linux-kernel - Re: [PATCH v5 09/12] Retry fault before vmentry

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <4C73900D.1080404@redhat.com>
Date:	Tue, 24 Aug 2010 12:25:33 +0300
From:	Avi Kivity <avi@...hat.com>
To:	Gleb Natapov <gleb@...hat.com>
CC:	kvm@...r.kernel.org, linux-mm@...ck.org,
	linux-kernel@...r.kernel.org, mingo@...e.hu,
	a.p.zijlstra@...llo.nl, tglx@...utronix.de, hpa@...or.com,
	riel@...hat.com, cl@...ux-foundation.org, mtosatti@...hat.com
Subject: Re: [PATCH v5 09/12] Retry fault before vmentry

  On 07/19/2010 06:30 PM, Gleb Natapov wrote:
> When page is swapped in it is mapped into guest memory only after guest
> tries to access it again and generate another fault. To save this fault
> we can map it immediately since we know that guest is going to access
> the page.
>
>
>
> -static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
> -				u32 error_code)
> +static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa, u32 error_code,
> +			  bool sync)

'sync' means something else in the shadow mmu.  Please rename to 
something longer, maybe 'apf_completion'.

Alternatively, split to two functions, a base function that doesn't do 
apf and a wrapper that handles apf.

> @@ -505,6 +506,37 @@ out_unlock:
>   	return 0;
>   }
>
> +static int FNAME(page_fault_other_cr3)(struct kvm_vcpu *vcpu, gpa_t cr3,
> +				       gva_t addr, u32 error_code)
> +{
> +	int r = 0;
> +	gpa_t curr_cr3 = vcpu->arch.cr3;
> +
> +	if (curr_cr3 != cr3) {
> +		/*
> +		 * We do page fault on behalf of a process that is sleeping
> +		 * because of async PF. PV guest takes reference to mm that cr3
> +		 * belongs too, so it has to be valid here.
> +		 */
> +		kvm_set_cr3(vcpu, cr3);
> +		if (kvm_mmu_reload(vcpu))
> +			goto switch_cr3;
> +	}

With nested virtualization, we need to switch cr0, cr4, and efer as well...

> +
> +	r = FNAME(page_fault)(vcpu, addr, error_code, true);
> +
> +	if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
> +		kvm_mmu_sync_roots(vcpu);

Why is this needed?

> +
> +switch_cr3:
> +	if (curr_cr3 != vcpu->arch.cr3) {
> +		kvm_set_cr3(vcpu, curr_cr3);
> +		kvm_mmu_reload(vcpu);
> +	}
> +
> +	return r;
> +}

This has the nasty effect of flushing the TLB on AMD.

> +
>   static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
>   {
>   	struct kvm_shadow_walk_iterator iterator;
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index 2603cc4..5482db0 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -5743,6 +5743,15 @@ void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
>   }
>   EXPORT_SYMBOL_GPL(kvm_set_rflags);
>
> +void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu,
> +			       struct kvm_async_pf *work)
> +{
> +	if (!vcpu->arch.mmu.page_fault_other_cr3 || is_error_page(work->page))
> +		return;
> +	vcpu->arch.mmu.page_fault_other_cr3(vcpu, work->arch.cr3, work->gva,
> +					    work->arch.error_code);
> +}
> +
>   static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
>   {
>   	if (unlikely(vcpu->arch.apf_memslot_ver !=
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index f56e8ac..de1d5b6 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -1348,6 +1348,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
>   			spin_lock(&vcpu->async_pf_lock);
>   			list_del(&work->link);
>   			spin_unlock(&vcpu->async_pf_lock);
> +			kvm_arch_async_page_ready(vcpu, work);
>   			put_page(work->page);
>   			async_pf_work_free(work);
>   			list_del(&work->queue);
> @@ -1366,6 +1367,7 @@ void kvm_check_async_pf_completion(struct kvm_vcpu *vcpu)
>   	list_del(&work->queue);
>   	vcpu->async_pf_queued--;
>
> +	kvm_arch_async_page_ready(vcpu, work);
>   	kvm_arch_inject_async_page_present(vcpu, work);
>
>   	put_page(work->page);


-- 
error compiling committee.c: too many arguments to function

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/