diff mbox

[v13,22/26] COLO proxy: implement setup/teardown/preresume/postresume/checkpoint

Message ID 1458888273-7469-23-git-send-email-xiecl.fnst@cn.fujitsu.com (mailing list archive)
State New, archived
Headers show

Commit Message

Changlong Xie March 25, 2016, 6:44 a.m. UTC
From: Wen Congyang <wency@cn.fujitsu.com>

setup/teardown/preresume/postresume/checkpoint of COLO proxy module.
we use netlink to communicate with proxy module.
About colo-proxy module:
http://www.spinics.net/lists/netdev/msg333520.html
https://github.com/wencongyang/colo-proxy
How to use:
http://wiki.xen.org/wiki/COLO_-_Coarse_Grain_Lock_Stepping

Signed-off-by: Yang Hongyang <hongyang.yang@easystack.cn>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Changlong Xie <xiecl.fnst@cn.fujitsu.com>
Acked-by: Ian Jackson <ian.jackson@eu.citrix.com>
---
 tools/libxl/Makefile           |   1 +
 tools/libxl/libxl_colo.h       |  32 +++++
 tools/libxl/libxl_colo_proxy.c | 277 +++++++++++++++++++++++++++++++++++++++++
 tools/libxl/libxl_internal.h   |   3 +
 4 files changed, 313 insertions(+)
 create mode 100644 tools/libxl/libxl_colo_proxy.c
diff mbox

Patch

diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
index 701c069..72f3b1a 100644
--- a/tools/libxl/Makefile
+++ b/tools/libxl/Makefile
@@ -67,6 +67,7 @@  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 90345f4..a529ce8 100644
--- a/tools/libxl/libxl_colo.h
+++ b/tools/libxl/libxl_colo.h
@@ -16,21 +16,43 @@ 
 #ifndef LIBXL_COLO_H
 #define LIBXL_COLO_H
 
+#include <linux/netlink.h>
+
 struct libxl__ao;
 struct libxl__egc;
 struct libxl__colo_save_state;
 struct libxl__checkpoint_devices_state;
 
+/* Consistent with the new COLO netlink channel in kernel side */
+#define NETLINK_COLO 28
+
 enum {
     LIBXL_COLO_SETUPED,
     LIBXL_COLO_SUSPENDED,
     LIBXL_COLO_RESUMED,
 };
 
+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 */
+};
+
 typedef struct libxl__colo_qdisk {
     bool setuped;
 } libxl__colo_qdisk;
 
+typedef struct libxl__colo_proxy_state libxl__colo_proxy_state;
+struct libxl__colo_proxy_state {
+    /* set by caller of colo_proxy_setup */
+    struct libxl__ao *ao;
+
+    int sock_fd;
+    int index;
+};
+
 typedef struct libxl__domain_create_state libxl__domain_create_state;
 typedef void libxl__domain_create_cb(struct libxl__egc *egc,
                                      libxl__domain_create_state *dcs,
@@ -58,6 +80,9 @@  struct libxl__colo_restore_state {
     bool qdisk_setuped;
     const char *host;
     const char *port;
+
+    /* private, used by colo-proxy */
+    libxl__colo_proxy_state cps;
 };
 
