All of lore.kernel.org
 help / color / mirror / Atom feed
From: Wen Congyang <wency@cn.fujitsu.com>
To: xen devel <xen-devel@lists.xen.org>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Ian Campbell <ian.campbell@citrix.com>,
	Ian Jackson <ian.jackson@eu.citrix.com>,
	Wei Liu <wei.liu2@citrix.com>
Cc: Lars Kurth <lars.kurth@citrix.com>,
	Changlong Xie <xiecl.fnst@cn.fujitsu.com>,
	Wen Congyang <wency@cn.fujitsu.com>,
	Gui Jianfeng <guijianfeng@cn.fujitsu.com>,
	Jiang Yunhong <yunhong.jiang@intel.com>,
	Dong Eddie <eddie.dong@intel.com>,
	Shriram Rajagopalan <rshriram@cs.ubc.ca>,
	Yang Hongyang <hongyang.yang@easystack.cn>
Subject: [PATCH v10 16/31] secondary vm suspend/resume/checkpoint code
Date: Mon, 22 Feb 2016 10:52:20 +0800	[thread overview]
Message-ID: <1456109555-28299-17-git-send-email-wency@cn.fujitsu.com> (raw)
In-Reply-To: <1456109555-28299-1-git-send-email-wency@cn.fujitsu.com>

Secondary vm is running in colo mode. So we will do
the following things again and again:
1. Resume secondary vm
   a. Send CHECKPOINT_SVM_READY to master.
   b. If it is not the first resume, call libxl__checkpoint_devices_preresume().
   c. If it is the first resume(resume right after live migration),
      - call libxl__xc_domain_restore_done() to build the secondary vm.
      - enable secondary vm's logdirty.
      - call libxl__domain_resume() to resume secondary vm.
      - call libxl__checkpoint_devices_setup() to setup checkpoint devices.
   d. Send CHECKPOINT_SVM_RESUMED to master.
2. Wait a new checkpoint
   a. Call libxl__checkpoint_devices_commit().
   b. Read CHECKPOINT_NEW from master.
3. Suspend secondary vm
   a. Suspend secondary vm.
   b. Call libxl__checkpoint_devices_postsuspend().
   c. Send CHECKPOINT_SVM_SUSPENDED to master.

Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Signed-off-by: Yang Hongyang <hongyang.yang@easystack.cn>
---
 tools/libxc/xc_sr_common.h       |    2 +
 tools/libxc/xc_sr_save.c         |    3 +-
 tools/libxl/Makefile             |    1 +
 tools/libxl/libxl_colo.h         |   24 +
 tools/libxl/libxl_colo_restore.c | 1038 ++++++++++++++++++++++++++++++++++++++
 tools/libxl/libxl_create.c       |   37 ++
 tools/libxl/libxl_internal.h     |   19 +
 tools/libxl/libxl_save_callout.c |    7 +-
 tools/libxl/libxl_stream_read.c  |   12 +
 tools/libxl/libxl_types.idl      |    1 +
 10 files changed, 1142 insertions(+), 2 deletions(-)
 create mode 100644 tools/libxl/libxl_colo.h
 create mode 100644 tools/libxl/libxl_colo_restore.c

diff --git a/tools/libxc/xc_sr_common.h b/tools/libxc/xc_sr_common.h
index 5d9f497..2bfed64 100644
--- a/tools/libxc/xc_sr_common.h
+++ b/tools/libxc/xc_sr_common.h
@@ -184,10 +184,12 @@ struct xc_sr_context
      * migration stream
      * 0: Plain VM
      * 1: Remus
+     * 2: COLO
      */
     enum {
         MIG_STREAM_NONE, /* plain stream */
         MIG_STREAM_REMUS,
+        MIG_STREAM_COLO,
     } migration_stream;
 
     union /* Common save or restore data. */
diff --git a/tools/libxc/xc_sr_save.c b/tools/libxc/xc_sr_save.c
index fe210cc..7393355 100644
--- a/tools/libxc/xc_sr_save.c
+++ b/tools/libxc/xc_sr_save.c
@@ -846,7 +846,8 @@ int xc_domain_save(xc_interface *xch, int io_fd, uint32_t dom,
 
     /* If altering migration_stream update this assert too. */
     assert(checkpointed_stream == MIG_STREAM_NONE ||
-           checkpointed_stream == MIG_STREAM_REMUS);
+           checkpointed_stream == MIG_STREAM_REMUS ||
+           checkpointed_stream == MIG_STREAM_COLO);
 
     /*
      * TODO: Find some time to better tweak the live migration algorithm.
diff --git a/tools/libxl/Makefile b/tools/libxl/Makefile
index 789a12e..d8612eb 100644
--- a/tools/libxl/Makefile
+++ b/tools/libxl/Makefile
@@ -65,6 +65,7 @@ LIBXL_OBJS-y += libxl_no_convert_callout.o
 endif
 
