1 files changed, 216 insertions, 55 deletions

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 4c2f0bd06285..935a1d0ddb97 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -28,17 +28,27 @@
 enum {
 	VHOST_VDPA_BACKEND_FEATURES =
 	(1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) |
-	(1ULL << VHOST_BACKEND_F_IOTLB_BATCH),
+	(1ULL << VHOST_BACKEND_F_IOTLB_BATCH) |
+	(1ULL << VHOST_BACKEND_F_IOTLB_ASID),
 };
 
 #define VHOST_VDPA_DEV_MAX (1U << MINORBITS)
 
+#define VHOST_VDPA_IOTLB_BUCKETS 16
+
+struct vhost_vdpa_as {
+	struct hlist_node hash_link;
+	struct vhost_iotlb iotlb;
+	u32 id;
+};
+
 struct vhost_vdpa {
 	struct vhost_dev vdev;
 	struct iommu_domain *domain;
 	struct vhost_virtqueue *vqs;
 	struct completion completion;
 	struct vdpa_device *vdpa;
+	struct hlist_head as[VHOST_VDPA_IOTLB_BUCKETS];
 	struct device dev;
 	struct cdev cdev;
 	atomic_t opened;
@@ -48,12 +58,89 @@ struct vhost_vdpa {
 	struct eventfd_ctx *config_ctx;
 	int in_batch;
 	struct vdpa_iova_range range;
+	u32 batch_asid;
 };
 
 static DEFINE_IDA(vhost_vdpa_ida);
 
 static dev_t vhost_vdpa_major;
 
+static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
+{
+	struct vhost_vdpa_as *as = container_of(iotlb, struct
+						vhost_vdpa_as, iotlb);
+	return as->id;
+}
+
+static struct vhost_vdpa_as *asid_to_as(struct vhost_vdpa *v, u32 asid)
+{
+	struct hlist_head *head = &v->as[asid % VHOST_VDPA_IOTLB_BUCKETS];
+	struct vhost_vdpa_as *as;
+
+	hlist_for_each_entry(as, head, hash_link)
+		if (as->id == asid)
+			return as;
+
+	return NULL;
+}
+
+static struct vhost_iotlb *asid_to_iotlb(struct vhost_vdpa *v, u32 asid)
+{
+	struct vhost_vdpa_as *as = asid_to_as(v, asid);
+
+	if (!as)
+		return NULL;
+
+	return &as->iotlb;
+}
+
+static struct vhost_vdpa_as *vhost_vdpa_alloc_as(struct vhost_vdpa *v, u32 asid)
+{
+	struct hlist_head *head = &v->as[asid % VHOST_VDPA_IOTLB_BUCKETS];
+	struct vhost_vdpa_as *as;
+
+	if (asid_to_as(v, asid))
+		return NULL;
+
+	if (asid >= v->vdpa->nas)
+		return NULL;
+
+	as = kmalloc(sizeof(*as), GFP_KERNEL);
+	if (!as)
+		return NULL;
+
+	vhost_iotlb_init(&as->iotlb, 0, 0);
+	as->id = asid;
+	hlist_add_head(&as->hash_link, head);
+
+	return as;
+}
+
+static struct vhost_vdpa_as *vhost_vdpa_find_alloc_as(struct vhost_vdpa *v,
+						      u32 asid)
+{
+	struct vhost_vdpa_as *as = asid_to_as(v, asid);
+
+	if (as)
+		return as;
+
+	return vhost_vdpa_alloc_as(v, asid);
+}
+
+static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)
+{
+	struct vhost_vdpa_as *as = asid_to_as(v, asid);
+
+	if (!as)
+		return -EINVAL;
+
+	hlist_del(&as->hash_link);
+	vhost_iotlb_reset(&as->iotlb);
+	kfree(as);
+
+	return 0;
+}
+
 static void handle_vq_kick(struct vhost_work *work)
 {
 	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -411,6 +498,22 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 			return -EFAULT;
 		ops->set_vq_ready(vdpa, idx, s.num);
 		return 0;
+	case VHOST_VDPA_GET_VRING_GROUP:
+		s.index = idx;
+		s.num = ops->get_vq_group(vdpa, idx);
+		if (s.num >= vdpa->ngroups)
+			return -EIO;
+		else if (copy_to_user(argp, &s, sizeof(s)))
+			return -EFAULT;
+		return 0;
+	case VHOST_VDPA_SET_GROUP_ASID:
+		if (copy_from_user(&s, argp, sizeof(s)))
+			return -EFAULT;
+		if (s.num >= vdpa->nas)
+			return -EINVAL;
+		if (!ops->set_group_asid)
+			return -EOPNOTSUPP;
+		return ops->set_group_asid(vdpa, idx, s.num);
 	case VHOST_GET_VRING_BASE:
 		r = ops->get_vq_state(v->vdpa, idx, &vq_state);
 		if (r)
@@ -505,6 +608,15 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 	case VHOST_VDPA_GET_VRING_NUM:
 		r = vhost_vdpa_get_vring_num(v, argp);
 		break;
+	case VHOST_VDPA_GET_GROUP_NUM:
+		if (copy_to_user(argp, &v->vdpa->ngroups,
+				 sizeof(v->vdpa->ngroups)))
+			r = -EFAULT;
+		break;
+	case VHOST_VDPA_GET_AS_NUM:
+		if (copy_to_user(argp, &v->vdpa->nas, sizeof(v->vdpa->nas)))
+			r = -EFAULT;
+		break;
 	case VHOST_SET_LOG_BASE:
 	case VHOST_SET_LOG_FD:
 		r = -ENOIOCTLCMD;
@@ -537,10 +649,11 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 	return r;
 }
 
