| 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: <CACGkMEvWBrtBtT2bnPcdOMFy0mOROvd-c9vqkJVDSHnbhmyzYw@mail.gmail.com>
Date: Wed, 24 Sep 2025 08:55:00 +0800
From: Jason Wang <jasowang@...hat.com>
To: Eugenio Perez Martin <eperezma@...hat.com>
Cc: "Michael S . Tsirkin" <mst@...hat.com>, Yongji Xie <xieyongji@...edance.com>,
Maxime Coquelin <mcoqueli@...hat.com>, linux-kernel@...r.kernel.org,
Xuan Zhuo <xuanzhuo@...ux.alibaba.com>, virtualization@...ts.linux.dev,
Cindy Lu <lulu@...hat.com>, Laurent Vivier <lvivier@...hat.com>,
Stefano Garzarella <sgarzare@...hat.com>
Subject: Re: [PATCH v3 5/6] vduse: add vq group asid support
On Wed, Sep 24, 2025 at 1:26 AM Eugenio Perez Martin
<eperezma@...hat.com> wrote:
>
> On Mon, Sep 22, 2025 at 3:50 AM Jason Wang <jasowang@...hat.com> wrote:
> >
> > On Fri, Sep 19, 2025 at 5:34 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:
> > > * Get the vduse domain through the vduse_as in the map functions
> > > (Jason).
> > > * Squash with the patch creating the vduse_as struct (Jason).
> > > * Create VDUSE_DEV_MAX_AS instead of comparing agains a magic number
> > > (Jason)
> > >
> > > v2:
> > > * Convert the use of mutex to rwlock.
> > >
> > > RFC 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.
> > >
> > > RFC 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 | 327 ++++++++++++++++++++---------
> > > include/uapi/linux/vduse.h | 51 ++++-
> > > 2 files changed, 281 insertions(+), 97 deletions(-)
> > >
> > > diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c b/drivers/vdpa/vdpa_user/vduse_dev.c
> > > index 6fdabc3c910e..c6c70cfd4887 100644
> > > --- a/drivers/vdpa/vdpa_user/vduse_dev.c
> > > +++ b/drivers/vdpa/vdpa_user/vduse_dev.c
> > > @@ -42,6 +42,7 @@
> > >
> > > #define VDUSE_DEV_MAX (1U << MINORBITS)
> > > #define VDUSE_DEV_MAX_GROUPS 0xffff
> > > +#define VDUSE_DEV_MAX_AS 0xffff
> > > #define VDUSE_MAX_BOUNCE_SIZE (1024 * 1024 * 1024)
> > > #define VDUSE_MIN_BOUNCE_SIZE (1024 * 1024)
> > > #define VDUSE_BOUNCE_SIZE (64 * 1024 * 1024)
> > > @@ -89,7 +90,14 @@ struct vduse_umem {
> > > struct mm_struct *mm;
> > > };
> > >
> > > +struct vduse_as {
> > > + struct vduse_iova_domain *domain;
> > > + struct vduse_umem *umem;
> > > + struct mutex mem_lock;
> > > +};
> > > +
> > > struct vduse_vq_group {
> > > + struct vduse_as *as;
> > > struct vduse_dev *dev;
> > > };
> > >
> > > @@ -97,7 +105,7 @@ struct vduse_dev {
> > > struct vduse_vdpa *vdev;
> > > struct device *dev;
> > > struct vduse_virtqueue **vqs;
> > > - struct vduse_iova_domain *domain;
> > > + struct vduse_as *as;
> > > char *name;
> > > struct mutex lock;
> > > spinlock_t msg_lock;
> > > @@ -125,9 +133,8 @@ struct vduse_dev {
> > > u32 vq_num;
> > > u32 vq_align;
> > > u32 ngroups;
> > > - struct vduse_umem *umem;
> > > + u32 nas;
> > > struct vduse_vq_group *groups;
> > > - struct mutex mem_lock;
> > > unsigned int bounce_size;
> > > rwlock_t domain_lock;
> > > };
> > > @@ -324,7 +331,7 @@ 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 };
> > > @@ -333,8 +340,14 @@ 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);
> > > }
> > > @@ -446,14 +459,29 @@ 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)
> > > +{
> > > + write_lock(&dev->domain_lock);
> > > + dev->groups[group].as = &dev->as[asid];
> > > + write_unlock(&dev->domain_lock);
> > > +}
> > > +
> > > static void vduse_dev_reset(struct vduse_dev *dev)
> > > {
> > > int i;
> > > - struct vduse_iova_domain *domain = dev->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);
> > >
> > > @@ -639,6 +667,29 @@ 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)
> > > {
> > > @@ -810,13 +861,13 @@ 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->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->domain, iotlb);
> > > + vduse_domain_clear_map(dev->as[asid].domain, iotlb);
> > > return ret;
> > > }
> > >
> > > @@ -859,6 +910,7 @@ 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,
> > > };
> > > @@ -874,9 +926,10 @@ static void vduse_dev_sync_single_for_device(union virtio_map token,
> > > return;
> > >
> > > vdev = token.group->dev;
> > > - domain = vdev->domain;
> > > -
> > > + read_lock(&vdev->domain_lock);
> >
> > This introduce atomic operation in the datapath, I wonder if we can
> > switch to use RCU instead.
> >
>
> I think it is a path that is worth exploring. The reason I chose
> rwlock (and just plain mutex before) is that
> vduse_domain_sync_single_for_device and
> vduse_domain_sync_single_for_cpu already take a read lock, so it seems
> the overhead was ok.
>
> Can we do it on top of this series? I think both using RCU can improve
> the performance for sure, but just taking out one of them would not
> buy us a lot.
That's fine.
Thanks
Powered by blists - more mailing lists