Home
last modified time | relevance | path

Searched refs:huge (Results 1 – 25 of 76) sorted by relevance

1234

/linux/arch/powerpc/include/asm/nohash/32/
H A Dpte-8xx.h123 unsigned long clr, unsigned long set, int huge);
136 int huge = psize > mmu_virtual_psize ? 1 : 0; in __ptep_set_access_flags() local
138 pte_update(vma->vm_mm, address, ptep, clr, set, huge); in __ptep_set_access_flags()
175 static inline int number_of_cells_per_pte(pmd_t *pmd, pte_basic_t val, int huge) in number_of_cells_per_pte() argument
177 if (!huge) in number_of_cells_per_pte()
188 unsigned long clr, unsigned long set, int huge) in __pte_update() argument
196 num = number_of_cells_per_pte(pmd, new, huge); in __pte_update()
211 unsigned long clr, unsigned long set, int huge) in pte_update() argument
215 if (huge && ptep_is_8m_pmdp(mm, addr, ptep)) { in pte_update()
218 old = __pte_update(mm, addr, pte_offset_kernel(pmdp, 0), clr, set, huge); in pte_update()
[all …]
/linux/Documentation/admin-guide/mm/
H A Dtranshuge.rst11 using huge pages for the backing of virtual memory with huge pages
20 the huge page size is 2M, although the actual numbers may vary
56 prominent because the size of each page isn't as huge as the PMD-sized
66 collapses sequences of basic pages into huge pages of either PMD size
126 PMD-sized huge pages unconditionally.
197 MADV_COLLAPSE)`` can still cause transparent huge pages to be
200 By default kernel tries to use huge, PMD-mappable zero page on read
201 page fault to anonymous mapping. It's possible to disable huge zero
331 swap when collapsing a group of pages into a transparent huge page::
426 Traditionally, tmpfs only supported a single huge page size ("PMD"). Today,
[all …]
H A Dconcepts.rst79 `huge`. Usage of huge pages significantly reduces pressure on TLB,
83 memory with the huge pages. The first one is `HugeTLB filesystem`, or
86 the memory and mapped using huge pages. The hugetlbfs is described at
89 Another, more recent, mechanism that enables use of the huge pages is
92 the system memory should and can be mapped by the huge pages, THP
201 buffer for DMA, or when THP allocates a huge page. Memory `compaction`
/linux/tools/testing/selftests/mm/
H A Dcharge_reserved_hugetlb.sh60 if [[ -e /mnt/huge ]]; then
61 rm -rf /mnt/huge/*
62 umount /mnt/huge || echo error
63 rmdir /mnt/huge
286 if [[ -e /mnt/huge ]]; then
287 rm -rf /mnt/huge/*
288 umount /mnt/huge
289 rmdir /mnt/huge
316 mkdir -p /mnt/huge
317 mount -t hugetlbfs -o pagesize=${MB}M none /mnt/huge
[all...]
H A Drun_vmtests.sh77 test transparent huge pages
79 test hugetlbfs huge pages
137 for huge in -t -T "-H -m $hugetlb_mb"; do
149 $huge $test_cmd $write $share $num
/linux/arch/powerpc/include/asm/book3s/64/
H A Dhash.h162 pte_t *ptep, unsigned long pte, int huge);
190 int huge) in hash__pte_update() argument
196 if (IS_ENABLED(CONFIG_PPC_4K_PAGES) && huge) { in hash__pte_update()
213 if (!huge) in hash__pte_update()
217 hpte_need_flush(mm, addr, ptep, old, huge); in hash__pte_update()
H A Dradix.h176 int huge) in radix__pte_update() argument
181 if (!huge) in radix__pte_update()
/linux/arch/powerpc/include/asm/nohash/
H A Dpgtable.h7 unsigned long clr, unsigned long set, int huge);
60 unsigned long clr, unsigned long set, int huge) in pte_update() argument
71 if (huge) in pte_update()
97 if (!huge) in pte_update()
149 int huge = psize > mmu_virtual_psize ? 1 : 0; in __ptep_set_access_flags() local
151 pte_update(vma->vm_mm, address, ptep, 0, set, huge); in __ptep_set_access_flags()
/linux/Documentation/driver-api/cxl/allocation/
H A Dhugepages.rst19 Different huge page sizes allow different memory configurations.
24 for use as 2MB huge pages.
/linux/mm/
H A Dshmem.c122 int huge; member
539 * Definitions for "huge tmpfs": tmpfs mounted with the huge= option
542 * disables huge pages for the mount;
544 * enables huge pages for the mount;
546 * only allocate huge pages if the page will be fully within i_size,
549 * only allocate huge pages if requested with madvise();
562 * disables huge on shm_mnt and all mounts, for emergency use;
564 * enables huge on shm_mnt and all mounts, w/o needing option, for testing;
644 * The huge orde in shmem_huge_global_enabled()
673 int huge; shmem_parse_huge() local
706 shmem_format_huge(int huge) shmem_format_huge() argument
5461 int huge, err; shmem_enabled_store() local
5595 int huge; setup_transparent_hugepage_shmem() local
5610 int huge; setup_transparent_hugepage_tmpfs() local
[all...]
H A Dmemory-failure.c2742 bool huge = false; in unpoison_memory() local
2798 huge = true; in unpoison_memory()
2814 huge = true; in unpoison_memory()
2832 if (!huge) in unpoison_memory()
2855 bool huge = folio_test_hugetlb(folio); in soft_offline_in_use_page() local
2864 if (!huge && folio_test_large(folio)) { in soft_offline_in_use_page()
2883 if (!huge) in soft_offline_in_use_page()
2892 if (!huge && folio_test_lru(folio) && !folio_test_swapcache(folio)) in soft_offline_in_use_page()
2921 bool release = !huge; in soft_offline_in_use_page()
