Re: [PATCH 01/21] KVM: x86: Split core of hypercall emulation to helper function

[Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx>]

On 2/28/2024 7:20 AM, Paolo Bonzini wrote:
> From: Sean Christopherson <seanjc@xxxxxxxxxx>
>
> By necessity, TDX will use a different register ABI for hypercalls.
> Break out the core functionality so that it may be reused for TDX.
>
> Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> Message-Id: <5134caa55ac3dec33fb2addb5545b52b3b52db02.1705965635.git.isaku.yamahata@xxxxxxxxx>
> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>

Reviewed-by: Binbin Wu <binbin.wu@xxxxxxxxxxxxxxx>

> ---
>   arch/x86/include/asm/kvm_host.h |  4 +++
>   arch/x86/kvm/x86.c              | 56 ++++++++++++++++++++++-----------
>   2 files changed, 42 insertions(+), 18 deletions(-)
>
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 724a0c778f79..85dc0f7d09e3 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -2133,6 +2133,10 @@ static inline void kvm_clear_apicv_inhibit(struct kvm *kvm,
>   	kvm_set_or_clear_apicv_inhibit(kvm, reason, false);
>   }
>   
> +unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
> +				      unsigned long a0, unsigned long a1,
> +				      unsigned long a2, unsigned long a3,
> +				      int op_64_bit, int cpl);
>   int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
>   
>   int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 error_code,
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index b9dfe3179332..f10a5a617120 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -10046,26 +10046,15 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
>   	return kvm_skip_emulated_instruction(vcpu);
>   }
>   
> -int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
> +unsigned long __kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
> +				      unsigned long a0, unsigned long a1,
> +				      unsigned long a2, unsigned long a3,
> +				      int op_64_bit, int cpl)
>   {
> -	unsigned long nr, a0, a1, a2, a3, ret;
> -	int op_64_bit;
> -
> -	if (kvm_xen_hypercall_enabled(vcpu->kvm))
> -		return kvm_xen_hypercall(vcpu);
> -
> -	if (kvm_hv_hypercall_enabled(vcpu))
> -		return kvm_hv_hypercall(vcpu);
> -
> -	nr = kvm_rax_read(vcpu);
> -	a0 = kvm_rbx_read(vcpu);
> -	a1 = kvm_rcx_read(vcpu);
> -	a2 = kvm_rdx_read(vcpu);
> -	a3 = kvm_rsi_read(vcpu);
> +	unsigned long ret;
>   
>   	trace_kvm_hypercall(nr, a0, a1, a2, a3);
>   
> -	op_64_bit = is_64_bit_hypercall(vcpu);
>   	if (!op_64_bit) {
>   		nr &= 0xFFFFFFFF;
>   		a0 &= 0xFFFFFFFF;
> @@ -10074,7 +10063,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
>   		a3 &= 0xFFFFFFFF;
>   	}
>   
> -	if (static_call(kvm_x86_get_cpl)(vcpu) != 0) {
> +	if (cpl) {
>   		ret = -KVM_EPERM;
>   		goto out;
>   	}
> @@ -10135,18 +10124,49 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
>   
>   		WARN_ON_ONCE(vcpu->run->hypercall.flags & KVM_EXIT_HYPERCALL_MBZ);
>   		vcpu->arch.complete_userspace_io = complete_hypercall_exit;
> +		/* stat is incremented on completion. */
>   		return 0;
>   	}
>   	default:
>   		ret = -KVM_ENOSYS;
>   		break;
>   	}
> +
>   out:
> +	++vcpu->stat.hypercalls;
> +	return ret;
> +}
> +EXPORT_SYMBOL_GPL(__kvm_emulate_hypercall);
> +
> +int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
> +{
> +	unsigned long nr, a0, a1, a2, a3, ret;
> +	int op_64_bit;
> +	int cpl;
> +
> +	if (kvm_xen_hypercall_enabled(vcpu->kvm))
> +		return kvm_xen_hypercall(vcpu);
> +
> +	if (kvm_hv_hypercall_enabled(vcpu))
> +		return kvm_hv_hypercall(vcpu);
> +
> +	nr = kvm_rax_read(vcpu);
> +	a0 = kvm_rbx_read(vcpu);
> +	a1 = kvm_rcx_read(vcpu);
> +	a2 = kvm_rdx_read(vcpu);
> +	a3 = kvm_rsi_read(vcpu);
> +	op_64_bit = is_64_bit_hypercall(vcpu);
> +	cpl = static_call(kvm_x86_get_cpl)(vcpu);
> +
> +	ret = __kvm_emulate_hypercall(vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl);
> +	if (nr == KVM_HC_MAP_GPA_RANGE && !ret)
> +		/* MAP_GPA tosses the request to the user space. */
> +		return 0;
> +
>   	if (!op_64_bit)
>   		ret = (u32)ret;
>   	kvm_rax_write(vcpu, ret);
>   
> -	++vcpu->stat.hypercalls;
>   	return kvm_skip_emulated_instruction(vcpu);
>   }
>   EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);