 LIBXL_OBJS-y += libxl_remus.o libxl_checkpoint_device.o libxl_remus_disk_drbd.o
+LIBXL_OBJS-y += libxl_colo_restore.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
new file mode 100644
index 0000000..8bea1a2
--- /dev/null
+++ b/tools/libxl/libxl_colo.h
@@ -0,0 +1,24 @@
+/*
+ * Copyright (C) 2014 FUJITSU LIMITED
+ * Author: Wen Congyang <wency@cn.fujitsu.com>
+ *
+ * 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.
+ */
+
+#ifndef LIBXL_COLO_H
+#define LIBXL_COLO_H
+
+extern void libxl__colo_restore_setup(libxl__egc *egc,
+                                      libxl__colo_restore_state *crs);
+extern void libxl__colo_restore_teardown(libxl__egc *egc, void *dcs_void,
+                                         int ret, int retval, int errnoval);
+
+#endif
diff --git a/tools/libxl/libxl_colo_restore.c b/tools/libxl/libxl_colo_restore.c
new file mode 100644
index 0000000..a417e6e
--- /dev/null
+++ b/tools/libxl/libxl_colo_restore.c
@@ -0,0 +1,1038 @@
+/*
+ * Copyright (C) 2014 FUJITSU LIMITED
+ * Author: Wen Congyang <wency@cn.fujitsu.com>
+ *         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"
+#include "libxl_colo.h"
+#include "libxl_sr_stream_format.h"
+
+enum {
+    LIBXL_COLO_SETUPED,
+    LIBXL_COLO_SUSPENDED,
+    LIBXL_COLO_RESUMED,
+};
+
+typedef struct libxl__colo_restore_checkpoint_state libxl__colo_restore_checkpoint_state;
+struct libxl__colo_restore_checkpoint_state {
+    libxl__domain_suspend_state dsps;
+    libxl__logdirty_switch lds;
+    libxl__colo_restore_state *crs;
+    libxl__stream_write_state sws;
+    int status;
+    bool preresume;
+    /* used for teardown */
+    int teardown_devices;
+    int saved_rc;
+    char *state_file;
+
+    void (*callback)(libxl__egc *,
+                     libxl__colo_restore_checkpoint_state *,
+                     int);
+};
+
+
+static void libxl__colo_restore_domain_resume_callback(void *data);
+static void libxl__colo_restore_domain_checkpoint_callback(void *data);
+static void libxl__colo_restore_domain_wait_checkpoint_callback(void *data);
+static void libxl__colo_restore_domain_suspend_callback(void *data);
+
+static const libxl__checkpoint_device_instance_ops *colo_restore_ops[] = {
+    NULL,
+};
+
+/* ===================== colo: common functions ===================== */
+static void colo_enable_logdirty(libxl__colo_restore_state *crs, libxl__egc *egc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    /* Convenience aliases */
+    const uint32_t domid = crs->domid;
+    libxl__logdirty_switch *const lds = &crcs->lds;
+
+    EGC_GC;
+
+    /* we need to know which pages are dirty to restore the guest */
+    if (xc_shadow_control(CTX->xch, domid,
+                          XEN_DOMCTL_SHADOW_OP_ENABLE_LOGDIRTY,
+                          NULL, 0, NULL, 0, NULL) < 0) {
+        LOG(ERROR, "cannot enable secondary vm's logdirty");
+        lds->callback(egc, lds, ERROR_FAIL);
+        return;
+    }
+
+    if (crs->hvm) {
+        libxl__domain_common_switch_qemu_logdirty(egc, domid, 1, lds);
+        return;
+    }
+
+    lds->callback(egc, lds, 0);
+}
+
+static void colo_disable_logdirty(libxl__colo_restore_state *crs,
+                                  libxl__egc *egc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    /* Convenience aliases */
+    const uint32_t domid = crs->domid;
+    libxl__logdirty_switch *const lds = &crcs->lds;
+
+    EGC_GC;
+
+    /* we need to know which pages are dirty to restore the guest */
+    if (xc_shadow_control(CTX->xch, domid, XEN_DOMCTL_SHADOW_OP_OFF,
+                          NULL, 0, NULL, 0, NULL) < 0)
+        LOG(WARN, "cannot disable secondary vm's logdirty");
+
+    if (crs->hvm) {
+        libxl__domain_common_switch_qemu_logdirty(egc, domid, 0, lds);
+        return;
+    }
+
+    lds->callback(egc, lds, 0);
+}
+
+static void colo_resume_vm(libxl__egc *egc,
+                           libxl__colo_restore_checkpoint_state *crcs,
+                           int restore_device_model)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+    int rc;
+
+    /* Convenience aliases */
+    libxl__colo_restore_state *const crs = crcs->crs;
+
+    EGC_GC;
+
+    if (!crs->saved_cb) {
+        /* TODO: sync mmu for hvm? */
+        if (restore_device_model) {
+            rc = libxl__domain_restore_device_model(gc, crs->domid,
+                                                    crcs->state_file);
+            if (rc) {
+                LOG(ERROR, "cannot restore device model for secondary vm");
+                crcs->callback(egc, crcs, rc);
+                return;
+            }
+        }
+        rc = libxl__domain_resume(gc, crs->domid, 0);
+        if (rc)
+            LOG(ERROR, "cannot resume secondary vm");
+
+        crcs->callback(egc, crcs, rc);
+        return;
+    }
+
+    /*
+     * TODO: get store gfn and console gfn
+     *  We should call the callback restore_results in
+     *  xc_domain_restore() before resuming the guest.
+     */
+    libxl__xc_domain_restore_done(egc, dcs, 0, 0, 0);
+
+    return;
+}
+
+static int init_device_subkind(libxl__checkpoint_devices_state *cds)
+{
+    /* init device subkind-specific state in the libxl ctx */
+    int rc;
+    STATE_AO_GC(cds->ao);
+
+    rc = 0;
+    return rc;
+}
+
+static void cleanup_device_subkind(libxl__checkpoint_devices_state *cds)
+{
+    /* cleanup device subkind-specific state in the libxl ctx */
+    STATE_AO_GC(cds->ao);
+}
+
+
+/* ================ colo: setup restore environment ================ */
+static void libxl__colo_domain_create_cb(libxl__egc *egc,
+                                         libxl__domain_create_state *dcs,
+                                         int rc, uint32_t domid);
+
+static int init_dsps(libxl__domain_suspend_state *dsps)
+{
+    int rc = ERROR_FAIL;
+    libxl_domain_type type;
+
+    STATE_AO_GC(dsps->ao);
+
+    libxl__xswait_init(&dsps->pvcontrol);
+    libxl__ev_evtchn_init(&dsps->guest_evtchn);
+    libxl__ev_xswatch_init(&dsps->guest_watch);
+    libxl__ev_time_init(&dsps->guest_timeout);
+
+    type = libxl__domain_type(gc, dsps->domid);
+    if (type == LIBXL_DOMAIN_TYPE_INVALID)
+        goto out;
+
+    dsps->type = type;
+
+    dsps->guest_evtchn.port = -1;
+    dsps->guest_evtchn_lockfd = -1;
+    dsps->guest_responded = 0;
+    dsps->dm_savefile = libxl__device_model_savefile(gc, dsps->domid);
+
+    /* Secondary vm is not created, so we cannot get evtchn port */
+
+    rc = 0;
+
+out:
+    return rc;
+}
+
+void libxl__colo_restore_setup(libxl__egc *egc,
+                               libxl__colo_restore_state *crs)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs;
+    int rc = ERROR_FAIL;
+
+    /* Convenience aliases */
+    libxl__srm_restore_autogen_callbacks *const callbacks =
+        &dcs->srs.shs.callbacks.restore.a;
+    const int domid = crs->domid;
+
+    STATE_AO_GC(crs->ao);
+
+    GCNEW(crcs);
+    crs->crcs = crcs;
+    crcs->crs = crs;
+
+    /* setup dsps */
+    crcs->dsps.ao = ao;
+    crcs->dsps.domid = domid;
+    if (init_dsps(&crcs->dsps))
+        goto err;
+
+    callbacks->suspend = libxl__colo_restore_domain_suspend_callback;
+    callbacks->postcopy = libxl__colo_restore_domain_resume_callback;
+    callbacks->checkpoint = libxl__colo_restore_domain_checkpoint_callback;
+    callbacks->wait_checkpoint = libxl__colo_restore_domain_wait_checkpoint_callback;
+
+    /*
+     * Secondary vm is running in colo mode, so we need to call
+     * libxl__xc_domain_restore_done() to create secondary vm.
+     * But we will exit in domain_create_cb(). So replace the
+     * callback here.
+     */
+    crs->saved_cb = dcs->callback;
+    dcs->callback = libxl__colo_domain_create_cb;
+    crcs->state_file = GCSPRINTF(LIBXL_DEVICE_MODEL_RESTORE_FILE".%d", domid);
+    crcs->status = LIBXL_COLO_SETUPED;
+
