- Devel - libvirt List Archives

[libvirt] [PATCH] nodedev: Add new module node_device_util
by Erik Skultety 12 Nov '18

12 Nov '18

There's a lot of stuff going on in src/conf/nodedev_conf which not always has to do anything with config, so even though we're trying, we're not really consistent in putting only parser/formatter related stuff here like we do for domains. So, start the cleanup simply by adding a new module to the nodedev driver and put a few helper APIs which want to open a secondary driver connection in there (similar to storage_util module). Signed-off-by: Erik Skultety <eskultet(a)redhat.com> --- I verified the build with debian 9, centos 7, fedora 28, rawhide, and freebsd 11 src/conf/Makefile.inc.am | 1 + src/conf/node_device_conf.c | 199 ----------------------- src/conf/node_device_conf.h | 11 -- src/conf/virstorageobj.c | 1 + src/libvirt_private.syms | 8 +- src/node_device/Makefile.inc.am | 17 +- src/node_device/node_device_driver.c | 1 + src/node_device/node_device_util.c | 229 +++++++++++++++++++++++++++ src/node_device/node_device_util.h | 35 ++++ src/storage/Makefile.inc.am | 1 + src/storage/storage_backend_scsi.c | 1 + 11 files changed, 290 insertions(+), 214 deletions(-) create mode 100644 src/node_device/node_device_util.c create mode 100644 src/node_device/node_device_util.h diff --git a/src/conf/Makefile.inc.am b/src/conf/Makefile.inc.am index af23810640..7cb6c29d70 100644 --- a/src/conf/Makefile.inc.am +++ b/src/conf/Makefile.inc.am @@ -163,6 +163,7 @@ libvirt_la_BUILT_LIBADD += libvirt_conf.la libvirt_conf_la_SOURCES = $(CONF_SOURCES) libvirt_conf_la_CFLAGS = \ -I$(srcdir)/conf \ + -I$(srcdir)/node_device \ $(AM_CFLAGS) \ $(NULL) libvirt_conf_la_LDFLAGS = $(AM_LDFLAGS) diff --git a/src/conf/node_device_conf.c b/src/conf/node_device_conf.c index 03bd794dc0..74a7bc3933 100644 --- a/src/conf/node_device_conf.c +++ b/src/conf/node_device_conf.c @@ -2220,205 +2220,6 @@ virNodeDevCapsDefFree(virNodeDevCapsDefPtr caps) } -/* virNodeDeviceGetParentName - * @conn: Connection pointer - * @nodedev_name: Node device to lookup - * - * Lookup the node device by name and return the parent name - * - * Returns parent name on success, caller is responsible for freeing; - * otherwise, returns NULL on failure - */ -char * -virNodeDeviceGetParentName(virConnectPtr conn, - const char *nodedev_name) -{ - virNodeDevicePtr device = NULL; - char *parent; - - if (!(device = virNodeDeviceLookupByName(conn, nodedev_name))) { - virReportError(VIR_ERR_XML_ERROR, - _("Cannot find '%s' in node device database"), - nodedev_name); - return NULL; - } - - ignore_value(VIR_STRDUP(parent, virNodeDeviceGetParent(device))); - virObjectUnref(device); - - return parent; -} - - -/** - * @fchost: Pointer to vHBA adapter - * - * Create a vHBA for Storage. This code accomplishes this via searching - * through the sysfs for scsi_host/fc_host in order to first ensure some - * vHBA doesn't already exist for the requested wwnn/wwpn (e.g. an unmanaged - * vHBA) and to search for the parent vport capable scsi_host by name, - * wwnn/wwpn, or fabric_wwn (if provided). If no parent is provided, then - * a vport capable scsi_host will be selected. - * - * Returns vHBA name on success, NULL on failure with an error message set - */ -char * -virNodeDeviceCreateVport(virStorageAdapterFCHostPtr fchost) -{ - unsigned int parent_host; - char *name = NULL; - char *parent_hoststr = NULL; - bool skip_capable_check = false; - - VIR_DEBUG("parent='%s', wwnn='%s' wwpn='%s'", - NULLSTR(fchost->parent), fchost->wwnn, fchost->wwpn); - - if (fchost->parent) { - if (VIR_STRDUP(parent_hoststr, fchost->parent) < 0) - goto cleanup; - } else if (fchost->parent_wwnn && fchost->parent_wwpn) { - if (!(parent_hoststr = virVHBAGetHostByWWN(NULL, fchost->parent_wwnn, - fchost->parent_wwpn))) { - virReportError(VIR_ERR_XML_ERROR, "%s", - _("cannot find parent using provided wwnn/wwpn")); - goto cleanup; - } - } else if (fchost->parent_fabric_wwn) { - if (!(parent_hoststr = - virVHBAGetHostByFabricWWN(NULL, fchost->parent_fabric_wwn))) { - virReportError(VIR_ERR_XML_ERROR, "%s", - _("cannot find parent using provided fabric_wwn")); - goto cleanup; - } - } else { - if (!(parent_hoststr = virVHBAFindVportHost(NULL))) { - virReportError(VIR_ERR_XML_ERROR, "%s", - _("'parent' for vHBA not specified, and " - "cannot find one on this host")); - goto cleanup; - } - skip_capable_check = true; - } - - if (virSCSIHostGetNumber(parent_hoststr, &parent_host) < 0) - goto cleanup; - - /* NOTE: - * We do not save the parent_hoststr in fchost->parent since - * we could be writing out the 'def' to the saved XML config. - * If we wrote out the name in the XML, then future starts would - * always use the same parent rather than finding the "best available" - * parent. Besides we have a way to determine the parent based on - * the 'name' field. - */ - if (!skip_capable_check && !virVHBAPathExists(NULL, parent_host)) { - virReportError(VIR_ERR_XML_ERROR, - _("parent '%s' specified for vHBA does not exist"), - parent_hoststr); - goto cleanup; - } - - if (virVHBAManageVport(parent_host, fchost->wwpn, fchost->wwnn, - VPORT_CREATE) < 0) - goto cleanup; - - /* Let's ensure the device was created */ - virWaitForDevices(); - if (!(name = virVHBAGetHostByWWN(NULL, fchost->wwnn, fchost->wwpn))) { - ignore_value(virVHBAManageVport(parent_host, fchost->wwpn, fchost->wwnn, - VPORT_DELETE)); - goto cleanup; - } - - cleanup: - VIR_FREE(parent_hoststr); - return name; -} - - -/** - * @conn: Connection pointer - * @fchost: Pointer to vHBA adapter - * - * As long as the vHBA is being managed, search for the scsi_host via the - * provided wwnn/wwpn and then find the corresponding parent scsi_host in - * order to send the delete request. - * - * Returns 0 on success, -1 on failure - */ -int -virNodeDeviceDeleteVport(virConnectPtr conn, - virStorageAdapterFCHostPtr fchost) -{ - char *name = NULL; - char *scsi_host_name = NULL; - unsigned int parent_host; - char *vhba_parent = NULL; - int ret = -1; - - VIR_DEBUG("conn=%p parent='%s', managed='%d' wwnn='%s' wwpn='%s'", - conn, NULLSTR(fchost->parent), fchost->managed, - fchost->wwnn, fchost->wwpn); - - /* If we're not managing the deletion of the vHBA, then just return */ - if (fchost->managed != VIR_TRISTATE_BOOL_YES) - return 0; - - /* Find our vHBA by searching the fc_host sysfs tree for our wwnn/wwpn */ - if (!(name = virVHBAGetHostByWWN(NULL, fchost->wwnn, fchost->wwpn))) { - virReportError(VIR_ERR_INTERNAL_ERROR, - _("Failed to find fc_host for wwnn='%s' and wwpn='%s'"), - fchost->wwnn, fchost->wwpn); - goto cleanup; - } - - if (virAsprintf(&scsi_host_name, "scsi_%s", name) < 0) - goto cleanup; - - /* If at startup time we provided a parent, then use that to - * get the parent_host value; otherwise, we have to determine - * the parent scsi_host which we did not save at startup time - */ - if (fchost->parent) { - /* Someone provided a parent string at startup time that - * was the same as the scsi_host - meaning we have a pool - * backed to an HBA, so there won't be a vHBA to delete */ - if (STREQ(scsi_host_name, fchost->parent)) { - ret = 0; - goto cleanup; - } - - if (virSCSIHostGetNumber(fchost->parent, &parent_host) < 0) - goto cleanup; - } else { - if (!(vhba_parent = virNodeDeviceGetParentName(conn, scsi_host_name))) - goto cleanup; - - /* If the parent is not a scsi_host, then this is a pool backed - * directly to an HBA and there's no vHBA to remove - so we're done */ - if (!STRPREFIX(vhba_parent, "scsi_host")) { - ret = 0; - goto cleanup; - } - - if (virSCSIHostGetNumber(vhba_parent, &parent_host) < 0) - goto cleanup; - } - - if (virVHBAManageVport(parent_host, fchost->wwpn, fchost->wwnn, - VPORT_DELETE) < 0) - goto cleanup; - - ret = 0; - - cleanup: - VIR_FREE(name); - VIR_FREE(vhba_parent); - VIR_FREE(scsi_host_name); - return ret; -} - - int virNodeDeviceUpdateCaps(virNodeDeviceDefPtr def) { diff --git a/src/conf/node_device_conf.h b/src/conf/node_device_conf.h index 685ae30347..fde239183d 100644 --- a/src/conf/node_device_conf.h +++ b/src/conf/node_device_conf.h @@ -367,17 +367,6 @@ virNodeDevCapsDefFree(virNodeDevCapsDefPtr caps); VIR_CONNECT_LIST_NODE_DEVICES_CAP_MDEV | \ VIR_CONNECT_LIST_NODE_DEVICES_CAP_CCW_DEV) -char * -virNodeDeviceGetParentName(virConnectPtr conn, - const char *nodedev_name); - -char * -virNodeDeviceCreateVport(virStorageAdapterFCHostPtr fchost); - -int -virNodeDeviceDeleteVport(virConnectPtr conn, - virStorageAdapterFCHostPtr fchost); - int virNodeDeviceGetSCSIHostCaps(virNodeDevCapSCSIHostPtr scsi_host); diff --git a/src/conf/virstorageobj.c b/src/conf/virstorageobj.c index 0b3ba84af2..30aabb2b37 100644 --- a/src/conf/virstorageobj.c +++ b/src/conf/virstorageobj.c @@ -22,6 +22,7 @@ #include "datatypes.h" #include "node_device_conf.h" +#include "node_device_util.h" #include "virstorageobj.h" #include "viralloc.h" diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms index 335210c31d..e2f10acff4 100644 --- a/src/libvirt_private.syms +++ b/src/libvirt_private.syms @@ -722,14 +722,11 @@ virNodeDevCapsDefFree; virNodeDevCapTypeFromString; virNodeDevCapTypeToString; virNodeDeviceCapsListExport; -virNodeDeviceCreateVport; virNodeDeviceDefFormat; virNodeDeviceDefFree; virNodeDeviceDefParseFile; virNodeDeviceDefParseNode; virNodeDeviceDefParseString; -virNodeDeviceDeleteVport; -virNodeDeviceGetParentName; virNodeDeviceGetPCIDynamicCaps; virNodeDeviceGetSCSIHostCaps; virNodeDeviceGetSCSITargetCaps; @@ -1317,6 +1314,11 @@ virLogManagerFree; virLogManagerNew; +# node_device/node_device_util.h +virNodeDeviceCreateVport; +virNodeDeviceDeleteVport; +virNodeDeviceGetParentName; + # secret/secret_util.h virSecretGetSecretString; diff --git a/src/node_device/Makefile.inc.am b/src/node_device/Makefile.inc.am index 0c3ad51273..f7aec97ba9 100644 --- a/src/node_device/Makefile.inc.am +++ b/src/node_device/Makefile.inc.am @@ -3,6 +3,11 @@ NODE_DEVICE_DRIVER_SOURCES = \ node_device/node_device_driver.h \ $(NULL) +NODE_DEVICE_UTIL_SOURCES = \ + node_device/node_device_util.h \ + node_device/node_device_util.c \ + $(NULL) + NODE_DEVICE_DRIVER_HAL_SOURCES = \ node_device/node_device_hal.c \ node_device/node_device_hal.h \ @@ -17,6 +22,7 @@ DRIVER_SOURCE_FILES += \ $(NODE_DEVICE_DRIVER_SOURCES) \ $(NODE_DEVICE_DRIVER_HAL_SOURCES) \ $(NODE_DEVICE_DRIVER_UDEV_SOURCES) \ + $(NODE_DEVICE_UTIL_SOURCES) \ $(NULL) STATEFUL_DRIVER_SOURCE_FILES += \ @@ -27,13 +33,22 @@ EXTRA_DIST += \ $(NODE_DEVICE_DRIVER_SOURCES) \ $(NODE_DEVICE_DRIVER_HAL_SOURCES) \ $(NODE_DEVICE_DRIVER_UDEV_SOURCES) \ + $(NODE_DEVICE_UTIL_SOURCES) \ $(NULL) +noinst_LTLIBRARIES += libvirt_nodedev.la +libvirt_la_BUILT_LIBADD += libvirt_nodedev.la +libvirt_nodedev_la_CFLAGS = $(AM_CFLAGS) +libvirt_nodedev_la_LDFLAGS = $(AM_LDFLAGS) +libvirt_nodedev_la_SOURCES = $(NODE_DEVICE_UTIL_SOURCES) if WITH_NODE_DEVICES # Needed to keep automake quiet about conditionals mod_LTLIBRARIES += libvirt_driver_nodedev.la -libvirt_driver_nodedev_la_SOURCES = $(NODE_DEVICE_DRIVER_SOURCES) +libvirt_driver_nodedev_la_SOURCES = \ + $(NODE_DEVICE_DRIVER_SOURCES) \ + $(NODE_DEVICE_UTIL_SOURCES) \ + $(NULL) libvirt_driver_nodedev_la_CFLAGS = \ -I$(srcdir)/access \ diff --git a/src/node_device/node_device_driver.c b/src/node_device/node_device_driver.c index c46d0fbe12..0bcb3de053 100644 --- a/src/node_device/node_device_driver.c +++ b/src/node_device/node_device_driver.c @@ -37,6 +37,7 @@ #include "node_device_event.h" #include "node_device_driver.h" #include "node_device_hal.h" +#include "node_device_util.h" #include "virvhba.h" #include "viraccessapicheck.h" #include "virnetdev.h" diff --git a/src/node_device/node_device_util.c b/src/node_device/node_device_util.c new file mode 100644 index 0000000000..d1d9c3ee49 --- /dev/null +++ b/src/node_device/node_device_util.c @@ -0,0 +1,229 @@ +/* + * node_device_util.c: helper functions for the node device driver + * + * This library 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; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library. If not, see + * <http://www.gnu.org/licenses/>. + */ + +#include <config.h> + +#include "internal.h" + +#include "node_device_util.h" +#include "virlog.h" +#include "virscsihost.h" +#include "virstring.h" +#include "virvhba.h" + +#define VIR_FROM_THIS VIR_FROM_NODEDEV + +VIR_LOG_INIT("node_device.node_device_util"); + +/* virNodeDeviceGetParentName + * @conn: Connection pointer + * @nodedev_name: Node device to lookup + * + * Lookup the node device by name and return the parent name + * + * Returns parent name on success, caller is responsible for freeing; + * otherwise, returns NULL on failure + */ +char * +virNodeDeviceGetParentName(virConnectPtr conn, + const char *nodedev_name) +{ + virNodeDevicePtr device = NULL; + char *parent; + + if (!(device = virNodeDeviceLookupByName(conn, nodedev_name))) { + virReportError(VIR_ERR_XML_ERROR, + _("Cannot find '%s' in node device database"), + nodedev_name); + return NULL; + } + + ignore_value(VIR_STRDUP(parent, virNodeDeviceGetParent(device))); + virObjectUnref(device); + + return parent; +} + + +/** + * @fchost: Pointer to vHBA adapter + * + * Create a vHBA for Storage. This code accomplishes this via searching + * through the sysfs for scsi_host/fc_host in order to first ensure some + * vHBA doesn't already exist for the requested wwnn/wwpn (e.g. an unmanaged + * vHBA) and to search for the parent vport capable scsi_host by name, + * wwnn/wwpn, or fabric_wwn (if provided). If no parent is provided, then + * a vport capable scsi_host will be selected. + * + * Returns vHBA name on success, NULL on failure with an error message set + */ +char * +virNodeDeviceCreateVport(virStorageAdapterFCHostPtr fchost) +{ + unsigned int parent_host; + char *name = NULL; + char *parent_hoststr = NULL; + bool skip_capable_check = false; + + VIR_DEBUG("parent='%s', wwnn='%s' wwpn='%s'", + NULLSTR(fchost->parent), fchost->wwnn, fchost->wwpn); + + if (fchost->parent) { + if (VIR_STRDUP(parent_hoststr, fchost->parent) < 0) + goto cleanup; + } else if (fchost->parent_wwnn && fchost->parent_wwpn) { + if (!(parent_hoststr = virVHBAGetHostByWWN(NULL, fchost->parent_wwnn, + fchost->parent_wwpn))) { + virReportError(VIR_ERR_XML_ERROR, "%s", + _("cannot find parent using provided wwnn/wwpn")); + goto cleanup; + } + } else if (fchost->parent_fabric_wwn) { + if (!(parent_hoststr = + virVHBAGetHostByFabricWWN(NULL, fchost->parent_fabric_wwn))) { + virReportError(VIR_ERR_XML_ERROR, "%s", + _("cannot find parent using provided fabric_wwn")); + goto cleanup; + } + } else { + if (!(parent_hoststr = virVHBAFindVportHost(NULL))) { + virReportError(VIR_ERR_XML_ERROR, "%s", + _("'parent' for vHBA not specified, and " + "cannot find one on this host")); + goto cleanup; + } + skip_capable_check = true; + } + + if (virSCSIHostGetNumber(parent_hoststr, &parent_host) < 0) + goto cleanup; + + /* NOTE: + * We do not save the parent_hoststr in fchost->parent since + * we could be writing out the 'def' to the saved XML config. + * If we wrote out the name in the XML, then future starts would + * always use the same parent rather than finding the "best available" + * parent. Besides we have a way to determine the parent based on + * the 'name' field. + */ + if (!skip_capable_check && !virVHBAPathExists(NULL, parent_host)) { + virReportError(VIR_ERR_XML_ERROR, + _("parent '%s' specified for vHBA does not exist"), + parent_hoststr); + goto cleanup; + } + + if (virVHBAManageVport(parent_host, fchost->wwpn, fchost->wwnn, + VPORT_CREATE) < 0) + goto cleanup; + + /* Let's ensure the device was created */ + virWaitForDevices(); + if (!(name = virVHBAGetHostByWWN(NULL, fchost->wwnn, fchost->wwpn))) { + ignore_value(virVHBAManageVport(parent_host, fchost->wwpn, fchost->wwnn, + VPORT_DELETE)); + goto cleanup; + } + + cleanup: + VIR_FREE(parent_hoststr); + return name; +} + + +/** + * @conn: Connection pointer + * @fchost: Pointer to vHBA adapter + * + * As long as the vHBA is being managed, search for the scsi_host via the + * provided wwnn/wwpn and then find the corresponding parent scsi_host in + * order to send the delete request. + * + * Returns 0 on success, -1 on failure + */ +int +virNodeDeviceDeleteVport(virConnectPtr conn, + virStorageAdapterFCHostPtr fchost) +{ + char *name = NULL; + char *scsi_host_name = NULL; + unsigned int parent_host; + char *vhba_parent = NULL; + int ret = -1; + + VIR_DEBUG("conn=%p parent='%s', managed='%d' wwnn='%s' wwpn='%s'", + conn, NULLSTR(fchost->parent), fchost->managed, + fchost->wwnn, fchost->wwpn); + + /* If we're not managing the deletion of the vHBA, then just return */ + if (fchost->managed != VIR_TRISTATE_BOOL_YES) + return 0; + + /* Find our vHBA by searching the fc_host sysfs tree for our wwnn/wwpn */ + if (!(name = virVHBAGetHostByWWN(NULL, fchost->wwnn, fchost->wwpn))) { + virReportError(VIR_ERR_INTERNAL_ERROR, + _("Failed to find fc_host for wwnn='%s' and wwpn='%s'"), + fchost->wwnn, fchost->wwpn); + goto cleanup; + } + + if (virAsprintf(&scsi_host_name, "scsi_%s", name) < 0) + goto cleanup; + + /* If at startup time we provided a parent, then use that to + * get the parent_host value; otherwise, we have to determine + * the parent scsi_host which we did not save at startup time + */ + if (fchost->parent) { + /* Someone provided a parent string at startup time that + * was the same as the scsi_host - meaning we have a pool + * backed to an HBA, so there won't be a vHBA to delete */ + if (STREQ(scsi_host_name, fchost->parent)) { + ret = 0; + goto cleanup; + } + + if (virSCSIHostGetNumber(fchost->parent, &parent_host) < 0) + goto cleanup; + } else { + if (!(vhba_parent = virNodeDeviceGetParentName(conn, scsi_host_name))) + goto cleanup; + + /* If the parent is not a scsi_host, then this is a pool backed + * directly to an HBA and there's no vHBA to remove - so we're done */ + if (!STRPREFIX(vhba_parent, "scsi_host")) { + ret = 0; + goto cleanup; + } + + if (virSCSIHostGetNumber(vhba_parent, &parent_host) < 0) + goto cleanup; + } + + if (virVHBAManageVport(parent_host, fchost->wwpn, fchost->wwnn, + VPORT_DELETE) < 0) + goto cleanup; + + ret = 0; + + cleanup: + VIR_FREE(name); + VIR_FREE(vhba_parent); + VIR_FREE(scsi_host_name); + return ret; +} diff --git a/src/node_device/node_device_util.h b/src/node_device/node_device_util.h new file mode 100644 index 0000000000..5cb225d03e --- /dev/null +++ b/src/node_device/node_device_util.h @@ -0,0 +1,35 @@ +/* + * node_device_util.h: utility functions for node device driver + * + * This library 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; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library. If not, see + * <http://www.gnu.org/licenses/>. + */ + +#ifndef __VIR_NODE_DEVICE_UTIL_H__ +# define __VIR_NODE_DEVICE_UTIL_H__ + +# include "conf/storage_adapter_conf.h" + +char * +virNodeDeviceGetParentName(virConnectPtr conn, + const char *nodedev_name); + +char * +virNodeDeviceCreateVport(virStorageAdapterFCHostPtr fchost); + +int +virNodeDeviceDeleteVport(virConnectPtr conn, + virStorageAdapterFCHostPtr fchost); + +#endif /* __VIR_NODE_DEVICE_UTIL_H__ */ diff --git a/src/storage/Makefile.inc.am b/src/storage/Makefile.inc.am index b4400b556f..c1fd8cc7b3 100644 --- a/src/storage/Makefile.inc.am +++ b/src/storage/Makefile.inc.am @@ -221,6 +221,7 @@ if WITH_STORAGE_SCSI libvirt_storage_backend_scsi_la_SOURCES = $(STORAGE_DRIVER_SCSI_SOURCES) libvirt_storage_backend_scsi_la_CFLAGS = \ -I$(srcdir)/conf \ + -I$(srcdir)/node_device \ $(AM_CFLAGS) \ $(NULL) diff --git a/src/storage/storage_backend_scsi.c b/src/storage/storage_backend_scsi.c index 7c927c4d95..fe3a1e36ac 100644 --- a/src/storage/storage_backend_scsi.c +++ b/src/storage/storage_backend_scsi.c @@ -35,6 +35,7 @@ #include "virstring.h" #include "storage_util.h" #include "node_device_conf.h" +#include "node_device_util.h" #include "driver.h" #define VIR_FROM_THIS VIR_FROM_STORAGE -- 2.17.2

2 2

[libvirt] [tck PATCH 0/3] Improvements to virtual network testing and misc fixes
by Daniel P. Berrangé 12 Nov '18

12 Nov '18

The main goal of this patch series is addition of tests which create a virtual network with every possible forwarding mode, and attempt to boot a guest with them. A couple of other pieces were added at the end. Daniel P. Berrangé (3): Add tests for virtual network <-> guest connections Fix incorrect warning about deleting everything Allow tests to be listed as positional arguments bin/libvirt-tck | 69 ++++++++------- lib/Sys/Virt/TCK.pm | 33 ++++++++ lib/Sys/Virt/TCK/NetworkBuilder.pm | 33 +++++++- scripts/networks/300-guest-network-isolated.t | 82 ++++++++++++++++++ scripts/networks/310-guest-network-nat.t | 83 +++++++++++++++++++ scripts/networks/320-guest-network-route.t | 83 +++++++++++++++++++ scripts/networks/330-guest-network-open.t | 83 +++++++++++++++++++ scripts/networks/340-guest-network-bridge.t | 79 ++++++++++++++++++ scripts/networks/350-guest-network-private.t | 81 ++++++++++++++++++ scripts/networks/360-guest-network-vepa.t | 81 ++++++++++++++++++ .../networks/370-guest-network-passthrough.t | 81 ++++++++++++++++++ scripts/networks/380-guest-network-hostdev.t | 82 ++++++++++++++++++ t/080-network-builder.t | 2 +- 13 files changed, 838 insertions(+), 34 deletions(-) create mode 100644 scripts/networks/300-guest-network-isolated.t create mode 100644 scripts/networks/310-guest-network-nat.t create mode 100644 scripts/networks/320-guest-network-route.t create mode 100644 scripts/networks/330-guest-network-open.t create mode 100644 scripts/networks/340-guest-network-bridge.t create mode 100644 scripts/networks/350-guest-network-private.t create mode 100644 scripts/networks/360-guest-network-vepa.t create mode 100644 scripts/networks/370-guest-network-passthrough.t create mode 100644 scripts/networks/380-guest-network-hostdev.t -- 2.19.1

2 7

[libvirt] [PATCH 0/2] Fix some errors around VIR_ACCESS_DENIED
by John Ferlan 12 Nov '18

12 Nov '18

Patch 1 fixes my own error made in this release fortunately, but only seen because I was invesigating Patch 2 Patch 2 is perhaps a longer term issue, but perhaps coming more to light now that the nwfilter bindings have been separated and use a virConnectOpen for nwfilter:///system during reconnection processing; whereas, previously the filter bindings would have been "hidden" within various nwfilter, domain, and network driver callbacks and throughs. John Ferlan (2): util: Fix VIR_ERR_ACCESS_DENIED formatting qemu: Set identity for the reconnect all thread src/qemu/qemu_process.c | 5 +++++ src/util/virerror.c | 4 ++-- 2 files changed, 7 insertions(+), 2 deletions(-) -- 2.17.2

2 4

[libvirt] [PATCH v4 00/37] BaselineHypervisorCPU using QEMU QMP exchanges
by Chris Venteicher 11 Nov '18

11 Nov '18

Some architectures (S390) depend on QEMU to compute baseline CPU model and expand a models feature set. Interacting with QEMU requires starting the QEMU process and completing one or more query-cpu-model-baseline QMP exchanges with QEMU in addition to a query-cpu-model-expansion QMP exchange to expand all features in the model. See "s390x CPU models: exposing features" patch set on Qemu-devel for discussion of QEMU aspects. This is part of resolution of: https://bugzilla.redhat.com/show_bug.cgi?id=1511999 Version 4 attempts to address all issues from V1,2,3 including making the QEMU process activation for QMP Queries generic (not specific to capabilities) and moving that code from qemu_capabilities to qemu_process. Version 4 greatly expands the number of patches to make the set easier to review. The patches to do hypervisor baseline using QEMU are primarily in qemu_driver.c The patches to make the process code generic (not capabilities specific) are mostly in qemu_process.c Many of the patches are cut / paste of existing code. The patches that change functionality are as modular and minimal as possible to make reviewing easier. I attempted to make the new qemu_process functions consistent with the existing domain activation qemu_process functions. A thread safe library function creates a unique directory under libDir for each QEMU process (for QMP messaging) to decouple processes in terms of sockets and file system footprint. The last patch is based on past discussion of QEMU cpu expansion only returning migratable features except for one x86 case where non-migratable features are explicitly requested. The patch records that features are migratable based on QEMU only returning migratable features. The main result is the CPU xml for S390 CPU's contains the same migratability info the X86 currently does. The testcases were updated to reflect the change. Every patch should compile independently if applied in sequence. Thanks, Chris Chris Venteicher (37): qemu_monitor: Introduce qemuMonitorCPUModelInfoNew qemu_monitor: Introduce qemuMonitorCPUModelInfo / JSON conversion qemu_capabilities: Introduce virQEMuCapsMigratablePropsDiff qemu_monitor: qemuMonitorGetCPUModelExpansion inputs and outputs CPUModelInfo qemu_process: Move process code from qemu_capabilities to qemu_process qemu_process: Use qemuProcess prefix qemu_process: Limit qemuProcessNew to const input strings qemu_process: Refer to proc not cmd in process code qemu_process: Use consistent name for stop process function qemu_capabilities: Stop QEMU process before freeing qemu_process: Use qemuProcess struct for a single process qemu_process: Persist stderr in qemuProcess struct qemu_capabilities: Detect caps probe failure by checking monitor ptr qemu_process: Introduce qemuProcessStartQmp qemu_process: Add debug message in qemuProcessLaunchQmp qemu_process: Collect monitor code in single function qemu_process: Store libDir in qemuProcess struct qemu_process: Setup paths within qemuProcessInitQmp qemu_process: Stop retaining Qemu Monitor config in qemuProcess qemu_process: Don't open monitor if process failed qemu_process: Cleanup qemuProcess alloc function qemu_process: Cleanup qemuProcessStopQmp function qemu_process: Catch process free before process stop qemu_monitor: Make monitor callbacks optional qemu_process: Enter QMP command mode when starting QEMU Process qemu_process: Use unique directories for QMP processes qemu_process: Stop locking QMP process monitor immediately qemu_capabilities: Introduce CPUModelInfo to virCPUDef function qemu_capabilities: Introduce virCPUDef to CPUModelInfo function qemu_monitor: Support query-cpu-model-baseline QMP command qemu_driver: Consolidate code to baseline using libvirt qemu_driver: Decouple code for baseline using libvirt qemu_driver: Identify using libvirt as a distinct way to compute baseline qemu_driver: Support baseline calculation using QEMU qemu_driver: Support feature expansion via QEMU when baselining cpu qemu_driver: Remove unsupported props in expanded hypervisor baseline output qemu_monitor: Default props to migratable when expanding cpu model src/qemu/qemu_capabilities.c | 567 ++++++++---------- src/qemu/qemu_capabilities.h | 4 + src/qemu/qemu_driver.c | 219 ++++++- src/qemu/qemu_monitor.c | 184 +++++- src/qemu/qemu_monitor.h | 29 +- src/qemu/qemu_monitor_json.c | 226 +++++-- src/qemu/qemu_monitor_json.h | 12 +- src/qemu/qemu_process.c | 359 +++++++++++ src/qemu/qemu_process.h | 37 ++ tests/cputest.c | 11 +- .../caps_2.10.0.s390x.xml | 60 +- .../caps_2.11.0.s390x.xml | 58 +- .../caps_2.12.0.s390x.xml | 56 +- .../qemucapabilitiesdata/caps_2.8.0.s390x.xml | 32 +- .../qemucapabilitiesdata/caps_2.9.0.s390x.xml | 34 +- .../qemucapabilitiesdata/caps_3.0.0.s390x.xml | 64 +- tests/qemucapabilitiestest.c | 7 + 17 files changed, 1388 insertions(+), 571 deletions(-) -- 2.17.1

2 40

[libvirt] [PATCH] Add armv6l Support as guest
by infos＠nafets.de 09 Nov '18

09 Nov '18

From: Stefan Schallenberg <nafets227(a)users.noreply.github.com> Support for armv6l qemu guests has been added. Tested with arm1176 CPU on x86. Signed-off-by Stefan Schallenberg <infos at nafets.de> --- docs/news.xml | 9 +++++ docs/schemas/basictypes.rng | 1 + src/qemu/qemu_capabilities.c | 5 ++- src/qemu/qemu_command.c | 4 +- src/qemu/qemu_domain.c | 11 ++++-- src/qemu/qemu_domain_address.c | 6 ++- tests/capabilityschemadata/caps-qemu-kvm.xml | 10 +++++ tests/testutilsqemu.c | 40 +++++++++++++++++++- 8 files changed, 75 insertions(+), 11 deletions(-) diff --git a/docs/news.xml b/docs/news.xml index 88774c55ae..b01bcbf949 100644 --- a/docs/news.xml +++ b/docs/news.xml @@ -25,6 +25,15 @@ <section title="New features"> </section> <section title="Improvements"> + <change> + <summary> + Add armv6l Support as guest + </summary> + <description> + Support for armv6l qemu guests has been added. + Tested with arm1176 CPU on x86. + </description> + </change> </section> <section title="Bug fixes"> </section> diff --git a/docs/schemas/basictypes.rng b/docs/schemas/basictypes.rng index 14a3670e5c..8a01b854c0 100644 --- a/docs/schemas/basictypes.rng +++ b/docs/schemas/basictypes.rng @@ -380,6 +380,7 @@ <value>aarch64</value> <value>alpha</value> <value>armv7l</value> + <value>armv6l</value> <value>cris</value> <value>i686</value> <value>ia64</value> diff --git a/src/qemu/qemu_capabilities.c b/src/qemu/qemu_capabilities.c index 2ca5af3297..4871e89324 100644 --- a/src/qemu/qemu_capabilities.c +++ b/src/qemu/qemu_capabilities.c @@ -618,7 +618,7 @@ static const char *virQEMUCapsArchToString(virArch arch) { if (arch == VIR_ARCH_I686) return "i386"; - else if (arch == VIR_ARCH_ARMV7L) + else if (arch == VIR_ARCH_ARMV6L || arch == VIR_ARCH_ARMV7L) return "arm"; else if (arch == VIR_ARCH_OR32) return "or32"; @@ -2179,7 +2179,7 @@ static const char *preferredMachines[] = { NULL, /* VIR_ARCH_NONE (not a real arch :) */ "clipper", /* VIR_ARCH_ALPHA */ - NULL, /* VIR_ARCH_ARMV6L (no QEMU impl) */ + "versatilepb", /* VIR_ARCH_ARMV6L */ "integratorcp", /* VIR_ARCH_ARMV7L */ "integratorcp", /* VIR_ARCH_ARMV7B */ @@ -4157,6 +4157,7 @@ virQEMUCapsInitQMPMonitor(virQEMUCapsPtr qemuCaps, /* GIC capabilities, eg. available GIC versions */ if ((qemuCaps->arch == VIR_ARCH_AARCH64 || + qemuCaps->arch == VIR_ARCH_ARMV6L || qemuCaps->arch == VIR_ARCH_ARMV7L) && virQEMUCapsProbeQMPGICCapabilities(qemuCaps, mon) < 0) goto cleanup; diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index f59cbf559e..2aa5dab049 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -9072,7 +9072,9 @@ static bool qemuChrIsPlatformDevice(const virDomainDef *def, virDomainChrDefPtr chr) { - if (def->os.arch == VIR_ARCH_ARMV7L || def->os.arch == VIR_ARCH_AARCH64) { + if (def->os.arch == VIR_ARCH_ARMV6L || + def->os.arch == VIR_ARCH_ARMV7L || + def->os.arch == VIR_ARCH_AARCH64) { /* pl011 (used on mach-virt) is a platform device */ if (chr->deviceType == VIR_DOMAIN_CHR_DEVICE_TYPE_SERIAL && diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index e25afdad6b..2a757683c8 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -3253,6 +3253,7 @@ qemuDomainDefAddDefaultDevices(virDomainDefPtr def, addPCIRoot = true; break; + case VIR_ARCH_ARMV6L: case VIR_ARCH_ARMV7L: case VIR_ARCH_AARCH64: addDefaultUSB = false; @@ -3297,7 +3298,6 @@ qemuDomainDefAddDefaultDevices(virDomainDefPtr def, addPCIRoot = true; break; - case VIR_ARCH_ARMV6L: case VIR_ARCH_ARMV7B: case VIR_ARCH_CRIS: case VIR_ARCH_ITANIUM: @@ -5908,7 +5908,8 @@ qemuDomainDefaultNetModel(const virDomainDef *def, if (ARCH_IS_S390(def->os.arch)) return "virtio"; - if (def->os.arch == VIR_ARCH_ARMV7L || + if (def->os.arch == VIR_ARCH_ARMV6L || + def->os.arch == VIR_ARCH_ARMV7L || def->os.arch == VIR_ARCH_AARCH64) { if (STREQ(def->os.machine, "versatilepb")) return "smc91c111"; @@ -9691,7 +9692,8 @@ bool qemuDomainMachineIsARMVirt(const char *machine, const virArch arch) { - if (arch != VIR_ARCH_ARMV7L && + if (arch != VIR_ARCH_ARMV6L && + arch != VIR_ARCH_ARMV7L && arch != VIR_ARCH_AARCH64) return false; @@ -10497,7 +10499,8 @@ qemuDomainSupportsNicdev(virDomainDefPtr def, virDomainNetDefPtr net) { /* non-virtio ARM nics require legacy -net nic */ - if (((def->os.arch == VIR_ARCH_ARMV7L) || + if (((def->os.arch == VIR_ARCH_ARMV6L) || + (def->os.arch == VIR_ARCH_ARMV7L) || (def->os.arch == VIR_ARCH_AARCH64)) && net->info.type != VIR_DOMAIN_DEVICE_ADDRESS_TYPE_VIRTIO_MMIO && net->info.type != VIR_DOMAIN_DEVICE_ADDRESS_TYPE_PCI) diff --git a/src/qemu/qemu_domain_address.c b/src/qemu/qemu_domain_address.c index 27c9bfb946..64a6595717 100644 --- a/src/qemu/qemu_domain_address.c +++ b/src/qemu/qemu_domain_address.c @@ -468,7 +468,8 @@ static void qemuDomainAssignARMVirtioMMIOAddresses(virDomainDefPtr def, virQEMUCapsPtr qemuCaps) { - if (def->os.arch != VIR_ARCH_ARMV7L && + if (def->os.arch != VIR_ARCH_ARMV6L && + def->os.arch != VIR_ARCH_ARMV7L && def->os.arch != VIR_ARCH_AARCH64) return; @@ -2185,7 +2186,8 @@ static bool qemuDomainSupportsPCI(virDomainDefPtr def, virQEMUCapsPtr qemuCaps) { - if ((def->os.arch != VIR_ARCH_ARMV7L) && + if ((def->os.arch != VIR_ARCH_ARMV6L) && + (def->os.arch != VIR_ARCH_ARMV7L) && (def->os.arch != VIR_ARCH_AARCH64) && !ARCH_IS_RISCV(def->os.arch)) return true; diff --git a/tests/capabilityschemadata/caps-qemu-kvm.xml b/tests/capabilityschemadata/caps-qemu-kvm.xml index 1aa98d140f..01cebcab16 100644 --- a/tests/capabilityschemadata/caps-qemu-kvm.xml +++ b/tests/capabilityschemadata/caps-qemu-kvm.xml @@ -81,6 +81,16 @@ </features> </guest> +<guest> + <os_type>hvm</os_type> + <arch name='armv7l'> + <wordsize>32</wordsize> + <emulator>/usr/bin/qemu-system-arm</emulator> + <machine>versatilepb</machine> + <domain type='qemu'/> + </arch> + </guest> + <guest> <os_type>hvm</os_type> <arch name='armv7l'> diff --git a/tests/testutilsqemu.c b/tests/testutilsqemu.c index 332885eb77..1c60aaee03 100644 --- a/tests/testutilsqemu.c +++ b/tests/testutilsqemu.c @@ -392,7 +392,39 @@ static int testQemuAddS390Guest(virCapsPtr caps) return -1; } -static int testQemuAddArmGuest(virCapsPtr caps) +static int testQemuAddArm6Guest(virCapsPtr caps) +{ + static const char *machines[] = { "versatilepb" }; + virCapsGuestMachinePtr *capsmachines = NULL; + virCapsGuestPtr guest; + + capsmachines = virCapabilitiesAllocMachines(machines, + ARRAY_CARDINALITY(machines)); + if (!capsmachines) + goto error; + + guest = virCapabilitiesAddGuest(caps, VIR_DOMAIN_OSTYPE_HVM, VIR_ARCH_ARMV6L, + QEMUBinList[TEST_UTILS_QEMU_BIN_ARM], + NULL, + ARRAY_CARDINALITY(machines), + capsmachines); + if (!guest) + goto error; + + if (!virCapabilitiesAddGuestDomain(guest, VIR_DOMAIN_VIRT_QEMU, NULL, NULL, 0, NULL)) + goto error; + if (!virCapabilitiesAddGuestDomain(guest, VIR_DOMAIN_VIRT_KVM, + NULL, NULL, 0, NULL)) + goto error; + + return 0; + + error: + virCapabilitiesFreeMachines(capsmachines, ARRAY_CARDINALITY(machines)); + return -1; +} + +static int testQemuAddArm7Guest(virCapsPtr caps) { static const char *machines[] = { "vexpress-a9", "vexpress-a15", @@ -426,6 +458,7 @@ static int testQemuAddArmGuest(virCapsPtr caps) return -1; } + static int testQemuAddAARCH64Guest(virCapsPtr caps) { static const char *machines[] = { "virt"}; @@ -514,7 +547,10 @@ virCapsPtr testQemuCapsInit(void) if (testQemuAddS390Guest(caps)) goto cleanup; - if (testQemuAddArmGuest(caps)) + if (testQemuAddArm6Guest(caps)) + goto cleanup; + + if (testQemuAddArm7Guest(caps)) goto cleanup; if (testQemuAddAARCH64Guest(caps)) -- 2.19.1

