Re: [dpdk-dev] [PATCH v8 03/18] mbuf: add definitions of unified packet types

[Olivier MATZ <olivier.matz@6wind.com>]

Hi Helin,

This is greatly documented, thanks!
Please find a small comment below.

On 06/23/2015 03:50 AM, Helin Zhang wrote:
> As there are only 6 bit flags in ol_flags for indicating packet
> types, which is not enough to describe all the possible packet
> types hardware can recognize. For example, i40e hardware can
> recognize more than 150 packet types. Unified packet type is
> composed of L2 type, L3 type, L4 type, tunnel type, inner L2 type,
> inner L3 type and inner L4 type fields, and can be stored in
> 'struct rte_mbuf' of 32 bits field 'packet_type'.
> To avoid breaking ABI compatibility, all the changes would be
> enabled by RTE_NEXT_ABI, which is disabled by default.
>
> [...]
> diff --git a/lib/librte_mbuf/rte_mbuf.h b/lib/librte_mbuf/rte_mbuf.h
> index 0315561..0ee0c55 100644
> --- a/lib/librte_mbuf/rte_mbuf.h
> +++ b/lib/librte_mbuf/rte_mbuf.h
> @@ -201,6 +201,493 @@ extern "C" {
>   /* Use final bit of flags to indicate a control mbuf */
>   #define CTRL_MBUF_FLAG       (1ULL << 63) /**< Mbuf contains control data */
>
> +#ifdef RTE_NEXT_ABI
> +/*
> + * 32 bits are divided into several fields to mark packet types. Note that
> + * each field is indexical.
> + * - Bit 3:0 is for L2 types.
> + * - Bit 7:4 is for L3 or outer L3 (for tunneling case) types.
> + * - Bit 11:8 is for L4 or outer L4 (for tunneling case) types.
> + * - Bit 15:12 is for tunnel types.
> + * - Bit 19:16 is for inner L2 types.
> + * - Bit 23:20 is for inner L3 types.
> + * - Bit 27:24 is for inner L4 types.
> + * - Bit 31:28 is reserved.
> + *
> + * To be compatible with Vector PMD, RTE_PTYPE_L3_IPV4, RTE_PTYPE_L3_IPV4_EXT,
> + * RTE_PTYPE_L3_IPV6, RTE_PTYPE_L3_IPV6_EXT, RTE_PTYPE_L4_TCP, RTE_PTYPE_L4_UDP
> + * and RTE_PTYPE_L4_SCTP should be kept as below in a contiguous 7 bits.
> + *
> + * Note that L3 types values are selected for checking IPV4/IPV6 header from
> + * performance point of view. Reading annotations of RTE_ETH_IS_IPV4_HDR and
> + * RTE_ETH_IS_IPV6_HDR is needed for any future changes of L3 type values.
> + *
> + * Note that the packet types of the same packet recognized by different
> + * hardware may be different, as different hardware may have different
> + * capability of packet type recognition.
> + *
> + * examples:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=0x29
> + * | 'version'=6, 'next header'=0x3A
> + * | 'ICMPv6 header'>
> + * will be recognized on i40e hardware as packet type combination of,
> + * RTE_PTYPE_L2_MAC |
> + * RTE_PTYPE_L3_IPV4_EXT_UNKNOWN |
> + * RTE_PTYPE_TUNNEL_IP |
> + * RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
> + * RTE_PTYPE_INNER_L4_ICMP.
> + *
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=0x2F
> + * | 'GRE header'
> + * | 'version'=6, 'next header'=0x11
> + * | 'UDP header'>
> + * will be recognized on i40e hardware as packet type combination of,
> + * RTE_PTYPE_L2_MAC |
> + * RTE_PTYPE_L3_IPV6_EXT_UNKNOWN |
> + * RTE_PTYPE_TUNNEL_GRENAT |
> + * RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN |
> + * RTE_PTYPE_INNER_L4_UDP.
> + */
> +#define RTE_PTYPE_UNKNOWN                   0x00000000
> +/**
> + * MAC (Media Access Control) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * Packet format:
> + * <'ether type'=[0x0800|0x86DD|others]>
> + */
> +#define RTE_PTYPE_L2_MAC                    0x00000001

I'm wondering if RTE_PTYPE_L2_ETHER is not a better name?


