These FPU states are properly maintained by KVM but not yet by TCG. So
far we unconditionally set them to 0 in the guest which may cause
state corruptions, though not with modern guests.
To avoid breaking backward migration, use a conditional subsection that
is only written if any of the three fields is non-zero. The guest's
FNINIT clears them frequently, and cleared IA32_MISC_ENABLE MSR[2]
reduces the probability of non-zero values further so that this
subsection is not expected to restrict migration in any common scenario.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patchset enables a new CPU feature SMEP (Supervisor Mode Execution
Protection) in QEMU-KVM. SMEP prevents kernel from executing code in application.
Updated Intel SDM describes this CPU feature. The document will be published soon.
SMEP is identified by CPUID leaf 7 EBX[7], which is 0 before. Get the right value by query KVM kernel module, so that guest can get SMEP through CPUID.
Signed-off-by: Yang, Wei <wei.y.yang@intel.com>
Singed-off-by: Shan, Haitao <haitao.shan@intel.com>
Singed-off-by: Li, Xin <xin.li@intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When KVM is running on VIA CPU with host cpu's model, the
feautures of VIA CPU will be passed into kvm guest by calling
the CPUID instruction for Centaur.
Signed-off-by: BrillyWu<brillywu@viatech.com.cn>
Signed-off-by: KaryJin<karyjin@viatech.com.cn>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
While trying to use qemu -cpu pentium3 to test for incorrect uses of certain
SSE2 instructions, I found that QEMU allowed the mfence and lfence
instructions to be executed even though Pentium 3 doesn't support them.
According to the processor specs (and experience on a real Pentium 3), these
instructions are only available with SSE2, but QEMU is checking for SSE. The
check for the related sfence instruction is correct (it works with SSE).
This trival patch fixes the test.
Signed-off-by: Martin Simmons <martin@lispworks.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
This patch removes all references to signal.h when qemu-common.h is included
as they become redundant.
Signed-off-by: Alexandre Raymond <cerbere@gmail.com>
Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Instead of using a table which doesn't correspond to anything from
physical in the CPU, use directly the constants in helper_fld*_ST0().
Cc: Andreas Färber <andreas.faerber@web.de>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Now that target-i386 uses softfloat, floatx80 is always available and
there is no need anymore to have code handling both float64 and floax80.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This interrupt name is used by i386, CRIS, and MicroBlaze.
Copy the name into each target.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
SMI, VIRQ, INIT, SIPI, and MCE are all only used by the i386 port.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
We have two bits that can represent kvmclock in cpuid.
They signal the guest which msr set to use. When we tweak flags
involving this value - specially when we use "-", we have to act on both.
Signed-off-by: Glauber Costa <glommer@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
kvmclock is represented by two feature bits. Therefore, lookup_feature
needs to continue its search even after the first match. Enhance it
accordingly and switch to a bool return type at this chance.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Use the features provided by KVM_GET_SUPPORTED_CPUID directly to
mask out features from guest-visible cpuid.
The old get_para_features() mechanism is kept for older kernels that do not implement it.
Signed-off-by: Glauber Costa <glommer@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Use the new CPU86_LDouble <-> double conversion functions to make logarithmic
and trigonometric helpers working with softfloat.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Add functions to convert CPU86_LDouble to double and vice versa. They
are going to be used to implement logarithmic and trigonometric function
until softfloat implement them.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
With softfloat it's not possible to play with the overflow of an
unsigned value to get the 0 case partially correct. Use a special case
for that. Using a division to generate an infinity is the easiest way
that works for both softfloat and softfloat-native.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Use the scalbn softfloat function to implement helper_fscale(). This
fixes corner cases (e.g. NaN) and makes a few more GNU libc math tests
to pass.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
The previous patch removed the need for parameter puc.
Is is now unused, so remove it.
Cc: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Function gen_pc_load was introduced in commit
d2856f1ad4.
The only reason for parameter searched_pc was
a debug statement in target-i386/translate.c.
Parameter puc was needed by target-sparc until
commit d7da2a1040.
Remove searched_pc from the debug statement and remove both
parameters from the parameter list of gen_pc_load.
As the function name gen_pc_load was also misleading,
it is now called restore_state_to_opc. This new name
was suggested by Peter Maydell, thanks.
v2: Remove last parameter, too, and rename the function.
v3: Fix [] typo in target-arm/translate.c.
Fix wrong SHA1 object name in commit message (copy+paste error).
Cc: Aurelien Jarno <aurelien@aurel32.net>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
float*_eq functions have a different semantics than other comparison
functions. Fix that by first renaming float*_quiet() into float*_eq_quiet().
