mm/zswap: use only one pool in zswap

Zswap uses 32 pools to workaround the locking scalability problem in zswap
backends (mainly zsmalloc nowadays), which brings its own problems like
memory waste and more memory fragmentation.

Testing results show that we can have near performance with only one pool
in zswap after changing zsmalloc to use per-size_class lock instead of
pool spinlock.

Testing kernel build (make bzImage -j32) on tmpfs with memory.max=1GB, and
zswap shrinker enabled with 10GB swapfile on ext4.

                                real    user    sys
6.10.0-rc3                      138.18  1241.38 1452.73
6.10.0-rc3-onepool              149.45  1240.45 1844.69
6.10.0-rc3-onepool-perclass     138.23  1242.37 1469.71

And do the same testing using zbud, which shows a little worse performance
as expected since we don't do any locking optimization for zbud.  I think
it's acceptable since zsmalloc became a lot more popular than other
backends, and we may want to support only zsmalloc in the future.

                                real    user    sys
6.10.0-rc3-zbud			138.23  1239.58 1430.09
6.10.0-rc3-onepool-zbud		139.64  1241.37 1516.59

[chengming.zhou@linux.dev: fix error handling in zswap_pool_create(), per Dan Carpenter]
  Link: https://lkml.kernel.org/r/20240621-zsmalloc-lock-mm-everything-v2-2-d30e9cd2b793@linux.dev
[chengming.zhou@linux.dev: fix error handling again in zswap_pool_create(), per Yosry]
  Link: https://lkml.kernel.org/r/20240625-zsmalloc-lock-mm-everything-v3-2-ad941699cb61@linux.dev
Link: https://lkml.kernel.org/r/20240617-zsmalloc-lock-mm-everything-v1-2-5e5081ea11b3@linux.dev
Signed-off-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 20 insertions, 41 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index a546c01602aa..66decab33d14 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -124,9 +124,6 @@ static unsigned int zswap_accept_thr_percent = 90; /* of max pool size */
 module_param_named(accept_threshold_percent, zswap_accept_thr_percent,
 		   uint, 0644);
 
-/* Number of zpools in zswap_pool (empirically determined for scalability) */
-#define ZSWAP_NR_ZPOOLS 32
-
 /* Enable/disable memory pressure-based shrinker. */
 static bool zswap_shrinker_enabled = IS_ENABLED(
 		CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
@@ -162,7 +159,7 @@ struct crypto_acomp_ctx {
  * needs to be verified that it's still valid in the tree.
  */
 struct zswap_pool {
-	struct zpool *zpools[ZSWAP_NR_ZPOOLS];
+	struct zpool *zpool;
 	struct crypto_acomp_ctx __percpu *acomp_ctx;
 	struct percpu_ref ref;
 	struct list_head list;
@@ -244,7 +241,7 @@ static inline struct xarray *swap_zswap_tree(swp_entry_t swp)
 
 #define zswap_pool_debug(msg, p)				\
 	pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name,		\
-		 zpool_get_type((p)->zpools[0]))
+		 zpool_get_type((p)->zpool))
 
 /*********************************
 * pool functions
@@ -253,7 +250,6 @@ static void __zswap_pool_empty(struct percpu_ref *ref);
 
 static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 {
-	int i;
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
@@ -274,18 +270,14 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	if (!pool)
 		return NULL;
 
-	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++) {
-		/* unique name for each pool specifically required by zsmalloc */
-		snprintf(name, 38, "zswap%x",
-			 atomic_inc_return(&zswap_pools_count));
-
-		pool->zpools[i] = zpool_create_pool(type, name, gfp);
-		if (!pool->zpools[i]) {
-			pr_err("%s zpool not available\n", type);
-			goto error;
-		}
+	/* unique name for each pool specifically required by zsmalloc */
+	snprintf(name, 38, "zswap%x", atomic_inc_return(&zswap_pools_count));
+	pool->zpool = zpool_create_pool(type, name, gfp);
+	if (!pool->zpool) {
+		pr_err("%s zpool not available\n", type);
+		goto error;
 	}
-	pr_debug("using %s zpool\n", zpool_get_type(pool->zpools[0]));
+	pr_debug("using %s zpool\n", zpool_get_type(pool->zpool));
 
 	strscpy(pool->tfm_name, compressor, sizeof(pool->tfm_name));
 
