On Wed, Sep 17, 2025 at 6:40 PM Eugenio Perez Martin
<epere...@redhat.com> wrote:
>
> On Wed, Sep 17, 2025 at 10:56 AM Jason Wang <jasow...@redhat.com> wrote:
> >
> > On Tue, Sep 16, 2025 at 9:09 PM Eugenio Pérez <epere...@redhat.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 <epere...@redhat.com>
> > > ---
> > > 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 | 324 +++++++++++++++++++++--------
> > > include/uapi/linux/vduse.h | 51 ++++-
> > > 2 files changed, 284 insertions(+), 91 deletions(-)
> > >
> > > diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c
> > > b/drivers/vdpa/vdpa_user/vduse_dev.c
> > > index b45b1d22784f..06b7790380b7 100644
> > > --- a/drivers/vdpa/vdpa_user/vduse_dev.c
> > > +++ b/drivers/vdpa/vdpa_user/vduse_dev.c
> > > @@ -93,6 +93,7 @@ struct vduse_as {
> > > };
> > >
> > > struct vduse_vq_group_int {
> > > + struct vduse_iova_domain *domain;
> > > struct vduse_dev *dev;
> >
> > This confuses me, I think it should be an asid. And the vduse_dev
> > pointer seems to be useless here.
> >
>
> The *dev pointer is used to take the rwlock, in case the vhost driver
> calls VHOST_VDPA_SET_GROUP_ASID (or equivalent) at the same time
> vduse_dev_sync_single_for_device (or _for_cpu, or equivalent) run.
>
> > > };
> > >
> > > @@ -100,7 +101,7 @@ 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;
> > > @@ -128,6 +129,7 @@ struct vduse_dev {
> > > u32 vq_num;
> > > u32 vq_align;
> > > u32 ngroups;
> > > + u32 nas;
> > > struct vduse_vq_group_int *groups;
> > > unsigned int bounce_size;
> > > rwlock_t domain_lock;
> > > @@ -318,7 +320,7 @@ 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 };
> > > @@ -327,8 +329,14 @@ 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);
> > > }
> > > @@ -440,14 +448,29 @@ 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].domain = dev->as[asid].domain;
> >
> > I think it would be better to stick the group->as an indirection which
> > should be .
> >
> > dev->groups.asid = asid;
> >
> > Or
> >
> > dev->group->as = as;
> >
>
> That involves an extra memory jump for functions that may be in the
> hot path. I've not profiled it, but I'm ok with changing it that way
> if you prefer.
>
> > > + write_unlock(&dev->domain_lock);
> > > +}
> > > +
> > > 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);
> > >
> > > @@ -621,6 +644,29 @@ 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)
> > > {
> > > @@ -792,13 +838,13 @@ 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;
> > > }
> > >
> > > @@ -841,6 +887,7 @@ 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,
> > > };
> > > @@ -850,9 +897,12 @@ 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;
> > >
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > vduse_domain_sync_single_for_device(domain, dma_addr, size, dir);
> > > + read_unlock(&vdev->domain_lock);
> > > }
> > >
> > > static void vduse_dev_sync_single_for_cpu(union virtio_map token,
> > > @@ -860,9 +910,12 @@ 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;
> > >
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> >
> > I think the domain is better fetched via vduse_as.
