May 2010 - Devel - libvirt List Archives

[libvirt] [PATCH v3] Add host UUID (to libvirt capabilities)
by Stefan Berger 25 May '10

25 May '10

This patch adds the host UUID (to the capabilities of libvirt). The user may provide it in libvirtd.conf overriding whatever sysfs may return. If none or no valid UUID is provided in libvirtd.conf, reading the UUID from sysfs is attempted. If that function doesn't provide a valid (not all digits may be equal), generate a temporary one. virSetHostUUIDStr() should be called first with the UUID read from libvirtd.conf, but may only be called once. Subsequently the function virGetHostUUID() can be called to get the UUID of the host. changes from V2 to V3: - addressing more comments from D. Berrange: - removing virGetHostUUIDStr() function - adding uuid to all test cases' data files - failing libvirt if host_uuid is malformatted or considered invalid - extended virCapsHost with host_uuid field - initializing virCapsHost's host_uuid field in qemu_driver's init function Changes from V1 to V2: - addressing comments from Daniel Berrange: - rewrite/ code to get the UUID from 2 possible sysfs files - got rid of dmidecide dependency - call the newly added virGetHostUUID() function in udevGetDMIData() to get the UUID of the host ( even if it's just a temporary UUID ) Besides that, this patch - adds uuid to the capabilties XML schema - displays the UUID in in 'virsh capabilities' - adds 3 public functions to uuid.h for setting and getting the UUID of the host Signed-off-by: Stefan Berger <stefanb(a)us.ibm.com> --- daemon/libvirtd.c | 9 ++ daemon/libvirtd.conf | 10 ++ docs/schemas/capability.rng | 14 +++ src/conf/capabilities.c | 5 + src/conf/capabilities.h | 1 src/libvirt_private.syms | 2 src/node_device/node_device_udev.c | 6 - src/qemu/qemu_driver.c | 6 + src/util/uuid.c | 116 +++++++++++++++++++++++++++ src/util/uuid.h | 3 tests/capabilityschemadata/caps-qemu-kvm.xml | 1 tests/capabilityschemadata/caps-test.xml | 1 tests/confdata/libvirtd.conf | 9 ++ tests/confdata/libvirtd.out | 7 + tests/xencapsdata/xen-i686-pae-hvm.xml | 1 tests/xencapsdata/xen-i686-pae.xml | 1 tests/xencapsdata/xen-i686.xml | 1 tests/xencapsdata/xen-ia64-be-hvm.xml | 1 tests/xencapsdata/xen-ia64-be.xml | 1 tests/xencapsdata/xen-ia64-hvm.xml | 1 tests/xencapsdata/xen-ia64.xml | 1 tests/xencapsdata/xen-ppc64.xml | 1 tests/xencapsdata/xen-x86_64-hvm.xml | 1 tests/xencapsdata/xen-x86_64.xml | 1 24 files changed, 195 insertions(+), 5 deletions(-) Index: libvirt-acl/daemon/libvirtd.c =================================================================== --- libvirt-acl.orig/daemon/libvirtd.c +++ libvirt-acl/daemon/libvirtd.c @@ -57,6 +57,7 @@ #include "dispatch.h" #include "util.h" +#include "uuid.h" #include "remote_driver.h" #include "conf.h" #include "event.h" @@ -2718,6 +2719,7 @@ remoteReadConfigFile (struct qemud_serve char *unix_sock_rw_perms = NULL; char *unix_sock_group = NULL; char *buf = NULL; + char *host_uuid = NULL; #if HAVE_POLKIT /* Change the default back to no auth for non-root */ @@ -2840,11 +2842,18 @@ remoteReadConfigFile (struct qemud_serve GET_CONF_INT (conf, filename, max_requests); GET_CONF_INT (conf, filename, max_client_requests); + GET_CONF_STR (conf, filename, host_uuid); + if (virSetHostUUIDStr(host_uuid)) + goto free_and_fail; + + VIR_FREE(host_uuid); + virConfFree (conf); return 0; free_and_fail: virConfFree (conf); + VIR_FREE(host_uuid); VIR_FREE(mdns_name); VIR_FREE(unix_sock_ro_perms); VIR_FREE(unix_sock_rw_perms); Index: libvirt-acl/src/util/uuid.h =================================================================== --- libvirt-acl.orig/src/util/uuid.h +++ libvirt-acl/src/util/uuid.h @@ -22,6 +22,9 @@ #ifndef __VIR_UUID_H__ # define __VIR_UUID_H__ +int virSetHostUUIDStr(const char *host_uuid); +int virGetHostUUID(unsigned char *host_uuid); + int virUUIDGenerate(unsigned char *uuid); int virUUIDParse(const char *uuidstr, Index: libvirt-acl/src/util/uuid.c =================================================================== --- libvirt-acl.orig/src/util/uuid.c +++ libvirt-acl/src/util/uuid.c @@ -38,11 +38,14 @@ #include "util.h" #include "virterror_internal.h" #include "logging.h" +#include "memory.h" #ifndef ENODATA # define ENODATA EIO #endif +static unsigned char host_uuid[VIR_UUID_BUFLEN]; + static int virUUIDGenerateRandomBytes(unsigned char *buf, int buflen) @@ -208,3 +211,116 @@ void virUUIDFormat(const unsigned char * uuid[12], uuid[13], uuid[14], uuid[15]); uuidstr[VIR_UUID_STRING_BUFLEN-1] = '\0'; } + + + +/** + * isValidHostUUID + * + * @uuid: The UUID to test + * + * Do some basic tests to check whether the given UUID is + * valid as a host UUID. + * Basic tests: + * - Not all of the digits may be equal + */ +static int +isValidHostUUID(unsigned char *uuid) +{ + unsigned int i, ctr = 1; + unsigned char c; + + if (!uuid) + return 0; + + c = uuid[0]; + + for (i = 1; i < VIR_UUID_BUFLEN; i++) + if (uuid[i] == c) + ctr++; + + return (ctr != VIR_UUID_BUFLEN); +} + +static int +getDMISystemUUID(char *uuid, int len) +{ + unsigned int i = 0; + const char *paths[] = { + "/sys/devices/virtual/dmi/id/product_uuid", + "/sys/class/dmi/id/product_uuid", + NULL + }; + + while (paths[i]) { + int fd = open(paths[i], O_RDONLY); + if (fd > 0) { + if (saferead(fd, uuid, len) == len) { + close(fd); + return 0; + } + close(fd); + } + i++; + } + + return -1; +} + + +/** + * setHostUUID + * + * @host_uuid: UUID that the host is supposed to have + * + * Set the UUID of the host if it hasn't been set, yet + * Returns 0 in case of success, an error code in case of error. + */ +int +virSetHostUUIDStr(const char *uuid) +{ + int rc; + char dmiuuid[VIR_UUID_STRING_BUFLEN]; + + if (isValidHostUUID(host_uuid)) + return EEXIST; + + if (!uuid) { + if (!getDMISystemUUID(dmiuuid, sizeof(dmiuuid))) { + if (!virUUIDParse(dmiuuid, host_uuid)) + return 0; + } + } else { + rc = virUUIDParse(uuid, host_uuid); + if (rc) + return rc; + if (!isValidHostUUID(host_uuid)) + return EINVAL; + } + + if (!isValidHostUUID(host_uuid)) + return virUUIDGenerate(host_uuid); + + return 0; +} + +/** + * getHostUUID: + * + * @host_uuid: memory to store the host_uuid into + * + * Get the UUID of the host. Returns 0 in case of success, + * an error code otherwise. + * Returns 0 in case of success, an error code in case of error. + */ +int virGetHostUUID(unsigned char *uuid) +{ + int ret = 0; + + if (!isValidHostUUID(host_uuid)) + ret = virSetHostUUIDStr(NULL); + + memcpy(uuid, host_uuid, sizeof(host_uuid)); + + return ret; +} Index: libvirt-acl/src/conf/capabilities.c =================================================================== --- libvirt-acl.orig/src/conf/capabilities.c +++ libvirt-acl/src/conf/capabilities.c @@ -27,6 +27,7 @@ #include "buf.h" #include "memory.h" #include "util.h" +#include "uuid.h" #include "cpu_conf.h" /** @@ -662,9 +663,13 @@ virCapabilitiesFormatXML(virCapsPtr caps { virBuffer xml = VIR_BUFFER_INITIALIZER; int i, j, k; + char host_uuid[VIR_UUID_STRING_BUFLEN]; + + virUUIDFormat(caps->host.host_uuid, host_uuid); virBufferAddLit(&xml, "<capabilities>\n\n"); virBufferAddLit(&xml, " <host>\n"); + virBufferVSprintf(&xml," <uuid>%s</uuid>\n", host_uuid); virBufferAddLit(&xml, " <cpu>\n"); virBufferVSprintf(&xml, " <arch>%s</arch>\n", caps->host.arch); Index: libvirt-acl/docs/schemas/capability.rng =================================================================== --- libvirt-acl.orig/docs/schemas/capability.rng +++ libvirt-acl/docs/schemas/capability.rng @@ -18,6 +18,9 @@ <define name='hostcaps'> <element name='host'> + <element name='uuid'> + <ref name='UUID'/> + </element> <element name='cpu'> <element name='arch'> <ref name='archnames'/> @@ -349,4 +352,15 @@ <param name='pattern'>[a-zA-Z0-9\-_]+</param> </data> </define> + + <define name="UUID"> + <choice> + <data type="string"> + <param name="pattern">[a-fA-F0-9]{32}</param> + </data> + <data type="string"> + <param name="pattern">[a-fA-F0-9]{8}\-([a-fA-F0-9]{4}\-){3}[a-fA-F0-9]{12}</param> + </data> + </choice> + </define> </grammar> Index: libvirt-acl/src/libvirt_private.syms =================================================================== --- libvirt-acl.orig/src/libvirt_private.syms +++ libvirt-acl/src/libvirt_private.syms @@ -708,6 +708,8 @@ usbDeviceFileIterate; virUUIDFormat; virUUIDGenerate; virUUIDParse; +virSetHostUUIDStr; +virGetHostUUID; # virterror_internal.h Index: libvirt-acl/daemon/libvirtd.conf =================================================================== --- libvirt-acl.orig/daemon/libvirtd.conf +++ libvirt-acl/daemon/libvirtd.conf @@ -312,3 +312,13 @@ # e.g.: # log_outputs="3:syslog:libvirtd" # to log all warnings and errors to syslog under the libvirtd ident + +# UUID of the host: +# Provide the UUID of the host here in case the command +# 'dmidecode -s system-uuid' does not provide a valid uuid. In case +# 'dmidecode' does not provide a valid UUID and none is provided here, a +# temporary UUID will be generated. +# Keep the format of the example UUID below. UUID must not have all digits +# be the same. + +#host_uuid = "8510b1a1-1afa-4da6-8111-785fae202c1e" Index: libvirt-acl/src/node_device/node_device_udev.c =================================================================== --- libvirt-acl.orig/src/node_device/node_device_udev.c +++ libvirt-acl/src/node_device/node_device_udev.c @@ -1473,12 +1473,8 @@ udevGetDMIData(union _virNodeDevCapData goto out; } - if (udevGetStringSysfsAttr(device, - "product_uuid", - &tmp) == PROPERTY_ERROR) { + if (virGetHostUUID(data->system.hardware.uuid)) goto out; - } - virUUIDParse(tmp, data->system.hardware.uuid); if (udevGetStringSysfsAttr(device, "bios_vendor", Index: libvirt-acl/tests/capabilityschemadata/caps-qemu-kvm.xml =================================================================== --- libvirt-acl.orig/tests/capabilityschemadata/caps-qemu-kvm.xml +++ libvirt-acl/tests/capabilityschemadata/caps-qemu-kvm.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>x86_64</arch> </cpu> Index: libvirt-acl/tests/capabilityschemadata/caps-test.xml =================================================================== --- libvirt-acl.orig/tests/capabilityschemadata/caps-test.xml +++ libvirt-acl/tests/capabilityschemadata/caps-test.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>i686</arch> <features> Index: libvirt-acl/tests/xencapsdata/xen-i686-pae-hvm.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-i686-pae-hvm.xml +++ libvirt-acl/tests/xencapsdata/xen-i686-pae-hvm.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>i686</arch> <features> Index: libvirt-acl/tests/xencapsdata/xen-i686-pae.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-i686-pae.xml +++ libvirt-acl/tests/xencapsdata/xen-i686-pae.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>i686</arch> <features> Index: libvirt-acl/tests/xencapsdata/xen-i686.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-i686.xml +++ libvirt-acl/tests/xencapsdata/xen-i686.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>i686</arch> </cpu> Index: libvirt-acl/tests/xencapsdata/xen-ia64-be-hvm.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-ia64-be-hvm.xml +++ libvirt-acl/tests/xencapsdata/xen-ia64-be-hvm.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>ia64</arch> </cpu> Index: libvirt-acl/tests/xencapsdata/xen-ia64-be.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-ia64-be.xml +++ libvirt-acl/tests/xencapsdata/xen-ia64-be.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>ia64</arch> </cpu> Index: libvirt-acl/tests/xencapsdata/xen-ia64-hvm.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-ia64-hvm.xml +++ libvirt-acl/tests/xencapsdata/xen-ia64-hvm.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>ia64</arch> </cpu> Index: libvirt-acl/tests/xencapsdata/xen-ia64.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-ia64.xml +++ libvirt-acl/tests/xencapsdata/xen-ia64.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>ia64</arch> </cpu> Index: libvirt-acl/tests/xencapsdata/xen-ppc64.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-ppc64.xml +++ libvirt-acl/tests/xencapsdata/xen-ppc64.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>ppc64</arch> </cpu> Index: libvirt-acl/tests/xencapsdata/xen-x86_64-hvm.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-x86_64-hvm.xml +++ libvirt-acl/tests/xencapsdata/xen-x86_64-hvm.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>x86_64</arch> <features> Index: libvirt-acl/tests/xencapsdata/xen-x86_64.xml =================================================================== --- libvirt-acl.orig/tests/xencapsdata/xen-x86_64.xml +++ libvirt-acl/tests/xencapsdata/xen-x86_64.xml @@ -1,6 +1,7 @@ <capabilities> <host> + <uuid>29b3d3aa-7ff5-3c36-ae20-ea64941ce1b2</uuid> <cpu> <arch>x86_64</arch> <features> Index: libvirt-acl/tests/confdata/libvirtd.conf =================================================================== --- libvirt-acl.orig/tests/confdata/libvirtd.conf +++ libvirt-acl/tests/confdata/libvirtd.conf @@ -218,3 +218,12 @@ tls_allowed_dn_list = ["DN1", "DN2"] # # By default, no Username's are checked sasl_allowed_username_list = ["joe(a)EXAMPLE.COM", "fred(a)EXAMPLE.COM" ] + +# UUID of the host: +# Provide the UUID of the host here in case the command +# 'dmidecode -s system-uuid' does not provide a valid uuid. In case +# 'dmidecode' does not provide a valid UUID and none is provided here, a +# temporary UUID will be generated. +# Keep the format of the example UUID below. + +host_uuid = "8510b1a1-1afa-4da6-8111-785fae202c1e" Index: libvirt-acl/tests/confdata/libvirtd.out =================================================================== --- libvirt-acl.orig/tests/confdata/libvirtd.out +++ libvirt-acl/tests/confdata/libvirtd.out @@ -178,3 +178,10 @@ tls_allowed_dn_list = [ "DN1", "DN2" ] # # By default, no Username's are checked sasl_allowed_username_list = [ "joe(a)EXAMPLE.COM", "fred(a)EXAMPLE.COM" ] +# UUID of the host: +# Provide the UUID of the host here in case the command +# 'dmidecode -s system-uuid' does not provide a valid uuid. In case +# 'dmidecode' does not provide a valid UUID and none is provided here, a +# temporary UUID will be generated. +# Keep the format of the example UUID below. +host_uuid = "8510b1a1-1afa-4da6-8111-785fae202c1e" Index: libvirt-acl/src/conf/capabilities.h =================================================================== --- libvirt-acl.orig/src/conf/capabilities.h +++ libvirt-acl/src/conf/capabilities.h @@ -110,6 +110,7 @@ struct _virCapsHost { virCapsHostNUMACellPtr *numaCell; virCapsHostSecModel secModel; virCPUDefPtr cpu; + unsigned char host_uuid[VIR_UUID_BUFLEN]; }; typedef struct _virCaps virCaps; Index: libvirt-acl/src/qemu/qemu_driver.c =================================================================== --- libvirt-acl.orig/src/qemu/qemu_driver.c +++ libvirt-acl/src/qemu/qemu_driver.c @@ -1334,6 +1334,11 @@ qemuCreateCapabilities(virCapsPtr oldcap caps->privateDataXMLFormat = qemuDomainObjPrivateXMLFormat; caps->privateDataXMLParse = qemuDomainObjPrivateXMLParse; + if (virGetHostUUID(caps->host.host_uuid)) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, + "%s", _("cannot get the host uuid")); + goto err_exit; + } /* Security driver data */ if (driver->securityPrimaryDriver) { @@ -1355,6 +1360,7 @@ qemuCreateCapabilities(virCapsPtr oldcap no_memory: virReportOOMError(); +err_exit: virCapabilitiesFree(caps); return NULL; }

