Merge tag 'drm-xe-next-2023-12-21-pr1-1' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Introduce a new DRM driver for Intel GPUs

Xe, is a new driver for Intel GPUs that supports both integrated and
discrete platforms. The experimental support starts with Tiger Lake.
i915 will continue be the main production driver for the platforms
up to Meteor Lake and Alchemist. Then the goal is to make this Intel
Xe driver the primary driver for Lunar Lake and newer platforms.

It uses most, if not all, of the key drm concepts, in special: TTM,
drm-scheduler, drm-exec, drm-gpuvm/gpuva and others.

Signed-off-by: Dave Airlie <airlied@redhat.com>

[airlied: add an extra X86 check, fix a typo, fix drm_exec_init interface
change].

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ZYSwLgXZUZ57qGPQ@intel.com

3 files changed, 1547 insertions, 0 deletions

diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h
index f893d9c9b641..0f9c73d2e70e 100644
--- a/include/drm/drm_gpuvm.h
+++ b/include/drm/drm_gpuvm.h
@@ -1008,6 +1008,16 @@ struct drm_gpuva_ops {
 	list_for_each_entry_from_reverse(op, &(ops)->list, entry)
 
 /**
+ * drm_gpuva_for_each_op_reverse - iterator to walk over &drm_gpuva_ops in reverse
+ * @op: &drm_gpuva_op to assign in each iteration step
+ * @ops: &drm_gpuva_ops to walk
+ *
+ * This iterator walks over all ops within a given list of operations in reverse
+ */
+#define drm_gpuva_for_each_op_reverse(op, ops) \
+	list_for_each_entry_reverse(op, &(ops)->list, entry)
+
+/**
  * drm_gpuva_first_op() - returns the first &drm_gpuva_op from &drm_gpuva_ops
  * @ops: the &drm_gpuva_ops to get the fist &drm_gpuva_op from
  */
diff --git a/include/drm/xe_pciids.h b/include/drm/xe_pciids.h
new file mode 100644
index 000000000000..de1a344737bc
--- /dev/null
+++ b/include/drm/xe_pciids.h
@@ -0,0 +1,190 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2022 Intel Corporation
+ */
+
+#ifndef _XE_PCIIDS_H_
+#define _XE_PCIIDS_H_
+
+/*
+ * Lists below can be turned into initializers for a struct pci_device_id
+ * by defining INTEL_VGA_DEVICE:
+ *
+ * #define INTEL_VGA_DEVICE(id, info) { \
+ *	0x8086, id,			\
+ *	~0, ~0,				\
+ *	0x030000, 0xff0000,		\
+ *	(unsigned long) info }
+ *
+ * And then calling like:
+ *
+ * XE_TGL_12_GT1_IDS(INTEL_VGA_DEVICE, ## __VA_ARGS__)
+ *
+ * To turn them into something else, just provide a different macro passed as
+ * first argument.
+ */
+
+/* TGL */
+#define XE_TGL_GT1_IDS(MACRO__, ...)		\
+	MACRO__(0x9A60, ## __VA_ARGS__),	\
+	MACRO__(0x9A68, ## __VA_ARGS__),	\
+	MACRO__(0x9A70, ## __VA_ARGS__)
+
+#define XE_TGL_GT2_IDS(MACRO__, ...)		\
+	MACRO__(0x9A40, ## __VA_ARGS__),	\
+	MACRO__(0x9A49, ## __VA_ARGS__),	\
+	MACRO__(0x9A59, ## __VA_ARGS__),	\
+	MACRO__(0x9A78, ## __VA_ARGS__),	\
+	MACRO__(0x9AC0, ## __VA_ARGS__),	\
+	MACRO__(0x9AC9, ## __VA_ARGS__),	\
+	MACRO__(0x9AD9, ## __VA_ARGS__),	\
+	MACRO__(0x9AF8, ## __VA_ARGS__)
+
+#define XE_TGL_IDS(MACRO__, ...)		\
+	XE_TGL_GT1_IDS(MACRO__, ## __VA_ARGS__),\
+	XE_TGL_GT2_IDS(MACRO__, ## __VA_ARGS__)
+
+/* RKL */
+#define XE_RKL_IDS(MACRO__, ...)		\
+	MACRO__(0x4C80, ## __VA_ARGS__),	\
+	MACRO__(0x4C8A, ## __VA_ARGS__),	\
+	MACRO__(0x4C8B, ## __VA_ARGS__),	\
+	MACRO__(0x4C8C, ## __VA_ARGS__),	\
+	MACRO__(0x4C90, ## __VA_ARGS__),	\
+	MACRO__(0x4C9A, ## __VA_ARGS__)
+
+/* DG1 */
+#define XE_DG1_IDS(MACRO__, ...)		\
+	MACRO__(0x4905, ## __VA_ARGS__),	\
+	MACRO__(0x4906, ## __VA_ARGS__),	\
+	MACRO__(0x4907, ## __VA_ARGS__),	\
+	MACRO__(0x4908, ## __VA_ARGS__),	\
+	MACRO__(0x4909, ## __VA_ARGS__)
+
+/* ADL-S */
+#define XE_ADLS_IDS(MACRO__, ...)		\
+	MACRO__(0x4680, ## __VA_ARGS__),	\
+	MACRO__(0x4682, ## __VA_ARGS__),	\
+	MACRO__(0x4688, ## __VA_ARGS__),	\
+	MACRO__(0x468A, ## __VA_ARGS__),	\
+	MACRO__(0x468B, ## __VA_ARGS__),	\
+	MACRO__(0x4690, ## __VA_ARGS__),	\
+	MACRO__(0x4692, ## __VA_ARGS__),	\
+	MACRO__(0x4693, ## __VA_ARGS__)
+
+/* ADL-P */
+#define XE_ADLP_IDS(MACRO__, ...)		\
+	MACRO__(0x46A0, ## __VA_ARGS__),	\
+	MACRO__(0x46A1, ## __VA_ARGS__),	\
+	MACRO__(0x46A2, ## __VA_ARGS__),	\
+	MACRO__(0x46A3, ## __VA_ARGS__),	\
+	MACRO__(0x46A6, ## __VA_ARGS__),	\
+	MACRO__(0x46A8, ## __VA_ARGS__),	\
+	MACRO__(0x46AA, ## __VA_ARGS__),	\
+	MACRO__(0x462A, ## __VA_ARGS__),	\
+	MACRO__(0x4626, ## __VA_ARGS__),	\
+	MACRO__(0x4628, ## __VA_ARGS__),	\
+	MACRO__(0x46B0, ## __VA_ARGS__),	\
+	MACRO__(0x46B1, ## __VA_ARGS__),	\
+	MACRO__(0x46B2, ## __VA_ARGS__),	\
+	MACRO__(0x46B3, ## __VA_ARGS__),	\
+	MACRO__(0x46C0, ## __VA_ARGS__),	\
+	MACRO__(0x46C1, ## __VA_ARGS__),	\
+	MACRO__(0x46C2, ## __VA_ARGS__),	\
+	MACRO__(0x46C3, ## __VA_ARGS__)
+
+/* ADL-N */
+#define XE_ADLN_IDS(MACRO__, ...)		\
+	MACRO__(0x46D0, ## __VA_ARGS__),	\
+	MACRO__(0x46D1, ## __VA_ARGS__),	\
+	MACRO__(0x46D2, ## __VA_ARGS__)
+
+/* RPL-S */
+#define XE_RPLS_IDS(MACRO__, ...)		\
+	MACRO__(0xA780, ## __VA_ARGS__),	\
+	MACRO__(0xA781, ## __VA_ARGS__),	\
+	MACRO__(0xA782, ## __VA_ARGS__),	\
+	MACRO__(0xA783, ## __VA_ARGS__),	\
+	MACRO__(0xA788, ## __VA_ARGS__),	\
+	MACRO__(0xA789, ## __VA_ARGS__),	\
+	MACRO__(0xA78A, ## __VA_ARGS__),	\
+	MACRO__(0xA78B, ## __VA_ARGS__)
+
+/* RPL-U */
+#define XE_RPLU_IDS(MACRO__, ...)		\
+	MACRO__(0xA721, ## __VA_ARGS__),	\
+	MACRO__(0xA7A1, ## __VA_ARGS__),	\
+	MACRO__(0xA7A9, ## __VA_ARGS__),	\
+	MACRO__(0xA7AC, ## __VA_ARGS__),	\
+	MACRO__(0xA7AD, ## __VA_ARGS__)
+
+/* RPL-P */
+#define XE_RPLP_IDS(MACRO__, ...)		\
+	XE_RPLU_IDS(MACRO__, ## __VA_ARGS__),	\
+	MACRO__(0xA720, ## __VA_ARGS__),	\
+	MACRO__(0xA7A0, ## __VA_ARGS__),	\
