Re: [PATCH v14 003/113] KVM: x86/vmx: Refactor KVM VMX module init/exit functions

[Zhi Wang]

On Sun, 28 May 2023 21:18:45 -0700
isaku.yamahata@xxxxxxxxx wrote:

> From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> 
> Currently, KVM VMX module initialization/exit functions are a single
> function each.  Refactor KVM VMX module initialization functions into KVM
> common part and VMX part so that TDX specific part can be added cleanly.
> Opportunistically refactor module exit function as well.
> 
> The current module initialization flow is,
> 0.) Check if VMX is supported,
> 1.) hyper-v specific initialization,
> 2.) system-wide x86 specific and vendor specific initialization,
> 3.) Final VMX specific system-wide initialization,
> 4.) calculate the sizes of VMX kvm structure and VMX vcpu structure,
> 5.) report those sizes to the KVM common layer and KVM common
>     initialization
> 
> Refactor the KVM VMX module initialization function into functions with a
> wrapper function to separate VMX logic in vmx.c from a file, main.c, common
> among VMX and TDX.  Introduce a wrapper function for vmx_init().
> 
> The KVM architecture common layer allocates struct kvm with reported size
> for architecture-specific code.  The KVM VMX module defines its structure
> as struct vmx_kvm { struct kvm; VMX specific members;} and uses it as
> struct vmx kvm.  Similar for vcpu structure. TDX KVM patches will define
> TDX specific kvm and vcpu structures.
> 
> The current module exit function is also a single function, a combination
> of VMX specific logic and common KVM logic.  Refactor it into VMX specific
> logic and KVM common logic.  This is just refactoring to keep the VMX
> specific logic in vmx.c from main.c.
> 
> Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
> ---
>  arch/x86/kvm/vmx/main.c    | 50 +++++++++++++++++++++++++++++++++++
>  arch/x86/kvm/vmx/vmx.c     | 54 +++++---------------------------------
>  arch/x86/kvm/vmx/x86_ops.h | 13 ++++++++-
>  3 files changed, 68 insertions(+), 49 deletions(-)
> 
> diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
> index a59559ff140e..791ee271393d 100644
> --- a/arch/x86/kvm/vmx/main.c
> +++ b/arch/x86/kvm/vmx/main.c
> @@ -165,3 +165,53 @@ struct kvm_x86_init_ops vt_init_ops __initdata = {
>  	.runtime_ops = &vt_x86_ops,
>  	.pmu_ops = &intel_pmu_ops,
>  };
> +
> +static int __init vt_init(void)
> +{
> +	unsigned int vcpu_size, vcpu_align;
> +	int r;
> +
> +	if (!kvm_is_vmx_supported())
> +		return -EOPNOTSUPP;
> +
> +	/*
> +	 * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing
> +	 * to unwind if a later step fails.
> +	 */
> +	hv_init_evmcs();
> +
> +	r = kvm_x86_vendor_init(&vt_init_ops);
> +	if (r)
> +		return r;
> +
> +	r = vmx_init();
> +	if (r)
> +		goto err_vmx_init;
> +
> +	/*
> +	 * Common KVM initialization _must_ come last, after this, /dev/kvm is
> +	 * exposed to userspace!
> +	 */
> +	vcpu_size = sizeof(struct vcpu_vmx);
> +	vcpu_align = __alignof__(struct vcpu_vmx);
> +	r = kvm_init(vcpu_size, vcpu_align, THIS_MODULE);
> +	if (r)
> +		goto err_kvm_init;
> +
> +	return 0;
> +
---------------------------------
> +err_kvm_init:
> +	vmx_exit();
> +err_vmx_init:
> +	kvm_x86_vendor_exit();
> +	return r;
> +}
> +module_init(vt_init);
> +
----------------------------------
> +static void vt_exit(void)
> +{
> +	kvm_exit();
> +	kvm_x86_vendor_exit();
> +	vmx_exit();
----------------------------------

It seems the exiting sequences above are a little bit different with
each other (PS: It is not a prob introduced in this patch):

vmx_exit()
kvm_x86_vendor_exit()
....

and

...
kvm_x86_vnedor_exit()
vmx_exit()

I was wondering which one should be correct. Literally, the exiting
sequence would be in reversing order of the initialization sequence.

