Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things and hotfixes

 - ocfs2

 - almost all of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (139 commits)
  kernel/memremap.c: remove the unused device_private_entry_fault() export
  mm: delete find_get_entries_tag
  mm/huge_memory.c: make __thp_get_unmapped_area static
  mm/mprotect.c: fix compilation warning because of unused 'mm' variable
  mm/page-writeback: introduce tracepoint for wait_on_page_writeback()
  mm/vmscan: simplify trace_reclaim_flags and trace_shrink_flags
  mm/Kconfig: update "Memory Model" help text
  mm/vmscan.c: don't disable irq again when count pgrefill for memcg
  mm: memblock: make keeping memblock memory opt-in rather than opt-out
  hugetlbfs: always use address space in inode for resv_map pointer
  mm/z3fold.c: support page migration
  mm/z3fold.c: add structure for buddy handles
  mm/z3fold.c: improve compression by extending search
  mm/z3fold.c: introduce helper functions
  mm/page_alloc.c: remove unnecessary parameter in rmqueue_pcplist
  mm/hmm: add ARCH_HAS_HMM_MIRROR ARCH_HAS_HMM_DEVICE Kconfig
  mm/vmscan.c: simplify shrink_inactive_list()
  fs/sync.c: sync_file_range(2) may use WB_SYNC_ALL writeback
  xen/privcmd-buf.c: convert to use vm_map_pages_zero()
  xen/gntdev.c: convert to use vm_map_pages()
  ...

1 files changed, 75 insertions, 128 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index fd9de504e516..d96c54703948 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -346,7 +346,7 @@ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone
 	int zid;
 
 	if (!mem_cgroup_disabled())
-		lru_size = mem_cgroup_get_lru_size(lruvec, lru);
+		lru_size = lruvec_page_state(lruvec, NR_LRU_BASE + lru);
 	else
 		lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru);
 
@@ -1107,6 +1107,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	unsigned nr_reclaimed = 0;
+	unsigned pgactivate = 0;
 
 	memset(stat, 0, sizeof(*stat));
 	cond_resched();
@@ -1466,8 +1467,10 @@ activate_locked:
 			try_to_free_swap(page);
 		VM_BUG_ON_PAGE(PageActive(page), page);
 		if (!PageMlocked(page)) {
+			int type = page_is_file_cache(page);
 			SetPageActive(page);
-			stat->nr_activate++;
+			pgactivate++;
+			stat->nr_activate[type] += hpage_nr_pages(page);
 			count_memcg_page_event(page, PGACTIVATE);
 		}
 keep_locked:
@@ -1482,7 +1485,7 @@ keep:
 	free_unref_page_list(&free_pages);
 
 	list_splice(&ret_pages, page_list);
-	count_vm_events(PGACTIVATE, stat->nr_activate);
+	count_vm_events(PGACTIVATE, pgactivate);
 
 	return nr_reclaimed;
 }
@@ -1804,40 +1807,54 @@ static int too_many_isolated(struct pglist_data *pgdat, int file,
 	return isolated > inactive;
 }
 
-static noinline_for_stack void
-putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
+/*
+ * This moves pages from @list to corresponding LRU list.
+ *
+ * We move them the other way if the page is referenced by one or more
+ * processes, from rmap.
+ *
+ * If the pages are mostly unmapped, the processing is fast and it is
+ * appropriate to hold zone_lru_lock across the whole operation.  But if
+ * the pages are mapped, the processing is slow (page_referenced()) so we
+ * should drop zone_lru_lock around each page.  It's impossible to balance
+ * this, so instead we remove the pages from the LRU while processing them.
+ * It is safe to rely on PG_active against the non-LRU pages in here because
+ * nobody will play with that bit on a non-LRU page.
+ *
+ * The downside is that we have to touch page->_refcount against each page.
+ * But we had to alter page->flags anyway.
+ *
+ * Returns the number of pages moved to the given lruvec.
+ */
+
+static unsigned noinline_for_stack move_pages_to_lru(struct lruvec *lruvec,
+						     struct list_head *list)
 {
-	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+	int nr_pages, nr_moved = 0;
 	LIST_HEAD(pages_to_free);
+	struct page *page;
+	enum lru_list lru;
 
-	/*
-	 * Put back any unfreeable pages.
-	 */
-	while (!list_empty(page_list)) {
-		struct page *page = lru_to_page(page_list);
-		int lru;
-
+	while (!list_empty(list)) {
+		page = lru_to_page(list);
 		VM_BUG_ON_PAGE(PageLRU(page), page);
-		list_del(&page->lru);
 		if (unlikely(!page_evictable(page))) {
+			list_del(&page->lru);
 			spin_unlock_irq(&pgdat->lru_lock);
 			putback_lru_page(page);
 			spin_lock_irq(&pgdat->lru_lock);
 			continue;
 		}
-
 		lruvec = mem_cgroup_page_lruvec(page, pgdat);
 