4 6

[libvirt] How to obtain rights to extend libvirt documentation pages
by Марк Коренберг 25 May '10

25 May '10

For example, http://libvirt.org/formatdomain.html#elementsDisks does not contain <serial>xxxx</serial> tag. (https://bugzilla.redhat.com/show_bug.cgi?id=593266) I wrote to community (users and developers). No one has added this information to the site... -- Segmentation fault

3 2

[libvirt] [PATCH] Allow nwfilter functions to be compiled with C++
by Chris Lalancette 25 May '10

25 May '10

Unfortunately the NWFilter functions were outside of the "extern C { ... }" declaration in include/libvirt/libvirt.h.in, which means that they couldn't be properly used with C++. Move them inside of the braces, which should fix the problem. Signed-off-by: Chris Lalancette <clalance(a)redhat.com> --- include/libvirt/libvirt.h.in | 8 ++++---- 1 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/libvirt/libvirt.h.in b/include/libvirt/libvirt.h.in index d95d7ae..e6e4d0c 100644 --- a/include/libvirt/libvirt.h.in +++ b/include/libvirt/libvirt.h.in @@ -2213,10 +2213,6 @@ int virConnectDomainEventRegisterAny(virConnectPtr conn, int virConnectDomainEventDeregisterAny(virConnectPtr conn, int callbackID); -#ifdef __cplusplus -} -#endif - /** * virNWFilter: @@ -2280,4 +2276,8 @@ int virNWFilterGetUUIDString (virNWFilterPtr nwfilter, char * virNWFilterGetXMLDesc (virNWFilterPtr nwfilter, int flags); +#ifdef __cplusplus +} +#endif + #endif /* __VIR_VIRLIB_H__ */ -- 1.6.6.1

