[RFC,v4,04/27] header update against 5.2.0-rc1 and IOMMU/VFIO nested stage APIs

diff --git a/linux-headers/linux/iommu.h b/linux-headers/linux/iommu.h
new file mode 100644
index 0000000000..0a59d6439c
--- /dev/null
+++ b/linux-headers/linux/iommu.h
@@ -0,0 +1,280 @@ 
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * IOMMU user API definitions
+ */
+
+#ifndef _IOMMU_H
+#define _IOMMU_H
+
+#include <linux/types.h>
+
+#define IOMMU_FAULT_PERM_READ	(1 << 0) /* read */
+#define IOMMU_FAULT_PERM_WRITE	(1 << 1) /* write */
+#define IOMMU_FAULT_PERM_EXEC	(1 << 2) /* exec */
+#define IOMMU_FAULT_PERM_PRIV	(1 << 3) /* privileged */
+
+/* Generic fault types, can be expanded IRQ remapping fault */
+enum iommu_fault_type {
+	IOMMU_FAULT_DMA_UNRECOV = 1,	/* unrecoverable fault */
+	IOMMU_FAULT_PAGE_REQ,		/* page request fault */
+};
+
+enum iommu_fault_reason {
+	IOMMU_FAULT_REASON_UNKNOWN = 0,
+
+	/* Could not access the PASID table (fetch caused external abort) */
+	IOMMU_FAULT_REASON_PASID_FETCH,
+
+	/* PASID entry is invalid or has configuration errors */
+	IOMMU_FAULT_REASON_BAD_PASID_ENTRY,
+
+	/*
+	 * PASID is out of range (e.g. exceeds the maximum PASID
+	 * supported by the IOMMU) or disabled.
+	 */
+	IOMMU_FAULT_REASON_PASID_INVALID,
+
+	/*
+	 * An external abort occurred fetching (or updating) a translation
+	 * table descriptor
+	 */
+	IOMMU_FAULT_REASON_WALK_EABT,
+
+	/*
+	 * Could not access the page table entry (Bad address),
+	 * actual translation fault
+	 */
+	IOMMU_FAULT_REASON_PTE_FETCH,
+
+	/* Protection flag check failed */
+	IOMMU_FAULT_REASON_PERMISSION,
+
+	/* access flag check failed */
+	IOMMU_FAULT_REASON_ACCESS,
+
+	/* Output address of a translation stage caused Address Size fault */
+	IOMMU_FAULT_REASON_OOR_ADDRESS,
+};
+
+/**
+ * struct iommu_fault_unrecoverable - Unrecoverable fault data
+ * @reason: reason of the fault, from &enum iommu_fault_reason
+ * @flags: parameters of this fault (IOMMU_FAULT_UNRECOV_* values)
+ * @pasid: Process Address Space ID
+ * @perm: Requested permission access using by the incoming transaction
+ *        (IOMMU_FAULT_PERM_* values)
+ * @addr: offending page address
+ * @fetch_addr: address that caused a fetch abort, if any
+ */
+struct iommu_fault_unrecoverable {
+	__u32	reason;
+#define IOMMU_FAULT_UNRECOV_PASID_VALID		(1 << 0)
+#define IOMMU_FAULT_UNRECOV_ADDR_VALID		(1 << 1)
+#define IOMMU_FAULT_UNRECOV_FETCH_ADDR_VALID	(1 << 2)
+	__u32	flags;
+	__u32	pasid;
+	__u32	perm;
+	__u64	addr;
+	__u64	fetch_addr;
+};
+
+/**
+ * struct iommu_fault_page_request - Page Request data
+ * @flags: encodes whether the corresponding fields are valid and whether this
+ *         is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values)
+ * @pasid: Process Address Space ID
+ * @grpid: Page Request Group Index
+ * @perm: requested page permissions (IOMMU_FAULT_PERM_* values)
+ * @addr: page address
+ * @private_data: device-specific private information
+ */
+struct iommu_fault_page_request {
+#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID	(1 << 0)
+#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE	(1 << 1)
+#define IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA	(1 << 2)
+	__u32	flags;
+	__u32	pasid;
+	__u32	grpid;
+	__u32	perm;
+	__u64	addr;
+	__u64	private_data[2];
+};
+
+/**
+ * struct iommu_fault - Generic fault data
+ * @type: fault type from &enum iommu_fault_type
+ * @padding: reserved for future use (should be zero)
+ * @event: Fault event, when @type is %IOMMU_FAULT_DMA_UNRECOV
+ * @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ
+ */
+struct iommu_fault {
+	__u32	type;
+	__u32	padding;
+	union {
+		struct iommu_fault_unrecoverable event;
+		struct iommu_fault_page_request prm;
+	};
+};
+
+/**
+ * struct iommu_pasid_smmuv3 - ARM SMMUv3 Stream Table Entry stage 1 related
+ *     information
+ * @version: API version of this structure
+ * @s1fmt: STE s1fmt (format of the CD table: single CD, linear table
+ *         or 2-level table)
+ * @s1dss: STE s1dss (specifies the behavior when @pasid_bits != 0
+ *         and no PASID is passed along with the incoming transaction)
+ * @padding: reserved for future use (should be zero)
+ *
+ * The PASID table is referred to as the Context Descriptor (CD) table on ARM
+ * SMMUv3. Please refer to the ARM SMMU 3.x spec (ARM IHI 0070A) for full
+ * details.
+ */
+struct iommu_pasid_smmuv3 {
+#define PASID_TABLE_SMMUV3_CFG_VERSION_1 1
+	__u32	version;
+	__u8	s1fmt;
+	__u8	s1dss;
+	__u8	padding[2];
+};
+
+/**
+ * struct iommu_pasid_table_config - PASID table data used to bind guest PASID
+ *     table to the host IOMMU
+ * @version: API version to prepare for future extensions
+ * @format: format of the PASID table
+ * @base_ptr: guest physical address of the PASID table
+ * @pasid_bits: number of PASID bits used in the PASID table
+ * @config: indicates whether the guest translation stage must
+ *          be translated, bypassed or aborted.
+ * @padding: reserved for future use (should be zero)
+ * @smmuv3: table information when @format is %IOMMU_PASID_FORMAT_SMMUV3
+ */
+struct iommu_pasid_table_config {
+#define PASID_TABLE_CFG_VERSION_1 1
