KVM: SEV: Do cache maintenance on the source VM during intra-host migrationgrafted

Manually perform cache maintenance on the source VM during intra-host
migration to ensure no stale data is left in CPU caches after the VM is
destroyed.  Because the source VM is "converted" to a non-SEV VM, KVM's
memory reclaim flows won't trigger cache maintenance, e.g. when all guest
memory is reclaimed in response to detaching from the mmu_notifier.

Note, relying on the destination VM to do cache maintenance isn't an option
as KVM doesn't require identical guest memory configurations, i.e. the
source VM may have access to memory that the destination VM does not.
Enforcing equivalent memory configurations is infeasible, as it would
require a *deep* comparison of memslots, e.g. to verify that not only are
the memslot identical, but what the memslots point at is also identical.

Fixes: b56639318bb2 ("KVM: SEV: Add support for SEV intra host migration")
Cc: stable@vger.kernel.org
Reported-by: Stefan Teodorescu <fane@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20260923163721.1584779-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

34 files changed, 29862 insertions, 0 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
new file mode 100644
index 000000000..42a5fa8ad
--- /dev/null
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -0,0 +1,1701 @@
+/* amdgpu_drm.h -- Public header for the amdgpu driver -*- linux-c -*-
+ *
+ * Copyright 2000 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Fremont, California.
+ * Copyright 2002 Tungsten Graphics, Inc., Cedar Park, Texas.
+ * Copyright 2014 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Kevin E. Martin <martin@valinux.com>
+ *    Gareth Hughes <gareth@valinux.com>
+ *    Keith Whitwell <keith@tungstengraphics.com>
+ */
+
+#ifndef __AMDGPU_DRM_H__
+#define __AMDGPU_DRM_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_AMDGPU_GEM_CREATE		0x00
+#define DRM_AMDGPU_GEM_MMAP		0x01
+#define DRM_AMDGPU_CTX			0x02
+#define DRM_AMDGPU_BO_LIST		0x03
+#define DRM_AMDGPU_CS			0x04
+#define DRM_AMDGPU_INFO			0x05
+#define DRM_AMDGPU_GEM_METADATA		0x06
+#define DRM_AMDGPU_GEM_WAIT_IDLE	0x07
+#define DRM_AMDGPU_GEM_VA		0x08
+#define DRM_AMDGPU_WAIT_CS		0x09
+#define DRM_AMDGPU_GEM_OP		0x10
+#define DRM_AMDGPU_GEM_USERPTR		0x11
+#define DRM_AMDGPU_WAIT_FENCES		0x12
+#define DRM_AMDGPU_VM			0x13
+#define DRM_AMDGPU_FENCE_TO_HANDLE	0x14
+#define DRM_AMDGPU_SCHED		0x15
+#define DRM_AMDGPU_USERQ		0x16
+#define DRM_AMDGPU_USERQ_SIGNAL		0x17
+#define DRM_AMDGPU_USERQ_WAIT		0x18
+#define DRM_AMDGPU_GEM_LIST_HANDLES	0x19
+#define DRM_AMDGPU_PROC_OPTIONS		0x1A
+
+#define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
+#define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
+#define DRM_IOCTL_AMDGPU_CTX		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_CTX, union drm_amdgpu_ctx)
+#define DRM_IOCTL_AMDGPU_BO_LIST	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_BO_LIST, union drm_amdgpu_bo_list)
+#define DRM_IOCTL_AMDGPU_CS		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_CS, union drm_amdgpu_cs)
+#define DRM_IOCTL_AMDGPU_INFO		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_INFO, struct drm_amdgpu_info)
+#define DRM_IOCTL_AMDGPU_GEM_METADATA	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_METADATA, struct drm_amdgpu_gem_metadata)
+#define DRM_IOCTL_AMDGPU_GEM_WAIT_IDLE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_WAIT_IDLE, union drm_amdgpu_gem_wait_idle)
+#define DRM_IOCTL_AMDGPU_GEM_VA		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_VA, struct drm_amdgpu_gem_va)
+#define DRM_IOCTL_AMDGPU_WAIT_CS	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_CS, union drm_amdgpu_wait_cs)
+#define DRM_IOCTL_AMDGPU_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_OP, struct drm_amdgpu_gem_op)
+#define DRM_IOCTL_AMDGPU_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_USERPTR, struct drm_amdgpu_gem_userptr)
+#define DRM_IOCTL_AMDGPU_WAIT_FENCES	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_WAIT_FENCES, union drm_amdgpu_wait_fences)
+#define DRM_IOCTL_AMDGPU_VM		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_VM, union drm_amdgpu_vm)
+#define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
+#define DRM_IOCTL_AMDGPU_SCHED		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched)
+#define DRM_IOCTL_AMDGPU_USERQ		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ, union drm_amdgpu_userq)
+#define DRM_IOCTL_AMDGPU_USERQ_SIGNAL	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_SIGNAL, struct drm_amdgpu_userq_signal)
+#define DRM_IOCTL_AMDGPU_USERQ_WAIT	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_WAIT, struct drm_amdgpu_userq_wait)
+#define DRM_IOCTL_AMDGPU_GEM_LIST_HANDLES DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_LIST_HANDLES, struct drm_amdgpu_gem_list_handles)
+#define DRM_IOCTL_AMDGPU_PROC_OPTIONS	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_PROC_OPTIONS, struct drm_amdgpu_proc_options)
+
+/**
+ * DOC: memory domains
+ *
+ * %AMDGPU_GEM_DOMAIN_CPU	System memory that is not GPU accessible.
+ * Memory in this pool could be swapped out to disk if there is pressure.
+ *
+ * %AMDGPU_GEM_DOMAIN_GTT	GPU accessible system memory, mapped into the
+ * GPU's virtual address space via gart. Gart memory linearizes non-contiguous
+ * pages of system memory, allows GPU access system memory in a linearized
+ * fashion.
+ *
+ * %AMDGPU_GEM_DOMAIN_VRAM	Local video memory. For APUs, it is memory
+ * carved out by the BIOS.
+ *
+ * %AMDGPU_GEM_DOMAIN_GDS	Global on-chip data storage used to share data
+ * across shader threads.
+ *
+ * %AMDGPU_GEM_DOMAIN_GWS	Global wave sync, used to synchronize the
+ * execution of all the waves on a device.
+ *
+ * %AMDGPU_GEM_DOMAIN_OA	Ordered append, used by 3D or Compute engines
+ * for appending data.
+ *
+ * %AMDGPU_GEM_DOMAIN_DOORBELL	Doorbell. It is an MMIO region for
+ * signalling user mode queues.
+ */
+#define AMDGPU_GEM_DOMAIN_CPU		0x1
+#define AMDGPU_GEM_DOMAIN_GTT		0x2
+#define AMDGPU_GEM_DOMAIN_VRAM		0x4
+#define AMDGPU_GEM_DOMAIN_GDS		0x8
+#define AMDGPU_GEM_DOMAIN_GWS		0x10
+#define AMDGPU_GEM_DOMAIN_OA		0x20
+#define AMDGPU_GEM_DOMAIN_DOORBELL	0x40
+#define AMDGPU_GEM_DOMAIN_MASK		(AMDGPU_GEM_DOMAIN_CPU | \
+					 AMDGPU_GEM_DOMAIN_GTT | \
+					 AMDGPU_GEM_DOMAIN_VRAM | \
+					 AMDGPU_GEM_DOMAIN_GDS | \
+					 AMDGPU_GEM_DOMAIN_GWS | \
+					 AMDGPU_GEM_DOMAIN_OA |	\
+					 AMDGPU_GEM_DOMAIN_DOORBELL)
+
+/* Flag that CPU access will be required for the case of VRAM domain */
+#define AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED	(1 << 0)
+/* Flag that CPU access will not work, this VRAM domain is invisible */
+#define AMDGPU_GEM_CREATE_NO_CPU_ACCESS		(1 << 1)
+/* Flag that USWC attributes should be used for GTT */
+#define AMDGPU_GEM_CREATE_CPU_GTT_USWC		(1 << 2)
+/* Flag that the memory should be in VRAM and cleared */
+#define AMDGPU_GEM_CREATE_VRAM_CLEARED		(1 << 3)
+/* Flag that allocating the BO should use linear VRAM */
+#define AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS	(1 << 5)
+/* Flag that BO is always valid in this VM */
+#define AMDGPU_GEM_CREATE_VM_ALWAYS_VALID	(1 << 6)
+/* Flag that BO sharing will be explicitly synchronized */
+#define AMDGPU_GEM_CREATE_EXPLICIT_SYNC		(1 << 7)
+/* Flag that indicates allocating MQD gart on GFX9, where the mtype
+ * for the second page onward should be set to NC. It should never
+ * be used by user space applications.
+ */
+#define AMDGPU_GEM_CREATE_CP_MQD_GFX9		(1 << 8)
+/* Flag that BO may contain sensitive data that must be wiped before
+ * releasing the memory
+ */
+#define AMDGPU_GEM_CREATE_VRAM_WIPE_ON_RELEASE	(1 << 9)
+/* Flag that BO will be encrypted and that the TMZ bit should be
+ * set in the PTEs when mapping this buffer via GPUVM or
+ * accessing it with various hw blocks
+ */
+#define AMDGPU_GEM_CREATE_ENCRYPTED		(1 << 10)
+/* Flag that BO will be used only in preemptible context, which does
+ * not require GTT memory accounting
+ */
+#define AMDGPU_GEM_CREATE_PREEMPTIBLE		(1 << 11)
+/* Flag that BO can be discarded under memory pressure without keeping the
+ * content.
+ */
+#define AMDGPU_GEM_CREATE_DISCARDABLE		(1 << 12)
+/* Flag that BO is shared coherently between multiple devices or CPU threads.
+ * May depend on GPU instructions to flush caches to system scope explicitly.
+ *
+ * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and
+ * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
+ */
+#define AMDGPU_GEM_CREATE_COHERENT		(1 << 13)
+/* Flag that BO should not be cached by GPU. Coherent without having to flush
+ * GPU caches explicitly
+ *
+ * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and
+ * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
+ */
+#define AMDGPU_GEM_CREATE_UNCACHED		(1 << 14)
+/* Flag that BO should be coherent across devices when using device-level
+ * atomics. May depend on GPU instructions to flush caches to device scope
+ * explicitly, promoting them to system scope automatically.
+ *
+ * This influences the choice of MTYPE in the PTEs on GFXv9 and later GPUs and
+ * may override the MTYPE selected in AMDGPU_VA_OP_MAP.
+ */
+#define AMDGPU_GEM_CREATE_EXT_COHERENT		(1 << 15)
+/* Set PTE.D and recompress during GTT->VRAM moves according to TILING flags. */
+#define AMDGPU_GEM_CREATE_GFX12_DCC		(1 << 16)
+
+struct drm_amdgpu_gem_create_in  {
+	/** the requested memory size */
+	__u64 bo_size;
+	/** physical start_addr alignment in bytes for some HW requirements */
+	__u64 alignment;
+	/** the requested memory domains */
+	__u64 domains;
+	/** allocation flags */
+	__u64 domain_flags;
+};
+
+struct drm_amdgpu_gem_create_out  {
+	/** returned GEM object handle */
+	__u32 handle;
+	__u32 _pad;
+};
+
+union drm_amdgpu_gem_create {
+	struct drm_amdgpu_gem_create_in		in;
+	struct drm_amdgpu_gem_create_out	out;
+};
+
+/** Opcode to create new residency list.  */
+#define AMDGPU_BO_LIST_OP_CREATE	0
+/** Opcode to destroy previously created residency list */
+#define AMDGPU_BO_LIST_OP_DESTROY	1
+/** Opcode to update resource information in the list */
+#define AMDGPU_BO_LIST_OP_UPDATE	2
+
+struct drm_amdgpu_bo_list_in {
+	/** Type of operation */
+	__u32 operation;
+	/** Handle of list or 0 if we want to create one */
+	__u32 list_handle;
+	/** Number of BOs in list  */
+	__u32 bo_number;
+	/** Size of each element describing BO */
+	__u32 bo_info_size;
+	/** Pointer to array describing BOs */
+	__u64 bo_info_ptr;
+};
+
+struct drm_amdgpu_bo_list_entry {
+	/** Handle of BO */
+	__u32 bo_handle;
+	/** New (if specified) BO priority to be used during migration */
+	__u32 bo_priority;
+};
+
+struct drm_amdgpu_bo_list_out {
+	/** Handle of resource list  */
+	__u32 list_handle;
+	__u32 _pad;
+};
+
+union drm_amdgpu_bo_list {
+	struct drm_amdgpu_bo_list_in in;
+	struct drm_amdgpu_bo_list_out out;
+};
+
+/* context related */
+#define AMDGPU_CTX_OP_ALLOC_CTX	1
+#define AMDGPU_CTX_OP_FREE_CTX	2
+#define AMDGPU_CTX_OP_QUERY_STATE	3
+#define AMDGPU_CTX_OP_QUERY_STATE2	4
+#define AMDGPU_CTX_OP_GET_STABLE_PSTATE	5
+#define AMDGPU_CTX_OP_SET_STABLE_PSTATE	6
+
+/* GPU reset status */
+#define AMDGPU_CTX_NO_RESET		0
+/* this the context caused it */
+#define AMDGPU_CTX_GUILTY_RESET		1
+/* some other context caused it */
+#define AMDGPU_CTX_INNOCENT_RESET	2
+/* unknown cause */
+#define AMDGPU_CTX_UNKNOWN_RESET	3
+
+/* indicate gpu reset occurred after ctx created */
+#define AMDGPU_CTX_QUERY2_FLAGS_RESET    (1<<0)
+/* indicate vram lost occurred after ctx created */
+#define AMDGPU_CTX_QUERY2_FLAGS_VRAMLOST (1<<1)
+/* indicate some job from this context once cause gpu hang */
+#define AMDGPU_CTX_QUERY2_FLAGS_GUILTY   (1<<2)
+/* indicate some errors are detected by RAS */
+#define AMDGPU_CTX_QUERY2_FLAGS_RAS_CE   (1<<3)
+#define AMDGPU_CTX_QUERY2_FLAGS_RAS_UE   (1<<4)
+/* indicate that the reset hasn't completed yet */
+#define AMDGPU_CTX_QUERY2_FLAGS_RESET_IN_PROGRESS (1<<5)
+
+/* Context priority level */
+#define AMDGPU_CTX_PRIORITY_UNSET       -2048
+#define AMDGPU_CTX_PRIORITY_VERY_LOW    -1023
+#define AMDGPU_CTX_PRIORITY_LOW         -512
+#define AMDGPU_CTX_PRIORITY_NORMAL      0
+/*
+ * When used in struct drm_amdgpu_ctx_in, a priority above NORMAL requires
+ * CAP_SYS_NICE or DRM_MASTER
+*/
+#define AMDGPU_CTX_PRIORITY_HIGH        512
+#define AMDGPU_CTX_PRIORITY_VERY_HIGH   1023
+
+/* select a stable profiling pstate for perfmon tools */
+#define AMDGPU_CTX_STABLE_PSTATE_FLAGS_MASK  0xf
+#define AMDGPU_CTX_STABLE_PSTATE_NONE  0
+#define AMDGPU_CTX_STABLE_PSTATE_STANDARD  1
+#define AMDGPU_CTX_STABLE_PSTATE_MIN_SCLK  2
+#define AMDGPU_CTX_STABLE_PSTATE_MIN_MCLK  3
+#define AMDGPU_CTX_STABLE_PSTATE_PEAK  4
+
+struct drm_amdgpu_ctx_in {
+	/** AMDGPU_CTX_OP_* */
+	__u32	op;
+	/** Flags */
+	__u32	flags;
+	__u32	ctx_id;
+	/** AMDGPU_CTX_PRIORITY_* */
+	__s32	priority;
+};
+
+union drm_amdgpu_ctx_out {
+		struct {
+			__u32	ctx_id;
+			__u32	_pad;
+		} alloc;
+
+		struct {
+			/** For future use, no flags defined so far */
+			__u64	flags;
+			/** Number of resets caused by this context so far. */
+			__u32	hangs;
+			/** Reset status since the last call of the ioctl. */
+			__u32	reset_status;
+		} state;
+
+		struct {
+			__u32	flags;
+			__u32	_pad;
+		} pstate;
+};
+
+union drm_amdgpu_ctx {
+	struct drm_amdgpu_ctx_in in;
+	union drm_amdgpu_ctx_out out;
+};
+
+/* user queue IOCTL operations */
+#define AMDGPU_USERQ_OP_CREATE	1
+#define AMDGPU_USERQ_OP_FREE	2
+
+/* queue priority levels */
+/* low < normal low < normal high < high */
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK  0x3
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_SHIFT 0
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_NORMAL_LOW 0
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_LOW 1
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_NORMAL_HIGH 2
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_HIGH 3 /* admin only */
+/* for queues that need access to protected content */
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE  (1 << 2)
+
+/*
+ * This structure is a container to pass input configuration
+ * info for all supported userqueue related operations.
+ * For operation AMDGPU_USERQ_OP_CREATE: user is expected
+ *  to set all fields, excep the parameter 'queue_id'.
+ * For operation AMDGPU_USERQ_OP_FREE: the only input parameter expected
+ *  to be set is 'queue_id', eveything else is ignored.
+ */
+struct drm_amdgpu_userq_in {
+	/** AMDGPU_USERQ_OP_* */
+	__u32	op;
+	/** Queue id passed for operation USERQ_OP_FREE */
+	__u32	queue_id;
+	/** the target GPU engine to execute workload (AMDGPU_HW_IP_*) */
+	__u32   ip_type;
+	/**
+	 * @doorbell_handle: the handle of doorbell GEM object
+	 * associated with this userqueue client.
+	 */
+	__u32   doorbell_handle;
+	/**
+	 * @doorbell_offset: 32-bit offset of the doorbell in the doorbell bo.
+	 * Kernel will generate absolute doorbell offset using doorbell_handle
+	 * and doorbell_offset in the doorbell bo.
+	 */
+	__u32   doorbell_offset;
+	/**
+	 * @flags: flags used for queue parameters
+	 */
+	__u32 flags;
+	/**
+	 * @queue_va: Virtual address of the GPU memory which holds the queue
+	 * object. The queue holds the workload packets.
+	 */
+	__u64   queue_va;
+	/**
+	 * @queue_size: Size of the queue in bytes, this needs to be 256-byte
+	 * aligned.
+	 */
+	__u64   queue_size;
+	/**
+	 * @rptr_va : Virtual address of the GPU memory which holds the ring RPTR.
+	 * This object must be at least 8 byte in size and aligned to 8-byte offset.
+	 */
+	__u64   rptr_va;
+	/**
+	 * @wptr_va : Virtual address of the GPU memory which holds the ring WPTR.
+	 * This object must be at least 8 byte in size and aligned to 8-byte offset.
+	 *
+	 * Queue, RPTR and WPTR can come from the same object, as long as the size
+	 * and alignment related requirements are met.
+	 */
+	__u64   wptr_va;
+	/**
+	 * @mqd: MQD (memory queue descriptor) is a set of parameters which allow
+	 * the GPU to uniquely define and identify a usermode queue.
+	 *
+	 * MQD data can be of different size for different GPU IP/engine and
+	 * their respective versions/revisions, so this points to a __u64 *
+	 * which holds IP specific MQD of this usermode queue.
+	 */
+	__u64 mqd;
+	/**
+	 * @size: size of MQD data in bytes, it must match the MQD structure
+	 * size of the respective engine/revision defined in UAPI for ex, for
+	 * gfx11 workloads, size = sizeof(drm_amdgpu_userq_mqd_gfx11).
+	 */
+	__u64 mqd_size;
+};
+
+/* The structure to carry output of userqueue ops */
+struct drm_amdgpu_userq_out {
+	/**
+	 * For operation AMDGPU_USERQ_OP_CREATE: This field contains a unique
+	 * queue ID to represent the newly created userqueue in the system, otherwise
+	 * it should be ignored.
+	 */
+	__u32	queue_id;
+	__u32 _pad;
+};
+
+union drm_amdgpu_userq {
+	struct drm_amdgpu_userq_in in;
+	struct drm_amdgpu_userq_out out;
+};
+
+/* GFX V11 IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_gfx11 {
+	/**
+	 * @shadow_va: Virtual address of the GPU memory to hold the shadow buffer.
+	 * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+	 */
+	__u64   shadow_va;
+	/**
+	 * @csa_va: Virtual address of the GPU memory to hold the CSA buffer.
+	 * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+	 */
+	__u64   csa_va;
+};
+
+/* GFX V11 SDMA IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_sdma_gfx11 {
+	/**
+	 * @csa_va: Virtual address of the GPU memory to hold the CSA buffer.
+	 * This must be a from a separate GPU object, and use AMDGPU_INFO IOCTL
+	 * to get the size.
+	 */
+	__u64   csa_va;
+};
+
+/* GFX V11 Compute IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_compute_gfx11 {
+	/**
+	 * @eop_va: Virtual address of the GPU memory to hold the EOP buffer.
+	 * This must be a from a separate GPU object, and use AMDGPU_INFO IOCTL
+	 * to get the size.
+	 */
+	__u64   eop_va;
+};
+
+/* userq signal/wait ioctl */
+struct drm_amdgpu_userq_signal {
+	/**
+	 * @queue_id: Queue handle used by the userq fence creation function
+	 * to retrieve the WPTR.
+	 */
+	__u32	queue_id;
+	__u32	pad;
+	/**
+	 * @syncobj_handles: The list of syncobj handles submitted by the user queue
+	 * job to be signaled.
+	 */
+	__u64	syncobj_handles;
+	/**
+	 * @num_syncobj_handles: A count that represents the number of syncobj handles in
+	 * @syncobj_handles.
+	 */
+	__u16	num_syncobj_handles;
+	__u16	pad0;
+	__u32	pad1;
+	/**
+	 * @bo_read_handles: The list of BO handles that the submitted user queue job
+	 * is using for read only. This will update BO fences in the kernel.
+	 */
+	__u64	bo_read_handles;
+	/**
+	 * @bo_write_handles: The list of BO handles that the submitted user queue job
+	 * is using for write only. This will update BO fences in the kernel.
+	 */
+	__u64	bo_write_handles;
+	/**
+	 * @num_bo_read_handles: A count that represents the number of read BO handles in
+	 * @bo_read_handles.
+	 */
+	__u32	num_bo_read_handles;
+	/**
+	 * @num_bo_write_handles: A count that represents the number of write BO handles in
+	 * @bo_write_handles.
+	 */
+	__u32	num_bo_write_handles;
+};
+
+struct drm_amdgpu_userq_fence_info {
+	/**
+	 * @va: A gpu address allocated for each queue which stores the
+	 * read pointer (RPTR) value.
+	 */
+	__u64	va;
+	/**
+	 * @value: A 64 bit value represents the write pointer (WPTR) of the
+	 * queue commands which compared with the RPTR value to signal the
+	 * fences.
+	 */
+	__u64	value;
+};
+
+struct drm_amdgpu_userq_wait {
+	/**
+	 * @waitq_id: Queue handle used by the userq wait IOCTL to retrieve the
+	 * wait queue and maintain the fence driver references in it.
+	 */
+	__u32	waitq_id;
+	__u32	pad;
+	/**
+	 * @syncobj_handles: The list of syncobj handles submitted by the user queue
+	 * job to get the va/value pairs.
+	 */
+	__u64	syncobj_handles;
+	/**
+	 * @syncobj_timeline_handles: The list of timeline syncobj handles submitted by
+	 * the user queue job to get the va/value pairs at given @syncobj_timeline_points.
+	 */
+	__u64	syncobj_timeline_handles;
+	/**
+	 * @syncobj_timeline_points: The list of timeline syncobj points submitted by the
+	 * user queue job for the corresponding @syncobj_timeline_handles.
+	 */
+	__u64	syncobj_timeline_points;
+	/**
+	 * @bo_read_handles: The list of read BO handles submitted by the user queue
+	 * job to get the va/value pairs.
+	 */
+	__u64	bo_read_handles;
+	/**
+	 * @bo_write_handles: The list of write BO handles submitted by the user queue
+	 * job to get the va/value pairs.
+	 */
+	__u64	bo_write_handles;
+	/**
+	 * @num_syncobj_timeline_handles: A count that represents the number of timeline
+	 * syncobj handles in @syncobj_timeline_handles.
+	 */
+	__u16	num_syncobj_timeline_handles;
+	/**
+	 * @num_fences: This field can be used both as input and output. As input it defines
+	 * the maximum number of fences that can be returned and as output it will specify
+	 * how many fences were actually returned from the ioctl.
+	 */
+	__u16	num_fences;
+	/**
+	 * @num_syncobj_handles: A count that represents the number of syncobj handles in
+	 * @syncobj_handles.
+	 */
+	__u16	num_syncobj_handles;
+	__u16	pad0;
+	/**
+	 * @num_bo_read_handles: A count that represents the number of read BO handles in
+	 * @bo_read_handles.
+	 */
+	__u32	num_bo_read_handles;
+	/**
+	 * @num_bo_write_handles: A count that represents the number of write BO handles in
+	 * @bo_write_handles.
+	 */
+	__u32	num_bo_write_handles;
+	/**
+	 * @out_fences: The field is a return value from the ioctl containing the list of
+	 * address/value pairs to wait for.
+	 */
+	__u64	out_fences;
+};
+
+/* vm ioctl */
+#define AMDGPU_VM_OP_RESERVE_VMID	1
+#define AMDGPU_VM_OP_UNRESERVE_VMID	2
+
+struct drm_amdgpu_vm_in {
+	/** AMDGPU_VM_OP_* */
+	__u32	op;
+	__u32	flags;
+};
+
+struct drm_amdgpu_vm_out {
+	/** For future use, no flags defined so far */
+	__u64	flags;
+};
+
+union drm_amdgpu_vm {
+	struct drm_amdgpu_vm_in in;
+	struct drm_amdgpu_vm_out out;
+};
+
+/* sched ioctl */
+#define AMDGPU_SCHED_OP_PROCESS_PRIORITY_OVERRIDE	1
+#define AMDGPU_SCHED_OP_CONTEXT_PRIORITY_OVERRIDE	2
+
+struct drm_amdgpu_sched_in {
+	/* AMDGPU_SCHED_OP_* */
+	__u32	op;
+	__u32	fd;
+	/** AMDGPU_CTX_PRIORITY_* */
+	__s32	priority;
+	__u32   ctx_id;
+};
+
+union drm_amdgpu_sched {
+	struct drm_amdgpu_sched_in in;
+};
+
+/*
+ * This is not a reliable API and you should expect it to fail for any
+ * number of reasons and have fallback path that do not use userptr to
+ * perform any operation.
+ */
+#define AMDGPU_GEM_USERPTR_READONLY	(1 << 0)
+#define AMDGPU_GEM_USERPTR_ANONONLY	(1 << 1)
+#define AMDGPU_GEM_USERPTR_VALIDATE	(1 << 2)
+#define AMDGPU_GEM_USERPTR_REGISTER	(1 << 3)
+
+struct drm_amdgpu_gem_userptr {
+	__u64		addr;
+	__u64		size;
+	/* AMDGPU_GEM_USERPTR_* */
+	__u32		flags;
+	/* Resulting GEM handle */
+	__u32		handle;
+};
+
+/* SI-CI-VI: */
+/* same meaning as the GB_TILE_MODE and GL_MACRO_TILE_MODE fields */
+#define AMDGPU_TILING_ARRAY_MODE_SHIFT			0
+#define AMDGPU_TILING_ARRAY_MODE_MASK			0xf
+#define AMDGPU_TILING_PIPE_CONFIG_SHIFT			4
+#define AMDGPU_TILING_PIPE_CONFIG_MASK			0x1f
+#define AMDGPU_TILING_TILE_SPLIT_SHIFT			9
+#define AMDGPU_TILING_TILE_SPLIT_MASK			0x7
+#define AMDGPU_TILING_MICRO_TILE_MODE_SHIFT		12
+#define AMDGPU_TILING_MICRO_TILE_MODE_MASK		0x7
+#define AMDGPU_TILING_BANK_WIDTH_SHIFT			15
+#define AMDGPU_TILING_BANK_WIDTH_MASK			0x3
+#define AMDGPU_TILING_BANK_HEIGHT_SHIFT			17
+#define AMDGPU_TILING_BANK_HEIGHT_MASK			0x3
+#define AMDGPU_TILING_MACRO_TILE_ASPECT_SHIFT		19
+#define AMDGPU_TILING_MACRO_TILE_ASPECT_MASK		0x3
+#define AMDGPU_TILING_NUM_BANKS_SHIFT			21
+#define AMDGPU_TILING_NUM_BANKS_MASK			0x3
+
+/* GFX9 - GFX11: */
+#define AMDGPU_TILING_SWIZZLE_MODE_SHIFT		0
+#define AMDGPU_TILING_SWIZZLE_MODE_MASK			0x1f
+#define AMDGPU_TILING_DCC_OFFSET_256B_SHIFT		5
+#define AMDGPU_TILING_DCC_OFFSET_256B_MASK		0xFFFFFF
+#define AMDGPU_TILING_DCC_PITCH_MAX_SHIFT		29
+#define AMDGPU_TILING_DCC_PITCH_MAX_MASK		0x3FFF
+#define AMDGPU_TILING_DCC_INDEPENDENT_64B_SHIFT		43
+#define AMDGPU_TILING_DCC_INDEPENDENT_64B_MASK		0x1
+#define AMDGPU_TILING_DCC_INDEPENDENT_128B_SHIFT	44
+#define AMDGPU_TILING_DCC_INDEPENDENT_128B_MASK		0x1
+#define AMDGPU_TILING_SCANOUT_SHIFT			63
+#define AMDGPU_TILING_SCANOUT_MASK			0x1
+
+/* GFX12 and later: */
+#define AMDGPU_TILING_GFX12_SWIZZLE_MODE_SHIFT			0
+#define AMDGPU_TILING_GFX12_SWIZZLE_MODE_MASK			0x7
+/* These are DCC recompression settings for memory management: */
+#define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_SHIFT	3
+#define AMDGPU_TILING_GFX12_DCC_MAX_COMPRESSED_BLOCK_MASK	0x3 /* 0:64B, 1:128B, 2:256B */
+#define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_SHIFT		5
+#define AMDGPU_TILING_GFX12_DCC_NUMBER_TYPE_MASK		0x7 /* CB_COLOR0_INFO.NUMBER_TYPE */
+#define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_SHIFT		8
+#define AMDGPU_TILING_GFX12_DCC_DATA_FORMAT_MASK		0x3f /* [0:4]:CB_COLOR0_INFO.FORMAT, [5]:MM */
+/* When clearing the buffer or moving it from VRAM to GTT, don't compress and set DCC metadata
+ * to uncompressed. Set when parts of an allocation bypass DCC and read raw data. */
+#define AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE_SHIFT	14
+#define AMDGPU_TILING_GFX12_DCC_WRITE_COMPRESS_DISABLE_MASK	0x1
+/* bit gap */
+#define AMDGPU_TILING_GFX12_SCANOUT_SHIFT			63
+#define AMDGPU_TILING_GFX12_SCANOUT_MASK			0x1
+
+/* Set/Get helpers for tiling flags. */
+#define AMDGPU_TILING_SET(field, value) \
+	(((__u64)(value) & AMDGPU_TILING_##field##_MASK) << AMDGPU_TILING_##field##_SHIFT)
+#define AMDGPU_TILING_GET(value, field) \
+	(((__u64)(value) >> AMDGPU_TILING_##field##_SHIFT) & AMDGPU_TILING_##field##_MASK)
+
+#define AMDGPU_GEM_METADATA_OP_SET_METADATA                  1
+#define AMDGPU_GEM_METADATA_OP_GET_METADATA                  2
+
+/** The same structure is shared for input/output */
+struct drm_amdgpu_gem_metadata {
+	/** GEM Object handle */
+	__u32	handle;
+	/** Do we want get or set metadata */
+	__u32	op;
+	struct {
+		/** For future use, no flags defined so far */
+		__u64	flags;
+		/** family specific tiling info */
+		__u64	tiling_info;
+		__u32	data_size_bytes;
+		__u32	data[64];
+	} data;
+};
+
+struct drm_amdgpu_gem_mmap_in {
+	/** the GEM object handle */
+	__u32 handle;
+	__u32 _pad;
+};
+
+struct drm_amdgpu_gem_mmap_out {
+	/** mmap offset from the vma offset manager */
+	__u64 addr_ptr;
+};
+
+union drm_amdgpu_gem_mmap {
+	struct drm_amdgpu_gem_mmap_in   in;
+	struct drm_amdgpu_gem_mmap_out out;
+};
+
+struct drm_amdgpu_gem_wait_idle_in {
+	/** GEM object handle */
+	__u32 handle;
+	/** For future use, no flags defined so far */
+	__u32 flags;
+	/** Absolute timeout to wait */
+	__u64 timeout;
+};
+
+struct drm_amdgpu_gem_wait_idle_out {
+	/** BO status:  0 - BO is idle, 1 - BO is busy */
+	__u32 status;
+	/** Returned current memory domain */
+	__u32 domain;
+};
+
+union drm_amdgpu_gem_wait_idle {
+	struct drm_amdgpu_gem_wait_idle_in  in;
+	struct drm_amdgpu_gem_wait_idle_out out;
+};
+
+struct drm_amdgpu_wait_cs_in {
+	/* Command submission handle
+         * handle equals 0 means none to wait for
+         * handle equals ~0ull means wait for the latest sequence number
+         */
+	__u64 handle;
+	/** Absolute timeout to wait */
+	__u64 timeout;
+	__u32 ip_type;
+	__u32 ip_instance;
+	__u32 ring;
+	__u32 ctx_id;
+};
+
+struct drm_amdgpu_wait_cs_out {
+	/** CS status:  0 - CS completed, 1 - CS still busy */
+	__u64 status;
+};
+
+union drm_amdgpu_wait_cs {
+	struct drm_amdgpu_wait_cs_in in;
+	struct drm_amdgpu_wait_cs_out out;
+};
+
+struct drm_amdgpu_fence {
+	__u32 ctx_id;
+	__u32 ip_type;
+	__u32 ip_instance;
+	__u32 ring;
+	__u64 seq_no;
+};
+
+struct drm_amdgpu_wait_fences_in {
+	/** This points to uint64_t * which points to fences */
+	__u64 fences;
+	__u32 fence_count;
+	__u32 wait_all;
+	__u64 timeout_ns;
+};
+
+struct drm_amdgpu_wait_fences_out {
+	__u32 status;
+	__u32 first_signaled;
+};
+
+union drm_amdgpu_wait_fences {
+	struct drm_amdgpu_wait_fences_in in;
+	struct drm_amdgpu_wait_fences_out out;
+};
+
+#define AMDGPU_GEM_OP_GET_GEM_CREATE_INFO	0
+#define AMDGPU_GEM_OP_SET_PLACEMENT		1
+#define AMDGPU_GEM_OP_GET_MAPPING_INFO		2
+
+struct drm_amdgpu_gem_vm_entry {
+	/* Start of mapping (in bytes) */
+	__u64 addr;
+
+	/* Size of mapping (in bytes) */
+	__u64 size;
+
+	/* Mapping offset */
+	__u64 offset;
+
+	/* flags needed to recreate mapping */
+	__u64 flags;
+};
+
+/* Sets or returns a value associated with a buffer. */
+struct drm_amdgpu_gem_op {
+	/** GEM object handle */
+	__u32	handle;
+	/** AMDGPU_GEM_OP_* */
+	__u32	op;
+	/** Input or return value. For MAPPING_INFO op: pointer to array of struct drm_amdgpu_gem_vm_entry */
+	__u64	value;
+	/** For MAPPING_INFO op: number of mappings (in/out) */
+	__u32	num_entries;
+
+	__u32	padding;
+};
+
+#define AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT	(1 << 0)
+
+struct drm_amdgpu_gem_list_handles {
+	/* User pointer to array of drm_amdgpu_gem_bo_info_entry */
+	__u64   entries;
+
+	/* Size of entries buffer / Number of handles in process (if larger than size of buffer, must retry) */
+	__u32   num_entries;
+
+	__u32 padding;
+};
+
+struct drm_amdgpu_gem_list_handles_entry {
+	/* gem handle of buffer object */
+	__u32 gem_handle;
+
+	/* Currently just one flag: IS_IMPORT */
+	__u32 flags;
+
+	/* Size of bo */
+	__u64 size;
+
+	/* Preferred domains for GEM_CREATE */
+	__u64 preferred_domains;
+
+	/* GEM_CREATE flags for re-creation of buffer */
+	__u64 alloc_flags;
+
+	/* physical start_addr alignment in bytes for some HW requirements */
+	__u64 alignment;
+};
+
+#define AMDGPU_VA_OP_MAP			1
+#define AMDGPU_VA_OP_UNMAP			2
+#define AMDGPU_VA_OP_CLEAR			3
+#define AMDGPU_VA_OP_REPLACE			4
+
+/* Delay the page table update till the next CS */
+#define AMDGPU_VM_DELAY_UPDATE		(1 << 0)
+
+/* Mapping flags */
+/* readable mapping */
+#define AMDGPU_VM_PAGE_READABLE		(1 << 1)
+/* writable mapping */
+#define AMDGPU_VM_PAGE_WRITEABLE	(1 << 2)
+/* executable mapping, new for VI */
+#define AMDGPU_VM_PAGE_EXECUTABLE	(1 << 3)
+/* unmapped page of partially resident textures */
+#define AMDGPU_VM_PAGE_PRT		(1 << 4)
+/* MTYPE flags use bit 5 to 8 */
+#define AMDGPU_VM_MTYPE_MASK		(0xf << 5)
+/* Default MTYPE. Pre-AI must use this.  Recommended for newer ASICs. */
+#define AMDGPU_VM_MTYPE_DEFAULT		(0 << 5)
+/* Use Non Coherent MTYPE instead of default MTYPE */
+#define AMDGPU_VM_MTYPE_NC		(1 << 5)
+/* Use Write Combine MTYPE instead of default MTYPE */
+#define AMDGPU_VM_MTYPE_WC		(2 << 5)
+/* Use Cache Coherent MTYPE instead of default MTYPE */
+#define AMDGPU_VM_MTYPE_CC		(3 << 5)
+/* Use UnCached MTYPE instead of default MTYPE */
+#define AMDGPU_VM_MTYPE_UC		(4 << 5)
+/* Use Read Write MTYPE instead of default MTYPE */
+#define AMDGPU_VM_MTYPE_RW		(5 << 5)
+/* don't allocate MALL */
+#define AMDGPU_VM_PAGE_NOALLOC		(1 << 9)
+
+struct drm_amdgpu_gem_va {
+	/** GEM object handle */
+	__u32 handle;
+	__u32 _pad;
+	/** AMDGPU_VA_OP_* */
+	__u32 operation;
+	/** AMDGPU_VM_PAGE_* */
+	__u32 flags;
+	/** va address to assign . Must be correctly aligned.*/
+	__u64 va_address;
+	/** Specify offset inside of BO to assign. Must be correctly aligned.*/
+	__u64 offset_in_bo;
+	/** Specify mapping size. Must be correctly aligned. */
+	__u64 map_size;
+	/**
+	 * vm_timeline_point is a sequence number used to add new timeline point.
+	 */
+	__u64 vm_timeline_point;
+	/**
+	 * The vm page table update fence is installed in given vm_timeline_syncobj_out
+	 * at vm_timeline_point.
+	 */
+	__u32 vm_timeline_syncobj_out;
+	/** the number of syncobj handles in @input_fence_syncobj_handles */
+	__u32 num_syncobj_handles;
+	/** Array of sync object handle to wait for given input fences */
+	__u64 input_fence_syncobj_handles;
+};
+
+#define AMDGPU_HW_IP_GFX          0
+#define AMDGPU_HW_IP_COMPUTE      1
+#define AMDGPU_HW_IP_DMA          2
+#define AMDGPU_HW_IP_UVD          3
+#define AMDGPU_HW_IP_VCE          4
+#define AMDGPU_HW_IP_UVD_ENC      5
+#define AMDGPU_HW_IP_VCN_DEC      6
+/*
+ * From VCN4, AMDGPU_HW_IP_VCN_ENC is re-used to support
+ * both encoding and decoding jobs.
+ */
+#define AMDGPU_HW_IP_VCN_ENC      7
+#define AMDGPU_HW_IP_VCN_JPEG     8
+#define AMDGPU_HW_IP_VPE          9
+#define AMDGPU_HW_IP_NUM          10
+
+#define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1
+
+#define AMDGPU_CHUNK_ID_IB		0x01
+#define AMDGPU_CHUNK_ID_FENCE		0x02
+#define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
+#define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
+#define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
+#define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
+#define AMDGPU_CHUNK_ID_SCHEDULED_DEPENDENCIES	0x07
+#define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_WAIT    0x08
+#define AMDGPU_CHUNK_ID_SYNCOBJ_TIMELINE_SIGNAL  0x09
+#define AMDGPU_CHUNK_ID_CP_GFX_SHADOW   0x0a
+
+struct drm_amdgpu_cs_chunk {
+	__u32		chunk_id;
+	__u32		length_dw;
+	__u64		chunk_data;
+};
+
+struct drm_amdgpu_cs_in {
+	/** Rendering context id */
+	__u32		ctx_id;
+	/**  Handle of resource list associated with CS */
+	__u32		bo_list_handle;
+	__u32		num_chunks;
+	__u32		flags;
+	/** this points to __u64 * which point to cs chunks */
+	__u64		chunks;
+};
+
+struct drm_amdgpu_cs_out {
+	__u64 handle;
+};
+
+union drm_amdgpu_cs {
+	struct drm_amdgpu_cs_in in;
+	struct drm_amdgpu_cs_out out;
+};
+
+/* Specify flags to be used for IB */
+
+/* This IB should be submitted to CE */
+#define AMDGPU_IB_FLAG_CE	(1<<0)
+
+/* Preamble flag, which means the IB could be dropped if no context switch */
+#define AMDGPU_IB_FLAG_PREAMBLE (1<<1)
+
+/* Preempt flag, IB should set Pre_enb bit if PREEMPT flag detected */
+#define AMDGPU_IB_FLAG_PREEMPT (1<<2)
+
+/* The IB fence should do the L2 writeback but not invalidate any shader
+ * caches (L2/vL1/sL1/I$). */
+#define AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE (1 << 3)
+
+/* Set GDS_COMPUTE_MAX_WAVE_ID = DEFAULT before PACKET3_INDIRECT_BUFFER.
+ * This will reset wave ID counters for the IB.
