> -----Original Message-----
> From: Hu, Jiayu
> Sent: Friday, June 23, 2017 10:43 PM
> To: dev@dpdk.org
> Cc: Ananyev, Konstantin <konstantin.anan...@intel.com>; Tan, Jianfeng
> <jianfeng....@intel.com>; step...@networkplumber.org;
> y...@fridaylinux.org; Wiles, Keith <keith.wi...@intel.com>; Bie, Tiwei
> <tiwei....@intel.com>; Yao, Lei A <lei.a....@intel.com>; Hu, Jiayu
> <jiayu...@intel.com>
> Subject: [PATCH v6 3/3] app/testpmd: enable TCP/IPv4 GRO
>
> This patch enables TCP/IPv4 GRO library in csum forwarding engine.
> By default, GRO is turned off. Users can use command "gro (on|off)
> (port_id)" to enable or disable GRO for a given port. If a port is
> enabled GRO, all TCP/IPv4 packets received from the port are performed
> GRO. Besides, users can set max flow number and packets number per-flow
> by command "gro set (max_flow_num) (max_item_num_per_flow)
> (port_id)".
>
> Signed-off-by: Jiayu Hu <jiayu...@intel.com>
Tested-By: Lei Yao<lei.a....@intel.com>
This patch is tested on the following test bench:
OS: Ubuntu 16.04
CPU: Intel(R) Xeon(R) CPU E5-2680 v2 @ 2.80GHz
NIC: XXV710 25G
We can see the iperf result improve a lot after enable GRO. The data
flow is NIC1->NIC2->testpmd(GRO on/off)->vhost->virtio-net(in VM)
> ---
> app/test-pmd/cmdline.c | 125
> ++++++++++++++++++++++++++++
> app/test-pmd/config.c | 37 ++++++++
> app/test-pmd/csumonly.c | 5 ++
> app/test-pmd/testpmd.c | 3 +
> app/test-pmd/testpmd.h | 11 +++
> doc/guides/testpmd_app_ug/testpmd_funcs.rst | 34 ++++++++
> 6 files changed, 215 insertions(+)
>
> diff --git a/app/test-pmd/cmdline.c b/app/test-pmd/cmdline.c
> index ff8ffd2..cb359e1 100644
> --- a/app/test-pmd/cmdline.c
> +++ b/app/test-pmd/cmdline.c
> @@ -76,6 +76,7 @@
> #include <rte_devargs.h>
> #include <rte_eth_ctrl.h>
> #include <rte_flow.h>
> +#include <rte_gro.h>
>
> #include <cmdline_rdline.h>
> #include <cmdline_parse.h>
> @@ -419,6 +420,14 @@ static void cmd_help_long_parsed(void
> *parsed_result,
> "tso show (portid)"
> " Display the status of TCP Segmentation
> Offload.\n\n"
>
> + "gro (on|off) (port_id)"
> + " Enable or disable Generic Receive Offload in io"
> + " forward engine.\n\n"
> +
> + "gro set (max_flow_num)
> (max_item_num_per_flow) (port_id)\n"
> + " Set max flow number and max packet number
> per-flow"
> + " for GRO.\n\n"
> +
> "set fwd (%s)\n"
> " Set packet forwarding mode.\n\n"
>
> @@ -3827,6 +3836,120 @@ cmdline_parse_inst_t cmd_tunnel_tso_show = {
> },
> };
>
> +/* *** SET GRO FOR A PORT *** */
> +struct cmd_gro_result {
> + cmdline_fixed_string_t cmd_keyword;
> + cmdline_fixed_string_t mode;
> + uint8_t port_id;
> +};
> +
> +static void
> +cmd_enable_gro_parsed(void *parsed_result,
> + __attribute__((unused)) struct cmdline *cl,
> + __attribute__((unused)) void *data)
> +{
> + struct cmd_gro_result *res;
> +
> + res = parsed_result;
> + setup_gro(res->mode, res->port_id);
> +}
> +
> +cmdline_parse_token_string_t cmd_gro_keyword =
> + TOKEN_STRING_INITIALIZER(struct cmd_gro_result,
> + cmd_keyword, "gro");
> +cmdline_parse_token_string_t cmd_gro_mode =
> + TOKEN_STRING_INITIALIZER(struct cmd_gro_result,
> + mode, "on#off");
> +cmdline_parse_token_num_t cmd_gro_pid =
> + TOKEN_NUM_INITIALIZER(struct cmd_gro_result,
> + port_id, UINT8);
> +
> +cmdline_parse_inst_t cmd_enable_gro = {
> + .f = cmd_enable_gro_parsed,
> + .data = NULL,
> + .help_str = "gro (on|off) (port_id)",
> + .tokens = {
> + (void *)&cmd_gro_keyword,
> + (void *)&cmd_gro_mode,
> + (void *)&cmd_gro_pid,
> + NULL,
> + },
> +};
> +
> +/* *** SET MAX FLOW NUMBER AND ITEM NUM PER FLOW FOR GRO ***
> */
> +struct cmd_gro_set_result {
> + cmdline_fixed_string_t gro;
> + cmdline_fixed_string_t mode;
> + uint16_t flow_num;
> + uint16_t item_num_per_flow;
> + uint8_t port_id;
> +};
> +
> +static void
> +cmd_gro_set_parsed(void *parsed_result,
> + __attribute__((unused)) struct cmdline *cl,
> + __attribute__((unused)) void *data)
> +{
> + struct cmd_gro_set_result *res = parsed_result;
> +
> + if (port_id_is_invalid(res->port_id, ENABLED_WARN))
> + return;
> + if (test_done == 0) {
> + printf("Before set GRO flow_num and item_num_per_flow,"
> + " please stop forwarding first\n");
> + return;
> + }
> +
> + if (!strcmp(res->mode, "set")) {
> + if (res->flow_num == 0)
> + printf("Invalid flow number. Revert to default value:"
> + " %u.\n",
> GRO_DEFAULT_FLOW_NUM);
> + else
> + gro_ports[res->port_id].param.max_flow_num =
> + res->flow_num;
> +
> + if (res->item_num_per_flow == 0)
> + printf("Invalid item number per-flow. Revert"
> + " to default value:%u.\n",
> +
> GRO_DEFAULT_ITEM_NUM_PER_FLOW);
> + else
> + gro_ports[res->port_id].param.max_item_per_flow
> =
> + res->item_num_per_flow;
> + }
> +}
> +
> +cmdline_parse_token_string_t cmd_gro_set_gro =
> + TOKEN_STRING_INITIALIZER(struct cmd_gro_set_result,
> + gro, "gro");
> +cmdline_parse_token_string_t cmd_gro_set_mode =
> + TOKEN_STRING_INITIALIZER(struct cmd_gro_set_result,
> + mode, "set");
> +cmdline_parse_token_num_t cmd_gro_set_flow_num =
> + TOKEN_NUM_INITIALIZER(struct cmd_gro_set_result,
> + flow_num, UINT16);
> +cmdline_parse_token_num_t cmd_gro_set_item_num_per_flow =
> + TOKEN_NUM_INITIALIZER(struct cmd_gro_set_result,
> + item_num_per_flow, UINT16);
> +cmdline_parse_token_num_t cmd_gro_set_portid =
> + TOKEN_NUM_INITIALIZER(struct cmd_gro_set_result,
> + port_id, UINT8);
> +
> +cmdline_parse_inst_t cmd_gro_set = {
> + .f = cmd_gro_set_parsed,
> + .data = NULL,
> + .help_str = "gro set <max_flow_num> <max_item_num_per_flow>
> "
> + "<port_id>: set max flow number and max packet number
> per-flow "
> + "for GRO",
> + .tokens = {
> + (void *)&cmd_gro_set_gro,
> + (void *)&cmd_gro_set_mode,
> + (void *)&cmd_gro_set_flow_num,
> + (void *)&cmd_gro_set_item_num_per_flow,
> + (void *)&cmd_gro_set_portid,
> + NULL,
> + },
> +};
> +
> /* *** ENABLE/DISABLE FLUSH ON RX STREAMS *** */
> struct cmd_set_flush_rx {
> cmdline_fixed_string_t set;
> @@ -13732,6 +13855,8 @@ cmdline_parse_ctx_t main_ctx[] = {
> (cmdline_parse_inst_t *)&cmd_tso_show,
> (cmdline_parse_inst_t *)&cmd_tunnel_tso_set,
> (cmdline_parse_inst_t *)&cmd_tunnel_tso_show,
> + (cmdline_parse_inst_t *)&cmd_enable_gro,
> + (cmdline_parse_inst_t *)&cmd_gro_set,
> (cmdline_parse_inst_t *)&cmd_link_flow_control_set,
> (cmdline_parse_inst_t *)&cmd_link_flow_control_set_rx,
> (cmdline_parse_inst_t *)&cmd_link_flow_control_set_tx,
> diff --git a/app/test-pmd/config.c b/app/test-pmd/config.c
> index b0b340e..2a33a63 100644
> --- a/app/test-pmd/config.c
> +++ b/app/test-pmd/config.c
> @@ -71,6 +71,7 @@
> #ifdef RTE_LIBRTE_BNXT_PMD
> #include <rte_pmd_bnxt.h>
> #endif
> +#include <rte_gro.h>
>
> #include "testpmd.h"
>
> @@ -2414,6 +2415,42 @@ set_tx_pkt_segments(unsigned *seg_lengths,
> unsigned nb_segs)
> tx_pkt_nb_segs = (uint8_t) nb_segs;
> }
>
> +void
> +setup_gro(const char *mode, uint8_t port_id)
> +{
> + if (!rte_eth_dev_is_valid_port(port_id)) {
> + printf("invalid port id %u\n", port_id);
> + return;
> + }
> + if (test_done == 0) {
> + printf("Before enable/disable GRO,"
> + " please stop forwarding first\n");
> + return;
> + }
> + if (strcmp(mode, "on") == 0) {
> + if (gro_ports[port_id].enable) {
> + printf("port %u has enabled GRO\n", port_id);
> + return;
> + }
> + gro_ports[port_id].enable = 1;
> + gro_ports[port_id].param.desired_gro_types =
> GRO_TCP_IPV4;
> + gro_ports[port_id].param.max_packet_size = UINT16_MAX;
> +
> + if (gro_ports[port_id].param.max_flow_num == 0)
> + gro_ports[port_id].param.max_flow_num =
> + GRO_DEFAULT_FLOW_NUM;
> + if (gro_ports[port_id].param.max_item_per_flow == 0)
> + gro_ports[port_id].param.max_item_per_flow =
> + GRO_DEFAULT_ITEM_NUM_PER_FLOW;
> + } else {
> + if (gro_ports[port_id].enable == 0) {
> + printf("port %u has disabled GRO\n", port_id);
> + return;
> + }
> + gro_ports[port_id].enable = 0;
> + }
> +}
> +
> char*
> list_pkt_forwarding_modes(void)
> {
> diff --git a/app/test-pmd/csumonly.c b/app/test-pmd/csumonly.c
> index 66fc9a0..430bd8b 100644
> --- a/app/test-pmd/csumonly.c
> +++ b/app/test-pmd/csumonly.c
> @@ -71,6 +71,7 @@
> #include <rte_prefetch.h>
> #include <rte_string_fns.h>
> #include <rte_flow.h>
> +#include <rte_gro.h>
> #include "testpmd.h"
>
> #define IP_DEFTTL 64 /* from RFC 1340. */
> @@ -658,6 +659,10 @@ pkt_burst_checksum_forward(struct fwd_stream
> *fs)
> nb_pkt_per_burst);
> if (unlikely(nb_rx == 0))
> return;
> + if (unlikely(gro_ports[fs->rx_port].enable))
> + nb_rx = rte_gro_reassemble_burst(pkts_burst,
> + nb_rx,
> + gro_ports[fs->rx_port].param);
>
> #ifdef RTE_TEST_PMD_RECORD_BURST_STATS
> fs->rx_burst_stats.pkt_burst_spread[nb_rx]++;
> diff --git a/app/test-pmd/testpmd.c b/app/test-pmd/testpmd.c
> index b29328a..ed27c7a 100644
> --- a/app/test-pmd/testpmd.c
> +++ b/app/test-pmd/testpmd.c
> @@ -90,6 +90,7 @@
> #ifdef RTE_LIBRTE_LATENCY_STATS
> #include <rte_latencystats.h>
> #endif
> +#include <rte_gro.h>
>
> #include "testpmd.h"
>
> @@ -378,6 +379,8 @@ lcoreid_t bitrate_lcore_id;
> uint8_t bitrate_enabled;
> #endif
>
> +struct gro_status gro_ports[RTE_MAX_ETHPORTS];
> +