1 0

[libvirt] [PATCH 0/2] qemu: Drop priv->gotShutdown
by Jiri Denemark 09 Nov '18

09 Nov '18

Jiri Denemark (2): qemu: Drop unreachable code from qemuProcessHandleStop qemu: Drop priv->gotShutdown src/qemu/qemu_domain.h | 1 - src/qemu/qemu_driver.c | 3 ++- src/qemu/qemu_process.c | 13 +------------ 3 files changed, 3 insertions(+), 14 deletions(-) -- 2.19.1

2 3

[libvirt] [PATCH] qemu:address:Fix segfault in qemuDomainPrimeVirtioDeviceAddresses
by Wang Yechao 09 Nov '18

09 Nov '18

On aarch64, lauch vm with the follow configuration: <interface type="hostdev" managed="yes"> <mac address="fa:16:3e:14:41:00"/> <source> <address type="pci" domain="0x0000" bus="0x01" slot="0x0b" function="0x2"/> </source> </interface> libvirtd will crash when access the net->model. Signed-off-by: Wang Yechao <wang.yechao255(a)zte.com.cn> --- src/qemu/qemu_domain_address.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/qemu/qemu_domain_address.c b/src/qemu/qemu_domain_address.c index 24dd7c1..27c9bfb 100644 --- a/src/qemu/qemu_domain_address.c +++ b/src/qemu/qemu_domain_address.c @@ -324,7 +324,8 @@ qemuDomainPrimeVirtioDeviceAddresses(virDomainDefPtr def, for (i = 0; i < def->nnets; i++) { virDomainNetDefPtr net = def->nets[i]; - if (STREQ(net->model, "virtio") && + if (net->model && + STREQ(net->model, "virtio") && net->info.type == VIR_DOMAIN_DEVICE_ADDRESS_TYPE_NONE) { net->info.type = type; } -- 1.8.3.1

2 1

[libvirt] [PATCH] news: Add entry for soft reset support in Xen
by Jim Fehlig 08 Nov '18

08 Nov '18

Signed-off-by: Jim Fehlig <jfehlig(a)suse.com> --- I'm torn on whether this is a new feature, improvement, or even simply a bug fix... docs/news.xml | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/docs/news.xml b/docs/news.xml index 9d98c34df2..e1d10cf7f1 100644 --- a/docs/news.xml +++ b/docs/news.xml @@ -35,6 +35,17 @@ <libvirt> <release version="v4.10.0" date="unreleased"> <section title="New features"> + <change> + <summary> + Xen: Add support for soft reset shutdown event + </summary> + <description> + The pvops Linux kernel uses soft reset to handle the crash + machine operation. The libxl driver now supports the soft + reset shutdown event, allowing proper crash handling of + pvops-based HVM domains. + </description> + </change> </section> <section title="Improvements"> </section> -- 2.18.0

2 2

[libvirt] [PATCH v2 0/3] Add "memfd" memory backing type
by marcandre.lureau＠redhat.com 08 Nov '18

08 Nov '18

From: Marc-André Lureau <marcandre.lureau(a)redhat.com> Hi, This is an alternative series from "[PATCH 0/5] Use memfd if possible". Instead of automatically using memfd for anonymous memory when available (as suggested by Daniel), it introduces the "memfd" memory backing type. Although using memfd transparently when possible is a good idea, it is a source of various complications for migration & save/restore. This could eventually be challenged in a different series. The first two patches have been modified and reviewed by John Ferlan. Hopefully they can be merged early, regardless of the last patch outcome, to avoid the painful rebase conflicts due to capabilities checks introduction. Thanks Marc-André Lureau (3): qemu: add memory-backend-memfd capability check qemu: check memory-backend-memfd.hugetlb capability qemu: add memfd source type docs/formatdomain.html.in | 9 +- docs/schemas/domaincommon.rng | 1 + src/conf/domain_conf.c | 3 +- src/conf/domain_conf.h | 1 + src/qemu/qemu_capabilities.c | 10 ++ src/qemu/qemu_capabilities.h | 2 + src/qemu/qemu_command.c | 69 +++++++---- src/qemu/qemu_domain.c | 12 +- .../caps_2.12.0.aarch64.replies | 94 ++++++++++++--- .../caps_2.12.0.aarch64.xml | 4 +- .../caps_2.12.0.ppc64.replies | 90 +++++++++++--- .../caps_2.12.0.ppc64.xml | 4 +- .../caps_2.12.0.s390x.replies | 98 ++++++++++++---- .../caps_2.12.0.s390x.xml | 4 +- .../caps_2.12.0.x86_64.replies | 110 +++++++++++++----- .../caps_2.12.0.x86_64.xml | 4 +- .../caps_3.0.0.ppc64.replies | 90 +++++++++++--- .../qemucapabilitiesdata/caps_3.0.0.ppc64.xml | 4 +- .../caps_3.0.0.riscv32.replies | 86 +++++++++++--- .../caps_3.0.0.riscv32.xml | 2 + .../caps_3.0.0.riscv64.replies | 86 +++++++++++--- .../caps_3.0.0.riscv64.xml | 2 + .../caps_3.0.0.x86_64.replies | 110 +++++++++++++----- .../caps_3.0.0.x86_64.xml | 4 +- .../memfd-memory-numa.x86_64-latest.args | 34 ++++++ tests/qemuxml2argvdata/memfd-memory-numa.xml | 36 ++++++ tests/qemuxml2argvtest.c | 2 + 27 files changed, 788 insertions(+), 183 deletions(-) create mode 100644 tests/qemuxml2argvdata/memfd-memory-numa.x86_64-latest.args create mode 100644 tests/qemuxml2argvdata/memfd-memory-numa.xml -- 2.19.0

8 17

[libvirt] [PATCH] spec: Drop support for Fedora 27
by Andrea Bolognani 08 Nov '18

08 Nov '18

In accordance with our platform support policy, now that Fedora 29 is out we no longer support building on Fedora 27. This allows us to remove a few version checks. Signed-off-by: Andrea Bolognani <abologna(a)redhat.com> --- libvirt.spec.in | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/libvirt.spec.in b/libvirt.spec.in index 90daefe6f1..71cd45c603 100644 --- a/libvirt.spec.in +++ b/libvirt.spec.in @@ -4,7 +4,7 @@ # that's still supported by the vendor. It may work on other distros # or versions, but no effort will be made to ensure that going forward. %define min_rhel 7 -%define min_fedora 27 +%define min_fedora 28 %if (0%{?fedora} && 0%{?fedora} >= %{min_fedora}) || (0%{?rhel} && 0%{?rhel} >= %{min_rhel}) %define supported_platform 1 @@ -72,7 +72,7 @@ %endif # We need a recent enough libiscsi (>= 1.18.0) -%if 0%{?fedora} >= 28 || 0%{?rhel} > 7 +%if 0%{?fedora} || 0%{?rhel} > 7 %define with_storage_iscsi_direct 0%{!?_without_storage_iscsi_direct:1} %else %define with_storage_iscsi_direct 0 @@ -258,7 +258,7 @@ BuildRequires: /usr/bin/pod2man %endif BuildRequires: gcc BuildRequires: git -%if 0%{?fedora} >= 27 || 0%{?rhel} > 7 +%if 0%{?fedora} || 0%{?rhel} > 7 BuildRequires: perl-interpreter %else BuildRequires: perl @@ -386,7 +386,7 @@ BuildRequires: wireshark-devel >= 2.1.0 BuildRequires: libssh-devel >= 0.7.0 %endif -%if 0%{?fedora} > 27 || 0%{?rhel} > 7 +%if 0%{?fedora} || 0%{?rhel} > 7 BuildRequires: rpcgen BuildRequires: libtirpc-devel %endif -- 2.19.1

3 2

[libvirt] [PATCH v2] lxc: Clang is complaining about possible NULL pointer.
by Julio Faracco 08 Nov '18

08 Nov '18

The array "mount" inside lxc_container is not being checked before for loop. Clang syntax scan is complaining about this segmentation fault. Signed-off-by: Julio Faracco <jcfaracco(a)gmail.com> --- src/lxc/lxc_container.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) diff --git a/src/lxc/lxc_container.c b/src/lxc/lxc_container.c index 918194dacd..d834bf01d7 100644 --- a/src/lxc/lxc_container.c +++ b/src/lxc/lxc_container.c @@ -867,9 +867,13 @@ static int lxcContainerSetReadOnly(void) } } - if (mounts) - qsort(mounts, nmounts, sizeof(mounts[0]), - virStringSortRevCompare); + if (!mounts) { + ret = 0; + goto cleanup; + } + + qsort(mounts, nmounts, sizeof(mounts[0]), + virStringSortRevCompare); for (i = 0; i < nmounts; i++) { VIR_DEBUG("Bind readonly %s", mounts[i]); @@ -883,9 +887,7 @@ static int lxcContainerSetReadOnly(void) ret = 0; cleanup: - for (i = 0; i < nmounts; i++) - VIR_FREE(mounts[i]); - VIR_FREE(mounts); + virStringListFreeCount(mounts, nmounts); endmntent(procmnt); return ret; -- 2.17.1

3 2

[libvirt] [PATCH 0/3] add disk driver metadata_cache_size option
by Nikolay Shirokovskiy 08 Nov '18

08 Nov '18

Hi, all. This is a patch series after offlist agreement on introducing metadata-cache-size option for disks. The options itself is described in 2nd patch of the series. There is a plenty of attempts to add option to set qcow2 metadata cache sizes in past, see [1] [2] to name recent that has comments I tried to address or has work I reused to some extent. I would like to address Peter's comment in [1] that this option is image's option rather then disk's here. While this makes sense if we set specific cache value that covers disk only partially, here when we have maximum policy that covers whole disk it makes sense to set same value for all images. The setted value is only upper limit on cache size and thus cache for every image will grow proportionally to image data size "visible from top" eventually I guess. And these sizes are changing during guest lifetime - thus we need set whole disk limit for every image for 'maxium' effect. On the other hand if we add policies different from 'maximum' it may require per image option. Well I can't imagine name for element for backing chain that will have cache size attribute better then 'driver'). And driver is already used for top image so I leave it this way. KNOWN ISSUES 1. when using -driver to configure disks in command line cache size does not get propagated thru backing chain 2. when making external disk snapshot cache size sneak into backing file filename and thus cache size for backing image became remembered there 3. blockcommit after such snapshot will not work because libvirt is not ready for backing file name is reported as json sometimes Looks like 1 can be addressed in qemu. The reason for behaviour in 2 I do not understand honestly. And 3 will be naturally addessed after blockjobs starts working with blockdev configuration I guess. LINKS [1] [PATCH] qemu: Added support L2 table cache for qcow2 disk https://www.redhat.com/archives/libvir-list/2018-July/msg00166.html [2] [PATCH v6 0/2] Add support for qcow2 cache https://www.redhat.com/archives/libvir-list/2017-September/msg00553.html Nikolay Shirokovskiy (3): qemu: caps: add drive.qcow2.l2-cache-size xml: add disk driver metadata_cache_size option qemu: support metadata-cache-size for blockdev docs/formatdomain.html.in | 7 ++++ docs/schemas/domaincommon.rng | 10 +++++ src/conf/domain_conf.c | 17 ++++++++ src/conf/domain_conf.h | 9 ++++ src/qemu/qemu_block.c | 5 ++- src/qemu/qemu_capabilities.c | 3 ++ src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 26 ++++++++++++ src/qemu/qemu_domain.c | 2 + src/util/virstoragefile.c | 1 + src/util/virstoragefile.h | 1 + tests/qemucapabilitiesdata/caps_2.10.0.aarch64.xml | 1 + tests/qemucapabilitiesdata/caps_2.10.0.ppc64.xml | 1 + tests/qemucapabilitiesdata/caps_2.10.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_2.10.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.11.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_2.11.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.12.0.aarch64.xml | 1 + tests/qemucapabilitiesdata/caps_2.12.0.ppc64.xml | 1 + tests/qemucapabilitiesdata/caps_2.12.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_2.12.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.5.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.aarch64.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.ppc64.xml | 1 + tests/qemucapabilitiesdata/caps_2.6.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.7.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_2.7.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.8.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_2.8.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_2.9.0.ppc64.xml | 1 + tests/qemucapabilitiesdata/caps_2.9.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_2.9.0.x86_64.xml | 1 + tests/qemucapabilitiesdata/caps_3.0.0.ppc64.xml | 1 + tests/qemucapabilitiesdata/caps_3.0.0.riscv32.xml | 1 + tests/qemucapabilitiesdata/caps_3.0.0.riscv64.xml | 1 + tests/qemucapabilitiesdata/caps_3.0.0.s390x.xml | 1 + tests/qemucapabilitiesdata/caps_3.0.0.x86_64.xml | 1 + .../qemuxml2argvdata/disk-metadata_cache_size.args | 34 +++++++++++++++ .../qemuxml2argvdata/disk-metadata_cache_size.xml | 42 +++++++++++++++++++ tests/qemuxml2argvtest.c | 2 + .../disk-metadata_cache_size.xml | 48 ++++++++++++++++++++++ tests/qemuxml2xmltest.c | 2 + 42 files changed, 235 insertions(+), 1 deletion(-) create mode 100644 tests/qemuxml2argvdata/disk-metadata_cache_size.args create mode 100644 tests/qemuxml2argvdata/disk-metadata_cache_size.xml create mode 100644 tests/qemuxml2xmloutdata/disk-metadata_cache_size.xml -- 1.8.3.1

3 12

[libvirt] [PATCH] virNetworkDefUpdateDNSHost: Require both IP and a hostname to match
by W. Trevor King 08 Nov '18

08 Nov '18

Since fc19a0059 (network: backend functions for updating network dns host/srv/txt, 2012-11-12), the matching logic for various network components has been: 1) for HOST records, it's considered a match if the IP address or any of the hostnames of an existing record matches. 2) for SRV records, it's a match if all of domain+service+protocol+target *which have been specified* are matched. 3) for TXT records, there is only a single field to match - name (value can be the same for multiple records, and isn't considered a search term), so by definition there can be no ambiguous matches. But HOST records can have the same hostname for multiple records (similar to TXT records with the same value). The value that needs to be distinct for HOST records is the IP address. This commit updates the matching logic to only consider the IP address. Compared to the previous HOST logic: 1. You can now delete entries from an existing network like: <dns> <host ip="192.168.1.1"> <hostname>example</hostname> </host> <host ip="192.168.1.2"> <hostname>example</hostname> </host> </dns> with input like: <host ip="192.168.1.1"> </host> or: <host ip="192.168.1.1"> <hostname>example</hostname> </host> Previously, only the former would work (the latter used to raise "multiple matching DNS HOST records were found in network"). 2. You can no longer remove entries by hostname alone. Previously, you may have been able to remove an entry from an existing network like: <dns> <host ip="192.168.1.1"> <hostname>example-1</hostname> </host> <host ip="192.168.1.2"> <hostname>example-2</hostname> </host> </dns> with input like: <host name="example"> <hostname>example-1</hostname> </host> using the 'name' property to get through the partialOkay check in virNetworkDHCPHostDefParseXML. Now that input will raise "Missing IP address in network '%s' DNS HOST record". 3. You can now add multiple entries with a common hostname (as long as they have distinct IP addresses). Previously, adding: <host ip="192.168.1.1"> <hostname>example</hostname> </host> to an existing: <host ip="192.168.1.2"> <hostname>example</hostname> </host> would have raised "there is already at least one DNS HOST record with a matching field in network". --- I'm actually not clear on whether the 'ip' attribute is required to be unique or not. If not, maybe the logic should be: * Deletes with just an IP remove all <host> entries that match that IP. * Deletes with just a hostname remove all <hostname> entries that match that hostname. * Deletes with an IP and a hostname remove matching <hostname> entries from <host> entries which match the IP. * If <hostname> removal completely empties a <host>, the <host> is also removed. Thoughts? src/conf/network_conf.c | 31 ++++++++++--------------------- 1 file changed, 10 insertions(+), 21 deletions(-) diff --git a/src/conf/network_conf.c b/src/conf/network_conf.c index 39a13b4..8ed62ac 100644 --- a/src/conf/network_conf.c +++ b/src/conf/network_conf.c @@ -587,14 +587,14 @@ virNetworkDNSHostDefParseXML(const char *networkName, xmlNodePtr cur; char *ip; - if (!(ip = virXMLPropString(node, "ip")) && !partialOkay) { + if (!(ip = virXMLPropString(node, "ip"))) { virReportError(VIR_ERR_XML_DETAIL, _("Missing IP address in network '%s' DNS HOST record"), networkName); goto error; } - if (ip && (virSocketAddrParse(&def->ip, ip, AF_UNSPEC) < 0)) { + if (virSocketAddrParse(&def->ip, ip, AF_UNSPEC) < 0) { virReportError(VIR_ERR_XML_DETAIL, _("Invalid IP address in network '%s' DNS HOST record"), networkName); @@ -603,6 +603,13 @@ virNetworkDNSHostDefParseXML(const char *networkName, } VIR_FREE(ip); + if (!VIR_SOCKET_ADDR_VALID(&def->ip)) { + virReportError(VIR_ERR_XML_DETAIL, + _("Invalid IP address in network '%s' DNS HOST record"), + networkName); + goto error; + } + cur = node->children; while (cur != NULL) { if (cur->type == XML_ELEMENT_NODE && @@ -631,13 +638,6 @@ virNetworkDNSHostDefParseXML(const char *networkName, goto error; } - if (!VIR_SOCKET_ADDR_VALID(&def->ip) && def->nnames == 0) { - virReportError(VIR_ERR_XML_DETAIL, - _("Missing ip and hostname in network '%s' DNS HOST record"), - networkName); - goto error; - } - return 0; error: @@ -3334,18 +3334,7 @@ virNetworkDefUpdateDNSHost(virNetworkDefPtr def, goto cleanup; for (i = 0; i < dns->nhosts; i++) { - bool foundThisTime = false; - - if (virSocketAddrEqual(&host.ip, &dns->hosts[i].ip)) - foundThisTime = true; - - for (j = 0; j < host.nnames && !foundThisTime; j++) { - for (k = 0; k < dns->hosts[i].nnames && !foundThisTime; k++) { - if (STREQ(host.names[j], dns->hosts[i].names[k])) - foundThisTime = true; - } - } - if (foundThisTime) { + if virSocketAddrEqual(&host.ip, &dns->hosts[i].ip) { foundCt++; foundIdx = i; } -- 1.8.3.1

2 4

[libvirt] Parsing of memory.stat in libvirt
by Peter.Chubb＠data61.csiro.au 08 Nov '18

08 Nov '18

Hi Folks, libvirt currently spams the logs with error : virCgroupGetMemoryStat:2490 : internal error: Cannot parse 'memory.stat' cgroup file whenever someone does ps in a container. This is because the parser for memory/stat is incorrect: the `line' variable is never updated, so each time through the loop, the same start-of-line is compared for the token; and as all spaces are eventually replaced with NUL the error exit is taken instead of ending the loop properly. Here is a strawman patch to fix the problem. Please note, I'm not subscribed to this list; I reported the bug as https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=913023 and was asked to send the patch upstream. src/util/vircgroup.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) --- libvirt.orig/src/util/vircgroup.c +++ libvirt/src/util/vircgroup.c @@ -2477,7 +2477,7 @@ virCgroupGetMemoryStat(virCgroupPtr grou line = stat; - while (line) { + while (*line) { char *newLine = strchr(line, '\n'); char *valueStr = strchr(line, ' '); unsigned long long value; @@ -2507,6 +2507,11 @@ virCgroupGetMemoryStat(virCgroupPtr grou inactiveFileVal = value >> 10; else if (STREQ(line, "unevictable")) unevictableVal = value >> 10; + + if (newLine) + line = newLine + 1; + else + break; } *cache = cacheVal; -- Dr Peter Chubb Tel: +61 2 9490 5852 http://ts.data61.csiro.au/ Trustworthy Systems Group Data61 (formerly NICTA)

2 2

[libvirt] [PATCH] tests: Use correct function name in error path
by John Ferlan 07 Nov '18

07 Nov '18

Commit id 5eb61e6846 neglected to change the name in the wrong value output to virCgroupGetPercpuStats from virCgroupGetMemoryUsage. Signed-off-by: John Ferlan <jferlan(a)redhat.com> --- Pushed under the trivial rule. tests/vircgrouptest.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/vircgrouptest.c b/tests/vircgrouptest.c index 8fcee21bb2..310e1fb6a2 100644 --- a/tests/vircgrouptest.c +++ b/tests/vircgrouptest.c @@ -756,7 +756,7 @@ static int testCgroupGetPercpuStats(const void *args ATTRIBUTE_UNUSED) if (params[i].value.ul != expected[i]) { fprintf(stderr, - "Wrong value from virCgroupGetMemoryUsage at %zu (expected %llu)\n", + "Wrong value from virCgroupGetPercpuStats at %zu (expected %llu)\n", i, params[i].value.ul); goto cleanup; } -- 2.17.2

1 0

[libvirt] [PATCH 0/3] qemu: don't duplicate suspended events and state changes
by Nikolay Shirokovskiy 07 Nov '18

07 Nov '18

This patch series is similar in implementation to [1] but the motivation is simply to avoid suspended event duplication. [1] https://www.redhat.com/archives/libvir-list/2018-September/msg01304.html Nikolay Shirokovskiy (3): qemu: pass stop reason from qemuProcessStopCPUs to stop handler qemu: map suspended state reason to suspended event detail qemu: don't duplicate suspended events and state changes src/qemu/qemu_domain.c | 34 ++++++++++++++++++++++++++++++++++ src/qemu/qemu_domain.h | 7 +++++++ src/qemu/qemu_driver.c | 26 +++----------------------- src/qemu/qemu_migration.c | 42 ++++++------------------------------------ src/qemu/qemu_migration.h | 4 ---- src/qemu/qemu_process.c | 37 +++++++++++++++++++++++++------------ 6 files changed, 75 insertions(+), 75 deletions(-) -- 1.8.3.1

2 12

[libvirt] [PATCH 0/2] conf: Forbid some nonsensical combinations under <memoryBackend>
by Michal Privoznik 07 Nov '18

07 Nov '18

*** BLURB HERE *** Michal Prívozník (2): conf: Forbid hugepages and <source type='file'/> conf: Forbid hugepages and <allocation mode="ondemand"/> src/conf/domain_conf.c | 25 +++++++++++++++++-- .../qemuxml2argvdata/hugepages-memaccess2.xml | 1 - 2 files changed, 23 insertions(+), 3 deletions(-) -- 2.18.1

3 5

[libvirt] [PATCH] qemu: Don't ignore resume events
by Jiri Denemark 07 Nov '18

07 Nov '18

Since commit v4.7.0-302-ge6d77a75c4 processing RESUME event is mandatory for updating domain state. But the event handler explicitly ignored this event in some cases. Thus the state would be wrong after a fake reboot or when a domain was rebooted after it crashed. BTW, the code to ignore RESUME event after SHUTDOWN didn't make sense even before making RESUME event mandatory. Most likely it was there as a result of careless copy&paste from qemuProcessHandleStop. https://bugzilla.redhat.com/show_bug.cgi?id=1612943 Signed-off-by: Jiri Denemark <jdenemar(a)redhat.com> --- src/qemu/qemu_process.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index c698c3b29c..59ca7cd333 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -719,12 +719,7 @@ qemuProcessHandleResume(qemuMonitorPtr mon ATTRIBUTE_UNUSED, priv->runningReason = VIR_DOMAIN_RUNNING_UNKNOWN; } - if (virDomainObjGetState(vm, NULL) == VIR_DOMAIN_PAUSED) { - if (priv->gotShutdown) { - VIR_DEBUG("Ignoring RESUME event after SHUTDOWN"); - goto unlock; - } - + if (virDomainObjGetState(vm, NULL) != VIR_DOMAIN_RUNNING) { eventDetail = qemuDomainRunningReasonToResumeEvent(reason); VIR_DEBUG("Transitioned guest %s out of paused into resumed state, " "reason '%s', event detail %d", @@ -742,7 +737,6 @@ qemuProcessHandleResume(qemuMonitorPtr mon ATTRIBUTE_UNUSED, } } - unlock: virObjectUnlock(vm); virObjectEventStateQueue(driver->domainEventState, event); virObjectUnref(cfg); -- 2.19.1

2 3

[libvirt] [PATCH] qemu: snapshot: better error for active external readonly disk
by Nikolay Shirokovskiy 07 Nov '18

07 Nov '18

External snapshot of readonly disk of active domain is impossible but error message [1] is cryptic (it's source is qemu). Let's make error message more user friendly. The problem is libvirtd precreates snapshot image with no write permission which is not expected by qemu. [1] current error message error: internal error: unable to execute QEMU command 'transaction': Could not create file: Permission denied Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy(a)virtuozzo.com> --- By the way if domain is not active then snapshot is possible. However top image will have write permissions after snapshot. We can make snapshot work for active domain I guess if we precreate writable snapshot image, but then we end up running readonly disk on writable image. Also making snapshot of readonly disk is not that practical so let's just fix error message for now. src/qemu/qemu_driver.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index a52e249..e75931e 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -14683,6 +14683,14 @@ qemuDomainSnapshotPrepare(virDomainObjPtr vm, active, reuse) < 0) goto cleanup; + if (dom_disk->src->readonly && active) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("external snapshot for readonly disk %s " + "of active domain is not supported"), + disk->name); + goto cleanup; + } + external++; break; -- 1.8.3.1

2 1

[libvirt] [PATCH v2 0/8] Usb hub Cold(un)plug and hot(un)plug support
by Han Han 07 Nov '18

07 Nov '18

v1: https://www.redhat.com/archives/libvir-list/2018-October/msg00563.html Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1375423 Han Han (8): qemu: Allow coldplugging of hub device qemu: Allow coldunplugging of hub device qemu_alias: Refactor hub alias assignment for hotplug qemu_command: Make qemuBuildHubDevStr global private_syms: add virDomainHubDefFree to libvirt_private.syms qemu: implement usb hub device hotplug qemu: implement usb hub device hotunplug news: Cold(un)plug and hot(un)plug support for usb hub device docs/news.xml | 5 ++ src/conf/domain_conf.c | 30 +++++++++ src/conf/domain_conf.h | 3 + src/libvirt_private.syms | 2 + src/qemu/qemu_alias.c | 22 +++++-- src/qemu/qemu_alias.h | 4 ++ src/qemu/qemu_command.c | 2 +- src/qemu/qemu_command.h | 4 ++ src/qemu/qemu_driver.c | 30 +++++++-- src/qemu/qemu_hotplug.c | 132 ++++++++++++++++++++++++++++++++++++++- src/qemu/qemu_hotplug.h | 12 ++++ 11 files changed, 236 insertions(+), 10 deletions(-) -- 2.19.1

2 21

[libvirt] [PATCH v3 00/20] Incremental Backup API additions
by Eric Blake 07 Nov '18

07 Nov '18

The following is the latest version of my API proposal for incremental backups, and matches the demo I will be presenting as part of my KVM Forum 2018 talk tomorrow afternoon: https://kvmforum2018.sched.com/event/FzuB/facilitating-incremental-backup-e… The patches are also available via https://repo.or.cz/libvirt/ericb.git at the tag backup-v3. The qemu integration is still incomplete (I don't have push mode backups working, only pull mode; and there are still some things to fine-tune as I figure out how to better support external snapshots and block commit/stream), and I still haven't gotten any opinions on whether it is better to have: virDomainSnapshotCreateXML("<domainsnapshot>...") # existing virDomainBackupBegin("<domainbackup>...", "<domaincheckpoint>...") # this series virDomainSnapshotCheckpointCreateXML("<domainsnapshot>...", "<domaincheckpoint>...") # new or to make checkpoint creation part of the snapshot and backup XML, as in: virDomainSnapshotCreateXML("<domainsnapshot><domaincheckpoint>...</domainsnapshot>") # extension of existing virDomainBackupBegin("<domainbackup><domaincheckpoint>...</domainbackup>") # tweak to this series It's also obvious that we don't want to check in the qemu implementation until after Peter's blockdev work has landed AND qemu has gotten rid of the x- prefix in its QMP interactions, although the state of this series SHOULD be sufficient to prove that the proposed interface is at least flexible enough to adapt to whatever qemu tweaks land and whatever other hypervisors may support. Whether to accept the API now (to make backporting qemu support downstream across versions without rebasing to an even later date for the API) is a harder question; Jirka has already expressed distaste at the idea. There are probably still loads of things needing fixing in this version, I already know I did not address all of Peter's review comments on v2. My unit test coverage is not very complete on the XML parsing, and there are definitely some hacks in place to get things to the point of a working demo that need to be polished for robustness. Below is a diff since the v2 posting (patches 1-10 here, for later patches a comparison against the state of my tree at the time I posted v2): https://www.redhat.com/archives/libvir-list/2018-October/msg00700.html 001/20:[----] [--] 'snapshots: Avoid term 'checkpoint' for full system snapshot' 002/20:[----] [--] 'domain_conf: Expose virDomainStorageNetworkParseHost' 003/20:[down] 'qemu: Allow optional export name during NBD export' 004/20:[----] [--] 'backup: Document nuances between different state capture APIs' 005/20:[----] [--] 'backup: Introduce virDomainCheckpointPtr' 006/20:[0012] [FC] 'backup: Document new XML for backups' 007/20:[----] [--] 'backup: Introduce virDomainCheckpoint APIs' 008/20:[0024] [FC] 'backup: Introduce virDomainBackup APIs' 009/20:[----] [--] 'backup: Add new domain:checkpoint access control' 010/20:[0001] [FC] 'backup: Implement backup APIs for remote driver' 011/20:[0007] [FC] 'wip: backup: Parse and output checkpoint XML' 012/20:[0199] [FC] 'wip: backup: Parse and output backup XML' 013/20:[----] [--] 'backup: Implement virsh support for checkpoints' 014/20:[----] [--] 'wip: backup: virsh support for backup' 015/20:[0223] [FC] 'backup: Add new qemu monitor interactions' 016/20:[0123] [FC] 'backup: qemu: Implement metadata tracking for checkpoint APIs' 017/20:[down] 'wip: backup: Wire up qemu checkpoint commands over QMP' 018/20:[0072] [FC] 'wip: backup: qemu: Implement framework for backup job APIs' 019/20:[down] 'backup: Wire up qemu full pull backup commands over QMP' 020/20:[down] 'backup: implement qemu incremental pull backup' No direct dependency on this one, but included in my git tag: https://www.redhat.com/archives/libvir-list/2018-October/msg00899.html Eric Blake (20): snapshots: Avoid term 'checkpoint' for full system snapshot domain_conf: Expose virDomainStorageNetworkParseHost qemu: Allow optional export name during NBD export backup: Document nuances between different state capture APIs backup: Introduce virDomainCheckpointPtr backup: Document new XML for backups backup: Introduce virDomainCheckpoint APIs backup: Introduce virDomainBackup APIs backup: Add new domain:checkpoint access control backup: Implement backup APIs for remote driver wip: backup: Parse and output checkpoint XML wip: backup: Parse and output backup XML backup: Implement virsh support for checkpoints wip: backup: virsh support for backup backup: Add new qemu monitor interactions backup: qemu: Implement metadata tracking for checkpoint APIs wip: backup: Wire up qemu checkpoint commands over QMP wip: backup: qemu: Implement framework for backup job APIs backup: Wire up qemu full pull backup commands over QMP backup: implement qemu incremental pull backup include/libvirt/virterror.h | 6 +- src/util/virerror.c | 21 +- include/libvirt/libvirt-domain-checkpoint.h | 177 ++ include/libvirt/libvirt-domain-snapshot.h | 2 +- include/libvirt/libvirt-domain.h | 17 +- include/libvirt/libvirt.h | 3 +- src/access/viraccessperm.h | 8 +- src/conf/checkpoint_conf.h | 218 +++ src/conf/domain_conf.h | 16 +- src/datatypes.h | 31 +- src/driver-hypervisor.h | 74 +- src/qemu/qemu_conf.h | 2 + src/qemu/qemu_domain.h | 29 +- src/qemu/qemu_monitor.h | 17 + src/qemu/qemu_monitor_json.h | 19 + tools/virsh-checkpoint.h | 29 + tools/virsh-completer.h | 4 + tools/virsh-util.h | 3 + tools/virsh.h | 1 + docs/Makefile.am | 3 + docs/apibuild.py | 2 + docs/docs.html.in | 9 +- docs/domainstatecapture.html.in | 314 ++++ docs/format.html.in | 1 + docs/formatcheckpoint.html.in | 291 ++++ docs/formatsnapshot.html.in | 33 +- docs/index.html.in | 3 +- docs/schemas/domainbackup.rng | 185 ++ docs/schemas/domaincheckpoint.rng | 94 ++ examples/object-events/event-test.c | 3 + libvirt.spec.in | 3 + mingw-libvirt.spec.in | 6 + po/POTFILES | 3 + src/Makefile.am | 2 + src/access/viraccessperm.c | 5 +- src/conf/Makefile.inc.am | 2 + src/conf/checkpoint_conf.c | 1541 +++++++++++++++++ src/conf/domain_conf.c | 52 +- src/conf/snapshot_conf.c | 4 +- src/datatypes.c | 62 +- src/libvirt-domain-checkpoint.c | 925 ++++++++++ src/libvirt-domain-snapshot.c | 7 +- src/libvirt-domain.c | 8 +- src/libvirt_private.syms | 30 + src/libvirt_public.syms | 23 + src/qemu/qemu_conf.c | 5 + src/qemu/qemu_domain.c | 205 ++- src/qemu/qemu_driver.c | 1494 ++++++++++++++++- src/qemu/qemu_migration.c | 2 +- src/qemu/qemu_monitor.c | 73 +- src/qemu/qemu_monitor_json.c | 217 +++ src/qemu/qemu_process.c | 7 + src/remote/remote_daemon_dispatch.c | 15 + src/remote/remote_driver.c | 33 +- src/remote/remote_protocol.x | 239 ++- src/remote_protocol-structs | 129 ++ src/rpc/gendispatch.pl | 32 +- tests/Makefile.am | 15 +- tests/domainbackupxml2xmlin/backup-pull.xml | 9 + tests/domainbackupxml2xmlin/backup-push.xml | 9 + tests/domainbackupxml2xmlin/empty.xml | 1 + tests/domainbackupxml2xmlout/backup-pull.xml | 9 + tests/domainbackupxml2xmlout/backup-push.xml | 9 + tests/domainbackupxml2xmlout/empty.xml | 7 + tests/domaincheckpointxml2xmlin/empty.xml | 1 + tests/domaincheckpointxml2xmlin/sample.xml | 7 + tests/domaincheckpointxml2xmlout/empty.xml | 10 + tests/domaincheckpointxml2xmlout/sample.xml | 16 + tests/domaincheckpointxml2xmltest.c | 231 +++ tests/qemumonitorjsontest.c | 2 +- tests/virschematest.c | 4 + tools/Makefile.am | 3 +- tools/virsh-checkpoint.c | 1578 ++++++++++++++++++ tools/virsh-completer.c | 52 +- tools/virsh-domain.c | 6 +- tools/virsh-snapshot.c | 2 +- tools/virsh-util.c | 11 + tools/virsh.c | 2 + tools/virsh.pod | 14 +- 79 files changed, 8619 insertions(+), 118 deletions(-) create mode 100644 include/libvirt/libvirt-domain-checkpoint.h create mode 100644 src/conf/checkpoint_conf.h create mode 100644 tools/virsh-checkpoint.h create mode 100644 docs/domainstatecapture.html.in create mode 100644 docs/formatcheckpoint.html.in create mode 100644 docs/schemas/domainbackup.rng create mode 100644 docs/schemas/domaincheckpoint.rng create mode 100644 src/conf/checkpoint_conf.c create mode 100644 src/libvirt-domain-checkpoint.c create mode 100644 tests/domainbackupxml2xmlin/backup-pull.xml create mode 100644 tests/domainbackupxml2xmlin/backup-push.xml create mode 100644 tests/domainbackupxml2xmlin/empty.xml create mode 100644 tests/domainbackupxml2xmlout/backup-pull.xml create mode 100644 tests/domainbackupxml2xmlout/backup-push.xml create mode 100644 tests/domainbackupxml2xmlout/empty.xml create mode 100644 tests/domaincheckpointxml2xmlin/empty.xml create mode 100644 tests/domaincheckpointxml2xmlin/sample.xml create mode 100644 tests/domaincheckpointxml2xmlout/empty.xml create mode 100644 tests/domaincheckpointxml2xmlout/sample.xml create mode 100644 tests/domaincheckpointxml2xmltest.c create mode 100644 tools/virsh-checkpoint.c -- 2.17.2