-static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v,
+				struct vhost_iotlb *iotlb,
+				u64 start, u64 last)
 {
 	struct vhost_dev *dev = &v->vdev;
-	struct vhost_iotlb *iotlb = dev->iotlb;
 	struct vhost_iotlb_map *map;
 	struct page *page;
 	unsigned long pfn, pinned;
@@ -559,10 +672,10 @@ static void vhost_vdpa_pa_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 	}
 }
 
-static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+static void vhost_vdpa_va_unmap(struct vhost_vdpa *v,
+				struct vhost_iotlb *iotlb,
+				u64 start, u64 last)
 {
-	struct vhost_dev *dev = &v->vdev;
-	struct vhost_iotlb *iotlb = dev->iotlb;
 	struct vhost_iotlb_map *map;
 	struct vdpa_map_file *map_file;
 
@@ -574,23 +687,16 @@ static void vhost_vdpa_va_unmap(struct vhost_vdpa *v, u64 start, u64 last)
 	}
 }
 
-static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
+				   struct vhost_iotlb *iotlb,
+				   u64 start, u64 last)
 {
 	struct vdpa_device *vdpa = v->vdpa;
 
 	if (vdpa->use_va)
-		return vhost_vdpa_va_unmap(v, start, last);
-
-	return vhost_vdpa_pa_unmap(v, start, last);
-}
-
-static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v)
-{
-	struct vhost_dev *dev = &v->vdev;
+		return vhost_vdpa_va_unmap(v, iotlb, start, last);
 
-	vhost_vdpa_iotlb_unmap(v, 0ULL, 0ULL - 1);
-	kfree(dev->iotlb);
-	dev->iotlb = NULL;
+	return vhost_vdpa_pa_unmap(v, iotlb, start, last);
 }
 
 static int perm_to_iommu_flags(u32 perm)
@@ -615,30 +721,31 @@ static int perm_to_iommu_flags(u32 perm)
 	return flags | IOMMU_CACHE;
 }
 
-static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova,
-			  u64 size, u64 pa, u32 perm, void *opaque)
+static int vhost_vdpa_map(struct vhost_vdpa *v, struct vhost_iotlb *iotlb,
+			  u64 iova, u64 size, u64 pa, u32 perm, void *opaque)
 {
 	struct vhost_dev *dev = &v->vdev;
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	u32 asid = iotlb_to_asid(iotlb);
 	int r = 0;
 
-	r = vhost_iotlb_add_range_ctx(dev->iotlb, iova, iova + size - 1,
+	r = vhost_iotlb_add_range_ctx(iotlb, iova, iova + size - 1,
 				      pa, perm, opaque);
 	if (r)
 		return r;
 
 	if (ops->dma_map) {
-		r = ops->dma_map(vdpa, iova, size, pa, perm, opaque);
+		r = ops->dma_map(vdpa, asid, iova, size, pa, perm, opaque);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
-			r = ops->set_map(vdpa, dev->iotlb);
+			r = ops->set_map(vdpa, asid, iotlb);
 	} else {
 		r = iommu_map(v->domain, iova, pa, size,
 			      perm_to_iommu_flags(perm));
 	}
 	if (r) {
-		vhost_iotlb_del_range(dev->iotlb, iova, iova + size - 1);
+		vhost_iotlb_del_range(iotlb, iova, iova + size - 1);
 		return r;
 	}
 
@@ -648,25 +755,34 @@ static int vhost_vdpa_map(struct vhost_vdpa *v, u64 iova,
 	return 0;
 }
 
-static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
+static void vhost_vdpa_unmap(struct vhost_vdpa *v,
+			     struct vhost_iotlb *iotlb,
+			     u64 iova, u64 size)
 {
-	struct vhost_dev *dev = &v->vdev;
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	u32 asid = iotlb_to_asid(iotlb);
 
-	vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1);
+	vhost_vdpa_iotlb_unmap(v, iotlb, iova, iova + size - 1);
 
 	if (ops->dma_map) {
-		ops->dma_unmap(vdpa, iova, size);
+		ops->dma_unmap(vdpa, asid, iova, size);
 	} else if (ops->set_map) {
 		if (!v->in_batch)
-			ops->set_map(vdpa, dev->iotlb);
+			ops->set_map(vdpa, asid, iotlb);
 	} else {
 		iommu_unmap(v->domain, iova, size);
 	}
+
+	/* If we are in the middle of batch processing, delay the free
+	 * of AS until BATCH_END.
+	 */
+	if (!v->in_batch && !iotlb->nmaps)
+		vhost_vdpa_remove_as(v, asid);
 }
 
 static int vhost_vdpa_va_map(struct vhost_vdpa *v,
+			     struct vhost_iotlb *iotlb,
 			     u64 iova, u64 size, u64 uaddr, u32 perm)
 {
 	struct vhost_dev *dev = &v->vdev;
@@ -696,7 +812,7 @@ static int vhost_vdpa_va_map(struct vhost_vdpa *v,
 		offset = (vma->vm_pgoff << PAGE_SHIFT) + uaddr - vma->vm_start;
 		map_file->offset = offset;
 		map_file->file = get_file(vma->vm_file);
-		ret = vhost_vdpa_map(v, map_iova, map_size, uaddr,
+		ret = vhost_vdpa_map(v, iotlb, map_iova, map_size, uaddr,
 				     perm, map_file);
 		if (ret) {
 			fput(map_file->file);
@@ -709,7 +825,7 @@ next:
 		map_iova += map_size;
 	}
 	if (ret)
-		vhost_vdpa_unmap(v, iova, map_iova - iova);
+		vhost_vdpa_unmap(v, iotlb, iova, map_iova - iova);
 
 	mmap_read_unlock(dev->mm);
 
