From mboxrd@z Thu Jan  1 00:00:00 1970
From: Rui Xiang <rui.xiang@huawei.com>
Subject: Re: [request for stable inclusion][Patch 3.4.y] x86, kvm: use kernel_fpu_begin/end()
 in kvm_load/put_guest_fpu()
Date: Fri, 31 Jul 2015 11:03:48 +0800
Message-ID: <55BAE594.9040201@huawei.com>
References: <1438167814-8284-1-git-send-email-rui.xiang@huawei.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="ISO-8859-1"
Content-Transfer-Encoding: 7bit
Cc: <stable@vger.kernel.org>, <huangzhichao@huawei.com>
To: Zefan Li <lizefan@huawei.com>,
	"H. Peter Anvin" <hpa@linux.intel.com>,
	Suresh Siddha <suresh.b.siddha@intel.com>,
	Suresh Siddha <sbsiddha@gmail.com>,
	Paolo Bonzini <pbonzini@redhat.com>, <kvm@vger.kernel.org>
Return-path: <stable-owner@vger.kernel.org>
In-Reply-To: <1438167814-8284-1-git-send-email-rui.xiang@huawei.com>
Sender: stable-owner@vger.kernel.org
List-Id: kvm.vger.kernel.org

ping....

On 2015/7/29 19:03, Rui Xiang wrote:
> Hi Zefan, Suresh or Peter,
> 
> 9c1c3fac53378c9782c18f80107965578d7b7167
> x86, kvm: use kernel_fpu_begin/end() in kvm_load/put_guest_fpu()
> 
> We never cause the "Device Not Available" exception in kernel mode,
> but without this patch, the orign unlazy_fpu() do stts(), the following
> fpu_restore_checking() will trigger a DNA(Device Not Available), this 
> may corrupt the user process fpu. And an crash happened through a fault
> injection in our scenario.
> 
> b1a74bf8212367be2b1d6685c11a84e056eaaaf1
> x86, kvm: fix kvm's usage of kernel_fpu_begin/end()
> 
> The commit b1a74bf82123 fix a bug introduced by comit 9c1c3fac5337
> (x86, kvm: use kernel_fpu_begin/end() in kvm_load/put_guest_fpu())
> 
> They look applicable to stable-3.4.y. The first one can be applied
> cleanly, the other need some adjustments to backport.
> The following patche is the backport for b1a74bf82123.
> 
> And what do you think?
> 
> Thanks.
> 
> 
> 
> .
>