3 23

[libvirt] [PATCH] qemu: Fix debug message in qemuProcessHandleResume
by Jiri Denemark 07 Nov '18

07 Nov '18

The message talks about "resumed" state, which is a bit confusing. While we have a "resumed" event, the corresponding state is called "running". Signed-off-by: Jiri Denemark <jdenemar(a)redhat.com> --- src/qemu/qemu_process.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 59ca7cd333..4e93b2d741 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -721,7 +721,7 @@ qemuProcessHandleResume(qemuMonitorPtr mon ATTRIBUTE_UNUSED, if (virDomainObjGetState(vm, NULL) != VIR_DOMAIN_RUNNING) { eventDetail = qemuDomainRunningReasonToResumeEvent(reason); - VIR_DEBUG("Transitioned guest %s out of paused into resumed state, " + VIR_DEBUG("Transitioned guest %s out of paused into running state, " "reason '%s', event detail %d", vm->def->name, virDomainRunningReasonTypeToString(reason), eventDetail); -- 2.19.1

2 1

[libvirt] [PATCH v2 0/3] qemu: Restore lost shutdown reason
by John Ferlan 07 Nov '18

07 Nov '18

v1: https://www.redhat.com/archives/libvir-list/2018-October/msg00945.html Changes since v1: Patch 1 (NEW) - Set the priv->allowReboot prior to any error processing since we could/should be using that. Patch 2 (ADJUSTED LOGIC) - Rather than open code the "reason" to use the -no-shutdown flag, let's create a qemu_domain helper for that so that both the command line building and the Reconnection failure logic can use it. Patch 3 (NEW) - Let's narrow the window for using VIR_DOMAIN_SHUTOFF_CRASHED to just the period where we try to open a monitor channel. If we cannot do so, then "assume" the reason was crashed. There are a few open failure steps that may not exactly fit the model, but those are probably splitting hairs. John Ferlan (3): qemu: Move allow reboot check setting qemu: Restore lost shutdown reason qemu: Narrow the shutdown reconnection failure reason window src/qemu/qemu_command.c | 6 +----- src/qemu/qemu_domain.c | 17 +++++++++++++++++ src/qemu/qemu_domain.h | 3 +++ src/qemu/qemu_process.c | 27 ++++++++++++++++++--------- 4 files changed, 39 insertions(+), 14 deletions(-) -- 2.17.2

2 10

[libvirt] [jenkins-ci PATCH 0/4] Add Fedora 29, drop Fedora 27
by Andrea Bolognani 07 Nov '18

07 Nov '18

It's that time of the year again :) Andrea Bolognani (4): guests: Add Fedora 29 Build on Fedora 29 Stop building on Fedora 27 guests: Drop Fedora 27 guests/host_vars/libvirt-fedora-27/docker.yml | 2 - guests/host_vars/libvirt-fedora-29/docker.yml | 2 + .../install.yml | 2 +- .../main.yml | 2 +- guests/inventory | 2 +- guests/playbooks/build/jobs/defaults.yml | 4 +- .../playbooks/build/projects/libvirt-dbus.yml | 6 +- .../build/projects/libvirt-ocaml.yml | 2 +- .../build/projects/libvirt-sandbox.yml | 4 +- .../playbooks/build/projects/libvirt-tck.yml | 4 +- guests/playbooks/build/projects/libvirt.yml | 2 +- .../playbooks/build/projects/virt-manager.yml | 6 +- .../playbooks/build/projects/virt-viewer.yml | 1 + guests/vars/mappings.yml | 1 - guests/vars/vault.yml | 82 +++++++++---------- jobs/defaults.yaml | 4 +- projects/libvirt-dbus.yaml | 6 +- projects/libvirt-ocaml.yaml | 2 +- projects/libvirt-sandbox.yaml | 4 +- projects/libvirt-tck.yaml | 4 +- projects/libvirt.yaml | 2 +- projects/virt-manager.yaml | 6 +- projects/virt-viewer.yaml | 1 + 23 files changed, 76 insertions(+), 75 deletions(-) delete mode 100644 guests/host_vars/libvirt-fedora-27/docker.yml create mode 100644 guests/host_vars/libvirt-fedora-29/docker.yml rename guests/host_vars/{libvirt-fedora-27 => libvirt-fedora-29}/install.yml (66%) rename guests/host_vars/{libvirt-fedora-27 => libvirt-fedora-29}/main.yml (95%) -- 2.19.1

2 5

[libvirt] [PATCH] libxl: Properly dispose libxl_domain_config object
by Jim Fehlig 06 Nov '18

06 Nov '18

V2 of the libxl soft reset patch, which was pushed as commit da4b0fd9, dropped the hunk that disposed of the libxl_domain_config object. Add the missing hunk to properly dispose the object. Signed-off-by: Jim Fehlig <jfehlig(a)suse.com> --- Pushing as trivial... src/libxl/libxl_domain.c | 1 + 1 file changed, 1 insertion(+) diff --git a/src/libxl/libxl_domain.c b/src/libxl/libxl_domain.c index 6aca7eebf8..5fe3f44fbe 100644 --- a/src/libxl/libxl_domain.c +++ b/src/libxl/libxl_domain.c @@ -605,6 +605,7 @@ libxlDomainShutdownThread(void *opaque) virObjectEventStateQueue(driver->domainEventState, dom_event); libxl_event_free(cfg->ctx, ev); VIR_FREE(shutdown_info); + libxl_domain_config_dispose(&d_config); virObjectUnref(cfg); } -- 2.18.0

1 0

[libvirt] [PATCH v2] lxc: Include support to lxc version 3.0 or higher.
by Julio Faracco 06 Nov '18

06 Nov '18

This patch introduce the new settings for LXC 3.0 or higher. The older versions keep the compatibility to deprecated settings for LXC, but after release 3.0, the compatibility was removed. This commit adds the support to the refactored settings. Signed-off-by: Julio Faracco <jcfaracco(a)gmail.com> --- src/lxc/lxc_native.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) diff --git a/src/lxc/lxc_native.c b/src/lxc/lxc_native.c index cbdec723dd..8604cbaf46 100644 --- a/src/lxc/lxc_native.c +++ b/src/lxc/lxc_native.c @@ -200,7 +200,9 @@ lxcSetRootfs(virDomainDefPtr def, int type = VIR_DOMAIN_FS_TYPE_MOUNT; VIR_AUTOFREE(char *) value = NULL; - if (virConfGetValueString(properties, "lxc.rootfs", &value) <= 0) + if (virConfGetValueString(properties, "lxc.rootfs", &value) <= 0 && + /* Legacy config keys were removed after release 3.0. */ + virConfGetValueString(properties, "lxc.rootfs.path", &value) <= 0) return -1; if (STRPREFIX(value, "/dev/")) @@ -684,7 +686,9 @@ lxcCreateConsoles(virDomainDefPtr def, virConfPtr properties) virDomainChrDefPtr console; size_t i; - if (virConfGetValueString(properties, "lxc.tty", &value) <= 0) + if (virConfGetValueString(properties, "lxc.tty", &value) <= 0 && + /* Legacy config keys were removed after release 3.0. */ + virConfGetValueString(properties, "lxc.tty.max", &value) <= 0) return 0; if (virStrToLong_i(value, NULL, 10, &nbttys) < 0) { @@ -724,7 +728,7 @@ lxcIdmapWalkCallback(const char *name, virConfValuePtr value, void *data) char type; unsigned long start, target, count; - if (STRNEQ(name, "lxc.id_map") || !value->str) + if (STRNEQ(name, "lxc.id_map") || STRNEQ(name, "lxc.idmap") || !value->str) return 0; if (sscanf(value->str, "%c %lu %lu %lu", &type, @@ -1041,7 +1045,9 @@ lxcParseConfigString(const char *config, if (VIR_STRDUP(vmdef->os.init, "/sbin/init") < 0) goto error; - if (virConfGetValueString(properties, "lxc.utsname", &value) <= 0 || + if ((virConfGetValueString(properties, "lxc.utsname", &value) <= 0 && + /* Legacy config keys were removed after release 3.0. */ + virConfGetValueString(properties, "lxc.uts.name", &value) <= 0) || VIR_STRDUP(vmdef->name, value) < 0) goto error; if (!vmdef->name && (VIR_STRDUP(vmdef->name, "unnamed") < 0)) @@ -1051,7 +1057,9 @@ lxcParseConfigString(const char *config, goto error; /* Look for fstab: we shouldn't have it */ - if (virConfGetValue(properties, "lxc.mount")) { + if (virConfGetValue(properties, "lxc.mount") || + /* Legacy config keys were removed after release 3.0. */ + virConfGetValue(properties, "lxc.mount.fstab")) { virReportError(VIR_ERR_ARGUMENT_UNSUPPORTED, "%s", _("lxc.mount found, use lxc.mount.entry lines instead")); goto error; -- 2.17.1

3 2

[libvirt] [PATCH v4 0/2] Refactor virFileIsCDROM to check cdrom status
by Han Han 06 Nov '18

06 Nov '18

v3: https://www.redhat.com/archives/libvir-list/2018-July/msg00675.html v2: https://www.redhat.com/archives/libvir-list/2018-July/msg00655.html v1: https://www.redhat.com/archives/libvir-list/2018-July/msg00103.html Refactor virFileIsCDROM to virFileCheckCDROM and add new argument filled with cdrom status. Give more detailed when fail to read cdrom backend vol. Han Han (2): util: Refactor virFileIsCDROM to virFileCheckCDROM storage: Improve error handling on cdrom backend src/libvirt_private.syms | 2 +- src/qemu/qemu_domain.c | 4 ++-- src/storage/storage_util.c | 32 ++++++++++++++++++++++++++++++++ src/util/virfile.c | 36 +++++++++++++++++++++++++++++++----- src/util/virfile.h | 12 +++++++++++- 5 files changed, 77 insertions(+), 9 deletions(-) -- 2.19.1

2 4

[libvirt] [PATCH V2 0/3] libxl: add support for soft reset
by Jim Fehlig 06 Nov '18

06 Nov '18

Patches 1 and 2 are new to V2 and make slight improvements to libxlDomainShutdownThread. Patch 3 is adjusted to work with Xen 4.6. Jim Fehlig (3): libxl: remove redundant calls to virObjectEventStateQueue libxl: Remove some goto labels in libxlDomainShutdownThread libxl: add support for soft reset src/libxl/libxl_domain.c | 99 ++++++++++++++++++++++++++++------------ 1 file changed, 69 insertions(+), 30 deletions(-) -- 2.18.0

2 5

[libvirt] RFC: VIR_DOMAIN_SNAPSHOT_LIST_NO_METADATA is not functional?
by Han Han 06 Nov '18

06 Nov '18

Hello, I found snapshot APIs(like virDomainSnapshotNum) invoked with VIR_DOMAIN_SNAPSHOT_LIST_NO_METADATA will return 0 even there are internal no-metadata snapshots in the domain. Then I find the reason is in virDomainSnapshotObjListGetNames(): 937 /* If this common code is being used, we assume that all snapshots 938 ┆* have metadata, and thus can handle METADATA up front as an 939 ┆* all-or-none filter. XXX This might not always be true, if we 940 ┆* add the ability to track qcow2 internal snapshots without the 941 ┆* use of metadata. */ 942 if ((data.flags & VIR_DOMAIN_SNAPSHOT_FILTERS_METADATA) == 943 ┆ VIR_DOMAIN_SNAPSHOT_LIST_NO_METADATA) 944 ┆ return 0; So currently, with VIR_DOMAIN_SNAPSHOT_LIST_NO_METADATA, no snapshot will be returned. I checked the commit. It is really old(6478ec1673a Eric Blake 2012-08-13 18:09:12 -0600) . I guess it was initially designed for the function to list internal snapshots without metadata. However, now internal snapshot seems lower prioritized than external snapshot. Do we have plan to design this function? Since the APIs invoked with this flag don't return the **right** result, if the function for VIR_DOMAIN_SNAPSHOT_LIST_NO_METADATA will not be designed, how will we deal with the flag? Remove it from code OR update the docs to mark it unsupported? -- Best regards, ----------------------------------- Han Han Quality Engineer Redhat. Email: hhan(a)redhat.com Phone: +861065339333

2 2

[libvirt] [PATCH v2] snapshot: Don't hose list on deletion failure
by Eric Blake 06 Nov '18

06 Nov '18

If qemuDomainSnapshotDiscard() fails for any reason (rare, but possible with an ill-timed ENOMEM or if qemuDomainSnapshotForEachQcow2() has problems talking to the qemu guest monitor), then an attempt to retry the snapshot deletion API will crash because we didn't undo the effects of virDomainSnapshotDropParent() temporarily rearranging the internal list structures, and the second attempt to drop parents will dereference NULL. Fix it by instead noting that there are only two callers to qemuDomainSnapshotDiscard(), and only one of the two callers wants the parent to be updated; thus we can move the call to virDomainSnapshotDropParent() into a code path that only gets executed on success. Signed-off-by: Eric Blake <eblake(a)redhat.com> --- v2: avoid use-after-free --- src/qemu/qemu_domain.c | 6 ++++-- src/qemu/qemu_driver.c | 1 - 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index f00f1b3fdb..dd67be5e2a 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -8246,7 +8246,7 @@ int qemuDomainSnapshotDiscard(virQEMUDriverPtr driver, virDomainObjPtr vm, virDomainSnapshotObjPtr snap, - bool update_current, + bool update_parent, bool metadata_only) { char *snapFile = NULL; @@ -8275,7 +8275,7 @@ qemuDomainSnapshotDiscard(virQEMUDriverPtr driver, goto cleanup; if (snap == vm->current_snapshot) { - if (update_current && snap->def->parent) { + if (update_parent && snap->def->parent) { parentsnap = virDomainSnapshotFindByName(vm->snapshots, snap->def->parent); if (!parentsnap) { @@ -8298,6 +8298,8 @@ qemuDomainSnapshotDiscard(virQEMUDriverPtr driver, if (unlink(snapFile) < 0) VIR_WARN("Failed to unlink %s", snapFile); + if (update_parent) + virDomainSnapshotDropParent(snap); virDomainSnapshotObjListRemove(vm->snapshots, snap); ret = 0; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index a52e2495d5..9f71641dfa 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -16526,7 +16526,6 @@ qemuDomainSnapshotDelete(virDomainSnapshotPtr snapshot, snap->first_child = NULL; ret = 0; } else { - virDomainSnapshotDropParent(snap); ret = qemuDomainSnapshotDiscard(driver, vm, snap, true, metadata_only); } -- 2.17.2

2 2

[libvirt] [PATCH v7 00/14] PCI passthrough support on s390
by Yi Min Zhao 06 Nov '18

06 Nov '18

Abstract ======== The PCI representation in QEMU has been extended for S390 allowing configuration of zPCI attributes like uid (user-defined identifier) and fid (PCI function identifier). The details can be found here: https://lists.gnu.org/archive/html/qemu-devel/2016-06/msg07262.html To support the new zPCI feature of the S390 platform, a new element of PCI address is introduced. It has two optional attributes, @uid and @fid. For example: <hostdev mode='subsystem' type='pci'> <driver name='vfio'/> <source> <address domain='0x0001' bus='0x00' slot='0x00' function='0x0'/> </source> <address type='pci' domain='0x0000' bus='0x00' slot='0x01' function='0x0'> <zpci uid='0x0003' fid='0x00000027'/> </address> </hostdev> If they are defined by the user, unique values within the guest domain must be used. If they are not specified and the architecture requires them, they are automatically generated with non-conflicting values. zPCI address as an extension of the PCI address are stored in a new structure 'virZPCIDeviceAddress' which is a member of common PCI Address structure. Additionally, two hashtables are used for assignment and reservation of zPCI uid/fid. In support of extending the PCI address, a new PCI address extension flag is introduced. This extension flag allows is not only dedicated for the S390 platform but also other architectures needing certain extensions to PCI address space. Code Base ========= commit in master: 3a1cdb06fd conf: Fix bug in finding alloc through matching vcpus Change Log ========== v6->v7: 1. Optimize some functions' names and code logic. 2. Fixup build error. 3. Add negative test case for patch 9. 4. Use virXMLFormatElement() in virDomainDeviceInfoFormat(). v5->v6: 1. Modify zPCI XML definition. 2. Optimize the logic of zPCI address assignment and reservation. 3. Add extension flag into PCI address structure. 4. Update commit messages. v4->v5: 1. Update the version number. 2. Fixup code style error. 3. Separate qemu code into single patch. 4. Rebase the patches to the new code of master branch. v3->v4: 1. Update docs. 2. Format code style. 3. Optimize zPCI support check. 4. Move the check of zPCI defined in xml but unsupported by Qemu to qemuDomainDeviceDefValidate(). 5. Change zpci address member of PCI address struct from pointer to instance. 6. Modify zpci address definition principle. Currently the user must either define both of uid and fid or not. v2->v3: 1. Revise code style. 2. Update test cases. 3. Introduce qemuDomainCollectPCIAddressExtension() to collect PCI extension addresses. 4. Introduce virDeviceInfoPCIAddressExtensionPresent() to check if zPCI address exists. 5. Optimize zPCI address check logic. 6. Optimize passed parameters of zPCI addr alloc/release/reserve functions. 7. Report enum range error in qemuDomainDeviceSupportZPCI(). 8. Update commit messages. v1->v2: 1. Separate test commit and merge testcases into corresponding commits that introduce the functionalities firstly. 2. Spare some checks for zpci device. 3. Add vsock and controller support. 4. Add uin32 type schema. 5. Rename zpciuid and zpcifid to zpci_uid and zpci_fid. 6. Always return multibus support on S390. Yi Min Zhao (14): conf: Add definitions for 'uid' and 'fid' PCI address attributes qemu: Introduce zPCI capability conf: Introduce a new PCI address extension flag qemu: Enable PCI multi bus for S390 guests qemu: Auto add pci-root for s390/s390x guests conf: Introduce address caching for PCI extensions conf: use virXMLFormatElement() in virDomainDeviceInfoFormat() conf: Introduce parser, formatter for uid and fid qemu: Add zPCI address definition check conf: Allocate/release 'uid' and 'fid' in PCI address qemu: Generate and use zPCI device in QEMU command line qemu: Add hotpluging support for PCI devices on S390 guests docs: Add 'uid' and 'fid' information news: Update news for PCI address extension attributes cfg.mk | 1 + docs/formatdomain.html.in | 10 +- docs/news.xml | 11 + docs/schemas/basictypes.rng | 27 ++ docs/schemas/domaincommon.rng | 1 + src/bhyve/bhyve_device.c | 3 +- src/conf/device_conf.c | 69 ++++ src/conf/device_conf.h | 7 + src/conf/domain_addr.c | 340 +++++++++++++++++- src/conf/domain_addr.h | 27 +- src/conf/domain_conf.c | 50 ++- src/libvirt_private.syms | 7 + src/qemu/qemu_capabilities.c | 6 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 104 ++++++ src/qemu/qemu_command.h | 2 + src/qemu/qemu_domain.c | 37 ++ src/qemu/qemu_domain_address.c | 205 ++++++++++- src/qemu/qemu_hotplug.c | 160 ++++++++- src/util/virpci.c | 26 ++ src/util/virpci.h | 15 + .../caps_2.10.0.s390x.xml | 1 + .../caps_2.11.0.s390x.xml | 1 + .../caps_2.12.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_2.7.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_2.8.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_2.9.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.s390x.xml | 1 + .../disk-virtio-s390-zpci.args | 26 ++ .../disk-virtio-s390-zpci.xml | 19 + .../hostdev-vfio-zpci-autogenerate.args | 25 ++ .../hostdev-vfio-zpci-autogenerate.xml | 18 + .../hostdev-vfio-zpci-boundaries.args | 29 ++ .../hostdev-vfio-zpci-boundaries.xml | 30 ++ .../hostdev-vfio-zpci-multidomain-many.args | 39 ++ .../hostdev-vfio-zpci-multidomain-many.xml | 79 ++++ .../hostdev-vfio-zpci-wrong-arch.xml | 34 ++ tests/qemuxml2argvdata/hostdev-vfio-zpci.args | 25 ++ tests/qemuxml2argvdata/hostdev-vfio-zpci.xml | 21 ++ tests/qemuxml2argvtest.c | 22 ++ .../disk-virtio-s390-zpci.xml | 31 ++ .../hostdev-vfio-zpci-autogenerate.xml | 34 ++ .../hostdev-vfio-zpci-boundaries.xml | 48 +++ .../hostdev-vfio-zpci-multidomain-many.xml | 97 +++++ .../qemuxml2xmloutdata/hostdev-vfio-zpci.xml | 32 ++ tests/qemuxml2xmltest.c | 17 + 46 files changed, 1707 insertions(+), 35 deletions(-) create mode 100644 tests/qemuxml2argvdata/disk-virtio-s390-zpci.args create mode 100644 tests/qemuxml2argvdata/disk-virtio-s390-zpci.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-autogenerate.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-autogenerate.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-boundaries.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-boundaries.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-multidomain-many.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-multidomain-many.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-wrong-arch.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci.xml create mode 100644 tests/qemuxml2xmloutdata/disk-virtio-s390-zpci.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci-autogenerate.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci-boundaries.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci-multidomain-many.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci.xml -- Yi Min

2 23

[libvirt] [PATCH RESEND] qemu: Process RDMA GID state change event
by Yuval Shaia 06 Nov '18

06 Nov '18

This event is emitted on the monitor when a GID table in pvrdma device is modified and the change needs to be propagate to the backend RDMA device's GID table. The control over the RDMA device's GID table is done by updating the device's Ethernet function addresses. Usually the first GID entry is determine by the MAC address, the second by the first IPv6 address and the third by the IPv4 address. Other entries can be added by adding more IP addresses. The opposite is the same, i.e. whenever an address is removed, the corresponding GID entry is removed. The process is done by the network and RDMA stacks. Whenever an address is added the ib_core driver is notified and calls the device driver's add_gid function which in turn update the device. To support this in pvrdma device we need to hook into the create_bind and destroy_bind HW commands triggered by pvrdma driver in guest. Whenever a changed is made to the pvrdma device's GID table a special QMP messages is sent to be processed by libvirt to update the address of the backend Ethernet device. Signed-off-by: Yuval Shaia <yuval.shaia(a)oracle.com> --- src/qemu/qemu_domain.c | 3 ++ src/qemu/qemu_domain.h | 15 +++++++++ src/qemu/qemu_driver.c | 40 ++++++++++++++++++++++++ src/qemu/qemu_monitor.c | 28 +++++++++++++++++ src/qemu/qemu_monitor.h | 13 ++++++++ src/qemu/qemu_monitor_json.c | 36 ++++++++++++++++++++++ src/qemu/qemu_process.c | 59 ++++++++++++++++++++++++++++++++++++ 7 files changed, 194 insertions(+) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index ba3fff607a..8da54c7ee9 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -13479,6 +13479,9 @@ qemuProcessEventFree(struct qemuProcessEvent *event) case QEMU_PROCESS_EVENT_GUESTPANIC: qemuMonitorEventPanicInfoFree(event->data); break; + case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED: + qemuMonitorEventRdmaGidStatusFree(event->data); + break; case QEMU_PROCESS_EVENT_WATCHDOG: case QEMU_PROCESS_EVENT_DEVICE_DELETED: case QEMU_PROCESS_EVENT_NIC_RX_FILTER_CHANGED: diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h index 80bd4bde91..1b188843e3 100644 --- a/src/qemu/qemu_domain.h +++ b/src/qemu/qemu_domain.h @@ -478,6 +478,18 @@ struct _qemuDomainVsockPrivate { }; +typedef struct _qemuDomainRdmaGidStatusChangedPrivate qemuDomainRdmaGidStatusChangedPrivate; +typedef qemuDomainRdmaGidStatusChangedPrivate *qemuDomainRdmaGidStatusChangedPrivatePtr; +struct _qemuDomainRdmaGidStatusChangedPrivate { + virObject parent; + + char *netdev; + bool gid_status; + uint64_t subnet_prefix; + uint64_t interface_id; +}; + + typedef enum { QEMU_PROCESS_EVENT_WATCHDOG = 0, QEMU_PROCESS_EVENT_GUESTPANIC, @@ -487,6 +499,7 @@ typedef enum { QEMU_PROCESS_EVENT_BLOCK_JOB, QEMU_PROCESS_EVENT_MONITOR_EOF, QEMU_PROCESS_EVENT_PR_DISCONNECT, + QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED, QEMU_PROCESS_EVENT_LAST } qemuProcessEventType; @@ -499,6 +512,8 @@ struct qemuProcessEvent { void *data; }; +void qemuMonitorEventRdmaGidStatusFree(qemuDomainRdmaGidStatusChangedPrivatePtr info); + void qemuProcessEventFree(struct qemuProcessEvent *event); typedef struct _qemuDomainLogContext qemuDomainLogContext; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index a52e2495d5..dc088d844f 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4788,6 +4788,43 @@ processPRDisconnectEvent(virDomainObjPtr vm) } +static void +processRdmaGidStatusChangedEvent(virDomainObjPtr vm, + qemuDomainRdmaGidStatusChangedPrivatePtr info) +{ + unsigned int prefix_len; + virSocketAddr addr = {0}; + int rc; + + if (!virDomainObjIsActive(vm)) + return; + + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + info->netdev, info->gid_status, info->subnet_prefix, + info->interface_id); + + if (info->subnet_prefix) { + prefix_len = 64; + uint32_t ipv6[4]; + memcpy(&ipv6[0], &info->subnet_prefix, sizeof(info->subnet_prefix)); + memcpy(&ipv6[2], &info->interface_id, sizeof(info->subnet_prefix)); + virSocketAddrSetIPv6AddrNetOrder(&addr, ipv6); + } else { + prefix_len = 24; + virSocketAddrSetIPv4AddrNetOrder(&addr, info->interface_id >> 32); + } + + if (info->gid_status) + rc = virNetDevIPAddrAdd(info->netdev, &addr, NULL, prefix_len); + else + rc = virNetDevIPAddrDel(info->netdev, &addr, prefix_len); + + if (rc) + VIR_ERROR(_("Fail to update address 0x%lx to %s"), info->interface_id, + info->netdev); +} + + static void qemuProcessEventHandler(void *data, void *opaque) { struct qemuProcessEvent *processEvent = data; @@ -4828,6 +4865,9 @@ static void qemuProcessEventHandler(void *data, void *opaque) case QEMU_PROCESS_EVENT_PR_DISCONNECT: processPRDisconnectEvent(vm); break; + case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED: + processRdmaGidStatusChangedEvent(vm, processEvent->data); + break; case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c index 7f7013e115..375ed7ceaf 100644 --- a/src/qemu/qemu_monitor.c +++ b/src/qemu/qemu_monitor.c @@ -1686,6 +1686,23 @@ qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon, } +int +qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id) +{ + int ret = -1; + VIR_DEBUG("mon=%p", mon); + VIR_DEBUG("netdev='%s',gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + netdev, gid_status, subnet_prefix, interface_id); + + QEMU_MONITOR_CALLBACK(mon, ret, domainRdmaGidStatusChanged, mon->vm, netdev, + gid_status, subnet_prefix, interface_id); + + return ret; +} + + int qemuMonitorSetCapabilities(qemuMonitorPtr mon) { @@ -4298,6 +4315,17 @@ qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfoPtr info) } +void +qemuMonitorEventRdmaGidStatusFree(qemuDomainRdmaGidStatusChangedPrivatePtr info) +{ + if (!info) + return; + + VIR_FREE(info->netdev); + VIR_FREE(info); +} + + int qemuMonitorSetWatchdogAction(qemuMonitorPtr mon, const char *action) diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h index 48b142a4f4..f5affe615a 100644 --- a/src/qemu/qemu_monitor.h +++ b/src/qemu/qemu_monitor.h @@ -281,6 +281,14 @@ typedef int (*qemuMonitorDomainPRManagerStatusChangedCallback)(qemuMonitorPtr mo bool connected, void *opaque); +typedef int (*qemuMonitorDomainRdmaGidStatusChangedCallback)(qemuMonitorPtr mon, + virDomainObjPtr vm, + const char *netdev, + bool gid_status, + uint64_t subnet_prefix, + uint64_t interface_id, + void *opaque); + typedef struct _qemuMonitorCallbacks qemuMonitorCallbacks; typedef qemuMonitorCallbacks *qemuMonitorCallbacksPtr; struct _qemuMonitorCallbacks { @@ -314,6 +322,7 @@ struct _qemuMonitorCallbacks { qemuMonitorDomainBlockThresholdCallback domainBlockThreshold; qemuMonitorDomainDumpCompletedCallback domainDumpCompleted; qemuMonitorDomainPRManagerStatusChangedCallback domainPRManagerStatusChanged; + qemuMonitorDomainRdmaGidStatusChangedCallback domainRdmaGidStatusChanged; }; char *qemuMonitorEscapeArg(const char *in); @@ -448,6 +457,10 @@ int qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon, const char *prManager, bool connected); +int qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id); + int qemuMonitorStartCPUs(qemuMonitorPtr mon); int qemuMonitorStopCPUs(qemuMonitorPtr mon); diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c index 3de298c9e2..8df9b426ba 100644 --- a/src/qemu/qemu_monitor_json.c +++ b/src/qemu/qemu_monitor_json.c @@ -91,6 +91,7 @@ static void qemuMonitorJSONHandleAcpiOstInfo(qemuMonitorPtr mon, virJSONValuePtr static void qemuMonitorJSONHandleBlockThreshold(qemuMonitorPtr mon, virJSONValuePtr data); static void qemuMonitorJSONHandleDumpCompleted(qemuMonitorPtr mon, virJSONValuePtr data); static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data); +static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data); typedef struct { const char *type; @@ -114,6 +115,7 @@ static qemuEventHandler eventHandlers[] = { { "NIC_RX_FILTER_CHANGED", qemuMonitorJSONHandleNicRxFilterChanged, }, { "POWERDOWN", qemuMonitorJSONHandlePowerdown, }, { "PR_MANAGER_STATUS_CHANGED", qemuMonitorJSONHandlePRManagerStatusChanged, }, + { "RDMA_GID_STATUS_CHANGED", qemuMonitorJSONHandleRdmaGidStatusChanged, }, { "RESET", qemuMonitorJSONHandleReset, }, { "RESUME", qemuMonitorJSONHandleResume, }, { "RTC_CHANGE", qemuMonitorJSONHandleRTCChange, }, @@ -1351,6 +1353,40 @@ static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, } +static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, + virJSONValuePtr data) +{ + const char *netdev; + bool gid_status; + unsigned long long subnet_prefix, interface_id; + + if (!(netdev = virJSONValueObjectGetString(data, "netdev"))) { + VIR_WARN("missing netdev in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetBoolean(data, "gid-status", &gid_status)) { + VIR_WARN("missing gid-status in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "subnet-prefix", + &subnet_prefix)) { + VIR_WARN("missing subnet-prefix in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "interface-id", + &interface_id)) { + VIR_WARN("missing interface-id in GID_STATUS_CHANGED event"); + return; + } + + qemuMonitorEmitRdmaGidStatusChanged(mon, netdev, gid_status, subnet_prefix, + interface_id); +} + + int qemuMonitorJSONHumanCommandWithFd(qemuMonitorPtr mon, const char *cmd_str, diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 9cf971808c..45fc155d31 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -1703,6 +1703,64 @@ qemuProcessHandlePRManagerStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED, } +static int +qemuProcessHandleRdmaGidStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED, + virDomainObjPtr vm, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id, void *opaque) +{ + virQEMUDriverPtr driver = opaque; + qemuDomainObjPrivatePtr priv; + struct qemuProcessEvent *processEvent = NULL; + qemuDomainRdmaGidStatusChangedPrivatePtr rdmaGitStatusChangedPriv; + int ret = -1; + + virObjectLock(vm); + + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + netdev, gid_status, subnet_prefix, interface_id); + + priv = vm->privateData; + priv->prDaemonRunning = false; + + if (VIR_ALLOC(rdmaGitStatusChangedPriv) < 0) + goto out_unlock; + + if (VIR_STRDUP(rdmaGitStatusChangedPriv->netdev, netdev) < 0) + goto out_free_rdma_priv; + + rdmaGitStatusChangedPriv->gid_status = gid_status; + rdmaGitStatusChangedPriv->subnet_prefix = subnet_prefix; + rdmaGitStatusChangedPriv->interface_id = interface_id; + + if (VIR_ALLOC(processEvent) < 0) + goto out_free_rdma_priv_netdev; + + processEvent->eventType = QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED; + processEvent->vm = virObjectRef(vm); + processEvent->data = rdmaGitStatusChangedPriv; + + if (virThreadPoolSendJob(driver->workerPool, 0, processEvent) < 0) { + qemuProcessEventFree(processEvent); + virObjectUnref(vm); + goto out_free_rdma_priv_netdev; + } + + ret = 0; + goto out_unlock; + + out_free_rdma_priv_netdev: + VIR_FREE(rdmaGitStatusChangedPriv->netdev); + + out_free_rdma_priv: + VIR_FREE(rdmaGitStatusChangedPriv); + + out_unlock: + virObjectUnlock(vm); + return ret; +} + + static qemuMonitorCallbacks monitorCallbacks = { .eofNotify = qemuProcessHandleMonitorEOF, .errorNotify = qemuProcessHandleMonitorError, @@ -1732,6 +1790,7 @@ static qemuMonitorCallbacks monitorCallbacks = { .domainBlockThreshold = qemuProcessHandleBlockThreshold, .domainDumpCompleted = qemuProcessHandleDumpCompleted, .domainPRManagerStatusChanged = qemuProcessHandlePRManagerStatusChanged, + .domainRdmaGidStatusChanged = qemuProcessHandleRdmaGidStatusChanged, }; static void -- 2.17.2

