1 files changed, 237 insertions, 279 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1bad301820c7..a9add06fe768 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -66,6 +66,8 @@
 #include <linux/kthread.h>
 #include <linux/memcontrol.h>
 #include <linux/ftrace.h>
+#include <linux/lockdep.h>
+#include <linux/nmi.h>
 
 #include <asm/sections.h>
 #include <asm/tlbflush.h>
@@ -2535,9 +2537,14 @@ void drain_all_pages(struct zone *zone)
 
 #ifdef CONFIG_HIBERNATION
 
+/*
+ * Touch the watchdog for every WD_PAGE_COUNT pages.
+ */
+#define WD_PAGE_COUNT	(128*1024)
+
 void mark_free_pages(struct zone *zone)
 {
-	unsigned long pfn, max_zone_pfn;
+	unsigned long pfn, max_zone_pfn, page_count = WD_PAGE_COUNT;
 	unsigned long flags;
 	unsigned int order, t;
 	struct page *page;
@@ -2552,6 +2559,11 @@ void mark_free_pages(struct zone *zone)
 		if (pfn_valid(pfn)) {
 			page = pfn_to_page(pfn);
 
+			if (!--page_count) {
+				touch_nmi_watchdog();
+				page_count = WD_PAGE_COUNT;
+			}
+
 			if (page_zone(page) != zone)
 				continue;
 
@@ -2565,8 +2577,13 @@ void mark_free_pages(struct zone *zone)
 			unsigned long i;
 
 			pfn = page_to_pfn(page);
-			for (i = 0; i < (1UL << order); i++)
+			for (i = 0; i < (1UL << order); i++) {
+				if (!--page_count) {
+					touch_nmi_watchdog();
+					page_count = WD_PAGE_COUNT;
+				}
 				swsusp_set_page_free(pfn_to_page(pfn + i));
+			}
 		}
 	}
 	spin_unlock_irqrestore(&zone->lock, flags);
@@ -2934,7 +2951,7 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 {
 	long min = mark;
 	int o;
-	const bool alloc_harder = (alloc_flags & ALLOC_HARDER);
+	const bool alloc_harder = (alloc_flags & (ALLOC_HARDER|ALLOC_OOM));
 
 	/* free_pages may go negative - that's OK */
 	free_pages -= (1 << order) - 1;
@@ -2947,10 +2964,21 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 	 * the high-atomic reserves. This will over-estimate the size of the
 	 * atomic reserve but it avoids a search.
 	 */
-	if (likely(!alloc_harder))
+	if (likely(!alloc_harder)) {
 		free_pages -= z->nr_reserved_highatomic;
-	else
-		min -= min / 4;
+	} else {
+		/*
+		 * OOM victims can try even harder than normal ALLOC_HARDER
+		 * users on the grounds that it's definitely going to be in
+		 * the exit path shortly and free memory. Any allocation it
+		 * makes during the free path will be small and short-lived.
+		 */
+		if (alloc_flags & ALLOC_OOM)
+			min -= min / 2;
+		else
+			min -= min / 4;
+	}
+
 
 #ifdef CONFIG_CMA
 	/* If allocation can't use CMA areas don't use free CMA pages */
@@ -3188,7 +3216,7 @@ static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 	 * of allowed nodes.
 	 */
 	if (!(gfp_mask & __GFP_NOMEMALLOC))
-		if (test_thread_flag(TIF_MEMDIE) ||
+		if (tsk_is_oom_victim(current) ||
 		    (current->flags & (PF_MEMALLOC | PF_EXITING)))
 			filter &= ~SHOW_MEM_FILTER_NODES;
 	if (in_interrupt() || !(gfp_mask & __GFP_DIRECT_RECLAIM))
@@ -3275,10 +3303,13 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order,
 	/*
 	 * Go through the zonelist yet one more time, keep very high watermark
 	 * here, this is only to catch a parallel oom killing, we must fail if
-	 * we're still under heavy pressure.
+	 * we're still under heavy pressure. But make sure that this reclaim
+	 * attempt shall not depend on __GFP_DIRECT_RECLAIM && !__GFP_NORETRY
+	 * allocation which will never fail due to oom_lock already held.
 	 */
-	page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order,
-					ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
+	page = get_page_from_freelist((gfp_mask | __GFP_HARDWALL) &
+				      ~__GFP_DIRECT_RECLAIM, order,
+				      ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac);
 	if (page)
 		goto out;
 
