- 26 4月, 2018 3 次提交
-
-
由 Martin Kletzander 提交于
That is a job of libvirtd and virtlogd has a dependency on it, so that will prevent it properly. Doing it one extra time in virtlogd might also cause AVC denials because it is not allowed to call that dbus method. Caused by commit df34363d. Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1547250Signed-off-by: NMartin Kletzander <mkletzan@redhat.com> Reviewed-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Ján Tomko 提交于
The script assumed to be run in the source directory. Pass top_srcdir as the argument to fix VPATH builds. My commit 81a7571 broke this. Signed-off-by: NJán Tomko <jtomko@redhat.com>
-
由 Ján Tomko 提交于
Introduce a perl script that is able to regroup both the QEMU_CAPS constants and the capability strings. Check correct grouping as a part of syntax check. For in-place regrouping after a rebase, just run: tests/group-qemu-caps.pl without any parameters. Signed-off-by: NJán Tomko <jtomko@redhat.com> Reviewed-by: NJohn Ferlan <jferlan@redhat.com>
-
- 25 4月, 2018 10 次提交
-
-
由 Daniel P. Berrangé 提交于
Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Roman Bogorodskiy 提交于
virNetDevTapGetRealDeviceName() is used on FreeBSD because interface names (such as one sees in output of tools like ifconfig(8)) might not match their /dev entity names, and for bhyve we need the latter. Current implementation is not very efficient because in order to find /dev name, it goes through all /dev/tap* entries and tries to issue TAPGIFNAME ioctl on it. Not only this is slow, but also there's a bug in this implementation when more than one NIC is passed to a VM: once we find the tap interface we're looking for, we set its state to UP because opening it for issuing ioctl sets it DOWN, even if it was UP before. When we have more than 1 NIC for a VM, we have only last one UP because others remain DOWN after unsuccessful attempts to match interface name. New implementation just uses sysctl(3), so it should be faster and won't make interfaces go down to get name. Signed-off-by: NRoman Bogorodskiy <bogorodskiy@gmail.com> Reviewed-by: NMichal Privoznik <mprivozn@redhat.com>
-
由 Daniel P. Berrangé 提交于
The code for building UNIX socket paths will be getting more complex to cope with accessing various different daemons. Refactor it to eliminate the code duplication and isolation the logic for constructing paths. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
Currently the remote driver extracts the transport from URI scheme and plays games to temporarily hide the driver part when formatting URIs. Refactor the code to split the URI scheme upfront so the two pieces are easily available where needed. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
The libvirtd daemon currently ignores the return status of virDriverLoadModule entirely. This is way too loose, resulting in many important problems going undiagnosed, resulting in a libvirtd that may never work correctly. We should only ignore a non-existant module, and pass back any fatal errors. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
Currently the driver module loading code does not report an error if the driver module is physically missing on disk. This is useful for distro packaging optional pieces. When the daemons are split up into one daemon per driver, we will expect module loading to always succeed. If a driver is not desired, the entire daemon should not be installed. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
The driver module loading code is one of the few places that still uses VIR_ERROR for reporting failures. Convert it to normal error reporting APIs. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
Currently we do a access(R_OK) check to see whether a loadable module exists, treating failure as non-fatal. This is unreasonably loose, as a module which exists but has had incorrect permissions set will turn into a silent skip. We only want to skip loading if the module genuinely does not exist on disk, due to the optional package not being installed. Furthermore, checking the return value of virDriverLoadModuleFile() is not a suitable witness that the module does not exist. This method can return NULL if dlopen() fails, for example due to being unable to resolve symbols in the library. This is should always be reported as an error because it is a sign of the bad installation where either the module build doesn't match the libvirtd build, or where some 3rd party libraries are missing or broken. Both these problems can be fixed by using virFileExists in the caller instead. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
