linux-kernel - Re: [KVM timekeeping fixes 4/4] TSC catchup mode

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:	Mon, 20 Sep 2010 12:38:20 -0300
From:	Marcelo Tosatti <mtosatti@...hat.com>
To:	Zachary Amsden <zamsden@...hat.com>
Cc:	kvm@...r.kernel.org, Avi Kivity <avi@...hat.com>,
	Glauber Costa <glommer@...hat.com>,
	linux-kernel@...r.kernel.org
Subject: Re: [KVM timekeeping fixes 4/4] TSC catchup mode

On Sat, Sep 18, 2010 at 02:38:15PM -1000, Zachary Amsden wrote:
> Negate the effects of AN TYM spell while kvm thread is preempted by tracking
> conversion factor to the highest TSC rate and catching the TSC up when it has
> fallen behind the kernel view of time.  Note that once triggered, we don't
> turn off catchup mode.
> 
> A slightly more clever version of this is possible, which only does catchup
> when TSC rate drops, and which specifically targets only CPUs with broken
> TSC, but since these all are considered unstable_tsc(), this patch covers
> all necessary cases.
> 
> Signed-off-by: Zachary Amsden <zamsden@...hat.com>
> ---
>  arch/x86/include/asm/kvm_host.h |    6 +++
>  arch/x86/kvm/x86.c              |   87 +++++++++++++++++++++++++++++---------
>  2 files changed, 72 insertions(+), 21 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 8c5779d..e209078 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -384,6 +384,9 @@ struct kvm_vcpu_arch {
>  	u64 last_host_tsc;
>  	u64 last_guest_tsc;
>  	u64 last_kernel_ns;
> +	u64 last_tsc_nsec;
> +	u64 last_tsc_write;
> +	bool tsc_catchup;
>  
>  	bool nmi_pending;
>  	bool nmi_injected;
> @@ -444,6 +447,9 @@ struct kvm_arch {
>  	u64 last_tsc_nsec;
>  	u64 last_tsc_offset;
>  	u64 last_tsc_write;
> +	u32 virtual_tsc_khz;
> +	u32 virtual_tsc_mult;
> +	s8 virtual_tsc_shift;
>  
>  	struct kvm_xen_hvm_config xen_hvm_config;
>  
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 09f468a..9152156 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -962,6 +962,7 @@ static inline u64 get_kernel_ns(void)
>  }
>  
>  static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
> +unsigned long max_tsc_khz;
>  
>  static inline int kvm_tsc_changes_freq(void)
>  {
> @@ -985,6 +986,24 @@ static inline u64 nsec_to_cycles(u64 nsec)
>  	return ret;
>  }
>  
> +static void kvm_arch_set_tsc_khz(struct kvm *kvm, u32 this_tsc_khz)
> +{
> +	/* Compute a scale to convert nanoseconds in TSC cycles */
> +	kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
> +			   &kvm->arch.virtual_tsc_shift,
> +			   &kvm->arch.virtual_tsc_mult);
> +	kvm->arch.virtual_tsc_khz = this_tsc_khz;
> +}
> +
> +static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
> +{
> +	u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec,
> +				      vcpu->kvm->arch.virtual_tsc_mult,
> +				      vcpu->kvm->arch.virtual_tsc_shift);
> +	tsc += vcpu->arch.last_tsc_write;
> +	return tsc;
> +}
> +
>  void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
>  {
>  	struct kvm *kvm = vcpu->kvm;
> @@ -1029,6 +1048,8 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
>  
>  	/* Reset of TSC must disable overshoot protection below */
>  	vcpu->arch.hv_clock.tsc_timestamp = 0;
> +	vcpu->arch.last_tsc_write = data;
> +	vcpu->arch.last_tsc_nsec = ns;
>  }
>  EXPORT_SYMBOL_GPL(kvm_write_tsc);
>  
> @@ -1041,22 +1062,42 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
>  	s64 kernel_ns, max_kernel_ns;
>  	u64 tsc_timestamp;
>  
> -	if ((!vcpu->time_page))
> -		return 0;
> -
>  	/* Keep irq disabled to prevent changes to the clock */
>  	local_irq_save(flags);
>  	kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
>  	kernel_ns = get_kernel_ns();
>  	this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
> -	local_irq_restore(flags);
>  
>  	if (unlikely(this_tsc_khz == 0)) {
> +		local_irq_restore(flags);
>  		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
>  		return 1;
>  	}
>  
>  	/*
> +	 * We may have to catch up the TSC to match elapsed wall clock
> +	 * time for two reasons, even if kvmclock is used.
> +	 *   1) CPU could have been running below the maximum TSC rate

kvmclock handles frequency changes? 

> +	 *   2) Broken TSC compensation resets the base at each VCPU
> +	 *      entry to avoid unknown leaps of TSC even when running
> +	 *      again on the same CPU.  This may cause apparent elapsed
> +	 *      time to disappear, and the guest to stand still or run
> +	 *	very slowly.

I don't get this. Please explain.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/