- Devel - libvirt List Archives

[libvirt] [PATCH] Ensure client streams are closed when marking a client for close
by Daniel P. Berrange 15 Aug '11

15 Aug '11

From: "Daniel P. Berrange" <berrange(a)redhat.com> Every active stream results in a reference being held on the virNetServerClientPtr object. This meant that if a client quit with any streams active, although all I/O was stopped the virNetServerClientPtr object would leak. This causes libvirtd to leak any file handles associated with open streams when a client quit To fix this, when we call virNetServerClientClose there is a callback invoked which lets the daemon release the streams and thus the extra references * daemon/remote.c: Add a hook to close all streams * src/rpc/virnetserverclient.c, src/rpc/virnetserverclient.h: Allow registration of a hook to trigger when closing client --- daemon/remote.c | 13 ++++++++++--- src/rpc/virnetserverclient.c | 21 +++++++++++++++++++++ src/rpc/virnetserverclient.h | 5 +++++ 3 files changed, 36 insertions(+), 3 deletions(-) diff --git a/daemon/remote.c b/daemon/remote.c index ec261e2..0f088c6 100644 --- a/daemon/remote.c +++ b/daemon/remote.c @@ -419,8 +419,6 @@ static void remoteClientFreeFunc(void *data) { struct daemonClientPrivate *priv = data; - daemonRemoveAllClientStreams(priv->streams); - /* Deregister event delivery callback */ if (priv->conn) { int i; @@ -441,6 +439,13 @@ static void remoteClientFreeFunc(void *data) } +static void remoteClientCloseFunc(virNetServerClientPtr client) +{ + struct daemonClientPrivate *priv = virNetServerClientGetPrivateData(client); + + daemonRemoveAllClientStreams(priv->streams); +} + int remoteClientInitHook(virNetServerPtr srv ATTRIBUTE_UNUSED, virNetServerClientPtr client) @@ -462,7 +467,9 @@ int remoteClientInitHook(virNetServerPtr srv ATTRIBUTE_UNUSED, for (i = 0 ; i < VIR_DOMAIN_EVENT_ID_LAST ; i++) priv->domainEventCallbackID[i] = -1; - virNetServerClientSetPrivateData(client, priv, remoteClientFreeFunc); + virNetServerClientSetPrivateData(client, priv, + remoteClientFreeFunc); + virNetServerClientSetCloseHook(client, remoteClientCloseFunc); return 0; } diff --git a/src/rpc/virnetserverclient.c b/src/rpc/virnetserverclient.c index e246fa5..a73b06d 100644 --- a/src/rpc/virnetserverclient.c +++ b/src/rpc/virnetserverclient.c @@ -97,6 +97,7 @@ struct _virNetServerClient void *privateData; virNetServerClientFreeFunc privateDataFreeFunc; + virNetServerClientCloseFunc privateDataCloseFunc; }; @@ -492,6 +493,15 @@ void *virNetServerClientGetPrivateData(virNetServerClientPtr client) } +void virNetServerClientSetCloseHook(virNetServerClientPtr client, + virNetServerClientCloseFunc cf) +{ + virNetServerClientLock(client); + client->privateDataCloseFunc = cf; + virNetServerClientUnlock(client); +} + + void virNetServerClientSetDispatcher(virNetServerClientPtr client, virNetServerClientDispatchFunc func, void *opaque) @@ -560,6 +570,8 @@ void virNetServerClientFree(virNetServerClientPtr client) */ void virNetServerClientClose(virNetServerClientPtr client) { + virNetServerClientCloseFunc cf; + virNetServerClientLock(client); VIR_DEBUG("client=%p refs=%d", client, client->refs); if (!client->sock) { @@ -567,6 +579,15 @@ void virNetServerClientClose(virNetServerClientPtr client) return; } + if (client->privateDataCloseFunc) { + cf = client->privateDataCloseFunc; + client->refs++; + virNetServerClientUnlock(client); + (cf)(client); + virNetServerClientLock(client); + client->refs--; + } + /* Do now, even though we don't close the socket * until end, to ensure we don't get invoked * again due to tls shutdown */ diff --git a/src/rpc/virnetserverclient.h b/src/rpc/virnetserverclient.h index 3d2e1fb..bedb179 100644 --- a/src/rpc/virnetserverclient.h +++ b/src/rpc/virnetserverclient.h @@ -82,6 +82,11 @@ void virNetServerClientSetPrivateData(virNetServerClientPtr client, virNetServerClientFreeFunc ff); void *virNetServerClientGetPrivateData(virNetServerClientPtr client); +typedef void (*virNetServerClientCloseFunc)(virNetServerClientPtr client); + +void virNetServerClientSetCloseHook(virNetServerClientPtr client, + virNetServerClientCloseFunc cf); + void virNetServerClientSetDispatcher(virNetServerClientPtr client, virNetServerClientDispatchFunc func, void *opaque); -- 1.7.6

1 0

[libvirt] [PATCH] qemu: error message should show uri instead of (null)
by Peter Krempa 15 Aug '11

15 Aug '11

Fix pointer for error message uri if domain migration fails. BZ# 730244 --- src/qemu/qemu_migration.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/src/qemu/qemu_migration.c b/src/qemu/qemu_migration.c index 4d0e062..d900020 100644 --- a/src/qemu/qemu_migration.c +++ b/src/qemu/qemu_migration.c @@ -2079,7 +2079,7 @@ static int doPeer2PeerMigrate(struct qemud_driver *driver, qemuDomainObjExitRemoteWithDriver(driver, vm); if (dconn == NULL) { qemuReportError(VIR_ERR_OPERATION_FAILED, - _("Failed to connect to remote libvirt URI %s"), uri); + _("Failed to connect to remote libvirt URI %s"), dconnuri); return -1; } -- 1.7.3.4

5 4

[libvirt] [PATCH] libvirtd.init.in: stop/restart() - wrong return value in case of fail
by Douglas Schilling Landgraf 15 Aug '11

15 Aug '11

Currently the function stop() always return 0 (OK) from killproc() even in case of error. Signed-off-by: Douglas Schilling Landgraf <dougsland(a)redhat.com> --- daemon/libvirtd.init.in | 2 ++ 1 files changed, 2 insertions(+), 0 deletions(-) diff --git a/daemon/libvirtd.init.in b/daemon/libvirtd.init.in index aa7870c..0697a2b 100644 --- a/daemon/libvirtd.init.in +++ b/daemon/libvirtd.init.in @@ -76,6 +76,8 @@ stop() { rm -f @localstatedir@/lock/subsys/$SERVICE rm -f $PIDFILE rm -rf @localstatedir@/cache/libvirt/* + else + exit $RETVAL fi } -- 1.7.1

2 1

[libvirt] [PATCH] daemon: Fix regression of libvirtd reloading support
by Osier Yang 15 Aug '11

15 Aug '11

This is introduced by commit df0b57a95a, which forgot to add signal handler for SIGHUP. A simple reproduce method: 1) Create a domain XML under /etc/libvirt/qemu 2) % kill -SIGHUP $(pidof libvirtd) 3) % virsh list --all (the new created domain XML is not listed) --- daemon/libvirtd.c | 13 +++++++++++++ 1 files changed, 13 insertions(+), 0 deletions(-) diff --git a/daemon/libvirtd.c b/daemon/libvirtd.c index b866a01..3e0159b 100644 --- a/daemon/libvirtd.c +++ b/daemon/libvirtd.c @@ -1102,6 +1102,17 @@ static void daemonShutdownHandler(virNetServerPtr srv, virNetServerQuit(srv); } +static void daemonReloadHandler(virNetServerPtr srv ATTRIBUTE_UNUSED, + siginfo_t *sig ATTRIBUTE_UNUSED, + void *opaque ATTRIBUTE_UNUSED) +{ + VIR_INFO(_("Reloading configuration on SIGHUP")); + virHookCall(VIR_HOOK_DRIVER_DAEMON, "-", + VIR_HOOK_DAEMON_OP_RELOAD, SIGHUP, "SIGHUP", NULL); + if (virStateReload() < 0) + VIR_WARN("Error while reloading drivers"); +} + static int daemonSetupSignals(virNetServerPtr srv) { if (virNetServerAddSignalHandler(srv, SIGINT, daemonShutdownHandler, NULL) < 0) @@ -1110,6 +1121,8 @@ static int daemonSetupSignals(virNetServerPtr srv) return -1; if (virNetServerAddSignalHandler(srv, SIGTERM, daemonShutdownHandler, NULL) < 0) return -1; + if (virNetServerAddSignalHandler(srv, SIGHUP, daemonReloadHandler, NULL) < 0) + return -1; return 0; } -- 1.7.6

2 2

[libvirt] snapshots += domain description?
by Philipp Hahn 15 Aug '11

15 Aug '11

Hello, I just encountered a problem with the current snapshot implementation for qemu/kvm: To revert back to a snapshot, the domain description must closely match the domain description when the snapshot was created. If the ram-size doesn't match or the VM now contains fewer CPUs or contains additional disks, kvm will either not load the snapshot or the machine will be broken afterwarts. Is this a known problem? Without looking into the implementation details I think saving the full domain description instead of just a reference to the domain uuid as part of the snapshot description would work better. Or am I supposed to save the domain description myself in addition the the data saved in /var/lib/libvirt/qemu/snapshot/$DOMAIN_NAME/$SNAPSHOT_NAME.xml. I think this is very important feature, because when you - for example - notice that you need additional disk space and would like to include an additional block device, this is your ideal time to take a snapshot you can revert to when you do something wrong. Looking at VMware I see that reverting a VM there will not only revert the disks and ram back to the saved state, but also the description including name, ram size, etc. Any comment or advise is appreciated. Sincerely Philipp Hahn -- Philipp Hahn Open Source Software Engineer hahn(a)univention.de Univention GmbH Linux for Your Business fon: +49 421 22 232- 0 Mary-Somerville-Str.1 28359 Bremen fax: +49 421 22 232-99 http://www.univention.de

2 13

[libvirt] [PATCH] maint: let emacs avoid tabs in rng files
by Eric Blake 13 Aug '11

13 Aug '11

* .dir-locals.el: Add nxml-mode preferences. --- I'm getting tired of accidentally adding tabs when I touch .rng files, so I'm pushing this under the trivial rule. .dir-locals.el | 3 +++ 1 files changed, 3 insertions(+), 0 deletions(-) diff --git a/.dir-locals.el b/.dir-locals.el index d5eba86..c10603c 100644 --- a/.dir-locals.el +++ b/.dir-locals.el @@ -11,4 +11,7 @@ (sh-mode . ( (indent-tabs-mode . nil) )) + (nxml-mode . ( + (indent-tabs-mode . nil) + )) ) -- 1.7.4.4

1 0

[libvirt] [PATCH] doc: Document the Block Job API
by Adam Litke 13 Aug '11

13 Aug '11

Hi DV, This patch adds some basic documentation to the development guide for the Block Job APIs as you requested. Also included is a sample program that shows end-to-end use of the BlockPull operation. I hope this is close to what you had in mind. Signed-off-by: Adam Litke <agl(a)us.ibm.com> --- en-US/Guest_Domains.xml | 154 +++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 154 insertions(+), 0 deletions(-) diff --git a/en-US/Guest_Domains.xml b/en-US/Guest_Domains.xml index 0324e78..202881d 100644 --- a/en-US/Guest_Domains.xml +++ b/en-US/Guest_Domains.xml @@ -1219,6 +1219,160 @@ fprintf(stderr, "Device is suitable for passthrough to a guest\n"); </section> + <section id="Application_Development_Guide-Live_Config-Block_Jobs"> + <title>Block Device Jobs</title> + + <para> + Libvirt provides a generic Block Job API that can be used to initiate + and manage operations on disks that belong to a domain. Jobs are + started by calling the function associated with the desired operation + (eg. <literal>virDomainBlockPull</literal>). Once started, all block + jobs are managed in the same manner. They can be aborted, throttled, + and queried. Upon completion, an asynchronous event is issued to + indicate the final status. + </para> + + <para> + The following block jobs can be started: + </para> + <orderedlist> + <listitem> + <para> + <literal>virDomainBlockPull()</literal> starts a block pull + operation for the specified disk. This operation is valid only for + specially configured disks. BlockPull will populate a disk image + with data from its backing image. Once all data from its backing + image has been pulled, the disk no longer depends on a backing + image. + </para> + </listitem> + </orderedlist> + + <para> + A disk can be queried for active block jobs by using + <literal>virDomainGetBlockJobInfo()</literal>. If found, job + information is reported in a structure that contains: the job type, + bandwidth throttling setting, and progress information. + </para> + + <para> + <literal>virDomainBlockJobAbort()</literal> can be used to cancel the + active block job on the specified disk. + </para> + + <para> + Use <literal>virDomainBlockJobSetSpeed()</literal> to limit the amount + of bandwidth that a block job may consume. Bandwidth is specified in + units of MB/sec. + </para> + + <para> + When a block job operation completes, the final status is reported using + an asynchronous event. To receive this event, register a + <literal>virConnectDomainEventBlockJobCallback</literal> function which + will receive the disk, event type, and status as parameters. + </para> + + <programlisting> +<![CDATA[/* example blockpull-example.c */ +/* compile with: gcc -g -Wall blockpull-example.c -o blockpull-example -lvirt */ +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <libvirt/libvirt.h> + +int do_cmd(const char *cmdline) +{ + int status = system(cmdline); + if (status < 0) + return -1; + else + return WEXITSTATUS(status); +} + +virDomainPtr make_domain(virConnectPtr conn) +{ + virDomainPtr dom; + char domxml[] = \ + "<domain type='kvm'> \ + <name>example</name> \ + <memory>131072</memory> \ + <vcpu>1</vcpu> \ + <os> \ + <type arch='x86_64' machine='pc-0.13'>hvm</type> \ + </os> \ + <devices> \ + <disk type='file' device='disk'> \ + <driver name='qemu' type='qed'/> \ + <source file='/var/lib/libvirt/images/example.qed' /> \ + <target dev='vda' bus='virtio'/> \ + </disk> \ + </devices> \ + </domain>"; + + do_cmd("qemu-img create -f raw /var/lib/libvirt/images/backing.qed 100M"); + do_cmd("qemu-img create -f qed -b /var/lib/libvirt/images/backing.qed \ + /var/lib/libvirt/images/example.qed"); + + dom = virDomainCreateXML(conn, domxml, 0); + return dom; +} + +int main(int argc, char *argv[]) +{ + virConnectPtr conn; + virDomainPtr dom = NULL; + char disk[] = "/var/lib/libvirt/images/example.qed"; + + conn = virConnectOpen("qemu:///system"); + if (conn == NULL) { + fprintf(stderr, "Failed to open connection to qemu:///system\n"); + goto error; + } + + dom = make_domain(conn); + if (dom == NULL) { + fprintf(stderr, "Failed to create domain\n"); + goto error; + } + + if ((virDomainBlockPull(dom, disk, 0, 0)) < 0) { + fprintf(stderr, "Failed to start block pull"); + goto error; + } + + while (1) { + virDomainBlockJobInfo info; + int ret = virDomainGetBlockJobInfo(dom, disk, &info, 0); + + if (ret == 1) { + printf("BlockPull progress: %0.0f %%\n", + (float)(100 * info.cur / info.end)); + } else if (ret == 0) { + printf("BlockPull complete\n"); + break; + } else { + fprintf(stderr, "Failed to query block jobs\n"); + break; + } + usleep(100000); + } + +error: + unlink("/var/lib/libvirt/images/backing.qed"); + unlink("/var/lib/libvirt/images/example.qed"); + if (dom != NULL) { + virDomainDestroy(dom); + virDomainFree(dom); + } + if (conn != NULL) + virConnectClose(conn); + return 0; +}]]> + </programlisting> + + </section> + </section> <section id="Application_Development_Guide-Guest_Domains-Security"> -- 1.7.3

