This is mainly used by AMD vIOMMU to initialize virtualize hardware queue
using guest physical address where the address is specified via
@hw_queue->base_addr.

Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
---
 drivers/iommu/iommufd/viommu.c | 125 +++++++++++++++++++++++----------
 include/linux/iommufd.h        |   5 +-
 2 files changed, 91 insertions(+), 39 deletions(-)

diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index 462b457ffd0c..59b31b3e36be 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -353,62 +353,35 @@ iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd,
 	return ERR_PTR(rc);
 }
 
-int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd)
+static int _iommufd_hw_queue_init_phys(struct iommufd_ucmd *ucmd,
+				       struct iommufd_viommu *viommu)
 {
 	struct iommu_hw_queue_alloc *cmd = ucmd->cmd;
 	struct iommufd_hw_queue *hw_queue;
-	struct iommufd_viommu *viommu;
 	struct iommufd_access *access;
 	size_t hw_queue_size;
 	phys_addr_t base_pa;
-	u64 last;
 	int rc;
 
-	if (cmd->flags || cmd->type == IOMMU_HW_QUEUE_TYPE_DEFAULT)
-		return -EOPNOTSUPP;
-	if (!cmd->length)
-		return -EINVAL;
-	if (check_add_overflow(cmd->nesting_parent_iova, cmd->length - 1,
-			       &last))
-		return -EOVERFLOW;
-
-	viommu = iommufd_get_viommu(ucmd, cmd->viommu_id);
-	if (IS_ERR(viommu))
-		return PTR_ERR(viommu);
-
-	if (!viommu->ops || !viommu->ops->get_hw_queue_size ||
-	    !viommu->ops->hw_queue_init_phys) {
-		rc = -EOPNOTSUPP;
-		goto out_put_viommu;
-	}
-
 	hw_queue_size = viommu->ops->get_hw_queue_size(viommu, cmd->type);
-	if (!hw_queue_size) {
-		rc = -EOPNOTSUPP;
-		goto out_put_viommu;
-	}
+	if (!hw_queue_size)
+		return -EOPNOTSUPP;
 
 	/*
 	 * It is a driver bug for providing a hw_queue_size smaller than the
 	 * core HW queue structure size
 	 */
-	if (WARN_ON_ONCE(hw_queue_size < sizeof(*hw_queue))) {
-		rc = -EOPNOTSUPP;
-		goto out_put_viommu;
-	}
+	if (WARN_ON_ONCE(hw_queue_size < sizeof(*hw_queue)))
+		return -EOPNOTSUPP;
 
 	hw_queue = (struct iommufd_hw_queue *)_iommufd_object_alloc_ucmd(
 		ucmd, hw_queue_size, IOMMUFD_OBJ_HW_QUEUE);
-	if (IS_ERR(hw_queue)) {
-		rc = PTR_ERR(hw_queue);
-		goto out_put_viommu;
-	}
+	if (IS_ERR(hw_queue))
+		return PTR_ERR(hw_queue);
 
 	access = iommufd_hw_queue_alloc_phys(cmd, viommu, &base_pa);
-	if (IS_ERR(access)) {
-		rc = PTR_ERR(access);
-		goto out_put_viommu;
-	}
+	if (IS_ERR(access))
+		return PTR_ERR(access);
 
 	hw_queue->viommu = viommu;
 	refcount_inc(&viommu->obj.users);
@@ -419,9 +392,85 @@ int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd)
 
 	rc = viommu->ops->hw_queue_init_phys(hw_queue, cmd->index, base_pa);
 	if (rc)
-		goto out_put_viommu;
+		return rc;
 