@@ -3494,6 +3525,47 @@ should_compact_retry(struct alloc_context *ac, unsigned int order, int alloc_fla
 }
 #endif /* CONFIG_COMPACTION */
 
+#ifdef CONFIG_LOCKDEP
+struct lockdep_map __fs_reclaim_map =
+	STATIC_LOCKDEP_MAP_INIT("fs_reclaim", &__fs_reclaim_map);
+
+static bool __need_fs_reclaim(gfp_t gfp_mask)
+{
+	gfp_mask = current_gfp_context(gfp_mask);
+
+	/* no reclaim without waiting on it */
+	if (!(gfp_mask & __GFP_DIRECT_RECLAIM))
+		return false;
+
+	/* this guy won't enter reclaim */
+	if ((current->flags & PF_MEMALLOC) && !(gfp_mask & __GFP_NOMEMALLOC))
+		return false;
+
+	/* We're only interested __GFP_FS allocations for now */
+	if (!(gfp_mask & __GFP_FS))
+		return false;
+
+	if (gfp_mask & __GFP_NOLOCKDEP)
+		return false;
+
+	return true;
+}
+
+void fs_reclaim_acquire(gfp_t gfp_mask)
+{
+	if (__need_fs_reclaim(gfp_mask))
+		lock_map_acquire(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_acquire);
+
+void fs_reclaim_release(gfp_t gfp_mask)
+{
+	if (__need_fs_reclaim(gfp_mask))
+		lock_map_release(&__fs_reclaim_map);
+}
+EXPORT_SYMBOL_GPL(fs_reclaim_release);
+#endif
+
 /* Perform direct synchronous page reclaim */
 static int
 __perform_reclaim(gfp_t gfp_mask, unsigned int order,
@@ -3508,7 +3580,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
 	noreclaim_flag = memalloc_noreclaim_save();
-	lockdep_set_current_reclaim_state(gfp_mask);
+	fs_reclaim_acquire(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
 	current->reclaim_state = &reclaim_state;
 
@@ -3516,7 +3588,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order,
 								ac->nodemask);
 
 	current->reclaim_state = NULL;
-	lockdep_clear_current_reclaim_state();
+	fs_reclaim_release(gfp_mask);
 	memalloc_noreclaim_restore(noreclaim_flag);
 
 	cond_resched();
@@ -3607,21 +3679,46 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	return alloc_flags;
 }
 
-bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+static bool oom_reserves_allowed(struct task_struct *tsk)
 {
-	if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+	if (!tsk_is_oom_victim(tsk))
 		return false;
 
+	/*
+	 * !MMU doesn't have oom reaper so give access to memory reserves
+	 * only to the thread with TIF_MEMDIE set
+	 */
+	if (!IS_ENABLED(CONFIG_MMU) && !test_thread_flag(TIF_MEMDIE))
+		return false;
+
+	return true;
+}
+
+/*
+ * Distinguish requests which really need access to full memory
+ * reserves from oom victims which can live with a portion of it
+ */
+static inline int __gfp_pfmemalloc_flags(gfp_t gfp_mask)
+{
+	if (unlikely(gfp_mask & __GFP_NOMEMALLOC))
+		return 0;
 	if (gfp_mask & __GFP_MEMALLOC)
-		return true;
+		return ALLOC_NO_WATERMARKS;
 	if (in_serving_softirq() && (current->flags & PF_MEMALLOC))
-		return true;
-	if (!in_interrupt() &&
-			((current->flags & PF_MEMALLOC) ||
-			 unlikely(test_thread_flag(TIF_MEMDIE))))
-		return true;
+		return ALLOC_NO_WATERMARKS;
+	if (!in_interrupt()) {
+		if (current->flags & PF_MEMALLOC)
+			return ALLOC_NO_WATERMARKS;
+		else if (oom_reserves_allowed(current))
+			return ALLOC_OOM;
+	}
 
