[PATCH 2/2] mm/vmstat: Protect per cpu variables with preempt disable on RT

From: Mel Gorman
Date: Fri Jul 23 2021 - 06:01:08 EST


From: Ingo Molnar <mingo@xxxxxxx>

Disable preemption on -RT for the vmstat code. On vanila the code runs
in IRQ-off regions while on -RT it may not when stats are updated under
a local_lock. "preempt_disable" ensures that the same resources is not
updated in parallel due to preemption.

This patch differs from the preempt-rt version where __count_vm_event and
__count_vm_events are also protected. The counters are explicitly "allowed
to be to be racy" so there is no need to protect them from preemption. Only
the accurate page stats that are updated by a read-modify-write need
protection.

Signed-off-by: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
---
mm/vmstat.c | 12 ++++++++++++
1 file changed, 12 insertions(+)

diff --git a/mm/vmstat.c b/mm/vmstat.c
index b0534e068166..d06332c221b1 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -319,6 +319,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
long x;
long t;

+ preempt_disable_rt();
x = delta + __this_cpu_read(*p);

t = __this_cpu_read(pcp->stat_threshold);
@@ -328,6 +329,7 @@ void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
x = 0;
}
__this_cpu_write(*p, x);
+ preempt_enable_rt();
}
EXPORT_SYMBOL(__mod_zone_page_state);

@@ -350,6 +352,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
delta >>= PAGE_SHIFT;
}

+ preempt_disable_rt();
x = delta + __this_cpu_read(*p);

t = __this_cpu_read(pcp->stat_threshold);
@@ -359,6 +362,7 @@ void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item,
x = 0;
}
__this_cpu_write(*p, x);
+ preempt_enable_rt();
}
EXPORT_SYMBOL(__mod_node_page_state);

@@ -391,6 +395,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
s8 __percpu *p = pcp->vm_stat_diff + item;
s8 v, t;

+ preempt_disable_rt();
v = __this_cpu_inc_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v > t)) {
@@ -399,6 +404,7 @@ void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
zone_page_state_add(v + overstep, zone, item);
__this_cpu_write(*p, -overstep);
}
+ preempt_enable_rt();
}

void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -409,6 +415,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)

VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));

+ preempt_disable_rt();
v = __this_cpu_inc_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v > t)) {
@@ -417,6 +424,7 @@ void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
node_page_state_add(v + overstep, pgdat, item);
__this_cpu_write(*p, -overstep);
}
+ preempt_enable_rt();
}

void __inc_zone_page_state(struct page *page, enum zone_stat_item item)
@@ -437,6 +445,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
s8 __percpu *p = pcp->vm_stat_diff + item;
s8 v, t;

+ preempt_disable_rt();
v = __this_cpu_dec_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v < - t)) {
@@ -445,6 +454,7 @@ void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
zone_page_state_add(v - overstep, zone, item);
__this_cpu_write(*p, overstep);
}
+ preempt_enable_rt();
}

void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
@@ -455,6 +465,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)

VM_WARN_ON_ONCE(vmstat_item_in_bytes(item));

+ preempt_disable_rt();
v = __this_cpu_dec_return(*p);
t = __this_cpu_read(pcp->stat_threshold);
if (unlikely(v < - t)) {
@@ -463,6 +474,7 @@ void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
node_page_state_add(v - overstep, pgdat, item);
__this_cpu_write(*p, overstep);
}
+ preempt_enable_rt();
}

void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
--
2.26.2