RE: [PATCH v5 2/2] examples/l3fwd: relax RX Offload with option

[Konstantin Ananyev <konstantin.ananyev@huawei.com>]

> Now the port Rx offload mode is set to RTE_ETH_RX_OFFLOAD_CHECKSUM
> by default, but some hw and/or virtual interface does not support
> the offload mode presupposed, e.g., some virtio interfaces in
> the cloud may only partly support RTE_ETH_RX_OFFLOAD_UDP_CKSUM/
> RTE_ETH_RX_OFFLOAD_TCP_CKSUM,
> but not RTE_ETH_RX_OFFLOAD_IPV4_CKSUM, and the error msg here:
> 
> Ethdev port_id=0 requested Rx offloads 0xe does not match Rx offloads
> capabilities 0x201d in rte_eth_dev_configure()
> 
> So to enable the l3fwd running in that environment, the Rx mode requirement
> can be relaxed to reflect the hardware feature reality here with an option
> relax_rx_offload, and the l3fwd can run smoothly then.
> A warning msg would be provided to user in case it happens here.
> 
> On the other side, enabling the software cksum check in case missing the
> hw support.
> 
> The relax action for rx cksum offload is just enabled when
> relax_rx_offload is true which is false by default.
> 
> Signed-off-by: Trevor Tao <taozj888@163.com>
> ---
>  examples/l3fwd/l3fwd.h     | 12 ++++++++++--
>  examples/l3fwd/l3fwd_em.h  |  2 +-
>  examples/l3fwd/l3fwd_lpm.h |  2 +-
>  examples/l3fwd/main.c      | 24 ++++++++++++++++++++++++
>  4 files changed, 36 insertions(+), 4 deletions(-)
> 
> diff --git a/examples/l3fwd/l3fwd.h b/examples/l3fwd/l3fwd.h
> index b55855c932..e7ae0e5834 100644
> --- a/examples/l3fwd/l3fwd.h
> +++ b/examples/l3fwd/l3fwd.h
> @@ -159,7 +159,7 @@ send_single_packet(struct lcore_conf *qconf,
> 
>  #ifdef DO_RFC_1812_CHECKS
>  static inline int
> -is_valid_ipv4_pkt(struct rte_ipv4_hdr *pkt, uint32_t link_len)
> +is_valid_ipv4_pkt(struct rte_ipv4_hdr *pkt, uint32_t link_len, uint64_t ol_flags)
>  {
>  	/* From http://www.rfc-editor.org/rfc/rfc1812.txt section 5.2.2 */
>  	/*
> @@ -170,7 +170,15 @@ is_valid_ipv4_pkt(struct rte_ipv4_hdr *pkt, uint32_t link_len)
>  		return -1;
> 
>  	/* 2. The IP checksum must be correct. */
> -	/* this is checked in H/W */
> +	/* if this is not checked in H/W, check it. */
> +	if ((ol_flags & RTE_MBUF_F_RX_IP_CKSUM_MASK) == RTE_MBUF_F_RX_IP_CKSUM_NONE) {

Actually, we probably also need to check for RTE_MBUF_F_RX_IP_CKSUM_BAD,
But that is a subject for another patch (fix actually).