+ */
+#define AMDGPU_IB_FLAG_RESET_GDS_MAX_WAVE_ID (1 << 4)
+
+/* Flag the IB as secure (TMZ)
+ */
+#define AMDGPU_IB_FLAGS_SECURE  (1 << 5)
+
+/* Tell KMD to flush and invalidate caches
+ */
+#define AMDGPU_IB_FLAG_EMIT_MEM_SYNC  (1 << 6)
+
+struct drm_amdgpu_cs_chunk_ib {
+	__u32 _pad;
+	/** AMDGPU_IB_FLAG_* */
+	__u32 flags;
+	/** Virtual address to begin IB execution */
+	__u64 va_start;
+	/** Size of submission */
+	__u32 ib_bytes;
+	/** HW IP to submit to */
+	__u32 ip_type;
+	/** HW IP index of the same type to submit to  */
+	__u32 ip_instance;
+	/** Ring index to submit to */
+	__u32 ring;
+};
+
+struct drm_amdgpu_cs_chunk_dep {
+	__u32 ip_type;
+	__u32 ip_instance;
+	__u32 ring;
+	__u32 ctx_id;
+	__u64 handle;
+};
+
+struct drm_amdgpu_cs_chunk_fence {
+	__u32 handle;
+	__u32 offset;
+};
+
+struct drm_amdgpu_cs_chunk_sem {
+	__u32 handle;
+};
+
+struct drm_amdgpu_cs_chunk_syncobj {
+       __u32 handle;
+       __u32 flags;
+       __u64 point;
+};
+
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ	0
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNCOBJ_FD	1
+#define AMDGPU_FENCE_TO_HANDLE_GET_SYNC_FILE_FD	2
+
+union drm_amdgpu_fence_to_handle {
+	struct {
+		struct drm_amdgpu_fence fence;
+		__u32 what;
+		__u32 pad;
+	} in;
+	struct {
+		__u32 handle;
+	} out;
+};
+
+struct drm_amdgpu_cs_chunk_data {
+	union {
+		struct drm_amdgpu_cs_chunk_ib		ib_data;
+		struct drm_amdgpu_cs_chunk_fence	fence_data;
+	};
+};
+
+#define AMDGPU_CS_CHUNK_CP_GFX_SHADOW_FLAGS_INIT_SHADOW         0x1
+
+struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
+	__u64 shadow_va;
+	__u64 csa_va;
+	__u64 gds_va;
+	__u64 flags;
+};
+
+/*
+ *  Query h/w info: Flag that this is integrated (a.h.a. fusion) GPU
+ *
+ */
+#define AMDGPU_IDS_FLAGS_FUSION			0x01
+#define AMDGPU_IDS_FLAGS_PREEMPTION		0x02
+#define AMDGPU_IDS_FLAGS_TMZ			0x04
+#define AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD	0x08
+#define AMDGPU_IDS_FLAGS_GANG_SUBMIT		0x10
+
+/*
+ *  Query h/w info: Flag identifying VF/PF/PT mode
+ *
+ */
+#define AMDGPU_IDS_FLAGS_MODE_MASK      0x300
+#define AMDGPU_IDS_FLAGS_MODE_SHIFT     0x8
+#define AMDGPU_IDS_FLAGS_MODE_PF        0x0
+#define AMDGPU_IDS_FLAGS_MODE_VF        0x1
+#define AMDGPU_IDS_FLAGS_MODE_PT        0x2
+
+/* indicate if acceleration can be working */
+#define AMDGPU_INFO_ACCEL_WORKING		0x00
+/* get the crtc_id from the mode object id? */
+#define AMDGPU_INFO_CRTC_FROM_ID		0x01
+/* query hw IP info */
+#define AMDGPU_INFO_HW_IP_INFO			0x02
+/* query hw IP instance count for the specified type */
+#define AMDGPU_INFO_HW_IP_COUNT			0x03
+/* timestamp for GL_ARB_timer_query */
+#define AMDGPU_INFO_TIMESTAMP			0x05
+/* Query the firmware version */
+#define AMDGPU_INFO_FW_VERSION			0x0e
+	/* Subquery id: Query VCE firmware version */
+	#define AMDGPU_INFO_FW_VCE		0x1
+	/* Subquery id: Query UVD firmware version */
+	#define AMDGPU_INFO_FW_UVD		0x2
+	/* Subquery id: Query GMC firmware version */
+	#define AMDGPU_INFO_FW_GMC		0x03
+	/* Subquery id: Query GFX ME firmware version */
+	#define AMDGPU_INFO_FW_GFX_ME		0x04
+	/* Subquery id: Query GFX PFP firmware version */
+	#define AMDGPU_INFO_FW_GFX_PFP		0x05
+	/* Subquery id: Query GFX CE firmware version */
+	#define AMDGPU_INFO_FW_GFX_CE		0x06
+	/* Subquery id: Query GFX RLC firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC		0x07
+	/* Subquery id: Query GFX MEC firmware version */
+	#define AMDGPU_INFO_FW_GFX_MEC		0x08
+	/* Subquery id: Query SMC firmware version */
+	#define AMDGPU_INFO_FW_SMC		0x0a
+	/* Subquery id: Query SDMA firmware version */
+	#define AMDGPU_INFO_FW_SDMA		0x0b
+	/* Subquery id: Query PSP SOS firmware version */
+	#define AMDGPU_INFO_FW_SOS		0x0c
+	/* Subquery id: Query PSP ASD firmware version */
+	#define AMDGPU_INFO_FW_ASD		0x0d
+	/* Subquery id: Query VCN firmware version */
+	#define AMDGPU_INFO_FW_VCN		0x0e
+	/* Subquery id: Query GFX RLC SRLC firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_CNTL 0x0f
+	/* Subquery id: Query GFX RLC SRLG firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_GPM_MEM 0x10
+	/* Subquery id: Query GFX RLC SRLS firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLC_RESTORE_LIST_SRM_MEM 0x11
+	/* Subquery id: Query DMCU firmware version */
+	#define AMDGPU_INFO_FW_DMCU		0x12
+	#define AMDGPU_INFO_FW_TA		0x13
+	/* Subquery id: Query DMCUB firmware version */
+	#define AMDGPU_INFO_FW_DMCUB		0x14
+	/* Subquery id: Query TOC firmware version */
+	#define AMDGPU_INFO_FW_TOC		0x15
+	/* Subquery id: Query CAP firmware version */
+	#define AMDGPU_INFO_FW_CAP		0x16
+	/* Subquery id: Query GFX RLCP firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLCP		0x17
+	/* Subquery id: Query GFX RLCV firmware version */
+	#define AMDGPU_INFO_FW_GFX_RLCV		0x18
+	/* Subquery id: Query MES_KIQ firmware version */
+	#define AMDGPU_INFO_FW_MES_KIQ		0x19
+	/* Subquery id: Query MES firmware version */
+	#define AMDGPU_INFO_FW_MES		0x1a
+	/* Subquery id: Query IMU firmware version */
+	#define AMDGPU_INFO_FW_IMU		0x1b
+	/* Subquery id: Query VPE firmware version */
+	#define AMDGPU_INFO_FW_VPE		0x1c
+
+/* number of bytes moved for TTM migration */
+#define AMDGPU_INFO_NUM_BYTES_MOVED		0x0f
+/* the used VRAM size */
+#define AMDGPU_INFO_VRAM_USAGE			0x10
+/* the used GTT size */
+#define AMDGPU_INFO_GTT_USAGE			0x11
+/* Information about GDS, etc. resource configuration */
+#define AMDGPU_INFO_GDS_CONFIG			0x13
+/* Query information about VRAM and GTT domains */
+#define AMDGPU_INFO_VRAM_GTT			0x14
+/* Query information about register in MMR address space*/
+#define AMDGPU_INFO_READ_MMR_REG		0x15
+/* Query information about device: rev id, family, etc. */
+#define AMDGPU_INFO_DEV_INFO			0x16
+/* visible vram usage */
+#define AMDGPU_INFO_VIS_VRAM_USAGE		0x17
+/* number of TTM buffer evictions */
+#define AMDGPU_INFO_NUM_EVICTIONS		0x18
+/* Query memory about VRAM and GTT domains */
+#define AMDGPU_INFO_MEMORY			0x19
+/* Query vce clock table */
+#define AMDGPU_INFO_VCE_CLOCK_TABLE		0x1A
+/* Query vbios related information */
+#define AMDGPU_INFO_VBIOS			0x1B
+	/* Subquery id: Query vbios size */
+	#define AMDGPU_INFO_VBIOS_SIZE		0x1
+	/* Subquery id: Query vbios image */
+	#define AMDGPU_INFO_VBIOS_IMAGE		0x2
+	/* Subquery id: Query vbios info */
+	#define AMDGPU_INFO_VBIOS_INFO		0x3
+/* Query UVD handles */
+#define AMDGPU_INFO_NUM_HANDLES			0x1C
+/* Query sensor related information */
+#define AMDGPU_INFO_SENSOR			0x1D
+	/* Subquery id: Query GPU shader clock */
+	#define AMDGPU_INFO_SENSOR_GFX_SCLK		0x1
+	/* Subquery id: Query GPU memory clock */
+	#define AMDGPU_INFO_SENSOR_GFX_MCLK		0x2
+	/* Subquery id: Query GPU temperature */
+	#define AMDGPU_INFO_SENSOR_GPU_TEMP		0x3
+	/* Subquery id: Query GPU load */
+	#define AMDGPU_INFO_SENSOR_GPU_LOAD		0x4
+	/* Subquery id: Query average GPU power	*/
+	#define AMDGPU_INFO_SENSOR_GPU_AVG_POWER	0x5
+	/* Subquery id: Query northbridge voltage */
+	#define AMDGPU_INFO_SENSOR_VDDNB		0x6
+	/* Subquery id: Query graphics voltage */
+	#define AMDGPU_INFO_SENSOR_VDDGFX		0x7
+	/* Subquery id: Query GPU stable pstate shader clock */
+	#define AMDGPU_INFO_SENSOR_STABLE_PSTATE_GFX_SCLK		0x8
+	/* Subquery id: Query GPU stable pstate memory clock */
+	#define AMDGPU_INFO_SENSOR_STABLE_PSTATE_GFX_MCLK		0x9
+	/* Subquery id: Query GPU peak pstate shader clock */
+	#define AMDGPU_INFO_SENSOR_PEAK_PSTATE_GFX_SCLK			0xa
+	/* Subquery id: Query GPU peak pstate memory clock */
+	#define AMDGPU_INFO_SENSOR_PEAK_PSTATE_GFX_MCLK			0xb
+	/* Subquery id: Query input GPU power	*/
+	#define AMDGPU_INFO_SENSOR_GPU_INPUT_POWER	0xc
+/* Number of VRAM page faults on CPU access. */
+#define AMDGPU_INFO_NUM_VRAM_CPU_PAGE_FAULTS	0x1E
+#define AMDGPU_INFO_VRAM_LOST_COUNTER		0x1F
+/* query ras mask of enabled features*/
+#define AMDGPU_INFO_RAS_ENABLED_FEATURES	0x20
+/* RAS MASK: UMC (VRAM) */
+#define AMDGPU_INFO_RAS_ENABLED_UMC			(1 << 0)
+/* RAS MASK: SDMA */
+#define AMDGPU_INFO_RAS_ENABLED_SDMA			(1 << 1)
+/* RAS MASK: GFX */
+#define AMDGPU_INFO_RAS_ENABLED_GFX			(1 << 2)
+/* RAS MASK: MMHUB */
+#define AMDGPU_INFO_RAS_ENABLED_MMHUB			(1 << 3)
+/* RAS MASK: ATHUB */
+#define AMDGPU_INFO_RAS_ENABLED_ATHUB			(1 << 4)
+/* RAS MASK: PCIE */
+#define AMDGPU_INFO_RAS_ENABLED_PCIE			(1 << 5)
+/* RAS MASK: HDP */
+#define AMDGPU_INFO_RAS_ENABLED_HDP			(1 << 6)
+/* RAS MASK: XGMI */
+#define AMDGPU_INFO_RAS_ENABLED_XGMI			(1 << 7)
+/* RAS MASK: DF */
+#define AMDGPU_INFO_RAS_ENABLED_DF			(1 << 8)
+/* RAS MASK: SMN */
+#define AMDGPU_INFO_RAS_ENABLED_SMN			(1 << 9)
+/* RAS MASK: SEM */
+#define AMDGPU_INFO_RAS_ENABLED_SEM			(1 << 10)
+/* RAS MASK: MP0 */
+#define AMDGPU_INFO_RAS_ENABLED_MP0			(1 << 11)
+/* RAS MASK: MP1 */
+#define AMDGPU_INFO_RAS_ENABLED_MP1			(1 << 12)
+/* RAS MASK: FUSE */
+#define AMDGPU_INFO_RAS_ENABLED_FUSE			(1 << 13)
+/* query video encode/decode caps */
+#define AMDGPU_INFO_VIDEO_CAPS			0x21
+	/* Subquery id: Decode */
+	#define AMDGPU_INFO_VIDEO_CAPS_DECODE		0
+	/* Subquery id: Encode */
+	#define AMDGPU_INFO_VIDEO_CAPS_ENCODE		1
+/* Query the max number of IBs per gang per submission */
+#define AMDGPU_INFO_MAX_IBS			0x22
+/* query last page fault info */
+#define AMDGPU_INFO_GPUVM_FAULT			0x23
+/* query FW object size and alignment */
+#define AMDGPU_INFO_UQ_FW_AREAS			0x24
+
+#define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
+#define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
+#define AMDGPU_INFO_MMR_SH_INDEX_SHIFT	8
+#define AMDGPU_INFO_MMR_SH_INDEX_MASK	0xff
+
+struct drm_amdgpu_query_fw {
+	/** AMDGPU_INFO_FW_* */
+	__u32 fw_type;
+	/**
+	 * Index of the IP if there are more IPs of
+	 * the same type.
+	 */
+	__u32 ip_instance;
+	/**
+	 * Index of the engine. Whether this is used depends
+	 * on the firmware type. (e.g. MEC, SDMA)
+	 */
+	__u32 index;
+	__u32 _pad;
+};
+
+/* Input structure for the INFO ioctl */
+struct drm_amdgpu_info {
+	/* Where the return value will be stored */
+	__u64 return_pointer;
+	/* The size of the return value. Just like "size" in "snprintf",
+	 * it limits how many bytes the kernel can write. */
+	__u32 return_size;
+	/* The query request id. */
+	__u32 query;
+
+	union {
+		struct {
+			__u32 id;
+			__u32 _pad;
+		} mode_crtc;
+
+		struct {
+			/** AMDGPU_HW_IP_* */
+			__u32 type;
+			/**
+			 * Index of the IP if there are more IPs of the same
+			 * type. Ignored by AMDGPU_INFO_HW_IP_COUNT.
+			 */
+			__u32 ip_instance;
+		} query_hw_ip;
+
+		struct {
+			__u32 dword_offset;
+			/** number of registers to read */
+			__u32 count;
+			__u32 instance;
+			/** For future use, no flags defined so far */
+			__u32 flags;
+		} read_mmr_reg;
+
+		struct drm_amdgpu_query_fw query_fw;
+
+		struct {
+			__u32 type;
+			__u32 offset;
+		} vbios_info;
+
+		struct {
+			__u32 type;
+		} sensor_info;
+
+		struct {
+			__u32 type;
+		} video_cap;
+	};
+};
+
+struct drm_amdgpu_info_gds {
+	/** GDS GFX partition size */
+	__u32 gds_gfx_partition_size;
+	/** GDS compute partition size */
+	__u32 compute_partition_size;
+	/** total GDS memory size */
+	__u32 gds_total_size;
+	/** GWS size per GFX partition */
+	__u32 gws_per_gfx_partition;
+	/** GSW size per compute partition */
+	__u32 gws_per_compute_partition;
+	/** OA size per GFX partition */
+	__u32 oa_per_gfx_partition;
+	/** OA size per compute partition */
+	__u32 oa_per_compute_partition;
+	__u32 _pad;
+};
+
+struct drm_amdgpu_info_vram_gtt {
+	__u64 vram_size;
+	__u64 vram_cpu_accessible_size;
+	__u64 gtt_size;
+};
+
+struct drm_amdgpu_heap_info {
+	/** max. physical memory */
+	__u64 total_heap_size;
+
+	/** Theoretical max. available memory in the given heap */
+	__u64 usable_heap_size;
+
+	/**
+	 * Number of bytes allocated in the heap. This includes all processes
+	 * and private allocations in the kernel. It changes when new buffers
+	 * are allocated, freed, and moved. It cannot be larger than
+	 * heap_size.
+	 */
+	__u64 heap_usage;
+
+	/**
+	 * Theoretical possible max. size of buffer which
+	 * could be allocated in the given heap
+	 */
+	__u64 max_allocation;
+};
+
+struct drm_amdgpu_memory_info {
+	struct drm_amdgpu_heap_info vram;
+	struct drm_amdgpu_heap_info cpu_accessible_vram;
+	struct drm_amdgpu_heap_info gtt;
+};
+
+struct drm_amdgpu_info_firmware {
+	__u32 ver;
+	__u32 feature;
+};
+
+struct drm_amdgpu_info_vbios {
+	__u8 name[64];
+	__u8 vbios_pn[64];
+	__u32 version;
+	__u32 pad;
+	__u8 vbios_ver_str[32];
+	__u8 date[32];
+};
+
+#define AMDGPU_VRAM_TYPE_UNKNOWN 0
+#define AMDGPU_VRAM_TYPE_GDDR1 1
+#define AMDGPU_VRAM_TYPE_DDR2  2
+#define AMDGPU_VRAM_TYPE_GDDR3 3
+#define AMDGPU_VRAM_TYPE_GDDR4 4
+#define AMDGPU_VRAM_TYPE_GDDR5 5
+#define AMDGPU_VRAM_TYPE_HBM   6
+#define AMDGPU_VRAM_TYPE_DDR3  7
+#define AMDGPU_VRAM_TYPE_DDR4  8
+#define AMDGPU_VRAM_TYPE_GDDR6 9
+#define AMDGPU_VRAM_TYPE_DDR5  10
+#define AMDGPU_VRAM_TYPE_LPDDR4 11
+#define AMDGPU_VRAM_TYPE_LPDDR5 12
+#define AMDGPU_VRAM_TYPE_HBM3E 13
+#define AMDGPU_VRAM_TYPE_HBM4 14
+
+struct drm_amdgpu_info_device {
+	/** PCI Device ID */
+	__u32 device_id;
+	/** Internal chip revision: A0, A1, etc.) */
+	__u32 chip_rev;
+	__u32 external_rev;
+	/** Revision id in PCI Config space */
+	__u32 pci_rev;
+	__u32 family;
+	__u32 num_shader_engines;
+	__u32 num_shader_arrays_per_engine;
+	/* in KHz */
+	__u32 gpu_counter_freq;
+	__u64 max_engine_clock;
+	__u64 max_memory_clock;
+	/* cu information */
+	__u32 cu_active_number;
+	/* NOTE: cu_ao_mask is INVALID, DON'T use it */
+	__u32 cu_ao_mask;
+	__u32 cu_bitmap[4][4];
+	/** Render backend pipe mask. One render backend is CB+DB. */
+	__u32 enabled_rb_pipes_mask;
+	__u32 num_rb_pipes;
+	__u32 num_hw_gfx_contexts;
+	/* PCIe version (the smaller of the GPU and the CPU/motherboard) */
+	__u32 pcie_gen;
+	__u64 ids_flags;
+	/** Starting virtual address for UMDs. */
+	__u64 virtual_address_offset;
+	/** The maximum virtual address */
+	__u64 virtual_address_max;
+	/** Required alignment of virtual addresses. */
+	__u32 virtual_address_alignment;
+	/** Page table entry - fragment size */
+	__u32 pte_fragment_size;
+	__u32 gart_page_size;
+	/** constant engine ram size*/
+	__u32 ce_ram_size;
+	/** video memory type info*/
+	__u32 vram_type;
+	/** video memory bit width*/
+	__u32 vram_bit_width;
+	/* vce harvesting instance */
+	__u32 vce_harvest_config;
+	/* gfx double offchip LDS buffers */
+	__u32 gc_double_offchip_lds_buf;
+	/* NGG Primitive Buffer */
+	__u64 prim_buf_gpu_addr;
+	/* NGG Position Buffer */
+	__u64 pos_buf_gpu_addr;
+	/* NGG Control Sideband */
+	__u64 cntl_sb_buf_gpu_addr;
+	/* NGG Parameter Cache */
+	__u64 param_buf_gpu_addr;
+	__u32 prim_buf_size;
+	__u32 pos_buf_size;
+	__u32 cntl_sb_buf_size;
+	__u32 param_buf_size;
+	/* wavefront size*/
+	__u32 wave_front_size;
+	/* shader visible vgprs*/
+	__u32 num_shader_visible_vgprs;
+	/* CU per shader array*/
+	__u32 num_cu_per_sh;
+	/* number of tcc blocks*/
+	__u32 num_tcc_blocks;
+	/* gs vgt table depth*/
+	__u32 gs_vgt_table_depth;
+	/* gs primitive buffer depth*/
+	__u32 gs_prim_buffer_depth;
+	/* max gs wavefront per vgt*/
+	__u32 max_gs_waves_per_vgt;
+	/* PCIe number of lanes (the smaller of the GPU and the CPU/motherboard) */
+	__u32 pcie_num_lanes;
+	/* always on cu bitmap */
+	__u32 cu_ao_bitmap[4][4];
+	/** Starting high virtual address for UMDs. */
+	__u64 high_va_offset;
+	/** The maximum high virtual address */
+	__u64 high_va_max;
+	/* gfx10 pa_sc_tile_steering_override */
+	__u32 pa_sc_tile_steering_override;
+	__u32 pad;
+	/* disabled TCCs */
+	__u64 tcc_disabled_mask;
+	__u64 min_engine_clock;
+	__u64 min_memory_clock;
+	/* The following fields are only set on gfx11+, older chips set 0. */
+	__u32 tcp_cache_size;       /* AKA GL0, VMEM cache */
+	__u32 num_sqc_per_wgp;
+	__u32 sqc_data_cache_size;  /* AKA SMEM cache */
+	__u32 sqc_inst_cache_size;
+	__u32 gl1c_cache_size;
+	__u32 gl2c_cache_size;
+	__u64 mall_size;            /* AKA infinity cache */
+	/* high 32 bits of the rb pipes mask */
+	__u32 enabled_rb_pipes_mask_hi;
+	/* shadow area size for gfx11 */
+	__u32 shadow_size;
+	/* shadow area base virtual alignment for gfx11 */
+	__u32 shadow_alignment;
+	/* context save area size for gfx11 */
+	__u32 csa_size;
+	/* context save area base virtual alignment for gfx11 */
+	__u32 csa_alignment;
+	/* Userq IP mask (1 << AMDGPU_HW_IP_*) */
+	__u32 userq_ip_mask;
+};
+
+struct drm_amdgpu_info_hw_ip {
+	/** Version of h/w IP */
+	__u32  hw_ip_version_major;
+	__u32  hw_ip_version_minor;
+	/** Capabilities */
+	__u64  capabilities_flags;
+	/** command buffer address start alignment*/
+	__u32  ib_start_alignment;
+	/** command buffer size alignment*/
+	__u32  ib_size_alignment;
+	/** Bitmask of available rings. Bit 0 means ring 0, etc. */
+	__u32  available_rings;
+	/** version info: bits 23:16 major, 15:8 minor, 7:0 revision */
+	__u32  ip_discovery_version;
+	/* Userq available slots */
+	__u32  userq_num_slots;
+};
+
+struct drm_amdgpu_info_num_handles {
+	/** Max handles as supported by firmware for UVD */
+	__u32  uvd_max_handles;
+	/** Handles currently in use for UVD */
+	__u32  uvd_used_handles;
+};
+
+#define AMDGPU_VCE_CLOCK_TABLE_ENTRIES		6
+
+struct drm_amdgpu_info_vce_clock_table_entry {
+	/** System clock */
+	__u32 sclk;
+	/** Memory clock */
+	__u32 mclk;
+	/** VCE clock */
+	__u32 eclk;
+	__u32 pad;
+};
+
+struct drm_amdgpu_info_vce_clock_table {
+	struct drm_amdgpu_info_vce_clock_table_entry entries[AMDGPU_VCE_CLOCK_TABLE_ENTRIES];
+	__u32 num_valid_entries;
+	__u32 pad;
+};
+
+/* query video encode/decode caps */
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG2			0
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4			1
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VC1			2
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_MPEG4_AVC		3
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_HEVC			4
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_JPEG			5
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_VP9			6
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_AV1			7
+#define AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_COUNT			8
+
+struct drm_amdgpu_info_video_codec_info {
+	__u32 valid;
+	__u32 max_width;
+	__u32 max_height;
+	__u32 max_pixels_per_frame;
+	__u32 max_level;
+	__u32 pad;
+};
+
+struct drm_amdgpu_info_video_caps {
+	struct drm_amdgpu_info_video_codec_info codec_info[AMDGPU_INFO_VIDEO_CAPS_CODEC_IDX_COUNT];
+};
+
+#define AMDGPU_VMHUB_TYPE_MASK			0xff
+#define AMDGPU_VMHUB_TYPE_SHIFT			0
+#define AMDGPU_VMHUB_TYPE_GFX			0
+#define AMDGPU_VMHUB_TYPE_MM0			1
+#define AMDGPU_VMHUB_TYPE_MM1			2
+#define AMDGPU_VMHUB_IDX_MASK			0xff00
+#define AMDGPU_VMHUB_IDX_SHIFT			8
+
+struct drm_amdgpu_info_gpuvm_fault {
+	__u64 addr;
+	__u32 status;
+	__u32 vmhub;
+};
+
+struct drm_amdgpu_info_uq_metadata_gfx {
+	/* shadow area size for gfx11 */
+	__u32 shadow_size;
+	/* shadow area base virtual alignment for gfx11 */
+	__u32 shadow_alignment;
+	/* context save area size for gfx11 */
+	__u32 csa_size;
+	/* context save area base virtual alignment for gfx11 */
+	__u32 csa_alignment;
+};
+
+struct drm_amdgpu_info_uq_metadata_compute {
+	/* EOP size for gfx11 */
+	__u32 eop_size;
+	/* EOP base virtual alignment for gfx11 */
+	__u32 eop_alignment;
+};
+
+struct drm_amdgpu_info_uq_metadata_sdma {
+	/* context save area size for sdma6 */
+	__u32 csa_size;
+	/* context save area base virtual alignment for sdma6 */
+	__u32 csa_alignment;
+};
+
+struct drm_amdgpu_info_uq_metadata {
+	union {
+		struct drm_amdgpu_info_uq_metadata_gfx gfx;
+		struct drm_amdgpu_info_uq_metadata_compute compute;
+		struct drm_amdgpu_info_uq_metadata_sdma sdma;
+	};
+};
+
+/*
+ * Supported GPU families
+ */
+#define AMDGPU_FAMILY_UNKNOWN			0
+#define AMDGPU_FAMILY_SI			110 /* Hainan, Oland, Verde, Pitcairn, Tahiti */
+#define AMDGPU_FAMILY_CI			120 /* Bonaire, Hawaii */
+#define AMDGPU_FAMILY_KV			125 /* Kaveri, Kabini, Mullins */
+#define AMDGPU_FAMILY_VI			130 /* Iceland, Tonga */
+#define AMDGPU_FAMILY_CZ			135 /* Carrizo, Stoney */
+#define AMDGPU_FAMILY_AI			141 /* Vega10 */
+#define AMDGPU_FAMILY_RV			142 /* Raven */
+#define AMDGPU_FAMILY_NV			143 /* Navi10 */
+#define AMDGPU_FAMILY_VGH			144 /* Van Gogh */
+#define AMDGPU_FAMILY_GC_11_0_0			145 /* GC 11.0.0 */
+#define AMDGPU_FAMILY_YC			146 /* Yellow Carp */
+#define AMDGPU_FAMILY_GC_11_0_1			148 /* GC 11.0.1 */
+#define AMDGPU_FAMILY_GC_10_3_6			149 /* GC 10.3.6 */
+#define AMDGPU_FAMILY_GC_10_3_7			151 /* GC 10.3.7 */
+#define AMDGPU_FAMILY_GC_11_5_0			150 /* GC 11.5.0 */
+#define AMDGPU_FAMILY_GC_11_5_4			154 /* GC 11.5.4 */
+#define AMDGPU_FAMILY_GC_12_0_0			152 /* GC 12.0.0 */
+
+/*
+ * Definition of user options
+ *
+ * option: AMDGPU_PROC_OPTIONS_OP_KFD_SIGBUS_DELAY
+ *    0:          Disable sigbus delay - SIGBUS will be raised immediately
+ *    0xFFFFFFFF: SIGBUS will not be raised
+ *    other:      Set the sigbus delay in milliseconds
+ */
+#define AMDGPU_PROC_OPTIONS_OP_KFD_SIGBUS_DELAY		0
+
+#define AMDGPU_PROC_OPTIONS_KFD_SIGBUS_DELAY_DISABLED	0xFFFFFFFFu
+
+struct drm_amdgpu_proc_options {
+	__u32 op;
+	struct {
+		__u32 value;
+	} kfd_sigbus_delay;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h
new file mode 100644
index 000000000..51a507561
--- /dev/null
+++ b/include/uapi/drm/amdxdna_accel.h
@@ -0,0 +1,766 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2022-2024, Advanced Micro Devices, Inc.
+ */
+
+#ifndef _UAPI_AMDXDNA_ACCEL_H_
+#define _UAPI_AMDXDNA_ACCEL_H_
+
+#include <linux/stddef.h>
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define AMDXDNA_INVALID_CMD_HANDLE	(~0UL)
+#define AMDXDNA_INVALID_ADDR		(~0UL)
+#define AMDXDNA_INVALID_CTX_HANDLE	0
+#define AMDXDNA_INVALID_BO_HANDLE	0
+#define AMDXDNA_INVALID_FENCE_HANDLE	0
+#define AMDXDNA_INVALID_DOORBELL_OFFSET	(~0U)
+
+/*
+ * Define hardware context priority
+ */
+#define AMDXDNA_QOS_REALTIME_PRIORITY	0x100
+#define AMDXDNA_QOS_HIGH_PRIORITY	0x180
+#define AMDXDNA_QOS_NORMAL_PRIORITY	0x200
+#define AMDXDNA_QOS_LOW_PRIORITY	0x280
+
+enum amdxdna_device_type {
+	AMDXDNA_DEV_TYPE_UNKNOWN = -1,
+	AMDXDNA_DEV_TYPE_KMQ = 0,
+	AMDXDNA_DEV_TYPE_UMQ = 1,
+	AMDXDNA_DEV_TYPE_PF = 2,
+};
+
+enum amdxdna_drm_ioctl_id {
+	DRM_AMDXDNA_CREATE_HWCTX,
+	DRM_AMDXDNA_DESTROY_HWCTX,
+	DRM_AMDXDNA_CONFIG_HWCTX,
+	DRM_AMDXDNA_CREATE_BO,
+	DRM_AMDXDNA_GET_BO_INFO,
+	DRM_AMDXDNA_SYNC_BO,
+	DRM_AMDXDNA_EXEC_CMD,
+	DRM_AMDXDNA_GET_INFO,
+	DRM_AMDXDNA_SET_STATE,
+	DRM_AMDXDNA_WAIT_CMD,
+	DRM_AMDXDNA_GET_ARRAY,
+};
+
+/**
+ * struct qos_info - QoS information for driver.
+ * @gops: Giga operations per second.
+ * @fps: Frames per second.
+ * @dma_bandwidth: DMA bandwidtha.
+ * @latency: Frame response latency.
+ * @frame_exec_time: Frame execution time.
+ * @priority: Request priority.
+ *
+ * User program can provide QoS hints to driver.
+ */
+struct amdxdna_qos_info {
+	__u32 gops;
+	__u32 fps;
+	__u32 dma_bandwidth;
+	__u32 latency;
+	__u32 frame_exec_time;
+	__u32 priority;
+};
+
+/**
+ * struct amdxdna_drm_create_hwctx - Create hardware context.
+ * @ext: MBZ.
+ * @ext_flags: MBZ.
+ * @qos_p: Address of QoS info.
+ * @umq_bo: BO handle for user mode queue(UMQ).
+ * @log_buf_bo: BO handle for log buffer.
+ * @max_opc: Maximum operations per cycle.
+ * @num_tiles: Number of AIE tiles.
+ * @mem_size: Size of AIE tile memory.
+ * @umq_doorbell: Returned offset of doorbell associated with UMQ.
+ * @handle: Returned hardware context handle.
+ * @syncobj_handle: Returned syncobj handle for command completion.
+ */
+struct amdxdna_drm_create_hwctx {
+	__u64 ext;
+	__u64 ext_flags;
+	__u64 qos_p;
+	__u32 umq_bo;
+	__u32 log_buf_bo;
+	__u32 max_opc;
+	__u32 num_tiles;
+	__u32 mem_size;
+	__u32 umq_doorbell;
+	__u32 handle;
+	__u32 syncobj_handle;
+};
+
+/**
+ * struct amdxdna_drm_destroy_hwctx - Destroy hardware context.
+ * @handle: Hardware context handle.
+ * @pad: MBZ.
+ */
+struct amdxdna_drm_destroy_hwctx {
+	__u32 handle;
+	__u32 pad;
+};
+
+/**
+ * struct amdxdna_cu_config - configuration for one CU
+ * @cu_bo: CU configuration buffer bo handle.
+ * @cu_func: Function of a CU.
+ * @pad: MBZ.
+ */
+struct amdxdna_cu_config {
+	__u32 cu_bo;
+	__u8  cu_func;
+	__u8  pad[3];
+};
+
+/**
+ * struct amdxdna_hwctx_param_config_cu - configuration for CUs in hardware context
+ * @num_cus: Number of CUs to configure.
+ * @pad: MBZ.
+ * @cu_configs: Array of CU configurations of struct amdxdna_cu_config.
+ */
+struct amdxdna_hwctx_param_config_cu {
+	__u16 num_cus;
+	__u16 pad[3];
+	struct amdxdna_cu_config cu_configs[] __counted_by(num_cus);
+};
+
+enum amdxdna_drm_config_hwctx_param {
+	DRM_AMDXDNA_HWCTX_CONFIG_CU,
+	DRM_AMDXDNA_HWCTX_ASSIGN_DBG_BUF,
+	DRM_AMDXDNA_HWCTX_REMOVE_DBG_BUF,
+};
+
+/**
+ * struct amdxdna_drm_config_hwctx - Configure hardware context.
+ * @handle: hardware context handle.
+ * @param_type: Value in enum amdxdna_drm_config_hwctx_param. Specifies the
+ *              structure passed in via param_val.
+ * @param_val: A structure specified by the param_type struct member.
+ * @param_val_size: Size of the parameter buffer pointed to by the param_val.
+ *		    If param_val is not a pointer, driver can ignore this.
+ * @pad: MBZ.
+ *
+ * Note: if the param_val is a pointer pointing to a buffer, the maximum size
+ * of the buffer is 4KiB(PAGE_SIZE).
+ */
+struct amdxdna_drm_config_hwctx {
+	__u32 handle;
+	__u32 param_type;
+	__u64 param_val;
+	__u32 param_val_size;
+	__u32 pad;
+};
+
+enum amdxdna_bo_type {
+	AMDXDNA_BO_INVALID = 0,
+	AMDXDNA_BO_SHMEM = 1, /* Be compatible with legacy application code. */
+	AMDXDNA_BO_SHARE = 1,
+	AMDXDNA_BO_DEV_HEAP = 2,
+	AMDXDNA_BO_DEV = 3,
+	AMDXDNA_BO_CMD = 4,
+};
+
+/**
+ * struct amdxdna_drm_va_entry
+ * @vaddr: Virtual address.
+ * @len: Size of entry.
+ */
+struct amdxdna_drm_va_entry {
+	__u64 vaddr;
+	__u64 len;
+};
+
+/**
+ * struct amdxdna_drm_va_tbl
+ * @dmabuf_fd: The fd of dmabuf.
+ * @num_entries: Number of va entries.
+ * @va_entries: Array of va entries.
+ *
+ * The input can be either a dmabuf fd or a virtual address entry table.
+ * When dmabuf_fd is used, num_entries must be zero.
+ */
+struct amdxdna_drm_va_tbl {
+	__s32 dmabuf_fd;
+	__u32 num_entries;
+	struct amdxdna_drm_va_entry va_entries[];
+};
+
+/**
+ * struct amdxdna_drm_create_bo - Create a buffer object.
+ * @flags: Buffer flags. MBZ.
+ * @vaddr: User VA of buffer if applied. MBZ.
+ * @size: Size in bytes.
+ * @type: Buffer type.
+ * @handle: Returned DRM buffer object handle.
+ */
+struct amdxdna_drm_create_bo {
+	__u64	flags;
+	__u64	vaddr;
+	__u64	size;
+	__u32	type;
+	__u32	handle;
+};
+
+/**
+ * struct amdxdna_drm_get_bo_info - Get buffer object information.
+ * @ext: MBZ.
+ * @ext_flags: MBZ.
+ * @handle: DRM buffer object handle.
+ * @pad: MBZ.
+ * @map_offset: Returned DRM fake offset for mmap().
+ * @vaddr: Returned user VA of buffer. 0 in case user needs mmap().
+ * @xdna_addr: Returned XDNA device virtual address.
+ */
+struct amdxdna_drm_get_bo_info {
+	__u64 ext;
+	__u64 ext_flags;
+	__u32 handle;
+	__u32 pad;
+	__u64 map_offset;
+	__u64 vaddr;
+	__u64 xdna_addr;
+};
+
+/**
+ * struct amdxdna_drm_sync_bo - Sync buffer object.
+ * @handle: Buffer object handle.
+ * @direction: Direction of sync, can be from device or to device.
+ * @offset: Offset in the buffer to sync.
+ * @size: Size in bytes.
+ */
+struct amdxdna_drm_sync_bo {
+	__u32 handle;
+#define SYNC_DIRECT_TO_DEVICE	0U
+#define SYNC_DIRECT_FROM_DEVICE	1U
+	__u32 direction;
+	__u64 offset;
+	__u64 size;
+};
+
+enum amdxdna_cmd_type {
+	AMDXDNA_CMD_SUBMIT_EXEC_BUF = 0,
+	AMDXDNA_CMD_SUBMIT_DEPENDENCY,
+	AMDXDNA_CMD_SUBMIT_SIGNAL,
+};
+
+/**
+ * struct amdxdna_drm_exec_cmd - Execute command.
+ * @ext: MBZ.
+ * @ext_flags: MBZ.
+ * @hwctx: Hardware context handle.
+ * @type: One of command type in enum amdxdna_cmd_type.
+ * @cmd_handles: Array of command handles or the command handle itself
+ *               in case of just one.
+ * @args: Array of arguments for all command handles.
+ * @cmd_count: Number of command handles in the cmd_handles array.
+ * @arg_count: Number of arguments in the args array.
+ * @seq: Returned sequence number for this command.
+ */
+struct amdxdna_drm_exec_cmd {
+	__u64 ext;
+	__u64 ext_flags;
+	__u32 hwctx;
+	__u32 type;
+	__u64 cmd_handles;
+	__u64 args;
+	__u32 cmd_count;
+	__u32 arg_count;
+	__u64 seq;
+};
+
+/**
+ * struct amdxdna_drm_wait_cmd - Wait execution command.
+ *
+ * @hwctx: Context handle.
+ * @timeout: timeout in ms, 0 implies infinite wait.
+ * @seq: sequence number of the command returned by execute command.
+ *
+ * Wait a command specified by seq to be completed.
+ */
+struct amdxdna_drm_wait_cmd {
+	__u32 hwctx;
+	__u32 timeout;
+	__u64 seq;
+};
+
+/**
+ * struct amdxdna_drm_query_aie_status - Query the status of the AIE hardware
+ * @buffer: The user space buffer that will return the AIE status.
+ * @buffer_size: The size of the user space buffer.
+ * @cols_filled: A bitmap of AIE columns whose data has been returned in the buffer.
+ */
+struct amdxdna_drm_query_aie_status {
+	__u64 buffer; /* out */
+	__u32 buffer_size; /* in */
+	__u32 cols_filled; /* out */
+};
+
+/**
+ * struct amdxdna_drm_query_aie_version - Query the version of the AIE hardware
+ * @major: The major version number.
+ * @minor: The minor version number.
+ */
+struct amdxdna_drm_query_aie_version {
+	__u32 major; /* out */
+	__u32 minor; /* out */
+};
+
+/**
+ * struct amdxdna_drm_query_aie_tile_metadata - Query the metadata of AIE tile (core, mem, shim)
+ * @row_count: The number of rows.
+ * @row_start: The starting row number.
+ * @dma_channel_count: The number of dma channels.
+ * @lock_count: The number of locks.
+ * @event_reg_count: The number of events.
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_query_aie_tile_metadata {
+	__u16 row_count;
+	__u16 row_start;
+	__u16 dma_channel_count;
+	__u16 lock_count;
+	__u16 event_reg_count;
+	__u16 pad[3];
+};
+
+/**
+ * struct amdxdna_drm_query_aie_metadata - Query the metadata of the AIE hardware
+ * @col_size: The size of a column in bytes.
+ * @cols: The total number of columns.
+ * @rows: The total number of rows.
+ * @version: The version of the AIE hardware.
+ * @core: The metadata for all core tiles.
+ * @mem: The metadata for all mem tiles.
+ * @shim: The metadata for all shim tiles.
+ */
+struct amdxdna_drm_query_aie_metadata {
+	__u32 col_size;
+	__u16 cols;
+	__u16 rows;
+	struct amdxdna_drm_query_aie_version version;
+	struct amdxdna_drm_query_aie_tile_metadata core;
+	struct amdxdna_drm_query_aie_tile_metadata mem;
+	struct amdxdna_drm_query_aie_tile_metadata shim;
+};
+
+/**
+ * struct amdxdna_drm_query_clock - Metadata for a clock
+ * @name: The clock name.
+ * @freq_mhz: The clock frequency.
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_query_clock {
+	__u8 name[16];
+	__u32 freq_mhz;
+	__u32 pad;
+};
+
+/**
+ * struct amdxdna_drm_query_clock_metadata - Query metadata for clocks
+ * @mp_npu_clock: The metadata for MP-NPU clock.
+ * @h_clock: The metadata for H clock.
+ */
+struct amdxdna_drm_query_clock_metadata {
+	struct amdxdna_drm_query_clock mp_npu_clock;
+	struct amdxdna_drm_query_clock h_clock;
+};
+
+enum amdxdna_sensor_type {
+	AMDXDNA_SENSOR_TYPE_POWER,
+	AMDXDNA_SENSOR_TYPE_COLUMN_UTILIZATION
+};
+
+/**
+ * struct amdxdna_drm_query_sensor - The data for single sensor.
+ * @label: The name for a sensor.
+ * @input: The current value of the sensor.
+ * @max: The maximum value possible for the sensor.
+ * @average: The average value of the sensor.
+ * @highest: The highest recorded sensor value for this driver load for the sensor.
+ * @status: The sensor status.
+ * @units: The sensor units.
+ * @unitm: Translates value member variables into the correct unit via (pow(10, unitm) * value).
+ * @type: The sensor type from enum amdxdna_sensor_type.
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_query_sensor {
+	__u8  label[64];
+	__u32 input;
+	__u32 max;
+	__u32 average;
+	__u32 highest;
+	__u8  status[64];
+	__u8  units[16];
+	__s8  unitm;
+	__u8  type;
+	__u8  pad[6];
+};
+
+/**
+ * struct amdxdna_drm_query_hwctx - The data for single context.
+ * @context_id: The ID for this context.
+ * @start_col: The starting column for the partition assigned to this context.
+ * @num_col: The number of columns in the partition assigned to this context.
+ * @pad: Structure padding.
+ * @pid: The Process ID of the process that created this context.
+ * @command_submissions: The number of commands submitted to this context.
+ * @command_completions: The number of commands completed by this context.
+ * @migrations: The number of times this context has been moved to a different partition.
+ * @preemptions: The number of times this context has been preempted by another context in the
+ *               same partition.
+ * @errors: The errors for this context.
+ */
+struct amdxdna_drm_query_hwctx {
+	__u32 context_id;
+	__u32 start_col;
+	__u32 num_col;
+	__u32 pad;
+	__s64 pid;
+	__u64 command_submissions;
+	__u64 command_completions;
+	__u64 migrations;
+	__u64 preemptions;
+	__u64 errors;
+};
+
+enum amdxdna_power_mode_type {
+	POWER_MODE_DEFAULT, /* Fallback to calculated DPM */
+	POWER_MODE_LOW,     /* Set frequency to lowest DPM */
+	POWER_MODE_MEDIUM,  /* Set frequency to medium DPM */
+	POWER_MODE_HIGH,    /* Set frequency to highest DPM */
+	POWER_MODE_TURBO,   /* Maximum power */
+};
+
+/**
+ * struct amdxdna_drm_get_power_mode - Get the configured power mode
+ * @power_mode: The mode type from enum amdxdna_power_mode_type
+ * @pad: Structure padding.
+ */
+struct amdxdna_drm_get_power_mode {
+	__u8 power_mode;
+	__u8 pad[7];
+};
+
+/**
+ * struct amdxdna_drm_query_firmware_version - Query the firmware version
+ * @major: The major version number
+ * @minor: The minor version number
+ * @patch: The patch level version number
+ * @build: The build ID
+ */
+struct amdxdna_drm_query_firmware_version {
+	__u32 major; /* out */
+	__u32 minor; /* out */
+	__u32 patch; /* out */
+	__u32 build; /* out */
+};
+
+enum amdxdna_drm_get_param {
+	DRM_AMDXDNA_QUERY_AIE_STATUS,
+	DRM_AMDXDNA_QUERY_AIE_METADATA,
+	DRM_AMDXDNA_QUERY_AIE_VERSION,
+	DRM_AMDXDNA_QUERY_CLOCK_METADATA,
+	DRM_AMDXDNA_QUERY_SENSORS,
+	DRM_AMDXDNA_QUERY_HW_CONTEXTS,
+	DRM_AMDXDNA_QUERY_FIRMWARE_VERSION = 8,
+	DRM_AMDXDNA_GET_POWER_MODE,
+	DRM_AMDXDNA_QUERY_TELEMETRY,
+	DRM_AMDXDNA_GET_FORCE_PREEMPT_STATE,
+	DRM_AMDXDNA_QUERY_RESOURCE_INFO,
+	DRM_AMDXDNA_GET_FRAME_BOUNDARY_PREEMPT_STATE,
+};
+
+/**
+ * struct amdxdna_drm_get_resource_info - Get resource information
+ */
+struct amdxdna_drm_get_resource_info {
+	/** @npu_clk_max: max H-Clocks */
+	__u64 npu_clk_max;
+	/** @npu_tops_max: max TOPs */
+	__u64 npu_tops_max;
+	/** @npu_task_max: max number of tasks */
+	__u64 npu_task_max;
+	/** @npu_tops_curr: current TOPs */
+	__u64 npu_tops_curr;
+	/** @npu_task_curr: current number of tasks */
+	__u64 npu_task_curr;
+};
+
+/**
+ * struct amdxdna_drm_attribute_state - State of an attribute
+ */
+struct amdxdna_drm_attribute_state {
+	/** @state: enabled or disabled */
+	__u8 state;
+	/** @pad: MBZ */
+	__u8 pad[7];
+};
+
+/**
+ * struct amdxdna_drm_query_telemetry_header - Telemetry data header
+ */
+struct amdxdna_drm_query_telemetry_header {
+	/** @major: Firmware telemetry interface major version number */
+	__u32 major;
+	/** @minor: Firmware telemetry interface minor version number */
+	__u32 minor;
+	/** @type: Telemetry query type */
+	__u32 type;
+	/** @map_num_elements: Total number of elements in the map table */
+	__u32 map_num_elements;
+	/** @map: Element map */
+	__u32 map[];
+};
+
+/**
+ * struct amdxdna_drm_get_info - Get some information from the AIE hardware.
