Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH] xen-swiotlb: exchange memory with Xen only when pages are
 contiguous
To:     Dongli Zhang <dongli.zhang@oracle.com>
Cc:     Christoph Helwig <hch@lst.de>,
        Boris Ostrovsky <boris.ostrovsky@oracle.com>,
        Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
        konrad@kernel.org, John Sobecki <john.sobecki@oracle.com>,
        "xen-devel@lists.xenproject.org" <xen-devel@lists.xenproject.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
References: <bb6d87b4-c371-c6c0-8c48-bc95df018ad1@oracle.com>
 <20181024130246.GA22616@localhost.localdomain>
 <83900cf4-690c-9725-d022-d427fdeb4f7d@oracle.com>
 <581cb7ea-3112-791d-918d-9bb887e4744f@oracle.com>
 <24a62522-1629-5d0b-398e-6d2c1a0b97f7@oracle.com>
 <922914c9-22db-c5d1-33da-d07691ebd7d7@oracle.com>
 <a47fabe8-53d1-47b8-0efc-f9f1e5b4898a@oracle.com>
 <45f5ffe8-3f48-4485-53f0-5a056be69b0c@oracle.com>
 <5b64850f-9142-0360-fe4e-9e7bc74d2368@oracle.com>
 <20181026074802.GA4768@lst.de>
 <10301c25-5bbf-51b6-6cb2-77e30bcd9a99@oracle.com>
From:   Joe Jin <joe.jin@oracle.com>
Message-ID: <dac26047-7426-fec5-0360-fbfd6e211d69@oracle.com>
Date:   Fri, 26 Oct 2018 07:48:09 -0700
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:52.0)
 Gecko/20100101 Thunderbird/52.9.1
MIME-Version: 1.0
In-Reply-To: <10301c25-5bbf-51b6-6cb2-77e30bcd9a99@oracle.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 10/26/18 1:54 AM, Dongli Zhang wrote:
> If dom0 (or any domain) is happy, although it could try to exchange all its
> continuous dma pages back to xen hypervisor. From the perspective of each
> domain, they always would like to keep as much continuous dma page as possible.
> 
> I am thinking something different. If there is malicious domU keep exchanging
> memory and allocating continuous pages from xen hypervisor, will the
> continuously dma pages be used up (sort of DoS attack)?

This is a problem.

> 
> I am not sure if there is anything in xen hypervisor to prevent such behavior?

I'm not sure but I guess it hard to prevent it, xen hypervisor could not identify
if the requirement is reasonable or no.

Maybe Xen reserve some low memory for guest start?

Thanks,
Joe