 	cmd->out_hw_queue_id = hw_queue->obj.id;
+	return rc;
+}
+
+static int _iommufd_hw_queue_init(struct iommufd_ucmd *ucmd,
+				  struct iommufd_viommu *viommu)
+{
+	struct iommu_hw_queue_alloc *cmd = ucmd->cmd;
+	struct iommufd_hw_queue *hw_queue;
+	size_t hw_queue_size;
+	int rc;
+
+	hw_queue_size = viommu->ops->get_hw_queue_size(viommu, cmd->type);
+	if (!hw_queue_size)
+		return -EOPNOTSUPP;
+
+	/*
+	 * It is a driver bug for providing a hw_queue_size smaller than the
+	 * core HW queue structure size
+	 */
+	if (WARN_ON_ONCE(hw_queue_size < sizeof(*hw_queue)))
+		return -EOPNOTSUPP;
+
+	hw_queue = (struct iommufd_hw_queue *)_iommufd_object_alloc_ucmd(
+		ucmd, hw_queue_size, IOMMUFD_OBJ_HW_QUEUE);
+	if (IS_ERR(hw_queue))
+		return PTR_ERR(hw_queue);
+
+	hw_queue->viommu = viommu;
+	refcount_inc(&viommu->obj.users);
+	hw_queue->access = NULL;
+	hw_queue->type = cmd->type;
+	hw_queue->length = cmd->length;
+	hw_queue->base_addr = cmd->nesting_parent_iova;
+
+	rc = viommu->ops->hw_queue_init(hw_queue, cmd->index);
+	if (rc)
+		return rc;
+
+	cmd->out_hw_queue_id = hw_queue->obj.id;
+	return rc;
+}
+
+int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hw_queue_alloc *cmd = ucmd->cmd;
+	struct iommufd_viommu *viommu;
+	u64 last;
+	int rc;
+
+	if (cmd->flags || cmd->type == IOMMU_HW_QUEUE_TYPE_DEFAULT)
+		return -EOPNOTSUPP;
+	if (!cmd->length)
+		return -EINVAL;
+	if (check_add_overflow(cmd->nesting_parent_iova, cmd->length - 1,
+			       &last))
+		return -EOVERFLOW;
+
+	viommu = iommufd_get_viommu(ucmd, cmd->viommu_id);
+	if (IS_ERR(viommu))
+		return PTR_ERR(viommu);
+
+	if (!viommu->ops || !viommu->ops->get_hw_queue_size) {
+		rc = -EOPNOTSUPP;
+		goto out_put_viommu;
+	}
+
+	if (viommu->ops->hw_queue_init_phys)
+		rc = _iommufd_hw_queue_init_phys(ucmd, viommu);
+	else if (viommu->ops->hw_queue_init)
+		rc = _iommufd_hw_queue_init(ucmd, viommu);
+	else
+		rc = -EOPNOTSUPP;
+
+	if (rc)
+		goto out_put_viommu;
+
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_put_viommu:
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 6e7efe83bc5d..c0030677e13c 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -180,6 +180,9 @@ struct iommufd_hw_queue {
  *                      the physical location of the guest queue
  *                      If driver has a deinit function to revert what this op
  *                      does, it should set it to the @hw_queue->destroy pointer
+ * @hw_queue_init: Similar to hw_queue_init_phys, but driver providing this op
+ *                 indicates that HW accesses the guest queue memory via
+ *                 @hw_queue->baseaddr.
  */
 struct iommufd_viommu_ops {
 	void (*destroy)(struct iommufd_viommu *viommu);
@@ -192,9 +195,9 @@ struct iommufd_viommu_ops {
 	int (*vdevice_init)(struct iommufd_vdevice *vdev);
 	size_t (*get_hw_queue_size)(struct iommufd_viommu *viommu,
 				    enum iommu_hw_queue_type queue_type);
-	/* AMD's HW will add hw_queue_init simply using @hw_queue->base_addr */
 	int (*hw_queue_init_phys)(struct iommufd_hw_queue *hw_queue, u32 index,
 				  phys_addr_t base_addr_pa);
+	int (*hw_queue_init)(struct iommufd_hw_queue *hw_queue, u32 index);
 };
 
 #if IS_ENABLED(CONFIG_IOMMUFD)
-- 
2.34.1