mm: memcg: refactor page state unit helpers
Patch series "mm: memcg: fix tracking of pending stats updates values", v2.
While working on adjacent code [1], I realized that the values passed into
memcg_rstat_updated() to keep track of the magnitude of pending updates is
consistent. It is mostly in pages, but sometimes it can be in bytes or
KBs. Fix that.
Patch 1 reworks memcg_page_state_unit() so that we can reuse it in patch 2
to check and normalize the units of state updates.
[1]https://lore.kernel.org/lkml/20230921081057.3440885-1-yosryahmed@google.com/
This patch (of 2):
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.
Link: https://lkml.kernel.org/r/20230922175741.635002-1-yosryahmed@google.com
Link: https://lkml.kernel.org/r/20230922175741.635002-2-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Michal Koutný <mkoutny@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8713bc7..7e65d8c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1535,7 +1535,7 @@ 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) {
@@ -1543,13 +1543,6 @@ static int memcg_page_state_unit(int item)
case MEMCG_ZSWAP_B:
case NR_SLAB_RECLAIMABLE_B:
case NR_SLAB_UNRECLAIMABLE_B:
- case WORKINGSET_REFAULT_ANON:
- case WORKINGSET_REFAULT_FILE:
- case WORKINGSET_ACTIVATE_ANON:
- case WORKINGSET_ACTIVATE_FILE:
- case WORKINGSET_RESTORE_ANON:
- case WORKINGSET_RESTORE_FILE:
- case WORKINGSET_NODERECLAIM:
return 1;
case NR_KERNEL_STACK_KB:
return SZ_1K;
@@ -1558,10 +1551,39 @@ static int memcg_page_state_unit(int item)
}
}
+/* 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:
+ case WORKINGSET_ACTIVATE_FILE:
+ case WORKINGSET_RESTORE_ANON:
+ case WORKINGSET_RESTORE_FILE:
+ case WORKINGSET_NODERECLAIM:
+ return 1;
+ default:
+ 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)
@@ -4113,9 +4135,8 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
unsigned long nr;
- 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++)
@@ -4141,9 +4162,9 @@ static void memcg1_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
for (i = 0; i < ARRAY_SIZE(memcg1_stats); i++) {
unsigned long nr;
- 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++)
@@ -6625,7 +6646,8 @@ 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)
