[dpdk.git] / lib / librte_mbuf / rte_mbuf.h

/*-
 *   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
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#ifndef _RTE_MBUF_H_
#define _RTE_MBUF_H_

/**
 * @file
 * RTE Mbuf
 *
 * The mbuf library provides the ability to create and destroy buffers
 * that may be used by the RTE application to store message
 * 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
 * used to carry network packets.
 *
 * To understand the concepts of packet buffers or mbufs, you
 * should read "TCP/IP Illustrated, Volume 2: The Implementation,
 * Addison-Wesley, 1995, ISBN 0-201-63354-X from Richard Stevens"
 * http://www.kohala.com/start/tcpipiv2.html
 */

#include <stdint.h>
#include <rte_mempool.h>
#include <rte_memory.h>
#include <rte_atomic.h>
#include <rte_prefetch.h>
#include <rte_branch_prediction.h>

#ifdef __cplusplus
extern "C" {
#endif

/* 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      (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.
 */
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.
 */
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. */

        /* next 6 bytes are initialised on RX descriptor rearm */
        MARKER8 rearm_data;
        uint16_t data_off;

        /**
         * 16-bit Reference counter.
         * 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,
         * or non-atomic) is controlled by the CONFIG_RTE_MBUF_REFCNT_ATOMIC
         * config option.
         */
        union {
                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. */

        uint64_t ol_flags;        /**< Offload features. */

        /* 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 {
                uint32_t rss;     /**< RSS hash result if RSS enabled */
                struct {
                        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 */
        };

        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 {
                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 */

                        /* 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;

/**
 * Given the buf_addr returns the pointer to corresponding mbuf.
 */
#define RTE_MBUF_FROM_BADDR(ba)     (((struct rte_mbuf *)(ba)) - 1)

/**
 * Given the pointer to mbuf returns an address where it's  buf_addr
 * should point to.
 */
#define RTE_MBUF_TO_BADDR(mb)       (((struct rte_mbuf *)(mb)) + 1)

/**
 * Returns TRUE if given mbuf is indirect, or FALSE otherwise.
 */
#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_INDIRECT(mb))

/**
 * Private data in case of pktmbuf pool.
 *
 * A structure that contains some pktmbuf_pool-specific data that are
 * 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_priv_size;      /**< Size of private area in each mbuf. */
};

#ifdef RTE_LIBRTE_MBUF_DEBUG

/**  check mbuf type in debug mode */
#define __rte_mbuf_sanity_check(m, is_h) rte_mbuf_sanity_check(m, is_h)

/**  check mbuf type in debug mode if mbuf pointer is not null */
#define __rte_mbuf_sanity_check_raw(m, is_h)    do {       \
        if ((m) != NULL)                                   \
                rte_mbuf_sanity_check(m, is_h);          \
} while (0)

/**  MBUF asserts in debug mode */
#define RTE_MBUF_ASSERT(exp)                                         \
if (!(exp)) {                                                        \
        rte_panic("line%d\tassert \"" #exp "\" failed\n", __LINE__); \
}

#else /*  RTE_LIBRTE_MBUF_DEBUG */

/**  check mbuf type in debug mode */
#define __rte_mbuf_sanity_check(m, is_h) do { } while (0)

/**  check mbuf type in debug mode if mbuf pointer is not null */
#define __rte_mbuf_sanity_check_raw(m, is_h) do { } while (0)

/**  MBUF asserts in debug mode */
#define RTE_MBUF_ASSERT(exp)                do { } while (0)

#endif /*  RTE_LIBRTE_MBUF_DEBUG */

#ifdef RTE_MBUF_REFCNT_ATOMIC

/**
 * Adds given value to an mbuf's refcnt and returns its new value.
 * @param m
 *   Mbuf to update
 * @param value
 *   Value to add/subtract
 * @return
 *   Updated value
 */
static inline uint16_t
rte_mbuf_refcnt_update(struct rte_mbuf *m, int16_t value)
{
        return (uint16_t)(rte_atomic16_add_return(&m->refcnt_atomic, value));
}

/**
 * Reads the value of an mbuf's refcnt.
 * @param m
 *   Mbuf to read
 * @return
 *   Reference count number.
 */
static inline uint16_t
rte_mbuf_refcnt_read(const struct rte_mbuf *m)
{
        return (uint16_t)(rte_atomic16_read(&m->refcnt_atomic));
}