> >
> > > vduse_domain_sync_single_for_cpu(domain, dma_addr, size, dir);
> > > + read_unlock(&vdev->domain_lock);
> > > }
> > >
> > > static dma_addr_t vduse_dev_map_page(union virtio_map token, struct page
> > > *page,
> > > @@ -871,9 +924,15 @@ 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;
> > > + dma_addr_t r;
> > >
> > > - return vduse_domain_map_page(domain, page, offset, size, dir,
> > > attrs);
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > + r = vduse_domain_map_page(domain, page, offset, size, dir, attrs);
> > > + read_unlock(&vdev->domain_lock);
> > > +
> > > + return r;
> > > }
> > >
> > > static void vduse_dev_unmap_page(union virtio_map token, dma_addr_t
> > > dma_addr,
> > > @@ -881,27 +940,31 @@ static void vduse_dev_unmap_page(union virtio_map
> > > token, dma_addr_t dma_addr,
> > > unsigned long attrs)
> > > {
> > > struct vduse_dev *vdev = token.group->dev;
> > > - struct vduse_iova_domain *domain = vdev->as.domain;
> > > + struct vduse_iova_domain *domain;
> > >
> > > - return vduse_domain_unmap_page(domain, dma_addr, size, dir,
> > > attrs);
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > + vduse_domain_unmap_page(domain, dma_addr, size, dir, attrs);
> > > + read_unlock(&vdev->domain_lock);
> > > }
> > >
> > > static void *vduse_dev_alloc_coherent(union virtio_map token, size_t
> > > size,
> > > dma_addr_t *dma_addr, gfp_t flag)
> > > {
> > > struct vduse_dev *vdev = token.group->dev;
> > > - struct vduse_iova_domain *domain = vdev->as.domain;
> > > + struct vduse_iova_domain *domain;
> > > unsigned long iova;
> > > - void *addr;
> > > + void *addr = NULL;
> > >
> > > *dma_addr = DMA_MAPPING_ERROR;
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > addr = vduse_domain_alloc_coherent(domain, size,
> > > (dma_addr_t *)&iova, flag);
> > > - if (!addr)
> > > - return NULL;
> > > -
> > > - *dma_addr = (dma_addr_t)iova;
> > > + if (addr)
> > > + *dma_addr = (dma_addr_t)iova;
> > >
> > > + read_unlock(&vdev->domain_lock);
> > > return addr;
> > > }
> > >
> > > @@ -910,17 +973,26 @@ static void vduse_dev_free_coherent(union
> > > virtio_map token, size_t size,
> > > unsigned long attrs)
> > > {
> > > struct vduse_dev *vdev = token.group->dev;
> > > - struct vduse_iova_domain *domain = vdev->as.domain;
> > > + struct vduse_iova_domain *domain;
> > >
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > vduse_domain_free_coherent(domain, size, vaddr, dma_addr, attrs);
> > > + read_unlock(&vdev->domain_lock);
> > > }
> > >
> > > static bool vduse_dev_need_sync(union virtio_map token, dma_addr_t
> > > dma_addr)
> > > {
> > > struct vduse_dev *vdev = token.group->dev;
> > > - struct vduse_iova_domain *domain = vdev->as.domain;
> > > + struct vduse_iova_domain *domain;