2 2

[libvirt] [PATCH v6] add 802.1Qbh handling
by Stefan Berger 25 May '10

25 May '10

This patch builds on the work recently posted by Stefan Berger. It builds on top of Stefan's three posted patches: [PATCH v10] vepa: parsing for 802.1Qb{g|h} XML [RFC][PATCH 1/3] vepa+vsi: Introduce dependency on libnl [PATCH v3] Add host UUID (to libvirt capabilities) Stefan's RFC patches 2/3 and 3/3 are incorporated into my patch. Changes from v5 to v6: - Renamed occurrencvirVirtualPortProfileDef to virVirtualPortProfileParamses - 802.1Qbg part prepared for sending a RTM_SETLINK and getting processing status back plus a subsequent RTM_GETLINK to get IFLA_PORT_RESPONSE. Note: This interface for 802.1Qbg may still change Changes from v4 to v5: - [David Allan] move getPhysfn inside IFLA_VF_PORT_MAX to avoid compiler warning when latest if_link.h isn't available Changes from v3 to v4: - move from Stefan's 802.1Qb{g|h} XML v8 to v9 - move hostuuid and vf index calcs to inside doPortProfileOp8021Qbh Changes from v2 to v3: - remove debug fprintfs - use virGetHostUUID (thanks Stefan!) - fix compile issue when latest if_link.h isn't available - change poll timeout to 10s, at 1/8 intervals - if polling times out, log msg and return -ETIMEDOUT Changes from v1 to v2: - Add Stefan's code for getPortProfileStatus - Poll for up to 2 secs for port-profile status, at 1/8 sec intervals: - if status indicates error, abort openMacvtapTap - if status indicates success, exit polling - if status is "in-progress" after 2 secs of polling, exit polling loop silently, without error My patch finishes out the 802.1Qbh parts, which Stefan had mostly complete. I've tested using the recent kernel updates for VF_PORT netlink msgs and enic for Cisco's 10G Ethernet NIC. I tested many VMs, each with several direct interfaces, each configured with a port-profile per the XML. VM-to-VM, and VM-to-external work as expected. VM-to-VM on same host (using same NIC) works same as VM-to-VM where VMs are on diff hosts. I'm able to change settings on the port-profile while the VM is running to change the virtual port behaviour. For example, adjusting a QoS setting like rate limit. All VMs with interfaces using that port-profile immediatly see the effect of the change to the port-profile. I don't have a SR-IOV device to test so source dev is a non-SR-IOV device, but most of the code paths include support for specifing the source dev and VF index. We'll need to complete this by discovering the PF given the VF linkdev. Once we have the PF, we'll also have the VF index. All this info- mation is available from sysfs. Signed-off-by: Scott Feldman <scofeldm(a)cisco.com> Signed-off-by: Stefan Berger <stefanb(a)us.ibm.com> --- configure.ac | 16 - src/qemu/qemu_conf.c | 2 src/qemu/qemu_driver.c | 4 src/util/macvtap.c | 768 ++++++++++++++++++++++++++++++++++++++++++++++++- src/util/macvtap.h | 1 5 files changed, 775 insertions(+), 16 deletions(-) Index: libvirt-acl/configure.ac =================================================================== --- libvirt-acl.orig/configure.ac +++ libvirt-acl/configure.ac @@ -2005,13 +2005,26 @@ if test "$with_macvtap" != "no" ; then fi AM_CONDITIONAL([WITH_MACVTAP], [test "$with_macvtap" = "yes"]) +AC_TRY_COMPILE([ #include <sys/socket.h> + #include <linux/rtnetlink.h> ], + [ int x = IFLA_PORT_MAX; ], + [ with_virtualport=yes ], + [ with_virtualport=no ]) +if test "$with_virtualport" = "yes"; then + val=1 +else + val=0 +fi +AC_DEFINE_UNQUOTED([WITH_VIRTUALPORT], $val, [whether vsi vepa support is enabled]) +AM_CONDITIONAL([WITH_VIRTUALPORT], [test "$with_virtualport" = "yes"]) + dnl netlink library LIBNL_CFLAGS="" LIBNL_LIBS="" -if test "$with_macvtap" = "yes"; then +if test "$with_macvtap" = "yes" || "$with_virtualport" = "yes"; then PKG_CHECK_MODULES([LIBNL], [libnl-1 >= $LIBNL_REQUIRED], [ ], [ AC_MSG_ERROR([libnl >= $LIBNL_REQUIRED is required for macvtap support]) @@ -2084,6 +2097,7 @@ AC_MSG_NOTICE([ Network: $with_network]) AC_MSG_NOTICE([Libvirtd: $with_libvirtd]) AC_MSG_NOTICE([ netcf: $with_netcf]) AC_MSG_NOTICE([ macvtap: $with_macvtap]) +AC_MSG_NOTICE([virtport: $with_virtualport]) AC_MSG_NOTICE([]) AC_MSG_NOTICE([Storage Drivers]) AC_MSG_NOTICE([]) Index: libvirt-acl/src/qemu/qemu_conf.c =================================================================== --- libvirt-acl.orig/src/qemu/qemu_conf.c +++ libvirt-acl/src/qemu/qemu_conf.c @@ -1505,7 +1505,7 @@ qemudPhysIfaceConnect(virConnectPtr conn if (err) { close(rc); rc = -1; - delMacvtap(net->ifname, + delMacvtap(net->ifname, net->data.direct.linkdev, &net->data.direct.virtPortProfile); } } Index: libvirt-acl/src/qemu/qemu_driver.c =================================================================== --- libvirt-acl.orig/src/qemu/qemu_driver.c +++ libvirt-acl/src/qemu/qemu_driver.c @@ -3709,7 +3709,7 @@ static void qemudShutdownVMDaemon(struct for (i = 0; i < def->nnets; i++) { virDomainNetDefPtr net = def->nets[i]; if (net->type == VIR_DOMAIN_NET_TYPE_DIRECT) - delMacvtap(net->ifname, + delMacvtap(net->ifname, net->data.direct.linkdev, &net->data.direct.virtPortProfile); } #endif @@ -8513,7 +8513,7 @@ qemudDomainDetachNetDevice(struct qemud_ #if WITH_MACVTAP if (detach->type == VIR_DOMAIN_NET_TYPE_DIRECT) - delMacvtap(detach->ifname, + delMacvtap(detach->ifname, detach->data.direct.linkdev, &detach->data.direct.virtPortProfile); #endif Index: libvirt-acl/src/util/macvtap.c =================================================================== --- libvirt-acl.orig/src/util/macvtap.c +++ libvirt-acl/src/util/macvtap.c @@ -27,7 +27,7 @@ #include <config.h> -#if WITH_MACVTAP +#if WITH_MACVTAP || WITH_VIRTUALPORT # include <stdio.h> # include <errno.h> @@ -41,6 +41,8 @@ # include <linux/rtnetlink.h> # include <linux/if_tun.h> +# include <netlink/msg.h> + # include "util.h" # include "memory.h" # include "logging.h" @@ -48,6 +50,7 @@ # include "interface.h" # include "conf/domain_conf.h" # include "virterror_internal.h" +# include "uuid.h" # define VIR_FROM_THIS VIR_FROM_NET @@ -58,15 +61,23 @@ # define MACVTAP_NAME_PREFIX "macvtap" # define MACVTAP_NAME_PATTERN "macvtap%d" +# define MICROSEC_PER_SEC (1000 * 1000) + static int associatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileParamsPtr virtPort, - int vf, const unsigned char *vmuuid); static int disassociatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileParamsPtr virtPort); +enum virVirtualPortOp { + ASSOCIATE = 0x1, + DISASSOCIATE = 0x2, +}; + static int nlOpen(void) { @@ -159,6 +170,156 @@ err_exit: } +# ifdef IFLA_VF_PORT_MAX + +/** + * nlCommWaitSuccess: + * + * @nlmsg: pointer to netlink message + * @nl_grousp: the netlink multicast groups to send to + * @respbuf: pointer to pointer where response buffer will be allocated + * @respbuflen: pointer to integer holding the size of the response buffer + * on return of the function. + * @to_usecs: timeout in microseconds to wait for a success message + * to be returned + * + * Send the given message to the netlink multicast group and receive + * responses. Skip responses indicating an error and keep on receiving + * responses until a success response is returned. + * Returns 0 on success, -1 on error. In case of error, no response + * buffer will be returned. + */ +static int +nlCommWaitSuccess(struct nlmsghdr *nlmsg, int nl_groups, + char **respbuf, int *respbuflen, long to_usecs) +{ + int rc = 0; + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK, + .nl_pid = getpid(), + .nl_groups = nl_groups, + }; + int rcvChunkSize = 1024; // expecting less than that + int rcvoffset = 0; + ssize_t nbytes; + int n; + struct timeval tv = { + .tv_sec = to_usecs / MICROSEC_PER_SEC, + .tv_usec = to_usecs % MICROSEC_PER_SEC, + }; + fd_set rfds; + bool gotvalid = false; + int fd = nlOpen(); + static uint32_t seq = 0x1234; + uint32_t myseq = seq++; + uint32_t mypid = getpid(); + + if (fd < 0) + return -1; + + nlmsg->nlmsg_pid = mypid; + nlmsg->nlmsg_seq = myseq; + nlmsg->nlmsg_flags |= NLM_F_ACK; + + nbytes = sendto(fd, (void *)nlmsg, nlmsg->nlmsg_len, 0, + (struct sockaddr *)&nladdr, sizeof(nladdr)); + if (nbytes < 0) { + virReportSystemError(errno, + "%s", _("cannot send to netlink socket")); + rc = -1; + goto err_exit; + } + + while (!gotvalid) { + rcvoffset = 0; + while (1) { + socklen_t addrlen = sizeof(nladdr); + + if (VIR_REALLOC_N(*respbuf, rcvoffset+rcvChunkSize) < 0) { + virReportOOMError(); + rc = -1; + goto err_exit; + } + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + n = select(fd + 1, &rfds, NULL, NULL, &tv); + if (n == 0) { + rc = -1; + goto err_exit; + } + + nbytes = recvfrom(fd, &((*respbuf)[rcvoffset]), rcvChunkSize, 0, + (struct sockaddr *)&nladdr, &addrlen); + if (nbytes < 0) { + if (errno == EAGAIN || errno == EINTR) + continue; + virReportSystemError(errno, "%s", + _("error receiving from netlink socket")); + rc = -1; + goto err_exit; + } + rcvoffset += nbytes; + break; + } + *respbuflen = rcvoffset; + + /* check message for error */ + if (*respbuflen > NLMSG_LENGTH(0) && *respbuf != NULL) { + struct nlmsghdr *resp = (struct nlmsghdr *)*respbuf; + struct nlmsgerr *err; + + if (resp->nlmsg_pid != mypid || + resp->nlmsg_seq != myseq) + continue; + + /* skip reflected message */ + if (resp->nlmsg_type & 0x10) + continue; + + switch (resp->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(resp); + if (resp->nlmsg_len >= NLMSG_LENGTH(sizeof(*err))) { + if (-err->error != EOPNOTSUPP) { + /* assuming error msg from daemon */ + gotvalid = true; + break; + } + } + /* whatever this is, skip it */ + VIR_FREE(*respbuf); + *respbuf = NULL; + *respbuflen = 0; + break; + + case NLMSG_DONE: + gotvalid = true; + break; + + default: + VIR_FREE(*respbuf); + *respbuf = NULL; + *respbuflen = 0; + break; + } + } + } + +err_exit: + if (rc == -1) { + VIR_FREE(*respbuf); + *respbuf = NULL; + *respbuflen = 0; + } + + nlClose(fd); + return rc; +} + +# endif + static struct rtattr * rtattrCreate(char *buffer, int bufsize, int type, const void *data, int datalen) @@ -204,6 +365,8 @@ nlAppend(struct nlmsghdr *nlm, int totle } +# if WITH_MACVTAP + static int link_add(const char *type, const unsigned char *macaddress, int macaddrsize, @@ -655,8 +818,8 @@ create_name: } if (associatePortProfileId(cr_ifname, + linkdev, virtPortProfile, - -1, vmuuid) != 0) { rc = -1; goto link_del_exit; @@ -689,6 +852,7 @@ create_name: disassociate_exit: disassociatePortProfileId(cr_ifname, + linkdev, virtPortProfile); link_del_exit: @@ -701,6 +865,7 @@ link_del_exit: /** * delMacvtap: * @ifname : The name of the macvtap interface + * @linkdev: The interface name of the NIC to connect to the external bridge * @virtPortProfile: pointer to object holding the virtual port profile data * * Delete an interface given its name. Disassociate @@ -709,24 +874,593 @@ link_del_exit: */ void delMacvtap(const char *ifname, + const char *linkdev, virVirtualPortProfileParamsPtr virtPortProfile) { if (ifname) { disassociatePortProfileId(ifname, + linkdev, virtPortProfile); link_del(ifname); } } -#endif +# endif + + +# ifdef IFLA_PORT_MAX + +static struct nla_policy ifla_policy[IFLA_MAX + 1] = +{ + [IFLA_VF_PORTS] = { .type = NLA_NESTED }, +}; + +static struct nla_policy ifla_vf_ports_policy[IFLA_VF_PORT_MAX + 1] = +{ + [IFLA_VF_PORT] = { .type = NLA_NESTED }, +}; + +static struct nla_policy ifla_port_policy[IFLA_PORT_MAX + 1] = +{ + [IFLA_PORT_RESPONSE] = { .type = NLA_U16 }, +}; + + +static int +link_dump(bool multicast, int ifindex, struct nlattr **tb, char **recvbuf) +{ + int rc = 0; + char nlmsgbuf[256] = { 0, }; + struct nlmsghdr *nlm = (struct nlmsghdr *)nlmsgbuf, *resp; + struct nlmsgerr *err; + struct ifinfomsg i = { + .ifi_family = AF_UNSPEC, + .ifi_index = ifindex + }; + int recvbuflen; + + *recvbuf = NULL; + + nlInit(nlm, NLM_F_REQUEST, RTM_GETLINK); + + if (!nlAppend(nlm, sizeof(nlmsgbuf), &i, sizeof(i))) + goto buffer_too_small; + + if (!multicast) { + if (nlComm(nlm, recvbuf, &recvbuflen) < 0) + return -1; + } else { + if (nlCommWaitSuccess(nlm, RTMGRP_LINK, recvbuf, &recvbuflen, + 5 * MICROSEC_PER_SEC) < 0) + return -1; + } + + if (recvbuflen < NLMSG_LENGTH(0) || *recvbuf == NULL) + goto malformed_resp; + + resp = (struct nlmsghdr *)*recvbuf; + + switch (resp->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(resp); + if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err))) + goto malformed_resp; + + switch (-err->error) { + case 0: + break; + + default: + virReportSystemError(-err->error, + _("error dumping %d interface"), + ifindex); + rc = -1; + } + break; + + case GENL_ID_CTRL: + case NLMSG_DONE: + if (nlmsg_parse(resp, sizeof(struct ifinfomsg), + tb, IFLA_MAX, ifla_policy)) { + goto malformed_resp; + } + break; + + default: + goto malformed_resp; + } + + if (rc != 0) + VIR_FREE(*recvbuf); + + return rc; + +malformed_resp: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("malformed netlink response message")); + VIR_FREE(*recvbuf); + return -1; + +buffer_too_small: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("internal buffer is too small")); + return -1; +} + + +static int +getPortProfileStatus(struct nlattr **tb, int32_t vf, uint16_t *status) +{ + int rc = 1; + const char *msg = NULL; + struct nlattr *tb2[IFLA_VF_PORT_MAX + 1], + *tb3[IFLA_PORT_MAX+1]; + + if (vf == PORT_SELF_VF) { + if (tb[IFLA_PORT_SELF]) { + if (nla_parse_nested(tb3, IFLA_PORT_MAX, tb[IFLA_PORT_SELF], + ifla_port_policy)) { + msg = _("error parsing nested IFLA_VF_PORT part"); + goto err_exit; + } + } + } else { + if (tb[IFLA_VF_PORTS]) { + if (nla_parse_nested(tb2, IFLA_VF_PORT_MAX, tb[IFLA_VF_PORTS], + ifla_vf_ports_policy)) { + msg = _("error parsing nested IFLA_VF_PORTS part"); + goto err_exit; + } + if (tb2[IFLA_VF_PORT]) { + if (nla_parse_nested(tb3, IFLA_PORT_MAX, tb2[IFLA_VF_PORT], + ifla_port_policy)) { + msg = _("error parsing nested IFLA_VF_PORT part"); + goto err_exit; + } + } + } + } + if (tb3[IFLA_PORT_RESPONSE]) { + *status = *(uint16_t *)RTA_DATA(tb3[IFLA_PORT_RESPONSE]); + rc = 0; + } else { + msg = _("no IFLA_PORT_RESPONSE found in netlink message"); + goto err_exit; + } + +err_exit: + if (msg) + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", msg); + + return rc; +} + + +static int +doPortProfileOpSetLink(bool multicast, + int ifindex, + const char *profileId, + struct ifla_port_vsi *portVsi, + const unsigned char *instanceId, + const unsigned char *hostUUID, + int32_t vf, + uint8_t op) +{ + int rc = 0; + char nlmsgbuf[256]; + struct nlmsghdr *nlm = (struct nlmsghdr *)nlmsgbuf, *resp; + struct nlmsgerr *err; + char rtattbuf[64]; + struct rtattr *rta, *vfports = NULL, *vfport; + struct ifinfomsg ifinfo = { + .ifi_family = AF_UNSPEC, + .ifi_index = ifindex, + }; + char *recvbuf = NULL; + int recvbuflen = 0; + + memset(&nlmsgbuf, 0, sizeof(nlmsgbuf)); + + nlInit(nlm, NLM_F_REQUEST, RTM_SETLINK); + + if (!nlAppend(nlm, sizeof(nlmsgbuf), &ifinfo, sizeof(ifinfo))) + goto buffer_too_small; + + if (vf == PORT_SELF_VF) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_SELF, NULL, 0); + } else { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_VF_PORTS, NULL, 0); + if (!rta) + goto buffer_too_small; + + if (!(vfports = nlAppend(nlm, sizeof(nlmsgbuf), + rtattbuf, rta->rta_len))) + goto buffer_too_small; + + /* beging nesting vfports */ + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_VF_PORT, NULL, 0); + } + + if (!rta) + goto buffer_too_small; + + if (!(vfport = nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len))) + goto buffer_too_small; + + if (profileId) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_PROFILE, + profileId, strlen(profileId) + 1); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (portVsi) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_VSI_TYPE, + portVsi, sizeof(*portVsi)); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (instanceId) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_INSTANCE_UUID, + instanceId, VIR_UUID_BUFLEN); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (hostUUID) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_HOST_UUID, + hostUUID, VIR_UUID_BUFLEN); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (vf != PORT_SELF_VF) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_VF, + &vf, sizeof(vf)); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_REQUEST, + &op, sizeof(op)); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + + /* end nesting of vport */ + vfport->rta_len = (char *)nlm + nlm->nlmsg_len - (char *)vfport; + + if (vf != PORT_SELF_VF) { + /* end nesting of vfports */ + vfports->rta_len = (char *)nlm + nlm->nlmsg_len - (char *)vfports; + } + + if (!multicast) { + if (nlComm(nlm, &recvbuf, &recvbuflen) < 0) + return -1; + } else { + if (nlCommWaitSuccess(nlm, RTMGRP_LINK, &recvbuf, &recvbuflen, + 5 * MICROSEC_PER_SEC) < 0) + return -1; + } + + if (recvbuflen < NLMSG_LENGTH(0) || recvbuf == NULL) + goto malformed_resp; + + resp = (struct nlmsghdr *)recvbuf; + + switch (resp->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(resp); + if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err))) + goto malformed_resp; + + switch (-err->error) { + case 0: + break; + + default: + virReportSystemError(-err->error, + _("error during virtual port configuration of ifindex %d"), + ifindex); + rc = -1; + } + break; + + case NLMSG_DONE: + break; + + default: + goto malformed_resp; + } + + VIR_FREE(recvbuf); + + return rc; + +malformed_resp: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("malformed netlink response message")); + VIR_FREE(recvbuf); + return -1; + +buffer_too_small: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("internal buffer is too small")); + return -1; +} + + +static int +doPortProfileOpCommon(bool multicast, + int ifindex, + const char *profileId, + struct ifla_port_vsi *portVsi, + const unsigned char *instanceId, + const unsigned char *hostUUID, + int32_t vf, + uint8_t op) +{ + int rc; + char *recvbuf = NULL; + struct nlattr *tb[IFLA_MAX + 1]; + int repeats = 80; + uint16_t status = 0; + + rc = doPortProfileOpSetLink(multicast, + ifindex, + profileId, + portVsi, + instanceId, + hostUUID, + vf, + op); + + if (rc != 0) { + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("sending of PortProfileRequest failed.")); + return rc; + } + + while (--repeats) { + rc = link_dump(multicast, ifindex, tb, &recvbuf); + if (rc) + goto err_exit; + rc = getPortProfileStatus(tb, vf, &status); + if (rc == 0) { + if (status == PORT_PROFILE_RESPONSE_SUCCESS || + status == PORT_VDP_RESPONSE_SUCCESS) { + break; + } else if (status == PORT_PROFILE_RESPONSE_INPROGRESS) { + // keep trying... + } else { + virReportSystemError(EINVAL, + _("error %d during port-profile setlink on ifindex %d"), + status, ifindex); + rc = 1; + break; + } + } + usleep(125000); + + VIR_FREE(recvbuf); + } + + if (status == PORT_PROFILE_RESPONSE_INPROGRESS) { + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("port-profile setlink timed out")); + rc = -ETIMEDOUT; + } + +err_exit: + VIR_FREE(recvbuf); + + return rc; +} + +# endif /* IFLA_PORT_MAX */ + +static int +doPortProfileOp8021Qbg(const char *ifname, + const virVirtualPortProfileParamsPtr virtPort, + enum virVirtualPortOp virtPortOp) +{ + int rc; + +# ifndef IFLA_VF_PORT_MAX + + (void)ifname; + (void)virtPort; + (void)virtPortOp; + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Kernel VF Port support was missing at compile time.")); + rc = 1; + +# else /* IFLA_VF_PORT_MAX */ + + int op = PORT_REQUEST_ASSOCIATE; + struct ifla_port_vsi portVsi = { + .vsi_mgr_id = virtPort->u.virtPort8021Qbg.managerID, + .vsi_type_version = virtPort->u.virtPort8021Qbg.typeIDVersion, + }; + bool multicast = true; + int ifindex; + + if (ifaceGetIndex(true, ifname, &ifindex) != 0) { + rc = 1; + goto err_exit; + } + + portVsi.vsi_type_id[2] = virtPort->u.virtPort8021Qbg.typeID >> 16; + portVsi.vsi_type_id[1] = virtPort->u.virtPort8021Qbg.typeID >> 8; + portVsi.vsi_type_id[0] = virtPort->u.virtPort8021Qbg.typeID; + + switch (virtPortOp) { + case ASSOCIATE: + op = PORT_REQUEST_ASSOCIATE; + break; + case DISASSOCIATE: + op = PORT_REQUEST_DISASSOCIATE; + break; + default: + macvtapError(VIR_ERR_INTERNAL_ERROR, + _("operation type %d not supported"), op); + rc = 1; + goto err_exit; + } + + rc = doPortProfileOpCommon(multicast, ifindex, + NULL, + &portVsi, + virtPort->u.virtPort8021Qbg.instanceID, + NULL, + PORT_SELF_VF, + op); + +err_exit: + +# endif /* IFLA_VF_PORT_MAX */ + + return rc; +} + + +# ifdef IFLA_VF_PORT_MAX +static int +getPhysfn(const char *linkdev, + int32_t *vf, + char **physfndev) +{ + int rc = 0; + bool virtfn = false; + + if (virtfn) { + + // XXX: if linkdev is SR-IOV VF, then set vf = VF index + // XXX: and set linkdev = PF device + // XXX: need to use get_physical_function_linux() or + // XXX: something like that to get PF + // XXX: device and figure out VF index + + rc = 1; + + } else { + + /* Not SR-IOV VF: physfndev is linkdev and VF index + * refers to linkdev self + */ + + *vf = PORT_SELF_VF; + *physfndev = (char *)linkdev; + } + + return rc; +} +# endif /* IFLA_VF_PORT_MAX */ + +static int +doPortProfileOp8021Qbh(const char *ifname, + const virVirtualPortProfileParamsPtr virtPort, + const unsigned char *vm_uuid, + enum virVirtualPortOp virtPortOp) +{ + int rc; + +# ifndef IFLA_VF_PORT_MAX + + (void)ifname; + (void)virtPort; + (void)vm_uuid; + (void)virtPortOp; + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Kernel VF Port support was missing at compile time.")); + rc = 1; + +# else /* IFLA_VF_PORT_MAX */ + + char *physfndev; + unsigned char hostuuid[VIR_UUID_BUFLEN]; + int32_t vf; + int op = PORT_REQUEST_ASSOCIATE; + bool multicast = false; + int ifindex; + + rc = virGetHostUUID(hostuuid); + if (rc) + goto err_exit; + + rc = getPhysfn(ifname, &vf, &physfndev); + if (rc) + goto err_exit; + + if (ifaceGetIndex(true, physfndev, &ifindex) != 0) { + rc = 1; + goto err_exit; + } + + switch (virtPortOp) { + case ASSOCIATE: + op = PORT_REQUEST_ASSOCIATE; + break; + case DISASSOCIATE: + op = PORT_REQUEST_DISASSOCIATE; + break; + default: + macvtapError(VIR_ERR_INTERNAL_ERROR, + _("operation type %d not supported"), op); + rc = 1; + goto err_exit; + } + + rc = doPortProfileOpCommon(multicast, ifindex, + virtPort->u.virtPort8021Qbh.profileID, + NULL, + vm_uuid, + hostuuid, + vf, + op); + + switch (virtPortOp) { + case ASSOCIATE: + ifaceUp(ifname); + break; + case DISASSOCIATE: + ifaceDown(ifname); + break; + } + +err_exit: + +# endif /* IFLA_VF_PORT_MAX */ + + return rc; +} /** * associatePortProfile * * @macvtap_ifname: The name of the macvtap device + * @linkdev: The link device in case of macvtap * @virtPort: pointer to the object holding port profile parameters - * @vf: virtual function number, -1 if to be ignored * @vmuuid : the UUID of the virtual machine * * Associate a port on a swtich with a profile. This function @@ -740,15 +1474,14 @@ delMacvtap(const char *ifname, */ static int associatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileParamsPtr virtPort, - int vf, const unsigned char *vmuuid) { int rc = 0; + VIR_DEBUG("Associating port profile '%p' on link device '%s'", virtPort, macvtap_ifname); - (void)vf; - (void)vmuuid; switch (virtPort->virtPortType) { case VIR_VIRTUALPORT_NONE: @@ -756,11 +1489,14 @@ associatePortProfileId(const char *macvt break; case VIR_VIRTUALPORT_8021QBG: - + rc = doPortProfileOp8021Qbg(macvtap_ifname, virtPort, + ASSOCIATE); break; case VIR_VIRTUALPORT_8021QBH: - + rc = doPortProfileOp8021Qbh(linkdev, virtPort, + vmuuid, + ASSOCIATE); break; } @@ -772,6 +1508,7 @@ associatePortProfileId(const char *macvt * disassociatePortProfile * * @macvtap_ifname: The name of the macvtap device + * @linkdev: The link device in case of macvtap * @virtPort: point to object holding port profile parameters * * Returns 0 in case of success, != 0 otherwise with error @@ -779,9 +1516,11 @@ associatePortProfileId(const char *macvt */ static int disassociatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileParamsPtr virtPort) { int rc = 0; + VIR_DEBUG("Disassociating port profile id '%p' on link device '%s' ", virtPort, macvtap_ifname); @@ -791,13 +1530,18 @@ disassociatePortProfileId(const char *ma break; case VIR_VIRTUALPORT_8021QBG: - + rc = doPortProfileOp8021Qbg(macvtap_ifname, virtPort, + DISASSOCIATE); break; case VIR_VIRTUALPORT_8021QBH: - + rc = doPortProfileOp8021Qbh(linkdev, virtPort, + NULL, + DISASSOCIATE); break; } return rc; } + +#endif Index: libvirt-acl/src/util/macvtap.h =================================================================== --- libvirt-acl.orig/src/util/macvtap.h +++ libvirt-acl/src/util/macvtap.h @@ -72,6 +72,7 @@ int openMacvtapTap(const char *ifname, char **res_ifname); void delMacvtap(const char *ifname, + const char *linkdev, virVirtualPortProfileParamsPtr virtPortProfile); # endif /* WITH_MACVTAP */

