+ mm-memcg-use-rstat-for-non-hierarchical-stats.patch added to mm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: mm: memcg: use rstat for non-hierarchical stats
has been added to the -mm mm-unstable branch.  Its filename is
     mm-memcg-use-rstat-for-non-hierarchical-stats.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-memcg-use-rstat-for-non-hierarchical-stats.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days

------------------------------------------------------
From: Yosry Ahmed <yosryahmed@google.com>
Subject: mm: memcg: use rstat for non-hierarchical stats
Date: Wed, 26 Jul 2023 15:32:23 +0000

Currently, memcg uses rstat to maintain aggregated hierarchical stats. 
Counters are maintained for hierarchical stats at each memcg.  Rstat
tracks which cgroups have updates on which cpus to keep those counters
fresh on the read-side.

Non-hierarchical stats are currently not covered by rstat.  Their per-cpu
counters are summed up on every read, which is expensive.  The original
implementation did the same.  At some point before rstat, non-hierarchical
aggregated counters were introduced by commit a983b5ebee57 ("mm:
memcontrol: fix excessive complexity in memory.stat reporting").  However,
those counters were updated on the performance critical write-side, which
caused regressions, so they were later removed by commit 815744d75152
("mm: memcontrol: don't batch updates of local VM stats and events").  See
[1] for more detailed history.

Kernel versions in between a983b5ebee57 & 815744d75152 (a year and a half)
enjoyed cheap reads of non-hierarchical stats, specifically on cgroup v1. 
When moving to more recent kernels, a performance regression for reading
non-hierarchical stats is observed.

Now that we have rstat, we know exactly which percpu counters have updates
for each stat.  We can maintain non-hierarchical counters again, making
reads much more efficient, without affecting the performance critical
write-side.  Hence, add non-hierarchical (i.e local) counters for the
stats, and extend rstat flushing to keep those up-to-date.

A caveat is that we now need a stats flush before reading
local/non-hierarchical stats through {memcg/lruvec}_page_state_local() or
memcg_events_local(), where we previously only needed a flush to read
hierarchical stats.  Most contexts reading non-hierarchical stats are
already doing a flush, add a flush to the only missing context in
count_shadow_nodes().

With this patch, reading memory.stat from 1000 memcgs is 3x faster on a
machine with 256 cpus on cgroup v1:
 # for i in $(seq 1000); do mkdir /sys/fs/cgroup/memory/cg$i; done
 # time cat /dev/cgroup/memory/cg*/memory.stat > /dev/null
 real	 0m0.125s
 user	 0m0.005s
 sys	 0m0.120s

After:
 real	 0m0.032s
 user	 0m0.005s
 sys	 0m0.027s

[1] https://lore.kernel.org/lkml/20230725201811.GA1231514@cmpxchg.org/

Link: https://lkml.kernel.org/r/20230726153223.821757-2-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 include/linux/memcontrol.h |    7 ++-
 mm/memcontrol.c            |   67 +++++++++++++++++++----------------
 mm/workingset.c            |    1 
 3 files changed, 43 insertions(+), 32 deletions(-)

--- a/include/linux/memcontrol.h~mm-memcg-use-rstat-for-non-hierarchical-stats
+++ a/include/linux/memcontrol.h
@@ -111,6 +111,9 @@ struct lruvec_stats {
 	/* Aggregated (CPU and subtree) state */
 	long state[NR_VM_NODE_STAT_ITEMS];
 
+	/* Non-hierarchical (CPU aggregated) state */
+	long state_local[NR_VM_NODE_STAT_ITEMS];
+
 	/* Pending child counts during tree propagation */
 	long state_pending[NR_VM_NODE_STAT_ITEMS];
 };
@@ -1019,14 +1022,12 @@ static inline unsigned long lruvec_page_
 {
 	struct mem_cgroup_per_node *pn;
 	long x = 0;
-	int cpu;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	for_each_possible_cpu(cpu)
-		x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
+	x = READ_ONCE(pn->lruvec_stats.state_local[idx]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
--- a/mm/memcontrol.c~mm-memcg-use-rstat-for-non-hierarchical-stats
+++ a/mm/memcontrol.c
@@ -742,6 +742,10 @@ struct memcg_vmstats {
 	long			state[MEMCG_NR_STAT];
 	unsigned long		events[NR_MEMCG_EVENTS];
 
+	/* Non-hierarchical (CPU aggregated) page state & events */
+	long			state_local[MEMCG_NR_STAT];
+	unsigned long		events_local[NR_MEMCG_EVENTS];
+
 	/* Pending child counts during tree propagation */
 	long			state_pending[MEMCG_NR_STAT];
 	unsigned long		events_pending[NR_MEMCG_EVENTS];
@@ -775,11 +779,8 @@ void __mod_memcg_state(struct mem_cgroup
 /* idx can be of type enum memcg_stat_item or node_stat_item. */
 static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
 {
-	long x = 0;
-	int cpu;
+	long x = READ_ONCE(memcg->vmstats->state_local[idx]);
 
