Re: [dpdk-dev] [PATCH v5 1/4] example/vhost: add async vhost args parsing function

[Maxime Coquelin <maxime.coquelin@redhat.com>]

On 10/15/20 6:54 AM, Cheng Jiang wrote:
> This patch is to add async vhost driver arguments parsing function
> for CBDMA channel, DMA initiation function and args description.
> The meson build file is changed to fix dependency problem. With
> these arguments vhost device can be set to use CBDMA or CPU for
> enqueue operation and bind vhost device with specific CBDMA channel
> to accelerate data copy.
> 
> Signed-off-by: Cheng Jiang <Cheng1.jiang@intel.com>
> ---
>  examples/vhost/ioat.c      | 117 +++++++++++++++++++++++++++++++++++++
>  examples/vhost/main.c      |  43 +++++++++++++-
>  examples/vhost/main.h      |   2 +
>  examples/vhost/meson.build |   5 ++
>  4 files changed, 166 insertions(+), 1 deletion(-)
>  create mode 100644 examples/vhost/ioat.c
> 
> diff --git a/examples/vhost/ioat.c b/examples/vhost/ioat.c
> new file mode 100644
> index 000000000..c3158d3c3
> --- /dev/null
> +++ b/examples/vhost/ioat.c
> @@ -0,0 +1,117 @@
> +/* SPDX-License-Identifier: BSD-3-Clause
> + * Copyright(c) 2010-2017 Intel Corporation
> + */
> +
> +#include <rte_vhost.h>
> +#include <rte_rawdev.h>
> +#include <rte_ioat_rawdev.h>
> +#include <rte_pci.h>
> +
> +#include "main.h"
> +
> +#define MAX_VHOST_DEVICE 1024
> +#define IOAT_RING_SIZE 4096
> +
> +struct dma_info {
> +	struct rte_pci_addr addr;
> +	uint16_t dev_id;
> +	bool is_valid;
> +};
> +
> +struct dma_for_vhost {
> +	struct dma_info dmas[RTE_MAX_QUEUES_PER_PORT * 2];
> +	uint16_t nr;
> +};
> +
> +struct dma_for_vhost dma_bind[MAX_VHOST_DEVICE];
> +
> +int
> +open_ioat(const char *value)
> +{
> +	struct dma_for_vhost *dma_info = dma_bind;
> +	char *input = strndup(value, strlen(value) + 1);
> +	char *addrs = input;
> +	char *ptrs[2];
> +	char *start, *end, *substr;
> +	int64_t vid, vring_id;
> +	struct rte_ioat_rawdev_config config;
> +	struct rte_rawdev_info info = { .dev_private = &config };
> +	char name[32];
> +	int dev_id;
> +	int ret = 0;
> +	uint16_t i = 0;
> +	char *dma_arg[MAX_VHOST_DEVICE];
> +	uint8_t args_nr;
> +
> +	while (isblank(*addrs))
> +		addrs++;
> +	if (*addrs == '\0') {
> +		ret = -1;
> +		goto out;
> +	}
> +
> +	/* process DMA devices within bracket. */
> +	addrs++;
> +	substr = strtok(addrs, ";]");
> +	if (!substr) {
> +		ret = -1;
> +		goto out;
> +	}
> +	args_nr = rte_strsplit(substr, strlen(substr),
> +			dma_arg, MAX_VHOST_DEVICE, ',');
> +	do {
> +		char *arg_temp = dma_arg[i];
> +		rte_strsplit(arg_temp, strlen(arg_temp), ptrs, 2, '@');
> +
> +		start = strstr(ptrs[0], "txd");
> +		if (start == NULL) {
> +			ret = -1;
> +			goto out;
> +		}
> +
> +		start += 3;
> +		vid = strtol(start, &end, 0);
> +		if (end == start) {
> +			ret = -1;
> +			goto out;
> +		}
> +
> +		vring_id = 0 + VIRTIO_RXQ;
> +		if (rte_pci_addr_parse(ptrs[1],
> +				&(dma_info + vid)->dmas[vring_id].addr) < 0) {
> +			ret = -1;
> +			goto out;
> +		}
> +
> +		rte_pci_device_name(&(dma_info + vid)->dmas[vring_id].addr,
> +				name, sizeof(name));
> +		dev_id = rte_rawdev_get_dev_id(name);
> +		if (dev_id == (uint16_t)(-ENODEV) ||
> +		dev_id == (uint16_t)(-EINVAL)) {
> +			ret = -1;
> +			goto out;
> +		}
> +
> +		if (rte_rawdev_info_get(dev_id, &info, sizeof(config)) < 0 ||
> +		strstr(info.driver_name, "ioat") == NULL) {
> +			ret = -1;
> +			goto out;
> +		}
> +
> +		(dma_info + vid)->dmas[vring_id].dev_id = dev_id;
> +		(dma_info + vid)->dmas[vring_id].is_valid = true;
> +		config.ring_size = IOAT_RING_SIZE;
> +		config.hdls_disable = true;
> +		if (rte_rawdev_configure(dev_id, &info, sizeof(config)) < 0) {
> +			ret = -1;
> +			goto out;
> +		}
> +		rte_rawdev_start(dev_id);
> +
> +		dma_info->nr++;
> +		i++;
> +	} while (i < args_nr);
> +out:
> +	free(input);
> +	return ret;
> +}
> diff --git a/examples/vhost/main.c b/examples/vhost/main.c
> index 959c0c283..ab1b24409 100644
> --- a/examples/vhost/main.c
> +++ b/examples/vhost/main.c
> @@ -95,6 +95,10 @@ static int client_mode;
>  
>  static int builtin_net_driver;
>  
> +static int async_vhost_driver;
> +
> +static char dma_type[MAX_LONG_OPT_SZ];
> +
>  /* Specify timeout (in useconds) between retries on RX. */
>  static uint32_t burst_rx_delay_time = BURST_RX_WAIT_US;
>  /* Specify the number of retries on RX. */
> @@ -181,6 +185,21 @@ struct mbuf_table lcore_tx_queue[RTE_MAX_LCORE];
>  				 / US_PER_S * BURST_TX_DRAIN_US)
>  #define VLAN_HLEN       4
>  
> +static inline int
> +open_dma(const char *value)
> +{
> +#ifdef RTE_ARCH_X86
> +	if (strncmp(dma_type, "ioat", 4) == 0)
> +		return open_ioat(value);
> +	else
> +		return -1;
> +#else
> +	RTE_LOG(ERR, VHOST_PORT,
> +			"Error during opening ioat info: %s\n", value);
> +	return -1;
> +#endif

