Re: [PATCH v2 09/14] x86/hvm: Setup TSC scaling ratio

[Boris Ostrovsky <boris.ostrovsky@oracle.com>]

On 12/06/2015 03:58 PM, Haozhong Zhang wrote:
> This patch adds a field tsc_scaling_ratio in struct hvm_vcpu to
> record the TSC scaling ratio, and sets it up when tsc_set_info() is
> called for a vcpu or when a vcpu is restored or reset.
>
> Signed-off-by: Haozhong Zhang <haozhong.zhang@intel.com>

Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>

with a few nits below.

> ---
>   xen/arch/x86/hvm/hvm.c            | 30 ++++++++++++++++++++++++++++++
>   xen/arch/x86/hvm/svm/svm.c        |  6 ++++--
>   xen/arch/x86/time.c               | 13 ++++++++++++-
>   xen/include/asm-x86/hvm/hvm.h     |  5 +++++
>   xen/include/asm-x86/hvm/svm/svm.h |  3 ---
>   xen/include/asm-x86/hvm/vcpu.h    |  2 ++
>   xen/include/asm-x86/math64.h      | 30 ++++++++++++++++++++++++++++++
>   7 files changed, 83 insertions(+), 6 deletions(-)
>   create mode 100644 xen/include/asm-x86/math64.h
>
> diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
> index 0e63c33..52a0ef8 100644
> --- a/xen/arch/x86/hvm/hvm.c
> +++ b/xen/arch/x86/hvm/hvm.c
> @@ -65,6 +65,7 @@
>   #include <asm/mtrr.h>
>   #include <asm/apic.h>
>   #include <asm/vm_event.h>
> +#include <asm/math64.h>
>   #include <public/sched.h>
>   #include <public/hvm/ioreq.h>
>   #include <public/version.h>
> @@ -301,6 +302,29 @@ int hvm_set_guest_pat(struct vcpu *v, u64 guest_pat)
>       return 1;
>   }
>   
> +void hvm_setup_tsc_scaling(struct vcpu *v)
> +{
> +    u64 ratio;
> +
> +    if ( !hvm_funcs.tsc_scaling_supported )
> +        return;
> +
> +    /*
> +     * The multiplication of the first two terms may overflow a 64-bit
> +     * integer, so use mul_u64_u32_div() instead to keep precision.
> +     */
> +    ratio = mul_u64_u32_div(1ULL << hvm_funcs.tsc_scaling_ratio_frac_bits,
> +                            v->domain->arch.tsc_khz, cpu_khz);
> +
> +    if ( ratio == 0 || ratio > hvm_funcs.max_tsc_scaling_ratio )
> +        return;
> +
> +    v->arch.hvm_vcpu.tsc_scaling_ratio = ratio;
> +
> +    if ( hvm_funcs.setup_tsc_scaling )
> +        hvm_funcs.setup_tsc_scaling(v);
> +}
> +
>   void hvm_set_guest_tsc_fixed(struct vcpu *v, u64 guest_tsc, u64 at_tsc)
>   {
>       uint64_t tsc;
> @@ -2024,6 +2048,9 @@ static int hvm_load_cpu_ctxt(struct domain *d, hvm_domain_context_t *h)
>       if ( hvm_funcs.load_cpu_ctxt(v, &ctxt) < 0 )
>           return -EINVAL;
>   
> +    if ( hvm_funcs.tsc_scaling_supported )
> +        hvm_setup_tsc_scaling(v);
> +


I think you can drop the test here (and below) since you do the same 
check inside hvm_setup_tsc_scaling()


>       v->arch.hvm_vcpu.msr_tsc_aux = ctxt.msr_tsc_aux;
>   
>       seg.limit = ctxt.idtr_limit;
> @@ -5584,6 +5611,9 @@ void hvm_vcpu_reset_state(struct vcpu *v, uint16_t cs, uint16_t ip)
>       hvm_set_segment_register(v, x86_seg_gdtr, &reg);
>       hvm_set_segment_register(v, x86_seg_idtr, &reg);
>   
> +    if ( hvm_funcs.tsc_scaling_supported )
> +        hvm_setup_tsc_scaling(v);
> +
>       /* Sync AP's TSC with BSP's. */
>       v->arch.hvm_vcpu.cache_tsc_offset =
>           v->domain->vcpu[0]->arch.hvm_vcpu.cache_tsc_offset;
> diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
> index 9f741d0..d291327 100644
> --- a/xen/arch/x86/hvm/svm/svm.c
> +++ b/xen/arch/x86/hvm/svm/svm.c
> @@ -811,7 +811,7 @@ static uint64_t svm_scale_tsc(struct vcpu *v, uint64_t tsc)
>       if ( !cpu_has_tsc_ratio || d->arch.vtsc )
>           return tsc;
>   
> -    return scale_tsc(tsc, vcpu_tsc_ratio(v));
> +    return scale_tsc(tsc, v->arch.hvm_vcpu.tsc_scaling_ratio);
>   }
>   
>   static uint64_t svm_get_tsc_offset(uint64_t host_tsc, uint64_t guest_tsc,
> @@ -987,7 +987,7 @@ static inline void svm_tsc_ratio_save(struct vcpu *v)
>   static inline void svm_tsc_ratio_load(struct vcpu *v)
>   {
>       if ( cpu_has_tsc_ratio && !v->domain->arch.vtsc )
> -        wrmsrl(MSR_AMD64_TSC_RATIO, vcpu_tsc_ratio(v));
> +        wrmsrl(MSR_AMD64_TSC_RATIO, v->arch.hvm_vcpu.tsc_scaling_ratio);
>   }
>   
>   static void svm_ctxt_switch_from(struct vcpu *v)
> @@ -1193,6 +1193,8 @@ static int svm_vcpu_initialise(struct vcpu *v)
>   
>       svm_guest_osvw_init(v);
>   
> +    v->arch.hvm_vcpu.tsc_scaling_ratio = DEFAULT_TSC_RATIO;
> +
>       return 0;
>   }
>   
> diff --git a/xen/arch/x86/time.c b/xen/arch/x86/time.c
> index 732d1e9..d4a94eb 100644
> --- a/xen/arch/x86/time.c
> +++ b/xen/arch/x86/time.c
> @@ -1902,8 +1902,19 @@ void tsc_set_info(struct domain *d,
>       if ( has_hvm_container_domain(d) )
>       {
>           hvm_set_rdtsc_exiting(d, d->arch.vtsc);
> -        if ( d->vcpu && d->vcpu[0] && incarnation == 0 )
> +        if ( d->vcpu && d->vcpu[0] )
>           {
> +             /*
> +             * TSC scaling ratio on BSP is set here during initial boot, while

During domain creation rather then during boot.

> +             * the same TSC scaling ratio on APs will be set in
> +             * hvm_vcpu_reset_state().
> +             */
> +            if ( !d->arch.vtsc && hvm_funcs.tsc_scaling_supported )
> +                hvm_setup_tsc_scaling(d->vcpu[0]);
> +
> +            if ( incarnation )
> +                return;
> +
>               /*
>                * set_tsc_offset() is called from hvm_vcpu_initialise() before
>                * tsc_set_info(). New vtsc mode may require recomputing TSC
> diff --git a/xen/include/asm-x86/hvm/hvm.h b/xen/include/asm-x86/hvm/hvm.h
> index 8b10a67..e74524e 100644
> --- a/xen/include/asm-x86/hvm/hvm.h
> +++ b/xen/include/asm-x86/hvm/hvm.h
> @@ -226,6 +226,9 @@ struct hvm_function_table {
>       int (*altp2m_vcpu_emulate_vmfunc)(struct cpu_user_regs *regs);
>   
>       uint64_t (*scale_tsc)(struct vcpu *v, uint64_t tsc);
> +
> +    /* Architecture function to setup TSC scaling ratio */
> +    void (*setup_tsc_scaling)(struct vcpu *v);
>   };
>   
>   extern struct hvm_function_table hvm_funcs;
> @@ -261,6 +264,8 @@ void hvm_set_guest_tsc_fixed(struct vcpu *v, u64 guest_tsc, u64 at_tsc);
>   u64 hvm_get_guest_tsc_fixed(struct vcpu *v, u64 at_tsc);
>   #define hvm_get_guest_tsc(v) hvm_get_guest_tsc_fixed(v, 0)
>   
> +void hvm_setup_tsc_scaling(struct vcpu *v);
> +
>   int hvm_set_mode(struct vcpu *v, int mode);
>   void hvm_init_guest_time(struct domain *d);
>   void hvm_set_guest_time(struct vcpu *v, u64 guest_time);
> diff --git a/xen/include/asm-x86/hvm/svm/svm.h b/xen/include/asm-x86/hvm/svm/svm.h
> index d60ec23..c954b7e 100644
> --- a/xen/include/asm-x86/hvm/svm/svm.h
> +++ b/xen/include/asm-x86/hvm/svm/svm.h
> @@ -97,9 +97,6 @@ extern u32 svm_feature_flags;
>   /* TSC rate */
>   #define DEFAULT_TSC_RATIO       0x0000000100000000ULL
>   #define TSC_RATIO_RSVD_BITS     0xffffff0000000000ULL
> -#define TSC_RATIO(g_khz, h_khz) ( (((u64)(g_khz)<<32)/(u64)(h_khz)) & \
> -                                  ~TSC_RATIO_RSVD_BITS )
> -#define vcpu_tsc_ratio(v)       TSC_RATIO((v)->domain->arch.tsc_khz, cpu_khz)
>   
>   extern void svm_host_osvw_reset(void);
>   extern void svm_host_osvw_init(void);
> diff --git a/xen/include/asm-x86/hvm/vcpu.h b/xen/include/asm-x86/hvm/vcpu.h
> index 152d9f3..901c988 100644
> --- a/xen/include/asm-x86/hvm/vcpu.h
> +++ b/xen/include/asm-x86/hvm/vcpu.h
> @@ -175,6 +175,8 @@ struct hvm_vcpu {
>       u64                 msr_tsc_adjust;
>       u64                 msr_xss;
>   
> +    u64                 tsc_scaling_ratio;
> +
>       union {
>           struct arch_vmx_struct vmx;
>           struct arch_svm_struct svm;
> diff --git a/xen/include/asm-x86/math64.h b/xen/include/asm-x86/math64.h
> new file mode 100644
> index 0000000..9af6aee
> --- /dev/null
> +++ b/xen/include/asm-x86/math64.h
> @@ -0,0 +1,30 @@
> +#ifndef __X86_MATH64
> +#define __X86_MATH64
> +
> +/*
> + * (a * mul) / divisor
> + */
> +static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)

Since this is taken from Linux code I thinkit's worth mentioning so.

-boris

> +{
> +    union {
> +        u64 ll;
> +        struct {
> +            u32 low, high;
> +        } l;
> +    } u, rl, rh;
> +
> +    u.ll = a;
> +    rl.ll = (u64)u.l.low * mul;
> +    rh.ll = (u64)u.l.high * mul + rl.l.high;
> +
> +    /* Bits 32-63 of the result will be in rh.l.low. */
> +    rl.l.high = do_div(rh.ll, divisor);
> +
> +    /* Bits 0-31 of the result will be in rl.l.low. */
> +    do_div(rl.ll, divisor);
> +
> +    rl.l.high = rh.l.low;
> +    return rl.ll;
> +}
> +
> +#endif