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 <baohua@kernel.org>
Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
---
 include/uapi/linux/map_benchmark.h |   1 +
 kernel/dma/map_benchmark.c         | 117 ++++++++++++++++++++++++++++-
 2 files changed, 117 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.h
index e076748f2120..5fa3745e1651 100644
--- a/include/uapi/linux/map_benchmark.h
+++ b/include/uapi/linux/map_benchmark.h
@@ -19,6 +19,7 @@
 
 enum {
 	DMA_MAP_BENCH_SINGLE_MODE,
+	DMA_MAP_BENCH_SG_MODE,
 	DMA_MAP_BENCH_MODE_MAX
 };
 
diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index a6345c10901c..76c0e1d5ff08 100644
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -16,6 +16,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
+#include <linux/scatterlist.h>
 #include <linux/slab.h>
 #include <linux/timekeeping.h>
 #include <uapi/linux/map_benchmark.h>
@@ -117,8 +118,121 @@ static struct map_benchmark_ops dma_single_map_benchmark_ops = {
 	.do_unmap = dma_single_map_benchmark_do_unmap,
 };
 
+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 = 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 = map->bparam.granule;
+	params->dma_dir = map->bparam.dma_dir;
+	params->dev = map->dev;
+	params->buf = kmalloc_array(params->npages, sizeof(*params->buf),
+				    GFP_KERNEL);
+	if (!params->buf)
+		goto out;
+
+	if (sg_alloc_table(&params->sgt, params->npages, GFP_KERNEL))
+		goto free_buf;
+
+	for_each_sgtable_sg(&params->sgt, sg, i) {
+		params->buf[i] = (void *)__get_free_page(GFP_KERNEL);
+		if (!params->buf[i])
+			goto free_page;
+
+		sg_set_buf(sg, params->buf[i], PAGE_SIZE);
+	}
+
+	return_ptr(params);
+
+free_page:
+	while (i-- > 0)
+		free_page((unsigned long)params->buf[i]);
+
+	sg_free_table(&params->sgt);
+free_buf:
+	kfree(params->buf);
+out:
+	return NULL;
+}
+
+static void dma_sg_map_benchmark_unprepare(void *mparam)
+{
+	struct dma_sg_map_param *params = mparam;
+	int i;
+
+	for (i = 0; i < params->npages; i++)
+		free_page((unsigned long)params->buf[i]);
+
+	sg_free_table(&params->sgt);
+
+	kfree(params->buf);
+	kfree(params);
+}
+
+static void dma_sg_map_benchmark_prepare_data(void *mparam)
+{
+	struct dma_sg_map_param *params = mparam;
+	struct scatterlist *sg;
+	int i = 0;
+
+	if (params->dma_dir == DMA_FROM_DEVICE)
+		return;
+
+	for_each_sgtable_sg(&params->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 = mparam;
+	int ret = 0;
+
+	int sg_mapped = 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 = -ENOMEM;
+	}
+
+	return ret;
+}
+
+static void dma_sg_map_benchmark_do_unmap(void *mparam)
+{
+	struct dma_sg_map_param *params = mparam;
+
+	dma_unmap_sg(params->dev, params->sgt.sgl, params->npages,
+		     params->dma_dir);
+}
+
+static struct map_benchmark_ops dma_sg_map_benchmark_ops = {
+	.prepare = dma_sg_map_benchmark_prepare,
+	.unprepare = dma_sg_map_benchmark_unprepare,
+	.prepare_data = dma_sg_map_benchmark_prepare_data,
+	.do_map = dma_sg_map_benchmark_do_map,
+	.do_unmap = dma_sg_map_benchmark_do_unmap,
+};
+
 static struct map_benchmark_ops *dma_map_benchmark_ops[DMA_MAP_BENCH_MODE_MAX] = {
 	[DMA_MAP_BENCH_SINGLE_MODE] = &dma_single_map_benchmark_ops,
+	[DMA_MAP_BENCH_SG_MODE] = &dma_sg_map_benchmark_ops,
 };
 
 static int map_benchmark_thread(void *data)
@@ -290,7 +404,8 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case DMA_MAP_BENCHMARK:
-		if (map->bparam.map_mode >= DMA_MAP_BENCH_MODE_MAX) {
+		if (map->bparam.threads < 0 ||
+		    map->bparam.map_mode >= DMA_MAP_BENCH_MODE_MAX) {
 			pr_err("invalid map mode\n");
 			return -EINVAL;
 		}
-- 
2.33.0

