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

[Michael S. Tsirkin]

On Wed, Jan 18, 2017 at 04:56:58AM +0000, Li, Liang Z wrote:
> > > -	virtqueue_add_outbuf(vq, &sg, 1, vb, GFP_KERNEL);
> > > -	virtqueue_kick(vq);
> > > +static void do_set_resp_bitmap(struct virtio_balloon *vb,
> > > +		unsigned long base_pfn, int pages)
> > >
> > > -	/* When host has read buffer, this completes via balloon_ack */
> > > -	wait_event(vb->acked, virtqueue_get_buf(vq, &len));
> > > +{
> > > +	__le64 *range = vb->resp_data + vb->resp_pos;
> > >
> > > +	if (pages > (1 << VIRTIO_BALLOON_NR_PFN_BITS)) {
> > > +		/* when the length field can't contain pages, set it to 0 to
> > 
> > /*
> >  * Multi-line
> >  * comments
> >  * should look like this.
> >  */
> > 
> > Also, pls start sentences with an upper-case letter.
> > 
> 
> Sorry for that.
> 
> > > +		 * indicate the actual length is in the next __le64;
> > > +		 */
> > 
> > This is part of the interface so should be documented as such.
> > 
> > > +		*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.

Generally describe the format in the header in some way
so host and guest can easily stay in sync.

All the pointer math and void * means we get zero type
safety and I'm not happy about it.


> I didn't use this way because I don't want to include 'virtio-balloon.h' in page_alloc.c,
> or copy the define of this struct in page_alloc.c
> 
> Thanks!
> Liang


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