From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jingjing Wu Subject: =?utf-8?q?=5BPATCH_v2_3/3=5D_examples/vmdq=5Fdcb=3A_ex?= =?utf-8?q?tend_sample_for_X710_supporting?= Date: Wed, 17 Feb 2016 14:58:20 +0800 Message-ID: <1455692300-17883-4-git-send-email-jingjing.wu@intel.com> References: <1453280236-8778-1-git-send-email-jingjing.wu@intel.com> <1455692300-17883-1-git-send-email-jingjing.wu@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: dev@dpdk.org To: bruce.richardson@intel.com Return-path: Received: from mga01.intel.com (mga01.intel.com [192.55.52.88]) by dpdk.org (Postfix) with ESMTP id ED506C318 for ; Wed, 17 Feb 2016 07:58:34 +0100 (CET) In-Reply-To: <1455692300-17883-1-git-send-email-jingjing.wu@intel.com> List-Id: patches and discussions about DPDK List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org Sender: "dev" Currently, the example vmdq_dcb only works on Intel(R) 82599 NICs. This patch extended this sample to make it work both on Intel(R) 82599 and X710/XL710 NICs by following changes: 1. add VMDQ base queue checking to avoid forwarding on PF queues. 2. assign each VMDQ pools with MAC address. 3. add more arguments (nb-tcs, enable-rss) to change the default setting 4. extend the max number of queues from 128 to 1024. This patch also reworked the user guide for the vmdq_dcb sample. Signed-off-by: Jingjing Wu --- doc/guides/sample_app_ug/vmdq_dcb_forwarding.rst | 171 ++++++---- examples/vmdq_dcb/main.c | 390 +++++++++++++++++= +----- 2 files changed, 430 insertions(+), 131 deletions(-) diff --git a/doc/guides/sample_app_ug/vmdq_dcb_forwarding.rst b/doc/guide= s/sample_app_ug/vmdq_dcb_forwarding.rst index 9140a22..305636b 100644 --- a/doc/guides/sample_app_ug/vmdq_dcb_forwarding.rst +++ b/doc/guides/sample_app_ug/vmdq_dcb_forwarding.rst @@ -32,8 +32,8 @@ VMDQ and DCB Forwarding Sample Application =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D =20 The VMDQ and DCB Forwarding sample application is a simple example of pa= cket processing using the DPDK. -The application performs L2 forwarding using VMDQ and DCB to divide the = incoming traffic into 128 queues. -The traffic splitting is performed in hardware by the VMDQ and DCB featu= res of the Intel=C2=AE 82599 10 Gigabit Ethernet Controller. +The application performs L2 forwarding using VMDQ and DCB to divide the = incoming traffic into queues. +The traffic splitting is performed in hardware by the VMDQ and DCB featu= res of the Intel=C2=AE 82599 and X710/XL710 Ethernet Controllers. =20 Overview -------- @@ -41,28 +41,27 @@ Overview This sample application can be used as a starting point for developing a= new application that is based on the DPDK and uses VMDQ and DCB for traffic partitioning. =20 -The VMDQ and DCB filters work on VLAN traffic to divide the traffic into= 128 input queues on the basis of the VLAN ID field and -VLAN user priority field. -VMDQ filters split the traffic into 16 or 32 groups based on the VLAN ID= . -Then, DCB places each packet into one of either 4 or 8 queues within tha= t group, based upon the VLAN user priority field. - -In either case, 16 groups of 8 queues, or 32 groups of 4 queues, the tra= ffic can be split into 128 hardware queues on the NIC, -each of which can be polled individually by a DPDK application. +The VMDQ and DCB filters work on MAC and VLAN traffic to divide the traf= fic into input queues on the basis of the Destination MAC +address, VLAN ID and VLAN user priority fields. +VMDQ filters split the traffic into 16 or 32 groups based on the Destina= tion MAC and VLAN ID. +Then, DCB places each packet into one of queues within that group, based= upon the VLAN user priority field. =20 All traffic is read from a single incoming port (port 0) and output on p= ort 1, without any processing being performed. -The traffic is split into 128 queues on input, where each thread of the = application reads from multiple