Received-SPF: pass (google.com: domain of linux-kernel+bounces-43756-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Johannes Weiner <hannes@cmpxchg.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Nhat Pham <nphamcs@gmail.com>,
	Yosry Ahmed <yosryahmed@google.com>,
	Chengming Zhou <zhouchengming@bytedance.com>,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH 17/20] mm: zswap: function ordering: compress & decompress functions
Date: Mon, 29 Jan 2024 20:36:53 -0500
Message-ID: <20240130014208.565554-18-hannes@cmpxchg.org>
In-Reply-To: <20240130014208.565554-1-hannes@cmpxchg.org>
References: <20240130014208.565554-1-hannes@cmpxchg.org>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

Writeback needs to decompress. Move the (de)compression API above what
will be the consolidated shrinking/writeback code.

Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
---
 mm/zswap.c | 207 +++++++++++++++++++++++++++--------------------------
 1 file changed, 105 insertions(+), 102 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index 80adc2f7d1a2..17356b2e35c2 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -992,6 +992,111 @@ static void zswap_invalidate_entry(struct zswap_tree *tree,
 		zswap_entry_put(entry);
 }
 
+/*********************************
+* compressed storage functions
+**********************************/
+static bool zswap_compress(struct folio *folio, struct zswap_entry *entry)
+{
+	struct crypto_acomp_ctx *acomp_ctx;
+	struct scatterlist input, output;
+	unsigned int dlen = PAGE_SIZE;
+	unsigned long handle;
+	struct zpool *zpool;
+	char *buf;
+	gfp_t gfp;
+	int ret;
+	u8 *dst;
+
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+
+	mutex_lock(&acomp_ctx->mutex);
+
+	dst = acomp_ctx->buffer;
+	sg_init_table(&input, 1);
+	sg_set_page(&input, &folio->page, PAGE_SIZE, 0);
+
+	/*
+	 * We need PAGE_SIZE * 2 here since there maybe over-compression case,
+	 * and hardware-accelerators may won't check the dst buffer size, so
+	 * giving the dst buffer with enough length to avoid buffer overflow.
+	 */
+	sg_init_one(&output, dst, PAGE_SIZE * 2);
+	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
+
+	/*
+	 * it maybe looks a little bit silly that we send an asynchronous request,
+	 * then wait for its completion synchronously. This makes the process look
+	 * synchronous in fact.
+	 * Theoretically, acomp supports users send multiple acomp requests in one
+	 * acomp instance, then get those requests done simultaneously. but in this
+	 * case, zswap actually does store and load page by page, there is no
+	 * existing method to send the second page before the first page is done
+	 * in one thread doing zwap.
+	 * but in different threads running on different cpu, we have different
+	 * acomp instance, so multiple threads can do (de)compression in parallel.
+	 */
+	ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait);
+	dlen = acomp_ctx->req->dlen;
+	if (ret) {
+		zswap_reject_compress_fail++;
+		goto unlock;
+	}
+
+	zpool = zswap_find_zpool(entry);
+	gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
+	if (zpool_malloc_support_movable(zpool))
+		gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
+	ret = zpool_malloc(zpool, dlen, gfp, &handle);
+	if (ret == -ENOSPC) {
+		zswap_reject_compress_poor++;
+		goto unlock;
+	}
+	if (ret) {
+		zswap_reject_alloc_fail++;
+		goto unlock;
+	}
+
+	buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO);
+	memcpy(buf, dst, dlen);
+	zpool_unmap_handle(zpool, handle);
+
+	entry->handle = handle;
+	entry->length = dlen;
+
+unlock:
+	mutex_unlock(&acomp_ctx->mutex);
+	return ret == 0;
+}
+
+static void zswap_decompress(struct zswap_entry *entry, struct page *page)
+{
+	struct zpool *zpool = zswap_find_zpool(entry);
+	struct scatterlist input, output;
+	struct crypto_acomp_ctx *acomp_ctx;
+	u8 *src;
+
+	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	mutex_lock(&acomp_ctx->mutex);
+
+	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
+	if (!zpool_can_sleep_mapped(zpool)) {
+		memcpy(acomp_ctx->buffer, src, entry->length);
+		src = acomp_ctx->buffer;
+		zpool_unmap_handle(zpool, entry->handle);
+	}
+
+	sg_init_one(&input, src, entry->length);
+	sg_init_table(&output, 1);
+	sg_set_page(&output, page, PAGE_SIZE, 0);
+	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 (zpool_can_sleep_mapped(zpool))
+		zpool_unmap_handle(zpool, entry->handle);
+}
+
 /*********************************
 * shrinker functions
 **********************************/
@@ -1317,108 +1422,6 @@ static void shrink_worker(struct work_struct *w)
 	zswap_pool_put(pool);
 }
 