It would be cleaner to have something like:

static inline int
open_dma(const char *value)
{
	if (strncmp(dma_type, "ioat", 4) == 0)
		return open_ioat(value);

	return -1;
}

Then in main.h:

#ifdef RTE_ARCH_X86
int open_ioat(const char *value);
#else
static int open_ioat(const char *value)
{
	return -1;
}
#endif

> +}
> +
>  /*
>   * Builds up the correct configuration for VMDQ VLAN pool map
>   * according to the pool & queue limits.
> @@ -446,7 +465,9 @@ us_vhost_usage(const char *prgname)
>  	"		--socket-file: The path of the socket file.\n"
>  	"		--tx-csum [0|1] disable/enable TX checksum offload.\n"
>  	"		--tso [0|1] disable/enable TCP segment offload.\n"
> -	"		--client register a vhost-user socket as client mode.\n",
> +	"		--client register a vhost-user socket as client mode.\n"
> +	"		--dma-type register dma type for your vhost async driver. For example \"ioat\" for now.\n"
> +	"		--dmas register dma channel for specific vhost device.\n",
>  	       prgname);
>  }
>  
> @@ -472,6 +493,8 @@ us_vhost_parse_args(int argc, char **argv)
>  		{"tso", required_argument, NULL, 0},
>  		{"client", no_argument, &client_mode, 1},
>  		{"builtin-net-driver", no_argument, &builtin_net_driver, 1},
> +		{"dma-type", required_argument, NULL, 0},
> +		{"dmas", required_argument, NULL, 0},
>  		{NULL, 0, 0, 0},
>  	};
>  
> @@ -614,6 +637,24 @@ us_vhost_parse_args(int argc, char **argv)
>  				}
>  			}
>  
> +			if (!strncmp(long_option[option_index].name,
> +						"dma-type", MAX_LONG_OPT_SZ)) {
> +				strcpy(dma_type, optarg);
> +			}
> +
> +			if (!strncmp(long_option[option_index].name,
> +						"dmas", MAX_LONG_OPT_SZ)) {
> +				if (open_dma(optarg) == -1) {
> +					if (*optarg == -1) {
> +						RTE_LOG(INFO, VHOST_CONFIG,
> +							"Wrong DMA args\n");
> +						us_vhost_usage(prgname);
> +					}
> +					return -1;
> +				}
> +				async_vhost_driver = 1;
> +			}
> +
>  			break;
>  
>  			/* Invalid option - print options. */
> diff --git a/examples/vhost/main.h b/examples/vhost/main.h
> index 7cba0edbf..eac18824b 100644
> --- a/examples/vhost/main.h
> +++ b/examples/vhost/main.h
> @@ -90,3 +90,5 @@ uint16_t vs_dequeue_pkts(struct vhost_dev *dev, uint16_t queue_id,
>  			 struct rte_mempool *mbuf_pool,
>  			 struct rte_mbuf **pkts, uint16_t count);
>  #endif /* _MAIN_H_ */
> +
> +int open_ioat(const char *value);

It should be placed before the #endif /* _MAIN_H_ */

> diff --git a/examples/vhost/meson.build b/examples/vhost/meson.build
> index 872d51153..2a03f9779 100644
> --- a/examples/vhost/meson.build
> +++ b/examples/vhost/meson.build
> @@ -14,3 +14,8 @@ allow_experimental_apis = true
>  sources = files(
>  	'main.c', 'virtio_net.c'
>  )
> +
> +if dpdk_conf.has('RTE_ARCH_X86')
> +	deps += 'rawdev_ioat'
> +	sources += files('ioat.c')
> +endif
>