1 0

[libvirt] [PATCH] virDrvStorageVolLookupByKey and virDrvStorageVolLookupByPath should use virStoragePoolPtr as parameter
by Eduardo Otubo 25 May '10

25 May '10

Hello, These two functions, virDrvStorageVolLookupByKey and virDrvStorageVolLookupByPath should use virStoragePoolPtr as parameter instead of virConnectPtr for some few reasons: 1) Should follow the standard virStorage*Ptr parameters like the rest of storage related functions. 2) Functions now are able to access pool structure. This is particularly important for the optimization of the PowerHypervisor phypVolumeLookupByKey function. Thanks, -- Eduardo Otubo Software Engineer Linux Technology Center IBM Systems & Technology Group Mobile: +55 19 8135 0885 eotubo(a)linux.vnet.ibm.com -- diff --git a/src/driver.h b/src/driver.h index 0975b59..bb05306 100644 --- a/src/driver.h +++ b/src/driver.h @@ -798,10 +798,10 @@ typedef virStorageVolPtr (*virDrvStorageVolLookupByName) (virStoragePoolPtr pool, const char *name); typedef virStorageVolPtr - (*virDrvStorageVolLookupByKey) (virConnectPtr pool, + (*virDrvStorageVolLookupByKey) (virStoragePoolPtr pool, const char *key); typedef virStorageVolPtr - (*virDrvStorageVolLookupByPath) (virConnectPtr pool, + (*virDrvStorageVolLookupByPath) (virStoragePoolPtr pool, const char *path); diff --git a/src/libvirt.c b/src/libvirt.c index 9d42c76..c43ce9c 100644 --- a/src/libvirt.c +++ b/src/libvirt.c @@ -8418,11 +8418,12 @@ error: * Returns a storage volume, or NULL if not found / error */ virStorageVolPtr -virStorageVolLookupByKey(virConnectPtr conn, +virStorageVolLookupByKey(virStoragePoolPtr pool, const char *key) { - DEBUG("conn=%p, key=%s", conn, key); + DEBUG("pool=%p, key=%s", pool, key); + virConnectPtr conn = pool->conn; virResetLastError(); if (!VIR_IS_CONNECT(conn)) { @@ -8437,7 +8438,7 @@ virStorageVolLookupByKey(virConnectPtr conn, if (conn->storageDriver && conn->storageDriver->volLookupByKey) { virStorageVolPtr ret; - ret = conn->storageDriver->volLookupByKey (conn, key); + ret = conn->storageDriver->volLookupByKey (pool, key); if (!ret) goto error; return ret; @@ -8461,11 +8462,12 @@ error: * Returns a storage volume, or NULL if not found / error */ virStorageVolPtr -virStorageVolLookupByPath(virConnectPtr conn, +virStorageVolLookupByPath(virStoragePoolPtr pool, const char *path) { - DEBUG("conn=%p, path=%s", conn, path); + DEBUG("pool=%p, path=%s", pool, path); + virConnectPtr conn = pool->conn; virResetLastError(); if (!VIR_IS_CONNECT(conn)) { @@ -8480,7 +8482,7 @@ virStorageVolLookupByPath(virConnectPtr conn, if (conn->storageDriver && conn->storageDriver->volLookupByPath) { virStorageVolPtr ret; - ret = conn->storageDriver->volLookupByPath (conn, path); + ret = conn->storageDriver->volLookupByPath (pool, path); if (!ret) goto error; return ret; diff --git a/src/remote/remote_driver.c b/src/remote/remote_driver.c index 80977a3..12380f4 100644 --- a/src/remote/remote_driver.c +++ b/src/remote/remote_driver.c @@ -5559,9 +5559,10 @@ done: } static virStorageVolPtr -remoteStorageVolLookupByKey (virConnectPtr conn, +remoteStorageVolLookupByKey (virStoragePoolPtr pool, const char *key) { + virConnectPtr conn = pool->conn; virStorageVolPtr vol = NULL; remote_storage_vol_lookup_by_key_args args; remote_storage_vol_lookup_by_key_ret ret; @@ -5586,9 +5587,10 @@ done: } static virStorageVolPtr -remoteStorageVolLookupByPath (virConnectPtr conn, +remoteStorageVolLookupByPath (virStoragePoolPtr pool, const char *path) { + virConnectPtr conn = pool->conn; virStorageVolPtr vol = NULL; remote_storage_vol_lookup_by_path_args args; remote_storage_vol_lookup_by_path_ret ret; diff --git a/src/storage/storage_driver.c b/src/storage/storage_driver.c index b148e39..25fe1d1 100644 --- a/src/storage/storage_driver.c +++ b/src/storage/storage_driver.c @@ -1168,8 +1168,9 @@ cleanup: static virStorageVolPtr -storageVolumeLookupByKey(virConnectPtr conn, +storageVolumeLookupByKey(virStoragePoolPtr pool, const char *key) { + virConnectPtr conn = pool->conn; virStorageDriverStatePtr driver = conn->storagePrivateData; unsigned int i; virStorageVolPtr ret = NULL; @@ -1199,8 +1200,9 @@ storageVolumeLookupByKey(virConnectPtr conn, } static virStorageVolPtr -storageVolumeLookupByPath(virConnectPtr conn, +storageVolumeLookupByPath(virStoragePoolPtr pool, const char *path) { + virConnectPtr conn = pool->conn; virStorageDriverStatePtr driver = conn->storagePrivateData; unsigned int i; virStorageVolPtr ret = NULL; diff --git a/src/test/test_driver.c b/src/test/test_driver.c index 395c8c9..c65e4a0 100644 --- a/src/test/test_driver.c +++ b/src/test/test_driver.c @@ -4251,8 +4251,9 @@ cleanup: static virStorageVolPtr -testStorageVolumeLookupByKey(virConnectPtr conn, +testStorageVolumeLookupByKey(virStoragePoolPtr pool, const char *key) { + virConnectPtr conn = pool->conn; testConnPtr privconn = conn->privateData; unsigned int i; virStorageVolPtr ret = NULL; @@ -4285,8 +4286,9 @@ testStorageVolumeLookupByKey(virConnectPtr conn, } static virStorageVolPtr -testStorageVolumeLookupByPath(virConnectPtr conn, +testStorageVolumeLookupByPath(virStoragePoolPtr pool, const char *path) { + virConnectPtr conn = pool->conn; testConnPtr privconn = conn->privateData; unsigned int i; virStorageVolPtr ret = NULL; diff --git a/src/vbox/vbox_tmpl.c b/src/vbox/vbox_tmpl.c index 6a9a2bf..ce665ef 100644 --- a/src/vbox/vbox_tmpl.c +++ b/src/vbox/vbox_tmpl.c @@ -7547,7 +7547,8 @@ static virStorageVolPtr vboxStorageVolLookupByName(virStoragePoolPtr pool, const return ret; } -static virStorageVolPtr vboxStorageVolLookupByKey(virConnectPtr conn, const char *key) { +static virStorageVolPtr vboxStorageVolLookupByKey(virStoragePoolPtr pool, const char *key) { + virConnectPtr conn = pool->conn; VBOX_OBJECT_CHECK(conn, virStorageVolPtr, NULL); vboxIID *hddIID = NULL; IHardDisk *hardDisk = NULL; @@ -7616,7 +7617,8 @@ cleanup: return ret; } -static virStorageVolPtr vboxStorageVolLookupByPath(virConnectPtr conn, const char *path) { +static virStorageVolPtr vboxStorageVolLookupByPath(virStoragePoolPtr pool, const char *path) { + virConnectPtr conn = pool->conn; VBOX_OBJECT_CHECK(conn, virStorageVolPtr, NULL); PRUnichar *hddPathUtf16 = NULL; IHardDisk *hardDisk = NULL;

2 1

[libvirt] [PATCH v8] vepa: parsing for 802.1Qb{g|h} XML
by Stefan Berger 25 May '10