/**
 * Sets an mbuf's refcnt to a defined value.
 * @param m
 *   Mbuf to update
 * @param new_value
 *   Value set
 */
static inline void
rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value)
{
        rte_atomic16_set(&m->refcnt_atomic, new_value);
}

#else /* ! RTE_MBUF_REFCNT_ATOMIC */

/**
 * 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;
}

/**
 * Reads the value of an mbuf's refcnt.
 */
static inline uint16_t
rte_mbuf_refcnt_read(const struct rte_mbuf *m)
{
        return m->refcnt;
}

/**
 * Sets an mbuf's refcnt to the defined value.
 */
static inline void
rte_mbuf_refcnt_set(struct rte_mbuf *m, uint16_t new_value)
{
        m->refcnt = new_value;
}

#endif /* RTE_MBUF_REFCNT_ATOMIC */

/** Mbuf prefetch */
#define RTE_MBUF_PREFETCH_TO_FREE(m) do {       \
        if ((m) != NULL)                        \
                rte_prefetch0(m);               \
} while (0)


/**
 * Sanity checks on an mbuf.
 *
 * Check the consistency of the given mbuf. The function will cause a
 * panic if corruption is detected.
 *
 * @param m
 *   The mbuf to be checked.
 * @param is_header
 *   True if the mbuf is a packet header, false if it is a sub-segment
 *   of a packet (in this case, some fields like nb_segs are not checked)
 */
void
rte_mbuf_sanity_check(const struct rte_mbuf *m, int is_header);

/**
 * @internal Allocate a new mbuf from mempool *mp*.
 * The use of that function is reserved for RTE internal needs.
 * Please use rte_pktmbuf_alloc().
 *
 * @param mp
 *   The mempool from which mbuf is allocated.
 * @return
 *   - The pointer to the new mbuf on success.
 *   - NULL if allocation failed.
 */
static inline struct rte_mbuf *__rte_mbuf_raw_alloc(struct rte_mempool *mp)
{
        struct rte_mbuf *m;
        void *mb = NULL;
        if (rte_mempool_get(mp, &mb) < 0)
                return NULL;
        m = (struct rte_mbuf *)mb;
        RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0);
        rte_mbuf_refcnt_set(m, 1);
        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().
 *
 * @param m
 *   The mbuf to be freed.
 */
static inline void __attribute__((always_inline))
__rte_mbuf_raw_free(struct rte_mbuf *m)
{
        RTE_MBUF_ASSERT(rte_mbuf_refcnt_read(m) == 0);
        rte_mempool_put(m->pool, m);
}

/* Operations on ctrl mbuf */

/**
 * The control mbuf constructor.
 *
 * 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.
 *
 * @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().
 * @param m
 *   The mbuf to initialize.
 * @param i
 *   The index of the mbuf in the pool table.
 */
void rte_ctrlmbuf_init(struct rte_mempool *mp, void *opaque_arg,
                void *m, unsigned i);

/**
 * Allocate a new mbuf (type is ctrl) from mempool *mp*.
 *
 * This new mbuf is initialized with data pointing to the beginning of
 * buffer, and with a length of zero.
 *
 * @param mp
 *   The mempool from which the mbuf is allocated.
 * @return
 *   - The pointer to the new mbuf on success.
 *   - NULL if allocation failed.
 */
#define rte_ctrlmbuf_alloc(mp) rte_pktmbuf_alloc(mp)

/**
 * Free a control mbuf back into its original mempool.
 *
 * @param m
 *   The control mbuf to be freed.
 */
#define rte_ctrlmbuf_free(m) rte_pktmbuf_free(m)

/**
 * A macro that returns the pointer to the carried data.
 *
 * The value that can be read or assigned.
 *
 * @param m
 *   The control mbuf.
 */
#define rte_ctrlmbuf_data(m) ((char *)((m)->buf_addr) + (m)->data_off)

/**
 * A macro that returns the length of the carried data.
 *
 * The value that can be read or assigned.
 *
 * @param m
 *   The control mbuf.
 */
#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 */

/**
 * The packet mbuf constructor.
 *
 * 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.
 *
 * @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().
 * @param m
 *   The mbuf to initialize.
 * @param i
 *   The index of the mbuf in the pool table.
 */
void rte_pktmbuf_init(struct rte_mempool *mp, void *opaque_arg,
                      void *m, unsigned i);