 		SetPageLRU(page);
 		lru = page_lru(page);
-		add_page_to_lru_list(page, lruvec, lru);
 
-		if (is_active_lru(lru)) {
-			int file = is_file_lru(lru);
-			int numpages = hpage_nr_pages(page);
-			reclaim_stat->recent_rotated[file] += numpages;
-		}
+		nr_pages = hpage_nr_pages(page);
+		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
+		list_move(&page->lru, &lruvec->lists[lru]);
+
 		if (put_page_testzero(page)) {
 			__ClearPageLRU(page);
 			__ClearPageActive(page);
@@ -1850,13 +1867,17 @@ putback_inactive_pages(struct lruvec *lruvec, struct list_head *page_list)
 				spin_lock_irq(&pgdat->lru_lock);
 			} else
 				list_add(&page->lru, &pages_to_free);
+		} else {
+			nr_moved += nr_pages;
 		}
 	}
 
 	/*
 	 * To save our caller's stack, now use input list for pages to free.
 	 */
-	list_splice(&pages_to_free, page_list);
+	list_splice(&pages_to_free, list);
+
+	return nr_moved;
 }
 
 /*
@@ -1886,6 +1907,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	unsigned long nr_taken;
 	struct reclaim_stat stat;
 	int file = is_file_lru(lru);
+	enum vm_event_item item;
 	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
 	struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat;
 	bool stalled = false;
@@ -1913,17 +1935,10 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, nr_taken);
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
-	if (current_is_kswapd()) {
-		if (global_reclaim(sc))
-			__count_vm_events(PGSCAN_KSWAPD, nr_scanned);
-		count_memcg_events(lruvec_memcg(lruvec), PGSCAN_KSWAPD,
-				   nr_scanned);
-	} else {
-		if (global_reclaim(sc))
-			__count_vm_events(PGSCAN_DIRECT, nr_scanned);
-		count_memcg_events(lruvec_memcg(lruvec), PGSCAN_DIRECT,
-				   nr_scanned);
-	}
+	item = current_is_kswapd() ? PGSCAN_KSWAPD : PGSCAN_DIRECT;
+	if (global_reclaim(sc))
+		__count_vm_events(item, nr_scanned);
+	__count_memcg_events(lruvec_memcg(lruvec), item, nr_scanned);
 	spin_unlock_irq(&pgdat->lru_lock);
 
 	if (nr_taken == 0)
@@ -1934,19 +1949,14 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 
 	spin_lock_irq(&pgdat->lru_lock);
 
-	if (current_is_kswapd()) {
-		if (global_reclaim(sc))
-			__count_vm_events(PGSTEAL_KSWAPD, nr_reclaimed);
-		count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_KSWAPD,
-				   nr_reclaimed);
-	} else {
-		if (global_reclaim(sc))
-			__count_vm_events(PGSTEAL_DIRECT, nr_reclaimed);
-		count_memcg_events(lruvec_memcg(lruvec), PGSTEAL_DIRECT,
-				   nr_reclaimed);
-	}
+	item = current_is_kswapd() ? PGSTEAL_KSWAPD : PGSTEAL_DIRECT;
+	if (global_reclaim(sc))
+		__count_vm_events(item, nr_reclaimed);
+	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
+	reclaim_stat->recent_rotated[0] = stat.nr_activate[0];
+	reclaim_stat->recent_rotated[1] = stat.nr_activate[1];
 
-	putback_inactive_pages(lruvec, &page_list);
+	move_pages_to_lru(lruvec, &page_list);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 
@@ -1983,73 +1993,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 	return nr_reclaimed;
 }
 