2 3

[libvirt] [PATCH] lxc: Clang is complaining about possible NULL pointer.
by Julio Faracco 06 Nov '18

06 Nov '18

The array "mount" inside lxc_container is not being checked before for loop. Clang syntax scan is complaining about this segmentation fault. Signed-off-by: Julio Faracco <jcfaracco(a)gmail.com> --- src/lxc/lxc_container.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/lxc/lxc_container.c b/src/lxc/lxc_container.c index 918194dacd..6b7bcd8eb6 100644 --- a/src/lxc/lxc_container.c +++ b/src/lxc/lxc_container.c @@ -871,7 +871,7 @@ static int lxcContainerSetReadOnly(void) qsort(mounts, nmounts, sizeof(mounts[0]), virStringSortRevCompare); - for (i = 0; i < nmounts; i++) { + for (i = 0; i < nmounts && mounts; i++) { VIR_DEBUG("Bind readonly %s", mounts[i]); if (mount(mounts[i], mounts[i], "none", MS_BIND|MS_REC|MS_RDONLY|MS_REMOUNT, NULL) < 0) { virReportSystemError(errno, @@ -883,7 +883,7 @@ static int lxcContainerSetReadOnly(void) ret = 0; cleanup: - for (i = 0; i < nmounts; i++) + for (i = 0; i < nmounts && mounts; i++) VIR_FREE(mounts[i]); VIR_FREE(mounts); endmntent(procmnt); -- 2.17.1

3 2

[libvirt] [PATCH v2] qemu: Process RDMA GID state change event
by Yuval Shaia 06 Nov '18

06 Nov '18

This event is emitted on the monitor when a GID table in pvrdma device is modified and the change needs to be propagate to the backend RDMA device's GID table. The control over the RDMA device's GID table is done by updating the device's Ethernet function addresses. Usually the first GID entry is determine by the MAC address, the second by the first IPv6 address and the third by the IPv4 address. Other entries can be added by adding more IP addresses. The opposite is the same, i.e. whenever an address is removed, the corresponding GID entry is removed. The process is done by the network and RDMA stacks. Whenever an address is added the ib_core driver is notified and calls the device driver's add_gid function which in turn update the device. To support this in pvrdma device we need to hook into the create_bind and destroy_bind HW commands triggered by pvrdma driver in guest. Whenever a changed is made to the pvrdma device's GID table a special QMP messages is sent to be processed by libvirt to update the address of the backend Ethernet device. Signed-off-by: Yuval Shaia <yuval.shaia(a)oracle.com> --- v1 -> v2: * Address all comments from Michal Privoznik --- src/qemu/qemu_domain.c | 3 +++ src/qemu/qemu_domain.h | 1 + src/qemu/qemu_driver.c | 44 ++++++++++++++++++++++++++++++ src/qemu/qemu_monitor.c | 27 +++++++++++++++++++ src/qemu/qemu_monitor.h | 27 +++++++++++++++++++ src/qemu/qemu_monitor_json.c | 36 +++++++++++++++++++++++++ src/qemu/qemu_process.c | 52 ++++++++++++++++++++++++++++++++++++ 7 files changed, 190 insertions(+) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index ba3fff607a..8da54c7ee9 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -13479,6 +13479,9 @@ qemuProcessEventFree(struct qemuProcessEvent *event) case QEMU_PROCESS_EVENT_GUESTPANIC: qemuMonitorEventPanicInfoFree(event->data); break; + case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED: + qemuMonitorEventRdmaGidStatusFree(event->data); + break; case QEMU_PROCESS_EVENT_WATCHDOG: case QEMU_PROCESS_EVENT_DEVICE_DELETED: case QEMU_PROCESS_EVENT_NIC_RX_FILTER_CHANGED: diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h index 80bd4bde91..64bceb9a98 100644 --- a/src/qemu/qemu_domain.h +++ b/src/qemu/qemu_domain.h @@ -487,6 +487,7 @@ typedef enum { QEMU_PROCESS_EVENT_BLOCK_JOB, QEMU_PROCESS_EVENT_MONITOR_EOF, QEMU_PROCESS_EVENT_PR_DISCONNECT, + QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED, QEMU_PROCESS_EVENT_LAST } qemuProcessEventType; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index a52e2495d5..4e541abd05 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4788,6 +4788,47 @@ processPRDisconnectEvent(virDomainObjPtr vm) } +static void +processRdmaGidStatusChangedEvent(virDomainObjPtr vm, + qemuMonitorRdmaGidStatusChangedPrivatePtr info) +{ + unsigned int prefix_len; + virSocketAddr addr = {0}; + int rc; + + if (!virDomainObjIsActive(vm)) + return; + + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%llx,interface_id=0x%llx", + info->netdev, info->gid_status, info->subnet_prefix, + info->interface_id); + + if (info->subnet_prefix) { + prefix_len = 64; + uint32_t ipv6[4]; + memcpy(&ipv6[0], &info->subnet_prefix, sizeof(info->subnet_prefix)); + memcpy(&ipv6[2], &info->interface_id, sizeof(info->interface_id)); + virSocketAddrSetIPv6AddrNetOrder(&addr, ipv6); + } else { + prefix_len = 24; + virSocketAddrSetIPv4AddrNetOrder(&addr, info->interface_id >> 32); + } + + if (info->gid_status) { + VIR_DEBUG("Adding %s to %s", virSocketAddrFormat(&addr), info->netdev); + rc = virNetDevIPAddrAdd(info->netdev, &addr, NULL, prefix_len); + } else { + VIR_DEBUG("Removing %s from %s", virSocketAddrFormat(&addr), + info->netdev); + rc = virNetDevIPAddrDel(info->netdev, &addr, prefix_len); + } + + if (rc < 0) + VIR_WARN("Fail to update address %s to %s", virSocketAddrFormat(&addr), + info->netdev); +} + + static void qemuProcessEventHandler(void *data, void *opaque) { struct qemuProcessEvent *processEvent = data; @@ -4828,6 +4869,9 @@ static void qemuProcessEventHandler(void *data, void *opaque) case QEMU_PROCESS_EVENT_PR_DISCONNECT: processPRDisconnectEvent(vm); break; + case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED: + processRdmaGidStatusChangedEvent(vm, processEvent->data); + break; case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c index 7f7013e115..4bf71dbf8c 100644 --- a/src/qemu/qemu_monitor.c +++ b/src/qemu/qemu_monitor.c @@ -1686,6 +1686,22 @@ qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon, } +int +qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id) +{ + int ret = -1; + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + netdev, gid_status, subnet_prefix, interface_id); + + QEMU_MONITOR_CALLBACK(mon, ret, domainRdmaGidStatusChanged, mon->vm, netdev, + gid_status, subnet_prefix, interface_id); + + return ret; +} + + int qemuMonitorSetCapabilities(qemuMonitorPtr mon) { @@ -4298,6 +4314,17 @@ qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfoPtr info) } +void +qemuMonitorEventRdmaGidStatusFree(qemuMonitorRdmaGidStatusChangedPrivatePtr info) +{ + if (!info) + return; + + VIR_FREE(info->netdev); + VIR_FREE(info); +} + + int qemuMonitorSetWatchdogAction(qemuMonitorPtr mon, const char *action) diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h index 48b142a4f4..b639a0a9d2 100644 --- a/src/qemu/qemu_monitor.h +++ b/src/qemu/qemu_monitor.h @@ -109,8 +109,22 @@ struct _qemuMonitorEventPanicInfo { } data; }; + +typedef struct _qemuMonitorRdmaGidStatusChangedPrivate qemuMonitorRdmaGidStatusChangedPrivate; +typedef qemuMonitorRdmaGidStatusChangedPrivate *qemuMonitorRdmaGidStatusChangedPrivatePtr; +struct _qemuMonitorRdmaGidStatusChangedPrivate { + virObject parent; + + char *netdev; + bool gid_status; + unsigned long long subnet_prefix; + unsigned long long interface_id; +}; + + char *qemuMonitorGuestPanicEventInfoFormatMsg(qemuMonitorEventPanicInfoPtr info); void qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfoPtr info); +void qemuMonitorEventRdmaGidStatusFree(qemuMonitorRdmaGidStatusChangedPrivatePtr info); typedef void (*qemuMonitorDestroyCallback)(qemuMonitorPtr mon, virDomainObjPtr vm, @@ -281,6 +295,14 @@ typedef int (*qemuMonitorDomainPRManagerStatusChangedCallback)(qemuMonitorPtr mo bool connected, void *opaque); +typedef int (*qemuMonitorDomainRdmaGidStatusChangedCallback)(qemuMonitorPtr mon, + virDomainObjPtr vm, + const char *netdev, + bool gid_status, + uint64_t subnet_prefix, + uint64_t interface_id, + void *opaque); + typedef struct _qemuMonitorCallbacks qemuMonitorCallbacks; typedef qemuMonitorCallbacks *qemuMonitorCallbacksPtr; struct _qemuMonitorCallbacks { @@ -314,6 +336,7 @@ struct _qemuMonitorCallbacks { qemuMonitorDomainBlockThresholdCallback domainBlockThreshold; qemuMonitorDomainDumpCompletedCallback domainDumpCompleted; qemuMonitorDomainPRManagerStatusChangedCallback domainPRManagerStatusChanged; + qemuMonitorDomainRdmaGidStatusChangedCallback domainRdmaGidStatusChanged; }; char *qemuMonitorEscapeArg(const char *in); @@ -448,6 +471,10 @@ int qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon, const char *prManager, bool connected); +int qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id); + int qemuMonitorStartCPUs(qemuMonitorPtr mon); int qemuMonitorStopCPUs(qemuMonitorPtr mon); diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c index 3de298c9e2..8df9b426ba 100644 --- a/src/qemu/qemu_monitor_json.c +++ b/src/qemu/qemu_monitor_json.c @@ -91,6 +91,7 @@ static void qemuMonitorJSONHandleAcpiOstInfo(qemuMonitorPtr mon, virJSONValuePtr static void qemuMonitorJSONHandleBlockThreshold(qemuMonitorPtr mon, virJSONValuePtr data); static void qemuMonitorJSONHandleDumpCompleted(qemuMonitorPtr mon, virJSONValuePtr data); static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data); +static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data); typedef struct { const char *type; @@ -114,6 +115,7 @@ static qemuEventHandler eventHandlers[] = { { "NIC_RX_FILTER_CHANGED", qemuMonitorJSONHandleNicRxFilterChanged, }, { "POWERDOWN", qemuMonitorJSONHandlePowerdown, }, { "PR_MANAGER_STATUS_CHANGED", qemuMonitorJSONHandlePRManagerStatusChanged, }, + { "RDMA_GID_STATUS_CHANGED", qemuMonitorJSONHandleRdmaGidStatusChanged, }, { "RESET", qemuMonitorJSONHandleReset, }, { "RESUME", qemuMonitorJSONHandleResume, }, { "RTC_CHANGE", qemuMonitorJSONHandleRTCChange, }, @@ -1351,6 +1353,40 @@ static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, } +static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, + virJSONValuePtr data) +{ + const char *netdev; + bool gid_status; + unsigned long long subnet_prefix, interface_id; + + if (!(netdev = virJSONValueObjectGetString(data, "netdev"))) { + VIR_WARN("missing netdev in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetBoolean(data, "gid-status", &gid_status)) { + VIR_WARN("missing gid-status in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "subnet-prefix", + &subnet_prefix)) { + VIR_WARN("missing subnet-prefix in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "interface-id", + &interface_id)) { + VIR_WARN("missing interface-id in GID_STATUS_CHANGED event"); + return; + } + + qemuMonitorEmitRdmaGidStatusChanged(mon, netdev, gid_status, subnet_prefix, + interface_id); +} + + int qemuMonitorJSONHumanCommandWithFd(qemuMonitorPtr mon, const char *cmd_str, diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 9cf971808c..6cf0ace5cf 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -1703,6 +1703,57 @@ qemuProcessHandlePRManagerStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED, } +static int +qemuProcessHandleRdmaGidStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED, + virDomainObjPtr vm, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id, void *opaque) +{ + virQEMUDriverPtr driver = opaque; + struct qemuProcessEvent *processEvent = NULL; + qemuMonitorRdmaGidStatusChangedPrivatePtr rdmaGitStatusChangedPriv = NULL; + int ret = -1; + + virObjectLock(vm); + + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + netdev, gid_status, subnet_prefix, interface_id); + + if (VIR_ALLOC(rdmaGitStatusChangedPriv) < 0) + goto out_unlock; + + if (VIR_STRDUP(rdmaGitStatusChangedPriv->netdev, netdev) < 0) + goto out_free; + + rdmaGitStatusChangedPriv->gid_status = gid_status; + rdmaGitStatusChangedPriv->subnet_prefix = subnet_prefix; + rdmaGitStatusChangedPriv->interface_id = interface_id; + + if (VIR_ALLOC(processEvent) < 0) + goto out_free; + + processEvent->eventType = QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED; + processEvent->vm = virObjectRef(vm); + processEvent->data = rdmaGitStatusChangedPriv; + + if (virThreadPoolSendJob(driver->workerPool, 0, processEvent) < 0) { + qemuProcessEventFree(processEvent); + virObjectUnref(vm); + goto out_free; + } + + ret = 0; + goto out_unlock; + + out_free: + qemuMonitorEventRdmaGidStatusFree(rdmaGitStatusChangedPriv); + + out_unlock: + virObjectUnlock(vm); + return ret; +} + + static qemuMonitorCallbacks monitorCallbacks = { .eofNotify = qemuProcessHandleMonitorEOF, .errorNotify = qemuProcessHandleMonitorError, @@ -1732,6 +1783,7 @@ static qemuMonitorCallbacks monitorCallbacks = { .domainBlockThreshold = qemuProcessHandleBlockThreshold, .domainDumpCompleted = qemuProcessHandleDumpCompleted, .domainPRManagerStatusChanged = qemuProcessHandlePRManagerStatusChanged, + .domainRdmaGidStatusChanged = qemuProcessHandleRdmaGidStatusChanged, }; static void -- 2.17.2

1 0

[libvirt] [PATCH] qemu: Dissolve qemuBuildVhostuserCommandLine in qemuBuildInterfaceCommandLine
by Michal Privoznik 05 Nov '18

05 Nov '18

https://bugzilla.redhat.com/show_bug.cgi?id=1524230 The qemuBuildVhostuserCommandLine builds command line for vhostuser type interfaces. It is duplicating some code of the function it is called from (qemuBuildInterfaceCommandLine) because of the way it's called. If we merge it into the caller not only we save a few lines but we also enable checks that we would have to duplicate otherwise (e.g. QoS availability). While at it, reorder some VIR_FREE() in qemuBuildInterfaceCommandLine so that it is easier to track which variables are freed and which are not. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com> --- src/qemu/qemu_command.c | 113 +++++++++++++++++----------------------- 1 file changed, 48 insertions(+), 65 deletions(-) diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index 6e3ff67660..e338d3172e 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -8224,34 +8224,24 @@ qemuBuildGraphicsCommandLine(virQEMUDriverConfigPtr cfg, } static int -qemuBuildVhostuserCommandLine(virQEMUDriverPtr driver, +qemuInterfaceVhostuserConnect(virQEMUDriverPtr driver, virLogManagerPtr logManager, virSecurityManagerPtr secManager, virCommandPtr cmd, virDomainDefPtr def, virDomainNetDefPtr net, virQEMUCapsPtr qemuCaps, - unsigned int bootindex) + char **chardev) { virQEMUDriverConfigPtr cfg = virQEMUDriverGetConfig(driver); - char *chardev = NULL; - char *netdev = NULL; - unsigned int queues = net->driver.virtio.queues; - char *nic = NULL; int ret = -1; - if (!qemuDomainSupportsNicdev(def, net)) { - virReportError(VIR_ERR_INTERNAL_ERROR, - "%s", _("Nicdev support unavailable")); - goto cleanup; - } - switch ((virDomainChrType)net->data.vhostuser->type) { case VIR_DOMAIN_CHR_TYPE_UNIX: - if (!(chardev = qemuBuildChrChardevStr(logManager, secManager, - cmd, cfg, def, - net->data.vhostuser, - net->info.alias, qemuCaps, 0))) + if (!(*chardev = qemuBuildChrChardevStr(logManager, secManager, + cmd, cfg, def, + net->data.vhostuser, + net->info.alias, qemuCaps, 0))) goto cleanup; break; @@ -8274,42 +8264,9 @@ qemuBuildVhostuserCommandLine(virQEMUDriverPtr driver, goto cleanup; } - if (queues > 1 && - !virQEMUCapsGet(qemuCaps, QEMU_CAPS_VHOSTUSER_MULTIQUEUE)) { - virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", - _("multi-queue is not supported for vhost-user " - "with this QEMU binary")); - goto cleanup; - } - - if (!(netdev = qemuBuildHostNetStr(net, driver, - NULL, 0, NULL, 0))) - goto cleanup; - - if (virNetDevOpenvswitchGetVhostuserIfname(net->data.vhostuser->data.nix.path, - &net->ifname) < 0) - goto cleanup; - - virCommandAddArg(cmd, "-chardev"); - virCommandAddArg(cmd, chardev); - - virCommandAddArg(cmd, "-netdev"); - virCommandAddArg(cmd, netdev); - - if (!(nic = qemuBuildNicDevStr(def, net, bootindex, - queues, qemuCaps))) { - goto cleanup; - } - - virCommandAddArgList(cmd, "-device", nic, NULL); - ret = 0; cleanup: virObjectUnref(cfg); - VIR_FREE(netdev); - VIR_FREE(chardev); - VIR_FREE(nic); - return ret; } @@ -8328,7 +8285,9 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, int **nicindexes) { int ret = -1; - char *nic = NULL, *host = NULL; + char *nic = NULL; + char *host = NULL; + char *chardev = NULL; int *tapfd = NULL; size_t tapfdSize = 0; int *vhostfd = NULL; @@ -8337,6 +8296,7 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, char **vhostfdName = NULL; virDomainNetType actualType = virDomainNetGetActualType(net); virNetDevBandwidthPtr actualBandwidth; + bool requireNicdev = false; size_t i; @@ -8447,9 +8407,24 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, break; case VIR_DOMAIN_NET_TYPE_VHOSTUSER: - ret = qemuBuildVhostuserCommandLine(driver, logManager, secManager, cmd, def, - net, qemuCaps, bootindex); - goto cleanup; + requireNicdev = true; + + if (net->driver.virtio.queues > 1 && + !virQEMUCapsGet(qemuCaps, QEMU_CAPS_VHOSTUSER_MULTIQUEUE)) { + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", + _("multi-queue is not supported for vhost-user " + "with this QEMU binary")); + goto cleanup; + } + + if (qemuInterfaceVhostuserConnect(driver, logManager, secManager, + cmd, def, net, qemuCaps, &chardev) < 0) + goto cleanup; + + if (virNetDevOpenvswitchGetVhostuserIfname(net->data.vhostuser->data.nix.path, + &net->ifname) < 0) + goto cleanup; + break; case VIR_DOMAIN_NET_TYPE_USER: @@ -8564,6 +8539,9 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, goto cleanup; } + if (chardev) + virCommandAddArgList(cmd, "-chardev", chardev, NULL); + if (!(host = qemuBuildHostNetStr(net, driver, tapfdName, tapfdSize, vhostfdName, vhostfdSize))) @@ -8578,13 +8556,17 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, */ if (qemuDomainSupportsNicdev(def, net)) { if (!(nic = qemuBuildNicDevStr(def, net, bootindex, - vhostfdSize, qemuCaps))) + net->driver.virtio.queues, qemuCaps))) goto cleanup; virCommandAddArgList(cmd, "-device", nic, NULL); - } else { + } else if (!requireNicdev) { if (!(nic = qemuBuildLegacyNicStr(net))) goto cleanup; virCommandAddArgList(cmd, "-net", nic, NULL); + } else { + virReportError(VIR_ERR_INTERNAL_ERROR, + "%s", _("Nicdev support unavailable")); + goto cleanup; } ret = 0; @@ -8595,24 +8577,25 @@ qemuBuildInterfaceCommandLine(virQEMUDriverPtr driver, virSetError(saved_err); virFreeError(saved_err); } - for (i = 0; tapfd && i < tapfdSize && tapfd[i] >= 0; i++) { - if (ret < 0) - VIR_FORCE_CLOSE(tapfd[i]); - if (tapfdName) - VIR_FREE(tapfdName[i]); - } for (i = 0; vhostfd && i < vhostfdSize && vhostfd[i] >= 0; i++) { if (ret < 0) VIR_FORCE_CLOSE(vhostfd[i]); if (vhostfdName) VIR_FREE(vhostfdName[i]); } - VIR_FREE(tapfd); + VIR_FREE(vhostfdName); + for (i = 0; tapfd && i < tapfdSize && tapfd[i] >= 0; i++) { + if (ret < 0) + VIR_FORCE_CLOSE(tapfd[i]); + if (tapfdName) + VIR_FREE(tapfdName[i]); + } + VIR_FREE(tapfdName); VIR_FREE(vhostfd); - VIR_FREE(nic); + VIR_FREE(tapfd); + VIR_FREE(chardev); VIR_FREE(host); - VIR_FREE(tapfdName); - VIR_FREE(vhostfdName); + VIR_FREE(nic); return ret; } -- 2.18.1

2 3

[libvirt] Release of libvirt-4.9.0
by Daniel Veillard 04 Nov '18

04 Nov '18

Except an update to the news file no change was pushed to the tree since RC! so that looks like stable enough for release and so I did. It's tagged in git and signed tarball and rpms are available from the usual place: ftp://libvirt.org/libvirt/ I also tagged and pushed python bindings 4.9.0 release which can be found at ftp://libvirt.org/libvirt/python/ This release is a mix, with one important new feature, the new cgroup v2 and one important security bug for libvirt sockets, users are invited to upgrade: New features: - util: Add cgroup v2 support cgroup v2 support has been implemented in libvirt, with both "unified" (v2 only) and "hybrid" (v2 + v1) setups being usable; existing "legacy" (v1 only) setups will keep working. - qemu: Add vfio AP support The QEMU driver now has support to passthrough adjunct processors into QEMU guests on S390. Improvements: - rpc: Make 'genprotocol' output reproducible This is another step towards making libvirt builds fully reproducible. Bug fixes: - security: Fix permissions for UNIX sockets Since 4.5.0, libvirt is using FD passing to hand sockets over to QEMU, which in theory removes the need for them to be accessible by the user under which the QEMU process is running; however, other processes such as vdsm need to access the sockets as well, which means adjusting permissions is still necessary. - cpu_map: Add Icelake model definitions These CPU models will be available in the upcoming 3.1.0 QEMU release. - util: Properly parse URIs with missing trailing slash Some storage URIs were not parsed correctly, in which case libvirt ended up emitting XML that it would then refuse to parse back. Thanks everybody for your contributions to this release whatever form that took (ideas, bug reports, patches, reviews, docs ...), enjoy ! Daniel -- Daniel Veillard | Red Hat Developers Tools http://developer.redhat.com/ veillard(a)redhat.com | libxml Gnome XML XSLT toolkit http://xmlsoft.org/ http://veillard.com/ | virtualization library http://libvirt.org/

1 0

[libvirt] [PATCH] qemu: Process RDMA GID state change event
by Yuval Shaia 04 Nov '18

04 Nov '18

This event is emitted on the monitor when a GID table in pvrdma device is modified and the change needs to be propagate to the backend RDMA device's GID table. The control over the RDMA device's GID table is done by updating the device's Ethernet function addresses. Usually the first GID entry is determine by the MAC address, the second by the first IPv6 address and the third by the IPv4 address. Other entries can be added by adding more IP addresses. The opposite is the same, i.e. whenever an address is removed, the corresponding GID entry is removed. The process is done by the network and RDMA stacks. Whenever an address is added the ib_core driver is notified and calls the device driver's add_gid function which in turn update the device. To support this in pvrdma device we need to hook into the create_bind and destroy_bind HW commands triggered by pvrdma driver in guest. Whenever a changed is made to the pvrdma device's GID table a special QMP messages is sent to be processed by libvirt to update the address of the backend Ethernet device. Signed-off-by: Yuval Shaia <yuval.shaia(a)oracle.com> --- src/qemu/qemu_domain.c | 3 ++ src/qemu/qemu_domain.h | 15 +++++++++ src/qemu/qemu_driver.c | 40 ++++++++++++++++++++++++ src/qemu/qemu_monitor.c | 28 +++++++++++++++++ src/qemu/qemu_monitor.h | 13 ++++++++ src/qemu/qemu_monitor_json.c | 36 ++++++++++++++++++++++ src/qemu/qemu_process.c | 59 ++++++++++++++++++++++++++++++++++++ 7 files changed, 194 insertions(+) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index ba3fff607a..8da54c7ee9 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -13479,6 +13479,9 @@ qemuProcessEventFree(struct qemuProcessEvent *event) case QEMU_PROCESS_EVENT_GUESTPANIC: qemuMonitorEventPanicInfoFree(event->data); break; + case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED: + qemuMonitorEventRdmaGidStatusFree(event->data); + break; case QEMU_PROCESS_EVENT_WATCHDOG: case QEMU_PROCESS_EVENT_DEVICE_DELETED: case QEMU_PROCESS_EVENT_NIC_RX_FILTER_CHANGED: diff --git a/src/qemu/qemu_domain.h b/src/qemu/qemu_domain.h index 80bd4bde91..1b188843e3 100644 --- a/src/qemu/qemu_domain.h +++ b/src/qemu/qemu_domain.h @@ -478,6 +478,18 @@ struct _qemuDomainVsockPrivate { }; +typedef struct _qemuDomainRdmaGidStatusChangedPrivate qemuDomainRdmaGidStatusChangedPrivate; +typedef qemuDomainRdmaGidStatusChangedPrivate *qemuDomainRdmaGidStatusChangedPrivatePtr; +struct _qemuDomainRdmaGidStatusChangedPrivate { + virObject parent; + + char *netdev; + bool gid_status; + uint64_t subnet_prefix; + uint64_t interface_id; +}; + + typedef enum { QEMU_PROCESS_EVENT_WATCHDOG = 0, QEMU_PROCESS_EVENT_GUESTPANIC, @@ -487,6 +499,7 @@ typedef enum { QEMU_PROCESS_EVENT_BLOCK_JOB, QEMU_PROCESS_EVENT_MONITOR_EOF, QEMU_PROCESS_EVENT_PR_DISCONNECT, + QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED, QEMU_PROCESS_EVENT_LAST } qemuProcessEventType; @@ -499,6 +512,8 @@ struct qemuProcessEvent { void *data; }; +void qemuMonitorEventRdmaGidStatusFree(qemuDomainRdmaGidStatusChangedPrivatePtr info); + void qemuProcessEventFree(struct qemuProcessEvent *event); typedef struct _qemuDomainLogContext qemuDomainLogContext; diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index a52e2495d5..dc088d844f 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -4788,6 +4788,43 @@ processPRDisconnectEvent(virDomainObjPtr vm) } +static void +processRdmaGidStatusChangedEvent(virDomainObjPtr vm, + qemuDomainRdmaGidStatusChangedPrivatePtr info) +{ + unsigned int prefix_len; + virSocketAddr addr = {0}; + int rc; + + if (!virDomainObjIsActive(vm)) + return; + + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + info->netdev, info->gid_status, info->subnet_prefix, + info->interface_id); + + if (info->subnet_prefix) { + prefix_len = 64; + uint32_t ipv6[4]; + memcpy(&ipv6[0], &info->subnet_prefix, sizeof(info->subnet_prefix)); + memcpy(&ipv6[2], &info->interface_id, sizeof(info->subnet_prefix)); + virSocketAddrSetIPv6AddrNetOrder(&addr, ipv6); + } else { + prefix_len = 24; + virSocketAddrSetIPv4AddrNetOrder(&addr, info->interface_id >> 32); + } + + if (info->gid_status) + rc = virNetDevIPAddrAdd(info->netdev, &addr, NULL, prefix_len); + else + rc = virNetDevIPAddrDel(info->netdev, &addr, prefix_len); + + if (rc) + VIR_ERROR(_("Fail to update address 0x%lx to %s"), info->interface_id, + info->netdev); +} + + static void qemuProcessEventHandler(void *data, void *opaque) { struct qemuProcessEvent *processEvent = data; @@ -4828,6 +4865,9 @@ static void qemuProcessEventHandler(void *data, void *opaque) case QEMU_PROCESS_EVENT_PR_DISCONNECT: processPRDisconnectEvent(vm); break; + case QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED: + processRdmaGidStatusChangedEvent(vm, processEvent->data); + break; case QEMU_PROCESS_EVENT_LAST: break; } diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c index 7f7013e115..375ed7ceaf 100644 --- a/src/qemu/qemu_monitor.c +++ b/src/qemu/qemu_monitor.c @@ -1686,6 +1686,23 @@ qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon, } +int +qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id) +{ + int ret = -1; + VIR_DEBUG("mon=%p", mon); + VIR_DEBUG("netdev='%s',gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + netdev, gid_status, subnet_prefix, interface_id); + + QEMU_MONITOR_CALLBACK(mon, ret, domainRdmaGidStatusChanged, mon->vm, netdev, + gid_status, subnet_prefix, interface_id); + + return ret; +} + + int qemuMonitorSetCapabilities(qemuMonitorPtr mon) { @@ -4298,6 +4315,17 @@ qemuMonitorEventPanicInfoFree(qemuMonitorEventPanicInfoPtr info) } +void +qemuMonitorEventRdmaGidStatusFree(qemuDomainRdmaGidStatusChangedPrivatePtr info) +{ + if (!info) + return; + + VIR_FREE(info->netdev); + VIR_FREE(info); +} + + int qemuMonitorSetWatchdogAction(qemuMonitorPtr mon, const char *action) diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h index 48b142a4f4..f5affe615a 100644 --- a/src/qemu/qemu_monitor.h +++ b/src/qemu/qemu_monitor.h @@ -281,6 +281,14 @@ typedef int (*qemuMonitorDomainPRManagerStatusChangedCallback)(qemuMonitorPtr mo bool connected, void *opaque); +typedef int (*qemuMonitorDomainRdmaGidStatusChangedCallback)(qemuMonitorPtr mon, + virDomainObjPtr vm, + const char *netdev, + bool gid_status, + uint64_t subnet_prefix, + uint64_t interface_id, + void *opaque); + typedef struct _qemuMonitorCallbacks qemuMonitorCallbacks; typedef qemuMonitorCallbacks *qemuMonitorCallbacksPtr; struct _qemuMonitorCallbacks { @@ -314,6 +322,7 @@ struct _qemuMonitorCallbacks { qemuMonitorDomainBlockThresholdCallback domainBlockThreshold; qemuMonitorDomainDumpCompletedCallback domainDumpCompleted; qemuMonitorDomainPRManagerStatusChangedCallback domainPRManagerStatusChanged; + qemuMonitorDomainRdmaGidStatusChangedCallback domainRdmaGidStatusChanged; }; char *qemuMonitorEscapeArg(const char *in); @@ -448,6 +457,10 @@ int qemuMonitorEmitPRManagerStatusChanged(qemuMonitorPtr mon, const char *prManager, bool connected); +int qemuMonitorEmitRdmaGidStatusChanged(qemuMonitorPtr mon, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id); + int qemuMonitorStartCPUs(qemuMonitorPtr mon); int qemuMonitorStopCPUs(qemuMonitorPtr mon); diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c index 3de298c9e2..8df9b426ba 100644 --- a/src/qemu/qemu_monitor_json.c +++ b/src/qemu/qemu_monitor_json.c @@ -91,6 +91,7 @@ static void qemuMonitorJSONHandleAcpiOstInfo(qemuMonitorPtr mon, virJSONValuePtr static void qemuMonitorJSONHandleBlockThreshold(qemuMonitorPtr mon, virJSONValuePtr data); static void qemuMonitorJSONHandleDumpCompleted(qemuMonitorPtr mon, virJSONValuePtr data); static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data); +static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, virJSONValuePtr data); typedef struct { const char *type; @@ -114,6 +115,7 @@ static qemuEventHandler eventHandlers[] = { { "NIC_RX_FILTER_CHANGED", qemuMonitorJSONHandleNicRxFilterChanged, }, { "POWERDOWN", qemuMonitorJSONHandlePowerdown, }, { "PR_MANAGER_STATUS_CHANGED", qemuMonitorJSONHandlePRManagerStatusChanged, }, + { "RDMA_GID_STATUS_CHANGED", qemuMonitorJSONHandleRdmaGidStatusChanged, }, { "RESET", qemuMonitorJSONHandleReset, }, { "RESUME", qemuMonitorJSONHandleResume, }, { "RTC_CHANGE", qemuMonitorJSONHandleRTCChange, }, @@ -1351,6 +1353,40 @@ static void qemuMonitorJSONHandlePRManagerStatusChanged(qemuMonitorPtr mon, } +static void qemuMonitorJSONHandleRdmaGidStatusChanged(qemuMonitorPtr mon, + virJSONValuePtr data) +{ + const char *netdev; + bool gid_status; + unsigned long long subnet_prefix, interface_id; + + if (!(netdev = virJSONValueObjectGetString(data, "netdev"))) { + VIR_WARN("missing netdev in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetBoolean(data, "gid-status", &gid_status)) { + VIR_WARN("missing gid-status in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "subnet-prefix", + &subnet_prefix)) { + VIR_WARN("missing subnet-prefix in GID_STATUS_CHANGED event"); + return; + } + + if (virJSONValueObjectGetNumberUlong(data, "interface-id", + &interface_id)) { + VIR_WARN("missing interface-id in GID_STATUS_CHANGED event"); + return; + } + + qemuMonitorEmitRdmaGidStatusChanged(mon, netdev, gid_status, subnet_prefix, + interface_id); +} + + int qemuMonitorJSONHumanCommandWithFd(qemuMonitorPtr mon, const char *cmd_str, diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 9cf971808c..45fc155d31 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -1703,6 +1703,64 @@ qemuProcessHandlePRManagerStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED, } +static int +qemuProcessHandleRdmaGidStatusChanged(qemuMonitorPtr mon ATTRIBUTE_UNUSED, + virDomainObjPtr vm, const char *netdev, + bool gid_status, uint64_t subnet_prefix, + uint64_t interface_id, void *opaque) +{ + virQEMUDriverPtr driver = opaque; + qemuDomainObjPrivatePtr priv; + struct qemuProcessEvent *processEvent = NULL; + qemuDomainRdmaGidStatusChangedPrivatePtr rdmaGitStatusChangedPriv; + int ret = -1; + + virObjectLock(vm); + + VIR_DEBUG("netdev=%s,gid_status=%d,subnet_prefix=0x%lx,interface_id=0x%lx", + netdev, gid_status, subnet_prefix, interface_id); + + priv = vm->privateData; + priv->prDaemonRunning = false; + + if (VIR_ALLOC(rdmaGitStatusChangedPriv) < 0) + goto out_unlock; + + if (VIR_STRDUP(rdmaGitStatusChangedPriv->netdev, netdev) < 0) + goto out_free_rdma_priv; + + rdmaGitStatusChangedPriv->gid_status = gid_status; + rdmaGitStatusChangedPriv->subnet_prefix = subnet_prefix; + rdmaGitStatusChangedPriv->interface_id = interface_id; + + if (VIR_ALLOC(processEvent) < 0) + goto out_free_rdma_priv_netdev; + + processEvent->eventType = QEMU_PROCESS_EVENT_RDMA_GID_STATUS_CHANGED; + processEvent->vm = virObjectRef(vm); + processEvent->data = rdmaGitStatusChangedPriv; + + if (virThreadPoolSendJob(driver->workerPool, 0, processEvent) < 0) { + qemuProcessEventFree(processEvent); + virObjectUnref(vm); + goto out_free_rdma_priv_netdev; + } + + ret = 0; + goto out_unlock; + + out_free_rdma_priv_netdev: + VIR_FREE(rdmaGitStatusChangedPriv->netdev); + + out_free_rdma_priv: + VIR_FREE(rdmaGitStatusChangedPriv); + + out_unlock: + virObjectUnlock(vm); + return ret; +} + + static qemuMonitorCallbacks monitorCallbacks = { .eofNotify = qemuProcessHandleMonitorEOF, .errorNotify = qemuProcessHandleMonitorError, @@ -1732,6 +1790,7 @@ static qemuMonitorCallbacks monitorCallbacks = { .domainBlockThreshold = qemuProcessHandleBlockThreshold, .domainDumpCompleted = qemuProcessHandleDumpCompleted, .domainPRManagerStatusChanged = qemuProcessHandlePRManagerStatusChanged, + .domainRdmaGidStatusChanged = qemuProcessHandleRdmaGidStatusChanged, }; static void -- 2.17.2

1 0

[libvirt] [PATCH v1 1/1] qemu_domain, qemu_process: maxCpus check to non-x86 guests
by Daniel Henrique Barboza 03 Nov '18