queues. -For example, when run with 8 threads, that is, with the -c FF option, ea= ch thread receives and forwards packets from 16 queues. +With Intel=C2=AE 82599 NIC, for example, the traffic is split into 128 q= ueues on input, where each thread of the application reads from +multiple queues. When run with 8 threads, that is, with the -c FF option= , each thread receives and forwards packets from 16 queues. =20 -As supplied, the sample application configures the VMDQ feature to have = 16 pools with 8 queues each as indicated in :numref:`figure_vmdq_dcb_exam= ple`. -The Intel=C2=AE 82599 10 Gigabit Ethernet Controller NIC also supports t= he splitting of traffic into 32 pools of 4 queues each and -this can be used by changing the NUM_POOLS parameter in the supplied cod= e. -The NUM_POOLS parameter can be passed on the command line, after the EAL= parameters: +As supplied, the sample application configures the VMDQ feature to have = 32 pools with 4 queues each as indicated in :numref:`figure_vmdq_dcb_exam= ple`. +The Intel=C2=AE 82599 10 Gigabit Ethernet Controller NIC also supports t= he splitting of traffic into 16 pools of 8 queues. While the +Intel=C2=AE X710 or XL710 Ethernet Controller NICs support many configur= ations of VMDQ pools of 4 or 8 queues each. For simplicity, only 16 +or 32 pools is supported in this sample. And queues numbers for each VMD= Q pool can be changed by setting CONFIG_RTE_LIBRTE_I40E_QUEUE_NUM_PER_VM +in config/common_* file. +The nb-pools, nb-tcs and enable-rss parameters can be passed on the comm= and line, after the EAL parameters: =20 .. code-block:: console =20 - ./build/vmdq_dcb [EAL options] -- -p PORTMASK --nb-pools NP + ./build/vmdq_dcb [EAL options] -- -p PORTMASK --nb-pools NP --nb-tcs= TC --enable-rss =20 -where, NP can be 16 or 32. +where, NP can be 16 or 32, TC can be 4 or 8, rss is disabled by default. =20 .. _figure_vmdq_dcb_example: =20 @@ -72,9 +71,7 @@ where, NP can be 16 or 32. =20 =20 In Linux* user space, the application can display statistics with the nu= mber of packets received on each queue. -To have the application display the statistics, send a SIGHUP signal to = the running application process, as follows: - -where, is the process id of the application process. +To have the application display the statistics, send a SIGHUP signal to = the running application process. =20 The VMDQ and DCB Forwarding sample application is in many ways simpler t= han the L2 Forwarding application (see Chapter 9 , "L2 Forwarding Sample Application (in Real and Virtuali= zed Environments)") @@ -117,7 +114,7 @@ To run the example in a linuxapp environment: =20 .. code-block:: console =20 - user@target:~$ ./build/vmdq_dcb -c f -n 4 -- -p 0x3 --nb-pools 16 + user@target:~$ ./build/vmdq_dcb -c f -n 4 -- -p 0x3 --nb-pools 32 --= nb-tcs 4 =20 Refer to the *DPDK Getting Started Guide* for general information on run= ning applications and the Environment Abstraction Layer (EAL) options. @@ -143,34 +140,48 @@ a default structure is provided for VMDQ and DCB co= nfiguration to be filled in l .. code-block:: c =20 /* empty vmdq+dcb configuration structure. Filled in programmaticall= y */ - static const struct rte_eth_conf vmdq_dcb_conf_default =3D { .rxmode =3D { - .mq_mode =3D ETH_VMDQ_DCB, + .mq_mode =3D ETH_MQ_RX_VMDQ_DCB, .split_hdr_size =3D 0, - .header_split =3D 0, /**< Header Split disabled */ + .header_split =3D 0, /**< Header Split disabled */ .hw_ip_checksum =3D 0, /**< IP checksum offload disabled */ .hw_vlan_filter =3D 0, /**< VLAN filtering disabled */ - .jumbo_frame =3D 0, /**< Jumbo Frame Support disabled */ + .jumbo_frame =3D 0, /**< Jumbo Frame Support disabled */ }, - .txmode =3D { - .mq_mode =3D ETH_DCB_NONE, + .mq_mode =3D ETH_MQ_TX_VMDQ_DCB, }, - + /* + * should be overridden separately in code with + * appropriate values + */ .rx_adv_conf =3D { - /* - * should be overridden separately in code