Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:
 "This brings the first of three planned user IO page table invalidation
  operations:

   - IOMMU_HWPT_INVALIDATE allows invalidating the IOTLB integrated into
     the iommu itself. The Intel implementation will also generate an
     ATC invalidation to flush the device IOTLB as it unambiguously
     knows the device, but other HW will not.

  It goes along with the prior PR to implement userspace IO page tables
  (aka nested translation for VMs) to allow Intel to have full
  functionality for simple cases. An Intel implementation of the
  operation is provided.

  Also fix a small bug in the selftest mock iommu driver probe"

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd:
  iommufd/selftest: Check the bus type during probe
  iommu/vt-d: Add iotlb flush for nested domain
  iommufd: Add data structure for Intel VT-d stage-1 cache invalidation
  iommufd/selftest: Add coverage for IOMMU_HWPT_INVALIDATE ioctl
  iommufd/selftest: Add IOMMU_TEST_OP_MD_CHECK_IOTLB test op
  iommufd/selftest: Add mock_domain_cache_invalidate_user support
  iommu: Add iommu_copy_struct_from_user_array helper
  iommufd: Add IOMMU_HWPT_INVALIDATE
  iommu: Add cache_invalidate_user op

Author: torvalds

drivers/iommu/intel/nested.c

@@ -73,9 +73,97 @@ static void intel_nested_domain_free(struct iommu_domain *domain)
 	kfree(to_dmar_domain(domain));
 }
 
+static void nested_flush_dev_iotlb(struct dmar_domain *domain, u64 addr,
+				   unsigned int mask)
+{
+	struct device_domain_info *info;
+	unsigned long flags;
+	u16 sid, qdep;
+
+	spin_lock_irqsave(&domain->lock, flags);
+	list_for_each_entry(info, &domain->devices, link) {
+		if (!info->ats_enabled)
+			continue;
+		sid = info->bus << 8 | info->devfn;
+		qdep = info->ats_qdep;
+		qi_flush_dev_iotlb(info->iommu, sid, info->pfsid,
+				   qdep, addr, mask);
+		quirk_extra_dev_tlb_flush(info, addr, mask,
+					  IOMMU_NO_PASID, qdep);
+	}
+	spin_unlock_irqrestore(&domain->lock, flags);
+}
+
+static void intel_nested_flush_cache(struct dmar_domain *domain, u64 addr,
+				     unsigned long npages, bool ih)
+{
+	struct iommu_domain_info *info;
+	unsigned int mask;
+	unsigned long i;
+
+	xa_for_each(&domain->iommu_array, i, info)
+		qi_flush_piotlb(info->iommu,
+				domain_id_iommu(domain, info->iommu),
+				IOMMU_NO_PASID, addr, npages, ih);
+
+	if (!domain->has_iotlb_device)
+		return;
+
+	if (npages == U64_MAX)
+		mask = 64 - VTD_PAGE_SHIFT;
+	else
+		mask = ilog2(__roundup_pow_of_two(npages));
+
+	nested_flush_dev_iotlb(domain, addr, mask);
+}
+
+static int intel_nested_cache_invalidate_user(struct iommu_domain *domain,
+					      struct iommu_user_data_array *array)
+{
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+	struct iommu_hwpt_vtd_s1_invalidate inv_entry;
+	u32 index, processed = 0;
+	int ret = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_VTD_S1) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	for (index = 0; index < array->entry_num; index++) {
+		ret = iommu_copy_struct_from_user_array(&inv_entry, array,
+							IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+							index, __reserved);
+		if (ret)
+			break;
+
+		if ((inv_entry.flags & ~IOMMU_VTD_INV_FLAGS_LEAF) ||
+		    inv_entry.__reserved) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		if (!IS_ALIGNED(inv_entry.addr, VTD_PAGE_SIZE) ||
+		    ((inv_entry.npages == U64_MAX) && inv_entry.addr)) {
+			ret = -EINVAL;
+			break;
+		}
+
+		intel_nested_flush_cache(dmar_domain, inv_entry.addr,
+					 inv_entry.npages,
+					 inv_entry.flags & IOMMU_VTD_INV_FLAGS_LEAF);
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return ret;
+}
+
 static const struct iommu_domain_ops intel_nested_domain_ops = {
 	.attach_dev		= intel_nested_attach_dev,
 	.free			= intel_nested_domain_free,
+	.cache_invalidate_user	= intel_nested_cache_invalidate_user,
 };
 
