linux-kernel - Re: [PATCH 3/3] KVM: x86: improve reexecute

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: <20121129002339.GD17264@amt.cnet>
Date:	Wed, 28 Nov 2012 22:23:39 -0200
From:	Marcelo Tosatti <mtosatti@...hat.com>
To:	Xiao Guangrong <xiaoguangrong@...ux.vnet.ibm.com>
Cc:	Gleb Natapov <gleb@...hat.com>, Avi Kivity <avi@...hat.com>,
	LKML <linux-kernel@...r.kernel.org>, KVM <kvm@...r.kernel.org>
Subject: Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

On Thu, Nov 29, 2012 at 07:16:50AM +0800, Xiao Guangrong wrote:
> On 11/29/2012 06:40 AM, Xiao Guangrong wrote:
> > On 11/29/2012 05:57 AM, Marcelo Tosatti wrote:
> >> On Wed, Nov 28, 2012 at 10:59:35PM +0800, Xiao Guangrong wrote:
> >>> On 11/28/2012 10:12 PM, Gleb Natapov wrote:
> >>>> On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote:
> >>>>> On 11/27/2012 06:41 AM, Marcelo Tosatti wrote:
> >>>>>
> >>>>>>>
> >>>>>>> -	return false;
> >>>>>>> +again:
> >>>>>>> +	page_fault_count = ACCESS_ONCE(vcpu->kvm->arch.page_fault_count);
> >>>>>>> +
> >>>>>>> +	/*
> >>>>>>> +	 * if emulation was due to access to shadowed page table
> >>>>>>> +	 * and it failed try to unshadow page and re-enter the
> >>>>>>> +	 * guest to let CPU execute the instruction.
> >>>>>>> +	 */
> >>>>>>> +	kvm_mmu_unprotect_page(vcpu->kvm, gpa_to_gfn(gpa));
> >>>>>>> +	emulate = vcpu->arch.mmu.page_fault(vcpu, cr3, PFERR_WRITE_MASK, false);
> >>>>>>
> >>>>>> Can you explain what is the objective here?
> >>>>>>
> >>>>>
> >>>>> Sure. :)
> >>>>>
> >>>>> The instruction emulation is caused by fault access on cr3. After unprotect
> >>>>> the target page, we call vcpu->arch.mmu.page_fault to fix the mapping of cr3.
> >>>>> if it return 1, mmu can not fix the mapping, we should report the error,
> >>>>> otherwise it is good to return to guest and let it re-execute the instruction
> >>>>> again.
> >>>>>
> >>>>> page_fault_count is used to avoid the race on other vcpus, since after we
> >>>>> unprotect the target page, other cpu can enter page fault path and let the
> >>>>> page be write-protected again.
> >>>>>
> >>>>> This way can help us to detect all the case that mmu can not be fixed.
> >>>>>
> >>>> Can you write this in a comment above vcpu->arch.mmu.page_fault()?
> >>>
> >>> Okay, if Marcelo does not object this way. :)
> >>
> >> I do object, since it is possible to detect precisely the condition by 
> >> storing which gfns have been cached.
> >>
> >> Then, Xiao, you need a way to handle large read-only sptes.
> > 
> > Sorry, Marcelo, i am still confused why read-only sptes can not work
> > under this patch?
> > 
> > The code after read-only large spte is is:
> > 
> > +		if ((level > PT_PAGE_TABLE_LEVEL &&
> > +		   has_wrprotected_page(vcpu->kvm, gfn, level)) ||
> > +		      mmu_need_write_protect(vcpu, gfn, can_unsync)) {
> >  			pgprintk("%s: found shadow page for %llx, marking ro\n",
> >  				 __func__, gfn);
> >  			ret = 1;
> > 
> > It return 1, then reexecute_instruction return 0. It is the same as without
> > readonly large-spte.
> 
> Ah, wait, There is a case, the large page located at 0-2M, the 0-4K is used as a
> page-table (e.g. PDE), and the guest want to write the memory located at 5K which
> should be freely written. This patch can return 0 for both current code and readonly
> large spte.

Yes, should remove the read-only large spte if any write to 0-2M fails
(said 'unshadow' in the previous email but the correct is 'remove large
spte in range').

> I need to think it more.


--
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/