Lines Matching refs:pages
13 * Ok, demand-loading was easy, shared pages a little bit tricker. Shared
14 * pages started 02.12.91, seems to work. - Linus.
221 * Note: this doesn't free the actual pages themselves. That
561 * special mapping (even if there are underlying and valid "struct pages").
562 * COWed pages of a VM_PFNMAP are always normal.
564 * The way we recognize COWed pages within VM_PFNMAP mappings is through the
582 * page" backing, however the difference is that _all_ pages with a struct
584 * normal pages by the VM. The disadvantage is that pages are refcounted
636 * NOTE! We still have PageReserved() pages in the page tables.
679 * COW mappings require pages in both parent
922 * unmap shared but keep private pages.
1076 * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here
1081 * Unmap all pages in the vma list.
1084 * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to
1093 * ensure that any thus-far unmapped pages are flushed before unmap_vmas()
1182 * zap_page_range - remove user pages in a given range
1183 * @vma: vm_area_struct holding the applicable pages
1184 * @address: starting address of pages to zap
1208 * @address: starting address of pages to zap
1330 * has touched so far, we don't want to allocate unnecessary pages or
1344 struct page **pages, struct vm_area_struct **vmas)
1352 VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
1376 /* user gate pages are read-only */
1394 if (pages) {
1407 pages[i] = page;
1425 i = follow_hugetlb_page(mm, vma, pages, vmas,
1436 * pages and potentially allocating memory.
1482 if (pages) {
1483 pages[i] = page;
1499 * get_user_pages() - pin user pages in memory
1503 * @nr_pages: number of pages from start to pin
1504 * @write: whether pages will be written to by the caller
1508 * @pages: array that receives pointers to the pages pinned.
1510 * only intends to ensure the pages are faulted in.
1514 * Returns number of pages pinned. This may be fewer than the number
1515 * requested. If nr_pages is 0 or negative, returns 0. If no pages
1542 * addresses. The pages may be submitted for DMA to devices or accessed via
1550 struct page **pages, struct vm_area_struct **vmas)
1554 if (pages)
1561 return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
1609 * For historical reasons, it only allows reserved pages. Only
1611 * pages reserved for the old functions anyway.
1654 * This allows drivers to insert individual pages they've allocated
1716 * Similar to vm_inert_page, this allows drivers to insert individual pages
1724 * As this is called only for pages that do not currently exist, we
1784 * maps a range of physical memory into the requested pages. the old
1785 * mappings are removed. any references to nonexistent pages results
1869 * Physically remapped pages are special. Tell the
1871 * VM_IO tells people not to look at these pages
1875 * in 2.6 the LRU scan won't even find its pages, so this
1876 * flag means no more than count its pages in reserved_vm,
1878 * VM_PFNMAP tells the core MM that the base pages are just
1884 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
2090 * This routine handles present pages, when users try to write
2122 * We should not cow pages in a shared writeable mapping.
2123 * Just mark the pages writable as we can't do any dirty
2133 * Take out anonymous pages first, anonymous shared vmas are
2162 * Only catch write-faults on shared writable pages,
2163 * read-only shared pages can get COWed by
2361 * but still dirty their pages
2521 * across *all* the pages in each nonlinear VMA, not just the pages
2543 * partial pages.
2547 * @even_cows: 1 when truncating a file, unmap even private COWed pages;
2671 * hwpoisoned dirty swapcache pages are kept for killing
2897 * tries to share with existing pages, but makes a separate copy if
2901 * As this is called only for pages that do not currently exist, we
3065 * dirty their pages
3130 * These routines also need to handle stuff like marking pages dirty