> +/**
> + * MAC (Media Access Control) packet type for time sync.
> + *
> + * Packet format:
> + * <'ether type'=0x88F7>
> + */
> +#define RTE_PTYPE_L2_MAC_TIMESYNC           0x00000002
> +/**
> + * ARP (Address Resolution Protocol) packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x0806>
> + */
> +#define RTE_PTYPE_L2_ARP                    0x00000003
> +/**
> + * LLDP (Link Layer Discovery Protocol) packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x88CC>
> + */
> +#define RTE_PTYPE_L2_LLDP                   0x00000004

Maybe ETHER should appear in these names too, what do you think?




> +/**
> + * Mask of layer 2 packet types.
> + * It is used for outer packet for tunneling cases.
> + */
> +#define RTE_PTYPE_L2_MASK                   0x0000000f
> +/**
> + * IP (Internet Protocol) version 4 packet type.
> + * It is used for outer packet for tunneling cases, and does not contain any
> + * header option.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'ihl'=5>
> + */
> +#define RTE_PTYPE_L3_IPV4                   0x00000010
> +/**
> + * IP (Internet Protocol) version 4 packet type.
> + * It is used for outer packet for tunneling cases, and contains header
> + * options.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'ihl'=[6-15], 'options'>
> + */
> +#define RTE_PTYPE_L3_IPV4_EXT               0x00000030
> +/**
> + * IP (Internet Protocol) version 6 packet type.
> + * It is used for outer packet for tunneling cases, and does not contain any
> + * extension header.
> + *
> + * Packet format:
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=0x3B>
> + */
> +#define RTE_PTYPE_L3_IPV6                   0x00000040
> +/**
> + * IP (Internet Protocol) version 4 packet type.
> + * It is used for outer packet for tunneling cases, and may or maynot contain
> + * header options.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'ihl'=[5-15], <'options'>>
> + */
> +#define RTE_PTYPE_L3_IPV4_EXT_UNKNOWN       0x00000090
> +/**
> + * IP (Internet Protocol) version 6 packet type.
> + * It is used for outer packet for tunneling cases, and contains extension
> + * headers.
> + *
> + * Packet format:
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=[0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87],
> + *   'extension headers'>
> + */
> +#define RTE_PTYPE_L3_IPV6_EXT               0x000000c0
> +/**
> + * IP (Internet Protocol) version 6 packet type.
> + * It is used for outer packet for tunneling cases, and may or maynot contain
> + * extension headers.
> + *
> + * Packet format:
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=[0x3B|0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87],
> + *   <'extension headers'>>
> + */
> +#define RTE_PTYPE_L3_IPV6_EXT_UNKNOWN       0x000000e0
> +/**
> + * Mask of layer 3 packet types.
> + * It is used for outer packet for tunneling cases.
> + */
> +#define RTE_PTYPE_L3_MASK                   0x000000f0
> +/**
> + * TCP (Transmission Control Protocol) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=6, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=6>
> + */
> +#define RTE_PTYPE_L4_TCP                    0x00000100
> +/**
> + * UDP (User Datagram Protocol) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=17, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=17>
> + */
> +#define RTE_PTYPE_L4_UDP                    0x00000200
> +/**
> + * Fragmented IP (Internet Protocol) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * It refers to those packets of any IP types, which can be recognized as
> + * fragmented. A fragmented packet cannot be recognized as any other L4 types
> + * (RTE_PTYPE_L4_TCP, RTE_PTYPE_L4_UDP, RTE_PTYPE_L4_SCTP, RTE_PTYPE_L4_ICMP,
> + * RTE_PTYPE_L4_NONFRAG).
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'MF'=1>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=44>
> + */
> +#define RTE_PTYPE_L4_FRAG                   0x00000300
> +/**
> + * SCTP (Stream Control Transmission Protocol) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=132, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=132>
> + */
