#include "colo.h"
#include "net/filter.h"
#include "net/net.h"
-#include "qemu-common.h"
#include "qemu/error-report.h"
#include "qom/object.h"
#include "qemu/main-loop.h"
#include "qemu/iov.h"
#include "net/checksum.h"
-
-#define FILTER_COLO_REWRITER(obj) \
- OBJECT_CHECK(RewriterState, (obj), TYPE_FILTER_REWRITER)
+#include "net/colo.h"
+#include "migration/colo.h"
+#include "util.h"
#define TYPE_FILTER_REWRITER "filter-rewriter"
+OBJECT_DECLARE_SIMPLE_TYPE(RewriterState, FILTER_REWRITER)
+
+#define FAILOVER_MODE_ON true
+#define FAILOVER_MODE_OFF false
-typedef struct RewriterState {
+struct RewriterState {
NetFilterState parent_obj;
NetQueue *incoming_queue;
/* hashtable to save connection */
GHashTable *connection_track_table;
bool vnet_hdr;
-} RewriterState;
+ bool failover_mode;
+};
+
+static void filter_rewriter_failover_mode(RewriterState *s)
+{
+ s->failover_mode = FAILOVER_MODE_ON;
+}
static void filter_rewriter_flush(NetFilterState *nf)
{
- RewriterState *s = FILTER_COLO_REWRITER(nf);
+ RewriterState *s = FILTER_REWRITER(nf);
if (!qemu_net_queue_flush(s->incoming_queue)) {
/* Unable to empty the queue, purge remaining packets */
Connection *conn,
Packet *pkt, ConnectionKey *key)
{
- struct tcphdr *tcp_pkt;
+ struct tcp_hdr *tcp_pkt;
- tcp_pkt = (struct tcphdr *)pkt->transport_header;
- if (trace_event_get_state_backends(TRACE_COLO_FILTER_REWRITER_DEBUG)) {
+ tcp_pkt = (struct tcp_hdr *)pkt->transport_header;
+ if (trace_event_get_state_backends(TRACE_COLO_FILTER_REWRITER_PKT_INFO)) {
trace_colo_filter_rewriter_pkt_info(__func__,
inet_ntoa(pkt->ip->ip_src), inet_ntoa(pkt->ip->ip_dst),
ntohl(tcp_pkt->th_seq), ntohl(tcp_pkt->th_ack),
tcp_pkt->th_flags);
+ }
+ if (trace_event_get_state_backends(
+ TRACE_COLO_FILTER_REWRITER_CONN_OFFSET)) {
trace_colo_filter_rewriter_conn_offset(conn->offset);
}
tcp_pkt->th_ack = htonl(ntohl(tcp_pkt->th_ack) + conn->offset);
net_checksum_calculate((uint8_t *)pkt->data + pkt->vnet_hdr_len,
- pkt->size - pkt->vnet_hdr_len);
+ pkt->size - pkt->vnet_hdr_len, CSUM_TCP);
}
/*
* Active close step 2.
*/
if (conn->tcp_state == TCPS_FIN_WAIT_1) {
- conn->tcp_state = TCPS_TIME_WAIT;
/*
* For simplify implementation, we needn't wait 2MSL time
* in filter rewriter. Because guest kernel will track the
* TCP status and wait 2MSL time, if client resend the FIN
* packet, guest will apply the last ACK too.
+ * So, we skip the TCPS_TIME_WAIT state here and go straight
+ * to TCPS_CLOSED state.
*/
conn->tcp_state = TCPS_CLOSED;
g_hash_table_remove(rf->connection_track_table, key);
Connection *conn,
Packet *pkt, ConnectionKey *key)
{
- struct tcphdr *tcp_pkt;
+ struct tcp_hdr *tcp_pkt;
- tcp_pkt = (struct tcphdr *)pkt->transport_header;
+ tcp_pkt = (struct tcp_hdr *)pkt->transport_header;
- if (trace_event_get_state_backends(TRACE_COLO_FILTER_REWRITER_DEBUG)) {
+ if (trace_event_get_state_backends(TRACE_COLO_FILTER_REWRITER_PKT_INFO)) {
trace_colo_filter_rewriter_pkt_info(__func__,
inet_ntoa(pkt->ip->ip_src), inet_ntoa(pkt->ip->ip_dst),
ntohl(tcp_pkt->th_seq), ntohl(tcp_pkt->th_ack),
tcp_pkt->th_flags);
+ }
+ if (trace_event_get_state_backends(
+ TRACE_COLO_FILTER_REWRITER_CONN_OFFSET)) {
trace_colo_filter_rewriter_conn_offset(conn->offset);
}
tcp_pkt->th_seq = htonl(ntohl(tcp_pkt->th_seq) - conn->offset);
net_checksum_calculate((uint8_t *)pkt->data + pkt->vnet_hdr_len,
- pkt->size - pkt->vnet_hdr_len);
+ pkt->size - pkt->vnet_hdr_len, CSUM_TCP);
}
}
int iovcnt,
NetPacketSent *sent_cb)
{
- RewriterState *s = FILTER_COLO_REWRITER(nf);
+ RewriterState *s = FILTER_REWRITER(nf);
Connection *conn;
ConnectionKey key;
Packet *pkt;
vnet_hdr_len = nf->netdev->vnet_hdr_len;
}
- pkt = packet_new(buf, size, vnet_hdr_len);
- g_free(buf);
+ pkt = packet_new_nocopy(buf, size, vnet_hdr_len);
/*
* if we get tcp packet
*/
if (pkt && is_tcp_packet(pkt)) {
- fill_connection_key(pkt, &key);
+ fill_connection_key(pkt, &key, sender == nf->netdev);
- if (sender == nf->netdev) {
- /*
- * We need make tcp TX and RX packet
- * into one connection.
- */
- reverse_connection_key(&key);
+ /* After failover we needn't change new TCP packet */
+ if (s->failover_mode &&
+ !connection_has_tracked(s->connection_track_table, &key)) {
+ goto out;
}
+
conn = connection_get(s->connection_track_table,
&key,
NULL);
}
}
+out:
packet_destroy(pkt, NULL);
pkt = NULL;
return 0;
}
+static void reset_seq_offset(gpointer key, gpointer value, gpointer user_data)
+{
+ Connection *conn = (Connection *)value;
+
+ conn->offset = 0;
+}
+
+static gboolean offset_is_nonzero(gpointer key,
+ gpointer value,
+ gpointer user_data)
+{
+ Connection *conn = (Connection *)value;
+
+ return conn->offset ? true : false;
+}
+
+static void colo_rewriter_handle_event(NetFilterState *nf, int event,
+ Error **errp)
+{
+ RewriterState *rs = FILTER_REWRITER(nf);
+
+ switch (event) {
+ case COLO_EVENT_CHECKPOINT:
+ g_hash_table_foreach(rs->connection_track_table,
+ reset_seq_offset, NULL);
+ break;
+ case COLO_EVENT_FAILOVER:
+ if (!g_hash_table_find(rs->connection_track_table,
+ offset_is_nonzero, NULL)) {
+ filter_rewriter_failover_mode(rs);
+ }
+ break;
+ default:
+ break;
+ }
+}
+
static void colo_rewriter_cleanup(NetFilterState *nf)
{
- RewriterState *s = FILTER_COLO_REWRITER(nf);
+ RewriterState *s = FILTER_REWRITER(nf);
/* flush packets */
if (s->incoming_queue) {
filter_rewriter_flush(nf);
g_free(s->incoming_queue);
}
+
+ g_hash_table_destroy(s->connection_track_table);
}
static void colo_rewriter_setup(NetFilterState *nf, Error **errp)
{
- RewriterState *s = FILTER_COLO_REWRITER(nf);
+ RewriterState *s = FILTER_REWRITER(nf);
s->connection_track_table = g_hash_table_new_full(connection_key_hash,
connection_key_equal,
g_free,
- connection_destroy);
+ NULL);
s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf);
}
static bool filter_rewriter_get_vnet_hdr(Object *obj, Error **errp)
{
- RewriterState *s = FILTER_COLO_REWRITER(obj);
+ RewriterState *s = FILTER_REWRITER(obj);
return s->vnet_hdr;
}
bool value,
Error **errp)
{
- RewriterState *s = FILTER_COLO_REWRITER(obj);
+ RewriterState *s = FILTER_REWRITER(obj);
s->vnet_hdr = value;
}
static void filter_rewriter_init(Object *obj)
{
- RewriterState *s = FILTER_COLO_REWRITER(obj);
+ RewriterState *s = FILTER_REWRITER(obj);
s->vnet_hdr = false;
- object_property_add_bool(obj, "vnet_hdr_support",
- filter_rewriter_get_vnet_hdr,
- filter_rewriter_set_vnet_hdr, NULL);
+ s->failover_mode = FAILOVER_MODE_OFF;
}
static void colo_rewriter_class_init(ObjectClass *oc, void *data)
{
NetFilterClass *nfc = NETFILTER_CLASS(oc);
+ object_class_property_add_bool(oc, "vnet_hdr_support",
+ filter_rewriter_get_vnet_hdr,
+ filter_rewriter_set_vnet_hdr);
+
nfc->setup = colo_rewriter_setup;
nfc->cleanup = colo_rewriter_cleanup;
nfc->receive_iov = colo_rewriter_receive_iov;
+ nfc->handle_event = colo_rewriter_handle_event;
}
static const TypeInfo colo_rewriter_info = {