+    libxl__logdirty_init(&crcs->lds);
+    crcs->lds.ao = ao;
+
+    crcs->sws.fd = crs->send_back_fd;
+    crcs->sws.ao = ao;
+    crcs->sws.back_channel = true;
+
+    dcs->cds.concrete_data = crs;
+
+    libxl__stream_write_start(egc, &crcs->sws);
+
+    rc = 0;
+
+out:
+    crs->callback(egc, crs, rc);
+    return;
+
+err:
+    goto out;
+}
+
+static void libxl__colo_domain_create_cb(libxl__egc *egc,
+                                         libxl__domain_create_state *dcs,
+                                         int rc, uint32_t domid)
+{
+    libxl__colo_restore_checkpoint_state *crcs = dcs->crs.crcs;
+
+    crcs->callback(egc, crcs, rc);
+}
+
+
+/* ================ colo: teardown restore environment ================ */
+static void colo_restore_teardown_devices_done(libxl__egc *egc,
+    libxl__checkpoint_devices_state *cds, int rc);
+static void do_failover(libxl__egc *egc, libxl__colo_restore_state *crs);
+static void do_failover_done(libxl__egc *egc,
+                             libxl__colo_restore_checkpoint_state* crcs,
+                             int rc);
+static void colo_disable_logdirty_done(libxl__egc *egc,
+                                       libxl__logdirty_switch *lds,
+                                       int rc);
+static void libxl__colo_restore_teardown_done(libxl__egc *egc,
+                                              libxl__colo_restore_state *crs,
+                                              int rc);
+
+void libxl__colo_restore_teardown(libxl__egc *egc, void *dcs_void,
+                                  int ret, int retval, int errnoval)
+{
+    libxl__domain_create_state *dcs = dcs_void;
+    libxl__colo_restore_checkpoint_state *crcs = dcs->crs.crcs;
+    int rc = 1;
+
+    /* convenience aliases */
+    libxl__colo_restore_state *const crs = &dcs->crs;
+    EGC_GC;
+
+    if (ret == 0 && retval == 0)
+        rc = 0;
+
+    LOG(INFO, "%s", rc ? "colo fails" : "failover");
+
+    libxl__stream_write_abort(egc, &crcs->sws, 1);
+    if (crs->saved_cb) {
+        /* crcs->status is LIBXL_COLO_SETUPED */
+        dcs->srs.completion_callback = NULL;
+    }
+    libxl__xc_domain_restore_done(egc, dcs, ret, retval, errnoval);
+
+    crcs->saved_rc = rc;
+    if (!crcs->teardown_devices) {
+        colo_restore_teardown_devices_done(egc, &dcs->cds, 0);
+        return;
+    }
+
+    dcs->cds.callback = colo_restore_teardown_devices_done;
+    libxl__checkpoint_devices_teardown(egc, &dcs->cds);
+}
+
+static void colo_restore_teardown_devices_done(libxl__egc *egc,
+    libxl__checkpoint_devices_state *cds, int rc)
+{
+    libxl__colo_restore_state *crs = cds->concrete_data;
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+
+    EGC_GC;
+
+    if (rc)
+        LOG(ERROR, "COLO: failed to teardown device for guest with domid %u,"
+            " rc %d", cds->domid, rc);
+
+    if (crcs->teardown_devices)
+        cleanup_device_subkind(cds);
+
+    rc = crcs->saved_rc;
+    if (!rc) {
+        crcs->callback = do_failover_done;
+        do_failover(egc, crs);
+        return;
+    }
+
+    libxl__colo_restore_teardown_done(egc, crs, rc);
+}
+
+static void do_failover(libxl__egc *egc, libxl__colo_restore_state *crs)
+{
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    /* Convenience aliases */
+    const int status = crcs->status;
+    libxl__logdirty_switch *const lds = &crcs->lds;
+
+    EGC_GC;
+
+    switch(status) {
+    case LIBXL_COLO_SETUPED:
+        /*
+         * We will come here only when reading emulator xenstore data or
+         * emulator context fails, and libxl__xc_domain_restore_done()
+         * is not called. In this case, the migration is not finished,
+         * so we cannot do failover.
+         */
+        LOG(ERROR, "migration fails");
+        crcs->callback(egc, crcs, ERROR_FAIL);
+        return;
+    case LIBXL_COLO_SUSPENDED:
+    case LIBXL_COLO_RESUMED:
+        /* disable logdirty first */
+        lds->callback = colo_disable_logdirty_done;
+        colo_disable_logdirty(crs, egc);
+        return;
+    default:
+        LOG(ERROR, "invalid status: %d", status);
+        crcs->callback(egc, crcs, ERROR_FAIL);
+    }
+}
+
+static void do_failover_done(libxl__egc *egc,
+                             libxl__colo_restore_checkpoint_state* crcs,
+                             int rc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+
+    /* Convenience aliases */
+    libxl__colo_restore_state *const crs = crcs->crs;
+
+    EGC_GC;
+
+    if (rc)
+        LOG(ERROR, "cannot do failover");
+
+    libxl__colo_restore_teardown_done(egc, crs, rc);
+}
+
+static void colo_disable_logdirty_done(libxl__egc *egc,
+                                       libxl__logdirty_switch *lds,
+                                       int rc)
+{
+    libxl__colo_restore_checkpoint_state *crcs = CONTAINER_OF(lds, *crcs, lds);
+
+    EGC_GC;
+
+    if (rc)
+        LOG(WARN, "cannot disable logdirty");
+
+    if (crcs->status == LIBXL_COLO_SUSPENDED) {
+        /*
+         * failover when reading state from master, so no need to
+         * call libxl__domain_restore().
+         */
+        colo_resume_vm(egc, crcs, 0);
+        return;
+    }
+
+    /* If we cannot disable logdirty, we still can do failover */
+    crcs->callback(egc, crcs, 0);
+}
+
+static void libxl__colo_restore_teardown_done(libxl__egc *egc,
+                                              libxl__colo_restore_state *crs,
+                                              int rc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    EGC_GC;
+
+    /* convenience aliases */
+    const int domid = crs->domid;
+    const libxl_ctx *const ctx = libxl__gc_owner(gc);
+    xc_interface *const xch = ctx->xch;
+
+    if (!rc)
+        /* failover, no need to destroy the secondary vm */
+        goto out;
+
+    xc_domain_destroy(xch, domid);
+
+out:
+    if (crs->saved_cb) {
+        dcs->callback = crs->saved_cb;
+        crs->saved_cb = NULL;
+    }
+
+    dcs->callback(egc, dcs, rc, crs->domid);
+}
+
+/*
+ * checkpoint callbacks are called in the following order:
+ * 1. checkpoint
+ * 2. resume
+ * 3. wait checkpoint
+ * 4. suspend
+ */
+static void colo_common_write_stream_done(libxl__egc *egc,
+                                          libxl__stream_write_state *stream,
+                                          int rc);
+static void colo_common_read_stream_done(libxl__egc *egc,
+                                         libxl__stream_read_state *stream,
+                                         int rc);
+/* ======================== colo: checkpoint ======================= */
+/*
+ * Do the following things when resuming secondary vm:
+ *  1. read emulator xenstore data
+ *  2. read emulator context
+ *  3. REC_TYPE_CHECKPOINT_END
+ */
+static void libxl__colo_restore_domain_checkpoint_callback(void *data)
+{
+    libxl__save_helper_state *shs = data;
+    libxl__stream_read_state *srs = CONTAINER_OF(shs, *srs, shs);
+    libxl__domain_create_state *dcs = CONTAINER_OF(srs, *dcs, srs);
+    libxl__colo_restore_checkpoint_state *crcs = dcs->crs.crcs;
+
+    crcs->callback = NULL;
+    dcs->srs.checkpoint_callback = colo_common_read_stream_done;
+    libxl__stream_read_start_checkpoint(shs->egc, &dcs->srs);
+}
+
+
+/* ===================== colo: resume secondary vm ===================== */
+/*
+ * Do the following things when resuming secondary vm the first time:
+ *  1. resume secondary vm
+ *  2. enable log dirty
+ *  3. setup checkpoint devices
+ *  4. write CHECKPOINT_SVM_READY
+ *  5. unpause secondary vm
+ *  6. write CHECKPOINT_SVM_RESUMED
+ *
+ * Do the following things when resuming secondary vm:
+ *  1. write CHECKPOINT_SVM_READY
+ *  2. resume secondary vm
+ *  3. write CHECKPOINT_SVM_RESUMED
+ */
+static void colo_send_svm_ready(libxl__egc *egc,
+                                libxl__colo_restore_checkpoint_state *crcs);