> +}
> +module_exit(vt_exit);
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index ed7bf8fc55a8..9e4def64495b 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -554,7 +554,7 @@ static int hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu)
>  	return 0;
>  }
>  
> -static __init void hv_init_evmcs(void)
> +__init void hv_init_evmcs(void)
>  {
>  	int cpu;
>  
> @@ -590,7 +590,7 @@ static __init void hv_init_evmcs(void)
>  	}
>  }
>  
> -static void hv_reset_evmcs(void)
> +void hv_reset_evmcs(void)
>  {
>  	struct hv_vp_assist_page *vp_ap;
>  
> @@ -614,10 +614,6 @@ static void hv_reset_evmcs(void)
>  	vp_ap->current_nested_vmcs = 0;
>  	vp_ap->enlighten_vmentry = 0;
>  }
> -
> -#else /* IS_ENABLED(CONFIG_HYPERV) */
> -static void hv_init_evmcs(void) {}
> -static void hv_reset_evmcs(void) {}
>  #endif /* IS_ENABLED(CONFIG_HYPERV) */
>  
>  /*
> @@ -2715,7 +2711,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
>  	return 0;
>  }
>  
> -static bool kvm_is_vmx_supported(void)
> +bool kvm_is_vmx_supported(void)
>  {
>  	int cpu = raw_smp_processor_id();
>  
> @@ -8381,7 +8377,7 @@ static void vmx_cleanup_l1d_flush(void)
>  	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
>  }
>  
> -static void __vmx_exit(void)
> +void vmx_exit(void)
>  {
>  	allow_smaller_maxphyaddr = false;
>  
> @@ -8392,32 +8388,10 @@ static void __vmx_exit(void)
>  	vmx_cleanup_l1d_flush();
>  }
>  
> -static void vmx_exit(void)
> -{
> -	kvm_exit();
> -	kvm_x86_vendor_exit();
> -
> -	__vmx_exit();
> -}
> -module_exit(vmx_exit);
> -
> -static int __init vmx_init(void)
> +int __init vmx_init(void)
>  {
>  	int r, cpu;
>  
> -	if (!kvm_is_vmx_supported())
> -		return -EOPNOTSUPP;
> -
> -	/*
> -	 * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing
> -	 * to unwind if a later step fails.
> -	 */
> -	hv_init_evmcs();
> -
> -	r = kvm_x86_vendor_init(&vt_init_ops);
> -	if (r)
> -		return r;
> -
>  	/*
>  	 * Must be called after common x86 init so enable_ept is properly set
>  	 * up. Hand the parameter mitigation value in which was stored in
> @@ -8427,7 +8401,7 @@ static int __init vmx_init(void)
>  	 */
>  	r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
>  	if (r)
> -		goto err_l1d_flush;
> +		return r;
>  
>  	vmx_setup_fb_clear_ctrl();
>  
> @@ -8448,21 +8422,5 @@ static int __init vmx_init(void)
>  	if (!enable_ept)
>  		allow_smaller_maxphyaddr = true;
>  
> -	/*
> -	 * Common KVM initialization _must_ come last, after this, /dev/kvm is
> -	 * exposed to userspace!
> -	 */
> -	r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx),
> -		     THIS_MODULE);
> -	if (r)
> -		goto err_kvm_init;
> -
>  	return 0;
> -
> -err_kvm_init:
> -	__vmx_exit();
> -err_l1d_flush:
> -	kvm_x86_vendor_exit();
> -	return r;
>  }
> -module_init(vmx_init);
> diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
> index e9ec4d259ff5..051b5c4b5c2f 100644
> --- a/arch/x86/kvm/vmx/x86_ops.h
> +++ b/arch/x86/kvm/vmx/x86_ops.h
> @@ -8,11 +8,22 @@
>  
>  #include "x86.h"
>  
> -__init int vmx_hardware_setup(void);
> +#if IS_ENABLED(CONFIG_HYPERV)
> +__init void hv_init_evmcs(void);
> +void hv_reset_evmcs(void);
> +#else /* IS_ENABLED(CONFIG_HYPERV) */
> +static inline void hv_init_evmcs(void) {}
> +static inline void hv_reset_evmcs(void) {}
> +#endif /* IS_ENABLED(CONFIG_HYPERV) */
> +
> +bool kvm_is_vmx_supported(void);
> +int __init vmx_init(void);
> +void vmx_exit(void);
>  
>  extern struct kvm_x86_ops vt_x86_ops __initdata;
>  extern struct kvm_x86_init_ops vt_init_ops __initdata;
>  
> +__init int vmx_hardware_setup(void);
>  void vmx_hardware_unsetup(void);
>  int vmx_check_processor_compat(void);
>  int vmx_hardware_enable(void);