Re: [PATCH] KVM/nVMX: Use __vmx_vcpu_run in nested_vmx_check_vmentry_hw

[Paolo Bonzini <pbonzini@redhat.com>]

On 17/12/20 19:44, Uros Bizjak wrote:
> Replace inline assembly in nested_vmx_check_vmentry_hw
> with a call to __vmx_vcpu_run.  The function is not
> performance critical, so (double) GPR save/restore
> in __vmx_vcpu_run can be tolerated, as far as performance
> effects are concerned.
> 
> v2: Mark vmx_vmenter SYM_FUNC_START_LOCAL.
> 
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: Sean Christopherson <seanjc@google.com>
> Reviewed-and-tested-by: Sean Christopherson <seanjc@google.com>
> Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
> ---
>   arch/x86/kvm/vmx/nested.c  | 32 +++-----------------------------
>   arch/x86/kvm/vmx/vmenter.S |  2 +-
>   arch/x86/kvm/vmx/vmx.c     |  2 --
>   arch/x86/kvm/vmx/vmx.h     |  1 +
>   4 files changed, 5 insertions(+), 32 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index 89af692deb7e..6ab62bf277c4 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -12,6 +12,7 @@
>   #include "nested.h"
>   #include "pmu.h"
>   #include "trace.h"
> +#include "vmx.h"
>   #include "x86.h"
>   
>   static bool __read_mostly enable_shadow_vmcs = 1;
> @@ -3056,35 +3057,8 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
>   		vmx->loaded_vmcs->host_state.cr4 = cr4;
>   	}
>   
> -	asm(
> -		"sub $%c[wordsize], %%" _ASM_SP "\n\t" /* temporarily adjust RSP for CALL */
> -		"cmp %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t"
> -		"je 1f \n\t"
> -		__ex("vmwrite %%" _ASM_SP ", %[HOST_RSP]") "\n\t"
> -		"mov %%" _ASM_SP ", %c[host_state_rsp](%[loaded_vmcs]) \n\t"
> -		"1: \n\t"
> -		"add $%c[wordsize], %%" _ASM_SP "\n\t" /* un-adjust RSP */
> -
> -		/* Check if vmlaunch or vmresume is needed */
> -		"cmpb $0, %c[launched](%[loaded_vmcs])\n\t"
> -
> -		/*
> -		 * VMLAUNCH and VMRESUME clear RFLAGS.{CF,ZF} on VM-Exit, set
> -		 * RFLAGS.CF on VM-Fail Invalid and set RFLAGS.ZF on VM-Fail
> -		 * Valid.  vmx_vmenter() directly "returns" RFLAGS, and so the
> -		 * results of VM-Enter is captured via CC_{SET,OUT} to vm_fail.
> -		 */
> -		"call vmx_vmenter\n\t"
> -
> -		CC_SET(be)
> -	      : ASM_CALL_CONSTRAINT, CC_OUT(be) (vm_fail)
> -	      :	[HOST_RSP]"r"((unsigned long)HOST_RSP),
> -		[loaded_vmcs]"r"(vmx->loaded_vmcs),
> -		[launched]"i"(offsetof(struct loaded_vmcs, launched)),
> -		[host_state_rsp]"i"(offsetof(struct loaded_vmcs, host_state.rsp)),
> -		[wordsize]"i"(sizeof(ulong))
> -	      : "memory"
> -	);
> +	vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
> +				 vmx->loaded_vmcs->launched);
>   
>   	if (vmx->msr_autoload.host.nr)
>   		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
> diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
> index 90ad7a6246e3..14abe1e37359 100644
> --- a/arch/x86/kvm/vmx/vmenter.S
> +++ b/arch/x86/kvm/vmx/vmenter.S
> @@ -44,7 +44,7 @@
>    * they VM-Fail, whereas a successful VM-Enter + VM-Exit will jump
>    * to vmx_vmexit.
>    */
> -SYM_FUNC_START(vmx_vmenter)
> +SYM_FUNC_START_LOCAL(vmx_vmenter)
>   	/* EFLAGS.ZF is set if VMCS.LAUNCHED == 0 */
>   	je 2f
>   
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index 47b8357b9751..72b496c54bc9 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -6593,8 +6593,6 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
>   	}
>   }
>   
> -bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
> -
>   static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
>   					struct vcpu_vmx *vmx)
>   {
> diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
> index f6f66e5c6510..32db3b033e9b 100644
> --- a/arch/x86/kvm/vmx/vmx.h
> +++ b/arch/x86/kvm/vmx/vmx.h
> @@ -339,6 +339,7 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
>   struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr);
>   void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu);
>   void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
> +bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs, bool launched);
>   int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
>   void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
>   
> 

Queued, thanks.

Paolo