Note that it is purely mechanical, and the behaviour should be unchanged.
That said it clearly highlight problems due to this different semantics,
they are fixed later in this patch series.
Cc: Alexander Graf <agraf@suse.de>
Acked-by: Edgar E. Iglesias <edgar.iglesias@gmail.com>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
SSE instructions CMPUNORDPS/D and CMPORDPS/D do not trigger an invalid
exception if operands are qNANs.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Add floatx_{add,mul,sub} defines, and use them instead of using direct
C operations.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Use float unions from cpu-all.h instead of redefining new (wrong for arm)
ones in target-i386. This also allows building cpu-exec.o with softfloat.
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Use CPU_LDoubleU in cpu_dump_state() instead of redefining a union for
doing the conversion.
Based on a patch from Laurent Vivier <laurent@vivier.eu>.
Cc: Laurent Vivier <laurent@vivier.eu>
Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
tcg_gen_exit_tb takes a parameter of type tcg_target_long,
so the type casts of pointer to long should be replaced by
type casts of pointer to tcg_target_long (suggested by Blue Swirl).
These changes are needed for build environments where
sizeof(long) != sizeof(void *), especially for w64.
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This reverts commit c995b495b9.
From Jan Kiszka:
Ouch, indeed. Moreover, CPU_SAVE_VERSION was not updated (likely the
reason for the breakage). Thanks for debugging this!
Anthony (or whoever), please revert this unneeded commit in qemu.git.
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
There are no generic bits remaining in the handling of KVM_EXIT_DEBUG.
So push its logic completely into arch hands, i.e. only x86 so far.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Required for next patch which will access guest debug services from
kvm_arch_handle_exit. No functional changes.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Make the return code of kvm_arch_handle_exit directly usable for
kvm_cpu_exec. This is straightforward for x86 and ppc, just s390
would require more work. Avoid this for now by pushing the return code
translation logic into s390's kvm_arch_handle_exit.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Conforming to the Intel spec, set the power-on value of PAT also on
reset, but save it across INIT.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When an external interrupt is pending but IF is cleared, we must not
leave the halt state prematurely.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In Linux kernel HWPoison processing implementation, the virtual
address in processes mapping the error physical memory page is marked
as HWPoison. So that, the further accessing to the virtual
address will kill corresponding processes with SIGBUS.
If the error physical memory page is used by a KVM guest, the SIGBUS
will be sent to QEMU, and QEMU will simulate a MCE to report that
memory error to the guest OS. If the guest OS can not recover from
the error (for example, the page is accessed by kernel code), guest OS
will reboot the system. But because the underlying host virtual
address backing the guest physical memory is still poisoned, if the
guest system accesses the corresponding guest physical memory even
after rebooting, the SIGBUS will still be sent to QEMU and MCE will be
simulated. That is, guest system can not recover via rebooting.
In fact, across rebooting, the contents of guest physical memory page
need not to be kept. We can allocate a new host physical page to
back the corresponding guest physical address.
This patch fixes this issue in QEMU-KVM via calling qemu_ram_remap()
to clear the corresponding page table entry, so that make it possible
to allocate a new page to recover the issue.
[ Jan: rebasing and tiny cleanups]
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
There is no reason to continue if the kernel claims to support MCE but
then fails to process our request.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
There is nothing to abstract here. Fold kvm_setup_mce into its caller
and fix up the error reporting (return code of kvm_vcpu_ioctl holds the
error value).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This switches KVM's MCE injection path to cpu_x86_inject_mce, both for
SIGBUS and monitor initiated events. This means we prepare the MCA MSRs
in the VCPUState also for KVM.
We have to drop the MSRs writeback restrictions for this purpose which
is now safe as every uncoordinated MSR injection is removed with this
patch.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
We will use the current TCG-only MCE injection path for KVM as well, and
then this read-modify-write of the target VCPU state has to be performed
synchronously in the corresponding thread.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The current way of injecting MCE events without updating of and
synchronizing with the CPUState is broken and causes spurious
corruptions of the MCE-related parts of the CPUState.
As a first step towards a fix, enhance the state writeback code with
support for injecting events that are pending in the CPUState. A pending
exception will then be signaled via cpu_interrupt(CPU_INTERRUPT_MCE).
And, just like for TCG, we need to leave the halt state when
CPU_INTERRUPT_MCE is pending (left broken for the to-be-removed old KVM
code).
This will also allow to unify TCG and KVM injection code.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
We will broaden the scope of this function on x86 beyond irqchip events.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Pure function suffling to avoid multiple #ifdef KVM_CAP_MCE sections,
no functional changes. While at it, annotate some #ifdef sections.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Allow to tell cpu_x86_inject_mce that it should ignore Action Optional
MCE events when the target VCPU is still processing another one. This
will be used by KVM soon.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
As this service is used by the human monitor, make sure that errors get
reported to the right channel, and also raise the verbosity.
