| /linux/Documentation/mm/ |
| H A D | arch_pgtable_helpers.rst | 79 PMD Page Table Helpers
83 | pmd_same | Tests whether both PMD entries are the same |
85 | pmd_bad | Tests a non-table mapped PMD |
87 | pmd_leaf | Tests a leaf mapped PMD |
89 | pmd_trans_huge | Tests a Transparent Huge Page (THP) at PMD |
93 | pmd_young | Tests a young PMD |
95 | pmd_dirty | Tests a dirty PMD |
97 | pmd_write | Tests a writable PMD |
99 | pmd_special | Tests a special PMD |
101 | pmd_protnone | Tests a PROT_NONE PMD |
[all …]
|
| H A D | split_page_table_lock.rst | 11 access to the table. At the moment we use split lock for PTE and PMD
36 takes PMD table lock, returns pointer to taken lock;
38 returns pointer to PMD table lock;
44 Split page table lock for PMD tables is enabled, if it's enabled for PTE
50 Hugetlb can support several page sizes. We use split lock only for PMD
72 PMD split lock only makes sense if you have more than two page table
75 PMD split lock enabling requires pagetable_pmd_ctor() call on PMD table
79 pmd_free_tlb(), but make sure you cover all PMD table allocation / freeing
105 pagetable_pmd_ctor() for PMD table.
|
| H A D | vmemmap_dedup.rst | 115 | PMD | +-----------+ +-----------+
148 | PMD | +-----------+ | | |
221 | PMD | +-----------+ | | |
|
| H A D | page_tables.rst | 76 +-->| PMD |
129 PMD
252 The page table walk may end at one of the middle or upper layers (PMD, PUD).
258 1GB. They are respectively mapped by the PMD and PUD page entries.
|
| H A D | multigen_lru.rst | 192 adds the PMD entry pointing to the PTE table to the Bloom filter. This
202 PMD has a sufficient number of hot pages, its address is placed in the
|
| H A D | unevictable-lru.rst | 313 For each PTE (or PMD) being faulted into a VMA, the page add rmap function
448 the PMD on the border of a VM_LOCKED VMA will be split into a PTE table.
489 For each PTE (or PMD) being unmapped from a VMA, folio_remove_rmap_*() calls
514 for each PTE (or PMD) being unmapped from a VMA, folio_remove_rmap_*() calls
|
| /linux/Documentation/translations/zh_CN/mm/ |
| H A D | split_page_table_lock.rst | 19 PMD表使用分页锁。对高层表的访问由mm->page_table_lock保护。
33 取得PMD表锁，返回所取锁的指针。
35 返回指向PMD表锁的指针；
41 如果PMD表启用了分页锁，并且架构支持它，那么PMD表的分页锁就会被启用（见
47 Hugetlb可以支持多种页面大小。我们只对PMD级别使用分页锁，但不对PUD使用。
65 PMD分页锁只有在你有两个以上的页表级别时才有意义。
67 启用PMD分页锁需要在PMD表分配时调用pagetable_pmd_ctor()，在释放时调
71 中，但要确保覆盖所有的PMD表分配/释放路径：即X86_PAE在pgd_alloc()中预先
72 分配一些PMD。
93 PTE表的spinlock_t分配在pagetable_pte_ctor()中，PMD表的spinlock_t
|
| H A D | page_tables.rst | 72 +-->| PMD |
116 PMD
201 页表遍历可能在中间或者上层结束(PMD，PUD)。
205 PMD 和 PUD 页表项映射。
|
| H A D | page_table_check.rst | 21 当新的页面可以从用户空间访问时，页表检查通过将它们的页表项（PTEs PMD等）添加到页表中来执行额外
|
| /linux/arch/sparc/include/asm/ |
| H A D | pgalloc_64.h | 41 #define pud_populate(MM, PUD, PMD) __pud_populate(PUD, PMD) argument
72 #define pmd_populate_kernel(MM, PMD, PTE) pmd_set(MM, PMD, PTE) argument
73 #define pmd_populate(MM, PMD, PTE) pmd_set(MM, PMD, PTE) argument
|
| H A D | pgalloc_32.h | 36 #define pud_populate(MM, PGD, PMD) pud_set(PGD, PMD) argument
|
| H A D | pgtable_64.h | 1161 #define pmd_pgtable(PMD) ((pte_t *)pmd_page_vaddr(PMD)) argument
|
| /linux/Documentation/networking/device_drivers/fddi/ |