+	__u32	version;
+#define IOMMU_PASID_FORMAT_SMMUV3	1
+	__u32	format;
+	__u64	base_ptr;
+	__u8	pasid_bits;
+#define IOMMU_PASID_CONFIG_TRANSLATE	1
+#define IOMMU_PASID_CONFIG_BYPASS	2
+#define IOMMU_PASID_CONFIG_ABORT	3
+	__u8	config;
+	__u8    padding[6];
+	union {
+		struct iommu_pasid_smmuv3 smmuv3;
+	};
+};
+
+/* defines the granularity of the invalidation */
+enum iommu_inv_granularity {
+	IOMMU_INV_GRANU_DOMAIN,	/* domain-selective invalidation */
+	IOMMU_INV_GRANU_PASID,	/* PASID-selective invalidation */
+	IOMMU_INV_GRANU_ADDR,	/* page-selective invalidation */
+	IOMMU_INV_GRANU_NR,	/* number of invalidation granularities */
+};
+
+/**
+ * struct iommu_inv_addr_info - Address Selective Invalidation Structure
+ *
+ * @flags: indicates the granularity of the address-selective invalidation
+ * - If the PASID bit is set, the @pasid field is populated and the invalidation
+ *   relates to cache entries tagged with this PASID and matching the address
+ *   range.
+ * - If ARCHID bit is set, @archid is populated and the invalidation relates
+ *   to cache entries tagged with this architecture specific ID and matching
+ *   the address range.
+ * - Both PASID and ARCHID can be set as they may tag different caches.
+ * - If neither PASID or ARCHID is set, global addr invalidation applies.
+ * - The LEAF flag indicates whether only the leaf PTE caching needs to be
+ *   invalidated and other paging structure caches can be preserved.
+ * @pasid: process address space ID
+ * @archid: architecture-specific ID
+ * @addr: first stage/level input address
+ * @granule_size: page/block size of the mapping in bytes
+ * @nb_granules: number of contiguous granules to be invalidated
+ */
+struct iommu_inv_addr_info {
+#define IOMMU_INV_ADDR_FLAGS_PASID	(1 << 0)
+#define IOMMU_INV_ADDR_FLAGS_ARCHID	(1 << 1)
+#define IOMMU_INV_ADDR_FLAGS_LEAF	(1 << 2)
+	__u32	flags;
+	__u32	archid;
+	__u64	pasid;
+	__u64	addr;
+	__u64	granule_size;
+	__u64	nb_granules;
+};
+
+/**
+ * struct iommu_inv_pasid_info - PASID Selective Invalidation Structure
+ *
+ * @flags: indicates the granularity of the PASID-selective invalidation
+ * - If the PASID bit is set, the @pasid field is populated and the invalidation
+ *   relates to cache entries tagged with this PASID and matching the address
+ *   range.
+ * - If the ARCHID bit is set, the @archid is populated and the invalidation
+ *   relates to cache entries tagged with this architecture specific ID and
+ *   matching the address range.
+ * - Both PASID and ARCHID can be set as they may tag different caches.
+ * - At least one of PASID or ARCHID must be set.
+ * @pasid: process address space ID
+ * @archid: architecture-specific ID
+ */
+struct iommu_inv_pasid_info {
+#define IOMMU_INV_PASID_FLAGS_PASID	(1 << 0)
+#define IOMMU_INV_PASID_FLAGS_ARCHID	(1 << 1)
+	__u32	flags;
+	__u32	archid;
+	__u64	pasid;
+};
+
+/**
+ * struct iommu_cache_invalidate_info - First level/stage invalidation
+ *     information
+ * @version: API version of this structure
+ * @cache: bitfield that allows to select which caches to invalidate
+ * @granularity: defines the lowest granularity used for the invalidation:
+ *     domain > PASID > addr
+ * @padding: reserved for future use (should be zero)
+ * @pasid_info: invalidation data when @granularity is %IOMMU_INV_GRANU_PASID
+ * @addr_info: invalidation data when @granularity is %IOMMU_INV_GRANU_ADDR
+ *
+ * Not all the combinations of cache/granularity are valid:
+ *
+ * +--------------+---------------+---------------+---------------+
+ * | type /       |   DEV_IOTLB   |     IOTLB     |      PASID    |
+ * | granularity  |               |               |      cache    |
+ * +==============+===============+===============+===============+
+ * | DOMAIN       |       N/A     |       Y       |       Y       |
+ * +--------------+---------------+---------------+---------------+
+ * | PASID        |       Y       |       Y       |       Y       |
+ * +--------------+---------------+---------------+---------------+
+ * | ADDR         |       Y       |       Y       |       N/A     |
+ * +--------------+---------------+---------------+---------------+
+ *
+ * Invalidations by %IOMMU_INV_GRANU_DOMAIN don't take any argument other than
+ * @version and @cache.
+ *
+ * If multiple cache types are invalidated simultaneously, they all
+ * must support the used granularity.
+ */
+struct iommu_cache_invalidate_info {
+#define IOMMU_CACHE_INVALIDATE_INFO_VERSION_1 1
+	__u32	version;
+/* IOMMU paging structure cache */
+#define IOMMU_CACHE_INV_TYPE_IOTLB	(1 << 0) /* IOMMU IOTLB */
+#define IOMMU_CACHE_INV_TYPE_DEV_IOTLB	(1 << 1) /* Device IOTLB */
+#define IOMMU_CACHE_INV_TYPE_PASID	(1 << 2) /* PASID cache */
+#define IOMMU_CACHE_INV_TYPE_NR		(3)
+	__u8	cache;
+	__u8	granularity;
+	__u8	padding[2];
+	union {
+		struct iommu_inv_pasid_info pasid_info;
+		struct iommu_inv_addr_info addr_info;
+	};
+};
+
+#endif /* _IOMMU_H */
diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h
index 24f505199f..f8e355896c 100644
--- a/linux-headers/linux/vfio.h
+++ b/linux-headers/linux/vfio.h
@@ -14,6 +14,7 @@ 
 
