lkml.org 
[lkml]   [2010]   [Jun]   [16]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
DateWed, 16 Jun 2010 12:36:17 -1000
FromZachary Amsden <>
SubjectRe: [PATCH 16/17] TSC reset compensation
On 06/16/2010 03:52 AM, Glauber Costa wrote:
> On Mon, Jun 14, 2010 at 09:34:18PM -1000, Zachary Amsden wrote:
>
>> Attempt to synchronize TSCs which are reset to the same value. In the
>> case of a reliable hardware TSC, we can just re-use the same offset, but
>> on non-reliable hardware, we can get closer by adjusting the offset to
>> match the elapsed time.
>>
>> Signed-off-by: Zachary Amsden<zamsden@redhat.com>
>> ---
>> arch/x86/kvm/x86.c | 34 ++++++++++++++++++++++++++++++++--
>> 1 files changed, 32 insertions(+), 2 deletions(-)
>>
>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
>> index 8e836e9..cedb71f 100644
>> --- a/arch/x86/kvm/x86.c
>> +++ b/arch/x86/kvm/x86.c
>> @@ -937,14 +937,44 @@ static inline void kvm_request_guest_time_update(struct kvm_vcpu *v)
>> set_bit(KVM_REQ_CLOCK_SYNC,&v->requests);
>> }
>>
>> +static inline int kvm_tsc_reliable(void)
>> +{
>> + return (boot_cpu_has(X86_FEATURE_CONSTANT_TSC)&&
>> + boot_cpu_has(X86_FEATURE_NONSTOP_TSC)&&
>> + !check_tsc_unstable());
>> +}
>> +
>>
> why can't we re-use vmware TSC_RELIABLE flag?
>

It's only set for VMware. Basically, it means "you are running in a
VMware hypervisor, TSC is reliable". Which KVM won't ever be, at least,
not in production use, so it doesn't make that sort of sense here.
Besides, a system with a reliable TSC can become a system without a
reliable TSC : CPU hotplug will always guarantee this.

We could, however, have the guest set the TSC_RELIABLE flag for itself
if KVM somehow makes that promise (currently, it does not).

Zach


\
 
 \ /
  Last update: 2010-06-17 00:39    [from the cache]
©2003-2010