Merge tag 'v5.3.15' into dev-5.3dev-5.3

This is the 5.3.15 stable release

Signed-off-by: Joel Stanley <joel@jms.id.au>

7 files changed, 106 insertions, 126 deletions

diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index 68c2f2f3c05b..7a93e1e439dd 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -196,7 +196,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 again:
 	rcu_read_lock();
 	h_cg = hugetlb_cgroup_from_task(current);
-	if (!css_tryget_online(&h_cg->css)) {
+	if (!css_tryget(&h_cg->css)) {
 		rcu_read_unlock();
 		goto again;
 	}
diff --git a/mm/ksm.c b/mm/ksm.c
index 3dc4346411e4..4d5998ca31ae 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -885,13 +885,13 @@ static int remove_stable_node(struct stable_node *stable_node)
 		return 0;
 	}
 
-	if (WARN_ON_ONCE(page_mapped(page))) {
-		/*
-		 * This should not happen: but if it does, just refuse to let
-		 * merge_across_nodes be switched - there is no need to panic.
-		 */
-		err = -EBUSY;
-	} else {
+	/*
+	 * Page could be still mapped if this races with __mmput() running in
+	 * between ksm_exit() and exit_mmap(). Just refuse to let
+	 * merge_across_nodes/max_page_sharing be switched.
+	 */
+	err = -EBUSY;
+	if (!page_mapped(page)) {
 		/*
 		 * The stable node did not yet appear stale to get_ksm_page(),
 		 * since that allows for an unmapped ksm page to be recognized
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 89fd0829ebd0..515b050b7533 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -962,7 +962,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 			if (unlikely(!memcg))
 				memcg = root_mem_cgroup;
 		}
-	} while (!css_tryget_online(&memcg->css));
+	} while (!css_tryget(&memcg->css));
 	rcu_read_unlock();
 	return memcg;
 }
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c73f09913165..8431897acb54 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -331,7 +331,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long end_pfn)
 {
 	for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(start_pfn)))
+		if (unlikely(!pfn_to_online_page(start_pfn)))
 			continue;
 
 		if (unlikely(pfn_to_nid(start_pfn) != nid))
@@ -356,7 +356,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 	/* pfn is the end pfn of a memory section. */
 	pfn = end_pfn - 1;
 	for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
+		if (unlikely(!pfn_to_online_page(pfn)))
 			continue;
 
 		if (unlikely(pfn_to_nid(pfn) != nid))
@@ -415,7 +415,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 	 */
 	pfn = zone_start_pfn;
 	for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
+		if (unlikely(!pfn_to_online_page(pfn)))
 			continue;
 
 		if (page_zone(pfn_to_page(pfn)) != zone)
@@ -436,67 +436,33 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
-static void shrink_pgdat_span(struct pglist_data *pgdat,
-			      unsigned long start_pfn, unsigned long end_pfn)
+static void update_pgdat_span(struct pglist_data *pgdat)
 {
-	unsigned long pgdat_start_pfn = pgdat->node_start_pfn;
-	unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */
-	unsigned long pgdat_end_pfn = p;
-	unsigned long pfn;
-	int nid = pgdat->node_id;
-
-	if (pgdat_start_pfn == start_pfn) {
-		/*
-		 * If the section is smallest section in the pgdat, it need
-		 * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages.
-		 * In this case, we find second smallest valid mem_section
-		 * for shrinking zone.
-		 */
-		pfn = find_smallest_section_pfn(nid, NULL, end_pfn,
-						pgdat_end_pfn);
-		if (pfn) {
-			pgdat->node_start_pfn = pfn;
-			pgdat->node_spanned_pages = pgdat_end_pfn - pfn;
-		}
-	} else if (pgdat_end_pfn == end_pfn) {
-		/*
-		 * If the section is biggest section in the pgdat, it need
-		 * shrink pgdat->node_spanned_pages.
-		 * In this case, we find second biggest valid mem_section for
-		 * shrinking zone.
-		 */
-		pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn,
-					       start_pfn);
-		if (pfn)
-			pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1;
-	}
+	unsigned long node_start_pfn = 0, node_end_pfn = 0;
+	struct zone *zone;
 