/**
 * A  packet mbuf pool constructor.
 *
 * 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
 * pool creation. It can be extended by the user, for example, to
 * provide another packet size.
 *
 * @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().
 */
void rte_pktmbuf_pool_init(struct rte_mempool *mp, void *opaque_arg);

/**
 * 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.
 *
 * The given mbuf must have only one segment.
 *
 * @param m
 *   The packet mbuf to be resetted.
 */
static inline void rte_pktmbuf_reset(struct rte_mbuf *m)
{
        m->next = NULL;
        m->pkt_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;

        m->data_len = 0;
        __rte_mbuf_sanity_check(m, 1);
}

/**
 * Allocate a new mbuf from a mempool.
 *
 * This new mbuf contains one segment, which has a length of 0. The pointer
 * to data is initialized to have some bytes of headroom in the buffer
 * (if buffer size allows).
 *
 * @param mp
 *   The mempool from which the mbuf is allocated.
 * @return
 *   - The pointer to the new mbuf on success.
 *   - NULL if allocation failed.
 */
static inline struct rte_mbuf *rte_pktmbuf_alloc(struct rte_mempool *mp)
{
        struct rte_mbuf *m;
        if ((m = __rte_mbuf_raw_alloc(mp)) != NULL)
                rte_pktmbuf_reset(m);
        return (m);
}

/**
 * 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.
 */

static inline void rte_pktmbuf_attach(struct rte_mbuf *mi, struct rte_mbuf *md)
{
        RTE_MBUF_ASSERT(RTE_MBUF_DIRECT(md) &&
            RTE_MBUF_DIRECT(mi) &&
            rte_mbuf_refcnt_read(mi) == 1);

        rte_mbuf_refcnt_update(md, 1);
        mi->buf_physaddr = md->buf_physaddr;
        mi->buf_addr = md->buf_addr;
        mi->buf_len = md->buf_len;

        mi->next = md->next;
        mi->data_off = md->data_off;
        mi->data_len = md->data_len;
        mi->port = md->port;
        mi->vlan_tci = md->vlan_tci;
        mi->tx_offload = md->tx_offload;
        mi->hash = md->hash;

        mi->next = NULL;
        mi->pkt_len = mi->data_len;
        mi->nb_segs = 1;
        mi->ol_flags = md->ol_flags | IND_ATTACHED_MBUF;
        mi->packet_type = md->packet_type;

        __rte_mbuf_sanity_check(mi, 1);
        __rte_mbuf_sanity_check(md, 0);
}

/**
 * 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.
 *
 * @param m
 *   The indirect attached packet mbuf.
 */

static inline void rte_pktmbuf_detach(struct rte_mbuf *m)
{
        const struct rte_mempool *mp = m->pool;
        void *buf = RTE_MBUF_TO_BADDR(m);
        uint32_t buf_len = mp->elt_size - sizeof(*m);
        m->buf_physaddr = rte_mempool_virt2phy(mp, m) + sizeof (*m);

        m->buf_addr = buf;
        m->buf_len = (uint16_t)buf_len;

        m->data_off = (RTE_PKTMBUF_HEADROOM <= m->buf_len) ?
                        RTE_PKTMBUF_HEADROOM : m->buf_len;

        m->data_len = 0;

        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);

        /*
         * 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)) {

                rte_mbuf_refcnt_set(m, 0);

                /* if this is an indirect mbuf, then
                 *  - detach mbuf
                 *  - free attached mbuf segment
                 */
                if (RTE_MBUF_INDIRECT(m)) {
                        struct rte_mbuf *md = RTE_MBUF_FROM_BADDR(m->buf_addr);
                        rte_pktmbuf_detach(m);
                        if (rte_mbuf_refcnt_update(md, -1) == 0)
                                __rte_mbuf_raw_free(md);
                }
                return(m);
        }
        return (NULL);
}

/**
 * Free a segment of a packet mbuf into its original mempool.
 *
 * Free an mbuf, without parsing other segments in case of chained
 * buffers.
 *
 * @param m
 *   The packet mbuf segment to be freed.
 */
static inline void __attribute__((always_inline))
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);
        }
}

/**
 * Free a packet mbuf back into its original mempool.
 *
 * Free an mbuf, and all its segments in case of chained buffers. Each
 * segment is added back into its original mempool.
 *
 * @param m
 *   The packet mbuf to be freed.
 */
static inline void rte_pktmbuf_free(struct rte_mbuf *m)
{
        struct rte_mbuf *m_next;

