Without this qemu can even start on kvm modules with events support
since default value of exception_injected in zero and this is #DE
exception.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Now, if we inject a fatal MCE into guest OS, for example Linux, Linux
will go panic and then reboot. But if we inject another MCE now,
system will reset directly instead of go panic firstly, because
MCG_STATUS.MCIP is set to 1 and not cleared after reboot. This is does
not follow the behavior in real hardware.
This patch fixes this via set env->mcg_status to 0 during system reset.
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Similarly to what is done in 32938e127f
for "jmp im", trunc the immediate to 32-bit when not running in 64-bit
mode.
Reported-by: Kevin O'Connor <kevin@koconnor.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This reverts commit ebbc8a3d8e76d0402f8a08c10c0f32e24715d41d.
As suggested by Jan Kiszka,
"It was obsoleted by d1793b836f8f123b961c613de1bb1c0c185c84cc and now
saves/restores a useless field."
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
hw_breakpoint_type and hw_breakpoint_len used the wrong index multiplier
to extract type and len.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Marcelo correctly remarked that there are usage conflicts between QEMU
core code and KVM /wrt exception_index. So spend a separate field and
also save/restore it properly.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The CPUID features QEMU presented to the guest were not up-to-date
with QEMU's emulated feature set.
Add the missing bits of recent (and not so recent) additions to
QEMU's emulation engine.
For stability reasons only the user mode usable bits are exposed for
now, features like Monitor or CR8LEG are left out.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Currently, the msrs involved in setting up pvclock are not saved over
migration and/or save/restore. This patch puts their value in special
fields in our CPUState, and deal with them using vmstate.
kvm also has to account for it, by including them in the msr list
for the ioctls.
This is a backport from qemu-kvm.git
[v2: sucessfully build without kerneldir ]
Signed-off-by: Glauber Costa <glommer@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
As KVM now makes use of exception_index to keep pending exceptions, we
have to save&restore this field as well.
NOTE: We have to nail the arch-independent exception_index down to a
certain bit width for proper vmstate processing, namely to 32 bit.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The multicore CPUID code detects whether the guest is an Intel or an
AMD CPU, because the Linux kernel is picky about the CmpLegacy bit.
KVM by default passes through the host's vendor, which was not
catched by the code. So fork out the vendor determining bits into a
separate function to be used from both places and always get the real
vendor.
This fixes KVM's multicore setup on Intel CPUs.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Reported-by: Dietmar Maurer <dietmar@proxmox.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
KVM_GET_MSR_INDEX_LIST returns -E2BIG when the provided space is too
small for all MSRs. But this is precisely the error we trigger with the
initial request in order to obtain that size. Do not fail in that case.
This caused a subtle corruption of the guest state as MSR_STAR was not
properly saved/restored. The corruption became visible with latest kvm
optimizing the MSR updates.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This patch extends the qemu-kvm state sync logic with support for
KVM_GET/SET_VCPU_EVENTS, giving access to yet missing exception,
interrupt and NMI states.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Drop interrupt_bitmap from the cpustate and solely rely on the integer
interupt_injected. This prepares us for the new injected-interrupt
interface, which will deprecate the bitmap, while preserving
compatibility.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
There is absolutely no need to call reset functions when initializing
devices. Since we are already registering them, calling qemu_system_reset()
should suffice. Actually, it is what happens when we reboot the machine,
and using the same process instead of a special case semantics will even
allow us to find bugs easier.
Furthermore, the fact that we initialize things like the cpu quite early,
leads to the need to introduce synchronization stuff like qemu_system_cond.
This patch removes it entirely. All we need to do is call qemu_system_reset()
only when we're already sure the system is up and running
I tested it with qemu (with and without io-thread) and qemu-kvm, and it
seems to be doing okay - although qemu-kvm uses a slightly different patch.
[ v2: user mode still needs cpu_reset, so put it in ifdef. ]
[ v3: leave qemu_system_cond for now. ]
Signed-off-by: Glauber Costa <glommer@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
This allows to define VMSTATE_SINGLE with VMSTATE_SINGLE_TEST
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
lzcnt is a AMD Phenom/Barcelona added instruction returning the
number of leading zero bits in a word.
