ABM is not available on Sandy Bridge and older, and we want to make the
default CPU runnable in most hosts, so it won't be enabled by default in
KVM mode.
We should eventually have all features supported by TCG enabled by
default in TCG mode, but as we don't have a good mechanism today to
ensure we have different defaults in KVM and TCG mode, disable ABM in
the qemu64 CPU model entirely.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
SSE4a is not available in any Intel CPU, and we want to make the default
CPU runnable in most hosts, so it doesn't make sense to enable it by
default in KVM mode.
We should eventually have all features supported by TCG enabled by
default in TCG mode, but as we don't have a good mechanism today to
ensure we have different defaults in KVM and TCG mode, disable SSE4a in
the qemu64 CPU model entirely.
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The commit 317b0a6d8 fixed an issue which caused by the outdated
env->tsc value, but the fix lead to 'cpu_synchronize_all_states()'
called twice during live migration. The 'cpu_synchronize_all_states()'
takes about 130us for a VM which has 4 vcpus, it's a bit expensive.
Synchronize the whole CPU context just for updating env->tsc is too
wasting, this patch use a new function to update the env->tsc.
Comparing to 'cpu_synchronize_all_states()', it only takes about 20us.
Signed-off-by: Liang Li <liang.z.li@intel.com>
Message-Id: <1446695464-27116-2-git-send-email-liang.z.li@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This makes the purpose of the function clearer: it is not about the
version of QEMU that's running, but the version string exposed in the
emulated hardware.
Cc: Andrzej Zaborowski <balrogg@gmail.com>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: John Snow <jsnow@redhat.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <1446233769-7892-3-git-send-email-ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In this mode, referring an invalid element of the source forces the
result to false (table 4-7, last column) but referring an invalid
element of the destination forces the result to true, so the outer
loop should still be run even if some elements of the destination
will be invalid. They will be avoided in the inner loop, which
correctly bounds "i" to validd, but they will still contribute to a
positive outcome of the search.
This fixes tst_strstr in glibc 2.17.
Reported-by: Florian Weimer <fweimer@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Some targets already had this within their logic, but make sure
it's present for all targets.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Current default behavior of QEMU is to silently disable features that
are not supported by the host when a CPU model is requested in the
command-line. This means that in addition to risking breaking guest ABI
by default, we are silent about it.
I would like to enable "enforce" by default, but this can easily break
existing production systems because of the way libvirt makes assumptions
about CPU models today (this will change in the future, once QEMU
provide a proper interface for checking if a CPU model is runnable).
But there's no reason we should be silent about it. So, change
target-i386 to enable "check" mode by default so at least we have some
warning printed to stderr (and hopefully logged somewhere) when QEMU
disables a feature that is not supported by the host system.
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Left shift of negative values is undefined behavior. Detected by clang:
qemu/target-i386/translate.c:2423:26: runtime error:
left shift of negative value -8
This changes the code to reverse the sign after the left shift.
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Fix undefined behavior detected by clang runtime check:
qemu/target-i386/cpu.c:1494:15: runtime error:
left shift of 1 by 31 places cannot be represented in type 'int'
While doing that, add extra parenthesis for clarity.
Reported-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Now DE is supported by TCG so it can be enabled in CPUID bits.
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Bits 4-11 and 16-31 on DR6 are documented as always 1, so ensure they
can't be cleared by software.
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Introduce helper_get_dr so that we don't have to put CR4[DE]
into the scarce HFLAGS resource. At the same time, rename
helper_movl_drN_T0 to helper_set_dr and set the helper flags.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
If the debug register is not enabled, we need
do nothing besides update the register.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Bit 10 of DR7 is documented as always set to 1, so ensure that's
always the case.
Reviewed-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Before the last patch, we had an efficient loop that disabled
local breakpoints on task switch. Re-add that, but in a more
general way that handles changes to the global enable bits too.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
This moves the last of the iteration over breakpoints into
the bpt_helper.c file. This also allows us to make several
breakpoint functions static.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The host cache information may not make sense for the guest if the VM
CPU topology doesn't match the host CPU topology. To make sure we won't
expose broken cache information to the guest, disable cache info
passthrough by default, and add a new "host-cache-info" property that
can be used to enable the old behavior for users that really need it.
