qemu-devel
[Top][All Lists]
Advanced

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Qemu-devel] [PULL 05/27] net/colo.c: add colo.c to define and handle pa


From: Jason Wang
Subject: [Qemu-devel] [PULL 05/27] net/colo.c: add colo.c to define and handle packet
Date: Mon, 26 Sep 2016 16:59:13 +0800

From: Zhang Chen <address@hidden>

The net/colo.c is used by colo-compare and filter-rewriter.
this can share common data structure like net packet,
and other functions.

Signed-off-by: Zhang Chen <address@hidden>
Signed-off-by: Li Zhijian <address@hidden>
Signed-off-by: Wen Congyang <address@hidden>
Signed-off-by: Jason Wang <address@hidden>
---
 net/Makefile.objs  |   1 +
 net/colo-compare.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++++++--
 net/colo.c         |  86 ++++++++++++++++++++++++++++++++++++++++
 net/colo.h         |  37 +++++++++++++++++
 trace-events       |   6 +++
 5 files changed, 240 insertions(+), 4 deletions(-)
 create mode 100644 net/colo.c
 create mode 100644 net/colo.h

diff --git a/net/Makefile.objs b/net/Makefile.objs
index ba92f73..beb504b 100644
--- a/net/Makefile.objs
+++ b/net/Makefile.objs
@@ -17,3 +17,4 @@ 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
diff --git a/net/colo-compare.c b/net/colo-compare.c
index dc5f70c..cea9b27 100644
--- a/net/colo-compare.c
+++ b/net/colo-compare.c
@@ -14,6 +14,7 @@
 
 #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"
@@ -26,13 +27,34 @@
 #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
-
+/*
+  + 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;
 
@@ -44,6 +66,9 @@ typedef struct CompareState {
     CharDriverState *chr_out;
     SocketReadState pri_rs;
     SocketReadState sec_rs;
+
+    /* hashtable to save connection */
+    GHashTable *connection_track_table;
 } CompareState;
 
 typedef struct CompareClass {
@@ -54,6 +79,76 @@ 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)
+{
+    Packet *pkt = NULL;
+
+    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;
+    }
+    /* TODO: get connection key from pkt */
+
+    /*
+     * TODO: use connection key get conn from
+     * connection_track_table
+     */
+
+    /*
+     * TODO: insert pkt to it's conn->primary_list
+     * or conn->secondary_list
+     */
+
+    return 0;
+}
+
+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 char *compare_get_pri_indev(Object *obj, Error **errp)
 {
     CompareState *s = COLO_COMPARE(obj);
@@ -101,12 +196,21 @@ static void compare_set_outdev(Object *obj, const char 
*value, Error **errp)
 
 static void compare_pri_rs_finalize(SocketReadState *pri_rs)
 {
-    /* if packet_enqueue pri pkt failed we will send unsupported packet */
+    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);
+    }
 }
 
 static void compare_sec_rs_finalize(SocketReadState *sec_rs)
 {
-    /* if packet_enqueue sec pkt failed we will notify trace */
+    CompareState *s = container_of(sec_rs, CompareState, sec_rs);
+
+    if (packet_enqueue(s, SECONDARY_IN)) {
+        trace_colo_compare_main("secondary: unsupported packet in");
+    }
 }
 
 static int compare_chardev_opts(void *opaque,
@@ -204,6 +308,8 @@ static void colo_compare_complete(UserCreatable *uc, Error 
**errp)
     net_socket_rs_init(&s->pri_rs, compare_pri_rs_finalize);
     net_socket_rs_init(&s->sec_rs, compare_sec_rs_finalize);
 
+    /* use g_hash_table_new_full() to new a hashtable */
+
     return;
 }
 
diff --git a/net/colo.c b/net/colo.c
new file mode 100644
index 0000000..8582175
--- /dev/null
+++ b/net/colo.c
@@ -0,0 +1,86 @@
+/*
+ * 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 <address@hidden>
+ *
+ * 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"
+
+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;
+}
+
+Packet *packet_new(const void *data, int size)
+{
+    Packet *pkt = g_slice_new(Packet);
+
+    pkt->data = g_memdup(data, size);
+    pkt->size = size;
+
+    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);
+}
diff --git a/net/colo.h b/net/colo.h
new file mode 100644
index 0000000..e211eda
--- /dev/null
+++ b/net/colo.h
@@ -0,0 +1,37 @@
+/*
+ * 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 <address@hidden>
+ *
+ * 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"
+
+#define HASHTABLE_MAX_SIZE 16384
+
+typedef struct Packet {
+    void *data;
+    union {
+        uint8_t *network_header;
+        struct ip *ip;
+    };
+    uint8_t *transport_header;
+    int size;
+} Packet;
+
+int parse_packet_early(Packet *pkt);
+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/trace-events b/trace-events
index 8d59631..9b4186f 100644
--- a/trace-events
+++ b/trace-events
@@ -139,6 +139,12 @@ memory_region_subpage_write(int cpu_index, void *mr, 
uint64_t offset, uint64_t v
 memory_region_tb_read(int cpu_index, uint64_t addr, uint64_t value, unsigned 
size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
 memory_region_tb_write(int cpu_index, uint64_t addr, uint64_t value, unsigned 
size) "cpu %d addr %#"PRIx64" value %#"PRIx64" size %u"
 
+# net/colo.c
+colo_proxy_main(const char *chr) ": %s"
+
+# net/colo-compare.c
+colo_compare_main(const char *chr) ": %s"
+
 ### Guest events, keep at bottom
 
 # @vaddr: Access' virtual address.
-- 
2.7.4




reply via email to

[Prev in Thread] Current Thread [Next in Thread]