> > > + size_t bounce_size;
> > >
> > > - return dma_addr < domain->bounce_size;
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > + bounce_size = domain->bounce_size;
> > > + read_unlock(&vdev->domain_lock);
> > > +
> > > + return dma_addr < bounce_size;
> > > }
> > >
> > > static int vduse_dev_mapping_error(union virtio_map token, dma_addr_t
> > > dma_addr)
> > > @@ -933,9 +1005,15 @@ static int vduse_dev_mapping_error(union virtio_map
> > > token, dma_addr_t dma_addr)
> > > static size_t vduse_dev_max_mapping_size(union virtio_map token)
> > > {
> > > struct vduse_dev *vdev = token.group->dev;
> > > - struct vduse_iova_domain *domain = vdev->as.domain;
> > > + struct vduse_iova_domain *domain;
> > > + size_t bounce_size;
> > > +
> > > + read_lock(&vdev->domain_lock);
> > > + domain = token.group->domain;
> > > + bounce_size = domain->bounce_size;
> > > + read_unlock(&vdev->domain_lock);
> > >
> > > - return domain->bounce_size;
> > > + return bounce_size;
> > > }
> > >
> > > static const struct virtio_map_ops vduse_map_ops = {
> > > @@ -1075,39 +1153,40 @@ static int vduse_dev_queue_irq_work(struct
> > > vduse_dev *dev,
> > > return ret;
> > > }
> > >
> > > -static int vduse_dev_dereg_umem(struct vduse_dev *dev,
> > > +static int vduse_dev_dereg_umem(struct vduse_dev *dev, u32 asid,
> > > u64 iova, u64 size)
> > > {
> > > int ret;
> > >
> > > - mutex_lock(&dev->as.mem_lock);
> > > + mutex_lock(&dev->as[asid].mem_lock);
> > > ret = -ENOENT;
> > > - if (!dev->as.umem)
> > > + if (!dev->as[asid].umem)
> > > goto unlock;
> > >
> > > ret = -EINVAL;
> > > - if (!dev->as.domain)
> > > + if (!dev->as[asid].domain)
> > > goto unlock;
> > >
> > > - if (dev->as.umem->iova != iova || size !=
> > > dev->as.domain->bounce_size)
> > > + if (dev->as[asid].umem->iova != iova ||
> > > + size != dev->as[asid].domain->bounce_size)
> > > goto unlock;
> > >
> > > - vduse_domain_remove_user_bounce_pages(dev->as.domain);
> > > - unpin_user_pages_dirty_lock(dev->as.umem->pages,
> > > - dev->as.umem->npages, true);
> > > - atomic64_sub(dev->as.umem->npages, &dev->as.umem->mm->pinned_vm);
> > > - mmdrop(dev->as.umem->mm);
> > > - vfree(dev->as.umem->pages);
> > > - kfree(dev->as.umem);
> > > - dev->as.umem = NULL;
> > > + vduse_domain_remove_user_bounce_pages(dev->as[asid].domain);
> > > + unpin_user_pages_dirty_lock(dev->as[asid].umem->pages,
> > > + dev->as[asid].umem->npages, true);
> > > + atomic64_sub(dev->as[asid].umem->npages,
> > > &dev->as[asid].umem->mm->pinned_vm);
> > > + mmdrop(dev->as[asid].umem->mm);
> > > + vfree(dev->as[asid].umem->pages);
> > > + kfree(dev->as[asid].umem);
> > > + dev->as[asid].umem = NULL;
> >
> > We can avoid those changeset if we do those in the previous correctly
> > as it said it would make as an array.
