X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=dd08cb72b32ae8cbce41929eef9b92b3f974aedb;hb=b91c0f786e2562ab744822bb9ab8ec30e8fcbce5;hp=85a653c27ad6c29f84af6b77f7eaf949957631ac;hpb=febf2bb46d727563e0de7a6f43d5a2da9f68e17a;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 85a653c27a..dd08cb72b3 100644 --- a/lib/librte_mbuf/rte_mbuf.h +++ b/lib/librte_mbuf/rte_mbuf.h @@ -44,7 +44,14 @@ * buffers. The message buffers are stored in a mempool, using the * RTE mempool library. * - * This library provide an API to allocate/free packet mbufs, which are + * The preferred way to create a mbuf pool is to use + * rte_pktmbuf_pool_create(). However, in some situations, an + * application may want to have more control (ex: populate the pool with + * specific memory), in this case it is possible to use functions from + * rte_mempool. See how rte_pktmbuf_pool_create() is implemented for + * details. + * + * This library provides an API to allocate/free packet mbufs, which are * used to carry network packets. * * To understand the concepts of packet buffers or mbufs, you @@ -60,6 +67,7 @@ #include #include #include +#include #ifdef __cplusplus extern "C" { @@ -81,27 +89,74 @@ extern "C" { */ /** - * RX packet is a 802.1q VLAN packet. This flag was set by PMDs when - * the packet is recognized as a VLAN, but the behavior between PMDs - * was not the same. This flag is kept for some time to avoid breaking - * applications and should be replaced by PKT_RX_VLAN_STRIPPED. + * The RX packet is a 802.1q VLAN packet, and the tci has been + * saved in in mbuf->vlan_tci. + * If the flag PKT_RX_VLAN_STRIPPED is also present, the VLAN + * header has been stripped from mbuf data, else it is still + * present. */ -#define PKT_RX_VLAN_PKT (1ULL << 0) +#define PKT_RX_VLAN (1ULL << 0) #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. */ + +/** + * Deprecated. + * Checking this flag alone is deprecated: check the 2 bits of + * PKT_RX_L4_CKSUM_MASK. + * This flag was set when the L4 checksum of a packet was detected as + * wrong by the hardware. + */ +#define PKT_RX_L4_CKSUM_BAD (1ULL << 3) + +/** + * Deprecated. + * Checking this flag alone is deprecated: check the 2 bits of + * PKT_RX_IP_CKSUM_MASK. + * This flag was set when the IP checksum of a packet was detected as + * wrong by the hardware. + */ +#define PKT_RX_IP_CKSUM_BAD (1ULL << 4) + #define PKT_RX_EIP_CKSUM_BAD (1ULL << 5) /**< External IP header checksum error. */ /** * A vlan has been stripped by the hardware and its tci is saved in * mbuf->vlan_tci. This can only happen if vlan stripping is enabled * in the RX configuration of the PMD. + * When PKT_RX_VLAN_STRIPPED is set, PKT_RX_VLAN must also be set. */ #define PKT_RX_VLAN_STRIPPED (1ULL << 6) -/* hole, some bits can be reused here */ +/** + * Mask of bits used to determine the status of RX IP checksum. + * - PKT_RX_IP_CKSUM_UNKNOWN: no information about the RX IP checksum + * - PKT_RX_IP_CKSUM_BAD: the IP checksum in the packet is wrong + * - PKT_RX_IP_CKSUM_GOOD: the IP checksum in the packet is valid + * - PKT_RX_IP_CKSUM_NONE: the IP checksum is not correct in the packet + * data, but the integrity of the IP header is verified. + */ +#define PKT_RX_IP_CKSUM_MASK ((1ULL << 4) | (1ULL << 7)) + +#define PKT_RX_IP_CKSUM_UNKNOWN 0 +#define PKT_RX_IP_CKSUM_BAD (1ULL << 4) +#define PKT_RX_IP_CKSUM_GOOD (1ULL << 7) +#define PKT_RX_IP_CKSUM_NONE ((1ULL << 4) | (1ULL << 7)) + +/** + * Mask of bits used to determine the status of RX L4 checksum. + * - PKT_RX_L4_CKSUM_UNKNOWN: no information about the RX L4 checksum + * - PKT_RX_L4_CKSUM_BAD: the L4 checksum in the packet is wrong + * - PKT_RX_L4_CKSUM_GOOD: the L4 checksum in the packet is valid + * - PKT_RX_L4_CKSUM_NONE: the L4 checksum is not correct in the packet + * data, but the integrity of the L4 data is verified. + */ +#define PKT_RX_L4_CKSUM_MASK ((1ULL << 3) | (1ULL << 8)) + +#define PKT_RX_L4_CKSUM_UNKNOWN 0 +#define PKT_RX_L4_CKSUM_BAD (1ULL << 3) +#define PKT_RX_L4_CKSUM_GOOD (1ULL << 8) +#define PKT_RX_L4_CKSUM_NONE ((1ULL << 3) | (1ULL << 8)) #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.