-	return false;
+	return 0;
+}
+
+bool gfp_pfmemalloc_allowed(gfp_t gfp_mask)
+{
+	return !!__gfp_pfmemalloc_flags(gfp_mask);
 }
 
 /*
@@ -3774,6 +3871,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long alloc_start = jiffies;
 	unsigned int stall_timeout = 10 * HZ;
 	unsigned int cpuset_mems_cookie;
+	int reserve_flags;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -3879,15 +3977,16 @@ retry:
 	if (gfp_mask & __GFP_KSWAPD_RECLAIM)
 		wake_all_kswapds(order, ac);
 
-	if (gfp_pfmemalloc_allowed(gfp_mask))
-		alloc_flags = ALLOC_NO_WATERMARKS;
+	reserve_flags = __gfp_pfmemalloc_flags(gfp_mask);
+	if (reserve_flags)
+		alloc_flags = reserve_flags;
 
 	/*
 	 * Reset the zonelist iterators if memory policies can be ignored.
 	 * These allocations are high priority and system rather than user
 	 * orientated.
 	 */
-	if (!(alloc_flags & ALLOC_CPUSET) || (alloc_flags & ALLOC_NO_WATERMARKS)) {
+	if (!(alloc_flags & ALLOC_CPUSET) || reserve_flags) {
 		ac->zonelist = node_zonelist(numa_node_id(), gfp_mask);
 		ac->preferred_zoneref = first_zones_zonelist(ac->zonelist,
 					ac->high_zoneidx, ac->nodemask);
@@ -3964,8 +4063,8 @@ retry:
 		goto got_pg;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
-	if (test_thread_flag(TIF_MEMDIE) &&
-	    (alloc_flags == ALLOC_NO_WATERMARKS ||
+	if (tsk_is_oom_victim(current) &&
+	    (alloc_flags == ALLOC_OOM ||
 	     (gfp_mask & __GFP_NOMEMALLOC)))
 		goto nopage;
 
@@ -4045,7 +4144,8 @@ static inline bool prepare_alloc_pages(gfp_t gfp_mask, unsigned int order,
 			*alloc_flags |= ALLOC_CPUSET;
 	}
 
-	lockdep_trace_alloc(gfp_mask);
+	fs_reclaim_acquire(gfp_mask);
+	fs_reclaim_release(gfp_mask);
 
 	might_sleep_if(gfp_mask & __GFP_DIRECT_RECLAIM);
 
@@ -4447,7 +4547,7 @@ long si_mem_available(void)
 	 * Estimate the amount of memory available for userspace allocations,
 	 * without causing swapping.
 	 */
-	available = global_page_state(NR_FREE_PAGES) - totalreserve_pages;
+	available = global_zone_page_state(NR_FREE_PAGES) - totalreserve_pages;
 
 	/*
 	 * Not all the page cache can be freed, otherwise the system will
@@ -4476,7 +4576,7 @@ void si_meminfo(struct sysinfo *val)
 {
 	val->totalram = totalram_pages;
 	val->sharedram = global_node_page_state(NR_SHMEM);
-	val->freeram = global_page_state(NR_FREE_PAGES);
+	val->freeram = global_zone_page_state(NR_FREE_PAGES);
 	val->bufferram = nr_blockdev_pages();
 	val->totalhigh = totalhigh_pages;
 	val->freehigh = nr_free_highpages();
@@ -4611,11 +4711,11 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 		global_node_page_state(NR_SLAB_UNRECLAIMABLE),
 		global_node_page_state(NR_FILE_MAPPED),
 		global_node_page_state(NR_SHMEM),
-		global_page_state(NR_PAGETABLE),
-		global_page_state(NR_BOUNCE),
-		global_page_state(NR_FREE_PAGES),
+		global_zone_page_state(NR_PAGETABLE),
+		global_zone_page_state(NR_BOUNCE),
+		global_zone_page_state(NR_FREE_PAGES),
 		free_pcp,
-		global_page_state(NR_FREE_CMA_PAGES));
+		global_zone_page_state(NR_FREE_CMA_PAGES));
 
