1 files changed, 81 insertions, 48 deletions
diff --git a/mm/zswap.c b/mm/zswap.c
index f6316b66fb23..23365e76a3ce 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -43,7 +43,7 @@
 * statistics
 **********************************/
 /* The number of compressed pages currently stored in zswap */
-atomic_long_t zswap_stored_pages = ATOMIC_INIT(0);
+atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0);
 
 /*
  * The statistics below are not protected from concurrent access for
@@ -251,7 +251,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
-	int ret;
+	int ret, cpu;
 
 	if (!zswap_has_pool) {
 		/* if either are unset, pool initialization failed, and we
@@ -285,6 +285,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
+	for_each_possible_cpu(cpu)
+		mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex);
+
 	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
 				       &pool->node);
 	if (ret)
@@ -817,36 +820,41 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
-	struct crypto_acomp *acomp;
-	struct acomp_req *req;
+	struct crypto_acomp *acomp = NULL;
+	struct acomp_req *req = NULL;
+	u8 *buffer = NULL;
 	int ret;
 
-	mutex_init(&acomp_ctx->mutex);
-
-	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!acomp_ctx->buffer)
-		return -ENOMEM;
+	buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!buffer) {
+		ret = -ENOMEM;
+		goto fail;
+	}
 
 	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR(acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
 				pool->tfm_name, PTR_ERR(acomp));
 		ret = PTR_ERR(acomp);
-		goto acomp_fail;
+		goto fail;
 	}
-	acomp_ctx->acomp = acomp;
-	acomp_ctx->is_sleepable = acomp_is_async(acomp);
 
-	req = acomp_request_alloc(acomp_ctx->acomp);
+	req = acomp_request_alloc(acomp);
 	if (!req) {
 		pr_err("could not alloc crypto acomp_request %s\n",
 		       pool->tfm_name);
 		ret = -ENOMEM;
-		goto req_fail;
+		goto fail;
 	}
-	acomp_ctx->req = req;
 
+	/*
+	 * Only hold the mutex after completing allocations, otherwise we may
+	 * recurse into zswap through reclaim and attempt to hold the mutex
+	 * again resulting in a deadlock.
+	 */
+	mutex_lock(&acomp_ctx->mutex);
 	crypto_init_wait(&acomp_ctx->wait);
+
 	/*
 	 * if the backend of acomp is async zip, crypto_req_done() will wakeup
 	 * crypto_wait_req(); if the backend of acomp is scomp, the callback
@@ -855,12 +863,17 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
+	acomp_ctx->buffer = buffer;
+	acomp_ctx->acomp = acomp;
+	acomp_ctx->is_sleepable = acomp_is_async(acomp);
+	acomp_ctx->req = req;
+	mutex_unlock(&acomp_ctx->mutex);
 	return 0;
 
-req_fail:
-	crypto_free_acomp(acomp_ctx->acomp);
-acomp_fail:
-	kfree(acomp_ctx->buffer);
+fail:
+	if (acomp)
+		crypto_free_acomp(acomp);
+	kfree(buffer);
 	return ret;
 }
 
@@ -869,17 +882,45 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
 
+	mutex_lock(&acomp_ctx->mutex);
 	if (!IS_ERR_OR_NULL(acomp_ctx)) {
 		if (!IS_ERR_OR_NULL(acomp_ctx->req))
 			acomp_request_free(acomp_ctx->req);
+		acomp_ctx->req = NULL;
 		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 			crypto_free_acomp(acomp_ctx->acomp);
 		kfree(acomp_ctx->buffer);
 	}
+	mutex_unlock(&acomp_ctx->mutex);
 
 	return 0;
 }
 
+static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool)
+{
+	struct crypto_acomp_ctx *acomp_ctx;
+
+	for (;;) {
+		acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
+		mutex_lock(&acomp_ctx->mutex);
+		if (likely(acomp_ctx->req))
+			return acomp_ctx;
+		/*
+		 * It is possible that we were migrated to a different CPU after
+		 * getting the per-CPU ctx but before the mutex was acquired. If
+		 * the old CPU got offlined, zswap_cpu_comp_dead() could have
+		 * already freed ctx->req (among other things) and set it to
+		 * NULL. Just try again on the new CPU that we ended up on.
+		 */
+		mutex_unlock(&acomp_ctx->mutex);
+	}
+}
+
+static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx)
+{
+	mutex_unlock(&acomp_ctx->mutex);
+}
+
 static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 			   struct zswap_pool *pool)
 {
@@ -893,10 +934,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 	gfp_t gfp;
 	u8 *dst;
 
