Lines Matching full:memory
3 menu "Memory Management options"
13 bool "Support for paging of anonymous memory (swap)"
19 used to provide more virtual memory than the actual RAM present
30 compress them into a dynamically allocated RAM-based memory pool.
46 bool "Shrink the zswap pool on memory pressure"
52 written back to the backing swap device) on memory pressure.
57 and consume memory indefinitely.
174 bool "Configure for minimal memory footprint"
178 Configures the slab allocator in a way to achieve minimal memory
190 For reduced kernel memory fragmentation, slab caches can be
228 memory fragmentation, though in practice it's only a handful
254 to exploit memory-safety vulnerabilities by attacking vulnerable
255 co-located memory objects. Several modes are provided.
258 that effectively diverges the memory objects allocated for different
260 limited degree of memory and CPU overhead that relates to hardware
324 utilization of a direct-mapped memory-side-cache. See section
325 5.2.27 Heterogeneous Memory Attribute Table (HMAT) in the ACPI
327 the presence of a memory-side-cache. There are also incidental
355 bool "Allow mmapped anonymous memory to be uninitialized"
359 Normally, and according to the Linux spec, anonymous memory obtained
381 prompt "Memory model"
387 Linux manages its memory internally. Most users will
392 bool "Flat Memory"
402 spaces and for features like NUMA and memory hotplug,
403 choose "Sparse Memory".
405 If unsure, choose this option (Flat Memory) over any other.
408 bool "Sparse Memory"
412 memory hot-plug systems. This is normal.
415 holes is their physical address space and allows memory
418 If unsure, choose "Flat Memory" over this option.
486 # Enable memblock support for scratch memory which is needed for kexec handover
490 # Don't discard allocated memory used to track "memory" and "reserved" memblocks
491 # after early boot, so it can still be used to test for validity of memory.
492 # Also, memblocks are updated with memory hot(un)plug.
515 bool "Memory hotplug"
525 prompt "Memory Hotplug Default Online Type"
528 Default memory type for hotplugged memory.
530 This option sets the default policy setting for memory hotplug
531 onlining policy (/sys/devices/system/memory/auto_online_blocks) which
532 determines what happens to newly added memory regions. Policy setting
539 Select online_kernel to generally allow kernel usage of this memory.
540 Select online_movable to generally disallow kernel usage of this memory.
544 See Documentation/admin-guide/mm/memory-hotplug.rst for more information.
549 Hotplugged memory will not be onlined by default.
551 handle onlining of hotplug memory policy.
557 hotplugged memory into the zone it thinks is reasonable.
558 This memory may be utilized for kernel data.
564 hotplugged memory into a zone capable of being used for kernel
571 hotplug memory into ZONE_MOVABLE. This memory will generally
575 ZONE_NORMAL memory is available to describe hotplug memory,
576 otherwise hotplug memory may fail to online. For example,
577 sufficient kernel-capable memory (ZONE_NORMAL) must be
583 bool "Allow for memory hot remove"
624 # support for memory balloon
629 # support for memory balloon page migration
631 bool "Allow for balloon memory migration"
635 Allow for migration of pages inflated in a memory balloon such that
636 they can be allocated from memory areas only available for movable
638 migrated for memory defragmentation purposes by memory compaction.
641 # support for memory compaction
643 bool "Allow for memory compaction"
648 Compaction is the only memory management component to form
649 high order (larger physically contiguous) memory blocks
652 invocations for high order memory requests. You shouldn't
671 memory can be freed within the host for other uses.
682 demotion for memory tiering.
737 saving memory until one or another app needs to modify the content.
748 This is the portion of low virtual memory which should be protected
768 bool "Enable recovery from hardware memory errors"
772 Enables code to recover from some memory failures on systems
774 even when some of its memory has uncorrected errors. This requires
775 special hardware support and typically ECC memory.
788 of memory on which to store mappings, but it can only ask the system
823 from access to large folios for zeroing memory.
826 once and never freed. One full huge page's worth of memory shall
829 Say Y if your system has lots of memory. Say N if you are
830 memory constrained.
845 applications by speeding up page faults during memory
849 If memory constrained on embedded, you may want to say N.
863 memory footprint of applications without a guaranteed
872 memory footprint of applications without a guaranteed
906 increase the memory footprint of applications without a
950 increase the memory footprint of applications without a
1057 bool "Contiguous Memory Allocator"
1062 This enables the Contiguous Memory Allocator which allows other
1063 subsystems to allocate big physically-contiguous blocks of memory.
1064 CMA reserves a region of memory and allows only movable pages to
1065 be allocated from it. This way, the kernel can use the memory for
1132 bool "Track memory changes"
1136 This option enables memory changes tracking by introducing a
1189 be useful to tune memory cgroup limits and/or for job placement
1226 bool "Device memory (pmem, HMM, etc...) hotplug support"
1231 Device memory hotplug support allows for establishing pmem,
1232 or other device driver discovered memory regions, in the
1237 Enabling this option will reduce the entropy of x86 KASLR memory
1241 (5 level page table) and physical memory present on the system.
1256 bool "Unaddressable device memory (GPU memory, ...)"
1262 memory; i.e., memory that is only accessible from the device (or
1288 bool "Collect percpu memory statistics"
1292 be used to help understand percpu memory usage.
1350 memory areas visible only in the context of the owning process and
1358 Allow naming anonymous virtual memory areas.
1360 This feature allows assigning names to virtual memory areas. Assigned
1362 and help identifying individual anonymous memory areas.
1363 Assigning a name to anonymous virtual memory area might prevent that
1364 area from being merged with adjacent virtual memory areas due to the
1401 file-backed memory types like shmem and hugetlbfs.
1410 A high performance LRU implementation to overcommit memory. See
1426 This option has a per-memcg and per-node memory overhead.
1442 This feature allows locking each virtual memory area separately when