 #include <linux/types.h>
 #include <linux/ioctl.h>
+#include <linux/iommu.h>
 
 #define VFIO_API_VERSION	0
 
@@ -306,6 +307,10 @@  struct vfio_region_info_cap_type {
 #define VFIO_REGION_TYPE_GFX                    (1)
 #define VFIO_REGION_SUBTYPE_GFX_EDID            (1)
 
+#define VFIO_REGION_TYPE_NESTED			(2)
+#define VFIO_REGION_SUBTYPE_NESTED_FAULT_PROD	(1)
+#define VFIO_REGION_SUBTYPE_NESTED_FAULT_CONS	(2)
+
 /**
  * struct vfio_region_gfx_edid - EDID region layout.
  *
@@ -554,6 +559,7 @@  enum {
 	VFIO_PCI_MSIX_IRQ_INDEX,
 	VFIO_PCI_ERR_IRQ_INDEX,
 	VFIO_PCI_REQ_IRQ_INDEX,
+	VFIO_PCI_DMA_FAULT_IRQ_INDEX,
 	VFIO_PCI_NUM_IRQS
 };
 
@@ -700,6 +706,44 @@  struct vfio_device_ioeventfd {
 
 #define VFIO_DEVICE_IOEVENTFD		_IO(VFIO_TYPE, VFIO_BASE + 16)
 