2 1

[libvirt] KVM Forum 2011
by KVM Forum 2011 PC 13 Aug '11

13 Aug '11

For those who are travelling to the KVM Forum, looking forward to seeing you in Vancouver. And for those who can't make it, we'll be posting the presentations online as well as recording the presentations and making the videos available online (subject to presenter's approval). Here is the schedule if you haven't seen it already. http://www.linux-kvm.org/page/KVM_Forum_2011#Schedule thanks, -KVM Forum 2011 PC

1 0

[libvirt] [PATCH] build: silence gcc warning
by Eric Blake 13 Aug '11

13 Aug '11

util/virpidfile.c: In function 'virPidFileAcquirePath': util/virpidfile.c:308:66: error: nested extern declaration of '_gl_verify_function2' [-Wnested-externs] * src/util/virpidfile.c (virPidFileAcquirePath): Move verify to top level. --- Pushing under the build-breaker rule. src/util/virpidfile.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/src/util/virpidfile.c b/src/util/virpidfile.c index 38cc7e2..7dd3c51 100644 --- a/src/util/virpidfile.c +++ b/src/util/virpidfile.c @@ -299,13 +299,13 @@ cleanup: } +verify(sizeof(pid_t) <= sizeof(unsigned int)); int virPidFileAcquirePath(const char *path, pid_t pid) { int fd = -1; char pidstr[INT_BUFSIZE_BOUND(pid)]; - verify(sizeof(pid_t) <= sizeof(unsigned int)); if (path[0] == '\0') return 0; -- 1.7.4.4

1 1

[libvirt] [BUG?] killall -SIGHUP libvirtd / virStateReload
by Philipp Hahn 12 Aug '11

12 Aug '11

Hello, did something happen to sending SIGHUP to libvirtd? I can't find where the hook for SIGHUP is installed and virStateReload() seems to be uncalled. In 0.8.4 that was handled from qemudDispatchSignalEvent(), which seems to be gone. At least the manual page should be updated? Sincerely Philipp -- Philipp Hahn Open Source Software Engineer hahn(a)univention.de Univention GmbH Linux for Your Business fon: +49 421 22 232- 0 Mary-Somerville-Str.1 D-28359 Bremen fax: +49 421 22 232-99 http://www.univention.de/ diff --git a/daemon/libvirtd.pod.in b/daemon/libvirtd.pod.in index 6e699b8..8b39395 100644 --- a/daemon/libvirtd.pod.in +++ b/daemon/libvirtd.pod.in @@ -66,10 +66,6 @@ Display version information then exit. =back -=head1 SIGNALS - -On receipt of B<SIGHUP> libvirtd will reload its configuration. - =head1 FILES =over

2 1

[libvirt] [PATCH] snapshot: one less point of failure in qemu
by Eric Blake 12 Aug '11

12 Aug '11

https://bugzilla.redhat.com/show_bug.cgi?id=727709 mentions that if qemu fails to create the snapshot (such as what happens on Fedora 15 qemu, which has qmp but where savevm is only in hmp, and where libvirt is old enough to not try the hmp fallback), then 'virsh snapshot-list dom' will show a garbage snapshot entry, and the libvirt internal directory for storing snapshot metadata. This fixes the fallout bug of polluting the snapshot-list with garbage on failure (the root cause of the F15 bug of not having fallback to hmp has already been fixed in newer libvirt releases). * src/qemu/qemu_driver.c (qemuDomainSnapshotCreateXML): Allocate memory before making snapshot, and cleanup on failure. --- src/qemu/qemu_driver.c | 23 ++++++++++++++--------- 1 files changed, 14 insertions(+), 9 deletions(-) diff --git a/src/qemu/qemu_driver.c b/src/qemu/qemu_driver.c index 7802e08..da2703e 100644 --- a/src/qemu/qemu_driver.c +++ b/src/qemu/qemu_driver.c @@ -8665,7 +8665,7 @@ static virDomainSnapshotPtr qemuDomainSnapshotCreateXML(virDomainPtr domain, virDomainSnapshotObjPtr snap = NULL; virDomainSnapshotPtr snapshot = NULL; char uuidstr[VIR_UUID_STRING_BUFLEN]; - virDomainSnapshotDefPtr def; + virDomainSnapshotDefPtr def = NULL; virCheckFlags(0, NULL); @@ -8695,6 +8695,13 @@ static virDomainSnapshotPtr qemuDomainSnapshotCreateXML(virDomainPtr domain, goto cleanup; snap->def->state = virDomainObjGetState(vm, NULL); + if (vm->current_snapshot) { + def->parent = strdup(vm->current_snapshot->def->name); + if (def->parent == NULL) { + virReportOOMError(); + goto cleanup; + } + } /* actually do the snapshot */ if (!virDomainObjIsActive(vm)) { @@ -8711,14 +8718,6 @@ static virDomainSnapshotPtr qemuDomainSnapshotCreateXML(virDomainPtr domain, * on it, so we have to go forward the best we can */ - if (vm->current_snapshot) { - def->parent = strdup(vm->current_snapshot->def->name); - if (def->parent == NULL) { - virReportOOMError(); - goto cleanup; - } - } - /* Now we set the new current_snapshot for the domain */ vm->current_snapshot = snap; @@ -8732,6 +8731,12 @@ static virDomainSnapshotPtr qemuDomainSnapshotCreateXML(virDomainPtr domain, cleanup: if (vm) virDomainObjUnlock(vm); + if (!snapshot) { + if (snap) + virDomainSnapshotObjListRemove(&vm->snapshots, snap); + else + virDomainSnapshotDefFree(def); + } qemuDriverUnlock(driver); return snapshot; } -- 1.7.4.4

1 0

[libvirt] [PATCH 0/6] snapshot work - don't strand snapshot metadata
by Eric Blake 12 Aug '11

12 Aug '11

Maps pretty well to my RFC email trail, as amended with followups: https://www.redhat.com/archives/libvir-list/2011-August/msg00452.html The qemu_driver diffstat is deceptively large; there's some code motion thrown in on 3/6. This series requires acks on the earlier one: https://www.redhat.com/archives/libvir-list/2011-August/msg00493.html Eric Blake (6): snapshot: identify which snapshots have metadata snapshot: prevent stranding snapshot data on domain destruction snapshot: refactor some qemu code snapshot: cache qemu-img location snapshot: support new undefine flags in qemu snapshot: teach virsh about new undefine flags include/libvirt/libvirt.h.in | 29 +++- src/esx/esx_driver.c | 17 ++- src/libvirt.c | 58 +++++- src/qemu/qemu_conf.h | 1 + src/qemu/qemu_driver.c | 336 +++++++++++++++++++++-------------- src/vbox/vbox_tmpl.c | 19 ++- tools/virsh.c | 400 +++++++++++++++++++++++++++++++++++++----- tools/virsh.pod | 36 ++++- 8 files changed, 691 insertions(+), 205 deletions(-) -- 1.7.4.4

1 7

[libvirt] [PATCH] virsh: fix logic bug
by Eric Blake 12 Aug '11

12 Aug '11

Bug introduced in commit 9a0ec36. * tools/virsh.c (cmdUndefine): Add missing line. --- Pushing under the trivial rule. tools/virsh.c | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) diff --git a/tools/virsh.c b/tools/virsh.c index 070d461..f995ae6 100644 --- a/tools/virsh.c +++ b/tools/virsh.c @@ -1449,6 +1449,7 @@ cmdUndefine(vshControl *ctl, const vshCmd *cmd) return false; if (!(dom = vshCommandOptDomain(ctl, cmd, &name))) + return false; has_managed_save = virDomainHasManagedSaveImage(dom, 0); if (has_managed_save < 0) { -- 1.7.4.4

1 1

[libvirt] [PATCH 0/5] Some rearrangement & additions to pid file handling/locking
by Daniel P. Berrange 12 Aug '11

12 Aug '11

This series is a collection of changes related to pidfiles. First we define some wrappers around fcntl()'s lock file capability. Then all existing pidfile APIs from src/util/util.h are moved into a new file src/util/virpidfile.h. Next a new API for doing a sanity check on a PID (using /proc/$PID/exe) is introduced. Then two clever functions for doing race free, crash-safe acquisition & release of pidfiles are introduced. Finally libvirtd is converted to use the new pidfile acquisition API.

2 14

[libvirt] [PATCH 1/3] snapshot: allow deletion of just snapshot metadata
by Eric Blake 12 Aug '11

12 Aug '11

A future patch will make it impossible to remove a domain if it would leave behind any libvirt-tracked metadata about snapshots, since stale metadata interferes with a new domain by the same name. But requiring snaphot contents to be deleted before removing a domain is harsh; with qemu, qemu-img can still make use of the contents after the libvirt domain is gone. Therefore, we need an option to get rid of libvirt tracking information, but not the actual contents. For hypervisors that do not track any metadata in libvirt, the implementation is trivial; all remaining hypervisors (really, just qemu) will be dealt with separately. * include/libvirt/libvirt.h.in (VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY): New flag. * src/libvirt.c (virDomainSnapshotDelete): Document it. * src/esx/esx_driver.c (esxDomainSnapshotDelete): Trivially supported when there is no libvirt metadata. * src/vbox/vbox_tmpl.c (vboxDomainSnapshotDelete): Likewise. --- Progress towards implementing my RFC. Patch 2/3 took a lot more of my time to diagnose and fix than I was expecting. include/libvirt/libvirt.h.in | 1 + src/esx/esx_driver.c | 10 +++++++++- src/libvirt.c | 10 +++++++--- src/vbox/vbox_tmpl.c | 10 +++++++++- 4 files changed, 26 insertions(+), 5 deletions(-) diff --git a/include/libvirt/libvirt.h.in b/include/libvirt/libvirt.h.in index a625479..3aec4b0 100644 --- a/include/libvirt/libvirt.h.in +++ b/include/libvirt/libvirt.h.in @@ -2580,6 +2580,7 @@ int virDomainRevertToSnapshot(virDomainSnapshotPtr snapshot, /* Delete a snapshot */ typedef enum { VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN = (1 << 0), + VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY = (2 << 0), } virDomainSnapshotDeleteFlags; int virDomainSnapshotDelete(virDomainSnapshotPtr snapshot, diff --git a/src/esx/esx_driver.c b/src/esx/esx_driver.c index c097651..beeafbd 100644 --- a/src/esx/esx_driver.c +++ b/src/esx/esx_driver.c @@ -4543,7 +4543,8 @@ esxDomainSnapshotDelete(virDomainSnapshotPtr snapshot, unsigned int flags) esxVI_TaskInfoState taskInfoState; char *taskInfoErrorMessage = NULL; - virCheckFlags(VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN, -1); + virCheckFlags(VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN | + VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY, -1); if (esxVI_EnsureSession(priv->primary) < 0) { return -1; @@ -4561,6 +4562,13 @@ esxDomainSnapshotDelete(virDomainSnapshotPtr snapshot, unsigned int flags) goto cleanup; } + /* ESX snapshots do not require any libvirt metadata, making this + * flag trivial once we know we have a valid snapshot. */ + if (flags & VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY) { + result = 0; + goto cleanup; + } + if (esxVI_RemoveSnapshot_Task(priv->primary, snapshotTree->snapshot, removeChildren, &task) < 0 || esxVI_WaitForTaskCompletion(priv->primary, task, snapshot->domain->uuid, diff --git a/src/libvirt.c b/src/libvirt.c index c8af3e1..8ee9e96 100644 --- a/src/libvirt.c +++ b/src/libvirt.c @@ -15792,14 +15792,18 @@ error: /** * virDomainSnapshotDelete: * @snapshot: a domain snapshot object - * @flags: flag parameters + * @flags: bitwise-or of supported virDomainSnapshotDeleteFlags * * Delete the snapshot. * * If @flags is 0, then just this snapshot is deleted, and changes from * this snapshot are automatically merged into children snapshots. If - * flags is VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN, then this snapshot - * and any children snapshots are deleted. + * @flags includes VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN, then this snapshot + * and any children snapshots are deleted. If @flags includes + * VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY, then any snapshot metadata + * tracked by libvirt is removed while keeping the snapshot contents + * intact; if a hypervisor does not require any libvirt metadata to + * track snapshots, then this flag results in no changes. * * Returns 0 if the snapshot was successfully deleted, -1 on error. */ diff --git a/src/vbox/vbox_tmpl.c b/src/vbox/vbox_tmpl.c index 822e899..8de2bae 100644 --- a/src/vbox/vbox_tmpl.c +++ b/src/vbox/vbox_tmpl.c @@ -6361,7 +6361,8 @@ vboxDomainSnapshotDelete(virDomainSnapshotPtr snapshot, PRUint32 state; nsresult rc; - virCheckFlags(VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN, -1); + virCheckFlags(VIR_DOMAIN_SNAPSHOT_DELETE_CHILDREN | + VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY, -1); vboxIIDFromUUID(&domiid, dom->uuid); rc = VBOX_OBJECT_GET_MACHINE(domiid.value, &machine); @@ -6382,6 +6383,13 @@ vboxDomainSnapshotDelete(virDomainSnapshotPtr snapshot, goto cleanup; } + /* VBOX snapshots do not require any libvirt metadata, making this + * flag trivial once we know we have a valid snapshot. */ + if (flags & VIR_DOMAIN_SNAPSHOT_DELETE_METADATA_ONLY) { + ret = 0; + goto cleanup; + } + if (state >= MachineState_FirstOnline && state <= MachineState_LastOnline) { vboxError(VIR_ERR_OPERATION_INVALID, "%s", -- 1.7.4.4