 Acked-by: Konstantin Ananyev <konstantin.ananyev@huawei.com>


> +		uint16_t actual_cksum, expected_cksum;
> +		actual_cksum = pkt->hdr_checksum;
> +		pkt->hdr_checksum = 0;
> +		expected_cksum = rte_ipv4_cksum(pkt);
> +		if (actual_cksum != expected_cksum)
> +			return -2;
> +	}
> 
>  	/*
>  	 * 3. The IP version number must be 4. If the version number is not 4
> diff --git a/examples/l3fwd/l3fwd_em.h b/examples/l3fwd/l3fwd_em.h
> index 7d051fc076..1fee2e2e6c 100644
> --- a/examples/l3fwd/l3fwd_em.h
> +++ b/examples/l3fwd/l3fwd_em.h
> @@ -20,7 +20,7 @@ l3fwd_em_handle_ipv4(struct rte_mbuf *m, uint16_t portid,
> 
>  #ifdef DO_RFC_1812_CHECKS
>  	/* Check to make sure the packet is valid (RFC1812) */
> -	if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) {
> +	if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len, m->ol_flags) < 0) {
>  		rte_pktmbuf_free(m);
>  		return BAD_PORT;
>  	}
> diff --git a/examples/l3fwd/l3fwd_lpm.h b/examples/l3fwd/l3fwd_lpm.h
> index c61b969584..4ee61e8d88 100644
> --- a/examples/l3fwd/l3fwd_lpm.h
> +++ b/examples/l3fwd/l3fwd_lpm.h
> @@ -22,7 +22,7 @@ l3fwd_lpm_simple_forward(struct rte_mbuf *m, uint16_t portid,
> 
>  #ifdef DO_RFC_1812_CHECKS
>  		/* Check to make sure the packet is valid (RFC1812) */
> -		if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len) < 0) {
> +		if (is_valid_ipv4_pkt(ipv4_hdr, m->pkt_len, m->ol_flags) < 0) {
>  			rte_pktmbuf_free(m);
>  			return;
>  		}
> diff --git a/examples/l3fwd/main.c b/examples/l3fwd/main.c
> index b42365ef1b..851e7e68f9 100644
> --- a/examples/l3fwd/main.c
> +++ b/examples/l3fwd/main.c
> @@ -74,6 +74,8 @@ static int numa_on = 1; /**< NUMA is enabled by default. */
>  static int parse_ptype; /**< Parse packet type using rx callback, and */
>  			/**< disabled by default */
>  static int disable_rss; /**< Disable the RX RSS mode */
> +static int relax_rx_offload; /**< Relax RX offload mode, and */
> +			     /**< disabled by default */
>  static int per_port_pool; /**< Use separate buffer pools per port; disabled */
>  			  /**< by default */
> 
> @@ -680,6 +682,7 @@ static const char short_options[] =
>  #define CMD_LINE_OPT_HASH_ENTRY_NUM "hash-entry-num"
>  #define CMD_LINE_OPT_PARSE_PTYPE "parse-ptype"
>  #define CMD_LINE_OPT_DISABLE_RSS "disable-rss"
> +#define CMD_LINE_OPT_RELAX_RX_OFFLOAD "relax-rx-offload"
>  #define CMD_LINE_OPT_PER_PORT_POOL "per-port-pool"
>  #define CMD_LINE_OPT_MODE "mode"
>  #define CMD_LINE_OPT_EVENTQ_SYNC "eventq-sched"
> @@ -708,6 +711,7 @@ enum {
>  	CMD_LINE_OPT_HASH_ENTRY_NUM_NUM,
>  	CMD_LINE_OPT_PARSE_PTYPE_NUM,
>  	CMD_LINE_OPT_DISABLE_RSS_NUM,
> +	CMD_LINE_OPT_RELAX_RX_OFFLOAD_NUM,
>  	CMD_LINE_OPT_RULE_IPV4_NUM,
>  	CMD_LINE_OPT_RULE_IPV6_NUM,
>  	CMD_LINE_OPT_ALG_NUM,
> @@ -731,6 +735,7 @@ static const struct option lgopts[] = {
>  	{CMD_LINE_OPT_MAX_PKT_LEN, 1, 0, CMD_LINE_OPT_MAX_PKT_LEN_NUM},
>  	{CMD_LINE_OPT_HASH_ENTRY_NUM, 1, 0, CMD_LINE_OPT_HASH_ENTRY_NUM_NUM},
>  	{CMD_LINE_OPT_PARSE_PTYPE, 0, 0, CMD_LINE_OPT_PARSE_PTYPE_NUM},
> +	{CMD_LINE_OPT_RELAX_RX_OFFLOAD, 0, 0, CMD_LINE_OPT_RELAX_RX_OFFLOAD_NUM},
>  	{CMD_LINE_OPT_DISABLE_RSS, 0, 0, CMD_LINE_OPT_DISABLE_RSS_NUM},
>  	{CMD_LINE_OPT_PER_PORT_POOL, 0, 0, CMD_LINE_OPT_PARSE_PER_PORT_POOL},
>  	{CMD_LINE_OPT_MODE, 1, 0, CMD_LINE_OPT_MODE_NUM},
> @@ -857,6 +862,11 @@ parse_args(int argc, char **argv)
>  			parse_ptype = 1;
>  			break;
> 
> +		case CMD_LINE_OPT_RELAX_RX_OFFLOAD_NUM:
> +			printf("Relax rx offload mode is enabled\n");
> +			relax_rx_offload = 1;
> +			break;
> +
>  		case CMD_LINE_OPT_DISABLE_RSS_NUM:
>  			printf("Disable RX RSS\n");
>  			disable_rss = 1;
> @@ -1278,6 +1288,20 @@ l3fwd_poll_resource_setup(void)
>  				local_port_conf.rx_adv_conf.rss_conf.rss_hf);
>  		}
> 
> +		/* relax the rx offload requirement */
> +		if ((local_port_conf.rxmode.offloads & dev_info.rx_offload_capa) !=
> +			local_port_conf.rxmode.offloads) {
> +			printf("Port %u requested Rx offloads 0x%"PRIx64" does not"
> +				" match Rx offloads capabilities 0x%"PRIx64"\n",
> +				portid, local_port_conf.rxmode.offloads,
> +				dev_info.rx_offload_capa);
> +			if (relax_rx_offload) {
> +				local_port_conf.rxmode.offloads &= dev_info.rx_offload_capa;
> +				printf("warning: modified the rx offload to 0x%"PRIx64" based on device"
> +				" capability\n", local_port_conf.rxmode.offloads);
> +			}
> +		}
> +
>  		ret = rte_eth_dev_configure(portid, nb_rx_queue,
>  					(uint16_t)n_tx_queue, &local_port_conf);
>  		if (ret < 0)
> --
> 2.34.1