[其他] dpdk-rte_mbuf数据结构学习

//关于dpdk rte_mbuf数据结构的学习
/* define a set of marker types that can be used to refer to set points in the
 * mbuf */
/* 定义一组可用于引用 mbuf 中的设置点的标记类型*/
__extension__
typedef void  *MARKER[0];   /**< generic marker for a point in a structure */
__extension__
typedef uint8_t  MARKER8[0];  /**< generic marker with 1B alignment */
__extension__
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;/* 柔性数组，标记开头 */
void *buf_addr;       /**< Virtual address of segment buffer. */
/**
 * Physical address of segment buffer.
 * Force alignment to 8-bytes, so as to ensure we have the exact
 * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes
 * working on vector drivers easier.
 */
RTE_STD_C11
union {
rte_iova_t buf_iova;
rte_iova_t buf_physaddr; /**< deprecated */
} __rte_aligned(sizeof(rte_iova_t));
/* next 8 bytes are initialised on RX descriptor rearm */
MARKER64 rearm_data;
uint16_t data_off;
/**
 * Reference counter. Its size should at least equal to the size
 * of port field (16 bits), to support zero-copy broadcast.
 * It should only be accessed using the following functions:
 * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and
 * rte_mbuf_refcnt_set(). The functionality of these functions (atomic,
 * or non-atomic) is controlled by the CONFIG_RTE_MBUF_REFCNT_ATOMIC
 * config option.
 */
RTE_STD_C11
union {
rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */
uint16_t refcnt;        /**< Non-atomically accessed refcnt */
};
uint16_t nb_segs;     /**< Number of segments. */
/** Input port (16 bits to support more than 256 virtual ports). */
uint16_t port;
uint64_t ol_flags;    /**< Offload features. */
/* remaining bytes are set on RX when pulling packet from descriptor */
MARKER rx_descriptor_fields1;
/*
 * The packet type, which is the combination of outer/inner L2, L3, L4
 * and tunnel types. The packet_type is about data really present in the
 * mbuf. Example: if vlan stripping is enabled, a received vlan packet
 * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN because the
 * vlan is stripped from the data.
 */
RTE_STD_C11
union {
uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */
struct {
uint32_t l2_type:4; /**< (Outer) L2 type. */
uint32_t l3_type:4; /**< (Outer) L3 type. */
uint32_t l4_type:4; /**< (Outer) L4 type. */
uint32_t tun_type:4; /**< Tunnel type. */
RTE_STD_C11
union {
uint8_t inner_esp_next_proto;
/**< ESP next protocol type, valid if
 * RTE_PTYPE_TUNNEL_ESP tunnel type is set
 * on both Tx and Rx.
 */
__extension__
struct {
uint8_t inner_l2_type:4;
/**< Inner L2 type. */
uint8_t inner_l3_type:4;
/**< Inner L3 type. */
};
};
uint32_t inner_l4_type:4; /**< Inner L4 type. */
};
};
uint32_t pkt_len;     /**< Total pkt len: sum of all segments. */
uint16_t data_len;    /**< Amount of data in segment buffer. */
/** VLAN TCI (CPU order), valid if PKT_RX_VLAN_STRIPPED is set. */
uint16_t vlan_tci;
union {
uint32_t rss;   /**< RSS hash result if RSS enabled */
struct {
RTE_STD_C11
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 */
struct {
uint32_t lo;
uint32_t hi;
} sched;      /**< Hierarchical scheduler */
uint32_t usr;  /**< User defined tags. See rte_distributor_process() */
} hash;           /**< hash information */
/** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ_STRIPPED is set. */
uint16_t vlan_tci_outer;
uint16_t buf_len;     /**< Length of segment buffer. */
/** Valid if PKT_RX_TIMESTAMP is set. The unit and time reference
 * are not normalized but are always the same for a given port.
 */
uint64_t timestamp;
/* second cache line - fields only used in slow path or on TX */
MARKER cacheline1 __rte_cache_min_aligned;
RTE_STD_C11
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 */
RTE_STD_C11
union {
uint64_t tx_offload;     /**< combined for easy fetch */
__extension__
struct {
uint64_t l2_len:7;
/**< L2 (MAC) Header Length for non-tunneling pkt.
 * Outer_L4_len + ... + Inner_L2_len for tunneling pkt.
 */
uint64_t l3_len:9; /**< L3 (IP) Header Length. */
uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length. */
uint64_t tso_segsz:16; /**< TCP TSO segment size */
/* 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; */
};
};
/** Size of the application private data. In case of an indirect
 * mbuf, it stores the direct mbuf private data size. */
uint16_t priv_size;
/** Timesync flags for use with IEEE1588. */
uint16_t timesync;
/** Sequence number. See also rte_reorder_insert(). */
uint32_t seqn;
}

MARKER cacheline0;
typedef void  *MARKER[0];   /**< generic marker for a point in a structure */

void *buf_addr;       /**< Virtual address of segment buffer. */

/**
 * Physical address of segment buffer.
 * Force alignment to 8-bytes, so as to ensure we have the exact
 * same mbuf cacheline0 layout for 32-bit and 64-bit. This makes
 * working on vector drivers easier.
 */
RTE_STD_C11
union {
rte_iova_t buf_iova;
rte_iova_t buf_physaddr; /**< deprecated */
} __rte_aligned(sizeof(rte_iova_t));

/* next 8 bytes are initialised on RX descriptor rearm */
MARKER64 rearm_data;

uint16_t data_off;