The virFileFindResource method merely builds up the expected fully qualified path to the resource. It does not actually check if it exists on disk. The loadable module callers were mistakenly thinking a NULL indicates the file doesn't exist on disk, whereas it in fact indicates an out of memory error. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
Now that we've activated two hacks to prevent unloading of modules, there is no point passing back a pointer to the loaded library handle. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
- 24 4月, 2018 8 次提交
-
-
由 Daniel P. Berrangé 提交于
We previously added "-z nodelete" to the build of libvirt.so to prevent crashes when thread local destructors run which point to a code that has been dlclose()d: commit 8e44e559 Author: Daniel P. Berrange <berrange@redhat.com> Date: Thu Sep 1 17:57:06 2011 +0100 Prevent crash from dlclose() of libvirt.so The libvirtd loadable modules can suffer from the same problem if they were ever unloaded. Fortunately we don't ever call dlclose() on them, but lets add a second layer of protection by linking them with the "-z nodelete" flag. While we're doing this, lets add a third layer of protection by passing RTLD_NODELETE to dlopen(). Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
The Xen driver was recently deleted, but libvirtd has left over code that tries to use it. Fortunately this is dead code because WITH_XEN will never be defined anymore. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Daniel P. Berrangé 提交于
We previously added "-z nodelete" to the build of libvirt.so to prevent crashes when thread local destructors run which point to a code that has been dlclose()d: commit 8e44e559 Author: Daniel P. Berrange <berrange@redhat.com> Date: Thu Sep 1 17:57:06 2011 +0100 Prevent crash from dlclose() of libvirt.so We forgot to copy this protection into the libvirt-qemu.so, libvirt-lxc.so and libvirt-admin.so libraries when we introduced them. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 John Ferlan 提交于
Although legal, a few paths were not checking a return value < 0 for failure instead they checked a non zero failure. Clean them all up to be consistent. Signed-off-by: NJohn Ferlan <jferlan@redhat.com>
-
由 Michal Privoznik 提交于
https://bugzilla.redhat.com/show_bug.cgi?id=1569678 On some large systems (with ~400GB of RAM) it is possible for unsigned int to overflow in which case we report invalid number of 4K pages pool size. Switch to unsigned long long. We hit overflow in virNumaGetPages when doing: huge_page_sum += 1024 * page_size * page_avail; because although 'huge_page_sum' is an unsigned long long, the page_size and page_avail are both unsigned int, so the promotion to unsigned long long doesn't happen until the sum has been calculated, by which time we've already overflowed. Turning page_avail into a unsigned long long is not strictly needed until we need ability to represent more than 2^32 4k pages, which equates to 16 TB of RAM. That's not outside the realm of possibility, so makes sense that we change it to unsigned long long to avoid future problems. Signed-off-by: NMichal Privoznik <mprivozn@redhat.com> Reviewed-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Christian Ehrhardt 提交于
If another event in background while running libvirt-guests.sh completely undefines a guest it will no more be available for proper reporting of its shutdown. This appears in the log as: Failed to determint state of guest: <UUID>. Not tracking it anymore Shutdown of guest complete The first message already reports that we are giving up on the guest (per UUID which is all we have left at that point). To avoid the message with an empty guest_name in such a case lets check what guest_name returned and only print a report on valid content. Signed-off-by: NChristian Ehrhardt <christian.ehrhardt@canonical.com> Signed-off-by: NMichal Privoznik <mprivozn@redhat.com> Reviewed-by: NAndrea Bolognani <abologna@redhat.com> Reviewed-by: NDariusz Gadomski <dariusz.gadomski@canonical.com>
-
由 Christian Ehrhardt 提交于