 	for_each_online_pgdat(pgdat) {
 		if (show_mem_node_skip(filter, pgdat->node_id, nodemask))
@@ -4777,18 +4877,17 @@ static void zoneref_set_zone(struct zone *zone, struct zoneref *zoneref)
  *
  * Add all populated zones of a node to the zonelist.
  */
-static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
-				int nr_zones)
+static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs)
 {
 	struct zone *zone;
 	enum zone_type zone_type = MAX_NR_ZONES;
+	int nr_zones = 0;
 
 	do {
 		zone_type--;
 		zone = pgdat->node_zones + zone_type;
 		if (managed_zone(zone)) {
-			zoneref_set_zone(zone,
-				&zonelist->_zonerefs[nr_zones++]);
+			zoneref_set_zone(zone, &zonerefs[nr_zones++]);
 			check_highest_zone(zone_type);
 		}
 	} while (zone_type);
@@ -4796,52 +4895,18 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist,
 	return nr_zones;
 }
 
-
-/*
- *  zonelist_order:
- *  0 = automatic detection of better ordering.
- *  1 = order by ([node] distance, -zonetype)
- *  2 = order by (-zonetype, [node] distance)
- *
- *  If not NUMA, ZONELIST_ORDER_ZONE and ZONELIST_ORDER_NODE will create
- *  the same zonelist. So only NUMA can configure this param.
- */
-#define ZONELIST_ORDER_DEFAULT  0
-#define ZONELIST_ORDER_NODE     1
-#define ZONELIST_ORDER_ZONE     2
-
-/* zonelist order in the kernel.
- * set_zonelist_order() will set this to NODE or ZONE.
- */
-static int current_zonelist_order = ZONELIST_ORDER_DEFAULT;
-static char zonelist_order_name[3][8] = {"Default", "Node", "Zone"};
-
-
 #ifdef CONFIG_NUMA
-/* The value user specified ....changed by config */
-static int user_zonelist_order = ZONELIST_ORDER_DEFAULT;
-/* string for sysctl */
-#define NUMA_ZONELIST_ORDER_LEN	16
-char numa_zonelist_order[16] = "default";
-
-/*
- * interface for configure zonelist ordering.
- * command line option "numa_zonelist_order"
- *	= "[dD]efault	- default, automatic configuration.
- *	= "[nN]ode 	- order by node locality, then by zone within node
- *	= "[zZ]one      - order by zone, then by locality within zone
- */
 
 static int __parse_numa_zonelist_order(char *s)
 {
-	if (*s == 'd' || *s == 'D') {
-		user_zonelist_order = ZONELIST_ORDER_DEFAULT;
-	} else if (*s == 'n' || *s == 'N') {
-		user_zonelist_order = ZONELIST_ORDER_NODE;
-	} else if (*s == 'z' || *s == 'Z') {
-		user_zonelist_order = ZONELIST_ORDER_ZONE;
-	} else {
-		pr_warn("Ignoring invalid numa_zonelist_order value:  %s\n", s);
+	/*
+	 * We used to support different zonlists modes but they turned
+	 * out to be just not useful. Let's keep the warning in place
+	 * if somebody still use the cmd line parameter so that we do
+	 * not fail it silently
+	 */
+	if (!(*s == 'd' || *s == 'D' || *s == 'n' || *s == 'N')) {
+		pr_warn("Ignoring unsupported numa_zonelist_order value:  %s\n", s);
 		return -EINVAL;
 	}
 	return 0;
@@ -4849,19 +4914,15 @@ static int __parse_numa_zonelist_order(char *s)
 
 static __init int setup_numa_zonelist_order(char *s)
 {
-	int ret;
-
 	if (!s)
 		return 0;
 
-	ret = __parse_numa_zonelist_order(s);
-	if (ret == 0)
-		strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN);
-
-	return ret;
+	return __parse_numa_zonelist_order(s);
 }
 early_param("numa_zonelist_order", setup_numa_zonelist_order);
 