+ * @param: Value in enum amdxdna_drm_get_param. Specifies the structure passed in the buffer.
+ * @buffer_size: Size of the input buffer. Size needed/written by the kernel.
+ * @buffer: A structure specified by the param struct member.
+ */
+struct amdxdna_drm_get_info {
+	__u32 param; /* in */
+	__u32 buffer_size; /* in/out */
+	__u64 buffer; /* in/out */
+};
+
+#define AMDXDNA_HWCTX_STATE_IDLE	0
+#define AMDXDNA_HWCTX_STATE_ACTIVE	1
+
+/**
+ * struct amdxdna_drm_hwctx_entry - The hardware context array entry
+ */
+struct amdxdna_drm_hwctx_entry {
+	/** @context_id: Context ID. */
+	__u32 context_id;
+	/** @start_col: Start AIE array column assigned to context. */
+	__u32 start_col;
+	/** @num_col: Number of AIE array columns assigned to context. */
+	__u32 num_col;
+	/** @hwctx_id: The real hardware context id. */
+	__u32 hwctx_id;
+	/** @pid: ID of process which created this context. */
+	__s64 pid;
+	/** @command_submissions: Number of commands submitted. */
+	__u64 command_submissions;
+	/** @command_completions: Number of commands completed. */
+	__u64 command_completions;
+	/** @migrations: Number of times been migrated. */
+	__u64 migrations;
+	/** @preemptions: Number of times been preempted. */
+	__u64 preemptions;
+	/** @errors: Number of errors happened. */
+	__u64 errors;
+	/** @priority: Context priority. */
+	__u64 priority;
+	/** @heap_usage: Usage of device heap buffer. */
+	__u64 heap_usage;
+	/** @suspensions: Number of times been suspended. */
+	__u64 suspensions;
+	/**
+	 * @state: Context state.
+	 * %AMDXDNA_HWCTX_STATE_IDLE
+	 * %AMDXDNA_HWCTX_STATE_ACTIVE
+	 */
+	__u32 state;
+	/** @pasid: PASID been bound. */
+	__u32 pasid;
+	/** @gops: Giga operations per second. */
+	__u32 gops;
+	/** @fps: Frames per second. */
+	__u32 fps;
+	/** @dma_bandwidth: DMA bandwidth. */
+	__u32 dma_bandwidth;
+	/** @latency: Frame response latency. */
+	__u32 latency;
+	/** @frame_exec_time: Frame execution time. */
+	__u32 frame_exec_time;
+	/** @txn_op_idx: Index of last control code executed. */
+	__u32 txn_op_idx;
+	/** @ctx_pc: Program counter. */
+	__u32 ctx_pc;
+	/** @fatal_error_type: Fatal error type if context crashes. */
+	__u32 fatal_error_type;
+	/** @fatal_error_exception_type: Firmware exception type. */
+	__u32 fatal_error_exception_type;
+	/** @fatal_error_exception_pc: Firmware exception program counter. */
+	__u32 fatal_error_exception_pc;
+	/** @fatal_error_app_module: Exception module name. */
+	__u32 fatal_error_app_module;
+	/** @pad: Structure pad. */
+	__u32 pad;
+};
+
+/**
+ * struct amdxdna_async_error - XDNA async error structure
+ */
+struct amdxdna_async_error {
+	/** @err_code: Error code. */
+	__u64 err_code;
+	/** @ts_us: Timestamp. */
+	__u64 ts_us;
+	/** @ex_err_code: Extra error code */
+	__u64 ex_err_code;
+};
+
+/**
+ * struct amdxdna_drm_bo_usage - all types of BO usage
+ * BOs managed by XRT/SHIM/driver is counted as internal.
+ * Others are counted as external which are managed by applications.
+ *
+ * Among all types of BOs:
+ *   AMDXDNA_BO_DEV_HEAP - is counted for internal.
+ *   AMDXDNA_BO_SHARE    - is counted for external.
+ *   AMDXDNA_BO_CMD      - is counted for internal.
+ *   AMDXDNA_BO_DEV      - is counted by heap_usage only, not internal
+ *                         or external. It does not add to the total memory
+ *                         footprint since its mem comes from heap which is
+ *                         already counted as internal.
+ */
+struct amdxdna_drm_bo_usage {
+	/** @pid: The ID of the process to query from. */
+	__s64 pid;
+	/** @total_usage: Total BO size used by process. */
+	__u64 total_usage;
+	/** @internal_usage: Total internal BO size used by process. */
+	__u64 internal_usage;
+	/** @heap_usage: Total device BO size used by process. */
+	__u64 heap_usage;
+};
+
+/*
+ * Supported params in struct amdxdna_drm_get_array
+ */
+#define DRM_AMDXDNA_HW_CONTEXT_ALL	0
+#define DRM_AMDXDNA_HW_LAST_ASYNC_ERR	2
+#define DRM_AMDXDNA_BO_USAGE		6
+
+/**
+ * struct amdxdna_drm_get_array - Get information array.
+ */
+struct amdxdna_drm_get_array {
+	/**
+	 * @param:
+	 *
+	 * Supported params:
+	 *
+	 * %DRM_AMDXDNA_HW_CONTEXT_ALL:
+	 * Returns all created hardware contexts.
+	 *
+	 * %DRM_AMDXDNA_HW_LAST_ASYNC_ERR:
+	 * Returns last async error.
+	 *
+	 * %DRM_AMDXDNA_BO_USAGE:
+	 * Returns usage of heap/internal/external BOs.
+	 */
+	__u32 param;
+	/**
+	 * @element_size:
+	 *
+	 * Specifies maximum element size and returns the actual element size.
+	 */
+	__u32 element_size;
+	/**
+	 * @num_element:
+	 *
+	 * Specifies maximum number of elements and returns the actual number
+	 * of elements.
+	 */
+	__u32 num_element; /* in/out */
+	/** @pad: MBZ */
+	__u32 pad;
+	/**
+	 * @buffer:
+	 *
+	 * Specifies the match conditions and returns the matched information
+	 * array.
+	 */
+	__u64 buffer;
+};
+
+enum amdxdna_drm_set_param {
+	DRM_AMDXDNA_SET_POWER_MODE,
+	DRM_AMDXDNA_WRITE_AIE_MEM,
+	DRM_AMDXDNA_WRITE_AIE_REG,
+	DRM_AMDXDNA_SET_FORCE_PREEMPT,
+	DRM_AMDXDNA_SET_FRAME_BOUNDARY_PREEMPT,
+};
+
+/**
+ * struct amdxdna_drm_set_state - Set the state of the AIE hardware.
+ * @param: Value in enum amdxdna_drm_set_param.
+ * @buffer_size: Size of the input param.
+ * @buffer: Pointer to the input param.
+ */
+struct amdxdna_drm_set_state {
+	__u32 param; /* in */
+	__u32 buffer_size; /* in */
+	__u64 buffer; /* in */
+};
+
+/**
+ * struct amdxdna_drm_set_power_mode - Set the power mode of the AIE hardware
+ * @power_mode: The sensor type from enum amdxdna_power_mode_type
+ * @pad: MBZ.
+ */
+struct amdxdna_drm_set_power_mode {
+	__u8 power_mode;
+	__u8 pad[7];
+};
+
+#define DRM_IOCTL_AMDXDNA_CREATE_HWCTX \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_HWCTX, \
+		 struct amdxdna_drm_create_hwctx)
+
+#define DRM_IOCTL_AMDXDNA_DESTROY_HWCTX \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_DESTROY_HWCTX, \
+		 struct amdxdna_drm_destroy_hwctx)
+
+#define DRM_IOCTL_AMDXDNA_CONFIG_HWCTX \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CONFIG_HWCTX, \
+		 struct amdxdna_drm_config_hwctx)
+
+#define DRM_IOCTL_AMDXDNA_CREATE_BO \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_CREATE_BO, \
+		 struct amdxdna_drm_create_bo)
+
+#define DRM_IOCTL_AMDXDNA_GET_BO_INFO \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_BO_INFO, \
+		 struct amdxdna_drm_get_bo_info)
+
+#define DRM_IOCTL_AMDXDNA_SYNC_BO \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_SYNC_BO, \
+		 struct amdxdna_drm_sync_bo)
+
+#define DRM_IOCTL_AMDXDNA_EXEC_CMD \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_EXEC_CMD, \
+		 struct amdxdna_drm_exec_cmd)
+
+#define DRM_IOCTL_AMDXDNA_GET_INFO \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_INFO, \
+		 struct amdxdna_drm_get_info)
+
+#define DRM_IOCTL_AMDXDNA_SET_STATE \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_SET_STATE, \
+		 struct amdxdna_drm_set_state)
+
+#define DRM_IOCTL_AMDXDNA_GET_ARRAY \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDXDNA_GET_ARRAY, \
+		 struct amdxdna_drm_get_array)
+
+#define DRM_IOCTL_AMDXDNA_WAIT_CMD \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_AMDXDNA_WAIT_CMD, \
+		struct amdxdna_drm_wait_cmd)
+
+#if defined(__cplusplus)
+} /* extern c end */
+#endif
+
+#endif /* _UAPI_AMDXDNA_ACCEL_H_ */
diff --git a/include/uapi/drm/armada_drm.h b/include/uapi/drm/armada_drm.h
new file mode 100644
index 000000000..af1c14c83
--- /dev/null
+++ b/include/uapi/drm/armada_drm.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 Russell King
+ *  With inspiration from the i915 driver
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#ifndef DRM_ARMADA_IOCTL_H
+#define DRM_ARMADA_IOCTL_H
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_ARMADA_GEM_CREATE		0x00
+#define DRM_ARMADA_GEM_MMAP		0x02
+#define DRM_ARMADA_GEM_PWRITE		0x03
+
+#define ARMADA_IOCTL(dir, name, str) \
+	DRM_##dir(DRM_COMMAND_BASE + DRM_ARMADA_##name, struct drm_armada_##str)
+
+struct drm_armada_gem_create {
+	__u32 handle;
+	__u32 size;
+};
+#define DRM_IOCTL_ARMADA_GEM_CREATE \
+	ARMADA_IOCTL(IOWR, GEM_CREATE, gem_create)
+
+struct drm_armada_gem_mmap {
+	__u32 handle;
+	__u32 pad;
+	__u64 offset;
+	__u64 size;
+	__u64 addr;
+};
+#define DRM_IOCTL_ARMADA_GEM_MMAP \
+	ARMADA_IOCTL(IOWR, GEM_MMAP, gem_mmap)
+
+struct drm_armada_gem_pwrite {
+	__u64 ptr;
+	__u32 handle;
+	__u32 offset;
+	__u32 size;
+};
+#define DRM_IOCTL_ARMADA_GEM_PWRITE \
+	ARMADA_IOCTL(IOW, GEM_PWRITE, gem_pwrite)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/asahi_drm.h b/include/uapi/drm/asahi_drm.h
new file mode 100644
index 000000000..de67f1c60
--- /dev/null
+++ b/include/uapi/drm/asahi_drm.h
@@ -0,0 +1,1194 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright (C) The Asahi Linux Contributors
+ * Copyright (C) 2018-2023 Collabora Ltd.
+ * Copyright (C) 2014-2018 Broadcom
+ */
+#ifndef _ASAHI_DRM_H_
+#define _ASAHI_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * DOC: Introduction to the Asahi UAPI
+ *
+ * This documentation describes the Asahi IOCTLs.
+ *
+ * Just a few generic rules about the data passed to the Asahi IOCTLs (cribbed
+ * from Panthor):
+ *
+ * - Structures must be aligned on 64-bit/8-byte. If the object is not
+ *   naturally aligned, a padding field must be added.
+ * - Fields must be explicitly aligned to their natural type alignment with
+ *   pad[0..N] fields.
+ * - All padding fields will be checked by the driver to make sure they are
+ *   zeroed.
+ * - Flags can be added, but not removed/replaced.
+ * - New fields can be added to the main structures (the structures
+ *   directly passed to the ioctl). Those fields can be added at the end of
+ *   the structure, or replace existing padding fields. Any new field being
+ *   added must preserve the behavior that existed before those fields were
+ *   added when a value of zero is passed.
+ * - New fields can be added to indirect objects (objects pointed by the
+ *   main structure), iff those objects are passed a size to reflect the
+ *   size known by the userspace driver (see
+ *   drm_asahi_cmd_header::size).
+ * - If the kernel driver is too old to know some fields, those will be
+ *   ignored if zero, and otherwise rejected (and so will be zero on output).
+ * - If userspace is too old to know some fields, those will be zeroed
+ *   (input) before the structure is parsed by the kernel driver.
+ * - Each new flag/field addition must come with a driver version update so
+ *   the userspace driver doesn't have to guess which flags are supported.
+ * - Structures should not contain unions, as this would defeat the
+ *   extensibility of such structures.
+ * - IOCTLs can't be removed or replaced. New IOCTL IDs should be placed
+ *   at the end of the drm_asahi_ioctl_id enum.
+ */
+
+/**
+ * enum drm_asahi_ioctl_id - IOCTL IDs
+ *
+ * Place new ioctls at the end, don't re-order, don't replace or remove entries.
+ *
+ * These IDs are not meant to be used directly. Use the DRM_IOCTL_ASAHI_xxx
+ * definitions instead.
+ */
+enum drm_asahi_ioctl_id {
+	/** @DRM_ASAHI_GET_PARAMS: Query device properties. */
+	DRM_ASAHI_GET_PARAMS = 0,
+
+	/** @DRM_ASAHI_GET_TIME: Query device time. */
+	DRM_ASAHI_GET_TIME,
+
+	/** @DRM_ASAHI_VM_CREATE: Create a GPU VM address space. */
+	DRM_ASAHI_VM_CREATE,
+
+	/** @DRM_ASAHI_VM_DESTROY: Destroy a VM. */
+	DRM_ASAHI_VM_DESTROY,
+
+	/** @DRM_ASAHI_VM_BIND: Bind/unbind memory to a VM. */
+	DRM_ASAHI_VM_BIND,
+
+	/** @DRM_ASAHI_GEM_CREATE: Create a buffer object. */
+	DRM_ASAHI_GEM_CREATE,
+
+	/**
+	 * @DRM_ASAHI_GEM_MMAP_OFFSET: Get offset to pass to mmap() to map a
+	 * given GEM handle.
+	 */
+	DRM_ASAHI_GEM_MMAP_OFFSET,
+
+	/** @DRM_ASAHI_GEM_BIND_OBJECT: Bind memory as a special object */
+	DRM_ASAHI_GEM_BIND_OBJECT,
+
+	/** @DRM_ASAHI_QUEUE_CREATE: Create a scheduling queue. */
+	DRM_ASAHI_QUEUE_CREATE,
+
+	/** @DRM_ASAHI_QUEUE_DESTROY: Destroy a scheduling queue. */
+	DRM_ASAHI_QUEUE_DESTROY,
+
+	/** @DRM_ASAHI_SUBMIT: Submit commands to a queue. */
+	DRM_ASAHI_SUBMIT,
+};
+
+#define DRM_ASAHI_MAX_CLUSTERS	64
+
+/**
+ * struct drm_asahi_params_global - Global parameters.
+ *
+ * This struct may be queried by drm_asahi_get_params.
+ */
+struct drm_asahi_params_global {
+	/** @features: Feature bits from drm_asahi_feature */
+	__u64 features;
+
+	/** @gpu_generation: GPU generation, e.g. 13 for G13G */
+	__u32 gpu_generation;
+
+	/** @gpu_variant: GPU variant as a character, e.g. 'C' for G13C */
+	__u32 gpu_variant;
+
+	/**
+	 * @gpu_revision: GPU revision in BCD, e.g. 0x00 for 'A0' or
+	 * 0x21 for 'C1'
+	 */
+	__u32 gpu_revision;
+
+	/** @chip_id: Chip ID in BCD, e.g. 0x8103 for T8103 */
+	__u32 chip_id;
+
+	/** @num_dies: Number of dies in the SoC */
+	__u32 num_dies;
+
+	/** @num_clusters_total: Number of GPU clusters (across all dies) */
+	__u32 num_clusters_total;
+
+	/**
+	 * @num_cores_per_cluster: Number of logical cores per cluster
+	 * (including inactive/nonexistent)
+	 */
+	__u32 num_cores_per_cluster;
+
+	/** @max_frequency_khz: Maximum GPU core clock frequency */
+	__u32 max_frequency_khz;
+
+	/** @core_masks: Bitmask of present/enabled cores per cluster */
+	__u64 core_masks[DRM_ASAHI_MAX_CLUSTERS];
+
+	/**
+	 * @vm_start: VM range start VMA. Together with @vm_end, this defines
+	 * the window of valid GPU VAs. Userspace is expected to subdivide VAs
+	 * out of this window.
+	 *
+	 * This window contains all virtual addresses that userspace needs to
+	 * know about. There may be kernel-internal GPU VAs outside this range,
+	 * but that detail is not relevant here.
+	 */
+	__u64 vm_start;
+
+	/** @vm_end: VM range end VMA */
+	__u64 vm_end;
+
+	/**
+	 * @vm_kernel_min_size: Minimum kernel VMA window size.
+	 *
+	 * When creating a VM, userspace is required to carve out a section of
+	 * virtual addresses (within the range given by @vm_start and
+	 * @vm_end). The kernel will allocate various internal structures
+	 * within the specified VA range.
+	 *
+	 * Allowing userspace to choose the VA range for the kernel, rather than
+	 * the kernel reserving VAs and requiring userspace to cope, can assist
+	 * in implementing SVM.
+	 */
+	__u64 vm_kernel_min_size;
+
+	/**
+	 * @max_commands_per_submission: Maximum number of supported commands
+	 * per submission. This mirrors firmware limits. Userspace must split up
+	 * larger command buffers, which may require inserting additional
+	 * synchronization.
+	 */
+	__u32 max_commands_per_submission;
+
+	/**
+	 * @max_attachments: Maximum number of drm_asahi_attachment's per
+	 * command
+	 */
+	__u32 max_attachments;
+
+	/**
+	 * @command_timestamp_frequency_hz: Timebase frequency for timestamps
+	 * written during command execution, specified via drm_asahi_timestamp
+	 * structures. As this rate is controlled by the firmware, it is a
+	 * queryable parameter.
+	 *
+	 * Userspace must divide by this frequency to convert timestamps to
+	 * seconds, rather than hardcoding a particular firmware's rate.
+	 */
+	__u64 command_timestamp_frequency_hz;
+};
+
+/**
+ * enum drm_asahi_feature - Feature bits
+ *
+ * This covers only features that userspace cannot infer from the architecture
+ * version. Most features don't need to be here.
+ */
+enum drm_asahi_feature {
+	/**
+	 * @DRM_ASAHI_FEATURE_SOFT_FAULTS: GPU has "soft fault" enabled. Shader
+	 * loads of unmapped memory will return zero. Shader stores to unmapped
+	 * memory will be silently discarded. Note that only shader load/store
+	 * is affected. Other hardware units are not affected, notably including
+	 * texture sampling.
+	 *
+	 * Soft fault is set when initializing the GPU and cannot be runtime
+	 * toggled. Therefore, it is exposed as a feature bit and not a
+	 * userspace-settable flag on the VM. When soft fault is enabled,
+	 * userspace can speculate memory accesses more aggressively.
+	 */
+	DRM_ASAHI_FEATURE_SOFT_FAULTS = (1UL) << 0,
+};
+
+/**
+ * struct drm_asahi_get_params - Arguments passed to DRM_IOCTL_ASAHI_GET_PARAMS
+ */
+struct drm_asahi_get_params {
+	/** @param_group: Parameter group to fetch (MBZ) */
+	__u32 param_group;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @pointer: User pointer to write parameter struct */
+	__u64 pointer;
+
+	/**
+	 * @size: Size of the user buffer. In case of older userspace, this may
+	 * be less than sizeof(struct drm_asahi_params_global). The kernel will
+	 * not write past the length specified here, allowing extensibility.
+	 */
+	__u64 size;
+};
+
+/**
+ * struct drm_asahi_vm_create - Arguments passed to DRM_IOCTL_ASAHI_VM_CREATE
+ */
+struct drm_asahi_vm_create {
+	/**
+	 * @kernel_start: Start of the kernel-reserved address range. See
+	 * drm_asahi_params_global::vm_kernel_min_size.
+	 *
+	 * Both @kernel_start and @kernel_end must be within the range of
+	 * valid VAs given by drm_asahi_params_global::vm_start and
+	 * drm_asahi_params_global::vm_end. The size of the kernel range
+	 * (@kernel_end - @kernel_start) must be at least
+	 * drm_asahi_params_global::vm_kernel_min_size.
+	 *
+	 * Userspace must not bind any memory on this VM into this reserved
+	 * range, it is for kernel use only.
+	 */
+	__u64 kernel_start;
+
+	/**
+	 * @kernel_end: End of the kernel-reserved address range. See
+	 * @kernel_start.
+	 */
+	__u64 kernel_end;
+
+	/** @vm_id: Returned VM ID */
+	__u32 vm_id;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * struct drm_asahi_vm_destroy - Arguments passed to DRM_IOCTL_ASAHI_VM_DESTROY
+ */
+struct drm_asahi_vm_destroy {
+	/** @vm_id: VM ID to be destroyed */
+	__u32 vm_id;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * enum drm_asahi_gem_flags - Flags for GEM creation
+ */
+enum drm_asahi_gem_flags {
+	/**
+	 * @DRM_ASAHI_GEM_WRITEBACK: BO should be CPU-mapped as writeback.
+	 *
+	 * Map as writeback instead of write-combine. This optimizes for CPU
+	 * reads.
+	 */
+	DRM_ASAHI_GEM_WRITEBACK = (1L << 0),
+
+	/**
+	 * @DRM_ASAHI_GEM_VM_PRIVATE: BO is private to this GPU VM (no exports).
+	 */
+	DRM_ASAHI_GEM_VM_PRIVATE = (1L << 1),
+};
+
+/**
+ * struct drm_asahi_gem_create - Arguments passed to DRM_IOCTL_ASAHI_GEM_CREATE
+ */
+struct drm_asahi_gem_create {
+	/** @size: Size of the BO */
+	__u64 size;
+
+	/** @flags: Combination of drm_asahi_gem_flags flags. */
+	__u32 flags;
+
+	/**
+	 * @vm_id: VM ID to assign to the BO, if DRM_ASAHI_GEM_VM_PRIVATE is set
+	 */
+	__u32 vm_id;
+
+	/** @handle: Returned GEM handle for the BO */
+	__u32 handle;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * struct drm_asahi_gem_mmap_offset - Arguments passed to
+ * DRM_IOCTL_ASAHI_GEM_MMAP_OFFSET
+ */
+struct drm_asahi_gem_mmap_offset {
+	/** @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;
+};
+
+/**
+ * enum drm_asahi_bind_flags - Flags for GEM binding
+ */
+enum drm_asahi_bind_flags {
+	/**
+	 * @DRM_ASAHI_BIND_UNBIND: Instead of binding a GEM object to the range,
+	 * simply unbind the GPU VMA range.
+	 */
+	DRM_ASAHI_BIND_UNBIND = (1L << 0),
+
+	/** @DRM_ASAHI_BIND_READ: Map BO with GPU read permission */
+	DRM_ASAHI_BIND_READ = (1L << 1),
+
+	/** @DRM_ASAHI_BIND_WRITE: Map BO with GPU write permission */
+	DRM_ASAHI_BIND_WRITE = (1L << 2),
+
+	/**
+	 * @DRM_ASAHI_BIND_SINGLE_PAGE: Map a single page of the BO repeatedly
+	 * across the VA range.
+	 *
+	 * This is useful to fill a VA range with scratch pages or zero pages.
+	 * It is intended as a mechanism to accelerate sparse.
+	 */
+	DRM_ASAHI_BIND_SINGLE_PAGE = (1L << 3),
+};
+
+/**
+ * struct drm_asahi_gem_bind_op - Description of a single GEM bind operation.
+ */
+struct drm_asahi_gem_bind_op {
+	/** @flags: Combination of drm_asahi_bind_flags flags. */
+	__u32 flags;
+
+	/** @handle: GEM object to bind (except for UNBIND) */
+	__u32 handle;
+
+	/**
+	 * @offset: Offset into the object (except for UNBIND).
+	 *
+	 * For a regular bind, this is the beginning of the region of the GEM
+	 * object to bind.
+	 *
+	 * For a single-page bind, this is the offset to the single page that
+	 * will be repeatedly bound.
+	 *
+	 * Must be page-size aligned.
+	 */
+	__u64 offset;
+
+	/**
+	 * @range: Number of bytes to bind/unbind to @addr.
+	 *
+	 * Must be page-size aligned.
+	 */
+	__u64 range;
+
+	/**
+	 * @addr: Address to bind to.
+	 *
+	 * Must be page-size aligned.
+	 */
+	__u64 addr;
+};
+
+/**
+ * struct drm_asahi_vm_bind - Arguments passed to
+ * DRM_IOCTL_ASAHI_VM_BIND
+ */
+struct drm_asahi_vm_bind {
+	/** @vm_id: The ID of the VM to bind to */
+	__u32 vm_id;
+
+	/** @num_binds: number of binds in this IOCTL. */
+	__u32 num_binds;
+
+	/**
+	 * @stride: Stride in bytes between consecutive binds. This allows
+	 * extensibility of drm_asahi_gem_bind_op.
+	 */
+	__u32 stride;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/**
+	 * @userptr: User pointer to an array of @num_binds structures of type
+	 * @drm_asahi_gem_bind_op and size @stride bytes.
+	 */
+	__u64 userptr;
+};
+
+/**
+ * enum drm_asahi_bind_object_op - Special object bind operation
+ */
+enum drm_asahi_bind_object_op {
+	/** @DRM_ASAHI_BIND_OBJECT_OP_BIND: Bind a BO as a special GPU object */
+	DRM_ASAHI_BIND_OBJECT_OP_BIND = 0,
+
+	/** @DRM_ASAHI_BIND_OBJECT_OP_UNBIND: Unbind a special GPU object */
+	DRM_ASAHI_BIND_OBJECT_OP_UNBIND = 1,
+};
+
+/**
+ * enum drm_asahi_bind_object_flags - Special object bind flags
+ */
+enum drm_asahi_bind_object_flags {
+	/**
+	 * @DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS: Map a BO as a timestamp
+	 * buffer.
+	 */
+	DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS = (1L << 0),
+};
+
+/**
+ * struct drm_asahi_gem_bind_object - Arguments passed to
+ * DRM_IOCTL_ASAHI_GEM_BIND_OBJECT
+ */
+struct drm_asahi_gem_bind_object {
+	/** @op: Bind operation (enum drm_asahi_bind_object_op) */
+	__u32 op;
+
+	/** @flags: Combination of drm_asahi_bind_object_flags flags. */
+	__u32 flags;
+
+	/** @handle: GEM object to bind/unbind (BIND) */
+	__u32 handle;
+
+	/** @vm_id: The ID of the VM to operate on (MBZ currently) */
+	__u32 vm_id;
+
+	/** @offset: Offset into the object (BIND only) */
+	__u64 offset;
+
+	/** @range: Number of bytes to bind/unbind (BIND only) */
+	__u64 range;
+
+	/** @object_handle: Object handle (out for BIND, in for UNBIND) */
+	__u32 object_handle;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * enum drm_asahi_cmd_type - Command type
+ */
+enum drm_asahi_cmd_type {
+	/**
+	 * @DRM_ASAHI_CMD_RENDER: Render command, executing on the render
+	 * subqueue. Combined vertex and fragment operation.
+	 *
+	 * Followed by a @drm_asahi_cmd_render payload.
+	 */
+	DRM_ASAHI_CMD_RENDER = 0,
+
+	/**
+	 * @DRM_ASAHI_CMD_COMPUTE: Compute command on the compute subqueue.
+	 *
+	 * Followed by a @drm_asahi_cmd_compute payload.
+	 */
+	DRM_ASAHI_CMD_COMPUTE = 1,
+
+	/**
+	 * @DRM_ASAHI_SET_VERTEX_ATTACHMENTS: Software command to set
+	 * attachments for subsequent vertex shaders in the same submit.
+	 *
+	 * Followed by (possibly multiple) @drm_asahi_attachment payloads.
+	 */
+	DRM_ASAHI_SET_VERTEX_ATTACHMENTS = 2,
+
+	/**
+	 * @DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS: Software command to set
+	 * attachments for subsequent fragment shaders in the same submit.
+	 *
+	 * Followed by (possibly multiple) @drm_asahi_attachment payloads.
+	 */
+	DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS = 3,
+
+	/**
+	 * @DRM_ASAHI_SET_COMPUTE_ATTACHMENTS: Software command to set
+	 * attachments for subsequent compute shaders in the same submit.
+	 *
+	 * Followed by (possibly multiple) @drm_asahi_attachment payloads.
+	 */
+	DRM_ASAHI_SET_COMPUTE_ATTACHMENTS = 4,
+};
+
+/**
+ * enum drm_asahi_priority - Scheduling queue priority.
+ *
+ * These priorities are forwarded to the firmware to influence firmware
+ * scheduling. The exact policy is ultimately decided by firmware, but
+ * these enums allow userspace to communicate the intentions.
+ */
+enum drm_asahi_priority {
+	/** @DRM_ASAHI_PRIORITY_LOW: Low priority queue. */
+	DRM_ASAHI_PRIORITY_LOW = 0,
+
+	/** @DRM_ASAHI_PRIORITY_MEDIUM: Medium priority queue. */
+	DRM_ASAHI_PRIORITY_MEDIUM = 1,
+
+	/**
+	 * @DRM_ASAHI_PRIORITY_HIGH: High priority queue.
+	 *
+	 * Reserved for future extension.
+	 */
+	DRM_ASAHI_PRIORITY_HIGH = 2,
+
+	/**
+	 * @DRM_ASAHI_PRIORITY_REALTIME: Real-time priority queue.
+	 *
+	 * Reserved for future extension.
+	 */
+	DRM_ASAHI_PRIORITY_REALTIME = 3,
+};
+
+/**
+ * struct drm_asahi_queue_create - Arguments passed to
+ * DRM_IOCTL_ASAHI_QUEUE_CREATE
+ */
+struct drm_asahi_queue_create {
+	/** @flags: MBZ */
+	__u32 flags;
+
+	/** @vm_id: The ID of the VM this queue is bound to */
+	__u32 vm_id;
+
+	/** @priority: One of drm_asahi_priority */
+	__u32 priority;
+
+	/** @queue_id: The returned queue ID */
+	__u32 queue_id;
+
+	/**
+	 * @usc_exec_base: GPU base address for all USC binaries (shaders) on
+	 * this queue. USC addresses are 32-bit relative to this 64-bit base.
+	 *
+	 * This sets the following registers on all queue commands:
+	 *
+	 *	USC_EXEC_BASE_TA  (vertex)
+	 *	USC_EXEC_BASE_ISP (fragment)
+	 *	USC_EXEC_BASE_CP  (compute)
+	 *
+	 * While the hardware lets us configure these independently per command,
+	 * we do not have a use case for this. Instead, we expect userspace to
+	 * fix a 4GiB VA carveout for USC memory and pass its base address here.
+	 */
+	__u64 usc_exec_base;
+};
+
+/**
+ * struct drm_asahi_queue_destroy - Arguments passed to
+ * DRM_IOCTL_ASAHI_QUEUE_DESTROY
+ */
+struct drm_asahi_queue_destroy {
+	/** @queue_id: The queue ID to be destroyed */
+	__u32 queue_id;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * enum drm_asahi_sync_type - Sync item type
+ */
+enum drm_asahi_sync_type {
+	/** @DRM_ASAHI_SYNC_SYNCOBJ: Binary sync object */
+	DRM_ASAHI_SYNC_SYNCOBJ = 0,
+
+	/** @DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ: Timeline sync object */
+	DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ = 1,
+};
+
+/**
+ * struct drm_asahi_sync - Sync item
+ */
+struct drm_asahi_sync {
+	/** @sync_type: One of drm_asahi_sync_type */
+	__u32 sync_type;
+
+	/** @handle: The sync object handle */
+	__u32 handle;
+
+	/** @timeline_value: Timeline value for timeline sync objects */
+	__u64 timeline_value;
+};
+
+/**
+ * define DRM_ASAHI_BARRIER_NONE - Command index for no barrier
+ *
+ * This special value may be passed in to drm_asahi_command::vdm_barrier or
+ * drm_asahi_command::cdm_barrier to indicate that the respective subqueue
+ * should not wait on any previous work.
+ */
+#define DRM_ASAHI_BARRIER_NONE (0xFFFFu)
+
+/**
+ * struct drm_asahi_cmd_header - Top level command structure
+ *
+ * This struct is core to the command buffer definition and therefore is not
+ * extensible.
+ */
+struct drm_asahi_cmd_header {
+	/** @cmd_type: One of drm_asahi_cmd_type */
+	__u16 cmd_type;
+
+	/**
+	 * @size: Size of this command, not including this header.
+	 *
+	 * For hardware commands, this enables extensibility of commands without
+	 * requiring extra command types. Passing a command that is shorter
+	 * than expected is explicitly allowed for backwards-compatibility.
+	 * Truncated fields will be zeroed.
+	 *
+	 * For the synthetic attachment setting commands, this implicitly
+	 * encodes the number of attachments. These commands take multiple
+	 * fixed-size @drm_asahi_attachment structures as their payload, so size
+	 * equals number of attachments * sizeof(struct drm_asahi_attachment).
+	 */
+	__u16 size;
+
+	/**
+	 * @vdm_barrier: VDM (render) command index to wait on.
+	 *
+	 * Barriers are indices relative to the beginning of a given submit. A
+	 * barrier of 0 waits on commands submitted to the respective subqueue
+	 * in previous submit ioctls. A barrier of N waits on N previous
+	 * commands on the subqueue within the current submit ioctl. As a
+	 * special case, passing @DRM_ASAHI_BARRIER_NONE avoids waiting on any
+	 * commands in the subqueue.
+	 *
+	 * Examples:
+	 *
+	 *   0: This waits on all previous work.
+	 *
+	 *   NONE: This does not wait for anything on this subqueue.
+	 *
+	 *   1: This waits on the first render command in the submit.
+	 *   This is valid only if there are multiple render commands in the
+	 *   same submit.
+	 *
+	 * Barriers are valid only for hardware commands. Synthetic software
+	 * commands to set attachments must pass NONE here.
+	 */
+	__u16 vdm_barrier;
+
+	/**
+	 * @cdm_barrier: CDM (compute) command index to wait on.
+	 *
+	 * See @vdm_barrier, and replace VDM/render with CDM/compute.
+	 */
+	__u16 cdm_barrier;
+};
+
+/**
+ * struct drm_asahi_submit - Arguments passed to DRM_IOCTL_ASAHI_SUBMIT
+ */
+struct drm_asahi_submit {
+	/**
+	 * @syncs: An optional pointer to an array of drm_asahi_sync. The first
+	 * @in_sync_count elements are in-syncs, then the remaining
+	 * @out_sync_count elements are out-syncs. Using a single array with
+	 * explicit partitioning simplifies handling.
+	 */
+	__u64 syncs;
+
+	/**
+	 * @cmdbuf: Pointer to the command buffer to submit.
+	 *
+	 * This is a flat command buffer. By design, it contains no CPU
+	 * pointers, which makes it suitable for a virtgpu wire protocol without
+	 * requiring any serializing/deserializing step.
+	 *
+	 * It consists of a series of commands. Each command begins with a
+	 * fixed-size @drm_asahi_cmd_header header and is followed by a
+	 * variable-length payload according to the type and size in the header.
+	 *
+	 * The combined count of "real" hardware commands must be nonzero and at
+	 * most drm_asahi_params_global::max_commands_per_submission.
+	 */
+	__u64 cmdbuf;
+
+	/** @flags: Flags for command submission (MBZ) */
+	__u32 flags;
+
+	/** @queue_id: The queue ID to be submitted to */
+	__u32 queue_id;
+
+	/**
+	 * @in_sync_count: Number of sync objects to wait on before starting
+	 * this job.
+	 */
+	__u32 in_sync_count;
+
+	/**
+	 * @out_sync_count: Number of sync objects to signal upon completion of
+	 * this job.
+	 */
+	__u32 out_sync_count;
+
+	/** @cmdbuf_size: Command buffer size in bytes */
+	__u32 cmdbuf_size;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * struct drm_asahi_attachment - Describe an "attachment".
+ *
+ * Attachments are any memory written by shaders, notably including render
+ * target attachments written by the end-of-tile program. This is purely a hint
+ * about the accessed memory regions. It is optional to specify, which is
+ * fortunate as it cannot be specified precisely with bindless access anyway.
+ * But where possible, it's probably a good idea for userspace to include these
+ * hints, forwarded to the firmware.
+ *
+ * This struct is implicitly sized and therefore is not extensible.
+ */
+struct drm_asahi_attachment {
+	/** @pointer: Base address of the attachment */
+	__u64 pointer;
+
+	/** @size: Size of the attachment in bytes */
+	__u64 size;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	/** @flags: MBZ */
+	__u32 flags;
+};
+
+enum drm_asahi_render_flags {
+	/**
+	 * @DRM_ASAHI_RENDER_VERTEX_SCRATCH: A vertex stage shader uses scratch
+	 * memory.
+	 */
+	DRM_ASAHI_RENDER_VERTEX_SCRATCH = (1U << 0),
+
+	/**
+	 * @DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES: Process even empty tiles.
+	 * This must be set when clearing render targets.
+	 */
+	DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES = (1U << 1),
+
+	/**
+	 * @DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING: Run vertex stage on a single
+	 * cluster (on multi-cluster GPUs)
+	 *
+	 * This harms performance but can workaround certain sync/coherency
+	 * bugs, and therefore is useful for debugging.
+	 */
+	DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING = (1U << 2),
+
+	/**
+	 * @DRM_ASAHI_RENDER_DBIAS_IS_INT: Use integer depth bias formula.
+	 *
+	 * Graphics specifications contain two alternate formulas for depth
+	 * bias, a float formula used with floating-point depth buffers and an
+	 * integer formula using with unorm depth buffers. This flag specifies
+	 * that the integer formula should be used. If omitted, the float
+	 * formula is used instead.
+	 *
+	 * This corresponds to bit 18 of the relevant hardware control register,
+	 * so we match that here for efficiency.
+	 */
+	DRM_ASAHI_RENDER_DBIAS_IS_INT = (1U << 18),
+};
+
+/**
+ * struct drm_asahi_zls_buffer - Describe a depth or stencil buffer.
+ *
+ * These fields correspond to hardware registers in the ZLS (Z Load/Store) unit.
+ * There are three hardware registers for each field respectively for loads,
+ * stores, and partial renders. In practice, it makes sense to set all to the
+ * same values, except in exceptional cases not yet implemented in userspace, so
+ * we do not duplicate here for simplicity/efficiency.
+ *
+ * This struct is embedded in other structs and therefore is not extensible.
+ */
+struct drm_asahi_zls_buffer {
+	/** @base: Base address of the buffer */
+	__u64 base;
+
+	/**
+	 * @comp_base: If the load buffer is compressed, address of the
+	 * compression metadata section.
+	 */
+	__u64 comp_base;
+
+	/**
+	 * @stride: If layered rendering is enabled, the number of bytes
+	 * between each layer of the buffer.
+	 */
+	__u32 stride;
+
+	/**
+	 * @comp_stride: If layered rendering is enabled, the number of bytes
+	 * between each layer of the compression metadata.
+	 */
+	__u32 comp_stride;
+};
+
+/**
+ * struct drm_asahi_timestamp - Describe a timestamp write.
+ *
+ * The firmware can optionally write the GPU timestamp at render pass
+ * granularities, but it needs to be mapped specially via
+ * DRM_IOCTL_ASAHI_GEM_BIND_OBJECT. This structure therefore describes where to
+ * write as a handle-offset pair, rather than a GPU address like normal.
+ *
+ * This struct is embedded in other structs and therefore is not extensible.
+ */
+struct drm_asahi_timestamp {
+	/**
+	 * @handle: Handle of the timestamp buffer, or 0 to skip this
+	 * timestamp. If nonzero, this must equal the value returned in
+	 * drm_asahi_gem_bind_object::object_handle.
+	 */
+	__u32 handle;
+
+	/** @offset: Offset to write into the timestamp buffer */
+	__u32 offset;
+};
+
+/**
+ * struct drm_asahi_timestamps - Describe timestamp writes.
+ *
+ * Each operation that can be timestamped, can be timestamped at the start and
+ * end. Therefore, drm_asahi_timestamp structs always come in pairs, bundled
+ * together into drm_asahi_timestamps.
+ *
+ * This struct is embedded in other structs and therefore is not extensible.
+ */
+struct drm_asahi_timestamps {
+	/** @start: Timestamp recorded at the start of the operation */
+	struct drm_asahi_timestamp start;
+
+	/** @end: Timestamp recorded at the end of the operation */
+	struct drm_asahi_timestamp end;
+};
+
+/**
+ * struct drm_asahi_helper_program - Describe helper program configuration.
+ *
+ * The helper program is a compute-like kernel required for various hardware
+ * functionality. Its most important role is dynamically allocating
+ * scratch/stack memory for individual subgroups, by partitioning a static
+ * allocation shared for the whole device. It is supplied by userspace via
+ * drm_asahi_helper_program and internally dispatched by the hardware as needed.
+ *
+ * This struct is embedded in other structs and therefore is not extensible.
+ */
+struct drm_asahi_helper_program {
+	/**
+	 * @binary: USC address to the helper program binary. This is a tagged
+	 * pointer with configuration in the bottom bits.
+	 */
+	__u32 binary;
+
+	/** @cfg: Additional configuration bits for the helper program. */
+	__u32 cfg;
+
+	/**
+	 * @data: Data passed to the helper program. This value is not
+	 * interpreted by the kernel, firmware, or hardware in any way. It is
+	 * simply a sideband for userspace, set with the submit ioctl and read
+	 * via special registers inside the helper program.
+	 *
+	 * In practice, userspace will pass a 64-bit GPU VA here pointing to the
+	 * actual arguments, which presumably don't fit in 64-bits.
+	 */
+	__u64 data;
+};
+
+/**
+ * struct drm_asahi_bg_eot - Describe a background or end-of-tile program.
+ *
+ * The background and end-of-tile programs are dispatched by the hardware at the
+ * beginning and end of rendering. As the hardware "tilebuffer" is simply local
+ * memory, these programs are necessary to implement API-level render targets.
+ * The fragment-like background program is responsible for loading either the
+ * clear colour or the existing render target contents, while the compute-like
+ * end-of-tile program stores the tilebuffer contents to memory.
+ *
+ * This struct is embedded in other structs and therefore is not extensible.
+ */
+struct drm_asahi_bg_eot {
+	/**
+	 * @usc: USC address of the hardware USC words binding resources
+	 * (including images and uniforms) and the program itself. Note this is
+	 * an additional layer of indirection compared to the helper program,
+	 * avoiding the need for a sideband for data. This is a tagged pointer
+	 * with additional configuration in the bottom bits.
+	 */
+	__u32 usc;
+
+	/**
+	 * @rsrc_spec: Resource specifier for the program. This is a packed
+	 * hardware data structure describing the required number of registers,
+	 * uniforms, bound textures, and bound samplers.
+	 */
+	__u32 rsrc_spec;
+};
+
+/**
+ * struct drm_asahi_cmd_render - Command to submit 3D
+ *
+ * This command submits a single render pass. The hardware control stream may
+ * include many draws and subpasses, but within the command, the framebuffer
+ * dimensions and attachments are fixed.
