[libvirt] [PATCH v2 0/5] admin: Introduce APIs to get/set client-related limits
by Erik Skultety
since v1:
- symbols added to libvirt_remote.syms
- APIs renamed
- dropped some unwanted client-side flags checks
- dropped unnecessary ifs before calling virAdmServerFree (because it handles
NULL gracefully)
- a man page entry virt-admin's commands created
Erik Skultety (5):
virnetserver: Introduce server's client-related limits getters
admin: Introduce some public constants related to server's client
limits
admin: Introduce virAdmServerGetClientLimits
admin: Introduce virAdmServerSetClientLimits
virt-admin: Introduce commands srv-clients-info and srv-clients-set
daemon/admin.c | 82 +++++++++++++++++++
daemon/admin_server.c | 76 ++++++++++++++++++
daemon/admin_server.h | 10 +++
include/libvirt/libvirt-admin.h | 52 ++++++++++++
src/admin/admin_protocol.x | 30 ++++++-
src/admin/admin_remote.c | 74 +++++++++++++++++
src/admin_protocol-structs | 20 +++++
src/libvirt-admin.c | 85 ++++++++++++++++++++
src/libvirt_admin_private.syms | 3 +
src/libvirt_admin_public.syms | 2 +
src/libvirt_remote.syms | 4 +
src/rpc/virnetserver.c | 83 +++++++++++++++++++
src/rpc/virnetserver.h | 9 +++
tools/virt-admin.c | 174 ++++++++++++++++++++++++++++++++++++++++
tools/virt-admin.pod | 38 +++++++++
15 files changed, 741 insertions(+), 1 deletion(-)
--
2.5.5
8 years, 7 months
[libvirt] [PATCH] qemu: Don't lose VM runtime state on libvirt downgrade
by Cole Robinson
Run libvirtd from git with latest qemu, start a VM, stop libvirtd.
Run an older libvirtd version an you may see an error like:
qemuDomainObjPrivateXMLParse:857 : internal error: Unknown qemu capabilities flag device-tray-moved-event
Libvirt finds a cached capabilities flag it doesn't understand, and
fails to parse the VM runtime state. It now thinks the VM isn't
running, when it is. This is potentially serious since it could
lead to disk corruption if the VM is re-run.
For the common case of unknown qemu capabilities flags, treat an
unknown flag as non-fatal and continue on
---
src/qemu/qemu_domain.c | 18 +++++++++---------
1 file changed, 9 insertions(+), 9 deletions(-)
diff --git a/src/qemu/qemu_domain.c b/src/qemu/qemu_domain.c
index b0eb3b6..dbf8124 100644
--- a/src/qemu/qemu_domain.c
+++ b/src/qemu/qemu_domain.c
@@ -1411,18 +1411,18 @@ qemuDomainObjPrivateXMLParse(xmlXPathContextPtr ctxt,
goto error;
for (i = 0; i < n; i++) {
+ int flag;
char *str = virXMLPropString(nodes[i], "name");
- if (str) {
- int flag = virQEMUCapsTypeFromString(str);
- if (flag < 0) {
- virReportError(VIR_ERR_INTERNAL_ERROR,
- _("Unknown qemu capabilities flag %s"), str);
- VIR_FREE(str);
- goto error;
- }
- VIR_FREE(str);
+ if (!str)
+ continue;
+
+ flag = virQEMUCapsTypeFromString(str);
+ if (flag < 0) {
+ VIR_WARN("Unknown qemu capabilities flag %s", str);
+ } else {
virQEMUCapsSet(qemuCaps, flag);
}
+ VIR_FREE(str);
}
priv->qemuCaps = qemuCaps;
--
2.7.4
8 years, 7 months
[libvirt] [PATCH] qemu_cgroup: allow access to /dev/dri for virtio-vga
by Ján Tomko
QEMU needs access to the /dev/dri/render* device for
virgl to work.