2923 if (!page_handle_poison(page, huge, release)) in soft_offline_in_use_page()
[all …]
H A DKconfig363 providing a huge performance boost. If this option is not enabled,
821 of the huge zero folio and expand the places in the kernel
822 that can use huge zero folios. For instance, block I/O benefits
825 With this option enabled, the huge zero folio is allocated
826 once and never freed. One full huge page's worth of memory shall
842 Transparent Hugepages allows the kernel to use huge pages and
843 huge tlb transparently to the applications whenever possible.
899 transparent huge pages to be obtained even if this mode is
943 madvise(MADV_COLLAPSE) can still cause transparent huge pages
975 Swap transparent huge pages in one piece, without splitting.
[all …]
/linux/Documentation/admin-guide/hw-vuln/
H A Dmultihit.rst81 * - KVM: Mitigation: Split huge pages
111 In order to mitigate the vulnerability, KVM initially marks all huge pages
125 The KVM hypervisor mitigation mechanism for marking huge pages as
134 non-executable huge pages in Linux kernel KVM module. All huge
/linux/Documentation/core-api/
H A Dpin_user_pages.rst64 severely by huge pages, because each tail page adds a refcount to the
66 field, refcount overflows were seen in some huge page stress tests.
68 This also means that huge pages and large folios do not suffer
248 acquired since the system was powered on. For huge pages, the head page is
249 pinned once for each page (head page and each tail page) within the huge page.
250 This follows the same sort of behavior that get_user_pages() uses for huge
251 pages: the head page is refcounted once for each tail or head page in the huge
252 page, when get_user_pages() is applied to a huge page.
256 PAGE_SIZE granularity, even if the original pin was applied to a huge page.
/linux/arch/alpha/lib/
H A Dev6-clear_user.S86 subq $1, 16, $4 # .. .. .. E : If < 16, we can not use the huge loop
87 and $16, 0x3f, $2 # .. .. E .. : Forward work for huge loop
88 subq $2, 0x40, $3 # .. E .. .. : bias counter (huge loop)
/linux/Documentation/mm/
H A Darch_pgtable_helpers.rst136 | pmd_set_huge | Creates a PMD huge mapping |
138 | pmd_clear_huge | Clears a PMD huge mapping |
187 | pud_set_huge | Creates a PUD huge mapping |
189 | pud_clear_huge | Clears a PUD huge mapping |
H A Dunevictable-lru.rst315 (unless it is a PTE mapping of a part of a transparent huge page). Or when
350 hugetlbfs ranges, allocating the huge pages and populating the PTEs.
437 A transparent huge page is represented by a single entry on an LRU list.
441 If a user tries to mlock() part of a huge page, and no user mlock()s the
442 whole of the huge page, we want the rest of the page to be reclaimable.
447 We handle this by keeping PTE-mlocked huge pages on evictable LRU lists:
450 This way the huge page is accessible for vmscan. Under memory pressure the
455 of a transparent huge page which are mapped only by PTEs in VM_LOCKED VMAs.
491 (unless it was a PTE mapping of a part of a transparent huge page).
516 (unless it was a PTE mapping of a part of a transparent huge page).
/linux/Documentation/arch/riscv/
H A Dvm-layout.rst42 …0000004000000000 | +256 GB | ffffffbfffffffff | ~16M TB | ... huge, almost 64 bits wide hole of…
79 …0000800000000000 | +128 TB | ffff7fffffffffff | ~16M TB | ... huge, almost 64 bits wide hole of…
115 …0100000000000000 | +64 PB | feffffffffffffff | ~16K PB | ... huge, almost 64 bits wide hole of…
/linux/Documentation/features/vm/huge-vmap/
H A Darch-support.txt2 # Feature name: huge-vmap
/linux/Documentation/arch/x86/x86_64/
H A Dmm.rst36 …0000800000000000 | +128 TB | 7fffffffffffffff | ~8 EB | ... huge, almost 63 bits wide hole of…
47 …8000000000000000 | -8 EB | ffff7fffffffffff | ~8 EB | ... huge, almost 63 bits wide hole of…
107 …0100000000000000 | +64 PB | 7fffffffffffffff | ~8 EB | ... huge, almost 63 bits wide hole of…
117 …8000000000000000 | -8 EB | feffffffffffffff | ~8 EB | ... huge, almost 63 bits wide hole of…
/linux/tools/testing/selftests/kvm/include/x86/
H A Dkvm_util_arch.h21 u64 huge; member
/linux/fs/btrfs/
H A DKconfig109 - block size > page size support - needs transparent huge page and
112 - huge folios for data - folios can be as large as 2MiB now
/linux/Documentation/admin-guide/blockdev/
H A Dzram.rst177 size of the disk when not in use so a huge zram is wasteful.
386 echo huge > /sys/block/zramX/writeback
394 Additionally, if a user choose to writeback only huge and idle pages
501 algorithm can, for example, be more successful compressing huge pages (those
538 #HUGE pages recompression is activated by `huge` mode
539 echo "type=huge priority=2" > /sys/block/zram0/recompress
596 huge page
605 and the block's state is huge so it is written back to the backing
/linux/Documentation/filesystems/ext4/
H A Dbigalloc.rst9 exceeds the page size. However, for a filesystem of mostly huge files,
/linux/fs/netfs/
H A DKconfig8 segmentation, local caching and transparent huge page support.

1234