Cc: Benoît Canet <benoit@irqsave.net>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Processors up to the Pentium (says Bochs---I do not have old enough
manuals) require a 32KiB alignment for the SMBASE, but newer processors
do not need that, and Tiano Core will use non-aligned SMBASE values.
Reported-by: Michael D Kinney <michael.d.kinney@intel.com>
Cc: Laszlo Ersek <lersek@redhat.com>
Cc: Jordan Justen <jordan.l.justen@intel.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Laszlo Ersek <lersek@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
According to Microsoft documentation, the signature in the standard
hypervisor CPUID leaf at 0x40000000 identifies the Vendor ID and is
for reporting and diagnostic purposes only. We can therefore allow
the user to change it to whatever they want, within the 12 character
limit. Add a new hv-vendor-id option to the -cpu flag to allow
for this, ex:
-cpu host,hv_time,hv-vendor-id=KeenlyKVM
Link: http://msdn.microsoft.com/library/windows/hardware/hh975392
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Message-Id: <20151016153356.28104.48612.stgit@gimli.home>
[Adjust error message to match the property name, use error_report. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
The functions for checking xcrs, xsave and pit_state2 are
only used on x86, so they should reside in target-i386/kvm.c.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <1444933820-6968-1-git-send-email-thuth@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
In-kernel ITS emulation on ARM64 will require to supply requester IDs.
These IDs can now be retrieved from the device pointer using new
pci_requester_id() function.
This patch adds pci_dev pointer to KVM GSI routing functions and makes
callers passing it.
x86 architecture does not use requester IDs, but hw/i386/kvm/pci-assign.c
also made passing PCI device pointer instead of NULL for consistency with
the rest of the code.
Signed-off-by: Pavel Fedin <p.fedin@samsung.com>
Message-Id: <ce081423ba2394a4efc30f30708fca07656bc500.1444916432.git.p.fedin@samsung.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
HV_X64_MSR_VP_RUNTIME msr used by guest to get
"the time the virtual processor consumes running guest code,
and the time the associated logical processor spends running
hypervisor code on behalf of that guest."
Calculation of that time is performed by task_cputime_adjusted()
for vcpu task by KVM side.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
CC: "Andreas Färber" <afaerber@suse.de>
CC: Marcelo Tosatti <mtosatti@redhat.com>
Message-Id: <1442397584-16698-4-git-send-email-den@openvz.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Hyper-V features bit HV_X64_MSR_VP_INDEX_AVAILABLE value is
based on cpu option "hv-vpindex" and kernel support of
HV_X64_MSR_VP_INDEX.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
CC: "Andreas Färber" <afaerber@suse.de>
CC: Marcelo Tosatti <mtosatti@redhat.com>
Message-Id: <1442397584-16698-3-git-send-email-den@openvz.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
HV_X64_MSR_RESET msr is used by Hyper-V based Windows guest
to reset guest VM by hypervisor. This msr is stateless so
no migration/fetch/update is required.
This code checks cpu option "hv-reset" and support by
kernel. If both conditions are met appropriate Hyper-V features
cpuid bit is set.
Signed-off-by: Andrey Smetanin <asmetanin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
CC: "Andreas Färber" <afaerber@suse.de>
CC: Marcelo Tosatti <mtosatti@redhat.com>
Message-Id: <1442397584-16698-2-git-send-email-den@openvz.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Several devices don't survive object_unref(object_new(T)): they crash
or hang during cleanup, or they leave dangling pointers behind.
This breaks at least device-list-properties, because
qmp_device_list_properties() needs to create a device to find its
properties. Broken in commit f4eb32b "qmp: show QOM properties in
device-list-properties", v2.1. Example reproducer:
$ qemu-system-aarch64 -nodefaults -display none -machine none -S -qmp stdio
{"QMP": {"version": {"qemu": {"micro": 50, "minor": 4, "major": 2}, "package": ""}, "capabilities": []}}
{ "execute": "qmp_capabilities" }
{"return": {}}
{ "execute": "device-list-properties", "arguments": { "typename": "pxa2xx-pcmcia" } }
qemu-system-aarch64: /home/armbru/work/qemu/memory.c:1307: memory_region_finalize: Assertion `((&mr->subregions)->tqh_first == ((void *)0))' failed.
