X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=c973e9b6de8eba47a443b93255aeb1cbd1bb486b;hb=99a5744147ea079828a52ee904ea79ba52602c16;hp=7ec66826ba290376a9491451903fe8b7ee11e315;hpb=3031749c2df04a63cdcef186dcce3781e61436e8;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 7ec66826ba..c973e9b6de 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -2,6 +2,7 @@ * BSD LICENSE * * Copyright(c) 2010-2014 Intel Corporation. All rights reserved. + * Copyright 2014 6WIND S.A. * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -43,22 +44,19 @@ * buffers. The message buffers are stored in a mempool, using the * RTE mempool library. * - * This library provide an API to allocate/free mbufs, manipulate - * control message buffer (ctrlmbuf), which are generic message - * buffers, and packet buffers (pktmbuf), which are used to carry - * network packets. + * This library provide an API to allocate/free packet mbufs, which are + * used to carry network packets. * * To understand the concepts of packet buffers or mbufs, you * should read "TCP/IP Illustrated, Volume 2: The Implementation, * Addison-Wesley, 1995, ISBN 0-201-63354-X from Richard Stevens" * http://www.kohala.com/start/tcpipiv2.html - * - * The main modification of this implementation is the use of mbuf for - * transports other than packets. mbufs can have other types. */ #include +#include #include +#include #include #include #include @@ -67,117 +65,687 @@ extern "C" { #endif -/** - * A control message buffer. - */ -struct rte_ctrlmbuf { - void *data; /**< Pointer to data. */ - uint32_t data_len; /**< Length of data. */ -}; - +/* deprecated options */ +#pragma GCC poison RTE_MBUF_SCATTER_GATHER +#pragma GCC poison RTE_MBUF_REFCNT /* * Packet Offload Features Flags. It also carry packet type information. * Critical resources. Both rx/tx shared these bits. Be cautious on any change + * + * - RX flags start at bit position zero, and get added to the left of previous + * flags. + * - The most-significant 3 bits are reserved for generic mbuf flags + * - TX flags therefore start at bit position 60 (i.e. 63-3), and new flags get + * added to the right of the previously defined flags i.e. they should count + * downwards, not upwards. + * + * Keep these flags synchronized with rte_get_rx_ol_flag_name() and + * rte_get_tx_ol_flag_name(). */ -#define PKT_RX_VLAN_PKT 0x0001 /**< RX packet is a 802.1q VLAN packet. */ -#define PKT_RX_RSS_HASH 0x0002 /**< RX packet with RSS hash result. */ -#define PKT_RX_FDIR 0x0004 /**< RX packet with FDIR infos. */ -#define PKT_RX_L4_CKSUM_BAD 0x0008 /**< L4 cksum of RX pkt. is not OK. */ -#define PKT_RX_IP_CKSUM_BAD 0x0010 /**< IP cksum of RX pkt. is not OK. */ -#define PKT_RX_IPV4_HDR 0x0020 /**< RX packet with IPv4 header. */ -#define PKT_RX_IPV4_HDR_EXT 0x0040 /**< RX packet with extended IPv4 header. */ -#define PKT_RX_IPV6_HDR 0x0080 /**< RX packet with IPv6 header. */ -#define PKT_RX_IPV6_HDR_EXT 0x0100 /**< RX packet with extended IPv6 header. */ -#define PKT_RX_IEEE1588_PTP 0x0200 /**< RX IEEE1588 L2 Ethernet PT Packet. */ -#define PKT_RX_IEEE1588_TMST 0x0400 /**< RX IEEE1588 L2/L4 timestamped packet.*/ - -#define PKT_TX_VLAN_PKT 0x0800 /**< TX packet is a 802.1q VLAN packet. */ -#define PKT_TX_IP_CKSUM 0x1000 /**< IP cksum of TX pkt. computed by NIC. */ -/* - * Bit 14~13 used for L4 packet type with checksum enabled. - * 00: Reserved - * 01: TCP checksum - * 10: SCTP checksum - * 11: UDP checksum - */ -#define PKT_TX_L4_MASK 0x6000 /**< Mask bits for L4 checksum offload request. */ -#define PKT_TX_L4_NO_CKSUM 0x0000 /**< Disable L4 cksum of TX pkt. */ -#define PKT_TX_TCP_CKSUM 0x2000 /**< TCP cksum of TX pkt. computed by NIC. */ -#define PKT_TX_SCTP_CKSUM 0x4000 /**< SCTP cksum of TX pkt. computed by NIC. */ -#define PKT_TX_UDP_CKSUM 0x6000 /**< UDP cksum of TX pkt. computed by NIC. */ -/* Bit 15 */ -#define PKT_TX_IEEE1588_TMST 0x8000 /**< TX IEEE1588 packet to timestamp. */ - -/** - * Bit Mask to indicate what bits required for building TX context - */ -#define PKT_TX_OFFLOAD_MASK (PKT_TX_VLAN_PKT | PKT_TX_IP_CKSUM | PKT_TX_L4_MASK) - -/** Offload features */ -union rte_vlan_macip { - uint32_t data; - struct { - uint16_t l3_len:9; /**< L3 (IP) Header Length. */ - uint16_t l2_len:7; /**< L2 (MAC) Header Length. */ - uint16_t vlan_tci; - /**< VLAN Tag Control Identifier (CPU order). */ - } f; -}; +#define PKT_RX_VLAN_PKT (1ULL << 0) /**< RX packet is a 802.1q VLAN packet. */ +#define PKT_RX_RSS_HASH (1ULL << 1) /**< RX packet with RSS hash result. */ +#define PKT_RX_FDIR (1ULL << 2) /**< RX packet with FDIR match indicate. */ +#define PKT_RX_L4_CKSUM_BAD (1ULL << 3) /**< L4 cksum of RX pkt. is not OK. */ +#define PKT_RX_IP_CKSUM_BAD (1ULL << 4) /**< IP cksum of RX pkt. is not OK. */ +#define PKT_RX_EIP_CKSUM_BAD (0ULL << 0) /**< External IP header checksum error. */ +#define PKT_RX_OVERSIZE (0ULL << 0) /**< Num of desc of an RX pkt oversize. */ +#define PKT_RX_HBUF_OVERFLOW (0ULL << 0) /**< Header buffer overflow. */ +#define PKT_RX_RECIP_ERR (0ULL << 0) /**< Hardware processing error. */ +#define PKT_RX_MAC_ERR (0ULL << 0) /**< MAC error. */ +#define PKT_RX_IEEE1588_PTP (1ULL << 9) /**< RX IEEE1588 L2 Ethernet PT Packet. */ +#define PKT_RX_IEEE1588_TMST (1ULL << 10) /**< RX IEEE1588 L2/L4 timestamped packet.*/ +#define PKT_RX_FDIR_ID (1ULL << 13) /**< FD id reported if FDIR match. */ +#define PKT_RX_FDIR_FLX (1ULL << 14) /**< Flexible bytes reported if FDIR match. */ +#define PKT_RX_QINQ_PKT (1ULL << 15) /**< RX packet with double VLAN stripped. */ +/* add new RX flags here */ + +/* add new TX flags here */ + +/** + * Second VLAN insertion (QinQ) flag. + */ +#define PKT_TX_QINQ_PKT (1ULL << 49) /**< TX packet with double VLAN inserted. */ + +/** + * TCP segmentation offload. To enable this offload feature for a + * packet to be transmitted on hardware supporting TSO: + * - set the PKT_TX_TCP_SEG flag in mbuf->ol_flags (this flag implies + * PKT_TX_TCP_CKSUM) + * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 + * - if it's IPv4, set the PKT_TX_IP_CKSUM flag and write the IP checksum + * to 0 in the packet + * - fill the mbuf offload information: l2_len, l3_len, l4_len, tso_segsz + * - calculate the pseudo header checksum without taking ip_len in account, + * and set it in the TCP header. Refer to rte_ipv4_phdr_cksum() and + * rte_ipv6_phdr_cksum() that can be used as helpers. + */ +#define PKT_TX_TCP_SEG (1ULL << 50) + +#define PKT_TX_IEEE1588_TMST (1ULL << 51) /**< TX IEEE1588 packet to timestamp. */ + +/** + * Bits 52+53 used for L4 packet type with checksum enabled: 00: Reserved, + * 01: TCP checksum, 10: SCTP checksum, 11: UDP checksum. To use hardware + * L4 checksum offload, the user needs to: + * - fill l2_len and l3_len in mbuf + * - set the flags PKT_TX_TCP_CKSUM, PKT_TX_SCTP_CKSUM or PKT_TX_UDP_CKSUM + * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 + * - calculate the pseudo header checksum and set it in the L4 header (only + * for TCP or UDP). See rte_ipv4_phdr_cksum() and rte_ipv6_phdr_cksum(). + * For SCTP, set the crc field to 0. + */ +#define PKT_TX_L4_NO_CKSUM (0ULL << 