diff mbox series

[v3] libxl: fix migration of PV and PVH domUs with and without qemu

Message ID 20190510100416.16658-1-olaf@aepfle.de (mailing list archive)
State Superseded
Headers show
Series [v3] libxl: fix migration of PV and PVH domUs with and without qemu | expand

Commit Message

Olaf Hering May 10, 2019, 10:04 a.m. UTC
If a domU has a qemu-xen instance attached, it is required to call qemus
"xen-save-devices-state" method. Without it, the receiving side of a PV or
PVH migration may be unable to lock the image:

xen be: qdisk-51712: xen be: qdisk-51712: error: Failed to get "write" lock
error: Failed to get "write" lock
xen be: qdisk-51712: xen be: qdisk-51712: initialise() failed
initialise() failed

To fix this bug, libxl__domain_suspend_device_model() and
libxl__domain_resume_device_model() have to be called not only for HVM,
but also if the active device_model is QEMU_XEN.

Unfortunately, libxl__domain_build_info_setdefault() hardcodes
b_info->device_model_version to QEMU_XEN if it does not know it any
better. As a result libxl__device_model_version_running() will return
incorrect values. This breaks domUs without a device_model.
libxl__qmp_stop() would wait 10 seconds in qmp_open() for a qemu that
will never appear. During this long timeframe the domU remains in state
paused on the sending side. As a result network connections may be
dropped. Once this bug is fixed as well, by just removing the assumption
that every domU has a QEMU_XEN, there is no code to actually initialise
b_info->device_model_version.

There is a helper function libxl__need_xenpv_qemu(), which is used in
various places to decide if a device_model has to be spawned. This
function can not be used as is, just to fill device_model_version,
because store_libxl_entry() was already called earlier.

Create a new function to set device_model_version. Move existing code
from libxl__domain_build_info_setdefault() to cover the HVM case. Add
new code to cover non-HVM case, use libxl__need_xenpv_qemu() to set
device_model_version.

Update libxl__spawn_stub_dm() and initiate_domain_create() to call the
new function prior libxl__domain_build_info_setdefault() because
device_mode_version is expected to be initialzed.
libxl_domain_need_memory() needs no update because it does not have a
d_config available anyway, and the callers provide a populated b_info.

Introduce LIBXL_DEVICE_MODEL_VERSION_NONE_REQUIRED for PV and PVH that
have no need for a device_model to make the state explicit.

v03:
- rearrange code to make sure device_model_version is initialized before
  store_libxl_entry() is called
v02:
- update wording in a comment
- remove stale goto in domcreate_launch_dm
- initialize ret in libxl__need_xenpv_qemu

Signed-off-by: Olaf Hering <olaf@aepfle.de>
Cc: Roger Pau Monné <roger.pau@citrix.com>
Cc: Anthony PERARD <anthony.perard@citrix.com>
---

v3 not runtime tested


 tools/libxl/libxl_create.c      | 95 +++++++++++++++++++++++++++--------------
 tools/libxl/libxl_dm.c          |  2 +
 tools/libxl/libxl_dom_suspend.c |  8 +++-
 tools/libxl/libxl_internal.h    |  2 +
 tools/libxl/libxl_types.idl     |  1 +
 5 files changed, 73 insertions(+), 35 deletions(-)

Comments

Olaf Hering May 10, 2019, 1:49 p.m. UTC | #1
Am Fri, 10 May 2019 12:04:16 +0200
schrieb Olaf Hering <olaf@aepfle.de>:

> v3 not runtime tested

The initialization for device_model_stubdomain must be moved to the new function.


Olaf
diff mbox series

Patch

diff --git a/tools/libxl/libxl_create.c b/tools/libxl/libxl_create.c
index 89fe80fc9c..73ee66a67e 100644
--- a/tools/libxl/libxl_create.c
+++ b/tools/libxl/libxl_create.c
@@ -27,6 +27,62 @@ 
 
 #include <xen-xsm/flask/flask.h>
 
+int libxl__domain_set_device_model(libxl__gc *gc, libxl_domain_config *d_config)
+{
+    libxl_domain_build_info *b_info = &d_config->b_info;
+    int ret;
+
+    if (b_info->device_model_version)
+        return 0;
+
+    switch (b_info->type) {
+    case LIBXL_DOMAIN_TYPE_HVM:
+        if (libxl_defbool_val(b_info->device_model_stubdomain)) {
+            b_info->device_model_version =
+                LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
+        } else {
+            b_info->device_model_version = libxl__default_device_model(gc);
+        }
+        break;
+    default:
+        ret = libxl__need_xenpv_qemu(gc, d_config);
+        switch (ret) {
+        case 1:
+            d_config->b_info.device_model_version =
+                LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN;
+            break;
+        case 0:
+            d_config->b_info.device_model_version =
+                LIBXL_DEVICE_MODEL_VERSION_NONE_REQUIRED;
+            break;
+        default:
+            LOGE(ERROR, "Unable to determine QEMU requisite");
+            return ERROR_FAIL;
+        }
+    }
+
+    if (b_info->device_model_version == LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN) {
+        const char *dm;
+
+        dm = libxl__domain_device_model(gc, b_info);
+        ret = access(dm, X_OK);
+        if (ret < 0) {
+            /* qemu-xen unavailable, use qemu-xen-traditional */
+            if (errno == ENOENT) {
+                LOGE(INFO, "qemu-xen is unavailable"
+                     ", using qemu-xen-traditional instead");
+                b_info->device_model_version =
+                    LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
+            } else {
+                LOGE(ERROR, "qemu-xen access error");
+                return ERROR_FAIL;
+            }
+        }
+    }
+
+    return 0;
+}
+
 int libxl__domain_create_info_setdefault(libxl__gc *gc,
                                          libxl_domain_create_info *c_info)
 {
@@ -86,39 +142,6 @@  int libxl__domain_build_info_setdefault(libxl__gc *gc,
         !b_info->device_model_ssidref)
         b_info->device_model_ssidref = SECINITSID_DOMDM;
 