> +#define RTE_PTYPE_L4_SCTP                   0x00000400
> +/**
> + * ICMP (Internet Control Message Protocol) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=1, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=1>
> + */
> +#define RTE_PTYPE_L4_ICMP                   0x00000500
> +/**
> + * Non-fragmented IP (Internet Protocol) packet type.
> + * It is used for outer packet for tunneling cases.
> + *
> + * It refers to those packets of any IP types, while cannot be recognized as
> + * any of above L4 types (RTE_PTYPE_L4_TCP, RTE_PTYPE_L4_UDP,
> + * RTE_PTYPE_L4_FRAG, RTE_PTYPE_L4_SCTP, RTE_PTYPE_L4_ICMP).
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'!=[6|17|132|1], 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'!=[6|17|44|132|1]>
> + */
> +#define RTE_PTYPE_L4_NONFRAG                0x00000600
> +/**
> + * Mask of layer 4 packet types.
> + * It is used for outer packet for tunneling cases.
> + */
> +#define RTE_PTYPE_L4_MASK                   0x00000f00
> +/**
> + * IP (Internet Protocol) in IP (Internet Protocol) tunneling packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=[4|41]>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=[4|41]>
> + */
> +#define RTE_PTYPE_TUNNEL_IP                 0x00001000
> +/**
> + * GRE (Generic Routing Encapsulation) tunneling packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=47>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=47>
> + */
> +#define RTE_PTYPE_TUNNEL_GRE                0x00002000
> +/**
> + * VXLAN (Virtual eXtensible Local Area Network) tunneling packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=17
> + * | 'destination port'=4798>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=17
> + * | 'destination port'=4798>
> + */
> +#define RTE_PTYPE_TUNNEL_VXLAN              0x00003000
> +/**
> + * NVGRE (Network Virtualization using Generic Routing Encapsulation) tunneling
> + * packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=47
> + * | 'protocol type'=0x6558>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=47
> + * | 'protocol type'=0x6558'>
> + */
> +#define RTE_PTYPE_TUNNEL_NVGRE              0x00004000
> +/**
> + * GENEVE (Generic Network Virtualization Encapsulation) tunneling packet type.
> + *
> + * Packet format:
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=17
> + * | 'destination port'=6081>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=17
> + * | 'destination port'=6081>
> + */
> +#define RTE_PTYPE_TUNNEL_GENEVE             0x00005000
> +/**
> + * Tunneling packet type of Teredo, VXLAN (Virtual eXtensible Local Area
> + * Network) or GRE (Generic Routing Encapsulation) could be recognized as this
> + * packet type, if they can not be recognized independently as of hardware
> + * capability.
> + */
> +#define RTE_PTYPE_TUNNEL_GRENAT             0x00006000
> +/**
> + * Mask of tunneling packet types.
> + */
> +#define RTE_PTYPE_TUNNEL_MASK               0x0000f000
> +/**
> + * MAC (Media Access Control) packet type.
> + * It is used for inner packet type only.
> + *
> + * Packet format (inner only):
> + * <'ether type'=[0x800|0x86DD]>
> + */
> +#define RTE_PTYPE_INNER_L2_MAC              0x00010000
> +/**
> + * MAC (Media Access Control) packet type with VLAN (Virtual Local Area
> + * Network) tag.
> + *
> + * Packet format (inner only):
> + * <'ether type'=[0x800|0x86DD], vlan=[1-4095]>
> + */
> +#define RTE_PTYPE_INNER_L2_MAC_VLAN         0x00020000
> +/**
> + * Mask of inner layer 2 packet types.
> + */
> +#define RTE_PTYPE_INNER_L2_MASK             0x000f0000
> +/**
> + * IP (Internet Protocol) version 4 packet type.
> + * It is used for inner packet only, and does not contain any header option.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'ihl'=5>
> + */
> +#define RTE_PTYPE_INNER_L3_IPV4             0x00100000
> +/**
> + * IP (Internet Protocol) version 4 packet type.
> + * It is used for inner packet only, and contains header options.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'ihl'=[6-15], 'options'>
> + */
> +#define RTE_PTYPE_INNER_L3_IPV4_EXT         0x00200000
> +/**
