From nobody Wed Dec 17 01:12:00 2025 Received: from szxga05-in.huawei.com (szxga05-in.huawei.com [45.249.212.191]) (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 2E8502ED086 for ; Tue, 6 May 2025 03:01:11 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.191 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746500474; cv=none; b=NDenJDJgjGMRWGZ71xPM7p43Rj5yI5MqFfYhC2xTrltx12q4zLPCmXW3rLMojoPD0OWwMp1gI9+bqZDc/QYncbUup0QLO47lCr2PdX0rUmaoXZ7JexVABSirEstBPpBsMke3AaVS7Zo7qTIbPc4KF2Amps2MFBDN/Wh8IePUGLY= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746500474; c=relaxed/simple; bh=SqtyE3TdPNtRYgMPDp/JP8k0KsJ9GlwxkJZKGVuGB5s=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=py0RbLJG7Ul1O3T+K+PMWeRzV9k0s/HNNFvgofUZzzXYEZmbOAaXuySMElHHqFxBEdJaV8OCt3HUCop8wLu9LfDbuB0O7XxBxeCfDq2GAaIyp57cej3hREsIA1iNdR9kESgaGGX96SL91GxF2biF5Wg2T1mhUahsRv6yL7JUB8o= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com; spf=pass smtp.mailfrom=huawei.com; arc=none smtp.client-ip=45.249.212.191 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=quarantine dis=none) header.from=huawei.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=huawei.com Received: from mail.maildlp.com (unknown [172.19.163.44]) by szxga05-in.huawei.com (SkyGuard) with ESMTP id 4Zs34y2bH5z1R7fQ; Tue, 6 May 2025 10:58:58 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id B7F041401E9; Tue, 6 May 2025 11:01:03 +0800 (CST) Received: from localhost.huawei.com (10.90.30.45) by kwepemj200003.china.huawei.com (7.202.194.15) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1544.11; Tue, 6 May 2025 11:01:03 +0800 From: Qinxin Xia To: , CC: , , , , , , , Subject: [PATCH v2 3/4] dma-mapping: benchmark: add support for dma_map_sg Date: Tue, 6 May 2025 11:00:59 +0800 Message-ID: <20250506030100.394376-4-xiaqinxin@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20250506030100.394376-1-xiaqinxin@huawei.com> References: <20250506030100.394376-1-xiaqinxin@huawei.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-ClientProxiedBy: dggems705-chm.china.huawei.com (10.3.19.182) To kwepemj200003.china.huawei.com (7.202.194.15) Content-Type: text/plain; charset="utf-8" Support for dma scatter-gather mapping and is intended for testing mapping performance. It achieves by introducing the dma_sg_map_param structure and related functions, which enable the implementation of scatter-gather mapping preparation, mapping, and unmapping operations. Additionally, the dma_map_benchmark_ops array is updated to include operations for scatter-gather mapping. This commit aims to provide a wider range of mapping performance test to cater to different scenarios. Signed-off-by: Qinxin Xia --- include/linux/map_benchmark.h | 43 ++++++++++---- kernel/dma/map_benchmark.c | 102 ++++++++++++++++++++++++++++++++++ 2 files changed, 133 insertions(+), 12 deletions(-) diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 5294dfd1870f..bf8c9ade43fd 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -17,22 +17,41 @@ =20 enum { DMA_MAP_SINGLE_MODE, + DMA_MAP_SG_MODE, DMA_MAP_MODE_MAX }; =20 +/** + * struct map_benchmark - Benchmarking data for DMA mapping operations. + * @avg_map_100ns: Average map latency in 100ns. + * @map_stddev: Standard deviation of map latency. + * @avg_unmap_100ns: Average unmap latency in 100ns. + * @unmap_stddev: Standard deviation of unmap latency. + * @threads: Number of threads performing map/unmap operations in parallel. + * @seconds: Duration of the test in seconds. + * @node: NUMA node on which this benchmark will run. + * @dma_bits: DMA addressing capability. + * @dma_dir: DMA data direction. + * @dma_trans_ns: Time for DMA transmission in ns. + * @granule: Number of PAGE_SIZE units to map/unmap at once. + In SG mode, this represents the number of scatterlist entries. + In single mode, this represents the total size of the mapping. + * @map_mode: Mode of DMA mapping. + * @expansion: Reserved for