+
+/*
+ * Capability exposed by the Producer Fault Region
+ * @version: max fault ABI version supported by the kernel
+ */
+#define VFIO_REGION_INFO_CAP_PRODUCER_FAULT	6
+
+struct vfio_region_info_cap_fault {
+	struct vfio_info_cap_header header;
+	__u32 version;
+};
+
+/*
+ * Producer Fault Region (Read-Only from user space perspective)
+ * Contains the fault circular buffer and the producer index
+ * @version: version of the fault record uapi
+ * @entry_size: size of each fault record
+ * @offset: offset of the start of the queue
+ * @prod: producer index relative to the start of the queue
+ */
+struct vfio_region_fault_prod {
+	__u32   version;
+	__u32	nb_entries;
+	__u32   entry_size;
+	__u32	offset;
+	__u32   prod;
+};
+
+/*
+ * Consumer Fault Region (Write-Only from the user space perspective)
+ * @version: ABI version requested by the userspace
+ * @cons: consumer index relative to the start of the queue
+ */
+struct vfio_region_fault_cons {
+	__u32 version;
+	__u32 cons;
+};
+
 /* -------- API for Type1 VFIO IOMMU -------- */
 
 /**
@@ -763,6 +807,69 @@  struct vfio_iommu_type1_dma_unmap {
 #define VFIO_IOMMU_ENABLE	_IO(VFIO_TYPE, VFIO_BASE + 15)
 #define VFIO_IOMMU_DISABLE	_IO(VFIO_TYPE, VFIO_BASE + 16)
 
+/**
+ * VFIO_IOMMU_ATTACH_PASID_TABLE - _IOWR(VFIO_TYPE, VFIO_BASE + 22,
+ *			struct vfio_iommu_type1_attach_pasid_table)
+ *
+ * Passes the PASID table to the host. Calling ATTACH_PASID_TABLE
+ * while a table is already installed is allowed: it replaces the old
+ * table. DETACH does a comprehensive tear down of the nested mode.
+ */
+struct vfio_iommu_type1_attach_pasid_table {
+	__u32	argsz;
+	__u32	flags;
+	struct iommu_pasid_table_config config;
+};
+#define VFIO_IOMMU_ATTACH_PASID_TABLE	_IO(VFIO_TYPE, VFIO_BASE + 22)
+
+/**
+ * VFIO_IOMMU_DETACH_PASID_TABLE - - _IOWR(VFIO_TYPE, VFIO_BASE + 23)
+ * Detaches the PASID table
+ */
+#define VFIO_IOMMU_DETACH_PASID_TABLE	_IO(VFIO_TYPE, VFIO_BASE + 23)
+
+/**
+ * VFIO_IOMMU_CACHE_INVALIDATE - _IOWR(VFIO_TYPE, VFIO_BASE + 24,
+ *			struct vfio_iommu_type1_cache_invalidate)
+ *
+ * Propagate guest IOMMU cache invalidation to the host.
+ */
+struct vfio_iommu_type1_cache_invalidate {
+	__u32   argsz;
+	__u32   flags;
+	struct iommu_cache_invalidate_info info;
+};
+#define VFIO_IOMMU_CACHE_INVALIDATE      _IO(VFIO_TYPE, VFIO_BASE + 24)
+
+/**
+ * VFIO_IOMMU_BIND_MSI - _IOWR(VFIO_TYPE, VFIO_BASE + 25,
+ *			struct vfio_iommu_type1_bind_msi)
+ *
+ * Pass a stage 1 MSI doorbell mapping to the host so that this
+ * latter can build a nested stage2 mapping
+ */
+struct vfio_iommu_type1_bind_msi {
+	__u32   argsz;
+	__u32   flags;
+	__u64	iova;
+	__u64	gpa;
+	__u64	size;
+};
+#define VFIO_IOMMU_BIND_MSI      _IO(VFIO_TYPE, VFIO_BASE + 25)
+
+/**
+ * VFIO_IOMMU_UNBIND_MSI - _IOWR(VFIO_TYPE, VFIO_BASE + 26,
+ *			struct vfio_iommu_type1_unbind_msi)
+ *
+ * Unregister an MSI mapping
+ */
+struct vfio_iommu_type1_unbind_msi {
+	__u32   argsz;
+	__u32   flags;
+	__u64	iova;
+};
+#define VFIO_IOMMU_UNBIND_MSI      _IO(VFIO_TYPE, VFIO_BASE + 26)
+
 /* -------- Additional API for SPAPR TCE (Server POWERPC) IOMMU -------- */
 
 /*