| #
c865f654 |
| 09-Jun-2021 |
Cornelia Huck <cohuck@redhat.com> |
x86: unify header guards
Standardize header guards to _ASMX86_HEADER_H_, _X86_HEADER_H_,
and X86_HEADER_H.
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@red
x86: unify header guards
Standardize header guards to _ASMX86_HEADER_H_, _X86_HEADER_H_,
and X86_HEADER_H.
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Message-Id: <20210609143712.60933-8-cohuck@redhat.com>
show more ...
|
| #
7db17e21 |
| 27-Jun-2018 |
Thomas Huth <thuth@redhat.com> |
Make remaining x86 code compilable with -Wstrict-prototypes
This way the functions can not be called anymore with arbitrary
parameters by accident.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Mes
Make remaining x86 code compilable with -Wstrict-prototypes
This way the functions can not be called anymore with arbitrary
parameters by accident.
Signed-off-by: Thomas Huth <thuth@redhat.com>
Message-Id: <1530086528-21665-4-git-send-email-thuth@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
| #
c7853445 |
| 14-Jun-2016 |
Roman Kagan <rkagan@virtuozzo.com> |
x86: kvmclock: sync with kernel
Bring kvmclock code in sync with kernel (including the not yet merged
fixes for missing barriers from Minfei Huang <mnghuan@gmail.com> and the
read_begin/read_retry r
x86: kvmclock: sync with kernel
Bring kvmclock code in sync with kernel (including the not yet merged
fixes for missing barriers from Minfei Huang <mnghuan@gmail.com> and the
read_begin/read_retry rework from Paolo Bonzini <pbonzini@redhat.com>).
This gets rid of excessive memory barriers and speeds up kvmclock reads
by up to 50%. (There's another 2x speedup possible if lfence (aka
rmb()) is used instead of mfence (aka mb()) in rdtsc_ordered(); however
this is only supposed to be allowed on Intel CPUs and we don't have the
infrastructure ala kernel alternatives yet).
Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
| #
b4711e11 |
| 09-Mar-2016 |
David Matlack <dmatlack@google.com> |
x86: use new kvmclock MSRs
54750f2cf0 (KVM: x86: workaround SuSE's 2.6.16 pvclock vs masterclock
issue) disables masterclock if the boot VCPU uses the old kvmclock
system time MSR. This caused kvmcl
x86: use new kvmclock MSRs
54750f2cf0 (KVM: x86: workaround SuSE's 2.6.16 pvclock vs masterclock
issue) disables masterclock if the boot VCPU uses the old kvmclock
system time MSR. This caused kvmclock_test to start running with
masterclock disabled.
Since the old kvmclock MSRs are deprecated, and their usage disables
masterclock, switch to using the new kvmclock MSRs instead.
Signed-off-by: David Matlack <dmatlack@google.com>
Message-Id: <1457484503-90018-1-git-send-email-dmatlack@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
show more ...
|
| #
a7053e6d |
| 31-Aug-2010 |
Jason Wang <jasowang@redhat.com> |
Add a simple kvmclock driver
Most of the codes were borrowed from arxh/x86/kernel/kvmclock.c. A
special bit: PV_CLOCK_CYCLE_RAW_TEST_BIT is used to notify the driver
to return unadjusted cycles.
Si
Add a simple kvmclock driver
Most of the codes were borrowed from arxh/x86/kernel/kvmclock.c. A
special bit: PV_CLOCK_CYCLE_RAW_TEST_BIT is used to notify the driver
to return unadjusted cycles.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
show more ...
|