Re: [PATCH v6 kernel 3/5] virtio-balloon: speed up inflate/deflate process

From: "Michael S. Tsirkin" <mst@redhat.com>
To: "Li, Liang Z" <liang.z.li@intel.com>
Cc: "aarcange@redhat.com" <aarcange@redhat.com>,
	"virtio-dev@lists.oasis-open.org"
	<virtio-dev@lists.oasis-open.org>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	"Hansen, Dave" <dave.hansen@intel.com>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"virtualization@lists.linux-foundation.org"
	<virtualization@lists.linux-foundation.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"amit.shah@redhat.com" <amit.shah@redhat.com>,
	"pbonzini@redhat.com" <pbonzini@redhat.com>,
	"dgilbert@redhat.com" <dgilbert@redhat.com>
Subject: Re: [PATCH v6 kernel 3/5] virtio-balloon: speed up inflate/deflate process
Date: Fri, 20 Jan 2017 18:34:34 +0200	[thread overview]
Message-ID: <20170120183215-mutt-send-email-mst__9359.57142287425$1484930086$gmane$org@kernel.org> (raw)
In-Reply-To: <F2CBF3009FA73547804AE4C663CAB28E3C3578BF@shsmsx102.ccr.corp.intel.com>

On Thu, Jan 19, 2017 at 01:44:36AM +0000, Li, Liang Z wrote:
> > > > > +		*range = cpu_to_le64((base_pfn <<
> > > > > +				VIRTIO_BALLOON_NR_PFN_BITS) | 0);
> > > > > +		*(range + 1) = cpu_to_le64(pages);
> > > > > +		vb->resp_pos += 2;
> > > >
> > > > Pls use structs for this kind of stuff.
> > >
> > > I am not sure if you mean to use
> > >
> > > struct  range {
> > >  	__le64 pfn: 52;
> > > 	__le64 nr_page: 12
> > > }
> > > Instead of the shift operation?
> > 
> > Not just that. You want to add a pages field as well.
> > 
> 
> pages field? Could you give more hints?

Well look how you are formatting it manually above.
There is clearly a structure with two 64 bit fields.
First one includes pfn and 0 (no idea why does | 0 make
sense but that's a separate issue).
Second one includes the pages value.

> > Generally describe the format in the header in some way so host and guest
> > can easily stay in sync.
> 
> 'VIRTIO_BALLOON_NR_PFN_BITS' is for this purpose and it will be passed to the
> related function in page_alloc.c as a parameter.
> 
> Thanks!
> Liang
> > All the pointer math and void * means we get zero type safety and I'm not
> > happy about it.
> > 
> > It's not good that virtio format seeps out to page_alloc anyway.
> > If unavoidable it is not a good idea to try to hide this fact, people will assume
> > they can change the format at will.
> > 
> > --
> > MST