        __rte_mbuf_sanity_check(m, 1);

        while (m != NULL) {
                m_next = m->next;
                rte_pktmbuf_free_seg(m);
                m = m_next;
        }
}

/**
 * Creates a "clone" of the given packet mbuf.
 *
 * Walks through all segments of the given packet mbuf, and for each of them:
 *  - Creates a new packet mbuf from the given pool.
 *  - Attaches newly created mbuf to the segment.
 * Then updates pkt_len and nb_segs of the "clone" packet mbuf to match values
 * from the original packet mbuf.
 *
 * @param md
 *   The packet mbuf to be cloned.
 * @param mp
 *   The mempool from which the "clone" mbufs are allocated.
 * @return
 *   - The pointer to the new "clone" mbuf on success.
 *   - NULL if allocation fails.
 */
static inline struct rte_mbuf *rte_pktmbuf_clone(struct rte_mbuf *md,
                struct rte_mempool *mp)
{
        struct rte_mbuf *mc, *mi, **prev;
        uint32_t pktlen;
        uint8_t nseg;

        if (unlikely ((mc = rte_pktmbuf_alloc(mp)) == NULL))
                return (NULL);

        mi = mc;
        prev = &mi->next;
        pktlen = md->pkt_len;
        nseg = 0;

        do {
                nseg++;
                rte_pktmbuf_attach(mi, md);
                *prev = mi;
                prev = &mi->next;
        } while ((md = md->next) != NULL &&
            (mi = rte_pktmbuf_alloc(mp)) != NULL);

        *prev = NULL;
        mc->nb_segs = nseg;
        mc->pkt_len = pktlen;

        /* Allocation of new indirect segment failed */
        if (unlikely (mi == NULL)) {
                rte_pktmbuf_free(mc);
                return (NULL);
        }

        __rte_mbuf_sanity_check(mc, 1);
        return (mc);
}

/**
 * Adds given value to the refcnt of all packet mbuf segments.
 *
 * Walks through all segments of given packet mbuf and for each of them
 * invokes rte_mbuf_refcnt_update().
 *
 * @param m
 *   The packet mbuf whose refcnt to be updated.
 * @param v
 *   The value to add to the mbuf's segments refcnt.
 */
static inline void rte_pktmbuf_refcnt_update(struct rte_mbuf *m, int16_t v)
{
        __rte_mbuf_sanity_check(m, 1);

        do {
                rte_mbuf_refcnt_update(m, v);
        } while ((m = m->next) != NULL);
}

/**
 * Get the headroom in a packet mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   The length of the headroom.
 */
static inline uint16_t rte_pktmbuf_headroom(const struct rte_mbuf *m)
{
        __rte_mbuf_sanity_check(m, 1);
        return m->data_off;
}

/**
 * Get the tailroom of a packet mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   The length of the tailroom.
 */
static inline uint16_t rte_pktmbuf_tailroom(const struct rte_mbuf *m)
{
        __rte_mbuf_sanity_check(m, 1);
        return (uint16_t)(m->buf_len - rte_pktmbuf_headroom(m) -
                          m->data_len);
}

/**
 * Get the last segment of the packet.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   The last segment of the given mbuf.
 */
static inline struct rte_mbuf *rte_pktmbuf_lastseg(struct rte_mbuf *m)
{
        struct rte_mbuf *m2 = (struct rte_mbuf *)m;

        __rte_mbuf_sanity_check(m, 1);
        while (m2->next != NULL)
                m2 = m2->next;
        return m2;
}

/**
 * A macro that points to the start of the data in the mbuf.
 *
 * The returned pointer is cast to type t. Before using this
 * function, the user must ensure that m_headlen(m) is large enough to
 * read its data.
 *
 * @param m
 *   The packet mbuf.
 * @param t
 *   The type to cast the result into.
 */
#define rte_pktmbuf_mtod(m, t) ((t)((char *)(m)->buf_addr + (m)->data_off))

/**
 * A macro that returns the length of the packet.
 *
 * The value can be read or assigned.
 *
 * @param m
 *   The packet mbuf.
 */
#define rte_pktmbuf_pkt_len(m) ((m)->pkt_len)

/**
 * A macro that returns the length of the segment.
 *
 * The value can be read or assigned.
 *
 * @param m
 *   The packet mbuf.
 */
#define rte_pktmbuf_data_len(m) ((m)->data_len)

