Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri, 18 Mar 2022 18:34:54 +0300
From:   "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To:     Thomas Gleixner <tglx@linutronix.de>
Cc:     Peter Zijlstra <peterz@infradead.org>, mingo@redhat.com,
        bp@alien8.de, dave.hansen@intel.com, luto@kernel.org,
        sathyanarayanan.kuppuswamy@linux.intel.com, aarcange@redhat.com,
        ak@linux.intel.com, dan.j.williams@intel.com, david@redhat.com,
        hpa@zytor.com, jgross@suse.com, jmattson@google.com,
        joro@8bytes.org, jpoimboe@redhat.com, knsathya@kernel.org,
        pbonzini@redhat.com, sdeep@vmware.com, seanjc@google.com,
        tony.luck@intel.com, vkuznets@redhat.com, wanpengli@tencent.com,
        thomas.lendacky@amd.com, brijesh.singh@amd.com, x86@kernel.org,
        linux-kernel@vger.kernel.org,
        Sean Christopherson <sean.j.christopherson@intel.com>,
        Dave Hansen <dave.hansen@linux.intel.com>
Subject: Re: [PATCHv6 07/30] x86/traps: Add #VE support for TDX guest
Message-ID: <20220318153454.7ciwicqfghiwnv2t@black.fi.intel.com>
References: <20220316020856.24435-1-kirill.shutemov@linux.intel.com>
 <20220316020856.24435-8-kirill.shutemov@linux.intel.com>
 <877d8t2ykp.ffs@tglx>
 <20220317173354.rqymufl37lcrtmjh@black.fi.intel.com>
 <20220317202141.GO8939@worktop.programming.kicks-ass.net>
 <87a6dncphl.ffs@tglx>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <87a6dncphl.ffs@tglx>
Precedence: bulk

On Fri, Mar 18, 2022 at 03:19:34PM +0100, Thomas Gleixner wrote:
> On Thu, Mar 17 2022 at 21:21, Peter Zijlstra wrote:
> > On Thu, Mar 17, 2022 at 08:33:54PM +0300, Kirill A. Shutemov wrote:
> >>  - in NMI entry code (asm_exc_nmi()) before NMI nesting is safe:
> >>    + for NMI from user mode, before switched to thread stack
> >>    + for NMI from kernel, up to end_repead_nmi
> >> 
> >> After that points #VE is safe.
> >
> > In what way is it guaranteed that #VE isn't raised in those places? What
> > does an auditor / future coder looking to changes things, need to
> > consider to keep this so.
> >
> > From vague memories #VE can be raised on any memop, loading the stack
> > address in the syscall-gap is a memop. What makes that special? Can we
> > get a comment _there_ to explain how this is safe such that we can keep
> > it so?
> >
> > Same for the NMI path I suppose.
> 
> #VE is raised by HLT, CPUID, I/O-Port access, MSR read/write, EPT violations
> 
> So in the hairy places:
> 
>  - HLT:       No business
>  - I/O Ports: That would be outright stupid to use
> 
>  - CPUID:     Should never be used - Emphasis on should :)
>  - MSRs:      Same as CPUID
> 
>  - EPT:       Well....

EPT violation may result in #VE only on shared memory. If entry code
touches shared memory we have a bigger problem than syscall gap.

-- 
 Kirill A. Shutemov