X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_mbuf%2Frte_mbuf.h;h=ab6de676a10abf4e4b60e2e72ee6b819882d1e6b;hb=824cb29c0e7b8a2b3ed285546c3a39a8e0b3cd44;hp=71080e589aec3964ea93bcec3b6438ab26740940;hpb=08b563ffb19d8baf59dd84200f25bc85031d18a7;p=dpdk.git diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h index 71080e589a..ab6de676a1 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 @@ -62,71 +64,191 @@ 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. * 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 */ -/* - * Bit 14~13 used for L4 packet type with checksum enabled. - * 00: Reserved - * 01: TCP checksum - * 10: SCTP checksum - * 11: UDP checksum +#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 */ + +/** + * TCP segmentation offload. To enable this offload feature for a + * packet to be transmitted on hardware supporting TSO: + * - set the PKT_TX_TCP_SEG flag in mbuf->ol_flags (this flag implies + * PKT_TX_TCP_CKSUM) + * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 + * - if it's IPv4, set the PKT_TX_IP_CKSUM flag and write the IP checksum + * to 0 in the packet + * - fill the mbuf offload information: l2_len, l3_len, l4_len, tso_segsz + * - calculate the pseudo header checksum without taking ip_len in account, + * and set it in the TCP header. Refer to rte_ipv4_phdr_cksum() and + * rte_ipv6_phdr_cksum() that can be used as helpers. + */ +#define PKT_TX_TCP_SEG (1ULL << 50) + +#define PKT_TX_IEEE1588_TMST (1ULL << 51) /**< TX IEEE1588 packet to timestamp. */ + +/** + * Bits 52+53 used for L4 packet type with checksum enabled: 00: Reserved, + * 01: TCP checksum, 10: SCTP checksum, 11: UDP checksum. To use hardware + * L4 checksum offload, the user needs to: + * - fill l2_len and l3_len in mbuf + * - set the flags PKT_TX_TCP_CKSUM, PKT_TX_SCTP_CKSUM or PKT_TX_UDP_CKSUM + * - set the flag PKT_TX_IPV4 or PKT_TX_IPV6 + * - calculate the pseudo header checksum and set it in the L4 header (only + * for TCP or UDP). See rte_ipv4_phdr_cksum() and rte_ipv6_phdr_cksum(). + * For SCTP, set the crc field to 0. + */ +#define PKT_TX_L4_NO_CKSUM (0ULL << 52) /**< Disable L4 cksum of TX pkt. */ +#define PKT_TX_TCP_CKSUM (1ULL << 52) /**< TCP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_SCTP_CKSUM (2ULL << 52) /**< SCTP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_UDP_CKSUM (3ULL << 52) /**< UDP cksum of TX pkt. computed by NIC. */ +#define PKT_TX_L4_MASK (3ULL << 52) /**< Mask for L4 cksum offload request. */ + +/** + * Offload the IP checksum in the hardware. The flag PKT_TX_IPV4 should + * also be set by the application, although a PMD will only check + * PKT_TX_IP_CKSUM. + * - set the IP checksum field in the packet to 0 + * - fill the mbuf offload information: l2_len, l3_len + */ +#define PKT_TX_IP_CKSUM (1ULL << 54) + +/** + * Packet is IPv4. This flag must be set when using any offload feature + * (TSO, L3 or L4 checksum) to tell the NIC that the packet is an IPv4 + * packet. If the packet is a tunneled packet, this flag is related to + * the inner headers. + */ +#define PKT_TX_IPV4 (1ULL << 55) + +/** + * Packet is IPv6. This flag must be set when using an offload feature + * (TSO or L4 checksum) to tell the NIC that the packet is an IPv6 + * packet. If the packet is a tunneled packet, this flag is related to + * the inner headers. + */ +#define PKT_TX_IPV6 (1ULL << 56) + +#define PKT_TX_VLAN_PKT (1ULL << 57) /**< TX packet is a 802.1q VLAN packet. */ + +/** + * Offload the IP checksum of an external header in the hardware. The + * flag PKT_TX_OUTER_IPV4 should also be set by the application, alto ugh + * a PMD will only check PKT_TX_IP_CKSUM. The IP checksum field in the + * packet must be set to 0. + * - set the outer IP checksum field in the packet to 0 + * - fill the mbuf offload information: outer_l2_len, outer_l3_len + */ +#define PKT_TX_OUTER_IP_CKSUM (1ULL << 58) + +/** + * Packet outer header is IPv4. This flag must be set when using any + * outer offload feature (L3 or L4 checksum) to tell the NIC that the + * outer header of the tunneled packet is an IPv4 packet. + */ +#define PKT_TX_OUTER_IPV4 (1ULL << 59) + +/** + * Packet outer header is IPv6. This flag must be set when using any + * outer offload feature (L4 checksum) to tell the NIC that the outer + * header of the tunneled packet is an IPv6 packet. + */ +#define PKT_TX_OUTER_IPV6 (1ULL << 60) + +#define 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 */ + +/** + * Get the name of a RX offload flag + * + * @param mask + * The mask describing the flag. + * @return + * The name of this flag, or NULL if it's not a valid RX flag. + */ +const char *rte_get_rx_ol_flag_name(uint64_t