+char numa_zonelist_order[] = "Node";
+
 /*
  * sysctl handler for numa_zonelist_order
  */
@@ -4869,42 +4930,17 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
 		loff_t *ppos)
 {
-	char saved_string[NUMA_ZONELIST_ORDER_LEN];
+	char *str;
 	int ret;
-	static DEFINE_MUTEX(zl_order_mutex);
 
-	mutex_lock(&zl_order_mutex);
-	if (write) {
-		if (strlen((char *)table->data) >= NUMA_ZONELIST_ORDER_LEN) {
-			ret = -EINVAL;
-			goto out;
-		}
-		strcpy(saved_string, (char *)table->data);
-	}
-	ret = proc_dostring(table, write, buffer, length, ppos);
-	if (ret)
-		goto out;
-	if (write) {
-		int oldval = user_zonelist_order;
+	if (!write)
+		return proc_dostring(table, write, buffer, length, ppos);
+	str = memdup_user_nul(buffer, 16);
+	if (IS_ERR(str))
+		return PTR_ERR(str);
 
-		ret = __parse_numa_zonelist_order((char *)table->data);
-		if (ret) {
-			/*
-			 * bogus value.  restore saved string
-			 */
-			strncpy((char *)table->data, saved_string,
-				NUMA_ZONELIST_ORDER_LEN);
-			user_zonelist_order = oldval;
-		} else if (oldval != user_zonelist_order) {
-			mem_hotplug_begin();
-			mutex_lock(&zonelists_mutex);
-			build_all_zonelists(NULL, NULL);
-			mutex_unlock(&zonelists_mutex);
-			mem_hotplug_done();
-		}
-	}
-out:
-	mutex_unlock(&zl_order_mutex);
+	ret = __parse_numa_zonelist_order(str);
+	kfree(str);
 	return ret;
 }
 
@@ -4978,17 +5014,24 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
  * This results in maximum locality--normal zone overflows into local
  * DMA zone, if any--but risks exhausting DMA zone.
  */
-static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
+static void build_zonelists_in_node_order(pg_data_t *pgdat, int *node_order,
+		unsigned nr_nodes)
 {
-	int j;
-	struct zonelist *zonelist;
+	struct zoneref *zonerefs;
+	int i;
+
+	zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
+
+	for (i = 0; i < nr_nodes; i++) {
+		int nr_zones;
 
-	zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-	for (j = 0; zonelist->_zonerefs[j].zone != NULL; j++)
-		;
-	j = build_zonelists_node(NODE_DATA(node), zonelist, j);
-	zonelist->_zonerefs[j].zone = NULL;
-	zonelist->_zonerefs[j].zone_idx = 0;
+		pg_data_t *node = NODE_DATA(node_order[i]);
+
+		nr_zones = build_zonerefs_node(node, zonerefs);
+		zonerefs += nr_zones;
+	}
+	zonerefs->zone = NULL;
+	zonerefs->zone_idx = 0;
 }
 
 /*
@@ -4996,13 +5039,14 @@ static void build_zonelists_in_node_order(pg_data_t *pgdat, int node)
  */
 static void build_thisnode_zonelists(pg_data_t *pgdat)
 {
-	int j;
-	struct zonelist *zonelist;
+	struct zoneref *zonerefs;
+	int nr_zones;
 
-	zonelist = &pgdat->node_zonelists[ZONELIST_NOFALLBACK];
-	j = build_zonelists_node(pgdat, zonelist, 0);
-	zonelist->_zonerefs[j].zone = NULL;
-	zonelist->_zonerefs[j].zone_idx = 0;
+	zonerefs = pgdat->node_zonelists[ZONELIST_NOFALLBACK]._zonerefs;
+	nr_zones = build_zonerefs_node(pgdat, zonerefs);
+	zonerefs += nr_zones;
+	zonerefs->zone = NULL;
+	zonerefs->zone_idx = 0;
 }
 