with - * appropriate values - */ - .vmdq_dcb_conf =3D { - .nb_queue_pools =3D ETH_16_POOLS, + .nb_queue_pools =3D ETH_32_POOLS, + .enable_default_pool =3D 0, + .default_pool =3D 0, + .nb_pool_maps =3D 0, + .pool_map =3D {{0, 0},}, + .dcb_tc =3D {0}, + }, + .dcb_rx_conf =3D { + .nb_tcs =3D ETH_4_TCS, + /** Traffic class each UP mapped to. */ + .dcb_tc =3D {0}, + }, + .vmdq_rx_conf =3D { + .nb_queue_pools =3D ETH_32_POOLS, .enable_default_pool =3D 0, .default_pool =3D 0, .nb_pool_maps =3D 0, .pool_map =3D {{0, 0},}, - .dcb_queue =3D {0}, + }, + }, + .tx_adv_conf =3D { + .vmdq_dcb_tx_conf =3D { + .nb_queue_pools =3D ETH_32_POOLS, + .dcb_tc =3D {0}, }, }, }; @@ -178,11 +189,17 @@ a default structure is provided for VMDQ and DCB co= nfiguration to be filled in l The get_eth_conf() function fills in an rte_eth_conf structure with the = appropriate values, based on the global vlan_tags array, and dividing up the possible user priority values equally among the indi= vidual queues -(also referred to as traffic classes) within each pool, that is, -if the number of pools is 32, then the user priority fields are allocate= d two to a queue. +(also referred to as traffic classes) within each pool. With Intel=C2=AE= 82599 NIC, +if the number of pools is 32, then the user priority fields are allocate= d 2 to a queue. If 16 pools are used, then each of the 8 user priority fields is allocat= ed to its own queue within the pool. +With Intel=C2=AE X710/XL710 NICs, if number of tcs is 4, and number of q= ueues in pool is 8, +then the user priority fields are allocated 2 to one tc, and a tc has 2 = queues mapping to it, then +RSS will determine the destination queue in 2. For the VLAN IDs, each one can be allocated to possibly multiple pools o= f queues, so the pools parameter in the rte_eth_vmdq_dcb_conf structure is specifi= ed as a bitmask value. +For destination MAC, each VMDQ pool will be assigned with a MAC address.= In this sample, each VMDQ pool +is assigned to the MAC like 52:54:00:12::, that is, +the MAC of VMDQ pool 2 on port 1 is 52:54:00:12:01:02. =20 .. code-block:: c =20 @@ -193,38 +210,84 @@ so the pools parameter in the rte_eth_vmdq_dcb_conf= structure is specified as a 24, 25, 26, 27, 28, 29, 30, 31 }; =20 + /* pool mac addr template, pool mac addr is like: 52 54 00 12 port# = pool# */ + static struct ether_addr pool_addr_template =3D { + .addr_bytes =3D {0x52, 0x54, 0x00, 0x12, 0x00, 0x00} + }; =20 /* Builds up the correct configuration for vmdq+dcb based on the vla= n tags array * given above, and the number of traffic classes available for use.= */ - static inline int - get_eth_conf(struct rte_eth_conf *eth_conf, enum rte_eth_nb_pools nu= m_pools) + get_eth_conf(struct rte_eth_conf *eth_conf) { struct rte_eth_vmdq_dcb_conf conf; - unsigned i; - - if (num_pools !=3D ETH_16_POOLS && num_pools !=3D ETH_32_POOLS )= return -1; - - conf.nb_queue_pools =3D num_pools; + struct rte_eth_vmdq_rx_conf vmdq_conf; + struct rte_eth_dcb_rx_conf dcb_conf; + struct rte_eth_vmdq_dcb_tx_conf tx_conf; + uint8_t i; + + conf.nb_queue_pools =3D (enum rte_eth_nb_pools)num_pools; + vmdq_conf.nb_queue_pools =3D (enum rte_eth_nb_pools)num_pools; + tx_conf.nb_queue_pools =3D (enum rte_eth_nb_pools)num_pools; + conf.nb_pool_maps =3D num_pools; + vmdq_conf.nb_pool_maps =3D num_pools; conf.enable_default_pool =3D 0; + vmdq_conf.enable_default_pool =3D 0; conf.default_pool =3D 0; /* set explicit value, even if not used= */ - conf.nb_pool_maps =3D sizeof( vlan_tags )/sizeof( vlan_tags[ 0 ]= ); + vmdq_conf.default_pool =3D 0; =20 - for (i =3D 0; i < conf.nb_pool_maps; i++){ - conf.pool_map[i].vlan_id =3D vlan_tags[ i ]; - conf.pool_map[i].pools =3D 1 << (i % num_pools); + for (i =3D 0; i < conf.nb_pool_maps; i++) { + conf.pool_map[i].vlan_id =3D vlan_tags[i]; + vmdq_conf.pool_map[i].vlan_id =3D vlan_tags[i]; + conf.pool_map[i].pools =3D 1UL << i ; + vmdq_conf.pool_map[i].pools =3D 