iommufd: Keep track of each device's reserved regions instead of groups

The driver facing API in the iommu core makes the reserved regions
per-device. An algorithm in the core code consolidates the regions of all
the devices in a group to return the group view.

To allow for devices to be hotplugged into the group iommufd would re-load
the entire group's reserved regions for each device, just in case they
changed.

Further iommufd already has to deal with duplicated/overlapping reserved
regions as it must union all the groups together.

Thus simplify all of this to just use the device reserved regions
interface directly from the iommu driver.

Link: https://lore.kernel.org/r/5-v8-6659224517ea+532-iommufd_alloc_jgg@nvidia.comSuggested-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/iommu/iommufd/device.c

@@ -356,9 +356,8 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 		}
 	}
 
-	rc = iopt_table_enforce_group_resv_regions(&hwpt->ioas->iopt, idev->dev,
-						   idev->igroup->group,
-						   &sw_msi_start);
+	rc = iopt_table_enforce_dev_resv_regions(
+		&hwpt->ioas->iopt, idev->dev, &sw_msi_start);
 	if (rc)
 		goto err_unlock;
 

drivers/iommu/iommufd/io_pagetable.c

@@ -1169,25 +1169,22 @@ void iopt_remove_access(struct io_pagetable *iopt,
 	up_write(&iopt->domains_rwsem);
 }
 
-/* Narrow the valid_iova_itree to include reserved ranges from a group. */
-int iopt_table_enforce_group_resv_regions(struct io_pagetable *iopt,
-					  struct device *device,
-					  struct iommu_group *group,
-					  phys_addr_t *sw_msi_start)
+/* Narrow the valid_iova_itree to include reserved ranges from a device. */
+int iopt_table_enforce_dev_resv_regions(struct io_pagetable *iopt,
+					struct device *dev,
+					phys_addr_t *sw_msi_start)
 {
 	struct iommu_resv_region *resv;
-	struct iommu_resv_region *tmp;
-	LIST_HEAD(group_resv_regions);
+	LIST_HEAD(resv_regions);
 	unsigned int num_hw_msi = 0;
 	unsigned int num_sw_msi = 0;
 	int rc;
 
 	down_write(&iopt->iova_rwsem);
-	rc = iommu_get_group_resv_regions(group, &group_resv_regions);
-	if (rc)
-		goto out_unlock;
+	/* FIXME: drivers allocate memory but there is no failure propogated */
+	iommu_get_resv_regions(dev, &resv_regions);
 
-	list_for_each_entry(resv, &group_resv_regions, list) {
+	list_for_each_entry(resv, &resv_regions, list) {
 		if (resv->type == IOMMU_RESV_DIRECT_RELAXABLE)
 			continue;
 
@@ -1199,7 +1196,7 @@ int iopt_table_enforce_group_resv_regions(struct io_pagetable *iopt,
 		}
 
 		rc = iopt_reserve_iova(iopt, resv->start,
-				       resv->length - 1 + resv->start, device);
+				       resv->length - 1 + resv->start, dev);
 		if (rc)
 			goto out_reserved;
 	}
@@ -1214,11 +1211,9 @@ int iopt_table_enforce_group_resv_regions(struct io_pagetable *iopt,
 	goto out_free_resv;
 
 out_reserved:
-	__iopt_remove_reserved_iova(iopt, device);
+	__iopt_remove_reserved_iova(iopt, dev);
 out_free_resv:
-	list_for_each_entry_safe(resv, tmp, &group_resv_regions, list)
-		kfree(resv);
-out_unlock:
+	iommu_put_resv_regions(dev, &resv_regions);
 	up_write(&iopt->iova_rwsem);
 	return rc;
 }

drivers/iommu/iommufd/iommufd_private.h

@@ -76,10 +76,9 @@ int iopt_table_add_domain(struct io_pagetable *iopt,
 			  struct iommu_domain *domain);
 void iopt_table_remove_domain(struct io_pagetable *iopt,
 			      struct iommu_domain *domain);
-int iopt_table_enforce_group_resv_regions(struct io_pagetable *iopt,
-					  struct device *device,
-					  struct iommu_group *group,
-					  phys_addr_t *sw_msi_start);
+int iopt_table_enforce_dev_resv_regions(struct io_pagetable *iopt,
+					struct device *dev,
+					phys_addr_t *sw_msi_start);
 int iopt_set_allow_iova(struct io_pagetable *iopt,
 			struct rb_root_cached *allowed_iova);
 int iopt_reserve_iova(struct io_pagetable *iopt, unsigned long start,