*/ @@ -112,22 +167,72 @@ extern "C" { * The 2 vlans have been stripped by the hardware and their tci are * saved in mbuf->vlan_tci (inner) and mbuf->vlan_tci_outer (outer). * This can only happen if vlan stripping is enabled in the RX - * configuration of the PMD. If this flag is set, PKT_RX_VLAN_STRIPPED - * must also be set. + * configuration of the PMD. If this flag is set, + * When PKT_RX_QINQ_STRIPPED is set, the flags (PKT_RX_VLAN | + * PKT_RX_VLAN_STRIPPED | PKT_RX_QINQ) must also be set. */ #define PKT_RX_QINQ_STRIPPED (1ULL << 15) /** - * Deprecated. - * RX packet with double VLAN stripped. - * This flag is replaced by PKT_RX_QINQ_STRIPPED. + * When packets are coalesced by a hardware or virtual driver, this flag + * can be set in the RX mbuf, meaning that the m->tso_segsz field is + * valid and is set to the segment size of original packets. */ -#define PKT_RX_QINQ_PKT PKT_RX_QINQ_STRIPPED +#define PKT_RX_LRO (1ULL << 16) + +/** + * Indicate that the timestamp field in the mbuf is valid. + */ +#define PKT_RX_TIMESTAMP (1ULL << 17) + +/** + * Indicate that security offload processing was applied on the RX packet. + */ +#define PKT_RX_SEC_OFFLOAD (1ULL << 18) + +/** + * Indicate that security offload processing failed on the RX packet. + */ +#define PKT_RX_SEC_OFFLOAD_FAILED (1ULL << 19) + +/** + * The RX packet is a double VLAN, and the outer tci has been + * saved in in mbuf->vlan_tci_outer. + * If the flag PKT_RX_QINQ_STRIPPED is also present, both VLANs + * headers have been stripped from mbuf data, else they are still + * present. + */ +#define PKT_RX_QINQ (1ULL << 20) /* add new RX flags here */ /* add new TX flags here */ +/** + * Request security offload processing on the TX packet. + */ +#define PKT_TX_SEC_OFFLOAD (1ULL << 43) + +/** + * Offload the MACsec. This flag must be set by the application to enable + * this offload feature for a packet to be transmitted. + */ +#define PKT_TX_MACSEC (1ULL << 44) + +/** + * Bits 45:48 used for the tunnel type. + * When doing Tx offload like TSO or checksum, the HW needs to configure the + * tunnel type into the HW descriptors. + */ +#define PKT_TX_TUNNEL_VXLAN (0x1ULL << 45) +#define PKT_TX_TUNNEL_GRE (0x2ULL << 45) +#define PKT_TX_TUNNEL_IPIP (0x3ULL << 45) +#define PKT_TX_TUNNEL_GENEVE (0x4ULL << 45) +/**< TX packet with MPLS-in-UDP RFC 7510 header. */ +#define PKT_TX_TUNNEL_MPLSINUDP (0x5ULL << 45) +/* add new TX TUNNEL type here */ +#define PKT_TX_TUNNEL_MASK (0xFULL << 45) + /** * Second VLAN insertion (QinQ) flag. */ @@ -218,6 +323,22 @@ extern "C" { */ #define PKT_TX_OUTER_IPV6 (1ULL << 60) +/** + * Bitmask of all supported packet Tx offload features flags, + * which can be set for packet. + */ +#define PKT_TX_OFFLOAD_MASK ( \ + PKT_TX_IP_CKSUM | \ + PKT_TX_L4_MASK | \ + PKT_TX_OUTER_IP_CKSUM | \ + PKT_TX_TCP_SEG | \ + PKT_TX_IEEE1588_TMST | \ + PKT_TX_QINQ_PKT | \ + PKT_TX_VLAN_PKT | \ + PKT_TX_TUNNEL_MASK | \ + PKT_TX_MACSEC | \ + PKT_TX_SEC_OFFLOAD) + #define __RESERVED (1ULL << 61) /**< reserved for future mbuf use */ #define IND_ATTACHED_MBUF (1ULL << 62) /**< Indirect attached mbuf */ @@ -225,500 +346,6 @@ extern "C" { /* 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 -/** - * NSH (Network Service Header) packet type. - * - * Packet format: - * <'ether type'=0x894F> - */ -#define RTE_PTYPE_L2_ETHER_NSH 0x00000005 -/** - * 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 @@ -732,6 +359,20 @@ extern "C" { */ const char *rte_get_rx_ol_flag_name(uint64_t mask); +/** + * Dump the list of RX offload flags in a buffer + * + * @param mask + * The mask describing the RX flags. + * @param buf + * The output buffer. + * @param buflen + * The length of the buffer. + * @return + * 0 on success, (-1) on error. + */ +int rte_get_rx_ol_flag_list(uint64_t mask, char *buf, size_t buflen); + /** * Get the name of a TX offload flag * @@ -744,6 +385,20 @@ const char *rte_get_rx_ol_flag_name(uint64_t mask); */ const char *rte_get_tx_ol_flag_name(uint64_t mask); +/** + * Dump the list of TX offload flags in a buffer + * + * @param mask + * The mask describing the TX flags. + * @param buf + * The output buffer. + * @param buflen + * The length of the buffer. + * @return + * 0 on success, (-1) on error. + */ +int rte_get_tx_ol_flag_list(uint64_t mask, char *buf, size_t buflen); + /** * Some NICs need at least 2KB buffer to RX standard Ethernet frame without * splitting it into multiple segments. @@ -771,16 +426,25 @@ struct rte_mbuf { 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. */ + /** + * Physical address of segment buffer. + * Force alignment to 8-bytes, so as to ensure we have the exact + * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes + * working on vector drivers easier. + */ + RTE_STD_C11 + union { + rte_iova_t buf_iova; + rte_iova_t buf_physaddr; /**< deprecated */ + } __rte_aligned(sizeof(rte_iova_t)); - /* next 6 bytes are initialised on RX descriptor rearm */ - MARKER8 rearm_data; + /* next 8 bytes are initialised on RX descriptor rearm */ + MARKER64 rearm_data; uint16_t data_off; /** - * 16-bit Reference counter. + * Reference counter. Its size should at least equal to the size + * of port field (16 bits), to support zero-copy broadcast. * It should only be accessed using the following functions: * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and * rte_mbuf_refcnt_set(). The functionality of these functions (atomic, @@ -792,8 +456,10 @@ struct rte_mbuf { rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ uint16_t refcnt; /**< Non-atomically accessed refcnt */ }; - uint8_t nb_segs; /**< Number of segments. */ - uint8_t port; /**< Input port. */ + uint16_t nb_segs; /**< Number of segments. */ + + /** Input port (16 bits to support more than 256 virtual ports). */ + uint16_t port; uint64_t ol_flags; /**< Offload features. */ @@ -815,8 +481,21 @@ struct rte_mbuf { 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. */ + RTE_STD_C11 + union { + uint8_t inner_esp_next_proto; + /**< ESP next protocol type, valid if + * RTE_PTYPE_TUNNEL_ESP tunnel type is set + * on both Tx and Rx. + */ + __extension__ + struct { + uint8_t inner_l2_type:4; + /**< Inner L2 type. */ + uint8_t inner_l3_type:4; + /**< Inner L3 type. */ + }; + }; uint32_t inner_l4_type:4; /**< Inner L4 type. */ }; }; @@ -849,11 +528,16 @@ struct rte_mbuf { uint32_t usr; /**< User defined tags. See rte_distributor_process() */ } hash; /**< hash information */ - uint32_t seqn; /**< Sequence number. See also rte_reorder_insert() */ - /** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ_STRIPPED is set. */ uint16_t vlan_tci_outer; + uint16_t buf_len; /**< Length of segment buffer. */ + + /** Valid if PKT_RX_TIMESTAMP is set. The unit and time reference + * are not normalized but are always the same for a given port. + */ + uint64_t timestamp; + /* second cache line - fields only used in slow path or on TX */ MARKER cacheline1 __rte_cache_min_aligned; @@ -872,7 +556,10 @@ struct rte_mbuf { uint64_t tx_offload; /**< combined for easy fetch */ __extension__ struct { - uint64_t l2_len:7; /**< L2 (MAC) Header Length. */ + uint64_t l2_len:7; + /**< L2 (MAC) Header Length for non-tunneling pkt. + * Outer_L4_len + ... + Inner_L2_len for tunneling pkt. + */ 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 */ @@ -891,8 +578,15 @@ struct rte_mbuf { /** Timesync flags for use with IEEE1588. */ uint16_t timesync; + + /** Sequence number. See also rte_reorder_insert(). */ + uint32_t seqn; + } __rte_cache_aligned; +/**< Maximum number of nb_segs allowed. */ +#define RTE_MBUF_MAX_NB_SEGS UINT16_MAX + /** * Prefetch the first part of the mbuf * @@ -934,21 +628,28 @@ rte_mbuf_prefetch_part2(struct rte_mbuf *m) static inline uint16_t rte_pktmbuf_priv_size(struct rte_mempool *mp); /** - * Return the DMA address of the beginning of the mbuf data + * Return the IO address of the beginning of the mbuf data * * @param mb * The pointer to the mbuf. * @return - * The physical address of the beginning of the mbuf data + * The IO address of the beginning of the mbuf data */ +static inline rte_iova_t +rte_mbuf_data_iova(const struct rte_mbuf *mb) +{ + return mb->buf_iova + mb->data_off; +} + +__rte_deprecated static inline phys_addr_t rte_mbuf_data_dma_addr(const struct rte_mbuf *mb) { - return mb->buf_physaddr + mb->data_off; + return rte_mbuf_data_iova(mb); } /** - * Return the default DMA address of the beginning of the mbuf data + * Return the default IO address of the beginning of the mbuf data * * This function is used by drivers in their receive function, as it * returns the location where data should be written by the NIC, taking @@ -957,12 +658,19 @@ rte_mbuf_data_dma_addr(const struct rte_mbuf *mb) * @param mb * The pointer to the mbuf. * @return - * The physical address of the beginning of the mbuf data + * The IO address of the beginning of the mbuf data */ +static inline rte_iova_t +rte_mbuf_data_iova_default(const struct rte_mbuf *mb) +{ + return mb->buf_iova + RTE_PKTMBUF_HEADROOM; +} + +__rte_deprecated static inline phys_addr_t rte_mbuf_data_dma_addr_default(const struct rte_mbuf *mb) { - return mb->buf_physaddr + RTE_PKTMBUF_HEADROOM; + return rte_mbuf_data_iova_default(mb); } /** @@ -1056,6 +764,13 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) rte_atomic16_set(&m->refcnt_atomic, new_value); } +/* internal */ +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)); +} + /** * Adds given value to an mbuf's refcnt and returns its new value. * @param m @@ -1080,19 +795,26 @@ rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) return 1 + value; } - return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value)); + return __rte_mbuf_refcnt_update(m, value); } #else /* ! RTE_MBUF_REFCNT_ATOMIC */ +/* internal */ +static inline uint16_t +__rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) +{ + m->refcnt = (uint16_t)(m->refcnt + value); + return m->refcnt; +} + /** * Adds given value to an mbuf's refcnt and returns its new value. */ static inline uint16_t rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value) { - m->refcnt = (uint16_t)(m->refcnt + value); - return m->refcnt; + return __rte_mbuf_refcnt_update(m, value); } /** @@ -1137,14 +859,26 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) void rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header); +#define MBUF_RAW_ALLOC_CHECK(m) do { \ + RTE_ASSERT(rte_mbuf_refcnt_read(m) == 1); \ + RTE_ASSERT((m)->next == NULL); \ + RTE_ASSERT((m)->nb_segs == 1); \ + __rte_mbuf_sanity_check(m, 0); \ +} while (0) + /** - * Allocate an unitialized mbuf from mempool *mp*. + * Allocate an uninitialized mbuf from mempool *mp*. * * This function can be used by PMDs (especially in RX functions) to - * allocate an unitialized mbuf. The driver is responsible of + * allocate an uninitialized mbuf. The driver is responsible of * initializing all the required fields. See rte_pktmbuf_reset(). * For standard needs, prefer rte_pktmbuf_alloc(). * + * The