This requires to move Monitor typedef in qemu-common.h to resolve the
include dependency.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
MCEs can be injected asynchronously, so they can also terminate the halt
state.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Huang Ying <ying.huang@intel.com>
CC: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
CC: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
All implementations are now the same, and there is only one caller,
so inline the function there.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
We have qemu_cpu_self and qemu_thread_self. The latter is retrieving the
current thread, the former is checking for equality (using CPUState). We
also have qemu_thread_equal which is only used like qemu_cpu_self.
This refactors the interfaces, creating qemu_cpu_is_self and
qemu_thread_is_self as well ass qemu_thread_get_self.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
We do not need to abort, but the user should be notified that weird
things go on.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
We do not check them, and the only arch with non-empty implementations
always returns 0 (this is also true for qemu-kvm).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Effectively no functional change yet as kvm_irqchip_in_kernel still only
returns 0, but this patch will allow qemu-kvm to adopt the VCPU loop of
upsteam KVM.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Mixing up TCG bits with KVM already led to problems around eflags
emulation on x86. Moreover, quite some code that TCG requires on cpu
enty/exit is useless for KVM. So dispatch between tcg_cpu_exec and
kvm_cpu_exec as early as possible.
The core logic of cpu_halted from cpu_exec is added to
kvm_arch_process_irqchip_events. Moving away from cpu_exec makes
exception_index meaningless for KVM, we can simply pass the exit reason
directly (only "EXCP_DEBUG vs. rest" is relevant).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
If the machine is stopped, we should not record two different tsc values
upon a save operation. The same problem happens with kvmclock.
But kvmclock is taking a different diretion, being now seen as a separate
device. Since this is unlikely to happen with the tsc, I am taking the
approach here of simply registering a handler for state change, and
using a per-CPUState variable that prevents double updates for the TSC.
Signed-off-by: Glauber Costa <glommer@redhat.com>
CC: Jan Kiszka <jan.kiszka@web.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
KVM requires to reenter the kernel after IO exits in order to complete
instruction emulation. Failing to do so will leave the kernel state
inconsistently behind. To ensure that we will get back ASAP, we issue a
self-signal that will cause KVM_RUN to return once the pending
operations are completed.
We can move kvm_arch_process_irqchip_events out of the inner VCPU loop.
The only state that mattered at its old place was a pending INIT
request. Catch it in kvm_arch_pre_run and also trigger a self-signal to
process the request on next kvm_cpu_exec.
This patch also fixes the missing exit_request check in kvm_cpu_exec in
the CONFIG_IOTHREAD case.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Provide arch-independent kvm_on_sigbus* stubs to remove the #ifdef'ery
from cpus.c. This patch also fixes --disable-kvm build by providing the
missing kvm_on_sigbus_vcpu kvm-stub.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When broadcasting MCEs, we need to set MCIP and RIPV in mcg_status like
it is done for KVM. Use the symbolic constants at this chance.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
If the kernel does not support KVM_CAP_ASYNC_PF, it also does not know
about the related MSR. So skip it during state synchronization in that
case. Fixes annoying kernel warnings.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
All CPUX86State variables before CPU_COMMON are automatically cleared on
reset. Reorder nmi_injected and nmi_pending to avoid having to touch
them explicitly.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
In order to support loading BIOSes > 256K, reorder the code, adjusting
the base if the kernel supports moving the identity map.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Instead of splattering the code with #ifdefs and runtime checks for
capabilities we cannot work without anyway, provide central test
infrastructure for verifying their availability both at build and
runtime.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
If we lack kvm_para.h, MSR_KVM_ASYNC_PF_EN is not defined. The change in
kvm_arch_init_vcpu is just for consistency reasons.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Make sure to write the cleared MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
and MSR_KVM_ASYNC_PF_EN to the kernel state so that a freshly booted
guest cannot be disturbed by old values.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
CC: Glauber Costa <glommer@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Simplify kvm_has_msr_star/hsave_pa to booleans and push their one-time
initialization into kvm_arch_init. Also handle potential errors of that
setup procedure.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
For unknown reasons, xcr0 reset ended up in kvm_arch_update_guest_debug
on upstream merge. Fix this and also remove the misleading comment (1 is
THE reset value).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
kvm_arch_reset_vcpu initializes mp_state, and that function is invoked
right after kvm_arch_init_vcpu.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This code path will not yet be taken as we still lack in-kernel irqchip
support. But qemu-kvm can already make use of it and drop its own
mp_state access services.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
The ordering doesn't matter in this case, but better keep it consistent.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Introduce the cpu_dump_state flag CPU_DUMP_CODE and implement it for
x86. This writes out the code bytes around the current instruction
pointer. Make use of this feature in KVM to help debugging fatal vm
exits.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Report KVM_EXIT_UNKNOWN, KVM_EXIT_FAIL_ENTRY, and KVM_EXIT_EXCEPTION
with more details to stderr. The latter two are so far x86-only, so move
them into the arch-specific handler. Integrate the Intel real mode
warning on KVM_EXIT_FAIL_ENTRY that qemu-kvm carries, but actually
restrict it to Intel CPUs. Moreover, always dump the CPU state in case
we fail.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Ensure that we stop the guest whenever we face a fatal or unknown exit
reason. If we stop, we also have to enforce a cpu loop exit.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This exit only triggers activity in the common exit path, but we should
accept it in order to be able to detect unknown exit types.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This unbreaks guest debugging when the 4th hardware breakpoint used for
guest debugging is a watchpoint of 4 or 8 byte lenght. The 31st bit of
DR7 is set in that case and used to cause a sign extension to the high
word which was breaking the guest state (vm entry failure).