-	acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
-
-	mutex_lock(&acomp_ctx->mutex);
-
+	acomp_ctx = acomp_ctx_get_cpu_lock(pool);
 	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
 	sg_set_page(&input, page, PAGE_SIZE, 0);
@@ -949,7 +987,7 @@ unlock:
 	else if (alloc_ret)
 		zswap_reject_alloc_fail++;
 
-	mutex_unlock(&acomp_ctx->mutex);
+	acomp_ctx_put_unlock(acomp_ctx);
 	return comp_ret == 0 && alloc_ret == 0;
 }
 
@@ -960,9 +998,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src;
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(&acomp_ctx->mutex);
-
+	acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool);
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	/*
 	 * If zpool_map_handle is atomic, we cannot reliably utilize its mapped buffer
@@ -986,10 +1022,10 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
 	BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
-	mutex_unlock(&acomp_ctx->mutex);
 
 	if (src != acomp_ctx->buffer)
 		zpool_unmap_handle(zpool, entry->handle);
+	acomp_ctx_put_unlock(acomp_ctx);
 }
 
 /*********************************
@@ -1156,7 +1192,7 @@ static enum lru_status shrink_memcg_cb(struct list_head *item, struct list_lru_o
 
 	/*
 	 * It's safe to drop the lock here because we return either
-	 * LRU_REMOVED_RETRY or LRU_RETRY.
+	 * LRU_REMOVED_RETRY, LRU_RETRY or LRU_STOP.
 	 */
 	spin_unlock(&l->lock);
 
@@ -1409,9 +1445,9 @@ resched:
 * main API
 **********************************/
 
-static ssize_t zswap_store_page(struct page *page,
-				struct obj_cgroup *objcg,
-				struct zswap_pool *pool)
+static bool zswap_store_page(struct page *page,
+			     struct obj_cgroup *objcg,
+			     struct zswap_pool *pool)
 {
 	swp_entry_t page_swpentry = page_swap_entry(page);
 	struct zswap_entry *entry, *old;
@@ -1420,7 +1456,7 @@ static ssize_t zswap_store_page(struct page *page,
 	entry = zswap_entry_cache_alloc(GFP_KERNEL, page_to_nid(page));
 	if (!entry) {
 		zswap_reject_kmemcache_fail++;
-		return -EINVAL;
+		return false;
 	}
 
 	if (!zswap_compress(page, entry, pool))
@@ -1447,13 +1483,17 @@ static ssize_t zswap_store_page(struct page *page,
 
 	/*
 	 * The entry is successfully compressed and stored in the tree, there is
-	 * no further possibility of failure. Grab refs to the pool and objcg.
-	 * These refs will be dropped by zswap_entry_free() when the entry is
-	 * removed from the tree.
+	 * no further possibility of failure. Grab refs to the pool and objcg,
+	 * charge zswap memory, and increment zswap_stored_pages.
+	 * The opposite actions will be performed by zswap_entry_free()
+	 * when the entry is removed from the tree.
 	 */
 	zswap_pool_get(pool);
-	if (objcg)
+	if (objcg) {
 		obj_cgroup_get(objcg);
+		obj_cgroup_charge_zswap(objcg, entry->length);
+	}
+	atomic_long_inc(&zswap_stored_pages);
 
 	/*
 	 * We finish initializing the entry while it's already in xarray.
@@ -1474,13 +1514,13 @@ static ssize_t zswap_store_page(struct page *page,
 		zswap_lru_add(&zswap_list_lru, entry);
 	}
 
-	return entry->length;
+	return true;
 
 store_failed:
 	zpool_free(pool->zpool, entry->handle);
 compress_failed:
 	zswap_entry_cache_free(entry);
-	return -EINVAL;
+	return false;
 }
 
 bool zswap_store(struct folio *folio)
@@ -1490,7 +1530,6 @@ bool zswap_store(struct folio *folio)
 	struct obj_cgroup *objcg = NULL;
 	struct mem_cgroup *memcg = NULL;
 	struct zswap_pool *pool;
-	size_t compressed_bytes = 0;
 	bool ret = false;
 	long index;
 
@@ -1528,20 +1567,14 @@ bool zswap_store(struct folio *folio)
 
 	for (index = 0; index < nr_pages; ++index) {
 		struct page *page = folio_page(folio, index);
-		ssize_t bytes;
 
-		bytes = zswap_store_page(page, objcg, pool);
-		if (bytes < 0)
+		if (!zswap_store_page(page, objcg, pool))
 			goto put_pool;
-		compressed_bytes += bytes;
 	}
 
-	if (objcg) {
-		obj_cgroup_charge_zswap(objcg, compressed_bytes);
+	if (objcg)
 		count_objcg_events(objcg, ZSWPOUT, nr_pages);
-	}
 
-	atomic_long_add(nr_pages, &zswap_stored_pages);
 	count_vm_events(ZSWPOUT, nr_pages);
 
 	ret = true;