[PATCH linux-next v3 1/6] memcg: add per-memcg ksm_rmap_items stat

[<xu.xin16@zte.com.cn>]

From: xu xin <xu.xin16@zte.com.cn>

With the enablement of container-level KSM (e.g., via prctl), there is
a growing demand for container-level observability of KSM behavior.

The value of "ksm_rmap_items" indicates the total allocated ksm
rmap_items of this memcg, which could be used to determine how
unbeneficial the ksm-policy (like madvise), they are using brings,
since the bigger the ratio of ksm_rmap_items over ksm_merging_pages,
the more unbeneficial the ksm bring.

Add the counter in the existing memory.stat without adding a new interface.
We traverse all processes of a memcg and summing the processes'
ksm_rmap_items counters instead of adding enum item in memcg_stat_item
or node_stat_item and updating the corresponding enum counter when
ksmd manipulate pages.

Finally, we can look up ksm_rmap_items of per-memcg simply by:

    cat /sys/fs/cgroup/memory.stat | grep ksm_rmap_items

Signed-off-by: xu xin <xu.xin16@zte.com.cn>
---
 include/linux/ksm.h |  1 +
 mm/ksm.c            | 39 +++++++++++++++++++++++++++++++++++++++
 mm/memcontrol.c     |  5 +++++
 3 files changed, 45 insertions(+)

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 067538fc4d58..ce2a32b73f95 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -100,6 +100,7 @@ void collect_procs_ksm(const struct folio *folio, const struct page *page,
 		struct list_head *to_kill, int force_early);
 long ksm_process_profit(struct mm_struct *);
 bool ksm_process_mergeable(struct mm_struct *mm);
+void memcg_stat_ksm_show(struct mem_cgroup *memcg, struct seq_buf *s);

 #else  /* !CONFIG_KSM */

diff --git a/mm/ksm.c b/mm/ksm.c
index 2ef29802a49b..be0efa0f8f2b 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -40,6 +40,7 @@
 #include <linux/oom.h>
 #include <linux/numa.h>
 #include <linux/pagewalk.h>
+#include <linux/seq_buf.h>

 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -3308,6 +3309,44 @@ long ksm_process_profit(struct mm_struct *mm)
 }
 #endif /* CONFIG_PROC_FS */

+#ifdef CONFIG_MEMCG
+struct memcg_ksm_stat {
+	unsigned long ksm_rmap_items;
+};
+
+static int evaluate_memcg_ksm_stat(struct task_struct *task, void *arg)
+{
+	struct mm_struct *mm;
+	struct memcg_ksm_stat *ksm_stat = arg;
+
+	mm = get_task_mm(task);
+	if (mm) {
+		ksm_stat->ksm_rmap_items += mm->ksm_rmap_items;
+		mmput(mm);
+	}
+
+	return 0;
+}
+
+/* Show the ksm statistic count at memory.stat under cgroup mountpoint */
+void memcg_stat_ksm_show(struct mem_cgroup *memcg, struct seq_buf *s)
+{
+	struct memcg_ksm_stat ksm_stat;
+
+	if (mem_cgroup_is_root(memcg)) {
+		/* Just use the global counters when root memcg */
+		ksm_stat.ksm_rmap_items = ksm_rmap_items;
+	} else {
+		/* Initialization */
+		ksm_stat.ksm_rmap_items = 0;
+		/* Summing all processes'ksm statistic items */
+		mem_cgroup_scan_tasks(memcg, evaluate_memcg_ksm_stat, &ksm_stat);
+	}
+	/* Print memcg ksm statistic items */
+	seq_buf_printf(s, "ksm_rmap_items %lu\n", ksm_stat.ksm_rmap_items);
+}
+#endif
+
 #ifdef CONFIG_SYSFS
 /*
  * This all compiles without CONFIG_SYSFS, but is a waste of space.
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e090f29eb03b..705717f73b89 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -63,6 +63,7 @@
 #include <linux/seq_buf.h>
 #include <linux/sched/isolation.h>
 #include <linux/kmemleak.h>
+#include <linux/ksm.h>
 #include "internal.h"
 #include <net/sock.h>
 #include <net/ip.h>
@@ -1493,6 +1494,10 @@ static void memcg_stat_format(struct mem_cgroup *memcg, struct seq_buf *s)
 		}
 	}

+#ifdef CONFIG_KSM
+	memcg_stat_ksm_show(memcg, s);
+#endif
+
 	/* Accumulated memory events */
 	seq_buf_printf(s, "pgscan %lu\n",
 		       memcg_events(memcg, PGSCAN_KSWAPD) +
-- 
2.25.1