X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=c973e9b6de8eba47a443b93255aeb1cbd1bb486b;hb=99a5744147ea079828a52ee904ea79ba52602c16;hp=17ba7915dcf52f811839bb4af55f23925b491090;hpb=e1545b393a7e53b3dda09eefe2d7ecda4b4d49cf;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 17ba7915dc..c973e9b6de 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -54,6 +54,7 @@ */ #include +#include #include #include #include @@ -64,8 +65,9 @@ extern "C" { #endif -/* deprecated feature, renamed in RTE_MBUF_REFCNT */ +/* 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. @@ -73,9 +75,10 @@ extern "C" { * * - RX flags start at bit position zero, and get added to the left of previous * flags. - * - The most-significant 8 bits are reserved for generic mbuf flags - * - TX flags therefore start at bit position 55 (i.e. 63-8), and new flags get - * added to the right of the previously defined 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(). @@ -90,20 +93,20 @@ extern "C" { #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_IPV4_HDR (1ULL << 5) /**< RX packet with IPv4 header. */ -#define PKT_RX_IPV4_HDR_EXT (1ULL << 6) /**< RX packet with extended IPv4 header. */ -#define PKT_RX_IPV6_HDR (1ULL << 7) /**< RX packet with IPv6 header. */ -#define PKT_RX_IPV6_HDR_EXT (1ULL << 8) /**< RX packet with extended IPv6 header. */ #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_TUNNEL_IPV4_HDR (1ULL << 11) /**< RX tunnel packet with IPv4 header.*/ -#define PKT_RX_TUNNEL_IPV6_HDR (1ULL << 12) /**< RX tunnel packet with IPv6 header. */ #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: @@ -189,11 +192,503 @@ extern "C" { */ #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 */ +/* + * 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 + +/** + * 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. + */ +#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 * @@ -216,6 +711,16 @@ const char *rte_get_rx_ol_flag_name(uint64_t mask); */ const char *rte_get_tx_ol_flag_name(uint64_t mask); +/** + * 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 */ @@ -223,6 +728,9 @@ 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. */ @@ -258,17 +766,27 @@ struct rte_mbuf { /* remaining bytes are set on RX when pulling packet from descriptor */ MARKER rx_descriptor_fields1; - /** - * The packet type, which is used to indicate ordinary packet and also - * tunneled packet format, i.e. each number is represented a type of - * packet. + /* + * The packet type, which is the combination of outer/inner L2, L3, L4 + * and tunnel types. */ - uint16_t packet_type; + 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. */ + }; + }; - uint16_t data_len; /**< Amount of data in segment buffer. */ 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) */ - uint16_t reserved; + union { uint32_t rss; /**< RSS hash result if RSS enabled */ struct { @@ -284,14 +802,19 @@ struct rte_mbuf { /**< First 4 flexible bytes or FD ID, dependent on PKT_RX_FDIR_* flag in ol_flags. */ } fdir; /**< Filter identifier if FDIR enabled */ - uint32_t sched; /**< Hierarchical scheduler */ + 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_aligned; + MARKER cacheline1 __rte_cache_min_aligned; union { void *userdata; /**< Can be used for external metadata */ @@ -317,18 +840,49 @@ struct rte_mbuf { /* 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. @@ -347,7 +901,8 @@ 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 @@ -382,21 +937,6 @@ if (!(exp)) { \ #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 @@ -423,6 +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 */ /** @@ -497,7 +1064,7 @@ static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) m = (struct rte_mbuf *)mb; RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); rte_mbuf_refcnt_set(m, 1); - return (m); + return m; } /** @@ -593,7 +1160,7 @@ void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg, static inline int rte_is_ctrlmbuf(struct rte_mbuf *m) { - return (!!(m->ol_flags & CTRL_MBUF_FLAG)); + return !!(m->ol_flags & CTRL_MBUF_FLAG); } /* Operations on pkt mbuf */ @@ -639,6 +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. * @@ -653,6 +1301,7 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) m->pkt_len = 0; m->tx_offload = 0; m->vlan_tci = 0; + m->vlan_tci_outer = 0; m->nb_segs = 1; m->port = 0xff; @@ -683,56 +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; } /** * 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) && + struct rte_mbuf *md; + + RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(mi) && rte_mbuf_refcnt_read(mi) == 1); + /* 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_refcnt_update(md, 1); - mi->buf_physaddr = md->buf_physaddr; - mi->buf_addr = md->buf_addr; - mi->buf_len = md->buf_len; - - mi->next = md->next; - mi->data_off = md->data_off; - mi->data_len = md->data_len; - mi->port = md->port; - mi->vlan_tci = md->vlan_tci; - mi->tx_offload = md->tx_offload; - mi->hash = md->hash; + 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 = md->ol_flags | IND_ATTACHED_MBUF; - mi->packet_type = md->packet_type; + 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(md, 0); + __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. @@ -740,22 +1398,21 @@ 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_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; - m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? - RTE_PKTMBUF_HEADROOM : m->buf_len; + priv_size = rte_pktmbuf_priv_size(mp); + mbuf_size = sizeof(struct rte_mbuf) + priv_size; + buf_len = rte_pktmbuf_data_room_size(mp); + 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; } @@ -764,24 +1421,21 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) { __rte_mbuf_sanity_check(m, 0); - if (likely (rte_mbuf_refcnt_read(m) == 1) || - likely (rte_mbuf_refcnt_update(m, -1) == 0)) { - - 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 (RTE_MBUF_INDIRECT(m)) { - struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr); + 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); } - return(m); + return m; } - return (NULL); + return NULL; } /** @@ -849,7 +1503,7 @@ 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->next; @@ -871,11 +1525,11 @@ static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md, /* Allocation of new indirect segment failed */ if (unlikely (mi == NULL)) { rte_pktmbuf_free(mc); - return (NULL); + return NULL; } __rte_mbuf_sanity_check(mc, 1); - return (mc); + return mc; } /** @@ -945,19 +1599,57 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) 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)((char *)(m)->buf_addr + (m)->data_off)) +#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. @@ -1112,6 +1804,44 @@ static inline int rte_pktmbuf_is_contiguous(const struct rte_mbuf *m) 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; +} + /** * Dump an mbuf structure to the console. *