Allow access to all /dev/dri/* devices for domains with
<video>
<model type='virtio' heads='1' primary='yes'>
<acceleration accel3d='yes'/>
</model>
</video>
https://bugzilla.redhat.com/show_bug.cgi?id=1337290
---
src/qemu/qemu_cgroup.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/src/qemu/qemu_cgroup.c b/src/qemu/qemu_cgroup.c
index 1e04a68..d676d66 100644
--- a/src/qemu/qemu_cgroup.c
+++ b/src/qemu/qemu_cgroup.c
@@ -51,6 +51,7 @@ static const char *const defaultDeviceACL[] = {
};
#define DEVICE_PTY_MAJOR 136
#define DEVICE_SND_MAJOR 116
+#define DEVICE_DRI_MAJOR 226
static int
@@ -626,6 +627,19 @@ qemuSetupDevicesCgroup(virQEMUDriverPtr driver,
goto cleanup;
}
+ if (vm->def->nvideos) {
+ virDomainVideoDefPtr vid = vm->def->videos[0];
+ if (vid->type == VIR_DOMAIN_VIDEO_TYPE_VIRTIO &&
+ vid->accel && vid->accel->accel3d) {
+ rv = virCgroupAllowDevice(priv->cgroup, 'c', DEVICE_DRI_MAJOR, -1,
+ VIR_CGROUP_DEVICE_RW);
+ virDomainAuditCgroupMajor(vm, priv->cgroup, "allow", DEVICE_DRI_MAJOR,
+ "sound", "rw", rv == 0);
+ if (rv < 0)
+ goto cleanup;
+ }
+ }
+
for (i = 0; deviceACL[i] != NULL; i++) {
if (!virFileExists(deviceACL[i])) {
VIR_DEBUG("Ignoring non-existent device %s", deviceACL[i]);
--
2.7.3
8 years, 7 months
[libvirt] [PATCH v4 0/3] Add AES Secret Object support (for RBD only)
by John Ferlan
v3:
http://www.redhat.com/archives/libvir-list/2016-May/msg00444.html
Changes since v3 (by patch)...
1. Separate out the mock for virRandomBytes. I realize this is not the
desired state, but figured to at least be prepared for what would be
coming as a followup to:
http://www.redhat.com/archives/libvir-list/2016-May/msg00735.html
that I'd at least adjust the code to follow using a different random
number generator (use increasing i instead of just 0xff for all)
2. Changes from code review... Change name from IV to AES, plus others
qemuDomainSecretAESSetup is variable based on HAVE_GNUTLS_CIPHER_ENCRYPT
Changes to utilize virStringEncodeBase64
Moved qemuDomainSecretSetup into this version (and made i
3. Split out mock (into patch 1)
Comment cleanup
Still unresolved from code review is a review comment in
qemuBuildDriveStr regarding where the desire movement was.
There's a very specific order to where the "password-secret=%s,"
can be placed. It just wasn't clear from the review comment
where exactly it was expected to "move" those lines
John Ferlan (3):
tests: Add mock for virRandomBytes [NOT TO BE PUSHED]
qemu: Introduce new Secret AES API's
qemu: Utilize qemu secret objects for RBD auth/secret
configure.ac | 1 +
src/qemu/qemu_alias.c | 23 +++
src/qemu/qemu_alias.h | 2 +
src/qemu/qemu_command.c | 122 +++++++++++-
src/qemu/qemu_domain.c | 206 ++++++++++++++++++++-
...muxml2argv-disk-drive-network-rbd-auth-AES.args | 31 ++++
...emuxml2argv-disk-drive-network-rbd-auth-AES.xml | 42 +++++
tests/qemuxml2argvmock.c | 31 +++-
tests/qemuxml2argvtest.c | 3 +
9 files changed, 451 insertions(+), 10 deletions(-)
create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-disk-drive-network-rbd-auth-AES.args
create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-disk-drive-network-rbd-auth-AES.xml
--
2.5.5
8 years, 7 months
[libvirt] [PATCH v2 2/8] Release address in function granularity than slot
by Shivaprasad G Bhat
The commit 6fe678c is partly reverted. The code is moved around and cant revert
staright.
