#include "qom/object.h"
#include "qemu/typedefs.h"
#include "net/queue.h"
-#include "sysemu/char.h"
+#include "chardev/char-fe.h"
#include "qemu/sockets.h"
#include "qapi-visit.h"
#include "net/colo.h"
CharBackend chr_out;
SocketReadState pri_rs;
SocketReadState sec_rs;
+ bool vnet_hdr;
/* connection list: the connections belonged to this NIC could be found
* in this list.
GHashTable *connection_track_table;
/* compare thread, a thread for each NIC */
QemuThread thread;
+
+ GMainContext *worker_context;
+ GMainLoop *compare_loop;
} CompareState;
typedef struct CompareClass {
SECONDARY_IN,
};
-static int compare_chr_send(CharBackend *out,
+static int compare_chr_send(CompareState *s,
const uint8_t *buf,
- uint32_t size);
+ uint32_t size,
+ uint32_t vnet_hdr_len);
static gint seq_sorter(Packet *a, Packet *b, gpointer data)
{
Connection *conn;
if (mode == PRIMARY_IN) {
- pkt = packet_new(s->pri_rs.buf, s->pri_rs.packet_len);
+ pkt = packet_new(s->pri_rs.buf,
+ s->pri_rs.packet_len,
+ s->pri_rs.vnet_hdr_len);
} else {
- pkt = packet_new(s->sec_rs.buf, s->sec_rs.packet_len);
+ pkt = packet_new(s->sec_rs.buf,
+ s->sec_rs.packet_len,
+ s->sec_rs.vnet_hdr_len);
}
if (parse_packet_early(pkt)) {
* return: 0 means packet same
* > 0 || < 0 means packet different
*/
-static int colo_packet_compare(Packet *ppkt, Packet *spkt)
+static int colo_packet_compare_common(Packet *ppkt, Packet *spkt, int offset)
{
- trace_colo_compare_ip_info(ppkt->size, inet_ntoa(ppkt->ip->ip_src),
- inet_ntoa(ppkt->ip->ip_dst), spkt->size,
- inet_ntoa(spkt->ip->ip_src),
- inet_ntoa(spkt->ip->ip_dst));
+ if (trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
+ char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
+
+ strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
+ strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
+ strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
+ strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
+
+ trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
+ pri_ip_dst, spkt->size,
+ sec_ip_src, sec_ip_dst);
+ }
+
+ offset = ppkt->vnet_hdr_len + offset;
if (ppkt->size == spkt->size) {
- return memcmp(ppkt->data, spkt->data, spkt->size);
+ return memcmp(ppkt->data + offset,
+ spkt->data + offset,
+ spkt->size - offset);
} else {
+ trace_colo_compare_main("Net packet size are not the same");
return -1;
}
}
int res;
trace_colo_compare_main("compare tcp");
- if (ppkt->size != spkt->size) {
- if (trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
- trace_colo_compare_main("pkt size not same");
- }
- return -1;
- }
ptcp = (struct tcphdr *)ppkt->transport_header;
stcp = (struct tcphdr *)spkt->transport_header;
spkt->ip->ip_sum = ppkt->ip->ip_sum;
}
- res = memcmp(ppkt->data + ETH_HLEN, spkt->data + ETH_HLEN,
- (spkt->size - ETH_HLEN));
+ /*
+ * Check tcp header length for tcp option field.
+ * th_off > 5 means this tcp packet have options field.
+ * The tcp options maybe always different.
+ * for example:
+ * From RFC 7323.
+ * TCP Timestamps option (TSopt):
+ * Kind: 8
+ *
+ * Length: 10 bytes
+ *
+ * +-------+-------+---------------------+---------------------+
+ * |Kind=8 | 10 | TS Value (TSval) |TS Echo Reply (TSecr)|
+ * +-------+-------+---------------------+---------------------+
+ * 1 1 4 4
+ *
+ * In this case the primary guest's timestamp always different with
+ * the secondary guest's timestamp. COLO just focus on payload,
+ * so we just need skip this field.
