mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-15 08:46:45 +07:00
5df0ddfbc9
We currently allow for different fanout scheduling policies in pf_packet such as scheduling by skb's rxhash, round-robin, by cpu, and rollover. Also allow for a random, equidistributed selection of the socket from the fanout process group. Signed-off-by: Daniel Borkmann <dborkman@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
282 lines
7.0 KiB
C
282 lines
7.0 KiB
C
#ifndef __LINUX_IF_PACKET_H
|
|
#define __LINUX_IF_PACKET_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
struct sockaddr_pkt {
|
|
unsigned short spkt_family;
|
|
unsigned char spkt_device[14];
|
|
__be16 spkt_protocol;
|
|
};
|
|
|
|
struct sockaddr_ll {
|
|
unsigned short sll_family;
|
|
__be16 sll_protocol;
|
|
int sll_ifindex;
|
|
unsigned short sll_hatype;
|
|
unsigned char sll_pkttype;
|
|
unsigned char sll_halen;
|
|
unsigned char sll_addr[8];
|
|
};
|
|
|
|
/* Packet types */
|
|
|
|
#define PACKET_HOST 0 /* To us */
|
|
#define PACKET_BROADCAST 1 /* To all */
|
|
#define PACKET_MULTICAST 2 /* To group */
|
|
#define PACKET_OTHERHOST 3 /* To someone else */
|
|
#define PACKET_OUTGOING 4 /* Outgoing of any type */
|
|
/* These ones are invisible by user level */
|
|
#define PACKET_LOOPBACK 5 /* MC/BRD frame looped back */
|
|
#define PACKET_FASTROUTE 6 /* Fastrouted frame */
|
|
|
|
/* Packet socket options */
|
|
|
|
#define PACKET_ADD_MEMBERSHIP 1
|
|
#define PACKET_DROP_MEMBERSHIP 2
|
|
#define PACKET_RECV_OUTPUT 3
|
|
/* Value 4 is still used by obsolete turbo-packet. */
|
|
#define PACKET_RX_RING 5
|
|
#define PACKET_STATISTICS 6
|
|
#define PACKET_COPY_THRESH 7
|
|
#define PACKET_AUXDATA 8
|
|
#define PACKET_ORIGDEV 9
|
|
#define PACKET_VERSION 10
|
|
#define PACKET_HDRLEN 11
|
|
#define PACKET_RESERVE 12
|
|
#define PACKET_TX_RING 13
|
|
#define PACKET_LOSS 14
|
|
#define PACKET_VNET_HDR 15
|
|
#define PACKET_TX_TIMESTAMP 16
|
|
#define PACKET_TIMESTAMP 17
|
|
#define PACKET_FANOUT 18
|
|
#define PACKET_TX_HAS_OFF 19
|
|
|
|
#define PACKET_FANOUT_HASH 0
|
|
#define PACKET_FANOUT_LB 1
|
|
#define PACKET_FANOUT_CPU 2
|
|
#define PACKET_FANOUT_ROLLOVER 3
|
|
#define PACKET_FANOUT_RND 4
|
|
#define PACKET_FANOUT_FLAG_ROLLOVER 0x1000
|
|
#define PACKET_FANOUT_FLAG_DEFRAG 0x8000
|
|
|
|
struct tpacket_stats {
|
|
unsigned int tp_packets;
|
|
unsigned int tp_drops;
|
|
};
|
|
|
|
struct tpacket_stats_v3 {
|
|
unsigned int tp_packets;
|
|
unsigned int tp_drops;
|
|
unsigned int tp_freeze_q_cnt;
|
|
};
|
|
|
|
union tpacket_stats_u {
|
|
struct tpacket_stats stats1;
|
|
struct tpacket_stats_v3 stats3;
|
|
};
|
|
|
|
struct tpacket_auxdata {
|
|
__u32 tp_status;
|
