[PATCH v6 3/3] mm/zswap: reference the pool by id to shrink struct zswap_entry

[Jianyue Wu]

struct zswap_entry is one allocation per stored page, so its size is
pure overhead. It currently embeds an 8-byte pool pointer, even though
the live pools now sit in an allocating xarray keyed by a small integer
id that fits in a u8.

Replace the per-entry pool pointer with that u8 id and resolve it
through the xarray with xa_load(). xa_load() does its own RCU-protected
lookup, so the caller needs no rcu_read_lock() section of its own. The
resolved pool stays valid because a live entry pins it via percpu_ref
(taken in zswap_store_page()), so its id cannot be reused. A live entry
never uses the reserved id 0, so a zeroed id resolves to NULL and trips
a WARN rather than aliasing a live pool.

The u8 fits in the padding after the bool referenced field, shrinking
the entry from 56 to 48 bytes on 64-bit. This raises objs_per_slab from
73 to 85 and saves about 2MiB of metadata per 1GiB of data held in
zswap.

Suggested-by: Chris Li <chrisl@xxxxxxxxxx>
Signed-off-by: Jianyue Wu <wujianyue000@xxxxxxxxx>
---
 mm/zswap.c | 37 ++++++++++++++++++++++++++++++-------
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index 86db023d63ed..253eebb971b9 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -194,7 +194,7 @@ static struct shrinker *zswap_shrinker;
  *              writeback logic. The entry is only reclaimed by the writeback
  *              logic if referenced is unset. See comments in the shrinker
  *              section for context.
- * pool - the zswap_pool the entry's data is in
+ * pool_idx - id of the zswap_pool that the entry's data is in.
  * handle - zsmalloc allocation handle that stores the compressed page data
  * objcg - the obj_cgroup that the compressed memory is charged to
  * lru - handle to the pool's lru used to evict pages.
@@ -203,12 +203,22 @@ struct zswap_entry {
 	swp_entry_t swpentry;
 	unsigned int length;
 	bool referenced;
-	struct zswap_pool *pool;
+	u8 pool_idx;
 	unsigned long handle;
 	struct obj_cgroup *objcg;
 	struct list_head lru;
 };
 
+/*
+ * No RCU section is needed around the returned pointer: a stored entry pins
+ * its pool via percpu_ref (taken in zswap_store_page()), so the id cannot be
+ * reused under us.  Callers WARN and handle a NULL from a corrupt pool_idx.
+ */
+static struct zswap_pool *zswap_entry_pool(struct zswap_entry *entry)
+{
+	return xa_load(&zswap_pools, entry->pool_idx);
+}
+
 static struct xarray *zswap_trees[MAX_SWAPFILES];
 static unsigned int nr_zswap_trees[MAX_SWAPFILES];
 
@@ -759,9 +769,13 @@ static void zswap_entry_cache_free(struct zswap_entry *entry)
  */
 static void zswap_entry_free(struct zswap_entry *entry)
 {
+	struct zswap_pool *pool = zswap_entry_pool(entry);
+
 	zswap_lru_del(entry);
-	zs_free(entry->pool->zs_pool, entry->handle);
-	zswap_pool_put(entry->pool);
+	if (!WARN_ON_ONCE(!pool)) {
+		zs_free(pool->zs_pool, entry->handle);
+		zswap_pool_put(pool);
+	}
 	if (entry->objcg) {
 		obj_cgroup_uncharge_zswap(entry->objcg, entry->length);
 		obj_cgroup_put(entry->objcg);
@@ -918,12 +932,15 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 
 static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 {
-	struct zswap_pool *pool = entry->pool;
+	struct zswap_pool *pool = zswap_entry_pool(entry);
 	struct scatterlist input[2]; /* zsmalloc returns an SG list 1-2 entries */
 	struct scatterlist output;
 	struct crypto_acomp_ctx *acomp_ctx;
 	int ret = 0, dlen;
 
+	if (WARN_ON_ONCE(!pool))
+		return false;
+
 	acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
 	mutex_lock(&acomp_ctx->mutex);
 	zs_obj_read_sg_begin(pool->zs_pool, entry->handle, input, entry->length);
@@ -959,7 +976,7 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 	pr_alert_ratelimited("Decompression error from zswap (%d:%lu %s %u->%d)\n",
 						swp_type(entry->swpentry),
 						swp_offset(entry->swpentry),
-						entry->pool->tfm_name,
+						pool->tfm_name,
 						entry->length, dlen);
 	return false;
 }
@@ -1417,6 +1434,13 @@ static bool zswap_store_page(struct page *page,
 	if (!zswap_compress(page, entry, pool))
 		goto compress_failed;
 
+	/*
+	 * Set pool_idx before the xa_store() below publishes the entry, or a
+	 * concurrent reader could resolve a stale pool_idx left by slab reuse
+	 * to an unrelated live pool.
+	 */
+	entry->pool_idx = pool->idx;
+
 	old = xa_store(swap_zswap_tree(page_swpentry),
 		       swp_offset(page_swpentry),
 		       entry, GFP_KERNEL);
@@ -1462,7 +1486,6 @@ static bool zswap_store_page(struct page *page,
 	 *    The publishing order matters to prevent writeback from seeing
 	 *    an incoherent entry.
 	 */
-	entry->pool = pool;
 	entry->swpentry = page_swpentry;
 	entry->objcg = objcg;
 	entry->referenced = true;

-- 
2.43.0