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This seems to date back to the days KVM didn't support real mode. The
check is no longer needed and, even worse, is corrupting the guest state
in case SS.RPL != DPL.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The DPL is stored in the flags and not in the selector. In fact, the RPL
may differ from the DPL at some point in time, and so we were corrupting
the guest state so far.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Share same error handing, and rename this function after
MCIP (Machine Check In Progress) flag.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Add function for checking whether current CPU support mca broadcast.
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
When the following test case is injected with mce command, maybe user could not
get the expected result.
DATA
command cpu bank status mcg_status addr misc
(qemu) mce 1 1 0xbd00000000000000 0x05 0x1234 0x8c
Expected Result
panic type: "Fatal Machine check"
That is because each mce command can only inject the given cpu and could not
inject mce interrupt to other cpus. So user will get the following result:
panic type: "Fatal machine check on current CPU"
"broadcast" option is used for injecting dummy data into other cpus. Injecting
mce with this option the expected result could be gotten.
Usage:
Broadcast[on]
command broadcast cpu bank status mcg_status addr misc
(qemu) mce -b 1 1 0xbd00000000000000 0x05 0x1234 0x8c
Broadcast[off]
command cpu bank status mcg_status addr misc
(qemu) mce 1 1 0xbd00000000000000 0x05 0x1234 0x8c
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Clean up cpu_inject_x86_mce() for later patch.
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
simple cleanup and use existing helper: kvm_check_extension().
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Make use of the new KVM_NMI IOCTL to send NMIs into the KVM guest if the
user space raised them. (example: qemu monitor's "nmi" command)
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Acked-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Use this for assignment to the low byte or low word of a register.
Acked-by: Aurelien Jarno <aurelien@aurel32.net>
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@gmail.com>
Only bits 8..23 of the segment flags contain valid data, so only dump
those when printing the CPU state.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
softfloat.h's uint64 type has least-width semantics.
Use uint64_t instead since that is used in helpers.
v4:
* Summary change.
v3:
* Split off.
Signed-off-by: Andreas Färber <andreas.faerber@web.de>
Acked-by: Huang Ying <ying.huang@intel.com>
Acked-by: Juan Quintela <quintela@redhat.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
fprintf_function uses format checking with GCC_FMT_ATTR.
Format errors were fixed in
* target-i386/helper.c
* target-mips/translate.c
* target-ppc/translate.c
Cc: Blue Swirl <blauwirbel@gmail.com>
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
This patch removes following warnings:
target-i386/kvm.c: In function 'kvm_put_msrs':
target-i386/kvm.c:782: error: unused variable 'i'
target-i386/kvm.c: In function 'kvm_get_msrs':
target-i386/kvm.c:1083: error: label at end of compound statement
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
There is no reason why SRAO event received by the main thread
is the only one that being broadcasted.
According to the x86 ASDM vol.3A 15.10.4.1,
MCE signal is broadcast on processor version 06H_EH or later.
This change is required to handle SRAR in smp guests.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
And restruct this block to call kvm_mce_in_exception() only when it is
required.
