[PATCH 3/3] mm/zswap: Add per-memcg stat for proactive writeback

[Hao Jia <jiahao.kernel@gmail.com>]

From: Hao Jia <jiahao1@lixiang.com>

Currently, zswap writeback can be triggered by either the pool limit
being hit or by the proactive writeback mechanism. However, the
existing 'zswpwb' metric in memory.stat and /proc/vmstat counts all
written back pages, making it difficult to distinguish between pages
written back due to the pool limit and those written back proactively.

Add a new statistic 'zswpwb_proactive' to memory.stat and /proc/vmstat.
This counter tracks the number of pages written back due to proactive
writeback. This allows users to better monitor and tune the proactive
writeback mechanism.

Signed-off-by: Hao Jia <jiahao1@lixiang.com>
---
 Documentation/admin-guide/cgroup-v2.rst |  4 ++++
 include/linux/vm_event_item.h           |  1 +
 mm/memcontrol.c                         |  1 +
 mm/vmstat.c                             |  1 +
 mm/zswap.c                              | 11 +++++++++--
 5 files changed, 16 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 05b664b3b3e8..29a189b18efc 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1734,6 +1734,10 @@ The following nested keys are defined.
 	  zswpwb
 		Number of pages written from zswap to swap.
 
+	  zswpwb_proactive
+		Number of pages written from zswap to swap by proactive
+		writeback. This is a subset of zswpwb.
+
 	  zswap_incomp
 		Number of incompressible pages currently stored in zswap
 		without compression. These pages could not be compressed to
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 03fe95f5a020..7a5bee0a20b6 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -138,6 +138,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		ZSWPIN,
 		ZSWPOUT,
 		ZSWPWB,
+		ZSWPWB_PROACTIVE,
 #endif
 #ifdef CONFIG_X86
 		DIRECT_MAP_LEVEL2_SPLIT,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ba7f7b1954a8..830d895e77c3 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -572,6 +572,7 @@ static const unsigned int memcg_vm_event_stat[] = {
 	ZSWPIN,
 	ZSWPOUT,
 	ZSWPWB,
+	ZSWPWB_PROACTIVE,
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	THP_FAULT_ALLOC,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f534972f517d..66fd06d1bb01 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1452,6 +1452,7 @@ const char * const vmstat_text[] = {
 	[I(ZSWPIN)]				= "zswpin",
 	[I(ZSWPOUT)]				= "zswpout",
 	[I(ZSWPWB)]				= "zswpwb",
+	[I(ZSWPWB_PROACTIVE)]			= "zswpwb_proactive",
 #endif
 #ifdef CONFIG_X86
 	[I(DIRECT_MAP_LEVEL2_SPLIT)]		= "direct_map_level2_splits",
diff --git a/mm/zswap.c b/mm/zswap.c
index 1173ac6836fa..bf23c46e838e 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -1048,7 +1048,8 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
  * freed.
  */
 static int zswap_writeback_entry(struct zswap_entry *entry,
-				 swp_entry_t swpentry)
+				 swp_entry_t swpentry,
+				 bool proactive)
 {
 	struct xarray *tree;
 	pgoff_t offset = swp_offset(swpentry);
@@ -1108,6 +1109,12 @@ static int zswap_writeback_entry(struct zswap_entry *entry,
 	if (entry->objcg)
 		count_objcg_events(entry->objcg, ZSWPWB, 1);
 
+	if (proactive) {
+		count_vm_event(ZSWPWB_PROACTIVE);
+		if (entry->objcg)
+			count_objcg_events(entry->objcg, ZSWPWB_PROACTIVE, 1);
+	}
+
 	zswap_entry_free(entry);
 
 	/* folio is up to date */
@@ -1223,7 +1230,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 	 */
 	spin_unlock(&l->lock);
 
-	writeback_result = zswap_writeback_entry(entry, swpentry);
+	writeback_result = zswap_writeback_entry(entry, swpentry, proactive_wb);
 
 	if (writeback_result) {
 		zswap_reject_reclaim_fail++;
-- 
2.34.1