52) /**< Disable L4 cksum of TX pkt. */ +#define PKT_TX_TCP_CKSUM (1ULL << 52) /**< TCP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_SCTP_CKSUM (2ULL << 52) /**< SCTP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_UDP_CKSUM (3ULL << 52) /**< UDP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_L4_MASK (3ULL << 52) /**< Mask for L4 cksum offload request. */ + +/** + * Offload the IP checksum in the hardware. The flag PKT_TX_IPV4 should + * also be set by the application, although a PMD will only check + * PKT_TX_IP_CKSUM. + * - set the IP checksum field in the packet to 0 + * - fill the mbuf offload information: l2_len, l3_len + */ +#define PKT_TX_IP_CKSUM (1ULL << 54) + +/** + * Packet is IPv4. This flag must be set when using any offload feature + * (TSO, L3 or L4 checksum) to tell the NIC that the packet is an IPv4 + * packet. If the packet is a tunneled packet, this flag is related to + * the inner headers. + */ +#define PKT_TX_IPV4 (1ULL << 55) + +/** + * Packet is IPv6. This flag must be set when using an offload feature + * (TSO or L4 checksum) to tell the NIC that the packet is an IPv6 + * packet. If the packet is a tunneled packet, this flag is related to + * the inner headers. + */ +#define PKT_TX_IPV6 (1ULL << 56) + +#define PKT_TX_VLAN_PKT (1ULL << 57) /**< TX packet is a 802.1q VLAN packet. */ + +/** + * Offload the IP checksum of an external header in the hardware. The + * flag PKT_TX_OUTER_IPV4 should also be set by the application, alto ugh + * a PMD will only check PKT_TX_IP_CKSUM. The IP checksum field in the + * packet must be set to 0. + * - set the outer IP checksum field in the packet to 0 + * - fill the mbuf offload information: outer_l2_len, outer_l3_len + */ +#define PKT_TX_OUTER_IP_CKSUM (1ULL << 58) + +/** + * Packet outer header is IPv4. This flag must be set when using any + * outer offload feature (L3 or L4 checksum) to tell the NIC that the + * outer header of the tunneled packet is an IPv4 packet. + */ +#define PKT_TX_OUTER_IPV4 (1ULL << 59) + +/** + * Packet outer header is IPv6. This flag must be set when using any + * outer offload feature (L4 checksum) to tell the NIC that the outer + * header of the tunneled packet is an IPv6 packet. + */ +#define PKT_TX_OUTER_IPV6 (1ULL << 60) + +#define __RESERVED (1ULL << 61) /**< reserved for future mbuf use */ + +#define IND_ATTACHED_MBUF (1ULL << 62) /**< Indirect attached mbuf */ + +/* Use final bit of flags to indicate a control mbuf */ +#define CTRL_MBUF_FLAG (1ULL << 63) /**< Mbuf contains control data */ /* - * Compare mask for vlan_macip_len.data, - * should be in sync with rte_vlan_macip.f layout. - * */ -#define TX_VLAN_CMP_MASK 0xFFFF0000 /**< VLAN length - 16-bits. */ -#define TX_MAC_LEN_CMP_MASK 0x0000FE00 /**< MAC length - 7-bits. */ -#define TX_IP_LEN_CMP_MASK 0x000001FF /**< IP length - 9-bits. */ -/**< MAC+IP length. */ -#define TX_MACIP_LEN_CMP_MASK (TX_MAC_LEN_CMP_MASK | TX_IP_LEN_CMP_MASK) - -/** - * A packet message buffer. - */ -struct rte_pktmbuf { - /* valid for any segment */ - struct rte_mbuf *next; /**< Next segment of scattered packet. */ - void* data; /**< Start address of data in segment buffer. */ - uint16_t data_len; /**< Amount of data in segment buffer. */ - - /* these fields are valid for first segment only */ - uint8_t nb_segs; /**< Number of segments. */ - uint8_t in_port; /**< Input port. */ - uint32_t pkt_len; /**< Total pkt len: sum of all segment data_len. */ - - /* offload features */ - union rte_vlan_macip vlan_macip; - union { - uint32_t rss; /**< RSS hash result if RSS enabled */ - struct { - uint16_t hash; - uint16_t id; - } fdir; /**< Filter identifier if FDIR enabled */ - uint32_t sched; /**< Hierarchical scheduler */ - } hash; /**< hash information */ -}; + * 32 bits are divided into several fields to mark packet types. Note that + * each field is indexical. + * - Bit 3:0 is for L2 types. + * - Bit 7:4 is for L3 or outer L3 (for tunneling case) types. + * - Bit 11:8 is for L4 or outer L4 (for tunneling case) types. + * - Bit 15:12 is for tunnel types. + * - Bit 19:16 is for inner L2 types. + * - Bit 23:20 is for inner L3 types. + * - Bit 27:24 is for inner L4 types. + * - Bit 31:28 is reserved. + * + * To be compatible with Vector PMD, RTE_PTYPE_L3_IPV4, RTE_PTYPE_L3_IPV4_EXT, + * RTE_PTYPE_L3_IPV6, RTE_PTYPE_L3_IPV6_EXT, RTE_PTYPE_L4_TCP, RTE_PTYPE_L4_UDP + * and RTE_PTYPE_L4_SCTP should be kept as below in a contiguous 7 bits. + * + * Note that L3 types values are selected for checking IPV4/IPV6 header from + * performance point of view. Reading annotations of RTE_ETH_IS_IPV4_HDR and + * RTE_ETH_IS_IPV6_HDR is needed for any future changes of L3 type values. + * + * Note that the packet types of the same packet recognized by different + * hardware may be different, as different hardware may have different + * capability of packet type recognition. + * + * examples: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=0x29 + * | 'version'=6, 'next header'=0x3A + * | 'ICMPv6 header'> + * will be recognized on i40e hardware as packet type combination of, + * RTE_PTYPE_L2_ETHER | + * RTE_PTYPE_L3_IPV4_EXT_UNKNOWN | + * RTE_PTYPE_TUNNEL_IP | + * RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | + * RTE_PTYPE_INNER_L4_ICMP. + * + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=0x2F + * | 'GRE header' + * | 'version'=6, 'next header'=0x11 + * | 'UDP header'> + * will be recognized on i40e hardware as packet type combination of, + * RTE_PTYPE_L2_ETHER | + * RTE_PTYPE_L3_IPV6_EXT_UNKNOWN | + * RTE_PTYPE_TUNNEL_GRENAT | + * RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN | + * RTE_PTYPE_INNER_L4_UDP. + */ +#define RTE_PTYPE_UNKNOWN 0x00000000 +/** + * Ethernet packet type. + * It is used for outer packet for tunneling cases. + * + * Packet format: + * <'ether type'=[0x0800|0x86DD]> + */ +#define RTE_PTYPE_L2_ETHER 0x00000001 +/** + * Ethernet packet type for time sync. + * + * Packet format: + * <'ether type'=0x88F7> + */ +#define RTE_PTYPE_L2_ETHER_TIMESYNC 0x00000002 +/** + * ARP (Address Resolution Protocol) packet type. + * + * Packet format: + * <'ether type'=0x0806> + */ +#define RTE_PTYPE_L2_ETHER_ARP 0x00000003 +/** + * LLDP (Link Layer Discovery Protocol) packet type. + * + * Packet format: + * <'ether type'=0x88CC> + */ +#define RTE_PTYPE_L2_ETHER_LLDP 0x00000004 +/** + * Mask of layer 2 packet types. + * It is used for outer packet for tunneling cases. + */ +#define RTE_PTYPE_L2_MASK 0x0000000f +/** + * IP (Internet Protocol) version 4 packet type. + * It is used for outer packet for tunneling cases, and does not contain any + * header option. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'ihl'=5> + */ +#define RTE_PTYPE_L3_IPV4 0x00000010 +/** + * IP (Internet Protocol) version 4 packet type. + * It is used for outer packet for tunneling cases, and contains header + * options. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'ihl'=[6-15], 'options'> + */ +#define RTE_PTYPE_L3_IPV4_EXT 0x00000030 +/** + * IP (Internet Protocol) version 6 packet type. + * It is used for outer packet for tunneling cases, and does not contain any + * extension header. + * + * Packet format: + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=0x3B> + */ +#define RTE_PTYPE_L3_IPV6 0x00000040 +/** + * IP (Internet Protocol) version 4 packet type. + * It is used for outer packet for tunneling cases, and may or maynot contain + * header options. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'ihl'=[5-15], <'options'>> + */ +#define RTE_PTYPE_L3_IPV4_EXT_UNKNOWN 0x00000090 +/** + * IP (Internet Protocol) version 6 packet type. + * It is used for outer packet for tunneling cases, and contains extension + * headers. + * + * Packet format: + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=[0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87], + * 'extension headers'> + */ +#define RTE_PTYPE_L3_IPV6_EXT 0x000000c0 +/** + * IP (Internet Protocol) version 6 packet type. + * It is used for outer packet for tunneling cases, and may or maynot contain + * extension headers. + * + * Packet format: + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=[0x3B|0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87], + * <'extension headers'>> + */ +#define RTE_PTYPE_L3_IPV6_EXT_UNKNOWN 0x000000e0 +/** + * Mask of layer 3 packet types. + * It is used for outer packet for tunneling cases. + */ +#define RTE_PTYPE_L3_MASK 0x000000f0 +/** + * TCP (Transmission Control Protocol) packet type. + * It is used for outer packet for tunneling cases. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=6, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=6> + */ +#define RTE_PTYPE_L4_TCP 0x00000100 +/** + * UDP (User Datagram Protocol) packet type. + * It is used for outer packet for tunneling cases. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=17, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=17> + */ +#define RTE_PTYPE_L4_UDP 0x00000200 +/** + * Fragmented IP (Internet Protocol) packet type. + * It is used for outer packet for tunneling cases. + * + * It refers to those packets of any IP types, which can be recognized as + * fragmented. A fragmented packet cannot be recognized as any other L4 types + * (RTE_PTYPE_L4_TCP, RTE_PTYPE_L4_UDP, RTE_PTYPE_L4_SCTP, RTE_PTYPE_L4_ICMP, + * RTE_PTYPE_L4_NONFRAG). + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'MF'=1> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=44> + */ +#define RTE_PTYPE_L4_FRAG 0x00000300 +/** + * SCTP (Stream Control Transmission Protocol) packet type. + * It is used for outer packet for tunneling cases. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=132, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=132> + */ +#define RTE_PTYPE_L4_SCTP 0x00000400 +/** + * ICMP (Internet Control Message Protocol) packet type. + * It is used for outer packet for tunneling cases. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=1, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=1> + */ +#define RTE_PTYPE_L4_ICMP 0x00000500 +/** + * Non-fragmented IP (Internet Protocol) packet type. + * It is used for outer packet for tunneling cases. + * + * It refers to those packets of any IP types, while cannot be recognized as + * any of above L4 types (RTE_PTYPE_L4_TCP, RTE_PTYPE_L4_UDP, + * RTE_PTYPE_L4_FRAG, RTE_PTYPE_L4_SCTP, RTE_PTYPE_L4_ICMP). + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'!=[6|17|132|1], 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'!=[6|17|44|132|1]> + */ +#define RTE_PTYPE_L4_NONFRAG 0x00000600 +/** + * Mask of layer 4 packet types. + * It is used for outer packet for tunneling cases. + */ +#define RTE_PTYPE_L4_MASK 0x00000f00 +/** + * IP (Internet Protocol) in IP (Internet Protocol) tunneling packet type. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=[4|41]> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=[4|41]> + */ +#define RTE_PTYPE_TUNNEL_IP 0x00001000 +/** + * GRE (Generic Routing Encapsulation) tunneling packet type. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=47> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=47> + */ +#define RTE_PTYPE_TUNNEL_GRE 0x00002000 +/** + * VXLAN (Virtual eXtensible Local Area Network) tunneling packet type. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=17 + * | 'destination port'=4798> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=17 + * | 'destination port'=4798> + */ +#define RTE_PTYPE_TUNNEL_VXLAN 0x00003000 +/** + * NVGRE (Network Virtualization using Generic Routing Encapsulation) tunneling + * packet type. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=47 + * | 'protocol type'=0x6558> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=47 + * | 'protocol type'=0x6558'> + */ +#define RTE_PTYPE_TUNNEL_NVGRE 0x00004000 +/** + * GENEVE (Generic Network Virtualization Encapsulation) tunneling packet type. + * + * Packet format: + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=17 + * | 'destination port'=6081> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=17 + * | 'destination port'=6081> + */ +#define RTE_PTYPE_TUNNEL_GENEVE 0x00005000 +/** + * Tunneling packet type of Teredo, VXLAN (Virtual eXtensible Local Area + * Network) or GRE (Generic Routing Encapsulation) could be recognized as this + * packet type, if they can not be recognized independently as of hardware + * capability. + */ +#define RTE_PTYPE_TUNNEL_GRENAT 0x00006000 +/** + * Mask of tunneling packet types. + */ +#define RTE_PTYPE_TUNNEL_MASK 0x0000f000 +/** + * Ethernet packet type. + * It is used for inner packet type only. + * + * Packet format (inner only): + * <'ether type'=[0x800|0x86DD]> + */ +#define RTE_PTYPE_INNER_L2_ETHER 0x00010000 +/** + * Ethernet packet type with VLAN (Virtual Local Area Network) tag. + * + * Packet format (inner only): + * <'ether type'=[0x800|0x86DD], vlan=[1-4095]> + */ +#define RTE_PTYPE_INNER_L2_ETHER_VLAN 0x00020000 +/** + * Mask of inner layer 2 packet types. + */ +#define RTE_PTYPE_INNER_L2_MASK 0x000f0000 +/** + * IP (Internet Protocol) version 4 packet type. + * It is used for inner packet only, and does not contain any header option. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'ihl'=5> + */ +#define RTE_PTYPE_INNER_L3_IPV4 0x00100000 +/** + * IP (Internet Protocol) version 4 packet type. + * It is used for inner packet only, and contains header options. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'ihl'=[6-15], 'options'> + */ +#define RTE_PTYPE_INNER_L3_IPV4_EXT 0x00200000 +/** + * IP (Internet Protocol) version 6 packet type. + * It is used for inner packet only, and does not contain any extension header. + * + * Packet format (inner only): + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=0x3B> + */ +#define RTE_PTYPE_INNER_L3_IPV6 0x00300000 +/** + * IP (Internet Protocol) version 4 packet type. + * It is used for inner packet only, and may or maynot contain header options. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'ihl'=[5-15], <'options'>> + */ +#define RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN 0x00400000 +/** + * IP (Internet Protocol) version 6 packet type. + * It is used for inner packet only, and contains extension headers. + * + * Packet format (inner only): + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=[0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87], + * 'extension headers'> + */ +#define RTE_PTYPE_INNER_L3_IPV6_EXT 0x00500000 +/** + * IP (Internet Protocol) version 6 packet type. + * It is used for inner packet only, and may or maynot contain extension + * headers. + * + * Packet format (inner only): + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=[0x3B|0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87], + * <'extension headers'>> + */ +#define RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN 0x00600000 +/** + * Mask of inner layer 3 packet types. + */ +#define RTE_PTYPE_INNER_L3_MASK 0x00f00000 +/** + * TCP (Transmission Control Protocol) packet type. + * It is used for inner packet only. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=6, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=6> + */ +#define RTE_PTYPE_INNER_L4_TCP 0x01000000 +/** + * UDP (User Datagram Protocol) packet type. + * It is used for inner packet only. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=17, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=17> + */ +#define RTE_PTYPE_INNER_L4_UDP 0x02000000 +/** + * Fragmented IP (Internet Protocol) packet type. + * It is used for inner packet only, and may or maynot have layer 4 packet. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'MF'=1> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=44> + */ +#define RTE_PTYPE_INNER_L4_FRAG 0x03000000 +/** + * SCTP (Stream Control Transmission Protocol) packet type. + * It is used for inner packet only. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=132, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=132> + */ +#define RTE_PTYPE_INNER_L4_SCTP 0x04000000 +/** + * ICMP (Internet Control Message Protocol) packet type. + * It is used for inner packet only. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'=1, 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'=1> + */ +#define RTE_PTYPE_INNER_L4_ICMP 0x05000000 +/** + * Non-fragmented IP (Internet Protocol) packet type. + * It is used for inner packet only, and may or maynot have other unknown layer + * 4 packet types. + * + * Packet format (inner only): + * <'ether type'=0x0800 + * | 'version'=4, 'protocol'!=[6|17|132|1], 'MF'=0> + * or, + * <'ether type'=0x86DD + * | 'version'=6, 'next header'!=[6|17|44|132|1]> + */ +#define RTE_PTYPE_INNER_L4_NONFRAG 0x06000000 +/** + * Mask of inner layer 4 packet types. + */ +#define RTE_PTYPE_INNER_L4_MASK 0x0f000000 /** - * This enum indicates the mbuf type. + * Check if the (outer) L3 header is IPv4. To avoid comparing IPv4 types one by + * one, bit 4 is selected to be used for IPv4 only. Then checking bit 4 can + * determine if it is an IPV4 packet. */ -enum rte_mbuf_type { - RTE_MBUF_CTRL, /**< Control mbuf. */ - RTE_MBUF_PKT, /**< Packet mbuf. */ -}; +#define RTE_ETH_IS_IPV4_HDR(ptype) ((ptype) & RTE_PTYPE_L3_IPV4) + +/** + * Check if the (outer) L3 header is IPv4. To avoid comparing IPv4 types one by + * one, bit 6 is selected to be used for IPv4 only. Then checking bit 6 can + * determine if it is an IPV4 packet. + */ +#define RTE_ETH_IS_IPV6_HDR(ptype) ((ptype) & RTE_PTYPE_L3_IPV6) + +/* Check if it is a tunneling packet */ +#define RTE_ETH_IS_TUNNEL_PKT(ptype) ((ptype) & (RTE_PTYPE_TUNNEL_MASK | \ + RTE_PTYPE_INNER_L2_MASK | \ + RTE_PTYPE_INNER_L3_MASK | \ + RTE_PTYPE_INNER_L4_MASK)) + +/** Alignment constraint of mbuf private area. */ +#define RTE_MBUF_PRIV_ALIGN 8 + +/** + * Get the name of a RX offload flag + * + * @param mask + * The mask describing the flag. + * @return + * The name of this flag, or NULL if it's not a valid RX flag. + */ +const char *rte_get_rx_ol_flag_name(uint64_t mask); + +/** + * Get the name of a TX offload flag + * + * @param mask + * The mask describing the flag. Usually only one bit must be set. + * Several bits can be given if they belong to the same mask. + * Ex: PKT_TX_L4_MASK. + * @return + * The name of this flag, or NULL if it's not a valid TX flag. + */ +const char *rte_get_tx_ol_flag_name(uint64_t mask); /** - * The generic rte_mbuf, containing a packet mbuf or a control mbuf. + * Some NICs need at least 2KB buffer to RX standard Ethernet frame without + * splitting it into multiple segments. + * So, for mbufs that planned to be involved into RX/TX, the recommended + * minimal buffer length is 2KB + RTE_PKTMBUF_HEADROOM. + */ +#define RTE_MBUF_DEFAULT_DATAROOM 2048 +#define RTE_MBUF_DEFAULT_BUF_SIZE \ + (RTE_MBUF_DEFAULT_DATAROOM + RTE_PKTMBUF_HEADROOM) + +/* define a set of marker types that can be used to refer to set points in the + * mbuf */ +typedef void *MARKER[0]; /**< generic marker for a point in a structure */ +typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */ +typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes + * with a single assignment */ + +/** Opaque rte_mbuf_offload structure declarations */ +struct rte_mbuf_offload; + +/** + * The generic rte_mbuf, containing a packet mbuf. */ struct rte_mbuf { - struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */ + MARKER cacheline0; + void *buf_addr; /**< Virtual address of segment buffer. */ phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */ + uint16_t buf_len; /**< Length of segment buffer. */ -#ifdef RTE_MBUF_SCATTER_GATHER + + /* next 6 bytes are initialised on RX descriptor rearm */ + MARKER8 rearm_data; + uint16_t data_off; + /** * 16-bit Reference counter. * It should only be accessed using the following functions: @@ -187,43 +755,144 @@ struct rte_mbuf { * config option. */ union { - rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ - uint16_t refcnt; /**< Non-atomically accessed refcnt */ + rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ + uint16_t refcnt; /**< Non-atomically accessed refcnt */ }; -#else - uint16_t refcnt_reserved; /**< Do not use this field */ -#endif - uint8_t type; /**< Type of mbuf. */ - uint8_t reserved; /**< Unused field. Required for padding. */ - uint16_t ol_flags; /**< Offload features. */ + uint8_t nb_segs; /**< Number of segments. */ + uint8_t port; /**< Input port. */ + + uint64_t ol_flags; /**< Offload features. */ + + /* remaining bytes are set on RX when pulling packet from descriptor */ + MARKER rx_descriptor_fields1; + + /* + * The packet type, which is the combination of outer/inner L2, L3, L4 + * and tunnel types. + */ + union { + uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */ + struct { + uint32_t l2_type:4; /**< (Outer) L2 type. */ + uint32_t l3_type:4; /**< (Outer) L3 type. */ + uint32_t l4_type:4; /**< (Outer) L4 type. */ + uint32_t tun_type:4; /**< Tunnel type. */ + uint32_t inner_l2_type:4; /**< Inner L2 type. */ + uint32_t inner_l3_type:4; /**< Inner L3 type. */ + uint32_t inner_l4_type:4; /**< Inner L4 type. */ + }; + }; + + uint32_t pkt_len; /**< Total pkt len: sum of all segments. */ + uint16_t data_len; /**< Amount of data in segment buffer. */ + uint16_t vlan_tci; /**< VLAN Tag Control Identifier (CPU order) */ + + union { + uint32_t rss; /**< RSS hash result if RSS enabled */ + struct { + union { + struct { + uint16_t