Re: [PATCH 2/2] KVM: x86: MMU: Move handle_mmio_page_fault() call to kvm_mmu_page_fault()

[Paolo Bonzini]

On 22/02/2016 09:23, Takuya Yoshikawa wrote:
> Rather than placing a handle_mmio_page_fault() call in each
> vcpu->arch.mmu.page_fault() handler, moving it up to
> kvm_mmu_page_fault() makes the code better:
> 
>  - avoids code duplication
>  - for kvm_arch_async_page_ready(), which is the other caller of
>    vcpu->arch.mmu.page_fault(), removes an extra error_code check
>  - avoids returning both RET_MMIO_PF_* values and raw integer values
>    from vcpu->arch.mmu.page_fault()
> 
> Signed-off-by: Takuya Yoshikawa <yoshikawa_takuya_b1@xxxxxxxxxxxxx>
> ---
>  arch/x86/kvm/mmu.c         | 39 ++++++++++++++++-----------------------
>  arch/x86/kvm/paging_tmpl.h | 19 ++++++-------------
>  2 files changed, 22 insertions(+), 36 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index a28b734..2ce3892 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c
> @@ -3370,13 +3370,6 @@ static int nonpaging_page_fault(struct kvm_vcpu *vcpu, gva_t gva,
>  
>  	pgprintk("%s: gva %lx error %x\n", __func__, gva, error_code);
>  
> -	if (unlikely(error_code & PFERR_RSVD_MASK)) {
> -		r = handle_mmio_page_fault(vcpu, gva, true);
> -
> -		if (likely(r != RET_MMIO_PF_INVALID))
> -			return r;
> -	}
> -
>  	r = mmu_topup_memory_caches(vcpu);
>  	if (r)
>  		return r;
> @@ -3460,13 +3453,6 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
>  
>  	MMU_WARN_ON(!VALID_PAGE(vcpu->arch.mmu.root_hpa));
>  
> -	if (unlikely(error_code & PFERR_RSVD_MASK)) {
> -		r = handle_mmio_page_fault(vcpu, gpa, true);
> -
> -		if (likely(r != RET_MMIO_PF_INVALID))
> -			return r;
> -	}
> -
>  	r = mmu_topup_memory_caches(vcpu);
>  	if (r)
>  		return r;
> @@ -4361,18 +4347,27 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
>  	enum emulation_result er;
>  	bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
>  
> +	if (unlikely(error_code & PFERR_RSVD_MASK)) {
> +		r = handle_mmio_page_fault(vcpu, cr2, direct);
> +		if (r == RET_MMIO_PF_EMULATE) {
> +			emulation_type = 0;
> +			goto emulate;
> +		}
> +		if (r == RET_MMIO_PF_RETRY)
> +			return 1;
> +		if (r < 0)
> +			return r;

It's a bit weird how RET_MMIO_PF_RETRY is zero, but unifying all the
return values of page fault routines is best left for another day.

Applied to queue, thanks.

Paolo

> +	}
> +
>  	r = vcpu->arch.mmu.page_fault(vcpu, cr2, error_code, false);
>  	if (r < 0)
> -		goto out;
> -
> -	if (!r) {
> -		r = 1;
> -		goto out;
> -	}
> +		return r;
> +	if (!r)
> +		return 1;
>  
>  	if (mmio_info_in_cache(vcpu, cr2, direct))
>  		emulation_type = 0;
> -
> +emulate:
>  	er = x86_emulate_instruction(vcpu, cr2, emulation_type, insn, insn_len);
>  
>  	switch (er) {
> @@ -4386,8 +4381,6 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code,
>  	default:
>  		BUG();
>  	}
> -out:
> -	return r;
>  }
>  EXPORT_SYMBOL_GPL(kvm_mmu_page_fault);
>  
> diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h
> index 6c9fed9..05827ff 100644
> --- a/arch/x86/kvm/paging_tmpl.h
> +++ b/arch/x86/kvm/paging_tmpl.h
> @@ -702,24 +702,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr, u32 error_code,
>  
>  	pgprintk("%s: addr %lx err %x\n", __func__, addr, error_code);
>  
> -	if (unlikely(error_code & PFERR_RSVD_MASK)) {
> -		r = handle_mmio_page_fault(vcpu, addr, mmu_is_nested(vcpu));
> -		if (likely(r != RET_MMIO_PF_INVALID))
> -			return r;
> -
> -		/*
> -		 * page fault with PFEC.RSVD  = 1 is caused by shadow
> -		 * page fault, should not be used to walk guest page
> -		 * table.
> -		 */
> -		error_code &= ~PFERR_RSVD_MASK;
> -	};
> -
>  	r = mmu_topup_memory_caches(vcpu);
>  	if (r)
>  		return r;
>  
>  	/*
> +	 * If PFEC.RSVD is set, this is a shadow page fault.
> +	 * The bit needs to be cleared before walking guest page tables.
> +	 */
> +	error_code &= ~PFERR_RSVD_MASK;
> +
> +	/*
>  	 * Look up the guest pte for the faulting address.
>  	 */
>  	r = FNAME(walk_addr)(&walker, vcpu, addr, error_code);
>