> >
>
> I'm not following it. Is that different from squashing this patch with
> the previous one? I'm ok with doing it, but this changes are needed
> either way.
>
> > > ret = 0;
> > > unlock:
> > > - mutex_unlock(&dev->as.mem_lock);
> > > + mutex_unlock(&dev->as[asid].mem_lock);
> > > return ret;
> > > }
> > >
> > > static int vduse_dev_reg_umem(struct vduse_dev *dev,
> > > - u64 iova, u64 uaddr, u64 size)
> > > + u32 asid, u64 iova, u64 uaddr, u64 size)
> > > {
> > > struct page **page_list = NULL;
> > > struct vduse_umem *umem = NULL;
> > > @@ -1115,14 +1194,14 @@ static int vduse_dev_reg_umem(struct vduse_dev
> > > *dev,
> > > unsigned long npages, lock_limit;
> > > int ret;
> > >
> > > - if (!dev->as.domain || !dev->as.domain->bounce_map ||
> > > - size != dev->as.domain->bounce_size ||
> > > + if (!dev->as[asid].domain || !dev->as[asid].domain->bounce_map ||
> > > + size != dev->as[asid].domain->bounce_size ||
> > > iova != 0 || uaddr & ~PAGE_MASK)
> > > return -EINVAL;
> > >
> > > - mutex_lock(&dev->as.mem_lock);
> > > + mutex_lock(&dev->as[asid].mem_lock);
> > > ret = -EEXIST;
> > > - if (dev->as.umem)
> > > + if (dev->as[asid].umem)
> > > goto unlock;
> > >
> > > ret = -ENOMEM;
> > > @@ -1146,7 +1225,7 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev,
> > > goto out;
> > > }
> > >
> > > - ret = vduse_domain_add_user_bounce_pages(dev->as.domain,
> > > + ret = vduse_domain_add_user_bounce_pages(dev->as[asid].domain,
> > > page_list, pinned);
> > > if (ret)
> > > goto out;
> > > @@ -1159,7 +1238,7 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev,
> > > umem->mm = current->mm;
> > > mmgrab(current->mm);
> > >
> > > - dev->as.umem = umem;
> > > + dev->as[asid].umem = umem;
> > > out:
> > > if (ret && pinned > 0)
> > > unpin_user_pages(page_list, pinned);
> > > @@ -1170,7 +1249,7 @@ static int vduse_dev_reg_umem(struct vduse_dev *dev,
> > > vfree(page_list);
> > > kfree(umem);
> > > }
> > > - mutex_unlock(&dev->as.mem_lock);
> > > + mutex_unlock(&dev->as[asid].mem_lock);
> > > return ret;
> > > }
> > >
> > > @@ -1202,47 +1281,66 @@ static long vduse_dev_ioctl(struct file *file,
> > > unsigned int cmd,
> > >
> > > switch (cmd) {
> > > case VDUSE_IOTLB_GET_FD: {
> > > - struct vduse_iotlb_entry entry;
> > > + struct vduse_iotlb_entry_v2 entry;
> > > struct vhost_iotlb_map *map;
> > > struct vdpa_map_file *map_file;
> > > struct file *f = NULL;
> > > + u32 asid;
> > >
> > > ret = -EFAULT;
> > > - if (copy_from_user(&entry, argp, sizeof(entry)))
> > > - break;
> > > + if (dev->api_version >= VDUSE_API_VERSION_1) {
> > > + if (copy_from_user(&entry, argp, sizeof(entry)))
> > > + break;
> > > + } else {
> > > + entry.asid = 0;
> > > + if (copy_from_user(&entry.v1, argp,
> > > + sizeof(entry.v1)))
> > > + break;
> > > + }
> > >
> > > ret = -EINVAL;
> > > - if (entry.start > entry.last)
> > > + if (entry.v1.start > entry.v1.last)
> > > + break;
> > > +
> > > + if (entry.asid >= dev->nas)
> > > break;
> > >
> > > read_lock(&dev->domain_lock);
> > > - if (!dev->as.domain) {
> > > + asid = array_index_nospec(entry.asid, dev->nas);
> > > + if (!dev->as[asid].domain) {
> > > read_unlock(&dev->domain_lock);
> > > break;
> > > }
> > > - spin_lock(&dev->as.domain->iotlb_lock);
> > > - map = vhost_iotlb_itree_first(dev->as.domain->iotlb,
> > > - entry.start, entry.last);
> > > + spin_lock(&dev->as[asid].domain->iotlb_lock);
> > > + map = vhost_iotlb_itree_first(dev->as[asid].domain->iotlb,
> > > + entry.v1.start,
> > > entry.v1.last);
> > > if (map) {
> > > map_file = (struct vdpa_map_file *)map->opaque;
> > > f = get_file(map_file->file);
> > > - entry.offset = map_file->offset;
> > > - entry.start = map->start;
> > > - entry.last = map->last;
> > > - entry.perm = map->perm;
> > > + entry.v1.offset = map_file->offset;
> > > + entry.v1.start = map->start;
> > > + entry.v1.last = map->last;
> > > + entry.v1.perm = map->perm;
> > > }
> > > - spin_unlock(&dev->as.domain->iotlb_lock);
> > > + spin_unlock(&dev->as[asid].domain->iotlb_lock);
> > > read_unlock(&dev->domain_lock);
> > > ret = -EINVAL;
> > > if (!f)
> > > break;
> > >
> > > ret = -EFAULT;
> > > - if (copy_to_user(argp, &entry, sizeof(entry))) {
> > > + if (dev->api_version >= VDUSE_API_VERSION_1)
> > > + ret = copy_to_user(argp, &entry,
> > > + sizeof(entry));
> > > + else
> > > + ret = copy_to_user(argp, &entry.v1,
> > > + sizeof(entry.v1));
> > > +
> > > + if (ret) {
> > > fput(f);
> > > break;
> > > }
> > > - ret = receive_fd(f, NULL, perm_to_file_flags(entry.perm));
> > > + ret = receive_fd(f, NULL,
> > > perm_to_file_flags(entry.v1.perm));
> >
> > Nit: if we copy_from_user() twice and stick entry for v1 format, we
> > can avoid a lot of lines of changes.
> >
>
> Let me draft something and put it as a reply here to check I'm
> understanding your proposal.
