From: Yongji Xie <xieyongji@bytedance.com>
To: Jason Wang <jasowang@redhat.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>,
"Stefan Hajnoczi" <stefanha@redhat.com>,
"Stefano Garzarella" <sgarzare@redhat.com>,
"Parav Pandit" <parav@nvidia.com>,
"Christoph Hellwig" <hch@infradead.org>,
"Christian Brauner" <christian.brauner@canonical.com>,
"Randy Dunlap" <rdunlap@infradead.org>,
"Matthew Wilcox" <willy@infradead.org>,
viro@zeniv.linux.org.uk, "Jens Axboe" <axboe@kernel.dk>,
bcrl@kvack.org, "Jonathan Corbet" <corbet@lwn.net>,
"Mika Penttilä" <mika.penttila@nextfour.com>,
"Dan Carpenter" <dan.carpenter@oracle.com>,
virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org, kvm@vger.kernel.org,
linux-fsdevel@vger.kernel.org
Subject: Re: Re: [PATCH v6 08/10] vduse: Implement an MMU-based IOMMU driver
Date: Thu, 8 Apr 2021 13:27:27 +0800 [thread overview]
Message-ID: <CACycT3t+nAWtHDzWxWRvVdcinQdmTx-PL8Rk7yfBt2RXiQCn6Q@mail.gmail.com> (raw)
In-Reply-To: <30862242-293b-f42f-d8ce-2c31a52e3697@redhat.com>
On Thu, Apr 8, 2021 at 11:26 AM Jason Wang <jasowang@redhat.com> wrote:
>
>
> 在 2021/3/31 下午4:05, Xie Yongji 写道:
> > This implements an MMU-based IOMMU driver to support mapping
> > kernel dma buffer into userspace. The basic idea behind it is
> > treating MMU (VA->PA) as IOMMU (IOVA->PA). The driver will set
> > up MMU mapping instead of IOMMU mapping for the DMA transfer so
> > that the userspace process is able to use its virtual address to
> > access the dma buffer in kernel.
> >
> > And to avoid security issue, a bounce-buffering mechanism is
> > introduced to prevent userspace accessing the original buffer
> > directly.
> >
> > Signed-off-by: Xie Yongji <xieyongji@bytedance.com>
>
>
> Acked-by: Jason Wang <jasowang@redhat.com>
>
> With some nits:
>
>
> > ---
> > drivers/vdpa/vdpa_user/iova_domain.c | 521 +++++++++++++++++++++++++++++++++++
> > drivers/vdpa/vdpa_user/iova_domain.h | 70 +++++
> > 2 files changed, 591 insertions(+)
> > create mode 100644 drivers/vdpa/vdpa_user/iova_domain.c
> > create mode 100644 drivers/vdpa/vdpa_user/iova_domain.h
>
>
> [...]
>
>
> > +static void vduse_domain_bounce(struct vduse_iova_domain *domain,
> > + dma_addr_t iova, size_t size,
> > + enum dma_data_direction dir)
> > +{
> > + struct vduse_bounce_map *map;
> > + unsigned int offset;
> > + void *addr;
> > + size_t sz;
> > +
> > + while (size) {
> > + map = &domain->bounce_maps[iova >> PAGE_SHIFT];
> > + offset = offset_in_page(iova);
> > + sz = min_t(size_t, PAGE_SIZE - offset, size);
> > +
> > + if (WARN_ON(!map->bounce_page ||
> > + map->orig_phys == INVALID_PHYS_ADDR))
> > + return;
> > +
> > + addr = page_address(map->bounce_page) + offset;
> > + do_bounce(map->orig_phys + offset, addr, sz, dir);
> > + size -= sz;
> > + iova += sz;
> > + }
> > +}
> > +
> > +static struct page *
> > +vduse_domain_get_mapping_page(struct vduse_iova_domain *domain, u64 iova)
>
>
> It's better to rename this as "vduse_domain_get_coherent_page?".
>
OK.
>
> > +{
> > + u64 start = iova & PAGE_MASK;
> > + u64 last = start + PAGE_SIZE - 1;
> > + struct vhost_iotlb_map *map;
> > + struct page *page = NULL;
> > +
> > + spin_lock(&domain->iotlb_lock);
> > + map = vhost_iotlb_itree_first(domain->iotlb, start, last);
> > + if (!map)
> > + goto out;
> > +
> > + page = pfn_to_page((map->addr + iova - map->start) >> PAGE_SHIFT);
> > + get_page(page);
> > +out:
> > + spin_unlock(&domain->iotlb_lock);
> > +
> > + return page;
> > +}
> > +
>
>
> [...]
>
>
> > +
> > +static dma_addr_t
> > +vduse_domain_alloc_iova(struct iova_domain *iovad,
> > + unsigned long size, unsigned long limit)
> > +{
> > + unsigned long shift = iova_shift(iovad);
> > + unsigned long iova_len = iova_align(iovad, size) >> shift;
> > + unsigned long iova_pfn;
> > +
> > + if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
> > + iova_len = roundup_pow_of_two(iova_len);
>
>
> Let's add a comment as what has been done in dma-iommu.c?
>
Fine.
> (In the future, it looks to me it's better to move them to
> alloc_iova_fast()).
>
Agree.
