From nobody Sun Feb 8 09:11:15 2026 Received: from canpmsgout09.his.huawei.com (canpmsgout09.his.huawei.com [113.46.200.224]) (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 E4D09269D18 for ; Mon, 12 Jan 2026 09:34:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=113.46.200.224 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768210484; cv=none; b=qINkH/opMF/UgNnLeccUl3HSGJYTLWUINbw07eWV5m9KZp59SNZEloMwC6JsHbxUtZzdsc9Lq1gj+ZCeyZlUpjKKkmuvEmSziFNwBI4JfdUEX1aPgrSQ5eaNAoBhfXhkdSxO3Tw/QL+0qSe4gfSAV9PrA3B36W83i1PdBSUD4sg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768210484; c=relaxed/simple; bh=iI1Ivnkd6AKHOcBJCkAYDlvMy35YOJT78yQpAA/Bwnk=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=uvDU+gA0tOSrtSPqTPP/T1SS+qLF+r4oByUDlIyekgMo3TLF5oaoQYpwz2MvZfzhRO/lTxFTsdTQ/3edxm+bwwDMGV0dJh/mSAHhfAbjr1+FjWw7KwayIwvxADbzSOv2jN+VV/cC0yy4H942bgsQUqfZCKDYzfQcI2XRTdSZ+3g= 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; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b=c05U2+Tm; arc=none smtp.client-ip=113.46.200.224 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 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b="c05U2+Tm" dkim-signature: v=1; a=rsa-sha256; d=huawei.com; s=dkim; c=relaxed/relaxed; q=dns/txt; h=From; bh=/DqXmjQ18QQjo1tqIOKHQO/sPkU0u43E9gjpmnDmxd4=; b=c05U2+TmXT/AZSkV2tKGp6G7aAgIqgf04ZKS38jRZoJ/J+0RCJpXoSZ0aA5uPDSvrXXDNH+44 8uUx7ZySIBJbBFpOxRKd5nYIZ/Ufnxh5dDwkkFKZTTzSo3Gmg2mvqeo2EU7Oy8K0yGE81NU0pCg E381i3WvWkze/VlySX1Aw5U= Received: from mail.maildlp.com (unknown [172.19.162.92]) by canpmsgout09.his.huawei.com (SkyGuard) with ESMTPS id 4dqRvr5GfBz1cypS; Mon, 12 Jan 2026 17:31:20 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id 9CEAE40565; Mon, 12 Jan 2026 17:34:38 +0800 (CST) Received: from localhost.huawei.com (10.90.31.46) 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; Mon, 12 Jan 2026 17:34:38 +0800 From: Qinxin Xia To: <21cnbao@gmail.com>, , , CC: , , , , Subject: [PATCH v6 1/3] dma-mapping: benchmark: modify the framework to adapt to more map modes Date: Mon, 12 Jan 2026 17:34:34 +0800 Message-ID: <20260112093436.3456315-2-xiaqinxin@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20260112093436.3456315-1-xiaqinxin@huawei.com> References: <20260112093436.3456315-1-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: kwepems200002.china.huawei.com (7.221.188.68) To kwepemj200003.china.huawei.com (7.202.194.15) Content-Type: text/plain; charset="utf-8" This patch adjusts the DMA map benchmark framework to make the DMA map benchmark framework more flexible and adaptable to other mapping modes in the future. By abstracting the framework into five interfaces: prepare, unprepare, initialize_data, do_map, and do_unmap. The new map schema can be introduced more easily without major modifications to the existing code structure. Reviewed-by: Barry Song Signed-off-by: Qinxin Xia --- include/uapi/linux/map_benchmark.h | 8 +- kernel/dma/map_benchmark.c | 131 ++++++++++++++++++++++++----- 2 files changed, 115 insertions(+), 24 deletions(-) diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_be= nchmark.h index c2d91088a40d..e076748f2120 100644 --- a/include/uapi/linux/map_benchmark.h +++ b/include/uapi/linux/map_benchmark.h @@ -17,6 +17,11 @@ #define DMA_MAP_TO_DEVICE 1 #define DMA_MAP_FROM_DEVICE 2 =20 +enum { + DMA_MAP_BENCH_SINGLE_MODE, + DMA_MAP_BENCH_MODE_MAX +}; + struct map_benchmark { __u64 avg_map_100ns; /* average map latency in 100ns */ __u64 map_stddev; /* standard deviation of map latency */ @@ -29,7 +34,8 @@ struct map_benchmark { __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 expansion[76]; /* For future use */ + __u8 map_mode; /* the mode of dma map */ + __u8 expansion[75]; /* For future use */ }; =20 #endif /* _UAPI_DMA_BENCHMARK_H */ diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index 794041a39e65..cee3e451e844 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -5,6 +5,7 @@ =20 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt =20 +#include #include #include #include @@ -31,17 +32,105 @@ struct map_benchmark_data { atomic64_t loops; }; =20 +struct map_benchmark_ops { + void *(*prepare)(struct map_benchmark_data *map); + void (*unprepare)(void *mparam); + void (*initialize_data)(void *mparam); + int (*do_map)(void *mparam); + void (*do_unmap)(void *mparam); +}; + +struct dma_single_map_param { + struct device *dev; + dma_addr_t addr; + void *xbuf; + u32 npages; + u32 dma_dir; +}; + +static void *dma_single_map_benchmark_prepare(struct map_benchmark_data *m= ap) +{ + struct dma_single_map_param *params __free(kfree) =3D kzalloc(sizeof(*par= ams), + GFP_KERNEL); + if (!params) + return NULL; + + params->npages =3D map->bparam.granule; + params->dma_dir =3D map->bparam.dma_dir; + params->dev =3D map->dev; + params->xbuf =3D alloc_pages_exact(params->npages * PAGE_SIZE, GFP_KERNEL= ); + if (!params->xbuf) + return NULL; + + return_ptr(params); +} + +static void dma_single_map_benchmark_unprepare(void *mparam) +{ + struct dma_single_map_param *params =3D mparam; + + free_pages_exact(params->xbuf, params->npages * PAGE_SIZE); + kfree(params); +} + +static void dma_single_map_benchmark_initialize_data(void *mparam) +{ + struct dma_single_map_param *params =3D mparam; + + /* + * for a non-coherent device, if we don't stain them in the + * cache, this will give an underestimate of the real-world + * overhead of BIDIRECTIONAL or TO_DEVICE mappings; + * 66 means evertything goes well! 66 is lucky. + */ + if (params->dma_dir !=3D DMA_FROM_DEVICE) + memset(params->xbuf, 0x66, params->npages * PAGE_SIZE); +} + +static int dma_single_map_benchmark_do_map(void *mparam) +{ + struct dma_single_map_param *params =3D mparam; + + params->addr =3D dma_map_single(params->dev, params->xbuf, + params->npages * PAGE_SIZE, params->dma_dir); + if (unlikely(dma_mapping_error(params->dev, params->addr))) { + pr_err("dma_map_single failed on %s\n", dev_name(params->dev)); + return -ENOMEM; + } + + return 0; +} + +static void dma_single_map_benchmark_do_unmap(void *mparam) +{ + struct dma_single_map_param *params =3D mparam; + + dma_unmap_single(params->dev, params->addr, + params->npages * PAGE_SIZE, params->dma_dir); +} + +static struct map_benchmark_ops dma_single_map_benchmark_ops =3D { + .prepare =3D dma_single_map_benchmark_prepare, + .unprepare =3D dma_single_map_benchmark_unprepare, + .initialize_data =3D dma_single_map_benchmark_initialize_data, + .do_map =3D dma_single_map_benchmark_do_map, + .do_unmap =3D dma_single_map_benchmark_do_unmap, +}; + +static struct map_benchmark_ops *dma_map_benchmark_ops[DMA_MAP_BENCH_MODE_= MAX] =3D { + [DMA_MAP_BENCH_SINGLE_MODE] =3D &dma_single_map_benchmark_ops, +}; + static