mm: memcg: prepare for byte-sized vmstat items

To implement per-object slab memory accounting, we need to convert slab
vmstat counters to bytes.  Actually, out of 4 levels of counters: global,
per-node, per-memcg and per-lruvec only two last levels will require
byte-sized counters.  It's because global and per-node counters will be
counting the number of slab pages, and per-memcg and per-lruvec will be
counting the amount of memory taken by charged slab objects.

Converting all vmstat counters to bytes or even all slab counters to bytes
would introduce an additional overhead.  So instead let's store global and
per-node counters in pages, and memcg and lruvec counters in bytes.

To make the API clean all access helpers (both on the read and write
sides) are dealing with bytes.

To avoid back-and-forth conversions a new flavor of read-side helpers is
introduced, which always returns values in pages: node_page_state_pages()
and global_node_page_state_pages().

Actually new helpers are just reading raw values.  Old helpers are simple
wrappers, which will complain on an attempt to read byte value, because at
the moment no one actually needs bytes.

Thanks to Johannes Weiner for the idea of having the byte-sized API on top
of the page-sized internal storage.

Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20200623174037.3951353-3-guro@fb.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

drivers/base/node.c

@@ -513,7 +513,7 @@ static ssize_t node_read_vmstat(struct device *dev,
 
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
 		n += sprintf(buf+n, "%s %lu\n", node_stat_name(i),
-			     node_page_state(pgdat, i));
+			     node_page_state_pages(pgdat, i));
 
 	return n;
 }

include/linux/mmzone.h

@@ -206,6 +206,16 @@ enum node_stat_item {
 	NR_VM_NODE_STAT_ITEMS
 };
 
+/*
+ * Returns true if the value is measured in bytes (most vmstat values are
+ * measured in pages). This defines the API part, the internal representation
+ * might be different.
+ */
+static __always_inline bool vmstat_item_in_bytes(int idx)
+{
+	return false;
+}
+
 /*
  * We do arithmetic on the LRU lists in various places in the code,
  * so it is important to keep the active lists LRU_ACTIVE higher in

include/linux/vmstat.h

@@ -8,6 +8,7 @@
 #include <linux/vm_event_item.h>
 #include <linux/atomic.h>
 #include <linux/static_key.h>
+#include <linux/mmdebug.h>
 
 extern int sysctl_stat_interval;
 
@@ -192,7 +193,8 @@ static inline unsigned long global_zone_page_state(enum zone_stat_item item)
 	return x;
 }
 
-static inline unsigned long global_node_page_state(enum node_stat_item item)
+static inline
+unsigned long global_node_page_state_pages(enum node_stat_item item)
 {
 	long x = atomic_long_read(&vm_node_stat[item]);
 #ifdef CONFIG_SMP
@@ -202,6 +204,13 @@ static inline unsigned long global_node_page_state(enum node_stat_item item)
 	return x;
 }
 
+static inline unsigned long global_node_page_state(enum node_stat_item item)
+{
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
+	return global_node_page_state_pages(item);
+}
+
 static inline unsigned long zone_page_state(struct zone *zone,
 					enum zone_stat_item item)
 {
@@ -242,9 +251,12 @@ extern unsigned long sum_zone_node_page_state(int node,
 extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item);
 extern unsigned long node_page_state(struct pglist_data *pgdat,
 						enum node_stat_item item);
+extern unsigned long node_page_state_pages(struct pglist_data *pgdat,
+					   enum node_stat_item item);
 #else
 #define sum_zone_node_page_state(node, item) global_zone_page_state(item)
 #define node_page_state(node, item) global_node_page_state(item)
+#define node_page_state_pages(node, item) global_node_page_state_pages(item)
 #endif /* CONFIG_NUMA */
 
 #ifdef CONFIG_SMP

mm/memcontrol.c

@@ -681,13 +681,16 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_node *mctz)
  */
 void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
 {
-	long x;
+	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	if (mem_cgroup_disabled())
 		return;
 
+	if (vmstat_item_in_bytes(idx))
+		threshold <<= PAGE_SHIFT;
+
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
-	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+	if (unlikely(abs(x) > threshold)) {
 		struct mem_cgroup *mi;
 
 		/*
@@ -718,7 +721,7 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 {
 	struct mem_cgroup_per_node *pn;
 	struct mem_cgroup *memcg;
-	long x;
+	long x, threshold = MEMCG_CHARGE_BATCH;
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	memcg = pn->memcg;
@@ -729,8 +732,11 @@ void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
 	/* Update lruvec */
 	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
 
+	if (vmstat_item_in_bytes(idx))
+		threshold <<= PAGE_SHIFT;
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
-	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
+	if (unlikely(abs(x) > threshold)) {
 		pg_data_t *pgdat = lruvec_pgdat(lruvec);
 		struct mem_cgroup_per_node *pi;
 

mm/vmstat.c

@@ -341,6 +341,11 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
 	long x;
 	long t;
 
+	if (vmstat_item_in_bytes(item)) {
+		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
+		delta >>= PAGE_SHIFT;
+	}
+
 	x = delta + __this_cpu_read(*p);
 
 	t = __this_cpu_read(pcp->stat_threshold);
@@ -398,6 +403,8 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	s8 v, t;
 
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
 	v = __this_cpu_inc_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
 	if (unlikely(v > t)) {
@@ -442,6 +449,8 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	s8 v, t;
 
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
 	v = __this_cpu_dec_return(*p);
 	t = __this_cpu_read(pcp->stat_threshold);
 	if (unlikely(v < - t)) {
@@ -541,6 +550,11 @@ static inline void mod_node_state(struct pglist_data *pgdat,
 	s8 __percpu *p = pcp->vm_node_stat_diff + item;
 	long o, n, t, z;
 
+	if (vmstat_item_in_bytes(item)) {
+		VM_WARN_ON_ONCE(delta & (PAGE_SIZE - 1));
+		delta >>= PAGE_SHIFT;
+	}
+
 	do {
 		z = 0;  /* overflow to node counters */
 
@@ -989,8 +1003,8 @@ unsigned long sum_zone_numa_state(int node,
 /*
  * Determine the per node value of a stat item.
  */
-unsigned long node_page_state(struct pglist_data *pgdat,
+unsigned long node_page_state_pages(struct pglist_data *pgdat,
-				enum node_stat_item item)
+				    enum node_stat_item item)
 {
 	long x = atomic_long_read(&pgdat->vm_stat[item]);
 #ifdef CONFIG_SMP
@@ -999,6 +1013,14 @@ unsigned long node_page_state(struct pglist_data *pgdat,
 #endif
 	return x;
 }
+
+unsigned long node_page_state(struct pglist_data *pgdat,
+			      enum node_stat_item item)
+{
+	VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));
+
+	return node_page_state_pages(pgdat, item);
+}
 #endif
 
 #ifdef CONFIG_COMPACTION
@@ -1577,7 +1599,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		seq_printf(m, "\n  per-node stats");
 		for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++) {
 			seq_printf(m, "\n      %-12s %lu", node_stat_name(i),
-				   node_page_state(pgdat, i));
+				   node_page_state_pages(pgdat, i));
 		}
 	}
 	seq_printf(m,
@@ -1698,7 +1720,7 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos)
 #endif
 
 	for (i = 0; i < NR_VM_NODE_STAT_ITEMS; i++)
-		v[i] = global_node_page_state(i);
+		v[i] = global_node_page_state_pages(i);
 	v += NR_VM_NODE_STAT_ITEMS;
 
 	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,