+static void colo_send_svm_ready_done(libxl__egc *egc,
+                                     libxl__colo_restore_checkpoint_state *crcs,
+                                     int rc);
+static void colo_restore_preresume_cb(libxl__egc *egc,
+                                      libxl__checkpoint_devices_state *cds,
+                                      int rc);
+static void colo_restore_resume_vm(libxl__egc *egc,
+                                   libxl__colo_restore_checkpoint_state *crcs);
+static void colo_resume_vm_done(libxl__egc *egc,
+                                libxl__colo_restore_checkpoint_state *crcs,
+                                int rc);
+static void colo_write_svm_resumed(libxl__egc *egc,
+                                   libxl__colo_restore_checkpoint_state *crcs);
+static void colo_enable_logdirty_done(libxl__egc *egc,
+                                      libxl__logdirty_switch *lds,
+                                      int retval);
+static void colo_reenable_logdirty(libxl__egc *egc,
+                                   libxl__logdirty_switch *lds,
+                                   int rc);
+static void colo_reenable_logdirty_done(libxl__egc *egc,
+                                        libxl__logdirty_switch *lds,
+                                        int rc);
+static void colo_setup_checkpoint_devices(libxl__egc *egc,
+                                          libxl__colo_restore_state *crs);
+static void colo_restore_setup_cds_done(libxl__egc *egc,
+                                        libxl__checkpoint_devices_state *cds,
+                                        int rc);
+static void colo_unpause_svm(libxl__egc *egc,
+                             libxl__colo_restore_checkpoint_state *crcs);
+
+static void libxl__colo_restore_domain_resume_callback(void *data)
+{
+    libxl__save_helper_state *shs = data;
+    libxl__stream_read_state *srs = CONTAINER_OF(shs, *srs, shs);
+    libxl__domain_create_state *dcs = CONTAINER_OF(srs, *dcs, srs);
+    libxl__colo_restore_checkpoint_state *crcs = dcs->crs.crcs;
+
+    if (crcs->teardown_devices)
+        colo_send_svm_ready(shs->egc, crcs);
+    else
+        colo_restore_resume_vm(shs->egc, crcs);
+}
+
+static void colo_send_svm_ready(libxl__egc *egc,
+                               libxl__colo_restore_checkpoint_state *crcs)
+{
+    libxl_sr_checkpoint_state srcs = { .id = CHECKPOINT_SVM_READY };
+
+    crcs->callback = colo_send_svm_ready_done;
+    crcs->sws.checkpoint_callback = colo_common_write_stream_done;
+    libxl__stream_write_checkpoint_state(egc, &crcs->sws, &srcs);
+}
+
+static void colo_send_svm_ready_done(libxl__egc *egc,
+                                     libxl__colo_restore_checkpoint_state *crcs,
+                                     int rc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+
+    /* Convenience aliases */
+    libxl__checkpoint_devices_state *cds = &dcs->cds;
+
+    if (!crcs->preresume) {
+        crcs->preresume = true;
+        colo_unpause_svm(egc, crcs);
+        return;
+    }
+
+    cds->callback = colo_restore_preresume_cb;
+    libxl__checkpoint_devices_preresume(egc, cds);
+}
+
+static void colo_restore_preresume_cb(libxl__egc *egc,
+                                      libxl__checkpoint_devices_state *cds,
+                                      int rc)
+{
+    libxl__colo_restore_state *crs = cds->concrete_data;
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    /* Convenience aliases */
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "preresume fails");
+        goto out;
+    }
+
+    colo_restore_resume_vm(egc, crcs);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+static void colo_restore_resume_vm(libxl__egc *egc,
+                                   libxl__colo_restore_checkpoint_state *crcs)
+{
+
+    crcs->callback = colo_resume_vm_done;
+    colo_resume_vm(egc, crcs, 1);
+}
+
+static void colo_resume_vm_done(libxl__egc *egc,
+                                libxl__colo_restore_checkpoint_state *crcs,
+                                int rc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+
+    /* Convenience aliases */
+    libxl__colo_restore_state *const crs = crcs->crs;
+    libxl__logdirty_switch *const lds = &crcs->lds;
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "cannot resume secondary vm");
+        goto out;
+    }
+
+    crcs->status = LIBXL_COLO_RESUMED;
+
+    /* avoid calling stream->completion_callback() more than once */
+    if (crs->saved_cb) {
+        dcs->callback = crs->saved_cb;
+        crs->saved_cb = NULL;
+
+        dcs->srs.completion_callback = NULL;
+
+        lds->callback = colo_enable_logdirty_done;
+        colo_enable_logdirty(crs, egc);
+        return;
+    }
+
+    colo_write_svm_resumed(egc, crcs);
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+static void colo_write_svm_resumed(libxl__egc *egc,
+                                   libxl__colo_restore_checkpoint_state *crcs)
+{
+    libxl_sr_checkpoint_state srcs = { .id = CHECKPOINT_SVM_RESUMED };
+
+    crcs->callback = NULL;
+    crcs->sws.checkpoint_callback = colo_common_write_stream_done;
+    libxl__stream_write_checkpoint_state(egc, &crcs->sws, &srcs);
+}
+
+static void colo_enable_logdirty_done(libxl__egc *egc,
+                                      libxl__logdirty_switch *lds,
+                                      int rc)
+{
+    libxl__colo_restore_checkpoint_state *crcs = CONTAINER_OF(lds, *crcs, lds);
+
+    /* Convenience aliases */
+    libxl__colo_restore_state *const crs = crcs->crs;
+
+    EGC_GC;
+
+    if (rc) {
+        /*
+         * log-dirty already enabled? There's no test op,
+         * so attempt to disable then reenable it
+         */
+        lds->callback = colo_reenable_logdirty;
+        colo_disable_logdirty(crs, egc);
+        return;
+    }
+
+    colo_setup_checkpoint_devices(egc, crs);
+}
+
+static void colo_reenable_logdirty(libxl__egc *egc,
+                                   libxl__logdirty_switch *lds,
+                                   int rc)
+{
+    libxl__colo_restore_checkpoint_state *crcs = CONTAINER_OF(lds, *crcs, lds);
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+
+    /* Convenience aliases */
+    libxl__colo_restore_state *const crs = crcs->crs;
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "cannot enable logdirty");
+        goto out;
+    }
+
+    lds->callback = colo_reenable_logdirty_done;
+    colo_enable_logdirty(crs, egc);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+static void colo_reenable_logdirty_done(libxl__egc *egc,
+                                        libxl__logdirty_switch *lds,
+                                        int rc)
+{
+    libxl__colo_restore_checkpoint_state *crcs = CONTAINER_OF(lds, *crcs, lds);
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+
+    /* Convenience aliases */
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "cannot enable logdirty");
+        goto out;
+    }
+
+    colo_setup_checkpoint_devices(egc, crcs->crs);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+/*
+ * We cannot setup checkpoint devices in libxl__colo_restore_setup(),
+ * because the guest is not ready.
+ */
+static void colo_setup_checkpoint_devices(libxl__egc *egc,
+                                          libxl__colo_restore_state *crs)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    /* Convenience aliases */
+    libxl__checkpoint_devices_state *cds = &dcs->cds;
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    STATE_AO_GC(crs->ao);
+
+    /* TODO: disk/nic support */
+    cds->device_kind_flags = 0;
+    cds->callback = colo_restore_setup_cds_done;
+    cds->ao = ao;
+    cds->domid = crs->domid;
+    cds->ops = colo_restore_ops;
+
+    if (init_device_subkind(cds))