Signed-off-by: Shivaprasad G Bhat <sbhat(a)linux.vnet.ibm.com>
---
src/conf/domain_addr.c | 22 +++++++++-------------
src/libvirt_private.syms | 1 +
src/qemu/qemu_domain_address.c | 2 +-
3 files changed, 11 insertions(+), 14 deletions(-)
diff --git a/src/conf/domain_addr.c b/src/conf/domain_addr.c
index acd8ce6..35c7cd4 100644
--- a/src/conf/domain_addr.c
+++ b/src/conf/domain_addr.c
@@ -472,21 +472,17 @@ virDomainPCIAddressEnsureAddr(virDomainPCIAddressSetPtr addrs,
goto cleanup;
if (dev->type == VIR_DOMAIN_DEVICE_ADDRESS_TYPE_PCI) {
- /* We do not support hotplug multi-function PCI device now, so we should
- * reserve the whole slot. The function of the PCI device must be 0.
- */
- if (dev->addr.pci.function != 0) {
- virReportError(VIR_ERR_INTERNAL_ERROR, "%s",
- _("Only PCI device addresses with function=0"
- " are supported"));
- goto cleanup;
- }
+ if (((dev->addr.pci.function == 0) && (dev->addr.pci.multi == VIR_TRISTATE_SWITCH_ON)) ||
+ dev->addr.pci.function != 0) {
- if (!virDomainPCIAddressValidate(addrs, &dev->addr.pci,
- addrStr, flags, true))
- goto cleanup;
+ if (!virDomainPCIAddressValidate(addrs, &dev->addr.pci,
+ addrStr, flags, true))
+ goto cleanup;
- ret = virDomainPCIAddressReserveSlot(addrs, &dev->addr.pci, flags);
+ ret = virDomainPCIAddressReserveAddr(addrs, &dev->addr.pci, flags, false, true);
+ } else {
+ ret = virDomainPCIAddressReserveSlot(addrs, &dev->addr.pci, flags);
+ }
} else {
ret = virDomainPCIAddressReserveNextSlot(addrs, dev, flags);
}
diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms
index fb24808..e4953b7 100644
--- a/src/libvirt_private.syms
+++ b/src/libvirt_private.syms
@@ -98,6 +98,7 @@ virDomainPCIAddressBusSetModel;
virDomainPCIAddressEnsureAddr;
virDomainPCIAddressFlagsCompatible;
virDomainPCIAddressGetNextSlot;
+virDomainPCIAddressReleaseAddr;
virDomainPCIAddressReleaseSlot;
virDomainPCIAddressReserveAddr;
virDomainPCIAddressReserveNextSlot;
diff --git a/src/qemu/qemu_domain_address.c b/src/qemu/qemu_domain_address.c
index 9c8c262..1e7d98c 100644
--- a/src/qemu/qemu_domain_address.c
+++ b/src/qemu/qemu_domain_address.c
@@ -1682,7 +1682,7 @@ qemuDomainReleaseDeviceAddress(virDomainObjPtr vm,
NULLSTR(devstr));
else if (info->type == VIR_DOMAIN_DEVICE_ADDRESS_TYPE_PCI &&
virQEMUCapsGet(priv->qemuCaps, QEMU_CAPS_DEVICE) &&
- virDomainPCIAddressReleaseSlot(priv->pciaddrs,
+ virDomainPCIAddressReleaseAddr(priv->pciaddrs,
&info->addr.pci) < 0)
VIR_WARN("Unable to release PCI address on %s",
NULLSTR(devstr));
8 years, 7 months
[libvirt] [PATCH 0/4] qemu: Assign addresses via virDomainDefPostParse
by Cole Robinson
This series adds a new domain post parse callback
virDomainDefAssignAddressesCallback, which we use in the qemu driver to
trigger qemuDomainAssignAddresses via PostParse. This streamlines
things a bit, but is also needed for some future work.
