From nobody Sat Dec 27 03:30:49 2025 Received: from out-173.mta0.migadu.com (out-173.mta0.migadu.com [91.218.175.173]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 2749C4FF74 for ; Tue, 26 Dec 2023 15:54:54 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=fail (p=quarantine dis=none) header.from=bytedance.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. From: Chengming Zhou Date: Tue, 26 Dec 2023 15:54:09 +0000 Subject: [PATCH v4 2/6] mm/zswap: reuse dstmem when decompress Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable Message-Id: <20231213-zswap-dstmem-v4-2-f228b059dd89@bytedance.com> References: <20231213-zswap-dstmem-v4-0-f228b059dd89@bytedance.com> In-Reply-To: <20231213-zswap-dstmem-v4-0-f228b059dd89@bytedance.com> To: Andrew Morton , Seth Jennings , Johannes Weiner , Vitaly Wool , Nhat Pham , Chris Li , Yosry Ahmed , Dan Streetman Cc: linux-kernel@vger.kernel.org, Chengming Zhou , linux-mm@kvack.org, Nhat Pham , Yosry Ahmed , Chris Li X-Developer-Signature: v=1; a=ed25519-sha256; t=1703606082; l=4288; i=zhouchengming@bytedance.com; s=20231204; h=from:subject:message-id; bh=ee6CjzVfu3cdsKJFW0DjU4Yqsb6snUyFV2P+WjqVZ2k=; b=/M2fa/388zR47dnBIiQiB32KQcYRHMBqBcSykhWTPfpxspJa5FXo9+SaEpDo1xt/3FIcNllNz cLnkXIGD4JGCQBc8dxPU/SL9D1/IOJXC80mVvuuJ/DxyQRPRAi4uCfR X-Developer-Key: i=zhouchengming@bytedance.com; a=ed25519; pk=xFTmRtMG3vELGJBUiml7OYNdM393WOMv0iWWeQEVVdA= X-Migadu-Flow: FLOW_OUT In the !zpool_can_sleep_mapped() case such as zsmalloc, we need to first copy the entry->handle memory to a temporary memory, which is allocated using kmalloc. Obviously we can reuse the per-compressor dstmem to avoid allocating every time, since it's percpu-compressor and protected in percpu mutex. Reviewed-by: Nhat Pham Reviewed-by: Yosry Ahmed Acked-by: Chris Li (Google) Signed-off-by: Chengming Zhou --- mm/zswap.c | 44 ++++++++++++-------------------------------- 1 file changed, 12 insertions(+), 32 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index 976f278aa507..6b872744e962 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -1417,19 +1417,13 @@ static int zswap_writeback_entry(struct zswap_entry= *entry, struct crypto_acomp_ctx *acomp_ctx; struct zpool *pool =3D zswap_find_zpool(entry); bool page_was_allocated; - u8 *src, *tmp =3D NULL; + u8 *src; unsigned int dlen; int ret; struct writeback_control wbc =3D { .sync_mode =3D WB_SYNC_NONE, }; =20 - if (!zpool_can_sleep_mapped(pool)) { - tmp =3D kmalloc(PAGE_SIZE, GFP_KERNEL); - if (!tmp) - return -ENOMEM; - } - /* try to allocate swap cache page */ mpol =3D get_task_policy(current); page =3D __read_swap_cache_async(swpentry, GFP_KERNEL, mpol, @@ -1465,15 +1459,15 @@ static int zswap_writeback_entry(struct zswap_entry= *entry, /* decompress */ acomp_ctx =3D raw_cpu_ptr(entry->pool->acomp_ctx); dlen =3D PAGE_SIZE; + mutex_lock(acomp_ctx->mutex); =20 src =3D zpool_map_handle(pool, entry->handle, ZPOOL_MM_RO); if (!zpool_can_sleep_mapped(pool)) { - memcpy(tmp, src, entry->length); - src =3D tmp; + memcpy(acomp_ctx->dstmem, src, entry->length); + src =3D acomp_ctx->dstmem; zpool_unmap_handle(pool, entry->handle); } =20 - mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); sg_set_page(&output, page, PAGE_SIZE, 0); @@ -1482,9 +1476,7 @@ static int zswap_writeback_entry(struct zswap_entry *= entry, dlen =3D acomp_ctx->req->dlen; mutex_unlock(acomp_ctx->mutex); =20 - if (!zpool_can_sleep_mapped(pool)) - kfree(tmp); - else + if (zpool_can_sleep_mapped(pool)) zpool_unmap_handle(pool, entry->handle); =20 BUG_ON(ret); @@ -1508,9 +1500,6 @@ static int zswap_writeback_entry(struct zswap_entry *= entry, return ret; =20 fail: - if (!zpool_can_sleep_mapped(pool)) - kfree(tmp); - /* * If we get here because the page is already in swapcache, a * load may be happening concurrently. It is safe and okay to @@ -1771,7 +1760,7 @@ bool zswap_load(struct folio *folio) struct zswap_entry *entry; struct scatterlist input, output; struct crypto_acomp_ctx *acomp_ctx; - u8 *src, *dst, *tmp; + u8 *src, *dst; struct zpool *zpool; unsigned int dlen; bool ret; @@ -1796,26 +1785,19 @@ bool zswap_load(struct folio *folio) } =20 zpool =3D zswap_find_zpool(entry); - if (!zpool_can_sleep_mapped(zpool)) { - tmp =3D kmalloc(entry->length, GFP_KERNEL); - if (!tmp) { - ret =3D false; - goto freeentry; - } - } =20 /* decompress */ dlen =3D PAGE_SIZE; - src =3D zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); + acomp_ctx =3D raw_cpu_ptr(entry->pool->acomp_ctx); + mutex_lock(acomp_ctx->mutex); =20 + src =3D zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO); if (!zpool_can_sleep_mapped(zpool)) { - memcpy(tmp, src, entry->length); - src =3D tmp; + memcpy(acomp_ctx->dstmem, src, entry->length); + src =3D acomp_ctx->dstmem; zpool_unmap_handle(zpool, entry->handle); } =20 - acomp_ctx =3D raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(acomp_ctx->mutex); sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); sg_set_page(&output, page, PAGE_SIZE, 0); @@ -1826,15 +1808,13 @@ bool zswap_load(struct folio *folio) =20 if (zpool_can_sleep_mapped(zpool)) zpool_unmap_handle(zpool, entry->handle); - else - kfree(tmp); =20 ret =3D true; stats: count_vm_event(ZSWPIN); if (entry->objcg) count_objcg_event(entry->objcg, ZSWPIN); -freeentry: + spin_lock(&tree->lock); if (ret && zswap_exclusive_loads_enabled) { zswap_invalidate_entry(tree, entry); --=20 b4 0.10.1