mm: memcontrol: add {pgscan,pgsteal}_{kswapd,direct} items in memory.stat of cgroup v2

There are already statistics of {pgscan,pgsteal}_kswapd and
{pgscan,pgsteal}_direct of memcg event here, but now only the sum of the
two is displayed in memory.stat of cgroup v2.

In order to obtain more accurate information during monitoring and
debugging, and to align with the display in /proc/vmstat, it better to
display {pgscan,pgsteal}_kswapd and {pgscan,pgsteal}_direct separately.

Also, for forward compatibility, we still display pgscan and pgsteal items
so that it won't break existing applications.

[zhengqi.arch@bytedance.com: add comment for memcg_vm_event_stat (suggested by Michal)]
Link: https://lkml.kernel.org/r/20220606154028.55030-1-zhengqi.arch@bytedance.com
[zhengqi.arch@bytedance.com: fix the doc, thanks to Johannes]
Link: https://lkml.kernel.org/r/20220607064803.79363-1-zhengqi.arch@bytedance.com
Link: https://lkml.kernel.org/r/20220604082209.55174-1-zhengqi.arch@bytedance.com
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 176298f2f4def879ccc7f702dce63b75d9c4e8dc..ad9ba3ec90a5de3ebfc313d35452a2b44c06a2ec 100644 (file)
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1433,6 +1433,24 @@ PAGE_SIZE multiple when read back.
          workingset_nodereclaim
                Number of times a shadow node has been reclaimed
 
+         pgscan (npn)
+               Amount of scanned pages (in an inactive LRU list)
+
+         pgsteal (npn)
+               Amount of reclaimed pages
+
+         pgscan_kswapd (npn)
+               Amount of scanned pages by kswapd (in an inactive LRU list)
+
+         pgscan_direct (npn)
+               Amount of scanned pages directly  (in an inactive LRU list)
+
+         pgsteal_kswapd (npn)
+               Amount of reclaimed pages by kswapd
+
+         pgsteal_direct (npn)
+               Amount of reclaimed pages directly
+
          pgfault (npn)
                Total number of page faults incurred
 
@@ -1442,12 +1460,6 @@ PAGE_SIZE multiple when read back.
          pgrefill (npn)
                Amount of scanned pages (in an active LRU list)
 
-         pgscan (npn)
-               Amount of scanned pages (in an inactive LRU list)
-
-         pgsteal (npn)
-               Amount of reclaimed pages
-
          pgactivate (npn)
                Amount of pages moved to the active LRU list
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index abec50f31fe64100f4be5b029c7161b3a6077a74..28c1532cc91f235e867bcb144d34114581c4c2ac 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1460,6 +1460,29 @@ static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg,
        return memcg_page_state(memcg, item) * memcg_page_state_unit(item);
 }
 
+/* Subset of vm_event_item to report for memcg event stats */
+static const unsigned int memcg_vm_event_stat[] = {
+       PGSCAN_KSWAPD,
+       PGSCAN_DIRECT,
+       PGSTEAL_KSWAPD,
+       PGSTEAL_DIRECT,
+       PGFAULT,
+       PGMAJFAULT,
+       PGREFILL,
+       PGACTIVATE,
+       PGDEACTIVATE,
+       PGLAZYFREE,
+       PGLAZYFREED,
+#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+       ZSWPIN,
+       ZSWPOUT,
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+       THP_FAULT_ALLOC,
+       THP_COLLAPSE_ALLOC,
+#endif
+};
+
 static char *memory_stat_format(struct mem_cgroup *memcg)
 {
        struct seq_buf s;
@@ -1495,41 +1518,17 @@ static char *memory_stat_format(struct mem_cgroup *memcg)
        }
 
        /* Accumulated memory events */
-
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGFAULT),
-                      memcg_events(memcg, PGFAULT));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGMAJFAULT),
-                      memcg_events(memcg, PGMAJFAULT));
-       seq_buf_printf(&s, "%s %lu\n",  vm_event_name(PGREFILL),
-                      memcg_events(memcg, PGREFILL));
        seq_buf_printf(&s, "pgscan %lu\n",
                       memcg_events(memcg, PGSCAN_KSWAPD) +
                       memcg_events(memcg, PGSCAN_DIRECT));
        seq_buf_printf(&s, "pgsteal %lu\n",
                       memcg_events(memcg, PGSTEAL_KSWAPD) +
                       memcg_events(memcg, PGSTEAL_DIRECT));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGACTIVATE),
-                      memcg_events(memcg, PGACTIVATE));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGDEACTIVATE),
-                      memcg_events(memcg, PGDEACTIVATE));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREE),
-                      memcg_events(memcg, PGLAZYFREE));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(PGLAZYFREED),
-                      memcg_events(memcg, PGLAZYFREED));
-
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPIN),
-                      memcg_events(memcg, ZSWPIN));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(ZSWPOUT),
-                      memcg_events(memcg, ZSWPOUT));
-#endif
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_FAULT_ALLOC),
-                      memcg_events(memcg, THP_FAULT_ALLOC));
-       seq_buf_printf(&s, "%s %lu\n", vm_event_name(THP_COLLAPSE_ALLOC),
-                      memcg_events(memcg, THP_COLLAPSE_ALLOC));
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+       for (i = 0; i < ARRAY_SIZE(memcg_vm_event_stat); i++)
+               seq_buf_printf(&s, "%s %lu\n",
+                              vm_event_name(memcg_vm_event_stat[i]),
+                              memcg_events(memcg, memcg_vm_event_stat[i]));
 
        /* The above should easily fit into one page */
        WARN_ON_ONCE(seq_buf_has_overflowed(&s));