 /*
@@ -5011,79 +5055,13 @@ static void build_thisnode_zonelists(pg_data_t *pgdat)
  * exhausted, but results in overflowing to remote node while memory
  * may still exist in local DMA zone.
  */
-static int node_order[MAX_NUMNODES];
-
-static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes)
-{
-	int pos, j, node;
-	int zone_type;		/* needs to be signed */
-	struct zone *z;
-	struct zonelist *zonelist;
-
-	zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-	pos = 0;
-	for (zone_type = MAX_NR_ZONES - 1; zone_type >= 0; zone_type--) {
-		for (j = 0; j < nr_nodes; j++) {
-			node = node_order[j];
-			z = &NODE_DATA(node)->node_zones[zone_type];
-			if (managed_zone(z)) {
-				zoneref_set_zone(z,
-					&zonelist->_zonerefs[pos++]);
-				check_highest_zone(zone_type);
-			}
-		}
-	}
-	zonelist->_zonerefs[pos].zone = NULL;
-	zonelist->_zonerefs[pos].zone_idx = 0;
-}
-
-#if defined(CONFIG_64BIT)
-/*
- * Devices that require DMA32/DMA are relatively rare and do not justify a
- * penalty to every machine in case the specialised case applies. Default
- * to Node-ordering on 64-bit NUMA machines
- */
-static int default_zonelist_order(void)
-{
-	return ZONELIST_ORDER_NODE;
-}
-#else
-/*
- * On 32-bit, the Normal zone needs to be preserved for allocations accessible
- * by the kernel. If processes running on node 0 deplete the low memory zone
- * then reclaim will occur more frequency increasing stalls and potentially
- * be easier to OOM if a large percentage of the zone is under writeback or
- * dirty. The problem is significantly worse if CONFIG_HIGHPTE is not set.
- * Hence, default to zone ordering on 32-bit.
- */
-static int default_zonelist_order(void)
-{
-	return ZONELIST_ORDER_ZONE;
-}
-#endif /* CONFIG_64BIT */
-
-static void set_zonelist_order(void)
-{
-	if (user_zonelist_order == ZONELIST_ORDER_DEFAULT)
-		current_zonelist_order = default_zonelist_order();
-	else
-		current_zonelist_order = user_zonelist_order;
-}
 
 static void build_zonelists(pg_data_t *pgdat)
 {
-	int i, node, load;
+	static int node_order[MAX_NUMNODES];
+	int node, load, nr_nodes = 0;
 	nodemask_t used_mask;
 	int local_node, prev_node;
-	struct zonelist *zonelist;
-	unsigned int order = current_zonelist_order;
-
-	/* initialize zonelists */
-	for (i = 0; i < MAX_ZONELISTS; i++) {
-		zonelist = pgdat->node_zonelists + i;
-		zonelist->_zonerefs[0].zone = NULL;
-		zonelist->_zonerefs[0].zone_idx = 0;
-	}
 
 	/* NUMA-aware ordering of nodes */
 	local_node = pgdat->node_id;
@@ -5092,8 +5070,6 @@ static void build_zonelists(pg_data_t *pgdat)
 	nodes_clear(used_mask);
 
 	memset(node_order, 0, sizeof(node_order));
-	i = 0;
-
 	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
 		/*
 		 * We don't want to pressure a particular node.
@@ -5104,19 +5080,12 @@ static void build_zonelists(pg_data_t *pgdat)
 		    node_distance(local_node, prev_node))
 			node_load[node] = load;
 
+		node_order[nr_nodes++] = node;
 		prev_node = node;
 		load--;
-		if (order == ZONELIST_ORDER_NODE)
-			build_zonelists_in_node_order(pgdat, node);
-		else
-			node_order[i++] = node;	/* remember order */
-	}
-
-	if (order == ZONELIST_ORDER_ZONE) {
-		/* calculate node order -- i.e., DMA last! */
-		build_zonelists_in_zone_order(pgdat, i);
 	}
 
+	build_zonelists_in_node_order(pgdat, node_order, nr_nodes);
 	build_thisnode_zonelists(pgdat);
 }
 
@@ -5142,21 +5111,17 @@ static void setup_min_unmapped_ratio(void);
 static void setup_min_slab_ratio(void);
 #else	/* CONFIG_NUMA */
 