| H A D | defza.rst | 16 the standard MMF-PMD, however with a pair of ST connectors rather than
19 between the DEC proprietary ThinWire-PMD using a BNC connector and the
20 standard STP-PMD using a DE-9F connector. This option can interface to
21 a DECconcentrator 500 device and, in the case of the STP-PMD, also other
|
| /linux/Documentation/translations/zh_CN/arch/arm64/ |
| H A D | hugetlbpage.rst | 40 - CONT PTE PMD CONT PMD PUD
|
| /linux/Documentation/arch/powerpc/ |
| H A D | vmemmap_dedup.rst | 14 With 2M PMD level mapping, we require 32 struct pages and a single 64K vmemmap
46 With 4K page size, 2M PMD level mapping requires 512 struct pages and a single
62 | PMD | +-----------+ | | |
|
| /linux/Documentation/translations/zh_TW/arch/arm64/ |
| H A D | hugetlbpage.rst | 43 - CONT PTE PMD CONT PMD PUD
|
| /linux/Documentation/admin-guide/mm/ |
| H A D | transhuge.rst | 50 but smaller than traditional PMD-size (as described above), in
56 prominent because the size of each page isn't as huge as the PMD-sized
66 collapses sequences of basic pages into PMD-sized huge pages.
125 PMD-sized huge pages unconditionally.
147 By default, PMD-sized hugepages have enabled="inherit" and all other
199 By default kernel tries to use huge, PMD-mappable zero page on read
208 PMD-mappable transparent hugepage::
222 khugepaged will be automatically started when PMD-sized THP is enabled
225 PMD-sized THP is disabled (when both the per-size anon control and the
269 PMD-sized THP and no attempt is made to collapse to other THP
[all …]
|
| /linux/Documentation/arch/arm64/ |
| H A D | hugetlbpage.rst | 38 - CONT PTE PMD CONT PMD PUD
|
| H A D | ptdump.rst | 36 level PTE or block level PGD, PMD and PUD, and access status of a page
89 0xfff0000080000000-0xfff0000800000000 30G PMD
93 0xfff0000880000000-0xfff0040000000000 4062G PMD
|
| /linux/tools/testing/selftests/mm/ |
| H A D | mremap_test.c | 60 PMD = _2MB, enumerator
1401 test_cases[6] = MAKE_TEST(PMD, PTE, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS, in main()
1403 test_cases[7] = MAKE_TEST(PMD, _1MB, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS, in main()
1405 test_cases[8] = MAKE_TEST(PMD, PMD, _4MB, NON_OVERLAPPING, EXPECT_SUCCESS, in main()
1413 test_cases[11] = MAKE_TEST(PUD, PMD, _2GB, NON_OVERLAPPING, EXPECT_SUCCESS, in main()
1433 perf_test_cases[1] = MAKE_TEST(PMD, PMD, _1GB, NON_OVERLAPPING, EXPECT_SUCCESS, in main()
|
| H A D | run_vmtests.sh | 84 test handling of code that might set PTE/PMD dirty in
|
| /linux/Documentation/devicetree/bindings/net/ |
| H A D | broadcom-bcm87xx.txt | 24 * Set PMD Digital Control Register for
|
| /linux/arch/arm/kernel/ |
| H A D | head.S | 209 add r3, r4, #0x1000 @ first PMD table address
221 add r3, r3, #0x1000 @ next PMD table
225 add r4, r4, #0x1000 @ point to the PMD tables
|
| /linux/Documentation/translations/zh_CN/arch/riscv/ |
| H A D | boot.rst | 50 RISC-V内核期望被放置在PMD边界（对于rv64为2MB对齐，对于rv32为4MB对齐）。
|
| /linux/Documentation/filesystems/ |
| H A D | locking.rst | 624 ->huge_fault() is called when there is no PUD or PMD entry present. This
625 gives the filesystem the opportunity to install a PUD or PMD sized page.
626 Filesystems can also use the ->fault method to return a PMD sized page,
|