diff options
Diffstat (limited to 'mm/Kconfig')
| -rw-r--r-- | mm/Kconfig | 642 |
1 files changed, 424 insertions, 218 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 264a2df5ecf5..bd0ea5454af8 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -9,9 +9,6 @@ menu "Memory Management options" 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 @@ -26,7 +23,7 @@ config ZSWAP bool "Compressed cache for swap pages" depends on SWAP select CRYPTO - select ZPOOL + 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 @@ -45,21 +42,19 @@ config ZSWAP_DEFAULT_ON The selection made here can be overridden by using the kernel command line 'zswap.enabled=' option. -config ZSWAP_EXCLUSIVE_LOADS_DEFAULT_ON - bool "Invalidate zswap entries when pages are loaded" +config ZSWAP_SHRINKER_DEFAULT_ON + bool "Shrink the zswap pool on memory pressure" depends on ZSWAP + default n help - If selected, exclusive loads for zswap will be enabled at boot, - otherwise it will be disabled. + 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. - If exclusive loads are enabled, when a page is loaded from zswap, - the zswap entry is invalidated at once, as opposed to leaving it - in zswap until the swap entry is freed. - - This avoids having two copies of the same page in memory - (compressed and uncompressed) after faulting in a page from zswap. - The cost is that if the page was never dirtied and needs to be - swapped out again, it will be re-compressed. + 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" @@ -127,78 +122,18 @@ config ZSWAP_COMPRESSOR_DEFAULT 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 ZSMALLOC + tristate -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. +if ZSMALLOC -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. +menu "Zsmalloc allocator options" + depends on ZSMALLOC -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. +comment "Zsmalloc is a common backend allocator for zswap & zram" config ZSMALLOC_STAT bool "Export zsmalloc statistics" - depends on ZSMALLOC select DEBUG_FS help This option enables code in the zsmalloc to collect various @@ -210,7 +145,6 @@ config ZSMALLOC_CHAIN_SIZE int "Maximum number of physical pages per-zspage" default 8 range 4 16 - depends on ZSMALLOC help This option sets the upper limit on the number of physical pages that a zmalloc page (zspage) can consist of. The optimal zspage @@ -225,52 +159,26 @@ config ZSMALLOC_CHAIN_SIZE For more information, see zsmalloc documentation. -menu "SLAB allocator options" - -choice - prompt "Choose SLAB allocator" - default SLUB - help - This option allows to select a slab allocator. - -config SLAB_DEPRECATED - bool "SLAB (DEPRECATED)" - depends on !PREEMPT_RT - help - Deprecated and scheduled for removal in a few cycles. Replaced by - SLUB. +endmenu - If you cannot migrate to SLUB, please contact linux-mm@kvack.org - and the people listed in the SLAB ALLOCATOR section of MAINTAINERS - file, explaining why. +endif - 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. +menu "Slab allocator options" config SLUB - bool "SLUB (Unqueued 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. - -endchoice + def_bool y + select IRQ_WORK -config SLAB - bool - default y - depends on SLAB_DEPRECATED +config KVFREE_RCU_BATCHED + def_bool y + depends on !SLUB_TINY && !TINY_RCU config SLUB_TINY - bool "Configure SLUB for minimal memory footprint" - depends on SLUB && EXPERT + bool "Configure for minimal memory footprint" + depends on EXPERT && !COMPILE_TEST select SLAB_MERGE_DEFAULT help - Configures the SLUB allocator in a way to achieve minimal memory + 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 @@ -281,7 +189,6 @@ config SLUB_TINY 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. @@ -295,7 +202,7 @@ config SLAB_MERGE_DEFAULT config SLAB_FREELIST_RANDOM bool "Randomize slab freelist" - depends on SLAB || (SLUB && !SLUB_TINY) + depends on !SLUB_TINY help Randomizes the freelist order used on creating new pages. This security feature reduces the predictability of the kernel slab @@ -303,21 +210,36 @@ config SLAB_FREELIST_RANDOM config SLAB_FREELIST_HARDENED bool "Harden slab freelist metadata" - depends on SLAB || (SLUB && !SLUB_TINY) + 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. Some slab implementations have more - sanity-checking than others. This option is most effective with - CONFIG_SLUB. + 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 SLUB performance statistics" - depends on SLUB && SYSFS && !SLUB_TINY + bool "Enable performance statistics" + depends on SYSFS && !SLUB_TINY help - SLUB statistics are useful to debug SLUBs allocation behavior in + 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 @@ -327,8 +249,8 @@ config SLUB_STATS config SLUB_CPU_PARTIAL default y - depends on SLUB && SMP && !SLUB_TINY - bool "SLUB per cpu partial cache" + 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 @@ -338,7 +260,7 @@ config SLUB_CPU_PARTIAL config RANDOM_KMALLOC_CACHES default n - depends on SLUB && !SLUB_TINY + depends on !SLUB_TINY bool "Randomize slab caches for normal kmalloc" help A hardening feature that creates multiple copies of slab caches for @@ -353,7 +275,7 @@ config RANDOM_KMALLOC_CACHES limited degree of memory and CPU overhead that relates to hardware and system workload. -endmenu # SLAB allocator options +endmenu # Slab allocator options config SHUFFLE_PAGE_ALLOCATOR bool "Page allocator randomization" @@ -366,16 +288,15 @@ config SHUFFLE_PAGE_ALLOCATOR 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 i.e, 10th + 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 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. + 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. @@ -492,13 +413,15 @@ 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. @@ -509,13 +432,20 @@ config ARCH_WANT_OPTIMIZE_DAX_VMEMMAP 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. @@ -560,20 +490,63 @@ menuconfig MEMORY_HOTPLUG if MEMORY_HOTPLUG -config MEMORY_HOTPLUG_DEFAULT_ONLINE - bool "Online the newly added memory blocks by default" - depends on 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 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" @@ -602,17 +575,22 @@ config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE # 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 @@ -622,7 +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 @@ -637,7 +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 @@ -660,7 +638,6 @@ config COMPACT_UNEVICTABLE_DEFAULT # 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 @@ -672,7 +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 @@ -698,24 +675,26 @@ 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_ORDER and will be - clamped down to MAX_ORDER. + 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 PCP_BATCH_SCALE_MAX + int "Maximum scale factor of PCP (Per-CPU pageset) batch allocate/free" + default 5 + range 0 6 + help + 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 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 INTERVAL_TREE @@ -744,7 +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 @@ -761,8 +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 @@ -808,11 +786,31 @@ config ARCH_WANT_GENERAL_HUGETLB 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. @@ -847,6 +845,103 @@ 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 + +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 @@ -861,7 +956,7 @@ config THP_SWAP config READ_ONLY_THP_FOR_FS bool "Read-only THP for filesystems (EXPERIMENTAL)" - depends on TRANSPARENT_HUGEPAGE && SHMEM + depends on TRANSPARENT_HUGEPAGE help Allow khugepaged to put read-only file-backed pages in THP. @@ -870,8 +965,61 @@ config READ_ONLY_THP_FOR_FS 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 # @@ -907,15 +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 @@ -932,14 +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" @@ -973,6 +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 @@ -1004,6 +1179,12 @@ 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 @@ -1016,9 +1197,6 @@ config ARCH_HAS_CURRENT_STACK_POINTER register alias named "current_stack_pointer", this config can be selected. -config ARCH_HAS_PTE_DEVMAP - bool - config ARCH_HAS_ZONE_DMA_SET bool @@ -1036,7 +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 @@ -1057,7 +1234,6 @@ config HMM_MIRROR depends on MMU config GET_FREE_REGION - depends on SPARSEMEM bool config DEVICE_PRIVATE @@ -1078,13 +1254,10 @@ config ARCH_USES_HIGH_VMA_FLAGS config ARCH_HAS_PKEYS bool -config ARCH_USES_PG_ARCH_X +config ARCH_USES_PG_ARCH_2 + bool +config ARCH_USES_PG_ARCH_3 bool - help - Enable the definition of PG_arch_x page flags with x > 1. Only - suitable for 64-bit architectures with CONFIG_FLATMEM or - CONFIG_SPARSEMEM_VMEMMAP enabled, otherwise there may not be - enough room for additional bits in page->flags. config VM_EVENT_COUNTERS default y @@ -1140,16 +1313,6 @@ config DMAPOOL_TEST 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 @@ -1159,10 +1322,6 @@ 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 @@ -1189,13 +1348,6 @@ config ANON_VMA_NAME 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 @@ -1206,6 +1358,14 @@ config HAVE_ARCH_USERFAULTFD_MINOR 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 @@ -1215,6 +1375,7 @@ config PTE_MARKER_UFFD_WP 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 @@ -1240,6 +1401,10 @@ config LRU_GEN_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 @@ -1258,6 +1423,47 @@ 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 |