| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAJaqyWeKmxM=DDLka-QBv35YwXn4eJeLJOqxJ_3HnRz_mq8K6g@mail.gmail.com>
Date: Tue, 16 Sep 2025 11:30:50 +0200
From: Eugenio Perez Martin <eperezma@...hat.com>
To: Yongji Xie <xieyongji@...edance.com>
Cc: "Michael S . Tsirkin" <mst@...hat.com>, Cindy Lu <lulu@...hat.com>,
Stefano Garzarella <sgarzare@...hat.com>, Xuan Zhuo <xuanzhuo@...ux.alibaba.com>,
Laurent Vivier <lvivier@...hat.com>, virtualization@...ts.linux.dev,
linux-kernel <linux-kernel@...r.kernel.org>, Jason Wang <jasowang@...hat.com>,
Maxime Coquelin <mcoqueli@...hat.com>
Subject: Re: [PATCH 5/6] vduse: add vq group asid support
On Mon, Sep 8, 2025 at 2:12 PM Yongji Xie <xieyongji@...edance.com> wrote:
>
> Hi Eugenio,
>
> On Tue, Aug 26, 2025 at 7:27 PM Eugenio Pérez <eperezma@...hat.com> wrote:
> >
> > Add support for assigning Address Space Identifiers (ASIDs) to each VQ
> > group. This enables mapping each group into a distinct memory space.
> >
> > Now that the driver can change ASID in the middle of operation, the
> > domain that each vq address point is also protected by domain_lock.
> >
> > Signed-off-by: Eugenio Pérez <eperezma@...hat.com>
> > ---
> > v3:
> > * Increase VDUSE_MAX_VQ_GROUPS to 0xffff (Jason). It was set to a lower
> > value to reduce memory consumption, but vqs are already limited to
> > that value and userspace VDUSE is able to allocate that many vqs.
> > * Remove TODO about merging VDUSE_IOTLB_GET_FD ioctl with
> > VDUSE_IOTLB_GET_INFO.
> > * Use of array_index_nospec in VDUSE device ioctls.
> > * Embed vduse_iotlb_entry into vduse_iotlb_entry_v2.
> > * Move the umem mutex to asid struct so there is no contention between
> > ASIDs.
> >
> > v2:
> > * Make iotlb entry the last one of vduse_iotlb_entry_v2 so the first
> > part of the struct is the same.
> > ---
> > drivers/vdpa/vdpa_user/vduse_dev.c | 290 +++++++++++++++++++++--------
> > include/uapi/linux/vduse.h | 52 +++++-
> > 2 files changed, 259 insertions(+), 83 deletions(-)
> >
> > diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
> > index 7d2a3ed77b1e..2fb227713972 100644
> > --- a/drivers/vdpa/vdpa_user/vduse_dev.c
> > +++ b/drivers/vdpa/vdpa_user/vduse_dev.c
> > @@ -92,6 +92,7 @@ struct vduse_as {
> > };
> >
> > struct vduse_vq_group_int {
> > + struct vduse_iova_domain *domain;
> > struct vduse_dev *dev;
> > };
> >
> > @@ -99,7 +100,7 @@ struct vduse_dev {
> > struct vduse_vdpa *vdev;
> > struct device *dev;
> > struct vduse_virtqueue **vqs;
> > - struct vduse_as as;
> > + struct vduse_as *as;
> > char *name;
> > struct mutex lock;
> > spinlock_t msg_lock;
> > @@ -127,6 +128,7 @@ struct vduse_dev {
> > u32 vq_num;
> > u32 vq_align;
> > u32 ngroups;
> > + u32 nas;
> > struct vduse_vq_group_int *groups;
> > unsigned int bounce_size;
> > struct mutex domain_lock;
> > @@ -317,7 +319,7 @@ static int vduse_dev_set_status(struct vduse_dev *dev, u8 status)
> > return vduse_dev_msg_sync(dev, &msg);
> > }
> >
> > -static int vduse_dev_update_iotlb(struct vduse_dev *dev,
> > +static int vduse_dev_update_iotlb(struct vduse_dev *dev, u32 asid,
> > u64 start, u64 last)
> > {
> > struct vduse_dev_msg msg = { 0 };
> > @@ -326,8 +328,14 @@ static int vduse_dev_update_iotlb(struct vduse_dev *dev,
> > return -EINVAL;
> >
> > msg.req.type = VDUSE_UPDATE_IOTLB;
> > - msg.req.iova.start = start;
> > - msg.req.iova.last = last;
> > + if (dev->api_version < VDUSE_API_VERSION_1) {
> > + msg.req.iova.start = start;
> > + msg.req.iova.last = last;
> > + } else {
> > + msg.req.iova_v2.start = start;
> > + msg.req.iova_v2.last = last;
> > + msg.req.iova_v2.asid = asid;
> > + }
> >
> > return vduse_dev_msg_sync(dev, &msg);
> > }
> > @@ -439,14 +447,28 @@ static __poll_t vduse_dev_poll(struct file *file, poll_table *wait)
> > return mask;
> > }
> >
> > +/* Force set the asid to a vq group without a message to the VDUSE device */
> > +static void vduse_set_group_asid_nomsg(struct vduse_dev *dev,
> > + unsigned int group, unsigned int asid)
> > +{
> > + guard(mutex)(&dev->domain_lock);