On Tue, Dec 23, 2025 at 4:33 AM Qinxin Xia <xiaqinxin@huawei.com> wrote:
>
> 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 <baohua@kernel.org>
> Signed-off-by: Qinxin Xia <xiaqinxin@huawei.com>
> ---
>  include/uapi/linux/map_benchmark.h |   1 +
>  kernel/dma/map_benchmark.c         | 117 ++++++++++++++++++++++++++++-
>  2 files changed, 117 insertions(+), 1 deletion(-)
>
> diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.h
> index e076748f2120..5fa3745e1651 100644
> --- a/include/uapi/linux/map_benchmark.h
> +++ b/include/uapi/linux/map_benchmark.h
> @@ -19,6 +19,7 @@
>
>  enum {
>         DMA_MAP_BENCH_SINGLE_MODE,
> +       DMA_MAP_BENCH_SG_MODE,
>         DMA_MAP_BENCH_MODE_MAX
>  };
>
> diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
> index a6345c10901c..76c0e1d5ff08 100644
> --- a/kernel/dma/map_benchmark.c
> +++ b/kernel/dma/map_benchmark.c
> @@ -16,6 +16,7 @@
>  #include <linux/module.h>
>  #include <linux/pci.h>
>  #include <linux/platform_device.h>
> +#include <linux/scatterlist.h>
>  #include <linux/slab.h>
>  #include <linux/timekeeping.h>
>  #include <uapi/linux/map_benchmark.h>
> @@ -117,8 +118,121 @@ static struct map_benchmark_ops dma_single_map_benchmark_ops = {
>         .do_unmap = dma_single_map_benchmark_do_unmap,
>  };
>
> +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 = 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 = map->bparam.granule;
> +       params->dma_dir = map->bparam.dma_dir;
> +       params->dev = map->dev;
> +       params->buf = kmalloc_array(params->npages, sizeof(*params->buf),
> +                                   GFP_KERNEL);
> +       if (!params->buf)
> +               goto out;
> +
> +       if (sg_alloc_table(&params->sgt, params->npages, GFP_KERNEL))
> +               goto free_buf;
> +
> +       for_each_sgtable_sg(&params->sgt, sg, i) {
> +               params->buf[i] = (void *)__get_free_page(GFP_KERNEL);
> +               if (!params->buf[i])
> +                       goto free_page;
> +
> +               sg_set_buf(sg, params->buf[i], PAGE_SIZE);
> +       }
> +
> +       return_ptr(params);
> +
> +free_page:
> +       while (i-- > 0)
> +               free_page((unsigned long)params->buf[i]);
> +
> +       sg_free_table(&params->sgt);
> +free_buf:
> +       kfree(params->buf);
> +out:
> +       return NULL;
> +}
> +
> +static void dma_sg_map_benchmark_unprepare(void *mparam)
> +{
> +       struct dma_sg_map_param *params = mparam;
> +       int i;
> +
> +       for (i = 0; i < params->npages; i++)
> +               free_page((unsigned long)params->buf[i]);
> +
> +       sg_free_table(&params->sgt);
> +
> +       kfree(params->buf);
> +       kfree(params);
> +}
> +
> +static void dma_sg_map_benchmark_prepare_data(void *mparam)
> +{
> +       struct dma_sg_map_param *params = mparam;
> +       struct scatterlist *sg;
> +       int i = 0;
> +
> +       if (params->dma_dir == DMA_FROM_DEVICE)
> +               return;
> +
> +       for_each_sgtable_sg(&params->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 = mparam;
> +       int ret = 0;
> +
> +       int sg_mapped = 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 = -ENOMEM;
> +       }
> +
> +       return ret;
> +}
> +
> +static void dma_sg_map_benchmark_do_unmap(void *mparam)
> +{
> +       struct dma_sg_map_param *params = mparam;
> +
> +       dma_unmap_sg(params->dev, params->sgt.sgl, params->npages,
> +                    params->dma_dir);
> +}
> +
> +static struct map_benchmark_ops dma_sg_map_benchmark_ops = {
> +       .prepare = dma_sg_map_benchmark_prepare,
> +       .unprepare = dma_sg_map_benchmark_unprepare,
> +       .prepare_data = dma_sg_map_benchmark_prepare_data,

Instead of using both prepare and prepare_data, which are ambiguous,
it would be better to rename prepare_data to initialize_data.

Thanks
Barry