-	/*
-	 * If the section is not biggest or smallest mem_section in the pgdat,
-	 * it only creates a hole in the pgdat. So in this case, we need not
-	 * change the pgdat.
-	 * But perhaps, the pgdat has only hole data. Thus it check the pgdat
-	 * has only hole or not.
-	 */
-	pfn = pgdat_start_pfn;
-	for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) {
-		if (unlikely(!pfn_valid(pfn)))
-			continue;
+	for (zone = pgdat->node_zones;
+	     zone < pgdat->node_zones + MAX_NR_ZONES; zone++) {
+		unsigned long zone_end_pfn = zone->zone_start_pfn +
+					     zone->spanned_pages;
 
-		if (pfn_to_nid(pfn) != nid)
+		/* No need to lock the zones, they can't change. */
+		if (!zone->spanned_pages)
 			continue;
-
-		/* Skip range to be removed */
-		if (pfn >= start_pfn && pfn < end_pfn)
+		if (!node_end_pfn) {
+			node_start_pfn = zone->zone_start_pfn;
+			node_end_pfn = zone_end_pfn;
 			continue;
+		}
 
-		/* If we find valid section, we have nothing to do */
-		return;
+		if (zone_end_pfn > node_end_pfn)
+			node_end_pfn = zone_end_pfn;
+		if (zone->zone_start_pfn < node_start_pfn)
+			node_start_pfn = zone->zone_start_pfn;
 	}
 
-	/* The pgdat has no valid section */
-	pgdat->node_start_pfn = 0;
-	pgdat->node_spanned_pages = 0;
+	pgdat->node_start_pfn = node_start_pfn;
+	pgdat->node_spanned_pages = node_end_pfn - node_start_pfn;
 }
 
 static void __remove_zone(struct zone *zone, unsigned long start_pfn,
@@ -505,9 +471,19 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn,
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	unsigned long flags;
 
+#ifdef CONFIG_ZONE_DEVICE
+	/*
+	 * Zone shrinking code cannot properly deal with ZONE_DEVICE. So
+	 * we will not try to shrink the zones - which is okay as
+	 * set_zone_contiguous() cannot deal with ZONE_DEVICE either way.
+	 */
+	if (zone_idx(zone) == ZONE_DEVICE)
+		return;
+#endif
+
 	pgdat_resize_lock(zone->zone_pgdat, &flags);
 	shrink_zone_span(zone, start_pfn, start_pfn + nr_pages);
-	shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages);
+	update_pgdat_span(pgdat);
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 }
 
@@ -1687,6 +1663,18 @@ static int check_cpu_on_node(pg_data_t *pgdat)
 	return 0;
 }
 
+static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg)
+{
+	int nid = *(int *)arg;
+
+	/*
+	 * If a memory block belongs to multiple nodes, the stored nid is not
+	 * reliable. However, such blocks are always online (e.g., cannot get
+	 * offlined) and, therefore, are still spanned by the node.
+	 */
+	return mem->nid == nid ? -EEXIST : 0;
+}
+
 /**
  * try_offline_node
  * @nid: the node ID
@@ -1699,25 +1687,24 @@ static int check_cpu_on_node(pg_data_t *pgdat)
 void try_offline_node(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
-	unsigned long start_pfn = pgdat->node_start_pfn;
-	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
-	unsigned long pfn;
-
-	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		unsigned long section_nr = pfn_to_section_nr(pfn);
-
-		if (!present_section_nr(section_nr))
-			continue;
+	int rc;
 
-		if (pfn_to_nid(pfn) != nid)
-			continue;
+	/*
+	 * If the node still spans pages (especially ZONE_DEVICE), don't
+	 * offline it. A node spans memory after move_pfn_range_to_zone(),
+	 * e.g., after the memory block was onlined.
+	 */
+	if (pgdat->node_spanned_pages)
+		return;
 
-		/*
-		 * some memory sections of this node are not removed, and we
-		 * can't offline node now.
-		 */
+	/*
+	 * Especially offline memory blocks might not be spanned by the
+	 * node. They will get spanned by the node once they get onlined.
+	 * However, they link to the node in sysfs and can get onlined later.
+	 */
+	rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb);
+	if (rc)
 		return;
-	}
 
 	if (check_cpu_on_node(pgdat))
 		return;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 65e0874fce17..d9fd28f7ca44 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -666,7 +666,9 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
  * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * 0 - queue pages successfully or no misplaced page.
- * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified.
+ * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or
+ *         memory range specified by nodemask and maxnode points outside
+ *         your accessible address space (-EFAULT)
  */
 static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
@@ -1287,7 +1289,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
 	if (ret < 0) {
-		err = -EIO;
+		err = ret;
 		goto up_out;
 	}
 