future use. + */ struct map_benchmark { - __u64 avg_map_100ns; /* average map latency in 100ns */ - __u64 map_stddev; /* standard deviation of map latency */ - __u64 avg_unmap_100ns; /* as above */ + __u64 avg_map_100ns; + __u64 map_stddev; + __u64 avg_unmap_100ns; __u64 unmap_stddev; - __u32 threads; /* how many threads will do map/unmap in parallel */ - __u32 seconds; /* how long the test will last */ - __s32 node; /* which numa node this benchmark will run on */ - __u32 dma_bits; /* DMA addressing capability */ - __u32 dma_dir; /* DMA data direction */ - __u32 dma_trans_ns; /* time for DMA transmission in ns */ - __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ - __u8 map_mode; /* the mode of dma map */ - __u8 expansion[75]; /* For future use */ + __u32 threads; + __u32 seconds; + __s32 node; + __u32 dma_bits; + __u32 dma_dir; + __u32 dma_trans_ns; + __u32 granule; + __u8 map_mode; + __u8 expansion[75]; }; #endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index f04973eba1d8..72cd2c5f839e 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -17,6 +17,7 @@ #include #include #include +#include #include #include =20 @@ -110,8 +111,109 @@ static struct map_benchmark_ops dma_single_map_benchm= ark_ops =3D { .do_unmap =3D dma_single_map_benchmark_do_unmap, }; =20 +struct dma_sg_map_param { + struct sg_table sgt; + struct device *dev; + void **buf; + u32 npages; + u32 dma_dir; +}; + +static void *dma_sg_map_benchmark_prepare(struct map_benchmark_data *map) +{ + struct scatterlist *sg; + int i =3D 0; + + struct dma_sg_map_param *mparam __free(kfree) =3D kzalloc(sizeof(*mparam)= , GFP_KERNEL); + if (!mparam) + return NULL; + + /* + * Set the number of scatterlist entries based on the granule. + * In SG mode, 'granule' represents the number of scatterlist entries. + * Each scatterlist entry corresponds to a single page. + */ + mparam->npages =3D map->bparam.granule; + mparam->dma_dir =3D map->bparam.dma_dir; + mparam->dev =3D map->dev; + mparam->buf =3D kmalloc_array(mparam->npages, sizeof(*mparam->buf), + GFP_KERNEL); + if (!mparam->buf) + goto out; + + if (sg_alloc_table(&mparam->sgt, mparam->npages, GFP_KERNEL)) + goto free_buf; + + for_each_sgtable_sg(&mparam->sgt, sg, i) { + mparam->buf[i] =3D (void *)__get_free_page(GFP_KERNEL); + if (!mparam->buf[i]) + goto free_page; + + if (mparam->dma_dir !=3D DMA_FROM_DEVICE) + memset(mparam->buf[i], 0x66, PAGE_SIZE); + + sg_set_buf(sg, mparam->buf[i], PAGE_SIZE); + } + + return_ptr(mparam); + +free_page: + while (i-- > 0) + free_page((unsigned long)mparam->buf[i]); + + sg_free_table(&mparam->sgt); +free_buf: + kfree(mparam->buf); +out: + return NULL; +} + +static void dma_sg_map_benchmark_unprepare(void *arg) +{ + struct dma_sg_map_param *mparam =3D arg; + int i; + + for (i =3D 0; i < mparam->npages; i++) + free_page((unsigned long)mparam->buf[i]); + + sg_free_table(&mparam->sgt); + + kfree(mparam->buf); + kfree(mparam); +} + +static int dma_sg_map_benchmark_do_map(void *arg) +{ + struct dma_sg_map_param *mparam =3D arg; + + int sg_mapped =3D dma_map_sg(mparam->dev, mparam->sgt.sgl, + mparam->npages, mparam->dma_dir); + if (!sg_mapped) { + pr_err("dma_map_sg failed on %s\n", dev_name(mparam->dev)); + return -ENOMEM; + } + + return 0; +} + +static void dma_sg_map_benchmark_do_unmap(void *arg) +{ + struct dma_sg_map_param *mparam =3D arg; + + dma_unmap_sg(mparam->dev, mparam->sgt.sgl, mparam->npages, + mparam->dma_dir); +} + +static struct map_benchmark_ops dma_sg_map_benchmark_ops =3D { + .prepare =3D dma_sg_map_benchmark_prepare, + .unprepare =3D dma_sg_map_benchmark_unprepare, + .do_map =3D dma_sg_map_benchmark_do_map, + .do_unmap =3D dma_sg_map_benchmark_do_unmap, +}; + static struct map_benchmark_ops *dma_map_benchmark_ops[DMA_MAP_MODE_MAX] = =3D { [DMA_MAP_SINGLE_MODE] =3D &dma_single_map_benchmark_ops, + [DMA_MAP_SG_MODE] =3D &dma_sg_map_benchmark_ops, }; =20 static int map_benchmark_thread(void *data) --=20 2.33.0