+        goto out;
+
+    crcs->teardown_devices = 1;
+
+    libxl__checkpoint_devices_setup(egc, cds);
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+static void colo_restore_setup_cds_done(libxl__egc *egc,
+                                        libxl__checkpoint_devices_state *cds,
+                                        int rc)
+{
+    libxl__colo_restore_state *crs = cds->concrete_data;
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    /* Convenience aliases */
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "COLO: failed to setup device for guest with domid %u",
+            cds->domid);
+        goto out;
+    }
+
+    colo_send_svm_ready(egc, crcs);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+static void colo_unpause_svm(libxl__egc *egc,
+                             libxl__colo_restore_checkpoint_state *crcs)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+    int rc;
+
+    /* Convenience aliases */
+    const uint32_t domid = crcs->crs->domid;
+    libxl__save_helper_state *const shs = &dcs->srs.shs;
+
+    EGC_GC;
+
+    /* We have enabled secondary vm's logdirty, so we can unpause it now */
+    rc = libxl_domain_unpause(CTX, domid);
+    if (rc) {
+        LOG(ERROR, "cannot unpause secondary vm");
+        goto out;
+    }
+
+    colo_write_svm_resumed(egc, crcs);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, shs, 0);
+}
+
+
+/* ===================== colo: wait new checkpoint ===================== */
+static void colo_restore_commit_cb(libxl__egc *egc,
+                                   libxl__checkpoint_devices_state *cds,
+                                   int rc);
+static void colo_stream_read_done(libxl__egc *egc,
+                                  libxl__colo_restore_checkpoint_state *crcs,
+                                  int real_size);
+
+static void libxl__colo_restore_domain_wait_checkpoint_callback(void *data)
+{
+    libxl__save_helper_state *shs = data;
+    libxl__stream_read_state *srs = CONTAINER_OF(shs, *srs, shs);
+    libxl__domain_create_state *dcs = CONTAINER_OF(srs, *dcs, srs);
+
+    /* Convenience aliases */
+    libxl__checkpoint_devices_state *cds = &dcs->cds;
+
+    cds->callback = colo_restore_commit_cb;
+    libxl__checkpoint_devices_commit(shs->egc, cds);
+}
+
+static void colo_restore_commit_cb(libxl__egc *egc,
+                                   libxl__checkpoint_devices_state *cds,
+                                   int rc)
+{
+    libxl__colo_restore_state *crs = cds->concrete_data;
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "commit fails");
+        goto out;
+    }
+
+    crcs->callback = colo_stream_read_done;
+    dcs->srs.checkpoint_callback = colo_common_read_stream_done;
+    libxl__stream_read_checkpoint_state(egc, &dcs->srs);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dcs->srs.shs, 0);
+}
+
+static void colo_stream_read_done(libxl__egc *egc,
+                                  libxl__colo_restore_checkpoint_state *crcs,
+                                  int id)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+    int ok = 0;
+
+    EGC_GC;
+
+    if (id != CHECKPOINT_NEW) {
+        LOG(ERROR, "invalid section: %d", id);
+        goto out;
+    }
+
+    ok = 1;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dcs->srs.shs, ok);
+}
+
+
+/* ===================== colo: suspend secondary vm ===================== */
+/*
+ * Do the following things when resuming secondary vm:
+ *  1. suspend secondary vm
+ *  2. send CHECKPOINT_SVM_SUSPENDED
+ */
+static void colo_suspend_vm_done(libxl__egc *egc,
+                                 libxl__domain_suspend_state *dsps,
+                                 int ok);
+static void colo_restore_postsuspend_cb(libxl__egc *egc,
+                                        libxl__checkpoint_devices_state *cds,
+                                        int rc);
+
+static void libxl__colo_restore_domain_suspend_callback(void *data)
+{
+    libxl__save_helper_state *shs = data;
+    libxl__stream_read_state *srs = CONTAINER_OF(shs, *srs, shs);
+    libxl__domain_create_state *dcs = CONTAINER_OF(srs, *dcs, srs);
+    libxl__colo_restore_checkpoint_state *crcs = dcs->crs.crcs;
+
+    STATE_AO_GC(dcs->ao);
+
+    /* Convenience aliases */
+    libxl__domain_suspend_state *const dsps = &crcs->dsps;
+
+    /* suspend secondary vm */
+    dsps->callback_common_done = colo_suspend_vm_done;
+
+    libxl__domain_suspend(shs->egc, dsps);
+}
+
+static void colo_suspend_vm_done(libxl__egc *egc,
+                                 libxl__domain_suspend_state *dsps,
+                                 int rc)
+{
+    libxl__colo_restore_checkpoint_state *crcs = CONTAINER_OF(dsps, *crcs, dsps);
+    libxl__colo_restore_state *crs = crcs->crs;
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+
+    /* Convenience aliases */
+    libxl__checkpoint_devices_state *cds = &dcs->cds;
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "cannot suspend secondary vm");
+        goto out;
+    }
+
+    crcs->status = LIBXL_COLO_SUSPENDED;
+
+    cds->callback = colo_restore_postsuspend_cb;
+    libxl__checkpoint_devices_postsuspend(egc, cds);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dcs->srs.shs, !rc);
+}
+
+static void colo_restore_postsuspend_cb(libxl__egc *egc,
+                                        libxl__checkpoint_devices_state *cds,
+                                        int rc)
+{
+    libxl__colo_restore_state *crs = cds->concrete_data;
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+    libxl__colo_restore_checkpoint_state *crcs = crs->crcs;
+    libxl_sr_checkpoint_state srcs = { .id = CHECKPOINT_SVM_SUSPENDED };
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "postsuspend fails");
+        goto out;
+    }
+
+    crcs->callback = NULL;
+    crcs->sws.checkpoint_callback = colo_common_write_stream_done;
+    libxl__stream_write_checkpoint_state(egc, &crcs->sws, &srcs);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dcs->srs.shs, !rc);
+}
+
+
+/* ===================== colo: common callback ===================== */
+static void colo_common_write_stream_done(libxl__egc *egc,
+                                          libxl__stream_write_state *stream,
+                                          int rc)
+{
+    libxl__colo_restore_checkpoint_state *crcs =
+        CONTAINER_OF(stream, *crcs, sws);
+    libxl__domain_create_state *dcs = CONTAINER_OF(crcs->crs, *dcs, crs);
+    int ok;
+
+    EGC_GC;
+
+    if (rc < 0) {
+        /* TODO: it may be a internal error, but we don't know */
+        LOG(ERROR, "sending data fails");
+        ok = 2;
+        goto out;
+    }
+
+    if (!crcs->callback) {
+        /* Everythins is OK */
+        ok = 1;
+        goto out;
+    }
+
+    crcs->callback(egc, crcs, 0);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dcs->srs.shs, ok);
+}
+
+static void colo_common_read_stream_done(libxl__egc *egc,
+                                         libxl__stream_read_state *stream,
+                                         int rc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(stream, *dcs, srs);
+    libxl__colo_restore_checkpoint_state *crcs = dcs->crs.crcs;
+    int ok;
+
+    EGC_GC;
+
+    if (rc < 0) {
+        /* TODO: it may be a internal error, but we don't know */
+        LOG(ERROR, "reading data fails");
+        ok = 2;
+        goto out;
+    }
+
+    if (!crcs->callback) {
+        /* Everythins is OK */
+        ok = 1;
+        goto out;
+    }
+
+    /* rc contains the id */
+    crcs->callback(egc, crcs, rc);
+
+    return;
+
+out:
+    libxl__xc_domain_saverestore_async_callback_done(egc, &dcs->srs.shs, ok);
+}
diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c
index fc746fb..39458b7 100644
--- a/tools/libxl/libxl_create.c
+++ b/tools/libxl/libxl_create.c
@@ -19,6 +19,7 @@
 
