aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorZhang Chen <zhangchen.fnst@cn.fujitsu.com>2016-09-27 10:22:34 +0800
committerJason Wang <jasowang@redhat.com>2016-09-27 17:54:22 +0800
commit30656b097e9dd7978d3fe9416cb9f5a421a9e63e (patch)
treec6b5ffa87a684d35686d77f436c5bde8b513dbbd
parentafe461240940077e7ea8313e9c547a4898263cd2 (diff)
downloadqemu-30656b097e9dd7978d3fe9416cb9f5a421a9e63e.zip
qemu-30656b097e9dd7978d3fe9416cb9f5a421a9e63e.tar.gz
qemu-30656b097e9dd7978d3fe9416cb9f5a421a9e63e.tar.bz2
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>
-rw-r--r--net/colo.c2
-rw-r--r--net/colo.h7
-rw-r--r--net/filter-rewriter.c112
-rw-r--r--trace-events5
4 files changed, 124 insertions, 2 deletions
diff --git a/net/colo.c b/net/colo.c
index 124994c..6a6eacd 100644
--- a/net/colo.c
+++ b/net/colo.c
@@ -134,6 +134,8 @@ Connection *connection_new(ConnectionKey *key)
conn->ip_proto = key->ip_proto;
conn->processing = false;
+ conn->offset = 0;
+ conn->syn_flag = 0;
g_queue_init(&conn->primary_list);
g_queue_init(&conn->secondary_list);
diff --git a/net/colo.h b/net/colo.h
index 6720a3a..7c524f3 100644
--- a/net/colo.h
+++ b/net/colo.h
@@ -62,6 +62,13 @@ typedef struct Connection {
/* flag to enqueue unprocessed_connections */
bool processing;
uint8_t ip_proto;
+ /* offset = secondary_seq - primary_seq */
+ tcp_seq offset;
+ /*
+ * we use this flag update offset func
+ * run once in independent tcp connection
+ */
+ int syn_flag;
} Connection;
uint32_t connection_key_hash(const void *opaque);
diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c
index 9bf80d3..89abe72 100644
--- a/net/filter-rewriter.c
+++ b/net/filter-rewriter.c
@@ -10,6 +10,7 @@
*/
#include "qemu/osdep.h"
+#include "trace.h"
#include "net/colo.h"
#include "net/filter.h"
#include "net/net.h"
@@ -58,6 +59,93 @@ static int is_tcp_packet(Packet *pkt)
}
}
+/* handle tcp packet from primary guest */
+static int handle_primary_tcp_pkt(NetFilterState *nf,
+ Connection *conn,
+ Packet *pkt)
+{
+ struct tcphdr *tcp_pkt;
+
+ tcp_pkt = (struct tcphdr *)pkt->transport_header;
+ if (trace_event_get_state(TRACE_COLO_FILTER_REWRITER_DEBUG)) {
+ char *sdebug, *ddebug;
+ sdebug = strdup(inet_ntoa(pkt->ip->ip_src));
+ ddebug = strdup(inet_ntoa(pkt->ip->ip_dst));
+ trace_colo_filter_rewriter_pkt_info(__func__, sdebug, ddebug,
+ ntohl(tcp_pkt->th_seq), ntohl(tcp_pkt->th_ack),
+ tcp_pkt->th_flags);
+ trace_colo_filter_rewriter_conn_offset(conn->offset);
+ g_free(sdebug);
+ g_free(ddebug);
+ }
+
+ if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_SYN)) {
+ /*
+ * we use this flag update offset func
+ * run once in independent tcp connection
+ */
+ conn->syn_flag = 1;
+ }
+
+ if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_ACK)) {
+ if (conn->syn_flag) {
+ /*
+ * offset = secondary_seq - primary seq
+ * ack packet sent by guest from primary node,
+ * so we use th_ack - 1 get primary_seq
+ */
+ conn->offset -= (ntohl(tcp_pkt->th_ack) - 1);
+ conn->syn_flag = 0;
