From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andrew Cooper <andrew.cooper3@citrix.com>
Subject: Re: [PATCHv6 5/5] gnttab: use per-VCPU maptrack free
 lists
Date: Fri, 24 Apr 2015 11:02:01 +0100
Message-ID: <553A1499.4050708@citrix.com>
References: <1429718436-9782-1-git-send-email-david.vrabel@citrix.com>
	<1429718436-9782-6-git-send-email-david.vrabel@citrix.com>
	<553935E402000078000755B7@mail.emea.novell.com>	<553A0846.3030509@citrix.com>
	<553A2E0D0200007800075869@mail.emea.novell.com>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xen.org>
Received: from mail6.bemta3.messagelabs.com ([195.245.230.39])
	by lists.xen.org with esmtp (Exim 4.72)
	(envelope-from <Andrew.Cooper3@citrix.com>) id 1YlaQx-0002G5-60
	for xen-devel@lists.xenproject.org; Fri, 24 Apr 2015 10:02:07 +0000
In-Reply-To: <553A2E0D0200007800075869@mail.emea.novell.com>
List-Unsubscribe: <http://lists.xen.org/cgi-bin/mailman/options/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xen.org>
List-Help: <mailto:xen-devel-request@lists.xen.org?subject=help>
List-Subscribe: <http://lists.xen.org/cgi-bin/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xen.org?subject=subscribe>
Sender: xen-devel-bounces@lists.xen.org
Errors-To: xen-devel-bounces@lists.xen.org
To: Jan Beulich <JBeulich@suse.com>, David Vrabel <david.vrabel@citrix.com>, Malcolm Crossley <malcolm.crossley@citrix.com>
Cc: KeirFraser <keir@xen.org>, IanCampbell <ian.campbell@citrix.com>, Christoph Egger <chegger@amazon.de>, Tim Deegan <tim@xen.org>, Matt Wilson <msw@amazon.com>, xen-devel@lists.xenproject.org
List-Id: xen-devel@lists.xenproject.org

On 24/04/15 10:50, Jan Beulich wrote:
>>>> On 24.04.15 at 11:09, <malcolm.crossley@citrix.com> wrote:
>> On 23/04/15 17:11, Jan Beulich wrote:
>>>>>> On 22.04.15 at 18:00, <david.vrabel@citrix.com> wrote:
>>>> --- a/xen/include/xen/grant_table.h
>>>> +++ b/xen/include/xen/grant_table.h
>>>> @@ -60,6 +60,8 @@ struct grant_mapping {
>>>>      u32      ref;           /* grant ref */
>>>>      u16      flags;         /* 0-4: GNTMAP_* ; 5-15: unused */
>>>>      domid_t  domid;         /* granting domain */
>>>> +    u32      vcpu;          /* vcpu which created the grant mapping */
>>>> +    u16      pad[2];
>>>>  };
>>> What is this pad[] good for?
>> The pad is to keep the struct power of 2 sized because this allows the
>> compiler to optimise these macro's to right and left shifts:
>>
>> #define MAPTRACK_PER_PAGE (PAGE_SIZE / sizeof(struct grant_mapping))
>> #define maptrack_entry(t, e) \
>>     ((t)->maptrack[(e)/MAPTRACK_PER_PAGE][(e)%MAPTRACK_PER_PAGE])
> Okay, then why u16[2] instead of u32? And please add a brief
> comment explaining the reason.

Most likely because vcpu was a u16 in the first draft, and got bumped
during internal review.

>
> Apart from that I wonder whether fitting vcpu in the 10 unused
> flags bits (not 11, as the comment on the field suggests) would be
> an option. That would require limiting vCPU count to 4k, which I
> don't think would really be a problem for anyone.

8k VCPU PV guests do function, and are very good at finding scalability
limits.

It would be nice not to break this.

~Andrew