 #include "libxl_internal.h"
 #include "libxl_arch.h"
+#include "libxl_colo.h"
 
 #include <xc_dom.h>
 #include <xenguest.h>
@@ -981,6 +982,23 @@ static void domcreate_console_available(libxl__egc *egc,
                                         dcs->aop_console_how.for_event));
 }
 
+static void libxl__colo_restore_setup_done(libxl__egc *egc,
+                                           libxl__colo_restore_state *crs,
+                                           int rc)
+{
+    libxl__domain_create_state *dcs = CONTAINER_OF(crs, *dcs, crs);
+
+    EGC_GC;
+
+    if (rc) {
+        LOG(ERROR, "colo restore setup fails: %d", rc);
+        domcreate_stream_done(egc, &dcs->srs, rc);
+        return;
+    }
+
+    libxl__stream_read_start(egc, &dcs->srs);
+}
+
 static void domcreate_bootloader_done(libxl__egc *egc,
                                       libxl__bootloader_state *bl,
                                       int rc)
@@ -994,6 +1012,8 @@ static void domcreate_bootloader_done(libxl__egc *egc,
     const int restore_fd = dcs->restore_fd;
     libxl__domain_build_state *const state = &dcs->build_state;
     const int checkpointed_stream = dcs->restore_params.checkpointed_stream;
+    libxl__colo_restore_state *const crs = &dcs->crs;
+    libxl_domain_build_info *const info = &d_config->b_info;
 