1 3

[libvirt] Do not fail migration if the media is ejected inside guest.
by Osier Yang 12 Aug '11

12 Aug '11

The whole mail title should be "Do not fail migration if the media is ejected inside guest and the media source is removed". Following 2 patches are trying to solve it, please see the patch descriptions for more detail. BZ# https://bugzilla.redhat.com/show_bug.cgi?id=725673 [PATCH 1/2] qemu: Get the media status of removable block device [PATCH 2/2] qemu: Clear source path of removable block if it is Osier

2 9

[libvirt] [PATCH 1/2] virsh: don't reject undefine on active domain
by Eric Blake 12 Aug '11

12 Aug '11

The public API documents that undefine may be used to transition a running persistent domain into a transient one. Many drivers still do not support this usage, but virsh shouldn't be getting in the way of those that do support it. * tools/virsh.c (cmdUndefine): Allow undefine on active domains; the drivers may still reject it, but it is a valid API usage. * tests/undefine (error): Fix the test to match. --- tests/undefine | 9 +++++---- tools/virsh.c | 15 +-------------- 2 files changed, 6 insertions(+), 18 deletions(-) diff --git a/tests/undefine b/tests/undefine index f89a91e..5c39e27 100755 --- a/tests/undefine +++ b/tests/undefine @@ -1,7 +1,7 @@ #!/bin/sh # exercise virsh's "undefine" command -# Copyright (C) 2008-2009 Red Hat, Inc. +# Copyright (C) 2008-2009, 2011 Red Hat, Inc. # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by @@ -30,6 +30,7 @@ fi fail=0 # Attempt to undefine a running domain, by domain name. +# Although the API allows this, the test hypervisor does not. $abs_top_builddir/tools/virsh -q -c test:///default undefine test > out 2>&1 test $? = 1 || fail=1 cat <<\EOF > exp || fail=1 @@ -38,12 +39,12 @@ error: internal error Domain 'test' is still running EOF compare exp out || fail=1 -# A different diagnostic when specifying a domain ID +# A similar diagnostic when specifying a domain ID $abs_top_builddir/tools/virsh -q -c test:///default undefine 1 > out 2>&1 test $? = 1 || fail=1 cat <<\EOF > exp || fail=1 -error: a running domain like 1 cannot be undefined; -to undefine, first shutdown then undefine using its name or UUID +error: Failed to undefine domain 1 +error: internal error Domain 'test' is still running EOF compare exp out || fail=1 diff --git a/tools/virsh.c b/tools/virsh.c index b0d43ba..371e010 100644 --- a/tools/virsh.c +++ b/tools/virsh.c @@ -1431,7 +1431,6 @@ cmdUndefine(vshControl *ctl, const vshCmd *cmd) virDomainPtr dom; bool ret = true; const char *name = NULL; - int id; int flags = 0; int managed_save = vshCommandOptBool(cmd, "managed-save"); int has_managed_save = 0; @@ -1449,19 +1448,7 @@ cmdUndefine(vshControl *ctl, const vshCmd *cmd) if (vshCommandOptString(cmd, "domain", &name) <= 0) return false; - if (name && virStrToLong_i(name, NULL, 10, &id) == 0 - && id >= 0 && (dom = virDomainLookupByID(ctl->conn, id))) { - vshError(ctl, - _("a running domain like %s cannot be undefined;\n" - "to undefine, first shutdown then undefine" - " using its name or UUID"), - name); - virDomainFree(dom); - return false; - } - if (!(dom = vshCommandOptDomainBy(ctl, cmd, &name, - VSH_BYNAME|VSH_BYUUID))) - return false; + if (!(dom = vshCommandOptDomain(ctl, cmd, &name))) has_managed_save = virDomainHasManagedSaveImage(dom, 0); if (has_managed_save < 0) { -- 1.7.4.4

2 5

[libvirt] [PATCH 0/3] apibuild improvements
by Philipp Hahn 12 Aug '11

12 Aug '11

While working with the documentation, I found some issues I'd like to improve. Philipp Hahn (3): Align table cells on top Improve tokenizing of linkable terms Fix references to self.warning() docs/apibuild.py | 48 ++++++++++++++++++++++++++++++------------------ docs/libvirt.css | 4 ++++ docs/newapi.xsl | 9 ++++++--- 3 files changed, 40 insertions(+), 21 deletions(-)

3 9

[libvirt] [PATCH] Add some docs about the RPC protocol and APIs
by Daniel P. Berrange 12 Aug '11