|
__u32 tp_len;
|
|
__u32 tp_snaplen;
|
|
__u16 tp_mac;
|
|
__u16 tp_net;
|
|
__u16 tp_vlan_tci;
|
|
__u16 tp_padding;
|
|
};
|
|
|
|
/* Rx ring - header status */
|
|
#define TP_STATUS_KERNEL 0
|
|
#define TP_STATUS_USER (1 << 0)
|
|
#define TP_STATUS_COPY (1 << 1)
|
|
#define TP_STATUS_LOSING (1 << 2)
|
|
#define TP_STATUS_CSUMNOTREADY (1 << 3)
|
|
#define TP_STATUS_VLAN_VALID (1 << 4) /* auxdata has valid tp_vlan_tci */
|
|
#define TP_STATUS_BLK_TMO (1 << 5)
|
|
|
|
/* Tx ring - header status */
|
|
#define TP_STATUS_AVAILABLE 0
|
|
#define TP_STATUS_SEND_REQUEST (1 << 0)
|
|
#define TP_STATUS_SENDING (1 << 1)
|
|
#define TP_STATUS_WRONG_FORMAT (1 << 2)
|
|
|
|
/* Rx and Tx ring - header status */
|
|
#define TP_STATUS_TS_SOFTWARE (1 << 29)
|
|
#define TP_STATUS_TS_SYS_HARDWARE (1 << 30)
|
|
#define TP_STATUS_TS_RAW_HARDWARE (1 << 31)
|
|
|
|
/* Rx ring - feature request bits */
|
|
#define TP_FT_REQ_FILL_RXHASH 0x1
|
|
|
|
struct tpacket_hdr {
|
|
unsigned long tp_status;
|
|
unsigned int tp_len;
|
|
unsigned int tp_snaplen;
|
|
unsigned short tp_mac;
|
|
unsigned short tp_net;
|
|
unsigned int tp_sec;
|
|
unsigned int tp_usec;
|
|
};
|
|
|
|
#define TPACKET_ALIGNMENT 16
|
|
#define TPACKET_ALIGN(x) (((x)+TPACKET_ALIGNMENT-1)&~(TPACKET_ALIGNMENT-1))
|
|
#define TPACKET_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket_hdr)) + sizeof(struct sockaddr_ll))
|
|
|
|
struct tpacket2_hdr {
|
|
__u32 tp_status;
|
|
__u32 tp_len;
|
|
__u32 tp_snaplen;
|
|
__u16 tp_mac;
|
|
__u16 tp_net;
|
|
__u32 tp_sec;
|
|
__u32 tp_nsec;
|
|
__u16 tp_vlan_tci;
|
|
__u16 tp_padding;
|
|
};
|
|
|
|
struct tpacket_hdr_variant1 {
|
|
__u32 tp_rxhash;
|
|
__u32 tp_vlan_tci;
|
|
};
|
|
|
|
struct tpacket3_hdr {
|
|
__u32 tp_next_offset;
|
|
__u32 tp_sec;
|
|
__u32 tp_nsec;
|
|
__u32 tp_snaplen;
|
|
__u32 tp_len;
|
|
__u32 tp_status;
|
|
__u16 tp_mac;
|
|
__u16 tp_net;
|
|
/* pkt_hdr variants */
|
|
union {
|
|
struct tpacket_hdr_variant1 hv1;
|
|
};
|
|
};
|
|
|
|
struct tpacket_bd_ts {
|
|
unsigned int ts_sec;
|
|
union {
|
|
unsigned int ts_usec;
|
|
unsigned int ts_nsec;
|
|
};
|
|
};
|
|
|
|
struct tpacket_hdr_v1 {
|
|
__u32 block_status;
|
|
__u32 num_pkts;
|
|
__u32 offset_to_first_pkt;
|
|
|
|
/* Number of valid bytes (including padding)
|
|
* blk_len <= tp_block_size
|
|
*/
|
|
__u32 blk_len;
|
|
|
|
/*
|
|
* Quite a few uses of sequence number:
|
|
* 1. Make sure cache flush etc worked.
|
|
* Well, one can argue - why not use the increasing ts below?
|
|
* But look at 2. below first.
|
|
* 2. When you pass around blocks to other user space decoders,
|
|
* you can see which blk[s] is[are] outstanding etc.
|
|
* 3. Validate kernel code.