     if (rc) {
         domcreate_rebuild_done(egc, dcs, rc);
@@ -1022,6 +1042,13 @@ static void domcreate_bootloader_done(libxl__egc *egc,
 
     /* Restore */
 
+    /* COLO only supports HVM now */
+    if (info->type != LIBXL_DOMAIN_TYPE_HVM &&
+        checkpointed_stream == LIBXL_CHECKPOINTED_STREAM_COLO) {
+        rc = ERROR_FAIL;
+        goto out;
+    }
+
     rc = libxl__build_pre(gc, domid, d_config, state);
     if (rc)
         goto out;
@@ -1035,6 +1062,16 @@ static void domcreate_bootloader_done(libxl__egc *egc,
 
     if (restore_fd >= 0) {
         switch (checkpointed_stream) {
+        case LIBXL_CHECKPOINTED_STREAM_COLO:
+            /* colo restore setup */
+            crs->ao = ao;
+            crs->domid = domid;
+            crs->send_back_fd = dcs->send_back_fd;
+            crs->recv_fd = restore_fd;
+            crs->hvm = (info->type == LIBXL_DOMAIN_TYPE_HVM);
+            crs->callback = libxl__colo_restore_setup_done;
+            libxl__colo_restore_setup(egc, crs);
+            break;
         case LIBXL_CHECKPOINTED_STREAM_REMUS:
             libxl__remus_restore_setup(egc, dcs);
             /* fall through */
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index 33b658d..b9ca81c 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -3470,6 +3470,23 @@ libxl__stream_read_inuse(const libxl__stream_read_state *stream)
     return stream->running;
 }
 
+/* colo related structure */
+typedef struct libxl__colo_restore_state libxl__colo_restore_state;
+typedef void libxl__colo_callback(libxl__egc *,
+                                  libxl__colo_restore_state *, int rc);
+struct libxl__colo_restore_state {
+    /* must set by caller of libxl__colo_(setup|teardown) */
+    libxl__ao *ao;
+    uint32_t domid;
+    int send_back_fd;
+    int recv_fd;
+    int hvm;
+    libxl__colo_callback *callback;
+
+    /* private, colo restore checkpoint state */
+    libxl__domain_create_cb *saved_cb;
+    void *crcs;
+};
 
 struct libxl__domain_create_state {
     /* filled in by user */
@@ -3486,6 +3503,8 @@ struct libxl__domain_create_state {
     /* private to domain_create */
     int guest_domid;
     libxl__domain_build_state build_state;
+    libxl__colo_restore_state crs;
+    libxl__checkpoint_devices_state cds;
     libxl__bootloader_state bl;
     libxl__stub_dm_spawn_state dmss;
         /* If we're not doing stubdom, we use only dmss.dm,
diff --git a/tools/libxl/libxl_save_callout.c b/tools/libxl/libxl_save_callout.c
index 0d6949a..b1810b2 100644
--- a/tools/libxl/libxl_save_callout.c
+++ b/tools/libxl/libxl_save_callout.c
@@ -15,6 +15,7 @@
 #include "libxl_osdeps.h"
 
 #include "libxl_internal.h"
+#include "libxl_colo.h"
 
 /* stream_fd is as from the caller (eventually, the application).
  * It may be 0, 1 or 2, in which case we need to dup it elsewhere.
@@ -68,7 +69,11 @@ void libxl__xc_domain_restore(libxl__egc *egc, libxl__domain_create_state *dcs,
     shs->ao = ao;
     shs->domid = domid;
     shs->recv_callback = libxl__srm_callout_received_restore;
-    shs->completion_callback = libxl__xc_domain_restore_done;
+    if (dcs->restore_params.checkpointed_stream ==
+                                                LIBXL_CHECKPOINTED_STREAM_COLO)
+        shs->completion_callback = libxl__colo_restore_teardown;
+    else
+        shs->completion_callback = libxl__xc_domain_restore_done;
     shs->caller_state = dcs;
     shs->need_results = 1;
 
diff --git a/tools/libxl/libxl_stream_read.c b/tools/libxl/libxl_stream_read.c
index 5d980d9..d6bd2fe 100644
--- a/tools/libxl/libxl_stream_read.c
+++ b/tools/libxl/libxl_stream_read.c
@@ -846,6 +846,18 @@ void libxl__xc_domain_restore_done(libxl__egc *egc, void *dcs_void,
      */
     if (libxl__stream_read_inuse(stream)) {
         switch (checkpointed_stream) {
+        case LIBXL_CHECKPOINTED_STREAM_COLO:
+            if (stream->completion_callback) {
+                /*
+                 * restore, just build the secondary vm, don't close
+                 * the stream
+                 */
+                stream->completion_callback(egc, stream, 0);
+            } else {
+                /* failover, just close the stream */
+                stream_complete(egc, stream, 0);
+            }
+            break;
         case LIBXL_CHECKPOINTED_STREAM_REMUS:
             /*
              * Failover from primary. Domain state is currently at a
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
index 632c009..33f4a90 100644
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -232,6 +232,7 @@ libxl_hdtype = Enumeration("hdtype", [
 libxl_checkpointed_stream = Enumeration("checkpointed_stream", [
     (0, "NONE"),
     (1, "REMUS"),
+    (2, "COLO"),
     ])
 