+ */
+ if (ptcp->th_off > 5) {
+ ptrdiff_t tcp_offset;
+
+ tcp_offset = ppkt->transport_header - (uint8_t *)ppkt->data
+ + (ptcp->th_off * 4) - ppkt->vnet_hdr_len;
+ res = colo_packet_compare_common(ppkt, spkt, tcp_offset);
+ } else if (ptcp->th_sum == stcp->th_sum) {
+ res = colo_packet_compare_common(ppkt, spkt, ETH_HLEN);
+ } else {
+ res = -1;
+ }
if (res != 0 && trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
- trace_colo_compare_pkt_info_src(inet_ntoa(ppkt->ip->ip_src),
- ntohl(stcp->th_seq),
- ntohl(stcp->th_ack),
- res, stcp->th_flags,
- spkt->size);
-
- trace_colo_compare_pkt_info_dst(inet_ntoa(ppkt->ip->ip_dst),
- ntohl(ptcp->th_seq),
- ntohl(ptcp->th_ack),
- res, ptcp->th_flags,
- ppkt->size);
+ char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
+
+ strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
+ strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
+ strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
+ strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
+
+ trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
+ pri_ip_dst, spkt->size,
+ sec_ip_src, sec_ip_dst);
+
+ trace_colo_compare_tcp_info("pri tcp packet",
+ ntohl(ptcp->th_seq),
+ ntohl(ptcp->th_ack),
+ res, ptcp->th_flags,
+ ppkt->size);
+
+ trace_colo_compare_tcp_info("sec tcp packet",
+ ntohl(stcp->th_seq),
+ ntohl(stcp->th_ack),
+ res, stcp->th_flags,
+ spkt->size);
qemu_hexdump((char *)ppkt->data, stderr,
"colo-compare ppkt", ppkt->size);
static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt)
{
int ret;
+ int network_header_length = ppkt->ip->ip_hl * 4;
trace_colo_compare_main("compare udp");
- ret = colo_packet_compare(ppkt, spkt);
+
+ /*
+ * Because of ppkt and spkt are both in the same connection,
+ * The ppkt's src ip, dst ip, src port, dst port, ip_proto all are
+ * same with spkt. In addition, IP header's Identification is a random
+ * field, we can handle it in IP fragmentation function later.
+ * COLO just concern the response net packet payload from primary guest
+ * and secondary guest are same or not, So we ignored all IP header include
+ * other field like TOS,TTL,IP Checksum. we only need to compare
+ * the ip payload here.
+ */
+ ret = colo_packet_compare_common(ppkt, spkt,
+ network_header_length + ETH_HLEN);
if (ret) {
trace_colo_compare_udp_miscompare("primary pkt size", ppkt->size);
- qemu_hexdump((char *)ppkt->data, stderr, "colo-compare", ppkt->size);
trace_colo_compare_udp_miscompare("Secondary pkt size", spkt->size);
- qemu_hexdump((char *)spkt->data, stderr, "colo-compare", spkt->size);
+ if (trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
+ qemu_hexdump((char *)ppkt->data, stderr, "colo-compare pri pkt",
+ ppkt->size);
+ qemu_hexdump((char *)spkt->data, stderr, "colo-compare sec pkt",
+ spkt->size);
+ }
}
return ret;
*/
static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt)
{
- int network_length;
+ int network_header_length = ppkt->ip->ip_hl * 4;
trace_colo_compare_main("compare icmp");
- network_length = ppkt->ip->ip_hl * 4;
- if (ppkt->size != spkt->size ||
- ppkt->size < network_length + ETH_HLEN) {
- return -1;
- }
- if (colo_packet_compare(ppkt, spkt)) {
+ /*
+ * Because of ppkt and spkt are both in the same connection,
+ * The ppkt's src ip, dst ip, src port, dst port, ip_proto all are
+ * same with spkt. In addition, IP header's Identification is a random
+ * field, we can handle it in IP fragmentation function later.
+ * COLO just concern the response net packet payload from primary guest
+ * and secondary guest are same or not, So we ignored all IP header include
+ * other field like TOS,TTL,IP Checksum. we only need to compare
+ * the ip payload here.
