[Xen-devel] [PATCH v8 --for 4.6 COLO 20/25] COLO proxy: implement setup/teardown of COLO proxy module

[Yang Hongyang <yanghy@xxxxxxxxxxxxxx>]

setup/teardown of COLO proxy module.
we use netlink to communicate with proxy module.
About colo-proxy module:
https://lkml.org/lkml/2015/6/18/32
How to use:
http://wiki.xen.org/wiki/COLO_-_Coarse_Grain_Lock_Stepping

Signed-off-by: Yang Hongyang <yanghy@xxxxxxxxxxxxxx>
---
 tools/libxl/Makefile           |   1 +
 tools/libxl/libxl_colo.h       |   2 +
 tools/libxl/libxl_colo_proxy.c | 210 +++++++++++++++++++++++++++++++++++++++++
 tools/libxl/libxl_internal.h   |  12 +++
 4 files changed, 225 insertions(+)
 create mode 100644 tools/libxl/libxl_colo_proxy.c

diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
index e91ae79..d7a3540 100644
--- a/tools/libxl/Makefile
+++ b/tools/libxl/Makefile
@@ -65,6 +65,7 @@ endif
 LIBXL_OBJS-y += libxl_remus.o libxl_checkpoint_device.o libxl_remus_disk_drbd.o
 LIBXL_OBJS-y += libxl_colo_restore.o libxl_colo_save.o
 LIBXL_OBJS-y += libxl_colo_qdisk.o
+LIBXL_OBJS-y += libxl_colo_proxy.o
 
 LIBXL_OBJS-$(CONFIG_X86) += libxl_cpuid.o libxl_x86.o libxl_psr.o
 LIBXL_OBJS-$(CONFIG_ARM) += libxl_nocpuid.o libxl_arm.o libxl_libfdt_compat.o
diff --git a/tools/libxl/libxl_colo.h b/tools/libxl/libxl_colo.h
index 49a430b..46ca4cf 100644
--- a/tools/libxl/libxl_colo.h
+++ b/tools/libxl/libxl_colo.h
@@ -34,4 +34,6 @@ extern void libxl__colo_save_teardown(libxl__egc *egc,
                                       libxl__colo_save_state *css,
                                       int rc);
 
