From nobody Tue Dec 16 23:10:20 2025 Received: from szxga01-in.huawei.com (szxga01-in.huawei.com [45.249.212.187]) (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 1363F2ED065 for ; Tue, 6 May 2025 03:01:04 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.187 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746500467; cv=none; b=tLylRmTxe5RxXK8fybCrtuiFOvCPMeCqGZ2TE1qOUveVDgyZ/3U86ZmO91p0HL+2Ba/4Y6XCSkqB8TVxi7tPzCi0d/0Q6CMp9U7ivsTm1KUOPKw7ZXl6SKqTANmVHH0fCOz+ynd4G1qYr2gTEIpfgjKnz4EKZkI5MG0Ah24egAs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746500467; c=relaxed/simple; bh=YSXb+HAe5RzNl6xB9OxpaEV5fxxjpxEx4rsX6iAMgMk=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=sA5YRcvCe6MLiPvfDL7SRpTXQYUbZZ/u7fzSAk9+zbRGcrMNQsrX/QE/3suTzpPcEoZqIU0iXvgyhIrL+YxkXKbJSPb3DsQuPxytKzi5eL9p7dSQarEqCj19f35Bybl4xjAEjWMV3VyEONcwpgZgRJ5kKYemZ33xa1uhPOCPG3I= 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=45.249.212.187 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 [172.19.163.48]) by szxga01-in.huawei.com (SkyGuard) with ESMTP id 4Zs32S0gftzyVKW; Tue, 6 May 2025 10:56:48 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id E7AC21800B1; Tue, 6 May 2025 11:01:02 +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 11:01:02 +0800 From: Qinxin Xia To: , CC: , , , , , , , Subject: [PATCH v2 1/4] dma-mapping: benchmark: Add padding to ensure uABI remained consistent Date: Tue, 6 May 2025 11:00:57 +0800 Message-ID: <20250506030100.394376-2-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" Fix a problem about commit (8ddde07a3d285a0f3cec, "dma-mapping:benchmark: extract a common header file for map_benchmark definition") accidentally removed that padding, which has completely broken the ABIs. Signed-off-by: Qinxin Xia --- include/linux/map_benchmark.h | 1 + 1 file changed, 1 insertion(+) diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 62674c83bde4..2ac2fe52f248 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -27,5 +27,6 @@ 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 */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */ --=20 2.33.0 From nobody Tue Dec 16 23:10:20 2025 Received: from szxga07-in.huawei.com (szxga07-in.huawei.com [45.249.212.35]) (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 004BF2BF99A for ; Tue, 6 May 2025 03:17:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.35 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746501441; cv=none; b=EV2EZnL9dbCh7uTTyWhBDMrzwUczmsz09UKW/AaK8v8plmiQ+Isskt9F2G4pRWkwTDGI6cn3m3R4yOlMpUWQ9B+okTt6nqmaUxggEggN3HmRc7bbFps53vhhQA8BdrZOamGFLhdJkQD0jUNnqFzpuBF/FdlpSq0+UfWEqgF7Bzc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746501441; c=relaxed/simple; bh=BV88dmSy1qaxy2+m31onUn1M4H9b7Ce6DK3TPwajP18=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=egaCtIwbFVuoB/emOX4Pi2oMj9+7TcnKN6VECPId+ByYafRjAvBJoT9iVjT72pSXVn5+DFxzYdJdTt3ga4AOzBM7b8X8W7Kf7N1vroZzL/NXnmfVxITCkr25p4nyYBsFciHgd+4WtXBuw9Pe1bpPbX+fTsTQ+Lr17Kw0X6sxruU= 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=45.249.212.35 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 [172.19.88.234]) by szxga07-in.huawei.com (SkyGuard) with ESMTP id 4Zs36j6FSTzsTHh; Tue, 6 May 2025 11:00:29 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id 5165D14025A; 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 11:01:02 +0800 From: Qinxin Xia To: , CC: , , , , , , , Subject: [PATCH v2 2/4] dma mapping benchmark: modify the framework to adapt to more map modes Date: Tue, 6 May 2025 11:00:58 +0800 Message-ID: <20250506030100.394376-3-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" In this patch map_benchmark abstract in four interface: prepare, unprepare, do_map, do_unmap. When there's a new mode to add, need four steps: 1) Add the mode in map_benchmark.h 2) Defines the mode param, like struct dma_xxx_map_param, and this object will be return in prepare and as input parameter in other ops; 3) Defines the ops functions:prepare, unprepare, do_map, do_unmap. 4) Add the new mode in dma_map_benchmark_ops. Signed-off-by: Qinxin Xia --- include/linux/map_benchmark.h | 8 ++- kernel/dma/map_benchmark.c | 120 +++++++++++++++++++++++++++------- 2 files changed, 104 insertions(+), 24 deletions(-) diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 2ac2fe52f248..5294dfd1870f 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -15,6 +15,11 @@ #define DMA_MAP_TO_DEVICE 1 #define DMA_MAP_FROM_DEVICE 2 =20 +enum { + DMA_MAP_SINGLE_MODE, + DMA_MAP_MODE_MAX +}; + struct map_benchmark { __u64 avg_map_100ns; /* average map latency in 100ns */ __u64 map_stddev; /* standard deviation of map latency */ @@ -27,6 +32,7 @@ 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 */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index cc19a3efea89..f04973eba1d8 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 +32,97 @@ struct map_benchmark_data { atomic64_t loops; }; =20 +struct map_benchmark_ops { + void *(*prepare)(struct map_benchmark_data *map); + void (*unprepare)(void *arg); + int (*do_map)(void *arg); + void (*do_unmap)(void *arg); +}; + +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 *mparam __free(kfree) =3D kzalloc(sizeof(*mpa= ram), + GFP_KERNEL); + if (!mparam) + return NULL; + + mparam->npages =3D map->bparam.granule; + mparam->dma_dir =3D map->bparam.dma_dir; + mparam->dev =3D map->dev; + mparam->xbuf =3D alloc_pages_exact(mparam->npages * PAGE_SIZE, GFP_KERNEL= ); + if (!mparam->xbuf) + return NULL; + + /* + * 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 (mparam->dma_dir !=3D DMA_FROM_DEVICE) + memset(mparam->xbuf, 0x66, mparam->npages * PAGE_SIZE); + + return_ptr(mparam); +} + +static void dma_single_map_benchmark_unprepare(void *arg) +{ + struct dma_single_map_param *mparam =3D arg; + + free_pages_exact(mparam->xbuf, mparam->npages * PAGE_SIZE); + kfree(mparam); +} + +static int dma_single_map_benchmark_do_map(void *arg) +{ + struct dma_single_map_param *mparam =3D arg; + + mparam->addr =3D dma_map_single(mparam->dev, mparam->xbuf, + mparam->npages * PAGE_SIZE, mparam->dma_dir); + if (unlikely(dma_mapping_error(mparam->dev, mparam->addr))) { + pr_err("dma_map_single failed on %s\n", dev_name(mparam->dev)); + return -ENOMEM; + } + + return 0; +} + +static void dma_single_map_benchmark_do_unmap(void *arg) +{ + struct dma_single_map_param *mparam =3D arg; + + dma_unmap_single(mparam->dev, mparam->addr, + mparam->npages * PAGE_SIZE, mparam->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, + .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_MODE_MAX] = =3D { + [DMA_MAP_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) + void *arg =3D dma_map_benchmark_ops[map_mode]->prepare(map); + + if (!arg) return -ENOMEM; =20 while (!kthread_should_stop()) { @@ -49,23 +130,10 @@ 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); - 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 dma_map_benchmark_ops[map_mode]->do_map(arg); + if (ret) goto out; - } map_etime =3D ktime_get(); map_delta =3D ktime_sub(map_etime, map_stime); =20 @@ -73,7 +141,8 @@ 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); + dma_map_benchmark_ops[map_mode]->do_unmap(arg); + unmap_etime =3D ktime_get(); unmap_delta =3D ktime_sub(unmap_etime, unmap_stime); =20 @@ -108,7 +177,7 @@ static int map_benchmark_thread(void *data) } =20 out: - free_pages_exact(buf, size); + dma_map_benchmark_ops[map_mode]->unprepare(arg); return ret; } =20 @@ -209,6 +278,11 @@ static long map_benchmark_ioctl(struct file *file, uns= igned int cmd, =20 switch (cmd) { case DMA_MAP_BENCHMARK: + if (map->bparam.map_mode >=3D DMA_MAP_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 Tue Dec 16 23:10:20 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 From nobody Tue Dec 16 23:10:20 2025 Received: from szxga04-in.huawei.com (szxga04-in.huawei.com [45.249.212.190]) (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 27CA52ED070 for ; Tue, 6 May 2025 03:01:08 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=45.249.212.190 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746500472; cv=none; b=MK+jh4k4ukmrY/u/dsnTRLdZd3dqSke3fQpgBe3xBbTBrgQHH3pf6cupwb4uE7oKqtn0C8VlNyhWi6xXrG0y+dRx+Yu9PgkiQwJZFhBg5EI0AfZDuu2p3ZE7CilAwHxnSXq+YOvh24SCBGrHmjHrG04dTx8yqrBTxUD7/OK5SQk= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1746500472; c=relaxed/simple; bh=OvePDz61hU89iP6mjSJW/9XhetJ3HI8k3T4tIuDg20o=; h=From:To:CC:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=DFvUUbUpyCrvkON/G4ZFVfCRfLp0s6hHOhABDKiwdeeMqBT6T+fevD9nKlc6s5fgSlkQg5NcTXVVsh0fCbVjx0DfOmjj3lfbt9hCznTZ/0PsavRSwus19/vPGPGVB54MfWK8Tqh2prTR+ixpXh9xw306K4x6vjgOI8a9dM12yls= 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=45.249.212.190 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 [172.19.88.163]) by szxga04-in.huawei.com (SkyGuard) with ESMTP id 4Zs33H4mc4z2CdjW; Tue, 6 May 2025 10:57:31 +0800 (CST) Received: from kwepemj200003.china.huawei.com (unknown [7.202.194.15]) by mail.maildlp.com (Postfix) with ESMTPS id B0D221800B3; Tue, 6 May 2025 11:01:06 +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 4/4] dma mapping benchmark:add support for dma_map_sg Date: Tue, 6 May 2025 11:01:00 +0800 Message-ID: <20250506030100.394376-5-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_map_sg, add option '-m' to distinguish mode. i) Users can set option '-m' to select mode: DMA_MAP_SINGLE_MODE=3D0, DMA_MAP_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_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_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 Signed-off-by: Qinxin Xia --- tools/testing/selftests/dma/dma_map_benchmark.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/tools/testing/selftests/dma/dma_map_benchmark.c b/tools/testin= g/selftests/dma/dma_map_benchmark.c index b12f1f9babf8..036ddb5ac862 100644 --- a/tools/testing/selftests/dma/dma_map_benchmark.c +++ b/tools/testing/selftests/dma/dma_map_benchmark.c @@ -27,6 +27,7 @@ int main(int argc, char **argv) int fd, opt; /* default single thread, run 20 seconds on NUMA_NO_NODE */ int threads =3D 1, seconds =3D 20, node =3D -1; + int map_mode =3D DMA_MAP_SINGLE_MODE; /* default dma mask 32bit, bidirectional DMA */ int bits =3D 32, xdelay =3D 0, dir =3D DMA_MAP_BIDIRECTIONAL; /* default granule 1 PAGESIZE */ @@ -34,7 +35,7 @@ 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); @@ -57,11 +58,20 @@ 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 >=3D DMA_MAP_MODE_MAX) { + fprintf(stderr, "invalid map mode, DMA_MAP_SINGLE_MODE:%d, DMA_MAP_SG_MO= DE:%d\n", + DMA_MAP_SINGLE_MODE, DMA_MAP_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); @@ -111,13 +121,15 @@ 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", + printf("dma mapping mode: %d\n", map_mode); + printf("dma mapping benchmark: threads:%d seconds:%d node:%d dir:%s granu= le/sg_nents: %d\n", threads, seconds, node, dir[directions], granule); printf("average map latency(us):%.1f standard deviation:%.1f\n", map.avg_map_100ns/10.0, map.map_stddev/10.0); --=20 2.33.0