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:   Tue, 29 Mar 2022 13:20:35 +0000
From:   Wei Liu <wei.liu@kernel.org>
To:     Andrea Parri <parri.andrea@gmail.com>
Cc:     Michael Kelley <mikelley@microsoft.com>, kys@microsoft.com,
        haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org,
        linux-kernel@vger.kernel.org, linux-hyperv@vger.kernel.org,
        vkuznets@redhat.com, decui@microsoft.com
Subject: Re: [PATCH 1/1] hv: drivers: vmbus: Prevent load re-ordering when
 reading ring buffer
Message-ID: <20220329132035.k6zjsp6lpx4xm3k5@liuwe-devbox-debian-v2>
References: <1648394710-33480-1-git-send-email-mikelley@microsoft.com>
 <20220328231233.GA102571@anparri>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20220328231233.GA102571@anparri>
Precedence: bulk

On Tue, Mar 29, 2022 at 01:12:33AM +0200, Andrea Parri wrote:
> On Sun, Mar 27, 2022 at 08:25:10AM -0700, Michael Kelley wrote:
> > When reading a packet from a host-to-guest ring buffer, there is no
> > memory barrier between reading the write index (to see if there is
> > a packet to read) and reading the contents of the packet. The Hyper-V
> > host uses store-release when updating the write index to ensure that
> > writes of the packet data are completed first. On the guest side,
> > the processor can reorder and read the packet data before the write
> > index, and sometimes get stale packet data. Getting such stale packet
> > data has been observed in a reproducible case in a VM on ARM64.
> > 
> > Fix this by using virt_load_acquire() to read the write index,
> > ensuring that reads of the packet data cannot be reordered
> > before it. Preventing such reordering is logically correct, and
> > with this change, getting stale data can no longer be reproduced.
> > 
> > Signed-off-by: Michael Kelley <mikelley@microsoft.com>
> 
> Reviewed-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
> 
> Nit: subject prefix -> "Drivers: hv: vmbus:".

Applied to hyperv-fixes. Thanks.

> 
> Thanks,
>   Andrea