@@ -717,6 +833,7 @@ next:
 }
 
 static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
+			     struct vhost_iotlb *iotlb,
 			     u64 iova, u64 size, u64 uaddr, u32 perm)
 {
 	struct vhost_dev *dev = &v->vdev;
@@ -780,7 +897,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
 			if (last_pfn && (this_pfn != last_pfn + 1)) {
 				/* Pin a contiguous chunk of memory */
 				csize = PFN_PHYS(last_pfn - map_pfn + 1);
-				ret = vhost_vdpa_map(v, iova, csize,
+				ret = vhost_vdpa_map(v, iotlb, iova, csize,
 						     PFN_PHYS(map_pfn),
 						     perm, NULL);
 				if (ret) {
@@ -810,7 +927,7 @@ static int vhost_vdpa_pa_map(struct vhost_vdpa *v,
 	}
 
 	/* Pin the rest chunk */
-	ret = vhost_vdpa_map(v, iova, PFN_PHYS(last_pfn - map_pfn + 1),
+	ret = vhost_vdpa_map(v, iotlb, iova, PFN_PHYS(last_pfn - map_pfn + 1),
 			     PFN_PHYS(map_pfn), perm, NULL);
 out:
 	if (ret) {
@@ -830,7 +947,7 @@ out:
 			for (pfn = map_pfn; pfn <= last_pfn; pfn++)
 				unpin_user_page(pfn_to_page(pfn));
 		}
-		vhost_vdpa_unmap(v, start, size);
+		vhost_vdpa_unmap(v, iotlb, start, size);
 	}
 unlock:
 	mmap_read_unlock(dev->mm);
@@ -841,11 +958,10 @@ free:
 }
 
 static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
+					   struct vhost_iotlb *iotlb,
 					   struct vhost_iotlb_msg *msg)
 {
-	struct vhost_dev *dev = &v->vdev;
 	struct vdpa_device *vdpa = v->vdpa;
-	struct vhost_iotlb *iotlb = dev->iotlb;
 
 	if (msg->iova < v->range.first || !msg->size ||
 	    msg->iova > U64_MAX - msg->size + 1 ||
@@ -857,19 +973,21 @@ static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
 		return -EEXIST;
 
 	if (vdpa->use_va)
-		return vhost_vdpa_va_map(v, msg->iova, msg->size,
+		return vhost_vdpa_va_map(v, iotlb, msg->iova, msg->size,
 					 msg->uaddr, msg->perm);
 
-	return vhost_vdpa_pa_map(v, msg->iova, msg->size, msg->uaddr,
+	return vhost_vdpa_pa_map(v, iotlb, msg->iova, msg->size, msg->uaddr,
 				 msg->perm);
 }
 
-static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
+static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev, u32 asid,
 					struct vhost_iotlb_msg *msg)
 {
 	struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev);
 	struct vdpa_device *vdpa = v->vdpa;
 	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vhost_iotlb *iotlb = NULL;
+	struct vhost_vdpa_as *as = NULL;
 	int r = 0;
 
 	mutex_lock(&dev->mutex);
@@ -878,20 +996,47 @@ static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
 	if (r)
 		goto unlock;
 
+	if (msg->type == VHOST_IOTLB_UPDATE ||
+	    msg->type == VHOST_IOTLB_BATCH_BEGIN) {
+		as = vhost_vdpa_find_alloc_as(v, asid);
+		if (!as) {
+			dev_err(&v->dev, "can't find and alloc asid %d\n",
+				asid);
+			r = -EINVAL;
+			goto unlock;
+		}
+		iotlb = &as->iotlb;
+	} else
+		iotlb = asid_to_iotlb(v, asid);
+
+	if ((v->in_batch && v->batch_asid != asid) || !iotlb) {
+		if (v->in_batch && v->batch_asid != asid) {
+			dev_info(&v->dev, "batch id %d asid %d\n",
+				 v->batch_asid, asid);
+		}
+		if (!iotlb)
+			dev_err(&v->dev, "no iotlb for asid %d\n", asid);
+		r = -EINVAL;
+		goto unlock;
+	}
+
 	switch (msg->type) {
 	case VHOST_IOTLB_UPDATE:
-		r = vhost_vdpa_process_iotlb_update(v, msg);
+		r = vhost_vdpa_process_iotlb_update(v, iotlb, msg);
 		break;
 	case VHOST_IOTLB_INVALIDATE:
-		vhost_vdpa_unmap(v, msg->iova, msg->size);
+		vhost_vdpa_unmap(v, iotlb, msg->iova, msg->size);
 		break;
 	case VHOST_IOTLB_BATCH_BEGIN:
+		v->batch_asid = asid;
 		v->in_batch = true;
 		break;
 	case VHOST_IOTLB_BATCH_END:
 		if (v->in_batch && ops->set_map)
-			ops->set_map(vdpa, dev->iotlb);
+			ops->set_map(vdpa, asid, iotlb);
 		v->in_batch = false;
+		if (!iotlb->nmaps)
+			vhost_vdpa_remove_as(v, asid);
 		break;
 	default:
 		r = -EINVAL;
@@ -977,6 +1122,21 @@ static void vhost_vdpa_set_iova_range(struct vhost_vdpa *v)
 	}
 }
 