Thanks,
Yongji
next prev parent reply other threads:[~2021-04-08 5:27 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-03-31 8:05 [PATCH v6 00/10] Introduce VDUSE - vDPA Device in Userspace Xie Yongji
2021-03-31 8:05 ` [PATCH v6 01/10] file: Export receive_fd() to modules Xie Yongji
2021-03-31 9:15 ` Christian Brauner
2021-03-31 9:26 ` Dan Carpenter
2021-03-31 9:28 ` Christian Brauner
2021-03-31 11:32 ` Yongji Xie
2021-03-31 12:23 ` Christian Brauner
2021-03-31 13:59 ` Yongji Xie
2021-03-31 14:07 ` Christian Brauner
2021-03-31 14:37 ` Yongji Xie
2021-03-31 8:05 ` [PATCH v6 02/10] eventfd: Increase the recursion depth of eventfd_signal() Xie Yongji
2021-03-31 8:05 ` [PATCH v6 03/10] vhost-vdpa: protect concurrent access to vhost device iotlb Xie Yongji
2021-04-09 16:15 ` Michael S. Tsirkin
2021-04-11 5:36 ` Yongji Xie
2021-04-11 20:48 ` Michael S. Tsirkin
2021-04-12 2:29 ` Yongji Xie
2021-04-12 9:00 ` Michael S. Tsirkin
2021-03-31 8:05 ` [PATCH v6 04/10] vhost-iotlb: Add an opaque pointer for vhost IOTLB Xie Yongji
2021-03-31 8:05 ` [PATCH v6 05/10] vdpa: Add an opaque pointer for vdpa_config_ops.dma_map() Xie Yongji
2021-03-31 8:05 ` [PATCH v6 06/10] vdpa: factor out vhost_vdpa_pa_map() and vhost_vdpa_pa_unmap() Xie Yongji
2021-03-31 8:05 ` [PATCH v6 07/10] vdpa: Support transferring virtual addressing during DMA mapping Xie Yongji
2021-04-08 2:36 ` Jason Wang
2021-03-31 8:05 ` [PATCH v6 08/10] vduse: Implement an MMU-based IOMMU driver Xie Yongji
2021-04-08 3:25 ` Jason Wang
2021-04-08 5:27 ` Yongji Xie [this message]
2021-03-31 8:05 ` [PATCH v6 09/10] vduse: Introduce VDUSE - vDPA Device in Userspace Xie Yongji
2021-04-08 6:57 ` Jason Wang
2021-04-08 9:36 ` Yongji Xie
2021-04-09 5:36 ` Jason Wang
2021-04-09 8:02 ` Yongji Xie
2021-04-12 7:16 ` Jason Wang
2021-04-12 8:02 ` Yongji Xie
2021-04-12 9:37 ` Jason Wang
2021-04-12 9:59 ` Yongji Xie
2021-04-13 3:35 ` Jason Wang
2021-04-13 4:28 ` Yongji Xie
2021-04-14 8:18 ` Jason Wang
2021-04-16 3:24 ` Jason Wang
2021-04-16 8:43 ` Yongji Xie
2021-03-31 8:05 ` [PATCH v6 10/10] Documentation: Add documentation for VDUSE Xie Yongji
2021-04-08 7:18 ` Jason Wang
2021-04-08 8:09 ` Yongji Xie
2021-04-14 14:14 ` Stefan Hajnoczi
2021-04-15 5:38 ` Yongji Xie
2021-04-15 7:19 ` Stefan Hajnoczi
2021-04-15 8:33 ` Yongji Xie
2021-04-15 14:17 ` Stefan Hajnoczi
2021-04-15 8:36 ` Jason Wang
2021-04-15 9:04 ` Jason Wang
2021-04-15 11:17 ` Yongji Xie
2021-04-16 2:20 ` Jason Wang
2021-04-16 2:58 ` Yongji Xie
2021-04-16 3:02 ` Jason Wang
2021-04-16 3:18 ` Yongji Xie
2021-04-15 14:38 ` Stefan Hajnoczi
2021-04-16 2:23 ` Jason Wang
2021-04-16 3:19 ` Yongji Xie
2021-04-16 5:39 ` Jason Wang
2021-04-16 3:13 ` Yongji Xie
2021-04-14 7:34 ` [PATCH v6 00/10] Introduce VDUSE - vDPA Device in Userspace Michael S. Tsirkin
2021-04-14 7:49 ` Jason Wang
2021-04-14 7:54 ` 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=CACycT3t+nAWtHDzWxWRvVdcinQdmTx-PL8Rk7yfBt2RXiQCn6Q@mail.gmail.com \
--to=xieyongji@bytedance.com \
--cc=axboe@kernel.dk \
--cc=bcrl@kvack.org \
--cc=christian.brauner@canonical.com \
--cc=corbet@lwn.net \
--cc=dan.carpenter@oracle.com \
--cc=hch@infradead.org \
--cc=jasowang@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=mika.penttila@nextfour.com \
--cc=mst@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=parav@nvidia.com \
--cc=rdunlap@infradead.org \
--cc=sgarzare@redhat.com \
--cc=stefanha@redhat.com \
--cc=viro@zeniv.linux.org.uk \
--cc=virtualization@lists.linux-foundation.org \
--cc=willy@infradead.org \
/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: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).