caller can expect that the following fields of the mbuf structure + * are initialized: buf_addr, buf_iova, buf_len, refcnt=1, nb_segs=1, + * next=NULL, pool, priv_size. The other fields must be initialized + * by the caller. + * * @param mp * The mempool from which mbuf is allocated. * @return @@ -1159,28 +893,43 @@ 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; - RTE_ASSERT(rte_mbuf_refcnt_read(m) == 0); - rte_mbuf_refcnt_set(m, 1); - __rte_mbuf_sanity_check(m, 0); - + MBUF_RAW_ALLOC_CHECK(m); return m; } /** - * @internal Put mbuf back into its original mempool. - * The use of that function is reserved for RTE internal needs. - * Please use rte_pktmbuf_free(). + * Put mbuf back into its original mempool. + * + * The caller must ensure that the mbuf is direct and properly + * reinitialized (refcnt=1, next=NULL, nb_segs=1), as done by + * rte_pktmbuf_prefree_seg(). + * + * This function should be used with care, when optimization is + * required. For standard needs, prefer rte_pktmbuf_free() or + * rte_pktmbuf_free_seg(). * * @param m * The mbuf to be freed. */ -static inline void __attribute__((always_inline)) -__rte_mbuf_raw_free(struct rte_mbuf *m) +static __rte_always_inline void +rte_mbuf_raw_free(struct rte_mbuf *m) { - RTE_ASSERT(rte_mbuf_refcnt_read(m) == 0); + RTE_ASSERT(RTE_MBUF_DIRECT(m)); + RTE_ASSERT(rte_mbuf_refcnt_read(m) == 1); + RTE_ASSERT(m->next == NULL); + RTE_ASSERT(m->nb_segs == 1); + __rte_mbuf_sanity_check(m, 0); rte_mempool_put(m->pool, m); } +/* compat with older versions */ +__rte_deprecated +static inline void +__rte_mbuf_raw_free(struct rte_mbuf *m) +{ + rte_mbuf_raw_free(m); +} + /* Operations on ctrl mbuf */ /** @@ -1189,14 +938,14 @@ __rte_mbuf_raw_free(struct rte_mbuf *m) * This function initializes some fields in an mbuf structure that are * not modified by the user once created (mbuf type, origin pool, buffer * start address, and so on). This function is given as a callback function - * to rte_mempool_create() at pool creation time. + * to rte_mempool_obj_iter() or rte_mempool_create() at pool creation time. * * @param mp * The mempool from which the mbuf is allocated. * @param opaque_arg * A pointer that can be used by the user to retrieve useful information - * for mbuf initialization. This pointer comes from the ``init_arg`` - * parameter of rte_mempool_create(). + * for mbuf initialization. This pointer is the opaque argument passed to + * rte_mempool_obj_iter() or rte_mempool_create(). * @param m * The mbuf to initialize. * @param i @@ -1270,14 +1019,14 @@ rte_is_ctrlmbuf(struct rte_mbuf *m) * 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. + * rte_mempool_obj_iter() or rte_mempool_create() at pool creation time. * * @param mp * The mempool from which mbufs originate. * @param opaque_arg * A pointer that can be used by the user to retrieve useful information - * for mbuf initialization. This pointer comes from the ``init_arg`` - * parameter of rte_mempool_create(). + * for mbuf initialization. This pointer is the opaque argument passed to + * rte_mempool_obj_iter() or rte_mempool_create(). * @param m * The mbuf to initialize. * @param i @@ -1292,7 +1041,8 @@ void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg, * * This function initializes the mempool private data in the case of a * pktmbuf pool. This private data is needed by the driver. The - * function is given as a callback function to rte_mempool_create() at + * function must be called on the mempool before it is used, or it + * can be given as a callback function to rte_mempool_create() at * pool creation. It can be extended by the user, for example, to * provide another packet size. * @@ -1300,8 +1050,8 @@ void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg, * The mempool