+ }
+ /* handle packets to the secondary from the primary */
+ tcp_pkt->th_ack = htonl(ntohl(tcp_pkt->th_ack) + conn->offset);
+
+ net_checksum_calculate((uint8_t *)pkt->data, pkt->size);
+ }
+
+ return 0;
+}
+
+/* handle tcp packet from secondary guest */
+static int handle_secondary_tcp_pkt(NetFilterState *nf,
+ Connection *conn,
+ Packet *pkt)
+{
+ struct tcphdr *tcp_pkt;
+
+ tcp_pkt = (struct tcphdr *)pkt->transport_header;
+
+ if (trace_event_get_state(TRACE_COLO_FILTER_REWRITER_DEBUG)) {
+ char *sdebug, *ddebug;
+ sdebug = strdup(inet_ntoa(pkt->ip->ip_src));
+ ddebug = strdup(inet_ntoa(pkt->ip->ip_dst));
+ trace_colo_filter_rewriter_pkt_info(__func__, sdebug, ddebug,
+ ntohl(tcp_pkt->th_seq), ntohl(tcp_pkt->th_ack),
+ tcp_pkt->th_flags);
+ trace_colo_filter_rewriter_conn_offset(conn->offset);
+ g_free(sdebug);
+ g_free(ddebug);
+ }
+
+ if (((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == (TH_ACK | TH_SYN))) {
+ /*
+ * save offset = secondary_seq and then
+ * in handle_primary_tcp_pkt make offset
+ * = secondary_seq - primary_seq
+ */
+ conn->offset = ntohl(tcp_pkt->th_seq);
+ }
+
+ if ((tcp_pkt->th_flags & (TH_ACK | TH_SYN)) == TH_ACK) {
+ /* handle packets to the primary from the secondary*/
+ tcp_pkt->th_seq = htonl(ntohl(tcp_pkt->th_seq) - conn->offset);
+
+ net_checksum_calculate((uint8_t *)pkt->data, pkt->size);
+ }
+
+ return 0;
+}
+
static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
NetClientState *sender,
unsigned flags,
@@ -97,10 +185,30 @@ static ssize_t colo_rewriter_receive_iov(NetFilterState *nf,
if (sender == nf->netdev) {
/* NET_FILTER_DIRECTION_TX */
- /* handle_primary_tcp_pkt */
+ if (!handle_primary_tcp_pkt(nf, conn, pkt)) {
+ qemu_net_queue_send(s->incoming_queue, sender, 0,
+ (const uint8_t *)pkt->data, pkt->size, NULL);
+ packet_destroy(pkt, NULL);
+ pkt = NULL;
+ /*
+ * We block the packet here,after rewrite pkt
+ * and will send it
+ */
+ return 1;
+ }
} else {
/* NET_FILTER_DIRECTION_RX */
- /* handle_secondary_tcp_pkt */
+ if (!handle_secondary_tcp_pkt(nf, conn, pkt)) {
+ qemu_net_queue_send(s->incoming_queue, sender, 0,
+ (const uint8_t *)pkt->data, pkt->size, NULL);
+ packet_destroy(pkt, NULL);
+ pkt = NULL;
+ /*
+ * We block the packet here,after rewrite pkt
+ * and will send it
+ */
+ return 1;
+ }
}
}
diff --git a/trace-events b/trace-events
index b395368..1cb9d37 100644
--- a/trace-events
+++ b/trace-events
@@ -150,6 +150,11 @@ colo_compare_ip_info(int psize, const char *sta, const char *stb, int ssize, con
colo_old_packet_check_found(int64_t old_time) "%" PRId64
colo_compare_miscompare(void) ""
+# net/filter-rewriter.c
+colo_filter_rewriter_debug(void) ""
+colo_filter_rewriter_pkt_info(const char *func, const char *src, const char *dst, uint32_t seq, uint32_t ack, uint32_t flag) "%s: src/dst: %s/%s p: seq/ack=%u/%u flags=%x\n"
+colo_filter_rewriter_conn_offset(uint32_t offset) ": offset=%u\n"
+
### Guest events, keep at bottom
# @vaddr: Access' virtual address.