@@ -318,8 +310,8 @@ ref_fail:
 error:
 	if (pool->acomp_ctx)
 		free_percpu(pool->acomp_ctx);
-	while (i--)
-		zpool_destroy_pool(pool->zpools[i]);
+	if (pool->zpool)
+		zpool_destroy_pool(pool->zpool);
 	kfree(pool);
 	return NULL;
 }
@@ -368,15 +360,12 @@ static struct zswap_pool *__zswap_pool_create_fallback(void)
 
 static void zswap_pool_destroy(struct zswap_pool *pool)
 {
-	int i;
-
 	zswap_pool_debug("destroying", pool);
 
 	cpuhp_state_remove_instance(CPUHP_MM_ZSWP_POOL_PREPARE, &pool->node);
 	free_percpu(pool->acomp_ctx);
 
-	for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
-		zpool_destroy_pool(pool->zpools[i]);
+	zpool_destroy_pool(pool->zpool);
 	kfree(pool);
 }
 
@@ -471,8 +460,7 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor)
 	list_for_each_entry_rcu(pool, &zswap_pools, list) {
 		if (strcmp(pool->tfm_name, compressor))
 			continue;
-		/* all zpools share the same type */
-		if (strcmp(zpool_get_type(pool->zpools[0]), type))
+		if (strcmp(zpool_get_type(pool->zpool), type))
 			continue;
 		/* if we can't get it, it's about to be destroyed */
 		if (!zswap_pool_get(pool))
@@ -499,12 +487,8 @@ unsigned long zswap_total_pages(void)
 	unsigned long total = 0;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(pool, &zswap_pools, list) {
-		int i;
-
-		for (i = 0; i < ZSWAP_NR_ZPOOLS; i++)
-			total += zpool_get_total_pages(pool->zpools[i]);
-	}
+	list_for_each_entry_rcu(pool, &zswap_pools, list)
+		total += zpool_get_total_pages(pool->zpool);
 	rcu_read_unlock();
 
 	return total;
@@ -809,11 +793,6 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
 	kmem_cache_free(zswap_entry_cache, entry);
 }
 
-static struct zpool *zswap_find_zpool(struct zswap_entry *entry)
-{
-	return entry->pool->zpools[hash_ptr(entry, ilog2(ZSWAP_NR_ZPOOLS))];
-}
-
 /*
  * Carries out the common pattern of freeing and entry's zpool allocation,
  * freeing the entry itself, and decrementing the number of stored pages.
@@ -824,7 +803,7 @@ static void zswap_entry_free(struct zswap_entry *entry)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
 		zswap_lru_del(&zswap_list_lru, entry);
-		zpool_free(zswap_find_zpool(entry), entry->handle);
+	zpool_free(entry->pool->zpool, entry->handle);
 		zswap_pool_put(entry->pool);
 	}
 	if (entry->objcg) {
@@ -950,7 +929,7 @@ static bool zswap_compress(struct folio *folio, struct zswap_entry *entry)
 	if (comp_ret)
 		goto unlock;
 
-	zpool = zswap_find_zpool(entry);
+	zpool = entry->pool->zpool;
 	gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
 	if (zpool_malloc_support_movable(zpool))
 		gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
@@ -979,7 +958,7 @@ unlock:
 
 static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 {
-	struct zpool *zpool = zswap_find_zpool(entry);
+	struct zpool *zpool = entry->pool->zpool;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src;
@@ -1531,7 +1510,7 @@ store_failed:
 	if (!entry->length)
 		atomic_dec(&zswap_same_filled_pages);
 	else {
-		zpool_free(zswap_find_zpool(entry), entry->handle);
+		zpool_free(entry->pool->zpool, entry->handle);
 put_pool:
 		zswap_pool_put(entry->pool);
 	}
@@ -1753,7 +1732,7 @@ static int zswap_setup(void)
 	pool = __zswap_pool_create_fallback();
 	if (pool) {
 		pr_info("loaded using pool %s/%s\n", pool->tfm_name,
-			zpool_get_type(pool->zpools[0]));
+			zpool_get_type(pool->zpool));
 		list_add(&pool->list, &zswap_pools);
 		zswap_has_pool = true;
 		static_branch_enable(&zswap_ever_enabled);