-	for_each_possible_cpu(cpu)
-		x += per_cpu(memcg->vmstats_percpu->state[idx], cpu);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -926,16 +927,12 @@ static unsigned long memcg_events(struct
 
 static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 {
-	long x = 0;
-	int cpu;
 	int index = memcg_events_index(event);
 
 	if (index < 0)
 		return 0;
 
-	for_each_possible_cpu(cpu)
-		x += per_cpu(memcg->vmstats_percpu->events[index], cpu);
-	return x;
+	return READ_ONCE(memcg->vmstats->events_local[index]);
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
@@ -5517,7 +5514,7 @@ static void mem_cgroup_css_rstat_flush(s
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 	struct mem_cgroup *parent = parent_mem_cgroup(memcg);
 	struct memcg_vmstats_percpu *statc;
-	long delta, v;
+	long delta, delta_cpu, v;
 	int i, nid;
 
 	statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
@@ -5533,19 +5530,23 @@ static void mem_cgroup_css_rstat_flush(s
 			memcg->vmstats->state_pending[i] = 0;
 
 		/* Add CPU changes on this level since the last flush */
+		delta_cpu = 0;
 		v = READ_ONCE(statc->state[i]);
 		if (v != statc->state_prev[i]) {
-			delta += v - statc->state_prev[i];
+			delta_cpu = v - statc->state_prev[i];
+			delta += delta_cpu;
 			statc->state_prev[i] = v;
 		}
 
-		if (!delta)
-			continue;
-
 		/* Aggregate counts on this level and propagate upwards */
-		memcg->vmstats->state[i] += delta;
-		if (parent)
-			parent->vmstats->state_pending[i] += delta;
+		if (delta_cpu)
+			memcg->vmstats->state_local[i] += delta_cpu;
+
+		if (delta) {
+			memcg->vmstats->state[i] += delta;
+			if (parent)
+				parent->vmstats->state_pending[i] += delta;
+		}
 	}
 
 	for (i = 0; i < NR_MEMCG_EVENTS; i++) {
@@ -5553,18 +5554,22 @@ static void mem_cgroup_css_rstat_flush(s
 		if (delta)
 			memcg->vmstats->events_pending[i] = 0;
 
+		delta_cpu = 0;
 		v = READ_ONCE(statc->events[i]);
 		if (v != statc->events_prev[i]) {
-			delta += v - statc->events_prev[i];
+			delta_cpu = v - statc->events_prev[i];
+			delta += delta_cpu;
 			statc->events_prev[i] = v;
 		}
 
-		if (!delta)
-			continue;
+		if (delta_cpu)
+			memcg->vmstats->events_local[i] += delta_cpu;
 
-		memcg->vmstats->events[i] += delta;
-		if (parent)
-			parent->vmstats->events_pending[i] += delta;
+		if (delta) {
+			memcg->vmstats->events[i] += delta;
+			if (parent)
+				parent->vmstats->events_pending[i] += delta;
+		}
 	}
 
 	for_each_node_state(nid, N_MEMORY) {
@@ -5582,18 +5587,22 @@ static void mem_cgroup_css_rstat_flush(s
 			if (delta)
 				pn->lruvec_stats.state_pending[i] = 0;
 
+			delta_cpu = 0;
 			v = READ_ONCE(lstatc->state[i]);
 			if (v != lstatc->state_prev[i]) {
-				delta += v - lstatc->state_prev[i];
+				delta_cpu = v - lstatc->state_prev[i];
+				delta += delta_cpu;
 				lstatc->state_prev[i] = v;
 			}
 
-			if (!delta)
-				continue;
+			if (delta_cpu)
+				pn->lruvec_stats.state_local[i] += delta_cpu;
 
-			pn->lruvec_stats.state[i] += delta;
-			if (ppn)
-				ppn->lruvec_stats.state_pending[i] += delta;
+			if (delta) {
+				pn->lruvec_stats.state[i] += delta;
+				if (ppn)
+					ppn->lruvec_stats.state_pending[i] += delta;
+			}
 		}
 	}
 }
--- a/mm/workingset.c~mm-memcg-use-rstat-for-non-hierarchical-stats
+++ a/mm/workingset.c
@@ -664,6 +664,7 @@ static unsigned long count_shadow_nodes(
 		struct lruvec *lruvec;
 		int i;
 
+		mem_cgroup_flush_stats();
 		lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
 		for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
 			pages += lruvec_page_state_local(lruvec,
_

Patches currently in -mm which might be from yosryahmed@google.com are

mm-zswap-multiple-zpools-support.patch
mm-memcg-use-rstat-for-non-hierarchical-stats.patch