From: Michal Hocko <mhocko@xxxxxxxx> Subject: mm, fault_around: do not take a reference to a locked page filemap_map_pages takes a speculative reference to each page in the range before it tries to lock that page. While this is correct it also can influence page migration which will bail out when seeing an elevated reference count. The faultaround code would bail on seeing a locked page so we can pro-actively check the PageLocked bit before page_cache_get_speculative and prevent from pointless reference count churn. Link: http://lkml.kernel.org/r/20181211142741.2607-4-mhocko@xxxxxxxxxx Signed-off-by: Michal Hocko <mhocko@xxxxxxxx> Suggested-by: Jan Kara <jack@xxxxxxx> Acked-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Reviewed-by: David Hildenbrand <david@xxxxxxxxxx> Acked-by: Hugh Dickins <hughd@xxxxxxxxxx> Reviewed-by: William Kucharski <william.kucharski@xxxxxxxxxx> Cc: Oscar Salvador <osalvador@xxxxxxx> Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- --- a/mm/filemap.c~mm-fault_around-do-not-take-a-reference-to-a-locked-page +++ a/mm/filemap.c @@ -2614,6 +2614,13 @@ void filemap_map_pages(struct vm_fault * goto next; head = compound_head(page); + + /* + * Check for a locked page first, as a speculative + * reference may adversely influence page migration. + */ + if (PageLocked(head)) + goto next; if (!page_cache_get_speculative(head)) goto next; _
