diff options
| author | Barry Song <song.bao.hua@hisilicon.com> | 2021-02-05 14:33:25 +0300 |
|---|---|---|
| committer | Christoph Hellwig <hch@lst.de> | 2021-02-05 14:48:46 +0300 |
| commit | 9dc00b25eadf2908ae76ac0607b55a9f4e0e0cdc (patch) | |
| tree | 3a80c0139e2eca5de2fd134189c26900dae9824c /kernel/dma | |
| parent | 9f5f8ec50165630cfc49897410b30997d4d677b5 (diff) | |
| download | linux-9dc00b25eadf2908ae76ac0607b55a9f4e0e0cdc.tar.xz | |
dma-mapping: benchmark: pretend DMA is transmitting
In a real dma mapping user case, after dma_map is done, data will be
transmit. Thus, in multi-threaded user scenario, IOMMU contention
should not be that severe. For example, if users enable multiple
threads to send network packets through 1G/10G/100Gbps NIC, usually
the steps will be: map -> transmission -> unmap. Transmission delay
reduces the contention of IOMMU.
Here a delay is added to simulate the transmission between map and unmap
so that the tested result could be more accurate for TX and simple RX.
A typical TX transmission for NIC would be like: map -> TX -> unmap
since the socket buffers come from OS. Simple RX model eg. disk driver,
is also map -> RX -> unmap, but real RX model in a NIC could be more
complicated considering packets can come spontaneously and many drivers
are using pre-mapped buffers pool. This is in the TBD list.
Signed-off-by: Barry Song <song.bao.hua@hisilicon.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'kernel/dma')
| -rw-r--r-- | kernel/dma/map_benchmark.c | 12 |
1 files changed, 11 insertions, 1 deletions
diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c index da95df381483..e0e64f8b0739 100644 --- a/kernel/dma/map_benchmark.c +++ b/kernel/dma/map_benchmark.c @@ -21,6 +21,7 @@ #define DMA_MAP_BENCHMARK _IOWR('d', 1, struct map_benchmark) #define DMA_MAP_MAX_THREADS 1024 #define DMA_MAP_MAX_SECONDS 300 +#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC) #define DMA_MAP_BIDIRECTIONAL 0 #define DMA_MAP_TO_DEVICE 1 @@ -36,7 +37,8 @@ struct map_benchmark { __s32 node; /* which numa node this benchmark will run on */ __u32 dma_bits; /* DMA addressing capability */ __u32 dma_dir; /* DMA data direction */ - __u8 expansion[84]; /* For future use */ + __u32 dma_trans_ns; /* time for DMA transmission in ns */ + __u8 expansion[80]; /* For future use */ }; struct map_benchmark_data { @@ -87,6 +89,9 @@ static int map_benchmark_thread(void *data) map_etime = ktime_get(); map_delta = ktime_sub(map_etime, map_stime); + /* Pretend DMA is transmitting */ + ndelay(map->bparam.dma_trans_ns); + unmap_stime = ktime_get(); dma_unmap_single(map->dev, dma_addr, PAGE_SIZE, map->dir); unmap_etime = ktime_get(); @@ -218,6 +223,11 @@ static long map_benchmark_ioctl(struct file *file, unsigned int cmd, return -EINVAL; } + if (map->bparam.dma_trans_ns > DMA_MAP_MAX_TRANS_DELAY) { + pr_err("invalid transmission delay\n"); + return -EINVAL; + } + if (map->bparam.node != NUMA_NO_NODE && !node_possible(map->bparam.node)) { pr_err("invalid numa node\n"); |