diff options
Diffstat (limited to 'net')
| -rw-r--r-- | net/Makefile.objs | 3 | ||||
| -rw-r--r-- | net/colo-compare.c | 781 | ||||
| -rw-r--r-- | net/colo.c | 211 | ||||
| -rw-r--r-- | net/colo.h | 88 | ||||
| -rw-r--r-- | net/filter-rewriter.c | 263 | ||||
| -rw-r--r-- | net/net.c | 9 | ||||
| -rw-r--r-- | net/tap.c | 4 |
7 files changed, 1356 insertions, 3 deletions
diff --git a/net/Makefile.objs b/net/Makefile.objs index b7c22fddbf..2a80df5fa7 100644 --- a/net/Makefile.objs +++ b/net/Makefile.objs @@ -16,3 +16,6 @@ common-obj-$(CONFIG_NETMAP) += netmap.o common-obj-y += filter.o common-obj-y += filter-buffer.o common-obj-y += filter-mirror.o +common-obj-y += colo-compare.o +common-obj-y += colo.o +common-obj-y += filter-rewriter.o diff --git a/net/colo-compare.c b/net/colo-compare.c new file mode 100644 index 0000000000..22b1da19f5 --- /dev/null +++ b/net/colo-compare.c @@ -0,0 +1,781 @@ +/* + * 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 "qemu/error-report.h" +#include "trace.h" +#include "qemu-common.h" +#include "qapi/qmp/qerror.h" +#include "qapi/error.h" +#include "net/net.h" +#include "net/eth.h" +#include "qom/object_interfaces.h" +#include "qemu/iov.h" +#include "qom/object.h" +#include "qemu/typedefs.h" +#include "net/queue.h" +#include "sysemu/char.h" +#include "qemu/sockets.h" +#include "qapi-visit.h" +#include "net/colo.h" + +#define TYPE_COLO_COMPARE "colo-compare" +#define COLO_COMPARE(obj) \ + OBJECT_CHECK(CompareState, (obj), TYPE_COLO_COMPARE) + +#define COMPARE_READ_LEN_MAX NET_BUFSIZE +#define MAX_QUEUE_SIZE 1024 + +/* TODO: Should be configurable */ +#define REGULAR_PACKET_CHECK_MS 3000 + +/* + + CompareState ++ + | | + +---------------+ +---------------+ +---------------+ + |conn list +--->conn +--------->conn | + +---------------+ +---------------+ +---------------+ + | | | | | | + +---------------+ +---v----+ +---v----+ +---v----+ +---v----+ + |primary | |secondary |primary | |secondary + |packet | |packet + |packet | |packet + + +--------+ +--------+ +--------+ +--------+ + | | | | + +---v----+ +---v----+ +---v----+ +---v----+ + |primary | |secondary |primary | |secondary + |packet | |packet + |packet | |packet + + +--------+ +--------+ +--------+ +--------+ + | | | | + +---v----+ +---v----+ +---v----+ +---v----+ + |primary | |secondary |primary | |secondary + |packet | |packet + |packet | |packet + + +--------+ +--------+ +--------+ +--------+ +*/ +typedef struct CompareState { + Object parent; + + char *pri_indev; + char *sec_indev; + char *outdev; + CharDriverState *chr_pri_in; + CharDriverState *chr_sec_in; + CharDriverState *chr_out; + SocketReadState pri_rs; + SocketReadState sec_rs; + + /* connection list: the connections belonged to this NIC could be found + * in this list. + * element type: Connection + */ + GQueue conn_list; + /* hashtable to save connection */ + GHashTable *connection_track_table; + /* compare thread, a thread for each NIC */ + QemuThread thread; + /* Timer used on the primary to find packets that are never matched */ + QEMUTimer *timer; + QemuMutex timer_check_lock; +} CompareState; + +typedef struct CompareClass { + ObjectClass parent_class; +} CompareClass; + +typedef struct CompareChardevProps { + bool is_socket; +} CompareChardevProps; + +enum { + PRIMARY_IN = 0, + SECONDARY_IN, +}; + +static int compare_chr_send(CharDriverState *out, + const uint8_t *buf, + uint32_t size); + +/* + * Return 0 on success, if return -1 means the pkt + * is unsupported(arp and ipv6) and will be sent later + */ +static int packet_enqueue(CompareState *s, int mode) +{ + ConnectionKey key; + Packet *pkt = NULL; + Connection *conn; + + if (mode == PRIMARY_IN) { + pkt = packet_new(s->pri_rs.buf, s->pri_rs.packet_len); + } else { + pkt = packet_new(s->sec_rs.buf, s->sec_rs.packet_len); + } + + if (parse_packet_early(pkt)) { + packet_destroy(pkt, NULL); + pkt = NULL; + return -1; + } + fill_connection_key(pkt, &key); + + conn = connection_get(s->connection_track_table, + &key, + &s->conn_list); + + if (!conn->processing) { + g_queue_push_tail(&s->conn_list, conn); + conn->processing = true; + } + + if (mode == PRIMARY_IN) { + if (g_queue_get_length(&conn->primary_list) <= + MAX_QUEUE_SIZE) { + g_queue_push_tail(&conn->primary_list, pkt); + } else { + error_report("colo compare primary queue size too big," + "drop packet"); + } + } else { + if (g_queue_get_length(&conn->secondary_list) <= + MAX_QUEUE_SIZE) { + g_queue_push_tail(&conn->secondary_list, pkt); + } else { + error_report("colo compare secondary queue size too big," + "drop packet"); + } + } + + return 0; +} + +/* + * The IP packets sent by primary and secondary + * will be compared in here + * TODO support ip fragment, Out-Of-Order + * return: 0 means packet same + * > 0 || < 0 means packet different + */ +static int colo_packet_compare(Packet *ppkt, Packet *spkt) +{ + 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 (ppkt->size == spkt->size) { + return memcmp(ppkt->data, spkt->data, spkt->size); + } else { + return -1; + } +} + +/* + * Called from the compare thread on the primary + * for compare tcp packet + * compare_tcp copied from Dr. David Alan Gilbert's branch + */ +static int colo_packet_compare_tcp(Packet *spkt, Packet *ppkt) +{ + struct tcphdr *ptcp, *stcp; + int res; + char *sdebug, *ddebug; + + 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; + + /* + * The 'identification' field in the IP header is *very* random + * it almost never matches. Fudge this by ignoring differences in + * unfragmented packets; they'll normally sort themselves out if different + * anyway, and it should recover at the TCP level. + * An alternative would be to get both the primary and secondary to rewrite + * somehow; but that would need some sync traffic to sync the state + */ + if (ntohs(ppkt->ip->ip_off) & IP_DF) { + spkt->ip->ip_id = ppkt->ip->ip_id; + /* and the sum will be different if the IDs were different */ + spkt->ip->ip_sum = ppkt->ip->ip_sum; + } + + res = memcmp(ppkt->data + ETH_HLEN, spkt->data + ETH_HLEN, + (spkt->size - ETH_HLEN)); + + if (res != 0 && trace_event_get_state(TRACE_COLO_COMPARE_MISCOMPARE)) { + sdebug = strdup(inet_ntoa(ppkt->ip->ip_src)); + ddebug = strdup(inet_ntoa(ppkt->ip->ip_dst)); + fprintf(stderr, "%s: src/dst: %s/%s p: seq/ack=%u/%u" + " s: seq/ack=%u/%u res=%d flags=%x/%x\n", + __func__, sdebug, ddebug, + (unsigned int)ntohl(ptcp->th_seq), + (unsigned int)ntohl(ptcp->th_ack), + (unsigned int)ntohl(stcp->th_seq), + (unsigned int)ntohl(stcp->th_ack), + res, ptcp->th_flags, stcp->th_flags); + + fprintf(stderr, "Primary len = %d\n", ppkt->size); + qemu_hexdump((char *)ppkt->data, stderr, "colo-compare", ppkt->size); + fprintf(stderr, "Secondary len = %d\n", spkt->size); + qemu_hexdump((char *)spkt->data, stderr, "colo-compare", spkt->size); + + g_free(sdebug); + g_free(ddebug); + } + + return res; +} + +/* + * Called from the compare thread on the primary + * for compare udp packet + */ +static int colo_packet_compare_udp(Packet *spkt, Packet *ppkt) +{ + int ret; + + trace_colo_compare_main("compare udp"); + ret = colo_packet_compare(ppkt, spkt); + + 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); + } + + return ret; +} + +/* + * Called from the compare thread on the primary + * for compare