+extern int colo_proxy_setup(libxl__colo_proxy_state *cps);
+extern void colo_proxy_teardown(libxl__colo_proxy_state *cps);
 #endif
diff --git a/tools/libxl/libxl_colo_proxy.c b/tools/libxl/libxl_colo_proxy.c
new file mode 100644
index 0000000..9f1243e
--- /dev/null
+++ b/tools/libxl/libxl_colo_proxy.c
@@ -0,0 +1,210 @@
+/*
+ * Copyright (C) 2015 FUJITSU LIMITED
+ * Author: Yang Hongyang <yanghy@xxxxxxxxxxxxxx>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as published
+ * by the Free Software Foundation; version 2.1 only. with the special
+ * exception on linking described in file LICENSE.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ */
+
+#include "libxl_osdeps.h" /* must come before any other headers */
+
+#include "libxl_internal.h"
+#include "libxl_colo.h"
+#include <linux/netlink.h>
+
+#define NETLINK_COLO 28
+
+enum colo_netlink_op {
+    COLO_QUERY_CHECKPOINT = (NLMSG_MIN_TYPE + 1),
+    COLO_CHECKPOINT,
+    COLO_FAILOVER,
+    COLO_PROXY_INIT,
+    COLO_PROXY_RESET, /* UNUSED, will be used for continuous FT */
+};
+
+/* ========= colo-proxy: helper functions ========== */
+
+static int colo_proxy_send(libxl__colo_proxy_state *cps, uint8_t *buff, 
uint64_t size, int type)
+{
+    struct sockaddr_nl sa;
+    struct nlmsghdr msg;
+    struct iovec iov;
+    struct msghdr mh;
+    int ret;
+
+    STATE_AO_GC(cps->ao);
+
+    memset(&sa, 0, sizeof(sa));
+    sa.nl_family = AF_NETLINK;
+    sa.nl_pid = 0;
+    sa.nl_groups = 0;
+
+    msg.nlmsg_len = NLMSG_SPACE(0);
+    msg.nlmsg_flags = NLM_F_REQUEST;
+    if (type == COLO_PROXY_INIT) {
+        msg.nlmsg_flags |= NLM_F_ACK;
+    }
+    msg.nlmsg_seq = 0;
+    /* This is untrusty */
+    msg.nlmsg_pid = cps->index;
+    msg.nlmsg_type = type;
+
+    iov.iov_base = &msg;
+    iov.iov_len = msg.nlmsg_len;
+
+    mh.msg_name = &sa;
+    mh.msg_namelen = sizeof(sa);
+    mh.msg_iov = &iov;
+    mh.msg_iovlen = 1;
+    mh.msg_control = NULL;
+    mh.msg_controllen = 0;
+    mh.msg_flags = 0;
+
+    ret = sendmsg(cps->sock_fd, &mh, 0);
+    if (ret <= 0) {
+        LOG(ERROR, "can't send msg to kernel by netlink: %s",
+            strerror(errno));
+    }
+
+    return ret;
+}
+
+/* error: return -1, otherwise return 0 */
+static int64_t colo_proxy_recv(libxl__colo_proxy_state *cps, uint8_t **buff, 
int flags)
+{
+    struct sockaddr_nl sa;
+    struct iovec iov;
+    struct msghdr mh = {
+        .msg_name = &sa,
+        .msg_namelen = sizeof(sa),
+        .msg_iov = &iov,
+        .msg_iovlen = 1,
+    };
+    uint32_t size = 16384;
+    int64_t len = 0;
+    int ret;
+
+    STATE_AO_GC(cps->ao);
+    uint8_t *tmp = libxl__malloc(NOGC, size);
+
+    iov.iov_base = tmp;
+    iov.iov_len = size;
+next:
+   ret = recvmsg(cps->sock_fd, &mh, flags);
+    if (ret <= 0) {
+        goto out;
+    }
+
+    len += ret;
+    if (mh.msg_flags & MSG_TRUNC) {
+        size += 16384;
+        tmp = libxl__realloc(NOGC, tmp, size);
+        iov.iov_base = tmp + len;
+        iov.iov_len = size - len;
+        goto next;
+    }
+
+    *buff = tmp;
+    return len;
+
+out:
+    free(tmp);
+    *buff = NULL;
+    return ret;
+}
+
+/* ========= colo-proxy: setup and teardown ========== */
+
+int colo_proxy_setup(libxl__colo_proxy_state *cps)
+{
+    int skfd = 0;
+    struct sockaddr_nl sa;
+    struct nlmsghdr *h;
+    struct timeval tv = {0, 500000}; /* timeout for recvmsg from kernel */
+    int i = 1;
+    int ret = ERROR_FAIL;
+    uint8_t *buff = NULL;
+    int64_t size;
+
+    STATE_AO_GC(cps->ao);
+
+    skfd = socket(PF_NETLINK, SOCK_RAW, NETLINK_COLO);
+    if (skfd < 0) {
+        LOG(ERROR, "can not create a netlink socket: %s", strerror(errno));
+        goto out;
+    }
+    cps->sock_fd = skfd;
+    memset(&sa, 0, sizeof(sa));
+    sa.nl_family = AF_NETLINK;
+    sa.nl_groups = 0;
+retry:
+    sa.nl_pid = i++;
+
+    if (i > 10) {
+        LOG(ERROR, "netlink bind error");
+        goto out;
+    }
+
+    ret = bind(skfd, (struct sockaddr *)&sa, sizeof(sa));
+    if (ret < 0 && errno == EADDRINUSE) {
+        LOG(ERROR, "colo index %d has already in used", sa.nl_pid);
+        goto retry;
+    }
+
+    cps->index = sa.nl_pid;
+    ret = colo_proxy_send(cps, NULL, 0, COLO_PROXY_INIT);
+    if (ret < 0) {
+        goto out;
+    }
+    setsockopt(cps->sock_fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv));
+    ret = -1;
+    size = colo_proxy_recv(cps, &buff, 0);
+    /* disable SO_RCVTIMEO */
+    tv.tv_usec = 0;
+    setsockopt(cps->sock_fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv));
+    if (size < 0) {
+        LOG(ERROR, "Can't recv msg from kernel by netlink: %s",
+            strerror(errno));
+        goto out;
+    }
+
+    if (size) {
+        h = (struct nlmsghdr *)buff;
+
+        if (h->nlmsg_type == NLMSG_ERROR) {
+            struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h);
+            if (size - sizeof(*h) < sizeof(*err)) {
+                goto out;
+            }
+            ret = -err->error;
+            if (ret) {
+                goto out;
+            }
+        }
+    }
+
+    ret = 0;
+
+out:
+    free(buff);
+    if (ret) {
+        close(cps->sock_fd);
+        cps->sock_fd = -1;
+    }
+    return ret;
+}
+
+void colo_proxy_teardown(libxl__colo_proxy_state *cps)
+{
+    if (cps->sock_fd >= 0) {
+        close(cps->sock_fd);
+        cps->sock_fd = -1;
+    }
+}
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index 898e42c..23305f2 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3045,6 +3045,15 @@ libxl__stream_read_inuse(const libxl__stream_read_state 
*stream)
 }
 
 /*----- colo related state structure -----*/
+typedef struct libxl__colo_proxy_state libxl__colo_proxy_state;
+struct libxl__colo_proxy_state {
+    /* set by caller of colo_proxy_setup */
+    libxl__ao *ao;
+
+    int sock_fd;
+    int index;
+};
+
 typedef struct libxl__colo_save_state libxl__colo_save_state;
 struct libxl__colo_save_state {
     libxl__checkpoint_devices_state cds;
@@ -3059,6 +3068,9 @@ struct libxl__colo_save_state {
 
     /* private, used by qdisk block replication */
     bool qdisk_setuped;
+
+    /* private, used by colo-proxy */
+    libxl__colo_proxy_state cps;
 };
 
 /*----- Domain suspend (save) state structure -----*/
-- 
1.9.1


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel