[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20160729003622-mutt-send-email-mst@kernel.org>
Date: Fri, 29 Jul 2016 00:37:24 +0300
From: "Michael S. Tsirkin" <mst@...hat.com>
To: "Li, Liang Z" <liang.z.li@...el.com>
Cc: "linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
"virtualization@...ts.linux-foundation.org"
<virtualization@...ts.linux-foundation.org>,
"linux-mm@...ck.org" <linux-mm@...ck.org>,
"virtio-dev@...ts.oasis-open.org" <virtio-dev@...ts.oasis-open.org>,
"kvm@...r.kernel.org" <kvm@...r.kernel.org>,
"qemu-devel@...gnu.org" <qemu-devel@...gnu.org>,
"dgilbert@...hat.com" <dgilbert@...hat.com>,
"quintela@...hat.com" <quintela@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Vlastimil Babka <vbabka@...e.cz>,
Mel Gorman <mgorman@...hsingularity.net>,
Paolo Bonzini <pbonzini@...hat.com>,
Cornelia Huck <cornelia.huck@...ibm.com>,
Amit Shah <amit.shah@...hat.com>
Subject: Re: [PATCH v2 repost 7/7] virtio-balloon: tell host vm's free page
info
On Thu, Jul 28, 2016 at 07:50:52AM +0000, Li, Liang Z wrote:
> > > }
> > >
> > > +static void update_free_pages_stats(struct virtio_balloon *vb,
> >
> > why _stats?
>
> Will change.
>
> > > + max_pfn = get_max_pfn();
> > > + mutex_lock(&vb->balloon_lock);
> > > + while (pfn < max_pfn) {
> > > + memset(vb->page_bitmap, 0, vb->bmap_len);
> > > + ret = get_free_pages(pfn, pfn + vb->pfn_limit,
> > > + vb->page_bitmap, vb->bmap_len * BITS_PER_BYTE);
> > > + hdr->cmd = cpu_to_virtio16(vb->vdev,
> > BALLOON_GET_FREE_PAGES);
> > > + hdr->page_shift = cpu_to_virtio16(vb->vdev, PAGE_SHIFT);
> > > + hdr->req_id = cpu_to_virtio64(vb->vdev, req_id);
> > > + hdr->start_pfn = cpu_to_virtio64(vb->vdev, pfn);
> > > + bmap_len = vb->pfn_limit / BITS_PER_BYTE;
> > > + if (!ret) {
> > > + hdr->flag = cpu_to_virtio16(vb->vdev,
> > > +
> > BALLOON_FLAG_DONE);
> > > + if (pfn + vb->pfn_limit > max_pfn)
> > > + bmap_len = (max_pfn - pfn) /
> > BITS_PER_BYTE;
> > > + } else
> > > + hdr->flag = cpu_to_virtio16(vb->vdev,
> > > +
> > BALLOON_FLAG_CONT);
> > > + hdr->bmap_len = cpu_to_virtio64(vb->vdev, bmap_len);
> > > + sg_init_one(&sg_out, hdr,
> > > + sizeof(struct balloon_bmap_hdr) + bmap_len);
> >
> > Wait a second. This adds the same buffer multiple times in a loop.
> > We will overwrite the buffer without waiting for hypervisor to process it.
> > What did I miss?
>
> I am no quite sure about this part, I though the virtqueue_kick(vq) will prevent
> the buffer from overwrite, I realized it's wrong.
>
> > > +
> > > + virtqueue_add_outbuf(vq, &sg_out, 1, vb, GFP_KERNEL);
> >
> > this can fail. you want to maybe make sure vq has enough space before you
> > use it or check error and wait.
> >
> > > + virtqueue_kick(vq);
> >
> > why kick here within loop? wait until done. in fact kick outside lock is better
> > for smp.
>
> I will change this part in v3.
>
> >
> > > + pfn += vb->pfn_limit;
> > > + static const char * const names[] = { "inflate", "deflate", "stats",
> > > + "misc" };
> > > int err, nvqs;
> > >
> > > /*
> > > * We expect two virtqueues: inflate and deflate, and
> > > * optionally stat.
> > > */
> > > - nvqs = virtio_has_feature(vb->vdev,
> > VIRTIO_BALLOON_F_STATS_VQ) ? 3 : 2;
> > > + if (virtio_has_feature(vb->vdev, VIRTIO_BALLOON_F_MISC_VQ))
> > > + nvqs = 4;
> >
> > Does misc vq depend on stats vq feature then? if yes please validate that.
>
> Yes, what's you mean by 'validate' that?
Either handle misc vq without a stats vq, or
clear VIRTIO_BALLOON_F_MISC_VQ if stats vq is off.
> >
> >
> > > + else
> > > + nvqs = virtio_has_feature(vb->vdev,
> > > + VIRTIO_BALLOON_F_STATS_VQ) ? 3 :
> > 2;
> >
> > Replace that ? with else too pls.
>
> Will change.
>
> Thanks!
> Liang
Powered by blists - more mailing lists