ZONE_DMA_SET bool @@ -764,7 +1214,6 @@ config ZONE_DEVICE depends on MEMORY_HOTPLUG depends on MEMORY_HOTREMOVE depends on SPARSEMEM_VMEMMAP - depends on ARCH_HAS_PTE_DEVMAP select XARRAY_MULTI help @@ -776,9 +1225,6 @@ config ZONE_DEVICE 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. @@ -787,10 +1233,13 @@ config HMM_MIRROR bool depends on MMU +config GET_FREE_REGION + bool + config DEVICE_PRIVATE bool "Unaddressable device memory (GPU memory, ...)" depends on ZONE_DEVICE - select DEV_PAGEMAP_OPS + select GET_FREE_REGION help Allows creation of struct pages to represent unaddressable device @@ -805,6 +1254,20 @@ config ARCH_USES_HIGH_VMA_FLAGS config ARCH_HAS_PKEYS bool +config ARCH_USES_PG_ARCH_2 + bool +config ARCH_USES_PG_ARCH_3 + 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 @@ -830,38 +1293,26 @@ config GUP_TEST pin_user_pages*(), or pinned via get_user_pages*(), as specified by other command line arguments. - See tools/testing/selftests/vm/gup_test.c + See tools/testing/selftests/mm/gup_test.c comment "GUP_TEST needs to have DEBUG_FS enabled" depends on !GUP_TEST && !DEBUG_FS -config GUP_GET_PTE_LOW_HIGH +config GUP_GET_PXX_LOW_HIGH bool -config READ_ONLY_THP_FOR_FS - bool "Read-only THP for filesystems (EXPERIMENTAL)" - depends on TRANSPARENT_HUGEPAGE && SHMEM - +config DMAPOOL_TEST + tristate "Enable a module to run time tests on dma_pool" + depends on HAS_DMA 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. + Provides a test module that will allocate and free many blocks of + various sizes and report how long it takes. This is intended to + provide a consistent way to measure how changes to the + dma_pool_alloc/free routines affect performance. 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 @@ -871,12 +1322,17 @@ config KMAP_LOCAL config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY bool -# struct io_mapping based helper. Selected by drivers that need them -config IO_MAPPING - bool +config MEMFD_CREATE + bool "Enable memfd_create() system call" if EXPERT config SECRETMEM - def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED + default y + bool "Enable memfd_secret() system call" if EXPERT + depends on ARCH_HAS_SET_DIRECT_MAP + help + Enable the memfd_secret() system call with the ability to create + memory areas visible only in the context of the owning process and + not mapped to other processes and other kernel page tables. config ANON_VMA_NAME bool "Anonymous VMA name support" @@ -892,6 +1348,122 @@ config ANON_VMA_NAME area from being merged with adjacent virtual memory areas due to the difference in their name. +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 + +menuconfig 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. + +if USERFAULTFD +config PTE_MARKER_UFFD_WP + bool "Userfaultfd write protection support for shmem/hugetlbfs" + default y + depends on HAVE_ARCH_USERFAULTFD_WP + + 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. +endif # USERFAULTFD + +# multi-gen LRU { +config LRU_GEN + bool "Multi-Gen LRU" + depends on MMU + # make sure folio->flags has enough spare bits + depends on 64BIT || !SPARSEMEM || SPARSEMEM_VMEMMAP + help + A high performance LRU implementation to overcommit memory. See + Documentation/admin-guide/mm/multigen_lru.rst for details. + +config LRU_GEN_ENABLED + bool "Enable by default" + depends on LRU_GEN + help + This option enables the multi-gen LRU by default. + +config LRU_GEN_STATS + bool "Full stats for debugging" + depends on LRU_GEN + help + Do not enable this option unless you plan to look at historical stats + from evicted generations for debugging purpose. + + This option has a per-memcg and per-node memory overhead. + +config LRU_GEN_WALKS_MMU + def_bool y + depends on LRU_GEN && ARCH_HAS_HW_PTE_YOUNG +# } + +config ARCH_SUPPORTS_PER_VMA_LOCK + def_bool n + +config PER_VMA_LOCK + def_bool y + depends on ARCH_SUPPORTS_PER_VMA_LOCK && MMU && SMP + help + Allow per-vma locking during page fault handling. + + This feature allows locking each virtual memory area separately when + handling page faults instead of taking mmap_lock. + +config LOCK_MM_AND_FIND_VMA + bool + depends on !STACK_GROWSUP + +config IOMMU_MM_DATA + bool + +config EXECMEM + bool + +config NUMA_MEMBLKS + bool + +config NUMA_EMU + bool "NUMA emulation" + depends on NUMA_MEMBLKS + depends on X86 || GENERIC_ARCH_NUMA + help + Enable NUMA emulation. A flat machine will be split + into virtual nodes when booted with "numa=fake=N", where N is the + number of nodes. This is only useful for debugging. + +config ARCH_HAS_USER_SHADOW_STACK + bool + help + The architecture has hardware support for userspace shadow call + stacks (eg, x86 CET, arm64 GCS or RISC-V Zicfiss). + +config ARCH_SUPPORTS_PT_RECLAIM + def_bool n + +config PT_RECLAIM + bool "reclaim empty user page table pages" + default y + depends on ARCH_SUPPORTS_PT_RECLAIM && MMU && SMP + select MMU_GATHER_RCU_TABLE_FREE + help + Try to reclaim empty user page table pages in paths other than munmap + and exit_mmap path. + + Note: now only empty user PTE page table pages will be reclaimed. + +config FIND_NORMAL_PAGE + def_bool n + source "mm/damon/Kconfig" endmenu |