+	MACRO__(0xA7A8, ## __VA_ARGS__),	\
+	MACRO__(0xA7AA, ## __VA_ARGS__),	\
+	MACRO__(0xA7AB, ## __VA_ARGS__)
+
+/* DG2 */
+#define XE_DG2_G10_IDS(MACRO__, ...)		\
+	MACRO__(0x5690, ## __VA_ARGS__),	\
+	MACRO__(0x5691, ## __VA_ARGS__),	\
+	MACRO__(0x5692, ## __VA_ARGS__),	\
+	MACRO__(0x56A0, ## __VA_ARGS__),	\
+	MACRO__(0x56A1, ## __VA_ARGS__),	\
+	MACRO__(0x56A2, ## __VA_ARGS__)
+
+#define XE_DG2_G11_IDS(MACRO__, ...)		\
+	MACRO__(0x5693, ## __VA_ARGS__),	\
+	MACRO__(0x5694, ## __VA_ARGS__),	\
+	MACRO__(0x5695, ## __VA_ARGS__),	\
+	MACRO__(0x56A5, ## __VA_ARGS__),	\
+	MACRO__(0x56A6, ## __VA_ARGS__),	\
+	MACRO__(0x56B0, ## __VA_ARGS__),	\
+	MACRO__(0x56B1, ## __VA_ARGS__),	\
+	MACRO__(0x56BA, ## __VA_ARGS__),	\
+	MACRO__(0x56BB, ## __VA_ARGS__),	\
+	MACRO__(0x56BC, ## __VA_ARGS__),	\
+	MACRO__(0x56BD, ## __VA_ARGS__)
+
+#define XE_DG2_G12_IDS(MACRO__, ...)		\
+	MACRO__(0x5696, ## __VA_ARGS__),	\
+	MACRO__(0x5697, ## __VA_ARGS__),	\
+	MACRO__(0x56A3, ## __VA_ARGS__),	\
+	MACRO__(0x56A4, ## __VA_ARGS__),	\
+	MACRO__(0x56B2, ## __VA_ARGS__),	\
+	MACRO__(0x56B3, ## __VA_ARGS__)
+
+#define XE_DG2_IDS(MACRO__, ...)		\
+	XE_DG2_G10_IDS(MACRO__, ## __VA_ARGS__),\
+	XE_DG2_G11_IDS(MACRO__, ## __VA_ARGS__),\
+	XE_DG2_G12_IDS(MACRO__, ## __VA_ARGS__)
+
+#define XE_ATS_M150_IDS(MACRO__, ...)		\
+	MACRO__(0x56C0, ## __VA_ARGS__),	\
+	MACRO__(0x56C2, ## __VA_ARGS__)
+
+#define XE_ATS_M75_IDS(MACRO__, ...)		\
+	MACRO__(0x56C1, ## __VA_ARGS__)
+
+#define XE_ATS_M_IDS(MACRO__, ...)		\
+	XE_ATS_M150_IDS(MACRO__, ## __VA_ARGS__),\
+	XE_ATS_M75_IDS(MACRO__, ## __VA_ARGS__)
+
+/* MTL / ARL */
+#define XE_MTL_IDS(MACRO__, ...)		\
+	MACRO__(0x7D40, ## __VA_ARGS__),	\
+	MACRO__(0x7D45, ## __VA_ARGS__),	\
+	MACRO__(0x7D55, ## __VA_ARGS__),	\
+	MACRO__(0x7D60, ## __VA_ARGS__),	\
+	MACRO__(0x7D67, ## __VA_ARGS__),	\
+	MACRO__(0x7DD5, ## __VA_ARGS__)
+
+#define XE_LNL_IDS(MACRO__, ...) \
+	MACRO__(0x6420, ## __VA_ARGS__), \
+	MACRO__(0x64A0, ## __VA_ARGS__), \
+	MACRO__(0x64B0, ## __VA_ARGS__)
+
+#endif
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
new file mode 100644
index 000000000000..9fa3ae324731
--- /dev/null
+++ b/include/uapi/drm/xe_drm.h
@@ -0,0 +1,1347 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2023 Intel Corporation
+ */
+
+#ifndef _UAPI_XE_DRM_H_
+#define _UAPI_XE_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/*
+ * Please note that modifications to all structs defined here are
+ * subject to backwards-compatibility constraints.
+ * Sections in this file are organized as follows:
+ *   1. IOCTL definition
+ *   2. Extension definition and helper structs
+ *   3. IOCTL's Query structs in the order of the Query's entries.
+ *   4. The rest of IOCTL structs in the order of IOCTL declaration.
+ */
+
+/**
+ * DOC: Xe Device Block Diagram
+ *
+ * The diagram below represents a high-level simplification of a discrete
+ * GPU supported by the Xe driver. It shows some device components which
+ * are necessary to understand this API, as well as how their relations
+ * to each other. This diagram does not represent real hardware::
+ *
+ *   ┌──────────────────────────────────────────────────────────────────┐
+ *   │ ┌──────────────────────────────────────────────────┐ ┌─────────┐ │
+ *   │ │        ┌───────────────────────┐   ┌─────┐       │ │ ┌─────┐ │ │
+ *   │ │        │         VRAM0         ├───┤ ... │       │ │ │VRAM1│ │ │
+ *   │ │        └───────────┬───────────┘   └─GT1─┘       │ │ └──┬──┘ │ │
+ *   │ │ ┌──────────────────┴───────────────────────────┐ │ │ ┌──┴──┐ │ │
+ *   │ │ │ ┌─────────────────────┐  ┌─────────────────┐ │ │ │ │     │ │ │
+ *   │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │  │ ┌─────┐ ┌─────┐ │ │ │ │ │     │ │ │
+ *   │ │ │ │ │EU│ │EU│ │EU│ │EU│ │  │ │RCS0 │ │BCS0 │ │ │ │ │ │     │ │ │
+ *   │ │ │ │ └──┘ └──┘ └──┘ └──┘ │  │ └─────┘ └─────┘ │ │ │ │ │     │ │ │
+ *   │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │  │ ┌─────┐ ┌─────┐ │ │ │ │ │     │ │ │
+ *   │ │ │ │ │EU│ │EU│ │EU│ │EU│ │  │ │VCS0 │ │VCS1 │ │ │ │ │ │     │ │ │
+ *   │ │ │ │ └──┘ └──┘ └──┘ └──┘ │  │ └─────┘ └─────┘ │ │ │ │ │     │ │ │
+ *   │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │  │ ┌─────┐ ┌─────┐ │ │ │ │ │     │ │ │
+ *   │ │ │ │ │EU│ │EU│ │EU│ │EU│ │  │ │VECS0│ │VECS1│ │ │ │ │ │ ... │ │ │
+ *   │ │ │ │ └──┘ └──┘ └──┘ └──┘ │  │ └─────┘ └─────┘ │ │ │ │ │     │ │ │
+ *   │ │ │ │ ┌──┐ ┌──┐ ┌──┐ ┌──┐ │  │ ┌─────┐ ┌─────┐ │ │ │ │ │     │ │ │
+ *   │ │ │ │ │EU│ │EU│ │EU│ │EU│ │  │ │CCS0 │ │CCS1 │ │ │ │ │ │     │ │ │
+ *   │ │ │ │ └──┘ └──┘ └──┘ └──┘ │  │ └─────┘ └─────┘ │ │ │ │ │     │ │ │
+ *   │ │ │ └─────────DSS─────────┘  │ ┌─────┐ ┌─────┐ │ │ │ │ │     │ │ │
+ *   │ │ │                          │ │CCS2 │ │CCS3 │ │ │ │ │ │     │ │ │
+ *   │ │ │ ┌─────┐ ┌─────┐ ┌─────┐  │ └─────┘ └─────┘ │ │ │ │ │     │ │ │
+ *   │ │ │ │ ... │ │ ... │ │ ... │  │                 │ │ │ │ │     │ │ │
+ *   │ │ │ └─DSS─┘ └─DSS─┘ └─DSS─┘  └─────Engines─────┘ │ │ │ │     │ │ │
+ *   │ │ └───────────────────────────GT0────────────────┘ │ │ └─GT2─┘ │ │
+ *   │ └────────────────────────────Tile0─────────────────┘ └─ Tile1──┘ │
+ *   └─────────────────────────────Device0───────┬──────────────────────┘
+ *                                               │
+ *                        ───────────────────────┴────────── PCI bus
+ */
+
+/**
+ * DOC: Xe uAPI Overview
+ *
+ * This section aims to describe the Xe's IOCTL entries, its structs, and other
+ * Xe related uAPI such as uevents and PMU (Platform Monitoring Unit) related
+ * entries and usage.