03 Nov '18

This patch makes two quality of life changes for non-x86 guests. The first one is a maxCpus validation at qemuDomainDefValidate. The check is made by the same function used to do that at qemuProcessStartValidateXML, qemuValidateCpuCount. This ensures that the user doesn't goes over the board with the maxCpus value when editing the XML, only to be faced with a runtime error when starting it. To do that, the following changes were made: - qemuValidateCpuCount was made public. It was renamed to qemuProcessValidateCpuCount to be compliant with the other public methods at qemu_process.h; - the method signature was slightly adapted to fit the const 'def' variable used in qemuDomainDefValidate. This change has no downside in in its original usage at qemuProcessStartValidateXML. The second QoL change is adding the maxCpus value in the error message of the now qemuProcessValidateCpuCount. This simple change allows the user to quickly edit the XML to comply with the acceptable limit without having to know QEMU internals. x86 guests, that might have been created prior to the x86 qemuDomainDefValidate maxCpus check code, will also benefit from this change. After this patch, this is the expect result running a Power 9 guest with a maxCpus of 40000: $ ./virsh start dhb error: Failed to start domain dhb error: unsupported configuration: Maximum CPUs greater than specified machine type limit 240 And this is the result when trying to edit maxCpus to an invalid value: $ ./virsh edit dhb error: unsupported configuration: Maximum CPUs greater than specified machine type limit 240 Failed. Try again? [y,n,i,f,?]: error: unsupported configuration: Maximum CPUs greater than specified machine type limit 240 Signed-off-by: Daniel Henrique Barboza <danielhb413(a)gmail.com> --- src/qemu/qemu_domain.c | 5 +++++ src/qemu/qemu_process.c | 13 +++++++------ src/qemu/qemu_process.h | 3 +++ 3 files changed, 15 insertions(+), 6 deletions(-) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index 939b2a3da2..5a39b11da7 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -4100,6 +4100,11 @@ qemuDomainDefValidate(const virDomainDef *def, } } + if (!ARCH_IS_X86(def->os.arch) && + qemuProcessValidateCpuCount(def, qemuCaps) < 0) { + goto cleanup; + } + if (def->nresctrls && def->virtType != VIR_DOMAIN_VIRT_KVM) { virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 29b0ba1590..0de5b503d6 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -3901,9 +3901,9 @@ qemuProcessSPICEAllocatePorts(virQEMUDriverPtr driver, } -static int -qemuValidateCpuCount(virDomainDefPtr def, - virQEMUCapsPtr qemuCaps) +int +qemuProcessValidateCpuCount(const virDomainDef *def, + virQEMUCapsPtr qemuCaps) { unsigned int maxCpus = virQEMUCapsGetMachineMaxCpus(qemuCaps, def->os.machine); @@ -3914,8 +3914,9 @@ qemuValidateCpuCount(virDomainDefPtr def, } if (maxCpus > 0 && virDomainDefGetVcpusMax(def) > maxCpus) { - virReportError(VIR_ERR_CONFIG_UNSUPPORTED, "%s", - _("Maximum CPUs greater than specified machine type limit")); + virReportError(VIR_ERR_CONFIG_UNSUPPORTED, + _("Maximum CPUs greater than specified machine type limit %u"), + maxCpus); return -1; } @@ -5165,7 +5166,7 @@ qemuProcessStartValidateXML(virQEMUDriverPtr driver, * If back compat isn't a concern, XML validation should probably * be done at parse time. */ - if (qemuValidateCpuCount(vm->def, qemuCaps) < 0) + if (qemuProcessValidateCpuCount(vm->def, qemuCaps) < 0) return -1; /* checks below should not be executed when starting a qemu process for a diff --git a/src/qemu/qemu_process.h b/src/qemu/qemu_process.h index c2f7c2b5d2..1716230475 100644 --- a/src/qemu/qemu_process.h +++ b/src/qemu/qemu_process.h @@ -215,4 +215,7 @@ int qemuProcessStartManagedPRDaemon(virDomainObjPtr vm); void qemuProcessKillManagedPRDaemon(virDomainObjPtr vm); +int qemuProcessValidateCpuCount(const virDomainDef *def, + virQEMUCapsPtr qemuCaps); + #endif /* __QEMU_PROCESS_H__ */ -- 2.17.1

2 3

Re: [libvirt] [PATCH v1 2/7] pcihp: overwrite hotplug handler recursively from the start
by Igor Mammedov 02 Nov '18

02 Nov '18

On Wed, 24 Oct 2018 12:19:25 +0200 David Hildenbrand <david(a)redhat.com> wrote: > For now, the hotplug handler is not called for devices that are > being cold plugged. The hotplug handler is setup when the machine > initialization is fully done. Only bridges that were cold plugged are > considered. > > Set the hotplug handler for the root piix bus directly when realizing. > Overwrite the hotplug handler of bridges when hotplugging/coldplugging > them. > > This will now make sure that the ACPI PCI hotplug handler is also called > for cold-plugged devices (also on bridges) and for bridges that were > hotplugged. > > When trying to hotplug a device to a hotplugged bridge, we now correctly > get the error message > "Unsupported bus. Bus doesn't have property 'acpi-pcihp-bsel' set" > Insted of going via the standard PCI hotplug handler. Erroring out is probably not ok, since it can break existing setups where SHPC hotplugging to hotplugged bridge was working just fine before. Marcel/Michael what's your take on this change in behaviour? CCing libvirt in case they are doing this stuff > > Signed-off-by: David Hildenbrand <david(a)redhat.com> > --- > hw/acpi/pcihp.c | 10 ++++++++++ > hw/acpi/piix4.c | 16 +--------------- > 2 files changed, 11 insertions(+), 15 deletions(-) > > diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c > index 5e7cef173c..647b5e8d82 100644 > --- a/hw/acpi/pcihp.c > +++ b/hw/acpi/pcihp.c > @@ -30,6 +30,7 @@ > #include "hw/hw.h" > #include "hw/i386/pc.h" > #include "hw/pci/pci.h" > +#include "hw/pci/pci_bridge.h" > #include "hw/acpi/acpi.h" > #include "sysemu/sysemu.h" > #include "exec/address-spaces.h" > @@ -236,6 +237,15 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, > int slot = PCI_SLOT(pdev->devfn); > int bsel; > > + if (!s->legacy_piix && object_dynamic_cast(OBJECT(dev), TYPE_PCI_BRIDGE)) { > + PCIBus *sec = pci_bridge_get_sec_bus(PCI_BRIDGE(pdev)); > + > + /* Overwrite the default hotplug handler with the ACPI PCI one. */ > + qbus_set_hotplug_handler(BUS(sec), DEVICE(hotplug_dev), &error_abort); > + /* No need to do it recursively */ > + assert(QLIST_EMPTY(&sec->child)); > + } > + > /* Don't send event when device is enabled during qemu machine creation: > * it is present on boot, no hotplug event is necessary. We do send an > * event when the device is disabled later. */ > diff --git a/hw/acpi/piix4.c b/hw/acpi/piix4.c > index 167afe2cea..e611778daf 100644 > --- a/hw/acpi/piix4.c > +++ b/hw/acpi/piix4.c > @@ -446,15 +446,6 @@ static void piix4_device_unplug_cb(HotplugHandler *hotplug_dev, > } > } > > -static void piix4_update_bus_hotplug(PCIBus *pci_bus, void *opaque) > -{ > - PIIX4PMState *s = opaque; > - > - /* pci_bus cannot outlive PIIX4PMState, because /machine keeps it alive > - * and it's not hot-unpluggable */ > - qbus_set_hotplug_handler(BUS(pci_bus), DEVICE(s), &error_abort); > -} > - > static void piix4_pm_machine_ready(Notifier *n, void *opaque) > { > PIIX4PMState *s = container_of(n, PIIX4PMState, machine_ready); > @@ -468,12 +459,6 @@ static void piix4_pm_machine_ready(Notifier *n, void *opaque) > pci_conf[0x63] = 0x60; > pci_conf[0x67] = (memory_region_present(io_as, 0x3f8) ? 0x08 : 0) | > (memory_region_present(io_as, 0x2f8) ? 0x90 : 0); > - > - if (s->use_acpi_pci_hotplug) { > - pci_for_each_bus(pci_get_bus(d), piix4_update_bus_hotplug, s); > - } else { > - piix4_update_bus_hotplug(pci_get_bus(d), s); > - } > } > > static void piix4_pm_add_propeties(PIIX4PMState *s) > @@ -547,6 +532,7 @@ static void piix4_pm_realize(PCIDevice *dev, Error **errp) > > piix4_acpi_system_hot_add_init(pci_address_space_io(dev), > pci_get_bus(dev), s); > + qbus_set_hotplug_handler(BUS(pci_get_bus(dev)), DEVICE(s), &error_abort); > > piix4_pm_add_propeties(s); > }

3 4

[libvirt] [PATCH] news: Update for 4.9.0 release
by Andrea Bolognani 02 Nov '18

02 Nov '18

Signed-off-by: Andrea Bolognani <abologna(a)redhat.com> --- docs/news.xml | 49 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/docs/news.xml b/docs/news.xml index e5476a3332..b75df36ddb 100644 --- a/docs/news.xml +++ b/docs/news.xml @@ -35,6 +35,16 @@ <libvirt> <release version="v4.9.0" date="unreleased"> <section title="New features"> + <change> + <summary> + util: Add cgroup v2 support + </summary> + <description> + cgroup v2 support has been implemented in libvirt, with both + "unified" (v2 only) and "hybrid" (v2 + v1) setups being usable; + existing "legacy" (v1 only) setups will keep working. + </description> + </change> <change> <summary> qemu: Add vfio AP support @@ -46,8 +56,47 @@ </change> </section> <section title="Improvements"> + <change> + <summary> + rpc: Make 'genprotocol' output reproducible + </summary> + <description> + This is another step towards making libvirt builds fully + reproducible. + </description> + </change> </section> <section title="Bug fixes"> + <change> + <summary> + security: Fix permissions for UNIX sockets + </summary> + <description> + Since 4.5.0, libvirt is using FD passing to hand sockets over to + QEMU, which in theory removes the need for them to be accessible by + the user under which the QEMU process is running; however, other + processes such as vdsm need to access the sockets as well, which + means adjusting permissions is still necessary. + </description> + </change> + <change> + <summary> + cpu_map: Add Icelake model definitions + </summary> + <description> + These CPU models will be available in the upcoming 3.1.0 QEMU + release. + </description> + </change> + <change> + <summary> + util: Properly parse URIs with missing trailing slash + </summary> + <description> + Some storage URIs were not parsed correctly, in which case libvirt + ended up emitting XML that it would then refuse to parse back. + </description> + </change> </section> </release> <release version="v4.8.0" date="2018-10-01"> -- 2.19.1

2 1

[libvirt] External disk snapshot paths and the revert operation
by Povilas Kanapickas 02 Nov '18

02 Nov '18

Hey, It seems that there's an issue of how external disk snapshots currently work. The snapshot definition xml[1] that is supplied to the API has a list of disks each of which specify where the new overlay disks should be placed. This leads to ambiguities when we want to revert the domain to a snapshot with children. Consider the following situation: 0. Initial state: Domain definition: disk at disk-base.qcow2 1. We create a snapshot snap1 placing the overlay at disk-snap1.qcow2 Domain definition: disk at disk-snap1.qcow2 Disks: - disk-base.qcow2 (read-only) - disk-snap1.qcow2 (overlay, base: disk-base.qcow2) Snapshots: - snap1 (snapshot domain disk list: disk-base.qcow2, snapshot disk list: disk-snap1.qcow2) 2. We create another snapshot snap2 placing the overlay at disk-snap2.qcow2 VM definition: disk at disk-snap2.qcow2 Disks: - disk-base.qcow2 (read-only) - disk-snap1.qcow2 (overlay, base: disk-base.qcow2, read-only) - disk-snap2.qcow2 (overlay, base: disk-snap1.qcow2) Snapshots: - snap1 (snapshot domain disk list: disk-base.qcow2, snapshot disk list: disk-snap1.qcow2) - snap2 (snapshot domain disk list: disk-snap1.qcow2, snapshot disk list: disk-snap2.qcow2) Now what happens if we want to revert to snap1? We can't use any of the paths that snap1 itself references: both disk-base.qcow2 and disk-snap1.qcow2 are read-only as part of the backing chain for disks used by snap2. Possible options are these: - we can reuse disk-snap2.qcow2 which we no longer need as it contains overlay on top of snap2. This is non-optimal because now the path of the disk after revert depends on the disk path before it. - we can think of some name with the expectation that the user will change it later anyway. I think that both of the above are non-optimal because we don't actually revert to the exact state we took the snapshot of. The user is effectively no longer in control of the disk path after the revert. One of possible solutions would be add additional flag during the snapshot creation that would change the current behavior. Instead of creating a new disk for the overlay we could move the base disk to the specified path and create the overlay in its place. The advantages of this behavior would be the following: - the path to the current disk used in the domain would not change when taking snapshots. This way we could avoid the problem listed above and easily revert to any snapshot. - the confusion in naming of the overlay disks would be reduced. Currently the path specified when creating snapshot refers to the overlay image. Most of the time user does not know what will be changed in the domain until the next snapshot. So any path he chooses will likely not reflect what will end up in the overlay at the time of the next snapshot. If it was possible to specify the path where the current disk should be put instead, then the user could just name it after the snapshot and it would correctly represent the contents of that disk. The major disadvantage of the approach is that it would introduce extra complexity in the presently simple interface and also the underlying code. I've completely disregarded the case of taking snapshots while the domain is running, so there might be hidden complications there as well. Personally, I don't mind the current situation too much, but if libvirt developers think it's a thing worth fixing I would be willing to work on it. Any opinions? Regards, Povilas [1]: https://libvirt.org/formatsnapshot.html

2 3

[libvirt] [PATCH] nwfilter: intantiate filters on loading driver
by Nikolay Shirokovskiy 02 Nov '18

02 Nov '18

Before using filters binding filters instantiation was done by hypervisors drivers initialization code (qemu was the only such hypervisor). Now qemu reconnection done supposes it should be done by nwfilter driver probably. Let's add this missing step. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy(a)virtuozzo.com> --- src/nwfilter/nwfilter_driver.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/src/nwfilter/nwfilter_driver.c b/src/nwfilter/nwfilter_driver.c index 1ee5162..1ab906f 100644 --- a/src/nwfilter/nwfilter_driver.c +++ b/src/nwfilter/nwfilter_driver.c @@ -264,6 +264,9 @@ nwfilterStateInitialize(bool privileged, if (virNWFilterBindingObjListLoadAllConfigs(driver->bindings, driver->bindingDir) < 0) goto error; + if (virNWFilterBuildAll(driver, false) < 0) + goto error; + nwfilterDriverUnlock(); return 0; -- 1.8.3.1

2 10

[libvirt] [PATCH v2] nodedev: Document the udevEventHandleThread
by John Ferlan 02 Nov '18

02 Nov '18

Commit cdbe1332 neglected to document the API. So let's add some details about the algorithm and why it was used to help future readers understand the issues encountered. Based largely off a description provided by Erik Skultety <eskultet(a)redhat.com>. NB: Management of the processing udev device notification is a delicate balance between the udev process, the scheduler, and when exactly the data from/for the socket is received. The balance is particularly important for environments when multiple devices are added into the system more or less simultaneously such as is done for mdev. In these cases scheduler blocking on the udev recv() call is more noticeable. It's expected that future devices will follow similar algorithms. Even though the algorithm does present some challenges for older OS's (such as Centos 6), trying to rewrite the algorithm to fit both models would be more complex and involve pulling the monitor object out of the private data lockable object and would need to be guarded by a separate lock. Devising such an algorithm to work around issues with older OS's at the expense of more modern OS algorithms in newer event processing code may result in unexpected issues, so the choice is to encourage use of newer OS's with newer udev event processing code. Signed-off-by: John Ferlan <jferlan(a)redhat.com> --- v1: https://www.redhat.com/archives/libvir-list/2018-October/msg01053.html Changes are from code review with some minor tweaks/editing as I went along. Mistakes are my own! src/node_device/node_device_udev.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/src/node_device/node_device_udev.c b/src/node_device/node_device_udev.c index 22897591de..f2c2299d4d 100644 --- a/src/node_device/node_device_udev.c +++ b/src/node_device/node_device_udev.c @@ -1591,6 +1591,26 @@ udevEventMonitorSanityCheck(udevEventDataPtr priv, } +/** + * udevEventHandleThread + * @opaque: unused + * + * Thread to handle the udevEventHandleCallback processing when udev + * tells us there's a device change for us (add, modify, delete, etc). + * + * Once notified there is data to be processed, the actual @device + * data retrieval by libudev may be delayed due to how threads are + * scheduled. In fact, the event loop could be scheduled earlier than + * the handler thread, thus potentially emitting the very same event + * the handler thread is currently trying to process, simply because + * the data hadn't been retrieved from the socket. + * + * NB: Usage of event based socket algorithm causes some issues with + * older platforms such as CentOS 6 in which the data socket is opened + * without the NONBLOCK bit set. That can be avoided by moving the reset + * priv->dataReady to just after the udev_monitor_receive_device; however, + * scheduler issues would still come into play. + */ static void udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) { @@ -1637,6 +1657,9 @@ udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) return; } + /* Trying to move the reset of the @priv->dataReady flag to + * after the udev_monitor_receive_device wouldn't help much + * due to event mgmt and scheduler timing. */ virObjectLock(priv); priv->dataReady = false; virObjectUnlock(priv); @@ -1646,6 +1669,11 @@ udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) udevHandleOneDevice(device); udev_device_unref(device); + + /* Instead of waiting for the next event after processing @device + * data, let's keep reading from the udev monitor and only wait + * for the next event once either a EAGAIN or a EWOULDBLOCK error + * is encountered. */ } } -- 2.17.2

3 5

[libvirt] [jenkins-ci PATCH v2 0/3] Add libvirt-ocaml
by Pino Toscano 02 Nov '18

02 Nov '18

Now that the libvirt-ocaml repository is fixed, let's build it in CI. Changes from v1 to v2: - split according to Andrea's hints - removed --with-libvirt as argument for configure, no more needed after upstream changes Pino Toscano (3): guests: add mappings for OCaml components guests: pull dependencies for libvirt-ocaml Add libvirt-ocaml project guests/host_vars/libvirt-centos-7/main.yml | 1 + guests/host_vars/libvirt-debian-9/main.yml | 1 + guests/host_vars/libvirt-debian-sid/main.yml | 1 + guests/host_vars/libvirt-fedora-27/main.yml | 1 + guests/host_vars/libvirt-fedora-28/main.yml | 1 + .../host_vars/libvirt-fedora-rawhide/main.yml | 1 + guests/host_vars/libvirt-freebsd-10/main.yml | 1 + guests/host_vars/libvirt-freebsd-11/main.yml | 1 + .../libvirt-freebsd-current/main.yml | 1 + guests/host_vars/libvirt-ubuntu-16/main.yml | 1 + guests/host_vars/libvirt-ubuntu-18/main.yml | 1 + guests/playbooks/build/jobs/defaults.yml | 2 ++ .../build/projects/libvirt-ocaml.yml | 27 +++++++++++++++++++ guests/vars/mappings.yml | 6 +++++ guests/vars/projects/libvirt-ocaml.yml | 5 ++++ jobs/defaults.yaml | 2 ++ projects/libvirt-ocaml.yaml | 23 ++++++++++++++++ 17 files changed, 76 insertions(+) create mode 100644 guests/playbooks/build/projects/libvirt-ocaml.yml create mode 100644 guests/vars/projects/libvirt-ocaml.yml create mode 100644 projects/libvirt-ocaml.yaml -- 2.17.2

3 7

[libvirt] [PATCH] qemu: Restore lost shutdown reason
by John Ferlan 02 Nov '18

02 Nov '18

When qemuProcessReconnectHelper was introduced (commit d38897a5d) reconnection failure used VIR_DOMAIN_SHUTOFF_FAILED; however, that was changed in commit bda2f17d to either VIR_DOMAIN_SHUTOFF_CRASHED or VIR_DOMAIN_SHUTOFF_UNKNOWN. When QEMU_CAPS_NO_SHUTDOWN checking was removed in commit fe35b1ad6 the conditional state was just left at VIR_DOMAIN_SHUTOFF_CRASHED. Restore the logic adjustment using the same conditions as command line building and alter the comment to describe the reasoning. Signed-off-by: John Ferlan <jferlan(a)redhat.com> --- This was "discovered" while reviewing Nikolay's patch related to adding "DAEMON" as the shutdown reason: https://www.redhat.com/archives/libvir-list/2018-October/msg00493.html While working through the iterations of that - figured I'd at least post this. src/qemu/qemu_process.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 3955eda17c..4a39111d51 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -7985,11 +7985,16 @@ qemuProcessReconnect(void *opaque) if (virDomainObjIsActive(obj)) { /* We can't get the monitor back, so must kill the VM * to remove danger of it ending up running twice if - * user tries to start it again later - * If we couldn't get the monitor since QEMU supports - * no-shutdown, we can safely say that the domain - * crashed ... */ - state = VIR_DOMAIN_SHUTOFF_CRASHED; + * user tries to start it again later. + * + * If we cannot get to the monitor when the QEMU command + * line used -no-shutdown, then we can safely say that the + * domain crashed; otherwise we don't really know. */ + if (priv->monJSON && priv->allowReboot == VIR_TRISTATE_BOOL_YES) + state = VIR_DOMAIN_SHUTOFF_CRASHED; + else + state = VIR_DOMAIN_SHUTOFF_UNKNOWN; + /* If BeginJob failed, we jumped here without a job, let's hope another * thread didn't have a chance to start playing with the domain yet * (it's all we can do anyway). -- 2.17.2

2 3

[libvirt] [PATCH] nodedev: Document the udevEventHandleThread
by John Ferlan 01 Nov '18

01 Nov '18

Add details of the algorithm and why it was used to help future readers understand the issues encountered. Based largely off a description provided by Erik Skultety <eskultet(a)redhat.com>. Signed-off-by: John Ferlan <jferlan(a)redhat.com> --- see: https://www.redhat.com/archives/libvir-list/2018-October/msg00915.html src/node_device/node_device_udev.c | 49 ++++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/src/node_device/node_device_udev.c b/src/node_device/node_device_udev.c index 22897591de..8ca81e65ad 100644 --- a/src/node_device/node_device_udev.c +++ b/src/node_device/node_device_udev.c @@ -1591,6 +1591,53 @@ udevEventMonitorSanityCheck(udevEventDataPtr priv, } +/** + * udevEventHandleThread + * @opaque: unused + * + * Thread to handle the udevEventHandleCallback processing when udev + * tells us there's a device change for us (add, modify, delete, etc). + * + * Management of the processing udev device notification is a delicate + * balance between the udev process, the scheduler, and when exactly the + * data from/for the socket is received. The udev processing code notifies + * the udevEventHandleCallback that it has data; however, the actual recv() + * done in the udev code to fill in the @device structure can be delayed + * due to how threads are scheduled. + * + * As it turns out, the event loop could be scheduled (and it in fact + * was) earlier than the handler thread. What that essentially means is + * that by the time the thread actually handled the event and read the + * data from the monitor, the event loop fired the very same event, simply + * because the data hadn't been retrieved from the socket at that point yet. + * + * Thus this algorithm is that once udevEventHandleCallback is notified + * there is data, this loop will process as much data as possible until + * udev_monitor_receive_device fails to get the @device. This may be + * because we've processed everything or because the scheduling thread + * hasn't been able to populate data in the socket. Once we're done + * processing everything we can, wait on the next event/notification. + * Although this may incur a slight delay if the socket data wasn't + * populated, the event/notifications are fairly consistent so there's + * no need to use virCondWaitUntil. + * + * NB: Usage of event based socket algorithm causes some issues with + * older platforms such as CentOS 6 in which the data socket is opened + * without the NONBLOCK bit set. Still even if the reset of priv->dataReady + * were moved to just after the udev_monitor_receive_device in order to + * avoid the NONBLOCK issue, the scheduler would still come into play + * especially for environments when multiple devices are added into the + * system. Even those environments would still be blocked on the udev + * socket recv() call. The algorithm for handling that scenario would + * be more complex and involve pulling the monitor object out of the + * private data lockable object and would need to be guarded by a + * separate lock. Devising algorithms to work around issues with older + * OS's at the expense of more modern OS algorithms in newer event + * processing code may result in unexpected issues, so the choice is + * to encourage use of newer OS's with newer udev event processing code. + * Newer devices, such as mdevs make heavy usage of event processing + * and it's expected future devices would follow that model. + */ static void udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) { @@ -1637,6 +1684,8 @@ udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) return; } + /* See the above description why this needs to be here + * and not after the udev_monitor_receive_device. */ virObjectLock(priv); priv->dataReady = false; virObjectUnlock(priv); -- 2.17.2

2 2

[libvirt] Entering freeze for libvirt 4.9.0
by Daniel Veillard 01 Nov '18

01 Nov '18

with a bit of delay today, I finally just tagged the release candidate 1 in git and pushed signed tarball and rpms to the usual place: ftp://libvirt.org/libvirt/ Looks fine in my minimal testing, and most of CI seems to be green except for 3 tests https://ci.centos.org/view/libvirt/ . I will likely push RC2 mid-day on thursday and if everything goes well the final release on the week-end. Please give the RC1 some testing especially on other architectures or oses, thanks in advance, Daniel -- Daniel Veillard | Red Hat Developers Tools http://developer.redhat.com/ veillard(a)redhat.com | libxml Gnome XML XSLT toolkit http://xmlsoft.org/ http://veillard.com/ | virtualization library http://libvirt.org/

1 1

[libvirt] [PATCH] qemu: Report warning if QoS is set for vhostuser interface
by Michal Privoznik 01 Nov '18

01 Nov '18

https://bugzilla.redhat.com/show_bug.cgi?id=1524230 Because of historical reasons, we are not denying starting a domain which has QoS set for unsupported type of device. We do report just a warning instead. And even though we perhaps used to do so for vhostuser it got lost somewhere. Bring it back. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com> --- src/qemu/qemu_command.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/src/qemu/qemu_command.c b/src/qemu/qemu_command.c index 6e3ff67660..489e8bc689 100644 --- a/src/qemu/qemu_command.c +++ b/src/qemu/qemu_command.c @@ -8246,6 +8246,12 @@ qemuBuildVhostuserCommandLine(virQEMUDriverPtr driver, goto cleanup; } + if (virDomainNetGetActualBandwidth(net)) { + VIR_WARN("setting bandwidth on interfaces of " + "type '%s' is not implemented yet", + virDomainNetTypeToString(VIR_DOMAIN_NET_TYPE_VHOSTUSER)); + } + switch ((virDomainChrType)net->data.vhostuser->type) { case VIR_DOMAIN_CHR_TYPE_UNIX: if (!(chardev = qemuBuildChrChardevStr(logManager, secManager, -- 2.18.1

2 3

[libvirt] [PATCH libvirt-python] event-test.py: Report ERROR events
by Philipp Hahn 01 Nov '18

01 Nov '18

VIR_DOMAIN_EVENT_ID_IO_ERROR and VIR_DOMAIN_EVENT_ID_IO_ERROR_REASON callbacks receive the same 'action' parameter, so also translate that numeric action to a descriptive text for the first callback. Signed-off-by: Philipp Hahn <hahn(a)univention.de> --- examples/event-test.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/event-test.py b/examples/event-test.py index dabf4b0..709277b 100755 --- a/examples/event-test.py +++ b/examples/event-test.py @@ -526,8 +526,8 @@ def myDomainEventWatchdogCallback(conn, dom, action, opaque): def myDomainEventIOErrorCallback(conn, dom, srcpath, devalias, action, opaque): - print("myDomainEventIOErrorCallback: Domain %s(%s) %s %s %d" % ( - dom.name(), dom.ID(), srcpath, devalias, action)) + print("myDomainEventIOErrorCallback: Domain %s(%s) %s %s %s" % ( + dom.name(), dom.ID(), srcpath, devalias, ERROR_EVENTS[action])) def myDomainEventIOErrorReasonCallback(conn, dom, srcpath, devalias, action, reason, opaque): -- 2.11.0

2 1

[libvirt] [PATCH libvirt-python] event-test.py: Fix ERROR event
by Philipp Hahn 01 Nov '18

01 Nov '18

ERROR_EVENTS translates the numeric 'action' argument to a description, not the 'reason' argument which already contains a descriptive string like 'enospc'. > Traceback (most recent call last): > File "/usr/lib/python2.7/dist-packages/libvirt.py", line 4661, in _dispatchDomainEventIOErrorReasonCallback > reason, opaque) > File "libvirt-python/examples/event-test.py", line 536, in myDomainEventIOErrorReasonCallback > dom.name(), dom.ID(), srcpath, devalias, action, ERROR_EVENTS[reason])) > File "libvirt-python/examples/event-test.py", line 474, in __getitem__ > data = self.args[item] > TypeError: tuple indices must be integers, not str Fixes: f5928c6711654f1496707ca77f626b3192843d57 Signed-off-by: Philipp Hahn <hahn(a)univention.de> --- examples/event-test.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/examples/event-test.py b/examples/event-test.py index eeb2777..dabf4b0 100755 --- a/examples/event-test.py +++ b/examples/event-test.py @@ -531,8 +531,8 @@ def myDomainEventIOErrorCallback(conn, dom, srcpath, devalias, action, opaque): def myDomainEventIOErrorReasonCallback(conn, dom, srcpath, devalias, action, reason, opaque): - print("myDomainEventIOErrorReasonCallback: Domain %s(%s) %s %s %d %s" % ( - dom.name(), dom.ID(), srcpath, devalias, action, ERROR_EVENTS[reason])) + print("myDomainEventIOErrorReasonCallback: Domain %s(%s) %s %s %s %s" % ( + dom.name(), dom.ID(), srcpath, devalias, ERROR_EVENTS[action], reason)) def myDomainEventGraphicsCallback(conn, dom, phase, localAddr, remoteAddr, authScheme, subject, opaque): -- 2.11.0

2 1

[libvirt] [PATCH v2] vhost-user: define conventions for vhost-user backends
by Marc-André Lureau 01 Nov '18

01 Nov '18

As discussed during "[PATCH v4 00/29] vhost-user for input & GPU" review, let's define a common set of backend conventions to help with management layer implementation, and interoperability. v2: - drop --pidfile - add some notes about daemonizing & stdin/out/err Cc: libvir-list(a)redhat.com Cc: Gerd Hoffmann <kraxel(a)redhat.com> Cc: Daniel P. Berrangé <berrange(a)redhat.com> Cc: Changpeng Liu <changpeng.liu(a)intel.com> Cc: Dr. David Alan Gilbert <dgilbert(a)redhat.com> Cc: Felipe Franciosi <felipe(a)nutanix.com> Cc: Gonglei <arei.gonglei(a)huawei.com> Cc: Maxime Coquelin <maxime.coquelin(a)redhat.com> Cc: Michael S. Tsirkin <mst(a)redhat.com> Cc: Victor Kaplansky <victork(a)redhat.com> Signed-off-by: Marc-André Lureau <marcandre.lureau(a)redhat.com> --- docs/interop/vhost-user.txt | 109 +++++++++++++++++++++++++++++++++++- 1 file changed, 107 insertions(+), 2 deletions(-) diff --git a/docs/interop/vhost-user.txt b/docs/interop/vhost-user.txt index ba5e37d714..339b335e9c 100644 --- a/docs/interop/vhost-user.txt +++ b/docs/interop/vhost-user.txt @@ -17,8 +17,13 @@ The protocol defines 2 sides of the communication, master and slave. Master is the application that shares its virtqueues, in our case QEMU. Slave is the consumer of the virtqueues. -In the current implementation QEMU is the Master, and the Slave is intended to -be a software Ethernet switch running in user space, such as Snabbswitch. +In the current implementation QEMU is the Master, and the Slave is the +external process consuming the virtio queues, for example a software +Ethernet switch running in user space, such as Snabbswitch, or a block +device backend processing read & write to a virtual disk. In order to +facilitate interoperability between various backend implementations, +it is recommended to follow the "Backend program conventions" +described in this document. Master and slave can be either a client (i.e. connecting) or server (listening) in the socket communication. @@ -859,3 +864,103 @@ resilient for selective requests. For the message types that already solicit a reply from the client, the presence of VHOST_USER_PROTOCOL_F_REPLY_ACK or need_reply bit being set brings no behavioural change. (See the 'Communication' section for details.) + +Backend program conventions +--------------------------- + +vhost-user backends provide various services and they may need to be +configured manually depending on the use case. However, it is a good +idea to follow the conventions listed here when possible. Users, QEMU +or libvirt, can then rely on some common behaviour to avoid +heterogenous configuration and management of the backend program and +facilitate interoperability. + +In order to be discoverable, default vhost-user backends should be +located under "/usr/libexec", and be named "vhost-user-$device" where +"$device" is the device name in lower-case following the name listed +in the Linux virtio_ids.h header (ex: the VIRTIO_ID_RPROC_SERIAL +backend would be named "vhost-user-rproc-serial"). + +Mechanisms to list, and to select among alternatives implementations +or modify the default backend are not described at this point (a +distribution may use update-alternatives, for example, to list and to +pick a different default backend). + +The backend program must not daemonize itself, but it may be +daemonized by the management layer. It may also have a restricted +access to the system. + +File descriptors 0, 1 and 2 will exist, and have regular +stdin/stdout/stderr usage (they may be redirected to /dev/null by the +management layer, or to a log handler). + +The backend program must end (as quickly and cleanly as possible) when +the SIGTERM signal is received. Eventually, it may be SIGKILL by the +management layer after a few seconds. + +The following command line options have an expected behaviour. They +are mandatory, unless explicitly said differently: + +* --socket-path=PATH + +This option specify the location of the vhost-user Unix domain socket. +It is incompatible with --fd. + +* --fd=FDNUM + +When this argument is given, the backend program is started with the +vhost-user socket as file descriptor FDNUM. It is incompatible with +--socket-path. + +* --print-capabilities + +Output to stdout a line-seperated list of backend capabilities, and +then exit successfully. Other options and arguments should be ignored, +and the backend program should not perform its normal function. + +At the time of writing, there are no common capabilities. Some +device-specific capabilities are listed in the respective sections. By +convention, device-specific capabilities are prefixed by their device +name. + +vhost-user-input program conventions +------------------------------------ + +Capabilities: + +input-evdev-path + + The --evdev-path command line option is supported. + +input-no-grab + + The --no-grab command line option is supported. + +* --evdev-path=PATH (optional) + +Specify the linux input device. + +* --no-grab (optional) + +Do no request exclusive access to the input device. + +vhost-user-gpu program conventions +---------------------------------- + +Capabilities: + +gpu-render-node + + The --render-node command line option is supported. + +gpu-virgl + + The --virgl command line option is supported. + +* --render-node=PATH (optional) + +Specify the GPU DRM render node. + +* --virgl (optional) + +Enable virgl rendering support. -- 2.19.0

5 16

[libvirt] [PATCH] libxl: add support for soft reset
by Jim Fehlig 31 Oct '18

31 Oct '18

The pvops Linux kernel implements machine_ops.crash_shutdown as static void xen_hvm_crash_shutdown(struct pt_regs *regs) { native_machine_crash_shutdown(regs); xen_reboot(SHUTDOWN_soft_reset); } but currently the libxl driver does not handle the soft reset shutdown event. As a result, the guest domain never proceeds past xen_reboot(), making it impossible for HVM domains to save a crash dump using kexec. This patch adds support for handling the soft reset event by calling libxl_domain_soft_reset() and re-enabling domain death events, which is similar to the xl tool handling of soft reset shutdown event. Signed-off-by: Jim Fehlig <jfehlig(a)suse.com> --- src/libxl/libxl_domain.c | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/src/libxl/libxl_domain.c b/src/libxl/libxl_domain.c index 0032b9dd11..295ec04a85 100644 --- a/src/libxl/libxl_domain.c +++ b/src/libxl/libxl_domain.c @@ -447,8 +447,10 @@ libxlDomainShutdownThread(void *opaque) virObjectEventPtr dom_event = NULL; libxl_shutdown_reason xl_reason = ev->u.domain_shutdown.shutdown_reason; libxlDriverConfigPtr cfg; + libxl_domain_config d_config; cfg = libxlDriverConfigGet(driver); + libxl_domain_config_init(&d_config); vm = virDomainObjListFindByID(driver->domains, ev->domid); if (!vm) { @@ -532,6 +534,33 @@ libxlDomainShutdownThread(void *opaque) * after calling libxl_domain_suspend() are handled by it's callers. */ goto endjob; + } else if (xl_reason == LIBXL_SHUTDOWN_REASON_SOFT_RESET) { + libxlDomainObjPrivatePtr priv = vm->privateData; + int res; + + if (libxl_retrieve_domain_configuration(cfg->ctx, vm->def->id, + &d_config) != 0) { + VIR_ERROR(_("Failed to retrieve config for VM '%s'. " + "Unable to perform soft reset. Destroying VM"), + vm->def->name); + goto destroy; + } + + if (priv->deathW) { + libxl_evdisable_domain_death(cfg->ctx, priv->deathW); + priv->deathW = NULL; + } + + res = libxl_domain_soft_reset(cfg->ctx, &d_config, vm->def->id, + NULL, NULL); + if (res != 0) { + VIR_ERROR(_("Failed to soft reset VM '%s'. Destroying VM"), + vm->def->name); + goto destroy; + } + libxl_evenable_domain_death(cfg->ctx, vm->def->id, 0, &priv->deathW); + libxl_domain_unpause(cfg->ctx, vm->def->id); + goto endjob; } else { VIR_INFO("Unhandled shutdown_reason %d", xl_reason); goto endjob; @@ -565,6 +594,7 @@ libxlDomainShutdownThread(void *opaque) virObjectEventStateQueue(driver->domainEventState, dom_event); libxl_event_free(cfg->ctx, ev); VIR_FREE(shutdown_info); + libxl_domain_config_dispose(&d_config); virObjectUnref(cfg); } -- 2.18.0