|
|
*/
|
|
__aligned_u64 seq_num;
|
|
|
|
/*
|
|
* ts_last_pkt:
|
|
*
|
|
* Case 1. Block has 'N'(N >=1) packets and TMO'd(timed out)
|
|
* ts_last_pkt == 'time-stamp of last packet' and NOT the
|
|
* time when the timer fired and the block was closed.
|
|
* By providing the ts of the last packet we can absolutely
|
|
* guarantee that time-stamp wise, the first packet in the
|
|
* next block will never precede the last packet of the
|
|
* previous block.
|
|
* Case 2. Block has zero packets and TMO'd
|
|
* ts_last_pkt = time when the timer fired and the block
|
|
* was closed.
|
|
* Case 3. Block has 'N' packets and NO TMO.
|
|
* ts_last_pkt = time-stamp of the last pkt in the block.
|
|
*
|
|
* ts_first_pkt:
|
|
* Is always the time-stamp when the block was opened.
|
|
* Case a) ZERO packets
|
|
* No packets to deal with but atleast you know the
|
|
* time-interval of this block.
|
|
* Case b) Non-zero packets
|
|
* Use the ts of the first packet in the block.
|
|
*
|
|
*/
|
|
struct tpacket_bd_ts ts_first_pkt, ts_last_pkt;
|
|
};
|
|
|
|
union tpacket_bd_header_u {
|
|
struct tpacket_hdr_v1 bh1;
|
|
};
|
|
|
|
struct tpacket_block_desc {
|
|
__u32 version;
|
|
__u32 offset_to_priv;
|
|
union tpacket_bd_header_u hdr;
|
|
};
|
|
|
|
#define TPACKET2_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket2_hdr)) + sizeof(struct sockaddr_ll))
|
|
#define TPACKET3_HDRLEN (TPACKET_ALIGN(sizeof(struct tpacket3_hdr)) + sizeof(struct sockaddr_ll))
|
|
|
|
enum tpacket_versions {
|
|
TPACKET_V1,
|
|
TPACKET_V2,
|
|
TPACKET_V3
|
|
};
|
|
|
|
/*
|
|
Frame structure:
|
|
|
|
- Start. Frame must be aligned to TPACKET_ALIGNMENT=16
|
|
- struct tpacket_hdr
|
|
- pad to TPACKET_ALIGNMENT=16
|
|
- struct sockaddr_ll
|
|
- Gap, chosen so that packet data (Start+tp_net) alignes to TPACKET_ALIGNMENT=16
|
|
- Start+tp_mac: [ Optional MAC header ]
|
|
- Start+tp_net: Packet data, aligned to TPACKET_ALIGNMENT=16.
|
|
- Pad to align to TPACKET_ALIGNMENT=16
|
|
*/
|
|
|
|
struct tpacket_req {
|
|
unsigned int tp_block_size; /* Minimal size of contiguous block */
|
|
unsigned int tp_block_nr; /* Number of blocks */
|
|
unsigned int tp_frame_size; /* Size of frame */
|
|
unsigned int tp_frame_nr; /* Total number of frames */
|
|
};
|
|
|
|
struct tpacket_req3 {
|
|
unsigned int tp_block_size; /* Minimal size of contiguous block */
|
|
unsigned int tp_block_nr; /* Number of blocks */
|
|
unsigned int tp_frame_size; /* Size of frame */
|
|
unsigned int tp_frame_nr; /* Total number of frames */
|
|
unsigned int tp_retire_blk_tov; /* timeout in msecs */
|
|
unsigned int tp_sizeof_priv; /* offset to private data area */
|
|
unsigned int tp_feature_req_word;
|
|
};
|
|
|
|
union tpacket_req_u {
|
|
struct tpacket_req req;
|
|
struct tpacket_req3 req3;
|
|
};
|
|
|
|
struct packet_mreq {
|
|
int mr_ifindex;
|
|
unsigned short mr_type;
|
|
unsigned short mr_alen;
|
|
unsigned char mr_address[8];
|
|
};
|
|
|
|
#define PACKET_MR_MULTICAST 0
|
|
#define PACKET_MR_PROMISC 1
|
|
#define PACKET_MR_ALLMULTI 2
|
|
#define PACKET_MR_UNICAST 3
|
|
|
|
#endif
|