As this is similar to the "bsr" instruction, reuse the existing
code. There need to be some more changes, though, as lzcnt always
returns a valid value (in opposite to bsr, which has a special
case when the operand is 0).
lzcnt is guarded by the ABM CPUID bit (Fn8000_0001:ECX_5).
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
The arpl implementation in target-i386/translate.c uses cpu_A0
temporary across a brcond op. This patch fixes that issue.
Signed-off-by: Laurent Desnogues <laurent.desnogues@gmail.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This reduce the impact on hosts that have addressing modes with limited
offsets. Suggested by Laurent Desnogues.
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
There was a missmerge, and then we got a tail recursive call to cpu_post_load
without case base :)
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Commit 56aebc8916 changed gdbstub in way
that debugging 32 or 16-bit guest code is no longer possible with qemu
for x86_64 guest CPUs. Since that commit, qemu only provides registers
sets for 64-bit, forcing current and foreseeable gdb to also switch its
architecture to 64-bit. And this breaks if the inferior is 32 or 16 bit.
No question, this is a gdb issue. But, as it was confirmed in several
discusssions with gdb people, it is a non-trivial thing to fix. So until
qemu finds a gdb version attach with a rework x86 support, we have to
work around it by switching the register layout as the guest switches
its execution mode between 16/32 and 64 bit.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
mce_banks is always MCE_BANKS_DEF * 4 in size, value never change
CC: Huang Ying <ying.huang@intel.com>
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Don't even ask, being able to load/save between 64<->80bit floats should be forbidden
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
We save more that fpus on that 16 bits (fpstt), we need an additional field
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This makes the savevm code correct, and sign extensins gives us exactly
what we need (namely, sign extend to 64 bits when used with 64bit addresess.
Once there, change 0x100000 for 1 << 20, that maks all a20 use the same syntax.
Signed-off-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This patch corrects the following aspects of exception generation in
fxsave/fxrstor:
* Generate #GP if the operand is not aligned to a 16 byte boundary
* Generate #UD if the LOCK prefix is used
* For CR0.EM = 1 #NM is generated, not #UD
Signed-off-by: Kevin Wolf <mail@kevin-wolf.de>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
RDTSCP reads the time stamp counter and atomically also the content
of a 32-bit MSR, which can be freely set by the OS. This allows CPU
local data to be queried by userspace.
Linux uses this to allow a fast implementation of the getcpu()
syscall, which uses the vsyscall page to avoid a context switch.
AMD CPUs since K8RevF and Intel CPUs since Nehalem support this
instruction.
RDTSCP is guarded by the RDTSCP CPUID bit (Fn8000_0001:EDX[27]).
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This adds support for the AMD Phenom/Barcelona's SSE4a instructions.
Those include insertq and extrq, which are doing shift and mask on
XMM registers, in two versions (immediate shift/length values and
stored in another XMM register).
Additionally it implements movntss, movntsd, which are scalar
non-temporal stores (avoiding cache trashing). These are implemented
as normal stores, though.
SSE4a is guarded by the SSE4A CPUID bit (Fn8000_0001:ECX[6]).
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
AMD CPUs featuring a shortcut to access CR8 even from 32-bit mode.
If you use the LOCK prefix with "mov CR0", it accesses CR8 instead.
This behavior is guarded by the CR8_LEGACY CPUID bit
(Fn8000_0001:ECX[1]).
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
In the very least, a change like this requires discussion on the list.
The naming convention is goofy and it causes a massive merge problem. Something
like this _must_ be presented on the list first so people can provide input
and cope with it.
This reverts commit 99a0949b72.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The CPU state parameter is not used, remove it and adjust callers. Now we
can compile ioport.c once for all targets.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Problem: Our file sys-queue.h is a copy of the BSD file, but there are
some additions and it's not entirely compatible. Because of that, there have
been conflicts with system headers on BSD systems. Some hacks have been
introduced in the commits 15cc923584,
f40d753718,
96555a96d7 and
3990d09adf but the fixes were fragile.