hash; + uint16_t id; + }; + uint32_t lo; + /**< Second 4 flexible bytes */ + }; + uint32_t hi; + /**< First 4 flexible bytes or FD ID, dependent on + PKT_RX_FDIR_* flag in ol_flags. */ + } fdir; /**< Filter identifier if FDIR enabled */ + struct { + uint32_t lo; + uint32_t hi; + } sched; /**< Hierarchical scheduler */ + uint32_t usr; /**< User defined tags. See rte_distributor_process() */ + } hash; /**< hash information */ + + uint32_t seqn; /**< Sequence number. See also rte_reorder_insert() */ + + uint16_t vlan_tci_outer; /**< Outer VLAN Tag Control Identifier (CPU order) */ + + /* second cache line - fields only used in slow path or on TX */ + MARKER cacheline1 __rte_cache_min_aligned; + + union { + void *userdata; /**< Can be used for external metadata */ + uint64_t udata64; /**< Allow 8-byte userdata on 32-bit */ + }; + + struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */ + struct rte_mbuf *next; /**< Next segment of scattered packet. */ + /* fields to support TX offloads */ union { - struct rte_ctrlmbuf ctrl; - struct rte_pktmbuf pkt; + uint64_t tx_offload; /**< combined for easy fetch */ + struct { + uint64_t l2_len:7; /**< L2 (MAC) Header Length. */ + uint64_t l3_len:9; /**< L3 (IP) Header Length. */ + uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length. */ + uint64_t tso_segsz:16; /**< TCP TSO segment size */ + + /* fields for TX offloading of tunnels */ + uint64_t outer_l3_len:9; /**< Outer L3 (IP) Hdr Length. */ + uint64_t outer_l2_len:7; /**< Outer L2 (MAC) Hdr Length. */ + + /* uint64_t unused:8; */ + }; }; + + /** Size of the application private data. In case of an indirect + * mbuf, it stores the direct mbuf private data size. */ + uint16_t priv_size; + + /** Timesync flags for use with IEEE1588. */ + uint16_t timesync; + + /* Chain of off-load operations to perform on mbuf */ + struct rte_mbuf_offload *offload_ops; } __rte_cache_aligned; +static inline uint16_t rte_pktmbuf_priv_size(struct rte_mempool *mp); + /** - * Given the buf_addr returns the pointer to corresponding mbuf. + * Return the mbuf owning the data buffer address of an indirect mbuf. + * + * @param mi + * The pointer to the indirect mbuf. + * @return + * The address of the direct mbuf corresponding to buffer_addr. */ -#define RTE_MBUF_FROM_BADDR(ba) (((struct rte_mbuf *)(ba)) - 1) +static inline struct rte_mbuf * +rte_mbuf_from_indirect(struct rte_mbuf *mi) +{ + return (struct rte_mbuf *)RTE_PTR_SUB(mi->buf_addr, sizeof(*mi) + mi->priv_size); +} /** - * Given the pointer to mbuf returns an address where it's buf_addr - * should point to. + * Return the buffer address embedded in the given mbuf. + * + * @param md + * The pointer to the mbuf. + * @return + * The address of the data buffer owned by the mbuf. */ -#define RTE_MBUF_TO_BADDR(mb) (((struct rte_mbuf *)(mb)) + 1) +static inline char * +rte_mbuf_to_baddr(struct rte_mbuf *md) +{ + char *buffer_addr; + buffer_addr = (char *)md + sizeof(*md) + rte_pktmbuf_priv_size(md->pool); + return buffer_addr; +} /** * Returns TRUE if given mbuf is indirect, or FALSE otherwise. */ -#define RTE_MBUF_INDIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb)) +#define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF) /** * Returns TRUE if given mbuf is direct, or FALSE otherwise. */ -#define RTE_MBUF_DIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) == (mb)) - +#define RTE_MBUF_DIRECT(mb) (!RTE_MBUF_INDIRECT(mb)) /** * Private data in case of pktmbuf pool. @@ -232,18 +901,19 @@ struct rte_mbuf { * appended after the mempool structure (in private data). */ struct rte_pktmbuf_pool_private { - uint16_t mbuf_data_room_size; /**< Size of data space in each mbuf.*/ + uint16_t mbuf_data_room_size; /**< Size of data space in each mbuf. */ + uint16_t mbuf_priv_size; /**< Size of private area in each mbuf. */ }; #ifdef RTE_LIBRTE_MBUF_DEBUG /** check mbuf type in debug mode */ -#define __rte_mbuf_sanity_check(m, t, is_h) rte_mbuf_sanity_check(m, t, is_h) +#define __rte_mbuf_sanity_check(m, is_h) rte_mbuf_sanity_check(m, is_h) /** check mbuf type in debug mode if mbuf pointer is not null */ -#define __rte_mbuf_sanity_check_raw(m, t, is_h) do { \ +#define __rte_mbuf_sanity_check_raw(m, is_h) do { \ if ((m) != NULL) \ - rte_mbuf_sanity_check(m, t, is_h); \ + rte_mbuf_sanity_check(m, is_h); \ } while (0) /** MBUF asserts in debug mode */ @@ -255,34 +925,18 @@ if (!(exp)) { \ #else /* RTE_LIBRTE_MBUF_DEBUG */ /** check mbuf type in debug mode */ -#define __rte_mbuf_sanity_check(m, t, is_h) do { } while(0) +#define __rte_mbuf_sanity_check(m, is_h) do { } while (0) /** check mbuf type in debug mode if mbuf pointer is not null */ -#define __rte_mbuf_sanity_check_raw(m, t, is_h) do { } while(0) +#define __rte_mbuf_sanity_check_raw(m, is_h) do { } while (0) /** MBUF asserts in debug mode */ -#define RTE_MBUF_ASSERT(exp) do { } while(0) +#define RTE_MBUF_ASSERT(exp) do { } while (0) #endif /* RTE_LIBRTE_MBUF_DEBUG */ -#ifdef RTE_MBUF_SCATTER_GATHER #ifdef RTE_MBUF_REFCNT_ATOMIC -/** - * Adds given value to an mbuf's refcnt and returns its new value. - * @param m - * Mbuf to update - * @param value - * Value to add/subtract - * @return - * Updated value - */ -static inline uint16_t -rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) -{ - return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value)); -} - /** * Reads the value of an mbuf's refcnt. * @param m @@ -309,6 +963,33 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) rte_atomic16_set(&m->refcnt_atomic, new_value); } +/** + * Adds given value to an mbuf's refcnt and returns its new value. + * @param m + * Mbuf to update + * @param value + * Value to add/subtract + * @return + * Updated value + */ +static inline uint16_t +rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) +{ + /* + * The atomic_add is an expensive operation, so we don't want to + * call it in the case where we know we are the uniq holder of + * this mbuf (i.e. ref_cnt == 1). Otherwise, an atomic + * operation has to be used because concurrent accesses on the + * reference counter can occur. + */ + if (likely(rte_mbuf_refcnt_read(m) == 1)) { + rte_mbuf_refcnt_set(m, 1 + value); + return 1 + value; + } + + return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value)); +} + #else /* ! RTE_MBUF_REFCNT_ATOMIC */ /** @@ -347,15 +1028,6 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) rte_prefetch0(m); \ } while (0) -#else /* ! RTE_MBUF_SCATTER_GATHER */ - -/** Mbuf prefetch */ -#define RTE_MBUF_PREFETCH_TO_FREE(m) do { } while(0) - -#define rte_mbuf_refcnt_set(m,v) do { } while(0) - -#endif /* RTE_MBUF_SCATTER_GATHER */ - /** * Sanity checks on an mbuf. @@ -365,20 +1037,17 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) * * @param m * The mbuf to be checked. - * @param t - * The expected type of the mbuf. * @param is_header * True if the mbuf is a packet header, false if it is a sub-segment * of a packet (in this case, some fields like nb_segs are not checked) */ void -rte_mbuf_sanity_check(const struct rte_mbuf *m, enum rte_mbuf_type t, - int is_header); +rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header); /** * @internal