12 Aug '11

From: "Daniel P. Berrange" <berrange(a)redhat.com> * remote.html.in: Remove obsolete notes about internals of the RPC protocol * internals/rpc.html.in: Extensive docs on RPC protocol/API * sitemap.html.in: Add new page --- docs/internals/rpc.html.in | 876 ++++++++++++++++++++++++++++++++++++++++++++ docs/remote.html.in | 45 --- docs/sitemap.html.in | 4 + 3 files changed, 880 insertions(+), 45 deletions(-) create mode 100644 docs/internals/rpc.html.in diff --git a/docs/internals/rpc.html.in b/docs/internals/rpc.html.in new file mode 100644 index 0000000..761832a --- /dev/null +++ b/docs/internals/rpc.html.in @@ -0,0 +1,876 @@ +<html> + <body> + <h1>libvirt RPC infrastructure</h1> + + <ul id="toc"></ul> + + <p> + libvirt includes a basic protocol and code to implement + an extensible, secure client/server RPC service. This was + originally designed for communication between the libvirt + client library and the libvirtd daemon. It is also also + used for communication to the virtlockd daemon and (soon) + for the libvirt_lxc controller process. This document + provides an overview of the protocol and structure / operation + of the internal RPC library APIs. + </p> + + + <h2><a name="protocol">RPC protocol</a></h2> + + <p> + libvirt uses a simple, variable length, packet based RPC protocol. + All structured data within packets is encoded using the + <a href="http://en.wikipedia.org/wiki/External_Data_Representation">XDR standard</a> + as currently defined by <a href="https://tools.ietf.org/html/rfc4506">RFC 4506</a>. + On any connection running the RPC protocol, there can be multiple + programs active, each supporting one or more versions. A program + defines a set of procedures that it supports. The procedures can + support call+reply method invocation, asynchronous events, + and generic data streams. Method invocations can be overlapped, + so waiting for a reply to one will not block the receipt of the + reply to another outstanding method. The protocol was loosely + inspired by the design of SunRPC. The definition of the RC + protocol is in the file <code>src/rpc/virnetprotocol.x</code> + in the libvirt source tree. + </p> + + <h3><a href="protocolframing">Packet framing</a></h3> + + <p> + On the wire, there is no explicit packet framing marker. Instead + each packet is preceeded by an unsigned 32-bit integer giving + the total length of the packet in bytes. This length includes + the 4-bytes of the length word itself. Conceptually the framing + looks like this: + </p> + +<pre> +|~~~ Packet 1 ~~~|~~~ Packet 2 ~~~|~~~ Packet 3 ~~~|~~~ + ++-------+------------+-------+------------+-------+------------+... +| n=U32 | (n-4) * U8 | n=U32 | (n-4) * U8 | n=U32 | (n-4) * U8 | ++-------+------------+-------+------------+-------+------------+... + +|~ Len ~|~ Data ~|~ Len ~|~ Data ~|~ Len ~|~ Data ~|~ + +</pre> + + <h3><a href="protocoldata">Packet data</a></h3> + + <p> + The data in each packet is split into two parts, a short + fixed length header, followed by a variable length payload. + So a packet from the illustration above is more correctly + shown as + </p> + +<pre> + ++-------+-------------+---------------....---+ +| n=U32 | 6*U32 | (n-(7*4))*U8 | ++-------+-------------+---------------....---+ + +|~ Len ~|~ Header ~|~ Payload .... ~| +</pre> + + + <h3><a href="protocolheader">Packet header</a></h3> + <p> + The header contains 6 fields, encoded as signed/unsigned 32-bit + integers. + </p> + + <pre> ++---------------+ +| program=U32 | ++---------------+ +| version=U32 | ++---------------+ +| procedure=S32 | ++---------------+ +| type=S32 | ++---------------+ +| serial=U32 | ++---------------+ +| status=S32 | ++---------------+ + </pre> + + <dl> + <dt><code>program</code></dt> + <dd> + This is an arbitrarily chosen number that will uniquely + identify the "service" running over the stream. + </dd> + <dt><code>version</code></dt> + <dd> + This is the version number of the program, by convention + starting from '1'. When an incompatible change is made + to a program, the version number is incremented. Ideally + both versions will then be supported on the wire in + parallel for backwards compatibility. + </dd> + <dt><code>procedure</code></dt> + <dd> + This is an arbitrarily chosen number that will uniqely + identify the method call, or event associated with the + packet. By convention, procedure numbers start from 1 + and are assigned monotonically thereafter. + </dd> + <dt><code>type</code></dt> + <dd> + <p> + This can be one of the following enumeration values + </p> + <ol> + <li>call: invocation of a method call</li> + <li>reply: completion of a method call</li> + <li>event: an asynchronous event</li> + <li>stream: control info or data from a stream</li> + </ol> + </dd> + <dt><code>serial</code></dt> + <dd> + This is an number that starts from 1 and increases + each time a method call packet is sent. A reply or + stream packet will have a serial number matching the + original method call packet serial. Events always + have the serial number set to 0. + </dd> + <dt><code>status</code></dt> + <dd> + <p> + This can one of the following enumeration values + </p> + <ol> + <li>ok: a normal packet. this is always set for method calls or events. + For replies it indicates succesful completion of the method. For + streams it indicates confirmation of the end of file on the stream.</li> + <li>error: for replies this indicates that the method call failed + and error information is being returned. For streams this indicates + that not all data was sent and the stream has aborted</li> + <li>continue: for streams this indicates that further data packets + will be following</li> + </ol> + </dl> + + <h3><a href="protocolpayload">Packet payload</a></h3> + + <p> + The payload of a packet will vary depending on the <code>type</code> + and <code>status</code> fields from the header. + </p> + + <ul> + <li>type=call: the in parameters for the method call, XDR encoded</li> + <li>type=reply+status=ok: the return value and/or out parameters for the method call, XDR encoded</li> + <li>type=reply+status=error: the error information for the method, a virErrorPtr XDR encoded</li> + <li>type=event: the parameters for the event, XDR encoded</li> + <li>type=stream+status=ok: no payload</li> + <li>type=stream+status=error: the error information for the method, a virErrorPtr XDR encoded</li> + <li>type=stream+status=continue: the raw bytes of data for the stream. No XDR encoding</li> + </ul> + + <p> + For the exact payload information for each procedure, consult the XDR protocol + definition for the program+version in question + </p> + + <h3><a name="wireexamples">Wire examples</a></h3> + + <p> + The following diagrams illustrate some example packet exchanges + between a client and server + </p> + + <h4><a name="wireexamplescall">Method call</a></h4> + + <p> + A single method call and succesful + reply, for a program=8, version=1, procedure=3, which 10 bytes worth + of input args, and 4 bytes worth of return values. The overall input + packet length is is 4 + 24 + 10 == 38, and output packet length 32 + </p> + + <pre> + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 1 | 0 | .o.oOo.o. | --> S (call) + +--+-----------------------+-----------+ + + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 1 | 0 | .o.oOo | <-- S (reply) + +--+-----------------------+--------+ + </pre> + + <h4><a name="wireexamplescallerr">Method call with error</a></h4> + + <p> + An unsuccessful method call will instead return an error object + </p> + + <pre> + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 1 | 0 | .o.oOo.o. | --> S (call) + +--+-----------------------+-----------+ + + +--+-----------------------+--------------------------+ + C <-- |48| 8 | 1 | 3 | 2 | 1 | 0 | .o.oOo.o.oOo.o.oOo.o.oOo | <-- S (error) + +--+-----------------------+--------------------------+ + </pre> + + <h4><a name="wireexamplescallup">Method call with upload stream</a></h4> + + <p> + A method call which also involves uploading some data over + a stream will result in + </p> + + <pre> + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 1 | 0 | .o.oOo.o. | --> S (call) + +--+-----------------------+-----------+ + + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 1 | 0 | .o.oOo | <-- S (reply) + +--+-----------------------+--------+ + + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + ... + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+ + C --> |24| 8 | 1 | 3 | 3 | 1 | 0 | --> S (stream finish) + +--+-----------------------+ + +--+-----------------------+ + C <-- |24| 8 | 1 | 3 | 3 | 1 | 0 | <-- S (stream finish) + +--+-----------------------+ + </pre> + + <h4><a name="wireexamplescallbi">Method call bidirectional stream</a></h4> + + <p> + A method call which also involves a bi-directional stream will + result in + </p> + + <pre> + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 1 | 0 | .o.oOo.o. | --> S (call) + +--+-----------------------+-----------+ + + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 1 | 0 | .o.oOo | <-- S (reply) + +--+-----------------------+--------+ + + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C <-- |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | <-- S (stream data down) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C <-- |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | <-- S (stream data down) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C <-- |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | <-- S (stream data down) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C <-- |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | <-- S (stream data down) + +--+-----------------------+-------------....-------+ + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + .. + +--+-----------------------+-------------....-------+ + C --> |38| 8 | 1 | 3 | 3 | 1 | 2 | .o.oOo.o.oOo....o.oOo. | --> S (stream data up) + +--+-----------------------+-------------....-------+ + +--+-----------------------+ + C --> |24| 8 | 1 | 3 | 3 | 1 | 0 | --> S (stream finish) + +--+-----------------------+ + +--+-----------------------+ + C <-- |24| 8 | 1 | 3 | 3 | 1 | 0 | <-- S (stream finish) + +--+-----------------------+ + </pre> + + + <h4><a name="wireexamplescallmany">Method calls overlapping</a></h4> + <pre> + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 1 | 0 | .o.oOo.o. | --> S (call 1) + +--+-----------------------+-----------+ + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 2 | 0 | .o.oOo.o. | --> S (call 2) + +--+-----------------------+-----------+ + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 2 | 0 | .o.oOo | <-- S (reply 2) + +--+-----------------------+--------+ + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 3 | 0 | .o.oOo.o. | --> S (call 3) + +--+-----------------------+-----------+ + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 3 | 0 | .o.oOo | <-- S (reply 3) + +--+-----------------------+--------+ + +--+-----------------------+-----------+ + C --> |38| 8 | 1 | 3 | 0 | 4 | 0 | .o.oOo.o. | --> S (call 4) + +--+-----------------------+-----------+ + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 1 | 0 | .o.oOo | <-- S (reply 1) + +--+-----------------------+--------+ + +--+-----------------------+--------+ + C <-- |32| 8 | 1 | 3 | 1 | 4 | 0 | .o.oOo | <-- S (reply 4) + +--+-----------------------+--------+ + </pre> + + + <h2><a name="security">RPC security</a></h2> + + <p> + There are various things to consider to ensure an implementation + of the RPC protocol can be satisfactorily secured + </p> + + <h3><a name="securitytls">Authentication/encryption</a></h3> + + <p> + The basic RPC protocol does not define or require any specific + authentication/encryption capabilities. A generic solution to + providing encryption for the protocol is to run the protocol + over a TLS encrypted data stream. x509 certificate checks can + be done to form a crude authentication mechanism. It is also + possible for an RPC program to negotiate an encryption / + authentication capability, such as SASL, which may then also + provide per-packet data encryption. Finally the protocol data + stream can of course be tunnelled over transports such as SSH. + </p> + + <h3><a name="securitylimits">Data limits</a></h3> + + <p> + Although the protocol itself defines many arbitrary sized data values in the + payloads, to avoid denial of service attack there are a number of size limit + checks prior to encoding or decoding data. There is a limit on the maximum + size of a single RPC message, limit on the maximum string length, and limits + on any other parameter which uses a variable length array. These limits can + be raised, subject to agreement between client/server, without otherwise + breaking compatibility of the RPC data on the wire. + </p> + + <h3><a name="securityvalidate">Data validation</a></h3> + + <p> + It is important that all data be fully validated before performing + any actions based on the data. When reading an RPC packet, the + first four bytes must be read and the max packet size limit validated, + before any attempt is made to read the variable length packet data. + After a complete packet has been read, the header must be decoded + and all 6 fields fully validated, before attempting to dispatch + the payload. Once dispatched, the payload can be decoded and passed + onto the appropriate API for execution. The RPC code must not take + any action based on the payload, since it has no way to validate + the semantics of the payload data. It must delegate this to the + execution API (eg corresponding libvirt public API). + </p> + + <h2><a name="internals">RPC internal APIs</a></h2> + + <p> + The generic internal RPC library code lives in the <code>src/rpc/</code> + directory of the libvirt source tree. Unless otherwise noted, the + objects are all threadsafe. The core object types and their + purposes are: + </p> + + <h3><a name="apioverview">Overview of RPC objects</a></h3> + + <p> + The following is a high level overview of the role of each + of the main RPC objects + </p> + + <dl> + <dt><code>virNetSASLContextPtr</code> (virnetsaslcontext.h)</dt> + <dd>The virNetSASLContext APIs maintain SASL state for a network + service (server or client). This is primarily used on the server + to provide a whitelist of allowed SASL usernames for clients. + </dd> + + <dt><code>virNetSASLSessionPtr</code> (virnetsaslcontext.h)</dt> + <dd>The virNetSASLSession APIs maintain SASL state for a single + network connection (socket). This is used to perform the multi-step + SASL handshake and perform encryption/decryption of data once + authenticated, via integration with virNetSocket. + </dd> + + <dt><code>virNetTLSContextPtr</code> (virnettlscontext.h)</dt> + <dd>The virNetTLSContext APIs maintain TLS state for a network + service (server or client). This is primarily used on the server + to provide a whitelist of allowed x509 distinguished names, as + well as diffie-hellman keys. It can also do validation of + x509 certificates prior to initiating a connection, in order + to improve detection of configuration errors. + </dd> + + <dt><code>virNetTLSSessionPtr</code> (virnettlscontext.h)</dt> + <dd>The virNetTLSSession APIs maintain TLS state for a single + network connection (socket). This is used to perform the multi-step + TLS handshake and perform encryption/decryption of data once + authenticated, via integration with virNetSocket. + </dd> + + <dt><code>virNetSocketPtr</code> (virnetsocket.h)</dt> + <dd>The virNetSocket APIs provide a higher level wrapper around + the raw BSD sockets and getaddrinfo APIs. They allow for creation + of both server and client sockets. Data transports supported are + TCP, UNIX, SSH tunnel or external command tunnel. Internally the + TCP socket impl uses the getaddrinfo info APIs to ensure correct + protocol independant behaviour, thus supporting both IPv4 and IPv6. + The socket APIs can be associated with a virNetSASLSessionPtr or + virNetTLSSessionPtr object to allow seemless encryption/decryption + of all writes and reads. For UNIX sockets it is possible to obtain + the remote client user ID and process ID. Integration with the + libvirt event loop also allows use of callbacks for notification + of various I/O conditions + </dd> + + <dt><code>virNetMessagePtr</code> (virnetmessage.h)</dt> + <dd>The virNetMessage APIs provide a wrapper around the libxdr + API calls, to facilitate processing and creation of RPC + packets. There are convenience APIs for encoding/encoding the + packet headers, encoding/decoding the payload using an XDR + filter, encoding/decoding a raw payload (for streams), and + encoding a virErrorPtr object. There is also a means to + add to/serve from a linked-list queue of messages.</dd> + + <dt><code>virNetClientPtr</code> (virnetclient.h)</dt> + <dd>The virNetClient APIs provide a way to connect to a + remote server and run one or more RPC protocols over + the connection. Connections can be made over TCP, UNIX + sockets, SSH tunnels, or external command tunnels. There + is support for both TLS and SASL session encryption. + The client also supports management of multiple data streams + over each connection. Each client object can be used from + multiple threads concurrently, with method calls/replies + being interleaved on the wire as required. + </dd> + + <dt><code>virNetClientProgramPtr</code> (virnetclientprogram.h)</dt> + <dd>The virNetClientProgram APIs are used to register a + program+version with the connection. This then enables + invocation of method calls, receipt of asynchronous + events and use of data streams, within that program+version. + When created a set of callbacks must be supplied to take + care of dispatching any incoming asynchronous events. + </dd> + + <dt><code>virNetClientStreamPtr</code> (virnetclientstream.h)</dt> + <dd>The virNetClientStream APIs are used to control transmission and + receipt of data over a stream active on a client. Streams provide + a low latency, unlimited length, bi-directional raw data exchange + mechanism layered over the RPC connection + </dd> + + <dt><code>virNetServerPtr</code> (virnetserver.h)</dt> + <dd>The virNetServer APIs are used to manage a network server. A + server exposed one or more programs, over one or more services. + It manages multiple client connections invoking multiple RPC + calls in parallel, with dispatch across multiple worker threads. + </dd> + + <dt><code>virNetServerMDNSPtr</code> (virnetservermdns.h)</dt> + <dd>The virNetServerMDNS APIs are used to advertize a server + across the local network, enabling clients to automatically + detect the existance of remote services. This is done by + interfacing with the Avahi mDNS advertisement service. + </dd> + + <dt><code>virNetServerClientPtr</code> (virnetserverclient.h)</dt> + <dd>The virNetServerClient APIs are used to manage I/O related + to a single client network connection. It handles initial + validation and routing of incoming RPC packets, and transmission + of outgoing packets. + </dd> + + <dt><code>virNetServerProgramPtr</code> (virnetserverprogram.h)</dt> + <dd>The virNetServerProgram APIs are used to provide the implementation + of a single program/version set. Primarily this includes a set of + callbacks used to actually invoke the APIs corresponding to + program procedure numbers. It is responsible for all the serialization + of payloads to/from XDR.</dd> + + <dt><code>virNetServerServicePtr</code> (virnetserverservice.h)</dt> + <dd>The virNetServerService APIs are used to connect the server to + one or more network protocols. A single service may involve multiple + sockets (ie both IPv4 and IPv6). A service also has an associated + authentication policy for incoming clients. + </dd> + </dl> + + <h3><a name="apiclientdispatch">Client RPC dispatch</a></h3> + + <p> + The client RPC code must allow for multiple overlapping RPC method + calls to be invoked, transmission & receipt of data for mutliple + streams and receipt of asynchronous events. Understandably this + involves coordination of multiple threads. + </p> + + <p> + The core requirement in the client dispatch code is that only + one thread is allowed to be performing I/O on the socket at + any time. This thread is said to be "holding the buck". When + any other thread comes along and needs todo I/O it must place + its packets on a queue and delegate processing of them to the + thread that has the buck. This thread will send out the method + call, and if it sees a reply will pass it back to the waiting + thread. If the other thread's reply hasn't arrived, by the time + the main thread has got its own reply, then it will transfer + responsibility for I/O to the thread that has been waiting the + longest. It is said to be "passing the buck" for I/O. + </p> + + <p> + When no thread is performing any RPC method call, or sending + stream data there is still a need to monitor the socket for + incoming I/O related to asynchronous events, or stream data + receipt. For this task, a watch is registered with the event + loop which triggers whenever the socket is readable. This + watch is automatically disabled whenever any other thread + grabs the buck, and re-enabled when the buck is released. + </p> + + <h4><a name="apiclientdispatchex1">Example with buck passing</a></h4> + + <p> + In the first example, a second thread issues a API call + while the first thread holds the buck. The reply to the + first call arrives first, so the buck is passed to the + second thread. + </p> + + <pre> + Thread-1 + | + V + Call API1() + | + V + Grab Buck + | Thread-2 + V | + Send method1 V + | Call API2() + V | + Wait I/O V + |<--------Queue method2 + V | + Send method2 V + | Wait for buck + V | + Wait I/O | + | | + V | + Recv reply1 | + | | + V | + Pass the buck----->| + | V + V Wait I/O + Return API1() | + V + Recv reply2 + | + V + Release the buck + | + V + Return API2() + </pre> + + <h4><a name="apiclientdispatchex2">Example without buck passing</a></h4> + + <p> + In this second example, a second thread issues an API call + which is sent and replied to, before the first thread's + API call has completed. The first thread thus notifies + the second that its reply is ready, and there is no need + to pass the buck + </p> + + <pre> + Thread-1 + | + V + Call API1() + | + V + Grab Buck + | Thread-2 + V | + Send method1 V + | Call API2() + V | + Wait I/O V + |<--------Queue method2 + V | + Send method2 V + | Wait for buck + V | + Wait I/O | + | | + V | + Recv reply2 | + | | + V | + Notify reply2------>| + | V + V Return API2() + Wait I/O + | + V + Recv reply1 + | + V + Release the buck + | + V + Return API1() + </pre> + + <h4><a name="apiclientdispatchex3">Example with async events</a></h4> + + <p> + In this example, only one thread is present and it has to + deal with some async events arriving. The events are actually + dispatched to the application from the event loop thread + </p> + + <pre> + Thread-1 + | + V + Call API1() + | + V + Grab Buck + | + V + Send method1 + | + V + Wait I/O + | Event thread + V ... + Recv event1 | + | V + V Wait for timer/fd + Queue event1 | + | V + V Timer fires + Wait I/O | + | V + V Emit event1 + Recv reply1 | + | V + V Wait for timer/fd + Return API1() | + ... + </pre> + + <h3><a name="apiserverdispatch">Server RPC dispatch</a></h3> + + <p> + The RPC server code must support receipt of incoming RPC requests from + multiple client connections, and parallel processing of all RPC + requests, even many from a single client. This goal is achieved through + a combination of event driven I/O, and multiple processing threads. + </p> + + <p> + The main libvirt event loop thread is responsible for performing all + socket I/O. It will read incoming packets from clients and willl + transmit outgoing packets to clients. It will handle the I/O to/from + streams associated with client API calls. When doing client I/O it + will also take pass the data through any applicable encryption layer + (through use of the virNetSocket / virNetTLSSession and virNetSASLSession + integration). What is paramount is that the event loop thread never + do any task that can take a non-trivial amount of time. + </p> + + <p> + When reading packets, the event loop will first read the 4 byte length + word. This is validated to make sure it does not exceed the maximum + permissible packet size, and the client is set to allow receipt of the + rest of the packet data. Once a complete packet has been received, the + next step is to decode the RPC header. The header is validated to + ensure the request is sensible, ie the server should not receive a + method reply from a client. If the client has not yet authenticated, + a security check is also applied to make sure the procedure is on the + whitelist of those allowed prior to auth. If the packet is a method + call, it will be placed on a global processing queue. The event loop + thread is now done with the packet for the time being. + </p> + + <p> + The server has a pool of worker threads, which wait for method call + packets to be queued. One of them will grab the new method call off + the queue for processing. The first step is to decode the payload of + the packet to extract the method call arguments. The worker does not + attempt todo any semantic validation of the arguments, except to make + sure the size of any variable length fields is below defined limits. + </p> + + <p> + The worker now invokes the libvirt API call that corresponds to the + procedure number in the packet header. The worker is thus kept busy + until the API call completes. The implemementation of the API call + is responsible for doing semantic validation of parameters and any + MAC security checks on the objects affected. + </p> + + <p> + Once the API call has completed, the worker thread will take the + return value and output parameters, or error object and encode + them into a reply packet. Again it does not attempt todo any + semantic validation of output data, aside from variable length + field limit checks. The worker thread puts the reply packet onto + the transmission queue for the client. The worker is now finished + and goes back to wait for another incoming method call. + </p> + + <p> + The main event loop is back in charge and when the client socket + becomes writable, it will start sending the method reply packet + back to the client. + </p> + + <p> + At any time the libvirt connection object can emit asynchronous + events. These are handled by callbacks in the main event thread. + The callback will simply encode the event parameters into a new + data packet and place the packet on the client transmission + queue. + </p> + + <p> + Incoming and outgoing stream packets are also directly handled + by the main event thread. When an incoming stream packet is + received, instead of placing it in the global dispatch queue + for the worker threads, it is sidetracked into a per-stream + processing queue. When the stream becomes writable, queued + incoming stream packets will be processed, passing their data + payload onto the stream. Conversely when the stream becomes + readable, chunks of data will be read from it, encoded into + new outgoing packets, and placed on the client's transmit + queue + </p> + + <h4><a name="apiserverdispatchex1">Example with overlapping methods</a></h4> + + <p> + This example illustrates processing of two incoming methods with + overlapping execution + </p> + + <pre> + Event thread Worker 1 Worker 2 + | | | + V V V + Wait I/O Wait Job Wait Job + | | | + V | | + Recv method1 | | + | | | + V | | + Queue method1 V | + | Serve method1 | + V | | + Wait I/O V | + | Call API1() | + V | | + Recv method2 | | + | | | + V | | + Queue method2 | V + | | Serve method2 + V V | + Wait I/O Return API1() V + | | Call API2() + | V | + V Queue reply1 | + Send reply1 | | + | V V + V Wait Job Return API2() + Wait I/O | | + | ... V + V Queue reply2 + Send reply2 | + | V + V Wait Job + Wait I/O | + | ... + ... + </pre> + + <h4><a name="apiserverdispatchex2">Example with stream data</a></h4> + + <p> + This example illustrates processing of stream data + </p> + + <pre> + Event thread + | + V + Wait I/O + | + V + Recv stream1 + | + V + Queue stream1 + | + V + Wait I/O + | + V + Recv stream2 + | + V + Queue stream2 + | + V + Wait I/O + | + V + Write stream1 + | + V + Write stream2 + | + V + Wait I/O + | + ... + </pre> + + </body> +</html> diff --git a/docs/remote.html.in b/docs/remote.html.in index b554950..6a8e830 100644 --- a/docs/remote.html.in +++ b/docs/remote.html.in @@ -53,9 +53,6 @@ machines through authenticated and encrypted connections. <li> <a href="#Remote_limitations">Limitations</a> </li> - <li> - <a href="#Remote_implementation_notes">Implementation notes</a> - </li> </ul> <h3> <a name="Remote_basic_usage">Basic usage</a> @@ -880,47 +877,5 @@ just read-write/read-only as at present. <p> Please come and discuss these issues and more on <a href="https://www.redhat.com/mailman/listinfo/libvir-list" title="libvir-list mailing list">the mailing list</a>. </p> - <h3> - <a name="Remote_implementation_notes">Implementation notes</a> - </h3> - <p> -The current implementation uses <a href="http://en.wikipedia.org/wiki/External_Data_Representation" title="External Data Representation">XDR</a>-encoded packets with a -simple remote procedure call implementation which also supports -asynchronous messaging and asynchronous and out-of-order replies, -although these latter features are not used at the moment. -</p> - <p> -The implementation should be considered <b>strictly internal</b> to -libvirt and <b>subject to change at any time without notice</b>. If -you wish to talk to libvirtd, link to libvirt. If there is a problem -that means you think you need to use the protocol directly, please -first discuss this on <a href="https://www.redhat.com/mailman/listinfo/libvir-list" title="libvir-list mailing list">the mailing list</a>. -</p> - <p> -The messaging protocol is described in -<code>qemud/remote_protocol.x</code>. -</p> - <p> -Authentication and encryption (for TLS) is done using <a href="http://www.gnu.org/software/gnutls/" title="GnuTLS project
page">GnuTLS</a> and the RPC protocol is unaware of this layer. -</p> - <p> -Protocol messages are sent using a simple 32 bit length word (encoded -XDR int) followed by the message header (XDR -<code>remote_message_header</code>) followed by the message body. The -length count includes the length word itself, and is measured in -bytes. Maximum message size is <code>REMOTE_MESSAGE_MAX</code> and to -avoid denial of services attacks on the XDR decoders strings are -individually limited to <code>REMOTE_STRING_MAX</code> bytes. In the -TLS case, messages may be split over TLS records, but a TLS record -cannot contain parts of more than one message. In the common RPC case -a single <code>REMOTE_CALL</code> message is sent from client to -server, and the server then replies synchronously with a single -<code>REMOTE_REPLY</code> message, but other forms of messaging are -also possible. -</p> - <p> -The protocol contains support for multiple program types and protocol -versioning, modelled after SunRPC. -</p> </body> </html> diff --git a/docs/sitemap.html.in b/docs/sitemap.html.in index 897ee94..f50a8d2 100644 --- a/docs/sitemap.html.in +++ b/docs/sitemap.html.in @@ -289,6 +289,10 @@ <span>Spawning commands from libvirt driver code</span> </li> <li> + <a href="internals/rpc.html">RPC protocol & APIs</a> + <span>RPC protocol information and API / dispatch guide</span> + </li> + <li> <a href="internals/locking.html">Lock managers</a> <span>Use lock managers to protect disk content</span> </li> -- 1.7.6