Aborted (core dumped)
[Exit 134 (SIGABRT)]
Unfortunately, I can't fix the problems in these devices right now.
Instead, add DeviceClass member cannot_destroy_with_object_finalize_yet
to mark them:
* Hang during cleanup (didn't debug, so I can't say why):
"realview_pci", "versatile_pci".
* Dangling pointer in cpus: most CPUs, plus "allwinner-a10", "digic",
"fsl,imx25", "fsl,imx31", "xlnx,zynqmp", because they create such
CPUs
* Assert kvm_enabled(): "host-x86_64-cpu", host-i386-cpu",
"host-powerpc64-cpu", "host-embedded-powerpc-cpu",
"host-powerpc-cpu" (the powerpc ones can't currently reach the
assertion, because the CPUs are only registered when KVM is enabled,
but the assertion is arguably in the wrong place all the same)
Make qmp_device_list_properties() fail cleanly when the device is so
marked. This improves device-list-properties from "crashes, hangs or
leaves dangling pointers behind" to "fails". Not a complete fix, just
a better-than-nothing work-around. In the above reproducer,
device-list-properties now fails with "Can't list properties of device
'pxa2xx-pcmcia'".
This also protects -device FOO,help, which uses the same machinery
since commit ef52358 "qdev-monitor: include QOM properties in -device
FOO, help output", v2.2. Example reproducer:
$ qemu-system-aarch64 -machine none -device pxa2xx-pcmcia,help
Before:
qemu-system-aarch64: .../memory.c:1307: memory_region_finalize: Assertion `((&mr->subregions)->tqh_first == ((void *)0))' failed.
After:
Can't list properties of device 'pxa2xx-pcmcia'
Cc: "Andreas Färber" <afaerber@suse.de>
Cc: "Edgar E. Iglesias" <edgar.iglesias@gmail.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Anthony Green <green@moxielogic.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: Bastian Koppelmann <kbastian@mail.uni-paderborn.de>
Cc: Blue Swirl <blauwirbel@gmail.com>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: Jia Liu <proljc@gmail.com>
Cc: Leon Alrae <leon.alrae@imgtec.com>
Cc: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Walle <michael@walle.cc>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Maydell <peter.maydell@linaro.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: qemu-ppc@nongnu.org
Cc: qemu-stable@nongnu.org
Signed-off-by: Markus Armbruster <armbru@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Message-Id: <1443689999-12182-10-git-send-email-armbru@redhat.com>
It is no longer used, so tidy up everything reached by it.
This includes the gen_opc_* arrays, the search_pc parameter
and the inline gen_intermediate_code_internal functions.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
The gen_opc_* arrays are already redundant with the data stored in
the insn_start arguments. Transition restore_state_to_opc to use
data from the latter.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Adjust all translators to respect it.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
This symbol no longer exists.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Reduce the boilerplate required for each target. At the same time,
move the test for breakpoint after calling tcg_gen_insn_start.
Note that arm and aarch64 do not use cpu_breakpoint_test, but still
move the inline test down after tcg_gen_insn_start.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
This does tidy the icount test common to all targets.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
While we're at it, emit the opcode adjacent to where we currently
record data for search_pc. This puts gen_io_start et al on the
"correct" side of the marker.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
With an eye toward making it mandatory.
Reviewed-by: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <rth@twiddle.net>
After CPU hotplug has been converted to BUS-less hot-plug infrastructure,
the only function ICC bus performs is to propagate reset to LAPICs. However
LAPIC could be reset by registering its reset handler after all device are
initialized.
Do so and drop ~30LOC of not needed anymore ICCBus related code.
