4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Hugh Dickins <hughd@xxxxxxxxxx> commit e1f1b1572e8db87a56609fd05bef76f98f0e456a upstream. __split_huge_pmd_locked() must check if the cleared huge pmd was dirty, and propagate that to PageDirty: otherwise, data may be lost when a huge tmpfs page is modified then split then reclaimed. How has this taken so long to be noticed? Because there was no problem when the huge page is written by a write system call (shmem_write_end() calls set_page_dirty()), nor when the page is allocated for a write fault (fault_dirty_shared_page() calls set_page_dirty()); but when allocated for a read fault (which MAP_POPULATE simulates), no set_page_dirty(). Link: http://lkml.kernel.org/r/alpine.LSU.2.11.1807111741430.1106@eggly.anvils Fixes: d21b9e57c74c ("thp: handle file pages in split_huge_pmd()") Signed-off-by: Hugh Dickins <hughd@xxxxxxxxxx> Reported-by: Ashwin Chaugule <ashwinch@xxxxxxxxxx> Reviewed-by: Yang Shi <yang.shi@xxxxxxxxxxxxxxxxx> Reviewed-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: "Huang, Ying" <ying.huang@xxxxxxxxx> Cc: <stable@xxxxxxxxxxxxxxx> [4.8+] Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- mm/huge_memory.c | 2 ++ 1 file changed, 2 insertions(+) --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1642,6 +1642,8 @@ static void __split_huge_pmd_locked(stru if (vma_is_dax(vma)) return; page = pmd_page(_pmd); + if (!PageDirty(page) && pmd_dirty(_pmd)) + set_page_dirty(page); if (!PageReferenced(page) && pmd_young(_pmd)) SetPageReferenced(page); page_remove_rmap(page, true);
