On Thu, Oct 30, 2025 at 12:52 PM Yongji Xie <[email protected]> wrote: > > On Thu, Oct 30, 2025 at 6:01 PM Eugenio Pérez <[email protected]> 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. > > > > Acked-by: Jason Wang <[email protected]> > > Signed-off-by: Eugenio Pérez <[email protected]> > > --- > > v8: > > * Revert the mutex to rwlock change, it needs proper profiling to > > justify it. > > > > v7: > > * Take write lock in the error path (Jason). > > > > v6: > > * Make vdpa_dev_add use gotos for error handling (MST). > > * s/(dev->api_version < 1) ?/(dev->api_version < VDUSE_API_VERSION_1) ?/ > > (MST). > > * Fix struct name not matching in the doc. > > > > v5: > > * Properly return errno if copy_to_user returns >0 in VDUSE_IOTLB_GET_FD > > ioctl (Jason). > > * Properly set domain bounce size to divide equally between nas (Jason). > > * Exclude "padding" member from the only >V1 members in > > vduse_dev_request. > > > > v4: > > * Divide each domain bounce size between the device bounce size (Jason). > > * revert unneeded addr = NULL assignment (Jason) > > * Change if (x && (y || z)) return to if (x) { if (y) return; if (z) > > return; } (Jason) > > * Change a bad multiline comment, using @ caracter instead of * (Jason). > > * Consider config->nas == 0 as a fail (Jason). > > > > 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 | 348 ++++++++++++++++++++--------- > > include/uapi/linux/vduse.h | 53 ++++- > > 2 files changed, 292 insertions(+), 109 deletions(-) > > > > diff --git a/drivers/vdpa/vdpa_user/vduse_dev.c > > b/drivers/vdpa/vdpa_user/vduse_dev.c > > index 97be04f73fbf..c6909d73d06d 100644 > > --- a/drivers/vdpa/vdpa_user/vduse_dev.c > > +++ b/drivers/vdpa/vdpa_user/vduse_dev.c > > @@ -41,6 +41,7 @@ > > > > #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) > > @@ -86,7 +87,14 @@ 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; > > }; > > > > @@ -94,7 +102,7 @@ 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; > > @@ -122,9 +130,8 @@ 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; > > struct mutex domain_lock; > > }; > > @@ -314,7 +321,7 @@ 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 }; > > @@ -323,8 +330,14 @@ 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); > > } > > @@ -436,14 +449,29 @@ 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) > > +{ > > + mutex_lock(&dev->domain_lock); > > + dev->groups[group].as = &dev->as[asid]; > > + mutex_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); > > > > @@ -623,6 +651,29 @@ 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) > > { > > @@ -794,13 +845,13 @@ 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; > > } > > > > @@ -843,6 +894,7 @@ 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, > > }; > > @@ -858,9 +910,10 @@ static void vduse_dev_sync_single_for_device(union > > virtio_map token, > > return; > > > > vdev = token.group->dev; > > - domain = vdev->domain; > > - > > + mutex_lock(&vdev->domain_lock); > > + domain = token.group->as->domain; > > vduse_domain_sync_single_for_device(domain, dma_addr, size, dir); > > + mutex_unlock(&vdev->domain_lock); > > } > > > > static void vduse_dev_sync_single_for_cpu(union virtio_map token, > > @@ -874,9 +927,10 @@ static void vduse_dev_sync_single_for_cpu(union > > virtio_map token, > > return; > > > > vdev = token.group->dev; > > - domain = vdev->domain; > > - > > + mutex_lock(&vdev->domain_lock); > > + domain = token.group->as->domain; > > vduse_domain_sync_single_for_cpu(domain, dma_addr, size, dir); > > + mutex_unlock(&vdev->domain_lock); > > } > > > > static dma_addr_t vduse_dev_map_page(union virtio_map token, struct page > > *page, > > @@ -886,14 +940,18 @@ static dma_addr_t vduse_dev_map_page(union virtio_map > > token, struct page *page, > > { > > struct vduse_dev *vdev; > > struct vduse_iova_domain *domain; > > + dma_addr_t r; > > > > if (!token.group) > > return DMA_MAPPING_ERROR; > > > > vdev = token.group->dev; > > - domain = vdev->domain; > > + mutex_lock(&vdev->domain_lock); > > The mutex_lock can't be used here since the dma ops might be called in > atomic context. And I think we can just remove it since creation and > deletion operations of the iova domain are guaranteed not to execute > concurrently with I/O operations. >
That would be great indeed! Can you expand on this, what protects here from the moment the two syscalls are issues from userland?