>
We need a "struct vduse_iotlb_entry_v2" sooner or later anyway because
we need to finish with the corresponding copy_to_user. Either that, or
duplicate the copy_to_user too with something like:
copy_to_user(argp, &entry_vq, sizeof(entry_v1);
copy_to_user(argp + sizeof(struct vduse_iotlb_entry), &asid, sizeof(asid);
Saving the struct vduse_iotlb_entry_v2, this is the only change I can
do in that direction (from this patch):
diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c
b/drivers/vdpa/vdpa_user/vduse_dev.c
index 7da248f5616c..555b0fa079de 100644
--- a/drivers/vdpa/vdpa_user/vduse_dev.c
+++ b/drivers/vdpa/vdpa_user/vduse_dev.c
@@ -1341,14 +1341,13 @@ static long vduse_dev_ioctl(struct file *file,
unsigned int cmd,
u32 asid;
ret = -EFAULT;
- if (dev->api_version >= VDUSE_API_VERSION_1) {
- if (copy_from_user(&entry, argp, sizeof(entry)))
- break;
- } else {
+ if (copy_from_user(&entry.v1, argp, sizeof(entry.v1)))
+ break;
+ if (dev->api_version < VDUSE_API_VERSION_1) {
entry.asid = 0;
- if (copy_from_user(&entry.v1, argp,
- sizeof(entry.v1)))
- break;
+ } else if (copy_from_user(&entry.asid, argp,
+ sizeof(entry.asid))) {
+ break;
}
ret = -EINVAL;
> > > fput(f);
> > > break;
> > > }
> > > @@ -1384,6 +1482,7 @@ static long vduse_dev_ioctl(struct file *file,
> > > unsigned int cmd,
> > > }
> > > case VDUSE_IOTLB_REG_UMEM: {
> > > struct vduse_iova_umem umem;
> > > + u32 asid;
> > >
> > > ret = -EFAULT;
> > > if (copy_from_user(&umem, argp, sizeof(umem)))
> > > @@ -1391,17 +1490,21 @@ static long vduse_dev_ioctl(struct file *file,
> > > unsigned int cmd,
> > >
> > > ret = -EINVAL;
> > > if (!is_mem_zero((const char *)umem.reserved,
> > > - sizeof(umem.reserved)))
> > > + sizeof(umem.reserved)) ||
> > > + (dev->api_version < VDUSE_API_VERSION_1 &&
> > > + umem.asid != 0) || umem.asid >= dev->nas)
> > > break;
> > >
> > > write_lock(&dev->domain_lock);
> > > - ret = vduse_dev_reg_umem(dev, umem.iova,
> > > + asid = array_index_nospec(umem.asid, dev->nas);
> > > + ret = vduse_dev_reg_umem(dev, asid, umem.iova,
> > > umem.uaddr, umem.size);
> > > write_unlock(&dev->domain_lock);
> > > break;
> > > }
> > > case VDUSE_IOTLB_DEREG_UMEM: {
> > > struct vduse_iova_umem umem;
> > > + u32 asid;
> > >
> > > ret = -EFAULT;
> > > if (copy_from_user(&umem, argp, sizeof(umem)))
> > > @@ -1409,10 +1512,15 @@ static long vduse_dev_ioctl(struct file *file,
> > > unsigned int cmd,
> > >
> > > ret = -EINVAL;
> > > if (!is_mem_zero((const char *)umem.reserved,
> > > - sizeof(umem.reserved)))
> > > + sizeof(umem.reserved)) ||
> > > + (dev->api_version < VDUSE_API_VERSION_1 &&
> > > + umem.asid != 0) ||
> > > + umem.asid >= dev->nas)
> > > break;
> > > +
> > > write_lock(&dev->domain_lock);
> > > - ret = vduse_dev_dereg_umem(dev, umem.iova,
> > > + asid = array_index_nospec(umem.asid, dev->nas);
> > > + ret = vduse_dev_dereg_umem(dev, asid, umem.iova,
> > > umem.size);
> > > write_unlock(&dev->domain_lock);
> > > break;
> > > @@ -1420,6 +1528,7 @@ static long vduse_dev_ioctl(struct file *file,
> > > unsigned int cmd,
> > > case VDUSE_IOTLB_GET_INFO: {
> > > struct vduse_iova_info info;
> > > struct vhost_iotlb_map *map;
> > > + u32 asid;
> > >
> > > ret = -EFAULT;
> > > if (copy_from_user(&info, argp, sizeof(info)))
> > > @@ -1433,23 +1542,31 @@ static long vduse_dev_ioctl(struct file *file,
> > > unsigned int cmd,
> > > sizeof(info.reserved)))
> > > break;
> > >
> > > + if (dev->api_version < VDUSE_API_VERSION_1) {