+ */
+ if (colo_packet_compare_common(ppkt, spkt,
+ network_header_length + ETH_HLEN)) {
trace_colo_compare_icmp_miscompare("primary pkt size",
ppkt->size);
- qemu_hexdump((char *)ppkt->data, stderr, "colo-compare",
- ppkt->size);
trace_colo_compare_icmp_miscompare("Secondary pkt size",
spkt->size);
- qemu_hexdump((char *)spkt->data, stderr, "colo-compare",
- spkt->size);
+ if (trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
+ qemu_hexdump((char *)ppkt->data, stderr, "colo-compare pri pkt",
+ ppkt->size);
+ qemu_hexdump((char *)spkt->data, stderr, "colo-compare sec pkt",
+ spkt->size);
+ }
return -1;
} else {
return 0;
static int colo_packet_compare_other(Packet *spkt, Packet *ppkt)
{
trace_colo_compare_main("compare other");
- trace_colo_compare_ip_info(ppkt->size, inet_ntoa(ppkt->ip->ip_src),
- inet_ntoa(ppkt->ip->ip_dst), spkt->size,
- inet_ntoa(spkt->ip->ip_src),
- inet_ntoa(spkt->ip->ip_dst));
- return colo_packet_compare(ppkt, spkt);
+ if (trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) {
+ char pri_ip_src[20], pri_ip_dst[20], sec_ip_src[20], sec_ip_dst[20];
+
+ strcpy(pri_ip_src, inet_ntoa(ppkt->ip->ip_src));
+ strcpy(pri_ip_dst, inet_ntoa(ppkt->ip->ip_dst));
+ strcpy(sec_ip_src, inet_ntoa(spkt->ip->ip_src));
+ strcpy(sec_ip_dst, inet_ntoa(spkt->ip->ip_dst));
+
+ trace_colo_compare_ip_info(ppkt->size, pri_ip_src,
+ pri_ip_dst, spkt->size,
+ sec_ip_src, sec_ip_dst);
+ }
+
+ return colo_packet_compare_common(ppkt, spkt, 0);
}
static int colo_old_packet_check_one(Packet *pkt, int64_t *check_time)
}
}
-static void colo_old_packet_check_one_conn(void *opaque,
- void *user_data)
+static int colo_old_packet_check_one_conn(Connection *conn,
+ void *user_data)
{
- Connection *conn = opaque;
GList *result = NULL;
int64_t check_time = REGULAR_PACKET_CHECK_MS;
if (result) {
/* do checkpoint will flush old packet */
/* TODO: colo_notify_checkpoint();*/
+ return 0;
}
+
+ return 1;
}
/*
{
CompareState *s = opaque;
- g_queue_foreach(&s->conn_list, colo_old_packet_check_one_conn, NULL);
+ /*
+ * If we find one old packet, stop finding job and notify
+ * COLO frame do checkpoint.
+ */
+ g_queue_find_custom(&s->conn_list, NULL,
+ (GCompareFunc)colo_old_packet_check_one_conn);
}
/*
}
if (result) {
- ret = compare_chr_send(&s->chr_out, pkt->data, pkt->size);
+ ret = compare_chr_send(s,
+ pkt->data,
+ pkt->size,
+ pkt->vnet_hdr_len);
if (ret < 0) {
error_report("colo_send_primary_packet failed");
}
}
}
-static int compare_chr_send(CharBackend *out,
+static int compare_chr_send(CompareState *s,
const uint8_t *buf,
- uint32_t size)
+ uint32_t size,
+ uint32_t vnet_hdr_len)
{
int ret = 0;
uint32_t len = htonl(size);
return 0;
}
- ret = qemu_chr_fe_write_all(out, (uint8_t *)&len, sizeof(len));
+ ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
if (ret != sizeof(len)) {
goto err;
}
- ret = qemu_chr_fe_write_all(out, (uint8_t *)buf, size);
+ if (s->vnet_hdr) {
+ /*
+ * We send vnet header len make other module(like filter-redirector)
+ * know how to parse net packet correctly.
+ */
+ len = htonl(vnet_hdr_len);
+ ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)&len, sizeof(len));
+ if (ret != sizeof(len)) {
+ goto err;
+ }
+ }
+
+ ret = qemu_chr_fe_write_all(&s->chr_out, (uint8_t *)buf, size);
if (ret != size) {
goto err;
}
ret = net_fill_rstate(&s->pri_rs, buf, size);
if (ret == -1) {
- qemu_chr_fe_set_handlers(&s->chr_pri_in, NULL, NULL, NULL,
+ qemu_chr_fe_set_handlers(&s->chr_pri_in, NULL, NULL, NULL, NULL,
NULL, NULL, true);
error_report("colo-compare primary_in error");
}
ret = net_fill_rstate(&s->sec_rs, buf, size);
if (ret == -1) {
- qemu_chr_fe_set_handlers(&s->chr_sec_in, NULL, NULL, NULL,
+ qemu_chr_fe_set_handlers(&s->chr_sec_in, NULL, NULL, NULL, NULL,
NULL, NULL, true);
error_report("colo-compare secondary_in error");
}
static void *colo_compare_thread(void *opaque)
{
- GMainContext *worker_context;
- GMainLoop *compare_loop;
CompareState *s = opaque;
GSource *timeout_source;
- worker_context = g_main_context_new();
+ s->worker_context = g_main_context_new();