25 May '10

Below is David Alan's original patch with lots of changes. In particular, it now parses the following two XML descriptions, one for 802.1Qbg and 802.1Qbh and stored the data internally. The actual triggering of the switch setup protocol has not been implemented here but the relevant code to do that should go into the functions associatePortProfileId() and disassociatePortProfileId(). <interface type='direct'> <source dev='eth0.100' mode='vepa'/> <model type='virtio'/> <virtualport type='802.1Qbg'> <parameters managerid='12' typeid='0x123456' typeidversion='1' instanceid='fa9b7fff-b0a0-4893-8e0e-beef4ff18f8f'/> </virtualport> <filterref filter='clean-traffic'/> </interface> <interface type='direct'> <source dev='eth0.100' mode='vepa'/> <model type='virtio'/> <virtualport type='802.1Qbh'> <parameters profileid='my_profile'/> </virtualport> </interface> I'd suggest to use this patch as a base for triggering the setup protocol with the 802.1Qb{g|h} switch. Changes from V7 to V8: - Addressed most of Chris Wright's comments: - indicating error in case virtualport XML node cannot be parsed properly - parsing hex and decimal numbers using virStrToLong_ui() with parameter '0' for base - tgifname (target interface name) variable wasn't necessary to pass to openMacvtapTap function anymore - assigning the virtual port data structure to the virDomainNetDef only if it was previously parsed -> still leaving possibility to start a domain with macvtap but no profile Changes from V6 to V7: - make sure that the error code returned by openMacvtapTap() is a negative number in case the associatePortProfileId() function failed. Changes from V5 to V6: - renaming vsi in the XML to virtualport - replace all occurrences of vsi in the source as well Changes from V4 to V5: - removing mode and MAC address parameters from the functions that will communicate with the hareware diretctly or indirectly Changes from V3 to V4: - moving the associate and disassociate functions to the end of the file for subsequent patches to easier make them generally available for export - passing the macvtap interface name rather than the link device since this otherwise gives funny side effects when using netlink messages where IFLA_IFNAME and IFLA_ADDRESS are specified and the link dev all of a sudden gets the MAC address of the macvtap interface. - Removing rc = -1 error indications in the case of 802.1Qbg|h setup in case we wanted to use hook scripts for the setup and so the setup doesn't fail here. Changes from V2 to V3: - if instance ID UUID is not supplied it will automatically be generated - adapted schema to make instance ID UUID optional - added test case Some of the changes from V1 to V2: - parser and XML generator have been separated into their own functions so they can be re-used elsewhere (passthrough case for example) - Adapted XML parser and generator support the above shown type (802.1Qbg, 802.1Qbh). - Adapted schema to above XML - Adapted test XML to above XML - Passing through the VM's UUID which seems to be necessary for 802.1Qbh -- sorry no host UUID - adding virtual function ID to association function, in case it's necessary to use (for SR-IOV) Signed-off-by: Stefan Berger <stefanb(a)us.ibm.com> >From a945107f047c7cd71f9c1b74fd74c47d8cdc3670 Mon Sep 17 00:00:00 2001 From: David Allan <dallan(a)redhat.com> Date: Fri, 12 Mar 2010 13:25:04 -0500 Subject: [PATCH 1/1] POC of port profile id support * Modified schema per DanPB's feedback * Added test for modified schema --- docs/schemas/domain.rng | 69 ++++++++++++++ src/conf/domain_conf.c | 155 +++++++++++++++++++++++++++++++++ src/conf/domain_conf.h | 35 +++++++ src/qemu/qemu_conf.c | 18 +-- src/qemu/qemu_conf.h | 5 - src/qemu/qemu_driver.c | 17 +-- src/util/macvtap.c | 151 +++++++++++++++++++++++++++----- src/util/macvtap.h | 10 +- tests/domainschemadata/portprofile.xml | 36 +++++++ 9 files changed, 446 insertions(+), 50 deletions(-) create mode 100644 tests/domainschemadata/portprofile.xml Index: libvirt-acl/docs/schemas/domain.rng =================================================================== --- libvirt-acl.orig/docs/schemas/domain.rng +++ libvirt-acl/docs/schemas/domain.rng @@ -817,6 +817,9 @@ </optional> <empty/> </element> + <optional> + <ref name="virtualPortProfile"/> + </optional> <ref name="interface-options"/> </interleave> </group> @@ -902,6 +905,45 @@ </optional> </interleave> </define> + <define name="virtualPortProfile"> + <choice> + <group> + <element name="virtualport"> + <attribute name="type"> + <value>802.1Qbg</value> + </attribute> + <element name="parameters"> + <attribute name="managerid"> + <ref name="uint8range"/> + </attribute> + <attribute name="typeid"> + <ref name="uint24range"/> + </attribute> + <attribute name="typeidversion"> + <ref name="uint8range"/> + </attribute> + <optional> + <attribute name="instanceid"> + <ref name="UUID"/> + </attribute> + </optional> + </element> + </element> + </group> + <group> + <element name="virtualport"> + <attribute name="type"> + <value>802.1Qbh</value> + </attribute> + <element name="parameters"> + <attribute name="profileid"> + <ref name="virtualPortProfileID"/> + </attribute> + </element> + </element> + </group> + </choice> + </define>  @@ -1769,4 +1811,31 @@ <param name="pattern">[a-zA-Z0-9_\.:]+</param> </data> </define> + <define name="uint8range"> + <choice> + <data type="string"> + <param name="pattern">0x[0-9a-fA-F]{1,2}</param> + </data> + <data type="int"> + <param name="minInclusive">0</param> + <param name="maxInclusive">255</param> + </data> + </choice> + </define> + <define name="uint24range"> + <choice> + <data type="string"> + <param name="pattern">0x[0-9a-fA-F]{1,6}</param> + </data> + <data type="int"> + <param name="minInclusive">0</param> + <param name="maxInclusive">16777215</param> + </data> + </choice> + </define> + <define name="virtualPortProfileID"> + <data type="string"> + <param name="maxLength">39</param> + </data> + </define> </grammar> Index: libvirt-acl/src/conf/domain_conf.c =================================================================== --- libvirt-acl.orig/src/conf/domain_conf.c +++ libvirt-acl/src/conf/domain_conf.c @@ -242,6 +242,11 @@ VIR_ENUM_IMPL(virDomainNetdevMacvtap, VI "private", "bridge") +VIR_ENUM_IMPL(virVirtualPort, VIR_VIRTUALPORT_TYPE_LAST, + "none", + "802.1Qbg", + "802.1Qbh") + VIR_ENUM_IMPL(virDomainClockOffset, VIR_DOMAIN_CLOCK_OFFSET_LAST, "utc", "localtime", @@ -1807,6 +1812,190 @@ cleanup: } +static int +virVirtualPortProfileDefParseXML(xmlNodePtr node, + virVirtualPortProfileDefPtr virtPort) +{ + int ret = -1; + char *virtPortType; + char *virtPortManagerID = NULL; + char *virtPortTypeID = NULL; + char *virtPortTypeIDVersion = NULL; + char *virtPortInstanceID = NULL; + char *virtPortProfileID = NULL; + xmlNodePtr cur = node->children; + const char *msg = NULL; + + virtPortType = virXMLPropString(node, "type"); + if (!virtPortType) + return -1; + + while (cur != NULL) { + if (xmlStrEqual(cur->name, BAD_CAST "parameters")) { + + virtPortManagerID = virXMLPropString(cur, "managerid"); + virtPortTypeID = virXMLPropString(cur, "typeid"); + virtPortTypeIDVersion = virXMLPropString(cur, "typeidversion"); + virtPortInstanceID = virXMLPropString(cur, "instanceid"); + virtPortProfileID = virXMLPropString(cur, "profileid"); + + break; + } + + cur = cur->next; + } + + virtPort->virtPortType = VIR_VIRTUALPORT_NONE; + + switch (virVirtualPortTypeFromString(virtPortType)) { + + case VIR_VIRTUALPORT_8021QBG: + if (virtPortManagerID != NULL && virtPortTypeID != NULL && + virtPortTypeIDVersion != NULL) { + unsigned int val; + + if (virStrToLong_ui(virtPortManagerID, NULL, 0, &val)) { + msg = _("cannot parse value of managerid parameter"); + goto err_exit; + } + + if (val > 0xff) { + msg = _("value of managerid out of range"); + goto err_exit; + } + + virtPort->u.virtPort8021Qbg.managerID = (uint8_t)val; + + if (virStrToLong_ui(virtPortTypeID, NULL, 0, &val)) { + msg = _("cannot parse value of typeid parameter"); + goto err_exit; + } + + if (val > 0xffffff) { + msg = _("value for typeid out of range"); + goto err_exit; + } + + virtPort->u.virtPort8021Qbg.typeID = (uint32_t)val; + + if (virStrToLong_ui(virtPortTypeIDVersion, NULL, 0, &val)) { + msg = _("cannot parse value of typeidversion parameter"); + goto err_exit; + } + + if (val > 0xff) { + msg = _("value of typeidversion out of range"); + goto err_exit; + } + + virtPort->u.virtPort8021Qbg.typeIDVersion = (uint8_t)val; + + if (virtPortInstanceID != NULL) { + if (virUUIDParse(virtPortInstanceID, + virtPort->u.virtPort8021Qbg.instanceID)) { + msg = _("cannot parse instanceid parameter as a uuid"); + goto err_exit; + } + } else { + if (virUUIDGenerate(virtPort->u.virtPort8021Qbg.instanceID)) { + msg = _("cannot generate a random uuid for instanceid"); + goto err_exit; + } + } + + virtPort->virtPortType = VIR_VIRTUALPORT_8021QBG; + ret = 0; + } else { + msg = _("a parameter is missing for 802.1Qbg description"); + goto err_exit; + } + break; + + case VIR_VIRTUALPORT_8021QBH: + if (virtPortProfileID != NULL) { + if (virStrcpyStatic(virtPort->u.virtPort8021Qbh.profileID, + virtPortProfileID) != NULL) { + virtPort->virtPortType = VIR_VIRTUALPORT_8021QBH; + ret = 0; + } else { + msg = _("profileid parameter too long"); + goto err_exit; + } + } else { + msg = _("profileid parameter is missing for 802.1Qbh descripion"); + goto err_exit; + } + break; + + + default: + case VIR_VIRTUALPORT_NONE: + case VIR_VIRTUALPORT_TYPE_LAST: + msg = _("unknown virtualport type"); + goto err_exit; + break; + } + +err_exit: + + if (msg) + virDomainReportError(VIR_ERR_INTERNAL_ERROR, "%s", msg); + + VIR_FREE(virtPortManagerID); + VIR_FREE(virtPortTypeID); + VIR_FREE(virtPortTypeIDVersion); + VIR_FREE(virtPortInstanceID); + VIR_FREE(virtPortProfileID); + VIR_FREE(virtPortType); + + return ret; +} + + +static void +virVirtualPortProfileFormat(virBufferPtr buf, + virVirtualPortProfileDefPtr virtPort, + const char *indent) +{ + char uuidstr[VIR_UUID_STRING_BUFLEN]; + + if (virtPort->virtPortType == VIR_VIRTUALPORT_NONE) + return; + + virBufferVSprintf(buf, "%s<virtualport type='%s'>\n", + indent, + virVirtualPortTypeToString(virtPort->virtPortType)); + + switch (virtPort->virtPortType) { + case VIR_VIRTUALPORT_NONE: + case VIR_VIRTUALPORT_TYPE_LAST: + break; + + case VIR_VIRTUALPORT_8021QBG: + virUUIDFormat(virtPort->u.virtPort8021Qbg.instanceID, + uuidstr); + virBufferVSprintf(buf, + "%s <parameters managerid='%d' typeid='%d' " + "typeidversion='%d' instanceid='%s'/>\n", + indent, + virtPort->u.virtPort8021Qbg.managerID, + virtPort->u.virtPort8021Qbg.typeID, + virtPort->u.virtPort8021Qbg.typeIDVersion, + uuidstr); + break; + + case VIR_VIRTUALPORT_8021QBH: + virBufferVSprintf(buf, + "%s <parameters profileid='%s'/>\n", + indent, + virtPort->u.virtPort8021Qbh.profileID); + break; + } + + virBufferVSprintf(buf, "%s</virtualport>\n", indent); +} + + /* Parse the XML definition for a network interface * @param node XML nodeset to parse for net definition * @return 0 on success, -1 on failure @@ -1832,6 +2021,8 @@ virDomainNetDefParseXML(virCapsPtr caps, char *devaddr = NULL; char *mode = NULL; virNWFilterHashTablePtr filterparams = NULL; + virVirtualPortProfileDef virtPort; + bool virtPortParsed = false; if (VIR_ALLOC(def) < 0) { virReportOOMError(); @@ -1873,6 +2064,12 @@ virDomainNetDefParseXML(virCapsPtr caps, xmlStrEqual(cur->name, BAD_CAST "source")) { dev = virXMLPropString(cur, "dev"); mode = virXMLPropString(cur, "mode"); + } else if ((virtPortParsed == false) && + (def->type == VIR_DOMAIN_NET_TYPE_DIRECT) && + xmlStrEqual(cur->name, BAD_CAST "virtualport")) { + if (virVirtualPortProfileDefParseXML(cur, &virtPort)) + goto error; + virtPortParsed = true; } else if ((network == NULL) && ((def->type == VIR_DOMAIN_NET_TYPE_SERVER) || (def->type == VIR_DOMAIN_NET_TYPE_CLIENT) || @@ -2048,6 +2245,9 @@ virDomainNetDefParseXML(virCapsPtr caps, } else def->data.direct.mode = VIR_DOMAIN_NETDEV_MACVTAP_MODE_VEPA; + if (virtPortParsed) + def->data.direct.virtPortProfile = virtPort; + def->data.direct.linkdev = dev; dev = NULL; @@ -5140,6 +5340,8 @@ virDomainNetDefFormat(virBufferPtr buf, virBufferVSprintf(buf, " mode='%s'", virDomainNetdevMacvtapTypeToString(def->data.direct.mode)); virBufferAddLit(buf, "/>\n"); + virVirtualPortProfileFormat(buf, &def->data.direct.virtPortProfile, + " "); break; case VIR_DOMAIN_NET_TYPE_USER: Index: libvirt-acl/src/conf/domain_conf.h =================================================================== --- libvirt-acl.orig/src/conf/domain_conf.h +++ libvirt-acl/src/conf/domain_conf.h @@ -259,6 +259,39 @@ enum virDomainNetdevMacvtapType { }; +enum virVirtualPortType { + VIR_VIRTUALPORT_NONE, + VIR_VIRTUALPORT_8021QBG, + VIR_VIRTUALPORT_8021QBH, + + VIR_VIRTUALPORT_TYPE_LAST, +}; + +# ifdef IFLA_VF_PORT_PROFILE_MAX +# define LIBVIRT_IFLA_VF_PORT_PROFILE_MAX IFLA_VF_PORT_PROFILE_MAX +# else +# define LIBVIRT_IFLA_VF_PORT_PROFILE_MAX 40 +# endif + +/* profile data for macvtap (VEPA) */ +typedef struct _virVirtualPortProfileDef virVirtualPortProfileDef; +typedef virVirtualPortProfileDef *virVirtualPortProfileDefPtr; +struct _virVirtualPortProfileDef { + enum virVirtualPortType virtPortType; + union { + struct { + uint8_t managerID; + uint32_t typeID; // 24 bit valid + uint8_t typeIDVersion; + unsigned char instanceID[VIR_UUID_BUFLEN]; + } virtPort8021Qbg; + struct { + char profileID[LIBVIRT_IFLA_VF_PORT_PROFILE_MAX]; + } virtPort8021Qbh; + } u; +}; + + /* Stores the virtual network interface configuration */ typedef struct _virDomainNetDef virDomainNetDef; typedef virDomainNetDef *virDomainNetDefPtr; @@ -290,6 +323,7 @@ struct _virDomainNetDef { struct { char *linkdev; int mode; + virVirtualPortProfileDef virtPortProfile; } direct; } data; char *ifname; @@ -1089,6 +1123,7 @@ VIR_ENUM_DECL(virDomainSeclabel) VIR_ENUM_DECL(virDomainClockOffset) VIR_ENUM_DECL(virDomainNetdevMacvtap) +VIR_ENUM_DECL(virVirtualPort) VIR_ENUM_DECL(virDomainTimerName) VIR_ENUM_DECL(virDomainTimerTrack) Index: libvirt-acl/src/util/macvtap.c =================================================================== --- libvirt-acl.orig/src/util/macvtap.c +++ libvirt-acl/src/util/macvtap.c @@ -43,6 +43,7 @@ # include "util.h" # include "memory.h" +# include "logging.h" # include "macvtap.h" # include "interface.h" # include "conf/domain_conf.h" @@ -57,6 +58,16 @@ # define MACVTAP_NAME_PREFIX "macvtap" # define MACVTAP_NAME_PATTERN "macvtap%d" + +static int associatePortProfileId(const char *macvtap_ifname, + const virVirtualPortProfileDefPtr virtPort, + int vf, + const unsigned char *vmuuid); + +static int disassociatePortProfileId(const char *macvtap_ifname, + const virVirtualPortProfileDefPtr virtPort); + + static int nlOpen(void) { int fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); @@ -567,39 +578,36 @@ configMacvtapTap(int tapfd, int vnet_hdr return 0; } - - /** * openMacvtapTap: * Create an instance of a macvtap device and open its tap character * device. - * @tgifname: Interface name that the macvtap is supposed to have. May - * be NULL if this function is supposed to choose a name - * @macaddress: The MAC address for the macvtap device - * @linkdev: The interface name of the NIC to connect to the external bridge - * @mode_str: String describing the mode. Valid are 'bridge', 'vepa' and - * 'private'. + * @net: pointer to the virDomainNetDef object describing the direct + * type if an interface * @res_ifname: Pointer to a string pointer where the actual name of the * interface will be stored into if everything succeeded. It is up * to the caller to free the string. + * @vnet_hdr: Whether to enable IFF_VNET_HDR on the interface + * @vmuuid: The (raw) UUID of the VM * * Returns file descriptor of the tap device in case of success, * negative value otherwise with error reported. * + * Open a macvtap device and trigger the switch setup protocol + * if valid port profile parameters were provided. */ int -openMacvtapTap(const char *tgifname, - const unsigned char *macaddress, - const char *linkdev, - int mode, +openMacvtapTap(virDomainNetDefPtr net, char **res_ifname, - int vnet_hdr) + int vnet_hdr, + const unsigned char *vmuuid) { const char *type = "macvtap"; + const char *tgifname = net->ifname; int c, rc; char ifname[IFNAMSIZ]; int retries, do_retry = 0; - uint32_t macvtapMode = macvtapModeFromInt(mode); + uint32_t macvtapMode = macvtapModeFromInt(net->data.direct.mode); const char *cr_ifname; int ifindex; @@ -616,7 +624,7 @@ openMacvtapTap(const char *tgifname, return -1; } cr_ifname = tgifname; - rc = link_add(type, macaddress, 6, tgifname, linkdev, + rc = link_add(type, net->mac, 6, tgifname, net->data.direct.linkdev, macvtapMode, &do_retry); if (rc) return -1; @@ -626,7 +634,8 @@ create_name: for (c = 0; c < 8192; c++) { snprintf(ifname, sizeof(ifname), MACVTAP_NAME_PATTERN, c); if (ifaceGetIndex(false, ifname, &ifindex) == ENODEV) { - rc = link_add(type, macaddress, 6, ifname, linkdev, + rc = link_add(type, net->mac, 6, ifname, + net->data.direct.linkdev, macvtapMode, &do_retry); if (rc == 0) break; @@ -639,6 +648,14 @@ create_name: cr_ifname = ifname; } + if (associatePortProfileId(cr_ifname, + &net->data.direct.virtPortProfile, + -1, + vmuuid) != 0) { + rc = -1; + goto link_del_exit; + } + rc = ifaceUp(cr_ifname); if (rc != 0) { virReportSystemError(errno, @@ -647,7 +664,7 @@ create_name: "MAC address"), cr_ifname); rc = -1; - goto link_del_exit; + goto disassociate_exit; } rc = openTap(cr_ifname, 10); @@ -656,14 +673,18 @@ create_name: if (configMacvtapTap(rc, vnet_hdr) < 0) { close(rc); rc = -1; - goto link_del_exit; + goto disassociate_exit; } *res_ifname = strdup(cr_ifname); } else - goto link_del_exit; + goto disassociate_exit; return rc; +disassociate_exit: + disassociatePortProfileId(cr_ifname, + &net->data.direct.virtPortProfile); + link_del_exit: link_del(cr_ifname); @@ -673,14 +694,102 @@ link_del_exit: /** * delMacvtap: - * @ifname : The name of the macvtap interface + * @net: pointer to virDomainNetDef object * - * Delete an interface given its name. + * Delete an interface given its name. Disassociate + * it with the switch if port profile parameters + * were provided. */ void -delMacvtap(const char *ifname) +delMacvtap(virDomainNetDefPtr net) { - link_del(ifname); + if (net->ifname) { + disassociatePortProfileId(net->ifname, + &net->data.direct.virtPortProfile); + link_del(net->ifname); + } } #endif + + +/** + * associatePortProfile + * + * @macvtap_ifname: The name of the macvtap device + * @virtPort: pointer to the object holding port profile parameters + * @vf: virtual function number, -1 if to be ignored + * @vmuuid : the UUID of the virtual machine + * + * Associate a port on a swtich with a profile. This function + * may notify a kernel driver or an external daemon to run + * the setup protocol. If profile parameters were not supplied + * by the user, then this function returns without doing + * anything. + * + * Returns 0 in case of success, != 0 otherwise with error + * having been reported. + */ +static int +associatePortProfileId(const char *macvtap_ifname, + const virVirtualPortProfileDefPtr virtPort, + int vf, + const unsigned char *vmuuid) +{ + int rc = 0; + VIR_DEBUG("Associating port profile '%p' on link device '%s'", + virtPort, macvtap_ifname); + (void)vf; + (void)vmuuid; + + switch (virtPort->virtPortType) { + case VIR_VIRTUALPORT_NONE: + case VIR_VIRTUALPORT_TYPE_LAST: + break; + + case VIR_VIRTUALPORT_8021QBG: + + break; + + case VIR_VIRTUALPORT_8021QBH: + + break; + } + + return rc; +} + + +/** + * disassociatePortProfile + * + * @macvtap_ifname: The name of the macvtap device + * @virtPort: point to object holding port profile parameters + * + * Returns 0 in case of success, != 0 otherwise with error + * having been reported. + */ +static int +disassociatePortProfileId(const char *macvtap_ifname, + const virVirtualPortProfileDefPtr virtPort) +{ + int rc = 0; + VIR_DEBUG("Disassociating port profile id '%p' on link device '%s' ", + virtPort, macvtap_ifname); + + switch (virtPort->virtPortType) { + case VIR_VIRTUALPORT_NONE: + case VIR_VIRTUALPORT_TYPE_LAST: + break; + + case VIR_VIRTUALPORT_8021QBG: + + break; + + case VIR_VIRTUALPORT_8021QBH: + + break; + } + + return rc; +} Index: libvirt-acl/src/util/macvtap.h =================================================================== --- libvirt-acl.orig/src/util/macvtap.h +++ libvirt-acl/src/util/macvtap.h @@ -27,15 +27,14 @@ # if defined(WITH_MACVTAP) # include "internal.h" +# include "conf/domain_conf.h" -int openMacvtapTap(const char *ifname, - const unsigned char *macaddress, - const char *linkdev, - int mode, +int openMacvtapTap(virDomainNetDefPtr net, char **res_ifname, - int vnet_hdr); + int vnet_hdr, + const unsigned char *vmuuid); -void delMacvtap(const char *ifname); +void delMacvtap(virDomainNetDefPtr net); # endif /* WITH_MACVTAP */ Index: libvirt-acl/tests/domainschemadata/portprofile.xml =================================================================== --- /dev/null +++ libvirt-acl/tests/domainschemadata/portprofile.xml @@ -0,0 +1,36 @@ +<domain type='lxc'> + <name>portprofile</name> + <uuid>00000000-0000-0000-0000-000000000000</uuid> + <memory>1048576</memory> + <os> + <type>exe</type> + <init>/sh</init> + </os> + <devices> + <interface type='direct'> + <source dev='eth0' mode='vepa'/> + <virtualport type='802.1Qbg'> + <parameters managerid='12' typeid='1193046' typeidversion='1' + instanceid='fa9b7fff-b0a0-4893-8e0e-beef4ff18f8f'/> + </virtualport> + </interface> + <interface type='direct'> + <source dev='eth0' mode='vepa'/> + <virtualport type='802.1Qbg'> + <parameters managerid='12' typeid='1193046' typeidversion='1'/> + </virtualport> + </interface> + <interface type='direct'> + <source dev='eth0' mode='vepa'/> + <virtualport type='802.1Qbh'> + <parameters profileid='my_profile'/> + </virtualport> + </interface> + <interface type='direct'> + <source dev='eth0' mode='vepa'/> + </interface> + <interface type='direct'> + <source dev='eth0' mode='vepa'/> + </interface> + </devices> +</domain> Index: libvirt-acl/src/qemu/qemu_conf.h =================================================================== --- libvirt-acl.orig/src/qemu/qemu_conf.h +++ libvirt-acl/src/qemu/qemu_conf.h @@ -274,9 +274,8 @@ qemudOpenVhostNet(virDomainNetDefPtr net int qemudPhysIfaceConnect(virConnectPtr conn, struct qemud_driver *driver, virDomainNetDefPtr net, - char *linkdev, - int brmode, - unsigned long long qemuCmdFlags); + unsigned long long qemuCmdFlags, + const unsigned char *vmuuid); int qemudProbeMachineTypes (const char *binary, virCapsGuestMachinePtr **machines, Index: libvirt-acl/src/qemu/qemu_driver.c =================================================================== --- libvirt-acl.orig/src/qemu/qemu_driver.c +++ libvirt-acl/src/qemu/qemu_driver.c @@ -3702,10 +3702,8 @@ static void qemudShutdownVMDaemon(struct def = vm->def; for (i = 0; i < def->nnets; i++) { virDomainNetDefPtr net = def->nets[i]; - if (net->type == VIR_DOMAIN_NET_TYPE_DIRECT) { - if (net->ifname) - delMacvtap(net->ifname); - } + if (net->type == VIR_DOMAIN_NET_TYPE_DIRECT) + delMacvtap(net); } #endif @@ -7464,9 +7462,8 @@ static int qemudDomainAttachNetDevice(vi } if ((tapfd = qemudPhysIfaceConnect(conn, driver, net, - net->data.direct.linkdev, - net->data.direct.mode, - qemuCmdFlags)) < 0) + qemuCmdFlags, + vm->def->uuid)) < 0) return -1; } @@ -8509,10 +8506,8 @@ qemudDomainDetachNetDevice(struct qemud_ virNWFilterTearNWFilter(detach); #if WITH_MACVTAP - if (detach->type == VIR_DOMAIN_NET_TYPE_DIRECT) { - if (detach->ifname) - delMacvtap(detach->ifname); - } + if (detach->type == VIR_DOMAIN_NET_TYPE_DIRECT) + delMacvtap(detach); #endif if ((driver->macFilter) && (detach->ifname != NULL)) { Index: libvirt-acl/src/qemu/qemu_conf.c =================================================================== --- libvirt-acl.orig/src/qemu/qemu_conf.c +++ libvirt-acl/src/qemu/qemu_conf.c @@ -1470,9 +1470,8 @@ int qemudPhysIfaceConnect(virConnectPtr conn, struct qemud_driver *driver, virDomainNetDefPtr net, - char *linkdev, - int brmode, - unsigned long long qemuCmdFlags) + unsigned long long qemuCmdFlags, + const unsigned char *vmuuid) { int rc; #if WITH_MACVTAP @@ -1484,8 +1483,7 @@ qemudPhysIfaceConnect(virConnectPtr conn net->model && STREQ(net->model, "virtio")) vnet_hdr = 1; - rc = openMacvtapTap(net->ifname, net->mac, linkdev, brmode, - &res_ifname, vnet_hdr); + rc = openMacvtapTap(net, &res_ifname, vnet_hdr, vmuuid); if (rc >= 0) { VIR_FREE(net->ifname); net->ifname = res_ifname; @@ -1505,17 +1503,16 @@ qemudPhysIfaceConnect(virConnectPtr conn if (err) { close(rc); rc = -1; - delMacvtap(net->ifname); + delMacvtap(net); } } } #else (void)conn; (void)net; - (void)linkdev; - (void)brmode; (void)qemuCmdFlags; (void)driver; + (void)vmuuid; qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", _("No support for macvtap device")); rc = -1; @@ -4135,9 +4132,8 @@ int qemudBuildCommandLine(virConnectPtr goto no_memory; } else if (net->type == VIR_DOMAIN_NET_TYPE_DIRECT) { int tapfd = qemudPhysIfaceConnect(conn, driver, net, - net->data.direct.linkdev, - net->data.direct.mode, - qemuCmdFlags); + qemuCmdFlags, + def->uuid); if (tapfd < 0) goto error;