Signed-off-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Port qemu-kvm's
commit 1bab5d11545d8de5facf46c28630085a2f9651ae
Author: Huang Ying <ying.huang@intel.com>
Date: Wed Mar 3 16:52:46 2010 +0800
Add savevm/loadvm support for MCE
MCE registers are saved/load into/from CPUState in
kvm_arch_save/load_regs. To simulate the MCG_STATUS clearing upon
reset, MSR_MCG_STATUS is set to 0 for KVM_PUT_RESET_STATE.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Port qemu-kvm's
commit 4b62fff1101a7ad77553147717a8bd3bf79df7ef
Author: Huang Ying <ying.huang@intel.com>
Date: Mon Sep 21 10:43:25 2009 +0800
MCE: Relay UCR MCE to guest
UCR (uncorrected recovery) MCE is supported in recent Intel CPUs,
where some hardware error such as some memory error can be reported
without PCC (processor context corrupted). To recover from such MCE,
the corresponding memory will be unmapped, and all processes accessing
the memory will be killed via SIGBUS.
For KVM, if QEMU/KVM is killed, all guest processes will be killed
too. So we relay SIGBUS from host OS to guest system via a UCR MCE
injection. Then guest OS can isolate corresponding memory and kill
necessary guest processes only. SIGBUS sent to main thread (not VCPU
threads) will be broadcast to all VCPU threads as UCR MCE.
aliguori: fix build
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Port qemu-kvm's MCE support
commit c68b2374c9048812f488e00ffb95db66c0bc07a7
Author: Huang Ying <ying.huang@intel.com>
Date: Mon Jul 20 10:00:53 2009 +0800
Add MCE simulation support to qemu/kvm
KVM ioctls are used to initialize MCE simulation and inject MCE. The
real MCE simulation is implemented in Linux kernel. The Kernel part
has been merged.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch adds the svm cpuid feature flags to the qemu
intialization path. It also adds the svm features available
on phenom to its cpu-definition and extends the host cpu
type to support all svm features KVM can provide.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
This patch cleans the (stack-allocated) cpuid definition to
0 before actually initializing it.
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Compiling with GCC 4.6.0 20100925 produced warnings:
/src/qemu/target-i386/op_helper.c: In function 'switch_tss':
/src/qemu/target-i386/op_helper.c:283:53: error: variable 'new_trap' set but not used [-Werror=unused-but-set-variable]
Fix by adding a dummy cast so that the variable is not unused. Add also
pointer to docs.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Switch tree to lookup-by-name using qemu_find_opts().
Also hook up virtfs options so qemu_find_opts works for them too.
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Correct the calculation of the offset in the msrpm
for the MSR range 0 - 0x1fff.
Signed-off-by: Adam Lackorzynski <adam@os.inf.tu-dresden.de>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Replace array size calculations with ARRAY_SIZE macro.
Implemented with this Coccinelle semantic patch, adapted from
Linux kernel:
@@
type T;
T[] E;
@@
- (sizeof(E)/sizeof(*E))
+ ARRAY_SIZE(E)
@@
type T;
T[] E;
@@
- (sizeof(E)/sizeof(E[...]))
+ ARRAY_SIZE(E)
@@
type T;
T[] E;
@@
- (sizeof(E)/sizeof(T))
+ ARRAY_SIZE(E)
Some files (*-dis.c, tests/*) had to be filtered out.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
This patch simplifies target-i386/translate.c a bit by replacing some
code with gen_update_cc_op()
Signed-off-by: Jun Koi <junkoi2004@gmail.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This patch replaces constant value assigned for (DisasContext
*)->is_jmp with DISAS_TB_JUMP.
Signed-off-by: Jun Koi <junkoi2004@gmail.com>
Signed-off-by: Edgar E. Iglesias <edgar.iglesias@gmail.com>
i386 cpuid.c currently claims XSAVE is supported in the CPUID filter,
but that's not true: Only FXSAVE is supported. Remove that bit
from the filter.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
ssse3 uses tables with only two entries per op, but it is indexed
with b1 which can contain variables upto 3. This happens when ssse3
or sse4 are used with REP* prefixes.
Add boundary checking for this case.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
We were ignoring REX_B while special-casing NOP, i.e. xchg eax,eax.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
We currently only clear SVM_EVTINJ_VALID after successful interrupt
delivery. This apparently does not match real hardware which clears the
whole event_inj field on every vmexit, including unsuccessful interrupt
delivery.
Reported-by: Erik van der Kouwe <vdkouwe@cs.vu.nl>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
We can support it in KVM now. The 0xd leaf is queried from KVM.
Signed-off-by: Sheng Yang <sheng@linux.intel.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
the meaning of vendor_override is actually the opposite of how it
is currently used :-(
Fix it to allow KVM to export the non-native CPUID vendor if
explicitly requested by the user.