 struct iommu_domain *intel_nested_domain_alloc(struct iommu_domain *parent,

drivers/iommu/iommufd/hw_pagetable.c

@@ -373,3 +373,44 @@ int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
 	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
+
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_invalidate *cmd = ucmd->cmd;
+	struct iommu_user_data_array data_array = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.entry_len = cmd->entry_len,
+		.entry_num = cmd->entry_num,
+	};
+	struct iommufd_hw_pagetable *hwpt;
+	u32 done_num = 0;
+	int rc;
+
+	if (cmd->__reserved) {
+		rc = -EOPNOTSUPP;
+		goto out;
+	}
+
+	if (cmd->entry_num && (!cmd->data_uptr || !cmd->entry_len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt)) {
+		rc = PTR_ERR(hwpt);
+		goto out;
+	}
+
+	rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain,
+						      &data_array);
+	done_num = data_array.entry_num;
+
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+out:
+	cmd->entry_num = done_num;
+	if (iommufd_ucmd_respond(ucmd, sizeof(*cmd)))
+		return -EFAULT;
+	return rc;
+}

drivers/iommu/iommufd/iommufd_private.h

@@ -328,6 +328,15 @@ iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
 					       IOMMUFD_OBJ_HWPT_PAGING),
 			    struct iommufd_hwpt_paging, common.obj);
 }
+
+static inline struct iommufd_hw_pagetable *
+iommufd_get_hwpt_nested(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_NESTED),
+			    struct iommufd_hw_pagetable, obj);
+}
+
 int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
 int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
 
@@ -345,6 +354,7 @@ void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
 void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
 void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)

drivers/iommu/iommufd/iommufd_test.h

@@ -21,6 +21,7 @@ enum {
 	IOMMU_TEST_OP_ACCESS_REPLACE_IOAS,
 	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
 	IOMMU_TEST_OP_DIRTY,
+	IOMMU_TEST_OP_MD_CHECK_IOTLB,
 };
 
 enum {
@@ -121,6 +122,10 @@ struct iommu_test_cmd {
 			__aligned_u64 uptr;
 			__aligned_u64 out_nr_dirty;
 		} dirty;
+		struct {
+			__u32 id;
+			__u32 iotlb;
+		} check_iotlb;
 	};
 	__u32 last;
 };
@@ -148,4 +153,22 @@ struct iommu_hwpt_selftest {
 	__u32 iotlb;
 };
 
+/* Should not be equal to any defined value in enum iommu_hwpt_invalidate_data_type */
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST 0xdeadbeef
+#define IOMMU_HWPT_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef
+
+/**
+ * struct iommu_hwpt_invalidate_selftest - Invalidation data for Mock driver
+ *                                         (IOMMU_HWPT_INVALIDATE_DATA_SELFTEST)
+ * @flags: Invalidate flags
+ * @iotlb_id: Invalidate iotlb entry index
+ *
+ * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @iotlb_id will be ignored
+ */
+struct iommu_hwpt_invalidate_selftest {
+#define IOMMU_TEST_INVALIDATE_FLAG_ALL	(1 << 0)
+	__u32 flags;
+	__u32 iotlb_id;
+};
+
 #endif

drivers/iommu/iommufd/main.c

@@ -322,6 +322,7 @@ union ucmd_buffer {
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_invalidate cache;
 	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
@@ -360,6 +361,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
 		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_INVALIDATE, iommufd_hwpt_invalidate,
+		 struct iommu_hwpt_invalidate, __reserved),
 	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
 		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,

drivers/iommu/iommufd/selftest.c

@@ -25,6 +25,19 @@ static struct iommu_domain_ops domain_nested_ops;
 
 size_t iommufd_test_memory_limit = 65536;
 