6 8

[libvirt] [PATCH] Query block allocation extent from QEMU monitor
by Daniel P. Berrange 25 May '10

25 May '10

The virDomainGetBlockInfo API allows query physical block extent and allocated block extent. These are normally the same value unless storing a special format like qcow2 inside a block device. In this scenario we can query QEMU to get the actual allocated extent. Since last time: - Return fatal error in text monitor - Only invoke monitor command for block devices - Fix error handling JSON code * src/qemu/qemu_driver.c: Fill in block aloction extent when VM is running * src/qemu/qemu_monitor.c, src/qemu/qemu_monitor.h, src/qemu/qemu_monitor_json.c, src/qemu/qemu_monitor_json.h, src/qemu/qemu_monitor_text.c, src/qemu/qemu_monitor_text.h: Add API to query the highest block extent via info blockstats --- src/qemu/qemu_driver.c | 33 ++++++++++++--- src/qemu/qemu_monitor.c | 16 +++++++ src/qemu/qemu_monitor.h | 4 ++ src/qemu/qemu_monitor_json.c | 94 ++++++++++++++++++++++++++++++++++++++++++ src/qemu/qemu_monitor_json.h | 3 + src/qemu/qemu_monitor_text.c | 10 ++++ src/qemu/qemu_monitor_text.h | 4 +- 7 files changed, 156 insertions(+), 8 deletions(-) diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 4ef2f57..356c4be 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -9651,6 +9651,7 @@ static int qemuDomainGetBlockInfo(virDomainPtr dom, int fd = -1; off_t end; virStorageFileMetadata meta; + virDomainDiskDefPtr disk = NULL; struct stat sb; int i; @@ -9677,19 +9678,17 @@ static int qemuDomainGetBlockInfo(virDomainPtr dom, for (i = 0 ; i < vm->def->ndisks ; i++) { if (vm->def->disks[i]->src != NULL && STREQ (vm->def->disks[i]->src, path)) { - ret = 0; + disk = vm->def->disks[i]; break; } } - if (ret != 0) { + if (!disk) { qemuReportError(VIR_ERR_INVALID_ARG, _("invalid path %s not assigned to domain"), path); goto cleanup; } - ret = -1; - /* The path is correct, now try to open it and get its size. */ fd = open (path, O_RDONLY); if (fd == -1) { @@ -9740,11 +9739,31 @@ static int qemuDomainGetBlockInfo(virDomainPtr dom, if (meta.capacity) info->capacity = meta.capacity; - /* XXX allocation will need to be pulled from QEMU for - * the qcow inside LVM case */ + /* Set default value .. */ info->allocation = info->physical; - ret = 0; + /* ..but if guest is running & not using raw + disk format and on a block device, then query + highest allocated extent from QEMU */ + if (virDomainObjIsActive(vm) && + disk->type == VIR_DOMAIN_DISK_TYPE_BLOCK && + meta.format != VIR_STORAGE_FILE_RAW && + S_ISBLK(sb.st_mode)) { + qemuDomainObjPrivatePtr priv = vm->privateData; + if (qemuDomainObjBeginJob(vm) < 0) + goto cleanup; + + qemuDomainObjEnterMonitor(vm); + ret = qemuMonitorGetBlockExtent(priv->mon, + disk->info.alias, + &info->allocation); + qemuDomainObjExitMonitor(vm); + + if (qemuDomainObjEndJob(vm) == 0) + vm = NULL; + } else { + ret = 0; + } cleanup: if (fd != -1) diff --git a/src/qemu/qemu_monitor.c b/src/qemu/qemu_monitor.c index 582225e..efaf74a 100644 --- a/src/qemu/qemu_monitor.c +++ b/src/qemu/qemu_monitor.c @@ -1009,6 +1009,22 @@ int qemuMonitorGetBlockStatsInfo(qemuMonitorPtr mon, return ret; } +int qemuMonitorGetBlockExtent(qemuMonitorPtr mon, + const char *devname, + unsigned long long *extent) +{ + int ret; + DEBUG("mon=%p, fd=%d, devname=%p", + mon, mon->fd, devname); + + if (mon->json) + ret = qemuMonitorJSONGetBlockExtent(mon, devname, extent); + else + ret = qemuMonitorTextGetBlockExtent(mon, devname, extent); + + return ret; +} + int qemuMonitorSetVNCPassword(qemuMonitorPtr mon, const char *password) diff --git a/src/qemu/qemu_monitor.h b/src/qemu/qemu_monitor.h index 7b1589e..adfb3bc 100644 --- a/src/qemu/qemu_monitor.h +++ b/src/qemu/qemu_monitor.h @@ -185,6 +185,10 @@ int qemuMonitorGetBlockStatsInfo(qemuMonitorPtr mon, long long *wr_bytes, long long *errs); +int qemuMonitorGetBlockExtent(qemuMonitorPtr mon, + const char *devname, + unsigned long long *extent); + int qemuMonitorSetVNCPassword(qemuMonitorPtr mon, const char *password); diff --git a/src/qemu/qemu_monitor_json.c b/src/qemu/qemu_monitor_json.c index 6d8f328..31a66f1 100644 --- a/src/qemu/qemu_monitor_json.c +++ b/src/qemu/qemu_monitor_json.c @@ -1186,6 +1186,100 @@ cleanup: } +int qemuMonitorJSONGetBlockExtent(qemuMonitorPtr mon, + const char *devname, + unsigned long long *extent) +{ + int ret = -1; + int i; + int found = 0; + virJSONValuePtr cmd = qemuMonitorJSONMakeCommand("query-blockstats", + NULL); + virJSONValuePtr reply = NULL; + virJSONValuePtr devices; + + *extent = 0; + + if (!cmd) + return -1; + + if (qemuMonitorJSONCommand(mon, cmd, &reply) < 0) + goto cleanup; + + if (qemuMonitorJSONCheckError(cmd, reply) < 0) + goto cleanup; + + devices = virJSONValueObjectGet(reply, "return"); + if (!devices || devices->type != VIR_JSON_TYPE_ARRAY) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("blockstats reply was missing device list")); + goto cleanup; + } + + for (i = 0 ; i < virJSONValueArraySize(devices) ; i++) { + virJSONValuePtr dev = virJSONValueArrayGet(devices, i); + virJSONValuePtr stats; + virJSONValuePtr parent; + const char *thisdev; + if (!dev || dev->type != VIR_JSON_TYPE_OBJECT) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("blockstats device entry was not in expected format")); + goto cleanup; + } + + if ((thisdev = virJSONValueObjectGetString(dev, "device")) == NULL) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("blockstats device entry was not in expected format")); + goto cleanup; + } + + /* New QEMU has separate names for host & guest side of the disk + * and libvirt gives the host side a 'drive-' prefix. The passed + * in devname is the guest side though + */ + if (STRPREFIX(thisdev, QEMU_DRIVE_HOST_PREFIX)) + thisdev += strlen(QEMU_DRIVE_HOST_PREFIX); + + if (STRNEQ(thisdev, devname)) + continue; + + found = 1; + if ((parent = virJSONValueObjectGet(dev, "parent")) == NULL || + parent->type != VIR_JSON_TYPE_OBJECT) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("blockstats parent entry was not in expected format")); + goto cleanup; + } + + if ((stats = virJSONValueObjectGet(parent, "stats")) == NULL || + stats->type != VIR_JSON_TYPE_OBJECT) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("blockstats stats entry was not in expected format")); + goto cleanup; + } + + if (virJSONValueObjectGetNumberUlong(stats, "wr_highest_offset", extent) < 0) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, + _("cannot read %s statistic"), + "wr_highest_offset"); + goto cleanup; + } + } + + if (!found) { + qemuReportError(VIR_ERR_INTERNAL_ERROR, + _("cannot find statistics for device '%s'"), devname); + goto cleanup; + } + ret = 0; + +cleanup: + virJSONValueFree(cmd); + virJSONValueFree(reply); + return ret; +} + + int qemuMonitorJSONSetVNCPassword(qemuMonitorPtr mon, const char *password) { diff --git a/src/qemu/qemu_monitor_json.h b/src/qemu/qemu_monitor_json.h index 26fc865..14597f4 100644 --- a/src/qemu/qemu_monitor_json.h +++ b/src/qemu/qemu_monitor_json.h @@ -56,6 +56,9 @@ int qemuMonitorJSONGetBlockStatsInfo(qemuMonitorPtr mon, long long *wr_req, long long *wr_bytes, long long *errs); +int qemuMonitorJSONGetBlockExtent(qemuMonitorPtr mon, + const char *devname, + unsigned long long *extent); int qemuMonitorJSONSetVNCPassword(qemuMonitorPtr mon, diff --git a/src/qemu/qemu_monitor_text.c b/src/qemu/qemu_monitor_text.c index d725d6d..72e3fd5 100644 --- a/src/qemu/qemu_monitor_text.c +++ b/src/qemu/qemu_monitor_text.c @@ -711,6 +711,16 @@ int qemuMonitorTextGetBlockStatsInfo(qemuMonitorPtr mon, } +int qemuMonitorTextGetBlockExtent(qemuMonitorPtr mon ATTRIBUTE_UNUSED, + const char *devname ATTRIBUTE_UNUSED, + unsigned long long *extent ATTRIBUTE_UNUSED) +{ + qemuReportError(VIR_ERR_INTERNAL_ERROR, "%s", + _("unable to query block extent with this QEMU")); + return -1; +} + + static int qemuMonitorSendVNCPassphrase(qemuMonitorPtr mon ATTRIBUTE_UNUSED, qemuMonitorMessagePtr msg, diff --git a/src/qemu/qemu_monitor_text.h b/src/qemu/qemu_monitor_text.h index 2a62c7e..6fb7d7a 100644 --- a/src/qemu/qemu_monitor_text.h +++ b/src/qemu/qemu_monitor_text.h @@ -55,7 +55,9 @@ int qemuMonitorTextGetBlockStatsInfo(qemuMonitorPtr mon, long long *wr_req, long long *wr_bytes, long long *errs); - +int qemuMonitorTextGetBlockExtent(qemuMonitorPtr mon, + const char *devname, + unsigned long long *extent); int qemuMonitorTextSetVNCPassword(qemuMonitorPtr mon, const char *password); -- 1.6.6.1

3 6

[libvirt] [PATCH] lxcSetSchedulerParameters: reverse order of tests; improve a diagnostic
by Jim Meyering 25 May '10

