Re: [PATCH v5 4/9] KVM-HV: KVM Steal time implementation

[Marcelo Tosatti]

On Mon, Jul 04, 2011 at 11:32:23AM -0400, Glauber Costa wrote:
> To implement steal time, we need the hypervisor to pass the guest
> information about how much time was spent running other processes
> outside the VM, while the vcpu had meaningful work to do - halt
> time does not count.
> 
> This information is acquired through the run_delay field of
> delayacct/schedstats infrastructure, that counts time spent in a
> runqueue but not running.
> 
> Steal time is a per-cpu information, so the traditional MSR-based
> infrastructure is used. A new msr, KVM_MSR_STEAL_TIME, holds the
> memory area address containing information about steal time
> 
> This patch contains the hypervisor part of the steal time infrasructure,
> and can be backported independently of the guest portion.
> 
> Signed-off-by: Glauber Costa <glommer@xxxxxxxxxx>
> CC: Rik van Riel <riel@xxxxxxxxxx>
> CC: Jeremy Fitzhardinge <jeremy.fitzhardinge@xxxxxxxxxx>
> CC: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> CC: Avi Kivity <avi@xxxxxxxxxx>
> CC: Anthony Liguori <aliguori@xxxxxxxxxx>
> CC: Eric B Munson <emunson@xxxxxxxxx>
> ---
>  arch/x86/include/asm/kvm_host.h |    8 +++++
>  arch/x86/include/asm/kvm_para.h |    4 +++
>  arch/x86/kvm/Kconfig            |    1 +
>  arch/x86/kvm/x86.c              |   56 ++++++++++++++++++++++++++++++++++++--
>  4 files changed, 66 insertions(+), 3 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index da6bbee..9ba354d 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -389,6 +389,14 @@ struct kvm_vcpu_arch {
>  	unsigned int hw_tsc_khz;
>  	unsigned int time_offset;
>  	struct page *time_page;
> +
> +	struct {
> +		u64 msr_val;
> +		u64 last_steal;
> +		struct gfn_to_hva_cache stime;
> +		struct kvm_steal_time steal;
> +	} st;
> +
>  	u64 last_guest_tsc;
>  	u64 last_kernel_ns;
>  	u64 last_tsc_nsec;
> diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
> index 65f8bb9..c484ba8 100644
> --- a/arch/x86/include/asm/kvm_para.h
> +++ b/arch/x86/include/asm/kvm_para.h
> @@ -45,6 +45,10 @@ struct kvm_steal_time {
>  	__u32 pad[12];
>  };
>  
> +#define KVM_STEAL_ALIGNMENT_BITS 5
> +#define KVM_STEAL_VALID_BITS ((-1ULL << (KVM_STEAL_ALIGNMENT_BITS + 1)))
> +#define KVM_STEAL_RESERVED_MASK (((1 << KVM_STEAL_ALIGNMENT_BITS) - 1 ) << 1)
> +
>  #define KVM_MAX_MMU_OP_BATCH           32
>  
>  #define KVM_ASYNC_PF_ENABLED			(1 << 0)
> diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> index 50f6364..99c3f05 100644
> --- a/arch/x86/kvm/Kconfig
> +++ b/arch/x86/kvm/Kconfig
> @@ -31,6 +31,7 @@ config KVM
>  	select KVM_ASYNC_PF
>  	select USER_RETURN_NOTIFIER
>  	select KVM_MMIO
> +	select TASK_DELAY_ACCT
>  	---help---
>  	  Support hosting fully virtualized guest machines using hardware
>  	  virtualization extensions.  You will need a fairly recent
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 7167717..237bcdc 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -808,12 +808,12 @@ EXPORT_SYMBOL_GPL(kvm_get_dr);
>   * kvm-specific. Those are put in the beginning of the list.
>   */
>  
> -#define KVM_SAVE_MSRS_BEGIN	8
> +#define KVM_SAVE_MSRS_BEGIN	9
>  static u32 msrs_to_save[] = {
>  	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
>  	MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
>  	HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
> -	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN,
> +	HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN, MSR_KVM_STEAL_TIME,
>  	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
>  	MSR_STAR,
>  #ifdef CONFIG_X86_64
> @@ -1491,6 +1491,27 @@ static void kvmclock_reset(struct kvm_vcpu *vcpu)
>  	}
>  }
>  
> +static void record_steal_time(struct kvm_vcpu *vcpu)
> +{
> +	u64 delta;
> +
> +	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
> +		return;
> +
> +	if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
> +		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
> +		return;

The guest memory page is not pinned, sleeping via
__copy_from_user/to_user is not allowed in vcpu_load context. Either pin
it or use atomic acessors.

> +	case MSR_KVM_STEAL_TIME:
> +		vcpu->arch.st.msr_val = data;
> +
> +		if (!(data & KVM_MSR_ENABLED)) {
> +			break;
> +		}

On failure below this point, msr_val should be cleared of KVM_MSR_ENABLED?

> +
> +		if (unlikely(!sched_info_on()))
> +			break;
> +
> +		if (data & KVM_STEAL_RESERVED_MASK)
> +			return 1;
> +
> +		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
> +							data & KVM_STEAL_VALID_BITS))
> +			return 1;
> +
> +		vcpu->arch.st.last_steal = current->sched_info.run_delay;
> +
> +		record_steal_time(vcpu);
> +		break;
> +
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/