mm/rmap: always do TTU_IGNORE_ACCESS

Since commit 369ea8242c0f ("mm/rmap: update to new mmu_notifier semantic
v2"), the code to check the secondary MMU's page table access bit is
broken for !(TTU_IGNORE_ACCESS) because the page is unmapped from the
secondary MMU's page table before the check.  More specifically for those
secondary MMUs which unmap the memory in
mmu_notifier_invalidate_range_start() like kvm.

However memory reclaim is the only user of !(TTU_IGNORE_ACCESS) or the
absence of TTU_IGNORE_ACCESS and it explicitly performs the page table
access check before trying to unmap the page.  So, at worst the reclaim
will miss accesses in a very short window if we remove page table access
check in unmapping code.

There is an unintented consequence of !(TTU_IGNORE_ACCESS) for the memcg
reclaim.  From memcg reclaim the page_referenced() only account the
accesses from the processes which are in the same memcg of the target page
but the unmapping code is considering accesses from all the processes, so,
decreasing the effectiveness of memcg reclaim.

The simplest solution is to always assume TTU_IGNORE_ACCESS in unmapping
code.

Link: https://lkml.kernel.org/r/20201104231928.1494083-1-shakeelb@google.com
Fixes: 369ea8242c0f ("mm/rmap: update to new mmu_notifier semantic v2")
Signed-off-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jerome Glisse <jglisse@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 5 insertions, 9 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7b4e31eac2cf..0ec6321e9887 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1072,7 +1072,6 @@ static void page_check_dirty_writeback(struct page *page,
 static unsigned int shrink_page_list(struct list_head *page_list,
 				     struct pglist_data *pgdat,
 				     struct scan_control *sc,
-				     enum ttu_flags ttu_flags,
 				     struct reclaim_stat *stat,
 				     bool ignore_references)
 {
@@ -1297,7 +1296,7 @@ static unsigned int shrink_page_list(struct list_head *page_list,
 		 * processes. Try to unmap it here.
 		 */
 		if (page_mapped(page)) {
-			enum ttu_flags flags = ttu_flags | TTU_BATCH_FLUSH;
+			enum ttu_flags flags = TTU_BATCH_FLUSH;
 			bool was_swapbacked = PageSwapBacked(page);
 
 			if (unlikely(PageTransHuge(page)))
@@ -1514,7 +1513,7 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	}
 
 	nr_reclaimed = shrink_page_list(&clean_pages, zone->zone_pgdat, &sc,
-			TTU_IGNORE_ACCESS, &stat, true);
+					&stat, true);
 	list_splice(&clean_pages, page_list);
 	mod_node_page_state(zone->zone_pgdat, NR_ISOLATED_FILE,
 			    -(long)nr_reclaimed);
@@ -1958,8 +1957,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	if (nr_taken == 0)
 		return 0;
 
-	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, 0,
-				&stat, false);
+	nr_reclaimed = shrink_page_list(&page_list, pgdat, sc, &stat, false);
 
 	spin_lock_irq(&pgdat->lru_lock);
 
@@ -2131,8 +2129,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 
 		nr_reclaimed += shrink_page_list(&node_page_list,
 						NODE_DATA(nid),
-						&sc, 0,
-						&dummy_stat, false);
+						&sc, &dummy_stat, false);
 		while (!list_empty(&node_page_list)) {
 			page = lru_to_page(&node_page_list);
 			list_del(&page->lru);
@@ -2145,8 +2142,7 @@ unsigned long reclaim_pages(struct list_head *page_list)
 	if (!list_empty(&node_page_list)) {
 		nr_reclaimed += shrink_page_list(&node_page_list,
 						NODE_DATA(nid),
-						&sc, 0,
-						&dummy_stat, false);
+						&sc, &dummy_stat, false);
 		while (!list_empty(&node_page_list)) {
 			page = lru_to_page(&node_page_list);
 			list_del(&page->lru);