icmp packet + */ +static int colo_packet_compare_icmp(Packet *spkt, Packet *ppkt) +{ + int network_length; + + 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)) { + 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); + return -1; + } else { + return 0; + } +} + +/* + * Called from the compare thread on the primary + * for compare other packet + */ +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); +} + +static int colo_old_packet_check_one(Packet *pkt, int64_t *check_time) +{ + int64_t now = qemu_clock_get_ms(QEMU_CLOCK_HOST); + + if ((now - pkt->creation_ms) > (*check_time)) { + trace_colo_old_packet_check_found(pkt->creation_ms); + return 0; + } else { + return 1; + } +} + +static void colo_old_packet_check_one_conn(void *opaque, + void *user_data) +{ + Connection *conn = opaque; + GList *result = NULL; + int64_t check_time = REGULAR_PACKET_CHECK_MS; + + result = g_queue_find_custom(&conn->primary_list, + &check_time, + (GCompareFunc)colo_old_packet_check_one); + + if (result) { + /* do checkpoint will flush old packet */ + /* TODO: colo_notify_checkpoint();*/ + } +} + +/* + * Look for old packets that the secondary hasn't matched, + * if we have some then we have to checkpoint to wake + * the secondary up. + */ +static void colo_old_packet_check(void *opaque) +{ + CompareState *s = opaque; + + g_queue_foreach(&s->conn_list, colo_old_packet_check_one_conn, NULL); +} + +/* + * Called from the compare thread on the primary + * for compare connection + */ +static void colo_compare_connection(void *opaque, void *user_data) +{ + CompareState *s = user_data; + Connection *conn = opaque; + Packet *pkt = NULL; + GList *result = NULL; + int ret; + + while (!g_queue_is_empty(&conn->primary_list) && + !g_queue_is_empty(&conn->secondary_list)) { + qemu_mutex_lock(&s->timer_check_lock); + pkt = g_queue_pop_tail(&conn->primary_list); + qemu_mutex_unlock(&s->timer_check_lock); + switch (conn->ip_proto) { + case IPPROTO_TCP: + result = g_queue_find_custom(&conn->secondary_list, + pkt, (GCompareFunc)colo_packet_compare_tcp); + break; + case IPPROTO_UDP: + result = g_queue_find_custom(&conn->secondary_list, + pkt, (GCompareFunc)colo_packet_compare_udp); + break; + case IPPROTO_ICMP: + result = g_queue_find_custom(&conn->secondary_list, + pkt, (GCompareFunc)colo_packet_compare_icmp); + break; + default: + result = g_queue_find_custom(&conn->secondary_list, + pkt, (GCompareFunc)colo_packet_compare_other); + break; + } + + if (result) { + ret = compare_chr_send(s->chr_out, pkt->data, pkt->size); + if (ret < 0) { + error_report("colo_send_primary_packet failed"); + } + trace_colo_compare_main("packet same and release packet"); + g_queue_remove(&conn->secondary_list, result->data); + packet_destroy(pkt, NULL); + } else { + /* + * If one packet arrive late, the secondary_list or + * primary_list will be empty, so we can't compare it + * until next comparison. + */ + trace_colo_compare_main("packet different"); + qemu_mutex_lock(&s->timer_check_lock); + g_queue_push_tail(&conn->primary_list, pkt); + qemu_mutex_unlock(&s->timer_check_lock); + /* TODO: colo_notify_checkpoint();*/ + break; + } + } +} + +static int compare_chr_send(CharDriverState *out, + const uint8_t *buf, + uint32_t size) +{ + int ret = 0; + uint32_t len = htonl(size); + + if (!size) { + return 0; + } + + ret = qemu_chr_fe_write_all(out, (uint8_t *)&len, sizeof(len)); + if (ret != sizeof(len)) { + goto err; + } + + ret = qemu_chr_fe_write_all(out, (uint8_t *)buf, size); + if (ret != size) { + goto err; + } + + return 0; + +err: + return ret < 0 ? ret : -EIO; +} + +static int compare_chr_can_read(void *opaque) +{ + return COMPARE_READ_LEN_MAX; +} + +/* + * Called from the main thread on the primary for packets + * arriving over the socket from the primary. + */ +static void compare_pri_chr_in(void *opaque, const uint8_t *buf, int size) +{ + CompareState *s = COLO_COMPARE(opaque); + int ret; + + ret = net_fill_rstate(&s->pri_rs, buf, size); + if (ret == -1) { + qemu_chr_add_handlers(s->chr_pri_in, NULL, NULL, NULL, NULL); + error_report("colo-compare primary_in error"); + } +} + +/* + * Called from the main thread on the primary for packets + * arriving over the socket from the secondary. + */ +static void compare_sec_chr_in(void *opaque, const uint8_t *buf, int size) +{ + CompareState *s = COLO_COMPARE(opaque); + int ret; + + ret = net_fill_rstate(&s->sec_rs, buf, size); + if (ret == -1) { + qemu_chr_add_handlers(s->chr_sec_in, NULL, NULL, NULL, NULL); + error_report("colo-compare secondary_in error"); + } +} + +static void *colo_compare_thread(void *opaque) +{ + GMainContext *worker_context; + GMainLoop *compare_loop; + CompareState *s = opaque; + + worker_context = g_main_context_new(); + + qemu_chr_add_handlers_full(s->chr_pri_in, compare_chr_can_read, + compare_pri_chr_in, NULL, s, worker_context); + qemu_chr_add_handlers_full(s->chr_sec_in, compare_chr_can_read, + compare_sec_chr_in, NULL, s, worker_context); + + compare_loop = g_main_loop_new(worker_context, FALSE); + + g_main_loop_run(compare_loop); + + g_main_loop_unref(compare_loop); + g_main_context_unref(worker_context); + return NULL; +} + +static char *compare_get_pri_indev(Object *obj, Error **errp) +{ + CompareState *s = COLO_COMPARE(obj); + + return g_strdup(s->pri_indev); +} + +static void compare_set_pri_indev(Object *obj, const char *value, Error **errp) +{ + CompareState *s = COLO_COMPARE(obj); + + g_free(s->pri_indev); + s->pri_indev = g_strdup(value); +} + +static char *compare_get_sec_indev(Object *obj, Error **errp) +{ + CompareState *s = COLO_COMPARE(obj); + + return g_strdup(s->sec_indev); +} + +static void compare_set_sec_indev(Object *obj, const char *value, Error **errp) +{ + CompareState *s = COLO_COMPARE(obj); + + g_free(s->sec_indev); + s->sec_indev = g_strdup(value); +} + +static char *compare_get_outdev(Object *obj, Error **errp) +{ + CompareState *s = COLO_COMPARE(obj); + + return g_strdup(s->outdev); +} + +static void compare_set_outdev(Object *obj, const char *value, Error **errp) +{ + CompareState *s = COLO_COMPARE(obj); + + g_free(s->outdev); + s->outdev = g_strdup(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); + } else { + /* compare connection */ + g_queue_foreach(&s->conn_list, colo_compare_connection, s); + } +} + +static void compare_sec_rs_finalize(SocketReadState *sec_rs) +{ + CompareState *s = container_of(sec_rs, CompareState, sec_rs); + + if (packet_enqueue(s, SECONDARY_IN)) { + trace_colo_compare_main("secondary: unsupported packet in"); + } else { + /* compare connection */ + g_queue_foreach(&s->conn_list, colo_compare_connection, s); + } +} + +static int compare_chardev_opts(void *opaque, + const char *name, const char *value, + Error **errp) +{ + CompareChardevProps *props = opaque; + + if (strcmp(name, "backend") == 0 && + strcmp(value, "socket") == 0) { + props->is_socket = true; + return 0; + } else if (strcmp(name, "host") == 0 || + (strcmp(name, "port") == 0) || + (strcmp(name, "server") == 0) || + (strcmp(name, "wait") == 0) || + (strcmp(name, "path") == 0)) { + return 0; + } else { + error_setg(errp, + "COLO-compare does not support a chardev with option %s=%s", + name, value); + return -1; + } +} + +/* + * Return 0 is success. + * Return 1 is failed. + */ +static int find_and_check_chardev(CharDriverState **chr, + char *chr_name, + Error **errp) +{ + CompareChardevProps props; + + *chr = qemu_chr_find(chr_name); + if (*chr == NULL) { + error_setg(errp, "Device '%s' not found", + chr_name); + return 1; + } + + memset(&props, 0, sizeof(props)); + if (qemu_opt_foreach((*chr)->opts, compare_chardev_opts, &props, errp)) { + return 1; + } + + if (!props.is_socket) { + error_setg(errp, "chardev \"%s\" is not a tcp socket", + chr_name); + return 1; + } + return 0; +} + +/* + * Check old packet regularly so it can watch for any packets + * that the secondary hasn't produced equivalents of. + */ +static void check_old_packet_regular(void *opaque) +{ + CompareState *s = opaque; + + timer_mod(s->timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + + REGULAR_PACKET_CHECK_MS); + /* if have old packet we will notify checkpoint */ + /* + * TODO: Make timer handler run in compare thread + * like qemu_chr_add_handlers_full. + */ + qemu_mutex_lock(&s->timer_check_lock); + colo_old_packet_check(s); + qemu_mutex_unlock(&s->timer_check_lock); +} + +/* + * Called from the main thread on the primary + * to setup colo-compare. + */ +static void colo_compare_complete(UserCreatable *uc, Error **errp) +{ + CompareState *s = COLO_COMPARE(uc); + char thread_name[64]; + static int compare_id; + + if (!s->pri_indev || !s->sec_indev || !s->outdev) { + error_setg(errp, "colo compare needs 'primary_in' ," + "'secondary_in','outdev' property set"); + return; + } else if (!strcmp(s->pri_indev, s->outdev) || + !strcmp(s->sec_indev, s->outdev) || + !strcmp(s->pri_indev, s->sec_indev)) { + error_setg(errp, "'indev' and 'outdev' could not be same " + "for compare module"); + return; + } + + if (find_and_check_chardev(&s->chr_pri_in, s->pri_indev, errp)) { + return; + } + + if (find_and_check_chardev(&s->chr_sec_in, s->sec_indev, errp)) { + return; + } + + if (find_and_check_chardev(&s->chr_out, s->outdev, errp)) { + return; + } + + qemu_chr_fe_claim_no_fail(s->chr_pri_in); + + qemu_chr_fe_claim_no_fail(s->chr_sec_in); + + qemu_chr_fe_claim_no_fail(s->chr_out); + + net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize); + net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize); + + g_queue_init(&s->conn_list); + qemu_mutex_init(&s->timer_check_lock); + + s->connection_track_table = g_hash_table_new_full(connection_key_hash, + connection_key_equal, + g_free, + connection_destroy); + + sprintf(thread_name, "colo-compare %d", compare_id); + qemu_thread_create(&s->thread, thread_name, + colo_compare_thread, s, + QEMU_THREAD_JOINABLE); + compare_id++; + + /* A regular timer to kick any packets that the secondary doesn't match */ + s->timer = timer_new_ms(QEMU_CLOCK_VIRTUAL, /* Only when guest runs */ + check_old_packet_regular, s); + timer_mod(s->timer, qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) + + REGULAR_PACKET_CHECK_MS); + + return; +} + +static void colo_compare_class_init(ObjectClass *oc, void *data) +{ + UserCreatableClass *ucc = USER_CREATABLE_CLASS(oc); + + ucc->complete = colo_compare_complete; +} + +static void colo_compare_init(Object *obj) +{ + object_property_add_str(obj, "primary_in", + compare_get_pri_indev, compare_set_pri_indev, + NULL); + object_property_add_str(obj, "secondary_in", + compare_get_sec_indev, compare_set_sec_indev, + NULL); + object_property_add_str(obj, "outdev", + compare_get_outdev, compare_set_outdev, + NULL); +} + +static void colo_compare_finalize(Object *obj) +{ + CompareState *s = COLO_COMPARE(obj); + + if (s->chr_pri_in) { + qemu_chr_add_handlers(s->chr_pri_in, NULL, NULL, NULL, NULL); + qemu_chr_fe_release(s->chr_pri_in); + } + if (s->chr_sec_in) { + qemu_chr_add_handlers(s->chr_sec_in, NULL, NULL, NULL, NULL); + qemu_chr_fe_release(s->chr_sec_in); + } + if (s->chr_out) { + qemu_chr_fe_release(s->chr_out); + } + + g_queue_free(&s->conn_list); + + if (qemu_thread_is_self(&s->thread)) { + /* compare connection */ + g_queue_foreach(&s->conn_list, colo_compare_connection, s); + qemu_thread_join(&s->thread); + } + + if (s->timer) { + timer_del(s->timer); + } + + qemu_mutex_destroy(&s->timer_check_lock); + + g_free(s->pri_indev); + g_free(s->sec_indev); + g_free(s->outdev); +} + +static const TypeInfo colo_compare_info = { + .name = TYPE_COLO_COMPARE, + .parent = TYPE_OBJECT, + .instance_size = sizeof(CompareState), + .instance_init = colo_compare_init, + .instance_finalize = colo_compare_finalize, + .class_size = sizeof(CompareClass), + .class_init = colo_compare_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } +}; + +static void register_types(void) +{ + type_register_static(&colo_compare_info); +} + +type_init(register_types); diff --git a/net/colo.c b/net/colo.c new file mode 100644 index 0000000000..6a6eacd2dc --- /dev/null +++ b/net/colo.c @@ -0,0 +1,211 @@ +/* + * 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; + 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; +} diff --git a/net/colo.h b/net/colo.h new file mode 100644 index 0000000000..7c524f3a1c --- /dev/null +++ b/net/colo.h @@ -0,0 +1,88 @@ +/* + * 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" +#include "qemu/jhash.h" +#include "qemu/timer.h" + +#define HASHTABLE_MAX_SIZE 16384 + +#ifndef IPPROTO_DCCP +#define IPPROTO_DCCP 33 +#endif + +#ifndef IPPROTO_SCTP +#define IPPROTO_SCTP 132 +#endif + +#ifndef IPPROTO_UDPLITE +#define IPPROTO_UDPLITE 136 +#endif + +typedef struct Packet { + void *data; + union { + uint8_t *network_header; + struct ip *ip; + }; + uint8_t *transport_header; + int size; + /* Time of packet creation, in wall clock ms */ + int64_t creation_ms; +} Packet; + +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; + /* 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); +int connection_key_equal(const void *opaque1, const void *opaque2); +int parse_packet_early(Packet *pkt); +void fill_connection_key(Packet *pkt, ConnectionKey *key); +void reverse_connection_key(ConnectionKey *key); +Connection *connection_new(ConnectionKey *key); +void connection_destroy(void *opaque); +Connection *connection_get(GHashTable *connection_track_table, + ConnectionKey *key, + GQueue *conn_list); +void connection_hashtable_reset(GHashTable *connection_track_table); +Packet *packet_new(const void *data, int size); +void packet_destroy(void *opaque, void *user_data); + +#endif /* QEMU_COLO_PROXY_H */ diff --git a/net/filter-rewriter.c b/net/filter-rewriter.c new file mode 100644 index 0000000000..89abe72d4e --- /dev/null +++ b/net/filter-rewriter.c @@ -0,0 +1,263 @@ +/* + * 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" +#include "net/filter.h" +#include "net/net.h" +#include "qemu-common.h" +#include "qapi/error.h" +#include "qapi/qmp/qerror.h" +#include "qapi-visit.