[PATCH v11 22/24] mm: zswap: Allocate pool batching resources if the compressor supports batching.

[Kanchana P Sridhar <kanchana.p.sridhar@intel.com>]

This patch sets up zswap for allocating per-CPU resources optimally for
non-batching and batching compressors.

A new ZSWAP_MAX_BATCH_SIZE constant is defined as 8U, to set an upper
limit on the number of pages in large folios that will be batch
compressed.

As per Herbert's comments in [2] in response to the
crypto_acomp_batch_compress() and crypto_acomp_batch_decompress() API
proposed in [1], this series does not create new crypto_acomp batching
API. Instead, zswap compression batching uses the existing
crypto_acomp_compress() API in combination with the "void *kernel_data"
member added to "struct acomp_req" earlier in this series.

It is up to the compressor to manage multiple requests, as needed, to
accomplish batch parallelism. zswap only needs to allocate the per-CPU
dst buffers according to the batch size supported by the compressor.

A "u8 compr_batch_size" member is added to "struct zswap_pool", as per
Yosry's suggestion. pool->compr_batch_size is set as the minimum of the
compressor's max batch-size and ZSWAP_MAX_BATCH_SIZE. Accordingly, it
proceeds to allocate the necessary compression dst buffers in the
per-CPU acomp_ctx.

Another "u8 batch_size" member is added to "struct zswap_pool" to store
the unit for batching large folio stores: for batching compressors, this
is the pool->compr_batch_size. For non-batching compressors, this is
ZSWAP_MAX_BATCH_SIZE.

zswap does not use more than one dst buffer yet. Follow-up patches will
actually utilize the multiple acomp_ctx buffers for batch
compression/decompression of multiple pages.

Thus, ZSWAP_MAX_BATCH_SIZE limits the amount of extra memory used for
batching. There is a small extra memory overhead of allocating
the acomp_ctx->buffers array for compressors that do not support
batching: On x86_64, the overhead is 1 pointer per-CPU (i.e. 8 bytes).

[1]: https://patchwork.kernel.org/project/linux-mm/patch/20250508194134.28392-11-kanchana.p.sridhar@intel.com/
[2]: https://patchwork.kernel.org/comment/26382610

Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
---
 mm/zswap.c | 82 +++++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 63 insertions(+), 19 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index efd501a7fe294..63a997b999537 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -80,6 +80,9 @@ static bool zswap_pool_reached_full;
 
 #define ZSWAP_PARAM_UNSET ""
 
+/* Limit the batch size to limit per-CPU memory usage for dst buffers. */
+#define ZSWAP_MAX_BATCH_SIZE 8U
+
 static int zswap_setup(void);
 
 /* Enable/disable zswap */
@@ -147,7 +150,7 @@ struct crypto_acomp_ctx {
 	struct crypto_acomp *acomp;
 	struct acomp_req *req;
 	struct crypto_wait wait;
-	u8 *buffer;
+	u8 **buffers;
 	struct mutex mutex;
 	bool is_sleepable;
 };
@@ -166,6 +169,8 @@ struct zswap_pool {
 	struct work_struct release_work;
 	struct hlist_node node;
 	char tfm_name[CRYPTO_MAX_ALG_NAME];
+	u8 compr_batch_size;
+	u8 batch_size;
 };
 
 /* Global LRU lists shared by all zswap pools. */
@@ -258,8 +263,10 @@ static void __zswap_pool_empty(struct percpu_ref *ref);
  *   zswap_cpu_comp_prepare(), not others.
  * - Cleanup acomp_ctx resources on all cores in zswap_pool_destroy().
  */
-static void acomp_ctx_dealloc(struct crypto_acomp_ctx *acomp_ctx)
+static void acomp_ctx_dealloc(struct crypto_acomp_ctx *acomp_ctx, u8 nr_buffers)
 {
+	u8 i;
+
 	if (IS_ERR_OR_NULL(acomp_ctx))
 		return;
 
@@ -269,7 +276,11 @@ static void acomp_ctx_dealloc(struct crypto_acomp_ctx *acomp_ctx)
 	if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 		crypto_free_acomp(acomp_ctx->acomp);
 
-	kfree(acomp_ctx->buffer);
+	if (acomp_ctx->buffers) {
+		for (i = 0; i < nr_buffers; ++i)
+			kfree(acomp_ctx->buffers[i]);
+		kfree(acomp_ctx->buffers);
+	}
 }
 
 static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
@@ -290,6 +301,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 			return NULL;
 	}
 
+	/* Many things rely on the zero-initialization. */
 	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool)
 		return NULL;
@@ -352,13 +364,28 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto ref_fail;
 	INIT_LIST_HEAD(&pool->list);
 