+ *
+ * The hardware requires the firmware to set a large number of Control Registers
+ * setting up state at render pass granularity before each command rendering 3D.
+ * The firmware bundles this state into data structures. Unfortunately, we
+ * cannot expose either any of that directly to userspace, because the
+ * kernel-firmware ABI is not stable. Although we can guarantee the firmware
+ * updates in tandem with the kernel, we cannot break old userspace when
+ * upgrading the firmware and kernel. Therefore, we need to abstract well the
+ * data structures to avoid tying our hands with future firmwares.
+ *
+ * The bulk of drm_asahi_cmd_render therefore consists of values of hardware
+ * control registers, marshalled via the firmware interface.
+ *
+ * The framebuffer/tilebuffer dimensions are also specified here. In addition to
+ * being passed to the firmware/hardware, the kernel requires these dimensions
+ * to calculate various essential tiling-related data structures. It is
+ * unfortunate that our submits are heavier than on vendors with saner
+ * hardware-software interfaces. The upshot is all of this information is
+ * readily available to userspace with all current APIs.
+ *
+ * It looks odd - but it's not overly burdensome and it ensures we can remain
+ * compatible with old userspace.
+ */
+struct drm_asahi_cmd_render {
+	/** @flags: Combination of drm_asahi_render_flags flags. */
+	__u32 flags;
+
+	/**
+	 * @isp_zls_pixels: ISP_ZLS_PIXELS register value. This contains the
+	 * depth/stencil width/height, which may differ from the framebuffer
+	 * width/height.
+	 */
+	__u32 isp_zls_pixels;
+
+	/**
+	 * @vdm_ctrl_stream_base: VDM_CTRL_STREAM_BASE register value. GPU
+	 * address to the beginning of the VDM control stream.
+	 */
+	__u64 vdm_ctrl_stream_base;
+
+	/** @vertex_helper: Helper program used for the vertex shader */
+	struct drm_asahi_helper_program vertex_helper;
+
+	/** @fragment_helper: Helper program used for the fragment shader */
+	struct drm_asahi_helper_program fragment_helper;
+
+	/**
+	 * @isp_scissor_base: ISP_SCISSOR_BASE register value. GPU address of an
+	 * array of scissor descriptors indexed in the render pass.
+	 */
+	__u64 isp_scissor_base;
+
+	/**
+	 * @isp_dbias_base: ISP_DBIAS_BASE register value. GPU address of an
+	 * array of depth bias values indexed in the render pass.
+	 */
+	__u64 isp_dbias_base;
+
+	/**
+	 * @isp_oclqry_base: ISP_OCLQRY_BASE register value. GPU address of an
+	 * array of occlusion query results written by the render pass.
+	 */
+	__u64 isp_oclqry_base;
+
+	/** @depth: Depth buffer */
+	struct drm_asahi_zls_buffer depth;
+
+	/** @stencil: Stencil buffer */
+	struct drm_asahi_zls_buffer stencil;
+
+	/** @zls_ctrl: ZLS_CTRL register value */
+	__u64 zls_ctrl;
+
+	/** @ppp_multisamplectl: PPP_MULTISAMPLECTL register value */
+	__u64 ppp_multisamplectl;
+
+	/**
+	 * @sampler_heap: Base address of the sampler heap. This heap is used
+	 * for both vertex shaders and fragment shaders. The registers are
+	 * per-stage, but there is no known use case for separate heaps.
+	 */
+	__u64 sampler_heap;
+
+	/** @ppp_ctrl: PPP_CTRL register value */
+	__u32 ppp_ctrl;
+
+	/** @width_px: Framebuffer width in pixels */
+	__u16 width_px;
+
+	/** @height_px: Framebuffer height in pixels */
+	__u16 height_px;
+
+	/** @layers: Number of layers in the framebuffer */
+	__u16 layers;
+
+	/** @sampler_count: Number of samplers in the sampler heap. */
+	__u16 sampler_count;
+
+	/** @utile_width_px: Width of a logical tilebuffer tile in pixels */
+	__u8 utile_width_px;
+
+	/** @utile_height_px: Height of a logical tilebuffer tile in pixels */
+	__u8 utile_height_px;
+
+	/** @samples: # of samples in the framebuffer. Must be 1, 2, or 4. */
+	__u8 samples;
+
+	/** @sample_size_B: # of bytes in the tilebuffer required per sample. */
+	__u8 sample_size_B;
+
+	/**
+	 * @isp_merge_upper_x: 32-bit float used in the hardware triangle
+	 * merging. Calculate as: tan(60 deg) * width.
+	 *
+	 * Making these values UAPI avoids requiring floating-point calculations
+	 * in the kernel in the hot path.
+	 */
+	__u32 isp_merge_upper_x;
+
+	/**
+	 * @isp_merge_upper_y: 32-bit float. Calculate as: tan(60 deg) * height.
+	 * See @isp_merge_upper_x.
+	 */
+	__u32 isp_merge_upper_y;
+
+	/** @bg: Background program run for each tile at the start */
+	struct drm_asahi_bg_eot bg;
+
+	/** @eot: End-of-tile program ran for each tile at the end */
+	struct drm_asahi_bg_eot eot;
+
+	/**
+	 * @partial_bg: Background program ran at the start of each tile when
+	 * resuming the render pass during a partial render.
+	 */
+	struct drm_asahi_bg_eot partial_bg;
+
+	/**
+	 * @partial_eot: End-of-tile program ran at the end of each tile when
+	 * pausing the render pass during a partial render.
+	 */
+	struct drm_asahi_bg_eot partial_eot;
+
+	/**
+	 * @isp_bgobjdepth: ISP_BGOBJDEPTH register value. This is the depth
+	 * buffer clear value, encoded in the depth buffer's format: either a
+	 * 32-bit float or a 16-bit unorm (with upper bits zeroed).
+	 */
+	__u32 isp_bgobjdepth;
+
+	/**
+	 * @isp_bgobjvals: ISP_BGOBJVALS register value. The bottom 8-bits
+	 * contain the stencil buffer clear value.
+	 */
+	__u32 isp_bgobjvals;
+
+	/** @ts_vtx: Timestamps for the vertex portion of the render */
+	struct drm_asahi_timestamps ts_vtx;
+
+	/** @ts_frag: Timestamps for the fragment portion of the render */
+	struct drm_asahi_timestamps ts_frag;
+};
+
+/**
+ * struct drm_asahi_cmd_compute - Command to submit compute
+ *
+ * This command submits a control stream consisting of compute dispatches. There
+ * is essentially no limit on how many compute dispatches may be included in a
+ * single compute command, although timestamps are at command granularity.
+ */
+struct drm_asahi_cmd_compute {
+	/** @flags: MBZ */
+	__u32 flags;
+
+	/** @sampler_count: Number of samplers in the sampler heap. */
+	__u32 sampler_count;
+
+	/**
+	 * @cdm_ctrl_stream_base: CDM_CTRL_STREAM_BASE register value. GPU
+	 * address to the beginning of the CDM control stream.
+	 */
+	__u64 cdm_ctrl_stream_base;
+
+	/**
+	 * @cdm_ctrl_stream_end: GPU base address to the end of the hardware
+	 * control stream. Note this only considers the first contiguous segment
+	 * of the control stream, as the stream might jump elsewhere.
+	 */
+	__u64 cdm_ctrl_stream_end;
+
+	/** @sampler_heap: Base address of the sampler heap. */
+	__u64 sampler_heap;
+
+	/** @helper: Helper program used for this compute command */
+	struct drm_asahi_helper_program helper;
+
+	/** @ts: Timestamps for the compute command */
+	struct drm_asahi_timestamps ts;
+};
+
+/**
+ * struct drm_asahi_get_time - Arguments passed to DRM_IOCTL_ASAHI_GET_TIME
+ */
+struct drm_asahi_get_time {
+	/** @flags: MBZ. */
+	__u64 flags;
+
+	/** @gpu_timestamp: On return, the GPU timestamp in nanoseconds. */
+	__u64 gpu_timestamp;
+};
+
+/**
+ * DRM_IOCTL_ASAHI() - Build an Asahi IOCTL number
+ * @__access: Access type. Must be R, W or RW.
+ * @__id: One of the DRM_ASAHI_xxx id.
+ * @__type: Suffix of the type being passed to the IOCTL.
+ *
+ * Don't use this macro directly, use the DRM_IOCTL_ASAHI_xxx
+ * values instead.
+ *
+ * Return: An IOCTL number to be passed to ioctl() from userspace.
+ */
+#define DRM_IOCTL_ASAHI(__access, __id, __type) \
+	DRM_IO ## __access(DRM_COMMAND_BASE + DRM_ASAHI_ ## __id, \
+			   struct drm_asahi_ ## __type)
+
+/* Note: this is an enum so that it can be resolved by Rust bindgen. */
+enum {
+	DRM_IOCTL_ASAHI_GET_PARAMS       = DRM_IOCTL_ASAHI(W, GET_PARAMS, get_params),
+	DRM_IOCTL_ASAHI_GET_TIME         = DRM_IOCTL_ASAHI(WR, GET_TIME, get_time),
+	DRM_IOCTL_ASAHI_VM_CREATE        = DRM_IOCTL_ASAHI(WR, VM_CREATE, vm_create),
+	DRM_IOCTL_ASAHI_VM_DESTROY       = DRM_IOCTL_ASAHI(W, VM_DESTROY, vm_destroy),
+	DRM_IOCTL_ASAHI_VM_BIND          = DRM_IOCTL_ASAHI(W, VM_BIND, vm_bind),
+	DRM_IOCTL_ASAHI_GEM_CREATE       = DRM_IOCTL_ASAHI(WR, GEM_CREATE, gem_create),
+	DRM_IOCTL_ASAHI_GEM_MMAP_OFFSET  = DRM_IOCTL_ASAHI(WR, GEM_MMAP_OFFSET, gem_mmap_offset),
+	DRM_IOCTL_ASAHI_GEM_BIND_OBJECT  = DRM_IOCTL_ASAHI(WR, GEM_BIND_OBJECT, gem_bind_object),
+	DRM_IOCTL_ASAHI_QUEUE_CREATE     = DRM_IOCTL_ASAHI(WR, QUEUE_CREATE, queue_create),
+	DRM_IOCTL_ASAHI_QUEUE_DESTROY    = DRM_IOCTL_ASAHI(W, QUEUE_DESTROY, queue_destroy),
+	DRM_IOCTL_ASAHI_SUBMIT           = DRM_IOCTL_ASAHI(W, SUBMIT, submit),
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _ASAHI_DRM_H_ */
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
new file mode 100644
index 000000000..bc7ef7684
--- /dev/null
+++ b/include/uapi/drm/drm.h
@@ -0,0 +1,1480 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Header for the Direct Rendering Manager
+ *
+ * Author: Rickard E. (Rik) Faith <faith@valinux.com>
+ *
+ * Acknowledgments:
+ * Dec 1999, Richard Henderson <rth@twiddle.net>, move to generic cmpxchg.
+ */
+
+/*
+ * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
+ * All rights reserved.
+ */
+
+#ifndef _DRM_H_
+#define _DRM_H_
+
+#if defined(__KERNEL__)
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+typedef unsigned int drm_handle_t;
+
+#elif defined(__linux__)
+
+#include <linux/types.h>
+#include <asm/ioctl.h>
+typedef unsigned int drm_handle_t;
+
+#else /* One of the BSDs */
+
+#include <stdint.h>
+#include <sys/ioccom.h>
+#include <sys/types.h>
+typedef int8_t   __s8;
+typedef uint8_t  __u8;
+typedef int16_t  __s16;
+typedef uint16_t __u16;
+typedef int32_t  __s32;
+typedef uint32_t __u32;
+typedef int64_t  __s64;
+typedef uint64_t __u64;
+typedef size_t   __kernel_size_t;
+typedef unsigned long drm_handle_t;
+
+#endif
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_NAME	"drm"	  /**< Name in kernel, /dev, and /proc */
+#define DRM_MIN_ORDER	5	  /**< At least 2^5 bytes = 32 bytes */
+#define DRM_MAX_ORDER	22	  /**< Up to 2^22 bytes = 4MB */
+#define DRM_RAM_PERCENT 10	  /**< How much system ram can we lock? */
+
+#define _DRM_LOCK_HELD	0x80000000U /**< Hardware lock is held */
+#define _DRM_LOCK_CONT	0x40000000U /**< Hardware lock is contended */
+#define _DRM_LOCK_IS_HELD(lock)	   ((lock) & _DRM_LOCK_HELD)
+#define _DRM_LOCK_IS_CONT(lock)	   ((lock) & _DRM_LOCK_CONT)
+#define _DRM_LOCKING_CONTEXT(lock) ((lock) & ~(_DRM_LOCK_HELD|_DRM_LOCK_CONT))
+
+typedef unsigned int drm_context_t;
+typedef unsigned int drm_drawable_t;
+typedef unsigned int drm_magic_t;
+
+/*
+ * Cliprect.
+ *
+ * \warning: If you change this structure, make sure you change
+ * XF86DRIClipRectRec in the server as well
+ *
+ * \note KW: Actually it's illegal to change either for
+ * backwards-compatibility reasons.
+ */
+struct drm_clip_rect {
+	unsigned short x1;
+	unsigned short y1;
+	unsigned short x2;
+	unsigned short y2;
+};
+
+/*
+ * Drawable information.
+ */
+struct drm_drawable_info {
+	unsigned int num_rects;
+	struct drm_clip_rect *rects;
+};
+
+/*
+ * Texture region,
+ */
+struct drm_tex_region {
+	unsigned char next;
+	unsigned char prev;
+	unsigned char in_use;
+	unsigned char padding;
+	unsigned int age;
+};
+
+/*
+ * Hardware lock.
+ *
+ * The lock structure is a simple cache-line aligned integer.  To avoid
+ * processor bus contention on a multiprocessor system, there should not be any
+ * other data stored in the same cache line.
+ */
+struct drm_hw_lock {
+	__volatile__ unsigned int lock;		/**< lock variable */
+	char padding[60];			/**< Pad to cache line */
+};
+
+/*
+ * DRM_IOCTL_VERSION ioctl argument type.
+ *
+ * \sa drmGetVersion().
+ */
+struct drm_version {
+	int version_major;	  /**< Major version */
+	int version_minor;	  /**< Minor version */
+	int version_patchlevel;	  /**< Patch level */
+	__kernel_size_t name_len;	  /**< Length of name buffer */
+	char __user *name;	  /**< Name of driver */
+	__kernel_size_t date_len;	  /**< Length of date buffer */
+	char __user *date;	  /**< User-space buffer to hold date */
+	__kernel_size_t desc_len;	  /**< Length of desc buffer */
+	char __user *desc;	  /**< User-space buffer to hold desc */
+};
+
+/*
+ * DRM_IOCTL_GET_UNIQUE ioctl argument type.
+ *
+ * \sa drmGetBusid() and drmSetBusId().
+ */
+struct drm_unique {
+	__kernel_size_t unique_len;	  /**< Length of unique */
+	char __user *unique;	  /**< Unique name for driver instantiation */
+};
+
+struct drm_list {
+	int count;		  /**< Length of user-space structures */
+	struct drm_version __user *version;
+};
+
+struct drm_block {
+	int unused;
+};
+
+/*
+ * DRM_IOCTL_CONTROL ioctl argument type.
+ *
+ * \sa drmCtlInstHandler() and drmCtlUninstHandler().
+ */
+struct drm_control {
+	enum {
+		DRM_ADD_COMMAND,
+		DRM_RM_COMMAND,
+		DRM_INST_HANDLER,
+		DRM_UNINST_HANDLER
+	} func;
+	int irq;
+};
+
+/*
+ * Type of memory to map.
+ */
+enum drm_map_type {
+	_DRM_FRAME_BUFFER = 0,	  /**< WC (no caching), no core dump */
+	_DRM_REGISTERS = 1,	  /**< no caching, no core dump */
+	_DRM_SHM = 2,		  /**< shared, cached */
+	_DRM_AGP = 3,		  /**< AGP/GART */
+	_DRM_SCATTER_GATHER = 4,  /**< Scatter/gather memory for PCI DMA */
+	_DRM_CONSISTENT = 5	  /**< Consistent memory for PCI DMA */
+};
+
+/*
+ * Memory mapping flags.
+ */
+enum drm_map_flags {
+	_DRM_RESTRICTED = 0x01,	     /**< Cannot be mapped to user-virtual */
+	_DRM_READ_ONLY = 0x02,
+	_DRM_LOCKED = 0x04,	     /**< shared, cached, locked */
+	_DRM_KERNEL = 0x08,	     /**< kernel requires access */
+	_DRM_WRITE_COMBINING = 0x10, /**< use write-combining if available */
+	_DRM_CONTAINS_LOCK = 0x20,   /**< SHM page that contains lock */
+	_DRM_REMOVABLE = 0x40,	     /**< Removable mapping */
+	_DRM_DRIVER = 0x80	     /**< Managed by driver */
+};
+
+struct drm_ctx_priv_map {
+	unsigned int ctx_id;	 /**< Context requesting private mapping */
+	void *handle;		 /**< Handle of map */
+};
+
+/*
+ * DRM_IOCTL_GET_MAP, DRM_IOCTL_ADD_MAP and DRM_IOCTL_RM_MAP ioctls
+ * argument type.
+ *
+ * \sa drmAddMap().
+ */
+struct drm_map {
+	unsigned long offset;	 /**< Requested physical address (0 for SAREA)*/
+	unsigned long size;	 /**< Requested physical size (bytes) */
+	enum drm_map_type type;	 /**< Type of memory to map */
+	enum drm_map_flags flags;	 /**< Flags */
+	void *handle;		 /**< User-space: "Handle" to pass to mmap() */
+				 /**< Kernel-space: kernel-virtual address */
+	int mtrr;		 /**< MTRR slot used */
+	/*   Private data */
+};
+
+/*
+ * DRM_IOCTL_GET_CLIENT ioctl argument type.
+ */
+struct drm_client {
+	int idx;		/**< Which client desired? */
+	int auth;		/**< Is client authenticated? */
+	unsigned long pid;	/**< Process ID */
+	unsigned long uid;	/**< User ID */
+	unsigned long magic;	/**< Magic */
+	unsigned long iocs;	/**< Ioctl count */
+};
+
+enum drm_stat_type {
+	_DRM_STAT_LOCK,
+	_DRM_STAT_OPENS,
+	_DRM_STAT_CLOSES,
+	_DRM_STAT_IOCTLS,
+	_DRM_STAT_LOCKS,
+	_DRM_STAT_UNLOCKS,
+	_DRM_STAT_VALUE,	/**< Generic value */
+	_DRM_STAT_BYTE,		/**< Generic byte counter (1024bytes/K) */
+	_DRM_STAT_COUNT,	/**< Generic non-byte counter (1000/k) */
+
+	_DRM_STAT_IRQ,		/**< IRQ */
+	_DRM_STAT_PRIMARY,	/**< Primary DMA bytes */
+	_DRM_STAT_SECONDARY,	/**< Secondary DMA bytes */
+	_DRM_STAT_DMA,		/**< DMA */
+	_DRM_STAT_SPECIAL,	/**< Special DMA (e.g., priority or polled) */
+	_DRM_STAT_MISSED	/**< Missed DMA opportunity */
+	    /* Add to the *END* of the list */
+};
+
+/*
+ * DRM_IOCTL_GET_STATS ioctl argument type.
+ */
+struct drm_stats {
+	unsigned long count;
+	struct {
+		unsigned long value;
+		enum drm_stat_type type;
+	} data[15];
+};
+
+/*
+ * Hardware locking flags.
+ */
+enum drm_lock_flags {
+	_DRM_LOCK_READY = 0x01,	     /**< Wait until hardware is ready for DMA */
+	_DRM_LOCK_QUIESCENT = 0x02,  /**< Wait until hardware quiescent */
+	_DRM_LOCK_FLUSH = 0x04,	     /**< Flush this context's DMA queue first */
+	_DRM_LOCK_FLUSH_ALL = 0x08,  /**< Flush all DMA queues first */
+	/* These *HALT* flags aren't supported yet
+	   -- they will be used to support the
+	   full-screen DGA-like mode. */
+	_DRM_HALT_ALL_QUEUES = 0x10, /**< Halt all current and future queues */
+	_DRM_HALT_CUR_QUEUES = 0x20  /**< Halt all current queues */
+};
+
+/*
+ * DRM_IOCTL_LOCK, DRM_IOCTL_UNLOCK and DRM_IOCTL_FINISH ioctl argument type.
+ *
+ * \sa drmGetLock() and drmUnlock().
+ */
+struct drm_lock {
+	int context;
+	enum drm_lock_flags flags;
+};
+
+/*
+ * DMA flags
+ *
+ * \warning
+ * These values \e must match xf86drm.h.
+ *
+ * \sa drm_dma.
+ */
+enum drm_dma_flags {
+	/* Flags for DMA buffer dispatch */
+	_DRM_DMA_BLOCK = 0x01,	      /**<
+				       * Block until buffer dispatched.
+				       *
+				       * \note The buffer may not yet have
+				       * been processed by the hardware --
+				       * getting a hardware lock with the
+				       * hardware quiescent will ensure
+				       * that the buffer has been
+				       * processed.
+				       */
+	_DRM_DMA_WHILE_LOCKED = 0x02, /**< Dispatch while lock held */
+	_DRM_DMA_PRIORITY = 0x04,     /**< High priority dispatch */
+
+	/* Flags for DMA buffer request */
+	_DRM_DMA_WAIT = 0x10,	      /**< Wait for free buffers */
+	_DRM_DMA_SMALLER_OK = 0x20,   /**< Smaller-than-requested buffers OK */
+	_DRM_DMA_LARGER_OK = 0x40     /**< Larger-than-requested buffers OK */
+};
+
+/*
+ * DRM_IOCTL_ADD_BUFS and DRM_IOCTL_MARK_BUFS ioctl argument type.
+ *
+ * \sa drmAddBufs().
+ */
+struct drm_buf_desc {
+	int count;		 /**< Number of buffers of this size */
+	int size;		 /**< Size in bytes */
+	int low_mark;		 /**< Low water mark */
+	int high_mark;		 /**< High water mark */
+	enum {
+		_DRM_PAGE_ALIGN = 0x01,	/**< Align on page boundaries for DMA */
+		_DRM_AGP_BUFFER = 0x02,	/**< Buffer is in AGP space */
+		_DRM_SG_BUFFER = 0x04,	/**< Scatter/gather memory buffer */
+		_DRM_FB_BUFFER = 0x08,	/**< Buffer is in frame buffer */
+		_DRM_PCI_BUFFER_RO = 0x10 /**< Map PCI DMA buffer read-only */
+	} flags;
+	unsigned long agp_start; /**<
+				  * Start address of where the AGP buffers are
+				  * in the AGP aperture
+				  */
+};
+
+/*
+ * DRM_IOCTL_INFO_BUFS ioctl argument type.
+ */
+struct drm_buf_info {
+	int count;		/**< Entries in list */
+	struct drm_buf_desc __user *list;
+};
+
+/*
+ * DRM_IOCTL_FREE_BUFS ioctl argument type.
+ */
+struct drm_buf_free {
+	int count;
+	int __user *list;
+};
+
+/*
+ * Buffer information
+ *
+ * \sa drm_buf_map.
+ */
+struct drm_buf_pub {
+	int idx;		       /**< Index into the master buffer list */
+	int total;		       /**< Buffer size */
+	int used;		       /**< Amount of buffer in use (for DMA) */
+	void __user *address;	       /**< Address of buffer */
+};
+
+/*
+ * DRM_IOCTL_MAP_BUFS ioctl argument type.
+ */
+struct drm_buf_map {
+	int count;		/**< Length of the buffer list */
+#ifdef __cplusplus
+	void __user *virt;
+#else
+	void __user *virtual;		/**< Mmap'd area in user-virtual */
+#endif
+	struct drm_buf_pub __user *list;	/**< Buffer information */
+};
+
+/*
+ * DRM_IOCTL_DMA ioctl argument type.
+ *
+ * Indices here refer to the offset into the buffer list in drm_buf_get.
+ *
+ * \sa drmDMA().
+ */
+struct drm_dma {
+	int context;			  /**< Context handle */
+	int send_count;			  /**< Number of buffers to send */
+	int __user *send_indices;	  /**< List of handles to buffers */
+	int __user *send_sizes;		  /**< Lengths of data to send */
+	enum drm_dma_flags flags;	  /**< Flags */
+	int request_count;		  /**< Number of buffers requested */
+	int request_size;		  /**< Desired size for buffers */
+	int __user *request_indices;	  /**< Buffer information */
+	int __user *request_sizes;
+	int granted_count;		  /**< Number of buffers granted */
+};
+
+enum drm_ctx_flags {
+	_DRM_CONTEXT_PRESERVED = 0x01,
+	_DRM_CONTEXT_2DONLY = 0x02
+};
+
+/*
+ * DRM_IOCTL_ADD_CTX ioctl argument type.
+ *
+ * \sa drmCreateContext() and drmDestroyContext().
+ */
+struct drm_ctx {
+	drm_context_t handle;
+	enum drm_ctx_flags flags;
+};
+
+/*
+ * DRM_IOCTL_RES_CTX ioctl argument type.
+ */
+struct drm_ctx_res {
+	int count;
+	struct drm_ctx __user *contexts;
+};
+
+/*
+ * DRM_IOCTL_ADD_DRAW and DRM_IOCTL_RM_DRAW ioctl argument type.
+ */
+struct drm_draw {
+	drm_drawable_t handle;
+};
+
+/*
+ * DRM_IOCTL_UPDATE_DRAW ioctl argument type.
+ */
+typedef enum {
+	DRM_DRAWABLE_CLIPRECTS
+} drm_drawable_info_type_t;
+
+struct drm_update_draw {
+	drm_drawable_t handle;
+	unsigned int type;
+	unsigned int num;
+	unsigned long long data;
+};
+
+/*
+ * DRM_IOCTL_GET_MAGIC and DRM_IOCTL_AUTH_MAGIC ioctl argument type.
+ */
+struct drm_auth {
+	drm_magic_t magic;
+};
+
+/*
+ * DRM_IOCTL_IRQ_BUSID ioctl argument type.
+ *
+ * \sa drmGetInterruptFromBusID().
+ */
+struct drm_irq_busid {
+	int irq;	/**< IRQ number */
+	int busnum;	/**< bus number */
+	int devnum;	/**< device number */
+	int funcnum;	/**< function number */
+};
+
+enum drm_vblank_seq_type {
+	_DRM_VBLANK_ABSOLUTE = 0x0,	/**< Wait for specific vblank sequence number */
+	_DRM_VBLANK_RELATIVE = 0x1,	/**< Wait for given number of vblanks */
+	/* bits 1-6 are reserved for high crtcs */
+	_DRM_VBLANK_HIGH_CRTC_MASK = 0x0000003e,
+	_DRM_VBLANK_EVENT = 0x4000000,   /**< Send event instead of blocking */
+	_DRM_VBLANK_FLIP = 0x8000000,   /**< Scheduled buffer swap should flip */
+	_DRM_VBLANK_NEXTONMISS = 0x10000000,	/**< If missed, wait for next vblank */
+	_DRM_VBLANK_SECONDARY = 0x20000000,	/**< Secondary display controller */
+	_DRM_VBLANK_SIGNAL = 0x40000000	/**< Send signal instead of blocking, unsupported */
+};
+#define _DRM_VBLANK_HIGH_CRTC_SHIFT 1
+
+#define _DRM_VBLANK_TYPES_MASK (_DRM_VBLANK_ABSOLUTE | _DRM_VBLANK_RELATIVE)
+#define _DRM_VBLANK_FLAGS_MASK (_DRM_VBLANK_EVENT | _DRM_VBLANK_SIGNAL | \
+				_DRM_VBLANK_SECONDARY | _DRM_VBLANK_NEXTONMISS)
+
+struct drm_wait_vblank_request {
+	enum drm_vblank_seq_type type;
+	unsigned int sequence;
+	unsigned long signal;
+};
+
+struct drm_wait_vblank_reply {
+	enum drm_vblank_seq_type type;
+	unsigned int sequence;
+	long tval_sec;
+	long tval_usec;
+};
+
+/*
+ * DRM_IOCTL_WAIT_VBLANK ioctl argument type.
+ *
+ * \sa drmWaitVBlank().
+ */
+union drm_wait_vblank {
+	struct drm_wait_vblank_request request;
+	struct drm_wait_vblank_reply reply;
+};
+
+#define _DRM_PRE_MODESET 1
+#define _DRM_POST_MODESET 2
+
+/*
+ * DRM_IOCTL_MODESET_CTL ioctl argument type
+ *
+ * \sa drmModesetCtl().
+ */
+struct drm_modeset_ctl {
+	__u32 crtc;
+	__u32 cmd;
+};
+
+/*
+ * DRM_IOCTL_AGP_ENABLE ioctl argument type.
+ *
+ * \sa drmAgpEnable().
+ */
+struct drm_agp_mode {
+	unsigned long mode;	/**< AGP mode */
+};
+
+/*
+ * DRM_IOCTL_AGP_ALLOC and DRM_IOCTL_AGP_FREE ioctls argument type.
+ *
+ * \sa drmAgpAlloc() and drmAgpFree().
+ */
+struct drm_agp_buffer {
+	unsigned long size;	/**< In bytes -- will round to page boundary */
+	unsigned long handle;	/**< Used for binding / unbinding */
+	unsigned long type;	/**< Type of memory to allocate */
+	unsigned long physical;	/**< Physical used by i810 */
+};
+
+/*
+ * DRM_IOCTL_AGP_BIND and DRM_IOCTL_AGP_UNBIND ioctls argument type.
+ *
+ * \sa drmAgpBind() and drmAgpUnbind().
+ */
+struct drm_agp_binding {
+	unsigned long handle;	/**< From drm_agp_buffer */
+	unsigned long offset;	/**< In bytes -- will round to page boundary */
+};
+
+/*
+ * DRM_IOCTL_AGP_INFO ioctl argument type.
+ *
+ * \sa drmAgpVersionMajor(), drmAgpVersionMinor(), drmAgpGetMode(),
+ * drmAgpBase(), drmAgpSize(), drmAgpMemoryUsed(), drmAgpMemoryAvail(),
+ * drmAgpVendorId() and drmAgpDeviceId().
+ */
+struct drm_agp_info {
+	int agp_version_major;
+	int agp_version_minor;
+	unsigned long mode;
+	unsigned long aperture_base;	/* physical address */
+	unsigned long aperture_size;	/* bytes */
+	unsigned long memory_allowed;	/* bytes */
+	unsigned long memory_used;
+
+	/* PCI information */
+	unsigned short id_vendor;
+	unsigned short id_device;
+};
+
+/*
+ * DRM_IOCTL_SG_ALLOC ioctl argument type.
+ */
+struct drm_scatter_gather {
+	unsigned long size;	/**< In bytes -- will round to page boundary */
+	unsigned long handle;	/**< Used for mapping / unmapping */
+};
+
+/*
+ * DRM_IOCTL_SET_VERSION ioctl argument type.
+ */
+struct drm_set_version {
+	int drm_di_major;
+	int drm_di_minor;
+	int drm_dd_major;
+	int drm_dd_minor;
+};
+
+/**
+ * struct drm_gem_close - Argument for &DRM_IOCTL_GEM_CLOSE ioctl.
+ * @handle: Handle of the object to be closed.
+ * @pad: Padding.
+ *
+ * Releases the handle to an mm object.
+ */
+struct drm_gem_close {
+	__u32 handle;
+	__u32 pad;
+};
+
+/**
+ * struct drm_gem_flink - Argument for &DRM_IOCTL_GEM_FLINK ioctl.
+ * @handle: Handle for the object being named.
+ * @name: Returned global name.
+ *
+ * Create a global name for an object, returning the name.
+ *
+ * Note that the name does not hold a reference; when the object
+ * is freed, the name goes away.
+ */
+struct drm_gem_flink {
+	__u32 handle;
+	__u32 name;
+};
+
+/**
+ * struct drm_gem_open - Argument for &DRM_IOCTL_GEM_OPEN ioctl.
+ * @name: Name of object being opened.
+ * @handle: Returned handle for the object.
+ * @size: Returned size of the object
+ *
+ * Open an object using the global name, returning a handle and the size.
+ *
+ * This handle (of course) holds a reference to the object, so the object
+ * will not go away until the handle is deleted.
+ */
+struct drm_gem_open {
+	__u32 name;
+	__u32 handle;
+	__u64 size;
+};
+
+/**
+ * struct drm_gem_change_handle - Argument for &DRM_IOCTL_GEM_CHANGE_HANDLE ioctl.
+ * @handle: The handle of a gem object.
+ * @new_handle: An available gem handle.
+ *
+ * This ioctl changes the handle of a GEM object to the specified one.
+ * The new handle must be unused. On success the old handle is closed
+ * and all further IOCTL should refer to the new handle only.
+ * Calls to DRM_IOCTL_PRIME_FD_TO_HANDLE will return the new handle.
+ */
+struct drm_gem_change_handle {
+	__u32 handle;
+	__u32 new_handle;
+};
+
+/**
+ * DRM_CAP_DUMB_BUFFER
+ *
+ * If set to 1, the driver supports creating dumb buffers via the
+ * &DRM_IOCTL_MODE_CREATE_DUMB ioctl.
+ */
+#define DRM_CAP_DUMB_BUFFER		0x1
+/**
+ * DRM_CAP_VBLANK_HIGH_CRTC
+ *
+ * If set to 1, the kernel supports specifying a :ref:`CRTC index<crtc_index>`
+ * in the high bits of &drm_wait_vblank_request.type.
+ *
+ * Starting kernel version 2.6.39, this capability is always set to 1.
+ */
+#define DRM_CAP_VBLANK_HIGH_CRTC	0x2
+/**
+ * DRM_CAP_DUMB_PREFERRED_DEPTH
+ *
+ * The preferred bit depth for dumb buffers.
+ *
+ * The bit depth is the number of bits used to indicate the color of a single
+ * pixel excluding any padding. This is different from the number of bits per
+ * pixel. For instance, XRGB8888 has a bit depth of 24 but has 32 bits per
+ * pixel.
+ *
+ * Note that this preference only applies to dumb buffers, it's irrelevant for
+ * other types of buffers.
+ */
+#define DRM_CAP_DUMB_PREFERRED_DEPTH	0x3
+/**
+ * DRM_CAP_DUMB_PREFER_SHADOW
+ *
+ * If set to 1, the driver prefers userspace to render to a shadow buffer
+ * instead of directly rendering to a dumb buffer. For best speed, userspace
+ * should do streaming ordered memory copies into the dumb buffer and never
+ * read from it.
+ *
+ * Note that this preference only applies to dumb buffers, it's irrelevant for
+ * other types of buffers.
+ */
+#define DRM_CAP_DUMB_PREFER_SHADOW	0x4
+/**
+ * DRM_CAP_PRIME
+ *
+ * Bitfield of supported PRIME sharing capabilities. See &DRM_PRIME_CAP_IMPORT
+ * and &DRM_PRIME_CAP_EXPORT.
+ *
+ * Starting from kernel version 6.6, both &DRM_PRIME_CAP_IMPORT and
+ * &DRM_PRIME_CAP_EXPORT are always advertised.
+ *
+ * PRIME buffers are exposed as dma-buf file descriptors.
+ * See :ref:`prime_buffer_sharing`.
+ */
+#define DRM_CAP_PRIME			0x5
+/**
+ * DRM_PRIME_CAP_IMPORT
+ *
+ * If this bit is set in &DRM_CAP_PRIME, the driver supports importing PRIME
+ * buffers via the &DRM_IOCTL_PRIME_FD_TO_HANDLE ioctl.
+ *
+ * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME.
+ */
+#define  DRM_PRIME_CAP_IMPORT		0x1
+/**
+ * DRM_PRIME_CAP_EXPORT
+ *
+ * If this bit is set in &DRM_CAP_PRIME, the driver supports exporting PRIME
+ * buffers via the &DRM_IOCTL_PRIME_HANDLE_TO_FD ioctl.
+ *
+ * Starting from kernel version 6.6, this bit is always set in &DRM_CAP_PRIME.
+ */
+#define  DRM_PRIME_CAP_EXPORT		0x2
+/**
+ * DRM_CAP_TIMESTAMP_MONOTONIC
+ *
+ * If set to 0, the kernel will report timestamps with ``CLOCK_REALTIME`` in
+ * struct drm_event_vblank. If set to 1, the kernel will report timestamps with
+ * ``CLOCK_MONOTONIC``. See ``clock_gettime(2)`` for the definition of these
+ * clocks.
+ *
+ * Starting from kernel version 2.6.39, the default value for this capability
+ * is 1. Starting kernel version 4.15, this capability is always set to 1.
+ */
+#define DRM_CAP_TIMESTAMP_MONOTONIC	0x6
+/**
+ * DRM_CAP_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for legacy
+ * page-flips.
+ */
+#define DRM_CAP_ASYNC_PAGE_FLIP		0x7
+/**
+ * DRM_CAP_CURSOR_WIDTH
+ *
+ * The ``CURSOR_WIDTH`` and ``CURSOR_HEIGHT`` capabilities return a valid
+ * width x height combination for the hardware cursor. The intention is that a
+ * hardware agnostic userspace can query a cursor plane size to use.
+ *
+ * Note that the cross-driver contract is to merely return a valid size;
+ * drivers are free to attach another meaning on top, eg. i915 returns the
+ * maximum plane size.
+ */
+#define DRM_CAP_CURSOR_WIDTH		0x8
+/**
+ * DRM_CAP_CURSOR_HEIGHT
+ *
+ * See &DRM_CAP_CURSOR_WIDTH.
+ */
+#define DRM_CAP_CURSOR_HEIGHT		0x9
+/**
+ * DRM_CAP_ADDFB2_MODIFIERS
+ *
+ * If set to 1, the driver supports supplying modifiers in the
+ * &DRM_IOCTL_MODE_ADDFB2 ioctl.
+ */
+#define DRM_CAP_ADDFB2_MODIFIERS	0x10
+/**
+ * DRM_CAP_PAGE_FLIP_TARGET
+ *
+ * If set to 1, the driver supports the &DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE and
+ * &DRM_MODE_PAGE_FLIP_TARGET_RELATIVE flags in
+ * &drm_mode_crtc_page_flip_target.flags for the &DRM_IOCTL_MODE_PAGE_FLIP
+ * ioctl.
+ */
+#define DRM_CAP_PAGE_FLIP_TARGET	0x11
+/**
+ * DRM_CAP_CRTC_IN_VBLANK_EVENT
+ *
+ * If set to 1, the kernel supports reporting the CRTC ID in
+ * &drm_event_vblank.crtc_id for the &DRM_EVENT_VBLANK and
+ * &DRM_EVENT_FLIP_COMPLETE events.
+ *
+ * Starting kernel version 4.12, this capability is always set to 1.
+ */
+#define DRM_CAP_CRTC_IN_VBLANK_EVENT	0x12
+/**
+ * DRM_CAP_SYNCOBJ
+ *
+ * If set to 1, the driver supports sync objects. See :ref:`drm_sync_objects`.
+ */
+#define DRM_CAP_SYNCOBJ		0x13
+/**
+ * DRM_CAP_SYNCOBJ_TIMELINE
+ *
+ * If set to 1, the driver supports timeline operations on sync objects. See
+ * :ref:`drm_sync_objects`.
+ */
+#define DRM_CAP_SYNCOBJ_TIMELINE	0x14
+/**
+ * DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP
+ *
+ * If set to 1, the driver supports &DRM_MODE_PAGE_FLIP_ASYNC for atomic
+ * commits.
+ */
+#define DRM_CAP_ATOMIC_ASYNC_PAGE_FLIP	0x15
+
+/* DRM_IOCTL_GET_CAP ioctl argument type */
+struct drm_get_cap {
+	__u64 capability;
+	__u64 value;
+};
+
+/**
+ * DRM_CLIENT_CAP_STEREO_3D
+ *
+ * If set to 1, the DRM core will expose the stereo 3D capabilities of the
+ * monitor by advertising the supported 3D layouts in the flags of struct
+ * drm_mode_modeinfo. See ``DRM_MODE_FLAG_3D_*``.
+ *
+ * This capability is always supported for all drivers starting from kernel
+ * version 3.13.
+ */
+#define DRM_CLIENT_CAP_STEREO_3D	1
+
+/**
+ * DRM_CLIENT_CAP_UNIVERSAL_PLANES
+ *
+ * If set to 1, the DRM core will expose all planes (overlay, primary, and
+ * cursor) to userspace.
+ *
+ * This capability has been introduced in kernel version 3.15. Starting from
+ * kernel version 3.17, this capability is always supported for all drivers.
+ */
+#define DRM_CLIENT_CAP_UNIVERSAL_PLANES  2
+
+/**
+ * DRM_CLIENT_CAP_ATOMIC
+ *
+ * If set to 1, the DRM core will expose atomic properties to userspace. This
+ * implicitly enables &DRM_CLIENT_CAP_UNIVERSAL_PLANES and
+ * &DRM_CLIENT_CAP_ASPECT_RATIO.
+ *
+ * If the driver doesn't support atomic mode-setting, enabling this capability
+ * will fail with -EOPNOTSUPP.
+ *
+ * This capability has been introduced in kernel version 4.0. Starting from
+ * kernel version 4.2, this capability is always supported for atomic-capable
+ * drivers.
+ */
+#define DRM_CLIENT_CAP_ATOMIC	3
+
+/**
+ * DRM_CLIENT_CAP_ASPECT_RATIO
+ *
+ * If set to 1, the DRM core will provide aspect ratio information in modes.
+ * See ``DRM_MODE_FLAG_PIC_AR_*``.
+ *
+ * This capability is always supported for all drivers starting from kernel
+ * version 4.18.
+ */
+#define DRM_CLIENT_CAP_ASPECT_RATIO    4
+
+/**
+ * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
+ *
+ * If set to 1, the DRM core will expose special connectors to be used for
+ * writing back to memory the scene setup in the commit. The client must enable
+ * &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * This capability is always supported for atomic-capable drivers starting from
+ * kernel version 4.19.
+ */
+#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
+
+/**
+ * DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT
+ *
+ * Drivers for para-virtualized hardware (e.g. vmwgfx, qxl, virtio and
+ * virtualbox) have additional restrictions for cursor planes (thus
+ * making cursor planes on those drivers not truly universal,) e.g.
+ * they need cursor planes to act like one would expect from a mouse
+ * cursor and have correctly set hotspot properties.
+ * If this client cap is not set the DRM core will hide cursor plane on
+ * those virtualized drivers because not setting it implies that the
+ * client is not capable of dealing with those extra restictions.
+ * Clients which do set cursor hotspot and treat the cursor plane
+ * like a mouse cursor should set this property.
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ *
+ * Setting this property on drivers which do not special case
+ * cursor planes (i.e. non-virtualized drivers) will return
+ * EOPNOTSUPP, which can be used by userspace to gauge
+ * requirements of the hardware/drivers they're running on.
+ *
+ * This capability is always supported for atomic-capable virtualized
+ * drivers starting from kernel version 6.6.
+ */
+#define DRM_CLIENT_CAP_CURSOR_PLANE_HOTSPOT	6
+
+/**
+ * DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE
+ *
+ * If set to 1 the DRM core will allow setting the COLOR_PIPELINE
+ * property on a &drm_plane, as well as drm_colorop properties.
+ *
+ * Setting of these plane properties will be rejected when this client
+ * cap is set:
+ * - COLOR_ENCODING
+ * - COLOR_RANGE
+ *
+ * The client must enable &DRM_CLIENT_CAP_ATOMIC first.
