Home
last modified time | relevance | path

Searched refs:hugepage (Results 1 – 20 of 20) sorted by relevance

/linux-6.15/tools/testing/selftests/mm/
H A D.gitignore3 hugepage-mmap
4 hugepage-mremap
5 hugepage-shm
6 hugepage-vmemmap
H A DMakefile65 TEST_GEN_FILES += hugepage-mmap
66 TEST_GEN_FILES += hugepage-mremap
67 TEST_GEN_FILES += hugepage-shm
68 TEST_GEN_FILES += hugepage-vmemmap
H A Drun_vmtests.sh270 CATEGORY="hugetlb" run_test ./hugepage-mmap
276 CATEGORY="hugetlb" run_test ./hugepage-shm
281 CATEGORY="hugetlb" run_test ./hugepage-mremap
282 CATEGORY="hugetlb" run_test ./hugepage-vmemmap
/linux-6.15/Documentation/mm/
H A Dtranshuge.rst12 - "graceful fallback": mm components which don't have transparent hugepage
14 if necessary, split a transparent hugepage. Therefore these components
17 - if a hugepage allocation fails because of memory fragmentation,
30 is not specific to transparent hugepage support and it's a generic
52 hugepage backed mappings.
59 pmd_offset. It's trivial to make the code transparent hugepage aware
64 hugepage aware.
72 Example to make mremap.c transparent hugepage aware with a one liner
86 Locking in hugepage aware code
89 We want as much code as possible hugepage aware, as calling
[all …]
/linux-6.15/Documentation/arch/arm64/
H A Dhugetlbpage.rst20 mappings reduce the depth of page table walk needed to translate hugepage
35 The following hugepage sizes are supported -
/linux-6.15/mm/
H A Dhugetlb_cgroup.c48 return &h_cg->hugepage[idx]; in __hugetlb_cgroup_counter_from_cgroup()
215 page_counter_charge(&parent->hugepage[idx], nr_pages); in hugetlb_cgroup_move_parent()
217 counter = &h_cg->hugepage[idx]; in hugetlb_cgroup_move_parent()
494 page_counter_read(&h_cg->hugepage[idx]) * PAGE_SIZE); in hugetlb_cgroup_read_numa_stat()
524 counter = &h_cg->hugepage[MEMFILE_IDX(cft->private)]; in hugetlb_cgroup_read_u64()
559 counter = &h_cg->hugepage[idx]; in hugetlb_cgroup_read_u64_max()
648 counter = &h_cg->hugepage[MEMFILE_IDX(of_cft(of)->private)]; in hugetlb_cgroup_reset()
/linux-6.15/Documentation/admin-guide/mm/
H A Dtranshuge.rst74 entities). It doesn't require reservation to prevent hugepage
84 lived page allocations even for hugepage unaware applications that
119 where <size> is the hugepage size being addressed, the available sizes
126 Alternatively it is possible to specify that a given hugepage size
143 hugepage sizes have enabled="never". If enabling multiple hugepage
201 PMD-mappable transparent hugepage::
248 and how many milliseconds to wait in khugepaged if there's an hugepage
329 Similarly to ``transparent_hugepage``, you can control the hugepage
352 ``thp_shmem`` is not specified, PMD_ORDER hugepage will default to
679 memory region, the mmap region has to be hugepage naturally
[all …]
H A Dhugetlbpage.rst66 is the default hugepage size (in kB).
146 It will allocate 1 2M hugepage on node0 and 2 2M hugepages on node1.
319 When adjusting the persistent hugepage count via ``nr_hugepages_mempolicy``, any
469 not hugepage aligned. For example, munmap(2) will fail if memory is backed by
470 a hugetlb page and the length is smaller than the hugepage size.
481 ``hugepage-shm``
482 see tools/testing/selftests/mm/hugepage-shm.c
484 ``hugepage-mmap``
485 see tools/testing/selftests/mm/hugepage-mmap.c
H A Duserfaultfd.rst38 Vmas are not suitable for page- (or hugepage) granular fault tracking
/linux-6.15/include/linux/
H A Dhugetlb_cgroup.h41 struct page_counter hugepage[HUGE_MAX_HSTATE]; member
/linux-6.15/Documentation/admin-guide/sysctl/
H A Dvm.rst290 - For a page that is part of a transparent hugepage, soft-offline splits the
291 transparent hugepage into raw pages, then migrates only the raw error page.
292 As a result, user is transparently backed by 1 less hugepage, impacting
295 - For a page that is part of a HugeTLB hugepage, soft-offline first migrates
296 the entire HugeTLB hugepage, during which a free hugepage will be consumed
297 as migration target. Then the original hugepage is dissolved into raw
623 Change the minimum size of the hugepage pool.
668 Change the size of the hugepage pool at run-time on a specific
677 Change the maximum size of the hugepage pool. The maximum is
/linux-6.15/Documentation/translations/zh_TW/admin-guide/mm/damon/
H A Dusage.rst215 - ``hugepage``: 爲帶有 ``MADV_HUGEPAGE`` 的區域調用 ``madvise()`` 。
/linux-6.15/Documentation/translations/zh_CN/admin-guide/mm/damon/
H A Dusage.rst215 - ``hugepage``: 为带有 ``MADV_HUGEPAGE`` 的区域调用 ``madvise()`` 。
/linux-6.15/Documentation/trace/
H A Devents-kmem.rst119 pageblock_size is usually the size of the default hugepage size.
/linux-6.15/Documentation/admin-guide/cgroup-v1/
H A Dhugetlb.rst34 For a system supporting three hugepage sizes (64k, 32M and 1G), the control
/linux-6.15/Documentation/ABI/testing/
H A Dsysfs-kernel-mm-damon383 hugepage for the filter.
390 hugepage for the filter.
/linux-6.15/Documentation/ABI/stable/
H A Dsysfs-block646 since its granularity is based on the hugepage size.
/linux-6.15/Documentation/mm/damon/
H A Ddesign.rst446 - ``hugepage``: Call ``madvise()`` for the region with ``MADV_HUGEPAGE``.
/linux-6.15/Documentation/filesystems/
H A Dproc.rst551 "AnonHugePages" shows the amount of memory backed by transparent hugepage.
982 A page block is typically the size of the default hugepage size, e.g. 2MB on
/linux-6.15/Documentation/admin-guide/
H A Dkernel-parameters.txt7108 Control the default policy of each hugepage size for the
7378 Can be used to control the hugepage allocation policy for
7385 Can be used to control the default hugepage allocation policy