25 May '10

Investigating something else in the vicinity, I noticed that the ordering of tests was backwards. Here's the fix for that. Also, looking at the following code, I saw that failure of virCgroupSetCpuShares could evoke no diagnostic. Now it does. >From bc3404d9f12c42cf883a43395fee6fc14c952b2c Mon Sep 17 00:00:00 2001 From: Jim Meyering <meyering(a)redhat.com> Date: Tue, 11 May 2010 15:43:32 +0200 Subject: [PATCH] lxcSetSchedulerParameters: reverse order of tests; diagnose a failure * src/lxc/lxc_driver.c (lxcSetSchedulerParameters): Ensure that "->field" is "cpu_shares" before possibly giving a diagnostic about a type for a "cpu_shares" value. Also, virCgroupSetCpuShares could fail without evoking a diagnostic. Add one. --- src/lxc/lxc_driver.c | 19 ++++++++++++------- 1 files changed, 12 insertions(+), 7 deletions(-) diff --git a/src/lxc/lxc_driver.c b/src/lxc/lxc_driver.c index fc0df37..5636eee 100644 --- a/src/lxc/lxc_driver.c +++ b/src/lxc/lxc_driver.c @@ -2054,18 +2054,23 @@ static int lxcSetSchedulerParameters(virDomainPtr domain, for (i = 0; i < nparams; i++) { virSchedParameterPtr param = &params[i]; + + if (STRNEQ(param->field, "cpu_shares")) { + lxcError(VIR_ERR_INVALID_ARG, + _("Invalid parameter `%s'"), param->field); + goto cleanup; + } + if (param->type != VIR_DOMAIN_SCHED_FIELD_ULLONG) { lxcError(VIR_ERR_INVALID_ARG, "%s", - _("Invalid type for cpu_shares tunable, expected a 'ullong'")); + _("Invalid type for cpu_shares tunable, expected a 'ullong'")); goto cleanup; } - if (STREQ(param->field, "cpu_shares")) { - if (virCgroupSetCpuShares(group, params[i].value.ul) != 0) - goto cleanup; - } else { - lxcError(VIR_ERR_INVALID_ARG, - _("Invalid parameter `%s'"), param->field); + int rc = virCgroupSetCpuShares(group, params[i].value.ul); + if (rc != 0) { + virReportSystemError(-rc, _("failed to set cpu_shares=%llu"), + params[i].value.ul); goto cleanup; } } -- 1.7.1.189.g07419

2 3

[libvirt] [v4 PATCH] add 802.1Qbh handling for port-profiles based on Stefan's previous patches
by Scott Feldman 25 May '10

