mm,memcg: provide per-cgroup counters for NUMA balancing operations

The ability to observe the demotion and promotion decisions made by the
kernel on a per-cgroup basis is important for monitoring and tuning
containerized workloads on machines equipped with tiered memory.

Different containers in the system may experience drastically different
memory tiering actions that cannot be distinguished from the global
counters alone.

For example, a container running a workload that has a much hotter memory
accesses will likely see more promotions and fewer demotions, potentially
depriving a colocated container of top tier memory to such an extent that
its performance degrades unacceptably.

For another example, some containers may exhibit longer periods between
data reuse, causing much more numa_hint_faults than numa_pages_migrated. 
In this case, tuning hot_threshold_ms may be appropriate, but the signal
can easily be lost if only global counters are available.

In the long term, we hope to introduce per-cgroup control of promotion and
demotion actions to implement memory placement policies in tiering.

This patch set adds seven counters to memory.stat in a cgroup:
numa_pages_migrated, numa_pte_updates, numa_hint_faults, pgdemote_kswapd,
pgdemote_khugepaged, pgdemote_direct and pgpromote_success.  pgdemote_*
and pgpromote_success are also available in memory.numa_stat.

count_memcg_events_mm() is added to count multiple event occurrences at
once, and get_mem_cgroup_from_folio() is added because we need to get a
reference to the memcg of a folio before it's migrated to track
numa_pages_migrated.  The accounting of PGDEMOTE_* is moved to
shrink_inactive_list() before being changed to per-cgroup.

[kaiyang2@cs.cmu.edu: add documentation of the memcg counters in cgroup-v2.rst]
  Link: https://lkml.kernel.org/r/20240814235122.252309-1-kaiyang2@cs.cmu.edu
Link: https://lkml.kernel.org/r/20240814174227.30639-1-kaiyang2@cs.cmu.edu
Signed-off-by: Kaiyang Zhao <kaiyang2@cs.cmu.edu>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Wei Xu <weixugc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 22 insertions, 3 deletions

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ed170399179a..fe05fdb92779 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -784,6 +784,8 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
 struct mem_cgroup *get_mem_cgroup_from_current(void);
 
+struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio);
+
 struct lruvec *folio_lruvec_lock(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
@@ -1028,8 +1030,8 @@ static inline void count_memcg_folio_events(struct folio *folio,
 		count_memcg_events(memcg, idx, nr);
 }
 
-static inline void count_memcg_event_mm(struct mm_struct *mm,
-					enum vm_event_item idx)
+static inline void count_memcg_events_mm(struct mm_struct *mm,
+					enum vm_event_item idx, unsigned long count)
 {
 	struct mem_cgroup *memcg;
 
@@ -1039,10 +1041,16 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (likely(memcg))
-		count_memcg_events(memcg, idx, 1);
+		count_memcg_events(memcg, idx, count);
 	rcu_read_unlock();
 }
 
+static inline void count_memcg_event_mm(struct mm_struct *mm,
+					enum vm_event_item idx)
+{
+	count_memcg_events_mm(mm, idx, 1);
+}
+
 static inline void memcg_memory_event(struct mem_cgroup *memcg,
 				      enum memcg_memory_event event)
 {
@@ -1262,6 +1270,11 @@ static inline struct mem_cgroup *get_mem_cgroup_from_current(void)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
 {
@@ -1484,6 +1497,11 @@ static inline void count_memcg_folio_events(struct folio *folio,
 {
 }
 
+static inline void count_memcg_events_mm(struct mm_struct *mm,
+					enum vm_event_item idx, unsigned long count)
+{
+}
+
 static inline
 void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 9eb77c9007e6..d2761bf8ff32 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -32,6 +32,7 @@ struct reclaim_stat {
 	unsigned nr_ref_keep;
 	unsigned nr_unmap_fail;
 	unsigned nr_lazyfree_fail;
+	unsigned nr_demoted;
 };
 
 /* Stat data for system wide items */