The intended behavior is:
With TCG:
- always inject the configured vendor (either hard-coded, in config
files or via ",vendor=" commandline)
With KVM:
- by default inject the host's vendor
- if the user specifies ",vendor=" on the commandline, use this
instead of the host's vendor
- all pre-configured vendors (hard-coded, config file) are ignored
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This fixes a regression of 0e26b7b892: Reset halted also on INIT.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Make APICState completely private to apic.c by using DeviceState
in external APIs.
Move apic_init() to pc.c.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Move the actual CPUState contents handling to cpu.h and cpuid.c.
Handle CPU reset and set env->halted in pc.c.
Add a function to get the local APIC state of the current
CPU for the MMIO.
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Some hosts (amd64, ia64) have an ABI that ignores the high bits
of the 64-bit register when passing 32-bit arguments. Others
require the value to be properly sign-extended for the type.
I.e. "int32_t" must be sign-extended and "uint32_t" must be
zero-extended to 64-bits.
To effect this, extend the "sizemask" parameter to tcg_gen_callN
to include the signedness of the type of each parameter. If the
tcg target requires it, extend each 32-bit argument into a 64-bit
temp and pass that to the function call.
This ABI feature is required by sparc64, ppc64 and s390x.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Negative four byte displacements need to be sign-extended after
c086b783eb. Do so.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Acked-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
Create a kvm32 CPU model that describes a least common denominator
for KVM capable guest CPUs. Useful for migration purposes.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
On AMD some bits from 1.EDX are reported in 80000001.EDX. The mask used
to copy bits from 1.EDX to 80000001.EDX is incorrect resulting in
unsupported features passed into a guest.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Continue vcpu execution in case emulation failure happened while vcpu
was in userspace. In this case #UD will be injected into the guest
allowing guest OS to kill offending process and continue.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Validate that KVM vcpu state is only read/written from cpu thread itself
or that cpu is stopped.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
The proper logging for -d cpu is done in generic code.
Signed-off-by: Richard Henderson <rth@twiddle.net>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
If we use larger BIOS image than current 256KB, we would need move reserved
TSS and EPT identity mapping pages. Currently TSS support this, but not
EPT.
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Make use of the new KVM_GET/SET_DEBUGREGS to save/restore the x86 debug
registers.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Fixes clang errors:
CC i386-softmmu/kvm.o
/src/qemu/target-i386/kvm.c:40:9: error: 'dprintf' macro redefined
In file included from /src/qemu/target-i386/kvm.c:21:
In file included from /src/qemu/qemu-common.h:27:
In file included from /usr/include/stdio.h:910:
/usr/include/bits/stdio2.h:189:12: note: previous definition is here
CC i386-softmmu/kvm-all.o
/src/qemu/kvm-all.c:39:9: error: 'dprintf' macro redefined
In file included from /src/qemu/kvm-all.c:23:
In file included from /src/qemu/qemu-common.h:27:
In file included from /usr/include/stdio.h:910:
/usr/include/bits/stdio2.h:189:12: note: previous definition is here
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
With argument checking for cpu_fprintf, gcc throws this warning:
CC i386-softmmu/helper.o
cc1: warnings being treated as errors
/qemu/ar7/target-i386/helper.c: In function ‘cpu_x86_dump_seg_cache’:
/qemu/ar7/target-i386/helper.c:220: error: format not a string literal and no format arguments
The code is correct, but current gcc versions don't detect this.
Therefore the patch rewrites the statement to satisfy the compiler.
Signed-off-by: Stefan Weil <weil@mail.berlios.de>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
QEMU uses a fixed page size for the CPU TLB. If the guest uses large
pages then we effectively split these into multiple smaller pages, and
populate the corresponding TLB entries on demand.
When the guest invalidates the TLB by virtual address we must invalidate
all entries covered by the large page. However the address used to
invalidate the entry may not be present in the QEMU TLB, so we do not
know which regions to clear.
Implementing a full vaiable size TLB is hard and slow, so just keep a
simple address/mask pair to record which addresses may have been mapped by
large pages. If the guest invalidates this region then flush the
whole TLB.
Signed-off-by: Paul Brook <paul@codesourcery.com>
Enable all features of real CPU, unsupported features will be
trimmed depending on TCG or KVM capabilities.
Move the list of unsupported TCG features near the TCG capabilities
masks.
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Bump up the xlevel number for qemu32 to allow parsing of the processor
name string for this model.
Similiarly the 486 processor should have at least the feature bit
leaf enabled.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Since 64-bit capability is just another CPUID bit we now properly
mask, there is no reason anymore to hide the 64-bit capable CPU
models from a 32-bit only QEMU. All 64-bit CPUs can be used
perfectly in 32-bit legacy mode anyway, so these models also make
sense for 32-bit.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
In KVM we trim the user provided CPUID bits to match the host CPU's
one. Introduce a similar feature to QEMU/TCG. Create a mask of TCG's
capabilities and apply it to the user bits.
