@@ -812,7 +812,10 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma,
while (page_vma_mapped_walk(&pvmw)) {
address = pvmw.address;
- if (vma->vm_flags & VM_LOCKED) {
+ if ((vma->vm_flags & VM_LOCKED) &&
+ (!PageTransCompound(page) || !pvmw.pte)) {
+ /* Restore the mlock which got missed */
+ mlock_vma_page(page, vma, !pvmw.pte);
page_vma_mapped_walk_done(&pvmw);
pra->vm_flags |= VM_LOCKED;
return false; /* To break the loop */
@@ -851,7 +854,7 @@ static bool page_referenced_one(struct page *page, struct vm_area_struct *vma,
if (referenced) {
pra->referenced++;
- pra->vm_flags |= vma->vm_flags;
+ pra->vm_flags |= vma->vm_flags & ~VM_LOCKED;
}
if (!pra->mapcount)
@@ -1386,11 +1386,11 @@ static enum page_references page_check_references(struct page *page,
referenced_page = TestClearPageReferenced(page);
/*
- * Mlock lost the isolation race with us. Let try_to_unmap()
- * move the page to the unevictable list.
+ * The supposedly reclaimable page was found to be in a VM_LOCKED vma.
+ * Let the page, now marked Mlocked, be moved to the unevictable list.
*/
if (vm_flags & VM_LOCKED)
- return PAGEREF_RECLAIM;
+ return PAGEREF_ACTIVATE;
if (referenced_ptes) {
/*
4.8 commit 7751b2da6be0 ("vmscan: split file huge pages before paging them out") inserted a split_huge_page_to_list() into shrink_page_list() without considering the mlock case: no problem if the page has already been marked as Mlocked (the !page_evictable check much higher up will have skipped all this), but it has always been the case that races or omissions in setting Mlocked can rely on page reclaim to detect this and correct it before actually reclaiming - and that remains so, but what a shame if a hugepage is needlessly split before discovering it. It is surprising that page_check_references() returns PAGEREF_RECLAIM when VM_LOCKED, but there was a good reason for that: try_to_unmap_one() is where the condition is detected and corrected; and until now it could not be done in page_referenced_one(), because that does not always have the page locked. Now that mlock's requirement for page lock has gone, copy try_to_unmap_one()'s mlock restoration into page_referenced_one(), and let page_check_references() return PAGEREF_ACTIVATE in this case. But page_referenced_one() may find a pte mapping one part of a hugepage: what hold should a pte mapped in a VM_LOCKED area exert over the entire huge page? That's debatable. The approach taken here is to treat that pte mapping in page_referenced_one() as if not VM_LOCKED, and if no VM_LOCKED pmd mapping is found later in the walk, and lack of reference permits, then PAGEREF_RECLAIM take it to attempted splitting as before. Signed-off-by: Hugh Dickins <hughd@google.com> --- v2: same as v1. mm/rmap.c | 7 +++++-- mm/vmscan.c | 6 +++--- 2 files changed, 8 insertions(+), 5 deletions(-)