+ *
+ * List of supported IOCTLs:
+ *  - &DRM_IOCTL_XE_DEVICE_QUERY
+ *  - &DRM_IOCTL_XE_GEM_CREATE
+ *  - &DRM_IOCTL_XE_GEM_MMAP_OFFSET
+ *  - &DRM_IOCTL_XE_VM_CREATE
+ *  - &DRM_IOCTL_XE_VM_DESTROY
+ *  - &DRM_IOCTL_XE_VM_BIND
+ *  - &DRM_IOCTL_XE_EXEC_QUEUE_CREATE
+ *  - &DRM_IOCTL_XE_EXEC_QUEUE_DESTROY
+ *  - &DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY
+ *  - &DRM_IOCTL_XE_EXEC
+ *  - &DRM_IOCTL_XE_WAIT_USER_FENCE
+ */
+
+/*
+ * xe specific ioctls.
+ *
+ * The device specific ioctl range is [DRM_COMMAND_BASE, DRM_COMMAND_END) ie
+ * [0x40, 0xa0) (a0 is excluded). The numbers below are defined as offset
+ * against DRM_COMMAND_BASE and should be between [0x0, 0x60).
+ */
+#define DRM_XE_DEVICE_QUERY		0x00
+#define DRM_XE_GEM_CREATE		0x01
+#define DRM_XE_GEM_MMAP_OFFSET		0x02
+#define DRM_XE_VM_CREATE		0x03
+#define DRM_XE_VM_DESTROY		0x04
+#define DRM_XE_VM_BIND			0x05
+#define DRM_XE_EXEC_QUEUE_CREATE	0x06
+#define DRM_XE_EXEC_QUEUE_DESTROY	0x07
+#define DRM_XE_EXEC_QUEUE_GET_PROPERTY	0x08
+#define DRM_XE_EXEC			0x09
+#define DRM_XE_WAIT_USER_FENCE		0x0a
+/* Must be kept compact -- no holes */
+
+#define DRM_IOCTL_XE_DEVICE_QUERY		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_DEVICE_QUERY, struct drm_xe_device_query)
+#define DRM_IOCTL_XE_GEM_CREATE			DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_GEM_CREATE, struct drm_xe_gem_create)
+#define DRM_IOCTL_XE_GEM_MMAP_OFFSET		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_GEM_MMAP_OFFSET, struct drm_xe_gem_mmap_offset)
+#define DRM_IOCTL_XE_VM_CREATE			DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_CREATE, struct drm_xe_vm_create)
+#define DRM_IOCTL_XE_VM_DESTROY			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_VM_DESTROY, struct drm_xe_vm_destroy)
+#define DRM_IOCTL_XE_VM_BIND			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_VM_BIND, struct drm_xe_vm_bind)
+#define DRM_IOCTL_XE_EXEC_QUEUE_CREATE		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_CREATE, struct drm_xe_exec_queue_create)
+#define DRM_IOCTL_XE_EXEC_QUEUE_DESTROY		DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_DESTROY, struct drm_xe_exec_queue_destroy)
+#define DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY	DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_GET_PROPERTY, struct drm_xe_exec_queue_get_property)
+#define DRM_IOCTL_XE_EXEC			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC, struct drm_xe_exec)
+#define DRM_IOCTL_XE_WAIT_USER_FENCE		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_WAIT_USER_FENCE, struct drm_xe_wait_user_fence)
+
+/**
+ * DOC: Xe IOCTL Extensions
+ *
+ * Before detailing the IOCTLs and its structs, it is important to highlight
+ * that every IOCTL in Xe is extensible.
+ *
+ * Many interfaces need to grow over time. In most cases we can simply
+ * extend the struct and have userspace pass in more data. Another option,
+ * as demonstrated by Vulkan's approach to providing extensions for forward
+ * and backward compatibility, is to use a list of optional structs to
+ * provide those extra details.
+ *
+ * The key advantage to using an extension chain is that it allows us to
+ * redefine the interface more easily than an ever growing struct of
+ * increasing complexity, and for large parts of that interface to be
+ * entirely optional. The downside is more pointer chasing; chasing across
+ * the __user boundary with pointers encapsulated inside u64.
+ *
+ * Example chaining:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_xe_user_extension ext3 {
+ *		.next_extension = 0, // end
+ *		.name = ...,
+ *	};
+ *	struct drm_xe_user_extension ext2 {
+ *		.next_extension = (uintptr_t)&ext3,
+ *		.name = ...,
+ *	};
+ *	struct drm_xe_user_extension ext1 {
+ *		.next_extension = (uintptr_t)&ext2,
+ *		.name = ...,
+ *	};
+ *
+ * Typically the struct drm_xe_user_extension would be embedded in some uAPI
+ * struct, and in this case we would feed it the head of the chain(i.e ext1),
+ * which would then apply all of the above extensions.
+*/
+
+/**
+ * struct drm_xe_user_extension - Base class for defining a chain of extensions
+ */
+struct drm_xe_user_extension {
+	/**
+	 * @next_extension:
+	 *
+	 * Pointer to the next struct drm_xe_user_extension, or zero if the end.
+	 */
+	__u64 next_extension;
+
+	/**
+	 * @name: Name of the extension.
+	 *
+	 * Note that the name here is just some integer.
+	 *
+	 * Also note that the name space for this is not global for the whole
+	 * driver, but rather its scope/meaning is limited to the specific piece
+	 * of uAPI which has embedded the struct drm_xe_user_extension.
+	 */
+	__u32 name;
+
+	/**
+	 * @pad: MBZ
+	 *
+	 * All undefined bits must be zero.
+	 */
+	__u32 pad;
+};
+
+/**
+ * struct drm_xe_ext_set_property - Generic set property extension
+ *
+ * A generic struct that allows any of the Xe's IOCTL to be extended
+ * with a set_property operation.
+ */
+struct drm_xe_ext_set_property {
+	/** @base: base user extension */
+	struct drm_xe_user_extension base;
+
+	/** @property: property to set */
+	__u32 property;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @value: property value */
+	__u64 value;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_engine_class_instance - instance of an engine class
+ *
+ * It is returned as part of the @drm_xe_engine, but it also is used as
+ * the input of engine selection for both @drm_xe_exec_queue_create and
+ * @drm_xe_query_engine_cycles
+ *
+ * The @engine_class can be:
+ *  - %DRM_XE_ENGINE_CLASS_RENDER
+ *  - %DRM_XE_ENGINE_CLASS_COPY
+ *  - %DRM_XE_ENGINE_CLASS_VIDEO_DECODE
+ *  - %DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE
+ *  - %DRM_XE_ENGINE_CLASS_COMPUTE
+ *  - %DRM_XE_ENGINE_CLASS_VM_BIND - Kernel only classes (not actual
+ *    hardware engine class). Used for creating ordered queues of VM
+ *    bind operations.