1UL << i; } - for (i =3D 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++){ - conf.dcb_queue[i] =3D (uint8_t)(i % (NUM_QUEUES/num_pools)); + conf.dcb_tc[i] =3D i % num_tcs; + dcb_conf.dcb_tc[i] =3D i % num_tcs; + tx_conf.dcb_tc[i] =3D i % num_tcs; + } + dcb_conf.nb_tcs =3D (enum rte_eth_nb_tcs)num_tcs; + (void)(rte_memcpy(eth_conf, &vmdq_dcb_conf_default, sizeof(*eth_= conf))); + (void)(rte_memcpy(ð_conf->rx_adv_conf.vmdq_dcb_conf, &conf, + sizeof(conf))); + (void)(rte_memcpy(ð_conf->rx_adv_conf.dcb_rx_conf, &dcb_conf, + sizeof(dcb_conf))); + (void)(rte_memcpy(ð_conf->rx_adv_conf.vmdq_rx_conf, &vmdq_con= f, + sizeof(vmdq_conf))); + (void)(rte_memcpy(ð_conf->tx_adv_conf.vmdq_dcb_tx_conf, &tx_c= onf, + sizeof(tx_conf))); + if (rss_enable) { + eth_conf->rxmode.mq_mode=3D ETH_MQ_RX_VMDQ_DCB_RSS; + eth_conf->rx_adv_conf.rss_conf.rss_hf =3D ETH_RSS_IP | + ETH_RSS_UDP | + ETH_RSS_TCP | + ETH_RSS_SCTP; } - - (void) rte_memcpy(eth_conf, &vmdq_dcb_conf_default, sizeof(\*eth= _conf)); - (void) rte_memcpy(ð_conf->rx_adv_conf.vmdq_dcb_conf, &conf, s= izeof(eth_conf->rx_adv_conf.vmdq_dcb_conf)); - return 0; } =20 + ...... + + /* Set mac for each pool.*/ + for (q =3D 0; q < num_pools; q++) { + struct ether_addr mac; + mac =3D pool_addr_template; + mac.addr_bytes[4] =3D port; + mac.addr_bytes[5] =3D q; + printf("Port %u vmdq pool %u set mac %02x:%02x:%02x:%02x:%02x:%0= 2x\n", + port, q, + mac.addr_bytes[0], mac.addr_bytes[1], + mac.addr_bytes[2], mac.addr_bytes[3], + mac.addr_bytes[4], mac.addr_bytes[5]); + retval =3D rte_eth_dev_mac_addr_add(port, &mac, + q + vmdq_pool_base); + if (retval) { + printf("mac addr add failed at pool %d\n", q); + return retval; + } + } + Once the network port has been initialized using the correct VMDQ and DC= B values, the initialization of the port's RX and TX hardware rings is performed s= imilarly to that in the L2 Forwarding sample application. diff --git a/examples/vmdq_dcb/main.c b/examples/vmdq_dcb/main.c index b90ac28..5655a9a 100644 --- a/examples/vmdq_dcb/main.c +++ b/examples/vmdq_dcb/main.c @@ -70,18 +70,36 @@ #include =20 /* basic constants used in application */ -#define NUM_QUEUES 128 - -#define NUM_MBUFS 64*1024 +#define MAX_QUEUES 1024 +/* + * 1024 queues require to meet the needs of a large number of vmdq_pools= . + * (RX/TX_queue_nb * RX/TX_ring_descriptors_nb) per port. + */ +#define NUM_MBUFS_PER_PORT (MAX_QUEUES * RTE_MAX(RTE_TEST_RX_DESC_DEFAUL= T, \ + RTE_TEST_TX_DESC_DEFAULT)) #define MBUF_CACHE_SIZE 64 =20 +#define MAX_PKT_BURST 32 + +/* + * Configurable number of RX/TX ring descriptors + */ +#define RTE_TEST_RX_DESC_DEFAULT 128 +#define RTE_TEST_TX_DESC_DEFAULT 512 + #define INVALID_PORT_ID 0xFF =20 /* mask of enabled ports */ -static uint32_t enabled_port_mask =3D 0; +static uint32_t enabled_port_mask; +static uint8_t ports[RTE_MAX_ETHPORTS]; +static unsigned num_ports; =20 -/* number of pools (if user does not specify any, 16 by default */ -static enum rte_eth_nb_pools num_pools =3D ETH_16_POOLS; +/* number of pools (if user does not specify any, 32 by default */ +static enum rte_eth_nb_pools num_pools =3D ETH_32_POOLS; +static enum rte_eth_nb_tcs num_tcs =3D ETH_4_TCS; +static uint16_t num_queues, num_vmdq_queues; +static uint16_t vmdq_pool_base, vmdq_queue_base; +static uint8_t rss_enable; =20 /* empty vmdq+dcb configuration structure. Filled in programatically */ static const struct rte_eth_conf vmdq_dcb_conf_default =3D { @@ -94,29 +112,44 @@ static const struct rte_eth_conf vmdq_dcb_conf_defau= lt =3D { .jumbo_frame =3D 0, /**< Jumbo Frame Support disabled */ }, .txmode =3D { - .mq_mode =3D ETH_MQ_TX_NONE, + .mq_mode =3D ETH_MQ_TX_VMDQ_DCB, }, + /* + * should be overridden separately in code with + * appropriate values + */ .rx_adv_conf =3D { - /* - * should be overridden separately in code with - * appropriate values - */ .vmdq_dcb_conf =3D { - .nb_queue_pools =3D ETH_16_POOLS, + .nb_queue_pools =3D ETH_32_POOLS, .enable_default_pool =3D 0, .default_pool =3D 0, .nb_pool_maps =3D 0, .pool_map =3D {{0, 0},}, .dcb_tc =3D {0}, }, + .dcb_rx_conf =3D { + .nb_tcs =3D ETH_4_TCS, + /** Traffic class each UP mapped to. */ + .dcb_tc =3D {0}, + }, + .vmdq_rx_conf =3D { + .nb_queue_pools =3D ETH_32_POOLS, + .enable_default_pool =3D 0, + .default_pool =3D 0, + .nb_pool_maps =3D 0, + .pool_map =3D {{0, 0},}, + }, + }, + .tx_adv_conf =3D { + .vmdq_dcb_tx_conf =3D { + .nb_queue_pools =3D ETH_32_POOLS, + .dcb_tc =3D {0}, + }, }, }; =20 -static uint8_t ports[RTE_MAX_ETHPORTS]; -static unsigned num_ports =3D 0; - /* array used for printing out statistics */ -volatile unsigned long rxPackets[ NUM_QUEUES ] =3D {0}; +volatile unsigned long rxPackets[MAX_QUEUES] =3D {0}; =20 const uint16_t vlan_tags[] =3D { 0, 1, 2, 3, 4, 5, 6, 7, @@ -125,30 +158,64 @@ const uint16_t vlan_tags[] =3D { 24, 25, 26, 27, 28, 29, 30, 31 }; =20 +const uint16_t num_vlans =3D RTE_DIM(vlan_tags); +/* pool mac addr template, pool mac addr is like: 52 54 00 12 port# pool= # */ +static struct ether_addr pool_addr_template =3D { + .addr_bytes =3D {0x52, 0x54, 0x00, 0x12, 0x00, 0x00} +}; + +/* ethernet addresses of ports */ +static struct ether_addr vmdq_ports_eth_addr[RTE_MAX_ETHPORTS]; + /* Builds up the correct configuration for vmdq+dcb based on the vlan ta= gs array * given above, and the number of traffic classes available for use. */ static inline int -get_eth_conf(struct rte_eth_conf *eth_conf, enum rte_eth_nb_pools num_po= ols) +get_eth_conf(struct rte_eth_conf *eth_conf) { struct rte_eth_vmdq_dcb_conf conf; - unsigned i; - - if (num_pools !=3D ETH_16_POOLS && num_pools !=3D ETH_32_POOLS ) return= -1; - - conf.nb_queue_pools =3D num_pools; + struct rte_eth_vmdq_rx_conf vmdq_conf; + struct rte_eth_dcb_rx_conf dcb_conf; + struct rte_eth_vmdq_dcb_tx_conf tx_conf; + uint8_t i; + + conf.nb_queue_pools =3D (enum rte_eth_nb_pools)num_pools; + vmdq_conf.nb_queue_pools =3D (enum rte_eth_nb_pools)num_pools; + tx_conf.nb_queue_pools =3D (enum rte_eth_nb_pools)num_pools; + conf.nb_pool_maps =3D num_pools; + vmdq_conf.nb_pool_maps =3D num_pools; conf.enable_default_pool =3D 0; + vmdq_conf.enable_default_pool =3D 0; conf.default_pool =3D 0; /* set explicit value, even if not used */ - conf.nb_pool_maps =3D sizeof( vlan_tags )/sizeof( vlan_tags[ 0 ]); - for (i =3D 0; i < conf.nb_pool_maps; i++){ - conf.pool_map[i].vlan_id =3D vlan_tags[ i ]; - conf.pool_map[i].pools =3D 1 << (i % num_pools); + vmdq_conf.default_pool =3D 0; + + for (i =3D 0; i < conf.nb_pool_maps; i++) { + conf.pool_map[i].vlan_id =3D vlan_tags[i]; + vmdq_conf.pool_map[i].vlan_id =3D vlan_tags[i]; + conf.pool_map[i].pools =3D 1UL << i; + vmdq_conf.pool_map[i].pools =3D 1UL << i; } for (i =3D 0; i < ETH_DCB_NUM_USER_PRIORITIES; i++){ - conf.dcb_tc[i] =3D (uint8_t)(i % (NUM_QUEUES/num_pools)); + conf.dcb_tc[i] =3D i % num_tcs; + dcb_conf.dcb_tc[i] =3D i % num_tcs; + tx_conf.dcb_tc[i] =3D i % num_tcs; } + dcb_conf.nb_tcs =3D (enum rte_eth_nb_tcs)num_tcs; (void)(rte_memcpy(eth_conf, &vmdq_dcb_conf_default, sizeof(*eth_conf)))= ; (void)(rte_memcpy(ð_conf->rx_adv_conf.vmdq_dcb_conf, &conf, - sizeof(eth_conf->rx_adv_conf.vmdq_dcb_conf))); + sizeof(conf))); + (void)(rte_memcpy(ð_conf->rx_adv_conf.dcb_rx_conf, &dcb_conf, + sizeof(dcb_conf))); + (void)(rte_memcpy(ð_conf->rx_adv_conf.vmdq_rx_conf, &vmdq_conf, + sizeof(vmdq_conf))); + (void)(rte_memcpy(ð_conf->tx_adv_conf.vmdq_dcb_tx_conf, &tx_conf, + sizeof(tx_conf))); + if (rss_enable) { + eth_conf->rxmode.mq_mode =3D ETH_MQ_RX_VMDQ_DCB_RSS; + eth_conf->rx_adv_conf.rss_conf.rss_hf =3D ETH_RSS_IP | + ETH_RSS_UDP | + ETH_RSS_TCP | + ETH_RSS_SCTP; + } return 0; } =20 @@ -159,51 +226,136 @@ get_eth_conf(struct rte_eth_conf *eth_conf, enum r= te_eth_nb_pools num_pools) static inline int port_init(uint8_t port, struct rte_mempool *mbuf_pool) { - struct rte_eth_conf port_conf; - const