+ */
+#define DRM_CLIENT_CAP_PLANE_COLOR_PIPELINE	7
+
+/* DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
+struct drm_set_client_cap {
+	__u64 capability;
+	__u64 value;
+};
+
+#define DRM_RDWR O_RDWR
+#define DRM_CLOEXEC O_CLOEXEC
+struct drm_prime_handle {
+	__u32 handle;
+
+	/** Flags.. only applicable for handle->fd */
+	__u32 flags;
+
+	/** Returned dmabuf file descriptor */
+	__s32 fd;
+};
+
+struct drm_syncobj_create {
+	__u32 handle;
+#define DRM_SYNCOBJ_CREATE_SIGNALED (1 << 0)
+	__u32 flags;
+};
+
+struct drm_syncobj_destroy {
+	__u32 handle;
+	__u32 pad;
+};
+
+#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE         (1 << 1)
+#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0)
+#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE         (1 << 1)
+struct drm_syncobj_handle {
+	__u32 handle;
+	__u32 flags;
+
+	__s32 fd;
+	__u32 pad;
+
+	__u64 point;
+};
+
+struct drm_syncobj_transfer {
+	__u32 src_handle;
+	__u32 dst_handle;
+	__u64 src_point;
+	__u64 dst_point;
+	__u32 flags;
+	__u32 pad;
+};
+
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_ALL (1 << 0)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_FOR_SUBMIT (1 << 1)
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE (1 << 2) /* wait for time point to become available */
+#define DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE (1 << 3) /* set fence deadline to deadline_nsec */
+struct drm_syncobj_wait {
+	__u64 handles;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
+};
+
+struct drm_syncobj_timeline_wait {
+	__u64 handles;
+	/* wait on specific timeline point for every handles*/
+	__u64 points;
+	/* absolute timeout */
+	__s64 timeout_nsec;
+	__u32 count_handles;
+	__u32 flags;
+	__u32 first_signaled; /* only valid when not waiting all */
+	__u32 pad;
+	/**
+	 * @deadline_nsec - fence deadline hint
+	 *
+	 * Deadline hint, in absolute CLOCK_MONOTONIC, to set on backing
+	 * fence(s) if the DRM_SYNCOBJ_WAIT_FLAGS_WAIT_DEADLINE flag is
+	 * set.
+	 */
+	__u64 deadline_nsec;
+};
+
+/**
+ * struct drm_syncobj_eventfd
+ * @handle: syncobj handle.
+ * @flags: Zero to wait for the point to be signalled, or
+ *         &DRM_SYNCOBJ_WAIT_FLAGS_WAIT_AVAILABLE to wait for a fence to be
+ *         available for the point.
+ * @point: syncobj timeline point (set to zero for binary syncobjs).
+ * @fd: Existing eventfd to sent events to.
+ * @pad: Must be zero.
+ *
+ * Register an eventfd to be signalled by a syncobj. The eventfd counter will
+ * be incremented by one.
+ */
+struct drm_syncobj_eventfd {
+	__u32 handle;
+	__u32 flags;
+	__u64 point;
+	__s32 fd;
+	__u32 pad;
+};
+
+
+struct drm_syncobj_array {
+	__u64 handles;
+	__u32 count_handles;
+	__u32 pad;
+};
+
+#define DRM_SYNCOBJ_QUERY_FLAGS_LAST_SUBMITTED (1 << 0) /* last available point on timeline syncobj */
+struct drm_syncobj_timeline_array {
+	__u64 handles;
+	__u64 points;
+	__u32 count_handles;
+	__u32 flags;
+};
+
+
+/* Query current scanout sequence number */
+struct drm_crtc_get_sequence {
+	__u32 crtc_id;		/* requested crtc_id */
+	__u32 active;		/* return: crtc output is active */
+	__u64 sequence;		/* return: most recent vblank sequence */
+	__s64 sequence_ns;	/* return: most recent time of first pixel out */
+};
+
+/* Queue event to be delivered at specified sequence. Time stamp marks
+ * when the first pixel of the refresh cycle leaves the display engine
+ * for the display
+ */
+#define DRM_CRTC_SEQUENCE_RELATIVE		0x00000001	/* sequence is relative to current */
+#define DRM_CRTC_SEQUENCE_NEXT_ON_MISS		0x00000002	/* Use next sequence if we've missed */
+
+struct drm_crtc_queue_sequence {
+	__u32 crtc_id;
+	__u32 flags;
+	__u64 sequence;		/* on input, target sequence. on output, actual sequence */
+	__u64 user_data;	/* user data passed to event */
+};
+
+#define DRM_CLIENT_NAME_MAX_LEN		64
+struct drm_set_client_name {
+	__u64 name_len;
+	__u64 name;
+};
+
+
+#if defined(__cplusplus)
+}
+#endif
+
+#include "drm_mode.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_IOCTL_BASE			'd'
+#define DRM_IO(nr)			_IO(DRM_IOCTL_BASE,nr)
+#define DRM_IOR(nr,type)		_IOR(DRM_IOCTL_BASE,nr,type)
+#define DRM_IOW(nr,type)		_IOW(DRM_IOCTL_BASE,nr,type)
+#define DRM_IOWR(nr,type)		_IOWR(DRM_IOCTL_BASE,nr,type)
+
+#define DRM_IOCTL_VERSION		DRM_IOWR(0x00, struct drm_version)
+#define DRM_IOCTL_GET_UNIQUE		DRM_IOWR(0x01, struct drm_unique)
+#define DRM_IOCTL_GET_MAGIC		DRM_IOR( 0x02, struct drm_auth)
+#define DRM_IOCTL_IRQ_BUSID		DRM_IOWR(0x03, struct drm_irq_busid)
+#define DRM_IOCTL_GET_MAP               DRM_IOWR(0x04, struct drm_map)
+#define DRM_IOCTL_GET_CLIENT            DRM_IOWR(0x05, struct drm_client)
+#define DRM_IOCTL_GET_STATS             DRM_IOR( 0x06, struct drm_stats)
+#define DRM_IOCTL_SET_VERSION		DRM_IOWR(0x07, struct drm_set_version)
+#define DRM_IOCTL_MODESET_CTL           DRM_IOW(0x08, struct drm_modeset_ctl)
+/**
+ * DRM_IOCTL_GEM_CLOSE - Close a GEM handle.
+ *
+ * GEM handles are not reference-counted by the kernel. User-space is
+ * responsible for managing their lifetime. For example, if user-space imports
+ * the same memory object twice on the same DRM file description, the same GEM
+ * handle is returned by both imports, and user-space needs to ensure
+ * &DRM_IOCTL_GEM_CLOSE is performed once only. The same situation can happen
+ * when a memory object is allocated, then exported and imported again on the
+ * same DRM file description. The &DRM_IOCTL_MODE_GETFB2 IOCTL is an exception
+ * and always returns fresh new GEM handles even if an existing GEM handle
+ * already refers to the same memory object before the IOCTL is performed.
+ */
+#define DRM_IOCTL_GEM_CLOSE		DRM_IOW (0x09, struct drm_gem_close)
+#define DRM_IOCTL_GEM_FLINK		DRM_IOWR(0x0a, struct drm_gem_flink)
+#define DRM_IOCTL_GEM_OPEN		DRM_IOWR(0x0b, struct drm_gem_open)
+#define DRM_IOCTL_GET_CAP		DRM_IOWR(0x0c, struct drm_get_cap)
+#define DRM_IOCTL_SET_CLIENT_CAP	DRM_IOW( 0x0d, struct drm_set_client_cap)
+
+#define DRM_IOCTL_SET_UNIQUE		DRM_IOW( 0x10, struct drm_unique)
+#define DRM_IOCTL_AUTH_MAGIC		DRM_IOW( 0x11, struct drm_auth)
+#define DRM_IOCTL_BLOCK			DRM_IOWR(0x12, struct drm_block)
+#define DRM_IOCTL_UNBLOCK		DRM_IOWR(0x13, struct drm_block)
+#define DRM_IOCTL_CONTROL		DRM_IOW( 0x14, struct drm_control)
+#define DRM_IOCTL_ADD_MAP		DRM_IOWR(0x15, struct drm_map)
+#define DRM_IOCTL_ADD_BUFS		DRM_IOWR(0x16, struct drm_buf_desc)
+#define DRM_IOCTL_MARK_BUFS		DRM_IOW( 0x17, struct drm_buf_desc)
+#define DRM_IOCTL_INFO_BUFS		DRM_IOWR(0x18, struct drm_buf_info)
+#define DRM_IOCTL_MAP_BUFS		DRM_IOWR(0x19, struct drm_buf_map)
+#define DRM_IOCTL_FREE_BUFS		DRM_IOW( 0x1a, struct drm_buf_free)
+
+#define DRM_IOCTL_RM_MAP		DRM_IOW( 0x1b, struct drm_map)
+
+#define DRM_IOCTL_SET_SAREA_CTX		DRM_IOW( 0x1c, struct drm_ctx_priv_map)
+#define DRM_IOCTL_GET_SAREA_CTX 	DRM_IOWR(0x1d, struct drm_ctx_priv_map)
+
+#define DRM_IOCTL_SET_MASTER            DRM_IO(0x1e)
+#define DRM_IOCTL_DROP_MASTER           DRM_IO(0x1f)
+
+#define DRM_IOCTL_ADD_CTX		DRM_IOWR(0x20, struct drm_ctx)
+#define DRM_IOCTL_RM_CTX		DRM_IOWR(0x21, struct drm_ctx)
+#define DRM_IOCTL_MOD_CTX		DRM_IOW( 0x22, struct drm_ctx)
+#define DRM_IOCTL_GET_CTX		DRM_IOWR(0x23, struct drm_ctx)
+#define DRM_IOCTL_SWITCH_CTX		DRM_IOW( 0x24, struct drm_ctx)
+#define DRM_IOCTL_NEW_CTX		DRM_IOW( 0x25, struct drm_ctx)
+#define DRM_IOCTL_RES_CTX		DRM_IOWR(0x26, struct drm_ctx_res)
+#define DRM_IOCTL_ADD_DRAW		DRM_IOWR(0x27, struct drm_draw)
+#define DRM_IOCTL_RM_DRAW		DRM_IOWR(0x28, struct drm_draw)
+#define DRM_IOCTL_DMA			DRM_IOWR(0x29, struct drm_dma)
+#define DRM_IOCTL_LOCK			DRM_IOW( 0x2a, struct drm_lock)
+#define DRM_IOCTL_UNLOCK		DRM_IOW( 0x2b, struct drm_lock)
+#define DRM_IOCTL_FINISH		DRM_IOW( 0x2c, struct drm_lock)
+
+/**
+ * DRM_IOCTL_PRIME_HANDLE_TO_FD - Convert a GEM handle to a DMA-BUF FD.
+ *
+ * User-space sets &drm_prime_handle.handle with the GEM handle to export and
+ * &drm_prime_handle.flags, and gets back a DMA-BUF file descriptor in
+ * &drm_prime_handle.fd.
+ *
+ * The export can fail for any driver-specific reason, e.g. because export is
+ * not supported for this specific GEM handle (but might be for others).
+ *
+ * Support for exporting DMA-BUFs is advertised via &DRM_PRIME_CAP_EXPORT.
+ */
+#define DRM_IOCTL_PRIME_HANDLE_TO_FD    DRM_IOWR(0x2d, struct drm_prime_handle)
+/**
+ * DRM_IOCTL_PRIME_FD_TO_HANDLE - Convert a DMA-BUF FD to a GEM handle.
+ *
+ * User-space sets &drm_prime_handle.fd with a DMA-BUF file descriptor to
+ * import, and gets back a GEM handle in &drm_prime_handle.handle.
+ * &drm_prime_handle.flags is unused.
+ *
+ * If an existing GEM handle refers to the memory object backing the DMA-BUF,
+ * that GEM handle is returned. Therefore user-space which needs to handle
+ * arbitrary DMA-BUFs must have a user-space lookup data structure to manually
+ * reference-count duplicated GEM handles. For more information see
+ * &DRM_IOCTL_GEM_CLOSE.
+ *
+ * The import can fail for any driver-specific reason, e.g. because import is
+ * only supported for DMA-BUFs allocated on this DRM device.
+ *
+ * Support for importing DMA-BUFs is advertised via &DRM_PRIME_CAP_IMPORT.
+ */
+#define DRM_IOCTL_PRIME_FD_TO_HANDLE    DRM_IOWR(0x2e, struct drm_prime_handle)
+
+#define DRM_IOCTL_AGP_ACQUIRE		DRM_IO(  0x30)
+#define DRM_IOCTL_AGP_RELEASE		DRM_IO(  0x31)
+#define DRM_IOCTL_AGP_ENABLE		DRM_IOW( 0x32, struct drm_agp_mode)
+#define DRM_IOCTL_AGP_INFO		DRM_IOR( 0x33, struct drm_agp_info)
+#define DRM_IOCTL_AGP_ALLOC		DRM_IOWR(0x34, struct drm_agp_buffer)
+#define DRM_IOCTL_AGP_FREE		DRM_IOW( 0x35, struct drm_agp_buffer)
+#define DRM_IOCTL_AGP_BIND		DRM_IOW( 0x36, struct drm_agp_binding)
+#define DRM_IOCTL_AGP_UNBIND		DRM_IOW( 0x37, struct drm_agp_binding)
+
+#define DRM_IOCTL_SG_ALLOC		DRM_IOWR(0x38, struct drm_scatter_gather)
+#define DRM_IOCTL_SG_FREE		DRM_IOW( 0x39, struct drm_scatter_gather)
+
+#define DRM_IOCTL_WAIT_VBLANK		DRM_IOWR(0x3a, union drm_wait_vblank)
+
+#define DRM_IOCTL_CRTC_GET_SEQUENCE	DRM_IOWR(0x3b, struct drm_crtc_get_sequence)
+#define DRM_IOCTL_CRTC_QUEUE_SEQUENCE	DRM_IOWR(0x3c, struct drm_crtc_queue_sequence)
+
+#define DRM_IOCTL_UPDATE_DRAW		DRM_IOW(0x3f, struct drm_update_draw)
+
+#define DRM_IOCTL_MODE_GETRESOURCES	DRM_IOWR(0xA0, struct drm_mode_card_res)
+#define DRM_IOCTL_MODE_GETCRTC		DRM_IOWR(0xA1, struct drm_mode_crtc)
+#define DRM_IOCTL_MODE_SETCRTC		DRM_IOWR(0xA2, struct drm_mode_crtc)
+#define DRM_IOCTL_MODE_CURSOR		DRM_IOWR(0xA3, struct drm_mode_cursor)
+#define DRM_IOCTL_MODE_GETGAMMA		DRM_IOWR(0xA4, struct drm_mode_crtc_lut)
+#define DRM_IOCTL_MODE_SETGAMMA		DRM_IOWR(0xA5, struct drm_mode_crtc_lut)
+#define DRM_IOCTL_MODE_GETENCODER	DRM_IOWR(0xA6, struct drm_mode_get_encoder)
+#define DRM_IOCTL_MODE_GETCONNECTOR	DRM_IOWR(0xA7, struct drm_mode_get_connector)
+#define DRM_IOCTL_MODE_ATTACHMODE	DRM_IOWR(0xA8, struct drm_mode_mode_cmd) /* deprecated (never worked) */
+#define DRM_IOCTL_MODE_DETACHMODE	DRM_IOWR(0xA9, struct drm_mode_mode_cmd) /* deprecated (never worked) */
+
+#define DRM_IOCTL_MODE_GETPROPERTY	DRM_IOWR(0xAA, struct drm_mode_get_property)
+#define DRM_IOCTL_MODE_SETPROPERTY	DRM_IOWR(0xAB, struct drm_mode_connector_set_property)
+#define DRM_IOCTL_MODE_GETPROPBLOB	DRM_IOWR(0xAC, struct drm_mode_get_blob)
+#define DRM_IOCTL_MODE_GETFB		DRM_IOWR(0xAD, struct drm_mode_fb_cmd)
+#define DRM_IOCTL_MODE_ADDFB		DRM_IOWR(0xAE, struct drm_mode_fb_cmd)
+/**
+ * DRM_IOCTL_MODE_RMFB - Remove a framebuffer.
+ *
+ * This removes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * Warning: removing a framebuffer currently in-use on an enabled plane will
+ * disable that plane. The CRTC the plane is linked to may also be disabled
+ * (depending on driver capabilities).
+ */
+#define DRM_IOCTL_MODE_RMFB		DRM_IOWR(0xAF, unsigned int)
+#define DRM_IOCTL_MODE_PAGE_FLIP	DRM_IOWR(0xB0, struct drm_mode_crtc_page_flip)
+#define DRM_IOCTL_MODE_DIRTYFB		DRM_IOWR(0xB1, struct drm_mode_fb_dirty_cmd)
+
+/**
+ * DRM_IOCTL_MODE_CREATE_DUMB - Create a new dumb buffer object.
+ *
+ * KMS dumb buffers provide a very primitive way to allocate a buffer object
+ * suitable for scanout and map it for software rendering. KMS dumb buffers are
+ * not suitable for hardware-accelerated rendering nor video decoding. KMS dumb
+ * buffers are not suitable to be displayed on any other device than the KMS
+ * device where they were allocated from. Also see
+ * :ref:`kms_dumb_buffer_objects`.
+ *
+ * The IOCTL argument is a struct drm_mode_create_dumb.
+ *
+ * User-space is expected to create a KMS dumb buffer via this IOCTL, then add
+ * it as a KMS framebuffer via &DRM_IOCTL_MODE_ADDFB and map it via
+ * &DRM_IOCTL_MODE_MAP_DUMB.
+ *
+ * &DRM_CAP_DUMB_BUFFER indicates whether this IOCTL is supported.
+ * &DRM_CAP_DUMB_PREFERRED_DEPTH and &DRM_CAP_DUMB_PREFER_SHADOW indicate
+ * driver preferences for dumb buffers.
+ */
+#define DRM_IOCTL_MODE_CREATE_DUMB DRM_IOWR(0xB2, struct drm_mode_create_dumb)
+#define DRM_IOCTL_MODE_MAP_DUMB    DRM_IOWR(0xB3, struct drm_mode_map_dumb)
+#define DRM_IOCTL_MODE_DESTROY_DUMB    DRM_IOWR(0xB4, struct drm_mode_destroy_dumb)
+#define DRM_IOCTL_MODE_GETPLANERESOURCES DRM_IOWR(0xB5, struct drm_mode_get_plane_res)
+#define DRM_IOCTL_MODE_GETPLANE	DRM_IOWR(0xB6, struct drm_mode_get_plane)
+#define DRM_IOCTL_MODE_SETPLANE	DRM_IOWR(0xB7, struct drm_mode_set_plane)
+#define DRM_IOCTL_MODE_ADDFB2		DRM_IOWR(0xB8, struct drm_mode_fb_cmd2)
+#define DRM_IOCTL_MODE_OBJ_GETPROPERTIES	DRM_IOWR(0xB9, struct drm_mode_obj_get_properties)
+#define DRM_IOCTL_MODE_OBJ_SETPROPERTY	DRM_IOWR(0xBA, struct drm_mode_obj_set_property)
+#define DRM_IOCTL_MODE_CURSOR2		DRM_IOWR(0xBB, struct drm_mode_cursor2)
+#define DRM_IOCTL_MODE_ATOMIC		DRM_IOWR(0xBC, struct drm_mode_atomic)
+#define DRM_IOCTL_MODE_CREATEPROPBLOB	DRM_IOWR(0xBD, struct drm_mode_create_blob)
+#define DRM_IOCTL_MODE_DESTROYPROPBLOB	DRM_IOWR(0xBE, struct drm_mode_destroy_blob)
+
+#define DRM_IOCTL_SYNCOBJ_CREATE	DRM_IOWR(0xBF, struct drm_syncobj_create)
+#define DRM_IOCTL_SYNCOBJ_DESTROY	DRM_IOWR(0xC0, struct drm_syncobj_destroy)
+#define DRM_IOCTL_SYNCOBJ_HANDLE_TO_FD	DRM_IOWR(0xC1, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_FD_TO_HANDLE	DRM_IOWR(0xC2, struct drm_syncobj_handle)
+#define DRM_IOCTL_SYNCOBJ_WAIT		DRM_IOWR(0xC3, struct drm_syncobj_wait)
+#define DRM_IOCTL_SYNCOBJ_RESET		DRM_IOWR(0xC4, struct drm_syncobj_array)
+#define DRM_IOCTL_SYNCOBJ_SIGNAL	DRM_IOWR(0xC5, struct drm_syncobj_array)
+
+#define DRM_IOCTL_MODE_CREATE_LEASE	DRM_IOWR(0xC6, struct drm_mode_create_lease)
+#define DRM_IOCTL_MODE_LIST_LESSEES	DRM_IOWR(0xC7, struct drm_mode_list_lessees)
+#define DRM_IOCTL_MODE_GET_LEASE	DRM_IOWR(0xC8, struct drm_mode_get_lease)
+#define DRM_IOCTL_MODE_REVOKE_LEASE	DRM_IOWR(0xC9, struct drm_mode_revoke_lease)
+
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_WAIT	DRM_IOWR(0xCA, struct drm_syncobj_timeline_wait)
+#define DRM_IOCTL_SYNCOBJ_QUERY		DRM_IOWR(0xCB, struct drm_syncobj_timeline_array)
+#define DRM_IOCTL_SYNCOBJ_TRANSFER	DRM_IOWR(0xCC, struct drm_syncobj_transfer)
+#define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL	DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
+
+/**
+ * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
+ *
+ * This queries metadata about a framebuffer. User-space fills
+ * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the
+ * struct as the output.
+ *
+ * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
+ * will be filled with GEM buffer handles. Fresh new GEM handles are always
+ * returned, even if another GEM handle referring to the same memory object
+ * already exists on the DRM file description. The caller is responsible for
+ * removing the new handles, e.g. via the &DRM_IOCTL_GEM_CLOSE IOCTL. The same
+ * new handle will be returned for multiple planes in case they use the same
+ * memory object. Planes are valid until one has a zero handle -- this can be
+ * used to compute the number of planes.
+ *
+ * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
+ * until one has a zero &drm_mode_fb_cmd2.pitches.
+ *
+ * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
+ * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
+ * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ *
+ * To obtain DMA-BUF FDs for each plane without leaking GEM handles, user-space
+ * can export each handle via &DRM_IOCTL_PRIME_HANDLE_TO_FD, then immediately
+ * close each unique handle via &DRM_IOCTL_GEM_CLOSE, making sure to not
+ * double-close handles which are specified multiple times in the array.
+ */
+#define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
+
+/**
+ * DRM_IOCTL_SYNCOBJ_EVENTFD - Register an eventfd to be signalled by a syncobj.
+ *
+ * This can be used to integrate a syncobj in an event loop.
+ *
+ * The IOCTL argument is a struct drm_syncobj_eventfd.
+ */
+#define DRM_IOCTL_SYNCOBJ_EVENTFD	DRM_IOWR(0xCF, struct drm_syncobj_eventfd)
+
+/**
+ * DRM_IOCTL_MODE_CLOSEFB - Close a framebuffer.
+ *
+ * This closes a framebuffer previously added via ADDFB/ADDFB2. The IOCTL
+ * argument is a framebuffer object ID.
+ *
+ * This IOCTL is similar to &DRM_IOCTL_MODE_RMFB, except it doesn't disable
+ * planes and CRTCs. As long as the framebuffer is used by a plane, it's kept
+ * alive. When the plane no longer uses the framebuffer (because the
+ * framebuffer is replaced with another one, or the plane is disabled), the
+ * framebuffer is cleaned up.
+ *
+ * This is useful to implement flicker-free transitions between two processes.
+ *
+ * Depending on the threat model, user-space may want to ensure that the
+ * framebuffer doesn't expose any sensitive user information: closed
+ * framebuffers attached to a plane can be read back by the next DRM master.
+ */
+#define DRM_IOCTL_MODE_CLOSEFB		DRM_IOWR(0xD0, struct drm_mode_closefb)
+
+/**
+ * DRM_IOCTL_SET_CLIENT_NAME - Attach a name to a drm_file
+ *
+ * Having a name allows for easier tracking and debugging.
+ * The length of the name (without null ending char) must be
+ * <= DRM_CLIENT_NAME_MAX_LEN.
+ * The call will fail if the name contains whitespaces or non-printable chars.
+ */
+#define DRM_IOCTL_SET_CLIENT_NAME	DRM_IOWR(0xD1, struct drm_set_client_name)
+
+/**
+ * DRM_IOCTL_GEM_CHANGE_HANDLE - Move an object to a different handle
+ *
+ * Some applications (notably CRIU) need objects to have specific gem handles.
+ * This ioctl changes the object at one gem handle to use a new gem handle.
+ */
+#define DRM_IOCTL_GEM_CHANGE_HANDLE    DRM_IOWR(0xD2, struct drm_gem_change_handle)
+
+/*
+ * Device specific ioctls should only be in their respective headers
+ * The device specific ioctl range is from 0x40 to 0x9f.
+ * Generic IOCTLS restart at 0xA0.
+ *
+ * \sa drmCommandNone(), drmCommandRead(), drmCommandWrite(), and
+ * drmCommandReadWrite().
+ */
+#define DRM_COMMAND_BASE                0x40
+#define DRM_COMMAND_END			0xA0
+
+/**
+ * struct drm_event - Header for DRM events
+ * @type: event type.
+ * @length: total number of payload bytes (including header).
+ *
+ * This struct is a header for events written back to user-space on the DRM FD.
+ * A read on the DRM FD will always only return complete events: e.g. if the
+ * read buffer is 100 bytes large and there are two 64 byte events pending,
+ * only one will be returned.
+ *
+ * Event types 0 - 0x7fffffff are generic DRM events, 0x80000000 and
+ * up are chipset specific. Generic DRM events include &DRM_EVENT_VBLANK,
+ * &DRM_EVENT_FLIP_COMPLETE and &DRM_EVENT_CRTC_SEQUENCE.
+ */
+struct drm_event {
+	__u32 type;
+	__u32 length;
+};
+
+/**
+ * DRM_EVENT_VBLANK - vertical blanking event
+ *
+ * This event is sent in response to &DRM_IOCTL_WAIT_VBLANK with the
+ * &_DRM_VBLANK_EVENT flag set.
+ *
+ * The event payload is a struct drm_event_vblank.
+ */
+#define DRM_EVENT_VBLANK 0x01
+/**
+ * DRM_EVENT_FLIP_COMPLETE - page-flip completion event
+ *
+ * This event is sent in response to an atomic commit or legacy page-flip with
+ * the &DRM_MODE_PAGE_FLIP_EVENT flag set.
+ *
+ * The event payload is a struct drm_event_vblank.
+ */
+#define DRM_EVENT_FLIP_COMPLETE 0x02
+/**
+ * DRM_EVENT_CRTC_SEQUENCE - CRTC sequence event
+ *
+ * This event is sent in response to &DRM_IOCTL_CRTC_QUEUE_SEQUENCE.
+ *
+ * The event payload is a struct drm_event_crtc_sequence.
+ */
+#define DRM_EVENT_CRTC_SEQUENCE	0x03
+
+struct drm_event_vblank {
+	struct drm_event base;
+	__u64 user_data;
+	__u32 tv_sec;
+	__u32 tv_usec;
+	__u32 sequence;
+	__u32 crtc_id; /* 0 on older kernels that do not support this */
+};
+
+/* Event delivered at sequence. Time stamp marks when the first pixel
+ * of the refresh cycle leaves the display engine for the display
+ */
+struct drm_event_crtc_sequence {
+	struct drm_event	base;
+	__u64			user_data;
+	__s64			time_ns;
+	__u64			sequence;
+};
+
+/* typedef area */
+#ifndef __KERNEL__
+typedef struct drm_clip_rect drm_clip_rect_t;
+typedef struct drm_drawable_info drm_drawable_info_t;
+typedef struct drm_tex_region drm_tex_region_t;
+typedef struct drm_hw_lock drm_hw_lock_t;
+typedef struct drm_version drm_version_t;
+typedef struct drm_unique drm_unique_t;
+typedef struct drm_list drm_list_t;
+typedef struct drm_block drm_block_t;
+typedef struct drm_control drm_control_t;
+typedef enum drm_map_type drm_map_type_t;
+typedef enum drm_map_flags drm_map_flags_t;
+typedef struct drm_ctx_priv_map drm_ctx_priv_map_t;
+typedef struct drm_map drm_map_t;
+typedef struct drm_client drm_client_t;
+typedef enum drm_stat_type drm_stat_type_t;
+typedef struct drm_stats drm_stats_t;
+typedef enum drm_lock_flags drm_lock_flags_t;
+typedef struct drm_lock drm_lock_t;
+typedef enum drm_dma_flags drm_dma_flags_t;
+typedef struct drm_buf_desc drm_buf_desc_t;
+typedef struct drm_buf_info drm_buf_info_t;
+typedef struct drm_buf_free drm_buf_free_t;
+typedef struct drm_buf_pub drm_buf_pub_t;
+typedef struct drm_buf_map drm_buf_map_t;
+typedef struct drm_dma drm_dma_t;
+typedef union drm_wait_vblank drm_wait_vblank_t;
+typedef struct drm_agp_mode drm_agp_mode_t;
+typedef enum drm_ctx_flags drm_ctx_flags_t;
+typedef struct drm_ctx drm_ctx_t;
+typedef struct drm_ctx_res drm_ctx_res_t;
+typedef struct drm_draw drm_draw_t;
+typedef struct drm_update_draw drm_update_draw_t;
+typedef struct drm_auth drm_auth_t;
+typedef struct drm_irq_busid drm_irq_busid_t;
+typedef enum drm_vblank_seq_type drm_vblank_seq_type_t;
+
+typedef struct drm_agp_buffer drm_agp_buffer_t;
+typedef struct drm_agp_binding drm_agp_binding_t;
+typedef struct drm_agp_info drm_agp_info_t;
+typedef struct drm_scatter_gather drm_scatter_gather_t;
+typedef struct drm_set_version drm_set_version_t;
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
new file mode 100644
index 000000000..a103fdc0b
--- /dev/null
+++ b/include/uapi/drm/drm_fourcc.h
@@ -0,0 +1,1961 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright 2011 Intel Corporation
+ */
+
+#ifndef DRM_FOURCC_H
+#define DRM_FOURCC_H
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * DOC: overview
+ *
+ * In the DRM subsystem, framebuffer pixel formats are described using the
+ * fourcc codes defined in `include/uapi/drm/drm_fourcc.h`. In addition to the
+ * fourcc code, a Format Modifier may optionally be provided, in order to
+ * further describe the buffer's format - for example tiling or compression.
+ *
+ * Format Modifiers
+ * ----------------
+ *
+ * Format modifiers are used in conjunction with a fourcc code, forming a
+ * unique fourcc:modifier pair. This format:modifier pair must fully define the
+ * format and data layout of the buffer, and should be the only way to describe
+ * that particular buffer.
+ *
+ * Having multiple fourcc:modifier pairs which describe the same layout should
+ * be avoided, as such aliases run the risk of different drivers exposing
+ * different names for the same data format, forcing userspace to understand
+ * that they are aliases.
+ *
+ * Format modifiers may change any property of the buffer, including the number
+ * of planes and/or the required allocation size. Format modifiers are
+ * vendor-namespaced, and as such the relationship between a fourcc code and a
+ * modifier is specific to the modifier being used. For example, some modifiers
+ * may preserve meaning - such as number of planes - from the fourcc code,
+ * whereas others may not.
+ *
+ * Modifiers must uniquely encode buffer layout. In other words, a buffer must
+ * match only a single modifier. A modifier must not be a subset of layouts of
+ * another modifier. For instance, it's incorrect to encode pitch alignment in
+ * a modifier: a buffer may match a 64-pixel aligned modifier and a 32-pixel
+ * aligned modifier. That said, modifiers can have implicit minimal
+ * requirements.
+ *
+ * For modifiers where the combination of fourcc code and modifier can alias,
+ * a canonical pair needs to be defined and used by all drivers. Preferred
+ * combinations are also encouraged where all combinations might lead to
+ * confusion and unnecessarily reduced interoperability. An example for the
+ * latter is AFBC, where the ABGR layouts are preferred over ARGB layouts.
+ *
+ * There are two kinds of modifier users:
+ *
+ * - Kernel and user-space drivers: for drivers it's important that modifiers
+ *   don't alias, otherwise two drivers might support the same format but use
+ *   different aliases, preventing them from sharing buffers in an efficient
+ *   format.
+ * - Higher-level programs interfacing with KMS/GBM/EGL/Vulkan/etc: these users
+ *   see modifiers as opaque tokens they can check for equality and intersect.
+ *   These users mustn't need to know to reason about the modifier value
+ *   (i.e. they are not expected to extract information out of the modifier).
+ *
+ * Vendors should document their modifier usage in as much detail as
+ * possible, to ensure maximum compatibility across devices, drivers and
+ * applications.
+ *
+ * The authoritative list of format modifier codes is found in
+ * `include/uapi/drm/drm_fourcc.h`
+ *
+ * Open Source User Waiver
+ * -----------------------
+ *
+ * Because this is the authoritative source for pixel formats and modifiers
+ * referenced by GL, Vulkan extensions and other standards and hence used both
+ * by open source and closed source driver stacks, the usual requirement for an
+ * upstream in-kernel or open source userspace user does not apply.
+ *
+ * To ensure, as much as feasible, compatibility across stacks and avoid
+ * confusion with incompatible enumerations stakeholders for all relevant driver
+ * stacks should approve additions.
+ */
+
+#define fourcc_code(a, b, c, d) ((__u32)(a) | ((__u32)(b) << 8) | \
+				 ((__u32)(c) << 16) | ((__u32)(d) << 24))
+
+#define DRM_FORMAT_BIG_ENDIAN (1U<<31) /* format is big endian instead of little endian */
+
+/* Reserve 0 for the invalid format specifier */
+#define DRM_FORMAT_INVALID	0
+
+/* color index */
+#define DRM_FORMAT_C1		fourcc_code('C', '1', ' ', ' ') /* [7:0] C0:C1:C2:C3:C4:C5:C6:C7 1:1:1:1:1:1:1:1 eight pixels/byte */
+#define DRM_FORMAT_C2		fourcc_code('C', '2', ' ', ' ') /* [7:0] C0:C1:C2:C3 2:2:2:2 four pixels/byte */
+#define DRM_FORMAT_C4		fourcc_code('C', '4', ' ', ' ') /* [7:0] C0:C1 4:4 two pixels/byte */
+#define DRM_FORMAT_C8		fourcc_code('C', '8', ' ', ' ') /* [7:0] C */
+
+/* 1 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D1		fourcc_code('D', '1', ' ', ' ') /* [7:0] D0:D1:D2:D3:D4:D5:D6:D7 1:1:1:1:1:1:1:1 eight pixels/byte */
+
+/* 2 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D2		fourcc_code('D', '2', ' ', ' ') /* [7:0] D0:D1:D2:D3 2:2:2:2 four pixels/byte */
+
+/* 4 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D4		fourcc_code('D', '4', ' ', ' ') /* [7:0] D0:D1 4:4 two pixels/byte */
+
+/* 8 bpp Darkness (inverse relationship between channel value and brightness) */
+#define DRM_FORMAT_D8		fourcc_code('D', '8', ' ', ' ') /* [7:0] D */
+
+/* 1 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R1		fourcc_code('R', '1', ' ', ' ') /* [7:0] R0:R1:R2:R3:R4:R5:R6:R7 1:1:1:1:1:1:1:1 eight pixels/byte */
+
+/* 2 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R2		fourcc_code('R', '2', ' ', ' ') /* [7:0] R0:R1:R2:R3 2:2:2:2 four pixels/byte */
+
+/* 4 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R4		fourcc_code('R', '4', ' ', ' ') /* [7:0] R0:R1 4:4 two pixels/byte */
+
+/* 8 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R8		fourcc_code('R', '8', ' ', ' ') /* [7:0] R */
+
+/* 10 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R10		fourcc_code('R', '1', '0', ' ') /* [15:0] x:R 6:10 little endian */
+
+/* 12 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R12		fourcc_code('R', '1', '2', ' ') /* [15:0] x:R 4:12 little endian */
+
+/* 16 bpp Red (direct relationship between channel value and brightness) */
+#define DRM_FORMAT_R16		fourcc_code('R', '1', '6', ' ') /* [15:0] R little endian */
+
+/* 16 bpp RG */
+#define DRM_FORMAT_RG88		fourcc_code('R', 'G', '8', '8') /* [15:0] R:G 8:8 little endian */
+#define DRM_FORMAT_GR88		fourcc_code('G', 'R', '8', '8') /* [15:0] G:R 8:8 little endian */
+
+/* 32 bpp RG */
+#define DRM_FORMAT_RG1616	fourcc_code('R', 'G', '3', '2') /* [31:0] R:G 16:16 little endian */
+#define DRM_FORMAT_GR1616	fourcc_code('G', 'R', '3', '2') /* [31:0] G:R 16:16 little endian */
+
+/* 8 bpp RGB */
+#define DRM_FORMAT_RGB332	fourcc_code('R', 'G', 'B', '8') /* [7:0] R:G:B 3:3:2 */
+#define DRM_FORMAT_BGR233	fourcc_code('B', 'G', 'R', '8') /* [7:0] B:G:R 2:3:3 */
+
+/* 16 bpp RGB */
+#define DRM_FORMAT_XRGB4444	fourcc_code('X', 'R', '1', '2') /* [15:0] x:R:G:B 4:4:4:4 little endian */
+#define DRM_FORMAT_XBGR4444	fourcc_code('X', 'B', '1', '2') /* [15:0] x:B:G:R 4:4:4:4 little endian */
+#define DRM_FORMAT_RGBX4444	fourcc_code('R', 'X', '1', '2') /* [15:0] R:G:B:x 4:4:4:4 little endian */
+#define DRM_FORMAT_BGRX4444	fourcc_code('B', 'X', '1', '2') /* [15:0] B:G:R:x 4:4:4:4 little endian */
+
+#define DRM_FORMAT_ARGB4444	fourcc_code('A', 'R', '1', '2') /* [15:0] A:R:G:B 4:4:4:4 little endian */
+#define DRM_FORMAT_ABGR4444	fourcc_code('A', 'B', '1', '2') /* [15:0] A:B:G:R 4:4:4:4 little endian */
+#define DRM_FORMAT_RGBA4444	fourcc_code('R', 'A', '1', '2') /* [15:0] R:G:B:A 4:4:4:4 little endian */
+#define DRM_FORMAT_BGRA4444	fourcc_code('B', 'A', '1', '2') /* [15:0] B:G:R:A 4:4:4:4 little endian */
+
+#define DRM_FORMAT_XRGB1555	fourcc_code('X', 'R', '1', '5') /* [15:0] x:R:G:B 1:5:5:5 little endian */
+#define DRM_FORMAT_XBGR1555	fourcc_code('X', 'B', '1', '5') /* [15:0] x:B:G:R 1:5:5:5 little endian */
+#define DRM_FORMAT_RGBX5551	fourcc_code('R', 'X', '1', '5') /* [15:0] R:G:B:x 5:5:5:1 little endian */
+#define DRM_FORMAT_BGRX5551	fourcc_code('B', 'X', '1', '5') /* [15:0] B:G:R:x 5:5:5:1 little endian */
+
+#define DRM_FORMAT_ARGB1555	fourcc_code('A', 'R', '1', '5') /* [15:0] A:R:G:B 1:5:5:5 little endian */
+#define DRM_FORMAT_ABGR1555	fourcc_code('A', 'B', '1', '5') /* [15:0] A:B:G:R 1:5:5:5 little endian */
+#define DRM_FORMAT_RGBA5551	fourcc_code('R', 'A', '1', '5') /* [15:0] R:G:B:A 5:5:5:1 little endian */
+#define DRM_FORMAT_BGRA5551	fourcc_code('B', 'A', '1', '5') /* [15:0] B:G:R:A 5:5:5:1 little endian */
+
+#define DRM_FORMAT_RGB565	fourcc_code('R', 'G', '1', '6') /* [15:0] R:G:B 5:6:5 little endian */
+#define DRM_FORMAT_BGR565	fourcc_code('B', 'G', '1', '6') /* [15:0] B:G:R 5:6:5 little endian */
+
+/* 24 bpp RGB */
+#define DRM_FORMAT_RGB888	fourcc_code('R', 'G', '2', '4') /* [23:0] R:G:B little endian */
+#define DRM_FORMAT_BGR888	fourcc_code('B', 'G', '2', '4') /* [23:0] B:G:R little endian */
+
+/* 32 bpp RGB */
+#define DRM_FORMAT_XRGB8888	fourcc_code('X', 'R', '2', '4') /* [31:0] x:R:G:B 8:8:8:8 little endian */
+#define DRM_FORMAT_XBGR8888	fourcc_code('X', 'B', '2', '4') /* [31:0] x:B:G:R 8:8:8:8 little endian */
+#define DRM_FORMAT_RGBX8888	fourcc_code('R', 'X', '2', '4') /* [31:0] R:G:B:x 8:8:8:8 little endian */
+#define DRM_FORMAT_BGRX8888	fourcc_code('B', 'X', '2', '4') /* [31:0] B:G:R:x 8:8:8:8 little endian */
+
+#define DRM_FORMAT_ARGB8888	fourcc_code('A', 'R', '2', '4') /* [31:0] A:R:G:B 8:8:8:8 little endian */
+#define DRM_FORMAT_ABGR8888	fourcc_code('A', 'B', '2', '4') /* [31:0] A:B:G:R 8:8:8:8 little endian */
+#define DRM_FORMAT_RGBA8888	fourcc_code('R', 'A', '2', '4') /* [31:0] R:G:B:A 8:8:8:8 little endian */
+#define DRM_FORMAT_BGRA8888	fourcc_code('B', 'A', '2', '4') /* [31:0] B:G:R:A 8:8:8:8 little endian */
+
+#define DRM_FORMAT_XRGB2101010	fourcc_code('X', 'R', '3', '0') /* [31:0] x:R:G:B 2:10:10:10 little endian */
+#define DRM_FORMAT_XBGR2101010	fourcc_code('X', 'B', '3', '0') /* [31:0] x:B:G:R 2:10:10:10 little endian */
+#define DRM_FORMAT_RGBX1010102	fourcc_code('R', 'X', '3', '0') /* [31:0] R:G:B:x 10:10:10:2 little endian */
+#define DRM_FORMAT_BGRX1010102	fourcc_code('B', 'X', '3', '0') /* [31:0] B:G:R:x 10:10:10:2 little endian */
+
+#define DRM_FORMAT_ARGB2101010	fourcc_code('A', 'R', '3', '0') /* [31:0] A:R:G:B 2:10:10:10 little endian */
+#define DRM_FORMAT_ABGR2101010	fourcc_code('A', 'B', '3', '0') /* [31:0] A:B:G:R 2:10:10:10 little endian */
+#define DRM_FORMAT_RGBA1010102	fourcc_code('R', 'A', '3', '0') /* [31:0] R:G:B:A 10:10:10:2 little endian */
+#define DRM_FORMAT_BGRA1010102	fourcc_code('B', 'A', '3', '0') /* [31:0] B:G:R:A 10:10:10:2 little endian */
+
+/* 48 bpp RGB */
+#define DRM_FORMAT_RGB161616 fourcc_code('R', 'G', '4', '8') /* [47:0] R:G:B 16:16:16 little endian */
+#define DRM_FORMAT_BGR161616 fourcc_code('B', 'G', '4', '8') /* [47:0] B:G:R 16:16:16 little endian */
+
+/* 64 bpp RGB */
+#define DRM_FORMAT_XRGB16161616	fourcc_code('X', 'R', '4', '8') /* [63:0] x:R:G:B 16:16:16:16 little endian */
+#define DRM_FORMAT_XBGR16161616	fourcc_code('X', 'B', '4', '8') /* [63:0] x:B:G:R 16:16:16:16 little endian */
+
+#define DRM_FORMAT_ARGB16161616	fourcc_code('A', 'R', '4', '8') /* [63:0] A:R:G:B 16:16:16:16 little endian */
+#define DRM_FORMAT_ABGR16161616	fourcc_code('A', 'B', '4', '8') /* [63:0] A:B:G:R 16:16:16:16 little endian */
+
+/*
+ * Half-Floating point - 16b/component
+ * IEEE 754-2008 binary16 half-precision float
+ * [15:0] sign:exponent:mantissa 1:5:10
+ */
+#define DRM_FORMAT_XRGB16161616F fourcc_code('X', 'R', '4', 'H') /* [63:0] x:R:G:B 16:16:16:16 little endian */
+#define DRM_FORMAT_XBGR16161616F fourcc_code('X', 'B', '4', 'H') /* [63:0] x:B:G:R 16:16:16:16 little endian */
+
+#define DRM_FORMAT_ARGB16161616F fourcc_code('A', 'R', '4', 'H') /* [63:0] A:R:G:B 16:16:16:16 little endian */
+#define DRM_FORMAT_ABGR16161616F fourcc_code('A', 'B', '4', 'H') /* [63:0] A:B:G:R 16:16:16:16 little endian */
+
+#define DRM_FORMAT_R16F          fourcc_code('R', ' ', ' ', 'H') /* [15:0] R 16 little endian */
+#define DRM_FORMAT_GR1616F       fourcc_code('G', 'R', ' ', 'H') /* [31:0] G:R 16:16 little endian */
+#define DRM_FORMAT_BGR161616F    fourcc_code('B', 'G', 'R', 'H') /* [47:0] B:G:R 16:16:16 little endian */
+
+/*
+ * Floating point - 32b/component
+ * IEEE 754-2008 binary32 float
+ * [31:0] sign:exponent:mantissa 1:8:23
+ */
+#define DRM_FORMAT_R32F          fourcc_code('R', ' ', ' ', 'F') /* [31:0] R 32 little endian */
+#define DRM_FORMAT_GR3232F       fourcc_code('G', 'R', ' ', 'F') /* [63:0] G:R 32:32 little endian */
+#define DRM_FORMAT_BGR323232F    fourcc_code('B', 'G', 'R', 'F') /* [95:0] B:G:R 32:32:32 little endian */
+#define DRM_FORMAT_ABGR32323232F fourcc_code('A', 'B', '8', 'F') /* [127:0] A:B:G:R 32:32:32:32 little endian */
+
+/*
+ * RGBA format with 10-bit components packed in 64-bit per pixel, with 6 bits
+ * of unused padding per component:
+ */
+#define DRM_FORMAT_AXBXGXRX106106106106 fourcc_code('A', 'B', '1', '0') /* [63:0] A:x:B:x:G:x:R:x 10:6:10:6:10:6:10:6 little endian */
+
+/* packed YCbCr */
+#define DRM_FORMAT_YUYV		fourcc_code('Y', 'U', 'Y', 'V') /* [31:0] Cr0:Y1:Cb0:Y0 8:8:8:8 little endian */
+#define DRM_FORMAT_YVYU		fourcc_code('Y', 'V', 'Y', 'U') /* [31:0] Cb0:Y1:Cr0:Y0 8:8:8:8 little endian */
+#define DRM_FORMAT_UYVY		fourcc_code('U', 'Y', 'V', 'Y') /* [31:0] Y1:Cr0:Y0:Cb0 8:8:8:8 little endian */
+#define DRM_FORMAT_VYUY		fourcc_code('V', 'Y', 'U', 'Y') /* [31:0] Y1:Cb0:Y0:Cr0 8:8:8:8 little endian */
+
+#define DRM_FORMAT_AYUV		fourcc_code('A', 'Y', 'U', 'V') /* [31:0] A:Y:Cb:Cr 8:8:8:8 little endian */
+#define DRM_FORMAT_AVUY8888	fourcc_code('A', 'V', 'U', 'Y') /* [31:0] A:Cr:Cb:Y 8:8:8:8 little endian */
+#define DRM_FORMAT_XYUV8888	fourcc_code('X', 'Y', 'U', 'V') /* [31:0] X:Y:Cb:Cr 8:8:8:8 little endian */
+#define DRM_FORMAT_XVUY8888	fourcc_code('X', 'V', 'U', 'Y') /* [31:0] X:Cr:Cb:Y 8:8:8:8 little endian */
+#define DRM_FORMAT_VUY888	fourcc_code('V', 'U', '2', '4') /* [23:0] Cr:Cb:Y 8:8:8 little endian */
+#define DRM_FORMAT_VUY101010	fourcc_code('V', 'U', '3', '0') /* Y followed by U then V, 10:10:10. Non-linear modifier only */
+#define DRM_FORMAT_XVUY2101010	fourcc_code('X', 'Y', '3', '0') /* [31:0] x:Cr:Cb:Y 2:10:10:10 little endian */
+
+/*
+ * packed Y2xx indicate for each component, xx valid data occupy msb
+ * 16-xx padding occupy lsb
+ */
+#define DRM_FORMAT_Y210         fourcc_code('Y', '2', '1', '0') /* [63:0] Cr0:0:Y1:0:Cb0:0:Y0:0 10:6:10:6:10:6:10:6 little endian per 2 Y pixels */
+#define DRM_FORMAT_Y212         fourcc_code('Y', '2', '1', '2') /* [63:0] Cr0:0:Y1:0:Cb0:0:Y0:0 12:4:12:4:12:4:12:4 little endian per 2 Y pixels */
+#define DRM_FORMAT_Y216         fourcc_code('Y', '2', '1', '6') /* [63:0] Cr0:Y1:Cb0:Y0 16:16:16:16 little endian per 2 Y pixels */
+
+/*
+ * packed Y4xx indicate for each component, xx valid data occupy msb
+ * 16-xx padding occupy lsb except Y410
+ */
+#define DRM_FORMAT_Y410         fourcc_code('Y', '4', '1', '0') /* [31:0] A:Cr:Y:Cb 2:10:10:10 little endian */
+#define DRM_FORMAT_Y412         fourcc_code('Y', '4', '1', '2') /* [63:0] A:0:Cr:0:Y:0:Cb:0 12:4:12:4:12:4:12:4 little endian */
+#define DRM_FORMAT_Y416         fourcc_code('Y', '4', '1', '6') /* [63:0] A:Cr:Y:Cb 16:16:16:16 little endian */
+
+#define DRM_FORMAT_XVYU2101010	fourcc_code('X', 'V', '3', '0') /* [31:0] X:Cr:Y:Cb 2:10:10:10 little endian */
+#define DRM_FORMAT_XVYU12_16161616	fourcc_code('X', 'V', '3', '6') /* [63:0] X:0:Cr:0:Y:0:Cb:0 12:4:12:4:12:4:12:4 little endian */
+#define DRM_FORMAT_XVYU16161616	fourcc_code('X', 'V', '4', '8') /* [63:0] X:Cr:Y:Cb 16:16:16:16 little endian */
+
+/*
+ * packed YCbCr420 2x2 tiled formats
+ * first 64 bits will contain Y,Cb,Cr components for a 2x2 tile
+ */
+/* [63:0]   A3:A2:Y3:0:Cr0:0:Y2:0:A1:A0:Y1:0:Cb0:0:Y0:0  1:1:8:2:8:2:8:2:1:1:8:2:8:2:8:2 little endian */
+#define DRM_FORMAT_Y0L0		fourcc_code('Y', '0', 'L', '0')
+/* [63:0]   X3:X2:Y3:0:Cr0:0:Y2:0:X1:X0:Y1:0:Cb0:0:Y0:0  1:1:8:2:8:2:8:2:1:1:8:2:8:2:8:2 little endian */
+#define DRM_FORMAT_X0L0		fourcc_code('X', '0', 'L', '0')
+
+/* [63:0]   A3:A2:Y3:Cr0:Y2:A1:A0:Y1:Cb0:Y0  1:1:10:10:10:1:1:10:10:10 little endian */
+#define DRM_FORMAT_Y0L2		fourcc_code('Y', '0', 'L', '2')
+/* [63:0]   X3:X2:Y3:Cr0:Y2:X1:X0:Y1:Cb0:Y0  1:1:10:10:10:1:1:10:10:10 little endian */
+#define DRM_FORMAT_X0L2		fourcc_code('X', '0', 'L', '2')
+
+/*
+ * 1-plane YUV 4:2:0
+ * In these formats, the component ordering is specified (Y, followed by U
+ * then V), but the exact Linear layout is undefined.