+ */
+struct drm_xe_engine_class_instance {
+#define DRM_XE_ENGINE_CLASS_RENDER		0
+#define DRM_XE_ENGINE_CLASS_COPY		1
+#define DRM_XE_ENGINE_CLASS_VIDEO_DECODE	2
+#define DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE	3
+#define DRM_XE_ENGINE_CLASS_COMPUTE		4
+#define DRM_XE_ENGINE_CLASS_VM_BIND		5
+	/** @engine_class: engine class id */
+	__u16 engine_class;
+	/** @engine_instance: engine instance id */
+	__u16 engine_instance;
+	/** @gt_id: Unique ID of this GT within the PCI Device */
+	__u16 gt_id;
+	/** @pad: MBZ */
+	__u16 pad;
+};
+
+/**
+ * struct drm_xe_engine - describe hardware engine
+ */
+struct drm_xe_engine {
+	/** @instance: The @drm_xe_engine_class_instance */
+	struct drm_xe_engine_class_instance instance;
+
+	/** @reserved: Reserved */
+	__u64 reserved[3];
+};
+
+/**
+ * struct drm_xe_query_engines - describe engines
+ *
+ * If a query is made with a struct @drm_xe_device_query where .query
+ * is equal to %DRM_XE_DEVICE_QUERY_ENGINES, then the reply uses an array of
+ * struct @drm_xe_query_engines in .data.
+ */
+struct drm_xe_query_engines {
+	/** @num_engines: number of engines returned in @engines */
+	__u32 num_engines;
+	/** @pad: MBZ */
+	__u32 pad;
+	/** @engines: The returned engines for this device */
+	struct drm_xe_engine engines[];
+};
+
+/**
+ * enum drm_xe_memory_class - Supported memory classes.
+ */
+enum drm_xe_memory_class {
+	/** @DRM_XE_MEM_REGION_CLASS_SYSMEM: Represents system memory. */
+	DRM_XE_MEM_REGION_CLASS_SYSMEM = 0,
+	/**
+	 * @DRM_XE_MEM_REGION_CLASS_VRAM: On discrete platforms, this
+	 * represents the memory that is local to the device, which we
+	 * call VRAM. Not valid on integrated platforms.
+	 */
+	DRM_XE_MEM_REGION_CLASS_VRAM
+};
+
+/**
+ * struct drm_xe_mem_region - Describes some region as known to
+ * the driver.
+ */
+struct drm_xe_mem_region {
+	/**
+	 * @mem_class: The memory class describing this region.
+	 *
+	 * See enum drm_xe_memory_class for supported values.
+	 */
+	__u16 mem_class;
+	/**
+	 * @instance: The unique ID for this region, which serves as the
+	 * index in the placement bitmask used as argument for
+	 * &DRM_IOCTL_XE_GEM_CREATE
+	 */
+	__u16 instance;
+	/**
+	 * @min_page_size: Min page-size in bytes for this region.
+	 *
+	 * When the kernel allocates memory for this region, the
+	 * underlying pages will be at least @min_page_size in size.
+	 * Buffer objects with an allowable placement in this region must be
+	 * created with a size aligned to this value.
+	 * GPU virtual address mappings of (parts of) buffer objects that
+	 * may be placed in this region must also have their GPU virtual
+	 * address and range aligned to this value.
+	 * Affected IOCTLS will return %-EINVAL if alignment restrictions are
+	 * not met.
+	 */
+	__u32 min_page_size;
+	/**
+	 * @total_size: The usable size in bytes for this region.
+	 */
+	__u64 total_size;
+	/**
+	 * @used: Estimate of the memory used in bytes for this region.
+	 *
+	 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+	 * accounting.  Without this the value here will always equal
+	 * zero.
+	 */
+	__u64 used;
+	/**
+	 * @cpu_visible_size: How much of this region can be CPU
+	 * accessed, in bytes.
+	 *
+	 * This will always be <= @total_size, and the remainder (if
+	 * any) will not be CPU accessible. If the CPU accessible part
+	 * is smaller than @total_size then this is referred to as a
+	 * small BAR system.
+	 *
+	 * On systems without small BAR (full BAR), the probed_size will
+	 * always equal the @total_size, since all of it will be CPU
+	 * accessible.
+	 *
+	 * Note this is only tracked for DRM_XE_MEM_REGION_CLASS_VRAM
+	 * regions (for other types the value here will always equal
+	 * zero).
+	 */
+	__u64 cpu_visible_size;
+	/**
+	 * @cpu_visible_used: Estimate of CPU visible memory used, in
+	 * bytes.
+	 *
+	 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+	 * accounting. Without this the value here will always equal
+	 * zero.  Note this is only currently tracked for
+	 * DRM_XE_MEM_REGION_CLASS_VRAM regions (for other types the value
+	 * here will always be zero).
+	 */
+	__u64 cpu_visible_used;
+	/** @reserved: Reserved */
+	__u64 reserved[6];
+};
+
+/**
+ * struct drm_xe_query_mem_regions - describe memory regions
+ *
+ * If a query is made with a struct drm_xe_device_query where .query
+ * is equal to DRM_XE_DEVICE_QUERY_MEM_REGIONS, then the reply uses
+ * struct drm_xe_query_mem_regions in .data.
+ */
+struct drm_xe_query_mem_regions {
+	/** @num_mem_regions: number of memory regions returned in @mem_regions */
+	__u32 num_mem_regions;
+	/** @pad: MBZ */
+	__u32 pad;
+	/** @mem_regions: The returned memory regions for this device */
+	struct drm_xe_mem_region mem_regions[];
+};
+
+/**
+ * struct drm_xe_query_config - describe the device configuration
+ *
+ * If a query is made with a struct drm_xe_device_query where .query
+ * is equal to DRM_XE_DEVICE_QUERY_CONFIG, then the reply uses
+ * struct drm_xe_query_config in .data.
+ *
+ * The index in @info can be:
+ *  - %DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID - Device ID (lower 16 bits)
+ *    and the device revision (next 8 bits)
+ *  - %DRM_XE_QUERY_CONFIG_FLAGS - Flags describing the device
+ *    configuration, see list below
+ *
+ *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM - Flag is set if the device
+ *      has usable VRAM
+ *  - %DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT - Minimal memory alignment
+ *    required by this device, typically SZ_4K or SZ_64K
+ *  - %DRM_XE_QUERY_CONFIG_VA_BITS - Maximum bits of a virtual address
+ *  - %DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY - Value of the highest
+ *    available exec queue priority
+ */
+struct drm_xe_query_config {
+	/** @num_params: number of parameters returned in info */
+	__u32 num_params;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+#define DRM_XE_QUERY_CONFIG_REV_AND_DEVICE_ID	0
+#define DRM_XE_QUERY_CONFIG_FLAGS			1
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_VRAM	(1 << 0)
+#define DRM_XE_QUERY_CONFIG_MIN_ALIGNMENT		2
+#define DRM_XE_QUERY_CONFIG_VA_BITS			3
+#define DRM_XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY	4
+	/** @info: array of elements containing the config info */
+	__u64 info[];
+};
+
+/**
+ * struct drm_xe_gt - describe an individual GT.
+ *
+ * To be used with drm_xe_query_gt_list, which will return a list with all the
+ * existing GT individual descriptions.
+ * Graphics Technology (GT) is a subset of a GPU/tile that is responsible for
+ * implementing graphics and/or media operations.
+ *
+ * The index in @type can be:
+ *  - %DRM_XE_QUERY_GT_TYPE_MAIN
+ *  - %DRM_XE_QUERY_GT_TYPE_MEDIA
+ */
+struct drm_xe_gt {
+#define DRM_XE_QUERY_GT_TYPE_MAIN		0
+#define DRM_XE_QUERY_GT_TYPE_MEDIA		1
+	/** @type: GT type: Main or Media */
+	__u16 type;
+	/** @tile_id: Tile ID where this GT lives (Information only) */
+	__u16 tile_id;
+	/** @gt_id: Unique ID of this GT within the PCI Device */
+	__u16 gt_id;
+	/** @pad: MBZ */
+	__u16 pad[3];
+	/** @reference_clock: A clock frequency for timestamp */
+	__u32 reference_clock;
+	/**
+	 * @near_mem_regions: Bit mask of instances from
+	 * drm_xe_query_mem_regions that are nearest to the current engines
+	 * of this GT.
+	 * Each index in this mask refers directly to the struct
+	 * drm_xe_query_mem_regions' instance, no assumptions should
+	 * be made about order. The type of each region is described
+	 * by struct drm_xe_query_mem_regions' mem_class.