> /* Forward function declarations */
> static void map_port_queue_stats_mapping_registers(uint8_t pi, struct
> rte_port *port);
> static void check_all_ports_link_status(uint32_t port_mask);
> diff --git a/app/test-pmd/testpmd.h b/app/test-pmd/testpmd.h
> index 364502d..377d933 100644
> --- a/app/test-pmd/testpmd.h
> +++ b/app/test-pmd/testpmd.h
> @@ -34,6 +34,8 @@
> #ifndef _TESTPMD_H_
> #define _TESTPMD_H_
>
> +#include <rte_gro.h>
> +
> #define RTE_PORT_ALL (~(portid_t)0x0)
>
> #define RTE_TEST_RX_DESC_MAX 2048
> @@ -428,6 +430,14 @@ extern struct ether_addr
> peer_eth_addrs[RTE_MAX_ETHPORTS];
> extern uint32_t burst_tx_delay_time; /**< Burst tx delay time(us) for mac-
> retry. */
> extern uint32_t burst_tx_retry_num; /**< Burst tx retry number for mac-
> retry. */
>
> +#define GRO_DEFAULT_FLOW_NUM 4
> +#define GRO_DEFAULT_ITEM_NUM_PER_FLOW DEF_PKT_BURST
> +struct gro_status {
> + struct rte_gro_param param;
> + uint8_t enable;
> +};
> +extern struct gro_status gro_ports[RTE_MAX_ETHPORTS];
> +
> static inline unsigned int
> lcore_num(void)
> {
> @@ -626,6 +636,7 @@ void get_2tuple_filter(uint8_t port_id, uint16_t
> index);
> void get_5tuple_filter(uint8_t port_id, uint16_t index);
> int rx_queue_id_is_invalid(queueid_t rxq_id);
> int tx_queue_id_is_invalid(queueid_t txq_id);
> +void setup_gro(const char *mode, uint8_t port_id);
>
> /* Functions to manage the set of filtered Multicast MAC addresses */
> void mcast_addr_add(uint8_t port_id, struct ether_addr *mc_addr);
> diff --git a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> index 2b9a1ea..528c833 100644
> --- a/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> +++ b/doc/guides/testpmd_app_ug/testpmd_funcs.rst
> @@ -884,6 +884,40 @@ Display the status of TCP Segmentation Offload::
>
> testpmd> tso show (port_id)
>
> +gro
> +~~~~~~~~
> +
> +Enable or disable GRO in ``csum`` forwarding engine::
> +
> + testpmd> gro (on|off) (port_id)
> +
> +If enabled, the csum forwarding engine will perform GRO on the TCP/IPv4
> +packets received from the given port.
> +
> +If disabled, packets received from the given port won't be performed
> +GRO. By default, GRO is disabled for all ports.
> +
> +.. note::
> +
> + When enable GRO for a port, TCP/IPv4 packets received from the port
> + will be performed GRO. After GRO, the merged packets are multi-
> segments.
> + But csum forwarding engine doesn't support to calculate TCP checksum
> + for multi-segment packets in SW. So please select TCP HW checksum
> + calculation for the port which GROed packets are transmitted to.
> +
> +gro set
> +~~~~~~~~
> +
> +Set max flow number and max packet number per-flow for GRO::
> +
> + testpmd> gro set (max_flow_num) (max_item_num_per_flow) (port_id)
> +
> +The product of ``max_flow_num`` and ``max_item_num_per_flow`` is the
> max
> +number of packets a GRO table can store.
> +
> +If current packet number is greater than or equal to the max value, GRO
> +will stop processing incoming packets.
> +
> mac_addr add
> ~~~~~~~~~~~~
>
> --
> 2.7.4