-    if (!b_info->device_model_version) {
-        if (b_info->type == LIBXL_DOMAIN_TYPE_HVM) {
-            if (libxl_defbool_val(b_info->device_model_stubdomain)) {
-                b_info->device_model_version =
-                    LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
-            } else {
-                b_info->device_model_version = libxl__default_device_model(gc);
-            }
-        } else {
-            b_info->device_model_version =
-                LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN;
-        }
-        if (b_info->device_model_version
-                == LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN) {
-            const char *dm;
-
-            dm = libxl__domain_device_model(gc, b_info);
-            rc = access(dm, X_OK);
-            if (rc < 0) {
-                /* qemu-xen unavailable, use qemu-xen-traditional */
-                if (errno == ENOENT) {
-                    LOGE(INFO, "qemu-xen is unavailable"
-                         ", using qemu-xen-traditional instead");
-                    b_info->device_model_version =
-                        LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN_TRADITIONAL;
-                } else {
-                    LOGE(ERROR, "qemu-xen access error");
-                    return ERROR_FAIL;
-                }
-            }
-        }
-    }
-
     if (b_info->blkdev_start == NULL)
         b_info->blkdev_start = libxl__strdup(NOGC, "xvda");
 
@@ -938,6 +961,12 @@  static void initiate_domain_create(libxl__egc *egc,
         goto error_out;
     }
 
+    ret = libxl__domain_set_device_model(gc, d_config);
+    if (ret) {
+        LOGD(ERROR, domid, "Unable to set domain device model");
+        goto error_out;
+    }
+
     ret = libxl__domain_create_info_setdefault(gc, &d_config->c_info);
     if (ret) {
         LOGD(ERROR, domid, "Unable to set domain create info defaults");
diff --git a/tools/libxl/libxl_dm.c b/tools/libxl/libxl_dm.c
index 2f19786bdd..086e566311 100644
--- a/tools/libxl/libxl_dm.c
+++ b/tools/libxl/libxl_dm.c
@@ -2168,6 +2168,8 @@  void libxl__spawn_stub_dm(libxl__egc *egc, libxl__stub_dm_spawn_state *sdss)
     dm_config->c_info.run_hotplug_scripts =
         guest_config->c_info.run_hotplug_scripts;
 
+    ret = libxl__domain_set_device_model(gc, dm_config);
+    if (ret) goto out;
     ret = libxl__domain_create_info_setdefault(gc, &dm_config->c_info);
     if (ret) goto out;
     ret = libxl__domain_build_info_setdefault(gc, &dm_config->b_info);
diff --git a/tools/libxl/libxl_dom_suspend.c b/tools/libxl/libxl_dom_suspend.c
index d1af3a6573..c492fe5dd1 100644
--- a/tools/libxl/libxl_dom_suspend.c
+++ b/tools/libxl/libxl_dom_suspend.c
@@ -379,7 +379,9 @@  static void domain_suspend_common_guest_suspended(libxl__egc *egc,
     libxl__ev_xswatch_deregister(gc, &dsps->guest_watch);
     libxl__ev_time_deregister(gc, &dsps->guest_timeout);
 
-    if (dsps->type == LIBXL_DOMAIN_TYPE_HVM) {
+    if (dsps->type == LIBXL_DOMAIN_TYPE_HVM ||
+        libxl__device_model_version_running(gc, dsps->domid) ==
+        LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN) {
         dsps->callback_device_model_done = domain_suspend_common_done;
         libxl__domain_suspend_device_model(egc, dsps); /* must be last */
         return;
@@ -459,7 +461,9 @@  int libxl__domain_resume(libxl__gc *gc, uint32_t domid, int suspend_cancel)
         goto out;
     }
 
-    if (type == LIBXL_DOMAIN_TYPE_HVM) {
+    if (type == LIBXL_DOMAIN_TYPE_HVM ||
+        libxl__device_model_version_running(gc, domid) ==
+        LIBXL_DEVICE_MODEL_VERSION_QEMU_XEN) {
         rc = libxl__domain_resume_device_model(gc, domid);
         if (rc) {
             LOGD(ERROR, domid, "failed to resume device model:%d", rc);
diff --git a/tools/libxl/libxl_internal.h b/tools/libxl/libxl_internal.h
index 44e0221284..25f113404b 100644
--- a/tools/libxl/libxl_internal.h
+++ b/tools/libxl/libxl_internal.h
@@ -1374,6 +1374,8 @@  _hidden int libxl__device_nextid(libxl__gc *gc, uint32_t domid,
 _hidden int libxl__resolve_domid(libxl__gc *gc, const char *name,
                                  uint32_t *domid);
 
+_hidden int libxl__domain_set_device_model(libxl__gc *gc,
+                                           libxl_domain_config *d_config);
 /*
  * For each aggregate type which can be used as an input we provide:
  *
diff --git a/tools/libxl/libxl_types.idl b/tools/libxl/libxl_types.idl
index cb4702fd7a..7d75bd3850 100644
--- a/tools/libxl/libxl_types.idl
+++ b/tools/libxl/libxl_types.idl
@@ -106,6 +106,7 @@  libxl_device_model_version = Enumeration("device_model_version", [
     (0, "UNKNOWN"),
     (1, "QEMU_XEN_TRADITIONAL"), # Historical qemu-xen device model (qemu-dm)
     (2, "QEMU_XEN"),             # Upstream based qemu-xen device model
+    (3, "NONE_REQUIRED"),
     ])
 
 libxl_console_type = Enumeration("console_type", [