 #
-- 
2.5.0

  parent reply	other threads:[~2016-02-22  2:52 UTC|newest]

Thread overview: 70+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-02-22  2:52 [PATCH v10 00/31] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wen Congyang
2016-02-22  2:52 ` [PATCH v10 01/31] tools/libxl: introduce libxl__domain_restore_device_model to load qemu state Wen Congyang
2016-02-25 15:53   ` Wei Liu
2016-02-26  1:55     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 02/31] tools/libxl: introduce libxl__domain_common_switch_qemu_logdirty() Wen Congyang
2016-02-22  2:52 ` [PATCH v10 03/31] tools/libxl: Add back channel to allow migration target send data back Wen Congyang
2016-02-22  2:52 ` [PATCH v10 04/31] tools/libxl: Introduce new helper function dup_fd_helper() Wen Congyang
2016-02-25 15:53   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 05/31] tools/libx{l, c}: add back channel to libxc Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 06/31] docs: add colo readme Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 07/31] docs/libxl: Introduce CHECKPOINT_CONTEXT to support migration v2 colo streams Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-26  1:59     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 08/31] libxc/migration: Specification update for DIRTY_PFN_LIST records Wen Congyang
2016-02-22  2:52 ` [PATCH v10 09/31] libxc/migration: export read_record for common use Wen Congyang
2016-02-22  2:52 ` [PATCH v10 10/31] tools/libxl: add back channel support to write stream Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-26  2:11     ` Wen Congyang
2016-03-02 15:02       ` Wei Liu
2016-03-03  1:25         ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 11/31] tools/libxl: write checkpoint_state records into the stream Wen Congyang
2016-02-22  2:52 ` [PATCH v10 12/31] tools/libxl: add back channel support to read stream Wen Congyang
2016-02-25 15:54   ` Wei Liu
2016-02-26  2:16     ` Wen Congyang
2016-03-02 15:03       ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 13/31] tools/libxl: handle checkpoint_state records in a libxl migration v2 " Wen Congyang
2016-02-22  2:52 ` [PATCH v10 14/31] tools/libx{l, c}: introduce wait_checkpoint callback Wen Congyang
2016-02-22  2:52 ` [PATCH v10 15/31] tools/libx{l, c}: add postcopy/suspend callback to restore side Wen Congyang
2016-02-22  2:52 ` Wen Congyang [this message]
2016-02-25 15:56   ` [PATCH v10 16/31] secondary vm suspend/resume/checkpoint code Wei Liu
2016-02-26  2:30     ` Wen Congyang
2016-03-01 10:06     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 17/31] primary " Wen Congyang
2016-02-25 15:57   ` Wei Liu
2016-02-26  2:32     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 18/31] libxc/restore: support COLO restore Wen Congyang
2016-02-25 15:57   ` Wei Liu
2016-02-26  2:33     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 19/31] libxc/restore: send dirty pfn list to primary when checkpoint under colo Wen Congyang
2016-02-22  2:52 ` [PATCH v10 20/31] send store gfn and console gfn to xl before resuming secondary vm Wen Congyang
2016-02-22  2:52 ` [PATCH v10 21/31] libxc/save: support COLO save Wen Congyang
2016-02-25 15:58   ` Wei Liu
2016-02-26  2:35     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 22/31] implement the cmdline for COLO Wen Congyang
2016-03-02 15:03   ` Wei Liu
2016-03-03  1:30     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 23/31] COLO: introduce new API to prepare/start/do/get_error/stop replication Wen Congyang
2016-03-02 15:03   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 24/31] Support colo mode for qemu disk Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-03-03  1:40     ` Wen Congyang
2016-02-22  2:52 ` [PATCH v10 25/31] COLO: use qemu block replication Wen Congyang
2016-03-02 15:03   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 26/31] COLO proxy: implement setup/teardown of COLO proxy module Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-03-11 22:25   ` Konrad Rzeszutek Wilk
2016-03-14  9:13     ` Wen Congyang
2016-03-22  3:40       ` Changlong Xie
2016-02-22  2:52 ` [PATCH v10 27/31] COLO proxy: preresume, postresume and checkpoint Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 28/31] COLO nic: implement COLO nic subkind Wen Congyang
2016-03-02 15:04   ` Wei Liu
2016-02-22  2:52 ` [PATCH v10 29/31] setup and control colo proxy on primary side Wen Congyang
2016-02-22  2:52 ` [PATCH v10 30/31] setup and control colo proxy on secondary side Wen Congyang
2016-02-22  2:52 ` [PATCH v10 31/31] cmdline switches and config vars to control colo-proxy Wen Congyang
2016-03-02 15:05   ` Wei Liu
2016-03-03  1:41     ` Wen Congyang
2016-02-25 16:05 ` [PATCH v10 00/31] COarse-grain LOck-stepping Virtual Machines for Non-stop Service Wei Liu

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=1456109555-28299-17-git-send-email-wency@cn.fujitsu.com \
    --to=wency@cn.fujitsu.com \
    --cc=andrew.cooper3@citrix.com \
    --cc=eddie.dong@intel.com \
    --cc=guijianfeng@cn.fujitsu.com \
    --cc=hongyang.yang@easystack.cn \
    --cc=ian.campbell@citrix.com \
    --cc=ian.jackson@eu.citrix.com \
    --cc=konrad.wilk@oracle.com \
    --cc=lars.kurth@citrix.com \
    --cc=rshriram@cs.ubc.ca \
    --cc=wei.liu2@citrix.com \
    --cc=xen-devel@lists.xen.org \
    --cc=xiecl.fnst@cn.fujitsu.com \
    --cc=yunhong.jiang@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.