-static bool zswap_compress(struct folio *folio, struct zswap_entry *entry)
-{
-	struct crypto_acomp_ctx *acomp_ctx;
-	struct scatterlist input, output;
-	unsigned int dlen = PAGE_SIZE;
-	unsigned long handle;
-	struct zpool *zpool;
-	char *buf;
-	gfp_t gfp;
-	int ret;
-	u8 *dst;
-
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-
-	mutex_lock(&acomp_ctx->mutex);
-
-	dst = acomp_ctx->buffer;
-	sg_init_table(&input, 1);
-	sg_set_page(&input, &folio->page, PAGE_SIZE, 0);
-
-	/*
-	 * We need PAGE_SIZE * 2 here since there maybe over-compression case,
-	 * and hardware-accelerators may won't check the dst buffer size, so
-	 * giving the dst buffer with enough length to avoid buffer overflow.
-	 */
-	sg_init_one(&output, dst, PAGE_SIZE * 2);
-	acomp_request_set_params(acomp_ctx->req, &input, &output, PAGE_SIZE, dlen);
-
-	/*
-	 * it maybe looks a little bit silly that we send an asynchronous request,
-	 * then wait for its completion synchronously. This makes the process look
-	 * synchronous in fact.
-	 * Theoretically, acomp supports users send multiple acomp requests in one
-	 * acomp instance, then get those requests done simultaneously. but in this
-	 * case, zswap actually does store and load page by page, there is no
-	 * existing method to send the second page before the first page is done
-	 * in one thread doing zwap.
-	 * but in different threads running on different cpu, we have different
-	 * acomp instance, so multiple threads can do (de)compression in parallel.
-	 */
-	ret = crypto_wait_req(crypto_acomp_compress(acomp_ctx->req), &acomp_ctx->wait);
-	dlen = acomp_ctx->req->dlen;
-	if (ret) {
-		zswap_reject_compress_fail++;
-		goto unlock;
-	}
-
-	zpool = zswap_find_zpool(entry);
-	gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
-	if (zpool_malloc_support_movable(zpool))
-		gfp |= __GFP_HIGHMEM | __GFP_MOVABLE;
-	ret = zpool_malloc(zpool, dlen, gfp, &handle);
-	if (ret == -ENOSPC) {
-		zswap_reject_compress_poor++;
-		goto unlock;
-	}
-	if (ret) {
-		zswap_reject_alloc_fail++;
-		goto unlock;
-	}
-
-	buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO);
-	memcpy(buf, dst, dlen);
-	zpool_unmap_handle(zpool, handle);
-
-	entry->handle = handle;
-	entry->length = dlen;
-
-unlock:
-	mutex_unlock(&acomp_ctx->mutex);
-	return ret == 0;
-}
-
-static void zswap_decompress(struct zswap_entry *entry, struct page *page)
-{
-	struct zpool *zpool = zswap_find_zpool(entry);
-	struct scatterlist input, output;
-	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src;
-
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(&acomp_ctx->mutex);
-
-	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
-	if (!zpool_can_sleep_mapped(zpool)) {
-		memcpy(acomp_ctx->buffer, src, entry->length);
-		src = acomp_ctx->buffer;
-		zpool_unmap_handle(zpool, entry->handle);
-	}
-
-	sg_init_one(&input, src, entry->length);
-	sg_init_table(&output, 1);
-	sg_set_page(&output, page, PAGE_SIZE, 0);
-	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 (zpool_can_sleep_mapped(zpool))
-		zpool_unmap_handle(zpool, entry->handle);
-}
-
 /*********************************
 * writeback code
 **********************************/
-- 
2.43.0