> > > + if (info.asid)
> > > + break;
> > > + } else if (info.asid >= dev->nas)
> > > + break;
> > > +
> > > read_lock(&dev->domain_lock);
> > > - if (!dev->as.domain) {
> > > + asid = array_index_nospec(info.asid, dev->nas);
> > > + if (!dev->as[asid].domain) {
> > > read_unlock(&dev->domain_lock);
> > > break;
> > > }
> > > - spin_lock(&dev->as.domain->iotlb_lock);
> > > - map = vhost_iotlb_itree_first(dev->as.domain->iotlb,
> > > + spin_lock(&dev->as[asid].domain->iotlb_lock);
> > > + map = vhost_iotlb_itree_first(dev->as[asid].domain->iotlb,
> > > info.start, info.last);
> > > if (map) {
> > > info.start = map->start;
> > > info.last = map->last;
> > > info.capability = 0;
> > > - if (dev->as.domain->bounce_map && map->start == 0
> > > &&
> > > - map->last == dev->as.domain->bounce_size - 1)
> > > + if (dev->as[asid].domain->bounce_map &&
> > > + map->start == 0 &&
> > > + map->last ==
> > > dev->as[asid].domain->bounce_size - 1)
> > > info.capability |= VDUSE_IOVA_CAP_UMEM;
> > > }
> > > - spin_unlock(&dev->as.domain->iotlb_lock);
> > > + spin_unlock(&dev->as[asid].domain->iotlb_lock);
> > > read_unlock(&dev->domain_lock);
> > > if (!map)
> > > break;
> > > @@ -1474,8 +1591,10 @@ static int vduse_dev_release(struct inode *inode,
> > > struct file *file)
> > > struct vduse_dev *dev = file->private_data;
> > >
> > > write_lock(&dev->domain_lock);
> > > - if (dev->as.domain)
> > > - vduse_dev_dereg_umem(dev, 0, dev->as.domain->bounce_size);
> > > + for (int i = 0; i < dev->nas; i++)
> > > + if (dev->as[i].domain)
> > > + vduse_dev_dereg_umem(dev, i, 0,
> > > +
> > > dev->as[i].domain->bounce_size);
> > > write_unlock(&dev->domain_lock);
> > > spin_lock(&dev->msg_lock);
> > > /* Make sure the inflight messages can processed after
> > > reconncection */
> > > @@ -1694,7 +1813,6 @@ static struct vduse_dev *vduse_dev_create(void)
> > > return NULL;
> > >
> > > mutex_init(&dev->lock);
> > > - mutex_init(&dev->as.mem_lock);
> > > rwlock_init(&dev->domain_lock);
> > > spin_lock_init(&dev->msg_lock);
> > > INIT_LIST_HEAD(&dev->send_list);
> > > @@ -1745,8 +1863,11 @@ static int vduse_destroy_dev(char *name)
> > > idr_remove(&vduse_idr, dev->minor);
> > > kvfree(dev->config);
> > > vduse_dev_deinit_vqs(dev);
> > > - if (dev->as.domain)
> > > - vduse_domain_destroy(dev->as.domain);
> > > + for (int i = 0; i < dev->nas; i++) {
> > > + if (dev->as[i].domain)
> > > + vduse_domain_destroy(dev->as[i].domain);
> > > + }
> > > + kfree(dev->as);
> > > kfree(dev->name);
> > > kfree(dev->groups);
> > > vduse_dev_destroy(dev);
> > > @@ -1793,12 +1914,16 @@ static bool vduse_validate_config(struct
> > > vduse_dev_config *config,
> > > sizeof(config->reserved)))
> > > return false;
> > >
> > > - if (api_version < VDUSE_API_VERSION_1 && config->ngroups)
> > > + if (api_version < VDUSE_API_VERSION_1 &&
> > > + (config->ngroups || config->nas))
> > > return false;
> > >
> > > if (api_version >= VDUSE_API_VERSION_1 && config->ngroups >
> > > 0xffff)
> > > return false;
> > >
> > > + if (api_version >= VDUSE_API_VERSION_1 && config->nas > 0xffff)
> > > + return false;
> > > +
> > > if (config->vq_align > PAGE_SIZE)
> > > return false;
> > >
> > > @@ -1862,7 +1987,8 @@ static ssize_t bounce_size_store(struct device
> > > *device,
> > >
> > > ret = -EPERM;
> > > write_lock(&dev->domain_lock);
> > > - if (dev->as.domain)
> > > + /* Assuming that if the first domain is allocated, all are
> > > allocated */
> > > + if (dev->as[0].domain)
