Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Tue, 18 May 2021 20:37:58 +0000
From:   Sean Christopherson <seanjc@google.com>
To:     Andi Kleen <ak@linux.intel.com>
Cc:     Dave Hansen <dave.hansen@intel.com>,
        Kuppuswamy Sathyanarayanan 
        <sathyanarayanan.kuppuswamy@linux.intel.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Andy Lutomirski <luto@kernel.org>,
        Tony Luck <tony.luck@intel.com>,
        Kirill Shutemov <kirill.shutemov@linux.intel.com>,
        Kuppuswamy Sathyanarayanan <knsathya@kernel.org>,
        Dan Williams <dan.j.williams@intel.com>,
        Raj Ashok <ashok.raj@intel.com>, linux-kernel@vger.kernel.org
Subject: Re: [RFC v2-fix 1/1] x86/tdx: Handle in-kernel MMIO
Message-ID: <YKQlpuKHb7DFFG8y@google.com>
References: <3e9a26c3-8eee-88f5-f8e2-8a2dd2c028ea@intel.com>
 <20210518004807.258503-1-sathyanarayanan.kuppuswamy@linux.intel.com>
 <36cd2665-6d8b-9c0b-eec1-25152dcca2a3@intel.com>
 <43e583a3-ee2b-52d8-5275-e26a6609c126@linux.intel.com>
 <YKP1Xty7EEzHkZ6Y@google.com>
 <8fb0e52c-ed0a-2185-585a-27007c27ed56@linux.intel.com>
 <YKQF08wqTsCQ3qHL@google.com>
 <3a037a43-435b-fc28-63d0-48e543cddfdd@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <3a037a43-435b-fc28-63d0-48e543cddfdd@linux.intel.com>
Precedence: bulk

On Tue, May 18, 2021, Andi Kleen wrote:
> 
> On 5/18/2021 11:22 AM, Sean Christopherson wrote:
> > On Tue, May 18, 2021, Andi Kleen wrote:
> > > > The extra bytes for .altinstructions is very different than the extra bytes for
> > > > the code itself.  The .altinstructions section is freed after init, so yes it
> > > > bloats the kernel size a bit, but the runtime footprint is unaffected by the
> > > > patching metadata.
> > > > 
> > > > IIRC, patching read/write{b,w,l,q}() can be done with 3 bytes of .text overhead.
> > > > 
> > > > The other option to explore is to hook/patch IO_COND(), which can be done with
> > > > neglible overhead because the helpers that use IO_COND() are not inlined.  In a
> > > > TDX guest, redirecting IO_COND() to a paravirt helper would likely cover the
> > > > majority of IO/MMIO since virtio-pci exclusively uses the IO_COND() wrappers.
> > > > And if there are TDX VMMs that want to deploy virtio-mmio, hooking
> > > > drivers/virtio/virtio_mmio.c directly would be a viable option.
> > > Yes but what's the point of all that?
> > Patching IO_COND() is relatively low effort.  With some clever refactoring, I
> > suspect the net lines of code added would be less than 10.  That seems like a
> > worthwhile effort to avoid millions of faults over the lifetime of the guest.
> 
> AFAIK IO_COND is only for iomap users. But most drivers don't even use
> iomap. virtio doesn't for example, and that's really the only case we
> currently care about.

virtio-pci, which is going to used by pretty much all traditional VMs, uses iomap.
See vp_get(), vp_set(), and all the vp_io{read,write}*() wrappers.