+	 */
+	__u64 near_mem_regions;
+	/**
+	 * @far_mem_regions: Bit mask of instances from
+	 * drm_xe_query_mem_regions that are far from the engines of this GT.
+	 * In general, they have extra indirections when compared to the
+	 * @near_mem_regions. For a discrete device this could mean system
+	 * memory and memory living in a different tile.
+	 * Each index in this mask refers directly to the struct
+	 * drm_xe_query_mem_regions' instance, no assumptions should
+	 * be made about order. The type of each region is described
+	 * by struct drm_xe_query_mem_regions' mem_class.
+	 */
+	__u64 far_mem_regions;
+	/** @reserved: Reserved */
+	__u64 reserved[8];
+};
+
+/**
+ * struct drm_xe_query_gt_list - A list with GT description items.
+ *
+ * If a query is made with a struct drm_xe_device_query where .query
+ * is equal to DRM_XE_DEVICE_QUERY_GT_LIST, then the reply uses struct
+ * drm_xe_query_gt_list in .data.
+ */
+struct drm_xe_query_gt_list {
+	/** @num_gt: number of GT items returned in gt_list */
+	__u32 num_gt;
+	/** @pad: MBZ */
+	__u32 pad;
+	/** @gt_list: The GT list returned for this device */
+	struct drm_xe_gt gt_list[];
+};
+
+/**
+ * struct drm_xe_query_topology_mask - describe the topology mask of a GT
+ *
+ * This is the hardware topology which reflects the internal physical
+ * structure of the GPU.
+ *
+ * If a query is made with a struct drm_xe_device_query where .query
+ * is equal to DRM_XE_DEVICE_QUERY_GT_TOPOLOGY, then the reply uses
+ * struct drm_xe_query_topology_mask in .data.
+ *
+ * The @type can be:
+ *  - %DRM_XE_TOPO_DSS_GEOMETRY - To query the mask of Dual Sub Slices
+ *    (DSS) available for geometry operations. For example a query response
+ *    containing the following in mask:
+ *    ``DSS_GEOMETRY    ff ff ff ff 00 00 00 00``
+ *    means 32 DSS are available for geometry.
+ *  - %DRM_XE_TOPO_DSS_COMPUTE - To query the mask of Dual Sub Slices
+ *    (DSS) available for compute operations. For example a query response
+ *    containing the following in mask:
+ *    ``DSS_COMPUTE    ff ff ff ff 00 00 00 00``
+ *    means 32 DSS are available for compute.
+ *  - %DRM_XE_TOPO_EU_PER_DSS - To query the mask of Execution Units (EU)
+ *    available per Dual Sub Slices (DSS). For example a query response
+ *    containing the following in mask:
+ *    ``EU_PER_DSS    ff ff 00 00 00 00 00 00``
+ *    means each DSS has 16 EU.
+ */
+struct drm_xe_query_topology_mask {
+	/** @gt_id: GT ID the mask is associated with */
+	__u16 gt_id;
+
+#define DRM_XE_TOPO_DSS_GEOMETRY	(1 << 0)
+#define DRM_XE_TOPO_DSS_COMPUTE		(1 << 1)
+#define DRM_XE_TOPO_EU_PER_DSS		(1 << 2)
+	/** @type: type of mask */
+	__u16 type;
+
+	/** @num_bytes: number of bytes in requested mask */
+	__u32 num_bytes;
+
+	/** @mask: little-endian mask of @num_bytes */
+	__u8 mask[];
+};
+
+/**
+ * struct drm_xe_query_engine_cycles - correlate CPU and GPU timestamps
+ *
+ * If a query is made with a struct drm_xe_device_query where .query is equal to
+ * DRM_XE_DEVICE_QUERY_ENGINE_CYCLES, then the reply uses struct drm_xe_query_engine_cycles
+ * in .data. struct drm_xe_query_engine_cycles is allocated by the user and
+ * .data points to this allocated structure.
+ *
+ * The query returns the engine cycles, which along with GT's @reference_clock,
+ * can be used to calculate the engine timestamp. In addition the
+ * query returns a set of cpu timestamps that indicate when the command
+ * streamer cycle count was captured.
+ */
+struct drm_xe_query_engine_cycles {
+	/**
+	 * @eci: This is input by the user and is the engine for which command
+	 * streamer cycles is queried.
+	 */
+	struct drm_xe_engine_class_instance eci;
+
+	/**
+	 * @clockid: This is input by the user and is the reference clock id for
+	 * CPU timestamp. For definition, see clock_gettime(2) and
+	 * perf_event_open(2). Supported clock ids are CLOCK_MONOTONIC,
+	 * CLOCK_MONOTONIC_RAW, CLOCK_REALTIME, CLOCK_BOOTTIME, CLOCK_TAI.
+	 */
+	__s32 clockid;
+
+	/** @width: Width of the engine cycle counter in bits. */
+	__u32 width;
+
+	/**
+	 * @engine_cycles: Engine cycles as read from its register
+	 * at 0x358 offset.
+	 */
+	__u64 engine_cycles;
+
+	/**
+	 * @cpu_timestamp: CPU timestamp in ns. The timestamp is captured before
+	 * reading the engine_cycles register using the reference clockid set by the
+	 * user.
+	 */
+	__u64 cpu_timestamp;
+
+	/**
+	 * @cpu_delta: Time delta in ns captured around reading the lower dword
+	 * of the engine_cycles register.
+	 */
+	__u64 cpu_delta;
+};
+
+/**
+ * struct drm_xe_device_query - Input of &DRM_IOCTL_XE_DEVICE_QUERY - main
+ * structure to query device information
+ *
+ * The user selects the type of data to query among DRM_XE_DEVICE_QUERY_*
+ * and sets the value in the query member. This determines the type of
+ * the structure provided by the driver in data, among struct drm_xe_query_*.
+ *
+ * The @query can be:
+ *  - %DRM_XE_DEVICE_QUERY_ENGINES
+ *  - %DRM_XE_DEVICE_QUERY_MEM_REGIONS
+ *  - %DRM_XE_DEVICE_QUERY_CONFIG
+ *  - %DRM_XE_DEVICE_QUERY_GT_LIST
+ *  - %DRM_XE_DEVICE_QUERY_HWCONFIG - Query type to retrieve the hardware
+ *    configuration of the device such as information on slices, memory,
+ *    caches, and so on. It is provided as a table of key / value
+ *    attributes.
+ *  - %DRM_XE_DEVICE_QUERY_GT_TOPOLOGY
+ *  - %DRM_XE_DEVICE_QUERY_ENGINE_CYCLES
+ *
+ * If size is set to 0, the driver fills it with the required size for
+ * the requested type of data to query. If size is equal to the required
+ * size, the queried information is copied into data. If size is set to
+ * a value different from 0 and different from the required size, the
+ * IOCTL call returns -EINVAL.
+ *
+ * For example the following code snippet allows retrieving and printing
+ * information about the device engines with DRM_XE_DEVICE_QUERY_ENGINES:
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_query_engines *engines;
+ *     struct drm_xe_device_query query = {
+ *         .extensions = 0,
+ *         .query = DRM_XE_DEVICE_QUERY_ENGINES,
+ *         .size = 0,
+ *         .data = 0,
+ *     };
+ *     ioctl(fd, DRM_IOCTL_XE_DEVICE_QUERY, &query);
+ *     engines = malloc(query.size);
+ *     query.data = (uintptr_t)engines;
+ *     ioctl(fd, DRM_IOCTL_XE_DEVICE_QUERY, &query);
+ *     for (int i = 0; i < engines->num_engines; i++) {
+ *         printf("Engine %d: %s\n", i,
+ *             engines->engines[i].instance.engine_class ==
+ *                 DRM_XE_ENGINE_CLASS_RENDER ? "RENDER":
+ *             engines->engines[i].instance.engine_class ==
+ *                 DRM_XE_ENGINE_CLASS_COPY ? "COPY":
+ *             engines->engines[i].instance.engine_class ==
+ *                 DRM_XE_ENGINE_CLASS_VIDEO_DECODE ? "VIDEO_DECODE":
+ *             engines->engines[i].instance.engine_class ==
+ *                 DRM_XE_ENGINE_CLASS_VIDEO_ENHANCE ? "VIDEO_ENHANCE":
+ *             engines->engines[i].instance.engine_class ==
+ *                 DRM_XE_ENGINE_CLASS_COMPUTE ? "COMPUTE":
+ *             "UNKNOWN");
+ *     }
+ *     free(engines);
+ */
+struct drm_xe_device_query {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+#define DRM_XE_DEVICE_QUERY_ENGINES		0
+#define DRM_XE_DEVICE_QUERY_MEM_REGIONS		1
+#define DRM_XE_DEVICE_QUERY_CONFIG		2
+#define DRM_XE_DEVICE_QUERY_GT_LIST		3
+#define DRM_XE_DEVICE_QUERY_HWCONFIG		4
+#define DRM_XE_DEVICE_QUERY_GT_TOPOLOGY		5
+#define DRM_XE_DEVICE_QUERY_ENGINE_CYCLES	6
+	/** @query: The type of data to query */
+	__u32 query;
+
+	/** @size: Size of the queried data */
+	__u32 size;
+
+	/** @data: Queried data is placed here */
+	__u64 data;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_gem_create - Input of &DRM_IOCTL_XE_GEM_CREATE - A structure for
+ * gem creation
+ *
+ * The @flags can be:
+ *  - %DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING
+ *  - %DRM_XE_GEM_CREATE_FLAG_SCANOUT
+ *  - %DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM - When using VRAM as a
+ *    possible placement, ensure that the corresponding VRAM allocation
+ *    will always use the CPU accessible part of VRAM. This is important
+ *    for small-bar systems (on full-bar systems this gets turned into a
+ *    noop).