int map_benchmark_thread(void *data) { - void *buf; - dma_addr_t dma_addr; struct map_benchmark_data *map =3D data; - int npages =3D map->bparam.granule; - u64 size =3D npages * PAGE_SIZE; + __u8 map_mode =3D map->bparam.map_mode; int ret =3D 0; =20 - buf =3D alloc_pages_exact(size, GFP_KERNEL); - if (!buf) + struct map_benchmark_ops *mb_ops =3D dma_map_benchmark_ops[map_mode]; + void *mparam =3D mb_ops->prepare(map); + + if (!mparam) return -ENOMEM; =20 while (!kthread_should_stop()) { @@ -49,23 +138,12 @@ static int map_benchmark_thread(void *data) ktime_t map_stime, map_etime, unmap_stime, unmap_etime; ktime_t map_delta, unmap_delta; =20 - /* - * for a non-coherent device, if we don't stain them in the - * cache, this will give an underestimate of the real-world - * overhead of BIDIRECTIONAL or TO_DEVICE mappings; - * 66 means evertything goes well! 66 is lucky. - */ - if (map->dir !=3D DMA_FROM_DEVICE) - memset(buf, 0x66, size); - + mb_ops->initialize_data(mparam); map_stime =3D ktime_get(); - dma_addr =3D dma_map_single(map->dev, buf, size, map->dir); - if (unlikely(dma_mapping_error(map->dev, dma_addr))) { - pr_err("dma_map_single failed on %s\n", - dev_name(map->dev)); - ret =3D -ENOMEM; + ret =3D mb_ops->do_map(mparam); + if (ret) goto out; - } + map_etime =3D ktime_get(); map_delta =3D ktime_sub(map_etime, map_stime); =20 @@ -73,7 +151,8 @@ static int map_benchmark_thread(void *data) ndelay(map->bparam.dma_trans_ns); =20 unmap_stime =3D ktime_get(); - dma_unmap_single(map->dev, dma_addr, size, map->dir); + mb_ops->do_unmap(mparam); + unmap_etime =3D ktime_get(); unmap_delta =3D ktime_sub(unmap_etime, unmap_stime); =20 @@ -108,7 +187,7 @@ static int map_benchmark_thread(void *data) } =20 out: - free_pages_exact(buf, size); + mb_ops->unprepare(mparam); return ret; } =20 @@ -209,6 +288,12 @@ static long map_benchmark_ioctl(struct file *file, uns= igned int cmd, =20 switch (cmd) { case DMA_MAP_BENCHMARK: + if (map->bparam.map_mode < 0 || + map->bparam.map_mode >=3D DMA_MAP_BENCH_MODE_MAX) { + pr_err("invalid map mode\n"); + return -EINVAL; + } + if (map->bparam.threads =3D=3D 0 || map->bparam.threads > DMA_MAP_MAX_THREADS) { pr_err("invalid thread number\n"); --=20 2.33.0 From nobody Sun Feb 8 09:11:15 2026 Received: from canpmsgout11.his.huawei.com (canpmsgout11.his.huawei.com [113.46.200.226]) (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 B22A8349B0E for ; Mon, 12 Jan 2026 09:34:48 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=113.46.200.226 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768210493; cv=none; b=DjwrTDuFrxFJLwY4PCbdiEcz5TSRrAOleUJ9jHHKxQeOyYehVzE49OnY1RE0K6PV0h/plTUIsqIQMCpLbqv6aKTvBrQilOP91A1yQ+4Y1JWRKfYxRNUO8yb/xArL1If03/3vLAqrQL/0SSxfJYq17338q1hl3DNh36MyvLY5rgA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768210493; c=relaxed/simple; bh=KAGnsrh7CVz68ElXpAUuXK7pOEo7c/j+lvpaYGnmCMY=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=JpZGjzFv8meCsVzEXS9cFdFzD9cO2DquYcCRHS39kccteQJYT9AgPynJlFCbKqwsjmDpANd+gvMTD6KT0v51znR54AqDaFmh3XtzfMG9it56LF0vmAWM+WAXQ4b31jPKnOIOSyyLQJHPa9DThDBdvrNlRL+26G2x4BHugYRkI+k= 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; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b=OLMmSkYp; arc=none smtp.client-ip=113.46.200.226 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 