uint16_t rxRings =3D ETH_VMDQ_DCB_NUM_QUEUES, - txRings =3D (uint16_t)rte_lcore_count(); - const uint16_t rxRingSize =3D 128, txRingSize =3D 512; + struct rte_eth_dev_info dev_info; + struct rte_eth_conf port_conf =3D {0}; + const uint16_t rxRingSize =3D RTE_TEST_RX_DESC_DEFAULT; + const uint16_t txRingSize =3D RTE_TEST_TX_DESC_DEFAULT; int retval; uint16_t q; + uint16_t queues_per_pool; + uint32_t max_nb_pools; + + /* + * The max pool number from dev_info will be used to validate the pool + * number specified in cmd line + */ + rte_eth_dev_info_get(port, &dev_info); + max_nb_pools =3D (uint32_t)dev_info.max_vmdq_pools; + /* + * We allow to process part of VMDQ pools specified by num_pools in + * command line. + */ + if (num_pools > max_nb_pools) { + printf("num_pools %d >max_nb_pools %d\n", + num_pools, max_nb_pools); + return -1; + } =20 - retval =3D get_eth_conf(&port_conf, num_pools); + /* + * NIC queues are divided into pf queues and vmdq queues. + * There is assumption here all ports have the same configuration! + */ + vmdq_queue_base =3D dev_info.vmdq_queue_base; + vmdq_pool_base =3D dev_info.vmdq_pool_base; + printf("vmdq queue base: %d pool base %d\n", + vmdq_queue_base, vmdq_pool_base); + if (vmdq_pool_base =3D=3D 0) { + num_vmdq_queues =3D dev_info.max_rx_queues; + num_queues =3D dev_info.max_rx_queues; + if (num_tcs !=3D num_vmdq_queues / num_pools) { + printf("nb_tcs %d is invalid considering with" + " nb_pools %d, nb_tcs * nb_pools should =3D %d\n", + num_tcs, num_pools, num_vmdq_queues); + return -1; + } + } else { + queues_per_pool =3D dev_info.vmdq_queue_num / + dev_info.max_vmdq_pools; + if (num_tcs > queues_per_pool) { + printf("num_tcs %d > num of queues per pool %d\n", + num_tcs, queues_per_pool); + return -1; + } + num_vmdq_queues =3D num_pools * queues_per_pool; + num_queues =3D vmdq_queue_base + num_vmdq_queues; + printf("Configured vmdq pool num: %u," + " each vmdq pool has %u queues\n", + num_pools, queues_per_pool); + } + + if (port >=3D rte_eth_dev_count()) + return -1; + + retval =3D get_eth_conf(&port_conf); if (retval < 0) return retval; =20 - if (port >=3D rte_eth_dev_count()) return -1; - - retval =3D rte_eth_dev_configure(port, rxRings, txRings, &port_conf); + /* + * Though in this example, all queues including pf queues are setup. + * This is because VMDQ queues doesn't always start from zero, and the + * PMD layer doesn't support selectively initialising part of rx/tx + * queues. + */ + retval =3D rte_eth_dev_configure(port, num_queues, num_queues, &port_co= nf); if (retval !=3D 0) return retval; =20 - for (q =3D 0; q < rxRings; q ++) { + for (q =3D 0; q < num_queues; q++) { retval =3D rte_eth_rx_queue_setup(port, q, rxRingSize, - rte_eth_dev_socket_id(port), - NULL, - mbuf_pool); - if (retval < 0) + rte_eth_dev_socket_id(port), + NULL, + mbuf_pool); + if (retval < 0) { + printf("initialize rx queue %d failed\n", q); return retval; + } } =20 - for (q =3D 0; q < txRings; q ++) { + for (q =3D 0; q < num_queues; q++) { retval =3D rte_eth_tx_queue_setup(port, q, txRingSize, - rte_eth_dev_socket_id(port), - NULL); - if (retval < 0) + rte_eth_dev_socket_id(port), + NULL); + if (retval < 0) { + printf("initialize tx queue %d failed\n", q); return retval; + } } =20 retval =3D rte_eth_dev_start(port); - if (retval < 0) + if (retval < 0) { + printf("port %d start failed\n", port); return retval; + } =20 - struct ether_addr addr; - rte_eth_macaddr_get(port, &addr); + rte_eth_macaddr_get(port, &vmdq_ports_eth_addr[port]); printf("Port %u MAC: %02"PRIx8" %02"PRIx8" %02"PRIx8 " %02"PRIx8" %02"PRIx8" %02"PRIx8"\n", (unsigned)port, - addr.addr_bytes[0], addr.addr_bytes[1], addr.addr_bytes[2], - addr.addr_bytes[3], addr.addr_bytes[4], addr.addr_bytes[5]); + vmdq_ports_eth_addr[port].addr_bytes[0], + vmdq_ports_eth_addr[port].addr_bytes[1], + vmdq_ports_eth_addr[port].addr_bytes[2], + vmdq_ports_eth_addr[port].addr_bytes[3], + vmdq_ports_eth_addr[port].addr_bytes[4], + vmdq_ports_eth_addr[port].addr_bytes[5]); + + /* Set mac for each pool.