+ * These formats can only be used with a non-Linear modifier.
+ */
+#define DRM_FORMAT_YUV420_8BIT	fourcc_code('Y', 'U', '0', '8')
+#define DRM_FORMAT_YUV420_10BIT	fourcc_code('Y', 'U', '1', '0')
+
+/*
+ * 2 plane RGB + A
+ * index 0 = RGB plane, same format as the corresponding non _A8 format has
+ * index 1 = A plane, [7:0] A
+ */
+#define DRM_FORMAT_XRGB8888_A8	fourcc_code('X', 'R', 'A', '8')
+#define DRM_FORMAT_XBGR8888_A8	fourcc_code('X', 'B', 'A', '8')
+#define DRM_FORMAT_RGBX8888_A8	fourcc_code('R', 'X', 'A', '8')
+#define DRM_FORMAT_BGRX8888_A8	fourcc_code('B', 'X', 'A', '8')
+#define DRM_FORMAT_RGB888_A8	fourcc_code('R', '8', 'A', '8')
+#define DRM_FORMAT_BGR888_A8	fourcc_code('B', '8', 'A', '8')
+#define DRM_FORMAT_RGB565_A8	fourcc_code('R', '5', 'A', '8')
+#define DRM_FORMAT_BGR565_A8	fourcc_code('B', '5', 'A', '8')
+
+/*
+ * 2 plane YCbCr
+ * index 0 = Y plane, [7:0] Y
+ * index 1 = Cr:Cb plane, [15:0] Cr:Cb little endian
+ * or
+ * index 1 = Cb:Cr plane, [15:0] Cb:Cr little endian
+ */
+#define DRM_FORMAT_NV12		fourcc_code('N', 'V', '1', '2') /* 2x2 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV21		fourcc_code('N', 'V', '2', '1') /* 2x2 subsampled Cb:Cr plane */
+#define DRM_FORMAT_NV16		fourcc_code('N', 'V', '1', '6') /* 2x1 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV61		fourcc_code('N', 'V', '6', '1') /* 2x1 subsampled Cb:Cr plane */
+#define DRM_FORMAT_NV24		fourcc_code('N', 'V', '2', '4') /* non-subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV42		fourcc_code('N', 'V', '4', '2') /* non-subsampled Cb:Cr plane */
+/*
+ * 2 plane YCbCr
+ * index 0 = Y plane, [39:0] Y3:Y2:Y1:Y0 little endian
+ * index 1 = Cr:Cb plane, [39:0] Cr1:Cb1:Cr0:Cb0 little endian
+ */
+#define DRM_FORMAT_NV15		fourcc_code('N', 'V', '1', '5') /* 2x2 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV20		fourcc_code('N', 'V', '2', '0') /* 2x1 subsampled Cr:Cb plane */
+#define DRM_FORMAT_NV30		fourcc_code('N', 'V', '3', '0') /* non-subsampled Cr:Cb plane */
+
+/*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y:x [10:6] little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:x:Cb:x [10:6:10:6] little endian
+ */
+#define DRM_FORMAT_P210		fourcc_code('P', '2', '1', '0') /* 2x1 subsampled Cr:Cb plane, 10 bit per channel */
+
+/*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y:x [10:6] little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:x:Cb:x [10:6:10:6] little endian
+ */
+#define DRM_FORMAT_P010		fourcc_code('P', '0', '1', '0') /* 2x2 subsampled Cr:Cb plane 10 bits per channel */
+
+/*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y:x [12:4] little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:x:Cb:x [12:4:12:4] little endian
+ */
+#define DRM_FORMAT_P012		fourcc_code('P', '0', '1', '2') /* 2x2 subsampled Cr:Cb plane 12 bits per channel */
+
+/*
+ * 2 plane YCbCr MSB aligned
+ * index 0 = Y plane, [15:0] Y little endian
+ * index 1 = Cr:Cb plane, [31:0] Cr:Cb [16:16] little endian
+ */
+#define DRM_FORMAT_P016		fourcc_code('P', '0', '1', '6') /* 2x2 subsampled Cr:Cb plane 16 bits per channel */
+
+/* 2 plane YCbCr420.
+ * 3 10 bit components and 2 padding bits packed into 4 bytes.
+ * index 0 = Y plane, [31:0] x:Y2:Y1:Y0 2:10:10:10 little endian
+ * index 1 = Cr:Cb plane, [63:0] x:Cr2:Cb2:Cr1:x:Cb1:Cr0:Cb0 [2:10:10:10:2:10:10:10] little endian
+ */
+#define DRM_FORMAT_P030		fourcc_code('P', '0', '3', '0') /* 2x2 subsampled Cr:Cb plane 10 bits per channel packed */
+
+/*
+ * 2 plane YCbCr422.
+ * 3 10 bit components and 2 padding bits packed into 4 bytes.
+ * index 0 = Y plane, [31:0] x:Y2:Y1:Y0 2:10:10:10 little endian
+ * index 1 = Cr:Cb plane, [63:0] x:Cr2:Cb2:Cr1:x:Cb1:Cr0:Cb0 [2:10:10:10:2:10:10:10] little endian
+ */
+#define DRM_FORMAT_P230		fourcc_code('P', '2', '3', '0') /* 2x1 subsampled Cr:Cb plane 10 bits per channel packed */
+
+/* 3 plane non-subsampled (444) YCbCr
+ * 16 bits per component, but only 10 bits are used and 6 bits are padded
+ * index 0: Y plane, [15:0] Y:x [10:6] little endian
+ * index 1: Cb plane, [15:0] Cb:x [10:6] little endian
+ * index 2: Cr plane, [15:0] Cr:x [10:6] little endian
+ */
+#define DRM_FORMAT_Q410		fourcc_code('Q', '4', '1', '0')
+
+/* 3 plane non-subsampled (444) YCrCb
+ * 16 bits per component, but only 10 bits are used and 6 bits are padded
+ * index 0: Y plane, [15:0] Y:x [10:6] little endian
+ * index 1: Cr plane, [15:0] Cr:x [10:6] little endian
+ * index 2: Cb plane, [15:0] Cb:x [10:6] little endian
+ */
+#define DRM_FORMAT_Q401		fourcc_code('Q', '4', '0', '1')
+
+/*
+ * 3 plane non-subsampled (444) YCbCr LSB aligned
+ * 10 bpc, 30 bits per sample image data in a single contiguous buffer.
+ * index 0: Y plane,  [31:0] x:Y2:Y1:Y0    [2:10:10:10] little endian
+ * index 1: Cb plane, [31:0] x:Cb2:Cb1:Cb0 [2:10:10:10] little endian
+ * index 2: Cr plane, [31:0] x:Cr2:Cr1:Cr0 [2:10:10:10] little endian
+ */
+#define DRM_FORMAT_T430		fourcc_code('T', '4', '3', '0')
+
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^6=64. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [6:10] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [6:10] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [6:10] little endian
+ */
+#define DRM_FORMAT_S010	fourcc_code('S', '0', '1', '0') /* 2x2 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S210	fourcc_code('S', '2', '1', '0') /* 2x1 subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+#define DRM_FORMAT_S410	fourcc_code('S', '4', '1', '0') /* non-subsampled Cb (1) and Cr (2) planes 10 bits per channel */
+
+/*
+ * 3 plane YCbCr LSB aligned
+ * In order to use these formats in a similar fashion to MSB aligned ones
+ * implementation can multiply the values by 2^4=16. For that reason the padding
+ * must only contain zeros.
+ * index 0 = Y plane, [15:0] z:Y [4:12] little endian
+ * index 1 = Cb plane, [15:0] z:Cb [4:12] little endian
+ * index 2 = Cr plane, [15:0] z:Cr [4:12] little endian
+ */
+#define DRM_FORMAT_S012	fourcc_code('S', '0', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S212	fourcc_code('S', '2', '1', '2') /* 2x1 subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+#define DRM_FORMAT_S412	fourcc_code('S', '4', '1', '2') /* non-subsampled Cb (1) and Cr (2) planes 12 bits per channel */
+
+/*
+ * 3 plane YCbCr
+ * index 0 = Y plane, [15:0] Y little endian
+ * index 1 = Cb plane, [15:0] Cb little endian
+ * index 2 = Cr plane, [15:0] Cr little endian
+ */
+#define DRM_FORMAT_S016	fourcc_code('S', '0', '1', '6') /* 2x2 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S216	fourcc_code('S', '2', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+#define DRM_FORMAT_S416	fourcc_code('S', '4', '1', '6') /* non-subsampled Cb (1) and Cr (2) planes 16 bits per channel */
+
+/*
+ * 3 plane YCbCr
+ * index 0: Y plane, [7:0] Y
+ * index 1: Cb plane, [7:0] Cb
+ * index 2: Cr plane, [7:0] Cr
+ * or
+ * index 1: Cr plane, [7:0] Cr
+ * index 2: Cb plane, [7:0] Cb
+ */
+#define DRM_FORMAT_YUV410	fourcc_code('Y', 'U', 'V', '9') /* 4x4 subsampled Cb (1) and Cr (2) planes */
+#define DRM_FORMAT_YVU410	fourcc_code('Y', 'V', 'U', '9') /* 4x4 subsampled Cr (1) and Cb (2) planes */
+#define DRM_FORMAT_YUV411	fourcc_code('Y', 'U', '1', '1') /* 4x1 subsampled Cb (1) and Cr (2) planes */
+#define DRM_FORMAT_YVU411	fourcc_code('Y', 'V', '1', '1') /* 4x1 subsampled Cr (1) and Cb (2) planes */
+#define DRM_FORMAT_YUV420	fourcc_code('Y', 'U', '1', '2') /* 2x2 subsampled Cb (1) and Cr (2) planes */
+#define DRM_FORMAT_YVU420	fourcc_code('Y', 'V', '1', '2') /* 2x2 subsampled Cr (1) and Cb (2) planes */
+#define DRM_FORMAT_YUV422	fourcc_code('Y', 'U', '1', '6') /* 2x1 subsampled Cb (1) and Cr (2) planes */
+#define DRM_FORMAT_YVU422	fourcc_code('Y', 'V', '1', '6') /* 2x1 subsampled Cr (1) and Cb (2) planes */
+#define DRM_FORMAT_YUV444	fourcc_code('Y', 'U', '2', '4') /* non-subsampled Cb (1) and Cr (2) planes */
+#define DRM_FORMAT_YVU444	fourcc_code('Y', 'V', '2', '4') /* non-subsampled Cr (1) and Cb (2) planes */
+
+/*
+ * Y-only (greyscale) formats
+ *
+ * The Y-only formats are handled similarly to the YCbCr formats in the display
+ * pipeline, with the Cb and Cr implicitly neutral (0.0 in nominal values). This
+ * also means that COLOR_RANGE property applies to the Y-only formats.
+ */
+
+#define DRM_FORMAT_Y8		fourcc_code('G', 'R', 'E', 'Y')  /* 8-bit Y-only */
+#define DRM_FORMAT_XYYY2101010	fourcc_code('Y', 'P', 'A', '4')  /* [31:0] x:Y2:Y1:Y0 2:10:10:10 little endian */
+
+/*
+ * Format Modifiers:
+ *
+ * Format modifiers describe, typically, a re-ordering or modification
+ * of the data in a plane of an FB.  This can be used to express tiled/
+ * swizzled formats, or compression, or a combination of the two.
+ *
+ * The upper 8 bits of the format modifier are a vendor-id as assigned
+ * below.  The lower 56 bits are assigned as vendor sees fit.
+ */
+
+/* Vendor Ids: */
+#define DRM_FORMAT_MOD_VENDOR_NONE    0
+#define DRM_FORMAT_MOD_VENDOR_INTEL   0x01
+#define DRM_FORMAT_MOD_VENDOR_AMD     0x02
+#define DRM_FORMAT_MOD_VENDOR_NVIDIA  0x03
+#define DRM_FORMAT_MOD_VENDOR_SAMSUNG 0x04
+#define DRM_FORMAT_MOD_VENDOR_QCOM    0x05
+#define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06
+#define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
+#define DRM_FORMAT_MOD_VENDOR_ARM     0x08
+#define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09
+#define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a
+#define DRM_FORMAT_MOD_VENDOR_MTK     0x0b
+#define DRM_FORMAT_MOD_VENDOR_APPLE   0x0c
+
+/* add more to the end as needed */
+
+#define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
+
+#define fourcc_mod_get_vendor(modifier) \
+	(((modifier) >> 56) & 0xff)
+
+#define fourcc_mod_is_vendor(modifier, vendor) \
+	(fourcc_mod_get_vendor(modifier) == DRM_FORMAT_MOD_VENDOR_## vendor)
+
+#define fourcc_mod_code(vendor, val) \
+	((((__u64)DRM_FORMAT_MOD_VENDOR_## vendor) << 56) | ((val) & 0x00ffffffffffffffULL))
+
+/*
+ * Format Modifier tokens:
+ *
+ * When adding a new token please document the layout with a code comment,
+ * similar to the fourcc codes above. drm_fourcc.h is considered the
+ * authoritative source for all of these.
+ *
+ * Generic modifier names:
+ *
+ * DRM_FORMAT_MOD_GENERIC_* definitions are used to provide vendor-neutral names
+ * for layouts which are common across multiple vendors. To preserve
+ * compatibility, in cases where a vendor-specific definition already exists and
+ * a generic name for it is desired, the common name is a purely symbolic alias
+ * and must use the same numerical value as the original definition.
+ *
+ * Note that generic names should only be used for modifiers which describe
+ * generic layouts (such as pixel re-ordering), which may have
+ * independently-developed support across multiple vendors.
+ *
+ * In future cases where a generic layout is identified before merging with a
+ * vendor-specific modifier, a new 'GENERIC' vendor or modifier using vendor
+ * 'NONE' could be considered. This should only be for obvious, exceptional
+ * cases to avoid polluting the 'GENERIC' namespace with modifiers which only
+ * apply to a single vendor.
+ *
+ * Generic names should not be used for cases where multiple hardware vendors
+ * have implementations of the same standardised compression scheme (such as
+ * AFBC). In those cases, all implementations should use the same format
+ * modifier(s), reflecting the vendor of the standard.
+ */
+
+#define DRM_FORMAT_MOD_GENERIC_16_16_TILE DRM_FORMAT_MOD_SAMSUNG_16_16_TILE
+
+/*
+ * Invalid Modifier
+ *
+ * This modifier can be used as a sentinel to terminate the format modifiers
+ * list, or to initialize a variable with an invalid modifier. It might also be
+ * used to report an error back to userspace for certain APIs.
+ */
+#define DRM_FORMAT_MOD_INVALID	fourcc_mod_code(NONE, DRM_FORMAT_RESERVED)
+
+/*
+ * Linear Layout
+ *
+ * Just plain linear layout. Note that this is different from no specifying any
+ * modifier (e.g. not setting DRM_MODE_FB_MODIFIERS in the DRM_ADDFB2 ioctl),
+ * which tells the driver to also take driver-internal information into account
+ * and so might actually result in a tiled framebuffer.
+ */
+#define DRM_FORMAT_MOD_LINEAR	fourcc_mod_code(NONE, 0)
+
+/*
+ * Deprecated: use DRM_FORMAT_MOD_LINEAR instead
+ *
+ * The "none" format modifier doesn't actually mean that the modifier is
+ * implicit, instead it means that the layout is linear. Whether modifiers are
+ * used is out-of-band information carried in an API-specific way (e.g. in a
+ * flag for drm_mode_fb_cmd2).
+ */
+#define DRM_FORMAT_MOD_NONE	0
+
+/* Intel framebuffer modifiers */
+
+/*
+ * Intel X-tiling layout
+ *
+ * This is a tiled layout using 4Kb tiles (except on gen2 where the tiles 2Kb)
+ * in row-major layout. Within the tile bytes are laid out row-major, with
+ * a platform-dependent stride. On top of that the memory can apply
+ * platform-depending swizzling of some higher address bits into bit6.
+ *
+ * Note that this layout is only accurate on intel gen 8+ or valleyview chipsets.
+ * On earlier platforms the is highly platforms specific and not useful for
+ * cross-driver sharing. It exists since on a given platform it does uniquely
+ * identify the layout in a simple way for i915-specific userspace, which
+ * facilitated conversion of userspace to modifiers. Additionally the exact
+ * format on some really old platforms is not known.
+ */
+#define I915_FORMAT_MOD_X_TILED	fourcc_mod_code(INTEL, 1)
+
+/*
+ * Intel Y-tiling layout
+ *
+ * This is a tiled layout using 4Kb tiles (except on gen2 where the tiles 2Kb)
+ * in row-major layout. Within the tile bytes are laid out in OWORD (16 bytes)
+ * chunks column-major, with a platform-dependent height. On top of that the
+ * memory can apply platform-depending swizzling of some higher address bits
+ * into bit6.
+ *
+ * Note that this layout is only accurate on intel gen 8+ or valleyview chipsets.
+ * On earlier platforms the is highly platforms specific and not useful for
+ * cross-driver sharing. It exists since on a given platform it does uniquely
+ * identify the layout in a simple way for i915-specific userspace, which
+ * facilitated conversion of userspace to modifiers. Additionally the exact
+ * format on some really old platforms is not known.
+ */
+#define I915_FORMAT_MOD_Y_TILED	fourcc_mod_code(INTEL, 2)
+
+/*
+ * Intel Yf-tiling layout
+ *
+ * This is a tiled layout using 4Kb tiles in row-major layout.
+ * Within the tile pixels are laid out in 16 256 byte units / sub-tiles which
+ * are arranged in four groups (two wide, two high) with column-major layout.
+ * Each group therefore consists out of four 256 byte units, which are also laid
+ * out as 2x2 column-major.
+ * 256 byte units are made out of four 64 byte blocks of pixels, producing
+ * either a square block or a 2:1 unit.
+ * 64 byte blocks of pixels contain four pixel rows of 16 bytes, where the width
+ * in pixel depends on the pixel depth.
+ */
+#define I915_FORMAT_MOD_Yf_TILED fourcc_mod_code(INTEL, 3)
+
+/*
+ * Intel color control surface (CCS) for render compression
+ *
+ * The framebuffer format must be one of the 8:8:8:8 RGB formats.
+ * The main surface will be plane index 0 and must be Y/Yf-tiled,
+ * the CCS will be plane index 1.
+ *
+ * Each CCS tile matches a 1024x512 pixel area of the main surface.
+ * To match certain aspects of the 3D hardware the CCS is
+ * considered to be made up of normal 128Bx32 Y tiles, Thus
+ * the CCS pitch must be specified in multiples of 128 bytes.
+ *
+ * In reality the CCS tile appears to be a 64Bx64 Y tile, composed
+ * of QWORD (8 bytes) chunks instead of OWORD (16 bytes) chunks.
+ * But that fact is not relevant unless the memory is accessed
+ * directly.
+ */
+#define I915_FORMAT_MOD_Y_TILED_CCS	fourcc_mod_code(INTEL, 4)
+#define I915_FORMAT_MOD_Yf_TILED_CCS	fourcc_mod_code(INTEL, 5)
+
+/*
+ * Intel color control surfaces (CCS) for Gen-12 render compression.
+ *
+ * The main surface is Y-tiled and at plane index 0, the CCS is linear and
+ * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in
+ * main surface. In other words, 4 bits in CCS map to a main surface cache
+ * line pair. The main surface pitch is required to be a multiple of four
+ * Y-tile widths.
+ */
+#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS fourcc_mod_code(INTEL, 6)
+
+/*
+ * Intel color control surfaces (CCS) for Gen-12 media compression
+ *
+ * The main surface is Y-tiled and at plane index 0, the CCS is linear and
+ * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in
+ * main surface. In other words, 4 bits in CCS map to a main surface cache
+ * line pair. The main surface pitch is required to be a multiple of four
+ * Y-tile widths. For semi-planar formats like NV12, CCS planes follow the
+ * Y and UV planes i.e., planes 0 and 1 are used for Y and UV surfaces,
+ * planes 2 and 3 for the respective CCS.
+ */
+#define I915_FORMAT_MOD_Y_TILED_GEN12_MC_CCS fourcc_mod_code(INTEL, 7)
+
+/*
+ * Intel Color Control Surface with Clear Color (CCS) for Gen-12 render
+ * compression.
+ *
+ * The main surface is Y-tiled and is at plane index 0 whereas CCS is linear
+ * and at index 1. The clear color is stored at index 2, and the pitch should
+ * be 64 bytes aligned. The clear color structure is 256 bits. The first 128 bits
+ * represents Raw Clear Color Red, Green, Blue and Alpha color each represented
+ * by 32 bits. The raw clear color is consumed by the 3d engine and generates
+ * the converted clear color of size 64 bits. The first 32 bits store the Lower
+ * Converted Clear Color value and the next 32 bits store the Higher Converted
+ * Clear Color value when applicable. The Converted Clear Color values are
+ * consumed by the DE. The last 64 bits are used to store Color Discard Enable
+ * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line
+ * corresponds to an area of 4x1 tiles in the main surface. The main surface
+ * pitch is required to be a multiple of 4 tile widths.
+ */
+#define I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC fourcc_mod_code(INTEL, 8)
+
+/*
+ * Intel Tile 4 layout
+ *
+ * This is a tiled layout using 4KB tiles in a row-major layout. It has the same
+ * shape as Tile Y at two granularities: 4KB (128B x 32) and 64B (16B x 4). It
+ * only differs from Tile Y at the 256B granularity in between. At this
+ * granularity, Tile Y has a shape of 16B x 32 rows, but this tiling has a shape
+ * of 64B x 8 rows.
+ */
+#define I915_FORMAT_MOD_4_TILED         fourcc_mod_code(INTEL, 9)
+
+/*
+ * Intel color control surfaces (CCS) for DG2 render compression.
+ *
+ * The main surface is Tile 4 and at plane index 0. The CCS data is stored
+ * outside of the GEM object in a reserved memory area dedicated for the
+ * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The
+ * main surface pitch is required to be a multiple of four Tile 4 widths.
+ */
+#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS fourcc_mod_code(INTEL, 10)
+
+/*
+ * Intel color control surfaces (CCS) for DG2 media compression.
+ *
+ * The main surface is Tile 4 and at plane index 0. For semi-planar formats
+ * like NV12, the Y and UV planes are Tile 4 and are located at plane indices
+ * 0 and 1, respectively. The CCS for all planes are stored outside of the
+ * GEM object in a reserved memory area dedicated for the storage of the
+ * CCS data for all RC/RC_CC/MC compressible GEM objects. The main surface
+ * pitch is required to be a multiple of four Tile 4 widths.
+ */
+#define I915_FORMAT_MOD_4_TILED_DG2_MC_CCS fourcc_mod_code(INTEL, 11)
+
+/*
+ * Intel Color Control Surface with Clear Color (CCS) for DG2 render compression.
+ *
+ * The main surface is Tile 4 and at plane index 0. The CCS data is stored
+ * outside of the GEM object in a reserved memory area dedicated for the
+ * storage of the CCS data for all RC/RC_CC/MC compressible GEM objects. The
+ * main surface pitch is required to be a multiple of four Tile 4 widths. The
+ * clear color is stored at plane index 1 and the pitch should be 64 bytes
+ * aligned. The format of the 256 bits of clear color data matches the one used
+ * for the I915_FORMAT_MOD_Y_TILED_GEN12_RC_CCS_CC modifier, see its description
+ * for details.
+ */
+#define I915_FORMAT_MOD_4_TILED_DG2_RC_CCS_CC fourcc_mod_code(INTEL, 12)
+
+/*
+ * Intel Color Control Surfaces (CCS) for display ver. 14 render compression.
+ *
+ * The main surface is tile4 and at plane index 0, the CCS is linear and
+ * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in
+ * main surface. In other words, 4 bits in CCS map to a main surface cache
+ * line pair. The main surface pitch is required to be a multiple of four
+ * tile4 widths.
+ */
+#define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS fourcc_mod_code(INTEL, 13)
+
+/*
+ * Intel Color Control Surfaces (CCS) for display ver. 14 media compression
+ *
+ * The main surface is tile4 and at plane index 0, the CCS is linear and
+ * at index 1. A 64B CCS cache line corresponds to an area of 4x1 tiles in
+ * main surface. In other words, 4 bits in CCS map to a main surface cache
+ * line pair. The main surface pitch is required to be a multiple of four
+ * tile4 widths. For semi-planar formats like NV12, CCS planes follow the
+ * Y and UV planes i.e., planes 0 and 1 are used for Y and UV surfaces,
+ * planes 2 and 3 for the respective CCS.
+ */
+#define I915_FORMAT_MOD_4_TILED_MTL_MC_CCS fourcc_mod_code(INTEL, 14)
+
+/*
+ * Intel Color Control Surface with Clear Color (CCS) for display ver. 14 render
+ * compression.
+ *
+ * The main surface is tile4 and is at plane index 0 whereas CCS is linear
+ * and at index 1. The clear color is stored at index 2, and the pitch should
+ * be ignored. The clear color structure is 256 bits. The first 128 bits
+ * represents Raw Clear Color Red, Green, Blue and Alpha color each represented
+ * by 32 bits. The raw clear color is consumed by the 3d engine and generates
+ * the converted clear color of size 64 bits. The first 32 bits store the Lower
+ * Converted Clear Color value and the next 32 bits store the Higher Converted
+ * Clear Color value when applicable. The Converted Clear Color values are
+ * consumed by the DE. The last 64 bits are used to store Color Discard Enable
+ * and Depth Clear Value Valid which are ignored by the DE. A CCS cache line
+ * corresponds to an area of 4x1 tiles in the main surface. The main surface
+ * pitch is required to be a multiple of 4 tile widths.
+ */
+#define I915_FORMAT_MOD_4_TILED_MTL_RC_CCS_CC fourcc_mod_code(INTEL, 15)
+
+/*
+ * Intel Color Control Surfaces (CCS) for graphics ver. 20 unified compression
+ * on integrated graphics
+ *
+ * The main surface is Tile 4 and at plane index 0. For semi-planar formats
+ * like NV12, the Y and UV planes are Tile 4 and are located at plane indices
+ * 0 and 1, respectively. The CCS for all planes are stored outside of the
+ * GEM object in a reserved memory area dedicated for the storage of the
+ * CCS data for all compressible GEM objects.
+ */
+#define I915_FORMAT_MOD_4_TILED_LNL_CCS fourcc_mod_code(INTEL, 16)
+
+/*
+ * Intel Color Control Surfaces (CCS) for graphics ver. 20 unified compression
+ * on discrete graphics
+ *
+ * The main surface is Tile 4 and at plane index 0. For semi-planar formats
+ * like NV12, the Y and UV planes are Tile 4 and are located at plane indices
+ * 0 and 1, respectively. The CCS for all planes are stored outside of the
+ * GEM object in a reserved memory area dedicated for the storage of the
+ * CCS data for all compressible GEM objects. The GEM object must be stored in
+ * contiguous memory with a size aligned to 64KB
+ */
+#define I915_FORMAT_MOD_4_TILED_BMG_CCS fourcc_mod_code(INTEL, 17)
+
+/*
+ * Tiled, NV12MT, grouped in 64 (pixels) x 32 (lines) -sized macroblocks
+ *
+ * Macroblocks are laid in a Z-shape, and each pixel data is following the
+ * standard NV12 style.
+ * As for NV12, an image is the result of two frame buffers: one for Y,
+ * one for the interleaved Cb/Cr components (1/2 the height of the Y buffer).
+ * Alignment requirements are (for each buffer):
+ * - multiple of 128 pixels for the width
+ * - multiple of  32 pixels for the height
+ *
+ * For more information: see https://linuxtv.org/downloads/v4l-dvb-apis/re32.html
+ */
+#define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE	fourcc_mod_code(SAMSUNG, 1)
+
+/*
+ * Tiled, 16 (pixels) x 16 (lines) - sized macroblocks
+ *
+ * This is a simple tiled layout using tiles of 16x16 pixels in a row-major
+ * layout. For YCbCr formats Cb/Cr components are taken in such a way that
+ * they correspond to their 16x16 luma block.
+ */
+#define DRM_FORMAT_MOD_SAMSUNG_16_16_TILE	fourcc_mod_code(SAMSUNG, 2)
+
+/*
+ * Qualcomm Compressed Format
+ *
+ * Refers to a compressed variant of the base format that is compressed.
+ * Implementation may be platform and base-format specific.
+ *
+ * Each macrotile consists of m x n (mostly 4 x 4) tiles.
+ * Pixel data pitch/stride is aligned with macrotile width.
+ * Pixel data height is aligned with macrotile height.
+ * Entire pixel data buffer is aligned with 4k(bytes).
+ */
+#define DRM_FORMAT_MOD_QCOM_COMPRESSED	fourcc_mod_code(QCOM, 1)
+
+/*
+ * Qualcomm Tiled Format
+ *
+ * Similar to DRM_FORMAT_MOD_QCOM_COMPRESSED but not compressed.
+ * Implementation may be platform and base-format specific.
+ *
+ * Each macrotile consists of m x n (mostly 4 x 4) tiles.
+ * Pixel data pitch/stride is aligned with macrotile width.
+ * Pixel data height is aligned with macrotile height.
+ * Entire pixel data buffer is aligned with 4k(bytes).
+ */
+#define DRM_FORMAT_MOD_QCOM_TILED3	fourcc_mod_code(QCOM, 3)
+
+/*
+ * Qualcomm Alternate Tiled Format
+ *
+ * Alternate tiled format typically only used within GMEM.
+ * Implementation may be platform and base-format specific.
+ */
+#define DRM_FORMAT_MOD_QCOM_TILED2	fourcc_mod_code(QCOM, 2)
+
+
+/* Vivante framebuffer modifiers */
+
+/*
+ * Vivante 4x4 tiling layout
+ *
+ * This is a simple tiled layout using tiles of 4x4 pixels in a row-major
+ * layout.
+ */
+#define DRM_FORMAT_MOD_VIVANTE_TILED		fourcc_mod_code(VIVANTE, 1)
+
+/*
+ * Vivante 64x64 super-tiling layout
+ *
+ * This is a tiled layout using 64x64 pixel super-tiles, where each super-tile
+ * contains 8x4 groups of 2x4 tiles of 4x4 pixels (like above) each, all in row-
+ * major layout.
+ *
+ * For more information: see
+ * https://github.com/etnaviv/etna_viv/blob/master/doc/hardware.md#texture-tiling
+ */
+#define DRM_FORMAT_MOD_VIVANTE_SUPER_TILED	fourcc_mod_code(VIVANTE, 2)
+
+/*
+ * Vivante 4x4 tiling layout for dual-pipe
+ *
+ * Same as the 4x4 tiling layout, except every second 4x4 pixel tile starts at a
+ * different base address. Offsets from the base addresses are therefore halved
+ * compared to the non-split tiled layout.
+ */
+#define DRM_FORMAT_MOD_VIVANTE_SPLIT_TILED	fourcc_mod_code(VIVANTE, 3)
+
+/*
+ * Vivante 64x64 super-tiling layout for dual-pipe
+ *
+ * Same as the 64x64 super-tiling layout, except every second 4x4 pixel tile
+ * starts at a different base address. Offsets from the base addresses are
+ * therefore halved compared to the non-split super-tiled layout.
+ */
+#define DRM_FORMAT_MOD_VIVANTE_SPLIT_SUPER_TILED fourcc_mod_code(VIVANTE, 4)
+
+/*
+ * Vivante TS (tile-status) buffer modifiers. They can be combined with all of
+ * the color buffer tiling modifiers defined above. When TS is present it's a
+ * separate buffer containing the clear/compression status of each tile. The
+ * modifiers are defined as VIVANTE_MOD_TS_c_s, where c is the color buffer
+ * tile size in bytes covered by one entry in the status buffer and s is the
+ * number of status bits per entry.
+ * We reserve the top 8 bits of the Vivante modifier space for tile status
+ * clear/compression modifiers, as future cores might add some more TS layout
+ * variations.
+ */
+#define VIVANTE_MOD_TS_64_4               (1ULL << 48)
+#define VIVANTE_MOD_TS_64_2               (2ULL << 48)
+#define VIVANTE_MOD_TS_128_4              (3ULL << 48)
+#define VIVANTE_MOD_TS_256_4              (4ULL << 48)
+#define VIVANTE_MOD_TS_MASK               (0xfULL << 48)
+
+/*
+ * Vivante compression modifiers. Those depend on a TS modifier being present
+ * as the TS bits get reinterpreted as compression tags instead of simple
+ * clear markers when compression is enabled.
+ */
+#define VIVANTE_MOD_COMP_DEC400           (1ULL << 52)
+#define VIVANTE_MOD_COMP_MASK             (0xfULL << 52)
+
+/* Masking out the extension bits will yield the base modifier. */
+#define VIVANTE_MOD_EXT_MASK              (VIVANTE_MOD_TS_MASK | \
+                                           VIVANTE_MOD_COMP_MASK)
+
+/* NVIDIA frame buffer modifiers */
+
+/*
+ * Tegra Tiled Layout, used by Tegra 2, 3 and 4.
+ *
+ * Pixels are arranged in simple tiles of 16 x 16 bytes.
+ */
+#define DRM_FORMAT_MOD_NVIDIA_TEGRA_TILED fourcc_mod_code(NVIDIA, 1)
+
+/*
+ * Generalized Block Linear layout, used by desktop GPUs starting with NV50/G80,
+ * and Tegra GPUs starting with Tegra K1.
+ *
+ * Pixels are arranged in Groups of Bytes (GOBs).  GOB size and layout varies
+ * based on the architecture generation.  GOBs themselves are then arranged in
+ * 3D blocks, with the block dimensions (in terms of GOBs) always being a power
+ * of two, and hence expressible as their log2 equivalent (E.g., "2" represents
+ * a block depth or height of "4").
+ *
+ * Chapter 20 "Pixel Memory Formats" of the Tegra X1 TRM describes this format
+ * in full detail.
+ *
+ *       Macro
+ * Bits  Param Description
+ * ----  ----- -----------------------------------------------------------------
+ *
+ *  3:0  h     log2(height) of each block, in GOBs.  Placed here for
+ *             compatibility with the existing
+ *             DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK()-based modifiers.
+ *
+ *  4:4  -     Must be 1, to indicate block-linear layout.  Necessary for
+ *             compatibility with the existing
+ *             DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK()-based modifiers.
+ *
+ *  8:5  -     Reserved (To support 3D-surfaces with variable log2(depth) block
+ *             size).  Must be zero.
+ *
+ *             Note there is no log2(width) parameter.  Some portions of the
+ *             hardware support a block width of two gobs, but it is impractical
+ *             to use due to lack of support elsewhere, and has no known
+ *             benefits.
+ *
+ * 11:9  -     Reserved (To support 2D-array textures with variable array stride
+ *             in blocks, specified via log2(tile width in blocks)).  Must be
+ *             zero.
+ *
+ * 19:12 k     Page Kind.  This value directly maps to a field in the page
+ *             tables of all GPUs >= NV50.  It affects the exact layout of bits
+ *             in memory and can be derived from the tuple
+ *
+ *               (format, GPU model, compression type, samples per pixel)
+ *
+ *             Where compression type is defined below.  If GPU model were
+ *             implied by the format modifier, format, or memory buffer, page
+ *             kind would not need to be included in the modifier itself, but
+ *             since the modifier should define the layout of the associated
+ *             memory buffer independent from any device or other context, it
+ *             must be included here.
+ *
+ * 21:20 g     GOB Height and Page Kind Generation.  The height of a GOB changed
+ *             starting with Fermi GPUs.  Additionally, the mapping between page
+ *             kind and bit layout has changed at various points.
+ *
+ *               0 = Gob Height 8, Fermi - Volta, Tegra K1+ Page Kind mapping
+ *               1 = Gob Height 4, G80 - GT2XX Page Kind mapping
+ *               2 = Gob Height 8, Turing+ Page Kind mapping
+ *               3 = Reserved for future use.
+ *
+ * 22:22 s     Sector layout.  There is a further bit remapping step that occurs
+ * 26:27       at an even lower level than the page kind and block linear
+ *             swizzles.  This causes the bit arrangement of surfaces in memory
+ *             to differ subtly, and prevents direct sharing of surfaces between
+ *             GPUs with different layouts.
+ *
+ *               0 = Tegra K1 - Tegra Parker/TX2 Layout
+ *               1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout
+ *               2 = GB20x(Blackwell 2)+ 8 bpp surface layout
+ *               3 = GB20x(Blackwell 2)+ 16 bpp surface layout
+ *               4 = Reserved for future use.
+ *               5 = Reserved for future use.
+ *               6 = Reserved for future use.
+ *               7 = Reserved for future use.
+ *
+ * 25:23 c     Lossless Framebuffer Compression type.
+ *
+ *               0 = none
+ *               1 = ROP/3D, layout 1, exact compression format implied by Page
+ *                   Kind field
+ *               2 = ROP/3D, layout 2, exact compression format implied by Page
+ *                   Kind field
+ *               3 = CDE horizontal
+ *               4 = CDE vertical
+ *               5 = Reserved for future use
+ *               6 = Reserved for future use
+ *               7 = Reserved for future use
+ *
+ * 55:28 -     Reserved for future use.  Must be zero.
+ */
+#define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \
+	fourcc_mod_code(NVIDIA, (0x10 | \
+				 ((h) & 0xf) | \
+				 (((k) & 0xff) << 12) | \
+				 (((g) & 0x3) << 20) | \
+				 (((s) & 0x1) << 22) | \
+				 (((s) & 0x6) << 25) | \
+				 (((c) & 0x7) << 23)))
+
+/* To grandfather in prior block linear format modifiers to the above layout,
+ * the page kind "0", which corresponds to "pitch/linear" and hence is unusable
+ * with block-linear layouts, is remapped within drivers to the value 0xfe,
+ * which corresponds to the "generic" kind used for simple single-sample
+ * uncompressed color formats on Fermi - Volta GPUs.
+ */
+static inline __u64
+drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
+{
+	if (!(modifier & 0x10) || (modifier & (0xff << 12)))
+		return modifier;
+	else
+		return modifier | (0xfe << 12);
+}
+
+/*
+ * 16Bx2 Block Linear layout, used by Tegra K1 and later
+ *
+ * Pixels are arranged in 64x8 Groups Of Bytes (GOBs). GOBs are then stacked
+ * vertically by a power of 2 (1 to 32 GOBs) to form a block.