Signed-off-by: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
Signed-off-by: Zhu Guihua <zhugh.fnst@cn.fujitsu.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
When ICC bus/bridge is removed, APIC MMIO will be left
unmapped since it was mapped into system's address space
indirectly by ICC bridge.
Fix it by moving mapping into APIC code, so it would be
possible to remove ICC bus/bridge code later.
Signed-off-by: Chen Fan <chen.fan.fnst@cn.fujitsu.com>
Signed-off-by: Zhu Guihua <zhugh.fnst@cn.fujitsu.com>
Reviewed-by: Igor Mammedov <imammedo@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
When doing a re-initialization of a CPU core, the default state is to _not_
have 64-bit long mode enabled. This means the LME (long mode enable) and LMA
(long mode active) bits in the EFER model-specific register should be cleared.
However, the EFER state is part of the CPU environment which is
preserved by do_cpu_init(), so if EFER.LME and EFER.LMA were set at the
time an INIT IPI was received, they will remain set after the init completes.
This is contrary to what the Intel architecture manual describes and what
happens on real hardware, and it leaves the CPU in a weird state that the
guest can't clear.
To fix this, the 'efer' member of the CPUX86State structure has been moved
to an area outside the region preserved by do_cpu_init(), so that it can
be properly re-initialized by x86_cpu_reset().
Signed-off-by: Bill Paul <wpaul@windriver.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
ABM is only implemented as a single instruction set by AMD; all AMD
processors support both instructions or neither. Intel considers POPCNT
as part of SSE4.2, and LZCNT as part of BMI1, but Intel also uses AMD's
ABM flag to indicate support for both POPCNT and LZCNT. It has to be
added to Haswell and Broadwell because Haswell, by adding LZCNT, has
completed the ABM.
Tested with "qemu-kvm -cpu Haswell-noTSX,enforce" (and also with older
machine types) on an Haswell-EP machine.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
There's one report of migration breaking due to missing MSR_TSC_AUX
save/restore. Fix this by adding a new subsection that saves the state
of this MSR.
https://bugzilla.redhat.com/show_bug.cgi?id=1261797
Reported-by: Xiaoqing Wei <xwei@redhat.com>
Signed-off-by: Amit Shah <amit.shah@redhat.com>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Juan Quintela <quintela@redhat.com>
CC: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
CC: Marcelo Tosatti <mtosatti@redhat.com>
CC: Richard Henderson <rth@twiddle.net>
CC: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
The function is now only used from within a single file.
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
Convert the kvm_default_features and kvm_default_unset_features arrays
into a simple list of property/value pairs that will be applied to
X86CPU objects when using KVM.
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Eduardo Habkost <ehabkost@redhat.com>
This patch updates x86_cpu_exec_interrupt function.
It can process two interrupt request at a time (poll and another one).
This makes its execution non-deterministic. Determinism is requred
for recorded icount execution.
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Message-Id: <20150917162410.8676.13042.stgit@PASHA-ISP.def.inno>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Processing CPU_INTERRUPT_POLL requests in cpu_has_work functions
break the determinism of cpu_exec. This patch is required to make
interrupts processing deterministic.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru>
Message-Id: <20150917162331.8676.15286.stgit@PASHA-ISP.def.inno>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Rename ELF_MACHINE to be I386 specific. This is used as-is by the
multiboot loader.
Linux-user previously used this definition but will not anymore,
falling back to the default bahaviour of using ELF_ARCH as ELF_MACHINE.
This removes another architecture specific definition from the global
namespace.
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Eduardo Habkost <ehabkost@redhat.com>
Acked-by: Eduardo Habkost <ehabkost@redhat.com>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Acked-By: Riku Voipio <riku.voipio@linaro.org>
Signed-off-by: Peter Crosthwaite <crosthwaite.peter@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Added support emulator for the hmp command "info ioapic"
Signed-off-by: Pavel Butsykin <pbutsykin@virtuozzo.com>
Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Paolo Bonzini <pbonzini@redhat.com>
CC: Andreas Färber <afaerber@suse.de>
Message-Id: <1442927901-1084-10-git-send-email-den@openvz.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