2 3

[libvirt] [PATCH v2 0/3] qemu: guest dedicated crypto adapters
by Boris Fiuczynski 31 Oct '18

31 Oct '18

v2: + added singleton check for vfio-ap mediated device This patch series introduces initial libvirt support for guest dedicated crypto adapters on S390. It allows to specify a vfio-ap mediated device in a domain. Extensive documentation about AP is available in patch 6 of the QEMU patch series. KVM/kernel: guest dedicated crypto adapters https://lkml.org/lkml/2018/9/26/25 QEMU: s390x: vfio-ap: guest dedicated crypto adapters https://lists.gnu.org/archive/html/qemu-devel/2018-10/msg01993.html The qemu patch series has been included into master. https://git.qemu.org/?p=qemu.git;a=commit;h=69ac8c4cb93f2685839ff7b857cef30… Boris Fiuczynski (3): qemu: add vfio-ap capability qemu: vfio-ap device support news: Update news for vfio-ap support docs/formatdomain.html.in | 3 ++- docs/news.xml | 9 +++++++++ docs/schemas/domaincommon.rng | 1 + src/conf/domain_conf.c | 28 ++++++++++++++++++++++++++++ src/qemu/qemu_capabilities.c | 2 ++ src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 8 ++++++++ src/qemu/qemu_domain_address.c | 4 ++++ src/util/virmdev.c | 3 ++- src/util/virmdev.h | 1 + 10 files changed, 58 insertions(+), 2 deletions(-) -- 2.17.0

5 19

[libvirt] [PATCH 0/3] RfC: add support for deprecated devices.
by Gerd Hoffmann 30 Oct '18

30 Oct '18

Works simliar to machine types, by adding a deprecation_reason field (using the same name for easy grepping). Also deprecate two devices: adlib and cirrus. This is tagged as RfC because the deprecation notice is not added to introspecction yet. Gerd Hoffmann (3): qdev: add deprecation_reason to DeviceClass adlib: mark as insecure and deprecated. cirrus: mark as deprecated hw/audio/adlib.c | 1 + hw/core/qdev.c | 9 ++++++++- hw/display/cirrus_vga.c | 2 ++ hw/display/cirrus_vga_isa.c | 2 ++ include/hw/qdev-core.h | 1 + qdev-monitor.c | 7 +++++++ qemu-deprecated.texi | 8 ++++++++ 7 files changed, 29 insertions(+), 1 deletion(-) -- 2.9.3

9 34

[libvirt] RFC: "Determine if the domain has been updated."?
by Philipp Hahn 30 Oct '18

30 Oct '18

Hello, <https://libvirt.org/html/libvirt-libvirt-domain.html#virDomainIsUpdated> states: > int virDomainIsUpdated (virDomainPtr dom) > > Determine if the domain has been updated. > > dom: pointer to the domain object > Returns: 1 if updated, 0 if not, -1 on error Not very enlightening :-( So what's the meaning of "updated" here: "inactive XML got changed but the currently running VM was started from a different XML"? Only very few drivers seem to mention it at all and they seem to mean different things. Any nobody seems to update the variable, only 4 readers: > $ git grep -ne '->updated' > libxl/libxl_driver.c:4844: ret = vm->updated; > lxc/lxc_driver.c:343: ret = obj->updated; > qemu/qemu_driver.c:1628: ret = obj->updated; > uml/uml_driver.c:1456: ret = obj->updated; Thank you for the clarification. Philipp -- Philipp Hahn Open Source Software Engineer Univention GmbH be open. Mary-Somerville-Str. 1 D-28359 Bremen Tel.: +49 421 22232-0 Fax : +49 421 22232-99 hahn(a)univention.de http://www.univention.de/ Geschäftsführer: Peter H. Ganten HRB 20755 Amtsgericht Bremen Steuer-Nr.: 71-597-02876

1 0

Re: [libvirt] [PATCH v3 0/3] Deprecate QMP & HMP `cpu-add`; document vCPU hotplug
by Kashyap Chamarthy 30 Oct '18

30 Oct '18

[Cc: libvir-list] On Tue, Oct 30, 2018 at 01:35:23PM +0100, Kashyap Chamarthy wrote: > The first patch deprecates the QMP `cpu-add`, the second its HMP > equivalent, and the third documents vCPU hotplug procedure using QMP > `device_add` et al. > > v2: https://lists.gnu.org/archive/html/qemu-devel/2018-09/msg03191.html > > Kashyap Chamarthy (3): > Deprecate QMP `cpu-add` > Deprecate HMP `cpu-add` > docs: Document vCPU hotplug procedure > > docs/cpu-hotplug.rst | 142 +++++++++++++++++++++++++++++++++++++++++++ > hmp-commands.hx | 6 +- > hmp.c | 2 + > qapi/misc.json | 8 ++- > qemu-deprecated.texi | 5 ++ > 5 files changed, 160 insertions(+), 3 deletions(-) > create mode 100644 docs/cpu-hotplug.rst > > -- > 2.17.1 > -- /kashyap

2 1

[libvirt] [PATCH 0/2] Fix compatibility with MTTCG
by Daniel P. Berrangé 30 Oct '18

30 Oct '18

QEMU is using MTTCG by default on an increasingly large set of host/guest combinations. This allows us to use the normal vCPU pinning support we already have for KVM. We just need to stop throwing away the PID info, and stop artificially blocking pinning APIs. Daniel P. Berrangé (2): qemu: fix recording of vCPU pids for MTTCG Revert "qemu: Forbid pinning vCPUs for TCG domain" src/qemu/qemu_domain.c | 81 ++++++++++++++++++++++++++---------------- src/qemu/qemu_driver.c | 7 ---- 2 files changed, 51 insertions(+), 37 deletions(-) -- 2.17.2

3 8

[libvirt] [PATCH 0/2] Augment access denied error message and adjust polkit docs
by John Ferlan 30 Oct '18

30 Oct '18

Details in the patches John Ferlan (2): access: Modify the VIR_ERR_ACCESS_DENIED to include driverName docs: Enhance polkit documentation to describe secondary connection docs/aclpolkit.html.in | 117 ++++++++++++++++++++++++++++++++++ docs/libvirt.css | 1 + src/access/viraccessmanager.c | 25 ++++---- src/rpc/gendispatch.pl | 2 +- src/util/virerror.c | 4 +- 5 files changed, 134 insertions(+), 15 deletions(-) -- 2.17.2

2 4

[libvirt] [snmp PATCH 00/20] Misc cleanups and improvements
by Michal Privoznik 29 Oct '18

29 Oct '18

These are not pushed. I'll wait couple of moments if there is somebody who has opinion. If not I will push them. Michal Privoznik (20): libvirtGuestTable.c: Free duplicated domain name libvirtSnmp.c: Retab and realign configure: Drop support for libvirt older than 0.9.0 configure.ac: Drop useless "-lvirt" in LIBVIRT_LIBS showError: Switch to less ancient error reporting libvirtSnmp: Modernize libvirtSnmpLoadGuests libvirtSnmp: Modernize insertGuest libvirtSnmp: Rewrite some functions src: Fix header file defines src: Fix includes in header files libvirtRegisterEvents: Drop pthread_attr_init libvirtSnmp: turn showError() into printf-like function libvirtSnmpError: Drop 'extern' for printLibvirtError() libvirtSnmp: Drop 'extern' from function headers libvirtSnmp: s/showError/printLibvirtError/ libvirtSnmpError: Introduce and use printSystemError libvirtSnmp: Fix type of libvirtUnregisterEvents() libvirtSnmp: Report libvirt errors if no domain is found libvirtSnmpInit: Don't report errors from libvirtRegisterEvents() .gitignore: Ignore tags file .gitignore | 1 + configure.ac | 31 +- src/Makefile.am | 18 - src/event_poll.c | 724 ------------------------------------- src/event_poll.h | 132 ------- src/ignore-value.h | 64 ---- src/internal.h | 138 ------- src/libvirtGuestTable.c | 4 +- src/libvirtNotifications.h | 8 +- src/libvirtSnmp.c | 436 ++++++++-------------- src/libvirtSnmp.h | 30 +- src/libvirtSnmpError.c | 83 ++++- src/libvirtSnmpError.h | 23 +- src/memory.c | 313 ---------------- src/memory.h | 212 ----------- src/threads.c | 251 ------------- src/threads.h | 101 ------ src/util.c | 105 ------ src/util.h | 38 -- 19 files changed, 261 insertions(+), 2451 deletions(-) delete mode 100644 src/event_poll.c delete mode 100644 src/event_poll.h delete mode 100644 src/ignore-value.h delete mode 100644 src/internal.h delete mode 100644 src/memory.c delete mode 100644 src/memory.h delete mode 100644 src/threads.c delete mode 100644 src/threads.h delete mode 100644 src/util.c delete mode 100644 src/util.h -- 2.18.1

3 25

[libvirt] [PATCH] qemu: Introduce caching whether /dev/kvm is accessible
by Marc Hartmayer 29 Oct '18

29 Oct '18

Introduce caching whether /dev/kvm is usable as the QEMU user:QEMU group. This reduces the overhead of the QEMU capabilities cache lookup. Before this patch there were many fork() calls used for checking whether /dev/kvm is accessible. Now we store the result whether /dev/kvm is accessible or not and we only need to re-run the virFileAccessibleAs check if the ctime of /dev/kvm has changed. Suggested-by: Daniel P. Berrangé <berrange(a)redhat.com> Signed-off-by: Marc Hartmayer <mhartmay(a)linux.ibm.com> --- src/qemu/qemu_capabilities.c | 56 ++++++++++++++++++++++++++++++++++-- 1 file changed, 54 insertions(+), 2 deletions(-) diff --git a/src/qemu/qemu_capabilities.c b/src/qemu/qemu_capabilities.c index e228f52ec0bb..ea95915f0f71 100644 --- a/src/qemu/qemu_capabilities.c +++ b/src/qemu/qemu_capabilities.c @@ -3238,6 +3238,10 @@ struct _virQEMUCapsCachePriv { virArch hostArch; unsigned int microcodeVersion; char *kernelVersion; + + /* cache whether /dev/kvm is usable as runUid:runGuid */ + virTristateBool kvmUsable; + time_t kvmCtime; }; typedef struct _virQEMUCapsCachePriv virQEMUCapsCachePriv; typedef virQEMUCapsCachePriv *virQEMUCapsCachePrivPtr; @@ -3824,6 +3828,54 @@ virQEMUCapsSaveFile(void *data, } +/* Determine whether '/dev/kvm' is usable as QEMU user:QEMU group. */ +static bool +virQEMUCapsKVMUsable(virQEMUCapsCachePrivPtr priv) +{ + struct stat sb; + static const char *kvm_device = "/dev/kvm"; + virTristateBool value; + virTristateBool cached_value = priv->kvmUsable; + time_t kvm_ctime; + time_t cached_kvm_ctime = priv->kvmCtime; + + if (stat(kvm_device, &sb) < 0) { + virReportSystemError(errno, + _("Failed to stat %s"), kvm_device); + return false; + } + kvm_ctime = sb.st_ctime; + + if (cached_value != VIR_TRISTATE_BOOL_ABSENT) { + if (kvm_ctime != cached_kvm_ctime) { + VIR_DEBUG("%s has changed (%lld vs %lld)", kvm_device, + (long long)kvm_ctime, (long long)cached_kvm_ctime); + goto update; + } + + return cached_value == VIR_TRISTATE_BOOL_YES; + } + + update: + if (virFileAccessibleAs(kvm_device, R_OK | W_OK, + priv->runUid, priv->runGid) == 0) { + value = VIR_TRISTATE_BOOL_YES; + } else { + value = VIR_TRISTATE_BOOL_NO; + } + + /* There is a race window between 'stat' and + * 'virFileAccessibleAs'. However, since we're only interested in + * detecting changes *after* the virFileAccessibleAs check, we can + * neglect this here. + */ + priv->kvmCtime = kvm_ctime; + priv->kvmUsable = value; + + return value == VIR_TRISTATE_BOOL_YES; +} + + static bool virQEMUCapsIsValid(void *data, void *privData) @@ -3872,8 +3924,7 @@ virQEMUCapsIsValid(void *data, return true; } - kvmUsable = virFileAccessibleAs("/dev/kvm", R_OK | W_OK, - priv->runUid, priv->runGid) == 0; + kvmUsable = virQEMUCapsKVMUsable(priv); if (!virQEMUCapsGet(qemuCaps, QEMU_CAPS_KVM) && kvmUsable) { @@ -4684,6 +4735,7 @@ virQEMUCapsCacheNew(const char *libDir, priv->runUid = runUid; priv->runGid = runGid; priv->microcodeVersion = microcodeVersion; + priv->kvmUsable = VIR_TRISTATE_BOOL_ABSENT; if (uname(&uts) == 0 && virAsprintf(&priv->kernelVersion, "%s %s", uts.release, uts.version) < 0) -- 2.17.0

2 1

[libvirt] Plan for next release
by Daniel Veillard 29 Oct '18

29 Oct '18

I'm afraid I'm a bit behind. I suggest to enter freeze tomorrow morning then pushing rc2 on Thursday and if everything goes well push the GA during the w.e., a bit late but not too late. I hope this works for everybody, thanks, Daniel -- Daniel Veillard | Red Hat Developers Tools http://developer.redhat.com/ veillard(a)redhat.com | libxml Gnome XML XSLT toolkit http://xmlsoft.org/ http://veillard.com/ | virtualization library http://libvirt.org/

1 0

[libvirt] number of graphic device in vm xml is limited to only 1
by Huangyong 29 Oct '18

29 Oct '18

Hello, In qemu_command, vnc graphic device can’t be more than 1, as the following code show in qemuBuildCommandLineValidate(): If（sdl > 1 || vnc > 1 || spice > 1） { virReportError(….); return -1; } This check originally introduced by commit: 6fe9025eb. Qemu: Error on unsupported graphics config qemu can support multi-vnc-configuration in qemu process, but libvirt limit vnc graphics in only 1. Is there any considerations in libvirt? can remove this restriction? ------------------------------------------------------------------------------------------------------------------------------------- 本邮件及其附件含有新华三集团的保密信息，仅限于发送给上面地址中列出的个人或群组。禁止任何其他人以任何形式使用（包括但不限于全部或部分地泄露、复制、或散发）本邮件中的信息。如果您错收了本邮件，请您立即电话或邮件通知发件人并删除本邮件！ This e-mail and its attachments contain confidential information from New H3C, which is intended only for the person or entity whose address is listed above. Any use of the information contained herein in any way (including, but not limited to, total or partial disclosure, reproduction, or dissemination) by persons other than the intended recipient(s) is prohibited. If you receive this e-mail in error, please notify the sender by phone or email immediately and delete it!

2 1

[libvirt] [PATCH v2 0/2] nwfilter: don't reinstantiate rules if there is no need to
by Nikolay Shirokovskiy 29 Oct '18

29 Oct '18

Applied on top of [1] that restores reinstantiating filters on daemon reload. Note the fragile issue mentioned in ebiptablesDumpIstalledRules in respect to list of firewall tables we are using. I wonder can we instead of caching instantiate rules faster in the end? There is iptables-restore if we instantiate directly. And in case of firewalld mode why we instantiate filters via firewalld dbus interface after all? We use passthrough interface so looks like firewalld don't account our rules in any way. May be all we need is reloading rules on firewalld reload and always instantiate thru binaries? Then we can do things fast. Diff from v1 [2]: ------------ Approach is changed. Instead of checking whether applied filters changed or not (so we can miss firewall changes from outside) let's check that don't change both - rules we are going to apply and rules in firewall in comparion to previous instantiation. [1] [PATCH] nwfilter: intantiate filters on loading driver https://www.redhat.com/archives/libvir-list/2018-October/msg00787.html [2] [PATCH RFC 0/4] nwfilter: don't reinstantiate filters if they are not changed https://www.redhat.com/archives/libvir-list/2018-October/msg00904.html [3] [RFC] Faster libvirtd restart with nwfilter rules https://www.redhat.com/archives/libvir-list/2018-September/msg01206.html which continues in https://www.redhat.com/archives/libvir-list/2018-October/msg00657.html Nikolay Shirokovskiy (2): firewall: add dump function nwfilter: don't reinstantiate rules if there is no need to src/libvirt_private.syms | 1 + src/nwfilter/nwfilter_ebiptables_driver.c | 387 +++++++++++++++++++++++++++++- src/util/virfirewall.c | 111 +++++++++ src/util/virfirewall.h | 3 + 4 files changed, 500 insertions(+), 2 deletions(-) -- 1.8.3.1

1 2

[libvirt] [PATCH] conf: More clear error msg for incomplete coalesce xml
by Han Han 29 Oct '18

29 Oct '18

https://bugzilla.redhat.com/show_bug.cgi?id=1535930 Report more clear err msg instead of unknown error when coalesce settings is incomplete. Signed-off-by: Han Han <hhan(a)redhat.com> --- src/conf/domain_conf.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/src/conf/domain_conf.c b/src/conf/domain_conf.c index 9911d56130..e755f45d3d 100644 --- a/src/conf/domain_conf.c +++ b/src/conf/domain_conf.c @@ -7804,8 +7804,12 @@ virDomainNetDefCoalesceParseXML(xmlNodePtr node, ctxt->node = node; str = virXPathString("string(./rx/frames/@max)", ctxt); - if (!str) + if (!str) { + virReportError(VIR_ERR_XML_DETAIL, + "%s", + _("incomplete coalesce settings in interface xml")); goto cleanup; + } if (VIR_ALLOC(ret) < 0) goto cleanup; -- 2.19.1

3 5

[libvirt] [PULL v2 00/43] Machine queue, 2018-10-25
by Eduardo Habkost 26 Oct '18

26 Oct '18

Changes v1 -> v2: * Fix 'make check' warnings (Igor) The following changes since commit 13399aad4fa87b2878c49d02a5d3bafa6c966ba3: Merge remote-tracking branch 'remotes/armbru/tags/pull-error-2018-10-22' into staging (2018-10-23 17:20:23 +0100) are available in the Git repository at: git://github.com/ehabkost/qemu.git tags/machine-next-pull-request for you to fetch changes up to 8fa922c241e63f018f5b55c03ac494ae3d5fe594: net: xgmac: convert SysBus init method to a realize method (2018-10-24 06:44:59 -0300) ---------------------------------------------------------------- Machine queue, 2018-10-25 * sysbus init/realize cleanups (Cédric Le Goater, Philippe Mathieu-Daudé) * memory-device refactoring (David Hildenbrand) * -smp: deprecate incorrect CPUs topology (Igor Mammedov) * -numa parsing cleanups (Markus Armbruster) * Fix hostmem-file memory leak (Zhang Yi) * Typo fix (Li Qiang) ---------------------------------------------------------------- Queue for Machine Core patches Cédric Le Goater (11): net: etraxfs_eth: convert SysBus init method to a realize method net: etraxfs_eth: add a reset method net: lan9118: convert SysBus init method to a realize method net: lance: convert SysBus init method to a realize method net: milkymist_minimac2: convert SysBus init method to a realize method net: mipsnet: convert SysBus init method to a realize method net: opencores_eth: convert SysBus init method to a realize method net: smc91c111: convert SysBus init method to a realize method net: stellaris_enet: convert SysBus init method to a realize method net: stellaris_enet: add a reset method net: xgmac: convert SysBus init method to a realize method David Hildenbrand (16): memory-device: fix alignment error message memory-device: fix error message when hinted address is too small memory-device: improve "range conflicts" error message pc-dimm: pass PCDIMMDevice to pc_dimm_.*plug memory-device: use memory device terminology in error messages memory-device: introduce separate config option memory-device: forward errors in get_region_size()/get_plugged_size() memory-device: document MemoryDeviceClass memory-device: add and use memory_device_get_region_size() memory-device: factor out get_memory_region() from pc-dimm memory-device: drop get_region_size() memory-device: add device class function set_addr() memory-device: complete factoring out pre_plug handling memory-device: complete factoring out plug handling memory-device: complete factoring out unplug handling memory-device: trace when pre_plugging/plugging/unplugging Igor Mammedov (2): vl.c deprecate incorrect CPUs topology vl:c: make sure that sockets are calculated correctly in '-smp X' case Li Qiang (1): machine: fix a typo Philippe Mathieu-Daudé (12): trace-events: Fix copy/paste typo hw/timer/sun4v-rtc: Convert from DPRINTF() macro to trace events hw/timer/sun4v-rtc: Use DeviceState::realize rather than SysBusDevice::init hw/ssi/xilinx_spi: Use DeviceState::realize rather than SysBusDevice::init hw/sh4/sh_pci: Use DeviceState::realize rather than SysBusDevice::init hw/pci-host/bonito: Use DeviceState::realize rather than SysBusDevice::init hw/mips/gt64xxx_pci: Convert gt64120_reset() function into Device reset method hw/mips/gt64xxx_pci: Mark as bridge device hw/sparc64/niagara: Model the I/O Bridge with the 'unimplemented_device' hw/alpha/typhoon: Remove unuseful code hw/hppa/dino: Remove unuseful code hw/mips/malta: Remove unuseful code Zhang Yi (1): hostmem-file: fixed the memory leak while get pmem path. default-configs/i386-softmmu.mak | 3 +- default-configs/ppc64-softmmu.mak | 3 +- default-configs/sparc64-softmmu.mak | 1 - qapi/misc.json | 2 +- include/hw/mem/memory-device.h | 74 +++++++++++++++++--- include/hw/mem/pc-dimm.h | 10 +-- backends/hostmem-file.c | 10 ++- hw/alpha/typhoon.c | 13 ---- hw/core/machine.c | 2 +- hw/hppa/dino.c | 7 -- hw/i386/pc.c | 6 +- hw/mem/memory-device.c | 103 ++++++++++++++++++++++------ hw/mem/nvdimm.c | 9 ++- hw/mem/pc-dimm.c | 84 ++++++++--------------- hw/mips/gt64xxx_pci.c | 18 ++--- hw/mips/mips_malta.c | 13 ---- hw/net/etraxfs_eth.c | 44 ++++++++---- hw/net/lan9118.c | 9 +-- hw/net/lance.c | 8 +-- hw/net/milkymist-minimac2.c | 9 +-- hw/net/mipsnet.c | 9 +-- hw/net/opencores_eth.c | 8 +-- hw/net/smc91c111.c | 8 +-- hw/net/stellaris_enet.c | 15 ++-- hw/net/xgmac.c | 9 +-- hw/pci-host/bonito.c | 9 +-- hw/ppc/spapr.c | 29 +++----- hw/sh4/sh_pci.c | 20 +++--- hw/sparc64/niagara.c | 4 +- hw/ssi/xilinx_spi.c | 9 +-- hw/timer/sun4v-rtc.c | 23 +++---- tests/cpu-plug-test.c | 18 ++--- vl.c | 12 +++- hw/Makefile.objs | 2 +- hw/mem/Makefile.objs | 4 +- hw/mem/trace-events | 5 +- hw/timer/trace-events | 6 +- qemu-deprecated.texi | 12 ++++ 38 files changed, 344 insertions(+), 286 deletions(-) -- 2.18.0.rc1.1.g3f1ff2140

4 33

[libvirt] [PATCH 00/11] Avoid numerous calls of virQEMUCapsCacheLookup
by Marc Hartmayer 26 Oct '18

26 Oct '18

For a domain definition there are numerous calls of virQEMUCapsCacheLookup (the same applies to the domain start). This slows down the process since virQEMUCapsCacheLookup validates that the QEMU capabilitites are still valid (among other things, a fork is done for this if the user for the QEMU processes is 'qemu'). Therefore let's reduce the number of virQEMUCapsCacheLookup calls whenever possible and reasonable. In addition to the speed up, there is the risk that virQEMUCapsCacheLookup returns different QEMU capabilities during a task if, for example, the QEMU binary has changed during the task. The correct way would be: - get the QEMU capabilities only once per task via virQEMUCapsCacheLookup - do the task with these QEMU capabilities or - abort the task after a cache invalidation Note: With this patch series the behavior is still not (completely) fixed, but the performance has been significantly improved. In a quick test this gave a speed up of factor 4 for a simple define/undefine loop. In general, the more devices a domain has, the more drastic the overhead becomes (because a cache validation is performed for each device). Marc Hartmayer (11): qemu: Use VIR_STEAL_PTR macro qemu: Introduce qemuDomainUpdateQEMUCaps() qemu: Pass QEMUCaps to virDomainDefPostParse conf: Use getParseOpaque() in virDomainObjSetDefTransient conf: Add function description for virDomainDefPostParse conf: Get rid of virDomainDeviceDefPostParseOne conf: Extend virDomainDefValidate(Callback) for parseOpaque conf: Use domainPostParseData(Alloc|Free) in virDomainDefValidate qemu: Use @parseOpaque in qemuDomainDefValidate conf: Extend virDomainDeviceDefValidate(Callback) for parseOpaque qemu: Use @parseOpaque in qemuDomainDeviceDefValidate src/conf/domain_conf.c | 98 ++++++++++++++++++++++++++--------------- src/conf/domain_conf.h | 9 ++-- src/qemu/qemu_domain.c | 82 +++++++++++++++++++--------------- src/qemu/qemu_domain.h | 4 ++ src/qemu/qemu_process.c | 18 +++----- src/vz/vz_driver.c | 6 ++- 6 files changed, 128 insertions(+), 89 deletions(-) -- 2.17.0

5 40

[libvirt] [PATCH v2 0/9] Incremental Backup API additions
by Eric Blake 25 Oct '18

25 Oct '18

The following is the latest version of my API proposal for incremental backups. I have even more work-in-progress patches on top of these: https://repo.or.cz/libvirt/ericb.git which I am slowly improving to be more in line with my thread on the overview of the API usage: https://www.redhat.com/archives/libvir-list/2018-October/msg00217.html But I am fairly satisfied that the API as presented is sufficient for everything I have still been implementing in the qemu driver, and that even when qemu is slightly tweaked (such as dropping the x- prefix on various commands, or maybe adding a new command to make it easier to compute the estimated size of the union of several bitmaps), those changes will be limited to the src/qemu directory rather than affecting the API. Since I will be demonstrating the use of this API at the KVM Forum, I would really like a decision on whether we can commit the API into libvirt now, even if we have to wait for the qemu implementation of the API until qemu stabilizes its interfaces (also, having the libvirt API in place gives qemu an incentive to drop the x- prefix sooner rather than later). That in turn implies that I need code reviews; John Ferlan started reviewing v1, but mostly focused on the documentation grammar: https://www.redhat.com/archives/libvir-list/2018-June/msg01066.html The following gives an idea of how this series has changed since June (in part due to rebases, in part due to documentation improvements): The flags [FC] indicate (F)unctional and (C)ontextual differences, respectively 001/9:[0050] [FC] 'snapshots: Avoid term 'checkpoint' for full system snapshot' 002/9:[down] 'domain_conf: Expose virDomainStorageNetworkParseHost' 003/9:[0342] [FC] 'backup: Document nuances between different state capture APIs' 004/9:[0007] [FC] 'backup: Introduce virDomainCheckpointPtr' 005/9:[0100] [FC] 'backup: Document new XML for backups' 006/9:[0042] [FC] 'backup: Introduce virDomainCheckpoint APIs' 007/9:[0035] [FC] 'backup: Introduce virDomainBackup APIs' 008/9:[----] [--] 'backup: Add new domain:checkpoint access control' 009/9:[0039] [FC] 'backup: Implement backup APIs for remote driver' Eric Blake (9): snapshots: Avoid term 'checkpoint' for full system snapshot domain_conf: Expose virDomainStorageNetworkParseHost backup: Document nuances between different state capture APIs backup: Introduce virDomainCheckpointPtr backup: Document new XML for backups backup: Introduce virDomainCheckpoint APIs backup: Introduce virDomainBackup APIs backup: Add new domain:checkpoint access control backup: Implement backup APIs for remote driver include/libvirt/virterror.h | 6 +- src/util/virerror.c | 21 +- include/libvirt/libvirt-domain-checkpoint.h | 177 ++++ include/libvirt/libvirt-domain-snapshot.h | 2 +- include/libvirt/libvirt-domain.h | 14 +- include/libvirt/libvirt.h | 3 +- src/access/viraccessperm.h | 8 +- src/conf/domain_conf.h | 2 + src/datatypes.h | 31 +- src/driver-hypervisor.h | 74 +- docs/Makefile.am | 3 + docs/apibuild.py | 2 + docs/docs.html.in | 9 +- docs/domainstatecapture.html.in | 314 +++++++ docs/format.html.in | 1 + docs/formatcheckpoint.html.in | 285 ++++++ docs/formatsnapshot.html.in | 33 +- docs/index.html.in | 3 +- docs/schemas/domainbackup.rng | 185 ++++ docs/schemas/domaincheckpoint.rng | 94 ++ libvirt.spec.in | 3 + mingw-libvirt.spec.in | 6 + po/POTFILES | 1 + src/Makefile.am | 2 + src/access/viraccessperm.c | 5 +- src/conf/domain_conf.c | 43 +- src/conf/snapshot_conf.c | 4 +- src/datatypes.c | 62 +- src/libvirt-domain-checkpoint.c | 936 +++++++++++++++++++ src/libvirt-domain-snapshot.c | 7 +- src/libvirt-domain.c | 8 +- src/libvirt_private.syms | 3 + src/libvirt_public.syms | 23 + src/qemu/qemu_driver.c | 12 +- src/remote/remote_daemon_dispatch.c | 15 + src/remote/remote_driver.c | 33 +- src/remote/remote_protocol.x | 240 ++++- src/remote_protocol-structs | 129 +++ src/rpc/gendispatch.pl | 32 +- tests/Makefile.am | 6 +- tests/domainbackupxml2xmlin/backup-pull.xml | 9 + tests/domainbackupxml2xmlin/backup-push.xml | 9 + tests/domainbackupxml2xmlin/empty.xml | 1 + tests/domainbackupxml2xmlout/backup-pull.xml | 9 + tests/domainbackupxml2xmlout/backup-push.xml | 9 + tests/domainbackupxml2xmlout/empty.xml | 7 + tests/domaincheckpointxml2xmlin/empty.xml | 1 + tests/domaincheckpointxml2xmlin/sample.xml | 7 + tests/domaincheckpointxml2xmlout/empty.xml | 10 + tests/domaincheckpointxml2xmlout/sample.xml | 16 + tests/virschematest.c | 4 + tools/virsh-domain.c | 3 +- tools/virsh-snapshot.c | 2 +- tools/virsh.pod | 14 +- 54 files changed, 2846 insertions(+), 92 deletions(-) create mode 100644 include/libvirt/libvirt-domain-checkpoint.h create mode 100644 docs/domainstatecapture.html.in create mode 100644 docs/formatcheckpoint.html.in create mode 100644 docs/schemas/domainbackup.rng create mode 100644 docs/schemas/domaincheckpoint.rng create mode 100644 src/libvirt-domain-checkpoint.c create mode 100644 tests/domainbackupxml2xmlin/backup-pull.xml create mode 100644 tests/domainbackupxml2xmlin/backup-push.xml create mode 100644 tests/domainbackupxml2xmlin/empty.xml create mode 100644 tests/domainbackupxml2xmlout/backup-pull.xml create mode 100644 tests/domainbackupxml2xmlout/backup-push.xml create mode 100644 tests/domainbackupxml2xmlout/empty.xml create mode 100644 tests/domaincheckpointxml2xmlin/empty.xml create mode 100644 tests/domaincheckpointxml2xmlin/sample.xml create mode 100644 tests/domaincheckpointxml2xmlout/empty.xml create mode 100644 tests/domaincheckpointxml2xmlout/sample.xml -- 2.17.1

3 19

[libvirt] Release of libvirt-snmp-0.0.4
by Michal Prívozník 25 Oct '18

25 Oct '18

It's out. After 6 years we have a new libvirt-snmp release. Yay. You can obtain it from the usual sources: https://libvirt.org/sources/snmp/ I've pushed it into git and tagged. Thanks everybody who participated in any form. Changelog: - Replace placeholder org OID with libvirt OID - Fix object OIDs for SNMP traps - Send sysUptime in traps - Modernize spec file - Cleaned up some old code and rewritten it to use new Libvirt APIs - Fixed build with newer net-snmp package - Some bug fixes Michal

1 0

[libvirt] [snmp PATCH] configure: Fix MIB_DIR's prefix
by Michal Privoznik 25 Oct '18

25 Oct '18

So far we are taking whatever is `net-snmp-config --default-mibdirs` returns and using that as MIB_DIR to install our MIB. This has a drawback that it ignores whatever prefix user specifies to configure script (which is used by `make distcheck` too). The fix consists of querying for net-snmp-config --prefix and replacing that in MIB_DIR var. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com> --- This is similar to what we do for wireshark in libvirt. configure.ac | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/configure.ac b/configure.ac index baac0e1..f729ac1 100644 --- a/configure.ac +++ b/configure.ac @@ -73,6 +73,14 @@ if test "x$with_mibdir" = "x" ; then MIB_DIR=$(echo $MIB_DIR | awk -F : '{print $NF}') AC_MSG_RESULT([found $MIB_DIR]) + + dnl Replace net-snmp's exec_prefix with our own. + dnl Note that ${exec_prefix} is kept verbatim at this point in time, + dnl and will only be expanded later, when make is called: this makes + dnl it possible to override such prefix at compilation or installation + dnl time + MIB_PREFIX="`$SNMP_CONFIG --prefix`" + MIB_DIR='${exec_prefix}'"${MIB_DIR#$MIB_PREFIX}" else AC_MSG_CHECKING([accessibility of $with_mibdir]) if test ! -d "$with_mibdir" ; then -- 2.18.1

2 1

[libvirt] [PATCH 00/11] Allow modification of IOThread polling values (redux)
by John Ferlan 23 Oct '18

23 Oct '18

This series attempts to resurrect the concept of being able to modify the IOThread polling parameters; however, in a slightly different manner than the previous series posted by posted by Pavel Hrdina <phrdina(a)redhat.com>: https://www.redhat.com/archives/libvir-list/2017-February/msg01047.html The work is prompted by continued pleas found in the bz: https://bugzilla.redhat.com/show_bug.cgi?id=1545732 to provide some way to modify the paremters without needing to supply QEMU command line pass through values. It's accepted that the values being changed are fairly or extremely low level type knobs; however, it's also shown that by being able to turn the knob it is possible for certain, specific appliances to be able to gain a performance benefit for the thread at the expense of other competing threads. Unlike the previous series, this series does not attempt to save the polling values in the guest XML. Rather, it only modifies the live guest's IOThread with new values. It also doesn't provide the polling values in a virsh iothread* command, rather it uses the domstats in order to fetch and display the values. The theory being this leaves the onus on the higher level appliance/application to provide the "proper guidance" and "concerns" related to changing the values to the consumer. Not saving the values means whatever values that are chosen do not "live" in perpetuity. Once the guest is shut down or the IOThread removed from guest, the hypervisor default values take over again. Perhaps not a perfect situation in terms of what the bz requests; however, storage of default values that could cause performance issues is not an optimal situation. So this I figured is a "comprimise" of sorts. If it's still felt that no we don't want to do this, then fine, but please in doing so own the bz, state your case, and close it. I'm 50/50 on it, but figured at least I'd present this option and see what the concensus was. John Ferlan (11): qemu: Check for and return IOThread polling values if available qemu: Split qemuDomainGetIOThreadsLive qemu: Implement the ability to return IOThread stats virsh: Add ability to display IOThread stats lib: Introduce virDomainSetIOThreadParams qemu: Add monitor functions to set IOThread params qemu: Alter qemuDomainChgIOThread to take enum instead of bool qemu: Alter qemuDomainChgIOThread to take qemuMonitorIOThreadInfo qemu: Detect whether iothread polling is supported qemu: Introduce qemuDomainSetIOThreadParams tools: Add virsh iothreadset command include/libvirt/libvirt-domain.h | 45 ++ src/driver-hypervisor.h | 8 + src/libvirt-domain.c | 109 +++++ src/libvirt_public.syms | 5 + src/qemu/qemu_capabilities.c | 2 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_driver.c | 393 ++++++++++++++++-- src/qemu/qemu_monitor.c | 19 + src/qemu/qemu_monitor.h | 6 + src/qemu/qemu_monitor_json.c | 48 +++ src/qemu/qemu_monitor_json.h | 4 + src/remote/remote_driver.c | 1 + src/remote/remote_protocol.x | 21 +- src/remote_protocol-structs | 10 + .../caps_2.10.0.aarch64.xml | 1 + .../caps_2.10.0.ppc64.xml | 1 + .../caps_2.10.0.s390x.xml | 1 + .../caps_2.10.0.x86_64.xml | 1 + .../caps_2.11.0.s390x.xml | 1 + .../caps_2.11.0.x86_64.xml | 1 + .../caps_2.12.0.aarch64.xml | 1 + .../caps_2.12.0.ppc64.xml | 1 + .../caps_2.12.0.s390x.xml | 1 + .../caps_2.12.0.x86_64.xml | 1 + .../qemucapabilitiesdata/caps_2.9.0.ppc64.xml | 1 + .../qemucapabilitiesdata/caps_2.9.0.s390x.xml | 1 + .../caps_2.9.0.x86_64.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.ppc64.xml | 1 + .../caps_3.0.0.riscv32.xml | 1 + .../caps_3.0.0.riscv64.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.s390x.xml | 1 + .../caps_3.0.0.x86_64.xml | 1 + tools/virsh-domain-monitor.c | 7 + tools/virsh-domain.c | 110 +++++ tools/virsh.pod | 47 ++- 35 files changed, 810 insertions(+), 44 deletions(-) -- 2.17.1

