linux-6.8/mm/khugepaged.c

82  * default collapse hugepages if there is at least one pte mapped like
86  * Note that these are only respected if collapse was initiated by khugepaged.
247  * max_ptes_none controls if khugepaged should collapse hugepages over
650 		 * If collapse was initiated by khugepaged, check that there is  in __collapse_huge_page_isolate()
980  * Bring missing pages in from swap, to complete THP collapse.
1129 		 * that case.  Continuing to collapse causes inconsistency.  in collapse_huge_page()
1314 			 * Don't collapse the page if any of the small  in hpage_collapse_scan_pmd()
1375 		 * But such case is ephemeral we could always retry collapse  in hpage_collapse_scan_pmd()
1386 		 * If collapse was initiated by khugepaged, check that there is  in hpage_collapse_scan_pmd()
1465  * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at
1468  * @mm: process address space where collapse happens
1469  * @addr: THP collapse address
1767  * collapse_file - collapse filemap/tmpfs/shmem pages into huge one.
1769  * @mm: process address space where collapse happens
1770  * @addr: virtual collapse start address
1771  * @file: file that collapse on
1772  * @start: collapse start address
1773  * @cc: collapse context and scratchpad
1993 		 * blocked until we unlock page after collapse/during rollback.  in collapse_file()
2033 	 * If collapse is successful, flush must be done now before copying.  in collapse_file()
2034 	 * If collapse is unsuccessful, does flush actually need to be done?  in collapse_file()
2166 	 * The collapse has succeeded, so free the old pages.  in collapse_file()
2691 	 * specified memory range. khugepaged likely won't be able to collapse  in madvise_collapse_errno()