X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=6b1e50d4f64446c1a237f2910d0d33802dfd5a6e;hb=4769bc5a27ccaeb736542c4064ffc182bbd7e439;hp=68304cc2425e1083f28233d6712a90d3def0915d;hpb=a62bfb72b9ca4b0e3b1db5af125b63a16a3e507c;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 68304cc242..6b1e50d4f6 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 @@ -54,6 +55,7 @@ #include #include +#include #include #include #include @@ -68,58 +70,159 @@ 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 << 50) + +#define PKT_TX_IEEE1588_TMST (1ULL << 51) /**< TX IEEE1588 packet to timestamp. */ + +/** + * Bits 52+53 used for L4 packet type with checksum enabled: 00: Reserved, + * 01: TCP checksum, 10: SCTP checksum, 11: UDP checksum. To use hardware + * L4 checksum offload, the user needs to: + * - fill l2_len and l3_len in mbuf + * - set the flags PKT_TX_TCP_CKSUM, PKT_TX_SCTP_CKSUM or PKT_TX_UDP_CKSUM + * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 + * - calculate the pseudo header checksum and set it in the L4 header (only + * for TCP or UDP). See rte_ipv4_phdr_cksum() and rte_ipv6_phdr_cksum(). + * For SCTP, set the crc field to 0. + */ +#define PKT_TX_L4_NO_CKSUM (0ULL << 52) /**< Disable L4 cksum of TX pkt. */ +#define PKT_TX_TCP_CKSUM (1ULL << 52) /**< TCP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_SCTP_CKSUM (2ULL << 52) /**< SCTP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_UDP_CKSUM (3ULL << 52) /**< UDP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_L4_MASK (3ULL << 52) /**< Mask for L4 cksum offload request. */ + +/** + * Offload the IP checksum in the hardware. The flag PKT_TX_IPV4 should + * also be set by the application, although a PMD will only check + * PKT_TX_IP_CKSUM. + * - set the IP checksum field in the packet to 0 + * - fill the mbuf offload information: l2_len, l3_len + */ +#define PKT_TX_IP_CKSUM (1ULL << 54) + +/** + * Packet is IPv4. This flag must be set when using any offload feature + * (TSO, L3 or L4 checksum) to tell the NIC that the packet is an IPv4 + * packet. If the packet is a tunneled packet, this flag is related to + * the inner headers. + */ +#define PKT_TX_IPV4 (1ULL << 55) + +/** + * Packet is IPv6. This flag must be set when using an offload feature + * (TSO or L4 checksum) to tell the NIC that the packet is an IPv6 + * packet. If the packet is a tunneled packet, this flag is related to + * the inner headers. + */ +#define PKT_TX_IPV6 (1ULL << 56) + +#define PKT_TX_VLAN_PKT (1ULL << 57) /**< TX packet is a 802.1q VLAN packet. */ + +/** + * Offload the IP checksum of an external header in the hardware. The + * flag PKT_TX_OUTER_IPV4 should also be set by the application, alto ugh + * a PMD will only check PKT_TX_IP_CKSUM. The IP checksum field in the + * packet must be set to 0. + * - set the outer IP checksum field in the packet to 0 + * - fill the mbuf offload information: outer_l2_len, outer_l3_len */ -#define PKT_TX_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_OUTER_IP_CKSUM (1ULL << 58) + +/** + * Packet outer header is IPv4. This flag must be set when using any + * outer offload feature (L3 or L4 checksum) to tell the NIC that the + * outer header of the tunneled packet is an IPv4 packet. + */ +#define PKT_TX_OUTER_IPV4 (1ULL << 59) + +/** + * Packet outer header is IPv6. This flag must be set when using any + * outer offload feature (L4 checksum) to tell the NIC that the outer + * header of the tunneled packet is an IPv6 packet. + */ +#define PKT_TX_OUTER_IPV6 (1ULL << 60) + +#define IND_ATTACHED_MBUF (1ULL << 62) /**< Indirect attached mbuf */ /* 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 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 */ + /** * The generic rte_mbuf, containing a packet mbuf. */ @@ -129,9 +232,10 @@ struct rte_mbuf { 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. */ + + /* next 6 bytes are initialised on RX descriptor rearm */ + MARKER8 rearm_data; uint16_t data_off; /** @@ -143,11 +247,8 @@ struct rte_mbuf { * config option. */ union { -#ifdef RTE_MBUF_REFCNT rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ uint16_t refcnt; /**< Non-atomically accessed refcnt */ -#endif - uint16_t refcnt_reserved; /**< Do not use this field */ }; uint8_t nb_segs; /**< Number of segments. */ uint8_t port; /**< Input port. */ @@ -156,7 +257,14 @@ struct rte_mbuf { /* remaining bytes are set on RX when pulling packet from descriptor */ MARKER rx_descriptor_fields1; - uint16_t reserved2; /**< Unused field. Required for padding */ + + /** + * 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. */ uint16_t vlan_tci; /**< VLAN Tag Control Identifier (CPU order) */ @@ -164,12 +272,25 @@ struct rte_mbuf { 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 */ + /* sequence number - field used in distributor and reorder library */ + uint32_t seqn; + /* second cache line - fields only used in slow path or on TX */ MARKER cacheline1 __rte_cache_aligned; @@ -183,10 +304,18 @@ struct rte_mbuf { /* fields to support TX offloads */ union { - uint16_t l2_l3_len; /**< combined l2/l3 lengths as single var */ + uint64_t tx_offload; /**< combined for easy fetch */ struct { - uint16_t l3_len:9; /**< L3 (IP) Header Length. */ - uint16_t l2_len:7; /**< L2 (MAC) Header Length. */ + uint64_t l2_len:7; /**< L2 (MAC) Header Length. */ + uint64_t l3_len:9; /**< L3 (IP) Header Length. */ + uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length. */ + uint64_t tso_segsz:16; /**< TCP TSO segment size */ + + /* fields for TX offloading of tunnels */ + uint64_t outer_l3_len:9; /**< Outer L3 (IP) Hdr Length. */ + uint64_t outer_l2_len:7; /**< Outer L2 (MAC) Hdr Length. */ + + /* uint64_t unused:8; */ }; }; } __rte_cache_aligned; @@ -205,13 +334,12 @@ struct rte_mbuf { /** * Returns TRUE if given mbuf is indirect, or FALSE otherwise. */ -#define RTE_MBUF_INDIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb)) +#define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF) /** * Returns TRUE if given mbuf is direct, or FALSE otherwise. */ -#define RTE_MBUF_DIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) == (mb)) - +#define RTE_MBUF_DIRECT(mb) (!RTE_MBUF_INDIRECT(mb)) /** * Private data in case of pktmbuf pool. @@ -253,7 +381,6 @@ if (!(exp)) { \ #endif /* RTE_LIBRTE_MBUF_DEBUG */ -#ifdef RTE_MBUF_REFCNT #ifdef RTE_MBUF_REFCNT_ATOMIC /** @@ -335,15 +462,6 @@ rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value) rte_prefetch0(m); \ } while (0) -#else /* ! RTE_MBUF_REFCNT */ - -/** Mbuf prefetch */ -#define RTE_MBUF_PREFETCH_TO_FREE(m) do { } while(0) - -#define rte_mbuf_refcnt_set(m,v) do { } while(0) - -#endif /* RTE_MBUF_REFCNT */ - /** * Sanity checks on an mbuf. @@ -378,10 +496,8 @@ static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) if (rte_mempool_get(mp, &mb) < 0) return NULL; m = (struct rte_mbuf *)mb; -#ifdef RTE_MBUF_REFCNT RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); rte_mbuf_refcnt_set(m, 1); -#endif /* RTE_MBUF_REFCNT */ return (m); } @@ -396,9 +512,7 @@ static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp) static inline void __attribute__((always_inline)) __rte_mbuf_raw_free(struct rte_mbuf *m) { -#ifdef RTE_MBUF_REFCNT RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0); -#endif /* RTE_MBUF_REFCNT */ rte_mempool_put(m->pool, m); } @@ -538,12 +652,13 @@ 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; @@ -572,8 +687,6 @@ static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp) return (m); } -#ifdef RTE_MBUF_REFCNT - /** * Attach packet mbuf to another packet mbuf. * After attachment we refer the mbuf we attached as 'indirect', @@ -606,13 +719,14 @@ 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->ol_flags = md->ol_flags | IND_ATTACHED_MBUF; + mi->packet_type = md->packet_type; __rte_mbuf_sanity_check(mi, 1); __rte_mbuf_sanity_check(md, 0); @@ -642,20 +756,17 @@ static inline void rte_pktmbuf_detach(struct rte_mbuf *m) RTE_PKTMBUF_HEADROOM : m->buf_len; m->data_len = 0; -} - -#endif /* RTE_MBUF_REFCNT */ + m->ol_flags = 0; +} static inline struct rte_mbuf* __attribute__((always_inline)) __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) { __rte_mbuf_sanity_check(m, 0); -#ifdef RTE_MBUF_REFCNT if (likely (rte_mbuf_refcnt_read(m) == 1) || likely (rte_mbuf_refcnt_update(m, -1) == 0)) { - struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr); rte_mbuf_refcnt_set(m, 0); @@ -663,17 +774,15 @@ __rte_pktmbuf_prefree_seg(struct rte_mbuf *m) * - detach mbuf * - free attached mbuf segment */ - if (unlikely (md != m)) { + if (RTE_MBUF_INDIRECT(m)) { + struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr); rte_pktmbuf_detach(m); if (rte_mbuf_refcnt_update(md, -1) == 0) __rte_mbuf_raw_free(md); } -#endif return(m); -#ifdef RTE_MBUF_REFCNT } return (NULL); -#endif } /** @@ -716,8 +825,6 @@ static inline void rte_pktmbuf_free(struct rte_mbuf *m) } } -#ifdef RTE_MBUF_REFCNT - /** * Creates a "clone" of the given packet mbuf. * @@ -792,8 +899,6 @@ static inline void rte_pktmbuf_refcnt_update(struct rte_mbuf *m, int16_t v) } while ((m = m->next) != NULL); } -#endif /* RTE_MBUF_REFCNT */ - /** * Get the headroom in a packet mbuf. *