-static void set_zonelist_order(void)
-{
-	current_zonelist_order = ZONELIST_ORDER_ZONE;
-}
-
 static void build_zonelists(pg_data_t *pgdat)
 {
 	int node, local_node;
-	enum zone_type j;
-	struct zonelist *zonelist;
+	struct zoneref *zonerefs;
+	int nr_zones;
 
 	local_node = pgdat->node_id;
 
-	zonelist = &pgdat->node_zonelists[ZONELIST_FALLBACK];
-	j = build_zonelists_node(pgdat, zonelist, 0);
+	zonerefs = pgdat->node_zonelists[ZONELIST_FALLBACK]._zonerefs;
+	nr_zones = build_zonerefs_node(pgdat, zonerefs);
+	zonerefs += nr_zones;
 
 	/*
 	 * Now we build the zonelist so that it contains the zones
@@ -5169,16 +5134,18 @@ static void build_zonelists(pg_data_t *pgdat)
 	for (node = local_node + 1; node < MAX_NUMNODES; node++) {
 		if (!node_online(node))
 			continue;
-		j = build_zonelists_node(NODE_DATA(node), zonelist, j);
+		nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
+		zonerefs += nr_zones;
 	}
 	for (node = 0; node < local_node; node++) {
 		if (!node_online(node))
 			continue;
-		j = build_zonelists_node(NODE_DATA(node), zonelist, j);
+		nr_zones = build_zonerefs_node(NODE_DATA(node), zonerefs);
+		zonerefs += nr_zones;
 	}
 
-	zonelist->_zonerefs[j].zone = NULL;
-	zonelist->_zonerefs[j].zone_idx = 0;
+	zonerefs->zone = NULL;
+	zonerefs->zone_idx = 0;
 }
 
 #endif	/* CONFIG_NUMA */
@@ -5201,50 +5168,32 @@ static void build_zonelists(pg_data_t *pgdat)
 static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch);
 static DEFINE_PER_CPU(struct per_cpu_pageset, boot_pageset);
 static DEFINE_PER_CPU(struct per_cpu_nodestat, boot_nodestats);
-static void setup_zone_pageset(struct zone *zone);
-
-/*
- * Global mutex to protect against size modification of zonelists
- * as well as to serialize pageset setup for the new populated zone.
- */
-DEFINE_MUTEX(zonelists_mutex);
 
-/* return values int ....just for stop_machine() */
-static int __build_all_zonelists(void *data)
+static void __build_all_zonelists(void *data)
 {
 	int nid;
-	int cpu;
+	int __maybe_unused cpu;
 	pg_data_t *self = data;
+	static DEFINE_SPINLOCK(lock);
+
+	spin_lock(&lock);
 
 #ifdef CONFIG_NUMA
 	memset(node_load, 0, sizeof(node_load));
 #endif
 
+	/*
+	 * This node is hotadded and no memory is yet present.   So just
+	 * building zonelists is fine - no need to touch other nodes.
+	 */
 	if (self && !node_online(self->node_id)) {
 		build_zonelists(self);
-	}
-
-	for_each_online_node(nid) {
-		pg_data_t *pgdat = NODE_DATA(nid);
-
-		build_zonelists(pgdat);
-	}
+	} else {
+		for_each_online_node(nid) {
+			pg_data_t *pgdat = NODE_DATA(nid);
 
-	/*
-	 * Initialize the boot_pagesets that are going to be used
-	 * for bootstrapping processors. The real pagesets for
-	 * each zone will be allocated later when the per cpu
-	 * allocator is available.
-	 *
-	 * boot_pagesets are used also for bootstrapping offline
-	 * cpus if the system is already booted because the pagesets
-	 * are needed to initialize allocators on a specific cpu too.
-	 * F.e. the percpu allocator needs the page allocator which
-	 * needs the percpu allocator in order to allocate its pagesets
-	 * (a chicken-egg dilemma).
-	 */
-	for_each_possible_cpu(cpu) {
-		setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+			build_zonelists(pgdat);
+		}
 
