mm: vmstat: move slab statistics from zone to node counters

Patch series "mm: per-lruvec slab stats"

Josef is working on a new approach to balancing slab caches and the page
cache.  For this to work, he needs slab cache statistics on the lruvec
level.  These patches implement that by adding infrastructure that
allows updating and reading generic VM stat items per lruvec, then
switches some existing VM accounting sites, including the slab
accounting ones, to this new cgroup-aware API.

I'll follow up with more patches on this, because there is actually
substantial simplification that can be done to the memory controller
when we replace private memcg accounting with making the existing VM
accounting sites cgroup-aware.  But this is enough for Josef to base his
slab reclaim work on, so here goes.

This patch (of 5):

To re-implement slab cache vs.  page cache balancing, we'll need the
slab counters at the lruvec level, which, ever since lru reclaim was
moved from the zone to the node, is the intersection of the node, not
the zone, and the memcg.

We could retain the per-zone counters for when the page allocator dumps
its memory information on failures, and have counters on both levels -
which on all but NUMA node 0 is usually redundant.  But let's keep it
simple for now and just move them.  If anybody complains we can restore
the per-zone counters.

[hannes@cmpxchg.org: fix oops]
  Link: http://lkml.kernel.org/r/20170605183511.GA8915@cmpxchg.org
Link: http://lkml.kernel.org/r/20170530181724.27197-3-hannes@cmpxchg.orgSigned-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/base/node.c

@@ -129,11 +129,11 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
 		       nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE) +
-				sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_RECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE) +
+			      node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE)),
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)),
+		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
 		       nid, K(node_page_state(pgdat, NR_ANON_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
@@ -141,7 +141,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
 				       HPAGE_PMD_NR));
 #else
-		       nid, K(sum_zone_node_page_state(nid, NR_SLAB_UNRECLAIMABLE)));
+		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)));
 #endif
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;

include/linux/mmzone.h

@@ -125,8 +125,6 @@ enum zone_stat_item {
 	NR_ZONE_UNEVICTABLE,
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
-	NR_SLAB_RECLAIMABLE,
-	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
@@ -152,6 +150,8 @@ enum node_stat_item {
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_SLAB_RECLAIMABLE,
+	NR_SLAB_UNRECLAIMABLE,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_REFAULT,

mm/page_alloc.c

@@ -4643,8 +4643,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			" present:%lukB"
 			" managed:%lukB"
 			" mlocked:%lukB"
-			" slab_reclaimable:%lukB"
-			" slab_unreclaimable:%lukB"
 			" kernel_stack:%lukB"
 			" pagetables:%lukB"
 			" bounce:%lukB"
@@ -4666,8 +4664,6 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask)
 			K(zone->present_pages),
 			K(zone->managed_pages),
 			K(zone_page_state(zone, NR_MLOCK)),
-			K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
-			K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
 			zone_page_state(zone, NR_KERNEL_STACK_KB),
 			K(zone_page_state(zone, NR_PAGETABLE)),
 			K(zone_page_state(zone, NR_BOUNCE)),
@@ -5153,6 +5149,7 @@ 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);
 
 /*
@@ -6053,6 +6050,8 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	spin_lock_init(&pgdat->lru_lock);
 	lruvec_init(node_lruvec(pgdat));
 
+	pgdat->per_cpu_nodestats = &boot_nodestats;
+
 	for (j = 0; j < MAX_NR_ZONES; j++) {
 		struct zone *zone = pgdat->node_zones + j;
 		unsigned long size, realsize, freesize, memmap_pages;

mm/slab.c

@@ -1425,10 +1425,10 @@ static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
 
 	nr_pages = (1 << cachep->gfporder);
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		add_zone_page_state(page_zone(page),
+		add_node_page_state(page_pgdat(page),
 			NR_SLAB_RECLAIMABLE, nr_pages);
 	else
-		add_zone_page_state(page_zone(page),
+		add_node_page_state(page_pgdat(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
 
 	__SetPageSlab(page);
@@ -1459,10 +1459,10 @@ static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
 	kmemcheck_free_shadow(page, order);
 
 	if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
-		sub_zone_page_state(page_zone(page),
+		sub_node_page_state(page_pgdat(page),
 				NR_SLAB_RECLAIMABLE, nr_freed);
 	else
-		sub_zone_page_state(page_zone(page),
+		sub_node_page_state(page_pgdat(page),
 				NR_SLAB_UNRECLAIMABLE, nr_freed);
 
 	BUG_ON(!PageSlab(page));

mm/slub.c

@@ -1615,7 +1615,7 @@ static struct page *allocate_slab(struct kmem_cache *s, gfp_t flags, int node)
 	if (!page)
 		return NULL;
 
-	mod_zone_page_state(page_zone(page),
+	mod_node_page_state(page_pgdat(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		1 << oo_order(oo));
@@ -1655,7 +1655,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 
 	kmemcheck_free_shadow(page, compound_order(page));
 
-	mod_zone_page_state(page_zone(page),
+	mod_node_page_state(page_pgdat(page),
 		(s->flags & SLAB_RECLAIM_ACCOUNT) ?
 		NR_SLAB_RECLAIMABLE : NR_SLAB_UNRECLAIMABLE,
 		-pages);

mm/vmscan.c

@@ -3874,7 +3874,7 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
 	 * unmapped file backed pages.
 	 */
 	if (node_pagecache_reclaimable(pgdat) <= pgdat->min_unmapped_pages &&
-	    sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
+	    node_page_state(pgdat, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
 		return NODE_RECLAIM_FULL;
 
 	/*

mm/vmstat.c

@@ -928,8 +928,6 @@ const char * const vmstat_text[] = {
 	"nr_zone_unevictable",
 	"nr_zone_write_pending",
 	"nr_mlock",
-	"nr_slab_reclaimable",
-	"nr_slab_unreclaimable",
 	"nr_page_table_pages",
 	"nr_kernel_stack",
 	"nr_bounce",
@@ -952,6 +950,8 @@ const char * const vmstat_text[] = {
 	"nr_inactive_file",
 	"nr_active_file",
 	"nr_unevictable",
+	"nr_slab_reclaimable",
+	"nr_slab_unreclaimable",
 	"nr_isolated_anon",
 	"nr_isolated_file",
 	"workingset_refault",