X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=2e5fce5188ac8611fadc00c6edb16f8c8f422e35;hb=df2e9cec228be35ef3431eb03bf475e58edc7d26;hp=f855e64d99c90a8365e4f660327aa05242c2d79f;hpb=d93677d6e20a813d11e0c6d632b6c72ddeab4604;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index f855e64d99..2e5fce5188 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 @@ -68,61 +69,127 @@ extern "C" { /* * 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 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 + * + * 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_EIP_CKSUM_BAD 0x0000 /**< External IP header checksum error. */ -#define PKT_RX_OVERSIZE 0x0000 /**< Num of desc of an RX pkt oversize. */ -#define PKT_RX_HBUF_OVERFLOW 0x0000 /**< Header buffer overflow. */ -#define PKT_RX_RECIP_ERR 0x0000 /**< Hardware processing error. */ -#define PKT_RX_MAC_ERR 0x0000 /**< MAC error. */ -#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. */ -#define PKT_TX_IPV4_CSUM 0x1000 /**< Alias of PKT_TX_IP_CKSUM. */ -#define PKT_TX_IPV4 PKT_RX_IPV4_HDR /**< IPv4 with no IP checksum offload. */ -#define PKT_TX_IPV6 PKT_RX_IPV6_HDR /**< IPv6 packet */ +#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_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. */ +/* add new RX flags here */ + +/* add new TX flags here */ -/* - * Bit 14~13 used for L4 packet type with checksum enabled. - * 00: Reserved - * 01: TCP checksum - * 10: SCTP checksum - * 11: UDP checksum +/** + * 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 << 49) + +#define PKT_TX_VXLAN_CKSUM (1ULL << 50) /**< TX checksum of VXLAN computed by NIC */ +#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_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. */ +#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. */ + +#define PKT_TX_IP_CKSUM (1ULL << 54) /**< IP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_IPV4_CSUM PKT_TX_IP_CKSUM /**< Alias of PKT_TX_IP_CKSUM. */ + +/** Tell the NIC it's an IPv4 packet. Required for L4 checksum offload or TSO. */ +#define PKT_TX_IPV4 PKT_RX_IPV4_HDR + +/** Tell the NIC it's an IPv6 packet. Required for L4 checksum offload or TSO. */ +#define PKT_TX_IPV6 PKT_RX_IPV6_HDR + +#define PKT_TX_VLAN_PKT (1ULL << 55) /**< TX packet is a 802.1q VLAN packet. */ /* Use final bit of flags to indicate a control mbuf */ -#define CTRL_MBUF_FLAG (1ULL << 63) +#define CTRL_MBUF_FLAG (1ULL << 63) /**< Mbuf contains control data */ + +/** + * 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); /** - * Bit Mask to indicate what bits required for building TX context + * 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. */ -#define PKT_TX_OFFLOAD_MASK (PKT_TX_VLAN_PKT | PKT_TX_IP_CKSUM | PKT_TX_L4_MASK) +const char *rte_get_tx_ol_flag_name(uint64_t mask); +/* 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 uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes + * with a single assignment */ /** * The generic rte_mbuf, containing a packet mbuf. */ struct rte_mbuf { + MARKER cacheline0; + void *buf_addr; /**< Virtual address of segment buffer. */ phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */ /* next 8 bytes are initialised on RX descriptor rearm */ + MARKER64 rearm_data; uint16_t buf_len; /**< Length of segment buffer. */ uint16_t data_off; @@ -147,49 +214,66 @@ struct rte_mbuf { uint64_t ol_flags; /**< Offload features. */ /* remaining bytes are set on RX when pulling packet from descriptor */ - uint16_t reserved2; /**< Unused field. Required for padding */ + 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. + */ + uint16_t packet_type; + uint16_t data_len; /**< Amount of data in segment buffer. */ uint32_t pkt_len; /**< Total pkt len: sum of all segments. */ - union { - uint16_t l2_l3_len; /**< combined l2/l3 lengths as single var */ - 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) */ + uint16_t reserved; union { uint32_t rss; /**< RSS hash result if RSS enabled */ struct { - uint16_t hash; - uint16_t id; + 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 */ uint32_t sched; /**< Hierarchical scheduler */ + uint32_t usr; /**< User defined tags. See @rte_distributor_process */ } hash; /**< hash information */ - /* fields only used in slow path or on TX */ + /* second cache line - fields only used in slow path or on TX */ + MARKER cacheline1 __rte_cache_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. */ -} __rte_cache_aligned; + /* fields to support TX offloads */ + union { + 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 */ -#define RTE_MBUF_METADATA_UINT8(mbuf, offset) \ - (((uint8_t *)&(mbuf)[1])[offset]) -#define RTE_MBUF_METADATA_UINT16(mbuf, offset) \ - (((uint16_t *)&(mbuf)[1])[offset/sizeof(uint16_t)]) -#define RTE_MBUF_METADATA_UINT32(mbuf, offset) \ - (((uint32_t *)&(mbuf)[1])[offset/sizeof(uint32_t)]) -#define RTE_MBUF_METADATA_UINT64(mbuf, offset) \ - (((uint64_t *)&(mbuf)[1])[offset/sizeof(uint64_t)]) - -#define RTE_MBUF_METADATA_UINT8_PTR(mbuf, offset) \ - (&RTE_MBUF_METADATA_UINT8(mbuf, offset)) -#define RTE_MBUF_METADATA_UINT16_PTR(mbuf, offset) \ - (&RTE_MBUF_METADATA_UINT16(mbuf, offset)) -#define RTE_MBUF_METADATA_UINT32_PTR(mbuf, offset) \ - (&RTE_MBUF_METADATA_UINT32(mbuf, offset)) -#define RTE_MBUF_METADATA_UINT64_PTR(mbuf, offset) \ - (&RTE_MBUF_METADATA_UINT64(mbuf, offset)) + /* fields for TX offloading of tunnels */ + uint64_t inner_l3_len:9; /**< inner L3 (IP) Hdr Length. */ + uint64_t inner_l2_len:7; /**< inner L2 (MAC) Hdr Length. */ + + /* uint64_t unused:8; */ + }; + }; +} __rte_cache_aligned; /** * Given the buf_addr returns the pointer to corresponding mbuf. @@ -538,12 +622,13 @@ static inline void rte_pktmbuf_reset(struct rte_mbuf *m) { m->next = NULL; m->pkt_len = 0; - m->l2_l3_len = 0; + m->tx_offload = 0; m->vlan_tci = 0; m->nb_segs = 1; m->port = 0xff; m->ol_flags = 0; + m->packet_type = 0; m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ? RTE_PKTMBUF_HEADROOM : m->buf_len; @@ -606,13 +691,14 @@ static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md) mi->data_len = md->data_len; mi->port = md->port; mi->vlan_tci = md->vlan_tci; - mi->l2_l3_len = md->l2_l3_len; + mi->tx_offload = md->tx_offload; mi->hash = md->hash; mi->next = NULL; mi->pkt_len = mi->data_len; mi->nb_segs = 1; mi->ol_flags = md->ol_flags; + mi->packet_type = md->packet_type; __rte_mbuf_sanity_check(mi, 1); __rte_mbuf_sanity_check(md, 0); @@ -688,8 +774,10 @@ __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); + } } /**