Allocate a new mbuf from mempool *mp*. * The use of that function is reserved for RTE internal needs. - * Please use either rte_ctrlmbuf_alloc() or rte_pktmbuf_alloc(). + * Please use rte_pktmbuf_alloc(). * * @param mp * The mempool from which mbuf is allocated. @@ -393,17 +1062,15 @@ static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) if (rte_mempool_get(mp, &mb) < 0) return NULL; m = (struct rte_mbuf *)mb; -#ifdef RTE_MBUF_SCATTER_GATHER RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); rte_mbuf_refcnt_set(m, 1); -#endif /* RTE_MBUF_SCATTER_GATHER */ - return (m); + return m; } /** * @internal Put mbuf back into its original mempool. * The use of that function is reserved for RTE internal needs. - * Please use either rte_ctrlmbuf_free() or rte_pktmbuf_free(). + * Please use rte_pktmbuf_free(). * * @param m * The mbuf to be freed. @@ -411,9 +1078,7 @@ static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) static inline void __attribute__((always_inline)) __rte_mbuf_raw_free(struct rte_mbuf *m) { -#ifdef RTE_MBUF_SCATTER_GATHER RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); -#endif /* RTE_MBUF_SCATTER_GATHER */ rte_mempool_put(m->pool, m); } @@ -439,7 +1104,7 @@ __rte_mbuf_raw_free(struct rte_mbuf *m) * The index of the mbuf in the pool table. */ void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg, - void *m, unsigned i); + void *m, unsigned i); /** * Allocate a new mbuf (type is ctrl) from mempool *mp*. @@ -453,16 +1118,7 @@ void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg, * - The pointer to the new mbuf on success. * - NULL if allocation failed. */ -static inline struct rte_mbuf *rte_ctrlmbuf_alloc(struct rte_mempool *mp) -{ - struct rte_mbuf *m; - if ((m = __rte_mbuf_raw_alloc(mp)) != NULL) { - m->ctrl.data = m->buf_addr; - m->ctrl.data_len = 0; - __rte_mbuf_sanity_check(m, RTE_MBUF_CTRL, 0); - } - return (m); -} +#define rte_ctrlmbuf_alloc(mp) rte_pktmbuf_alloc(mp) /** * Free a control mbuf back into its original mempool. @@ -470,14 +1126,7 @@ static inline struct rte_mbuf *rte_ctrlmbuf_alloc(struct rte_mempool *mp) * @param m * The control mbuf to be freed. */ -static inline void rte_ctrlmbuf_free(struct rte_mbuf *m) -{ - __rte_mbuf_sanity_check(m, RTE_MBUF_CTRL, 0); -#ifdef RTE_MBUF_SCATTER_GATHER - if (rte_mbuf_refcnt_update(m, -1) == 0) -#endif /* RTE_MBUF_SCATTER_GATHER */ - __rte_mbuf_raw_free(m); -} +#define rte_ctrlmbuf_free(m) rte_pktmbuf_free(m) /** * A macro that returns the pointer to the carried data. @@ -487,7 +1136,7 @@ static inline void rte_ctrlmbuf_free(struct rte_mbuf *m) * @param m * The control mbuf. */ -#define rte_ctrlmbuf_data(m) ((m)->ctrl.data) +#define rte_ctrlmbuf_data(m) ((char *)((m)->buf_addr) + (m)->data_off) /** * A macro that returns the length of the carried data. @@ -497,15 +1146,30 @@ static inline void rte_ctrlmbuf_free(struct rte_mbuf *m) * @param m * The control mbuf. */ -#define rte_ctrlmbuf_len(m) ((m)->ctrl.data_len) +#define rte_ctrlmbuf_len(m) rte_pktmbuf_data_len(m) + +/** + * Tests if an mbuf is a control mbuf + * + * @param m + * The mbuf to be tested + * @return + * - True (1) if the mbuf is a control mbuf + * - False(0) otherwise + */ +static inline int +rte_is_ctrlmbuf(struct rte_mbuf *m) +{ + return !!(m->ol_flags & CTRL_MBUF_FLAG); +} /* Operations on pkt mbuf */ /** * The packet mbuf constructor. * - * This function initializes some fields in the mbuf structure that are not - * modified by the user once created (mbuf type, origin pool, buffer start + * This function initializes some fields in the mbuf structure that are + * not modified by the user once created (origin pool, buffer start * address, and so on). This function is given as a callback function to * rte_mempool_create() at pool creation time. * @@ -542,6 +1206,87 @@ void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg, */ void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg); +/** + * Create a mbuf pool. + * + * This function creates and initializes a packet mbuf pool. It is + * a wrapper to rte_mempool_create() with the proper packet constructor + * and mempool constructor. + * + * @param name + * The name of the mbuf pool. + * @param n + * The number of elements in the mbuf pool. The optimum size (in terms + * of memory usage) for a mempool is when n is a power of two minus one: + * n = (2^q - 1). + * @param cache_size + * Size of the per-core object cache. See rte_mempool_create() for + * details. + * @param priv_size + * Size of application private are between the rte_mbuf structure + * and the data buffer. This value must be aligned to RTE_MBUF_PRIV_ALIGN. + * @param data_room_size + * Size of data buffer in each mbuf, including RTE_PKTMBUF_HEADROOM. + * @param socket_id + * The socket identifier where the memory should be allocated. The + * value can be *SOCKET_ID_ANY* if there is no NUMA constraint for the + * reserved zone. + * @return + * The pointer to the new allocated mempool, on success. NULL on error + * with rte_errno set appropriately. Possible rte_errno values include: + * - E_RTE_NO_CONFIG - function could not get pointer to rte_config structure + * - E_RTE_SECONDARY - function was called from a secondary process instance + * - EINVAL - cache size provided is too large, or priv_size is not aligned. + * - ENOSPC - the maximum number of memzones has already been allocated + * - EEXIST - a memzone with the same name already exists + * - ENOMEM - no appropriate memory area found in which to create memzone + */ +struct rte_mempool * +rte_pktmbuf_pool_create(const char *name, unsigned n, + unsigned cache_size, uint16_t priv_size, uint16_t data_room_size, + int socket_id); + +/** + * Get the data room size of mbufs stored in a pktmbuf_pool + * + * The data room size is the amount of data that can be stored in a + * mbuf including the headroom (RTE_PKTMBUF_HEADROOM). + * + * @param mp + * The packet mbuf pool. + * @return + * The data room size of mbufs stored in this mempool. + */ +static inline uint16_t +rte_pktmbuf_data_room_size(struct rte_mempool *mp) +{ + struct rte_pktmbuf_pool_private *mbp_priv; + + mbp_priv = (struct rte_pktmbuf_pool_private *)rte_mempool_get_priv(mp); + return mbp_priv->mbuf_data_room_size; +} + +/** + * Get the application private size of mbufs stored in a pktmbuf_pool + * + * The private size of mbuf is a zone located between the rte_mbuf + * structure and the data buffer where an application can store data + * associated to a packet. + * + * @param mp + * The packet mbuf pool. + * @return + * The private size of mbufs stored in this mempool. + */ +static inline uint16_t +rte_pktmbuf_priv_size(struct rte_mempool *mp) +{ + struct rte_pktmbuf_pool_private *mbp_priv; + + mbp_priv = (struct rte_pktmbuf_pool_private *)rte_mempool_get_priv(mp); + return mbp_priv->mbuf_priv_size; +} + /** * Reset the fields of a packet mbuf to their default values. * @@ -552,25 +1297,25 @@ void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg); */ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) { - uint32_t buf_ofs; - - m->pkt.next = NULL; - m->pkt.pkt_len = 