mask); + +/** + * Get the name of a TX offload flag + * + * @param mask + * The mask describing the flag. Usually only one bit must be set. + * Several bits can be given if they belong to the same mask. + * Ex: PKT_TX_L4_MASK. + * @return + * The name of this flag, or NULL if it's not a valid TX flag. */ -#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. */ +const char *rte_get_tx_ol_flag_name(uint64_t mask); /** - * Bit Mask to indicate what bits required for building TX context + * 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 PKT_TX_OFFLOAD_MASK (PKT_TX_VLAN_PKT | PKT_TX_IP_CKSUM | PKT_TX_L4_MASK) +#define RTE_MBUF_DEFAULT_DATAROOM 2048 +#define RTE_MBUF_DEFAULT_BUF_SIZE \ + (RTE_MBUF_DEFAULT_DATAROOM + RTE_PKTMBUF_HEADROOM) + +/* define a set of marker types that can be used to refer to set points in the + * mbuf */ +typedef void *MARKER[0]; /**< generic marker for a point in a structure */ +typedef uint8_t MARKER8[0]; /**< generic marker with 1B alignment */ +typedef uint64_t MARKER64[0]; /**< marker that allows us to overwrite 8 bytes + * with a single assignment */ /** * The generic rte_mbuf, containing a packet mbuf. */ struct rte_mbuf { - struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */ + MARKER cacheline0; + void *buf_addr; /**< Virtual address of segment buffer. */ phys_addr_t buf_physaddr; /**< Physical address of segment buffer. */ + uint16_t buf_len; /**< Length of segment buffer. */ - /* valid for any segment */ - struct rte_mbuf *next; /**< Next segment of scattered packet. */ + /* next 6 bytes are initialised on RX descriptor rearm */ + MARKER8 rearm_data; uint16_t data_off; - uint16_t data_len; /**< Amount of data in segment buffer. */ - uint32_t pkt_len; /**< Total pkt len: sum of all segments. */ -#ifdef RTE_MBUF_REFCNT /** * 16-bit Reference counter. * It should only be accessed using the following functions: @@ -136,84 +258,129 @@ struct rte_mbuf { * config option. */ union { - rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ - uint16_t refcnt; /**< Non-atomically accessed refcnt */ + rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */ + uint16_t refcnt; /**< Non-atomically accessed refcnt */ }; -#else - uint16_t refcnt_reserved; /**< Do not use this field */ -#endif - uint16_t reserved; /**< Unused field. Required for padding */ - uint16_t ol_flags; /**< Offload features. */ + uint8_t nb_segs; /**< Number of segments. */ + uint8_t port; /**< Input port. */ - /* these fields are valid for first segment only */ - uint8_t nb_segs; /**< Number of segments. */ - uint8_t port; /**< Input port. */ + uint64_t ol_flags; /**< Offload features. */ - /* offload features, valid for first segment only */ + /* 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. + */ + 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) */ + uint16_t reserved; union { - uint16_t l2_l3_len; /**< combined l2/l3 lengths as single var */ + uint32_t rss; /**< RSS hash result if RSS enabled */ struct { - uint16_t l3_len:9; /**< L3 (IP) Header Length. */ - uint16_t l2_len:7; /**< L2 (MAC) Header Length. */ - }; + 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 */ + + uint32_t seqn; /**< Sequence number. See also rte_reorder_insert() */ + + /* 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 */ }; - uint16_t vlan_tci; /**< VLAN Tag Control Identifier (CPU order). */ + + struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */ + struct rte_mbuf *next; /**< Next segment of scattered packet. */ + + /* fields to support TX offloads */ union { - uint32_t rss; /**< RSS hash result if RSS enabled */ + uint64_t tx_offload; /**< combined for easy fetch */ struct { - uint16_t hash; - uint16_t id; - } fdir; /**< Filter identifier if FDIR enabled */ - uint32_t sched; /**< Hierarchical scheduler */ - } hash; /**< hash information */ + 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 */ - union { - uint8_t metadata[0]; - uint16_t metadata16[0]; - uint32_t metadata32[0]; - uint64_t metadata64[0]; - } __rte_cache_aligned; -} __rte_cache_aligned; + /* 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. */ -#define RTE_MBUF_METADATA_UINT8(mbuf, offset) \ - (mbuf->metadata[offset]) -#define RTE_MBUF_METADATA_UINT16(mbuf, offset) \ - (mbuf->metadata16[offset/sizeof(uint16_t)]) -#define RTE_MBUF_METADATA_UINT32(mbuf, offset) \ - (mbuf->metadata32[offset/sizeof(uint32_t)]) -#define RTE_MBUF_METADATA_UINT64(mbuf, offset) \ - (mbuf->metadata64[offset/sizeof(uint64_t)]) + /* uint64_t unused:8; */ + }; + }; -#define RTE_MBUF_METADATA_UINT8_PTR(mbuf, offset) \ - (&mbuf->metadata[offset]) -#define RTE_MBUF_METADATA_UINT16_PTR(mbuf, offset) \ - (&mbuf->metadata16[offset/sizeof(uint16_t)]) -#define RTE_MBUF_METADATA_UINT32_PTR(mbuf, offset) \ - (&mbuf->metadata32[offset/sizeof(uint32_t)]) -#define RTE_MBUF_METADATA_UINT64_PTR(mbuf, offset) \ - (&mbuf->metadata64[offset/sizeof(uint64_t)]) + /** Size of the application private data. In case of an indirect + * mbuf, it stores the direct mbuf private data size. */ + uint16_t priv_size; +} __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) +{ + struct rte_mbuf *md; + + /* mi->buf_addr and mi->priv_size correspond to buffer and + * private size of the direct mbuf */ + md = (struct rte_mbuf *)((char *)mi->buf_addr - sizeof(*mi) - + mi->priv_size); + return md; +} /** - * Given the pointer to mbuf returns an address where it's buf_addr - * should point to. + * Return the buffer address embedded in the given mbuf. + * + * @param md + * The pointer to the mbuf. + * @return + * The address of the data buffer owned by the mbuf. */ -#define RTE_MBUF_TO_BADDR(mb) (((struct rte_mbuf *)(mb)) + 1) +static inline char * +rte_mbuf_to_baddr(struct rte_mbuf *md) +{ + char *buffer_addr; + buffer_addr = (char *)md + sizeof(*md) + rte_pktmbuf_priv_size(md->pool); + return buffer_addr; +} /** * Returns TRUE if given mbuf is indirect, or FALSE otherwise. */ -#define RTE_MBUF_INDIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) != (mb)) +#define RTE_MBUF_INDIRECT(mb) ((mb)->ol_flags & IND_ATTACHED_MBUF) /** * Returns TRUE if given mbuf is direct, or FALSE otherwise. */ -#define RTE_MBUF_DIRECT(mb) (RTE_MBUF_FROM_BADDR((mb)->buf_addr) == (mb)) - +#define RTE_MBUF_DIRECT(mb) (!RTE_MBUF_INDIRECT(mb)) /** * Private data in case of pktmbuf pool. @@ -222,7 +389,8 @@ 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 @@ -255,7 +423,6 @@ if (!(exp)) { \ #endif /* RTE_LIBRTE_MBUF_DEBUG */ -#ifdef RTE_MBUF_REFCNT #ifdef RTE_MBUF_REFCNT_ATOMIC /** @@ -337,15 +504,6 @@ 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. @@ -380,10 +538,8 @@ 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); } @@ -398,9 +554,7 @@ 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); } @@ -470,6 +624,21 @@ void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg, */ #define rte_ctrlmbuf_len(m) rte_pktmbuf_data_len(m) +/** + * Tests if an mbuf is a control mbuf + * + * @param m + * The mbuf to be tested + * @return + * - True (1) if the mbuf is a control mbuf + * - False(0) otherwise + */ +static inline int +rte_is_ctrlmbuf(struct rte_mbuf *m) +{ + return (!!(m->ol_flags & CTRL_MBUF_FLAG)); +} + /* Operations on pkt mbuf */ /** @@ -513,6 +682,87 @@ 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. + * @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 + * - 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. * @@ -525,12 +775,13 @@ 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; @@ -559,54 +810,61 @@ 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', * 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->l2_l3_len = md->l2_l3_len; - 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->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; + 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. @@ -614,35 +872,41 @@ 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); + struct rte_mempool *mp = m->pool; + uint32_t mbuf_size, buf_len, priv_size; - m->buf_addr = buf; - m->buf_len = (uint16_t)buf_len; - - 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; } -#endif /* RTE_MBUF_REFCNT */ - - 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 + /* + * Check to see if this is the last reference to the mbuf. + * Note: the double check here is deliberate. If the ref_cnt is "atomic" + * the call to "refcnt_update" is a very expensive operation, so we + * don't want to call it in the case where we know we are the holder + * of the last reference to this mbuf i.e. ref_cnt == 1. + * If however, ref_cnt != 1, it's still possible that we may still be + * the final decrementer of the count, so we need to check that + * result also, to make sure the mbuf is freed properly. + */ 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); @@ -650,17 +914,15 @@ __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_indirect(m); rte_pktmbuf_detach(m); if (rte_mbuf_refcnt_update(md, -1) == 0) __rte_mbuf_raw_free(md); } -#endif return(m); -#ifdef RTE_MBUF_REFCNT } return (NULL); -#endif } /** @@ -675,8 +937,10 @@ __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); + } } /** @@ -701,8 +965,6 @@ static inline void rte_pktmbuf_free(struct rte_mbuf *m) } } -#ifdef RTE_MBUF_REFCNT - /** * Creates a "clone" of the given packet mbuf. * @@ -777,8 +1039,6 @@ 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. *