@@ -1306,10 +1308,12 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
 			err = -EIO;
-	} else
-		putback_movable_pages(&pagelist);
-
+	} else {
 up_out:
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
+	}
+
 	up_write(&mm->mmap_sem);
 mpol_out:
 	mpol_put(new);
diff --git a/mm/page_io.c b/mm/page_io.c
index 24ee600f9131..60a66a58b9bf 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -73,6 +73,7 @@ static void swap_slot_free_notify(struct page *page)
 {
 	struct swap_info_struct *sis;
 	struct gendisk *disk;
+	swp_entry_t entry;
 
 	/*
 	 * There is no guarantee that the page is in swap cache - the software
@@ -104,11 +105,10 @@ static void swap_slot_free_notify(struct page *page)
 	 * we again wish to reclaim it.
 	 */
 	disk = sis->bdev->bd_disk;
-	if (disk->fops->swap_slot_free_notify) {
-		swp_entry_t entry;
+	entry.val = page_private(page);
+	if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
 		unsigned long offset;
 
-		entry.val = page_private(page);
 		offset = swp_offset(entry);
 
 		SetPageDirty(page);
diff --git a/mm/slub.c b/mm/slub.c
index dac41cf0b94a..f24ea152cdbb 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1432,12 +1432,15 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 	void *old_tail = *tail ? *tail : *head;
 	int rsize;
 
-	if (slab_want_init_on_free(s)) {
-		void *p = NULL;
+	/* Head and tail of the reconstructed freelist */
+	*head = NULL;
+	*tail = NULL;
 
-		do {
-			object = next;
-			next = get_freepointer(s, object);
+	do {
+		object = next;
+		next = get_freepointer(s, object);
+
+		if (slab_want_init_on_free(s)) {
 			/*
 			 * Clear the object and the metadata, but don't touch
 			 * the redzone.
@@ -1447,29 +1450,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 							   : 0;
 			memset((char *)object + s->inuse, 0,
 			       s->size - s->inuse - rsize);
-			set_freepointer(s, object, p);
-			p = object;
-		} while (object != old_tail);
-	}
-
-/*
- * Compiler cannot detect this function can be removed if slab_free_hook()
- * evaluates to nothing.  Thus, catch all relevant config debug options here.
- */
-#if defined(CONFIG_LOCKDEP)	||		\
-	defined(CONFIG_DEBUG_KMEMLEAK) ||	\
-	defined(CONFIG_DEBUG_OBJECTS_FREE) ||	\
-	defined(CONFIG_KASAN)
-
-	next = *head;
-
-	/* Head and tail of the reconstructed freelist */
-	*head = NULL;
-	*tail = NULL;
 
-	do {
-		object = next;
-		next = get_freepointer(s, object);
+		}
 		/* If object's reuse doesn't have to be delayed */
 		if (!slab_free_hook(s, object)) {
 			/* Move object to the new freelist */
@@ -1484,9 +1466,6 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 		*tail = NULL;
 
 	return *head != NULL;
-#else
-	return true;
-#endif
 }
 
 static void *setup_object(struct kmem_cache *s, struct page *page,
@@ -2670,6 +2649,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 }
 
 /*
+ * If the object has been wiped upon free, make sure it's fully initialized by
+ * zeroing out freelist pointer.
+ */
+static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s,
+						   void *obj)
+{
+	if (unlikely(slab_want_init_on_free(s)) && obj)
+		memset((void *)((char *)obj + s->offset), 0, sizeof(void *));
+}
+
+/*
  * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
  * have the fastpath folded into their functions. So no function call
  * overhead for requests that can be satisfied on the fastpath.
@@ -2757,12 +2747,8 @@ redo:
 		prefetch_freepointer(s, next_object);
 		stat(s, ALLOC_FASTPATH);
 	}
-	/*
-	 * If the object has been wiped upon free, make sure it's fully
-	 * initialized by zeroing out freelist pointer.
-	 */
-	if (unlikely(slab_want_init_on_free(s)) && object)
-		memset(object + s->offset, 0, sizeof(void *));
+
+	maybe_wipe_obj_freeptr(s, object);
 
 	if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object)
 		memset(object, 0, s->object_size);
@@ -3176,10 +3162,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 				goto error;
 
 			c = this_cpu_ptr(s->cpu_slab);
+			maybe_wipe_obj_freeptr(s, p[i]);
+
 			continue; /* goto for-loop */
 		}
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
+		maybe_wipe_obj_freeptr(s, p[i]);
 	}
 	c->tid = next_tid(c->tid);
 	local_irq_enable();