+static void vhost_vdpa_cleanup(struct vhost_vdpa *v)
+{
+	struct vhost_vdpa_as *as;
+	u32 asid;
+
+	vhost_dev_cleanup(&v->vdev);
+	kfree(v->vdev.vqs);
+
+	for (asid = 0; asid < v->vdpa->nas; asid++) {
+		as = asid_to_as(v, asid);
+		if (as)
+			vhost_vdpa_remove_as(v, asid);
+	}
+}
+
 static int vhost_vdpa_open(struct inode *inode, struct file *filep)
 {
 	struct vhost_vdpa *v;
@@ -1010,15 +1170,9 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)
 	vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, false,
 		       vhost_vdpa_process_iotlb_msg);
 
-	dev->iotlb = vhost_iotlb_alloc(0, 0);
-	if (!dev->iotlb) {
-		r = -ENOMEM;
-		goto err_init_iotlb;
-	}
-
 	r = vhost_vdpa_alloc_domain(v);
 	if (r)
-		goto err_init_iotlb;
+		goto err_alloc_domain;
 
 	vhost_vdpa_set_iova_range(v);
 
@@ -1026,9 +1180,8 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)
 
 	return 0;
 
-err_init_iotlb:
-	vhost_dev_cleanup(&v->vdev);
-	kfree(vqs);
+err_alloc_domain:
+	vhost_vdpa_cleanup(v);
 err:
 	atomic_dec(&v->opened);
 	return r;
@@ -1052,11 +1205,9 @@ static int vhost_vdpa_release(struct inode *inode, struct file *filep)
 	vhost_vdpa_clean_irq(v);
 	vhost_vdpa_reset(v);
 	vhost_dev_stop(&v->vdev);
-	vhost_vdpa_iotlb_free(v);
 	vhost_vdpa_free_domain(v);
 	vhost_vdpa_config_put(v);
 	vhost_dev_cleanup(&v->vdev);
-	kfree(v->vdev.vqs);
 	mutex_unlock(&d->mutex);
 
 	atomic_dec(&v->opened);
@@ -1152,7 +1303,14 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 	const struct vdpa_config_ops *ops = vdpa->config;
 	struct vhost_vdpa *v;
 	int minor;
-	int r;
+	int i, r;
+
+	/* We can't support platform IOMMU device with more than 1
+	 * group or as
+	 */
+	if (!ops->set_map && !ops->dma_map &&
+	    (vdpa->ngroups > 1 || vdpa->nas > 1))
+		return -EOPNOTSUPP;
 
 	v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 	if (!v)
@@ -1196,6 +1354,9 @@ static int vhost_vdpa_probe(struct vdpa_device *vdpa)
 	init_completion(&v->completion);
 	vdpa_set_drvdata(vdpa, v);
 
+	for (i = 0; i < VHOST_VDPA_IOTLB_BUCKETS; i++)
+		INIT_HLIST_HEAD(&v->as[i]);
+
 	return 0;
 
 err: