Re: [PATCH v3 04/10] x86/hyper-v: fast hypercall implementation

[Andy Lutomirski]

On Mon, May 22, 2017 at 3:44 AM, Vitaly Kuznetsov <vkuznets@xxxxxxxxxx> wrote:
> Andy Lutomirski <luto@xxxxxxxxxx> writes:
>
>> On 05/19/2017 07:09 AM, Vitaly Kuznetsov wrote:
>>> Hyper-V supports 'fast' hypercalls when all parameters are passed through
>>> registers. Implement an inline version of a simpliest of these calls:
>>> hypercall with one 8-byte input and no output.
>>>
>>> Proper hypercall input interface (struct hv_hypercall_input) definition is
>>> added as well.
>>>
>>> Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
>>> Acked-by: K. Y. Srinivasan <kys@xxxxxxxxxxxxx>
>>> Tested-by: Simon Xiao <sixiao@xxxxxxxxxxxxx>
>>> Tested-by: Srikanth Myakam <v-srm@xxxxxxxxxxxxx>
>>> ---
>>>   arch/x86/include/asm/mshyperv.h    | 39 ++++++++++++++++++++++++++++++++++++++
>>>   arch/x86/include/uapi/asm/hyperv.h | 19 +++++++++++++++++++
>>>   2 files changed, 58 insertions(+)
>>>
>>> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
>>> index e293937..028e29b 100644
>>> --- a/arch/x86/include/asm/mshyperv.h
>>> +++ b/arch/x86/include/asm/mshyperv.h
>>> @@ -216,6 +216,45 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
>>>   #endif /* !x86_64 */
>>>   }
>>>   +/* Fast hypercall with 8 bytes of input and no output */
>>> +static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
>>> +{
>>> +    union hv_hypercall_input control = {0};
>>> +
>>> +    control.code = code;
>>> +    control.fast = 1;
>>> +#ifdef CONFIG_X86_64
>>> +    {
>>> +            u64 hv_status;
>>> +
>>> +            __asm__ __volatile__("call *%3"
>>> +                                 : "=a" (hv_status),
>>> +                                   "+c" (control.as_uint64), "+d" (input1)
>>> +                                 : "m" (hv_hypercall_pg)
>>> +                                 : "cc", "r8", "r9", "r10", "r11");
>>> +            return hv_status;
>>> +    }
>>> +#else
>>> +    {
>>> +            u32 hv_status_hi, hv_status_lo;
>>> +            u32 input1_hi = (u32)(input1 >> 32);
>>> +            u32 input1_lo = (u32)input1;
>>> +
>>> +            __asm__ __volatile__ ("call *%6"
>>> +                                  : "=d"(hv_status_hi),
>>> +                                    "=a"(hv_status_lo),
>>> +                                    "+c"(input1_lo)
>>> +                                  : "d" (control.as_uint32_hi),
>>> +                                    "a" (control.as_uint32_lo),
>>> +                                    "b" (input1_hi),
>>> +                                    "m" (hv_hypercall_pg)
>>> +                                  : "cc", "edi", "esi");
>>> +
>>> +            return hv_status_lo | ((u64)hv_status_hi << 32);
>>> +    }
>>> +#endif
>>
>> This is going to need an explicit "sp" annotation to force a stack
>> frame, I think.  Otherwise objtool is likely to get mad in a
>> frame-pointer-omitted build.
>>
>
> You mean I should do something like
>
> diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
> index 359967f..f86c4ae 100644
> --- a/arch/x86/include/asm/mshyperv.h
> +++ b/arch/x86/include/asm/mshyperv.h
> @@ -221,6 +221,7 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
>  static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
>  {
>         union hv_hypercall_input control = {0};
> +       register void *__sp asm(_ASM_SP);

Exactly.