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

2 files changed, 156 insertions, 0 deletions

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 3a556996fea7..1ea2a820e1eb 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -290,6 +290,23 @@ struct iommu_user_data {
 };
 
 /**
+ * struct iommu_user_data_array - iommu driver specific user space data array
+ * @type: The data type of all the entries in the user buffer array
+ * @uptr: Pointer to the user buffer array
+ * @entry_len: The fixed-width length of an entry in the array, in bytes
+ * @entry_num: The number of total entries in the array
+ *
+ * The user buffer includes an array of requests with format defined in
+ * include/uapi/linux/iommufd.h
+ */
+struct iommu_user_data_array {
+	unsigned int type;
+	void __user *uptr;
+	size_t entry_len;
+	u32 entry_num;
+};
+
+/**
  * __iommu_copy_struct_from_user - Copy iommu driver specific user space data
  * @dst_data: Pointer to an iommu driver specific user data that is defined in
  *            include/uapi/linux/iommufd.h
@@ -330,6 +347,57 @@ static inline int __iommu_copy_struct_from_user(
 				      offsetofend(typeof(*kdst), min_last))
 
 /**
+ * __iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                       data from an iommu_user_data_array
+ * @dst_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @src_array: Pointer to a struct iommu_user_data_array for a user space array
+ * @data_type: The data type of the @dst_data. Must match with @src_array.type
+ * @index: Index to the location in the array to copy user data from
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _dst)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int __iommu_copy_struct_from_user_array(
+	void *dst_data, const struct iommu_user_data_array *src_array,
+	unsigned int data_type, unsigned int index, size_t data_len,
+	size_t min_len)
+{
+	struct iommu_user_data src_data;
+
+	if (WARN_ON(!src_array || index >= src_array->entry_num))
+		return -EINVAL;
+	if (!src_array->entry_num)
+		return -EINVAL;
+	src_data.uptr = src_array->uptr + src_array->entry_len * index;
+	src_data.len = src_array->entry_len;
+	src_data.type = src_array->type;
+
+	return __iommu_copy_struct_from_user(dst_data, &src_data, data_type,
+					     data_len, min_len);
+}
+
+/**
+ * iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                     data from an iommu_user_data_array
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @user_array: Pointer to a struct iommu_user_data_array for a user space
+ *              array
+ * @data_type: The data type of the @kdst. Must match with @user_array->type
+ * @index: Index to the location in the array to copy user data from
+ * @min_last: The last member of the data structure @kdst points in the
+ *            initial version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \
+					  min_last)                           \
+	__iommu_copy_struct_from_user_array(                                  \
+		kdst, user_array, data_type, index, sizeof(*(kdst)),          \
+		offsetofend(typeof(*(kdst)), min_last))
+
+/**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
  * @hw_info: report iommu hardware information. The data buffer returned by this
@@ -445,6 +513,13 @@ struct iommu_ops {
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
+ * @cache_invalidate_user: Flush hardware cache for user space IO page table.
+ *                         The @domain must be IOMMU_DOMAIN_NESTED. The @array
+ *                         passes in the cache invalidation requests, in form
+ *                         of a driver data structure. The driver must update
+ *                         array->entry_num to report the number of handled
+ *                         invalidation requests. The driver data structure
+ *                         must be defined in include/uapi/linux/iommufd.h
  * @iova_to_phys: translate iova to physical address
  * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
  *                           including no-snoop TLPs on PCIe or other platform
@@ -470,6 +545,8 @@ struct iommu_domain_ops {
 			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
+	int (*cache_invalidate_user)(struct iommu_domain *domain,
+				     struct iommu_user_data_array *array);
 
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 0b2bc6252e2c..1dfeaa2e649e 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -49,6 +49,7 @@ enum {
 	IOMMUFD_CMD_GET_HW_INFO,
 	IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
+	IOMMUFD_CMD_HWPT_INVALIDATE,
 };
 
 /**
@@ -613,4 +614,82 @@ struct iommu_hwpt_get_dirty_bitmap {
 #define IOMMU_HWPT_GET_DIRTY_BITMAP _IO(IOMMUFD_TYPE, \
 					IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP)
 
+/**
+ * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation
+ *                                        Data Type
+ * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1
+ */
+enum iommu_hwpt_invalidate_data_type {
+	IOMMU_HWPT_INVALIDATE_DATA_VTD_S1,
+};
+
+/**
+ * enum iommu_hwpt_vtd_s1_invalidate_flags - Flags for Intel VT-d
+ *                                           stage-1 cache invalidation
+ * @IOMMU_VTD_INV_FLAGS_LEAF: Indicates whether the invalidation applies
+ *                            to all-levels page structure cache or just
+ *                            the leaf PTE cache.
+ */
+enum iommu_hwpt_vtd_s1_invalidate_flags {
+	IOMMU_VTD_INV_FLAGS_LEAF = 1 << 0,
+};
+
+/**
+ * struct iommu_hwpt_vtd_s1_invalidate - Intel VT-d cache invalidation
+ *                                       (IOMMU_HWPT_INVALIDATE_DATA_VTD_S1)
+ * @addr: The start address of the range to be invalidated. It needs to
+ *        be 4KB aligned.
+ * @npages: Number of contiguous 4K pages to be invalidated.
+ * @flags: Combination of enum iommu_hwpt_vtd_s1_invalidate_flags
+ * @__reserved: Must be 0
+ *
+ * The Intel VT-d specific invalidation data for user-managed stage-1 cache
+ * invalidation in nested translation. Userspace uses this structure to
+ * tell the impacted cache scope after modifying the stage-1 page table.
+ *
+ * Invalidating all the caches related to the page table by setting @addr
+ * to be 0 and @npages to be U64_MAX.
+ *
+ * The device TLB will be invalidated automatically if ATS is enabled.
+ */
+struct iommu_hwpt_vtd_s1_invalidate {
+	__aligned_u64 addr;
+	__aligned_u64 npages;
+	__u32 flags;
+	__u32 __reserved;
+};
+
+/**
+ * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE)
+ * @size: sizeof(struct iommu_hwpt_invalidate)
+ * @hwpt_id: ID of a nested HWPT for cache invalidation
+ * @data_uptr: User pointer to an array of driver-specific cache invalidation
+ *             data.
+ * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data
+ *             type of all the entries in the invalidation request array. It
+ *             should be a type supported by the hwpt pointed by @hwpt_id.
+ * @entry_len: Length (in bytes) of a request entry in the request array
+ * @entry_num: Input the number of cache invalidation requests in the array.
+ *             Output the number of requests successfully handled by kernel.
+ * @__reserved: Must be 0.
+ *
+ * Invalidate the iommu cache for user-managed page table. Modifications on a
+ * user-managed page table should be followed by this operation to sync cache.
+ * Each ioctl can support one or more cache invalidation requests in the array
+ * that has a total size of @entry_len * @entry_num.
+ *
+ * An empty invalidation request array by setting @entry_num==0 is allowed, and
+ * @entry_len and @data_uptr would be ignored in this case. This can be used to
+ * check if the given @data_type is supported or not by kernel.
+ */
+struct iommu_hwpt_invalidate {
+	__u32 size;
+	__u32 hwpt_id;
+	__aligned_u64 data_uptr;
+	__u32 data_type;
+	__u32 entry_len;
+	__u32 entry_num;
+	__u32 __reserved;
+};
+#define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE)
 #endif