+ *    Note1: System memory can be used as an extra placement if the kernel
+ *    should spill the allocation to system memory, if space can't be made
+ *    available in the CPU accessible part of VRAM (giving the same
+ *    behaviour as the i915 interface, see
+ *    I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS).
+ *    Note2: For clear-color CCS surfaces the kernel needs to read the
+ *    clear-color value stored in the buffer, and on discrete platforms we
+ *    need to use VRAM for display surfaces, therefore the kernel requires
+ *    setting this flag for such objects, otherwise an error is thrown on
+ *    small-bar systems.
+ *
+ * @cpu_caching supports the following values:
+ *  - %DRM_XE_GEM_CPU_CACHING_WB - Allocate the pages with write-back
+ *    caching. On iGPU this can't be used for scanout surfaces. Currently
+ *    not allowed for objects placed in VRAM.
+ *  - %DRM_XE_GEM_CPU_CACHING_WC - Allocate the pages as write-combined. This
+ *    is uncached. Scanout surfaces should likely use this. All objects
+ *    that can be placed in VRAM must use this.
+ */
+struct drm_xe_gem_create {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/**
+	 * @size: Size of the object to be created, must match region
+	 * (system or vram) minimum alignment (&min_page_size).
+	 */
+	__u64 size;
+
+	/**
+	 * @placement: A mask of memory instances of where BO can be placed.
+	 * Each index in this mask refers directly to the struct
+	 * drm_xe_query_mem_regions' instance, no assumptions should
+	 * be made about order. The type of each region is described
+	 * by struct drm_xe_query_mem_regions' mem_class.
+	 */
+	__u32 placement;
+
+#define DRM_XE_GEM_CREATE_FLAG_DEFER_BACKING		(1 << 0)
+#define DRM_XE_GEM_CREATE_FLAG_SCANOUT			(1 << 1)
+#define DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM	(1 << 2)
+	/**
+	 * @flags: Flags, currently a mask of memory instances of where BO can
+	 * be placed
+	 */
+	__u32 flags;
+
+	/**
+	 * @vm_id: Attached VM, if any
+	 *
+	 * If a VM is specified, this BO must:
+	 *
+	 *  1. Only ever be bound to that VM.
+	 *  2. Cannot be exported as a PRIME fd.
+	 */
+	__u32 vm_id;
+
+	/**
+	 * @handle: Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+
+#define DRM_XE_GEM_CPU_CACHING_WB                      1
+#define DRM_XE_GEM_CPU_CACHING_WC                      2
+	/**
+	 * @cpu_caching: The CPU caching mode to select for this object. If
+	 * mmaping the object the mode selected here will also be used.
+	 */
+	__u16 cpu_caching;
+	/** @pad: MBZ */
+	__u16 pad[3];
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_gem_mmap_offset - Input of &DRM_IOCTL_XE_GEM_MMAP_OFFSET
+ */
+struct drm_xe_gem_mmap_offset {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @handle: Handle for the object being mapped. */
+	__u32 handle;
+
+	/** @flags: Must be zero */
+	__u32 flags;
+
+	/** @offset: The fake offset to use for subsequent mmap call */
+	__u64 offset;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE
+ *
+ * The @flags can be:
+ *  - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE
+ *  - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts
+ *    exec submissions to its exec_queues that don't have an upper time
+ *    limit on the job execution time. But exec submissions to these
+ *    don't allow any of the flags DRM_XE_SYNC_FLAG_SYNCOBJ,
+ *    DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ, DRM_XE_SYNC_FLAG_DMA_BUF,
+ *    used as out-syncobjs, that is, together with DRM_XE_SYNC_FLAG_SIGNAL.
+ *    LR VMs can be created in recoverable page-fault mode using
+ *    DRM_XE_VM_CREATE_FLAG_FAULT_MODE, if the device supports it.
+ *    If that flag is omitted, the UMD can not rely on the slightly
+ *    different per-VM overcommit semantics that are enabled by
+ *    DRM_XE_VM_CREATE_FLAG_FAULT_MODE (see below), but KMD may
+ *    still enable recoverable pagefaults if supported by the device.
+ *  - %DRM_XE_VM_CREATE_FLAG_FAULT_MODE - Requires also
+ *    DRM_XE_VM_CREATE_FLAG_LR_MODE. It allows memory to be allocated on
+ *    demand when accessed, and also allows per-VM overcommit of memory.
+ *    The xe driver internally uses recoverable pagefaults to implement
+ *    this.
+ */
+struct drm_xe_vm_create {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+#define DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE	(1 << 0)
+#define DRM_XE_VM_CREATE_FLAG_LR_MODE	        (1 << 1)
+#define DRM_XE_VM_CREATE_FLAG_FAULT_MODE	(1 << 2)
+	/** @flags: Flags */
+	__u32 flags;
+
+	/** @vm_id: Returned VM ID */
+	__u32 vm_id;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_vm_destroy - Input of &DRM_IOCTL_XE_VM_DESTROY
+ */
+struct drm_xe_vm_destroy {
+	/** @vm_id: VM ID */
+	__u32 vm_id;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_vm_bind_op - run bind operations
+ *
+ * The @op can be:
+ *  - %DRM_XE_VM_BIND_OP_MAP
+ *  - %DRM_XE_VM_BIND_OP_UNMAP
+ *  - %DRM_XE_VM_BIND_OP_MAP_USERPTR
+ *  - %DRM_XE_VM_BIND_OP_UNMAP_ALL
+ *  - %DRM_XE_VM_BIND_OP_PREFETCH
+ *
+ * and the @flags can be:
+ *  - %DRM_XE_VM_BIND_FLAG_READONLY
+ *  - %DRM_XE_VM_BIND_FLAG_ASYNC
+ *  - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - Valid on a faulting VM only, do the
+ *    MAP operation immediately rather than deferring the MAP to the page
+ *    fault handler.
+ *  - %DRM_XE_VM_BIND_FLAG_NULL - When the NULL flag is set, the page
+ *    tables are setup with a special bit which indicates writes are
+ *    dropped and all reads return zero. In the future, the NULL flags
+ *    will only be valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
+ *    handle MBZ, and the BO offset MBZ. This flag is intended to
+ *    implement VK sparse bindings.
+ */
+struct drm_xe_vm_bind_op {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/**
+	 * @obj: GEM object to operate on, MBZ for MAP_USERPTR, MBZ for UNMAP
+	 */
+	__u32 obj;
+
+	/**
+	 * @pat_index: The platform defined @pat_index to use for this mapping.
+	 * The index basically maps to some predefined memory attributes,
+	 * including things like caching, coherency, compression etc.  The exact
+	 * meaning of the pat_index is platform specific and defined in the
+	 * Bspec and PRMs.  When the KMD sets up the binding the index here is
+	 * encoded into the ppGTT PTE.