/**
 * Prepend len bytes to an mbuf data area.
 *
 * Returns a pointer to the new
 * data start address. If there is not enough headroom in the first
 * segment, the function will return NULL, without modifying the mbuf.
 *
 * @param m
 *   The pkt mbuf.
 * @param len
 *   The amount of data to prepend (in bytes).
 * @return
 *   A pointer to the start of the newly prepended data, or
 *   NULL if there is not enough headroom space in the first segment
 */
static inline char *rte_pktmbuf_prepend(struct rte_mbuf *m,
                                        uint16_t len)
{
        __rte_mbuf_sanity_check(m, 1);

        if (unlikely(len > rte_pktmbuf_headroom(m)))
                return NULL;

        m->data_off -= len;
        m->data_len = (uint16_t)(m->data_len + len);
        m->pkt_len  = (m->pkt_len + len);

        return (char *)m->buf_addr + m->data_off;
}

/**
 * Append len bytes to an mbuf.
 *
 * Append len bytes to an mbuf and return a pointer to the start address
 * of the added data. If there is not enough tailroom in the last
 * segment, the function will return NULL, without modifying the mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @param len
 *   The amount of data to append (in bytes).
 * @return
 *   A pointer to the start of the newly appended data, or
 *   NULL if there is not enough tailroom space in the last segment
 */
static inline char *rte_pktmbuf_append(struct rte_mbuf *m, uint16_t len)
{
        void *tail;
        struct rte_mbuf *m_last;

        __rte_mbuf_sanity_check(m, 1);

        m_last = rte_pktmbuf_lastseg(m);
        if (unlikely(len > rte_pktmbuf_tailroom(m_last)))
                return NULL;

        tail = (char *)m_last->buf_addr + m_last->data_off + m_last->data_len;
        m_last->data_len = (uint16_t)(m_last->data_len + len);
        m->pkt_len  = (m->pkt_len + len);
        return (char*) tail;
}

/**
 * Remove len bytes at the beginning of an mbuf.
 *
 * Returns a pointer to the start address of the new data area. If the
 * length is greater than the length of the first segment, then the
 * function will fail and return NULL, without modifying the mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @param len
 *   The amount of data to remove (in bytes).
 * @return
 *   A pointer to the new start of the data.
 */
static inline char *rte_pktmbuf_adj(struct rte_mbuf *m, uint16_t len)
{
        __rte_mbuf_sanity_check(m, 1);

        if (unlikely(len > m->data_len))
                return NULL;

        m->data_len = (uint16_t)(m->data_len - len);
        m->data_off += len;
        m->pkt_len  = (m->pkt_len - len);
        return (char *)m->buf_addr + m->data_off;
}

/**
 * Remove len bytes of data at the end of the mbuf.
 *
 * If the length is greater than the length of the last segment, the
 * function will fail and return -1 without modifying the mbuf.
 *
 * @param m
 *   The packet mbuf.
 * @param len
 *   The amount of data to remove (in bytes).
 * @return
 *   - 0: On success.
 *   - -1: On error.
 */
static inline int rte_pktmbuf_trim(struct rte_mbuf *m, uint16_t len)
{
        struct rte_mbuf *m_last;

        __rte_mbuf_sanity_check(m, 1);

        m_last = rte_pktmbuf_lastseg(m);
        if (unlikely(len > m_last->data_len))
                return -1;

        m_last->data_len = (uint16_t)(m_last->data_len - len);
        m->pkt_len  = (m->pkt_len - len);
        return 0;
}

/**
 * Test if mbuf data is contiguous.
 *
 * @param m
 *   The packet mbuf.
 * @return
 *   - 1, if all data is contiguous (one segment).
 *   - 0, if there is several segments.
 */
static inline int rte_pktmbuf_is_contiguous(const struct rte_mbuf *m)
{
        __rte_mbuf_sanity_check(m, 1);
        return !!(m->nb_segs == 1);
}

/**
 * Dump an mbuf structure to the console.
 *
 * Dump all fields for the given packet mbuf and all its associated
 * segments (in the case of a chained buffer).
 *
 * @param f
 *   A pointer to a file for output
 * @param m
 *   The packet mbuf.
 * @param dump_len
 *   If dump_len != 0, also dump the "dump_len" first data bytes of
 *   the packet.
 */
void rte_pktmbuf_dump(FILE *f, const struct rte_mbuf *m, unsigned dump_len);

#ifdef __cplusplus
}
#endif

#endif /* _RTE_MBUF_H_ */