Re: [PATCH] kvm: x86: fix kvmclock update protocol

2015-04-24 Thread Marcelo Tosatti
On Thu, Apr 23, 2015 at 01:46:55PM +0200, Paolo Bonzini wrote: > From: Radim Krčmář > > The kvmclock spec says that the host will increment a version field to > an odd number, then update stuff, then increment it to an even number. > The host is buggy and doesn't do this, and the result is observ

Re: [PATCH] kvm: x86: fix kvmclock update protocol

2015-04-23 Thread Radim Krčmář
2015-04-23 13:46+0200, Paolo Bonzini: > From: Radim Krčmář > > The kvmclock spec says that the host will increment a version field to > an odd number, then update stuff, then increment it to an even number. > The host is buggy and doesn't do this, and the result is observable > when one vcpu read

[PATCH] kvm: x86: fix kvmclock update protocol

2015-04-23 Thread Paolo Bonzini
From: Radim Krčmář The kvmclock spec says that the host will increment a version field to an odd number, then update stuff, then increment it to an even number. The host is buggy and doesn't do this, and the result is observable when one vcpu reads another vcpu's kvmclock data. There's no good w