3 3

[libvirt] [PATCH v2] Implement DNS SRV record into the bridge driver
by Michal Novotny 12 Aug '11

12 Aug '11

Hi, this is the second version of my patch to the bridge driver and libvirt XML file to include support for the SRV records in the DNS. The syntax is based on DNSMasq man page and tests for both xml2xml and xml2argv were added as well. Differences between v1 and v2: - A minor rewrite of integer parsing functionality - Extend tests to test with both minimal and full set of attributes - Check for service name length implemented Signed-off-by: Michal Novotny <minovotn(a)redhat.com> --- docs/formatnetwork.html.in | 12 ++ docs/schemas/network.rng | 26 ++++ src/conf/network_conf.c | 130 +++++++++++++++++++- src/conf/network_conf.h | 16 +++ src/network/bridge_driver.c | 43 +++++++ .../nat-network-dns-srv-record-minimal.argv | 1 + .../nat-network-dns-srv-record-minimal.xml | 26 ++++ .../nat-network-dns-srv-record.argv | 1 + .../nat-network-dns-srv-record.xml | 26 ++++ tests/networkxml2argvtest.c | 2 + .../nat-network-dns-srv-record-minimal.xml | 26 ++++ .../nat-network-dns-srv-record.xml | 26 ++++ .../nat-network-dns-srv-record-minimal.xml | 26 ++++ .../nat-network-dns-srv-record.xml | 26 ++++ tests/networkxml2xmltest.c | 2 + 16 files changed, 391 insertions(+), 2 deletions(-) create mode 100644 tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.argv create mode 100644 tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.xml create mode 100644 tests/networkxml2argvdata/nat-network-dns-srv-record.argv create mode 100644 tests/networkxml2argvdata/nat-network-dns-srv-record.xml create mode 100644 tests/networkxml2xmlin/nat-network-dns-srv-record-minimal.xml create mode 100644 tests/networkxml2xmlin/nat-network-dns-srv-record.xml create mode 100644 tests/networkxml2xmlout/nat-network-dns-srv-record-minimal.xml create mode 100644 tests/networkxml2xmlout/nat-network-dns-srv-record.xml diff --git a/docs/formatnetwork.html.in b/docs/formatnetwork.html.in index 99031d0..51b1581 100644 --- a/docs/formatnetwork.html.in +++ b/docs/formatnetwork.html.in @@ -342,6 +342,7 @@ <mac address='00:16:3E:5D:C7:9E'/> <dns> <txt name="example" value="example value" /> + <srv service="name" protocol="tcp" domain="test-domain-name" target="." port="1024" priority="10" weight="10"/> </dns> <ip address="192.168.122.1" netmask="255.255.255.0"> <dhcp> @@ -390,6 +391,17 @@ <span class="since">Since 0.9.3</span> </dd> </dl> + <dl> + <dt><code>srv</code></dt> + <dd>The <code>dns</code> element can have also 0 or more <code>srv</code> + record elements. Each <code>srv</code> record element defines a DNS SRV record + and has 2 mandatory and 5 optional attributes. The mandatory attributes + are service name and protocol (tcp, udp) and the optional attributes are + target, port, priority, weight and domain as defined in DNS server SRV + RFC (RFC 2782). + <span class="since">Since 0.9.5</span> + </dd> + </dl> </dd> <dt><code>ip</code></dt> <dd>The <code>address</code> attribute defines an IPv4 address in diff --git a/docs/schemas/network.rng b/docs/schemas/network.rng index 1c44471..dae2799 100644 --- a/docs/schemas/network.rng +++ b/docs/schemas/network.rng @@ -138,6 +138,19 @@ </element> </zeroOrMore> <zeroOrMore> + <element name="srv"> + <attribute name="service"><text/></attribute> + <attribute name="protocol"><ref name="protocol"/></attribute> + <optional> + <attribute name="domain"><ref name="dnsName"/></attribute> + <attribute name="target"><text/></attribute> + <attribute name="port"><ref name="unsignedShort"/></attribute> + <attribute name="priority"><ref name="unsignedShort"/></attribute> + <attribute name="weight"><ref name="unsignedShort"/></attribute> + </optional> + </element> + </zeroOrMore> + <zeroOrMore> <element name="host"> <attribute name="ip"><ref name="ipv4Addr"/></attribute> <oneOrMore> @@ -206,6 +219,19 @@ </element> </define> + <define name='unsignedShort'> + <data type='integer'> + <param name="minInclusive">0</param> + <param name="maxInclusive">65535</param> + </data> + </define> + + <define name='protocol'> + <data type='string'> + <param name='pattern'>(tcp)|(udp)</param> + </data> + </define> + <define name='addr-family'> <data type='string'> <param name="pattern">(ipv4)|(ipv6)</param> diff --git a/src/conf/network_conf.c b/src/conf/network_conf.c index b11c482..517c4d6 100644 --- a/src/conf/network_conf.c +++ b/src/conf/network_conf.c @@ -137,6 +137,15 @@ static void virNetworkDNSDefFree(virNetworkDNSDefPtr def) } VIR_FREE(def->hosts); } + if (def->nsrvrecords) { + while (def->nsrvrecords--) { + VIR_FREE(def->srvrecords[def->nsrvrecords].domain); + VIR_FREE(def->srvrecords[def->nsrvrecords].service); + VIR_FREE(def->srvrecords[def->nsrvrecords].protocol); + VIR_FREE(def->srvrecords[def->nsrvrecords].target); + } + VIR_FREE(def->srvrecords); + } VIR_FREE(def); } } @@ -552,8 +561,99 @@ error: } static int +virNetworkDNSSrvDefParseXML(virNetworkDNSDefPtr def, + xmlNodePtr cur, + xmlXPathContextPtr ctxt) +{ + char *domain; + char *service; + char *protocol; + char *target; + int port; + int priority; + int weight; + int ret = 0; + char xpath[1024] = { 0 }; + + if (!(service = virXMLPropString(cur, "service"))) { + virNetworkReportError(VIR_ERR_XML_DETAIL, + "%s", _("Missing required service attribute in dns srv record")); + goto error; + } + + if (strlen(service) > DNS_RECORD_LENGTH_SRV) { + virNetworkReportError(VIR_ERR_XML_DETAIL, + "%s", _("Service name is too long, limit is %d bytes"), DNS_RECORD_LENGTH_SRV); + goto error; + } + + if (!(protocol = virXMLPropString(cur, "protocol"))) { + virNetworkReportError(VIR_ERR_XML_DETAIL, + _("Missing required protocol attribute in dns srv record '%s'"), service); + goto error; + } + + /* Check whether protocol value is the supported one */ + if (STRNEQ(protocol, "tcp") && (STRNEQ(protocol, "udp"))) { + virNetworkReportError(VIR_ERR_XML_DETAIL, + _("Invalid protocol attribute value '%s'"), protocol); + goto error; + } + + if (VIR_REALLOC_N(def->srvrecords, def->nsrvrecords + 1) < 0) { + virReportOOMError(); + goto error; + } + + def->srvrecords[def->nsrvrecords].service = service; + def->srvrecords[def->nsrvrecords].protocol = protocol; + def->srvrecords[def->nsrvrecords].domain = NULL; + def->srvrecords[def->nsrvrecords].target = NULL; + def->srvrecords[def->nsrvrecords].port = 0; + def->srvrecords[def->nsrvrecords].priority = 0; + def->srvrecords[def->nsrvrecords].weight = 0; + + /* Following attributes are optional but we had to make sure their NULL above */ + if ((target = virXMLPropString(cur, "target")) && (domain = virXMLPropString(cur, "domain"))) { + snprintf(xpath, sizeof(xpath), "string(//network/dns/srv[@service='%s']/@port)", service); + if (virXPathInt(xpath, ctxt, &port)) + def->srvrecords[def->nsrvrecords].port = port; + + snprintf(xpath, sizeof(xpath), "string(//network/dns/srv[@service='%s']/@priority)", service); + if (virXPathInt(xpath, ctxt, &priority)) + def->srvrecords[def->nsrvrecords].priority = priority; + + snprintf(xpath, sizeof(xpath), "string(//network/dns/srv[@service='%s']/@weight)", service); + if (virXPathInt(xpath, ctxt, &weight)) + def->srvrecords[def->nsrvrecords].weight = weight; + + def->srvrecords[def->nsrvrecords].domain = domain; + def->srvrecords[def->nsrvrecords].target = target; + def->srvrecords[def->nsrvrecords].port = port; + def->srvrecords[def->nsrvrecords].priority = priority; + def->srvrecords[def->nsrvrecords].weight = weight; + } + + def->nsrvrecords++; + + goto cleanup; + +error: + VIR_FREE(domain); + VIR_FREE(service); + VIR_FREE(protocol); + VIR_FREE(target); + + ret = 1; + +cleanup: + return ret; +} + +static int virNetworkDNSDefParseXML(virNetworkDNSDefPtr *dnsdef, - xmlNodePtr node) + xmlNodePtr node, + xmlXPathContextPtr ctxt) { xmlNodePtr cur; int ret = -1; @@ -598,6 +698,11 @@ virNetworkDNSDefParseXML(virNetworkDNSDefPtr *dnsdef, name = NULL; value = NULL; } else if (cur->type == XML_ELEMENT_NODE && + xmlStrEqual(cur->name, BAD_CAST "srv")) { + ret = virNetworkDNSSrvDefParseXML(def, cur, ctxt); + if (ret < 0) + goto error; + } else if (cur->type == XML_ELEMENT_NODE && xmlStrEqual(cur->name, BAD_CAST "host")) { ret = virNetworkDNSHostsDefParseXML(def, cur); if (ret < 0) @@ -888,7 +993,7 @@ virNetworkDefParseXML(xmlXPathContextPtr ctxt) dnsNode = virXPathNode("./dns", ctxt); if (dnsNode != NULL) { - if (virNetworkDNSDefParseXML(&def->dns, dnsNode) < 0) + if (virNetworkDNSDefParseXML(&def->dns, dnsNode, ctxt) < 0) goto error; } @@ -1147,6 +1252,27 @@ virNetworkDNSDefFormat(virBufferPtr buf, def->txtrecords[i].value); } + for (i = 0 ; i < def->nsrvrecords ; i++) { + if (def->srvrecords[i].service && def->srvrecords[i].protocol) { + virBufferAsprintf(buf, " <srv service='%s' protocol='%s' ", + def->srvrecords[i].service, + def->srvrecords[i].protocol); + + if (def->srvrecords[i].domain) + virBufferAsprintf(buf, "domain='%s' ", def->srvrecords[i].domain); + if (def->srvrecords[i].target) + virBufferAsprintf(buf, "target='%s' ", def->srvrecords[i].target); + if (def->srvrecords[i].port) + virBufferAsprintf(buf, "port='%d' ", def->srvrecords[i].port); + if (def->srvrecords[i].priority) + virBufferAsprintf(buf, "priority='%d' ", def->srvrecords[i].priority); + if (def->srvrecords[i].weight) + virBufferAsprintf(buf, "weight='%d' ", def->srvrecords[i].weight); + + virBufferAsprintf(buf, "/>\n"); + } + } + if (def->nhosts) { int ii, j; diff --git a/src/conf/network_conf.h b/src/conf/network_conf.h index 869085e..5f05a3a 100644 --- a/src/conf/network_conf.h +++ b/src/conf/network_conf.h @@ -24,6 +24,8 @@ #ifndef __NETWORK_CONF_H__ # define __NETWORK_CONF_H__ +#define DNS_RECORD_LENGTH_SRV (512 - 30) /* Limit minus overhead as mentioned in RFC-2782 */ + # include <libxml/parser.h> # include <libxml/tree.h> # include <libxml/xpath.h> @@ -67,6 +69,18 @@ struct _virNetworkDNSTxtRecordsDef { char *value; }; +typedef struct _virNetworkDNSSrvRecordsDef virNetworkDNSSrvRecordsDef; +typedef virNetworkDNSSrvRecordsDef *virNetworkDNSSrvRecordsDefPtr; +struct _virNetworkDNSSrvRecordsDef { + char *domain; + char *service; + char *protocol; + char *target; + int port; + int priority; + int weight; +}; + struct _virNetworkDNSHostsDef { virSocketAddr ip; int nnames; @@ -80,6 +94,8 @@ struct _virNetworkDNSDef { virNetworkDNSTxtRecordsDefPtr txtrecords; unsigned int nhosts; virNetworkDNSHostsDefPtr hosts; + unsigned int nsrvrecords; + virNetworkDNSSrvRecordsDefPtr srvrecords; }; typedef struct _virNetworkDNSDef *virNetworkDNSDefPtr; diff --git a/src/network/bridge_driver.c b/src/network/bridge_driver.c index c90db63..f4d952f 100644 --- a/src/network/bridge_driver.c +++ b/src/network/bridge_driver.c @@ -559,6 +559,49 @@ networkBuildDnsmasqArgv(virNetworkObjPtr network, virCommandAddArgPair(cmd, "--txt-record", record); VIR_FREE(record); } + + for (i = 0; i < dns->nsrvrecords; i++) { + char *record = NULL; + char *recordPort = NULL; + char *recordPriority = NULL; + char *recordWeight = NULL; + + if (dns->srvrecords[i].service && dns->srvrecords[i].protocol) { + if (dns->srvrecords[i].port) { + if (virAsprintf(&recordPort, "%d", dns->srvrecords[i].port) < 0) { + virReportOOMError(); + goto cleanup; + } + } + if (dns->srvrecords[i].priority) { + if (virAsprintf(&recordPriority, "%d", dns->srvrecords[i].priority) < 0) { + virReportOOMError(); + goto cleanup; + } + } + if (dns->srvrecords[i].weight) { + if (virAsprintf(&recordWeight, "%d", dns->srvrecords[i].weight) < 0) { + virReportOOMError(); + goto cleanup; + } + } + + if (virAsprintf(&record, "%s.%s.%s,%s,%s,%s,%s", + dns->srvrecords[i].service, + dns->srvrecords[i].protocol, + dns->srvrecords[i].domain ? dns->srvrecords[i].domain : "", + dns->srvrecords[i].target ? dns->srvrecords[i].target : "", + recordPort ? recordPort : "", + recordPriority ? recordPriority : "", + recordWeight ? recordWeight : "") < 0) { + virReportOOMError(); + goto cleanup; + } + + virCommandAddArgPair(cmd, "--srv-host", record); + VIR_FREE(record); + } + } } /* diff --git a/tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.argv b/tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.argv new file mode 100644 index 0000000..174f751 --- /dev/null +++ b/tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.argv @@ -0,0 +1 @@ +/usr/sbin/dnsmasq --strict-order --bind-interfaces --conf-file= --except-interface lo --srv-host=name.tcp.,,,, --listen-address 192.168.122.1 --listen-address 192.168.123.1 --listen-address 2001:db8:ac10:fe01::1 --listen-address 2001:db8:ac10:fd01::1 --listen-address 10.24.10.1 --dhcp-range 192.168.122.2,192.168.122.254 --dhcp-leasefile=/var/lib/libvirt/dnsmasq/default.leases --dhcp-lease-max=253 --dhcp-no-override --dhcp-hostsfile=/var/lib/libvirt/dnsmasq/default.hostsfile \ No newline at end of file diff --git a/tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.xml b/tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.xml new file mode 100644 index 0000000..e9b7680 --- /dev/null +++ b/tests/networkxml2argvdata/nat-network-dns-srv-record-minimal.xml @@ -0,0 +1,26 @@ +<network> + <name>default</name> + <uuid>81ff0d90-c91e-6742-64da-4a736edb9a9b</uuid> + <forward dev='eth1' mode='nat'> + <interface dev='eth1'/> + </forward> + <bridge name='virbr0' stp='on' delay='0' /> + <dns> + <srv service='name' protocol='tcp' /> + </dns> + <ip address='192.168.122.1' netmask='255.255.255.0'> + <dhcp> + <range start='192.168.122.2' end='192.168.122.254' /> + <host mac='00:16:3e:77:e2:ed' name='a.example.com' ip='192.168.122.10' /> + <host mac='00:16:3e:3e:a9:1a' name='b.example.com' ip='192.168.122.11' /> + </dhcp> + </ip> + <ip family='ipv4' address='192.168.123.1' netmask='255.255.255.0'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fe01::1' prefix='64'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fd01::1' prefix='64'> + </ip> + <ip family='ipv4' address='10.24.10.1'> + </ip> +</network> diff --git a/tests/networkxml2argvdata/nat-network-dns-srv-record.argv b/tests/networkxml2argvdata/nat-network-dns-srv-record.argv new file mode 100644 index 0000000..2ea9809 --- /dev/null +++ b/tests/networkxml2argvdata/nat-network-dns-srv-record.argv @@ -0,0 +1 @@ +/usr/sbin/dnsmasq --strict-order --bind-interfaces --conf-file= --except-interface lo --srv-host=name.tcp.test-domain-name,.,1024,10,10 --listen-address 192.168.122.1 --listen-address 192.168.123.1 --listen-address 2001:db8:ac10:fe01::1 --listen-address 2001:db8:ac10:fd01::1 --listen-address 10.24.10.1 --dhcp-range 192.168.122.2,192.168.122.254 --dhcp-leasefile=/var/lib/libvirt/dnsmasq/default.leases --dhcp-lease-max=253 --dhcp-no-override --dhcp-hostsfile=/var/lib/libvirt/dnsmasq/default.hostsfile \ No newline at end of file diff --git a/tests/networkxml2argvdata/nat-network-dns-srv-record.xml b/tests/networkxml2argvdata/nat-network-dns-srv-record.xml new file mode 100644 index 0000000..4be85b5 --- /dev/null +++ b/tests/networkxml2argvdata/nat-network-dns-srv-record.xml @@ -0,0 +1,26 @@ +<network> + <name>default</name> + <uuid>81ff0d90-c91e-6742-64da-4a736edb9a9b</uuid> + <forward dev='eth1' mode='nat'> + <interface dev='eth1'/> + </forward> + <bridge name='virbr0' stp='on' delay='0' /> + <dns> + <srv service='name' protocol='tcp' domain='test-domain-name' target='.' port='1024' priority='10' weight='10' /> + </dns> + <ip address='192.168.122.1' netmask='255.255.255.0'> + <dhcp> + <range start='192.168.122.2' end='192.168.122.254' /> + <host mac='00:16:3e:77:e2:ed' name='a.example.com' ip='192.168.122.10' /> + <host mac='00:16:3e:3e:a9:1a' name='b.example.com' ip='192.168.122.11' /> + </dhcp> + </ip> + <ip family='ipv4' address='192.168.123.1' netmask='255.255.255.0'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fe01::1' prefix='64'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fd01::1' prefix='64'> + </ip> + <ip family='ipv4' address='10.24.10.1'> + </ip> +</network> diff --git a/tests/networkxml2argvtest.c b/tests/networkxml2argvtest.c index 4a11d6f..2dd9b7f 100644 --- a/tests/networkxml2argvtest.c +++ b/tests/networkxml2argvtest.c @@ -120,6 +120,8 @@ mymain(void) DO_TEST("netboot-network"); DO_TEST("netboot-proxy-network"); DO_TEST("nat-network-dns-txt-record"); + DO_TEST("nat-network-dns-srv-record"); + DO_TEST("nat-network-dns-srv-record-minimal"); DO_TEST("nat-network-dns-hosts"); return (ret==0 ? EXIT_SUCCESS : EXIT_FAILURE); diff --git a/tests/networkxml2xmlin/nat-network-dns-srv-record-minimal.xml b/tests/networkxml2xmlin/nat-network-dns-srv-record-minimal.xml new file mode 100644 index 0000000..e9b7680 --- /dev/null +++ b/tests/networkxml2xmlin/nat-network-dns-srv-record-minimal.xml @@ -0,0 +1,26 @@ +<network> + <name>default</name> + <uuid>81ff0d90-c91e-6742-64da-4a736edb9a9b</uuid> + <forward dev='eth1' mode='nat'> + <interface dev='eth1'/> + </forward> + <bridge name='virbr0' stp='on' delay='0' /> + <dns> + <srv service='name' protocol='tcp' /> + </dns> + <ip address='192.168.122.1' netmask='255.255.255.0'> + <dhcp> + <range start='192.168.122.2' end='192.168.122.254' /> + <host mac='00:16:3e:77:e2:ed' name='a.example.com' ip='192.168.122.10' /> + <host mac='00:16:3e:3e:a9:1a' name='b.example.com' ip='192.168.122.11' /> + </dhcp> + </ip> + <ip family='ipv4' address='192.168.123.1' netmask='255.255.255.0'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fe01::1' prefix='64'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fd01::1' prefix='64'> + </ip> + <ip family='ipv4' address='10.24.10.1'> + </ip> +</network> diff --git a/tests/networkxml2xmlin/nat-network-dns-srv-record.xml b/tests/networkxml2xmlin/nat-network-dns-srv-record.xml new file mode 100644 index 0000000..4be85b5 --- /dev/null +++ b/tests/networkxml2xmlin/nat-network-dns-srv-record.xml @@ -0,0 +1,26 @@ +<network> + <name>default</name> + <uuid>81ff0d90-c91e-6742-64da-4a736edb9a9b</uuid> + <forward dev='eth1' mode='nat'> + <interface dev='eth1'/> + </forward> + <bridge name='virbr0' stp='on' delay='0' /> + <dns> + <srv service='name' protocol='tcp' domain='test-domain-name' target='.' port='1024' priority='10' weight='10' /> + </dns> + <ip address='192.168.122.1' netmask='255.255.255.0'> + <dhcp> + <range start='192.168.122.2' end='192.168.122.254' /> + <host mac='00:16:3e:77:e2:ed' name='a.example.com' ip='192.168.122.10' /> + <host mac='00:16:3e:3e:a9:1a' name='b.example.com' ip='192.168.122.11' /> + </dhcp> + </ip> + <ip family='ipv4' address='192.168.123.1' netmask='255.255.255.0'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fe01::1' prefix='64'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fd01::1' prefix='64'> + </ip> + <ip family='ipv4' address='10.24.10.1'> + </ip> +</network> diff --git a/tests/networkxml2xmlout/nat-network-dns-srv-record-minimal.xml b/tests/networkxml2xmlout/nat-network-dns-srv-record-minimal.xml new file mode 100644 index 0000000..e9b7680 --- /dev/null +++ b/tests/networkxml2xmlout/nat-network-dns-srv-record-minimal.xml @@ -0,0 +1,26 @@ +<network> + <name>default</name> + <uuid>81ff0d90-c91e-6742-64da-4a736edb9a9b</uuid> + <forward dev='eth1' mode='nat'> + <interface dev='eth1'/> + </forward> + <bridge name='virbr0' stp='on' delay='0' /> + <dns> + <srv service='name' protocol='tcp' /> + </dns> + <ip address='192.168.122.1' netmask='255.255.255.0'> + <dhcp> + <range start='192.168.122.2' end='192.168.122.254' /> + <host mac='00:16:3e:77:e2:ed' name='a.example.com' ip='192.168.122.10' /> + <host mac='00:16:3e:3e:a9:1a' name='b.example.com' ip='192.168.122.11' /> + </dhcp> + </ip> + <ip family='ipv4' address='192.168.123.1' netmask='255.255.255.0'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fe01::1' prefix='64'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fd01::1' prefix='64'> + </ip> + <ip family='ipv4' address='10.24.10.1'> + </ip> +</network> diff --git a/tests/networkxml2xmlout/nat-network-dns-srv-record.xml b/tests/networkxml2xmlout/nat-network-dns-srv-record.xml new file mode 100644 index 0000000..4be85b5 --- /dev/null +++ b/tests/networkxml2xmlout/nat-network-dns-srv-record.xml @@ -0,0 +1,26 @@ +<network> + <name>default</name> + <uuid>81ff0d90-c91e-6742-64da-4a736edb9a9b</uuid> + <forward dev='eth1' mode='nat'> + <interface dev='eth1'/> + </forward> + <bridge name='virbr0' stp='on' delay='0' /> + <dns> + <srv service='name' protocol='tcp' domain='test-domain-name' target='.' port='1024' priority='10' weight='10' /> + </dns> + <ip address='192.168.122.1' netmask='255.255.255.0'> + <dhcp> + <range start='192.168.122.2' end='192.168.122.254' /> + <host mac='00:16:3e:77:e2:ed' name='a.example.com' ip='192.168.122.10' /> + <host mac='00:16:3e:3e:a9:1a' name='b.example.com' ip='192.168.122.11' /> + </dhcp> + </ip> + <ip family='ipv4' address='192.168.123.1' netmask='255.255.255.0'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fe01::1' prefix='64'> + </ip> + <ip family='ipv6' address='2001:db8:ac10:fd01::1' prefix='64'> + </ip> + <ip family='ipv4' address='10.24.10.1'> + </ip> +</network> diff --git a/tests/networkxml2xmltest.c b/tests/networkxml2xmltest.c index 5cdbedb..b9f6546 100644 --- a/tests/networkxml2xmltest.c +++ b/tests/networkxml2xmltest.c @@ -87,6 +87,8 @@ mymain(void) DO_TEST("netboot-network"); DO_TEST("netboot-proxy-network"); DO_TEST("nat-network-dns-txt-record"); + DO_TEST("nat-network-dns-srv-record"); + DO_TEST("nat-network-dns-srv-record-minimal"); DO_TEST("nat-network-dns-hosts"); DO_TEST("8021Qbh-net"); DO_TEST("direct-net"); -- 1.7.4.4