 #ifdef CONFIG_HAVE_MEMORYLESS_NODES
 		/*
@@ -5255,45 +5204,53 @@ static int __build_all_zonelists(void *data)
 		 * secondary cpus' numa_mem as they come on-line.  During
 		 * node/memory hotplug, we'll fixup all on-line cpus.
 		 */
-		if (cpu_online(cpu))
+		for_each_online_cpu(cpu)
 			set_cpu_numa_mem(cpu, local_memory_node(cpu_to_node(cpu)));
 #endif
 	}
 
-	return 0;
+	spin_unlock(&lock);
 }
 
 static noinline void __init
 build_all_zonelists_init(void)
 {
+	int cpu;
+
 	__build_all_zonelists(NULL);
+
+	/*
+	 * Initialize the boot_pagesets that are going to be used
+	 * for bootstrapping processors. The real pagesets for
+	 * each zone will be allocated later when the per cpu
+	 * allocator is available.
+	 *
+	 * boot_pagesets are used also for bootstrapping offline
+	 * cpus if the system is already booted because the pagesets
+	 * are needed to initialize allocators on a specific cpu too.
+	 * F.e. the percpu allocator needs the page allocator which
+	 * needs the percpu allocator in order to allocate its pagesets
+	 * (a chicken-egg dilemma).
+	 */
+	for_each_possible_cpu(cpu)
+		setup_pageset(&per_cpu(boot_pageset, cpu), 0);
+
 	mminit_verify_zonelist();
 	cpuset_init_current_mems_allowed();
 }
 
 /*
- * Called with zonelists_mutex held always
  * unless system_state == SYSTEM_BOOTING.
  *
- * __ref due to (1) call of __meminit annotated setup_zone_pageset
- * [we're only called with non-NULL zone through __meminit paths] and
- * (2) call of __init annotated helper build_all_zonelists_init
+ * __ref due to call of __init annotated helper build_all_zonelists_init
  * [protected by SYSTEM_BOOTING].
  */
-void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
+void __ref build_all_zonelists(pg_data_t *pgdat)
 {
-	set_zonelist_order();
-
 	if (system_state == SYSTEM_BOOTING) {
 		build_all_zonelists_init();
 	} else {
-#ifdef CONFIG_MEMORY_HOTPLUG
-		if (zone)
-			setup_zone_pageset(zone);
-#endif
-		/* we have to stop all cpus to guarantee there is no user
-		   of zonelist */
-		stop_machine_cpuslocked(__build_all_zonelists, pgdat, NULL);
+		__build_all_zonelists(pgdat);
 		/* cpuset refresh routine should be here */
 	}
 	vm_total_pages = nr_free_pagecache_pages();
@@ -5309,9 +5266,8 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 	else
 		page_group_by_mobility_disabled = 0;
 
-	pr_info("Built %i zonelists in %s order, mobility grouping %s.  Total pages: %ld\n",
+	pr_info("Built %i zonelists, mobility grouping %s.  Total pages: %ld\n",
 		nr_online_nodes,
-		zonelist_order_name[current_zonelist_order],
 		page_group_by_mobility_disabled ? "off" : "on",
 		vm_total_pages);
 #ifdef CONFIG_NUMA
@@ -5565,7 +5521,7 @@ static void __meminit zone_pageset_init(struct zone *zone, int cpu)
 	pageset_set_high_and_batch(zone, pcp);
 }
 
-static void __meminit setup_zone_pageset(struct zone *zone)
+void __meminit setup_zone_pageset(struct zone *zone)
 {
 	int cpu;
 	zone->pageset = alloc_percpu(struct per_cpu_pageset);
@@ -7019,9 +6975,11 @@ static void __setup_per_zone_wmarks(void)
  */
 void setup_per_zone_wmarks(void)
 {
-	mutex_lock(&zonelists_mutex);
+	static DEFINE_SPINLOCK(lock);
+
+	spin_lock(&lock);
 	__setup_per_zone_wmarks();
-	mutex_unlock(&zonelists_mutex);
+	spin_unlock(&lock);
 }
 
 /*