+struct mock_bus_type {
+	struct bus_type bus;
+	struct notifier_block nb;
+};
+
+static struct mock_bus_type iommufd_mock_bus_type = {
+	.bus = {
+		.name = "iommufd_mock",
+	},
+};
+
+static atomic_t mock_dev_num;
+
 enum {
 	MOCK_DIRTY_TRACK = 1,
 	MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2,
@@ -437,6 +450,8 @@ static struct iommu_device mock_iommu_device = {
 
 static struct iommu_device *mock_probe_device(struct device *dev)
 {
+	if (dev->bus != &iommufd_mock_bus_type.bus)
+		return ERR_PTR(-ENODEV);
 	return &mock_iommu_device;
 }
 
@@ -473,9 +488,59 @@ static void mock_domain_free_nested(struct iommu_domain *domain)
 	kfree(mock_nested);
 }
 
+static int
+mock_domain_cache_invalidate_user(struct iommu_domain *domain,
+				  struct iommu_user_data_array *array)
+{
+	struct mock_iommu_domain_nested *mock_nested =
+		container_of(domain, struct mock_iommu_domain_nested, domain);
+	struct iommu_hwpt_invalidate_selftest inv;
+	u32 processed = 0;
+	int i = 0, j;
+	int rc = 0;
+
+	if (array->type != IOMMU_HWPT_INVALIDATE_DATA_SELFTEST) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	for ( ; i < array->entry_num; i++) {
+		rc = iommu_copy_struct_from_user_array(&inv, array,
+						       IOMMU_HWPT_INVALIDATE_DATA_SELFTEST,
+						       i, iotlb_id);
+		if (rc)
+			break;
+
+		if (inv.flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			rc = -EOPNOTSUPP;
+			break;
+		}
+
+		if (inv.iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX) {
+			rc = -EINVAL;
+			break;
+		}
+
+		if (inv.flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) {
+			/* Invalidate all mock iotlb entries and ignore iotlb_id */
+			for (j = 0; j < MOCK_NESTED_DOMAIN_IOTLB_NUM; j++)
+				mock_nested->iotlb[j] = 0;
+		} else {
+			mock_nested->iotlb[inv.iotlb_id] = 0;
+		}
+
+		processed++;
+	}
+
+out:
+	array->entry_num = processed;
+	return rc;
+}
+
 static struct iommu_domain_ops domain_nested_ops = {
 	.free = mock_domain_free_nested,
 	.attach_dev = mock_domain_nop_attach,
+	.cache_invalidate_user = mock_domain_cache_invalidate_user,
 };
 
 static inline struct iommufd_hw_pagetable *
@@ -526,19 +591,6 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
 	return hwpt;
 }
 
-struct mock_bus_type {
-	struct bus_type bus;
-	struct notifier_block nb;
-};
-
-static struct mock_bus_type iommufd_mock_bus_type = {
-	.bus = {
-		.name = "iommufd_mock",
-	},
-};
-
-static atomic_t mock_dev_num;
-
 static void mock_dev_release(struct device *dev)
 {
 	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
@@ -793,6 +845,28 @@ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd,
 	return 0;
 }
 
+static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd,
+				       u32 mockpt_id, unsigned int iotlb_id,
+				       u32 iotlb)
+{
+	struct mock_iommu_domain_nested *mock_nested;
+	struct iommufd_hw_pagetable *hwpt;
+	int rc = 0;
+
+	hwpt = get_md_pagetable_nested(ucmd, mockpt_id, &mock_nested);
+	if (IS_ERR(hwpt))
+		return PTR_ERR(hwpt);
+
+	mock_nested = container_of(hwpt->domain,
+				   struct mock_iommu_domain_nested, domain);
+
+	if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX ||
+	    mock_nested->iotlb[iotlb_id] != iotlb)
+		rc = -EINVAL;
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+	return rc;
+}
+
 struct selftest_access {
 	struct iommufd_access *access;
 	struct file *file;
@@ -1274,6 +1348,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 		return iommufd_test_md_check_refs(
 			ucmd, u64_to_user_ptr(cmd->check_refs.uptr),
 			cmd->check_refs.length, cmd->check_refs.refs);
+	case IOMMU_TEST_OP_MD_CHECK_IOTLB:
+		return iommufd_test_md_check_iotlb(ucmd, cmd->id,
+						   cmd->check_iotlb.id,
+						   cmd->check_iotlb.iotlb);
 	case IOMMU_TEST_OP_CREATE_ACCESS:
 		return iommufd_test_create_access(ucmd, cmd->id,
 						  cmd->create_access.flags);