3 6

[libvirt] [PATCH v2.5] daemon: Add early libvirtd start verbose errors.
by Peter Krempa 12 Aug '11

12 Aug '11

Early errors during start of libvirtd didn't have an error reporting mechanism and caused libvirtd to exit silently (only the return value indicated an error). Libvirt logging is initialized very early using enviroment variables and the internal error reporting API is used to report early errors. v2 changes: - print errors unconditionaly before logging starts - fix message to US spelling v2.5 changes: - initialize logging from enviroment - log all early errors using VIR_ERROR fixes: https://bugzilla.redhat.com/show_bug.cgi?id=728654 --- daemon/libvirtd.c | 41 ++++++++++++++++++++++++++++++----------- 1 files changed, 30 insertions(+), 11 deletions(-) diff --git a/daemon/libvirtd.c b/daemon/libvirtd.c index 53f1002..aa69f80 100644 --- a/daemon/libvirtd.c +++ b/daemon/libvirtd.c @@ -1285,11 +1285,14 @@ int main(int argc, char **argv) { {0, 0, 0, 0} }; + /* initialize early logging */ + virLogSetFromEnv(); + if (setlocale (LC_ALL, "") == NULL || bindtextdomain (PACKAGE, LOCALEDIR) == NULL || textdomain(PACKAGE) == NULL || virInitialize() < 0) { - fprintf(stderr, _("%s: initialization failed\n"), argv[0]); + VIR_ERROR(_("%s: initialization failed"), argv[0]); exit(EXIT_FAILURE); } @@ -1328,14 +1331,18 @@ int main(int argc, char **argv) { case 'p': VIR_FREE(pid_file); - if (!(pid_file = strdup(optarg))) + if (!(pid_file = strdup(optarg))) { + VIR_ERROR(_("Can't allocate memory")); exit(EXIT_FAILURE); + } break; case 'f': VIR_FREE(remote_config_file); - if (!(remote_config_file = strdup(optarg))) + if (!(remote_config_file = strdup(optarg))) { + VIR_ERROR(_("Can't allocate memory")); exit(EXIT_FAILURE); + } break; case OPT_VERSION: @@ -1347,27 +1354,33 @@ int main(int argc, char **argv) { return 2; default: - fprintf (stderr, _("%s: internal error: unknown flag: %c\n"), - argv[0], c); + VIR_ERROR(_("%s: internal error: unknown flag: %c"), + argv[0], c); exit (EXIT_FAILURE); } } - if (!(config = daemonConfigNew(privileged))) + if (!(config = daemonConfigNew(privileged))) { + VIR_ERROR(_("Can't create initial configuration")); exit(EXIT_FAILURE); + } /* No explicit config, so try and find a default one */ if (remote_config_file == NULL) { implicit_conf = true; if (daemonConfigFilePath(privileged, - &remote_config_file) < 0) + &remote_config_file) < 0) { + VIR_ERROR(_("Can't determine config path")); exit(EXIT_FAILURE); + } } /* Read the config file if it exists*/ if (remote_config_file && - daemonConfigLoad(config, remote_config_file, implicit_conf) < 0) + daemonConfigLoad(config, remote_config_file, implicit_conf) < 0) { + VIR_ERROR(_("Can't load config file '%s'"), remote_config_file); exit(EXIT_FAILURE); + } if (config->host_uuid && virSetHostUUIDStr(config->host_uuid) < 0) { @@ -1375,19 +1388,25 @@ int main(int argc, char **argv) { exit(EXIT_FAILURE); } - if (daemonSetupLogging(config, privileged, verbose, godaemon) < 0) + if (daemonSetupLogging(config, privileged, verbose, godaemon) < 0) { + VIR_ERROR(_("Can't initialize logging")); exit(EXIT_FAILURE); + } if (!pid_file && privileged && daemonPidFilePath(privileged, - &pid_file) < 0) + &pid_file) < 0) { + VIR_ERROR(_("Can't determine pid file path.")); exit(EXIT_FAILURE); + } if (daemonUnixSocketPaths(config, privileged, &sock_file, - &sock_file_ro) < 0) + &sock_file_ro) < 0) { + VIR_ERROR(_("Can't determine socket paths")); exit(EXIT_FAILURE); + } if (godaemon) { char ebuf[1024]; -- 1.7.6