+	 *
+	 * For coherency the @pat_index needs to be at least 1way coherent when
+	 * drm_xe_gem_create.cpu_caching is DRM_XE_GEM_CPU_CACHING_WB. The KMD
+	 * will extract the coherency mode from the @pat_index and reject if
+	 * there is a mismatch (see note below for pre-MTL platforms).
+	 *
+	 * Note: On pre-MTL platforms there is only a caching mode and no
+	 * explicit coherency mode, but on such hardware there is always a
+	 * shared-LLC (or is dgpu) so all GT memory accesses are coherent with
+	 * CPU caches even with the caching mode set as uncached.  It's only the
+	 * display engine that is incoherent (on dgpu it must be in VRAM which
+	 * is always mapped as WC on the CPU). However to keep the uapi somewhat
+	 * consistent with newer platforms the KMD groups the different cache
+	 * levels into the following coherency buckets on all pre-MTL platforms:
+	 *
+	 *	ppGTT UC -> COH_NONE
+	 *	ppGTT WC -> COH_NONE
+	 *	ppGTT WT -> COH_NONE
+	 *	ppGTT WB -> COH_AT_LEAST_1WAY
+	 *
+	 * In practice UC/WC/WT should only ever used for scanout surfaces on
+	 * such platforms (or perhaps in general for dma-buf if shared with
+	 * another device) since it is only the display engine that is actually
+	 * incoherent.  Everything else should typically use WB given that we
+	 * have a shared-LLC.  On MTL+ this completely changes and the HW
+	 * defines the coherency mode as part of the @pat_index, where
+	 * incoherent GT access is possible.
+	 *
+	 * Note: For userptr and externally imported dma-buf the kernel expects
+	 * either 1WAY or 2WAY for the @pat_index.
+	 *
+	 * For DRM_XE_VM_BIND_FLAG_NULL bindings there are no KMD restrictions
+	 * on the @pat_index. For such mappings there is no actual memory being
+	 * mapped (the address in the PTE is invalid), so the various PAT memory
+	 * attributes likely do not apply.  Simply leaving as zero is one
+	 * option (still a valid pat_index).
+	 */
+	__u16 pat_index;
+
+	/** @pad: MBZ */
+	__u16 pad;
+
+	union {
+		/**
+		 * @obj_offset: Offset into the object, MBZ for CLEAR_RANGE,
+		 * ignored for unbind
+		 */
+		__u64 obj_offset;
+
+		/** @userptr: user pointer to bind on */
+		__u64 userptr;
+	};
+
+	/**
+	 * @range: Number of bytes from the object to bind to addr, MBZ for UNMAP_ALL
+	 */
+	__u64 range;
+
+	/** @addr: Address to operate on, MBZ for UNMAP_ALL */
+	__u64 addr;
+
+#define DRM_XE_VM_BIND_OP_MAP		0x0
+#define DRM_XE_VM_BIND_OP_UNMAP		0x1
+#define DRM_XE_VM_BIND_OP_MAP_USERPTR	0x2
+#define DRM_XE_VM_BIND_OP_UNMAP_ALL	0x3
+#define DRM_XE_VM_BIND_OP_PREFETCH	0x4
+	/** @op: Bind operation to perform */
+	__u32 op;
+
+#define DRM_XE_VM_BIND_FLAG_READONLY	(1 << 0)
+#define DRM_XE_VM_BIND_FLAG_IMMEDIATE	(1 << 1)
+#define DRM_XE_VM_BIND_FLAG_NULL	(1 << 2)
+	/** @flags: Bind flags */
+	__u32 flags;
+
+	/**
+	 * @prefetch_mem_region_instance: Memory region to prefetch VMA to.
+	 * It is a region instance, not a mask.
+	 * To be used only with %DRM_XE_VM_BIND_OP_PREFETCH operation.
+	 */
+	__u32 prefetch_mem_region_instance;
+
+	/** @pad2: MBZ */
+	__u32 pad2;
+
+	/** @reserved: Reserved */
+	__u64 reserved[3];
+};
+
+/**
+ * struct drm_xe_vm_bind - Input of &DRM_IOCTL_XE_VM_BIND
+ *
+ * Below is an example of a minimal use of @drm_xe_vm_bind to
+ * asynchronously bind the buffer `data` at address `BIND_ADDRESS` to
+ * illustrate `userptr`. It can be synchronized by using the example
+ * provided for @drm_xe_sync.
+ *
+ * .. code-block:: C
+ *
+ *     data = aligned_alloc(ALIGNMENT, BO_SIZE);
+ *     struct drm_xe_vm_bind bind = {
+ *         .vm_id = vm,
+ *         .num_binds = 1,
+ *         .bind.obj = 0,
+ *         .bind.obj_offset = to_user_pointer(data),
+ *         .bind.range = BO_SIZE,
+ *         .bind.addr = BIND_ADDRESS,
+ *         .bind.op = DRM_XE_VM_BIND_OP_MAP_USERPTR,
+ *         .bind.flags = 0,
+ *         .num_syncs = 1,
+ *         .syncs = &sync,
+ *         .exec_queue_id = 0,
+ *     };
+ *     ioctl(fd, DRM_IOCTL_XE_VM_BIND, &bind);
+ *
+ */
+struct drm_xe_vm_bind {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @vm_id: The ID of the VM to bind to */
+	__u32 vm_id;
+
+	/**
+	 * @exec_queue_id: exec_queue_id, must be of class DRM_XE_ENGINE_CLASS_VM_BIND
+	 * and exec queue must have same vm_id. If zero, the default VM bind engine
+	 * is used.
+	 */
+	__u32 exec_queue_id;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @num_binds: number of binds in this IOCTL */
+	__u32 num_binds;
+
+	union {
+		/** @bind: used if num_binds == 1 */
+		struct drm_xe_vm_bind_op bind;
+
+		/**
+		 * @vector_of_binds: userptr to array of struct
+		 * drm_xe_vm_bind_op if num_binds > 1
+		 */
+		__u64 vector_of_binds;
+	};
+
+	/** @pad2: MBZ */
+	__u32 pad2;
+
+	/** @num_syncs: amount of syncs to wait on */
+	__u32 num_syncs;
+
+	/** @syncs: pointer to struct drm_xe_sync array */
+	__u64 syncs;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE
+ *
+ * The example below shows how to use @drm_xe_exec_queue_create to create
+ * a simple exec_queue (no parallel submission) of class
+ * &DRM_XE_ENGINE_CLASS_RENDER.