This allows to let the CPU models reflect their native archetypes.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Correct me if I am wrong, but kvm_trim looks like a really bloated
implementation of a bitwise AND. So remove this function and replace
it with the real stuff(TM).
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Some CPUID feature flags had no string value, so they could not be
switched on or off from the command line.
Add names for the missing ones mentioned in the current public CPUID
specification from both Intel and AMD. Those only mentioned in the
Linux kernel source I put as comments.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
the host_cpuid function was located at the end of the file and had
a prototype before it's first use. Move it up and remove the
prototype.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
This one was accidently removed with commit
bb0300dc57
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
CPUID leaf Fn8000_0001.EDX contains a copy of many Fn0000_0001.EDX bits.
Define a name for this mask to improve readability and avoid typos.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
about half of target-i386/helper.c consist of CPUID related functions.
Only one of them is a real TCG helper function. So move the whole
CPUID stuff out of this into a separate file to get better
maintainable parts.
This is only code reordering and should not affect QEMU's
functionality.
Signed-off-by: Andre Przywara <andre.przywara@amd.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
The commit c22549204a led movntps &
movntdq to be translated incorrectly.
Signed-off-by: TeLeMan <geleman@gmail.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Removes a set of ifdefs from exec.c.
Introduce TARGET_VIRT_ADDR_SPACE_BITS for all targets other
than Alpha. This will be used for page_find_alloc, which is
supposed to be using virtual addresses in the first place.
Signed-off-by: Richard Henderson <rth@twiddle.net>
A SIB byte with an index of 4 means "no scaled index", even if the scale
value is not 0. In 64-bit mode, if REX.X is used, an index of 4 selects
%r12. This is correctly handled by the computation of the index variable,
which includes the index bits, and also the REX.X prefix:
index = ((code >> 3) & 7) | REX_X(s);
Thanks to Avi Kivity, Jamie Lokier and Malc for the analysis of the
problem and the initial patch.
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
Do not write nmi_pending, sipi_vector, and mpstate unless we at least go
through a reset. And TSC as well as KVM wallclocks should only be
written on full sync, otherwise we risk to drop some time on state
read-modify-write.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
This grand cleanup drops all reset and vmsave/load related
synchronization points in favor of four(!) generic hooks:
- cpu_synchronize_all_states in qemu_savevm_state_complete
(initial sync from kernel before vmsave)
- cpu_synchronize_all_post_init in qemu_loadvm_state
(writeback after vmload)
- cpu_synchronize_all_post_init in main after machine init
- cpu_synchronize_all_post_reset in qemu_system_reset
(writeback after system reset)
These writeback points + the existing one of VCPU exec after
cpu_synchronize_state map on three levels of writeback:
- KVM_PUT_RUNTIME_STATE (during runtime, other VCPUs continue to run)
- KVM_PUT_RESET_STATE (on synchronous system reset, all VCPUs stopped)
- KVM_PUT_FULL_STATE (on init or vmload, all VCPUs stopped as well)
This level is passed to the arch-specific VCPU state writing function
that will decide which concrete substates need to be written. That way,
no writer of load, save or reset functions that interact with in-kernel
KVM states will ever have to worry about synchronization again. That
also means that a lot of reasons for races, segfaults and deadlocks are
eliminated.
cpu_synchronize_state remains untouched, just as Anthony suggested. We
continue to need it before reading or writing of VCPU states that are
also tracked by in-kernel KVM subsystems.
Consequently, this patch removes many cpu_synchronize_state calls that
are now redundant, just like remaining explicit register syncs.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
So far we synchronized any dirty VCPU state back into the kernel before
updating the guest debug state. This was a tribute to a deficite in x86
kernels before 2.6.33. But as this is an arch-dependent issue, it is
better handle in the x86 part of KVM and remove the writeback point for
generic code. This also avoids overwriting the flushed state later on if
user space decides to change some more registers before resuming the
guest.
We furthermore need to reinject guest exceptions via the appropriate
mechanism. That is KVM_SET_GUEST_DEBUG for older kernels and
KVM_SET_VCPU_EVENTS for recent ones. Using both mechanisms at the same
time will cause state corruptions.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
If you make use of hw breakpoints on a 32bit x86 linux host, qemu
will segmentation fault when processing the exception.
The problem is that the value of env is stored in $ebp in the op_helper
raise_exception() function, and it can have the wrong value when
calling it from non generated code.