> > + dev->groups[group].domain = dev->as[asid].domain;
> > +}
> > +
> > static void vduse_dev_reset(struct vduse_dev *dev)
> > {
> > int i;
> > - struct vduse_iova_domain *domain = dev->as.domain;
> >
> > /* The coherent mappings are handled in vduse_dev_free_coherent() */
> > - if (domain && domain->bounce_map)
> > - vduse_domain_reset_bounce_map(domain);
> > + for (i = 0; i < dev->nas; i++) {
> > + struct vduse_iova_domain *domain = dev->as[i].domain;
> > +
> > + if (domain && domain->bounce_map)
> > + vduse_domain_reset_bounce_map(domain);
> > + }
> > +
> > + for (i = 0; i < dev->ngroups; i++)
> > + vduse_set_group_asid_nomsg(dev, i, 0);
> >
> > down_write(&dev->rwsem);
> >
> > @@ -620,6 +642,29 @@ static union virtio_map vduse_get_vq_map(struct vdpa_device *vdpa, u16 idx)
> > return ret;
> > }
> >
> > +static int vduse_set_group_asid(struct vdpa_device *vdpa, unsigned int group,
> > + unsigned int asid)
> > +{
> > + struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> > + struct vduse_dev_msg msg = { 0 };
> > + int r;
> > +
> > + if (dev->api_version < VDUSE_API_VERSION_1 ||
> > + group >= dev->ngroups || asid >= dev->nas)
> > + return -EINVAL;
> > +
> > + msg.req.type = VDUSE_SET_VQ_GROUP_ASID;
> > + msg.req.vq_group_asid.group = group;
> > + msg.req.vq_group_asid.asid = asid;
> > +
> > + r = vduse_dev_msg_sync(dev, &msg);
> > + if (r < 0)
> > + return r;
> > +
> > + vduse_set_group_asid_nomsg(dev, group, asid);
> > + return 0;
> > +}
> > +
> > static int vduse_vdpa_get_vq_state(struct vdpa_device *vdpa, u16 idx,
> > struct vdpa_vq_state *state)
> > {
> > @@ -818,13 +863,13 @@ static int vduse_vdpa_set_map(struct vdpa_device *vdpa,
> > struct vduse_dev *dev = vdpa_to_vduse(vdpa);
> > int ret;
> >
> > - ret = vduse_domain_set_map(dev->as.domain, iotlb);
> > + ret = vduse_domain_set_map(dev->as[asid].domain, iotlb);
> > if (ret)
> > return ret;
> >
> > - ret = vduse_dev_update_iotlb(dev, 0ULL, ULLONG_MAX);
> > + ret = vduse_dev_update_iotlb(dev, asid, 0ULL, ULLONG_MAX);
> > if (ret) {
> > - vduse_domain_clear_map(dev->as.domain, iotlb);
> > + vduse_domain_clear_map(dev->as[asid].domain, iotlb);
> > return ret;
> > }
> >
> > @@ -867,6 +912,7 @@ static const struct vdpa_config_ops vduse_vdpa_config_ops = {
> > .get_vq_affinity = vduse_vdpa_get_vq_affinity,
> > .reset = vduse_vdpa_reset,
> > .set_map = vduse_vdpa_set_map,
> > + .set_group_asid = vduse_set_group_asid,
> > .get_vq_map = vduse_get_vq_map,
> > .free = vduse_vdpa_free,
> > };
> > @@ -876,8 +922,10 @@ static void vduse_dev_sync_single_for_device(union virtio_map token,
> > enum dma_data_direction dir)
> > {
> > struct vduse_dev *vdev = token.group->dev;
> > - struct vduse_iova_domain *domain = vdev->as.domain;
> > + struct vduse_iova_domain *domain;
> >
> > + guard(mutex)(&vdev->domain_lock);
> > + domain = token.group->domain;
> > vduse_domain_sync_single_for_device(domain, dma_addr, size, dir);
> > }
> >
> > @@ -886,8 +934,10 @@ static void vduse_dev_sync_single_for_cpu(union virtio_map token,
> > enum dma_data_direction dir)
> > {
> > struct vduse_dev *vdev = token.group->dev;
> > - struct vduse_iova_domain *domain = vdev->as.domain;
> > + struct vduse_iova_domain *domain;
> >
> > + guard(mutex)(&vdev->domain_lock);
> > + domain = token.group->domain;
> > vduse_domain_sync_single_for_cpu(domain, dma_addr, size, dir);
> > }
> >
> > @@ -897,8 +947,10 @@ static dma_addr_t vduse_dev_map_page(union virtio_map token, struct page *page,
> > unsigned long attrs)
> > {
> > struct vduse_dev *vdev = token.group->dev;
> > - struct vduse_iova_domain *domain = vdev->as.domain;
> > + struct vduse_iova_domain *domain;
> >
> > + guard(mutex)(&vdev->domain_lock);
>
> Won't this mutex lock hurt the performance? Can we use rw_lock/rcu_lock instead?
>
I think RCU is not valid as the driver expects iotlb changes to be
done when it returns, and do not allow in-flight requests to access
the old data.
Using rwlock for the next version, thanks!
Powered by blists - more mailing lists