[PATCH RFC 03/14] mm: vmstat: use s32 for vm_node_stat_diff in struct per_cpu_nodestat

From: Roman Gushchin
Date: Thu Sep 05 2019 - 17:46:28 EST


Currently s8 type is used for per-cpu caching of per-node statistics.
It works fine because the overfill threshold can't exceed 125.

But if some counters are in bytes (and the next commit in the series
will convert slab counters to bytes), it's not gonna work:
value in bytes can easily exceed s8 without exceeding the threshold
converted to bytes. So to avoid overfilling per-cpu caches and breaking
vmstats correctness, let's use s32 instead.

This doesn't affect per-zone statistics. There are no plans to use
zone-level byte-sized counters, so no reasons to change anything.

Signed-off-by: Roman Gushchin <guro@xxxxxx>
---
include/linux/mmzone.h | 2 +-
mm/vmstat.c | 16 ++++++++--------
2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bda20282746b..6e8233d52971 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -353,7 +353,7 @@ struct per_cpu_pageset {

struct per_cpu_nodestat {
s8 stat_threshold;
- s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
+ s32 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
};

#endif /* !__GENERATING_BOUNDS.H */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6afc892a148a..98f43725d910 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -337,7 +337,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
long delta)
{
struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
- s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ s32 __percpu *p = pcp->vm_node_stat_diff + item;
long x;
long t;

@@ -395,13 +395,13 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
- s8 __percpu *p = pcp->vm_node_stat_diff + item;
- s8 v, t;
+ s32 __percpu *p = pcp->vm_node_stat_diff + item;
+ s32 v, t;

v = __this_cpu_inc_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v > t)) {
- s8 overstep = t >> 1;
+ s32 overstep = t >> 1;

node_page_state_add(v + overstep, pgdat, item);
__this_cpu_write(*p, -overstep);
@@ -439,13 +439,13 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
{
struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
- s8 __percpu *p = pcp->vm_node_stat_diff + item;
- s8 v, t;
+ s32 __percpu *p = pcp->vm_node_stat_diff + item;
+ s32 v, t;

v = __this_cpu_dec_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v < - t)) {
- s8 overstep = t >> 1;
+ s32 overstep = t >> 1;

node_page_state_add(v - overstep, pgdat, item);
__this_cpu_write(*p, overstep);
@@ -538,7 +538,7 @@ static inline void mod_node_state(struct pglist_data *pgdat,
enum node_stat_item item, int delta, int overstep_mode)
{
struct per_cpu_nodestat __percpu *pcp = pgdat->per_cpu_nodestats;
- s8 __percpu *p = pcp->vm_node_stat_diff + item;
+ s32 __percpu *p = pcp->vm_node_stat_diff + item;
long o, n, t, z;

do {
--
2.21.0