Lines Matching refs:split
974 * When we COW a devmap PMD entry, we split it into PTEs, so we should
1069 * under splitting since we don't split the page itself, only pmd to
1086 * If this page is a potentially pinned page, split and retry the fault
1200 * under splitting since we don't split the page itself, only pud to
1608 * If user want to discard part-pages of THP, split it so MADV_FREE
1721 * With split pmd lock we also need to move preallocated
2090 * whole access to the hugepage during the split (which happens in
2104 * must remain set at all times on the pmd until the split is complete
2320 * previously contain an hugepage: check if we need to split
2330 * previously contain an hugepage: check if we need to split
2341 * contain an hugepage: check if we need to split an huge pmd.
2527 * of the tail pages after the split is complete.
2615 /* Racy check whether the huge page can be split */
2632 * subpage of huge page to split. Split doesn't change the position of @page.
2634 * Only caller must hold pin on the @page, otherwise split fails with -EBUSY.
2645 * Returns 0 if the hugepage is split successfully.
2673 * is taken to serialise against parallel split or collapse
2707 * Racy check if we can split the page, before unmap_page() will
2708 * split PMDs
2797 * this may cause a race condition to corrupt deferred split queue.
2846 int split = 0;
2876 split++;
2887 * Stop shrinker if we didn't split any page, but the queue is empty.
2890 if (!split && list_empty(&ds_queue->split_queue))
2892 return split;
2909 unsigned long total = 0, split = 0;
2933 split++;
2940 pr_info("%lu of %lu THP split\n", split, total);