Solution: Avoid the conflict entirely by renaming the functions and the
file. Revert the previous hacks.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Direct call to kvm_arch_get_registers() bypass logic in
cpu_synchronize_state()
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
cpu_synchronize_state() is a little unreadable since the 'modified'
argument isn't self-explanatory. Simplify it by making it always
synchronize the kernel state into qemu, and automatically flush the
registers back to the kernel if they've been synchronized on this
exit.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
In addition to the TCG based qemu64 type let's introduce a kvm64 CPU type,
which is the least common denominator of all KVM-capable x86-CPUs
(based on Intel Pentium 4 Prescott). It can be used as a base type
for migration.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The CPUID level determines how many CPUID leafs are exposed to the guest.
Some features (like multi-core) cannot be propagated without the proper
level, but guests maybe confused by bogus entries in some leafs.
So add level= and xlevel= to the list of -cpu options to allow the user to
override the default settings. While at it, merge unnecessary local
variables into one and allow hexadecimal arguments.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Controlled by the enhanced -smp option set the CPUID bits to present the
guest the desired topology. This is vendor specific, but (with the exception
of the CMP_LEGACY bit) not conflicting, so we set all bits everytime.
There is no real multithreading support for AMD CPUs, so report cores
instead.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Intel CPUs store the number of cores in CPUID leaf 4. So push
the maxleaf value to 4 to allow the guests access to this leaf.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
handle_cpu_signal is very nearly copy-paste code for each target, with a
few minor variations. This patch sets up appropriate defaults for a
generic handle_cpu_signal and provides overrides for particular targets
that did things differently. Fixing things like the persistent (XXX:
use sigsetjmp) should now become somewhat easier.
Previous comments on this patch suggest that the "activate soft MMU for
this block" comments refer to defunct functionality. I have removed
such blocks for the appropriate targets in this patch.
Signed-off-by: Nathan Froyd <froydnj@codesourcery.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
kqemu introduces a number of restrictions on the i386 target. The worst is that
it prevents large memory from working in the default build.
Furthermore, kqemu is fundamentally flawed in a number of ways. It relies on
the TSC as a time source which will not be reliable on a multiple processor
system in userspace. Since most modern processors are multicore, this severely
limits the utility of kqemu.
kvm is a viable alternative for people looking to accelerate qemu and has the
benefit of being supported by the upstream Linux kernel. If someone can
implement work arounds to remove the restrictions introduced by kqemu, I'm
happy to avoid and/or revert this patch.
N.B. kqemu will still function in the 0.11 series but this patch removes it from
the 0.12 series.
Paul, please Ack or Nack this patch.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Since we recently do not disable 3DNOW! support anymore, we should
avoid setting the bits in the default qemu64 CPU model to ease
migration. TCG does not support it anyway and even AMD deprecates
it's usage nowadays.
If you want to use it in KVM, use the phenom, athlon or host CPU
model.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This allows to set segment registers via gdb also in system emulation
mode. Basic sanity checks are applied and nothing is changed if they
fail. But screwing up the target via this interface will never be
complicated, so I avoided being too paranoid here.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Allocate enough memory for KVM_GET_MSR_INDEX_LIST as older kernels shot
far beyond their limits, corrupting user space memory.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
- MCE features are initialized when VCPU is intialized according to CPUID.
- A monitor command "mce" is added to inject a MCE.
- A new interrupt mask: CPU_INTERRUPT_MCE is added to inject the MCE.
aliguori: fix build for linux-user
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This patch aligns the KVM-related layout and encoding of the CPU state
to be saved to disk or migrated with qemu-kvm. The major differences are
reordering of fields and a compressed interrupt_bitmap into a single
number as there can be no more than one pending IRQ at a time.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
The KVM kernel will disable all bits in CPUID which are not present in
the host. As this is mostly true for the hypervisor bit (1.ecx),
preserve its value before the trim and restore it afterwards.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
KVM provides an in-kernel feature to disable CPUID bits that are not
present in the current host. So there is no need here to duplicate this
work. Additionally allows 3DNow! on capable processors, since the
restriction seems to apply to QEMU/TCG only.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
If we want to trim the user provided CPUID bits for KVM to be not greater
than that of the host, we should not remove the bits _after_ we sent
them to the kernel.
