qemu/net/colo.c

212 lines
5.3 KiB
C
Raw Normal View History

/*
* 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.
*/
#include "qemu/osdep.h"
#include "trace.h"
#include "net/colo.h"
uint32_t connection_key_hash(const void *opaque)
{
const ConnectionKey *key = opaque;
uint32_t a, b, c;
/* Jenkins hash */
a = b = c = JHASH_INITVAL + sizeof(*key);
a += key->src.s_addr;
b += key->dst.s_addr;
c += (key->src_port | key->dst_port << 16);
__jhash_mix(a, b, c);
a += key->ip_proto;
__jhash_final(a, b, c);
return c;
}
int connection_key_equal(const void *key1, const void *key2)
{
return memcmp(key1, key2, sizeof(ConnectionKey)) == 0;
}
int parse_packet_early(Packet *pkt)
{
int network_length;
static const uint8_t vlan[] = {0x81, 0x00};
uint8_t *data = pkt->data;
uint16_t l3_proto;
ssize_t l2hdr_len = eth_get_l2_hdr_length(data);
if (pkt->size < ETH_HLEN) {
trace_colo_proxy_main("pkt->size < ETH_HLEN");
return 1;
}
/*
* TODO: support vlan.
*/
if (!memcmp(&data[12], vlan, sizeof(vlan))) {
trace_colo_proxy_main("COLO-proxy don't support vlan");
return 1;
}
pkt->network_header = data + l2hdr_len;
const struct iovec l2vec = {
.iov_base = (void *) data,
.iov_len = l2hdr_len
};
l3_proto = eth_get_l3_proto(&l2vec, 1, l2hdr_len);
if (l3_proto != ETH_P_IP) {
return 1;
}
network_length = pkt->ip->ip_hl * 4;
if (pkt->size < l2hdr_len + network_length) {
trace_colo_proxy_main("pkt->size < network_header + network_length");
return 1;
}
pkt->transport_header = pkt->network_header + network_length;
return 0;
}
void fill_connection_key(Packet *pkt, ConnectionKey *key)
{
uint32_t tmp_ports;
memset(key, 0, sizeof(*key));
key->ip_proto = pkt->ip->ip_p;
switch (key->ip_proto) {
case IPPROTO_TCP:
case IPPROTO_UDP:
case IPPROTO_DCCP:
case IPPROTO_ESP:
case IPPROTO_SCTP:
case IPPROTO_UDPLITE:
tmp_ports = *(uint32_t *)(pkt->transport_header);
key->src = pkt->ip->ip_src;
key->dst = pkt->ip->ip_dst;
key->src_port = ntohs(tmp_ports & 0xffff);
key->dst_port = ntohs(tmp_ports >> 16);
break;
case IPPROTO_AH:
tmp_ports = *(uint32_t *)(pkt->transport_header + 4);
key->src = pkt->ip->ip_src;
key->dst = pkt->ip->ip_dst;
key->src_port = ntohs(tmp_ports & 0xffff);
key->dst_port = ntohs(tmp_ports >> 16);
break;
default:
break;
}
}
void reverse_connection_key(ConnectionKey *key)
{
struct in_addr tmp_ip;
uint16_t tmp_port;
tmp_ip = key->src;
key->src = key->dst;
key->dst = tmp_ip;
tmp_port = key->src_port;
key->src_port = key->dst_port;
key->dst_port = tmp_port;
}
Connection *connection_new(ConnectionKey *key)
{
Connection *conn = g_slice_new(Connection);
conn->ip_proto = key->ip_proto;
conn->processing = false;
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 05:22:34 +03:00
conn->offset = 0;
conn->syn_flag = 0;
g_queue_init(&conn->primary_list);
g_queue_init(&conn->secondary_list);
return conn;
}
void connection_destroy(void *opaque)
{
Connection *conn = opaque;
g_queue_foreach(&conn->primary_list, packet_destroy, NULL);
g_queue_free(&conn->primary_list);
g_queue_foreach(&conn->secondary_list, packet_destroy, NULL);
g_queue_free(&conn->secondary_list);
g_slice_free(Connection, conn);
}
Packet *packet_new(const void *data, int size)
{
Packet *pkt = g_slice_new(Packet);
pkt->data = g_memdup(data, size);
pkt->size = size;
pkt->creation_ms = qemu_clock_get_ms(QEMU_CLOCK_HOST);
return pkt;
}
void packet_destroy(void *opaque, void *user_data)
{
Packet *pkt = opaque;
g_free(pkt->data);
g_slice_free(Packet, pkt);
}
/*
* Clear hashtable, stop this hash growing really huge
*/
void connection_hashtable_reset(GHashTable *connection_track_table)
{
g_hash_table_remove_all(connection_track_table);
}
/* if not found, create a new connection and add to hash table */
Connection *connection_get(GHashTable *connection_track_table,
ConnectionKey *key,
GQueue *conn_list)
{
Connection *conn = g_hash_table_lookup(connection_track_table, key);
if (conn == NULL) {
ConnectionKey *new_key = g_memdup(key, sizeof(*key));
conn = connection_new(key);
if (g_hash_table_size(connection_track_table) > HASHTABLE_MAX_SIZE) {
trace_colo_proxy_main("colo proxy connection hashtable full,"
" clear it");
connection_hashtable_reset(connection_track_table);
/*
* clear the conn_list
*/
while (!g_queue_is_empty(conn_list)) {
connection_destroy(g_queue_pop_head(conn_list));
}
}
g_hash_table_insert(connection_track_table, new_key, conn);
}
return conn;
}