from which mbufs originate. * @param opaque_arg * A pointer that can be used by the user to retrieve useful information - * for mbuf initialization. This pointer comes from the ``init_arg`` - * parameter of rte_mempool_create(). + * for mbuf initialization. This pointer is the opaque argument passed to + * rte_mempool_create(). */ void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg); @@ -1309,8 +1059,7 @@ 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. + * a wrapper to rte_mempool functions. * * @param name * The name of the mbuf pool. @@ -1407,6 +1156,8 @@ static inline void rte_pktmbuf_reset_headroom(struct rte_mbuf *m) * @param m * The packet mbuf to be resetted. */ +#define MBUF_INVALID_PORT UINT16_MAX + static inline void rte_pktmbuf_reset(struct rte_mbuf *m) { m->next = NULL; @@ -1415,7 +1166,7 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) m->vlan_tci = 0; m->vlan_tci_outer = 0; m->nb_segs = 1; - m->port = 0xff; + m->port = MBUF_INVALID_PORT; m->ol_flags = 0; m->packet_type = 0; @@ -1458,6 +1209,7 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp) * Array size * @return * - 0: Success + * - -ENOENT: Not enough entries in the mempool; no mbufs are retrieved. */ static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, struct rte_mbuf **mbufs, unsigned count) @@ -1477,25 +1229,25 @@ static inline int rte_pktmbuf_alloc_bulk(struct rte_mempool *pool, switch (count % 4) { case 0: while (idx != count) { - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ case 3: - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ case 2: - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ case 1: - RTE_ASSERT(rte_mbuf_refcnt_read(mbufs[idx]) == 0); - rte_mbuf_refcnt_set(mbufs[idx], 1); + MBUF_RAW_ALLOC_CHECK(mbufs[idx]); rte_pktmbuf_reset(mbufs[idx]); idx++; + /* fall-through */ } } return 0; @@ -1533,11 +1285,10 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) rte_mbuf_refcnt_update(md, 1); mi->priv_size = m->priv_size; - mi->buf_physaddr = m->buf_physaddr; + mi->buf_iova = m->buf_iova; 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; @@ -1551,6 +1302,7 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *m) mi->nb_segs = 1; mi->ol_flags = m->ol_flags | IND_ATTACHED_MBUF; mi->packet_type = m->packet_type; + mi->timestamp = m->timestamp; __rte_mbuf_sanity_check(mi, 1); __rte_mbuf_sanity_check(m, 0); @@ -1581,30 +1333,75 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m) m->priv_size = priv_size; m->buf_addr = (char *)m + mbuf_size; - m->buf_physaddr = rte_mempool_virt2phy(mp, m) + mbuf_size; + m->buf_iova = rte_mempool_virt2iova(m) + mbuf_size; m->buf_len = (uint16_t)buf_len; rte_pktmbuf_reset_headroom(m); m->data_len = 0; m->ol_flags = 0; - if (rte_mbuf_refcnt_update(md, -1) == 0) - __rte_mbuf_raw_free(md); + if (rte_mbuf_refcnt_update(md, -1) == 0) { + md->next = NULL; + md->nb_segs = 1; + rte_mbuf_refcnt_set(md, 1); + rte_mbuf_raw_free(md); + } } -static inline struct rte_mbuf* __attribute__((always_inline)) -__rte_pktmbuf_prefree_seg(struct rte_mbuf *m) +/** + * Decrease reference counter and unlink a mbuf segment + * + * This function does the same than a free, except that it does not + * return the segment to its pool. + * It decreases the reference counter, and if it reaches 0, it is + * detached from its parent for an indirect mbuf. + * + * @param m + * The mbuf to be unlinked + * @return + * - (m) if it is the last reference. It can be recycled or freed. + * - (NULL) if the mbuf still has remaining references on it. + */ +static __rte_always_inline struct rte_mbuf * +rte_pktmbuf_prefree_seg(struct rte_mbuf *m) { __rte_mbuf_sanity_check(m, 0); - if (likely(rte_mbuf_refcnt_update(m, -1) == 0)) { - /* if this is an indirect mbuf, it is detached. */ + if (likely(rte_mbuf_refcnt_read(m) == 1)) { + if (RTE_MBUF_INDIRECT(m)) rte_pktmbuf_detach(m); + + if (m->next != NULL) { + m->next = NULL; + m->nb_segs = 1; + } + + return m; + + } else if (__rte_mbuf_refcnt_update(m, -1) == 0) { + + if (RTE_MBUF_INDIRECT(m)) + rte_pktmbuf_detach(m); + + if (m->next != NULL) { + m->next = NULL; + m->nb_segs = 1; + } + rte_mbuf_refcnt_set(m, 1); + return m; } return NULL; } +/* deprecated, replaced by rte_pktmbuf_prefree_seg() */ +__rte_deprecated +static inline struct rte_mbuf * +__rte_pktmbuf_prefree_seg(struct rte_mbuf *m) +{ + return rte_pktmbuf_prefree_seg(m); +} + /** * Free a segment of a packet mbuf into its original mempool. * @@ -1614,13 +1411,12 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) * @param m * The packet mbuf segment to be freed. */ -static inline void __attribute__((always_inline)) +static __rte_always_inline void rte_pktmbuf_free_seg(struct rte_mbuf *m) { - if (likely(NULL != (m = __rte_pktmbuf_prefree_seg(m)))) { - m->next = NULL; - __rte_mbuf_raw_free(m); - } + m = rte_pktmbuf_prefree_seg(m); + if (likely(m != NULL)) + rte_mbuf_raw_free(m); } /** @@ -1667,7 +1463,7 @@ static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md, { struct rte_mbuf *mc, *mi, **prev; uint32_t pktlen; - uint8_t nseg; + uint16_t nseg; if (unlikely ((mc = rte_pktmbuf_alloc(mp)) == NULL)) return NULL; @@ -1729,7 +1525,7 @@ 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, 1); + __rte_mbuf_sanity_check(m, 0); return m->data_off; } @@ -1743,7 +1539,7 @@ 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, 1); + __rte_mbuf_sanity_check(m, 0); return (uint16_t)(m->buf_len - rte_pktmbuf_headroom(m) - m->data_len); } @@ -1798,7 +1594,7 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) #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 + * A macro that returns the IO address that points to an offset of the * start of the data in the mbuf * * @param m @@ -1806,17 +1602,24 @@ static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m) * @param o * The offset into the data to calculate address from. */ +#define rte_pktmbuf_iova_offset(m, o) \ + (rte_iova_t)((m)->buf_iova + (m)->data_off + (o)) + +/* deprecated */ #define rte_pktmbuf_mtophys_offset(m, o) \ - (phys_addr_t)((m)->buf_physaddr + (m)->data_off + (o)) + rte_pktmbuf_iova_offset(m, o) /** - * A macro that returns the physical address that points to the start of the + * A macro that returns the IO 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) +#define rte_pktmbuf_iova(m) rte_pktmbuf_iova_offset(m, 0) + +/* deprecated */ +#define rte_pktmbuf_mtophys(m) rte_pktmbuf_iova(m) /** * A macro that returns the length of the packet. @@ -1971,6 +1774,41 @@ static inline int rte_pktmbuf_is_contiguous(const struct rte_mbuf *m) return !!(m->nb_segs == 1); } +/** + * @internal used by rte_pktmbuf_read(). + */ +const void *__rte_pktmbuf_read(const struct rte_mbuf *m, uint32_t off, + uint32_t len, void *buf); + +/** + * Read len data bytes in a mbuf at specified offset. + * + * If the data is contiguous, return the pointer in the mbuf data, else + * copy the data in the buffer provided by the user and return its + * pointer. + * + * @param m + * The pointer to the mbuf. + * @param off + * The offset of the data in the mbuf. + * @param len + * The amount of bytes to read. + * @param buf + * The buffer where data is copied if it is not contiguous in mbuf + * data. Its length should be at least equal to the len parameter. + * @return + * The pointer to the data, either in the mbuf if it is contiguous, + * or in the user buffer. If mbuf is too small, NULL is returned. + */ +static inline const void *rte_pktmbuf_read(const struct rte_mbuf *m, + uint32_t off, uint32_t len, void *buf) +{ + if (likely(off + len <= rte_pktmbuf_data_len(m))) + return rte_pktmbuf_mtod_offset(m, char *, off); + else + return __rte_pktmbuf_read(m, off, len, buf); +} + /** * Chain an mbuf to another, thereby creating a segmented packet. * @@ -1985,14 +1823,14 @@ static inline int rte_pktmbuf_is_contiguous(const struct rte_mbuf *m) * * @return * - 0, on success. - * - -EOVERFLOW, if the chain is full (256 entries) + * - -EOVERFLOW, if the chain segment limit exceeded */ 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)) + if (head->nb_segs + tail->nb_segs > RTE_MBUF_MAX_NB_SEGS) return -EOVERFLOW; /* Chain 'tail' onto the old tail */ @@ -2000,7 +1838,7 @@ static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail cur_tail->next = tail; /* accumulate number of segments and total length. */ - head->nb_segs = (uint8_t)(head->nb_segs + tail->nb_segs); + head->nb_segs += tail->nb_segs; head->pkt_len += tail->pkt_len; /* pkt_len is only set in the head */ @@ -2010,7 +1848,109 @@ static inline int rte_pktmbuf_chain(struct rte_mbuf *head, struct rte_mbuf *tail } /** - * Dump an mbuf structure to the console. + * Validate general requirements for Tx offload in mbuf. + * + * This function checks correctness and completeness of Tx offload settings. + * + * @param m + * The packet mbuf to be validated. + * @return + * 0 if packet is valid + */ +static inline int +rte_validate_tx_offload(const struct rte_mbuf *m) +{ + uint64_t ol_flags = m->ol_flags; + uint64_t inner_l3_offset = m->l2_len; + + /* Does packet set any of available offloads? */ + if (!(ol_flags & PKT_TX_OFFLOAD_MASK)) + return 0; + + if (ol_flags & PKT_TX_OUTER_IP_CKSUM) + inner_l3_offset += m->outer_l2_len + m->outer_l3_len; + + /* Headers are fragmented */ + if (rte_pktmbuf_data_len(m) < inner_l3_offset + m->l3_len + m->l4_len) + return -ENOTSUP; + + /* IP checksum can be counted only for IPv4 packet */ + if ((ol_flags & PKT_TX_IP_CKSUM) && (ol_flags & PKT_TX_IPV6)) + return -EINVAL; + + /* IP type not set when required */ + if (ol_flags & (PKT_TX_L4_MASK | PKT_TX_TCP_SEG)) + if (!(ol_flags & (PKT_TX_IPV4 | PKT_TX_IPV6))) + return -EINVAL; + + /* Check requirements for TSO packet */ + if (ol_flags & PKT_TX_TCP_SEG) + if ((m->tso_segsz == 0) || + ((ol_flags & PKT_TX_IPV4) && + !(ol_flags & PKT_TX_IP_CKSUM))) + return -EINVAL; + + /* PKT_TX_OUTER_IP_CKSUM set for non outer IPv4 packet. */ + if ((ol_flags & PKT_TX_OUTER_IP_CKSUM) && + !(ol_flags & PKT_TX_OUTER_IPV4)) + return -EINVAL; + + return 0; +} + +/** + * Linearize data in mbuf. + * + * This function moves the mbuf data in the first segment if there is enough + * tailroom. The subsequent segments are unchained and freed. + * + * @param mbuf + * mbuf to linearize + * @return + * - 0, on success + * - -1, on error + */ +static inline int +rte_pktmbuf_linearize(struct rte_mbuf *mbuf) +{ + int seg_len, copy_len; + struct rte_mbuf *m; + struct rte_mbuf *m_next; + char *buffer; + + if (rte_pktmbuf_is_contiguous(mbuf)) + return 0; + + /* Extend first segment to the total packet length */ + copy_len = rte_pktmbuf_pkt_len(mbuf) - rte_pktmbuf_data_len(mbuf); + + if (unlikely(copy_len > rte_pktmbuf_tailroom(mbuf))) + return -1; + + buffer = rte_pktmbuf_mtod_offset(mbuf, char *, mbuf->data_len); + mbuf->data_len = (uint16_t)(mbuf->pkt_len); + + /* Append data from next segments to the first one */ + m = mbuf->next; + while (m != NULL) { + m_next = m->next; + + seg_len = rte_pktmbuf_data_len(m); + rte_memcpy(buffer, rte_pktmbuf_mtod(m, char *), seg_len); + buffer += seg_len; + + rte_pktmbuf_free_seg(m); + m = m_next; + } + + mbuf->next = NULL; + mbuf->nb_segs = 1; + + return 0; +} + +/** + * Dump an mbuf structure to a file. * * Dump all fields for the given packet mbuf and all its associated * segments (in the case of a chained buffer).