2 1

[libvirt] [PATCH v3] Add support for fd: protocol
by Corey Bryant 12 Aug '11

12 Aug '11

sVirt provides SELinux MAC isolation for Qemu guest processes and their corresponding resources (image files). sVirt provides this support by labeling guests and resources with security labels that are stored in file system extended attributes. Some file systems, such as NFS, do not support the extended attribute security namespace, which is needed for image file isolation when using the sVirt SELinux security driver in libvirt. The proposed solution entails a combination of Qemu, libvirt, and SELinux patches that work together to isolate multiple guests' images when they're stored in the same NFS mount. This results in an environment where sVirt isolation and NFS image file isolation can both be provided. This patch contains the Qemu code to support this solution. I would like to solicit input from the libvirt community prior to starting the libvirt patch. Currently, Qemu opens an image file in addition to performing the necessary read and write operations. The proposed solution will move the open out of Qemu and into libvirt. Once libvirt opens an image file for the guest, it will pass the file descriptor to Qemu via a new fd: protocol. If the image file resides in an NFS mount, the following SELinux policy changes will provide image isolation: - A new SELinux boolean is created (e.g. virt_read_write_nfs) to allow Qemu (svirt_t) to only have SELinux read and write permissions on nfs_t files - Qemu (svirt_t) also gets SELinux use permissions on libvirt (virtd_t) file descriptors Following is a sample invocation of Qemu using the fd: protocol on the command line: qemu -drive file=fd:4,format=qcow2 The fd: protocol is also supported by the drive_add monitor command. This requires that the specified file descriptor is passed to the monitor alongside a prior getfd monitor command. There are some additional features provided by certain image types where Qemu reopens the image file. All of these scenarios will be unsupported for the fd: protocol, at least for this patch: - The -snapshot command line option - The savevm monitor command - The snapshot_blkdev monitor command - Use of copy-on-write image files - The -cdrom command line option - The -drive command line option with media=cdrom - The change monitor command The thought is that this support can be added in the future, but is not required for the initial fd: support. This patch was tested with the following formats: raw, cow, qcow, qcow2, qed, and vmdk, using the fd: protocol from the command line and the monitor. Tests were also run to verify existing file name support and qemu-img were not regressed. Non-valid file descriptors, fd: without format, snapshot and backing files, and cdrom were also tested. v2: - Add drive_add monitor command support - Fence off unsupported features that re-open image file v3: - Fence off cdrom and change monitor command support Signed-off-by: Corey Bryant <coreyb(a)linux.vnet.ibm.com> --- block.c | 16 ++++++++++ block.h | 1 + block/cow.c | 5 +++ block/qcow.c | 5 +++ block/qcow2.c | 5 +++ block/qed.c | 4 ++ block/raw-posix.c | 81 +++++++++++++++++++++++++++++++++++++++++++++++------ block/vmdk.c | 5 +++ block_int.h | 1 + blockdev.c | 19 ++++++++++++ monitor.c | 5 +++ monitor.h | 1 + qemu-options.hx | 8 +++-- qemu-tool.c | 5 +++ 14 files changed, 149 insertions(+), 12 deletions(-) diff --git a/block.c b/block.c index 24a25d5..500db84 100644 --- a/block.c +++ b/block.c @@ -536,6 +536,10 @@ int bdrv_open(BlockDriverState *bs, const char *filename, int flags, char tmp_filename[PATH_MAX]; char backing_filename[PATH_MAX]; + if (bdrv_is_fd_protocol(bs)) { + return -ENOTSUP; + } + /* if snapshot, we create a temporary backing file and open it instead of opening 'filename' directly */ @@ -585,6 +589,10 @@ int bdrv_open(BlockDriverState *bs, const char *filename, int flags, /* Find the right image format driver */ if (!drv) { + /* format must be specified for fd: protocol */ + if (bdrv_is_fd_protocol(bs)) { + return -ENOTSUP; + } ret = find_image_format(filename, &drv); } @@ -1460,6 +1468,11 @@ int bdrv_enable_write_cache(BlockDriverState *bs) return bs->enable_write_cache; } +int bdrv_is_fd_protocol(BlockDriverState *bs) +{ + return bs->fd_protocol; +} + /* XXX: no longer used */ void bdrv_set_change_cb(BlockDriverState *bs, void (*change_cb)(void *opaque, int reason), @@ -1964,6 +1977,9 @@ int bdrv_snapshot_create(BlockDriverState *bs, BlockDriver *drv = bs->drv; if (!drv) return -ENOMEDIUM; + if (bdrv_is_fd_protocol(bs)) { + return -ENOTSUP; + } if (drv->bdrv_snapshot_create) return drv->bdrv_snapshot_create(bs, sn_info); if (bs->file) diff --git a/block.h b/block.h index 859d1d9..0417b69 100644 --- a/block.h +++ b/block.h @@ -182,6 +182,7 @@ int bdrv_is_removable(BlockDriverState *bs); int bdrv_is_read_only(BlockDriverState *bs); int bdrv_is_sg(BlockDriverState *bs); int bdrv_enable_write_cache(BlockDriverState *bs); +int bdrv_is_fd_protocol(BlockDriverState *bs); int bdrv_is_inserted(BlockDriverState *bs); int bdrv_media_changed(BlockDriverState *bs); int bdrv_is_locked(BlockDriverState *bs); diff --git a/block/cow.c b/block/cow.c index 4cf543c..e17f8e7 100644 --- a/block/cow.c +++ b/block/cow.c @@ -82,6 +82,11 @@ static int cow_open(BlockDriverState *bs, int flags) pstrcpy(bs->backing_file, sizeof(bs->backing_file), cow_header.backing_file); + if (bs->backing_file[0] != '\0' && bdrv_is_fd_protocol(bs)) { + /* backing file currently not supported by fd: protocol */ + goto fail; + } + bitmap_size = ((bs->total_sectors + 7) >> 3) + sizeof(cow_header); s->cow_sectors_offset = (bitmap_size + 511) & ~511; return 0; diff --git a/block/qcow.c b/block/qcow.c index 227b104..964d411 100644 --- a/block/qcow.c +++ b/block/qcow.c @@ -157,6 +157,11 @@ static int qcow_open(BlockDriverState *bs, int flags) if (bdrv_pread(bs->file, header.backing_file_offset, bs->backing_file, len) != len) goto fail; bs->backing_file[len] = '\0'; + + if (bs->backing_file[0] != '\0' && bdrv_is_fd_protocol(bs)) { + /* backing file currently not supported by fd: protocol */ + goto fail; + } } return 0; diff --git a/block/qcow2.c b/block/qcow2.c index 48e1b95..7f6a4fa 100644 --- a/block/qcow2.c +++ b/block/qcow2.c @@ -270,6 +270,11 @@ static int qcow2_open(BlockDriverState *bs, int flags) goto fail; } bs->backing_file[len] = '\0'; + + if (bs->backing_file[0] != '\0' && bdrv_is_fd_protocol(bs)) { + ret = -ENOTSUP; + goto fail; + } } if (qcow2_read_snapshots(bs) < 0) { ret = -EINVAL; diff --git a/block/qed.c b/block/qed.c index 3970379..5028897 100644 --- a/block/qed.c +++ b/block/qed.c @@ -446,6 +446,10 @@ static int bdrv_qed_open(BlockDriverState *bs, int flags) return ret; } + if (bs->backing_file[0] != '\0' && bdrv_is_fd_protocol(bs)) { + return -ENOTSUP; + } + if (s->header.features & QED_F_BACKING_FORMAT_NO_PROBE) { pstrcpy(bs->backing_format, sizeof(bs->backing_format), "raw"); } diff --git a/block/raw-posix.c b/block/raw-posix.c index 34b64aa..cec4d36 100644 --- a/block/raw-posix.c +++ b/block/raw-posix.c @@ -28,6 +28,7 @@ #include "block_int.h" #include "module.h" #include "block/raw-posix-aio.h" +#include "monitor.h" #ifdef CONFIG_COCOA #include <paths.h> @@ -185,7 +186,8 @@ static int raw_open_common(BlockDriverState *bs, const char *filename, int bdrv_flags, int open_flags) { BDRVRawState *s = bs->opaque; - int fd, ret; + int fd = -1; + int ret; ret = raw_normalize_devicepath(&filename); if (ret != 0) { @@ -207,15 +209,17 @@ static int raw_open_common(BlockDriverState *bs, const char *filename, if (!(bdrv_flags & BDRV_O_CACHE_WB)) s->open_flags |= O_DSYNC; - s->fd = -1; - fd = qemu_open(filename, s->open_flags, 0644); - if (fd < 0) { - ret = -errno; - if (ret == -EROFS) - ret = -EACCES; - return ret; + if (s->fd == -1) { + fd = qemu_open(filename, s->open_flags, 0644); + if (fd < 0) { + ret = -errno; + if (ret == -EROFS) { + ret = -EACCES; + } + return ret; + } + s->fd = fd; } - s->fd = fd; s->aligned_buf = NULL; if ((bdrv_flags & BDRV_O_NOCACHE)) { @@ -272,6 +276,7 @@ static int raw_open(BlockDriverState *bs, const char *filename, int flags) { BDRVRawState *s = bs->opaque; + s->fd = -1; s->type = FTYPE_FILE; return raw_open_common(bs, filename, flags, 0); } @@ -892,6 +897,60 @@ static BlockDriver bdrv_file = { .create_options = raw_create_options, }; +static int raw_open_fd(BlockDriverState *bs, const char *filename, int flags) +{ + BDRVRawState *s = bs->opaque; + const char *fd_str; + int fd; + + /* extract the file descriptor - fail if it's not fd: */ + if (!strstart(filename, "fd:", &fd_str)) { + return -EINVAL; + } + + if (!qemu_isdigit(fd_str[0])) { + /* get fd from monitor */ + fd = qemu_get_fd(fd_str); + if (fd == -1) { + return -EBADF; + } + } else { + char *endptr = NULL; + + fd = strtol(fd_str, &endptr, 10); + if (*endptr || (fd == 0 && fd_str == endptr)) { + return -EBADF; + } + } + + s->fd = fd; + s->type = FTYPE_FILE; + + return raw_open_common(bs, filename, flags, 0); +} + +static BlockDriver bdrv_file_fd = { + .format_name = "file", + .protocol_name = "fd", + .instance_size = sizeof(BDRVRawState), + .bdrv_probe = NULL, /* no probe for protocols */ + .bdrv_file_open = raw_open_fd, + .bdrv_read = raw_read, + .bdrv_write = raw_write, + .bdrv_close = raw_close, + .bdrv_flush = raw_flush, + .bdrv_discard = raw_discard, + + .bdrv_aio_readv = raw_aio_readv, + .bdrv_aio_writev = raw_aio_writev, + .bdrv_aio_flush = raw_aio_flush, + + .bdrv_truncate = raw_truncate, + .bdrv_getlength = raw_getlength, + + .create_options = raw_create_options, +}; + /***********************************************/ /* host device */ @@ -1000,6 +1059,7 @@ static int hdev_open(BlockDriverState *bs, const char *filename, int flags) } #endif + s->fd = -1; s->type = FTYPE_FILE; #if defined(__linux__) { @@ -1170,6 +1230,7 @@ static int floppy_open(BlockDriverState *bs, const char *filename, int flags) BDRVRawState *s = bs->opaque; int ret; + s->fd = -1; s->type = FTYPE_FD; /* open will not fail even if no floppy is inserted, so add O_NONBLOCK */ @@ -1288,6 +1349,7 @@ static int cdrom_open(BlockDriverState *bs, const char *filename, int flags) { BDRVRawState *s = bs->opaque; + s->fd = -1; s->type = FTYPE_CD; /* open will not fail even if no CD is inserted, so add O_NONBLOCK */ @@ -1517,6 +1579,7 @@ static void bdrv_file_init(void) * Register all the drivers. Note that order is important, the driver * registered last will get probed first. */ + bdrv_register(&bdrv_file_fd); bdrv_register(&bdrv_file); bdrv_register(&bdrv_host_device); #ifdef __linux__ diff --git a/block/vmdk.c b/block/vmdk.c index 922b23d..2ea808e 100644 --- a/block/vmdk.c +++ b/block/vmdk.c @@ -353,6 +353,11 @@ static int vmdk_parent_open(BlockDriverState *bs) return -1; pstrcpy(bs->backing_file, end_name - p_name + 1, p_name); + + if (bs->backing_file[0] != '\0' && bdrv_is_fd_protocol(bs)) { + /* backing file currently not supported by fd: protocol */ + return -1; + } } return 0; diff --git a/block_int.h b/block_int.h index 1e265d2..441049c 100644 --- a/block_int.h +++ b/block_int.h @@ -152,6 +152,7 @@ struct BlockDriverState { int encrypted; /* if true, the media is encrypted */ int valid_key; /* if true, a valid encryption key has been set */ int sg; /* if true, the device is a /dev/sg* */ + int fd_protocol; /* if true, the fd: protocol was specified */ /* event callback when inserting/removing */ void (*change_cb)(void *opaque, int reason); void *change_opaque; diff --git a/blockdev.c b/blockdev.c index c263663..5cb7b56 100644 --- a/blockdev.c +++ b/blockdev.c @@ -542,6 +542,14 @@ DriveInfo *drive_init(QemuOpts *opts, int default_to_scsi) bdrv_flags |= ro ? 0 : BDRV_O_RDWR; + if (strncmp(file, "fd:", 3) == 0) { + if (media == MEDIA_CDROM) { + error_report("CD-ROM not supported by fd: protocol"); + goto err; + } + dinfo->bdrv->fd_protocol = 1; + } + ret = bdrv_open(dinfo->bdrv, file, bdrv_flags, drv); if (ret < 0) { error_report("could not open disk image %s: %s", @@ -602,6 +610,12 @@ int do_snapshot_blkdev(Monitor *mon, const QDict *qdict, QObject **ret_data) goto out; } + if (bdrv_is_fd_protocol(bs)) { + qerror_report(QERR_UNSUPPORTED); + ret = -1; + goto out; + } + pstrcpy(old_filename, sizeof(old_filename), bs->filename); old_drv = bs->drv; @@ -719,6 +733,11 @@ int do_change_block(Monitor *mon, const char *device, BlockDriver *drv = NULL; int bdrv_flags; + if (strncmp(filename, "fd:", 3) == 0) { + qerror_report(QERR_UNSUPPORTED); + return -1; + } + bs = bdrv_find(device); if (!bs) { qerror_report(QERR_DEVICE_NOT_FOUND, device); diff --git a/monitor.c b/monitor.c index a6388a9..e521b60 100644 --- a/monitor.c +++ b/monitor.c @@ -2832,6 +2832,11 @@ int monitor_get_fd(Monitor *mon, const char *fdname) return -1; } +int qemu_get_fd(const char *fdname) +{ + return cur_mon ? monitor_get_fd(cur_mon, fdname) : -1; +} + static const mon_cmd_t mon_cmds[] = { #include "hmp-commands.h" { NULL, NULL, }, diff --git a/monitor.h b/monitor.h index 4f2d328..de5b987 100644 --- a/monitor.h +++ b/monitor.h @@ -51,6 +51,7 @@ int monitor_read_bdrv_key_start(Monitor *mon, BlockDriverState *bs, void *opaque); int monitor_get_fd(Monitor *mon, const char *fdname); +int qemu_get_fd(const char *fdname); void monitor_vprintf(Monitor *mon, const char *fmt, va_list ap) GCC_FMT_ATTR(2, 0); diff --git a/qemu-options.hx b/qemu-options.hx index cb3347e..ab28541 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -116,7 +116,7 @@ using @file{/dev/cdrom} as filename (@pxref{host_drives}). ETEXI DEF("drive", HAS_ARG, QEMU_OPTION_drive, - "-drive [file=file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n" + "-drive [file=[fd:]file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n" " [,cyls=c,heads=h,secs=s[,trans=t]][,snapshot=on|off]\n" " [,cache=writethrough|writeback|none|unsafe][,format=f]\n" " [,serial=s][,addr=A][,id=name][,aio=threads|native]\n" @@ -129,10 +129,12 @@ STEXI Define a new drive. Valid options are: @table @option -@item file=@var{file} +@item file=[fd:]@var{file} This option defines which disk image (@pxref{disk_images}) to use with this drive. If the filename contains comma, you must double it -(for instance, "file=my,,file" to use file "my,file"). +(for instance, "file=my,,file" to use file "my,file"). @option{fd:}@var{file} +specifies the file descriptor of an already open disk image. +@option{format=}@var{format} is required by @option{fd:}@var{file}. @item if=@var{interface} This option defines on which type on interface the drive is connected. Available types are: ide, scsi, sd, mtd, floppy, pflash, virtio. diff --git a/qemu-tool.c b/qemu-tool.c index 41e5c41..8fe6b8c 100644 --- a/qemu-tool.c +++ b/qemu-tool.c @@ -96,3 +96,8 @@ int64_t qemu_get_clock_ns(QEMUClock *clock) { return 0; } + +int qemu_get_fd(const char *fdname) +{ + return -1; +} -- 1.7.3.4

8 20

[libvirt] [PATCH] daemon: Add early libvirtd start verbose errors.
by Peter Krempa 12 Aug '11

12 Aug '11

Early errors during start of libvirtd didn't have an error reporting mechanism and caused libvirtd to exit silently (only the return value indicated an error). This patch adds error messages printed to stderr if verbose parameter is specified to the daemon. fixes: https://bugzilla.redhat.com/show_bug.cgi?id=728654 --- daemon/libvirtd.c | 40 ++++++++++++++++++++++++++++++++-------- 1 files changed, 32 insertions(+), 8 deletions(-) diff --git a/daemon/libvirtd.c b/daemon/libvirtd.c index 53f1002..c3867af 100644 --- a/daemon/libvirtd.c +++ b/daemon/libvirtd.c @@ -1328,14 +1328,20 @@ int main(int argc, char **argv) { case 'p': VIR_FREE(pid_file); - if (!(pid_file = strdup(optarg))) + if (!(pid_file = strdup(optarg))) { + if (verbose) + fprintf(stderr, _("ERROR: Can't allocate memory\n")); exit(EXIT_FAILURE); + } break; case 'f': VIR_FREE(remote_config_file); - if (!(remote_config_file = strdup(optarg))) + if (!(remote_config_file = strdup(optarg))) { + if (verbose) + fprintf(stderr, _("ERROR: Can't allocate memory\n")); exit(EXIT_FAILURE); + } break; case OPT_VERSION: @@ -1353,21 +1359,30 @@ int main(int argc, char **argv) { } } - if (!(config = daemonConfigNew(privileged))) + if (!(config = daemonConfigNew(privileged))) { + if (verbose) + fprintf(stderr, _("ERROR: Can't create configuration\n")); exit(EXIT_FAILURE); + } /* No explicit config, so try and find a default one */ if (remote_config_file == NULL) { implicit_conf = true; if (daemonConfigFilePath(privileged, - &remote_config_file) < 0) + &remote_config_file) < 0) { + if (verbose) + fprintf(stderr, _("ERROR: Can't determine config path\n")); exit(EXIT_FAILURE); + } } /* Read the config file if it exists*/ if (remote_config_file && - daemonConfigLoad(config, remote_config_file, implicit_conf) < 0) + daemonConfigLoad(config, remote_config_file, implicit_conf) < 0) { + if (verbose) + fprintf(stderr, _("ERROR: Can't load config file '%s'\n"), remote_config_file); exit(EXIT_FAILURE); + } if (config->host_uuid && virSetHostUUIDStr(config->host_uuid) < 0) { @@ -1375,19 +1390,28 @@ int main(int argc, char **argv) { exit(EXIT_FAILURE); } - if (daemonSetupLogging(config, privileged, verbose, godaemon) < 0) + if (daemonSetupLogging(config, privileged, verbose, godaemon) < 0) { + if (verbose) + fprintf(stderr, _("ERROR: Can't initialise logging\n")); exit(EXIT_FAILURE); + } + + /* error logging is up, use libvirt's error logging from now */ if (!pid_file && privileged && daemonPidFilePath(privileged, - &pid_file) < 0) + &pid_file) < 0) { + VIR_ERROR(_("Can't determine pid file path.")); exit(EXIT_FAILURE); + } if (daemonUnixSocketPaths(config, privileged, &sock_file, - &sock_file_ro) < 0) + &sock_file_ro) < 0) { + VIR_ERROR(_("Can't determine socket paths")); exit(EXIT_FAILURE); + } if (godaemon) { char ebuf[1024]; -- 1.7.6

3 2

[libvirt] [PATCH] Bugfix: Check stdoutWatch before removing the handler.
by Juerg Haefliger 11 Aug '11

11 Aug '11

--- tools/console.c | 2 +- 1 files changed, 1 insertions(+), 1 deletions(-) diff --git a/tools/console.c b/tools/console.c index 11087e5..171ebc9 100644 --- a/tools/console.c +++ b/tools/console.c @@ -95,7 +95,7 @@ virConsoleShutdown(virConsolePtr con) virStreamFree(con->st); if (con->stdinWatch != -1) virEventRemoveHandle(con->stdinWatch); - if (con->stdinWatch != -1) + if (con->stdoutWatch != -1) virEventRemoveHandle(con->stdoutWatch); con->stdinWatch = -1; con->stdoutWatch = -1; -- 1.7.4.1

4 5

[libvirt] [PATCH 0/2] Directory shouldn't be listed as type 'file' with vol-list command
by Peter Krempa 11 Aug '11

11 Aug '11

After adding option to have directiories as storage volumes virsh reported type of this storage volumes as 'file'. This patch fixes this type in data structures and fixes the virsh output. https://bugzilla.redhat.com/show_bug.cgi?id=727088 Peter Krempa (2): storage: Directory shouldn't be listed as type 'file' virsh: Add dir type for listing volumes with vol-list include/libvirt/libvirt.h.in | 1 + src/storage/storage_backend_fs.c | 4 ++++ tools/virsh.c | 17 +++++++++++++---- 3 files changed, 18 insertions(+), 4 deletions(-) -- 1.7.6

2 3