Re: [V2 PATCH 8/8] KVM: selftests: x86: xen: Execute cpu specific vmcall instruction

[David Matlack]

On Thu, Sep 15, 2022 at 12:04:48AM +0000, Vishal Annapurve wrote:
> Update xen specific hypercall invocation to execute cpu specific vmcall
> instructions.
> 
> Suggested-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> Signed-off-by: Vishal Annapurve <vannapurve@xxxxxxxxxx>
> ---
>  .../selftests/kvm/x86_64/xen_shinfo_test.c    | 64 +++++++------------
>  .../selftests/kvm/x86_64/xen_vmcall_test.c    | 14 ++--
>  2 files changed, 34 insertions(+), 44 deletions(-)
> 
> diff --git a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
> index 8a5cb800f50e..92ed07f1c772 100644
> --- a/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
> +++ b/tools/testing/selftests/kvm/x86_64/xen_shinfo_test.c
> @@ -145,6 +145,23 @@ static void guest_wait_for_irq(void)
>  	guest_saw_irq = false;
>  }
>  
> +static unsigned long vmcall_helper(unsigned long reg_a, unsigned long reg_di,
> +	unsigned long reg_si)
> +{
> +	unsigned long ret;
> +
> +	if (is_amd_cpu())
> +		__asm__ __volatile__ ("vmmcall" :
> +			"=a" (ret) :
> +			"a" (reg_a), "D" (reg_di), "S" (reg_si));
> +	else
> +		__asm__ __volatile__ ("vmcall" :
> +			"=a" (ret) :
> +			"a" (reg_a), "D" (reg_di), "S" (reg_si));
> +
> +	return ret;
> +}
> +
>  static void guest_code(void)
>  {
>  	struct vcpu_runstate_info *rs = (void *)RUNSTATE_VADDR;
> @@ -217,12 +234,7 @@ static void guest_code(void)
>  	 * EVTCHNOP_send hypercall. */
>  	unsigned long rax;
>  	struct evtchn_send s = { .port = 127 };
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_event_channel_op),
> -			      "D" (EVTCHNOP_send),
> -			      "S" (&s));
> -
> +	rax = vmcall_helper(__HYPERVISOR_event_channel_op, EVTCHNOP_send, (unsigned long)&s);
>  	GUEST_ASSERT(rax == 0);
>  
>  	guest_wait_for_irq();
> @@ -232,12 +244,7 @@ static void guest_code(void)
>  	/* Deliver "outbound" event channel to an eventfd which
>  	 * happens to be one of our own irqfds. */
>  	s.port = 197;
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_event_channel_op),
> -			      "D" (EVTCHNOP_send),
> -			      "S" (&s));
> -
> +	rax = vmcall_helper(__HYPERVISOR_event_channel_op, EVTCHNOP_send, (unsigned long)&s);
>  	GUEST_ASSERT(rax == 0);
>  
>  	guest_wait_for_irq();
> @@ -245,10 +252,7 @@ static void guest_code(void)
>  	GUEST_SYNC(13);
>  
>  	/* Set a timer 100ms in the future. */
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_set_timer_op),
> -			      "D" (rs->state_entry_time + 100000000));
> +	rax = vmcall_helper(__HYPERVISOR_set_timer_op, (rs->state_entry_time + 100000000), 0);
>  	GUEST_ASSERT(rax == 0);
>  
>  	GUEST_SYNC(14);
> @@ -271,36 +275,21 @@ static void guest_code(void)
>  		.timeout = 0,
>  	};
>  
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_sched_op),
> -			      "D" (SCHEDOP_poll),
> -			      "S" (&p));
> -
> +	rax = vmcall_helper(__HYPERVISOR_sched_op, SCHEDOP_poll, (unsigned long)&p);
>  	GUEST_ASSERT(rax == 0);
>  
>  	GUEST_SYNC(17);
>  
>  	/* Poll for an unset port and wait for the timeout. */
>  	p.timeout = 100000000;
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_sched_op),
> -			      "D" (SCHEDOP_poll),
> -			      "S" (&p));
> -
> +	rax = vmcall_helper(__HYPERVISOR_sched_op, SCHEDOP_poll, (unsigned long)&p);
>  	GUEST_ASSERT(rax == 0);
>  
>  	GUEST_SYNC(18);
>  
>  	/* A timer will wake the masked port we're waiting on, while we poll */
>  	p.timeout = 0;
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_sched_op),
> -			      "D" (SCHEDOP_poll),
> -			      "S" (&p));
> -
> +	rax = vmcall_helper(__HYPERVISOR_sched_op, SCHEDOP_poll, (unsigned long)&p);
>  	GUEST_ASSERT(rax == 0);
>  
>  	GUEST_SYNC(19);
> @@ -309,12 +298,7 @@ static void guest_code(void)
>  	 * actual interrupt, while we're polling on a different port. */
>  	ports[0]++;
>  	p.timeout = 0;
> -	__asm__ __volatile__ ("vmcall" :
> -			      "=a" (rax) :
> -			      "a" (__HYPERVISOR_sched_op),
> -			      "D" (SCHEDOP_poll),
> -			      "S" (&p));
> -
> +	rax = vmcall_helper(__HYPERVISOR_sched_op, SCHEDOP_poll, (unsigned long)&p);
>  	GUEST_ASSERT(rax == 0);
>  
>  	guest_wait_for_irq();
> diff --git a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
> index 88914d48c65e..e78f1b5d3af8 100644
> --- a/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
> +++ b/tools/testing/selftests/kvm/x86_64/xen_vmcall_test.c
> @@ -37,10 +37,16 @@ static void guest_code(void)
>  	register unsigned long r9 __asm__("r9") = ARGVALUE(6);
>  
>  	/* First a direct invocation of 'vmcall' */
> -	__asm__ __volatile__("vmcall" :
> -			     "=a"(rax) :
> -			     "a"(rax), "D"(rdi), "S"(rsi), "d"(rdx),
> -			     "r"(r10), "r"(r8), "r"(r9));
> +	if (is_amd_cpu())
> +		__asm__ __volatile__("vmmcall" :
> +			"=a"(rax) :
> +			"a"(rax), "D"(rdi), "S"(rsi), "d"(rdx),
> +			"r"(r10), "r"(r8), "r"(r9));
> +	else
> +		__asm__ __volatile__("vmcall" :
> +			"=a"(rax) :
> +			"a"(rax), "D"(rdi), "S"(rsi), "d"(rdx),
> +			"r"(r10), "r"(r8), "r"(r9));

Can we create common helper functions or macros for doing hypercalls to
reduce the amount of duplicated inline assembly?

>  	GUEST_ASSERT(rax == RETVALUE);
>  
>  	/* Fill in the Xen hypercall page */
> -- 
> 2.37.2.789.g6183377224-goog
>