2016-09-27 04:22:27 +02:00
|
|
|
/*
|
|
|
|
* COarse-grain LOck-stepping Virtual Machines for Non-stop Service (COLO)
|
|
|
|
* (a.k.a. Fault Tolerance or Continuous Replication)
|
|
|
|
*
|
|
|
|
* Copyright (c) 2016 HUAWEI TECHNOLOGIES CO., LTD.
|
|
|
|
* Copyright (c) 2016 FUJITSU LIMITED
|
|
|
|
* Copyright (c) 2016 Intel Corporation
|
|
|
|
*
|
|
|
|
* Author: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
|
|
|
|
*
|
|
|
|
* This work is licensed under the terms of the GNU GPL, version 2 or
|
|
|
|
* later. See the COPYING file in the top-level directory.
|
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef QEMU_COLO_PROXY_H
|
|
|
|
#define QEMU_COLO_PROXY_H
|
|
|
|
|
|
|
|
#include "slirp/slirp.h"
|
2016-09-27 04:22:28 +02:00
|
|
|
#include "qemu/jhash.h"
|
2016-09-27 04:22:30 +02:00
|
|
|
#include "qemu/timer.h"
|
2016-09-27 04:22:27 +02:00
|
|
|
|
|
|
|
#define HASHTABLE_MAX_SIZE 16384
|
|
|
|
|
2016-09-27 04:22:29 +02:00
|
|
|
#ifndef IPPROTO_DCCP
|
|
|
|
#define IPPROTO_DCCP 33
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef IPPROTO_SCTP
|
|
|
|
#define IPPROTO_SCTP 132
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef IPPROTO_UDPLITE
|
|
|
|
#define IPPROTO_UDPLITE 136
|
|
|
|
#endif
|
|
|
|
|
2016-09-27 04:22:27 +02:00
|
|
|
typedef struct Packet {
|
|
|
|
void *data;
|
|
|
|
union {
|
|
|
|
uint8_t *network_header;
|
|
|
|
struct ip *ip;
|
|
|
|
};
|
|
|
|
uint8_t *transport_header;
|
|
|
|
int size;
|
2016-09-27 04:22:30 +02:00
|
|
|
/* Time of packet creation, in wall clock ms */
|
|
|
|
int64_t creation_ms;
|
2017-07-04 08:53:50 +02:00
|
|
|
/* Get vnet_hdr_len from filter */
|
|
|
|
uint32_t vnet_hdr_len;
|
2016-09-27 04:22:27 +02:00
|
|
|
} Packet;
|
|
|
|
|
2016-09-27 04:22:29 +02:00
|
|
|
typedef struct ConnectionKey {
|
|
|
|
/* (src, dst) must be grouped, in the same way than in IP header */
|
|
|
|
struct in_addr src;
|
|
|
|
struct in_addr dst;
|
|
|
|
uint16_t src_port;
|
|
|
|
uint16_t dst_port;
|
|
|
|
uint8_t ip_proto;
|
|
|
|
} QEMU_PACKED ConnectionKey;
|
|
|
|
|
|
|
|
typedef struct Connection {
|
|
|
|
/* connection primary send queue: element type: Packet */
|
|
|
|
GQueue primary_list;
|
|
|
|
/* connection secondary send queue: element type: Packet */
|
|
|
|
GQueue secondary_list;
|
|
|
|
/* flag to enqueue unprocessed_connections */
|
|
|
|
bool processing;
|
|
|
|
uint8_t ip_proto;
|
filter-rewriter: rewrite tcp packet to keep secondary connection
We will rewrite tcp packet secondary received and sent.
When colo guest is a tcp server.
Firstly, client start a tcp handshake. the packet's seq=client_seq,
ack=0,flag=SYN. COLO primary guest get this pkt and mirror(filter-mirror)
to secondary guest, secondary get it use filter-redirector.
Then,primary guest response pkt
(seq=primary_seq,ack=client_seq+1,flag=ACK|SYN).
secondary guest response pkt
(seq=secondary_seq,ack=client_seq+1,flag=ACK|SYN).
In here,we use filter-rewriter save the secondary_seq to it's tcp connection.
Finally handshake,client send pkt
(seq=client_seq+1,ack=primary_seq+1,flag=ACK).
Here,filter-rewriter can get primary_seq, and rewrite ack from primary_seq+1
to secondary_seq+1, recalculate checksum. So the secondary tcp connection
kept good.
When we send/recv packet.
client send pkt(seq=client_seq+1+data_len,ack=primary_seq+1,flag=ACK|PSH).
filter-rewriter rewrite ack and send to secondary guest.
primary guest response pkt
(seq=primary_seq+1,ack=client_seq+1+data_len,flag=ACK)
secondary guest response pkt
(seq=secondary_seq+1,ack=client_seq+1+data_len,flag=ACK)
we rewrite secondary guest seq from secondary_seq+1 to primary_seq+1.
So tcp connection kept good.
In code We use offset( = secondary_seq - primary_seq )
to rewrite seq or ack.
handle_primary_tcp_pkt: tcp_pkt->th_ack += offset;
handle_secondary_tcp_pkt: tcp_pkt->th_seq -= offset;
Signed-off-by: Zhang Chen <zhangchen.fnst@cn.fujitsu.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
2016-09-27 04:22:34 +02:00
|
|
|
/* offset = secondary_seq - primary_seq */
|
|
|
|
tcp_seq offset;
|
|
|
|
/*
|
|
|
|
* we use this flag update offset func
|
|
|
|
* run once in independent tcp connection
|
|
|
|
*/
|
|
|
|
int syn_flag;
|
2016-09-27 04:22:29 +02:00
|
|
|
} Connection;
|
|
|
|
|
|
|
|
uint32_t connection_key_hash(const void *opaque);
|
|
|
|
int connection_key_equal(const void *opaque1, const void *opaque2);
|
2016-09-27 04:22:27 +02:00
|
|
|
int parse_packet_early(Packet *pkt);
|
2017-10-13 08:32:09 +02:00
|
|
|
void extract_ip_and_port(uint32_t tmp_ports, ConnectionKey *key, Packet *pkt);
|
2016-09-27 04:22:29 +02:00
|
|
|
void fill_connection_key(Packet *pkt, ConnectionKey *key);
|
2016-09-27 04:22:33 +02:00
|
|
|
void reverse_connection_key(ConnectionKey *key);
|
2016-09-27 04:22:29 +02:00
|
|
|
Connection *connection_new(ConnectionKey *key);
|
|
|
|
void connection_destroy(void *opaque);
|
|
|
|
Connection *connection_get(GHashTable *connection_track_table,
|
|
|
|
ConnectionKey *key,
|
|
|
|
GQueue *conn_list);
|
2016-09-27 04:22:27 +02:00
|
|
|
void connection_hashtable_reset(GHashTable *connection_track_table);
|
2017-07-04 08:53:50 +02:00
|
|
|
Packet *packet_new(const void *data, int size, int vnet_hdr_len);
|
2016-09-27 04:22:27 +02:00
|
|
|
void packet_destroy(void *opaque, void *user_data);
|
|
|
|
|
|
|
|
#endif /* QEMU_COLO_PROXY_H */
|