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) + +#define TYPE_FILTER_REWRITER "filter-rewriter" + +typedef struct RewriterState { + NetFilterState parent_obj; + NetQueue *incoming_queue; + /* hashtable to save connection */ + GHashTable *connection_track_table; +} RewriterState; + +static void filter_rewriter_flush(NetFilterState *nf) +{ + RewriterState *s = FILTER_COLO_REWRITER(nf); + + if (!qemu_net_queue_flush(s->incoming_queue)) { + /* Unable to empty the queue, purge remaining packets */ + qemu_net_queue_purge(s->incoming_queue, nf->netdev); + } +} + +/* + * Return 1 on success, if return 0 means the pkt + * is not TCP packet + */ +static int is_tcp_packet(Packet *pkt) +{ + if (!parse_packet_early(pkt) && + pkt->ip->ip_p == IPPROTO_TCP) { + return 1; + } else { + return 0; + } +} + +/* 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, + const struct iovec *iov, + int iovcnt, + NetPacketSent *sent_cb) +{ + RewriterState *s = FILTER_COLO_REWRITER(nf); + Connection *conn; + ConnectionKey key; + Packet *pkt; + ssize_t size = iov_size(iov, iovcnt); + char *buf = g_malloc0(size); + + iov_to_buf(iov, iovcnt, 0, buf, size); + pkt = packet_new(buf, size); + + /* + * if we get tcp packet + * we will rewrite it to make secondary guest's + * connection established successfully + */ + if (pkt && is_tcp_packet(pkt)) { + + fill_connection_key(pkt, &key); + + if (sender == nf->netdev) { + /* + * We need make tcp TX and RX packet + * into one connection. + */ + reverse_connection_key(&key); + } + conn = connection_get(s->connection_track_table, + &key, + NULL); + + if (sender == nf->netdev) { + /* NET_FILTER_DIRECTION_TX */ + 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 */ + 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; + } + } + } + + packet_destroy(pkt, NULL); + pkt = NULL; + return 0; +} + +static void colo_rewriter_cleanup(NetFilterState *nf) +{ + RewriterState *s = FILTER_COLO_REWRITER(nf); + + /* flush packets */ + if (s->incoming_queue) { + filter_rewriter_flush(nf); + g_free(s->incoming_queue); + } +} + +static void colo_rewriter_setup(NetFilterState *nf, Error **errp) +{ + RewriterState *s = FILTER_COLO_REWRITER(nf); + + s->connection_track_table = g_hash_table_new_full(connection_key_hash, + connection_key_equal, + g_free, + connection_destroy); + s->incoming_queue = qemu_new_net_queue(qemu_netfilter_pass_to_next, nf); +} + +static void colo_rewriter_class_init(ObjectClass *oc, void *data) +{ + NetFilterClass *nfc = NETFILTER_CLASS(oc); + + nfc->setup = colo_rewriter_setup; + nfc->cleanup = colo_rewriter_cleanup; + nfc->receive_iov = colo_rewriter_receive_iov; +} + +static const TypeInfo colo_rewriter_info = { + .name = TYPE_FILTER_REWRITER, + .parent = TYPE_NETFILTER, + .class_init = colo_rewriter_class_init, + .instance_size = sizeof(RewriterState), +}; + +static void register_types(void) +{ + type_register_static(&colo_rewriter_info); +} + +type_init(register_types); diff --git a/net/net.c b/net/net.c index d51cb29882..ec984bf782 100644 --- a/net/net.c +++ b/net/net.c @@ -690,9 +690,13 @@ static ssize_t nc_sendv_compat(NetClientState *nc, const struct iovec *iov, buffer = iov[0].iov_base; offset = iov[0].iov_len; } else { - buf = g_new(uint8_t, NET_BUFSIZE); + offset = iov_size(iov, iovcnt); + if (offset > NET_BUFSIZE) { + return -1; + } + buf = g_malloc(offset); buffer = buf; - offset = iov_to_buf(iov, iovcnt, 0, buf, NET_BUFSIZE); + offset = iov_to_buf(iov, iovcnt, 0, buf, offset); } if (flags & QEMU_NET_PACKET_FLAG_RAW && nc->info->receive_raw) { @@ -1179,6 +1183,7 @@ void hmp_host_net_remove(Monitor *mon, const QDict *qdict) qemu_del_net_client(nc->peer); qemu_del_net_client(nc); + qemu_opts_del(qemu_opts_find(qemu_find_opts("net"), device)); } void netdev_add(QemuOpts *opts, Error **errp) diff --git a/net/tap.c b/net/tap.c index 6abb962efd..b6896a7b7c 100644 --- a/net/tap.c +++ b/net/tap.c @@ -857,7 +857,9 @@ free_fail: return -1; } - fd = net_bridge_run_helper(tap->helper, DEFAULT_BRIDGE_INTERFACE, + fd = net_bridge_run_helper(tap->helper, + tap->has_br ? + tap->br : DEFAULT_BRIDGE_INTERFACE, errp); if (fd == -1) { return -1; |