This fixes the masking of features that are not present on the host by
moving the trim function and it's call from helper.c to kvm.c.
It helps to use -cpu host.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Although the guest's CPUID bits can be controlled in a fine grained way
in QEMU, a simple way to inject the host CPU is missing. This is handy
for KVM desktop virtualization, where one wants the guest to support the
full host feature set.
Introduce another CPU type called 'host', which will propagate the host's
CPUID bits to the guest. Unwanted bits can still be turned off by using
the existing syntax (-cpu host,-skinit)
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
KVM defaults to the hypervisor CPUID bit to be set, whereas pure
QEMU clears it. On some occasions one wants to set or clear it the
other way round (for instance to get HyperV running inside a guest).
Move the bit-set to be done before the command line parsing and
enable it by default. One can disable it by using: -cpu qemu64,-hypervisor
Fix some whitespace damage on the way.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This should fix compilation problem in case of CONFIG_USER_ONLY.
Currently INIT/SIPI is handled in the context of CPU that sends IPI.
This patch changes this to handle them like all other events in a main
cpu exec loop. When KVM will gain thread per vcpu capability it will
be much more clear to handle those event by cpu thread itself and not
modify one cpu's state from the context of the other.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
As per the IA32 processor manual, the accessed bit is set to 1 in the
processor state after reset. qemu pc cpu_reset code was missing this
accessed bit setting.
Signed-off-by: Nitin A Kamble <nitin.a.kamble@intel.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
KVM-enabled QEMU will always report the vendor ID of the physical CPU it is
running on. Allow to override this if explicitly requested on the
command line. It will not suffice to name a CPU type (like -cpu phenom),
but you have to explicitly set the vendor: -cpu phenom,vendor=AuthenticAMD
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Save and restore all so far neglected KVM-specific CPU states. Handling
the TSC stabilizes migration in KVM mode. The interrupt_bitmap and
mp_state are currently unused, but will become relevant for in-kernel
irqchip support. By including proper saving/restoring already, we avoid
having to increment CPU_SAVE_VERSION later on once again.
v2:
- initialize mp_state runnable (for the boot CPU)
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
This patch adds the missing hooks to allow live migration in KVM mode.
It adds proper synchronization before/after saving/restoring the VCPU
states (note: PPC is untested), hooks into
cpu_physical_memory_set_dirty_tracking() to enable dirty memory logging
at KVM level, and synchronizes that drity log into QEMU's view before
running ram_live_save().
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
KVM_GET_SUPPORTED_CPUID has been known to fail to return -E2BIG
when it runs out of entries. Detect this by always trying again
with a bigger table if the ioctl() fills the table.
Signed-off-by: Mark McLoughlin <markmc@redhat.com>
Include assert.h from qemu-common.h and remove other direct uses.
cpu-all.h still need to include it because of the dyngen-exec.h hacks
Signed-off-by: Paul Brook <paul@codesourcery.com>
Remove cpu features that are not supported by kvm from the cpuid features
reported to the guest.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
QEMU allows adding or removing cpu features by using the syntax '-cpu +feature'
or '-cpu -feature'. Some cpuid features cause more than one bit to be set or
cleared; but QEMU stops after just one bit has been modified, causing the
feature bits to be inconsistent.
Fix by allowing all feature bits corresponding to a given name to be set.
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Amit Shah
Gleb Natapov
Huang Ying
Aurelien Jarno
Anthony Liguori
Jan Kiszka
Andre Przywara
Glauber Costa
Jan Kiszka
Hollis Blanchard
Blue Swirl
Juan Quintela
Laurent Desnogues
Kevin Wolf
malc
Avi Kivity
Nathan Froyd
Nitin A Kamble
Mark McLoughlin
Paul Brook