Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.31 as permitted sender) client-ip=23.128.96.31;
Date:   Fri, 22 Sep 2023 08:25:41 +0000
In-Reply-To: <20230922082542.466579-1-yosryahmed@google.com>
Mime-Version: 1.0
References: <20230922082542.466579-1-yosryahmed@google.com>
Message-ID: <20230922082542.466579-2-yosryahmed@google.com>
Subject: [PATCH 1/2] mm: memcg: refactor page state unit helpers
From:   Yosry Ahmed <yosryahmed@google.com>
To:     Andrew Morton <akpm@linux-foundation.org>,
        Shakeel Butt <shakeelb@google.com>
Cc:     Johannes Weiner <hannes@cmpxchg.org>,
        Michal Hocko <mhocko@kernel.org>,
        Roman Gushchin <roman.gushchin@linux.dev>,
        Muchun Song <muchun.song@linux.dev>,
        "=?UTF-8?q?Michal=20Koutn=C3=BD?=" <mkoutny@suse.com>,
        linux-mm@kvack.org, cgroups@vger.kernel.org,
        linux-kernel@vger.kernel.org, Yosry Ahmed <yosryahmed@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

memcg_page_state_unit() is currently used to identify the unit of a
memcg state item so that all stats in memory.stat are in bytes. However,
it lies about the units of WORKINGSET_* stats. These stats actually
represent pages, but we present them to userspace as a scalar number of
events. In retrospect, maybe those stats should have been memcg "events"
rather than memcg "state".

In preparation for using memcg_page_state_unit() for other purposes that
need to know the truthful units of different stat items, break it down
into two helpers:
- memcg_page_state_unit() retuns the actual unit of the item.
- memcg_page_state_output_unit() returns the unit used for output.

Use the latter instead of the former in memcg_page_state_output() and
lruvec_page_state_output(). While we are at it, let's show cgroup v1
some love and add memcg_page_state_local_output() for consistency.

No functional change intended.

Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
---
 mm/memcontrol.c | 44 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 33 insertions(+), 11 deletions(-)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index a4d3282493b6..683aa8405c22 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1533,7 +1533,7 @@ static const struct memory_stat memory_stats[] = {
 	{ "workingset_nodereclaim",	WORKINGSET_NODERECLAIM		},
 };
 
-/* Translate stat items to the correct unit for memory.stat output */
+/* The actual unit of the state item, not the same as the output unit */
 static int memcg_page_state_unit(int item)
 {
 	switch (item) {
@@ -1541,6 +1541,22 @@ static int memcg_page_state_unit(int item)
 	case MEMCG_ZSWAP_B:
 	case NR_SLAB_RECLAIMABLE_B:
 	case NR_SLAB_UNRECLAIMABLE_B:
+		return 1;
+	case NR_KERNEL_STACK_KB:
+		return SZ_1K;
+	default:
+		return PAGE_SIZE;
+	}
+}
+
+/* Translate stat items to the correct unit for memory.stat output */
+static int memcg_page_state_output_unit(int item)
+{
+	/*
+	 * Workingset state is actually in pages, but we export it to userspace
+	 * as a scalar count of events, so special case it here.
+	 */
+	switch (item) {
 	case WORKINGSET_REFAULT_ANON:
 	case WORKINGSET_REFAULT_FILE:
 	case WORKINGSET_ACTIVATE_ANON:
@@ -1549,17 +1565,23 @@ static int memcg_page_state_unit(int item)
 	case WORKINGSET_RESTORE_FILE:
 	case WORKINGSET_NODERECLAIM:
 		return 1;
-	case NR_KERNEL_STACK_KB:
-		return SZ_1K;
 	default:
-		return PAGE_SIZE;
+		return memcg_page_state_unit(item);
 	}
 }
 
 static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg,
 						    int item)
 {
-	return memcg_page_state(memcg, item) * memcg_page_state_unit(item);
+	return memcg_page_state(memcg, item) *
+		memcg_page_state_output_unit(item);
+}
+
+static inline unsigned long memcg_page_state_local_output(
+		struct mem_cgroup *memcg, int item)
+{
+	return memcg_page_state_local(memcg, item) *
+		memcg_page_state_output_unit(item);
 }
 
 static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
@@ -4100,9 +4122,8 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
-		nr = memcg_page_state_local(memcg, memcg1_stats[i]);
-		seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i],
-			   nr * memcg_page_state_unit(memcg1_stats[i]));
+		nr = memcg_page_state_local_output(memcg, memcg1_stats[i]);
+		seq_buf_printf(s, "%s %lu\n", memcg1_stat_names[i], nr);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -4131,9 +4152,9 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 
 		if (memcg1_stats[i] == MEMCG_SWAP && !do_memsw_account())
 			continue;
-		nr = memcg_page_state(memcg, memcg1_stats[i]);
+		nr = memcg_page_state_output(memcg, memcg1_stats[i]);
 		seq_buf_printf(s, "total_%s %llu\n", memcg1_stat_names[i],
-			   (u64)nr * memcg_page_state_unit(memcg1_stats[i]));
+			       (u64)nr);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(memcg1_events); i++)
@@ -6609,7 +6630,8 @@ static int memory_stat_show(struct seq_file *m, void *v)
 static inline unsigned long lruvec_page_state_output(struct lruvec *lruvec,
 						     int item)
 {
-	return lruvec_page_state(lruvec, item) * memcg_page_state_unit(item);
+	return lruvec_page_state(lruvec, item) *
+		memcg_page_state_output_unit(item);
 }
 
 static int memory_numa_stat_show(struct seq_file *m, void *v)
-- 
2.42.0.515.g380fc7ccd1-goog