After this series, the only remaining open coded
qemuDomainAssignAddresses calls involve populating the runtime VM
address caches, which I discussesd here:
http://www.redhat.com/archives/libvir-list/2016-May/msg01071.html
Cole Robinson (4):
domain: Add virDomainDefAssignAddressesCallback
qemu: Assign device addresses in PostParse
qemu: Remove redundant qemuDomainAssignAddresses calls
qemu: Call virDomainDefPostParse via CONFIG hotplug
src/conf/domain_conf.c | 7 ++
src/conf/domain_conf.h | 8 ++
src/qemu/qemu_domain.c | 25 ++++++
src/qemu/qemu_driver.c | 90 +++++++++-------------
.../qemuargv2xmldata/qemuargv2xml-pseries-disk.xml | 4 +-
tests/qemuxml2argvtest.c | 2 +-
tests/qemuxml2xmltest.c | 11 +--
7 files changed, 83 insertions(+), 64 deletions(-)
--
2.7.4
8 years, 7 months
[libvirt] [PATCH 0/2] vz: add domain snapshots functionality
by Nikolay Shirokovskiy
The first patch do all the job. It is rather large but does not touch
any existing code so I found it reasonable not to split it.
Nikolay Shirokovskiy (2):
vz: add domain snapshots functionality
vz: drop prlsdkDomainHasSnapshots
src/libvirt_private.syms | 2 +
src/vz/vz_driver.c | 535 +++++++++++++++++++++++++++++++++++++++++++++++
src/vz/vz_sdk.c | 303 +++++++++++++++++++++------
src/vz/vz_sdk.h | 5 +
src/vz/vz_utils.h | 1 +
5 files changed, 777 insertions(+), 69 deletions(-)
--
1.8.3.1
8 years, 7 months
[libvirt] [PATCH] Revert "qemu_hotplug: fix checking graphics ports"
by Pavel Hrdina
This reverts commit 1ccc7fbff34ea44e5b0cf01a359d127a4c62a695.
We cannot check ports if autoport is set because we set ports to 0 while
parsing device XML.
Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1336134
Signed-off-by: Pavel Hrdina <phrdina(a)redhat.com>
---
src/qemu/qemu_hotplug.c | 13 ++++++++-----
.../qemuhotplug-graphics-spice-listen-network.xml | 2 +-
2 files changed, 9 insertions(+), 6 deletions(-)
diff --git a/src/qemu/qemu_hotplug.c b/src/qemu/qemu_hotplug.c
index f40b34d..07b419d 100644
--- a/src/qemu/qemu_hotplug.c
+++ b/src/qemu/qemu_hotplug.c
@@ -2666,8 +2666,9 @@ qemuDomainChangeGraphics(virQEMUDriverPtr driver,
switch (dev->type) {
case VIR_DOMAIN_GRAPHICS_TYPE_VNC:
- if (olddev->data.vnc.autoport != dev->data.vnc.autoport ||
- olddev->data.vnc.port != dev->data.vnc.port) {
+ if ((olddev->data.vnc.autoport != dev->data.vnc.autoport) ||
+ (!dev->data.vnc.autoport &&
+ (olddev->data.vnc.port != dev->data.vnc.port))) {
virReportError(VIR_ERR_OPERATION_UNSUPPORTED, "%s",
_("cannot change port settings on vnc graphics"));
goto cleanup;
@@ -2709,9 +2710,11 @@ qemuDomainChangeGraphics(virQEMUDriverPtr driver,
break;
case VIR_DOMAIN_GRAPHICS_TYPE_SPICE:
- if (olddev->data.spice.autoport != dev->data.spice.autoport ||
- olddev->data.spice.port != dev->data.spice.port ||
- olddev->data.spice.tlsPort != dev->data.spice.tlsPort) {
+ if ((olddev->data.spice.autoport != dev->data.spice.autoport) ||
+ (!dev->data.spice.autoport &&
+ (olddev->data.spice.port != dev->data.spice.port)) ||
+ (!dev->data.spice.autoport &&
+ (olddev->data.spice.tlsPort != dev->data.spice.tlsPort))) {
virReportError(VIR_ERR_OPERATION_UNSUPPORTED, "%s",
_("cannot change port settings on spice graphics"));
goto cleanup;
diff --git a/tests/qemuhotplugtestdata/qemuhotplug-graphics-spice-listen-network.xml b/tests/qemuhotplugtestdata/qemuhotplug-graphics-spice-listen-network.xml
index f2a6aeb..426a14d 100644
--- a/tests/qemuhotplugtestdata/qemuhotplug-graphics-spice-listen-network.xml
+++ b/tests/qemuhotplugtestdata/qemuhotplug-graphics-spice-listen-network.xml
@@ -1,4 +1,4 @@
- <graphics autoport='yes' connected='disconnect' keymap='en-us' passwd='password2' passwdValidTo='2013-06-20T01:34:37' type='spice'>
+ <graphics autoport='yes' connected='disconnect' keymap='en-us' passwd='password2' passwdValidTo='2013-06-20T01:34:37' port='5900' tlsPort='5901' type='spice'>
<listen address='10.65.210.231' network='vdsm-rhevm' type='network'/>
<channel mode='secure' name='main'/>
<channel mode='secure' name='display'/>
--
2.8.2
8 years, 7 months
[libvirt] [PATCH 0/4] qemu: support for SLIC ACPI tables
by Ján Tomko
Windows uses this BLOB for activation purposes.