+ *
+ * Within a GOB, data is ordered as 16B x 2 lines sectors laid in Z-shape.
+ *
+ * Parameter 'v' is the log2 encoding of the number of GOBs stacked vertically.
+ * Valid values are:
+ *
+ * 0 == ONE_GOB
+ * 1 == TWO_GOBS
+ * 2 == FOUR_GOBS
+ * 3 == EIGHT_GOBS
+ * 4 == SIXTEEN_GOBS
+ * 5 == THIRTYTWO_GOBS
+ *
+ * Chapter 20 "Pixel Memory Formats" of the Tegra X1 TRM describes this format
+ * in full detail.
+ */
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(v) \
+	DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(0, 0, 0, 0, (v))
+
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_ONE_GOB \
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(0)
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_TWO_GOB \
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(1)
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_FOUR_GOB \
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(2)
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_EIGHT_GOB \
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(3)
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_SIXTEEN_GOB \
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(4)
+#define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_THIRTYTWO_GOB \
+	DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK(5)
+
+/*
+ * Some Broadcom modifiers take parameters, for example the number of
+ * vertical lines in the image. Reserve the lower 32 bits for modifier
+ * type, and the next 24 bits for parameters. Top 8 bits are the
+ * vendor code.
+ */
+#define __fourcc_mod_broadcom_param_shift 8
+#define __fourcc_mod_broadcom_param_bits 48
+#define fourcc_mod_broadcom_code(val, params) \
+	fourcc_mod_code(BROADCOM, ((((__u64)params) << __fourcc_mod_broadcom_param_shift) | val))
+#define fourcc_mod_broadcom_param(m) \
+	((int)(((m) >> __fourcc_mod_broadcom_param_shift) &	\
+	       ((1ULL << __fourcc_mod_broadcom_param_bits) - 1)))
+#define fourcc_mod_broadcom_mod(m) \
+	((m) & ~(((1ULL << __fourcc_mod_broadcom_param_bits) - 1) <<	\
+		 __fourcc_mod_broadcom_param_shift))
+
+/*
+ * Broadcom VC4 "T" format
+ *
+ * This is the primary layout that the V3D GPU can texture from (it
+ * can't do linear).  The T format has:
+ *
+ * - 64b utiles of pixels in a raster-order grid according to cpp.  It's 4x4
+ *   pixels at 32 bit depth.
+ *
+ * - 1k subtiles made of a 4x4 raster-order grid of 64b utiles (so usually
+ *   16x16 pixels).
+ *
+ * - 4k tiles made of a 2x2 grid of 1k subtiles (so usually 32x32 pixels).  On
+ *   even 4k tile rows, they're arranged as (BL, TL, TR, BR), and on odd rows
+ *   they're (TR, BR, BL, TL), where bottom left is start of memory.
+ *
+ * - an image made of 4k tiles in rows either left-to-right (even rows of 4k
+ *   tiles) or right-to-left (odd rows of 4k tiles).
+ */
+#define DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED fourcc_mod_code(BROADCOM, 1)
+
+/*
+ * Broadcom SAND format
+ *
+ * This is the native format that the H.264 codec block uses.  For VC4
+ * HVS, it is only valid for H.264 (NV12/21) and RGBA modes.
+ *
+ * The image can be considered to be split into columns, and the
+ * columns are placed consecutively into memory.  The width of those
+ * columns can be either 32, 64, 128, or 256 pixels, but in practice
+ * only 128 pixel columns are used.
+ *
+ * The pitch between the start of each column is set to optimally
+ * switch between SDRAM banks. This is passed as the number of lines
+ * of column width in the modifier (we can't use the stride value due
+ * to various core checks that look at it , so you should set the
+ * stride to width*cpp).
+ *
+ * Note that the column height for this format modifier is the same
+ * for all of the planes, assuming that each column contains both Y
+ * and UV.  Some SAND-using hardware stores UV in a separate tiled
+ * image from Y to reduce the column height, which is not supported
+ * with these modifiers.
+ *
+ * The DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT modifier is also
+ * supported for DRM_FORMAT_P030 where the columns remain as 128 bytes
+ * wide, but as this is a 10 bpp format that translates to 96 pixels.
+ */
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(2, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(3, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(4, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(5, v)
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32 \
+	DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64 \
+	DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128 \
+	DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256 \
+	DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0)
+
+/* Broadcom UIF format
+ *
+ * This is the common format for the current Broadcom multimedia
+ * blocks, including V3D 3.x and newer, newer video codecs, and
+ * displays.
+ *
+ * The image consists of utiles (64b blocks), UIF blocks (2x2 utiles),
+ * and macroblocks (4x4 UIF blocks).  Those 4x4 UIF block groups are
+ * stored in columns, with padding between the columns to ensure that
+ * moving from one column to the next doesn't hit the same SDRAM page
+ * bank.
+ *
+ * To calculate the padding, it is assumed that each hardware block
+ * and the software driving it knows the platform's SDRAM page size,
+ * number of banks, and XOR address, and that it's identical between
+ * all blocks using the format.  This tiling modifier will use XOR as
+ * necessary to reduce the padding.  If a hardware block can't do XOR,
+ * the assumption is that a no-XOR tiling modifier will be created.
+ */
+#define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6)
+
+/*
+ * Arm Framebuffer Compression (AFBC) modifiers
+ *
+ * AFBC is a proprietary lossless image compression protocol and format.
+ * It provides fine-grained random access and minimizes the amount of data
+ * transferred between IP blocks.
+ *
+ * AFBC has several features which may be supported and/or used, which are
+ * represented using bits in the modifier. Not all combinations are valid,
+ * and different devices or use-cases may support different combinations.
+ *
+ * Further information on the use of AFBC modifiers can be found in
+ * Documentation/gpu/afbc.rst
+ */
+
+/*
+ * The top 4 bits (out of the 56 bits allotted for specifying vendor specific
+ * modifiers) denote the category for modifiers. Currently we have three
+ * categories of modifiers ie AFBC, MISC and AFRC. We can have a maximum of
+ * sixteen different categories.
+ */
+#define DRM_FORMAT_MOD_ARM_CODE(__type, __val) \
+	fourcc_mod_code(ARM, ((__u64)(__type) << 52) | ((__val) & 0x000fffffffffffffULL))
+
+#define DRM_FORMAT_MOD_ARM_TYPE_AFBC 0x00
+#define DRM_FORMAT_MOD_ARM_TYPE_MISC 0x01
+
+#define DRM_FORMAT_MOD_ARM_AFBC(__afbc_mode) \
+	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_AFBC, __afbc_mode)
+
+/*
+ * AFBC superblock size
+ *
+ * Indicates the superblock size(s) used for the AFBC buffer. The buffer
+ * size (in pixels) must be aligned to a multiple of the superblock size.
+ * Four lowest significant bits(LSBs) are reserved for block size.
+ *
+ * Where one superblock size is specified, it applies to all planes of the
+ * buffer (e.g. 16x16, 32x8). When multiple superblock sizes are specified,
+ * the first applies to the Luma plane and the second applies to the Chroma
+ * plane(s). e.g. (32x8_64x4 means 32x8 Luma, with 64x4 Chroma).
+ * Multiple superblock sizes are only valid for multi-plane YCbCr formats.
+ */
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_MASK      0xf
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_16x16     (1ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8      (2ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_64x4      (3ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8_64x4 (4ULL)
+
+/*
+ * AFBC lossless colorspace transform
+ *
+ * Indicates that the buffer makes use of the AFBC lossless colorspace
+ * transform.
+ */
+#define AFBC_FORMAT_MOD_YTR     (1ULL <<  4)
+
+/*
+ * AFBC block-split
+ *
+ * Indicates that the payload of each superblock is split. The second
+ * half of the payload is positioned at a predefined offset from the start
+ * of the superblock payload.
+ */
+#define AFBC_FORMAT_MOD_SPLIT   (1ULL <<  5)
+
+/*
+ * AFBC sparse layout
+ *
+ * This flag indicates that the payload of each superblock must be stored at a
+ * predefined position relative to the other superblocks in the same AFBC
+ * buffer. This order is the same order used by the header buffer. In this mode
+ * each superblock is given the same amount of space as an uncompressed
+ * superblock of the particular format would require, rounding up to the next
+ * multiple of 128 bytes in size.
+ */
+#define AFBC_FORMAT_MOD_SPARSE  (1ULL <<  6)
+
+/*
+ * AFBC copy-block restrict
+ *
+ * Buffers with this flag must obey the copy-block restriction. The restriction
+ * is such that there are no copy-blocks referring across the border of 8x8
+ * blocks. For the subsampled data the 8x8 limitation is also subsampled.
+ */
+#define AFBC_FORMAT_MOD_CBR     (1ULL <<  7)
+
+/*
+ * AFBC tiled layout
+ *
+ * The tiled layout groups superblocks in 8x8 or 4x4 tiles, where all
+ * superblocks inside a tile are stored together in memory. 8x8 tiles are used
+ * for pixel formats up to and including 32 bpp while 4x4 tiles are used for
+ * larger bpp formats. The order between the tiles is scan line.
+ * When the tiled layout is used, the buffer size (in pixels) must be aligned
+ * to the tile size.
+ */
+#define AFBC_FORMAT_MOD_TILED   (1ULL <<  8)
+
+/*
+ * AFBC solid color blocks
+ *
+ * Indicates that the buffer makes use of solid-color blocks, whereby bandwidth
+ * can be reduced if a whole superblock is a single color.
+ */
+#define AFBC_FORMAT_MOD_SC      (1ULL <<  9)
+
+/*
+ * AFBC double-buffer
+ *
+ * Indicates that the buffer is allocated in a layout safe for front-buffer
+ * rendering.
+ */
+#define AFBC_FORMAT_MOD_DB      (1ULL << 10)
+
+/*
+ * AFBC buffer content hints
+ *
+ * Indicates that the buffer includes per-superblock content hints.
+ */
+#define AFBC_FORMAT_MOD_BCH     (1ULL << 11)
+
+/* AFBC uncompressed storage mode
+ *
+ * Indicates that the buffer is using AFBC uncompressed storage mode.
+ * In this mode all superblock payloads in the buffer use the uncompressed
+ * storage mode, which is usually only used for data which cannot be compressed.
+ * The buffer layout is the same as for AFBC buffers without USM set, this only
+ * affects the storage mode of the individual superblocks. Note that even a
+ * buffer without USM set may use uncompressed storage mode for some or all
+ * superblocks, USM just guarantees it for all.
+ */
+#define AFBC_FORMAT_MOD_USM	(1ULL << 12)
+
+/*
+ * Arm Fixed-Rate Compression (AFRC) modifiers
+ *
+ * AFRC is a proprietary fixed rate image compression protocol and format,
+ * designed to provide guaranteed bandwidth and memory footprint
+ * reductions in graphics and media use-cases.
+ *
+ * AFRC buffers consist of one or more planes, with the same components
+ * and meaning as an uncompressed buffer using the same pixel format.
+ *
+ * Within each plane, the pixel/luma/chroma values are grouped into
+ * "coding unit" blocks which are individually compressed to a
+ * fixed size (in bytes). All coding units within a given plane of a buffer
+ * store the same number of values, and have the same compressed size.
+ *
+ * The coding unit size is configurable, allowing different rates of compression.
+ *
+ * The start of each AFRC buffer plane must be aligned to an alignment granule which
+ * depends on the coding unit size.
+ *
+ * Coding Unit Size   Plane Alignment
+ * ----------------   ---------------
+ * 16 bytes           1024 bytes
+ * 24 bytes           512  bytes
+ * 32 bytes           2048 bytes
+ *
+ * Coding units are grouped into paging tiles. AFRC buffer dimensions must be aligned
+ * to a multiple of the paging tile dimensions.
+ * The dimensions of each paging tile depend on whether the buffer is optimised for
+ * scanline (SCAN layout) or rotated (ROT layout) access.
+ *
+ * Layout   Paging Tile Width   Paging Tile Height
+ * ------   -----------------   ------------------
+ * SCAN     16 coding units     4 coding units
+ * ROT      8  coding units     8 coding units
+ *
+ * The dimensions of each coding unit depend on the number of components
+ * in the compressed plane and whether the buffer is optimised for
+ * scanline (SCAN layout) or rotated (ROT layout) access.
+ *
+ * Number of Components in Plane   Layout      Coding Unit Width   Coding Unit Height
+ * -----------------------------   ---------   -----------------   ------------------
+ * 1                               SCAN        16 samples          4 samples
+ * Example: 16x4 luma samples in a 'Y' plane
+ *          16x4 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer
+ * -----------------------------   ---------   -----------------   ------------------
+ * 1                               ROT         8 samples           8 samples
+ * Example: 8x8 luma samples in a 'Y' plane
+ *          8x8 chroma 'V' values, in the 'V' plane of a fully-planar YUV buffer
+ * -----------------------------   ---------   -----------------   ------------------
+ * 2                               DONT CARE   8 samples           4 samples
+ * Example: 8x4 chroma pairs in the 'UV' plane of a semi-planar YUV buffer
+ * -----------------------------   ---------   -----------------   ------------------
+ * 3                               DONT CARE   4 samples           4 samples
+ * Example: 4x4 pixels in an RGB buffer without alpha
+ * -----------------------------   ---------   -----------------   ------------------
+ * 4                               DONT CARE   4 samples           4 samples
+ * Example: 4x4 pixels in an RGB buffer with alpha
+ */
+
+#define DRM_FORMAT_MOD_ARM_TYPE_AFRC 0x02
+
+#define DRM_FORMAT_MOD_ARM_AFRC(__afrc_mode) \
+	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_AFRC, __afrc_mode)
+
+/*
+ * AFRC coding unit size modifier.
+ *
+ * Indicates the number of bytes used to store each compressed coding unit for
+ * one or more planes in an AFRC encoded buffer. The coding unit size for chrominance
+ * is the same for both Cb and Cr, which may be stored in separate planes.
+ *
+ * AFRC_FORMAT_MOD_CU_SIZE_P0 indicates the number of bytes used to store
+ * each compressed coding unit in the first plane of the buffer. For RGBA buffers
+ * this is the only plane, while for semi-planar and fully-planar YUV buffers,
+ * this corresponds to the luma plane.
+ *
+ * AFRC_FORMAT_MOD_CU_SIZE_P12 indicates the number of bytes used to store
+ * each compressed coding unit in the second and third planes in the buffer.
+ * For semi-planar and fully-planar YUV buffers, this corresponds to the chroma plane(s).
+ *
+ * For single-plane buffers, AFRC_FORMAT_MOD_CU_SIZE_P0 must be specified
+ * and AFRC_FORMAT_MOD_CU_SIZE_P12 must be zero.
+ * For semi-planar and fully-planar buffers, both AFRC_FORMAT_MOD_CU_SIZE_P0 and
+ * AFRC_FORMAT_MOD_CU_SIZE_P12 must be specified.
+ */
+#define AFRC_FORMAT_MOD_CU_SIZE_MASK 0xf
+#define AFRC_FORMAT_MOD_CU_SIZE_16 (1ULL)
+#define AFRC_FORMAT_MOD_CU_SIZE_24 (2ULL)
+#define AFRC_FORMAT_MOD_CU_SIZE_32 (3ULL)
+
+#define AFRC_FORMAT_MOD_CU_SIZE_P0(__afrc_cu_size) (__afrc_cu_size)
+#define AFRC_FORMAT_MOD_CU_SIZE_P12(__afrc_cu_size) ((__afrc_cu_size) << 4)
+
+/*
+ * AFRC scanline memory layout.
+ *
+ * Indicates if the buffer uses the scanline-optimised layout
+ * for an AFRC encoded buffer, otherwise, it uses the rotation-optimised layout.
+ * The memory layout is the same for all planes.
+ */
+#define AFRC_FORMAT_MOD_LAYOUT_SCAN (1ULL << 8)
+
+/*
+ * Arm 16x16 Block U-Interleaved modifier
+ *
+ * This is used by Arm Mali Utgard and Midgard GPUs. It divides the image
+ * into 16x16 pixel blocks. Blocks are stored linearly in order, but pixels
+ * in the block are reordered.
+ */
+#define DRM_FORMAT_MOD_ARM_16X16_BLOCK_U_INTERLEAVED \
+	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_MISC, 1ULL)
+
+/*
+ * ARM 64k interleaved modifier
+ *
+ * This is used by ARM Mali v10+ GPUs. With this modifier, the plane is divided
+ * into 64k byte 1:1 or 2:1 -sided tiles. The 64k tiles are laid out linearly.
+ * Each 64k tile is divided into blocks of 16x16 texel blocks, which are
+ * themselves laid out linearly within a 64k tile. Then within each 16x16
+ * block, texel blocks are laid out according to U order, similar to
+ * 16X16_BLOCK_U_INTERLEAVED.
+ *
+ * Note that unlike 16X16_BLOCK_U_INTERLEAVED, the layout does not change
+ * depending on whether a format is compressed or not.
+ */
+#define DRM_FORMAT_MOD_ARM_INTERLEAVED_64K \
+	DRM_FORMAT_MOD_ARM_CODE(DRM_FORMAT_MOD_ARM_TYPE_MISC, 2ULL)
+
+/*
+ * Allwinner tiled modifier
+ *
+ * This tiling mode is implemented by the VPU found on all Allwinner platforms,
+ * codenamed sunxi. It is associated with a YUV format that uses either 2 or 3
+ * planes.
+ *
+ * With this tiling, the luminance samples are disposed in tiles representing
+ * 32x32 pixels and the chrominance samples in tiles representing 32x64 pixels.
+ * The pixel order in each tile is linear and the tiles are disposed linearly,
+ * both in row-major order.
+ */
+#define DRM_FORMAT_MOD_ALLWINNER_TILED fourcc_mod_code(ALLWINNER, 1)
+
+/*
+ * Amlogic Video Framebuffer Compression modifiers
+ *
+ * Amlogic uses a proprietary lossless image compression protocol and format
+ * for their hardware video codec accelerators, either video decoders or
+ * video input encoders.
+ *
+ * It considerably reduces memory bandwidth while writing and reading
+ * frames in memory.
+ *
+ * The underlying storage is considered to be 3 components, 8bit or 10-bit
+ * per component YCbCr 420, single plane :
+ * - DRM_FORMAT_YUV420_8BIT
+ * - DRM_FORMAT_YUV420_10BIT
+ *
+ * The first 8 bits of the mode defines the layout, then the following 8 bits
+ * defines the options changing the layout.
+ *
+ * Not all combinations are valid, and different SoCs may support different
+ * combinations of layout and options.
+ */
+#define __fourcc_mod_amlogic_layout_mask 0xff
+#define __fourcc_mod_amlogic_options_shift 8
+#define __fourcc_mod_amlogic_options_mask 0xff
+
+#define DRM_FORMAT_MOD_AMLOGIC_FBC(__layout, __options) \
+	fourcc_mod_code(AMLOGIC, \
+			((__layout) & __fourcc_mod_amlogic_layout_mask) | \
+			(((__options) & __fourcc_mod_amlogic_options_mask) \
+			 << __fourcc_mod_amlogic_options_shift))
+
+/* Amlogic FBC Layouts */
+
+/*
+ * Amlogic FBC Basic Layout
+ *
+ * The basic layout is composed of:
+ * - a body content organized in 64x32 superblocks with 4096 bytes per
+ *   superblock in default mode.
+ * - a 32 bytes per 128x64 header block
+ *
+ * This layout is transferrable between Amlogic SoCs supporting this modifier.
+ */
+#define AMLOGIC_FBC_LAYOUT_BASIC		(1ULL)
+
+/*
+ * Amlogic FBC Scatter Memory layout
+ *
+ * Indicates the header contains IOMMU references to the compressed
+ * frames content to optimize memory access and layout.
+ *
+ * In this mode, only the header memory address is needed, thus the
+ * content memory organization is tied to the current producer
+ * execution and cannot be saved/dumped neither transferrable between
+ * Amlogic SoCs supporting this modifier.
+ *
+ * Due to the nature of the layout, these buffers are not expected to
+ * be accessible by the user-space clients, but only accessible by the
+ * hardware producers and consumers.
+ *
+ * The user-space clients should expect a failure while trying to mmap
+ * the DMA-BUF handle returned by the producer.
+ */
+#define AMLOGIC_FBC_LAYOUT_SCATTER		(2ULL)
+
+/* Amlogic FBC Layout Options Bit Mask */
+
+/*
+ * Amlogic FBC Memory Saving mode
+ *
+ * Indicates the storage is packed when pixel size is multiple of word
+ * boundaries, i.e. 8bit should be stored in this mode to save allocation
+ * memory.
+ *
+ * This mode reduces body layout to 3072 bytes per 64x32 superblock with
+ * the basic layout and 3200 bytes per 64x32 superblock combined with
+ * the scatter layout.
+ */
+#define AMLOGIC_FBC_OPTION_MEM_SAVING		(1ULL << 0)
+
+/* MediaTek modifiers
+ * Bits  Parameter                Notes
+ * ----- ------------------------ ---------------------------------------------
+ *   7: 0 TILE LAYOUT              Values are MTK_FMT_MOD_TILE_*
+ *  15: 8 COMPRESSION              Values are MTK_FMT_MOD_COMPRESS_*
+ *  23:16 10 BIT LAYOUT            Values are MTK_FMT_MOD_10BIT_LAYOUT_*
+ *
+ */
+
+#define DRM_FORMAT_MOD_MTK(__flags)		fourcc_mod_code(MTK, __flags)
+
+/*
+ * MediaTek Tiled Modifier
+ * The lowest 8 bits of the modifier is used to specify the tiling
+ * layout. Only the 16L_32S tiling is used for now, but we define an
+ * "untiled" version and leave room for future expansion.
+ */
+#define MTK_FMT_MOD_TILE_MASK     0xf
+#define MTK_FMT_MOD_TILE_NONE     0x0
+#define MTK_FMT_MOD_TILE_16L32S   0x1
+
+/*
+ * Bits 8-15 specify compression options
+ */
+#define MTK_FMT_MOD_COMPRESS_MASK (0xf << 8)
+#define MTK_FMT_MOD_COMPRESS_NONE (0x0 << 8)
+#define MTK_FMT_MOD_COMPRESS_V1   (0x1 << 8)
+
+/*
+ * Bits 16-23 specify how the bits of 10 bit formats are
+ * stored out in memory
+ */
+#define MTK_FMT_MOD_10BIT_LAYOUT_MASK      (0xf << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_PACKED    (0x0 << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_LSBTILED  (0x1 << 16)
+#define MTK_FMT_MOD_10BIT_LAYOUT_LSBRASTER (0x2 << 16)
+
+/* alias for the most common tiling format */
+#define DRM_FORMAT_MOD_MTK_16L_32S_TILE  DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S)
+
+/*
+ * Apple GPU-tiled layouts.
+ *
+ * Apple GPUs support nonlinear tilings with optional lossless compression.
+ *
+ * GPU-tiled images are divided into 16KiB tiles:
+ *
+ *     Bytes per pixel  Tile size
+ *     ---------------  ---------
+ *                   1  128x128
+ *                   2  128x64
+ *                   4  64x64
+ *                   8  64x32
+ *                  16  32x32
+ *
+ * Tiles are raster-order. Pixels within a tile are interleaved (Morton order).
+ *
+ * Compressed images pad the body to 128-bytes and are immediately followed by a
+ * metadata section. The metadata section rounds the image dimensions to
+ * powers-of-two and contains 8 bytes for each 16x16 compression subtile.
+ * Subtiles are interleaved (Morton order).
+ *
+ * All images are 128-byte aligned.
+ *
+ * These layouts fundamentally do not have meaningful strides. No matter how we
+ * specify strides for these layouts, userspace unaware of Apple image layouts
+ * will be unable to use correctly the specified stride for any purpose.
+ * Userspace aware of the image layouts do not use strides. The most "correct"
+ * convention would be setting the image stride to 0. Unfortunately, some
+ * software assumes the stride is at least (width * bytes per pixel). We
+ * therefore require that stride equals (width * bytes per pixel). Since the
+ * stride is arbitrary here, we pick the simplest convention.
+ *
+ * Although containing two sections, compressed image layouts are treated in
+ * software as a single plane. This is modelled after AFBC, a similar
+ * scheme. Attempting to separate the sections to be "explicit" in DRM would
+ * only generate more confusion, as software does not treat the image this way.
+ *
+ * For detailed information on the hardware image layouts, see
+ * https://docs.mesa3d.org/drivers/asahi.html#image-layouts
+ */
+#define DRM_FORMAT_MOD_APPLE_GPU_TILED fourcc_mod_code(APPLE, 1)
+#define DRM_FORMAT_MOD_APPLE_GPU_TILED_COMPRESSED fourcc_mod_code(APPLE, 2)
+
+/*
+ * AMD modifiers
+ *
+ * Memory layout:
+ *
+ * without DCC:
+ *   - main surface
+ *
+ * with DCC & without DCC_RETILE:
+ *   - main surface in plane 0
+ *   - DCC surface in plane 1 (RB-aligned, pipe-aligned if DCC_PIPE_ALIGN is set)
+ *
+ * with DCC & DCC_RETILE:
+ *   - main surface in plane 0
+ *   - displayable DCC surface in plane 1 (not RB-aligned & not pipe-aligned)
+ *   - pipe-aligned DCC surface in plane 2 (RB-aligned & pipe-aligned)
+ *
+ * For multi-plane formats the above surfaces get merged into one plane for
+ * each format plane, based on the required alignment only.
+ *
+ * Bits    Parameter                Notes
+ * ------- ------------------------ ---------------------------------------------
+ *
+ * DRM format modifier fields on AMD GPUs:
+ *     7:0 TILE_VERSION             Values are AMD_FMT_MOD_TILE_VER_*
+ *    12:8 TILE                     Values are AMD_FMT_MOD_TILE_<version>_*
+ *      13 DCC                      Delta Color Compression, supported on GFX8 and newer
+ *   55:14 (chip specific)          See below for details, depends on GFX block version
+ *   63:56 Vendor                   Value is DRM_FORMAT_MOD_VENDOR_AMD
+ *
+ * Chip specific fields on Gfx9 and newer:
+ *      14 DCC_RETILE
+ *      15 DCC_PIPE_ALIGN
+ *      16 DCC_INDEPENDENT_64B
+ *      17 DCC_INDEPENDENT_128B
+ *   19:18 DCC_MAX_COMPRESSED_BLOCK Values are AMD_FMT_MOD_DCC_BLOCK_*
+ *      20 DCC_CONSTANT_ENCODE
+ *   23:21 PIPE_XOR_BITS            Only for some chips
+ *   26:24 BANK_XOR_BITS            Only for some chips
+ *   29:27 PACKERS                  Only for some chips
+ *   32:30 RB                       Only for some chips
+ *   35:33 PIPE                     Only for some chips
+ *   55:36 -                        Reserved for future use, must be zero
+ *
+ * Chip specific fields on Gfx6-8:
+ *   16:14 MICROTILE                Micro tile format
+ *   21:17 PIPE_CONFIG              Number of pipes and how pipes are interleaved
+ *   24:22 TILE_SPLIT               Tile split size
+ *   26:25 BANK_WIDTH               Number of tiles in the X direction in the same bank
+ *   28:27 BANK_HEIGHT              Number of tiles in the Y direction in the same bank
+ *   30:29 MACRO_TILE_ASPECT        Macro tile aspect ratio
+ *   32:31 NUM_BANKS                Number of banks
+ *   55:33 -                        Reserved for future use, must be zero
+ *
+ */
+#define AMD_FMT_MOD fourcc_mod_code(AMD, 0)
+
+#define IS_AMD_FMT_MOD(val) (((val) >> 56) == DRM_FORMAT_MOD_VENDOR_AMD)
+
+#define AMD_FMT_MOD_TILE_VER_GFX6 0
+#define AMD_FMT_MOD_TILE_VER_GFX9 1
+#define AMD_FMT_MOD_TILE_VER_GFX10 2
+#define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3
+#define AMD_FMT_MOD_TILE_VER_GFX11 4
+#define AMD_FMT_MOD_TILE_VER_GFX12 5
+
+/*
+ * Gfx6-8 tiling modes.
+ * A complete reference implementation is found in addrlib in the Mesa code base.
+ *
+ * - Microtiled modes (1D):
+ *   Pixel data is organized into micro tiles of 8x8 pixels.
+ *
+ * - Macrotiled modes (2D):
+ *   Micro tiles are further organized into macro tiles.
+ *   These are optimized for even load distribution among memory channels.
+ *
+ * Note that only THIN1 modes are exposed here.
+ * THICK and XTHICK are for 3D images and not relevant to DRM format modifiers.
+ */
+#define AMD_FMT_MOD_TILE_GFX6_1D_TILED_THIN1 0x2
+#define AMD_FMT_MOD_TILE_GFX6_2D_TILED_THIN1 0x4
+
+/*
+ * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical
+ * version.
+ */
+#define AMD_FMT_MOD_TILE_GFX9_64K_S 9
+
+/*
+ * 64K_D for non-32 bpp is the same for GFX9/GFX10/GFX10_RBPLUS and hence has
+ * GFX9 as canonical version.
+ *
+ * 64K_D_2D on GFX12 is identical to 64K_D on GFX11.
+ */
+#define AMD_FMT_MOD_TILE_GFX9_64K_D 10
+#define AMD_FMT_MOD_TILE_GFX9_4K_D_X 22
+#define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25
+#define AMD_FMT_MOD_TILE_GFX9_64K_D_X 26
+#define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27
+#define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31
+
+/* Gfx12 swizzle modes:
+ *    0 - LINEAR
+ *    1 - 256B_2D  - 2D block dimensions
+ *    2 - 4KB_2D
+ *    3 - 64KB_2D
+ *    4 - 256KB_2D
+ *    5 - 4KB_3D   - 3D block dimensions
+ *    6 - 64KB_3D
+ *    7 - 256KB_3D
+ */
+#define AMD_FMT_MOD_TILE_GFX12_256B_2D 1
+#define AMD_FMT_MOD_TILE_GFX12_4K_2D 2
+#define AMD_FMT_MOD_TILE_GFX12_64K_2D 3
+#define AMD_FMT_MOD_TILE_GFX12_256K_2D 4
+
+#define AMD_FMT_MOD_DCC_BLOCK_64B 0
+#define AMD_FMT_MOD_DCC_BLOCK_128B 1
+#define AMD_FMT_MOD_DCC_BLOCK_256B 2
+
+#define AMD_FMT_MOD_TILE_VERSION_SHIFT 0
+#define AMD_FMT_MOD_TILE_VERSION_MASK 0xFF
+#define AMD_FMT_MOD_TILE_SHIFT 8
+#define AMD_FMT_MOD_TILE_MASK 0x1F
+
+/* Whether DCC compression is enabled. */
+#define AMD_FMT_MOD_DCC_SHIFT 13
+#define AMD_FMT_MOD_DCC_MASK 0x1
+
+/*
+ * Whether to include two DCC surfaces, one which is rb & pipe aligned, and
+ * one which is not-aligned.
+ */
+#define AMD_FMT_MOD_DCC_RETILE_SHIFT 14
+#define AMD_FMT_MOD_DCC_RETILE_MASK 0x1
+
+/* Only set if DCC_RETILE = false */
+#define AMD_FMT_MOD_DCC_PIPE_ALIGN_SHIFT 15
+#define AMD_FMT_MOD_DCC_PIPE_ALIGN_MASK 0x1
+
+#define AMD_FMT_MOD_DCC_INDEPENDENT_64B_SHIFT 16
+#define AMD_FMT_MOD_DCC_INDEPENDENT_64B_MASK 0x1
+#define AMD_FMT_MOD_DCC_INDEPENDENT_128B_SHIFT 17
+#define AMD_FMT_MOD_DCC_INDEPENDENT_128B_MASK 0x1
+#define AMD_FMT_MOD_DCC_MAX_COMPRESSED_BLOCK_SHIFT 18
+#define AMD_FMT_MOD_DCC_MAX_COMPRESSED_BLOCK_MASK 0x3
+
+/*
+ * DCC supports embedding some clear colors directly in the DCC surface.
+ * However, on older GPUs the rendering HW ignores the embedded clear color
+ * and prefers the driver provided color. This necessitates doing a fastclear
+ * eliminate operation before a process transfers control.
+ *
+ * If this bit is set that means the fastclear eliminate is not needed for these
+ * embeddable colors.
+ */
+#define AMD_FMT_MOD_DCC_CONSTANT_ENCODE_SHIFT 20
+#define AMD_FMT_MOD_DCC_CONSTANT_ENCODE_MASK 0x1
+
+/*
+ * The below fields are for accounting for per GPU differences. These are only
+ * relevant for GFX9 and later and if the tile field is *_X/_T.
+ *
+ * PIPE_XOR_BITS = always needed
+ * BANK_XOR_BITS = only for TILE_VER_GFX9
+ * PACKERS = only for TILE_VER_GFX10_RBPLUS
+ * RB = only for TILE_VER_GFX9 & DCC
+ * PIPE = only for TILE_VER_GFX9 & DCC & (DCC_RETILE | DCC_PIPE_ALIGN)
+ */
+#define AMD_FMT_MOD_PIPE_XOR_BITS_SHIFT 21
+#define AMD_FMT_MOD_PIPE_XOR_BITS_MASK 0x7
+#define AMD_FMT_MOD_BANK_XOR_BITS_SHIFT 24
+#define AMD_FMT_MOD_BANK_XOR_BITS_MASK 0x7
+#define AMD_FMT_MOD_PACKERS_SHIFT 27
+#define AMD_FMT_MOD_PACKERS_MASK 0x7
+#define AMD_FMT_MOD_RB_SHIFT 30
+#define AMD_FMT_MOD_RB_MASK 0x7
+#define AMD_FMT_MOD_PIPE_SHIFT 33
+#define AMD_FMT_MOD_PIPE_MASK 0x7
+
+/*
+ * MICRO_TILE_MODE, 3 bits. Determines the micro tile format.
+ * Only relevant to Gfx6-8.
+ *
+ * DISPLAY - Displayable tiling
+ * THIN - Non-displayable tiling, a.k.a thin micro tiling
+ * DEPTH, THICK - not exposed, not relevant to DRM format modifier use cases
+ * ROTATED - not exposed, not implemented in Linux or Mesa
+ */
+#define AMD_FMT_MOD_MICROTILE_SHIFT 14ULL
+#define AMD_FMT_MOD_MICROTILE_MASK 0x7
+
+#define AMD_FMT_MOD_MICROTILE_DISPLAY 0x0
+#define AMD_FMT_MOD_MICROTILE_THIN 0x1
+
+/*
+ * PIPE_CONFIG, 5 bits. Number of pipes and how pipes are interleaved on the surface,
+ * which means the shader engine tile size and packer tile size.
+ * Typically matches the number of memory channels, or number of RBs.
+ * Only relevant to Gfx6-8 macro tiled modes.
+ *
+ * P<n>_<a>x<b>_<c>x<d>
+ * where:
+ * <n> - number of pipes
+ * <a>x<b> - shader engine tile size
+ * <c>x<d> - packer tile size
+ */
+#define AMD_FMT_MOD_PIPE_CONFIG_SHIFT 17ULL
+#define AMD_FMT_MOD_PIPE_CONFIG_MASK 0x1f
+
+#define AMD_FMT_MOD_PIPE_CONFIG_P2 0x0
+#define AMD_FMT_MOD_PIPE_CONFIG_P4_8x16 0x4
+#define AMD_FMT_MOD_PIPE_CONFIG_P4_16x16 0x5
+#define AMD_FMT_MOD_PIPE_CONFIG_P4_16x32 0x6
+#define AMD_FMT_MOD_PIPE_CONFIG_P4_32x32 0x7
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_16x16_8x16 0x8
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_16x32_8x16 0x9
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_32x32_8x16 0xa
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_16x32_16x16 0xb
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_32x32_16x16 0xc
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_32x32_16x32 0xd
+#define AMD_FMT_MOD_PIPE_CONFIG_P8_32x64_32x32 0xe
+#define AMD_FMT_MOD_PIPE_CONFIG_P16_32x32_8x16 0x10
+#define AMD_FMT_MOD_PIPE_CONFIG_P16_32x32_16x16 0x11
+
+/*
+ * TILE_SPLIT, 3 bits.
+ * Only relevant to Gfx6-8 macro tiled modes.
+ *
+ * On GFX6 (or with depth tiling modes on GFX7 and newer),
+ * the GFX block uses the GB_TILE_MODE.TILE_SPLIT field directly.
+ *
+ * On GFX7 and newer with non-depth tiling modes, the GFX block uses a
+ * split factor which is stored in the GB_TILE_MODE.SAMPLE_SPLIT field.
+ * SAMPLE_SPLIT may be: 0 - 1 byte; 1 - 2 bytes; 2 - 4 bytes; 3 - 8 bytes.
+ * The actual tile size and tile split bytes are calculated as follows:
+ *
+ *    bpp = ... <- bits per pixel in the current image
+ *    thickness = ... <- depends on array mode; may be: 1, 4, 8
+ *    num_samples = ... <- number of samples in the current image
+ *    tile_size_pixels = 8 * 8
+ *    tile_bytes_1x = thickness * tile_size_pixels * bpp / 8
+ *    sample_split_factor = 1 << SAMPLE_SPLIT
+ *    tile_split_bytes = clamp(tile_bytes_1x * sample_split_factor, 256, dram_row_size_bytes)
+ *    tile_bytes = clamp(tile_bytes_1x * num_samples, 64, tile_split_bytes)
+ *
+ * In both cases, the display block (DCE) has no SAMPLE_SPLIT
+ * and just needs the tile split bytes in the GRPH_CONTROL.GRPH_TILE_SPLIT field.
+ * To maximize compatibility between GFX6-7, we don't include the SAMPLE_SPLIT
+ * in the format modifiers.
+ *
+ * The actual tile split in bytes is: 64 << field value
+ * Possible values of this field:
+ *
+ * 0 - Tile split is 64 bytes
+ * 1 - Tile split is 128 bytes
+ * 2 - Tile split is 256 bytes
+ * 3 - Tile split is 512 bytes
+ * 4 - Tile split is 1 KiB
+ * 5 - Tile split is 2 KiB
+ * 6 - Tile split is 4 KiB
+ */
+#define AMD_FMT_MOD_TILE_SPLIT_SHIFT 22ULL
+#define AMD_FMT_MOD_TILE_SPLIT_MASK 0x7
+
+/*
+ * BANK_WIDTH, 2 bits. Number of tiles in the X direction in the same bank.
+ * Only relevant to Gfx6-8 macro tiled modes.
+ * The actual bank width is: 1 << field value
+ * Possible values:
+ *
+ * 0 - bank width is 1
+ * 1 - bank width is 2
+ * 2 - bank width is 4
+ * 3 - bank width is 8
+ */
+#define AMD_FMT_MOD_BANK_WIDTH_SHIFT 25ULL
+#define AMD_FMT_MOD_BANK_WIDTH_MASK 0x3
+
+/*
+ * BANK_HEIGHT, 2 bits. Number of tiles in the Y direction in the same bank.
+ * Only relevant to Gfx6-8 macro tiled modes.
+ * The actual bank height is: 1 << field value
+ * Possible values:
+ *
+ * 0 - bank height is 1
+ * 1 - bank height is 2
+ * 2 - bank height is 4
+ * 3 - bank height is 8
+ */
+#define AMD_FMT_MOD_BANK_HEIGHT_SHIFT 27ULL
+#define AMD_FMT_MOD_BANK_HEIGHT_MASK 0x3
+
+/*
+ * MACRO_TILE_ASPECT, 2 bits. Macro tile aspect ratio.
+ * Only relevant to Gfx6-8 macro tiled modes.
+ * Possible values:
+ *
+ * 0 - aspect ratio is 1:1
+ * 1 - aspect ratio is 4:1
+ * 2 - aspect ratio is 16:1
+ * 3 - aspect ratio is 64:1
+ */
+#define AMD_FMT_MOD_MACRO_TILE_ASPECT_SHIFT 29ULL
+#define AMD_FMT_MOD_MACRO_TILE_ASPECT_MASK 0x3
+
+/*
+ * NUM_BANKS, 2 bits. Number of banks.
+ * Only relevant to Gfx6-8 macro tiled modes.
+ * The actual number of banks is: 2 << field value
+ * Possible values:
+ *
+ * 0 - number of banks is 2
+ * 1 - number of banks is 4
+ * 2 - number of banks is 8
+ * 3 - number of banks is 16
+ */
+#define AMD_FMT_MOD_NUM_BANKS_SHIFT 31ULL
+#define AMD_FMT_MOD_NUM_BANKS_MASK 0x3
+
+#define AMD_FMT_MOD_SET(field, value) \
+	((__u64)(value) << AMD_FMT_MOD_##field##_SHIFT)
+#define AMD_FMT_MOD_GET(field, value) \
+	(((value) >> AMD_FMT_MOD_##field##_SHIFT) & AMD_FMT_MOD_##field##_MASK)
+#define AMD_FMT_MOD_CLEAR(field) \
+	(~((__u64)AMD_FMT_MOD_##field##_MASK << AMD_FMT_MOD_##field##_SHIFT))
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* DRM_FOURCC_H */
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
new file mode 100644
index 000000000..bd435effd
--- /dev/null
+++ b/include/uapi/drm/drm_mode.h
@@ -0,0 +1,1620 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright (c) 2007 Dave Airlie <airlied@linux.ie>
+ * Copyright (c) 2007 Jakob Bornecrantz <wallbraker@gmail.com>
+ * Copyright (c) 2008 Red Hat Inc.
+ * Copyright (c) 2007-2008 Tungsten Graphics, Inc., Cedar Park, TX., USA
+ * Copyright (c) 2007-2008 Intel Corporation
+ */
+
+#ifndef _DRM_MODE_H
+#define _DRM_MODE_H
+
+#include <linux/bits.h>
+#include <linux/const.h>
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * DOC: overview
+ *
+ * DRM exposes many UAPI and structure definitions to have a consistent
+ * and standardized interface with users.
+ * Userspace can refer to these structure definitions and UAPI formats
+ * to communicate to drivers.
+ */
+
+#define DRM_CONNECTOR_NAME_LEN	32
+#define DRM_DISPLAY_MODE_LEN	32
+#define DRM_PROP_NAME_LEN	32
+
+#define DRM_MODE_TYPE_BUILTIN	(1<<0) /* deprecated */
+#define DRM_MODE_TYPE_CLOCK_C	((1<<1) | DRM_MODE_TYPE_BUILTIN) /* deprecated */
+#define DRM_MODE_TYPE_CRTC_C	((1<<2) | DRM_MODE_TYPE_BUILTIN) /* deprecated */
+#define DRM_MODE_TYPE_PREFERRED	(1<<3)
+#define DRM_MODE_TYPE_DEFAULT	(1<<4) /* deprecated */
+#define DRM_MODE_TYPE_USERDEF	(1<<5)
+#define DRM_MODE_TYPE_DRIVER	(1<<6)
+
+#define DRM_MODE_TYPE_ALL	(DRM_MODE_TYPE_PREFERRED |	\
+				 DRM_MODE_TYPE_USERDEF |	\
+				 DRM_MODE_TYPE_DRIVER)
+
+/* Video mode flags */
+/* bit compatible with the xrandr RR_ definitions (bits 0-13)
+ *
+ * ABI warning: Existing userspace really expects
+ * the mode flags to match the xrandr definitions. Any
+ * changes that don't match the xrandr definitions will
+ * likely need a new client cap or some other mechanism
+ * to avoid breaking existing userspace. This includes
+ * allocating new flags in the previously unused bits!
+ */
+#define DRM_MODE_FLAG_PHSYNC			(1<<0)
+#define DRM_MODE_FLAG_NHSYNC			(1<<1)
+#define DRM_MODE_FLAG_PVSYNC			(1<<2)
+#define DRM_MODE_FLAG_NVSYNC			(1<<3)
+#define DRM_MODE_FLAG_INTERLACE			(1<<4)
+#define DRM_MODE_FLAG_DBLSCAN			(1<<5)
+#define DRM_MODE_FLAG_CSYNC			(1<<6)
+#define DRM_MODE_FLAG_PCSYNC			(1<<7)
+#define DRM_MODE_FLAG_NCSYNC			(1<<8)
+#define DRM_MODE_FLAG_HSKEW			(1<<9) /* hskew provided */
+#define DRM_MODE_FLAG_BCAST			(1<<10) /* deprecated */
+#define DRM_MODE_FLAG_PIXMUX			(1<<11) /* deprecated */
+#define DRM_MODE_FLAG_DBLCLK			(1<<12)
+#define DRM_MODE_FLAG_CLKDIV2			(1<<13)
+ /*
+  * When adding a new stereo mode don't forget to adjust DRM_MODE_FLAGS_3D_MAX
+  * (define not exposed to user space).
