From: "Michael S. Tsirkin" <mst@redhat.com> To: Jason Wang <jasowang@redhat.com> Cc: virtualization@lists.linux-foundation.org, linux-kernel@vger.kernel.org, xieyongji@bytedance.com, stefanha@redhat.com, file@sect.tu-berlin.de, ashish.kalra@amd.com, konrad.wilk@oracle.com, kvm@vger.kernel.org, hch@infradead.org Subject: Re: [RFC PATCH V2 0/7] Do not read from descripto ring Date: Thu, 6 May 2021 04:12:17 -0400 [thread overview] Message-ID: <20210506041057-mutt-send-email-mst@kernel.org> (raw) In-Reply-To: <0e9d70b7-6c8a-4ff5-1fa9-3c4f04885bb8@redhat.com> On Thu, May 06, 2021 at 11:20:30AM +0800, Jason Wang wrote: > > 在 2021/4/23 下午4:09, Jason Wang 写道: > > Hi: > > > > Sometimes, the driver doesn't trust the device. This is usually > > happens for the encrtpyed VM or VDUSE[1]. In both cases, technology > > like swiotlb is used to prevent the poking/mangling of memory from the > > device. But this is not sufficient since current virtio driver may > > trust what is stored in the descriptor table (coherent mapping) for > > performing the DMA operations like unmap and bounce so the device may > > choose to utilize the behaviour of swiotlb to perform attacks[2]. > > > > To protect from a malicous device, this series store and use the > > descriptor metadata in an auxiliay structure which can not be accessed > > via swiotlb instead of the ones in the descriptor table. This means > > the descriptor table is write-only from the view of the driver. > > > > Actually, we've almost achieved that through packed virtqueue and we > > just need to fix a corner case of handling mapping errors. For split > > virtqueue we just follow what's done in the packed. > > > > Note that we don't duplicate descriptor medata for indirect > > descriptors since it uses stream mapping which is read only so it's > > safe if the metadata of non-indirect descriptors are correct. > > > > For split virtqueue, the change increase the footprint due the the > > auxiliary metadata but it's almost neglectlable in the simple test > > like pktgen or netpef. > > > > Slightly tested with packed on/off, iommu on/of, swiotlb force/off in > > the guest. > > > > Please review. > > > > Changes from V1: > > - Always use auxiliary metadata for split virtqueue > > - Don't read from descripto when detaching indirect descriptor > > > Hi Michael: > > Our QE see no regression on the perf test for 10G but some regressions > (5%-10%) on 40G card. > > I think this is expected since we increase the footprint, are you OK with > this and we can try to optimize on top or you have other ideas? > > Thanks Let's try for just a bit, won't make this window anyway: I have an old idea. Add a way to find out that unmap is a nop (or more exactly does not use the address/length). Then in that case even with DMA API we do not need the extra data. Hmm? > > > > > [1] > > https://lore.kernel.org/netdev/fab615ce-5e13-a3b3-3715-a4203b4ab010@redhat.com/T/ > > [2] > > https://yhbt.net/lore/all/c3629a27-3590-1d9f-211b-c0b7be152b32@redhat.com/T/#mc6b6e2343cbeffca68ca7a97e0f473aaa871c95b > > > > Jason Wang (7): > > virtio-ring: maintain next in extra state for packed virtqueue > > virtio_ring: rename vring_desc_extra_packed > > virtio-ring: factor out desc_extra allocation > > virtio_ring: secure handling of mapping errors > > virtio_ring: introduce virtqueue_desc_add_split() > > virtio: use err label in __vring_new_virtqueue() > > virtio-ring: store DMA metadata in desc_extra for split virtqueue > > > > drivers/virtio/virtio_ring.c | 201 +++++++++++++++++++++++++---------- > > 1 file changed, 144 insertions(+), 57 deletions(-) > >
WARNING: multiple messages have this Message-ID (diff)
From: "Michael S. Tsirkin" <mst@redhat.com> To: Jason Wang <jasowang@redhat.com> Cc: ashish.kalra@amd.com, file@sect.tu-berlin.de, kvm@vger.kernel.org, konrad.wilk@oracle.com, linux-kernel@vger.kernel.org, virtualization@lists.linux-foundation.org, hch@infradead.org, xieyongji@bytedance.com, stefanha@redhat.com Subject: Re: [RFC PATCH V2 0/7] Do not read from descripto ring Date: Thu, 6 May 2021 04:12:17 -0400 [thread overview] Message-ID: <20210506041057-mutt-send-email-mst@kernel.org> (raw) In-Reply-To: <0e9d70b7-6c8a-4ff5-1fa9-3c4f04885bb8@redhat.com> On Thu, May 06, 2021 at 11:20:30AM +0800, Jason Wang wrote: > > 在 2021/4/23 下午4:09, Jason Wang 写道: > > Hi: > > > > Sometimes, the driver doesn't trust the device. This is usually > > happens for the encrtpyed VM or VDUSE[1]. In both cases, technology > > like swiotlb is used to prevent the poking/mangling of memory from the > > device. But this is not sufficient since current virtio driver may > > trust what is stored in the descriptor table (coherent mapping) for > > performing the DMA operations like unmap and bounce so the device may > > choose to utilize the behaviour of swiotlb to perform attacks[2]. > > > > To protect from a malicous device, this series store and use the > > descriptor metadata in an auxiliay structure which can not be accessed > > via swiotlb instead of the ones in the descriptor table. This means > > the descriptor table is write-only from the view of the driver. > > > > Actually, we've almost achieved that through packed virtqueue and we > > just need to fix a corner case of handling mapping errors. For split > > virtqueue we just follow what's done in the packed. > > > > Note that we don't duplicate descriptor medata for indirect > > descriptors since it uses stream mapping which is read only so it's > > safe if the metadata of non-indirect descriptors are correct. > > > > For split virtqueue, the change increase the footprint due the the > > auxiliary metadata but it's almost neglectlable in the simple test > > like pktgen or netpef. > > > > Slightly tested with packed on/off, iommu on/of, swiotlb force/off in > > the guest. > > > > Please review. > > > > Changes from V1: > > - Always use auxiliary metadata for split virtqueue > > - Don't read from descripto when detaching indirect descriptor > > > Hi Michael: > > Our QE see no regression on the perf test for 10G but some regressions > (5%-10%) on 40G card. > > I think this is expected since we increase the footprint, are you OK with > this and we can try to optimize on top or you have other ideas? > > Thanks Let's try for just a bit, won't make this window anyway: I have an old idea. Add a way to find out that unmap is a nop (or more exactly does not use the address/length). Then in that case even with DMA API we do not need the extra data. Hmm? > > > > > [1] > > https://lore.kernel.org/netdev/fab615ce-5e13-a3b3-3715-a4203b4ab010@redhat.com/T/ > > [2] > > https://yhbt.net/lore/all/c3629a27-3590-1d9f-211b-c0b7be152b32@redhat.com/T/#mc6b6e2343cbeffca68ca7a97e0f473aaa871c95b > > > > Jason Wang (7): > > virtio-ring: maintain next in extra state for packed virtqueue > > virtio_ring: rename vring_desc_extra_packed > > virtio-ring: factor out desc_extra allocation > > virtio_ring: secure handling of mapping errors > > virtio_ring: introduce virtqueue_desc_add_split() > > virtio: use err label in __vring_new_virtqueue() > > virtio-ring: store DMA metadata in desc_extra for split virtqueue > > > > drivers/virtio/virtio_ring.c | 201 +++++++++++++++++++++++++---------- > > 1 file changed, 144 insertions(+), 57 deletions(-) > > _______________________________________________ Virtualization mailing list Virtualization@lists.linux-foundation.org https://lists.linuxfoundation.org/mailman/listinfo/virtualization
next prev parent reply other threads:[~2021-05-06 8:12 UTC|newest] Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top 2021-04-23 8:09 [RFC PATCH V2 0/7] Do not read from descripto ring Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 1/7] virtio-ring: maintain next in extra state for packed virtqueue Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 2/7] virtio_ring: rename vring_desc_extra_packed Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 3/7] virtio-ring: factor out desc_extra allocation Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 4/7] virtio_ring: secure handling of mapping errors Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 5/7] virtio_ring: introduce virtqueue_desc_add_split() Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 6/7] virtio: use err label in __vring_new_virtqueue() Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-04-23 8:09 ` [RFC PATCH V2 7/7] virtio-ring: store DMA metadata in desc_extra for split virtqueue Jason Wang 2021-04-23 8:09 ` Jason Wang 2021-05-06 3:20 ` [RFC PATCH V2 0/7] Do not read from descripto ring Jason Wang 2021-05-06 3:20 ` Jason Wang 2021-05-06 8:12 ` Michael S. Tsirkin [this message] 2021-05-06 8:12 ` Michael S. Tsirkin 2021-05-06 12:38 ` Christoph Hellwig 2021-05-06 12:38 ` Christoph Hellwig 2021-05-14 11:13 ` Michael S. Tsirkin 2021-05-14 11:13 ` Michael S. Tsirkin 2021-06-04 5:38 ` Jason Wang 2021-06-04 5:38 ` Jason Wang 2021-07-11 16:08 ` Michael S. Tsirkin 2021-07-11 16:08 ` Michael S. Tsirkin 2021-07-12 3:07 ` Jason Wang 2021-07-12 3:07 ` Jason Wang 2021-07-12 12:58 ` Michael S. Tsirkin 2021-07-12 12:58 ` Michael S. Tsirkin 2021-05-13 16:27 ` Stefan Hajnoczi 2021-05-13 16:27 ` Stefan Hajnoczi 2021-05-14 6:06 ` Yongji Xie 2021-05-14 7:30 ` Jason Wang 2021-05-14 7:30 ` Jason Wang 2021-05-14 8:40 ` Yongji Xie 2021-05-14 7:29 ` Jason Wang 2021-05-14 7:29 ` Jason Wang 2021-05-14 11:16 ` Stefan Hajnoczi 2021-05-14 11:16 ` Stefan Hajnoczi 2021-05-14 11:27 ` Yongji Xie 2021-05-14 11:36 ` Michael S. Tsirkin 2021-05-14 11:36 ` Michael S. Tsirkin 2021-05-14 13:58 ` Yongji Xie
Reply instructions: You may reply publicly to this message via plain-text email using any one of the following methods: * Save the following mbox file, import it into your mail client, and reply-to-all from there: mbox Avoid top-posting and favor interleaved quoting: https://en.wikipedia.org/wiki/Posting_style#Interleaved_style * Reply using the --to, --cc, and --in-reply-to switches of git-send-email(1): git send-email \ --in-reply-to=20210506041057-mutt-send-email-mst@kernel.org \ --to=mst@redhat.com \ --cc=ashish.kalra@amd.com \ --cc=file@sect.tu-berlin.de \ --cc=hch@infradead.org \ --cc=jasowang@redhat.com \ --cc=konrad.wilk@oracle.com \ --cc=kvm@vger.kernel.org \ --cc=linux-kernel@vger.kernel.org \ --cc=stefanha@redhat.com \ --cc=virtualization@lists.linux-foundation.org \ --cc=xieyongji@bytedance.com \ /path/to/YOUR_REPLY https://kernel.org/pub/software/scm/git/docs/git-send-email.html * If your mail client supports setting the In-Reply-To header via mailto: links, try the mailto: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.