4 29

[libvirt] [PATCH] docs: fix repology link for qemu-kvm package
by Pavel Hrdina 23 Oct '18

23 Oct '18

Signed-off-by: Pavel Hrdina <phrdina(a)redhat.com> --- Pushed under trivial rule. docs/platforms.html.in | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/platforms.html.in b/docs/platforms.html.in index 0489c60aeb..a037074e1f 100644 --- a/docs/platforms.html.in +++ b/docs/platforms.html.in @@ -39,7 +39,7 @@ <ul> <li><a href="https://repology.org/metapackage/libvirt/versions">libvirt</a></li> <li><a href="https://repology.org/metapackage/qemu/versions">qemu</a></li> - <li><a href="https://repology.org/metapackage/qemu/versions">qemu-kvm</a></li> + <li><a href="https://repology.org/metapackage/qemu-kvm/versions">qemu-kvm</a></li> </ul> -- 2.17.2

1 0

[libvirt] [PATCH] docs: Fix minimum supported version
by Martin Kletzander 23 Oct '18

23 Oct '18

We already have that in the code (commit c1bc9c662b411), we just forgot to mention that in the docs. Signed-off-by: Martin Kletzander <mkletzan(a)redhat.com> --- Pushed as trivial docs/drvqemu.html.in | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/drvqemu.html.in b/docs/drvqemu.html.in index 13adb5c22b22..0d14027646d5 100644 --- a/docs/drvqemu.html.in +++ b/docs/drvqemu.html.in @@ -8,7 +8,7 @@ <p> The libvirt KVM/QEMU driver can manage any QEMU emulator from - version 0.12.0 or later. + version 1.5.0 or later. </p> <h2><a id="project">Project Links</a></h2> -- 2.19.1

1 0

[libvirt] [jenkins-ci PATCH 0/3] Add libvirt-ocaml
by Pino Toscano 22 Oct '18

22 Oct '18

Now that the libvirt-ocaml repository is fixed, let's build it in CI. Pino Toscano (3): guests: add mappings for OCaml components guests: add libvirt-ocaml project projects: add libvirt-ocaml project guests/host_vars/libvirt-centos-7/main.yml | 1 + guests/host_vars/libvirt-debian-9/main.yml | 1 + guests/host_vars/libvirt-debian-sid/main.yml | 1 + guests/host_vars/libvirt-fedora-27/main.yml | 1 + guests/host_vars/libvirt-fedora-28/main.yml | 1 + .../host_vars/libvirt-fedora-rawhide/main.yml | 1 + guests/host_vars/libvirt-freebsd-10/main.yml | 1 + guests/host_vars/libvirt-freebsd-11/main.yml | 1 + .../libvirt-freebsd-current/main.yml | 1 + guests/host_vars/libvirt-ubuntu-16/main.yml | 1 + guests/host_vars/libvirt-ubuntu-18/main.yml | 1 + guests/playbooks/build/jobs/defaults.yml | 2 ++ .../build/projects/libvirt-ocaml.yml | 27 +++++++++++++++++++ guests/vars/mappings.yml | 6 +++++ guests/vars/projects/libvirt-ocaml.yml | 5 ++++ jobs/defaults.yaml | 2 ++ projects/libvirt-ocaml.yaml | 23 ++++++++++++++++ 17 files changed, 76 insertions(+) create mode 100644 guests/playbooks/build/projects/libvirt-ocaml.yml create mode 100644 guests/vars/projects/libvirt-ocaml.yml create mode 100644 projects/libvirt-ocaml.yaml -- 2.17.2

4 8

[libvirt] [PATCH] util: Fix typo vcups -> vcpus
by Martin Kletzander 22 Oct '18

22 Oct '18

Signed-off-by: Martin Kletzander <mkletzan(a)redhat.com> --- Pushed as trivial src/util/virnuma.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/util/virnuma.h b/src/util/virnuma.h index a3ffb6d6c7c9..edc206100f78 100644 --- a/src/util/virnuma.h +++ b/src/util/virnuma.h @@ -27,7 +27,7 @@ # include "virutil.h" -char *virNumaGetAutoPlacementAdvice(unsigned short vcups, +char *virNumaGetAutoPlacementAdvice(unsigned short vcpus, unsigned long long balloon); int virNumaSetupMemoryPolicy(virDomainNumatuneMemMode mode, -- 2.19.1

1 0

[libvirt] BugFix - Libvirt Ruby Binding Memory Stats Val Method
by iletisim＠muhammetdilmac.com.tr 22 Oct '18

22 Oct '18

1 0

[libvirt] [PATCH 0/2] syntax-check: revert expensive cosmetic checks
by Ján Tomko 22 Oct '18

22 Oct '18

Also do not bother taking C++ style comments into account. Ján Tomko (2): syntax-check: revert indentation checks check-spacing: do not kill C++-style comments build-aux/check-spacing.pl | 459 ++++++++++++++------------------------------- src/libvirt.c | 4 +- 2 files changed, 142 insertions(+), 321 deletions(-) -- 2.16.4

3 5

[libvirt] [PATCH RFC 0/4]] nwfilter: don't reinstantiate filters if they are not changed
by Nikolay Shirokovskiy 22 Oct '18

22 Oct '18

The series adds optimization in network filters instantiation as suggested in [1]. Applied on top of [2]. However this approach has drawback I'm unfortunately discovered too late) Next steps will left us with no network filters after this series applied: systemctl stop libvirtd systemctl restart firewalld systemctl start libvirtd In case of system update libvirt binaries ctime will change and filters will be reinstalled. [1] https://www.redhat.com/archives/libvir-list/2018-October/msg00657.html [2] https://www.redhat.com/archives/libvir-list/2018-October/msg00787.html Nikolay Shirokovskiy (4): nwfilter: add nwfilter hash nwfilter: don't reinstantiate filters if they are not changed nwfilter: force filters reinstantiation on firewalld reload nwfilter: force filters reinstantiation on binary update src/conf/virnwfilterbindingobj.c | 40 +++++++++ src/conf/virnwfilterbindingobj.h | 10 +++ src/conf/virnwfilterobj.c | 145 +++++++++++++++++++++++++++++++++ src/conf/virnwfilterobj.h | 9 ++ src/libvirt_private.syms | 6 ++ src/nwfilter/nwfilter_driver.c | 11 ++- src/nwfilter/nwfilter_gentech_driver.c | 67 +++++++++++++-- src/nwfilter/nwfilter_gentech_driver.h | 6 +- 8 files changed, 283 insertions(+), 11 deletions(-) -- 1.8.3.1

2 6

[libvirt] [PATCHv6 00/18] Introduce x86 Cache Monitoring Technology (CMT)
by Wang Huaqiang 22 Oct '18

22 Oct '18

This series of patches and the series already been merged introduce the x86 Cache Monitoring Technology (CMT) to libvirt by interacting with kernel resource control (resctrl) interface. CMT is one of the Intel(R) x86 CPU feature which belongs to the Resource Director Technology (RDT). CMT reports the occupancy of the last level cache, which is shared by all CPU cores. In the v1 series, an original and complete feature for CMT was introduced The v2 and v3 patches address the feature for the host capability of CMT. v4 is addressing the feature for monitoring VM vcpu thread set cache occupancy and reporting it through a virsh command. We have serval discussion about the enabling of CMT, please refer to following links for the RFCs. RFCv3 https://www.redhat.com/archives/libvir-list/2018-August/msg01213.html RFCv2 https://www.redhat.com/archives/libvir-list/2018-July/msg00409.html https://www.redhat.com/archives/libvir-list/2018-July/msg01241.html RFCv1 https://www.redhat.com/archives/libvir-list/2018-June/msg00674.html And the merged commits are list as below, for host capability of CMT. 6af8417415508c31f8ce71234b573b4999f35980 8f6887998bf63594ae26e3db18d4d5896c5f2cb4 58fcee6f3a2b7e89c21c1fb4ec21429c31a0c5b8 12093f1feaf8f5023dcd9d65dff111022842183d a5d293c18831dcf69ec6195798387fbb70c9f461 1. About reason why CMT is necessary in libvirt? The perf events of 'CMT, MBML, MBMT' have been phased out since Linux kernel commit c39a0e2c8850f08249383f2425dbd8dbe4baad69, in libvirt the perf based cmt,mbm will not work with the latest linux kernel. These patches add CMT feature to libvirt through kernel resctrlfs interface. 2 Create cache monitoring group (cache monitor). The main interface for creating monitoring group is through XML file. The proposed configuration is like: <cputune> <cachetune vcpus='1'> <cache id='0' level='3' type='code' size='7680' unit='KiB'/> <cache id='1' level='3' type='data' size='3840' unit='KiB'/> + <monitor level='3' vcpus='1'/> </cachetune> <cachetune vcpus='4-7'> + <monitor level='3' vcpus='4-6'/> </cachetune> </cputune> In above XML, created 2 cache resctrl allocation groups and 2 resctrl monitoring groups. The changes of cache monitor will be effective in next booting of VM. 2 Show CMT result through command 'domstats' Adding the interface in qemu to report this information for resource monitor group through command 'virsh domstats --cpu-total'. Below is a typical output: # virsh domstats 1 --cpu-total Domain: 'ubuntu16.04-base' ... cpu.cache.monitor.count=2 cpu.cache.monitor.0.name=vcpus_1 cpu.cache.monitor.0.vcpus=1 cpu.cache.monitor.0.bank.count=2 cpu.cache.monitor.0.bank.0.id=0 cpu.cache.monitor.0.bank.0.bytes=4505600 cpu.cache.monitor.0.bank.1.id=1 cpu.cache.monitor.0.bank.1.bytes=5586944 cpu.cache.monitor.1.name=vcpus_4-6 cpu.cache.monitor.1.vcpus=4,5,6 cpu.cache.monitor.1.bank.count=2 cpu.cache.monitor.1.bank.0.id=0 cpu.cache.monitor.1.bank.0.bytes=17571840 cpu.cache.monitor.1.bank.1.id=1 cpu.cache.monitor.1.bank.1.bytes=29106176 Changes in v6: - Addressing John's review comments for v5. - Removed and cleaned the concepts of 'default allocation' and 'default monitor'. - qemu: virsh domstats --cpu-total output for CMT, add identifier 'monitor' for each itm. Changes in v5: - qemu: Setting up vcpu and adding pids to resctrl monitor groups during re-connection. - Add the document for domain configuration related to resctrl monitor. Changes in v4: v4 is addressing the feature for monitoring VM vcpu thread set cache occupancy and reporting it through a virsh command. - Introduced resctrl default allocation - Introduced resctrl monitor and default monitor Changes in v3: - Addressed John Ferlan's review. - Typo fixed. - Removed VIR_ENUM_DECL(virMonitor); Changes in v2: - Introduced MBM capability. - Capability layout changed * Moved <monitor> from cahe <bank> to <cache> * Renamed <Threshold> to <reuseThreshold> - Document for 'reuseThreshold' changed. - Introduced API virResctrlInfoGetMonitorPrefix - Added more tests, covering standalone CMT, fake new feature. - Creating CMT resource control group will be subsequent job. Wang Huaqiang (18): docs,util: Refactor schemas and virresctrl to support optional cache util: Introduce resctrl monitor for CMT util: Refactor code for determining allocation path util: Add interface to determine monitor path util: Refactor code for adding PID to the resource group util: Add interface for adding PID to the monitor util: Refactor code for creating resctrl group util: Add interface for creating monitor group util: Add more interfaces for resctrl monitor conf: Remove virDomainResctrlAppend and introduce virDomainResctrlNew conf: move virResctrlAllocIsEmpty to a place a litter lower conf: Introduce cache monitor element in cachetune qemu: enable resctrl monitor in qemu util: Add function for checking if monitor is running conf: Add 'id' to virDomainResctrlDef qemu: refactor qemuDomainGetStatsCpu qemu: Report cache occupancy (CMT) with domstats qemu: Setting up vcpu and adding pids to resctrl monitor groups during reconnection docs/formatdomain.html.in | 30 +- docs/schemas/domaincommon.rng | 14 +- src/conf/domain_conf.c | 310 ++++++++++-- src/conf/domain_conf.h | 12 + src/libvirt-domain.c | 9 + src/libvirt_private.syms | 10 + src/qemu/qemu_driver.c | 270 +++++++++- src/qemu/qemu_process.c | 69 ++- src/util/virresctrl.c | 563 +++++++++++++++++++-- src/util/virresctrl.h | 49 ++ tests/genericxml2xmlindata/cachetune-cdp.xml | 3 + .../cachetune-colliding-monitor.xml | 30 ++ tests/genericxml2xmlindata/cachetune-small.xml | 7 + tests/genericxml2xmltest.c | 2 + 14 files changed, 1282 insertions(+), 96 deletions(-) create mode 100644 tests/genericxml2xmlindata/cachetune-colliding-monitor.xml -- 2.7.4

1 18

[libvirt] [PULL 00/45] Machine queue, 2018-10-18
by Eduardo Habkost 20 Oct '18

20 Oct '18

The following changes since commit 09558375a634e17cea6cfbfec883ac2376d2dc7f: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20181016-1' into staging (2018-10-16 17:42:56 +0100) are available in the Git repository at: git://github.com/ehabkost/qemu.git tags/machine-next-pull-request for you to fetch changes up to 6d8e1bcc7dd5e819ce81e6a87fffe23e39c700cc: numa: Clean up error reporting in parse_numa() (2018-10-17 16:33:40 -0300) ---------------------------------------------------------------- Machine queue, 2018-10-18 * sysbus init/realize cleanups (Cédric Le Goater, Philippe Mathieu-Daudé) * memory-device refactoring (David Hildenbrand) * -smp: deprecate incorrect CPUs topology (Igor Mammedov) * -numa parsing cleanups (Markus Armbruster) * Fix hostmem-file memory leak (Zhang Yi) * Typo fix (Li Qiang) ---------------------------------------------------------------- Queue for Machine Core patches Cédric Le Goater (11): net: etraxfs_eth: convert SysBus init method to a realize method net: etraxfs_eth: add a reset method net: lan9118: convert SysBus init method to a realize method net: lance: convert SysBus init method to a realize method net: milkymist_minimac2: convert SysBus init method to a realize method net: mipsnet: convert SysBus init method to a realize method net: opencores_eth: convert SysBus init method to a realize method net: smc91c111: convert SysBus init method to a realize method net: stellaris_enet: convert SysBus init method to a realize method net: stellaris_enet: add a reset method net: xgmac: convert SysBus init method to a realize method David Hildenbrand (16): memory-device: fix alignment error message memory-device: fix error message when hinted address is too small memory-device: improve "range conflicts" error message pc-dimm: pass PCDIMMDevice to pc_dimm_.*plug memory-device: use memory device terminology in error messages memory-device: introduce separate config option memory-device: forward errors in get_region_size()/get_plugged_size() memory-device: document MemoryDeviceClass memory-device: add and use memory_device_get_region_size() memory-device: factor out get_memory_region() from pc-dimm memory-device: drop get_region_size() memory-device: add device class function set_addr() memory-device: complete factoring out pre_plug handling memory-device: complete factoring out plug handling memory-device: complete factoring out unplug handling memory-device: trace when pre_plugging/plugging/unplugging Igor Mammedov (2): vl.c deprecate incorrect CPUs topology vl:c: make sure that sockets are calculated correctly in '-smp X' case Li Qiang (1): machine: fix a typo Markus Armbruster (2): numa: Fix QMP command set-numa-node error handling numa: Clean up error reporting in parse_numa() Philippe Mathieu-Daudé (12): trace-events: Fix copy/paste typo hw/timer/sun4v-rtc: Convert from DPRINTF() macro to trace events hw/timer/sun4v-rtc: Use DeviceState::realize rather than SysBusDevice::init hw/ssi/xilinx_spi: Use DeviceState::realize rather than SysBusDevice::init hw/sh4/sh_pci: Use DeviceState::realize rather than SysBusDevice::init hw/pci-host/bonito: Use DeviceState::realize rather than SysBusDevice::init hw/mips/gt64xxx_pci: Convert gt64120_reset() function into Device reset method hw/mips/gt64xxx_pci: Mark as bridge device hw/sparc64/niagara: Model the I/O Bridge with the 'unimplemented_device' hw/alpha/typhoon: Remove unuseful code hw/hppa/dino: Remove unuseful code hw/mips/malta: Remove unuseful code Zhang Yi (1): hostmem-file: fixed the memory leak while get pmem path. default-configs/i386-softmmu.mak | 3 +- default-configs/ppc64-softmmu.mak | 3 +- default-configs/sparc64-softmmu.mak | 1 - qapi/misc.json | 2 +- include/hw/mem/memory-device.h | 74 +++++++++++++++++--- include/hw/mem/pc-dimm.h | 10 +-- include/sysemu/numa.h | 1 - backends/hostmem-file.c | 10 ++- hw/alpha/typhoon.c | 13 ---- hw/core/machine.c | 2 +- hw/hppa/dino.c | 7 -- hw/i386/pc.c | 6 +- hw/mem/memory-device.c | 103 ++++++++++++++++++++++------ hw/mem/nvdimm.c | 9 ++- hw/mem/pc-dimm.c | 84 ++++++++--------------- hw/mips/gt64xxx_pci.c | 18 ++--- hw/mips/mips_malta.c | 13 ---- hw/net/etraxfs_eth.c | 44 ++++++++---- hw/net/lan9118.c | 9 +-- hw/net/lance.c | 8 +-- hw/net/milkymist-minimac2.c | 9 +-- hw/net/mipsnet.c | 9 +-- hw/net/opencores_eth.c | 8 +-- hw/net/smc91c111.c | 8 +-- hw/net/stellaris_enet.c | 15 ++-- hw/net/xgmac.c | 9 +-- hw/pci-host/bonito.c | 9 +-- hw/ppc/spapr.c | 29 +++----- hw/sh4/sh_pci.c | 20 +++--- hw/sparc64/niagara.c | 4 +- hw/ssi/xilinx_spi.c | 9 +-- hw/timer/sun4v-rtc.c | 23 +++---- numa.c | 21 +++--- vl.c | 12 +++- hw/Makefile.objs | 2 +- hw/mem/Makefile.objs | 4 +- hw/mem/trace-events | 5 +- hw/timer/trace-events | 6 +- qemu-deprecated.texi | 12 ++++ 39 files changed, 347 insertions(+), 287 deletions(-) -- 2.18.0.rc1.1.g3f1ff2140

6 80

[libvirt] [PATCH] qemu: fix device name passed to error report
by Daniel P. Berrangé 19 Oct '18

19 Oct '18

Signed-off-by: Daniel P. Berrangé <berrange(a)redhat.com> --- src/qemu/qemu_hotplug.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/qemu/qemu_hotplug.c b/src/qemu/qemu_hotplug.c index 0a63741b9e..12bef16fd6 100644 --- a/src/qemu/qemu_hotplug.c +++ b/src/qemu/qemu_hotplug.c @@ -5814,7 +5814,7 @@ qemuDomainDetachNetDevice(virQEMUDriverPtr driver, if (qemuIsMultiFunctionDevice(vm->def, &detach->info)) { virReportError(VIR_ERR_OPERATION_FAILED, _("cannot hot unplug multifunction PCI device: %s"), - dev->data.disk->dst); + net->ifname); goto cleanup; } -- 2.17.2

2 1

[libvirt] [PATCH] qemu: Fix IOThread pids lost after qemuProcessReconnect
by Jie Wang 19 Oct '18

19 Oct '18

>From fca1732c0e1f691fb25c614349d5486bbc73a109 Mon Sep 17 00:00:00 2001 From: Jie Wang <wangjie88(a)huawei.com> Date: Wed, 17 Oct 2018 22:55:51 +0800 Subject: [PATCH] qemu: Fix IOThread pids lost after qemuProcessReconnect IOThread pids info will lost after libvirtd restart, then if we call pinIOThread, sched_setaffinity will be called with pid 0, not IOThread pid. So pinIOThread cannot work normally. Signed-off-by: Jie Wang <wangjie88.huawei.com> --- src/qemu/qemu_process.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 40d35cbe6b..5bf55721d2 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -7650,6 +7650,9 @@ qemuProcessReconnect(void *opaque) qemuDomainVcpuPersistOrder(obj->def); + if (qemuProcessDetectIOThreadPIDs(driver, obj, QEMU_ASYNC_JOB_NONE) < 0) + goto error; + if (qemuSecurityReserveLabel(driver->securityManager, obj->def, obj->pid) < 0) goto error; -- 2.16.2.windows.1

2 1

[libvirt] [PATCH v4 0/5] libxl: PVHv2 support
by Marek Marczykowski-Górecki 19 Oct '18

19 Oct '18

This is a respin of my old PVHv1 patch[1], converted to PVHv2. The actual code use "PVH" name. The guest ostype reuse VIR_DOMAIN_OSTYPE_XEN, but to request PVH machine, machine="xenpvh" attribute is used. Since PVHv2 relies on features in newer Xen versions, I needed to convert also some older code. For example b_info->u.hvm.nested_hvm was deprecated in favor of b_info->nested_hvm. While the code do handle both old and new versions (obviously refusing PVHv2 if Xen is too old), this isn't the case for tests. How it should be handled, if at all? To test this with all supported Xen versions (4.6, 4.7, 4.8, 4.9, 4.10, 4.11, unstable), I've extended travis configuration for that[2]. It isn't exactly trivial to build Xen 4.6-4.8 on recent system, mostly thanks to -Werror and new warnings, but also other toolchain changes. Because of this, the configuration is rather hacky. But it may be a good idea to include multiple pre-built Xen versions in the base docker image and choose one using ./configure options (maybe together with some symlink or environment variable like PKG_CONFIG_PATH). [1] https://www.redhat.com/archives/libvir-list/2016-August/msg00376.html [2] https://github.com/marmarek/libvirt/tree/travis-xen-pvh Changes in v2: - drop "docs: don't refer to deprecated 'linux' ostype in example" patch - migrating further away from "linux" os type is offtopic to this series and apparently is a controversial thing - drop "docs: update domain schema for machine attribute" patch - already applied - apply review comments from Jim - rebase on master Changes in v3: - rebase on master, drop already applied patches - use #ifdef LIBXL_DOMAIN_TYPE_PVH to detect PVH support, fix compilation failure on older Xen - exclude PVH from VIR_DOMAIN_OSTYPE_XEN <-> VIR_DOMAIN_OSTYPE_LINUX conversion - fix reported capabilities for PVH Changes in v4: - change PVH support detection method Marek Marczykowski-Górecki (5): libxl: reorder libxlMakeDomBuildInfo for upcoming PVH support libxl: add support for PVH tests: add basic Xen PVH test xenconfig: add support for parsing type= xl config entry xenconfig: add support for type="pvh" docs/formatcaps.html.in | 4 +- docs/schemas/domaincommon.rng | 1 +- m4/virt-driver-libxl.m4 | 3 +- src/conf/domain_conf.c | 6 +- src/libxl/libxl_capabilities.c | 38 +++++++++-- src/libxl/libxl_conf.c | 76 ++++++++++++++++------ src/libxl/libxl_driver.c | 6 +- src/xenconfig/xen_common.c | 27 ++++++-- src/xenconfig/xen_xl.c | 5 +- tests/libxlxml2domconfigdata/basic-pvh.json | 49 ++++++++++++++- tests/libxlxml2domconfigdata/basic-pvh.xml | 28 ++++++++- tests/libxlxml2domconfigtest.c | 3 +- tests/testutilsxen.c | 3 +- tests/xlconfigdata/test-fullvirt-type.cfg | 21 ++++++- tests/xlconfigdata/test-fullvirt-type.xml | 27 ++++++++- tests/xlconfigdata/test-paravirt-type.cfg | 13 ++++- tests/xlconfigdata/test-paravirt-type.xml | 25 +++++++- tests/xlconfigdata/test-pvh-type.cfg | 13 ++++- tests/xlconfigdata/test-pvh-type.xml | 25 +++++++- tests/xlconfigtest.c | 3 +- 20 files changed, 341 insertions(+), 35 deletions(-) create mode 100644 tests/libxlxml2domconfigdata/basic-pvh.json create mode 100644 tests/libxlxml2domconfigdata/basic-pvh.xml create mode 100644 tests/xlconfigdata/test-fullvirt-type.cfg create mode 100644 tests/xlconfigdata/test-fullvirt-type.xml create mode 100644 tests/xlconfigdata/test-paravirt-type.cfg create mode 100644 tests/xlconfigdata/test-paravirt-type.xml create mode 100644 tests/xlconfigdata/test-pvh-type.cfg create mode 100644 tests/xlconfigdata/test-pvh-type.xml base-commit: 199eee6aae7af3d813fbe98660c7e0fa1a8ae7b7 -- git-series 0.9.1

5 29

[libvirt] [PATCH v2 00/12] Allow modification of IOThread polling values (redux)
by John Ferlan 19 Oct '18

19 Oct '18

v1: https://www.redhat.com/archives/libvir-list/2018-October/msg00456.html Changes since v1 (from code review) Patch 2: Move the job back into qemuDomainGetIOThreadsLive Patch 3: Add check for ActiveJob before allowing, use true for *StatsWorker, and print 'iothread' in output not 'block' Patch 5: Use virCheckPositiveArgGoto(nparams, error) instead of using virCheckNonNegativeArgGoto(nparams, error). And then remove the if (nparams) before the virCheckNonNullArgGoto(params, error); Patch 6: Add ability to determine which parameter was set via bool set_poll_{max_ns|grow|shrink} values. Then use those in the macro that sets the value to determine whether or not the value will be set based on whether it was changed. Patch 10: Use bool's to set_ when the value is found in the incoming params list. Remove the check that says poll_max_ns needs to be set. Testing proves that if it's set to 0, then the grow and shrink values can be changed (although they do nothing) Patch 12: (NEW) - News article John Ferlan (12): qemu: Check for and return IOThread polling values if available qemu: Split qemuDomainGetIOThreadsLive qemu: Implement the ability to return IOThread stats virsh: Add ability to display IOThread stats lib: Introduce virDomainSetIOThreadParams qemu: Add monitor functions to set IOThread params qemu: Alter qemuDomainChgIOThread to take enum instead of bool qemu: Alter qemuDomainChgIOThread to take qemuMonitorIOThreadInfo qemu: Detect whether iothread polling is supported qemu: Introduce qemuDomainSetIOThreadParams tools: Add virsh iothreadset command docs: Add news article for IOThread polling docs/news.xml | 13 + include/libvirt/libvirt-domain.h | 45 ++ src/driver-hypervisor.h | 8 + src/libvirt-domain.c | 108 +++++ src/libvirt_public.syms | 5 + src/qemu/qemu_capabilities.c | 2 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_driver.c | 384 ++++++++++++++++-- src/qemu/qemu_monitor.c | 19 + src/qemu/qemu_monitor.h | 9 + src/qemu/qemu_monitor_json.c | 50 +++ src/qemu/qemu_monitor_json.h | 4 + src/remote/remote_driver.c | 1 + src/remote/remote_protocol.x | 21 +- src/remote_protocol-structs | 10 + .../caps_2.10.0.aarch64.xml | 1 + .../caps_2.10.0.ppc64.xml | 1 + .../caps_2.10.0.s390x.xml | 1 + .../caps_2.10.0.x86_64.xml | 1 + .../caps_2.11.0.s390x.xml | 1 + .../caps_2.11.0.x86_64.xml | 1 + .../caps_2.12.0.aarch64.xml | 1 + .../caps_2.12.0.ppc64.xml | 1 + .../caps_2.12.0.s390x.xml | 1 + .../caps_2.12.0.x86_64.xml | 1 + .../qemucapabilitiesdata/caps_2.9.0.ppc64.xml | 1 + .../qemucapabilitiesdata/caps_2.9.0.s390x.xml | 1 + .../caps_2.9.0.x86_64.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.ppc64.xml | 1 + .../caps_3.0.0.riscv32.xml | 1 + .../caps_3.0.0.riscv64.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.s390x.xml | 1 + .../caps_3.0.0.x86_64.xml | 1 + tools/virsh-domain-monitor.c | 7 + tools/virsh-domain.c | 110 +++++ tools/virsh.pod | 47 ++- 36 files changed, 825 insertions(+), 37 deletions(-) -- 2.17.2

1 12

[libvirt] [PATCH] virFileInData: Preserve errno on error
by Michal Privoznik 19 Oct '18

19 Oct '18

The virFileInData() function should return to the caller if the current position the passed file is in is a data section or a hole (and also how long the current section is). At any rate, upon return from this function (be it successful or not) the original position in the file is restored. This may mess up with errno which might have been set earlier. Save the errno into a local variable so it can be restored for the caller's sake. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com> --- src/util/virfile.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/src/util/virfile.c b/src/util/virfile.c index e09992e41a..f6f01ec1e1 100644 --- a/src/util/virfile.c +++ b/src/util/virfile.c @@ -4072,11 +4072,18 @@ virFileInData(int fd, ret = 0; cleanup: /* At any rate, reposition back to where we started. */ - if (cur != (off_t) -1 && - lseek(fd, cur, SEEK_SET) == (off_t) -1) { - virReportSystemError(errno, "%s", - _("unable to restore position in file")); - ret = -1; + if (cur != (off_t) -1) { + int theerrno = errno; + + if (lseek(fd, cur, SEEK_SET) == (off_t) -1) { + virReportSystemError(errno, "%s", + _("unable to restore position in file")); + ret = -1; + if (theerrno == 0) + theerrno = errno; + } + + errno = theerrno; } return ret; } -- 2.18.1

3 2

[libvirt] [PATCH] virfile: Take symlink into account in virFileIsSharedFixFUSE
by Michal Privoznik 19 Oct '18

19 Oct '18

https://bugzilla.redhat.com/show_bug.cgi?id=1640465 Weirdly enough, there can be symlinks in the path we are trying to fix. If it is the case our clever algorithm that finds matches against mount table won't work. Canonicalize path at the beginning then. Signed-off-by: Michal Privoznik <mprivozn(a)redhat.com> --- cfg.mk | 2 +- src/util/virfile.c | 17 ++++++++++++++--- tests/virfilemock.c | 33 ++++++++++++++++++++++++++++++++- tests/virfiletest.c | 1 + 4 files changed, 48 insertions(+), 5 deletions(-) diff --git a/cfg.mk b/cfg.mk index 4790d0b7e7..d0183c02ff 100644 --- a/cfg.mk +++ b/cfg.mk @@ -1229,7 +1229,7 @@ exclude_file_name_regexp--sc_prohibit_select = \ ^cfg\.mk$$ exclude_file_name_regexp--sc_prohibit_canonicalize_file_name = \ - ^cfg\.mk$$ + ^(cfg\.mk|tests/virfilemock\.c)$$ exclude_file_name_regexp--sc_prohibit_raw_allocation = \ ^(docs/hacking\.html\.in|src/util/viralloc\.[ch]|examples/.*|tests/(securityselinuxhelper|(vircgroup|nss)mock|commandhelper)\.c|tools/wireshark/src/packet-libvirt\.c)$$ diff --git a/src/util/virfile.c b/src/util/virfile.c index e09992e41a..4747a26ad3 100644 --- a/src/util/virfile.c +++ b/src/util/virfile.c @@ -3473,9 +3473,19 @@ virFileIsSharedFixFUSE(const char *path, char mntbuf[1024]; char *mntDir = NULL; char *mntType = NULL; + char *canonPath = NULL; size_t maxMatching = 0; int ret = -1; + if (!(canonPath = virFileCanonicalizePath(path))) { + virReportSystemError(errno, + _("unable to canonicalize %s"), + path); + return -1; + } + + VIR_DEBUG("Path %s after canonicalization %s", path, canonPath); + if (!(f = setmntent(PROC_MOUNTS, "r"))) { virReportSystemError(errno, _("Unable to open %s"), @@ -3487,7 +3497,7 @@ virFileIsSharedFixFUSE(const char *path, const char *p; size_t len = strlen(mb.mnt_dir); - if (!(p = STRSKIP(path, mb.mnt_dir))) + if (!(p = STRSKIP(canonPath, mb.mnt_dir))) continue; if (*(p - 1) != '/' && *p != '/' && *p != '\0') @@ -3504,13 +3514,14 @@ virFileIsSharedFixFUSE(const char *path, } if (STREQ_NULLABLE(mntType, "fuse.glusterfs")) { - VIR_DEBUG("Found gluster FUSE mountpoint=%s for path=%s. " - "Fixing shared FS type", mntDir, path); + VIR_DEBUG("Found gluster FUSE mountpoint=%s for canonPath=%s. " + "Fixing shared FS type", mntDir, canonPath); *f_type = GFS2_MAGIC; } ret = 0; cleanup: + VIR_FREE(canonPath); VIR_FREE(mntType); VIR_FREE(mntDir); endmntent(f); diff --git a/tests/virfilemock.c b/tests/virfilemock.c index 822c757380..ae5c8d025a 100644 --- a/tests/virfilemock.c +++ b/tests/virfilemock.c @@ -28,11 +28,14 @@ #endif #include "virmock.h" +#include "virstring.h" +#include "viralloc.h" #define VIR_FROM_THIS VIR_FROM_NONE static FILE *(*real_setmntent)(const char *filename, const char *type); static int (*real_statfs)(const char *path, struct statfs *buf); +static char *(*real_canonicalize_file_name)(const char *path); static void @@ -43,6 +46,7 @@ init_syms(void) VIR_MOCK_REAL_INIT(setmntent); VIR_MOCK_REAL_INIT(statfs); + VIR_MOCK_REAL_INIT(canonicalize_file_name); } @@ -94,6 +98,7 @@ statfs_mock(const char *mtab, FILE *f; struct mntent mb; char mntbuf[1024]; + char *canonPath = NULL; int ret = -1; if (!(f = real_setmntent(mtab, "r"))) { @@ -101,10 +106,16 @@ statfs_mock(const char *mtab, return -1; } + /* We don't need to do this in callers because real statfs(2) + * does that for us. However, in mocked implementation we + * need to do this. */ + if (!(canonPath = canonicalize_file_name(path))) + return -1; + while (getmntent_r(f, &mb, mntbuf, sizeof(mntbuf))) { int ftype; - if (STRNEQ(mb.mnt_dir, path)) + if (STRNEQ(mb.mnt_dir, canonPath)) continue; if (STREQ(mb.mnt_type, "nfs") || @@ -136,6 +147,7 @@ statfs_mock(const char *mtab, } endmntent(f); + VIR_FREE(canonPath); return ret; } @@ -152,3 +164,22 @@ statfs(const char *path, struct statfs *buf) return real_statfs(path, buf); } + + +char * +canonicalize_file_name(const char *path) +{ + if (getenv("LIBVIRT_MTAB")) { + const char *p; + char *ret; + + if ((p = STRSKIP(path, "/some/symlink"))) + ignore_value(virAsprintfQuiet(&ret, "/gluster%s", p)); + else + ignore_value(VIR_STRDUP_QUIET(ret, path)); + + return ret; + } + + return real_canonicalize_file_name(path); +} diff --git a/tests/virfiletest.c b/tests/virfiletest.c index 1f2be74c8d..f7b263f2e9 100644 --- a/tests/virfiletest.c +++ b/tests/virfiletest.c @@ -456,6 +456,7 @@ mymain(void) DO_TEST_FILE_IS_SHARED_FS_TYPE("mounts3.txt", "/nfs/blah", false); DO_TEST_FILE_IS_SHARED_FS_TYPE("mounts3.txt", "/gluster/file", true); DO_TEST_FILE_IS_SHARED_FS_TYPE("mounts3.txt", "/gluster/sshfs/file", false); + DO_TEST_FILE_IS_SHARED_FS_TYPE("mounts3.txt", "/some/symlink/file", true); return ret != 0 ? EXIT_FAILURE : EXIT_SUCCESS; } -- 2.18.1

2 1

[libvirt] [tck PATCH 0/3] a few minor TCK bugfixes
by Laine Stump 19 Oct '18

19 Oct '18

Laine Stump (3): reduce required libvirt version in rpm spec fix selinux/100-static-relabel-no test double timeout on nwfilter 060-concurrency test perl-Sys-Virt-TCK.spec.PL | 2 +- scripts/nwfilter/nwfilter_concurrent.sh | 2 +- scripts/selinux/100-static-relabel-no.t | 13 ++++++++++++- 3 files changed, 14 insertions(+), 3 deletions(-) -- 2.14.5

2 4

[libvirt] [PATCH] qemu: Avoid memleak on failure to format blockjobs
by Eric Blake 19 Oct '18

19 Oct '18

virXMLFormatElement() frees attrBuf on success, but not necessarily on failure. Most other callers of this function take the time to reset attrBuf afterwords, but qemuDomainObjPrivateXMLFOrmatBlockjobs() was relying on it succeeding, and could thus result in a memory leak. Signed-off-by: Eric Blake <eblake(a)redhat.com> --- src/qemu/qemu_domain.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c index dd67be5e2a..ad7a6fe136 100644 --- a/src/qemu/qemu_domain.c +++ b/src/qemu/qemu_domain.c @@ -2232,11 +2232,15 @@ qemuDomainObjPrivateXMLFormatBlockjobs(virBufferPtr buf, { virBuffer attrBuf = VIR_BUFFER_INITIALIZER; bool bj = qemuDomainHasBlockjob(vm, false); + ret = -1; virBufferAsprintf(&attrBuf, " active='%s'", virTristateBoolTypeToString(virTristateBoolFromBool(bj))); - return virXMLFormatElement(buf, "blockjobs", &attrBuf, NULL); + ret = virXMLFormatElement(buf, "blockjobs", &attrBuf, NULL); + cleanup: + virBufferFreeAndReset(&attrBuf); + return ret; } -- 2.17.2

2 2

[libvirt] [PATCH v6 00/13] PCI passthrough support on s390
by Yi Min Zhao 19 Oct '18

19 Oct '18

Abstract ======== The PCI representation in QEMU has recently been extended for S390 allowing configuration of zPCI attributes like uid (user-defined identifier) and fid (PCI function identifier). The details can be found here: https://lists.gnu.org/archive/html/qemu-devel/2016-06/msg07262.html To support the new zPCI feature of the S390 platform, a new element of PCI address is introduced. It has two optional attributes, @uid and @fid. For example: <hostdev mode='subsystem' type='pci'> <driver name='vfio'/> <source> <address domain='0x0001' bus='0x00' slot='0x00' function='0x0'/> </source> <address type='pci' domain='0x0000' bus='0x00' slot='0x01' function='0x0'> <zpci uid='0x0003' fid='0x00000027'/> </address> </hostdev> If they are defined by the user, unique values within the guest domain must be used. If they are not specified and the architecture requires them, they are automatically generated with non-conflicting values. zPCI address as an extension of the PCI address are stored in a new structure 'virZPCIDeviceAddress' which is a member of common PCI Address structure. Additionally, two hashtables are used for assignment and reservation of zPCI uid/fid. In support of extending the PCI address, a new PCI address extension flag is introduced. This extension flag allows is not only dedicated for the S390 platform but also other architectures needing certain extensions to PCI address space. Code Base ========= commit in master: b1a0f691ce4652fc71aca6776f085355040322da spec: Build ceph and gluster support everywhere Change Log ========== v5->v6: 1. Modify zPCI XML definition. 2. Optimize the logic of zPCI address assignment and reservation. 3. Add extension flag into PCI address structure. 4. Update commit messages. v4->v5: 1. Update the version number. 2. Fixup code style error. 3. Separate qemu code into single patch. 4. Rebase the patches to the new code of master branch. v3->v4: 1. Update docs. 2. Format code style. 3. Optimize zPCI support check. 4. Move the check of zPCI defined in xml but unsupported by Qemu to qemuDomainDeviceDefValidate(). 5. Change zpci address member of PCI address struct from pointer to instance. 6. Modify zpci address definition principle. Currently the user must either define both of uid and fid or not. v2->v3: 1. Revise code style. 2. Update test cases. 3. Introduce qemuDomainCollectPCIAddressExtension() to collect PCI extension addresses. 4. Introduce virDeviceInfoPCIAddressExtensionPresent() to check if zPCI address exists. 5. Optimize zPCI address check logic. 6. Optimize passed parameters of zPCI addr alloc/release/reserve functions. 7. Report enum range error in qemuDomainDeviceSupportZPCI(). 8. Update commit messages. v1->v2: 1. Separate test commit and merge testcases into corresponding commits that introduce the functionalities firstly. 2. Spare some checks for zpci device. 3. Add vsock and controller support. 4. Add uin32 type schema. 5. Rename zpciuid and zpcifid to zpci_uid and zpci_fid. 6. Always return multibus support on S390. Yi Min Zhao (13): conf: Add definitions for 'uid' and 'fid' PCI address attributes qemu: Introduce zPCI capability conf: Introduce a new PCI address extension flag qemu: Enable PCI multi bus for S390 guests qemu: Auto add pci-root for s390/s390x guests conf: Introduce address caching for PCI extensions conf: Introduce parser, formatter for uid and fid qemu: Add zPCI address definition check conf: Allocate/release 'uid' and 'fid' in PCI address qemu: Generate and use zPCI device in QEMU command line qemu: Add hotpluging support for PCI devices on S390 guests docs: Add 'uid' and 'fid' information news: Update news for PCI address extension attributes cfg.mk | 1 + docs/formatdomain.html.in | 9 +- docs/news.xml | 11 + docs/schemas/basictypes.rng | 27 ++ docs/schemas/domaincommon.rng | 1 + src/conf/device_conf.c | 90 +++++ src/conf/device_conf.h | 7 + src/conf/domain_addr.c | 332 ++++++++++++++++++ src/conf/domain_addr.h | 30 ++ src/conf/domain_conf.c | 14 +- src/libvirt_private.syms | 7 + src/qemu/qemu_capabilities.c | 6 + src/qemu/qemu_capabilities.h | 1 + src/qemu/qemu_command.c | 102 ++++++ src/qemu/qemu_command.h | 2 + src/qemu/qemu_domain.c | 39 ++ src/qemu/qemu_domain_address.c | 204 ++++++++++- src/qemu/qemu_hotplug.c | 162 ++++++++- src/util/virpci.c | 7 + src/util/virpci.h | 14 + .../caps_2.10.0.s390x.xml | 1 + .../caps_2.11.0.s390x.xml | 1 + .../caps_2.12.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_2.7.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_2.8.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_2.9.0.s390x.xml | 1 + .../qemucapabilitiesdata/caps_3.0.0.s390x.xml | 1 + .../disk-virtio-s390-zpci.args | 26 ++ .../disk-virtio-s390-zpci.xml | 19 + .../hostdev-vfio-zpci-autogenerate.args | 25 ++ .../hostdev-vfio-zpci-autogenerate.xml | 18 + .../hostdev-vfio-zpci-boundaries.args | 29 ++ .../hostdev-vfio-zpci-boundaries.xml | 30 ++ .../hostdev-vfio-zpci-multidomain-many.args | 39 ++ .../hostdev-vfio-zpci-multidomain-many.xml | 79 +++++ tests/qemuxml2argvdata/hostdev-vfio-zpci.args | 25 ++ tests/qemuxml2argvdata/hostdev-vfio-zpci.xml | 21 ++ tests/qemuxml2argvtest.c | 20 ++ .../disk-virtio-s390-zpci.xml | 31 ++ .../hostdev-vfio-zpci-autogenerate.xml | 34 ++ .../hostdev-vfio-zpci-boundaries.xml | 48 +++ .../hostdev-vfio-zpci-multidomain-many.xml | 97 +++++ .../qemuxml2xmloutdata/hostdev-vfio-zpci.xml | 32 ++ tests/qemuxml2xmltest.c | 17 + 44 files changed, 1648 insertions(+), 15 deletions(-) create mode 100644 tests/qemuxml2argvdata/disk-virtio-s390-zpci.args create mode 100644 tests/qemuxml2argvdata/disk-virtio-s390-zpci.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-autogenerate.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-autogenerate.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-boundaries.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-boundaries.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-multidomain-many.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci-multidomain-many.xml create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci.args create mode 100644 tests/qemuxml2argvdata/hostdev-vfio-zpci.xml create mode 100644 tests/qemuxml2xmloutdata/disk-virtio-s390-zpci.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci-autogenerate.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci-boundaries.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci-multidomain-many.xml create mode 100644 tests/qemuxml2xmloutdata/hostdev-vfio-zpci.xml -- Yi Min

5 53

[libvirt] [PATCH] libvirtd: fix potential deadlock when starting vm
by Bingsong Si 19 Oct '18

19 Oct '18

On CentOS 6, udev_monitor_receive_device will block until the socket becomes readable, udevEventHandleThread will hold the lock all the time and udevEventHandleCallback hard to get the lock, will block the event poll. To fix this, set dataReady to false after receive an udev event. Signed-off-by: Bingsong Si <owen.si(a)ucloud.cn> --- src/node_device/node_device_udev.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/src/node_device/node_device_udev.c b/src/node_device/node_device_udev.c index 22897591de..ce1101d7cc 100644 --- a/src/node_device/node_device_udev.c +++ b/src/node_device/node_device_udev.c @@ -1616,6 +1616,7 @@ udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) errno = 0; device = udev_monitor_receive_device(priv->udev_monitor); + priv->dataReady = false; virObjectUnlock(priv); if (!device) { @@ -1637,10 +1638,6 @@ udevEventHandleThread(void *opaque ATTRIBUTE_UNUSED) return; } - virObjectLock(priv); - priv->dataReady = false; - virObjectUnlock(priv); - continue; } -- 2.18.0

4 9

[libvirt] [PATCH] qemu: remove unreferenced variable
by Bjoern Walk 18 Oct '18

18 Oct '18

The QEMU config in @cfg is not actually referenced in qemuProcessInit, let's remove it. Signed-off-by: Bjoern Walk <bwalk(a)linux.ibm.com> --- src/qemu/qemu_process.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index e9c76188..3955eda1 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -5267,7 +5267,6 @@ qemuProcessInit(virQEMUDriverPtr driver, bool migration, unsigned int flags) { - virQEMUDriverConfigPtr cfg = virQEMUDriverGetConfig(driver); virCapsPtr caps = NULL; qemuDomainObjPrivatePtr priv = vm->privateData; int stopFlags; @@ -5347,7 +5346,6 @@ qemuProcessInit(virQEMUDriverPtr driver, cleanup: virCPUDefFree(origCPU); - virObjectUnref(cfg); virObjectUnref(caps); return ret; -- 2.17.0

2 1

[libvirt] [PATCH] nwfilter: fix learning address thread shutdown
by Nikolay Shirokovskiy 18 Oct '18

18 Oct '18

If learning thread is configured to learn on all ethernet frames (which is hardcoded) then chances are big that there is packet on every iteration of inspecting frames loop. As result we will hang on shutdown because we don't check threadsTerminate if there is packet. Let's just check termination conditions on every iteration. Signed-off-by: Nikolay Shirokovskiy <nshirokovskiy(a)virtuozzo.com> --- src/nwfilter/nwfilter_learnipaddr.c | 22 +++++++--------------- 1 file changed, 7 insertions(+), 15 deletions(-) diff --git a/src/nwfilter/nwfilter_learnipaddr.c b/src/nwfilter/nwfilter_learnipaddr.c index 008c24b..e6cb996 100644 --- a/src/nwfilter/nwfilter_learnipaddr.c +++ b/src/nwfilter/nwfilter_learnipaddr.c @@ -483,6 +483,12 @@ learnIPAddressThread(void *arg) while (req->status == 0 && vmaddr == 0) { int n = poll(fds, ARRAY_CARDINALITY(fds), PKT_TIMEOUT_MS); + if (threadsTerminate || req->terminate) { + req->status = ECANCELED; + showError = false; + break; + } + if (n < 0) { if (errno == EAGAIN || errno == EINTR) continue; @@ -492,15 +498,8 @@ learnIPAddressThread(void *arg) break; } - if (n == 0) { - if (threadsTerminate || req->terminate) { - VIR_DEBUG("Terminate request seen, cancelling pcap"); - req->status = ECANCELED; - showError = false; - break; - } + if (n == 0) continue; - } if (fds[0].revents & (POLLHUP | POLLERR)) { VIR_DEBUG("Error from FD probably dev deleted"); @@ -512,13 +511,6 @@ learnIPAddressThread(void *arg) packet = pcap_next(handle, &header); if (!packet) { - /* Already handled with poll, but lets be sure */ - if (threadsTerminate || req->terminate) { - req->status = ECANCELED; - showError = false; - break; - } - /* Again, already handled above, but lets be sure */ if (virNetDevValidateConfig(req->binding->portdevname, NULL, req->ifindex) <= 0) { virResetLastError(); -- 1.8.3.1

2 4

[libvirt] [PATCH] snapshot: Don't hose list on deletion failure
by Eric Blake 18 Oct '18

18 Oct '18

If qemuDomainSnapshotDiscard() fails for any reason (rare, but possible with an ill-timed ENOMEM or if qemuDomainSnapshotForEachQcow2() has problems talking to the qemu guest monitor), then an attempt to retry the snapshot deletion API will crash because we didn't undo the effects of virDomainSnapshotDropParent() temporarily rearranging the internal list structures, and the second attempt to drop parents will dereference NULL. Fix it by instead only rearranging the internal list on success. Signed-off-by: Eric Blake <eblake(a)redhat.com> --- Found by accident, since I copied this code to my checkpoint code and hit the segfault there. This one has been latent for years, but is not a security bug since there is no escalation if you already have sufficient privilege to delete snapshots. src/qemu/qemu_driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 3f143e91c1..9a3f2a090d 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -16699,8 +16699,9 @@ qemuDomainSnapshotDelete(virDomainSnapshotPtr snapshot, snap->first_child = NULL; ret = 0; } else { - virDomainSnapshotDropParent(snap); ret = qemuDomainSnapshotDiscard(driver, vm, snap, true, metadata_only); + if (ret == 0) + virDomainSnapshotDropParent(snap); } endjob: -- 2.17.2

1 1

[libvirt] [PATCH] network: add prefix to dhcp range of dnsmasq conf file for IPv4 too
by Laine Stump 18 Oct '18

18 Oct '18

dnsmasq documentation says that the *IPv4* prefix/network address/broadcast address sent to dhcp clients will be automatically determined by dnsmasq by looking at the interface it's listening on, so the original libvirt code that added dhcp support to virtual networks did not add a prefix to the dnsmasq commandline (or later, the dnsmasq conf file). For *IPv6* however, dnsmasq cannot automatically determine the prefix, so it must be explicitly provided in the conf file (as a part of the dhcp-range option). Years after the initial IPv4 support, when IPv6 dhcp support was added, libvirt added the prefix to dhcp-range, but only for IPv6 (following the "if it ain't broke, don't fix it" doctrine). Recently a user reported (privately, because they suspected a possible security implication, which turned out to be unfounded) a bug on a host where one of the interfaces was a superset of the libvirt network where dhcp is needed (e.g., the host's ethernet is 10.0.0.20/8, and the libvirt network is 10.10.0.1/24). For some reason dnsmasq was supplying the netmask/broadcast address for the /8 network to clients requesting an address on the /24 interface. This seems like a bug in dnsmasq, but even if/when it gets fixed there, it looks like there is no harm in just adding the prefix to all dhcp-range options regardless of IPv4 vs IPv6, so that's what this patch does. Signed-off-by: Laine Stump <laine(a)laine.org> --- src/network/bridge_driver.c | 7 ++----- tests/networkxml2confdata/dhcp6-nat-network.conf | 2 +- tests/networkxml2confdata/isolated-network.conf | 2 +- tests/networkxml2confdata/nat-network-dns-srv-record-minimal.conf | 2 +- tests/networkxml2confdata/nat-network-dns-srv-record.conf | 2 +- tests/networkxml2confdata/nat-network-dns-txt-record.conf | 2 +- tests/networkxml2confdata/nat-network-name-with-quotes.conf | 2 +- tests/networkxml2confdata/nat-network.conf | 2 +- tests/networkxml2confdata/netboot-network.conf | 2 +- tests/networkxml2confdata/netboot-proxy-network.conf | 2 +- tests/networkxml2confdata/ptr-domains-auto.conf | 2 +- 11 files changed, 12 insertions(+), 15 deletions(-) diff --git a/src/network/bridge_driver.c b/src/network/bridge_driver.c index 4bbc4f5a6d..7f5ff79fdc 100644 --- a/src/network/bridge_driver.c +++ b/src/network/bridge_driver.c @@ -1416,11 +1416,8 @@ networkDnsmasqConfContents(virNetworkObjPtr obj, !(eaddr = virSocketAddrFormat(&ipdef->ranges[r].end))) goto cleanup; - virBufferAsprintf(&configbuf, "dhcp-range=%s,%s", - saddr, eaddr); - if (VIR_SOCKET_ADDR_IS_FAMILY(&ipdef->address, AF_INET6)) - virBufferAsprintf(&configbuf, ",%d", prefix); - virBufferAddLit(&configbuf, "\n"); + virBufferAsprintf(&configbuf, "dhcp-range=%s,%s,%d\n", + saddr, eaddr, prefix); VIR_FREE(saddr); VIR_FREE(eaddr); diff --git a/tests/networkxml2confdata/dhcp6-nat-network.conf b/tests/networkxml2confdata/dhcp6-nat-network.conf index d1058df3b6..e1e110fe23 100644 --- a/tests/networkxml2confdata/dhcp6-nat-network.conf +++ b/tests/networkxml2confdata/dhcp6-nat-network.conf @@ -8,7 +8,7 @@ strict-order except-interface=lo bind-dynamic interface=virbr0 -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-range=2001:db8:ac10:fd01::1:10,2001:db8:ac10:fd01::1:ff,64 diff --git a/tests/networkxml2confdata/isolated-network.conf b/tests/networkxml2confdata/isolated-network.conf index ce4a59f6c1..d182f42f0a 100644 --- a/tests/networkxml2confdata/isolated-network.conf +++ b/tests/networkxml2confdata/isolated-network.conf @@ -10,7 +10,7 @@ bind-interfaces listen-address=192.168.152.1 dhcp-option=3 no-resolv -dhcp-range=192.168.152.2,192.168.152.254 +dhcp-range=192.168.152.2,192.168.152.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 diff --git a/tests/networkxml2confdata/nat-network-dns-srv-record-minimal.conf b/tests/networkxml2confdata/nat-network-dns-srv-record-minimal.conf index f35ea1d5d4..678e4a4bfd 100644 --- a/tests/networkxml2confdata/nat-network-dns-srv-record-minimal.conf +++ b/tests/networkxml2confdata/nat-network-dns-srv-record-minimal.conf @@ -13,7 +13,7 @@ listen-address=fc00:db8:ac10:fe01::1 listen-address=fc00:db8:ac10:fd01::1 listen-address=10.24.10.1 srv-host=_name._tcp -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 diff --git a/tests/networkxml2confdata/nat-network-dns-srv-record.conf b/tests/networkxml2confdata/nat-network-dns-srv-record.conf index af1ed70758..4f21eb18b3 100644 --- a/tests/networkxml2confdata/nat-network-dns-srv-record.conf +++ b/tests/networkxml2confdata/nat-network-dns-srv-record.conf @@ -15,7 +15,7 @@ srv-host=_name4._tcp.test4.com,test4.example.com,4444 srv-host=_name5._udp,test5.example.com,1,55,555 srv-host=_name6._tcp.test6.com,test6.example.com,6666,0,666 srv-host=_name7._tcp.test7.com,test7.example.com,1,0,777 -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 diff --git a/tests/networkxml2confdata/nat-network-dns-txt-record.conf b/tests/networkxml2confdata/nat-network-dns-txt-record.conf index 7f560fbb5c..12e13c999e 100644 --- a/tests/networkxml2confdata/nat-network-dns-txt-record.conf +++ b/tests/networkxml2confdata/nat-network-dns-txt-record.conf @@ -9,7 +9,7 @@ except-interface=lo bind-dynamic interface=virbr0 txt-record=example,example value -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 diff --git a/tests/networkxml2confdata/nat-network-name-with-quotes.conf b/tests/networkxml2confdata/nat-network-name-with-quotes.conf index 36e11d17b9..63475ef511 100644 --- a/tests/networkxml2confdata/nat-network-name-with-quotes.conf +++ b/tests/networkxml2confdata/nat-network-name-with-quotes.conf @@ -13,7 +13,7 @@ listen-address=fc00:db8:ac10:fe01::1 listen-address=fc00:db8:ac10:fd01::1 listen-address=10.24.10.1 srv-host=_name._tcp -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 diff --git a/tests/networkxml2confdata/nat-network.conf b/tests/networkxml2confdata/nat-network.conf index a3c8b102d3..015d51c952 100644 --- a/tests/networkxml2confdata/nat-network.conf +++ b/tests/networkxml2confdata/nat-network.conf @@ -8,7 +8,7 @@ strict-order except-interface=lo bind-dynamic interface=virbr0 -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 diff --git a/tests/networkxml2confdata/netboot-network.conf b/tests/networkxml2confdata/netboot-network.conf index b554a5456c..987164c24c 100644 --- a/tests/networkxml2confdata/netboot-network.conf +++ b/tests/networkxml2confdata/netboot-network.conf @@ -10,7 +10,7 @@ expand-hosts except-interface=lo bind-interfaces listen-address=192.168.122.1 -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative enable-tftp diff --git a/tests/networkxml2confdata/netboot-proxy-network.conf b/tests/networkxml2confdata/netboot-proxy-network.conf index afb4033f7e..ad7e55fd09 100644 --- a/tests/networkxml2confdata/netboot-proxy-network.conf +++ b/tests/networkxml2confdata/netboot-proxy-network.conf @@ -10,7 +10,7 @@ expand-hosts except-interface=lo bind-interfaces listen-address=192.168.122.1 -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-boot=pxeboot.img,,10.20.30.40 diff --git a/tests/networkxml2confdata/ptr-domains-auto.conf b/tests/networkxml2confdata/ptr-domains-auto.conf index 7f1a393dd5..3be679ac4d 100644 --- a/tests/networkxml2confdata/ptr-domains-auto.conf +++ b/tests/networkxml2confdata/ptr-domains-auto.conf @@ -10,7 +10,7 @@ local=/1.0.e.f.0.1.c.a.8.b.d.0.1.0.0.2.ip6.arpa/ except-interface=lo bind-dynamic interface=virbr0 -dhcp-range=192.168.122.2,192.168.122.254 +dhcp-range=192.168.122.2,192.168.122.254,24 dhcp-no-override dhcp-authoritative dhcp-lease-max=253 -- 2.14.5

1 1

[libvirt] [PATCH] qemu: Fix IOThread pids lost after qemuProcessReconnect
by Jie Wang 17 Oct '18

17 Oct '18

>From fca1732c0e1f691fb25c614349d5486bbc73a109 Mon Sep 17 00:00:00 2001 From: Jie Wang <wangjie88(a)huawei.com> Date: Wed, 17 Oct 2018 22:55:51 +0800 Subject: [PATCH] qemu: Fix IOThread pids lost after qemuProcessReconnect IOThread pids info will lost after libvirtd restart, then if we call pinIOThread, sched_setaffinity will be called with pid 0, not IOThread pid. So pinIOThread cannot work normally. Signed-off-by: Jie Wang <wangjie88.huawei.com> --- src/qemu/qemu_process.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/src/qemu/qemu_process.c b/src/qemu/qemu_process.c index 40d35cbe6b..5bf55721d2 100644 --- a/src/qemu/qemu_process.c +++ b/src/qemu/qemu_process.c @@ -7650,6 +7650,9 @@ qemuProcessReconnect(void *opaque) qemuDomainVcpuPersistOrder(obj->def); + if (qemuProcessDetectIOThreadPIDs(driver, obj, QEMU_ASYNC_JOB_NONE) < 0) + goto error; + if (qemuSecurityReserveLabel(driver->securityManager, obj->def, obj->pid) < 0) goto error; -- 2.16.2.windows.1

1 0

[libvirt] [PATCH] util: Fix a typo in comments of virresctrl.c
by Wang Huaqiang 17 Oct '18

17 Oct '18

Signed-off-by: Wang Huaqiang <huaqiang.wang(a)intel.com> --- src/util/virresctrl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/util/virresctrl.c b/src/util/virresctrl.c index df5b512..5d811a2 100644 --- a/src/util/virresctrl.c +++ b/src/util/virresctrl.c @@ -259,7 +259,7 @@ virResctrlInfoMonFree(virResctrlInfoMonPtr mon) * all of them. While doing that we store the bitmask in a sparse array of * virBitmaps named `masks` indexed the same way as `sizes`. The upper bounds * of the sparse arrays are stored in nmasks or nsizes, respectively. - + * + * * =====Memory Bandwidth allocation technology (MBA)===== * * The memory bandwidth allocation support in virResctrlAlloc works in the -- 2.7.4

2 1

[libvirt] [PATCH v2 1/1] Add attribute single_usage_restriction for mdev type-id
by Kirti Wankhede 17 Oct '18

17 Oct '18

Generally a single instance of mdev device, a share of physical device, is assigned to user space application or a VM. There are cases when multiple instances of mdev devices of same or different types are required by user space application or VM. For example in case of vGPU, multiple mdev devices of type which represents whole GPU can be assigned to one instance of application or VM. All types of mdev devices may not support assigning multiple mdev devices to a user space application. In that case vendor driver can fail open() call of mdev device. But there is no way to know User space application to about the configuration supported by vendor driver. To expose supported configuration, vendor driver should add 'single_usage_restriction' attribute to type-id directory. Returning Y for this attribute indicates vendor driver has restriction of single mdev device of particular <type-id> assigned to one user space application. Returning N indicates that multiple mdev devices of particular <type-id> can be assigned to one user space application. User space application should read if 'single_usage_restriction' attibute is present in <type-id> directory of all mdev devices which are going to be used. If all read N then user space application can proceed with multiple mdev devices. This is optional and readonly attribute. Signed-off-by: Kirti Wankhede <kwankhede(a)nvidia.com> Reviewed-by: Neo Jia <cjia(a)nvidia.com> --- Documentation/ABI/testing/sysfs-bus-vfio-mdev | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/Documentation/ABI/testing/sysfs-bus-vfio-mdev b/Documentation/ABI/testing/sysfs-bus-vfio-mdev index 452dbe39270e..3aca352a70e5 100644 --- a/Documentation/ABI/testing/sysfs-bus-vfio-mdev +++ b/Documentation/ABI/testing/sysfs-bus-vfio-mdev @@ -85,6 +85,22 @@ Users: a particular <type-id> that can help in understanding the features provided by that type of mediated device. +What: /sys/.../mdev_supported_types/<type-id>/single_usage_restriction +Date: October 2018 +Contact: Kirti Wankhede <kwankhede(a)nvidia.com> +Description: + Reading this attribute will return Y or N. Returning Y indicates + vendor driver has restriction of single mdev device of this + particular <type-id> assigned to one user space application. + Returning N indicates that multiple mdev devices of particular + <type-id> can be assigned to one user space application. + This is optional and readonly attribute. +Users: + User space application should read if 'single_usage_restriction' + attibute is present in <type-id> directory of all mdev devices + which are going to be used. If all read N then user space + application can proceed with multiple mdev devices. + What: /sys/.../<device>/<UUID>/ Date: October 2016 Contact: Kirti Wankhede <kwankhede(a)nvidia.com> -- 2.7.0

5 5

[libvirt] [RFC PATCH 0/2] Add new mdev type for aggregated resources
by Zhenyu Wang 17 Oct '18

17 Oct '18

Current mdev device create interface depends on fixed mdev type, which get uuid from user to create instance of mdev device. If user wants to use customized number of resource for mdev device, then only can create new mdev type for that which may not be flexible. To allow to create user defined resources for mdev, this RFC trys to extend mdev create interface by adding new "instances=xxx" parameter following uuid, for target mdev type if aggregation is supported, it can create new mdev device which contains resources combined by number of instances, e.g echo "<uuid>,instances=10" > create VM manager e.g libvirt can check mdev type with "aggregation" attribute which can support this setting. And new sysfs attribute "instances" is created for each mdev device to show allocated number. Default number of 1 or no "instances" file can be used for compatibility check. This RFC trys to create new KVMGT type with minimal vGPU resources which can be combined with "instances=x" setting to allocate for user wanted resources. Zhenyu Wang (2): vfio/mdev: Add new instances parameters for mdev create drm/i915/gvt: Add new aggregation type drivers/gpu/drm/i915/gvt/gvt.c | 26 ++++++++++++--- drivers/gpu/drm/i915/gvt/gvt.h | 14 +++++--- drivers/gpu/drm/i915/gvt/kvmgt.c | 9 +++-- drivers/gpu/drm/i915/gvt/vgpu.c | 56 ++++++++++++++++++++++++++++---- drivers/s390/cio/vfio_ccw_ops.c | 3 +- drivers/vfio/mdev/mdev_core.c | 11 ++++--- drivers/vfio/mdev/mdev_private.h | 6 +++- drivers/vfio/mdev/mdev_sysfs.c | 42 ++++++++++++++++++++---- include/linux/mdev.h | 3 +- samples/vfio-mdev/mbochs.c | 3 +- samples/vfio-mdev/mdpy.c | 3 +- samples/vfio-mdev/mtty.c | 3 +- 12 files changed, 141 insertions(+), 38 deletions(-) -- 2.18.0.rc2

6 37

[libvirt] [PATCH] conf: Fix typos in pcie controllers' name
by Han Han 17 Oct '18

17 Oct '18

Signed-off-by: Han Han <hhan(a)redhat.com> --- src/conf/domain_addr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/src/conf/domain_addr.c b/src/conf/domain_addr.c index 442e6aab94..e4ed143b76 100644 --- a/src/conf/domain_addr.c +++ b/src/conf/domain_addr.c @@ -158,9 +158,9 @@ virDomainPCIAddressFlagsCompatible(virPCIDeviceAddressPtr addr, } else if (devFlags & VIR_PCI_CONNECT_TYPE_PCIE_ROOT_PORT) { connectStr = "pcie-root-port"; } else if (devFlags & VIR_PCI_CONNECT_TYPE_PCIE_SWITCH_UPSTREAM_PORT) { - connectStr = "pci-switch-upstream-port"; + connectStr = "pcie-switch-upstream-port"; } else if (devFlags & VIR_PCI_CONNECT_TYPE_PCIE_SWITCH_DOWNSTREAM_PORT) { - connectStr = "pci-switch-downstream-port"; + connectStr = "pcie-switch-downstream-port"; } else if (devFlags & VIR_PCI_CONNECT_TYPE_DMI_TO_PCI_BRIDGE) { connectStr = "dmi-to-pci-bridge"; } else if (devFlags & VIR_PCI_CONNECT_TYPE_PCIE_TO_PCI_BRIDGE) { -- 2.19.1

2 1

[libvirt] [PATCHv5 00/19] Introduce x86 Cache Monitoring Technology (CMT)
by Wang Huaqiang 17 Oct '18

17 Oct '18

This series of patches and the series already been merged introduce the x86 Cache Monitoring Technology (CMT) to libvirt by interacting with kernel resource control (resctrl) interface. CMT is one of the Intel(R) x86 CPU feature which belongs to the Resource Director Technology (RDT). CMT reports the occupancy of the last level cache, which is shared by all CPU cores. In the v1 series, an original and complete feature for CMT was introduced The v2 and v3 patches address the feature for the host capability of CMT. v4 is addressing the feature for monitoring VM vcpu thread set cache occupancy and reporting it through a virsh command. We have serval discussion about the enabling of CMT, please refer to following links for the RFCs. RFCv3 https://www.redhat.com/archives/libvir-list/2018-August/msg01213.html RFCv2 https://www.redhat.com/archives/libvir-list/2018-July/msg00409.html https://www.redhat.com/archives/libvir-list/2018-July/msg01241.html RFCv1 https://www.redhat.com/archives/libvir-list/2018-June/msg00674.html And the merged commits are list as below, for host capability of CMT. 6af8417415508c31f8ce71234b573b4999f35980 8f6887998bf63594ae26e3db18d4d5896c5f2cb4 58fcee6f3a2b7e89c21c1fb4ec21429c31a0c5b8 12093f1feaf8f5023dcd9d65dff111022842183d a5d293c18831dcf69ec6195798387fbb70c9f461 1. About reason why CMT is necessary in libvirt? The perf events of 'CMT, MBML, MBMT' have been phased out since Linux kernel commit c39a0e2c8850f08249383f2425dbd8dbe4baad69, in libvirt the perf based cmt,mbm will not work with the latest linux kernel. These patches add CMT feature to libvirt through kernel resctrlfs interface. 2 Create cache monitoring group (cache monitor). The main interface for creating monitoring group is through XML file. The proposed configuration is like: <cputune> <cachetune vcpus='1'> <cache id='0' level='3' type='code' size='7680' unit='KiB'/> <cache id='1' level='3' type='data' size='3840' unit='KiB'/> + <monitor level='3' vcpus='1'/> </cachetune> <cachetune vcpus='4-7'> + <monitor level='3' vcpus='4-6'/> </cachetune> </cputune> In above XML, created 2 cache resctrl allocation groups and 2 resctrl monitoring groups. The changes of cache monitor will be effective in next booting of VM. 2 Show CMT result through command 'domstats' Adding the interface in qemu to report this information for resource monitor group through command 'virsh domstats --cpu-total'. Below is a typical output: # virsh domstats 1 --cpu-total Domain: 'ubuntu16.04-base' ... cpu.cache.monitor.count=2 cpu.cache.0.name=vcpus_1 cpu.cache.0.vcpus=1 cpu.cache.0.bank.count=2 cpu.cache.0.bank.0.id=0 cpu.cache.0.bank.0.bytes=4505600 cpu.cache.0.bank.1.id=1 cpu.cache.0.bank.1.bytes=5586944 cpu.cache.1.name=vcpus_4-6 cpu.cache.1.vcpus=4,5,6 cpu.cache.1.bank.count=2 cpu.cache.1.bank.0.id=0 cpu.cache.1.bank.0.bytes=17571840 cpu.cache.1.bank.1.id=1 cpu.cache.1.bank.1.bytes=29106176 Changes in v5: - qemu: Setting up vcpu and adding pids to resctrl monitor groups during re-connection. - Add the document for domain configuration related to resctrl monitor. Changes in v4: v4 is addressing the feature for monitoring VM vcpu thread set cache occupancy and reporting it through a virsh command. - Introduced resctrl default allocation - Introduced resctrl monitor and default monitor Changes in v3: - Addressed John Ferlan's review. - Typo fixed. - Removed VIR_ENUM_DECL(virMonitor); Changes in v2: - Introduced MBM capability. - Capability layout changed * Moved <monitor> from cahe <bank> to <cache> * Renamed <Threshold> to <reuseThreshold> - Document for 'reuseThreshold' changed. - Introduced API virResctrlInfoGetMonitorPrefix - Added more tests, covering standalone CMT, fake new feature. - Creating CMT resource control group will be subsequent job. Wang Huaqiang (19): docs: Refactor schemas to support default allocation util: Introduce resctrl monitor for CMT util: Refactor code for adding PID to the resource group util: Add interface for adding PID to monitor util: Refactor code for determining allocation path util: Add monitor interface to determine path util: Refactor code for creating resctrl group util: Add interface for creating monitor group util: Add more interfaces for resctrl monitor util: Introduce default monitor conf: Refactor code for matching existing resctrls conf: Refactor virDomainResctrlAppend conf: Add resctrl monitor configuration Util: Add function for checking if monitor is running qemu: enable resctrl monitor in qemu conf: Add a 'id' to virDomainResctrlDef qemu: refactor qemuDomainGetStatsCpu qemu: Report cache occupancy (CMT) with domstats qemu: Setting up vcpu and adding pids to resctrl monitor groups during reconnection docs/formatdomain.html.in | 30 +- docs/schemas/domaincommon.rng | 14 +- src/conf/domain_conf.c | 327 ++++++++++-- src/conf/domain_conf.h | 12 + src/libvirt-domain.c | 9 + src/libvirt_private.syms | 12 + src/qemu/qemu_driver.c | 271 +++++++++- src/qemu/qemu_process.c | 52 +- src/util/virresctrl.c | 562 ++++++++++++++++++++- src/util/virresctrl.h | 49 ++ tests/genericxml2xmlindata/cachetune-cdp.xml | 3 + .../cachetune-colliding-monitor.xml | 30 ++ tests/genericxml2xmlindata/cachetune-small.xml | 7 + tests/genericxml2xmltest.c | 2 + 14 files changed, 1277 insertions(+), 103 deletions(-) create mode 100644 tests/genericxml2xmlindata/cachetune-colliding-monitor.xml -- 2.7.4

3 70

[libvirt] [PATCH] network: honor the ipv6 network option
by Ryan Goodfellow 16 Oct '18

16 Oct '18

According the the documentation for the ipv6 network attribute https://libvirt.org/formatnetwork.html "When set to yes, the optional parameter ipv6 enables a network definition with no IPv6 gateway addresses specified to have guest-to-guest communications." But this is not the current behavior, the ipv6 attribute is ignored and the resulting /proc/sys/net/ipv6/conf/<virbrX>/disable_ipv6 gets set to 1 even when ipv6="yes". This commit fixes that by checking for the ipv6 network attribute during bridge setup. Signed-off-by: Ryan C Goodfellow <rgoodfel(a)isi.edu> --- src/network/bridge_driver.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/src/network/bridge_driver.c b/src/network/bridge_driver.c index 4bbc4f5a6d..69022fbfbb 100644 --- a/src/network/bridge_driver.c +++ b/src/network/bridge_driver.c @@ -2221,7 +2221,8 @@ networkSetIPv6Sysctls(virNetworkObjPtr obj) virNetworkDefPtr def = virNetworkObjGetDef(obj); char *field = NULL; int ret = -1; - bool enableIPv6 = !!virNetworkDefGetIPByIndex(def, AF_INET6, 0); + bool enableIPv6 = !!virNetworkDefGetIPByIndex(def, AF_INET6, 0) | + def->ipv6nogw; /* set disable_ipv6 if there are no ipv6 addresses defined for the * network. But also unset it if there *are* ipv6 addresses, as we -- 2.17.1

2 1