Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Domenico Cerasuolo <cerasuolodomenico@gmail.com>
To:     vitaly.wool@konsulko.com, minchan@kernel.org,
        senozhatsky@chromium.org, yosryahmed@google.com, linux-mm@kvack.org
Cc:     ddstreet@ieee.org, sjenning@redhat.com, nphamcs@gmail.com,
        hannes@cmpxchg.org, akpm@linux-foundation.org,
        linux-kernel@vger.kernel.org, kernel-team@meta.com,
        Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Subject: [PATCH v3 6/7] mm: zswap: simplify writeback function
Date:   Mon, 12 Jun 2023 11:38:14 +0200
Message-Id: <20230612093815.133504-7-cerasuolodomenico@gmail.com>
In-Reply-To: <20230612093815.133504-1-cerasuolodomenico@gmail.com>
References: <20230612093815.133504-1-cerasuolodomenico@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

zswap_writeback_entry() used to be a callback for the backends, which
don't know about struct zswap_entry.

Now that the only user is the generic zswap LRU reclaimer, it can be
simplified: pass the pinned zswap_entry directly, and consolidate the
refcount management in the shrink function.

Tested-by: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
---
 mm/zswap.c | 70 +++++++++++++++---------------------------------------
 1 file changed, 19 insertions(+), 51 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index a4f8c20e161b..3a6b07a19262 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -254,7 +254,8 @@ static bool zswap_has_pool;
 	pr_debug("%s pool %s/%s\n", msg, (p)->tfm_name,		\
 		 zpool_get_type((p)->zpool))
 
-static int zswap_writeback_entry(struct zpool *pool, unsigned long handle);
+static int zswap_writeback_entry(struct zswap_entry *entry, struct zswap_header *zhdr,
+				 struct zswap_tree *tree);
 static int zswap_pool_get(struct zswap_pool *pool);
 static void zswap_pool_put(struct zswap_pool *pool);
 
@@ -635,7 +636,7 @@ static int zswap_reclaim_entry(struct zswap_pool *pool)
 	zswap_entry_get(entry);
 	spin_unlock(&tree->lock);
 
-	ret = zswap_writeback_entry(pool->zpool, entry->handle);
+	ret = zswap_writeback_entry(entry, zhdr, tree);
 
 	spin_lock(&tree->lock);
 	if (ret) {
@@ -643,8 +644,17 @@ static int zswap_reclaim_entry(struct zswap_pool *pool)
 		spin_lock(&pool->lru_lock);
 		list_move(&entry->lru, &pool->lru);
 		spin_unlock(&pool->lru_lock);
+		goto put_unlock;
 	}
 
+	/* Check for invalidate() race */
+	if (entry != zswap_rb_search(&tree->rbroot, swpoffset))
+		goto put_unlock;
+
+	/* Drop base reference */
+	zswap_entry_put(tree, entry);
+
+put_unlock:
 	/* Drop local reference */
 	zswap_entry_put(tree, entry);
 unlock:
@@ -1045,16 +1055,14 @@ static int zswap_get_swap_cache_page(swp_entry_t entry,
  * the swap cache, the compressed version stored by zswap can be
  * freed.
  */
-static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
+static int zswap_writeback_entry(struct zswap_entry *entry, struct zswap_header *zhdr,
+				 struct zswap_tree *tree)
 {
-	struct zswap_header *zhdr;
-	swp_entry_t swpentry;
-	struct zswap_tree *tree;
-	pgoff_t offset;
-	struct zswap_entry *entry;
+	swp_entry_t swpentry = zhdr->swpentry;
 	struct page *page;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
+	struct zpool *pool = entry->pool->zpool;
 
 	u8 *src, *tmp = NULL;
 	unsigned int dlen;
@@ -1069,25 +1077,6 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 			return -ENOMEM;
 	}
 
-	/* extract swpentry from data */
-	zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
-	swpentry = zhdr->swpentry; /* here */
-	tree = zswap_trees[swp_type(swpentry)];
-	offset = swp_offset(swpentry);
-	zpool_unmap_handle(pool, handle);
-
-	/* find and ref zswap entry */
-	spin_lock(&tree->lock);
-	entry = zswap_entry_find_get(&tree->rbroot, offset);
-	if (!entry) {
-		/* entry was invalidated */
-		spin_unlock(&tree->lock);
-		kfree(tmp);
-		return 0;
-	}
-	spin_unlock(&tree->lock);
-	BUG_ON(offset != entry->offset);
-
 	/* try to allocate swap cache page */
 	switch (zswap_get_swap_cache_page(swpentry, &page)) {
 	case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
@@ -1121,12 +1110,12 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 		dlen = PAGE_SIZE;
 
-		zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
+		zhdr = zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO);
 		src = (u8 *)zhdr + sizeof(struct zswap_header);
 		if (!zpool_can_sleep_mapped(pool)) {
 			memcpy(tmp, src, entry->length);
 			src = tmp;
-			zpool_unmap_handle(pool, handle);
+			zpool_unmap_handle(pool, entry->handle);
 		}
 
 		mutex_lock(acomp_ctx->mutex);
@@ -1141,7 +1130,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		if (!zpool_can_sleep_mapped(pool))
 			kfree(tmp);
 		else
-			zpool_unmap_handle(pool, handle);
+			zpool_unmap_handle(pool, entry->handle);
 
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
@@ -1158,23 +1147,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	put_page(page);
 	zswap_written_back_pages++;
 
-	spin_lock(&tree->lock);
-	/* drop local reference */
-	zswap_entry_put(tree, entry);
-
-	/*
-	* There are two possible situations for entry here:
-	* (1) refcount is 1(normal case),  entry is valid and on the tree
-	* (2) refcount is 0, entry is freed and not on the tree
-	*     because invalidate happened during writeback
-	*  search the tree and free the entry if find entry
-	*/
-	if (entry == zswap_rb_search(&tree->rbroot, offset))
-		zswap_entry_put(tree, entry);
-	spin_unlock(&tree->lock);
-
 	return ret;
-
 fail:
 	if (!zpool_can_sleep_mapped(pool))
 		kfree(tmp);
@@ -1183,13 +1156,8 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	* if we get here due to ZSWAP_SWAPCACHE_EXIST
 	* a load may be happening concurrently.
 	* it is safe and okay to not free the entry.
-	* if we free the entry in the following put
 	* it is also okay to return !0
 	*/
-	spin_lock(&tree->lock);
-	zswap_entry_put(tree, entry);
-	spin_unlock(&tree->lock);
-
 	return ret;
 }
 
-- 
2.34.1