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_engine_class_instance instance = {
+ *         .engine_class = DRM_XE_ENGINE_CLASS_RENDER,
+ *     };
+ *     struct drm_xe_exec_queue_create exec_queue_create = {
+ *          .extensions = 0,
+ *          .vm_id = vm,
+ *          .num_bb_per_exec = 1,
+ *          .num_eng_per_bb = 1,
+ *          .instances = to_user_pointer(&instance),
+ *     };
+ *     ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create);
+ *
+ */
+struct drm_xe_exec_queue_create {
+#define DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY		0
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY		0
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE		1
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PREEMPTION_TIMEOUT	2
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_PERSISTENCE		3
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_JOB_TIMEOUT		4
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_TRIGGER		5
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_NOTIFY		6
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_ACC_GRANULARITY	7
+/* Monitor 128KB contiguous region with 4K sub-granularity */
+#define     DRM_XE_ACC_GRANULARITY_128K				0
+/* Monitor 2MB contiguous region with 64KB sub-granularity */
+#define     DRM_XE_ACC_GRANULARITY_2M				1
+/* Monitor 16MB contiguous region with 512KB sub-granularity */
+#define     DRM_XE_ACC_GRANULARITY_16M				2
+/* Monitor 64MB contiguous region with 2M sub-granularity */
+#define     DRM_XE_ACC_GRANULARITY_64M				3
+
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @width: submission width (number BB per exec) for this exec queue */
+	__u16 width;
+
+	/** @num_placements: number of valid placements for this exec queue */
+	__u16 num_placements;
+
+	/** @vm_id: VM to use for this exec queue */
+	__u32 vm_id;
+
+	/** @flags: MBZ */
+	__u32 flags;
+
+	/** @exec_queue_id: Returned exec queue ID */
+	__u32 exec_queue_id;
+
+	/**
+	 * @instances: user pointer to a 2-d array of struct
+	 * drm_xe_engine_class_instance
+	 *
+	 * length = width (i) * num_placements (j)
+	 * index = j + i * width
+	 */
+	__u64 instances;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_exec_queue_destroy - Input of &DRM_IOCTL_XE_EXEC_QUEUE_DESTROY
+ */
+struct drm_xe_exec_queue_destroy {
+	/** @exec_queue_id: Exec queue ID */
+	__u32 exec_queue_id;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_exec_queue_get_property - Input of &DRM_IOCTL_XE_EXEC_QUEUE_GET_PROPERTY
+ *
+ * The @property can be:
+ *  - %DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN
+ */
+struct drm_xe_exec_queue_get_property {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @exec_queue_id: Exec queue ID */
+	__u32 exec_queue_id;
+
+#define DRM_XE_EXEC_QUEUE_GET_PROPERTY_BAN	0
+	/** @property: property to get */
+	__u32 property;
+
+	/** @value: property value */
+	__u64 value;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_sync - sync object
+ *
+ * The @type can be:
+ *  - %DRM_XE_SYNC_TYPE_SYNCOBJ
+ *  - %DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ
+ *  - %DRM_XE_SYNC_TYPE_USER_FENCE
+ *
+ * and the @flags can be:
+ *  - %DRM_XE_SYNC_FLAG_SIGNAL
+ *
+ * A minimal use of @drm_xe_sync looks like this:
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_sync sync = {
+ *         .flags = DRM_XE_SYNC_FLAG_SIGNAL,
+ *         .type = DRM_XE_SYNC_TYPE_SYNCOBJ,
+ *     };
+ *     struct drm_syncobj_create syncobj_create = { 0 };
+ *     ioctl(fd, DRM_IOCTL_SYNCOBJ_CREATE, &syncobj_create);
+ *     sync.handle = syncobj_create.handle;
+ *         ...
+ *         use of &sync in drm_xe_exec or drm_xe_vm_bind
+ *         ...
+ *     struct drm_syncobj_wait wait = {
+ *         .handles = &sync.handle,
+ *         .timeout_nsec = INT64_MAX,
+ *         .count_handles = 1,
+ *         .flags = 0,
+ *         .first_signaled = 0,
+ *         .pad = 0,
+ *     };
+ *     ioctl(fd, DRM_IOCTL_SYNCOBJ_WAIT, &wait);
+ */
+struct drm_xe_sync {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+#define DRM_XE_SYNC_TYPE_SYNCOBJ		0x0
+#define DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ	0x1
+#define DRM_XE_SYNC_TYPE_USER_FENCE		0x2
+	/** @type: Type of the this sync object */
+	__u32 type;
+
+#define DRM_XE_SYNC_FLAG_SIGNAL	(1 << 0)
+	/** @flags: Sync Flags */
+	__u32 flags;
+
+	union {
+		/** @handle: Handle for the object */
+		__u32 handle;
+
+		/**
+		 * @addr: Address of user fence. When sync is passed in via exec
+		 * IOCTL this is a GPU address in the VM. When sync passed in via
+		 * VM bind IOCTL this is a user pointer. In either case, it is
+		 * the users responsibility that this address is present and
+		 * mapped when the user fence is signalled. Must be qword
+		 * aligned.
+		 */
+		__u64 addr;
+	};
+
+	/**
+	 * @timeline_value: Input for the timeline sync object. Needs to be
+	 * different than 0 when used with %DRM_XE_SYNC_FLAG_TIMELINE_SYNCOBJ.
+	 */
+	__u64 timeline_value;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_exec - Input of &DRM_IOCTL_XE_EXEC
+ *
+ * This is an example to use @drm_xe_exec for execution of the object
+ * at BIND_ADDRESS (see example in @drm_xe_vm_bind) by an exec_queue
+ * (see example in @drm_xe_exec_queue_create). It can be synchronized
+ * by using the example provided for @drm_xe_sync.
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_exec exec = {
+ *         .exec_queue_id = exec_queue,
+ *         .syncs = &sync,
+ *         .num_syncs = 1,
+ *         .address = BIND_ADDRESS,
+ *         .num_batch_buffer = 1,
+ *     };
+ *     ioctl(fd, DRM_IOCTL_XE_EXEC, &exec);
+ *
+ */
+struct drm_xe_exec {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @exec_queue_id: Exec queue ID for the batch buffer */
+	__u32 exec_queue_id;
+
+	/** @num_syncs: Amount of struct drm_xe_sync in array. */
+	__u32 num_syncs;
+
+	/** @syncs: Pointer to struct drm_xe_sync array. */
+	__u64 syncs;
+
+	/**
+	 * @address: address of batch buffer if num_batch_buffer == 1 or an
+	 * array of batch buffer addresses
+	 */
+	__u64 address;
+
+	/**
+	 * @num_batch_buffer: number of batch buffer in this exec, must match
+	 * the width of the engine
+	 */
+	__u16 num_batch_buffer;
+
+	/** @pad: MBZ */
+	__u16 pad[3];
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_wait_user_fence - Input of &DRM_IOCTL_XE_WAIT_USER_FENCE
+ *
+ * Wait on user fence, XE will wake-up on every HW engine interrupt in the
+ * instances list and check if user fence is complete::
+ *
+ *	(*addr & MASK) OP (VALUE & MASK)
+ *
+ * Returns to user on user fence completion or timeout.
+ *
+ * The @op can be:
+ *  - %DRM_XE_UFENCE_WAIT_OP_EQ
+ *  - %DRM_XE_UFENCE_WAIT_OP_NEQ
+ *  - %DRM_XE_UFENCE_WAIT_OP_GT
+ *  - %DRM_XE_UFENCE_WAIT_OP_GTE
+ *  - %DRM_XE_UFENCE_WAIT_OP_LT
+ *  - %DRM_XE_UFENCE_WAIT_OP_LTE
+ *
+ * and the @flags can be:
+ *  - %DRM_XE_UFENCE_WAIT_FLAG_ABSTIME
+ *  - %DRM_XE_UFENCE_WAIT_FLAG_SOFT_OP
+ *
+ * The @mask values can be for example:
+ *  - 0xffu for u8
+ *  - 0xffffu for u16
+ *  - 0xffffffffu for u32
+ *  - 0xffffffffffffffffu for u64
+ */
+struct drm_xe_wait_user_fence {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/**
+	 * @addr: user pointer address to wait on, must qword aligned
+	 */
+	__u64 addr;
+
+#define DRM_XE_UFENCE_WAIT_OP_EQ	0x0
+#define DRM_XE_UFENCE_WAIT_OP_NEQ	0x1
+#define DRM_XE_UFENCE_WAIT_OP_GT	0x2
+#define DRM_XE_UFENCE_WAIT_OP_GTE	0x3
+#define DRM_XE_UFENCE_WAIT_OP_LT	0x4
+#define DRM_XE_UFENCE_WAIT_OP_LTE	0x5
+	/** @op: wait operation (type of comparison) */
+	__u16 op;
+
+#define DRM_XE_UFENCE_WAIT_FLAG_ABSTIME	(1 << 0)
+	/** @flags: wait flags */
+	__u16 flags;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @value: compare value */
+	__u64 value;
+
+	/** @mask: comparison mask */
+	__u64 mask;
+
+	/**
+	 * @timeout: how long to wait before bailing, value in nanoseconds.
+	 * Without DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flag set (relative timeout)
+	 * it contains timeout expressed in nanoseconds to wait (fence will
+	 * expire at now() + timeout).
+	 * When DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flat is set (absolute timeout) wait
+	 * will end at timeout (uses system MONOTONIC_CLOCK).
+	 * Passing negative timeout leads to neverending wait.
+	 *
+	 * On relative timeout this value is updated with timeout left
+	 * (for restarting the call in case of signal delivery).
+	 * On absolute timeout this value stays intact (restarted call still
+	 * expire at the same point of time).
+	 */
+	__s64 timeout;
+
+	/** @exec_queue_id: exec_queue_id returned from xe_exec_queue_create_ioctl */
+	__u32 exec_queue_id;
+
+	/** @pad2: MBZ */
+	__u32 pad2;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_XE_DRM_H_ */