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b="OLMmSkYp" dkim-signature: v=1; a=rsa-sha256; d=huawei.com; s=dkim; c=relaxed/relaxed; q=dns/txt; h=From; bh=+QumefmoBBh7FpAA+6NaKipllHdL/cOdongraibadiU=; b=OLMmSkYpBmrVLEkrHjOWncqsJN1B/cNsvmwS3e7LH2ALqJ1W06i+4K/oz8sAACSgbHE7zrdHy oZoNTixHGCLj058MymM6K7PcOywnUP0j4Nv62ksbPyh7Nwz8yP3ArwtJ71otlfaEAsaHNPLv82H +Bj8r/4Zd9N/1gCbDNwdldI= Received: from mail.maildlp.com (unknown [172.19.163.15]) by canpmsgout11.his.huawei.com (SkyGuard) with ESMTPS id 4dqRvr04xZzKm4N; Mon, 12 Jan 2026 17:31:20 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id 1259040565; Mon, 12 Jan 2026 17:34:39 +0800 (CST) Received: from localhost.huawei.com (10.90.31.46) 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; Mon, 12 Jan 2026 17:34:38 +0800 From: Qinxin Xia To: <21cnbao@gmail.com>, , , CC: , , , , Subject: [PATCH v6 2/3] dma-mapping: benchmark: add support for dma_map_sg Date: Mon, 12 Jan 2026 17:34:35 +0800 Message-ID: <20260112093436.3456315-3-xiaqinxin@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20260112093436.3456315-1-xiaqinxin@huawei.com> References: <20260112093436.3456315-1-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: kwepems200002.china.huawei.com (7.221.188.68) 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. Reviewed-by: Barry Song Signed-off-by: Qinxin Xia --- include/uapi/linux/map_benchmark.h | 1 + kernel/dma/map_benchmark.c | 115 +++++++++++++++++++++++++++++ 2 files changed, 116 insertions(+) diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_be= nchmark.h index e076748f2120..5fa3745e1651 100644 --- a/include/uapi/linux/map_benchmark.h +++ b/include/uapi/linux/map_benchmark.h @@ -19,6 +19,7 @@ =20 enum { DMA_MAP_BENCH_SINGLE_MODE, + DMA_MAP_BENCH_SG_MODE, DMA_MAP_BENCH_MODE_MAX }; =20 diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index cee3e451e844..590cb1228289 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -117,8 +118,122 @@ 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; + + struct dma_sg_map_param *params =3D kzalloc(sizeof(*params), GFP_KERNEL); + + if (!params) + 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. + */ + params->npages =3D map->bparam.granule; + params->dma_dir =3D map->bparam.dma_dir; + params->dev =3D map->dev; + params->buf =3D kmalloc_array(params->npages, sizeof(*params->buf), + GFP_KERNEL); + if (!params->buf) + goto out; + + if (sg_alloc_table(¶ms->sgt, params->npages, GFP_KERNEL)) + goto free_buf; + + for_each_sgtable_sg(¶ms->sgt, sg, i) { + params->buf[i] =3D (void *)__get_free_page(GFP_KERNEL); + if (!params->buf[i]) + goto free_page; + + sg_set_buf(sg, params->buf[i], PAGE_SIZE); + } + + return params; + +free_page: + while (i-- > 0) + free_page((unsigned long)params->buf[i]); + + sg_free_table(¶ms->sgt); +free_buf: + kfree(params->buf); +out: + kfree(params); + return NULL; +} + +static void dma_sg_map_benchmark_unprepare(void *mparam) +{ + struct dma_sg_map_param *params =3D mparam; + int i; + + for (i =3D 0; i < params->npages; i++) + free_page((unsigned long)params->buf[i]); + + sg_free_table(¶ms->sgt); + + kfree(params->buf); + kfree(params); +} + +static void dma_sg_map_benchmark_initialize_data(void *mparam) +{ + struct dma_sg_map_param *params =3D mparam; + struct scatterlist *sg; + int i =3D 0; + + if (params->dma_dir =3D=3D