It is possible to work around the problem by restoring the value of
env before calling raise_exception() using a new helper function that
takes (CPUState *) as one of the arguments.
Signed-off-by: Jason Wessel <jason.wessel@windriver.com>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>
helper.o(.text+0x11e0): In function `listflags':
/src/qemu/target-i386/helper.c:661: warning: sprintf() is often misused, please use snprintf()
Signed-off-by: Blue Swirl <blauwirbel@gmail.com>
This is a reimplementation of prior versions which adds
the ability to define cpu models for contemporary processors.
The added models are likewise selected via -cpu <name>,
and are intended to displace the existing convention
of "-cpu qemu64" augmented with a series of feature flags.
A primary motivation was determination of a least common
denominator within a given processor class to simplify guest
migration. It is still possible to modify an arbitrary model
via additional feature flags however the goal here was to
make doing so unnecessary in typical usage. The other
consideration was providing models names reflective of
current processors. Both AMD and Intel have reviewed the
models in terms of balancing generality of migration vs.
excessive feature downgrade relative to released silicon.
This version of the patch replaces the prior hard wired
definitions with a configuration file approach for new
models. Existing models are thus far left as-is but may
easily be transitioned to (or may be overridden by) the
configuration file representation.
Proposed new model definitions are provided here for current
AMD and Intel processors. Each model consists of a name
used to select it on the command line (-cpu <name>), and a
model_id which corresponds to a least common denominator
commercial instance of the processor class.
A table of names/model_ids may be queried via "-cpu ?model":
:
x86 Opteron_G3 AMD Opteron 23xx (Gen 3 Class Opteron)
x86 Opteron_G2 AMD Opteron 22xx (Gen 2 Class Opteron)
x86 Opteron_G1 AMD Opteron 240 (Gen 1 Class Opteron)
x86 Nehalem Intel Core i7 9xx (Nehalem Class Core i7)
x86 Penryn Intel Core 2 Duo P9xxx (Penryn Class Core 2)
x86 Conroe Intel Celeron_4x0 (Conroe/Merom Class Core 2)
:
Also added is "-cpu ?dump" which exhaustively outputs all config
data for all defined models, and "-cpu ?cpuid" which enumerates
all qemu recognized CPUID feature flags.
The pseudo cpuid flag 'check' when added to the feature flag list
will warn when feature flags (either implicit in a cpu model or
explicit on the command line) would have otherwise been quietly
unavailable to a guest:
# qemu-system-x86_64 ... -cpu Nehalem,check
warning: host cpuid 0000_0001 lacks requested flag 'sse4.2|sse4_2' [0x00100000]
warning: host cpuid 0000_0001 lacks requested flag 'popcnt' [0x00800000]
A similar 'enforce' pseudo flag exists which in addition
to the above causes qemu to error exit if requested flags are
unavailable.
Configuration data for a cpu model resides in the target config
file which by default will be installed as:
/usr/local/etc/qemu/target-<arch>.conf
The format of this file should be self explanatory given the
definitions for the above six models and essentially mimics
the structure of the static x86_def_t x86_defs.
Encoding of cpuid flags names now allows aliases for both the
configuration file and the command line which reconciles some
Intel/AMD/Linux/Qemu naming differences.
This patch was tested relative to qemu.git.
Signed-off-by: john cooper <john.cooper@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Remove all references to KVM_CR3_CACHE as it was never implemented.
Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Hi,
Kevin and I have agreed on the approach for this one now. So here is
the latest version of the patch for QEMU, submitting e820 reservation
entries via fw_cfg.
Cheers,
Jes
Use qemu-cfg to provide the BIOS with an optional table of e820 entries.
Notify the BIOS of the location of the TSS+EPT range to by reserving
it via the e820 table.
This matches a corresponding patch for Seabios, however older versions
of Seabios will default to the hardcoded address range and stay
compatible with current QEMU.
Signed-off-by: Jes Sorensen <Jes.Sorensen@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
From qemu-kvm: Kernels before 2.6.30 misreported some essential CPU
features via KVM_GET_SUPPORTED_CPUID. Fix them up.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
The final version of VCPU events in 2.6.33 will allow to skip
nmi_pending and sipi_vector on KVM_SET_VCPU_EVENTS. For now let's write
them unconditionally, which is unproblematic for upstream due to missing
SMP support. Future version which enable SMP will write them only on
reset.
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
These are unused since edea5f0 (no need to define global registers in
cpu-exec.c, 2008-05-10).
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
Initialize KVM paravirt cpuid leaf and allow user to control guest
visible PV features through -cpu flag.
Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Anthony Liguori <aliguori@us.ibm.com>
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 ebbc8a3d8e.
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>