qemu_chr_fe_set_handlers(&s->chr_pri_in, compare_chr_can_read,
- compare_pri_chr_in, NULL, s, worker_context, true);
+ compare_pri_chr_in, NULL, NULL,
+ s, s->worker_context, true);
qemu_chr_fe_set_handlers(&s->chr_sec_in, compare_chr_can_read,
- compare_sec_chr_in, NULL, s, worker_context, true);
+ compare_sec_chr_in, NULL, NULL,
+ s, s->worker_context, true);
- compare_loop = g_main_loop_new(worker_context, FALSE);
+ s->compare_loop = g_main_loop_new(s->worker_context, FALSE);
/* To kick any packets that the secondary doesn't match */
timeout_source = g_timeout_source_new(REGULAR_PACKET_CHECK_MS);
g_source_set_callback(timeout_source,
(GSourceFunc)check_old_packet_regular, s, NULL);
- g_source_attach(timeout_source, worker_context);
+ g_source_attach(timeout_source, s->worker_context);
- g_main_loop_run(compare_loop);
+ g_main_loop_run(s->compare_loop);
g_source_unref(timeout_source);
- g_main_loop_unref(compare_loop);
- g_main_context_unref(worker_context);
+ g_main_loop_unref(s->compare_loop);
+ g_main_context_unref(s->worker_context);
return NULL;
}
s->outdev = g_strdup(value);
}
+static bool compare_get_vnet_hdr(Object *obj, Error **errp)
+{
+ CompareState *s = COLO_COMPARE(obj);
+
+ return s->vnet_hdr;
+}
+
+static void compare_set_vnet_hdr(Object *obj,
+ bool value,
+ Error **errp)
+{
+ CompareState *s = COLO_COMPARE(obj);
+
+ s->vnet_hdr = value;
+}
+
static void compare_pri_rs_finalize(SocketReadState *pri_rs)
{
CompareState *s = container_of(pri_rs, CompareState, pri_rs);
if (packet_enqueue(s, PRIMARY_IN)) {
trace_colo_compare_main("primary: unsupported packet in");
- compare_chr_send(&s->chr_out, pri_rs->buf, pri_rs->packet_len);
+ compare_chr_send(s,
+ pri_rs->buf,
+ pri_rs->packet_len,
+ pri_rs->vnet_hdr_len);
} else {
/* compare connection */
g_queue_foreach(&s->conn_list, colo_compare_connection, s);
return;
}
- net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize);
- net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
+ net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize, s->vnet_hdr);
+ net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize, s->vnet_hdr);
g_queue_init(&s->conn_list);
return;
}
+static void colo_flush_packets(void *opaque, void *user_data)
+{
+ CompareState *s = user_data;
+ Connection *conn = opaque;
+ Packet *pkt = NULL;
+
+ while (!g_queue_is_empty(&conn->primary_list)) {
+ pkt = g_queue_pop_head(&conn->primary_list);
+ compare_chr_send(s,
+ pkt->data,
+ pkt->size,
+ pkt->vnet_hdr_len);
+ packet_destroy(pkt, NULL);
+ }
+ while (!g_queue_is_empty(&conn->secondary_list)) {
+ pkt = g_queue_pop_head(&conn->secondary_list);
+ packet_destroy(pkt, NULL);
+ }
+}
+
static void colo_compare_class_init(ObjectClass *oc, void *data)
{
UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc);
static void colo_compare_init(Object *obj)
{
+ CompareState *s = COLO_COMPARE(obj);
+
object_property_add_str(obj, "primary_in",
compare_get_pri_indev, compare_set_pri_indev,
NULL);
object_property_add_str(obj, "outdev",
compare_get_outdev, compare_set_outdev,
NULL);
+
+ s->vnet_hdr = false;
+ object_property_add_bool(obj, "vnet_hdr_support", compare_get_vnet_hdr,
+ compare_set_vnet_hdr, NULL);
}
static void colo_compare_finalize(Object *obj)
{
CompareState *s = COLO_COMPARE(obj);
- qemu_chr_fe_deinit(&s->chr_pri_in);
- qemu_chr_fe_deinit(&s->chr_sec_in);
- qemu_chr_fe_deinit(&s->chr_out);
+ qemu_chr_fe_deinit(&s->chr_pri_in, false);
+ qemu_chr_fe_deinit(&s->chr_sec_in, false);
+ qemu_chr_fe_deinit(&s->chr_out, false);
- g_queue_free(&s->conn_list);
+ g_main_loop_quit(s->compare_loop);
+ qemu_thread_join(&s->thread);
- if (qemu_thread_is_self(&s->thread)) {
- /* compare connection */
- g_queue_foreach(&s->conn_list, colo_compare_connection, s);
- qemu_thread_join(&s->thread);
- }
+ /* Release all unhandled packets after compare thead exited */
+ g_queue_foreach(&s->conn_list, colo_flush_packets, s);
+
+ g_queue_clear(&s->conn_list);
+ g_hash_table_destroy(s->connection_track_table);
g_free(s->pri_indev);
g_free(s->sec_indev);
g_free(s->outdev);
projects / qemu.git / blobdiff