/**
 * Reference counter. Its size should at least equal to the size
 * of port field (16 bits), to support zero-copy broadcast.
 * It should only be accessed using the following functions:
 * rte_mbuf_refcnt_update(), rte_mbuf_refcnt_read(), and
 * rte_mbuf_refcnt_set(). The functionality of these functions (atomic,
 * or non-atomic) is controlled by the CONFIG_RTE_MBUF_REFCNT_ATOMIC
 * config option.
 */
RTE_STD_C11
union {
rte_atomic16_t refcnt_atomic; /**< Atomically accessed refcnt */
uint16_t refcnt;        /**< Non-atomically accessed refcnt */
};

uint16_t nb_segs;     /**< Number of segments. */

/** Input port (16 bits to support more than 256 virtual ports). */
uint16_t port;

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

/* remaining bytes are set on RX when pulling packet from descriptor */
MARKER rx_descriptor_fields1;

/*
 * The packet type, which is the combination of outer/inner L2, L3, L4
 * and tunnel types. The packet_type is about data really present in the
 * mbuf. Example: if vlan stripping is enabled, a received vlan packet
 * would have RTE_PTYPE_L2_ETHER and not RTE_PTYPE_L2_VLAN because the
 * vlan is stripped from the data.
 */
 /* 数据包类型，它是外部/内部 L2、L3、L4 和隧道类型的组合。 
  * packet_type 是关于 mbuf 中真正存在的数据。 
  * 如果启用了 vlan 剥离，则接收到的 vlan 数据包将具有 RTE_PTYPE_L2_ETHER 
  * 而不是 RTE_PTYPE_L2_VLAN，因为 vlan 已从数据中剥离。 
  */
RTE_STD_C11
union {
uint32_t packet_type; /**< L2/L3/L4 and tunnel information. */
struct {
uint32_t l2_type:4; /**< (Outer) L2 type. */
uint32_t l3_type:4; /**< (Outer) L3 type. */
uint32_t l4_type:4; /**< (Outer) L4 type. */
uint32_t tun_type:4; /**< Tunnel type. */
RTE_STD_C11
union {
uint8_t inner_esp_next_proto;
/**< ESP next protocol type, valid if
 * RTE_PTYPE_TUNNEL_ESP tunnel type is set
 * on both Tx and Rx.
 */
__extension__
struct {
uint8_t inner_l2_type:4;
/**< Inner L2 type. */
uint8_t inner_l3_type:4;
/**< Inner L3 type. */
};
};
uint32_t inner_l4_type:4; /**< Inner L4 type. */
};
};

uint32_t pkt_len;     /**< Total pkt len: sum of all segments. */
uint16_t data_len;    /**< Amount of data in segment buffer. */

/** VLAN TCI (CPU order), valid if PKT_RX_VLAN_STRIPPED is set. */
uint16_t vlan_tci;

union {
uint32_t rss;   /**< RSS hash result if RSS enabled */
struct {
RTE_STD_C11
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 */
struct {
uint32_t lo;
uint32_t hi;
} sched;      /**< Hierarchical scheduler */
uint32_t usr;  /**< User defined tags. See rte_distributor_process() */
} hash;           /**< hash information */

/** Outer VLAN TCI (CPU order), valid if PKT_RX_QINQ_STRIPPED is set. */
uint16_t vlan_tci_outer;

uint16_t buf_len;     /**< Length of segment buffer. */

/** Valid if PKT_RX_TIMESTAMP is set. The unit and time reference
 * are not normalized but are always the same for a given port.
 */
uint64_t timestamp;

/* second cache line - fields only used in slow path or on TX */
MARKER cacheline1 __rte_cache_min_aligned;

RTE_STD_C11
union {
void *userdata;   /**< Can be used for external metadata */
uint64_t udata64; /**< Allow 8-byte userdata on 32-bit */
};
//#define RTE_STD_C11 __extension__

struct rte_mempool *pool; /**< Pool from which mbuf was allocated. */

struct rte_mbuf *next;  /**< Next segment of scattered packet. */

/* fields to support TX offloads */
/* 用于支持发包硬件卸载的字段 */
RTE_STD_C11
union {
uint64_t tx_offload;     /**< combined for easy fetch */
/* tx_offload 组合起来，方便取用 */
__extension__
struct {
uint64_t l2_len:7;
/**< L2 (MAC) Header Length for non-tunneling pkt.
 * Outer_L4_len + ... + Inner_L2_len for tunneling pkt.
 */
uint64_t l3_len:9; /**< L3 (IP) Header Length. */
uint64_t l4_len:8; /**< L4 (TCP/UDP) Header Length. */
uint64_t tso_segsz:16; /**< TCP TSO segment size */
/* TSO（TCP Segment Offload）是一种利用网卡的少量处理能力，
 降低CPU发送数据包负载的技术，需要网卡硬件及驱动的支持。 */
/* 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; */
};
};

/** Size of the application private data. In case of an indirect
 * mbuf, it stores the direct mbuf private data size. */
uint16_t priv_size;

/** Timesync flags for use with IEEE1588. */
/* IEEE1588 协议，又称 PTP（ precise time protocol，精确时间协议），
 * 可以达到亚微秒级别时间同步精度，于 2002 年发布 version 1，
 * 2008 年发布 version 2。 */
uint16_t timesync;

/** Sequence number. See also rte_reorder_insert(). */
uint32_t seqn;