0; - m->pkt.vlan_macip.data = 0; - m->pkt.nb_segs = 1; - m->pkt.in_port = 0xff; + m->next = NULL; + m->pkt_len = 0; + m->tx_offload = 0; + m->vlan_tci = 0; + m->vlan_tci_outer = 0; + m->nb_segs = 1; + m->port = 0xff; m->ol_flags = 0; - buf_ofs = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? + m->packet_type = 0; + m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? RTE_PKTMBUF_HEADROOM : m->buf_len; - m->pkt.data = (char*) m->buf_addr + buf_ofs; - m->pkt.data_len = 0; - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + m->data_len = 0; + __rte_mbuf_sanity_check(m, 1); } /** - * Allocate a new mbuf (type is pkt) from a mempool. + * Allocate a new mbuf from a mempool. * * This new mbuf contains one segment, which has a length of 0. The pointer * to data is initialized to have some bytes of headroom in the buffer @@ -587,51 +1332,65 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp) struct rte_mbuf *m; if ((m = __rte_mbuf_raw_alloc(mp)) != NULL) rte_pktmbuf_reset(m); - return (m); + return m; } -#ifdef RTE_MBUF_SCATTER_GATHER - /** * Attach packet mbuf to another packet mbuf. + * * After attachment we refer the mbuf we attached as 'indirect', * while mbuf we attached to as 'direct'. * Right now, not supported: - * - attachment to indirect mbuf (e.g. - md has to be direct). * - attachment for already indirect mbuf (e.g. - mi has to be direct). * - mbuf we trying to attach (mi) is used by someone else * e.g. it's reference counter is greater then 1. * * @param mi * The indirect packet mbuf. - * @param md - * The direct packet mbuf. + * @param m + * The packet mbuf we're attaching to. */ - -static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md) +static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) { - RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(md) && - RTE_MBUF_DIRECT(mi) && - rte_mbuf_refcnt_read(mi) == 1); - - rte_mbuf_refcnt_update(md, 1); - mi->buf_physaddr = md->buf_physaddr; - mi->buf_addr = md->buf_addr; - mi->buf_len = md->buf_len; + struct rte_mbuf *md; - mi->pkt = md->pkt; + RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(mi) && + rte_mbuf_refcnt_read(mi) == 1); - mi->pkt.next = NULL; - mi->pkt.pkt_len = mi->pkt.data_len; - mi->pkt.nb_segs = 1; - mi->ol_flags = md->ol_flags; + /* if m is not direct, get the mbuf that embeds the data */ + if (RTE_MBUF_DIRECT(m)) + md = m; + else + md = rte_mbuf_from_indirect(m); - __rte_mbuf_sanity_check(mi, RTE_MBUF_PKT, 1); - __rte_mbuf_sanity_check(md, RTE_MBUF_PKT, 0); + rte_mbuf_refcnt_update(md, 1); + mi->priv_size = m->priv_size; + mi->buf_physaddr = m->buf_physaddr; + mi->buf_addr = m->buf_addr; + mi->buf_len = m->buf_len; + + mi->next = m->next; + mi->data_off = m->data_off; + mi->data_len = m->data_len; + mi->port = m->port; + mi->vlan_tci = m->vlan_tci; + mi->vlan_tci_outer = m->vlan_tci_outer; + mi->tx_offload = m->tx_offload; + mi->hash = m->hash; + + mi->next = NULL; + mi->pkt_len = mi->data_len; + mi->nb_segs = 1; + mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF; + mi->packet_type = m->packet_type; + + __rte_mbuf_sanity_check(mi, 1); + __rte_mbuf_sanity_check(m, 0); } /** - * Detach an indirect packet mbuf - + * Detach an indirect packet mbuf. + * * - restore original mbuf address and length values. * - reset pktmbuf data and data_len to their default values. * All other fields of the given packet mbuf will be left intact. @@ -639,55 +1398,44 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md) * @param m * The indirect attached packet mbuf. */ - static inline void rte_pktmbuf_detach(struct rte_mbuf *m) { - const struct rte_mempool *mp = m->pool; - void *buf = RTE_MBUF_TO_BADDR(m); - uint32_t buf_ofs; - uint32_t buf_len = mp->elt_size - sizeof(*m); - m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof (*m); - - m->buf_addr = buf; - m->buf_len = (uint16_t)buf_len; + struct rte_mempool *mp = m->pool; + uint32_t mbuf_size, buf_len, priv_size; - buf_ofs = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? - RTE_PKTMBUF_HEADROOM : m->buf_len; - m->pkt.data = (char*) m->buf_addr + buf_ofs; + priv_size = rte_pktmbuf_priv_size(mp); + mbuf_size = sizeof(struct rte_mbuf) + priv_size; + buf_len = rte_pktmbuf_data_room_size(mp); - m->pkt.data_len = 0; + m->priv_size = priv_size; + m->buf_addr = (char *)m + mbuf_size; + m->buf_physaddr = rte_mempool_virt2phy(mp, m) + mbuf_size; + m->buf_len = (uint16_t)buf_len; + m->data_off = RTE_MIN(RTE_PKTMBUF_HEADROOM, (uint16_t)m->buf_len); + m->data_len = 0; + m->ol_flags = 0; } -#endif /* RTE_MBUF_SCATTER_GATHER */ - - static inline struct rte_mbuf* __attribute__((always_inline)) __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 0); + __rte_mbuf_sanity_check(m, 0); -#ifdef RTE_MBUF_SCATTER_GATHER - if (likely (rte_mbuf_refcnt_read(m) == 1) || - likely (rte_mbuf_refcnt_update(m, -1) == 0)) { - struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr); - - rte_mbuf_refcnt_set(m, 0); + if (likely(rte_mbuf_refcnt_update(m, -1) == 0)) { /* if this is an indirect mbuf, then * - detach mbuf * - free attached mbuf segment */ - if (unlikely (md != m)) { + if (RTE_MBUF_INDIRECT(m)) { + struct rte_mbuf *md = rte_mbuf_from_indirect(m); rte_pktmbuf_detach(m); if (rte_mbuf_refcnt_update(md, -1) == 0) __rte_mbuf_raw_free(md); } -#endif - return(m); -#ifdef RTE_MBUF_SCATTER_GATHER + return m; } - return (NULL); -#endif + return NULL; } /** @@ -702,8 +1450,10 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) static inline void __attribute__((always_inline)) rte_pktmbuf_free_seg(struct rte_mbuf *m) { - if (likely(NULL != (m = __rte_pktmbuf_prefree_seg(m)))) + if (likely(NULL != (m = __rte_pktmbuf_prefree_seg(m)))) { + m->next = NULL; __rte_mbuf_raw_free(m); + } } /** @@ -719,17 +1469,15 @@ static inline void rte_pktmbuf_free(struct rte_mbuf *m) { struct rte_mbuf *m_next; - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); while (m != NULL) { - m_next = m->pkt.next; + m_next = m->next; rte_pktmbuf_free_seg(m); m = m_next; } } -#ifdef RTE_MBUF_SCATTER_GATHER - /** * Creates a "clone" of the given packet mbuf. * @@ -755,33 +1503,33 @@ static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md, uint8_t nseg; if (unlikely ((mc = rte_pktmbuf_alloc(mp)) == NULL)) - return (NULL); + return NULL; mi = mc; - prev = &mi->pkt.next; - pktlen = md->pkt.pkt_len; + prev = &mi->next; + pktlen = md->pkt_len; nseg = 0; do { nseg++; rte_pktmbuf_attach(mi, md); *prev = mi; - prev = &mi->pkt.next; - } while ((md = md->pkt.next) != NULL && + prev = &mi->next; + } while ((md = md->next) != NULL && (mi = rte_pktmbuf_alloc(mp)) != NULL); *prev = NULL; - mc->pkt.nb_segs = nseg; - mc->pkt.pkt_len = pktlen; + mc->nb_segs = nseg; + mc->pkt_len = pktlen; /* Allocation of new indirect segment failed */ if (unlikely (mi == NULL)) { rte_pktmbuf_free(mc); - return (NULL); + return NULL; } - __rte_mbuf_sanity_check(mc, RTE_MBUF_PKT, 1); - return (mc); + __rte_mbuf_sanity_check(mc, 1); + return mc; } /** @@ -797,15 +1545,13 @@ static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md, */ static inline void rte_pktmbuf_refcnt_update(struct rte_mbuf *m, int16_t v) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); do { rte_mbuf_refcnt_update(m, v); - } while ((m = m->pkt.next) != NULL); + } while ((m = m->next) != NULL); } -#endif /* RTE_MBUF_SCATTER_GATHER */ - /** * Get the headroom in a packet mbuf. * @@ -816,8 +1562,8 @@ static inline void rte_pktmbuf_refcnt_update(struct rte_mbuf *m, int16_t v) */ static inline uint16_t rte_pktmbuf_headroom(const struct rte_mbuf *m) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); - return (uint16_t) ((char*) m->pkt.data - (char*) m->buf_addr); + __rte_mbuf_sanity_check(m, 1); + return m->data_off; } /** @@ -830,9 +1576,9 @@ static inline uint16_t rte_pktmbuf_headroom(const struct rte_mbuf *m) */ static inline uint16_t rte_pktmbuf_tailroom(const struct rte_mbuf *m) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); return (uint16_t)(m->buf_len - rte_pktmbuf_headroom(m) - - m->pkt.data_len); + m->data_len); } /** @@ -847,25 +1593,63 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) { struct rte_mbuf *m2 = (struct rte_mbuf *)m; - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); - while (m2->pkt.next != NULL) - m2 = m2->pkt.next; + __rte_mbuf_sanity_check(m, 1); + while (m2->next != NULL) + m2 = m2->next; return m2; } +/** + * A macro that points to an offset into the data in the mbuf. + * + * The returned pointer is cast to type t. Before using this + * function, the user must ensure that the first segment is large + * enough to accommodate its data. + * + * @param m + * The packet mbuf. + * @param o + * The offset into the mbuf data. + * @param t + * The type to cast the result into. + */ +#define rte_pktmbuf_mtod_offset(m, t, o) \ + ((t)((char *)(m)->buf_addr + (m)->data_off + (o))) + /** * A macro that points to the start of the data in the mbuf. * * The returned pointer is cast to type t. Before using this - * function, the user must ensure that m_headlen(m) is large enough to - * read its data. + * function, the user must ensure that the first segment is large + * enough to accommodate its data. * * @param m * The packet mbuf. * @param t * The type to cast the result into. */ -#define rte_pktmbuf_mtod(m, t) ((t)((m)->pkt.data)) +#define rte_pktmbuf_mtod(m, t) rte_pktmbuf_mtod_offset(m, t, 0) + +/** + * A macro that returns the physical address that points to an offset of the + * start of the data in the mbuf + * + * @param m + * The packet mbuf. + * @param o + * The offset into the data to calculate address from. + */ +#define rte_pktmbuf_mtophys_offset(m, o) \ + (phys_addr_t)((m)->buf_physaddr + (m)->data_off + (o)) + +/** + * A macro that returns the physical address that points to the start of the + * data in the mbuf + * + * @param m + * The packet mbuf. + */ +#define rte_pktmbuf_mtophys(m) rte_pktmbuf_mtophys_offset(m, 0) /** * A macro that returns the length of the packet. @@ -875,7 +1659,7 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) * @param m * The packet mbuf. */ -#define rte_pktmbuf_pkt_len(m) ((m)->pkt.pkt_len) +#define rte_pktmbuf_pkt_len(m) ((m)->pkt_len) /** * A macro that returns the length of the segment. @@ -885,7 +1669,7 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) * @param m * The packet mbuf. */ -#define rte_pktmbuf_data_len(m) ((m)->pkt.data_len) +#define rte_pktmbuf_data_len(m) ((m)->data_len) /** * Prepend len bytes to an mbuf data area. @@ -905,16 +1689,16 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) static inline char *rte_pktmbuf_prepend(struct rte_mbuf *m, uint16_t len) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); if (unlikely(len > rte_pktmbuf_headroom(m))) return NULL; - m->pkt.data = (char*) m->pkt.data - len; - m->pkt.data_len = (uint16_t)(m->pkt.data_len + len); - m->pkt.pkt_len = (m->pkt.pkt_len + len); + m->data_off -= len; + m->data_len = (uint16_t)(m->data_len + len); + m->pkt_len = (m->pkt_len + len); - return (char*) m->pkt.data; + return (char *)m->buf_addr + m->data_off; } /** @@ -937,15 +1721,15 @@ static inline char *rte_pktmbuf_append(struct rte_mbuf *m, uint16_t len) void *tail; struct rte_mbuf *m_last; - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); m_last = rte_pktmbuf_lastseg(m); if (unlikely(len > rte_pktmbuf_tailroom(m_last))) return NULL; - tail = (char*) m_last->pkt.data + m_last->pkt.data_len; - m_last->pkt.data_len = (uint16_t)(m_last->pkt.data_len + len); - m->pkt.pkt_len = (m->pkt.pkt_len + len); + tail = (char *)m_last->buf_addr + m_last->data_off + m_last->data_len; + m_last->data_len = (uint16_t)(m_last->data_len + len); + m->pkt_len = (m->pkt_len + len); return (char*) tail; } @@ -965,15 +1749,15 @@ static inline char *rte_pktmbuf_append(struct rte_mbuf *m, uint16_t len) */ static inline char *rte_pktmbuf_adj(struct rte_mbuf *m, uint16_t len) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); - if (unlikely(len > m->pkt.data_len)) + if (unlikely(len > m->data_len)) return NULL; - m->pkt.data_len = (uint16_t)(m->pkt.data_len - len); - m->pkt.data = ((char*) m->pkt.data + len); - m->pkt.pkt_len = (m->pkt.pkt_len - len); - return (char*) m->pkt.data; + m->data_len = (uint16_t)(m->data_len - len); + m->data_off += len; + m->pkt_len = (m->pkt_len - len); + return (char *)m->buf_addr + m->data_off; } /** @@ -994,14 +1778,14 @@ static inline int rte_pktmbuf_trim(struct rte_mbuf *m, uint16_t len) { struct rte_mbuf *m_last; - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); + __rte_mbuf_sanity_check(m, 1); m_last = rte_pktmbuf_lastseg(m); - if (unlikely(len > m_last->pkt.data_len)) + if (unlikely(len > m_last->data_len)) return -1; - m_last->pkt.data_len = (uint16_t)(m_last->pkt.data_len - len); - m->pkt.pkt_len = (m->pkt.pkt_len - len); + m_last->data_len = (uint16_t)(m_last->data_len - len); + m->pkt_len = (m->pkt_len - len); return 0; } @@ -1016,8 +1800,46 @@ static inline int rte_pktmbuf_trim(struct rte_mbuf *m, uint16_t len) */ static inline int rte_pktmbuf_is_contiguous(const struct rte_mbuf *m) { - __rte_mbuf_sanity_check(m, RTE_MBUF_PKT, 1); - return !!(m->pkt.nb_segs == 1); + __rte_mbuf_sanity_check(m, 1); + return !!(m->nb_segs == 1); +} + +/** + * Chain an mbuf to another, thereby creating a segmented packet. + * + * Note: The implementation will do a linear walk over the segments to find + * the tail entry. For cases when there are many segments, it's better to + * chain the entries manually. + * + * @param head + * The head of the mbuf chain (the first packet) + * @param tail + * The mbuf to put last in the chain + * + * @return + * - 0, on success. + * - -EOVERFLOW, if the chain is full (256 entries) + */ +static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail) +{ + struct rte_mbuf *cur_tail; + + /* Check for number-of-segments-overflow */ + if (head->nb_segs + tail->nb_segs >= 1 << (sizeof(head->nb_segs) * 8)) + return -EOVERFLOW; + + /* Chain 'tail' onto the old tail */ + cur_tail = rte_pktmbuf_lastseg(head); + cur_tail->next = tail; + + /* accumulate number of segments and total length. */ + head->nb_segs = (uint8_t)(head->nb_segs + tail->nb_segs); + head->pkt_len += tail->pkt_len; + + /* pkt_len is only set in the head */ + tail->pkt_len = tail->data_len; + + return 0; } /**