| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <7fd4101c-d778-468f-98be-43cccdb03b1a@huawei.com>
Date: Tue, 23 Dec 2025 10:51:31 +0800
From: Qinxin Xia <xiaqinxin@...wei.com>
To: Barry Song <21cnbao@...il.com>
CC: <jonathan.cameron@...wei.com>, <wangzhou1@...ilicon.com>,
<iommu@...ts.linux.dev>, <prime.zeng@...wei.com>, <fanghao11@...wei.com>,
<linux-kernel@...r.kernel.org>, <linuxarm@...wei.com>
Subject: Re: [PATCH v5 1/3] dma-mapping: benchmark: modify the framework to
adapt to more map modes
On 2025/12/23 05:03:46, Barry Song <21cnbao@...il.com> wrote:
> On Tue, Dec 23, 2025 at 4:33 AM Qinxin Xia <xiaqinxin@...wei.com> wrote:
>>
>> 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 four interfaces:
>> prepare, unprepare, prepare_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@...nel.org>
>> Signed-off-by: Qinxin Xia <xiaqinxin@...wei.com>
>> ---
>> include/uapi/linux/map_benchmark.h | 8 +-
>> kernel/dma/map_benchmark.c | 130 ++++++++++++++++++++++++-----
>> 2 files changed, 115 insertions(+), 23 deletions(-)
>>
>> diff --git a/include/uapi/linux/map_benchmark.h b/include/uapi/linux/map_benchmark.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
>>
>> +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 794041a39e65..a6345c10901c 100644
>> --- 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>
>
> Are you still using scope-api and need cleanup.h?
>
Yes, in dma_single_map_benchmark_prepare:
struct dma_single_map_param *params __free(kfree)
>> #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 (*prepare_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_prepare_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 evertything 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,
>> + .prepare_data = dma_single_map_benchmark_prepare_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 +138,14 @@ 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);
>> + if (!mb_ops->prepare_data)
>> + mb_ops->prepare_data(mparam);
>
> Did you actually test it? and why don't you need prepare_data() sometimes?
>
> Thanks
> Barry
'if (mb_ops->prepare_data)' is correct.
If you want to do some tests before I release the next version, you can
modify it in this way. I have tested it and it is work.
To be compatible with other modes that in the future, 'prepare_data' may
not be necessary. So, I add a judgment here.We can delete it in the
current version and add it after this scenario occurs.
--
Thanks,
Qinxin
Powered by blists - more mailing lists