mm/munlock: replace clear_page_mlock() by final clearance

Placing munlock_vma_page() at the end of page_remove_rmap() shifts most
of the munlocking to clear_page_mlock(), since PageMlocked is typically
still set when mapcount has fallen to 0.  That is not what we want: we
want /proc/vmstat's unevictable_pgs_cleared to remain as a useful check
on the integrity of of the mlock/munlock protocol - small numbers are
not surprising, but big numbers mean the protocol is not working.

That could be easily fixed by placing munlock_vma_page() at the start of
page_remove_rmap(); but later in the series we shall want to batch the
munlocking, and that too would tend to leave PageMlocked still set at
the point when it is checked.

So delete clear_page_mlock() now: leave it instead to release_pages()
(and __page_cache_release()) to do this backstop clearing of Mlocked,
when page refcount has fallen to 0.  If a pinned page occasionally gets
counted as Mlocked and Unevictable until it is unpinned, that's okay.

A slightly regrettable side-effect of this change is that, since
release_pages() and __page_cache_release() may be called at interrupt
time, those places which update NR_MLOCK with interrupts enabled
had better use mod_zone_page_state() than __mod_zone_page_state()
(but holding the lruvec lock always has interrupts disabled).

This change, forcing Mlocked off when refcount 0 instead of earlier
when mapcount 0, is not fundamental: it can be reversed if performance
or something else is found to suffer; but this is the easiest way to
separate the stats - let's not complicate that without good reason.

Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>

1 files changed, 24 insertions, 8 deletions

diff --git a/mm/swap.c b/mm/swap.c
index bcf3ac288b56..ff4810e4a4bc 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -74,8 +74,8 @@ static DEFINE_PER_CPU(struct lru_pvecs, lru_pvecs) = {
 };
 
 /*
- * This path almost never happens for VM activity - pages are normally
- * freed via pagevecs.  But it gets used by networking.
+ * This path almost never happens for VM activity - pages are normally freed
+ * via pagevecs.  But it gets used by networking - and for compound pages.
  */
 static void __page_cache_release(struct page *page)
 {
@@ -89,6 +89,14 @@ static void __page_cache_release(struct page *page)
 		__clear_page_lru_flags(page);
 		unlock_page_lruvec_irqrestore(lruvec, flags);
 	}
+	/* See comment on PageMlocked in release_pages() */
+	if (unlikely(PageMlocked(page))) {
+		int nr_pages = thp_nr_pages(page);
+
+		__ClearPageMlocked(page);
+		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
+		count_vm_events(UNEVICTABLE_PGCLEARED, nr_pages);
+	}
 	__ClearPageWaiters(page);
 }
 
@@ -489,12 +497,8 @@ void lru_cache_add_inactive_or_unevictable(struct page *page,
 	unevictable = (vma->vm_flags & (VM_LOCKED | VM_SPECIAL)) == VM_LOCKED;
 	if (unlikely(unevictable) && !TestSetPageMlocked(page)) {
 		int nr_pages = thp_nr_pages(page);
-		/*
-		 * We use the irq-unsafe __mod_zone_page_state because this
-		 * counter is not modified from interrupt context, and the pte
-		 * lock is held(spinlock), which implies preemption disabled.
-		 */
-		__mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
+
+		mod_zone_page_state(page_zone(page), NR_MLOCK, nr_pages);
 		count_vm_events(UNEVICTABLE_PGMLOCKED, nr_pages);
 	}
 	lru_cache_add(page);
@@ -969,6 +973,18 @@ void release_pages(struct page **pages, int nr)
 			__clear_page_lru_flags(page);
 		}
 
+		/*
+		 * In rare cases, when truncation or holepunching raced with
+		 * munlock after VM_LOCKED was cleared, Mlocked may still be
+		 * found set here.  This does not indicate a problem, unless
+		 * "unevictable_pgs_cleared" appears worryingly large.
+		 */
+		if (unlikely(PageMlocked(page))) {
+			__ClearPageMlocked(page);
+			dec_zone_page_state(page, NR_MLOCK);
+			count_vm_event(UNEVICTABLE_PGCLEARED);
+		}
+
 		__ClearPageWaiters(page);
 
 		list_add(&page->lru, &pages_to_free);