From: =?UTF-8?B?RmVybmFuZG8gTHVpcyBWw6F6cXVleiBDYW8=?= Subject: Re: [PATCH] kvm: clear guest TSC on reset Date: Thu, 05 Dec 2013 15:08:42 +0900 Message-ID: <52A0186A.2050207@lab.ntt.co.jp> References: <1386054500.25757.10.camel@nexus> <529D90A6.2080801@lab.ntt.co.jp> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: kvm@vger.kernel.org, Will Auld , qemu-devel@nongnu.org To: Paolo Bonzini , Gleb Natapov Return-path: Received: from tama50.ecl.ntt.co.jp ([129.60.39.147]:60834 "EHLO tama50.ecl.ntt.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750973Ab3LEGI6 (ORCPT ); Thu, 5 Dec 2013 01:08:58 -0500 In-Reply-To: <529D90A6.2080801@lab.ntt.co.jp> Sender: kvm-owner@vger.kernel.org List-ID: I realized that the TSC reset should be done in QEMU so I will be replying with a QEMU patch instead of a KVM one. - Fernando On 12/03/2013 05:04 PM, Fernando Luis V=C3=A1zquez Cao wrote: > I think there is a problem with the current patch, so please > ignore for the moment. I will be replying with an update ASAP. > > Sorry for the noise. > > - Fernando > > > On 12/03/2013 04:08 PM, Fernando Luis V=C3=A1zquez Cao wrote: >> VCPU TSC is not cleared by a warm reset (*), which leaves many Linux >> guests vulnerable to the overflow in cyc2ns_offset fixed by upstream >> commit 9993bc635d01a6ee7f6b833b4ee65ce7c06350b1 ("sched/x86: Fix=20 >> overflow >> in cyc2ns_offset"). >> >> To put it in a nutshell, if a Linux guest without the patch above=20 >> applied >> has been up more than 208 days and attempts a warm reset chances are= =20 >> that >> the newly booted kernel will panic or hang. >> >> (*) Intel Xeon E5 processors show the same broken behavior due to >> the errata "TSC is Not Affected by Warm Reset" (Intel=C2=AE Xeo= n=C2=AE >> Processor E5 Family Specification Update - August 2013): "The >> TSC (Time Stamp Counter MSR 10H) should be cleared on >> reset. Due to this erratum the TSC is not affected by warm >> reset." >> >> Cc: stable@vger.kernel.org >> Cc: Will Auld >> Signed-off-by: Fernando Luis Vazquez Cao >> --- >> >> diff -urNp linux-3.13-rc2-orig/arch/x86/kvm/x86.c=20 >> linux-3.13-rc2/arch/x86/kvm/x86.c >> --- linux-3.13-rc2-orig/arch/x86/kvm/x86.c 2013-11-30=20 >> 05:57:14.000000000 +0900 >> +++ linux-3.13-rc2/arch/x86/kvm/x86.c 2013-12-03=20 >> 14:51:53.747600839 +0900 >> @@ -6716,18 +6716,24 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu >> return r; >> } >> -int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) >> +static void kvm_tsc_reset(struct kvm_vcpu *vcpu) >> { >> - int r; >> struct msr_data msr; >> - r =3D vcpu_load(vcpu); >> - if (r) >> - return r; >> msr.data =3D 0x0; >> msr.index =3D MSR_IA32_TSC; >> msr.host_initiated =3D true; >> kvm_write_tsc(vcpu, &msr); >> +} >> + >> +int kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu) >> +{ >> + int r; >> + >> + r =3D vcpu_load(vcpu); >> + if (r) >> + return r; >> + kvm_tsc_reset(vcpu); >> vcpu_put(vcpu); >> return r; >> @@ -6770,6 +6776,10 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcp >> kvm_pmu_reset(vcpu); >> + kvm_tsc_reset(vcpu); >> + if (guest_cpuid_has_tsc_adjust(vcpu)) >> + vcpu->arch.ia32_tsc_adjust_msr =3D 0x0; >> + >> memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs)); >> vcpu->arch.regs_avail =3D ~0; >> vcpu->arch.regs_dirty =3D ~0; >> >> >