> > > goto unlock;
> > >
> > > ret = kstrtouint(buf, 10, &bounce_size);
> > > @@ -1923,6 +2049,13 @@ static int vduse_create_dev(struct
> > > vduse_dev_config *config,
> > > for (u32 i = 0; i < dev->ngroups; ++i)
> > > dev->groups[i].dev = dev;
> > >
> > > + dev->nas = (dev->api_version < 1) ? 1 : (config->nas ?: 1);
> > > + dev->as = kcalloc(dev->nas, sizeof(dev->as[0]), GFP_KERNEL);
> > > + if (!dev->as)
> > > + goto err_as;
> > > + for (int i = 0; i < dev->nas; i++)
> > > + mutex_init(&dev->as[i].mem_lock);
> > > +
> > > dev->name = kstrdup(config->name, GFP_KERNEL);
> > > if (!dev->name)
> > > goto err_str;
> > > @@ -1959,6 +2092,8 @@ static int vduse_create_dev(struct vduse_dev_config
> > > *config,
> > > err_idr:
> > > kfree(dev->name);
> > > err_str:
> > > + kfree(dev->as);
> > > +err_as:
> > > kfree(dev->groups);
> > > err_vq_groups:
> > > vduse_dev_destroy(dev);
> > > @@ -2084,7 +2219,7 @@ static int vduse_dev_init_vdpa(struct vduse_dev
> > > *dev, const char *name)
> > >
> > > vdev = vdpa_alloc_device(struct vduse_vdpa, vdpa, dev->dev,
> > > &vduse_vdpa_config_ops, &vduse_map_ops,
> > > - dev->ngroups, 1, name, true);
> > > + dev->ngroups, dev->nas, name, true);
> > > if (IS_ERR(vdev))
> > > return PTR_ERR(vdev);
> > >
> > > @@ -2113,11 +2248,20 @@ static int vdpa_dev_add(struct vdpa_mgmt_dev
> > > *mdev, const char *name,
> > > return ret;
> > >
> > > write_lock(&dev->domain_lock);
> > > - if (!dev->as.domain)
> > > - dev->as.domain = vduse_domain_create(VDUSE_IOVA_SIZE - 1,
> > > - dev->bounce_size);
> > > + ret = 0;
> > > +
> > > + for (int i = 0; i < dev->nas; ++i) {
> > > + dev->as[i].domain = vduse_domain_create(VDUSE_IOVA_SIZE -
> > > 1,
> > > + dev->bounce_size);
> > > + if (!dev->as[i].domain) {
> > > + ret = -ENOMEM;
> > > + for (int j = 0; j < i; ++j)
> > > + vduse_domain_destroy(dev->as[j].domain);
> > > + }
> > > + }
> > > +
> > > write_unlock(&dev->domain_lock);
> > > - if (!dev->as.domain) {
> > > + if (ret == -ENOMEM) {
> > > put_device(&dev->vdev->vdpa.dev);
> > > return -ENOMEM;
> > > }
> > > @@ -2126,8 +2270,12 @@ static int vdpa_dev_add(struct vdpa_mgmt_dev
> > > *mdev, const char *name,
> > > if (ret) {
> > > put_device(&dev->vdev->vdpa.dev);
> > > write_lock(&dev->domain_lock);
> > > - vduse_domain_destroy(dev->as.domain);
> > > - dev->as.domain = NULL;
> > > + for (int i = 0; i < dev->nas; i++) {
> > > + if (dev->as[i].domain) {
> > > + vduse_domain_destroy(dev->as[i].domain);
> > > + dev->as[i].domain = NULL;
> > > + }
> > > + }
> > > write_unlock(&dev->domain_lock);
> > > return ret;
> > > }
> > > diff --git a/include/uapi/linux/vduse.h b/include/uapi/linux/vduse.h
> > > index a3d51cf6df3a..da73c3f2c280 100644
> > > --- a/include/uapi/linux/vduse.h
> > > +++ b/include/uapi/linux/vduse.h
> > > @@ -47,7 +47,8 @@ struct vduse_dev_config {
> > > __u32 vq_num;
> > > __u32 vq_align;
> > > __u32 ngroups; /* if VDUSE_API_VERSION >= 1 */
> > > - __u32 reserved[12];
> > > + __u32 nas; /* if VDUSE_API_VERSION >= 1 */
> > > + __u32 reserved[11];
> > > __u32 config_size;
> > > __u8 config[];
> > > };
> > > @@ -82,6 +83,18 @@ struct vduse_iotlb_entry {
> > > __u8 perm;
> > > };
> > >
> > > +/**
> > > + * struct vduse_iotlb_entry_v2 - entry of IOTLB to describe one IOVA
> > > region in an ASID
> > > + * @v1: the original vduse_iotlb_entry
> > > + * @asid: address space ID of the IOVA region
> > > + *
> > > + * Structure used by VDUSE_IOTLB_GET_FD ioctl to find an overlapped IOVA
> > > region.
