[PATCH v3 3/4] 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                              | 41 ++++++++++++++++++-------
 5 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 6564abf0dec5..7d65aef83f7b 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1748,6 +1748,10 @@ 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 e205e5de193d..7648b3fd940e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -571,6 +571,7 @@ 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 7bcbf788f634..b45d094f532a 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -160,6 +160,11 @@ struct zswap_pool {
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
 };
 
+struct zswap_shrink_walk_arg {
+	bool proactive;
+	bool encountered_page_in_swapcache;
+};
+
 /* Global LRU lists shared by all zswap pools. */
 static struct list_lru zswap_list_lru;
 
@@ -1042,7 +1047,8 @@ 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);
@@ -1097,6 +1103,12 @@ 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 */
@@ -1146,7 +1158,8 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 				       void *arg)
 {
 	struct zswap_entry *entry = container_of(item, struct zswap_entry, lru);
-	bool *encountered_page_in_swapcache = (bool *)arg;
+	struct zswap_shrink_walk_arg *walk_arg = arg;
+	bool proactive_wb = walk_arg && walk_arg->proactive;
 	swp_entry_t swpentry;
 	enum lru_status ret = LRU_REMOVED_RETRY;
 	int writeback_result;
@@ -1201,7 +1214,7 @@ 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++;
@@ -1212,9 +1225,9 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 		 * into the warmer region. We should terminate shrinking (if we're in the dynamic
 		 * shrinker context).
 		 */
-		if (writeback_result == -EEXIST && encountered_page_in_swapcache) {
+		if (writeback_result == -EEXIST && walk_arg) {
 			ret = LRU_STOP;
-			*encountered_page_in_swapcache = true;
+			walk_arg->encountered_page_in_swapcache = true;
 		}
 	} else {
 		zswap_written_back_pages++;
@@ -1226,8 +1239,11 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
 		struct shrink_control *sc)
 {
+	struct zswap_shrink_walk_arg walk_arg = {
+		.proactive = false,
+		.encountered_page_in_swapcache = false,
+	};
 	unsigned long shrink_ret;
-	bool encountered_page_in_swapcache = false;
 
 	if (!zswap_shrinker_enabled ||
 			!mem_cgroup_zswap_writeback_enabled(sc->memcg)) {
@@ -1236,9 +1252,9 @@ static unsigned long zswap_shrinker_scan(struct shrinker *shrinker,
 	}
 
 	shrink_ret = list_lru_shrink_walk(&zswap_list_lru, sc, &shrink_memcg_cb,
-		&encountered_page_in_swapcache);
+		&walk_arg);
 
-	if (encountered_page_in_swapcache)
+	if (walk_arg.encountered_page_in_swapcache)
 		return SHRINK_STOP;
 
 	return shrink_ret ? shrink_ret : SHRINK_STOP;
@@ -1709,7 +1725,10 @@ static long zswap_proactive_shrink_memcg(struct mem_cgroup *memcg,
 		return -ENOENT;
 
 	for_each_node_state(nid, N_NORMAL_MEMORY) {
-		bool encountered_page_in_swapcache = false;
+		struct zswap_shrink_walk_arg walk_arg = {
+			.proactive = true,
+			.encountered_page_in_swapcache = false,
+		};
 		unsigned long nr_to_scan, nr_scanned = 0;
 
 		/*
@@ -1743,12 +1762,12 @@ static long zswap_proactive_shrink_memcg(struct mem_cgroup *memcg,
 
 			nr_written += list_lru_walk_one(&zswap_list_lru, nid, memcg,
 							&shrink_memcg_cb,
-							&encountered_page_in_swapcache,
+							&walk_arg,
 							&nr_to_walk);
 
 			if (nr_written >= nr_to_write)
 				return nr_written;
-			if (encountered_page_in_swapcache)
+			if (walk_arg.encountered_page_in_swapcache)
 				break;
 
 			cond_resched();
-- 
2.34.1