dma-mapping: benchmark: add support for dma_map_sg

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>
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20260225093800.3625054-3-xiaqinxin@huawei.com

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
 };
 
@@ -33,7 +34,9 @@ struct map_benchmark {
 	__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 */
+	__u32 granule;  /* - SINGLE_MODE: number of pages mapped/unmapped per operation
+			 * - SG_MODE: number of scatterlist entries (each maps one page)
+			 */
 	__u8 map_mode;  /* the mode of dma map */
 	__u8 expansion[75]; /* For future use */
 };

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 +118,122 @@ 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 params;
+
+free_page:
+	while (i-- > 0)
+		free_page((unsigned long)params->buf[i]);
+
+	sg_free_table(&params->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 = 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_initialize_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,
+	.initialize_data = dma_sg_map_benchmark_initialize_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)