dma-mapping: benchmark: modify the framework to adapt to more map modes

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 <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/20260225093800.3625054-2-xiaqinxin@huawei.com

diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.h
index c2d91088a40dd12bfd51f6bc528fa7bb55e76bf0..e076748f2120d21e5ea448f3ac904edb80f30732 100644 (file)
--- 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
 
+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 */
 };
 
 #endif /* _UAPI_DMA_BENCHMARK_H */

diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
index 0f33b3ea7daf88e5e13e098079638834a1e7c862..b80e0fb399b1768b6e49c3529230dfd31f43c91e 100644 (file)
--- a/kernel/dma/map_benchmark.c
+++ b/kernel/dma/map_benchmark.c
@@ -5,6 +5,7 @@
 
 #define pr_fmt(fmt)    KBUILD_MODNAME ": " fmt
 
+#include <linux/cleanup.h>
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/device.h>
@@ -31,17 +32,105 @@ struct map_benchmark_data {
        atomic64_t loops;
 };
 
+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 *map)
+{
+       struct dma_single_map_param *params __free(kfree) = kzalloc(sizeof(*params),
+                                                                   GFP_KERNEL);
+       if (!params)
+               return NULL;
+
+       params->npages = map->bparam.granule;
+       params->dma_dir = map->bparam.dma_dir;
+       params->dev = map->dev;
+       params->xbuf = 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 = 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 = 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 everything goes well! 66 is lucky.
+        */
+       if (params->dma_dir != 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 = mparam;
+
+       params->addr = 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 = 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 = {
+       .prepare = dma_single_map_benchmark_prepare,
+       .unprepare = dma_single_map_benchmark_unprepare,
+       .initialize_data = dma_single_map_benchmark_initialize_data,
+       .do_map = dma_single_map_benchmark_do_map,
+       .do_unmap = dma_single_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,
+};
+
 static int map_benchmark_thread(void *data)
 {
-       void *buf;
-       dma_addr_t dma_addr;
        struct map_benchmark_data *map = data;
-       int npages = map->bparam.granule;
-       u64 size = npages * PAGE_SIZE;
+       __u8 map_mode = map->bparam.map_mode;
        int ret = 0;
 
-       buf = alloc_pages_exact(size, GFP_KERNEL);
-       if (!buf)
+       struct map_benchmark_ops *mb_ops = dma_map_benchmark_ops[map_mode];
+       void *mparam = mb_ops->prepare(map);
+
+       if (!mparam)
                return -ENOMEM;
 
        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;
 
-               /*
-                * 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 != DMA_FROM_DEVICE)
-                       memset(buf, 0x66, size);
-
+               mb_ops->initialize_data(mparam);
                map_stime = ktime_get();
-               dma_addr = 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 = -ENOMEM;
+               ret = mb_ops->do_map(mparam);
+               if (ret)
                        goto out;
-               }
+
                map_etime = ktime_get();
                map_delta = ktime_sub(map_etime, map_stime);
 
@@ -73,7 +151,8 @@ static int map_benchmark_thread(void *data)
                ndelay(map->bparam.dma_trans_ns);
 
                unmap_stime = ktime_get();
-               dma_unmap_single(map->dev, dma_addr, size, map->dir);
+               mb_ops->do_unmap(mparam);
+
                unmap_etime = ktime_get();
                unmap_delta = ktime_sub(unmap_etime, unmap_stime);
 
@@ -108,7 +187,7 @@ static int map_benchmark_thread(void *data)
        }
 
 out:
-       free_pages_exact(buf, size);
+       mb_ops->unprepare(mparam);
        return ret;
 }
 
@@ -209,6 +288,12 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd,
 
        switch (cmd) {
        case DMA_MAP_BENCHMARK:
+               if (map->bparam.map_mode < 0 ||
+                   map->bparam.map_mode >= DMA_MAP_BENCH_MODE_MAX) {
+                       pr_err("invalid map mode\n");
+                       return -EINVAL;
+               }
+
                if (map->bparam.threads == 0 ||
                    map->bparam.threads > DMA_MAP_MAX_THREADS) {
                        pr_err("invalid thread number\n");