*/ + for (q =3D 0; q < num_pools; q++) { + struct ether_addr mac; + mac =3D pool_addr_template; + mac.addr_bytes[4] =3D port; + mac.addr_bytes[5] =3D q; + printf("Port %u vmdq pool %u set mac %02x:%02x:%02x:%02x:%02x:%02x\n", + port, q, + mac.addr_bytes[0], mac.addr_bytes[1], + mac.addr_bytes[2], mac.addr_bytes[3], + mac.addr_bytes[4], mac.addr_bytes[5]); + retval =3D rte_eth_dev_mac_addr_add(port, &mac, + q + vmdq_pool_base); + if (retval) { + printf("mac addr add failed at pool %d\n", q); + return retval; + } + } =20 return 0; } @@ -229,6 +381,28 @@ vmdq_parse_num_pools(const char *q_arg) return 0; } =20 +/* Check num_tcs parameter and set it if OK*/ +static int +vmdq_parse_num_tcs(const char *q_arg) +{ + char *end =3D NULL; + int n; + + /* parse number string */ + n =3D strtol(q_arg, &end, 10); + if ((q_arg[0] =3D=3D '\0') || (end =3D=3D NULL) || (*end !=3D '\0')) + return -1; + + if (n !=3D 4 && n !=3D 8) + return -1; + if (n =3D=3D 4) + num_tcs =3D ETH_4_TCS; + else + num_tcs =3D ETH_8_TCS; + + return 0; +} + static int parse_portmask(const char *portmask) { @@ -251,7 +425,9 @@ static void vmdq_usage(const char *prgname) { printf("%s [EAL options] -- -p PORTMASK]\n" - " --nb-pools NP: number of pools (16 default, 32)\n", + " --nb-pools NP: number of pools (32 default, 16)\n" + " --nb-tcs NP: number of TCs (4 default, 8)\n" + " --enable-rss: enable RSS (disabled by default)\n", prgname); } =20 @@ -265,11 +441,14 @@ vmdq_parse_args(int argc, char **argv) const char *prgname =3D argv[0]; static struct option long_option[] =3D { {"nb-pools", required_argument, NULL, 0}, + {"nb-tcs", required_argument, NULL, 0}, + {"enable-rss", 0, NULL, 0}, {NULL, 0, 0, 0} }; =20 /* Parse command line */ - while ((opt =3D getopt_long(argc, argv, "p:",long_option,&option_index)= ) !=3D EOF) { + while ((opt =3D getopt_long(argc, argv, "p:", long_option, + &option_index)) !=3D EOF) { switch (opt) { /* portmask */ case 'p': @@ -281,43 +460,71 @@ vmdq_parse_args(int argc, char **argv) } break; case 0: - if (vmdq_parse_num_pools(optarg) =3D=3D -1){ - printf("invalid number of pools\n"); - vmdq_usage(prgname); - return -1; + if (!strcmp(long_option[option_index].name, "nb-pools")) { + if (vmdq_parse_num_pools(optarg) =3D=3D -1) { + printf("invalid number of pools\n"); + return -1; + } } + + if (!strcmp(long_option[option_index].name, "nb-tcs")) { + if (vmdq_parse_num_tcs(optarg) =3D=3D -1) { + printf("invalid number of tcs\n"); + return -1; + } + } + + if (!strcmp(long_option[option_index].name, "enable-rss")) + rss_enable =3D 1; break; + default: vmdq_usage(prgname); return -1; } } =20 - for(i =3D 0; i < RTE_MAX_ETHPORTS; i++) - { + for (i =3D 0; i < RTE_MAX_ETHPORTS; i++) { if (enabled_port_mask & (1 << i)) ports[num_ports++] =3D (uint8_t)i; } =20 if (num_ports < 2 || num_ports % 2) { printf("Current enabled port number is %u," - "but it should be even and at least 2\n",num_ports); + " but it should be even and at least 2\n", num_ports); return -1; } =20 return 0; } =20 +static void +update_mac_address(struct rte_mbuf *m, unsigned dst_port) +{ + struct ether_hdr *eth; + void *tmp; + + eth =3D rte_pktmbuf_mtod(m, struct ether_hdr *); + + /* 02:00:00:00:00:xx */ + tmp =3D ð->d_addr.addr_bytes[0]; + *((uint64_t *)tmp) =3D 0x000000000002 + ((uint64_t)dst_port << 40); + + /* src addr */ + ether_addr_copy(&vmdq_ports_eth_addr[dst_port], ð->s_addr); +} =20 /* When we receive a HUP signal, print out our stats */ static void sighup_handler(int signum) { - unsigned q; - for (q =3D 0; q < NUM_QUEUES; q ++) { - if (q % (NUM_QUEUES/num_pools) =3D=3D 0) - printf("\nPool %u: ", q/(NUM_QUEUES/num_pools)); - printf("%lu ", rxPackets[ q ]); + unsigned q =3D vmdq_queue_base; + + for (; q < num_queues; q++) { + if (q % (num_vmdq_queues / num_pools) =3D=3D 0) + printf("\nPool %u: ", (q - vmdq_queue_base) / + (num_vmdq_queues / num_pools)); + printf("%lu ", rxPackets[q]); } printf("\nFinished handling signal %d\n", signum); } @@ -326,20 +533,43 @@ sighup_handler(int signum) * Main thread that does the work, reading from INPUT_PORT * and writing to OUTPUT_PORT */ -static __attribute__((noreturn)) int +static int lcore_main(void *arg) { const uintptr_t core_num =3D (uintptr_t)arg; const unsigned num_cores =3D rte_lcore_count(); - uint16_t startQueue =3D (uint16_t)(core_num * (NUM_QUEUES/num_cores)); - uint16_t endQueue =3D (uint16_t)(startQueue + (NUM_QUEUES/num_cores)); + uint16_t startQueue, endQueue; uint16_t q, i, p; + const uint16_t quot =3D (uint16_t)(num_vmdq_queues / num_cores); + const uint16_t remainder =3D (uint16_t)(num_vmdq_queues % num_cores); + + + if (remainder) { + if (core_num < remainder) { + startQueue =3D (uint16_t)(core_num * (quot + 1)); + endQueue =3D (uint16_t)(startQueue + quot + 1); + } else { + startQueue =3D (uint16_t)(core_num * quot + remainder); + endQueue =3D (uint16_t)(startQueue + quot); + } + } else { + startQueue =3D (uint16_t)(core_num * quot); + endQueue =3D (uint16_t)(startQueue + quot); + } =20 + /* vmdq queue idx doesn't always start from zero.*/ + startQueue +=3D vmdq_queue_base; + endQueue +=3D vmdq_queue_base; printf("Core %u(lcore %u) reading queues %i-%i\n", (unsigned)core_num, rte_lcore_id(), startQueue, endQueue - 1); =20 + if (startQueue =3D=3D endQueue) { + printf("lcore %u has nothing to do\n", (unsigned)core_num); + return 0; + } + for (;;) { - struct rte_mbuf *buf[32]; + struct rte_mbuf *buf[MAX_PKT_BURST]; const uint16_t buf_size =3D sizeof(buf) / sizeof(buf[0]); for (p =3D 0; p < num_ports; p++) { const uint8_t src =3D ports[p]; @@ -351,12 +581,17 @@ lcore_main(void *arg) for (q =3D startQueue; q < endQueue; q++) { const uint16_t rxCount =3D rte_eth_rx_burst(src, q, buf, buf_size); - if (rxCount =3D=3D 0) + + if (unlikely(rxCount =3D=3D 0)) continue; + rxPackets[q] +=3D rxCount; =20 + for (i =3D 0; i < rxCount; i++) + update_mac_address(buf[i], dst); + const uint16_t txCount =3D rte_eth_tx_burst(dst, - (uint16_t)core_num, buf, rxCount); + q, buf, rxCount); if (txCount !=3D rxCount) { for (i =3D txCount; i < rxCount; i++) rte_pktmbuf_free(buf[i]); @@ -381,12 +616,12 @@ static unsigned check_ports_num(unsigned nb_ports) num_ports =3D nb_ports; } =20 - for (portid =3D 0; portid < num_ports; portid ++) { + for (portid =3D 0; portid < num_ports; portid++) { if (ports[portid] >=3D nb_ports) { printf("\nSpecified port ID(%u) exceeds max system port ID(%u)\n", ports[portid], (nb_ports - 1)); ports[portid] =3D INVALID_PORT_ID; - valid_num_ports --; + valid_num_ports--; } } return valid_num_ports; @@ -420,16 +655,16 @@ main(int argc, char *argv[]) rte_exit(EXIT_FAILURE, "Invalid VMDQ argument\n"); =20 cores =3D rte_lcore_count(); - if ((cores & (cores - 1)) !=3D 0 || cores > 128) { + if ((cores & (cores - 1)) !=3D 0 || cores > RTE_MAX_LCORE) { rte_exit(EXIT_FAILURE,"This program can only run on an even" - "number of cores(1-128)\n\n"); + " number of cores(1-%d)\n\n", RTE_MAX_LCORE); } =20 nb_ports =3D rte_eth_dev_count(); if (nb_ports > RTE_MAX_ETHPORTS) nb_ports =3D RTE_MAX_ETHPORTS; =20 - /* + /* * Update the global var NUM_PORTS and global array PORTS * and get value of var VALID_NUM_PORTS according to system ports numbe= r */ @@ -440,8 +675,9 @@ main(int argc, char *argv[]) rte_exit(EXIT_FAILURE, "Error with valid ports number is not even or l= ess than 2\n"); } =20 - mbuf_pool =3D rte_pktmbuf_pool_create("MBUF_POOL", NUM_MBUFS * nb_ports= , - MBUF_CACHE_SIZE, 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id()); + mbuf_pool =3D rte_pktmbuf_pool_create("MBUF_POOL", + NUM_MBUFS_PER_PORT * nb_ports, MBUF_CACHE_SIZE, + 0, RTE_MBUF_DEFAULT_BUF_SIZE, rte_socket_id()); if (mbuf_pool =3D=3D NULL) rte_exit(EXIT_FAILURE, "Cannot create mbuf pool\n"); =20 --=20 2.4.0