https://bugzilla.redhat.com/show_bug.cgi?id=1327537
Ján Tomko (4):
Separate virDomainDefParseBootOptions
conf: add <acpi table> to <os>
qemu: format SLIC ACPI table command line
security: label the slic_table
docs/formatdomain.html.in | 6 +
docs/schemas/domaincommon.rng | 10 ++
src/conf/domain_conf.c | 159 +++++++++++++--------
src/conf/domain_conf.h | 1 +
src/qemu/qemu_command.c | 4 +
src/security/security_dac.c | 5 +
src/security/security_selinux.c | 5 +
src/security/virt-aa-helper.c | 4 +
.../qemuxml2argvdata/qemuxml2argv-acpi-table.args | 19 +++
tests/qemuxml2argvdata/qemuxml2argv-acpi-table.xml | 28 ++++
tests/qemuxml2argvtest.c | 2 +
.../qemuxml2xmlout-acpi-table.xml | 32 +++++
tests/qemuxml2xmltest.c | 3 +
13 files changed, 215 insertions(+), 63 deletions(-)
create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-acpi-table.args
create mode 100644 tests/qemuxml2argvdata/qemuxml2argv-acpi-table.xml
create mode 100644 tests/qemuxml2xmloutdata/qemuxml2xmlout-acpi-table.xml
--
2.7.3
8 years, 7 months
[libvirt] [PATCH v2 0/4] Don't disable auto_login for iSCSI targets
by John Ferlan
v1: http://www.redhat.com/archives/libvir-list/2016-May/msg01027.html
Changes since v2:
* Patch 2
* Remove the 'str' fetch/free - it was unnecessary
* Initialize and free 'error'
* Did not adjust reported error since with the usage of exitstatus
the call to virCommandRunRegex, that means the virCommandWait code
will return the error rather than reporting it. So the reporting is
left to this code to handle. Kept the same error code (INTERNAL) as
virCommandWait
Patch 3-5
* Remove 3, combine 4 & 5, but remove the setting of the autologin for
libvirt managed targets. This is essentially Fritz's initial patch:
http://www.redhat.com/archives/libvir-list/2016-May/msg00002.html
but with the adjustment to add the "ATTRIBUTE_UNUSED" for the
initiatoriqn parameter (it'll be removed in the next patch as
it is a bit more invasive).
Fritz Elfert (1):
util: Remove disabling of autologin for iscsi-targets
John Ferlan (3):
util: Add exitstatus parameter to virCommandRunRegex
iscsi: Add exit status checking for virISCSIGetSession
iscsi: Remove initiatoriqn from virISCSIScanTargets
src/storage/storage_backend_fs.c | 2 +-
src/storage/storage_backend_iscsi.c | 8 ++---
src/storage/storage_backend_logical.c | 10 +++---
src/util/vircommand.c | 9 ++++--
src/util/vircommand.h | 3 +-
src/util/viriscsi.c | 60 +++++++++++++++--------------------
src/util/viriscsi.h | 1 -
tests/viriscsitest.c | 7 ++--
8 files changed, 46 insertions(+), 54 deletions(-)
--
2.5.5
8 years, 7 months