25 May '10

From: Scott Feldman <scofeldm(a)cisco.com> This patch builds on the work recently posted by Stefan Berger. It builds on top of Stefan's three posted patches: [PATCH v9] vepa: parsing for 802.1Qb{g|h} XML [RFC][PATCH 1/3] vepa+vsi: Introduce dependency on libnl [PATCH v3] Add host UUID (to libvirt capabilities) Stefan's RFC patches 2/3 and 3/3 are incorporated into my patch. Changes from v3 to v4: - move from Stafan's 802.1Qb{g|h} XML v8 to v9 - move hostuuid and vf index calcs to inside doPortProfileOp8021Qbh Changes from v2 to v3: - remove debug fprintfs - use virGetHostUUID (thanks Stefan!) - fix compile issue when latest if_link.h isn't available - change poll timeout to 10s, at 1/8 intervals - if polling times out, log msg and return -ETIMEDOUT Changes from v1 to v2: - Add Stefan's code for getPortProfileStatus - Poll for up to 2 secs for port-profile status, at 1/8 sec intervals: - if status indicates error, abort openMacvtapTap - if status indicates success, exit polling - if status is "in-progress" after 2 secs of polling, exit polling loop silently, without error My patch finishes out the 802.1Qbh parts, which Stefan had mostly complete. I've tested using the recent kernel updates for VF_PORT netlink msgs and enic for Cisco's 10G Ethernet NIC. I tested many VMs, each with several direct interfaces, each configured with a port-profile per the XML. VM-to-VM, and VM-to-external work as expected. VM-to-VM on same host (using same NIC) works same as VM-to-VM where VMs are on diff hosts. I'm able to change settings on the port-profile while the VM is running to change the virtual port behaviour. For example, adjusting a QoS setting like rate limit. All VMs with interfaces using that port-profile immediatly see the effect of the change to the port-profile. I don't have a SR-IOV device to test so source dev is a non-SR-IOV device, but most of the code paths include support for specifing the source dev and VF index. We'll need to complete this by discovering the PF given the VF linkdev. Once we have the PF, we'll also have the VF index. All this info- mation is available from sysfs. Signed-off-by: Scott Feldman <scofeldm(a)cisco.com> --- configure.ac | 16 + src/qemu/qemu_conf.c | 2 src/qemu/qemu_driver.c | 4 src/util/macvtap.c | 778 +++++++++++++++++++++++++++++++++++++++++++++++- src/util/macvtap.h | 1 5 files changed, 785 insertions(+), 16 deletions(-) diff --git a/configure.ac b/configure.ac index 36ba703..885b0ae 100644 --- a/configure.ac +++ b/configure.ac @@ -2005,13 +2005,26 @@ if test "$with_macvtap" != "no" ; then fi AM_CONDITIONAL([WITH_MACVTAP], [test "$with_macvtap" = "yes"]) +AC_TRY_COMPILE([ #include <sys/socket.h> + #include <linux/rtnetlink.h> ], + [ int x = IFLA_PORT_MAX; ], + [ with_virtualport=yes ], + [ with_virtualport=no ]) +if test "$with_virtualport" = "yes"; then + val=1 +else + val=0 +fi +AC_DEFINE_UNQUOTED([WITH_VIRTUALPORT], $val, [whether vsi vepa support is enabled]) +AM_CONDITIONAL([WITH_VIRTUALPORT], [test "$with_virtualport" = "yes"]) + dnl netlink library LIBNL_CFLAGS="" LIBNL_LIBS="" -if test "$with_macvtap" = "yes"; then +if test "$with_macvtap" = "yes" || "$with_virtualport" = "yes"; then PKG_CHECK_MODULES([LIBNL], [libnl-1 >= $LIBNL_REQUIRED], [ ], [ AC_MSG_ERROR([libnl >= $LIBNL_REQUIRED is required for macvtap support]) @@ -2084,6 +2097,7 @@ AC_MSG_NOTICE([ Network: $with_network]) AC_MSG_NOTICE([Libvirtd: $with_libvirtd]) AC_MSG_NOTICE([ netcf: $with_netcf]) AC_MSG_NOTICE([ macvtap: $with_macvtap]) +AC_MSG_NOTICE([virtport: $with_virtualport]) AC_MSG_NOTICE([]) AC_MSG_NOTICE([Storage Drivers]) AC_MSG_NOTICE([]) diff --git a/src/qemu/qemu_conf.c b/src/qemu/qemu_conf.c index 111fa6e..95d4c1a 100644 --- a/src/qemu/qemu_conf.c +++ b/src/qemu/qemu_conf.c @@ -1505,7 +1505,7 @@ qemudPhysIfaceConnect(virConnectPtr conn, if (err) { close(rc); rc = -1; - delMacvtap(net->ifname, + delMacvtap(net->ifname, net->data.direct.linkdev, &net->data.direct.virtPortProfile); } } diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index f02bf3b..f1a0d0e 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -3679,7 +3679,7 @@ static void qemudShutdownVMDaemon(struct qemud_driver *driver, for (i = 0; i < def->nnets; i++) { virDomainNetDefPtr net = def->nets[i]; if (net->type == VIR_DOMAIN_NET_TYPE_DIRECT) - delMacvtap(net->ifname, + delMacvtap(net->ifname, net->data.direct.linkdev, &net->data.direct.virtPortProfile); } #endif @@ -8369,7 +8369,7 @@ qemudDomainDetachNetDevice(struct qemud_driver *driver, #if WITH_MACVTAP if (detach->type == VIR_DOMAIN_NET_TYPE_DIRECT) - delMacvtap(detach->ifname, + delMacvtap(detach->ifname, detach->data.direct.linkdev, &detach->data.direct.virtPortProfile); #endif diff --git a/src/util/macvtap.c b/src/util/macvtap.c index 5cbd02b..d5a08d9 100644 --- a/src/util/macvtap.c +++ b/src/util/macvtap.c @@ -27,7 +27,7 @@ #include <config.h> -#if WITH_MACVTAP +#if WITH_MACVTAP || WITH_VIRTUALPORT # include <stdio.h> # include <errno.h> @@ -41,6 +41,8 @@ # include <linux/rtnetlink.h> # include <linux/if_tun.h> +# include <netlink/msg.h> + # include "util.h" # include "memory.h" # include "logging.h" @@ -48,6 +50,7 @@ # include "interface.h" # include "conf/domain_conf.h" # include "virterror_internal.h" +# include "uuid.h" # define VIR_FROM_THIS VIR_FROM_NET @@ -58,15 +61,23 @@ # define MACVTAP_NAME_PREFIX "macvtap" # define MACVTAP_NAME_PATTERN "macvtap%d" +# define MICROSEC_PER_SEC (1000 * 1000) + static int associatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileDefPtr virtPort, - int vf, const unsigned char *vmuuid); static int disassociatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileDefPtr virtPort); +enum virVirtualPortOp { + ASSOCIATE = 0x1, + DISASSOCIATE = 0x2, +}; + static int nlOpen(void) { @@ -159,6 +170,156 @@ err_exit: } +# ifdef IFLA_VF_PORT_MAX + +/** + * nlCommWaitSuccess: + * + * @nlmsg: pointer to netlink message + * @nl_grousp: the netlink multicast groups to send to + * @respbuf: pointer to pointer where response buffer will be allocated + * @respbuflen: pointer to integer holding the size of the response buffer + * on return of the function. + * @to_usecs: timeout in microseconds to wait for a success message + * to be returned + * + * Send the given message to the netlink multicast group and receive + * responses. Skip responses indicating an error and keep on receiving + * responses until a success response is returned. + * Returns 0 on success, -1 on error. In case of error, no response + * buffer will be returned. + */ +static int +nlCommWaitSuccess(struct nlmsghdr *nlmsg, int nl_groups, + char **respbuf, int *respbuflen, long to_usecs) +{ + int rc = 0; + struct sockaddr_nl nladdr = { + .nl_family = AF_NETLINK, + .nl_pid = getpid(), + .nl_groups = nl_groups, + }; + int rcvChunkSize = 1024; // expecting less than that + int rcvoffset = 0; + ssize_t nbytes; + int n; + struct timeval tv = { + .tv_sec = to_usecs / MICROSEC_PER_SEC, + .tv_usec = to_usecs % MICROSEC_PER_SEC, + }; + fd_set rfds; + bool gotvalid = false; + int fd = nlOpen(); + static uint32_t seq = 0x1234; + uint32_t myseq = seq++; + uint32_t mypid = getpid(); + + if (fd < 0) + return -1; + + nlmsg->nlmsg_pid = mypid; + nlmsg->nlmsg_seq = myseq; + nlmsg->nlmsg_flags |= NLM_F_ACK; + + nbytes = sendto(fd, (void *)nlmsg, nlmsg->nlmsg_len, 0, + (struct sockaddr *)&nladdr, sizeof(nladdr)); + if (nbytes < 0) { + virReportSystemError(errno, + "%s", _("cannot send to netlink socket")); + rc = -1; + goto err_exit; + } + + while (!gotvalid) { + rcvoffset = 0; + while (1) { + socklen_t addrlen = sizeof(nladdr); + + if (VIR_REALLOC_N(*respbuf, rcvoffset+rcvChunkSize) < 0) { + virReportOOMError(); + rc = -1; + goto err_exit; + } + + FD_ZERO(&rfds); + FD_SET(fd, &rfds); + + n = select(fd + 1, &rfds, NULL, NULL, &tv); + if (n == 0) { + rc = -1; + goto err_exit; + } + + nbytes = recvfrom(fd, &((*respbuf)[rcvoffset]), rcvChunkSize, 0, + (struct sockaddr *)&nladdr, &addrlen); + if (nbytes < 0) { + if (errno == EAGAIN || errno == EINTR) + continue; + virReportSystemError(errno, "%s", + _("error receiving from netlink socket")); + rc = -1; + goto err_exit; + } + rcvoffset += nbytes; + break; + } + *respbuflen = rcvoffset; + + /* check message for error */ + if (*respbuflen > NLMSG_LENGTH(0) && *respbuf != NULL) { + struct nlmsghdr *resp = (struct nlmsghdr *)*respbuf; + struct nlmsgerr *err; + + if (resp->nlmsg_pid != mypid || + resp->nlmsg_seq != myseq) + continue; + + /* skip reflected message */ + if (resp->nlmsg_type & 0x10) + continue; + + switch (resp->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(resp); + if (resp->nlmsg_len >= NLMSG_LENGTH(sizeof(*err))) { + if (-err->error != EOPNOTSUPP) { + /* assuming error msg from daemon */ + gotvalid = true; + break; + } + } + /* whatever this is, skip it */ + VIR_FREE(*respbuf); + *respbuf = NULL; + *respbuflen = 0; + break; + + case NLMSG_DONE: + gotvalid = true; + break; + + default: + VIR_FREE(*respbuf); + *respbuf = NULL; + *respbuflen = 0; + break; + } + } + } + +err_exit: + if (rc == -1) { + VIR_FREE(*respbuf); + *respbuf = NULL; + *respbuflen = 0; + } + + nlClose(fd); + return rc; +} + +#endif + static struct rtattr * rtattrCreate(char *buffer, int bufsize, int type, const void *data, int datalen) @@ -204,6 +365,8 @@ nlAppend(struct nlmsghdr *nlm, int totlen, const void *data, int datalen) } +# if WITH_MACVTAP + static int link_add(const char *type, const unsigned char *macaddress, int macaddrsize, @@ -655,8 +818,8 @@ create_name: } if (associatePortProfileId(cr_ifname, + linkdev, virtPortProfile, - -1, vmuuid) != 0) { rc = -1; goto link_del_exit; @@ -689,6 +852,7 @@ create_name: disassociate_exit: disassociatePortProfileId(cr_ifname, + linkdev, virtPortProfile); link_del_exit: @@ -701,6 +865,7 @@ link_del_exit: /** * delMacvtap: * @ifname : The name of the macvtap interface + * @linkdev: The interface name of the NIC to connect to the external bridge * @virtPortProfile: pointer to object holding the virtual port profile data * * Delete an interface given its name. Disassociate @@ -709,24 +874,603 @@ link_del_exit: */ void delMacvtap(const char *ifname, + const char *linkdev, virVirtualPortProfileDefPtr virtPortProfile) { if (ifname) { disassociatePortProfileId(ifname, + linkdev, virtPortProfile); link_del(ifname); } } -#endif +# endif + + +# ifdef IFLA_PORT_MAX + +static struct nla_policy ifla_policy[IFLA_MAX + 1] = +{ + [IFLA_VF_PORTS] = { .type = NLA_NESTED }, +}; + +static struct nla_policy ifla_vf_ports_policy[IFLA_VF_PORT_MAX + 1] = +{ + [IFLA_VF_PORT] = { .type = NLA_NESTED }, +}; + +static struct nla_policy ifla_port_policy[IFLA_PORT_MAX + 1] = +{ + [IFLA_PORT_RESPONSE] = { .type = NLA_U16 }, +}; + + +static int +link_dump(int ifindex, struct nlattr **tb, char **recvbuf) +{ + int rc = 0; + char nlmsgbuf[256] = { 0, }; + struct nlmsghdr *nlm = (struct nlmsghdr *)nlmsgbuf, *resp; + struct nlmsgerr *err; + struct ifinfomsg i = { + .ifi_family = AF_UNSPEC, + .ifi_index = ifindex + }; + int recvbuflen; + + *recvbuf = NULL; + + nlInit(nlm, NLM_F_REQUEST, RTM_GETLINK); + + if (!nlAppend(nlm, sizeof(nlmsgbuf), &i, sizeof(i))) + goto buffer_too_small; + + if (nlComm(nlm, recvbuf, &recvbuflen) < 0) + return -1; + + if (recvbuflen < NLMSG_LENGTH(0) || *recvbuf == NULL) + goto malformed_resp; + resp = (struct nlmsghdr *)*recvbuf; + + switch (resp->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(resp); + if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err))) + goto malformed_resp; + + switch (-err->error) { + case 0: + break; + + default: + virReportSystemError(-err->error, + _("error dumping %d interface"), + ifindex); + rc = -1; + } + break; + + case GENL_ID_CTRL: + case NLMSG_DONE: + if (nlmsg_parse(resp, sizeof(struct ifinfomsg), + tb, IFLA_MAX, ifla_policy)) { + goto malformed_resp; + } + break; + + default: + goto malformed_resp; + } + + if (rc != 0) + VIR_FREE(*recvbuf); + + return rc; + +malformed_resp: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("malformed netlink response message")); + VIR_FREE(*recvbuf); + return -1; + +buffer_too_small: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("internal buffer is too small")); + return -1; +} + + +static int +getPortProfileStatus(struct nlattr **tb, int32_t vf, uint16_t *status) +{ + int rc = 1; + const char *msg = NULL; + struct nlattr *tb2[IFLA_VF_PORT_MAX + 1], + *tb3[IFLA_PORT_MAX+1]; + + if (vf == PORT_SELF_VF) { + if (tb[IFLA_PORT_SELF]) { + if (nla_parse_nested(tb3, IFLA_PORT_MAX, tb[IFLA_PORT_SELF], + ifla_port_policy)) { + msg = _("error parsing nested IFLA_VF_PORT part"); + goto err_exit; + } + } + } else { + if (tb[IFLA_VF_PORTS]) { + if (nla_parse_nested(tb2, IFLA_VF_PORT_MAX, tb[IFLA_VF_PORTS], + ifla_vf_ports_policy)) { + msg = _("error parsing nested IFLA_VF_PORTS part"); + goto err_exit; + } + if (tb2[IFLA_VF_PORT]) { + if (nla_parse_nested(tb3, IFLA_PORT_MAX, tb2[IFLA_VF_PORT], + ifla_port_policy)) { + msg = _("error parsing nested IFLA_VF_PORT part"); + goto err_exit; + } + } + } + } + + if (tb3[IFLA_PORT_RESPONSE]) { + *status = *(uint16_t *)RTA_DATA(tb3[IFLA_PORT_RESPONSE]); + rc = 0; + } else { + msg = _("no IFLA_PORT_RESPONSE found in netlink message"); + goto err_exit; + } + +err_exit: + if (msg) + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", msg); + + return rc; +} + + +static int +doPortProfileOpSetLink(bool multicast, + int ifindex, + const char *profileId, + struct ifla_port_vsi *portVsi, + const unsigned char *instanceId, + const unsigned char *hostUUID, + int32_t vf, + uint8_t op) +{ + int rc = 0; + char nlmsgbuf[256]; + struct nlmsghdr *nlm = (struct nlmsghdr *)nlmsgbuf, *resp; + struct nlmsgerr *err; + char rtattbuf[64]; + struct rtattr *rta, *vfports, *vfport; + struct ifinfomsg ifinfo = { + .ifi_family = AF_UNSPEC, + .ifi_index = ifindex, + }; + char *recvbuf = NULL; + int recvbuflen = 0; + + memset(&nlmsgbuf, 0, sizeof(nlmsgbuf)); + + nlInit(nlm, NLM_F_REQUEST, RTM_SETLINK); + + if (!nlAppend(nlm, sizeof(nlmsgbuf), &ifinfo, sizeof(ifinfo))) + goto buffer_too_small; + + if (vf == PORT_SELF_VF) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_SELF, NULL, 0); + } else { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_VF_PORTS, NULL, 0); + if (!rta) + goto buffer_too_small; + + if (!(vfports = nlAppend(nlm, sizeof(nlmsgbuf), + rtattbuf, rta->rta_len))) + goto buffer_too_small; + + /* beging nesting vfports */ + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_VF_PORT, NULL, 0); + } + + if (!rta) + goto buffer_too_small; + + if (!(vfport = nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len))) + goto buffer_too_small; + + if (profileId) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_PROFILE, + profileId, strlen(profileId) + 1); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (portVsi) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_VSI_TYPE, + portVsi, sizeof(*portVsi)); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (instanceId) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_INSTANCE_UUID, + instanceId, VIR_UUID_BUFLEN); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (hostUUID) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_HOST_UUID, + hostUUID, VIR_UUID_BUFLEN); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + if (vf != PORT_SELF_VF) { + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_VF, + &vf, sizeof(vf)); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + } + + rta = rtattrCreate(rtattbuf, sizeof(rtattbuf), IFLA_PORT_REQUEST, + &op, sizeof(op)); + if (!rta) + goto buffer_too_small; + + if (!nlAppend(nlm, sizeof(nlmsgbuf), rtattbuf, rta->rta_len)) + goto buffer_too_small; + + /* end nesting of vport */ + vfport->rta_len = (char *)nlm + nlm->nlmsg_len - (char *)vfport; + + if (vf != PORT_SELF_VF) { + /* end nesting of vfports */ + vfports->rta_len = (char *)nlm + nlm->nlmsg_len - (char *)vfports; + } + + if (!multicast) { + if (nlComm(nlm, &recvbuf, &recvbuflen) < 0) + return -1; + } else { + if (nlCommWaitSuccess(nlm, RTMGRP_LINK, &recvbuf, &recvbuflen, + 5 * MICROSEC_PER_SEC) < 0) + return -1; + } + + if (recvbuflen < NLMSG_LENGTH(0) || recvbuf == NULL) + goto malformed_resp; + + resp = (struct nlmsghdr *)recvbuf; + + switch (resp->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(resp); + if (resp->nlmsg_len < NLMSG_LENGTH(sizeof(*err))) + goto malformed_resp; + + switch (-err->error) { + case 0: + break; + + default: + virReportSystemError(-err->error, + _("error during virtual port configuration of ifindex %d"), + ifindex); + rc = -1; + } + break; + + case NLMSG_DONE: + break; + + default: + goto malformed_resp; + } + + VIR_FREE(recvbuf); + + return rc; + +malformed_resp: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("malformed netlink response message")); + VIR_FREE(recvbuf); + return -1; + +buffer_too_small: + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("internal buffer is too small")); + return -1; +} + + +static int +doPortProfileOpCommon(bool multicast, + int ifindex, + const char *profileId, + struct ifla_port_vsi *portVsi, + const unsigned char *instanceId, + const unsigned char *hostUUID, + int32_t vf, + uint8_t op) +{ + int rc; + char *recvbuf = NULL; + struct nlattr *tb[IFLA_MAX + 1]; + int repeats = 80; + uint16_t status = 0; + + rc = doPortProfileOpSetLink(multicast, + ifindex, + profileId, + portVsi, + instanceId, + hostUUID, + vf, + op); + + if (rc != 0) { + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("sending of PortProfileRequest failed.\n")); + return rc; + } + + if (!multicast) { + while (--repeats) { + rc = link_dump(ifindex, tb, &recvbuf); + if (rc) + goto err_exit; + rc = getPortProfileStatus(tb, vf, &status); + if (rc == 0) { + if (status == PORT_PROFILE_RESPONSE_SUCCESS || + status == PORT_VDP_RESPONSE_SUCCESS) { + break; + } else if (status == PORT_PROFILE_RESPONSE_INPROGRESS) { + // keep trying... + } else { + virReportSystemError(EINVAL, + _("error %d during port-profile setlink on ifindex %d"), + status, ifindex); + rc = 1; + break; + } + } + usleep(125000); + + VIR_FREE(recvbuf); + } + } + + if (status == PORT_PROFILE_RESPONSE_INPROGRESS) { + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("port-profile setlink timed out")); + rc = -ETIMEDOUT; + } + +err_exit: + VIR_FREE(recvbuf); + + return rc; +} + +# endif /* IFLA_PORT_MAX */ + +static int +doPortProfileOp8021Qbg(const char *ifname, + const virVirtualPortProfileDefPtr virtPort, + enum virVirtualPortOp virtPortOp) +{ + int rc; + +# ifndef IFLA_VF_PORT_MAX + + (void)ifname; + (void)virtPort; + (void)vf; + (void)virtPortOp; + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Kernel VF Port support was missing at compile time.")); + rc = 1; + +# else /* IFLA_VF_PORT_MAX */ + + int op = PORT_REQUEST_ASSOCIATE; + struct ifla_port_vsi portVsi = { + .vsi_mgr_id = virtPort->u.virtPort8021Qbg.managerID, + .vsi_type_version = virtPort->u.virtPort8021Qbg.typeIDVersion, + }; + bool multicast = true; + int ifindex; + + if (ifaceGetIndex(true, ifname, &ifindex) != 0) { + rc = 1; + goto err_exit; + } + + portVsi.vsi_type_id[2] = virtPort->u.virtPort8021Qbg.typeID >> 16; + portVsi.vsi_type_id[1] = virtPort->u.virtPort8021Qbg.typeID >> 8; + portVsi.vsi_type_id[0] = virtPort->u.virtPort8021Qbg.typeID; + + switch (virtPortOp) { + case ASSOCIATE: + op = PORT_REQUEST_ASSOCIATE; + break; + case DISASSOCIATE: + op = PORT_REQUEST_DISASSOCIATE; + break; + default: + macvtapError(VIR_ERR_INTERNAL_ERROR, + _("operation type %d not supported"), op); + rc = 1; + goto err_exit; + } + + rc = doPortProfileOpCommon(multicast, ifindex, + NULL, + &portVsi, + virtPort->u.virtPort8021Qbg.instanceID, + NULL, + PORT_SELF_VF, + op); + +err_exit: + +# endif /* IFLA_VF_PORT_MAX */ + + return rc; +} + + +static int +getPhysfn(const char *linkdev, + int32_t *vf, + char **physfndev) +{ + int rc = 0; + +# ifndef IFLA_VF_PORT_MAX + + (void)linkdev; + (void)vf; + (void)physfndev; + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Kernel VF Port support was missing at compile time.")); + rc = 1; + +# else /* IFLA_VF_PORT_MAX */ + + bool virtfn = false; + + if (virtfn) { + + // XXX: if linkdev is SR-IOV VF, then set vf = VF index + // XXX: and set linkdev = PF device + // XXX: need to use get_physical_function_linux() or + // XXX: something like that to get PF + // XXX: device and figure out VF index + + rc = 1; + + } else { + + /* Not SR-IOV VF: physfndev is linkdev and VF index + * refers to linkdev self + */ + + *vf = PORT_SELF_VF; + *physfndev = (char *)linkdev; + } + +# endif /* IFLA_VF_PORT_MAX */ + + return rc; +} + + +static int +doPortProfileOp8021Qbh(const char *ifname, + const virVirtualPortProfileDefPtr virtPort, + const unsigned char *vm_uuid, + enum virVirtualPortOp virtPortOp) +{ + int rc; + +# ifndef IFLA_VF_PORT_MAX + + (void)ifname; + (void)virtPort; + (void)vm_uuid; + (void)virtPortOp; + macvtapError(VIR_ERR_INTERNAL_ERROR, "%s", + _("Kernel VF Port support was missing at compile time.")); + rc = 1; + +# else /* IFLA_VF_PORT_MAX */ + + char *physfndev; + unsigned char hostuuid[VIR_UUID_BUFLEN]; + int32_t vf; + int op = PORT_REQUEST_ASSOCIATE; + bool multicast = false; + int ifindex; + + rc = virGetHostUUID(hostuuid); + if (rc) + goto err_exit; + + rc = getPhysfn(ifname, &vf, &physfndev); + if (rc) + goto err_exit; + + if (ifaceGetIndex(true, physfndev, &ifindex) != 0) { + rc = 1; + goto err_exit; + } + + switch (virtPortOp) { + case ASSOCIATE: + op = PORT_REQUEST_ASSOCIATE; + break; + case DISASSOCIATE: + op = PORT_REQUEST_DISASSOCIATE; + break; + default: + macvtapError(VIR_ERR_INTERNAL_ERROR, + _("operation type %d not supported"), op); + rc = 1; + goto err_exit; + } + + rc = doPortProfileOpCommon(multicast, ifindex, + virtPort->u.virtPort8021Qbh.profileID, + NULL, + vm_uuid, + hostuuid, + vf, + op); + + switch (virtPortOp) { + case ASSOCIATE: + ifaceUp(ifname); + break; + case DISASSOCIATE: + ifaceDown(ifname); + break; + } + +err_exit: + +# endif /* IFLA_VF_PORT_MAX */ + + return rc; +} /** * associatePortProfile * * @macvtap_ifname: The name of the macvtap device + * @linkdev: The link device in case of macvtap * @virtPort: pointer to the object holding port profile parameters - * @vf: virtual function number, -1 if to be ignored * @vmuuid : the UUID of the virtual machine * * Associate a port on a swtich with a profile. This function @@ -740,15 +1484,14 @@ delMacvtap(const char *ifname, */ static int associatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileDefPtr virtPort, - int vf, const unsigned char *vmuuid) { int rc = 0; + VIR_DEBUG("Associating port profile '%p' on link device '%s'", virtPort, macvtap_ifname); - (void)vf; - (void)vmuuid; switch (virtPort->virtPortType) { case VIR_VIRTUALPORT_NONE: @@ -756,11 +1499,14 @@ associatePortProfileId(const char *macvtap_ifname, break; case VIR_VIRTUALPORT_8021QBG: - + rc = doPortProfileOp8021Qbg(macvtap_ifname, virtPort, + ASSOCIATE); break; case VIR_VIRTUALPORT_8021QBH: - + rc = doPortProfileOp8021Qbh(linkdev, virtPort, + vmuuid, + ASSOCIATE); break; } @@ -772,6 +1518,7 @@ associatePortProfileId(const char *macvtap_ifname, * disassociatePortProfile * * @macvtap_ifname: The name of the macvtap device + * @linkdev: The link device in case of macvtap * @virtPort: point to object holding port profile parameters * * Returns 0 in case of success, != 0 otherwise with error @@ -779,9 +1526,11 @@ associatePortProfileId(const char *macvtap_ifname, */ static int disassociatePortProfileId(const char *macvtap_ifname, + const char *linkdev, const virVirtualPortProfileDefPtr virtPort) { int rc = 0; + VIR_DEBUG("Disassociating port profile id '%p' on link device '%s' ", virtPort, macvtap_ifname); @@ -791,13 +1540,18 @@ disassociatePortProfileId(const char *macvtap_ifname, break; case VIR_VIRTUALPORT_8021QBG: - + rc = doPortProfileOp8021Qbg(macvtap_ifname, virtPort, + DISASSOCIATE); break; case VIR_VIRTUALPORT_8021QBH: - + rc = doPortProfileOp8021Qbh(linkdev, virtPort, + NULL, + DISASSOCIATE); break; } return rc; } + +#endif diff --git a/src/util/macvtap.h b/src/util/macvtap.h index ae11c5c..35db31c 100644 --- a/src/util/macvtap.h +++ b/src/util/macvtap.h @@ -72,6 +72,7 @@ int openMacvtapTap(const char *ifname, char **res_ifname); void delMacvtap(const char *ifname, + const char *linkdev, virVirtualPortProfileDefPtr virtPortProfile); # endif /* WITH_MACVTAP */

2 1

[libvirt] [PATCH 0/2] Device assignment hotplug fixes
by Alex Williamson 25 May '10

25 May '10

These add a couple fixes for device assignment hotplug --- Alex Williamson (2): qemu: Release bus address on PCI host device remove qemu: avoid corrupting guest info struct on host device PCI hot add src/qemu/qemu_driver.c | 23 +++++++++++++++-------- 1 files changed, 15 insertions(+), 8 deletions(-)

3 5