The recent fix to libvirt-guests.sh.in works for what it intended to fix (variable scope) but failed to adapt the loop in check_guests_shutdown correctly. Due to that it currently might detect all guests as "Failed to determine state of guest" by bad var content or just assumes they are shut down by picking up an empty variable. This commit fixes loop to use the passed value and the call in the loop to actually use the variable assigned in the iterated. Fixes: 7e476356 "tools: fix variable scope in in check_guests_shutdown" Fixes: https://bugs.launchpad.net/ubuntu/+source/libvirt/+bug/1764668Reviewed-by: NDariusz Gadomski <dariusz.gadomski@canonical.com> Signed-off-by: NChristian Ehrhardt <christian.ehrhardt@canonical.com> Signed-off-by: NMichal Privoznik <mprivozn@redhat.com> Reviewed-by: NAndrea Bolognani <abologna@redhat.com>
-
- 23 4月, 2018 7 次提交
-
-
由 Andrea Bolognani 提交于
Signed-off-by: NAndrea Bolognani <abologna@redhat.com>
-
由 Andrea Bolognani 提交于
Even though we just introduced the rom.enabled attribute to properly cover the use case, there might be guests out there that use the only previously available way of disabling PCI ROM loading by not opting in to schema validation. To make sure such guests will keep working going forward, introduce a test case covering the legacy workaround. Signed-off-by: NAndrea Bolognani <abologna@redhat.com>
-
由 Andrea Bolognani 提交于
The attribute can be used to disable ROM loading completely for a device. This might be needed because, even when the guest is configured such that the PCI ROM will not be loaded in the PCI BAR, some hypervisors (eg. QEMU) might still make it available to the guest in a form (eg. fw_cfg) that some firmwares (eg. SeaBIOS) will consume, thus not achieving the desired result. Resolves: https://bugzilla.redhat.com/show_bug.cgi?id=1425058Signed-off-by: NAndrea Bolognani <abologna@redhat.com>
-
由 Andrea Bolognani 提交于
The attribute can be used to disable ROM loading completely for a device. This might be needed because, even when the guest is configured such that the PCI ROM will not be loaded in the PCI BAR, some hypervisors (eg. QEMU) might still make it available to the guest in a form (eg. fw_cfg) that some firmwares (eg. SeaBIOS) will consume, thus not achieving the desired result. Signed-off-by: NAndrea Bolognani <abologna@redhat.com>
-
由 John Ferlan 提交于
Rework the code such that virDomainObjListFindByID will always return a locked/ref counted object so that the callers can always do the same cleanup logic to call virDomainObjEndAPI. Makes accessing the objects much more consistent. NB: There were 2 callers (lxcDomainLookupByID and qemuDomainLookupByID) that were already using the ByID name, but not virDomainObjEndAPI - these were changed as well in this update/patch. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NJim Fehlig <jfehlig@suse.com>
-
由 John Ferlan 提交于
Now that every caller is using virDomainObjListFindByUUIDRef, let's just remove it and keep the name as virDomainObjListFindByUUID. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NJim Fehlig <jfehlig@suse.com>
-
由 Daniel P. Berrangé 提交于
The "git-publish" tool is a useful git extension for sending patch series for code review. It automatically creates versioned tags each time code on a branch is sent, so that there is a record of each version. It also remembers the cover letter so it does not need re-entering each time the series is reposted. With this config file present it is now sufficient[1] to run $ git publish to send all patches in a branch to the list for review [1] Assuming your $HOME/.gitconfig has an SMTP server listed at least e.g. [sendemail] smtpserver = smtp.example.com Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
- 21 4月, 2018 1 次提交
-
-
由 Jim Fehlig 提交于
Many of the old xm and sexpr test files used qemu-dm as the emulator. Modern Xen systems no longer use the old, forked qemu-dm, instead preferring the distro provided qemu or an "upstream" qemu that is built when the Xen tools are built. This qemu is typically installed in /usr/lib/xen/bin/qemu-system-i386. The libxl test files already use /usr/lib/xen/bin/qemu-system-i386. For consistency, change the old test files to use the same emulator Signed-off-by: NJim Fehlig <jfehlig@suse.com> Reviewed-by: NJán Tomko <jtomko@redhat.com>
-
- 20 4月, 2018 11 次提交
-
-
由 John Ferlan 提交于