-/*
- * This moves pages from the active list to the inactive list.
- *
- * We move them the other way if the page is referenced by one or more
- * processes, from rmap.
- *
- * If the pages are mostly unmapped, the processing is fast and it is
- * appropriate to hold pgdat->lru_lock across the whole operation.  But if
- * the pages are mapped, the processing is slow (page_referenced()) so we
- * should drop pgdat->lru_lock around each page.  It's impossible to balance
- * this, so instead we remove the pages from the LRU while processing them.
- * It is safe to rely on PG_active against the non-LRU pages in here because
- * nobody will play with that bit on a non-LRU page.
- *
- * The downside is that we have to touch page->_refcount against each page.
- * But we had to alter page->flags anyway.
- *
- * Returns the number of pages moved to the given lru.
- */
-
-static unsigned move_active_pages_to_lru(struct lruvec *lruvec,
-				     struct list_head *list,
-				     struct list_head *pages_to_free,
-				     enum lru_list lru)
-{
-	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
-	struct page *page;
-	int nr_pages;
-	int nr_moved = 0;
-
-	while (!list_empty(list)) {
-		page = lru_to_page(list);
-		lruvec = mem_cgroup_page_lruvec(page, pgdat);
-
-		VM_BUG_ON_PAGE(PageLRU(page), page);
-		SetPageLRU(page);
-
-		nr_pages = hpage_nr_pages(page);
-		update_lru_size(lruvec, lru, page_zonenum(page), nr_pages);
-		list_move(&page->lru, &lruvec->lists[lru]);
-
-		if (put_page_testzero(page)) {
-			__ClearPageLRU(page);
-			__ClearPageActive(page);
-			del_page_from_lru_list(page, lruvec, lru);
-
-			if (unlikely(PageCompound(page))) {
-				spin_unlock_irq(&pgdat->lru_lock);
-				mem_cgroup_uncharge(page);
-				(*get_compound_page_dtor(page))(page);
-				spin_lock_irq(&pgdat->lru_lock);
-			} else
-				list_add(&page->lru, pages_to_free);
-		} else {
-			nr_moved += nr_pages;
-		}
-	}
-
-	if (!is_active_lru(lru)) {
-		__count_vm_events(PGDEACTIVATE, nr_moved);
-		count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE,
-				   nr_moved);
-	}
-
-	return nr_moved;
-}
-
 static void shrink_active_list(unsigned long nr_to_scan,
 			       struct lruvec *lruvec,
 			       struct scan_control *sc,
@@ -2079,7 +2022,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	reclaim_stat->recent_scanned[file] += nr_taken;
 
 	__count_vm_events(PGREFILL, nr_scanned);
-	count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
+	__count_memcg_events(lruvec_memcg(lruvec), PGREFILL, nr_scanned);
 
 	spin_unlock_irq(&pgdat->lru_lock);
 
@@ -2136,13 +2079,19 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	 */
 	reclaim_stat->recent_rotated[file] += nr_rotated;
 
-	nr_activate = move_active_pages_to_lru(lruvec, &l_active, &l_hold, lru);
-	nr_deactivate = move_active_pages_to_lru(lruvec, &l_inactive, &l_hold, lru - LRU_ACTIVE);
+	nr_activate = move_pages_to_lru(lruvec, &l_active);
+	nr_deactivate = move_pages_to_lru(lruvec, &l_inactive);
+	/* Keep all free pages in l_active list */
+	list_splice(&l_inactive, &l_active);
+
+	__count_vm_events(PGDEACTIVATE, nr_deactivate);
+	__count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
+
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
 	spin_unlock_irq(&pgdat->lru_lock);
 
-	mem_cgroup_uncharge_list(&l_hold);
-	free_unref_page_list(&l_hold);
+	mem_cgroup_uncharge_list(&l_active);
+	free_unref_page_list(&l_active);
 	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
 			nr_deactivate, nr_rotated, sc->priority, file);
 }
@@ -3212,10 +3161,7 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	if (throttle_direct_reclaim(sc.gfp_mask, zonelist, nodemask))
 		return 1;
 
-	trace_mm_vmscan_direct_reclaim_begin(order,
-				sc.may_writepage,
-				sc.gfp_mask,
-				sc.reclaim_idx);
+	trace_mm_vmscan_direct_reclaim_begin(order, sc.gfp_mask);
 
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
 
@@ -3246,9 +3192,7 @@ unsigned long mem_cgroup_shrink_node(struct mem_cgroup *memcg,
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 
 	trace_mm_vmscan_memcg_softlimit_reclaim_begin(sc.order,
-						      sc.may_writepage,
-						      sc.gfp_mask,
-						      sc.reclaim_idx);
+						      sc.gfp_mask);
 
 	/*
 	 * NOTE: Although we can get the priority field, using it
@@ -3297,10 +3241,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 
 	zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];
 
-	trace_mm_vmscan_memcg_reclaim_begin(0,
-					    sc.may_writepage,
-					    sc.gfp_mask,
-					    sc.reclaim_idx);
+	trace_mm_vmscan_memcg_reclaim_begin(0, sc.gfp_mask);
 
 	psi_memstall_enter(&pflags);
 	noreclaim_flag = memalloc_noreclaim_save();
@@ -4149,6 +4090,9 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 		.reclaim_idx = gfp_zone(gfp_mask),
 	};
 
+	trace_mm_vmscan_node_reclaim_begin(pgdat->node_id, order,
+					   sc.gfp_mask);
+
 	cond_resched();
 	fs_reclaim_acquire(sc.gfp_mask);
 	/*
@@ -4175,6 +4119,9 @@ static int __node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned in
 	current->flags &= ~PF_SWAPWRITE;
 	memalloc_noreclaim_restore(noreclaim_flag);
 	fs_reclaim_release(sc.gfp_mask);
+
+	trace_mm_vmscan_node_reclaim_end(sc.nr_reclaimed);
+
 	return sc.nr_reclaimed >= nr_pages;
 }