DMA_FROM_DEVICE) + return; + + for_each_sgtable_sg(¶ms->sgt, sg, i) + memset(params->buf[i], 0x66, PAGE_SIZE); +} + +static int dma_sg_map_benchmark_do_map(void *mparam) +{ + struct dma_sg_map_param *params =3D mparam; + int ret =3D 0; + + int sg_mapped =3D dma_map_sg(params->dev, params->sgt.sgl, + params->npages, params->dma_dir); + if (!sg_mapped) { + pr_err("dma_map_sg failed on %s\n", dev_name(params->dev)); + ret =3D -ENOMEM; + } + + return ret; +} + +static void dma_sg_map_benchmark_do_unmap(void *mparam) +{ + struct dma_sg_map_param *params =3D mparam; + + dma_unmap_sg(params->dev, params->sgt.sgl, params->npages, + params->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, + .initialize_data =3D dma_sg_map_benchmark_initialize_data, + .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_BENCH_MODE_= MAX] =3D { [DMA_MAP_BENCH_SINGLE_MODE] =3D &dma_single_map_benchmark_ops, + [DMA_MAP_BENCH_SG_MODE] =3D &dma_sg_map_benchmark_ops, }; =20 static int map_benchmark_thread(void *data) --=20 2.33.0 From nobody Sun Feb 8 09:11:15 2026 Received: from canpmsgout03.his.huawei.com (canpmsgout03.his.huawei.com [113.46.200.218]) (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 836F326E718 for ; Mon, 12 Jan 2026 09:34:41 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=113.46.200.218 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768210483; cv=none; b=HQLg6ZfLezVeXHaAQ0YoRAVyiHFKdo2xubecEzXSUINB22GEtCc++d0tUffcGh3CvSw7laiNjPFzy/xE5fC+lGP75Nym3SRQ+lHnOqmZeQfDJ308Qw4FIaDR+okzXFrAnX4M2dYHzn5bFwPKj7PsE4Ms2vsAZgxV+IrLlNY+bAw= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1768210483; c=relaxed/simple; bh=8sft5Cfo0r/EQQFuug/6sOpg/zghyhwLBpb8GYf+0f4=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=FtZndiv+fwAHSKxcwNvYjy+uLCMaOGEARG3AfbHqLQT/ZwQRGHhE4uwxDwd0Wn0KPdYyDG+XOgax3x6uTzvh/6LHzaDrnNAKgYB3e5DGnuGmHIITzrW2J9iISBMKwoKsaQ4yPr5+VkH+4zcaD782AP9Np/Fd8sAL0W4ydZ1LAuw= 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; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b=CG6chLH8; arc=none smtp.client-ip=113.46.200.218 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 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=huawei.com header.i=@huawei.com header.b="CG6chLH8" dkim-signature: v=1; a=rsa-sha256; d=huawei.com; s=dkim; c=relaxed/relaxed; q=dns/txt; h=From; bh=uO7P1QvCPLUDxnK/XMa556cfvssPiwxe/AQofsK7HVo=; b=CG6chLH8U08Fi0pIrGoNIlTVZwCLRR8773YYkGDAJugYvlO0hqcwOAmbpxsmhL6eEqufrXyIV opXAZfx0C1EDSoab/uUZZoXVZ1CvjPRm/3XDZ23bR6cK06plhSAyM9c3W81yHZtoQMIclth50ct oBCwO2IJxhx7uSxF+le7Gxo= Received: from mail.maildlp.com (unknown [172.19.162.140]) by canpmsgout03.his.huawei.com (SkyGuard) with ESMTPS id 4dqRvd346MzpSv8; Mon, 12 Jan 2026 17:31:09 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id 714BA2016A; Mon, 12 Jan 2026 17:34:39 +0800 (CST) Received: from localhost.huawei.com (10.90.31.46) 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; Mon, 12 Jan 2026 17:34:38 +0800 From: Qinxin Xia To: <21cnbao@gmail.com>, , , CC: , , , , Subject: [PATCH v6 3/3] tools/dma: Add dma_map_sg support Date: Mon, 12 Jan 2026 17:34:36 +0800 Message-ID: <20260112093436.3456315-4-xiaqinxin@huawei.com> X-Mailer: git-send-email 2.33.0 In-Reply-To: <20260112093436.3456315-1-xiaqinxin@huawei.com> References: <20260112093436.3456315-1-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: kwepems200002.china.huawei.com (7.221.188.68) To kwepemj200003.china.huawei.com (7.202.194.15) Content-Type: text/plain; charset="utf-8" Support for dma_map_sg, add option '-m' to distinguish mode. i) Users can set option '-m' to select mode: DMA_MAP_BENCH_SINGLE_MODE=3D0, DMA_MAP_BENCH_SG_MODE:=3D1 (The mode is also show in the test result). ii) Users can set option '-g' to set sg_nents (total count of entries in scatterlist) the maximum number is 1024. Each of sg buf size is PAGE_SIZE. e.g [root@localhost]# ./dma_map_benchmark -m 1 -g 8 -t 8 -s 30 -d 2 dma mapping mode: DMA_MAP_BENCH_SG_MODE dma mapping benchmark: threads:8 seconds:30 node:-1 dir:FROM_DEVICE granule/sg_nents: 8 average map latency(us):1.4 standard deviation:0.3 average unmap latency(us):1.3 standard deviation:0.3 [root@localhost]# ./dma_map_benchmark -m 0 -g 8 -t 8 -s 30 -d 2 dma mapping mode: DMA_MAP_BENCH_SINGLE_MODE dma mapping benchmark: threads:8 seconds:30 node:-1 dir:FROM_DEVICE granule/sg_nents: 8 average map latency(us):1.0 standard deviation:0.3 average unmap latency(us):1.3 standard deviation:0.5 Reviewed-by: Barry Song Signed-off-by: Qinxin Xia --- tools/dma/dma_map_benchmark.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/tools/dma/dma_map_benchmark.c b/tools/dma/dma_map_benchmark.c index dd0ed528e6df..143ca8dab8af 100644 --- a/tools/dma/dma_map_benchmark.c +++ b/tools/dma/dma_map_benchmark.c @@ -20,12 +20,19 @@ static char *directions[] =3D { "FROM_DEVICE", }; =20 +static char *mode[] =3D { + "SINGLE_MODE", + "SG_MODE", +}; + int main(int argc, char **argv) { struct map_benchmark map; int fd, opt; /* default single thread, run 20 seconds on NUMA_NO_NODE */ int threads =3D 1, seconds =3D 20, node =3D -1; + /* default single map mode */ + int map_mode =3D DMA_MAP_BENCH_SINGLE_MODE; /* default dma mask 32bit, bidirectional DMA */ int bits =3D 32, xdelay =3D 0, dir =3D DMA_MAP_BIDIRECTIONAL; /* default granule 1 PAGESIZE */ @@ -33,7 +40,7 @@ int main(int argc, char **argv) =20 int cmd =3D DMA_MAP_BENCHMARK; =20 - while ((opt =3D getopt(argc, argv, "t:s:n:b:d:x:g:")) !=3D -1) { + while ((opt =3D getopt(argc, argv, "t:s:n:b:d:x:g:m:")) !=3D -1) { switch (opt) { case 't': threads =3D atoi(optarg); @@ -56,11 +63,20 @@ int main(int argc, char **argv) case 'g': granule =3D atoi(optarg); break; + case 'm': + map_mode =3D atoi(optarg); + break; default: return -1; } } =20 + if (map_mode < 0 || map_mode >=3D DMA_MAP_BENCH_MODE_MAX) { + fprintf(stderr, "invalid map mode, SINGLE_MODE:%d, SG_MODE: %d\n", + DMA_MAP_BENCH_SINGLE_MODE, DMA_MAP_BENCH_SG_MODE); + exit(1); + } + if (threads <=3D 0 || threads > DMA_MAP_MAX_THREADS) { fprintf(stderr, "invalid number of threads, must be in 1-%d\n", DMA_MAP_MAX_THREADS); @@ -110,14 +126,15 @@ int main(int argc, char **argv) map.dma_dir =3D dir; map.dma_trans_ns =3D xdelay; map.granule =3D granule; + map.map_mode =3D map_mode; =20 if (ioctl(fd, cmd, &map)) { perror("ioctl"); exit(1); } =20 - printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granu= le: %d\n", - threads, seconds, node, directions[dir], granule); + printf("dma mapping benchmark(%s): threads:%d seconds:%d node:%d dir:%s g= ranule:%d\n", + mode[map_mode], threads, seconds, node, directions[dir], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0); printf("average unmap latency(us):%.1f standard deviation:%.1f\n", --=20 2.33.0