For vzDomainLookupByID and vzDomainLookupByUUID let's return a locked and referenced @vm object so that callers can then use the common and more consistent virDomainObjEndAPI in order to handle cleanup rather than needing to know that the returned object is locked and calling virObjectUnlock. The LookupByName already returns the ref counted and locked object, so this will make things more consistent. Also adjust the prlsdkHandle{VmState|VmRemoved|Perf}Event APIs in the same manner. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NNikolay Shirokovskiy <nshirokovskiy@virtuozzo.com>
-
由 John Ferlan 提交于
Rather than have two API's doing different things for different callers, let's make one API that will always return a locked and ref counted object. That way, the callers will always know that they must call virDomainObjEndAPI and not have to decide whether they should call virObjectUnlock instead. This will make things consistent with LookupByName which returns the locked and ref counted object. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NNikolay Shirokovskiy <nshirokovskiy@virtuozzo.com>
-
由 John Ferlan 提交于
For vmwareDomObjFromDomainLocked and vmwareDomainLookupByID let's return a locked and referenced @vm object so that callers can then use the common and more consistent virDomainObjEndAPI in order to handle cleanup rather than needing to know that the returned object is locked and calling virObjectUnlock. The LookupByName already returns the ref counted and locked object, so this will make things more consistent. For vmwareDomainUndefineFlags and vmwareDomainShutdownFlags since virDomainObjListRemove will return an unlocked object, we need to relock before making the EndAPI call. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NPavel Hrdina <phrdina@redhat.com>
-
由 John Ferlan 提交于
If vmwareDomainLookupByID or vmwareDomainLookupByName fails to find a vm, let's be a bit more descriptive by providing the failing id or name in the error message. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NPavel Hrdina <phrdina@redhat.com>
-
由 John Ferlan 提交于
Rather than repeat code throughout, create and use a couple of accessors in order to lookup by UUID. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NPavel Hrdina <phrdina@redhat.com>
-
由 John Ferlan 提交于
The virDomainObjListFindByName returns a locked and reffed domain object, all we did was unlock it, leaving an extra ref. Use the virDomainObjEndAPI to cleanup instead. Signed-off-by: NJohn Ferlan <jferlan@redhat.com> Reviewed-by: NPavel Hrdina <phrdina@redhat.com>
-
由 Daniel P. Berrangé 提交于
The generated source files for dispatching libvirtd RPC messages contain translations and are thus listed in POTFILES. This means they are required in order to build libvirt.pot. Rather than changing the files that go into libvirt.pot dynamically, just unconditionally build the remote driver sources so they are always available for building libvirt.pot. This ensures we don't silently loose translation messages based on configure args. This fixes the mingw build which needs to create libvirt.pot but has libvirtd disabled. Signed-off-by: NDaniel P. Berrangé <berrange@redhat.com>
-
由 Michal Privoznik 提交于
While working on discard feature I've noticed some long lines that should be wrapped. Signed-off-by: NMichal Privoznik <mprivozn@redhat.com>
-
由 Pino Toscano 提交于
When writing the VMX file from the domain XML, write cpuid.coresPerSocket if there is a specified CPU topology in the guest. Use the domain XML of esx-in-the-wild-9 in vmx2xml as testcase for xml2vmxtest. Signed-off-by: NPino Toscano <ptoscano@redhat.com> Acked-by: NRichard W.M. Jones <rjones@redhat.com> Reviewed-by: NJán Tomko <jtomko@redhat.com> Signed-off-by: NJán Tomko <jtomko@redhat.com>
-
由 Pino Toscano 提交于
Convert the cpuid.coresPerSocket key as both number of CPU sockets, and cores per socket. Add the VMX file attached to RHBZ#1568148 as testcase esx-in-the-wild-9; adapt the resulting XML of testcase esx-in-the-wild-8 to the CPU topology present in that VMX. https://bugzilla.redhat.com/show_bug.cgi?id=1568148Signed-off-by: NPino Toscano <ptoscano@redhat.com> Acked-by: NRichard W.M. Jones <rjones@redhat.com> Reviewed-by: NJán Tomko <jtomko@redhat.com> Signed-off-by: NJán Tomko <jtomko@redhat.com>
-
由 John Ferlan 提交于
Commit id '6df5d777' somehow during the move from one branch to another added an erroneous '!'... Signed-off-by: NJohn Ferlan <jferlan@redhat.com>
-