> + * IP (Internet Protocol) version 6 packet type.
> + * It is used for inner packet only, and does not contain any extension header.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=0x3B>
> + */
> +#define RTE_PTYPE_INNER_L3_IPV6             0x00300000
> +/**
> + * IP (Internet Protocol) version 4 packet type.
> + * It is used for inner packet only, and may or maynot contain header options.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'ihl'=[5-15], <'options'>>
> + */
> +#define RTE_PTYPE_INNER_L3_IPV4_EXT_UNKNOWN 0x00400000
> +/**
> + * IP (Internet Protocol) version 6 packet type.
> + * It is used for inner packet only, and contains extension headers.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=[0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87],
> + *   'extension headers'>
> + */
> +#define RTE_PTYPE_INNER_L3_IPV6_EXT         0x00500000
> +/**
> + * IP (Internet Protocol) version 6 packet type.
> + * It is used for inner packet only, and may or maynot contain extension
> + * headers.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=[0x3B|0x0|0x2B|0x2C|0x32|0x33|0x3C|0x87],
> + *   <'extension headers'>>
> + */
> +#define RTE_PTYPE_INNER_L3_IPV6_EXT_UNKNOWN 0x00600000
> +/**
> + * Mask of inner layer 3 packet types.
> + */
> +#define RTE_PTYPE_INNER_INNER_L3_MASK       0x00f00000
> +/**
> + * TCP (Transmission Control Protocol) packet type.
> + * It is used for inner packet only.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=6, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=6>
> + */
> +#define RTE_PTYPE_INNER_L4_TCP              0x01000000
> +/**
> + * UDP (User Datagram Protocol) packet type.
> + * It is used for inner packet only.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=17, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=17>
> + */
> +#define RTE_PTYPE_INNER_L4_UDP              0x02000000
> +/**
> + * Fragmented IP (Internet Protocol) packet type.
> + * It is used for inner packet only, and may or maynot have layer 4 packet.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'MF'=1>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=44>
> + */
> +#define RTE_PTYPE_INNER_L4_FRAG             0x03000000
> +/**
> + * SCTP (Stream Control Transmission Protocol) packet type.
> + * It is used for inner packet only.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=132, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=132>
> + */
> +#define RTE_PTYPE_INNER_L4_SCTP             0x04000000
> +/**
> + * ICMP (Internet Control Message Protocol) packet type.
> + * It is used for inner packet only.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'=1, 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'=1>
> + */
> +#define RTE_PTYPE_INNER_L4_ICMP             0x05000000
> +/**
> + * Non-fragmented IP (Internet Protocol) packet type.
> + * It is used for inner packet only, and may or maynot have other unknown layer
> + * 4 packet types.
> + *
> + * Packet format (inner only):
> + * <'ether type'=0x0800
> + * | 'version'=4, 'protocol'!=[6|17|132|1], 'MF'=0>
> + * or,
> + * <'ether type'=0x86DD
> + * | 'version'=6, 'next header'!=[6|17|44|132|1]>
> + */
> +#define RTE_PTYPE_INNER_L4_NONFRAG          0x06000000
> +/**
> + * Mask of inner layer 4 packet types.
> + */
> +#define RTE_PTYPE_INNER_L4_MASK             0x0f000000
> +
> +/**
> + * Check if the (outer) L3 header is IPv4. To avoid comparing IPv4 types one by
> + * one, bit 4 is selected to be used for IPv4 only. Then checking bit 4 can
> + * determin if it is an IPV4 packet.
> + */
> +#define  RTE_ETH_IS_IPV4_HDR(ptype) ((ptype) & RTE_PTYPE_L3_IPV4)
> +
> +/**
> + * Check if the (outer) L3 header is IPv4. To avoid comparing IPv4 types one by
> + * one, bit 6 is selected to be used for IPv4 only. Then checking bit 6 can
> + * determin if it is an IPV4 packet.
> + */
> +#define  RTE_ETH_IS_IPV6_HDR(ptype) ((ptype) & RTE_PTYPE_L3_IPV6)
> +
> +/* Check if it is a tunneling packet */
> +#define RTE_ETH_IS_TUNNEL_PKT(ptype) ((ptype) & RTE_PTYPE_TUNNEL_MASK)
> +#endif /* RTE_NEXT_ABI */
> +
>   /**
>    * Get the name of a RX offload flag
>    *
>