+	/*
+	 * Set the unit of compress batching for large folios, for quick
+	 * retrieval in the zswap_compress() fast path:
+	 * If the compressor is sequential (@pool->compr_batch_size is 1),
+	 * large folios will be compressed in batches of ZSWAP_MAX_BATCH_SIZE
+	 * pages, where each page in the batch is compressed sequentially.
+	 * We see better performance by processing the folio in batches of
+	 * ZSWAP_MAX_BATCH_SIZE, due to cache locality of working set
+	 * structures.
+	 */
+	pool->batch_size = (pool->compr_batch_size > 1) ?
+				pool->compr_batch_size : ZSWAP_MAX_BATCH_SIZE;
+
 	zswap_pool_debug("created", pool);
 
 	return pool;
 
 ref_fail:
 	for_each_possible_cpu(cpu)
-		acomp_ctx_dealloc(per_cpu_ptr(pool->acomp_ctx, cpu));
+		acomp_ctx_dealloc(per_cpu_ptr(pool->acomp_ctx, cpu),
+				  pool->compr_batch_size);
+
 error:
 	if (pool->acomp_ctx)
 		free_percpu(pool->acomp_ctx);
@@ -417,7 +444,8 @@ static void zswap_pool_destroy(struct zswap_pool *pool)
 	zswap_pool_debug("destroying", pool);
 
 	for_each_possible_cpu(cpu)
-		acomp_ctx_dealloc(per_cpu_ptr(pool->acomp_ctx, cpu));
+		acomp_ctx_dealloc(per_cpu_ptr(pool->acomp_ctx, cpu),
+				  pool->compr_batch_size);
 
 	free_percpu(pool->acomp_ctx);
 
@@ -876,6 +904,7 @@ 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);
 	int ret = -ENOMEM;
+	u8 i;
 
 	/*
 	 * The per-CPU pool->acomp_ctx is zero-initialized on allocation.
@@ -888,10 +917,6 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
 		return 0;
 
-	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!acomp_ctx->buffer)
-		return ret;
-
 	acomp_ctx->acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR_OR_NULL(acomp_ctx->acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
@@ -904,17 +929,36 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_ctx->req = acomp_request_alloc(acomp_ctx->acomp);
 	if (IS_ERR_OR_NULL(acomp_ctx->req)) {
 		pr_err("could not alloc crypto acomp_request %s\n",
-		       pool->tfm_name);
+			pool->tfm_name);
 		goto fail;
 	}
 
-	crypto_init_wait(&acomp_ctx->wait);
+	/*
+	 * Allocate up to ZSWAP_MAX_BATCH_SIZE dst buffers if the
+	 * compressor supports batching.
+	 */
+	pool->compr_batch_size = min(ZSWAP_MAX_BATCH_SIZE,
+				     crypto_acomp_batch_size(acomp_ctx->acomp));
+
+	acomp_ctx->buffers = kcalloc_node(pool->compr_batch_size, sizeof(u8 *),
+					  GFP_KERNEL, cpu_to_node(cpu));
+	if (!acomp_ctx->buffers)
+		goto fail;
+
+	for (i = 0; i < pool->compr_batch_size; ++i) {
+		acomp_ctx->buffers[i] = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL,
+						     cpu_to_node(cpu));
+		if (!acomp_ctx->buffers[i])
+			goto fail;
+	}
 
 	/*
 	 * 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
 	 * won't be called, crypto_wait_req() will return without blocking.
 	 */
+	crypto_init_wait(&acomp_ctx->wait);
+
 	acomp_request_set_callback(acomp_ctx->req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
@@ -922,7 +966,7 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	return 0;
 
 fail:
-	acomp_ctx_dealloc(acomp_ctx);
+	acomp_ctx_dealloc(acomp_ctx, pool->compr_batch_size);
 	return ret;
 }
 
@@ -942,7 +986,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 
 	mutex_lock(&acomp_ctx->mutex);
 
-	dst = acomp_ctx->buffer;
+	dst = acomp_ctx->buffers[0];
 	sg_init_table(&input, 1);
 	sg_set_page(&input, page, PAGE_SIZE, 0);
 
@@ -1003,19 +1047,19 @@ static bool zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 	mutex_lock(&acomp_ctx->mutex);
-	obj = zpool_obj_read_begin(zpool, entry->handle, acomp_ctx->buffer);
+	obj = zpool_obj_read_begin(zpool, entry->handle, acomp_ctx->buffers[0]);
 
 	/*
 	 * zpool_obj_read_begin() might return a kmap address of highmem when
-	 * acomp_ctx->buffer is not used.  However, sg_init_one() does not
-	 * handle highmem addresses, so copy the object to acomp_ctx->buffer.
+	 * acomp_ctx->buffers[0] is not used.  However, sg_init_one() does not
+	 * handle highmem addresses, so copy the object to acomp_ctx->buffers[0].
 	 */
 	if (virt_addr_valid(obj)) {
 		src = obj;
 	} else {
-		WARN_ON_ONCE(obj == acomp_ctx->buffer);
-		memcpy(acomp_ctx->buffer, obj, entry->length);
-		src = acomp_ctx->buffer;
+		WARN_ON_ONCE(obj == acomp_ctx->buffers[0]);
+		memcpy(acomp_ctx->buffers[0], obj, entry->length);
+		src = acomp_ctx->buffers[0];
 	}
 
 	sg_init_one(&input, src, entry->length);
-- 
2.27.0