 int init_subkind_qdisk(struct libxl__checkpoint_devices_state *cds);
@@ -73,4 +98,11 @@  extern void libxl__colo_save_setup(struct libxl__egc *egc,
 extern void libxl__colo_save_teardown(struct libxl__egc *egc,
                                       struct 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);
+extern void colo_proxy_preresume(libxl__colo_proxy_state *cps);
+extern void colo_proxy_postresume(libxl__colo_proxy_state *cps);
+extern int colo_proxy_checkpoint(libxl__colo_proxy_state *cps,
+                                 unsigned int timeout_us);
+
 #endif
diff --git a/tools/libxl/libxl_colo_proxy.c b/tools/libxl/libxl_colo_proxy.c
new file mode 100644
index 0000000..991bd0d
--- /dev/null
+++ b/tools/libxl/libxl_colo_proxy.c
@@ -0,0 +1,277 @@ 
+/*
+ * Copyright (C) 2016 FUJITSU LIMITED
+ * Author: Yang Hongyang <hongyang.yang@easystack.cn>
+ *
+ * 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"
+
+/* ========= 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;
+    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,
+                               unsigned int timeout_us)
+{
+    struct sockaddr_nl sa;
+    struct iovec iov;
+    struct msghdr mh = {
+        .msg_name = &sa,
+        .msg_namelen = sizeof(sa),
+        .msg_iov = &iov,
+        .msg_iovlen = 1,
+    };
+    struct timeval tv;
+    uint32_t size = 16384;
+    int64_t len = 0;
+    int ret;
+
+    STATE_AO_GC(cps->ao);
+    uint8_t *tmp = libxl__malloc(NOGC, size);
+
+    if (timeout_us) {
+        tv.tv_sec = timeout_us / 1000000;
+        tv.tv_usec = timeout_us % 1000000;
+        setsockopt(cps->sock_fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv));
+    }
+
+    iov.iov_base = tmp;
+    iov.iov_len = size;
+next:
+    ret = recvmsg(cps->sock_fd, &mh, 0);
+    if (ret <= 0) {
+        if (errno != EAGAIN && errno != EWOULDBLOCK)
+            LOGE(ERROR, "can't recv msg from kernel by netlink");
+        goto err;
+    }
+
+    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;
+    ret = len;
+    goto out;
+
+err:
+    free(tmp);
+    *buff = NULL;
+
+out:
+    if (timeout_us) {
+        tv.tv_sec = 0;
+        tv.tv_usec = 0;
+        setsockopt(cps->sock_fd, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv));
+    }
+    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;
+    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;
+    } else if (ret < 0) {
+        LOG(ERROR, "netlink bind error");
+        goto out;
+    }
+
+    cps->index = sa.nl_pid;
+    ret = colo_proxy_send(cps, NULL, 0, COLO_PROXY_INIT);
+    if (ret < 0)
+        goto out;
+
+    /* receive ack */
+    size = colo_proxy_recv(cps, &buff, 500000);
+    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) {
+            /* ack's type is NLMSG_ERROR */
+            struct nlmsgerr *err = (struct nlmsgerr *)NLMSG_DATA(h);
+
+            if (size - sizeof(*h) < sizeof(*err)) {
+                LOG(ERROR, "NLMSG_LENGTH is too short");
+                goto out;
+            }
+
+            if (err->error) {
+                LOG(ERROR, "NLMSG_ERROR contains error %d", err->error);
+                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;
+    }
+}
+
+/* ========= colo-proxy: preresume, postresume and checkpoint ========== */
+
+void colo_proxy_preresume(libxl__colo_proxy_state *cps)
+{
+    colo_proxy_send(cps, NULL, 0, COLO_CHECKPOINT);
+    /* TODO: need to handle if the call fails... */
+}
+
+void colo_proxy_postresume(libxl__colo_proxy_state *cps)
+{
+    /* nothing to do... */
+}
+
+typedef struct colo_msg {
+    bool is_checkpoint;
+} colo_msg;
+
+/*
+ * Return value:
+ * -1: error
+ *  0: no checkpoint event is received before timeout
+ *  1: do checkpoint
+ */
+int colo_proxy_checkpoint(libxl__colo_proxy_state *cps,
+                          unsigned int timeout_us)
+{
+    uint8_t *buff;
+    int64_t size;
+    struct nlmsghdr *h;
+    struct colo_msg *m;
+    int ret = -1;
+
+    STATE_AO_GC(cps->ao);
+
+    size = colo_proxy_recv(cps, &buff, timeout_us);
+
+    /* timeout, return no checkpoint message. */
+    if (size <= 0)
+        return 0;
+
+    h = (struct nlmsghdr *) buff;
+
+    if (h->nlmsg_type == NLMSG_ERROR) {
+        LOG(ERROR, "receive NLMSG_ERROR");
+        goto out;
+    }
+
+    if (h->nlmsg_len < NLMSG_LENGTH(sizeof(*m))) {
+        LOG(ERROR, "NLMSG_LENGTH is too short");
+        goto out;
+    }
+
+    m = NLMSG_DATA(h);
+
+    ret = m->is_checkpoint ? 1 : 0;
+
+out:
+    free(buff);
+    return ret;
+}
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index c3366d7..8f02222 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3216,6 +3216,9 @@  struct libxl__colo_save_state {
     /* private, used by qdisk block replication */
     bool qdisk_used;
     bool qdisk_setuped;
+
+    /* private, used by colo-proxy */
+    libxl__colo_proxy_state cps;
 };
 
 typedef struct libxl__logdirty_switch {