> > > + */
> > > +struct vduse_iotlb_entry_v2 {
> > > + struct vduse_iotlb_entry v1;
> > > + __u32 asid;
> > > +};
> > > +
> > > /*
> > > * Find the first IOVA region that overlaps with the range [start, last]
> > > * and return the corresponding file descriptor. Return -EINVAL means the
> > > @@ -166,6 +179,16 @@ struct vduse_vq_state_packed {
> > > __u16 last_used_idx;
> > > };
> > >
> > > +/**
> > > + * struct vduse_vq_group - virtqueue group
> > > + @ @group: Index of the virtqueue group
> > > + * @asid: Address space ID of the group
> > > + */
> > > +struct vduse_vq_group_asid {
> > > + __u32 group;
> > > + __u32 asid;
> > > +};
> > > +
> > > /**
> > > * struct vduse_vq_info - information of a virtqueue
> > > * @index: virtqueue index
> > > @@ -225,6 +248,7 @@ struct vduse_vq_eventfd {
> > > * @uaddr: start address of userspace memory, it must be aligned to page
> > > size
> > > * @iova: start of the IOVA region
> > > * @size: size of the IOVA region
> > > + * @asid: Address space ID of the IOVA region
> > > * @reserved: for future use, needs to be initialized to zero
> > > *
> > > * Structure used by VDUSE_IOTLB_REG_UMEM and VDUSE_IOTLB_DEREG_UMEM
> > > @@ -234,7 +258,8 @@ struct vduse_iova_umem {
> > > __u64 uaddr;
> > > __u64 iova;
> > > __u64 size;
> > > - __u64 reserved[3];
> > > + __u32 asid;
> > > + __u32 reserved[5];
> > > };
> > >
> > > /* Register userspace memory for IOVA regions */
> > > @@ -248,6 +273,7 @@ struct vduse_iova_umem {
> > > * @start: start of the IOVA region
> > > * @last: last of the IOVA region
> > > * @capability: capability of the IOVA region
> > > + * @asid: Address space ID of the IOVA region, only if device API
> > > version >= 1
> > > * @reserved: for future use, needs to be initialized to zero
> > > *
> > > * Structure used by VDUSE_IOTLB_GET_INFO ioctl to get information of
> > > @@ -258,7 +284,8 @@ struct vduse_iova_info {
> > > __u64 last;
> > > #define VDUSE_IOVA_CAP_UMEM (1 << 0)
> > > __u64 capability;
> > > - __u64 reserved[3];
> > > + __u32 asid; /* Only if device API version >= 1 */
> > > + __u32 reserved[5];
> > > };
> > >
> > > /*
> > > @@ -280,6 +307,7 @@ enum vduse_req_type {
> > > VDUSE_GET_VQ_STATE,
> > > VDUSE_SET_STATUS,
> > > VDUSE_UPDATE_IOTLB,
> > > + VDUSE_SET_VQ_GROUP_ASID,
> > > };
> > >
> > > /**
> > > @@ -314,6 +342,18 @@ struct vduse_iova_range {
> > > __u64 last;
> > > };
> > >
> > > +/**
> > > + * struct vduse_iova_range - IOVA range [start, last] if API_VERSION >= 1
> > > + * @start: start of the IOVA range
> > > + * @last: last of the IOVA range
> > > + * @asid: address space ID of the IOVA range
> > > + */
> > > +struct vduse_iova_range_v2 {
> > > + __u64 start;
> > > + __u64 last;
> > > + __u32 asid;
> > > +};
> > > +
> > > /**
> > > * struct vduse_dev_request - control request
> > > * @type: request type
> > > @@ -322,6 +362,8 @@ struct vduse_iova_range {
> > > * @vq_state: virtqueue state, only index field is available
> > > * @s: device status
> > > * @iova: IOVA range for updating
> > > + * @iova_v2: IOVA range for updating if API_VERSION >= 1
> > > + * @vq_group_asid: ASID of a virtqueue group
> > > * @padding: padding
> > > *
> > > * Structure used by read(2) on /dev/vduse/$NAME.
> > > @@ -334,6 +376,9 @@ struct vduse_dev_request {
> > > struct vduse_vq_state vq_state;
> > > struct vduse_dev_status s;
> > > struct vduse_iova_range iova;
> > > + /* Following members only if vduse api version >= 1 */;
> > > + struct vduse_iova_range_v2 iova_v2;
> > > + struct vduse_vq_group_asid vq_group_asid;
> > > __u32 padding[32];
> > > };
> > > };
> > > --
> > > 2.51.0
> > >
> >
> > Thanks
> >