+  */
+#define DRM_MODE_FLAG_3D_MASK			(0x1f<<14)
+#define  DRM_MODE_FLAG_3D_NONE		(0<<14)
+#define  DRM_MODE_FLAG_3D_FRAME_PACKING		(1<<14)
+#define  DRM_MODE_FLAG_3D_FIELD_ALTERNATIVE	(2<<14)
+#define  DRM_MODE_FLAG_3D_LINE_ALTERNATIVE	(3<<14)
+#define  DRM_MODE_FLAG_3D_SIDE_BY_SIDE_FULL	(4<<14)
+#define  DRM_MODE_FLAG_3D_L_DEPTH		(5<<14)
+#define  DRM_MODE_FLAG_3D_L_DEPTH_GFX_GFX_DEPTH	(6<<14)
+#define  DRM_MODE_FLAG_3D_TOP_AND_BOTTOM	(7<<14)
+#define  DRM_MODE_FLAG_3D_SIDE_BY_SIDE_HALF	(8<<14)
+
+/* Picture aspect ratio options */
+#define DRM_MODE_PICTURE_ASPECT_NONE		0
+#define DRM_MODE_PICTURE_ASPECT_4_3		1
+#define DRM_MODE_PICTURE_ASPECT_16_9		2
+#define DRM_MODE_PICTURE_ASPECT_64_27		3
+#define DRM_MODE_PICTURE_ASPECT_256_135		4
+
+/* Content type options */
+#define DRM_MODE_CONTENT_TYPE_NO_DATA		0
+#define DRM_MODE_CONTENT_TYPE_GRAPHICS		1
+#define DRM_MODE_CONTENT_TYPE_PHOTO		2
+#define DRM_MODE_CONTENT_TYPE_CINEMA		3
+#define DRM_MODE_CONTENT_TYPE_GAME		4
+
+/* Aspect ratio flag bitmask (4 bits 22:19) */
+#define DRM_MODE_FLAG_PIC_AR_MASK		(0x0F<<19)
+#define  DRM_MODE_FLAG_PIC_AR_NONE \
+			(DRM_MODE_PICTURE_ASPECT_NONE<<19)
+#define  DRM_MODE_FLAG_PIC_AR_4_3 \
+			(DRM_MODE_PICTURE_ASPECT_4_3<<19)
+#define  DRM_MODE_FLAG_PIC_AR_16_9 \
+			(DRM_MODE_PICTURE_ASPECT_16_9<<19)
+#define  DRM_MODE_FLAG_PIC_AR_64_27 \
+			(DRM_MODE_PICTURE_ASPECT_64_27<<19)
+#define  DRM_MODE_FLAG_PIC_AR_256_135 \
+			(DRM_MODE_PICTURE_ASPECT_256_135<<19)
+
+#define  DRM_MODE_FLAG_ALL	(DRM_MODE_FLAG_PHSYNC |		\
+				 DRM_MODE_FLAG_NHSYNC |		\
+				 DRM_MODE_FLAG_PVSYNC |		\
+				 DRM_MODE_FLAG_NVSYNC |		\
+				 DRM_MODE_FLAG_INTERLACE |	\
+				 DRM_MODE_FLAG_DBLSCAN |	\
+				 DRM_MODE_FLAG_CSYNC |		\
+				 DRM_MODE_FLAG_PCSYNC |		\
+				 DRM_MODE_FLAG_NCSYNC |		\
+				 DRM_MODE_FLAG_HSKEW |		\
+				 DRM_MODE_FLAG_DBLCLK |		\
+				 DRM_MODE_FLAG_CLKDIV2 |	\
+				 DRM_MODE_FLAG_3D_MASK)
+
+/* DPMS flags */
+/* bit compatible with the xorg definitions. */
+#define DRM_MODE_DPMS_ON	0
+#define DRM_MODE_DPMS_STANDBY	1
+#define DRM_MODE_DPMS_SUSPEND	2
+#define DRM_MODE_DPMS_OFF	3
+
+/* Scaling mode options */
+#define DRM_MODE_SCALE_NONE		0 /* Unmodified timing (display or
+					     software can still scale) */
+#define DRM_MODE_SCALE_FULLSCREEN	1 /* Full screen, ignore aspect */
+#define DRM_MODE_SCALE_CENTER		2 /* Centered, no scaling */
+#define DRM_MODE_SCALE_ASPECT		3 /* Full screen, preserve aspect */
+
+/* Dithering mode options */
+#define DRM_MODE_DITHERING_OFF	0
+#define DRM_MODE_DITHERING_ON	1
+#define DRM_MODE_DITHERING_AUTO 2
+
+/* Dirty info options */
+#define DRM_MODE_DIRTY_OFF      0
+#define DRM_MODE_DIRTY_ON       1
+#define DRM_MODE_DIRTY_ANNOTATE 2
+
+/* Link Status options */
+#define DRM_MODE_LINK_STATUS_GOOD	0
+#define DRM_MODE_LINK_STATUS_BAD	1
+
+/* Panel type property */
+#define DRM_MODE_PANEL_TYPE_UNKNOWN	0
+#define DRM_MODE_PANEL_TYPE_OLED	1
+#define DRM_MODE_PANEL_TYPE_LCD		2
+
+/*
+ * DRM_MODE_ROTATE_<degrees>
+ *
+ * Signals that a drm plane is been rotated <degrees> degrees in counter
+ * clockwise direction.
+ *
+ * This define is provided as a convenience, looking up the property id
+ * using the name->prop id lookup is the preferred method.
+ */
+#define DRM_MODE_ROTATE_0       (1<<0)
+#define DRM_MODE_ROTATE_90      (1<<1)
+#define DRM_MODE_ROTATE_180     (1<<2)
+#define DRM_MODE_ROTATE_270     (1<<3)
+
+/*
+ * DRM_MODE_ROTATE_MASK
+ *
+ * Bitmask used to look for drm plane rotations.
+ */
+#define DRM_MODE_ROTATE_MASK (\
+		DRM_MODE_ROTATE_0  | \
+		DRM_MODE_ROTATE_90  | \
+		DRM_MODE_ROTATE_180 | \
+		DRM_MODE_ROTATE_270)
+
+/*
+ * DRM_MODE_REFLECT_<axis>
+ *
+ * Signals that the contents of a drm plane is reflected along the <axis> axis,
+ * in the same way as mirroring.
+ * See kerneldoc chapter "Plane Composition Properties" for more details.
+ *
+ * This define is provided as a convenience, looking up the property id
+ * using the name->prop id lookup is the preferred method.
+ */
+#define DRM_MODE_REFLECT_X      (1<<4)
+#define DRM_MODE_REFLECT_Y      (1<<5)
+
+/*
+ * DRM_MODE_REFLECT_MASK
+ *
+ * Bitmask used to look for drm plane reflections.
+ */
+#define DRM_MODE_REFLECT_MASK (\
+		DRM_MODE_REFLECT_X | \
+		DRM_MODE_REFLECT_Y)
+
+/* Content Protection Flags */
+#define DRM_MODE_CONTENT_PROTECTION_UNDESIRED	0
+#define DRM_MODE_CONTENT_PROTECTION_DESIRED     1
+#define DRM_MODE_CONTENT_PROTECTION_ENABLED     2
+
+/**
+ * struct drm_mode_modeinfo - Display mode information.
+ * @clock: pixel clock in kHz
+ * @hdisplay: horizontal display size
+ * @hsync_start: horizontal sync start
+ * @hsync_end: horizontal sync end
+ * @htotal: horizontal total size
+ * @hskew: horizontal skew
+ * @vdisplay: vertical display size
+ * @vsync_start: vertical sync start
+ * @vsync_end: vertical sync end
+ * @vtotal: vertical total size
+ * @vscan: vertical scan
+ * @vrefresh: approximate vertical refresh rate in Hz
+ * @flags: bitmask of misc. flags, see DRM_MODE_FLAG_* defines
+ * @type: bitmask of type flags, see DRM_MODE_TYPE_* defines
+ * @name: string describing the mode resolution
+ *
+ * This is the user-space API display mode information structure. For the
+ * kernel version see struct drm_display_mode.
+ */
+struct drm_mode_modeinfo {
+	__u32 clock;
+	__u16 hdisplay;
+	__u16 hsync_start;
+	__u16 hsync_end;
+	__u16 htotal;
+	__u16 hskew;
+	__u16 vdisplay;
+	__u16 vsync_start;
+	__u16 vsync_end;
+	__u16 vtotal;
+	__u16 vscan;
+
+	__u32 vrefresh;
+
+	__u32 flags;
+	__u32 type;
+	char name[DRM_DISPLAY_MODE_LEN];
+};
+
+struct drm_mode_card_res {
+	__u64 fb_id_ptr;
+	__u64 crtc_id_ptr;
+	__u64 connector_id_ptr;
+	__u64 encoder_id_ptr;
+	__u32 count_fbs;
+	__u32 count_crtcs;
+	__u32 count_connectors;
+	__u32 count_encoders;
+	__u32 min_width;
+	__u32 max_width;
+	__u32 min_height;
+	__u32 max_height;
+};
+
+struct drm_mode_crtc {
+	__u64 set_connectors_ptr;
+	__u32 count_connectors;
+
+	__u32 crtc_id; /**< Id */
+	__u32 fb_id; /**< Id of framebuffer */
+
+	__u32 x; /**< x Position on the framebuffer */
+	__u32 y; /**< y Position on the framebuffer */
+
+	__u32 gamma_size;
+	__u32 mode_valid;
+	struct drm_mode_modeinfo mode;
+};
+
+#define DRM_MODE_PRESENT_TOP_FIELD	(1<<0)
+#define DRM_MODE_PRESENT_BOTTOM_FIELD	(1<<1)
+
+/* Planes blend with or override other bits on the CRTC */
+struct drm_mode_set_plane {
+	__u32 plane_id;
+	__u32 crtc_id;
+	__u32 fb_id; /* fb object contains surface format type */
+	__u32 flags; /* see above flags */
+
+	/* Signed dest location allows it to be partially off screen */
+	__s32 crtc_x;
+	__s32 crtc_y;
+	__u32 crtc_w;
+	__u32 crtc_h;
+
+	/* Source values are 16.16 fixed point */
+	__u32 src_x;
+	__u32 src_y;
+	__u32 src_h;
+	__u32 src_w;
+};
+
+/**
+ * struct drm_mode_get_plane - Get plane metadata.
+ *
+ * Userspace can perform a GETPLANE ioctl to retrieve information about a
+ * plane.
+ *
+ * To retrieve the number of formats supported, set @count_format_types to zero
+ * and call the ioctl. @count_format_types will be updated with the value.
+ *
+ * To retrieve these formats, allocate an array with the memory needed to store
+ * @count_format_types formats. Point @format_type_ptr to this array and call
+ * the ioctl again (with @count_format_types still set to the value returned in
+ * the first ioctl call).
+ */
+struct drm_mode_get_plane {
+	/**
+	 * @plane_id: Object ID of the plane whose information should be
+	 * retrieved. Set by caller.
+	 */
+	__u32 plane_id;
+
+	/** @crtc_id: Object ID of the current CRTC. */
+	__u32 crtc_id;
+	/** @fb_id: Object ID of the current fb. */
+	__u32 fb_id;
+
+	/**
+	 * @possible_crtcs: Bitmask of CRTC's compatible with the plane. CRTC's
+	 * are created and they receive an index, which corresponds to their
+	 * position in the bitmask. Bit N corresponds to
+	 * :ref:`CRTC index<crtc_index>` N.
+	 */
+	__u32 possible_crtcs;
+	/** @gamma_size: Never used. */
+	__u32 gamma_size;
+
+	/** @count_format_types: Number of formats. */
+	__u32 count_format_types;
+	/**
+	 * @format_type_ptr: Pointer to ``__u32`` array of formats that are
+	 * supported by the plane. These formats do not require modifiers.
+	 */
+	__u64 format_type_ptr;
+};
+
+struct drm_mode_get_plane_res {
+	__u64 plane_id_ptr;
+	__u32 count_planes;
+};
+
+#define DRM_MODE_ENCODER_NONE	0
+#define DRM_MODE_ENCODER_DAC	1
+#define DRM_MODE_ENCODER_TMDS	2
+#define DRM_MODE_ENCODER_LVDS	3
+#define DRM_MODE_ENCODER_TVDAC	4
+#define DRM_MODE_ENCODER_VIRTUAL 5
+#define DRM_MODE_ENCODER_DSI	6
+#define DRM_MODE_ENCODER_DPMST	7
+#define DRM_MODE_ENCODER_DPI	8
+
+struct drm_mode_get_encoder {
+	__u32 encoder_id;
+	__u32 encoder_type;
+
+	__u32 crtc_id; /**< Id of crtc */
+
+	__u32 possible_crtcs;
+	__u32 possible_clones;
+};
+
+/* This is for connectors with multiple signal types. */
+/* Try to match DRM_MODE_CONNECTOR_X as closely as possible. */
+enum drm_mode_subconnector {
+	DRM_MODE_SUBCONNECTOR_Automatic   = 0,  /* DVI-I, TV     */
+	DRM_MODE_SUBCONNECTOR_Unknown     = 0,  /* DVI-I, TV, DP */
+	DRM_MODE_SUBCONNECTOR_VGA	  = 1,  /*            DP */
+	DRM_MODE_SUBCONNECTOR_DVID	  = 3,  /* DVI-I      DP */
+	DRM_MODE_SUBCONNECTOR_DVIA	  = 4,  /* DVI-I         */
+	DRM_MODE_SUBCONNECTOR_Composite   = 5,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_SVIDEO	  = 6,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_Component   = 8,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_SCART	  = 9,  /*        TV     */
+	DRM_MODE_SUBCONNECTOR_DisplayPort = 10, /*            DP */
+	DRM_MODE_SUBCONNECTOR_HDMIA       = 11, /*            DP */
+	DRM_MODE_SUBCONNECTOR_Native      = 15, /*            DP */
+	DRM_MODE_SUBCONNECTOR_Wireless    = 18, /*            DP */
+};
+
+#define DRM_MODE_CONNECTOR_Unknown	0
+#define DRM_MODE_CONNECTOR_VGA		1
+#define DRM_MODE_CONNECTOR_DVII		2
+#define DRM_MODE_CONNECTOR_DVID		3
+#define DRM_MODE_CONNECTOR_DVIA		4
+#define DRM_MODE_CONNECTOR_Composite	5
+#define DRM_MODE_CONNECTOR_SVIDEO	6
+#define DRM_MODE_CONNECTOR_LVDS		7
+#define DRM_MODE_CONNECTOR_Component	8
+#define DRM_MODE_CONNECTOR_9PinDIN	9
+#define DRM_MODE_CONNECTOR_DisplayPort	10
+#define DRM_MODE_CONNECTOR_HDMIA	11
+#define DRM_MODE_CONNECTOR_HDMIB	12
+#define DRM_MODE_CONNECTOR_TV		13
+#define DRM_MODE_CONNECTOR_eDP		14
+#define DRM_MODE_CONNECTOR_VIRTUAL      15
+#define DRM_MODE_CONNECTOR_DSI		16
+#define DRM_MODE_CONNECTOR_DPI		17
+#define DRM_MODE_CONNECTOR_WRITEBACK	18
+#define DRM_MODE_CONNECTOR_SPI		19
+#define DRM_MODE_CONNECTOR_USB		20
+
+/**
+ * struct drm_mode_get_connector - Get connector metadata.
+ *
+ * User-space can perform a GETCONNECTOR ioctl to retrieve information about a
+ * connector. User-space is expected to retrieve encoders, modes and properties
+ * by performing this ioctl at least twice: the first time to retrieve the
+ * number of elements, the second time to retrieve the elements themselves.
+ *
+ * To retrieve the number of elements, set @count_props and @count_encoders to
+ * zero, set @count_modes to 1, and set @modes_ptr to a temporary struct
+ * drm_mode_modeinfo element.
+ *
+ * To retrieve the elements, allocate arrays for @encoders_ptr, @modes_ptr,
+ * @props_ptr and @prop_values_ptr, then set @count_modes, @count_props and
+ * @count_encoders to their capacity.
+ *
+ * Performing the ioctl only twice may be racy: the number of elements may have
+ * changed with a hotplug event in-between the two ioctls. User-space is
+ * expected to retry the last ioctl until the number of elements stabilizes.
+ * The kernel won't fill any array which doesn't have the expected length.
+ *
+ * **Force-probing a connector**
+ *
+ * If the @count_modes field is set to zero and the DRM client is the current
+ * DRM master, the kernel will perform a forced probe on the connector to
+ * refresh the connector status, modes and EDID. A forced-probe can be slow,
+ * might cause flickering and the ioctl will block.
+ *
+ * User-space needs to force-probe connectors to ensure their metadata is
+ * up-to-date at startup and after receiving a hot-plug event. User-space
+ * may perform a forced-probe when the user explicitly requests it. User-space
+ * shouldn't perform a forced-probe in other situations.
+ */
+struct drm_mode_get_connector {
+	/** @encoders_ptr: Pointer to ``__u32`` array of object IDs. */
+	__u64 encoders_ptr;
+	/** @modes_ptr: Pointer to struct drm_mode_modeinfo array. */
+	__u64 modes_ptr;
+	/** @props_ptr: Pointer to ``__u32`` array of property IDs. */
+	__u64 props_ptr;
+	/** @prop_values_ptr: Pointer to ``__u64`` array of property values. */
+	__u64 prop_values_ptr;
+
+	/** @count_modes: Number of modes. */
+	__u32 count_modes;
+	/** @count_props: Number of properties. */
+	__u32 count_props;
+	/** @count_encoders: Number of encoders. */
+	__u32 count_encoders;
+
+	/** @encoder_id: Object ID of the current encoder. */
+	__u32 encoder_id;
+	/** @connector_id: Object ID of the connector. */
+	__u32 connector_id;
+	/**
+	 * @connector_type: Type of the connector.
+	 *
+	 * See DRM_MODE_CONNECTOR_* defines.
+	 */
+	__u32 connector_type;
+	/**
+	 * @connector_type_id: Type-specific connector number.
+	 *
+	 * This is not an object ID. This is a per-type connector number. Each
+	 * (type, type_id) combination is unique across all connectors of a DRM
+	 * device.
+	 *
+	 * The (type, type_id) combination is not a stable identifier: the
+	 * type_id can change depending on the driver probe order.
+	 */
+	__u32 connector_type_id;
+
+	/**
+	 * @connection: Status of the connector.
+	 *
+	 * See enum drm_connector_status.
+	 */
+	__u32 connection;
+	/** @mm_width: Width of the connected sink in millimeters. */
+	__u32 mm_width;
+	/** @mm_height: Height of the connected sink in millimeters. */
+	__u32 mm_height;
+	/**
+	 * @subpixel: Subpixel order of the connected sink.
+	 *
+	 * See enum subpixel_order.
+	 */
+	__u32 subpixel;
+
+	/** @pad: Padding, must be zero. */
+	__u32 pad;
+};
+
+#define DRM_MODE_PROP_PENDING	(1<<0) /* deprecated, do not use */
+#define DRM_MODE_PROP_RANGE	(1<<1)
+#define DRM_MODE_PROP_IMMUTABLE	(1<<2)
+#define DRM_MODE_PROP_ENUM	(1<<3) /* enumerated type with text strings */
+#define DRM_MODE_PROP_BLOB	(1<<4)
+#define DRM_MODE_PROP_BITMASK	(1<<5) /* bitmask of enumerated types */
+
+/* non-extended types: legacy bitmask, one bit per type: */
+#define DRM_MODE_PROP_LEGACY_TYPE  ( \
+		DRM_MODE_PROP_RANGE | \
+		DRM_MODE_PROP_ENUM | \
+		DRM_MODE_PROP_BLOB | \
+		DRM_MODE_PROP_BITMASK)
+
+/* extended-types: rather than continue to consume a bit per type,
+ * grab a chunk of the bits to use as integer type id.
+ */
+#define DRM_MODE_PROP_EXTENDED_TYPE	0x0000ffc0
+#define DRM_MODE_PROP_TYPE(n)		((n) << 6)
+#define DRM_MODE_PROP_OBJECT		DRM_MODE_PROP_TYPE(1)
+#define DRM_MODE_PROP_SIGNED_RANGE	DRM_MODE_PROP_TYPE(2)
+
+/* the PROP_ATOMIC flag is used to hide properties from userspace that
+ * is not aware of atomic properties.  This is mostly to work around
+ * older userspace (DDX drivers) that read/write each prop they find,
+ * without being aware that this could be triggering a lengthy modeset.
+ */
+#define DRM_MODE_PROP_ATOMIC        0x80000000
+
+/**
+ * struct drm_mode_property_enum - Description for an enum/bitfield entry.
+ * @value: numeric value for this enum entry.
+ * @name: symbolic name for this enum entry.
+ *
+ * See struct drm_property_enum for details.
+ */
+struct drm_mode_property_enum {
+	__u64 value;
+	char name[DRM_PROP_NAME_LEN];
+};
+
+/**
+ * struct drm_mode_get_property - Get property metadata.
+ *
+ * User-space can perform a GETPROPERTY ioctl to retrieve information about a
+ * property. The same property may be attached to multiple objects, see
+ * "Modeset Base Object Abstraction".
+ *
+ * The meaning of the @values_ptr field changes depending on the property type.
+ * See &drm_property.flags for more details.
+ *
+ * The @enum_blob_ptr and @count_enum_blobs fields are only meaningful when the
+ * property has the type &DRM_MODE_PROP_ENUM or &DRM_MODE_PROP_BITMASK. For
+ * backwards compatibility, the kernel will always set @count_enum_blobs to
+ * zero when the property has the type &DRM_MODE_PROP_BLOB. User-space must
+ * ignore these two fields if the property has a different type.
+ *
+ * User-space is expected to retrieve values and enums by performing this ioctl
+ * at least twice: the first time to retrieve the number of elements, the
+ * second time to retrieve the elements themselves.
+ *
+ * To retrieve the number of elements, set @count_values and @count_enum_blobs
+ * to zero, then call the ioctl. @count_values will be updated with the number
+ * of elements. If the property has the type &DRM_MODE_PROP_ENUM or
+ * &DRM_MODE_PROP_BITMASK, @count_enum_blobs will be updated as well.
+ *
+ * To retrieve the elements themselves, allocate an array for @values_ptr and
+ * set @count_values to its capacity. If the property has the type
+ * &DRM_MODE_PROP_ENUM or &DRM_MODE_PROP_BITMASK, allocate an array for
+ * @enum_blob_ptr and set @count_enum_blobs to its capacity. Calling the ioctl
+ * again will fill the arrays.
+ */
+struct drm_mode_get_property {
+	/** @values_ptr: Pointer to a ``__u64`` array. */
+	__u64 values_ptr;
+	/** @enum_blob_ptr: Pointer to a struct drm_mode_property_enum array. */
+	__u64 enum_blob_ptr;
+
+	/**
+	 * @prop_id: Object ID of the property which should be retrieved. Set
+	 * by the caller.
+	 */
+	__u32 prop_id;
+	/**
+	 * @flags: ``DRM_MODE_PROP_*`` bitfield. See &drm_property.flags for
+	 * a definition of the flags.
+	 */
+	__u32 flags;
+	/**
+	 * @name: Symbolic property name. User-space should use this field to
+	 * recognize properties.
+	 */
+	char name[DRM_PROP_NAME_LEN];
+
+	/** @count_values: Number of elements in @values_ptr. */
+	__u32 count_values;
+	/** @count_enum_blobs: Number of elements in @enum_blob_ptr. */
+	__u32 count_enum_blobs;
+};
+
+struct drm_mode_connector_set_property {
+	__u64 value;
+	__u32 prop_id;
+	__u32 connector_id;
+};
+
+#define DRM_MODE_OBJECT_CRTC 0xcccccccc
+#define DRM_MODE_OBJECT_CONNECTOR 0xc0c0c0c0
+#define DRM_MODE_OBJECT_ENCODER 0xe0e0e0e0
+#define DRM_MODE_OBJECT_MODE 0xdededede
+#define DRM_MODE_OBJECT_PROPERTY 0xb0b0b0b0
+#define DRM_MODE_OBJECT_FB 0xfbfbfbfb
+#define DRM_MODE_OBJECT_BLOB 0xbbbbbbbb
+#define DRM_MODE_OBJECT_PLANE 0xeeeeeeee
+#define DRM_MODE_OBJECT_COLOROP 0xfafafafa
+#define DRM_MODE_OBJECT_ANY 0
+
+struct drm_mode_obj_get_properties {
+	__u64 props_ptr;
+	__u64 prop_values_ptr;
+	__u32 count_props;
+	__u32 obj_id;
+	__u32 obj_type;
+};
+
+struct drm_mode_obj_set_property {
+	__u64 value;
+	__u32 prop_id;
+	__u32 obj_id;
+	__u32 obj_type;
+};
+
+struct drm_mode_get_blob {
+	__u32 blob_id;
+	__u32 length;
+	__u64 data;
+};
+
+struct drm_mode_fb_cmd {
+	__u32 fb_id;
+	__u32 width;
+	__u32 height;
+	__u32 pitch;
+	__u32 bpp;
+	__u32 depth;
+	/* driver specific handle */
+	__u32 handle;
+};
+
+#define DRM_MODE_FB_INTERLACED	(1<<0) /* for interlaced framebuffers */
+#define DRM_MODE_FB_MODIFIERS	(1<<1) /* enables ->modifier[] */
+
+/**
+ * struct drm_mode_fb_cmd2 - Frame-buffer metadata.
+ *
+ * This struct holds frame-buffer metadata. There are two ways to use it:
+ *
+ * - User-space can fill this struct and perform a &DRM_IOCTL_MODE_ADDFB2
+ *   ioctl to register a new frame-buffer. The new frame-buffer object ID will
+ *   be set by the kernel in @fb_id.
+ * - User-space can set @fb_id and perform a &DRM_IOCTL_MODE_GETFB2 ioctl to
+ *   fetch metadata about an existing frame-buffer.
+ *
+ * In case of planar formats, this struct allows up to 4 buffer objects with
+ * offsets and pitches per plane. The pitch and offset order are dictated by
+ * the format FourCC as defined by ``drm_fourcc.h``, e.g. NV12 is described as:
+ *
+ *     YUV 4:2:0 image with a plane of 8-bit Y samples followed by an
+ *     interleaved U/V plane containing 8-bit 2x2 subsampled colour difference
+ *     samples.
+ *
+ * So it would consist of a Y plane at ``offsets[0]`` and a UV plane at
+ * ``offsets[1]``.
+ *
+ * To accommodate tiled, compressed, etc formats, a modifier can be specified.
+ * For more information see the "Format Modifiers" section. Note that even
+ * though it looks like we have a modifier per-plane, we in fact do not. The
+ * modifier for each plane must be identical. Thus all combinations of
+ * different data layouts for multi-plane formats must be enumerated as
+ * separate modifiers.
+ *
+ * All of the entries in @handles, @pitches, @offsets and @modifier must be
+ * zero when unused. Warning, for @offsets and @modifier zero can't be used to
+ * figure out whether the entry is used or not since it's a valid value (a zero
+ * offset is common, and a zero modifier is &DRM_FORMAT_MOD_LINEAR).
+ */
+struct drm_mode_fb_cmd2 {
+	/** @fb_id: Object ID of the frame-buffer. */
+	__u32 fb_id;
+	/** @width: Width of the frame-buffer. */
+	__u32 width;
+	/** @height: Height of the frame-buffer. */
+	__u32 height;
+	/**
+	 * @pixel_format: FourCC format code, see ``DRM_FORMAT_*`` constants in
+	 * ``drm_fourcc.h``.
+	 */
+	__u32 pixel_format;
+	/**
+	 * @flags: Frame-buffer flags (see &DRM_MODE_FB_INTERLACED and
+	 * &DRM_MODE_FB_MODIFIERS).
+	 */
+	__u32 flags;
+
+	/**
+	 * @handles: GEM buffer handle, one per plane. Set to 0 if the plane is
+	 * unused. The same handle can be used for multiple planes.
+	 */
+	__u32 handles[4];
+	/** @pitches: Pitch (aka. stride) in bytes, one per plane. */
+	__u32 pitches[4];
+	/** @offsets: Offset into the buffer in bytes, one per plane. */
+	__u32 offsets[4];
+	/**
+	 * @modifier: Format modifier, one per plane. See ``DRM_FORMAT_MOD_*``
+	 * constants in ``drm_fourcc.h``. All planes must use the same
+	 * modifier. Ignored unless &DRM_MODE_FB_MODIFIERS is set in @flags.
+	 */
+	__u64 modifier[4];
+};
+
+#define DRM_MODE_FB_DIRTY_ANNOTATE_COPY 0x01
+#define DRM_MODE_FB_DIRTY_ANNOTATE_FILL 0x02
+#define DRM_MODE_FB_DIRTY_FLAGS         0x03
+
+#define DRM_MODE_FB_DIRTY_MAX_CLIPS     256
+
+/*
+ * Mark a region of a framebuffer as dirty.
+ *
+ * Some hardware does not automatically update display contents
+ * as a hardware or software draw to a framebuffer. This ioctl
+ * allows userspace to tell the kernel and the hardware what
+ * regions of the framebuffer have changed.
+ *
+ * The kernel or hardware is free to update more then just the
+ * region specified by the clip rects. The kernel or hardware
+ * may also delay and/or coalesce several calls to dirty into a
+ * single update.
+ *
+ * Userspace may annotate the updates, the annotates are a
+ * promise made by the caller that the change is either a copy
+ * of pixels or a fill of a single color in the region specified.
+ *
+ * If the DRM_MODE_FB_DIRTY_ANNOTATE_COPY flag is given then
+ * the number of updated regions are half of num_clips given,
+ * where the clip rects are paired in src and dst. The width and
+ * height of each one of the pairs must match.
+ *
+ * If the DRM_MODE_FB_DIRTY_ANNOTATE_FILL flag is given the caller
+ * promises that the region specified of the clip rects is filled
+ * completely with a single color as given in the color argument.
+ */
+
+struct drm_mode_fb_dirty_cmd {
+	__u32 fb_id;
+	__u32 flags;
+	__u32 color;
+	__u32 num_clips;
+	__u64 clips_ptr;
+};
+
+struct drm_mode_mode_cmd {
+	__u32 connector_id;
+	struct drm_mode_modeinfo mode;
+};
+
+#define DRM_MODE_CURSOR_BO	0x01
+#define DRM_MODE_CURSOR_MOVE	0x02
+#define DRM_MODE_CURSOR_FLAGS	0x03
+
+/*
+ * depending on the value in flags different members are used.
+ *
+ * CURSOR_BO uses
+ *    crtc_id
+ *    width
+ *    height
+ *    handle - if 0 turns the cursor off
+ *
+ * CURSOR_MOVE uses
+ *    crtc_id
+ *    x
+ *    y
+ */
+struct drm_mode_cursor {
+	__u32 flags;
+	__u32 crtc_id;
+	__s32 x;
+	__s32 y;
+	__u32 width;
+	__u32 height;
+	/* driver specific handle */
+	__u32 handle;
+};
+
+struct drm_mode_cursor2 {
+	__u32 flags;
+	__u32 crtc_id;
+	__s32 x;
+	__s32 y;
+	__u32 width;
+	__u32 height;
+	/* driver specific handle */
+	__u32 handle;
+	__s32 hot_x;
+	__s32 hot_y;
+};
+
+struct drm_mode_crtc_lut {
+	__u32 crtc_id;
+	__u32 gamma_size;
+
+	/* pointers to arrays */
+	__u64 red;
+	__u64 green;
+	__u64 blue;
+};
+
+struct drm_color_ctm {
+	/*
+	 * Conversion matrix in S31.32 sign-magnitude
+	 * (not two's complement!) format.
+	 *
+	 * out   matrix    in
+	 * |R|   |0 1 2|   |R|
+	 * |G| = |3 4 5| x |G|
+	 * |B|   |6 7 8|   |B|
+	 */
+	__u64 matrix[9];
+};
+
+struct drm_color_ctm_3x4 {
+	/*
+	 * Conversion matrix with 3x4 dimensions in S31.32 sign-magnitude
+	 * (not two's complement!) format.
+	 *
+	 * out   matrix          in
+	 * |R|   |0  1  2  3 |   | R |
+	 * |G| = |4  5  6  7 | x | G |
+	 * |B|   |8  9  10 11|   | B |
+	 *                       |1.0|
+	 */
+	__u64 matrix[12];
+};
+
+struct drm_color_lut {
+	/*
+	 * Values are mapped linearly to 0.0 - 1.0 range, with 0x0 == 0.0 and
+	 * 0xffff == 1.0.
+	 */
+	__u16 red;
+	__u16 green;
+	__u16 blue;
+	__u16 reserved;
+};
+
+/*
+ * struct drm_color_lut32
+ *
+ * 32-bit per channel color LUT entry, similar to drm_color_lut.
+ */
+struct drm_color_lut32 {
+	__u32 red;
+	__u32 green;
+	__u32 blue;
+	__u32 reserved;
+};
+
+/**
+ * enum drm_colorop_type - Type of color operation
+ *
+ * drm_colorops can be of many different types. Each type behaves differently
+ * and defines a different set of properties. This enum defines all types and
+ * gives a high-level description.
+ */
+enum drm_colorop_type {
+	/**
+	 * @DRM_COLOROP_1D_CURVE:
+	 *
+	 * enum string "1D Curve"
+	 *
+	 * A 1D curve that is being applied to all color channels. The
+	 * curve is specified via the CURVE_1D_TYPE colorop property.
+	 */
+	DRM_COLOROP_1D_CURVE,
+
+	/**
+	 * @DRM_COLOROP_1D_LUT:
+	 *
+	 * enum string "1D LUT"
+	 *
+	 * A simple 1D LUT of uniformly spaced &drm_color_lut32 entries,
+	 * packed into a blob via the DATA property. The driver's
+	 * expected LUT size is advertised via the SIZE property.
+	 *
+	 * The DATA blob is an array of struct drm_color_lut32 with size
+	 * of "size".
+	 */
+	DRM_COLOROP_1D_LUT,
+
+	/**
+	 * @DRM_COLOROP_CTM_3X4:
+	 *
+	 * enum string "3x4 Matrix"
+	 *
+	 * A 3x4 matrix. Its values are specified via the
+	 * &drm_color_ctm_3x4 struct provided via the DATA property.
+	 *
+	 * The DATA blob is a float[12]:
+	 * out   matrix          in
+	 * | R |   | 0  1  2  3  |   | R |
+	 * | G | = | 4  5  6  7  | x | G |
+	 * | B |   | 8  9  10 12 |   | B |
+	 */
+	DRM_COLOROP_CTM_3X4,
+
+	/**
+	 * @DRM_COLOROP_MULTIPLIER:
+	 *
+	 * enum string "Multiplier"
+	 *
+	 * A simple multiplier, applied to all color values. The
+	 * multiplier is specified as a S31.32 via the MULTIPLIER
+	 * property.
+	 */
+	DRM_COLOROP_MULTIPLIER,
+
+	/**
+	 * @DRM_COLOROP_3D_LUT:
+	 *
+	 * enum string "3D LUT"
+	 *
+	 * A 3D LUT of &drm_color_lut32 entries,
+	 * packed into a blob via the DATA property. The driver's expected
+	 * LUT size is advertised via the SIZE property, i.e., a 3D LUT with
+	 * 17x17x17 entries will have SIZE set to 17.
+	 *
+	 * The DATA blob is a 3D array of struct drm_color_lut32 with dimension
+	 * length of "size".
+	 * The LUT elements are traversed like so:
+	 *
+	 *   for B in range 0..n
+	 *     for G in range 0..n
+	 *       for R in range 0..n
+	 *        index = R + n * (G + n * B)
+	 *         color = lut3d[index]
+	 */
+	DRM_COLOROP_3D_LUT,
+};
+
+/**
+ * enum drm_colorop_lut3d_interpolation_type - type of 3DLUT interpolation
+ */
+enum drm_colorop_lut3d_interpolation_type {
+	/**
+	 * @DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL:
+	 *
+	 * Tetrahedral 3DLUT interpolation
+	 */
+	DRM_COLOROP_LUT3D_INTERPOLATION_TETRAHEDRAL,
+};
+
+/**
+ * enum drm_colorop_lut1d_interpolation_type - type of interpolation for 1D LUTs
+ */
+enum drm_colorop_lut1d_interpolation_type {
+	/**
+	 * @DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR:
+	 *
+	 * Linear interpolation. Values between points of the LUT will be
+	 * linearly interpolated.
+	 */
+	DRM_COLOROP_LUT1D_INTERPOLATION_LINEAR,
+};
+
+/**
+ * struct drm_plane_size_hint - Plane size hints
+ * @width: The width of the plane in pixel
+ * @height: The height of the plane in pixel
+ *
+ * The plane SIZE_HINTS property blob contains an
+ * array of struct drm_plane_size_hint.
+ */
+struct drm_plane_size_hint {
+	__u16 width;
+	__u16 height;
+};
+
+/**
+ * struct hdr_metadata_infoframe - HDR Metadata Infoframe Data.
+ *
+ * HDR Metadata Infoframe as per CTA 861.G spec. This is expected
+ * to match exactly with the spec.
+ *
+ * Userspace is expected to pass the metadata information as per
+ * the format described in this structure.
+ */
+struct hdr_metadata_infoframe {
+	/**
+	 * @eotf: Electro-Optical Transfer Function (EOTF)
+	 * used in the stream.
+	 */
+	__u8 eotf;
+	/**
+	 * @metadata_type: Static_Metadata_Descriptor_ID.
+	 */
+	__u8 metadata_type;
+	/**
+	 * @display_primaries: Color Primaries of the Data.
+	 * These are coded as unsigned 16-bit values in units of
+	 * 0.00002, where 0x0000 represents zero and 0xC350
+	 * represents 1.0000.
+	 * @display_primaries.x: X coordinate of color primary.
+	 * @display_primaries.y: Y coordinate of color primary.
+	 */
+	struct {
+		__u16 x, y;
+	} display_primaries[3];
+	/**
+	 * @white_point: White Point of Colorspace Data.
+	 * These are coded as unsigned 16-bit values in units of
+	 * 0.00002, where 0x0000 represents zero and 0xC350
+	 * represents 1.0000.
+	 * @white_point.x: X coordinate of whitepoint of color primary.
+	 * @white_point.y: Y coordinate of whitepoint of color primary.
+	 */
+	struct {
+		__u16 x, y;
+	} white_point;
+	/**
+	 * @max_display_mastering_luminance: Max Mastering Display Luminance.
+	 * This value is coded as an unsigned 16-bit value in units of 1 cd/m2,
+	 * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2.
+	 */
+	__u16 max_display_mastering_luminance;
+	/**
+	 * @min_display_mastering_luminance: Min Mastering Display Luminance.
+	 * This value is coded as an unsigned 16-bit value in units of
+	 * 0.0001 cd/m2, where 0x0001 represents 0.0001 cd/m2 and 0xFFFF
+	 * represents 6.5535 cd/m2.
+	 */
+	__u16 min_display_mastering_luminance;
+	/**
+	 * @max_cll: Max Content Light Level.
+	 * This value is coded as an unsigned 16-bit value in units of 1 cd/m2,
+	 * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2.
+	 */
+	__u16 max_cll;
+	/**
+	 * @max_fall: Max Frame Average Light Level.
+	 * This value is coded as an unsigned 16-bit value in units of 1 cd/m2,
+	 * where 0x0001 represents 1 cd/m2 and 0xFFFF represents 65535 cd/m2.
+	 */
+	__u16 max_fall;
+};
+
+/**
+ * struct hdr_output_metadata - HDR output metadata
+ *
+ * Metadata Information to be passed from userspace
+ */
+struct hdr_output_metadata {
+	/**
+	 * @metadata_type: Static_Metadata_Descriptor_ID.
+	 */
+	__u32 metadata_type;
+	/**
+	 * @hdmi_metadata_type1: HDR Metadata Infoframe.
+	 */
+	union {
+		struct hdr_metadata_infoframe hdmi_metadata_type1;
+	};
+};
+
+/**
+ * DRM_MODE_PAGE_FLIP_EVENT
+ *
+ * Request that the kernel sends back a vblank event (see
+ * struct drm_event_vblank) with the &DRM_EVENT_FLIP_COMPLETE type when the
+ * page-flip is done.
+ *
+ * When used with atomic uAPI, one event will be delivered per CRTC included in
+ * the atomic commit. A CRTC is included in an atomic commit if one of its
+ * properties is set, or if a property is set on a connector or plane linked
+ * via the CRTC_ID property to the CRTC. At least one CRTC must be included,
+ * and all pulled in CRTCs must be either previously or newly powered on (in
+ * other words, a powered off CRTC which stays off cannot be included in the
+ * atomic commit).
+ */
+#define DRM_MODE_PAGE_FLIP_EVENT 0x01
+/**
+ * DRM_MODE_PAGE_FLIP_ASYNC
+ *
+ * Request that the page-flip is performed as soon as possible, ie. with no
+ * delay due to waiting for vblank. This may cause tearing to be visible on
+ * the screen.
+ *
+ * When used with atomic uAPI, the driver will return an error if the hardware
+ * doesn't support performing an asynchronous page-flip for this update.
+ * User-space should handle this, e.g. by falling back to a regular page-flip.
+ *
+ * Note, some hardware might need to perform one last synchronous page-flip
+ * before being able to switch to asynchronous page-flips. As an exception,
+ * the driver will return success even though that first page-flip is not
+ * asynchronous.
+ */
+#define DRM_MODE_PAGE_FLIP_ASYNC 0x02
+#define DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE 0x4
+#define DRM_MODE_PAGE_FLIP_TARGET_RELATIVE 0x8
+#define DRM_MODE_PAGE_FLIP_TARGET (DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE | \
+				   DRM_MODE_PAGE_FLIP_TARGET_RELATIVE)
+/**
+ * DRM_MODE_PAGE_FLIP_FLAGS
+ *
+ * Bitmask of flags suitable for &drm_mode_crtc_page_flip_target.flags.
+ */
+#define DRM_MODE_PAGE_FLIP_FLAGS (DRM_MODE_PAGE_FLIP_EVENT | \
+				  DRM_MODE_PAGE_FLIP_ASYNC | \
+				  DRM_MODE_PAGE_FLIP_TARGET)
+
+/*
+ * Request a page flip on the specified crtc.
+ *
+ * This ioctl will ask KMS to schedule a page flip for the specified
+ * crtc.  Once any pending rendering targeting the specified fb (as of
+ * ioctl time) has completed, the crtc will be reprogrammed to display
+ * that fb after the next vertical refresh.  The ioctl returns
+ * immediately, but subsequent rendering to the current fb will block
+ * in the execbuffer ioctl until the page flip happens.  If a page
+ * flip is already pending as the ioctl is called, EBUSY will be
+ * returned.
+ *
+ * Flag DRM_MODE_PAGE_FLIP_EVENT requests that drm sends back a vblank
+ * event (see drm.h: struct drm_event_vblank) when the page flip is
+ * done.  The user_data field passed in with this ioctl will be
+ * returned as the user_data field in the vblank event struct.
+ *
+ * Flag DRM_MODE_PAGE_FLIP_ASYNC requests that the flip happen
+ * 'as soon as possible', meaning that it not delay waiting for vblank.
+ * This may cause tearing on the screen.
+ *
+ * The reserved field must be zero.
+ */
+
+struct drm_mode_crtc_page_flip {
+	__u32 crtc_id;
+	__u32 fb_id;
+	__u32 flags;
+	__u32 reserved;
+	__u64 user_data;
+};
+
+/*
+ * Request a page flip on the specified crtc.
+ *
+ * Same as struct drm_mode_crtc_page_flip, but supports new flags and
+ * re-purposes the reserved field:
+ *
+ * The sequence field must be zero unless either of the
+ * DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags is specified. When
+ * the ABSOLUTE flag is specified, the sequence field denotes the absolute
+ * vblank sequence when the flip should take effect. When the RELATIVE
+ * flag is specified, the sequence field denotes the relative (to the
+ * current one when the ioctl is called) vblank sequence when the flip
+ * should take effect. NOTE: DRM_IOCTL_WAIT_VBLANK must still be used to
+ * make sure the vblank sequence before the target one has passed before
+ * calling this ioctl. The purpose of the
+ * DRM_MODE_PAGE_FLIP_TARGET_ABSOLUTE/RELATIVE flags is merely to clarify
+ * the target for when code dealing with a page flip runs during a
+ * vertical blank period.
+ */
+
+struct drm_mode_crtc_page_flip_target {
+	__u32 crtc_id;
+	__u32 fb_id;
+	__u32 flags;
+	__u32 sequence;
+	__u64 user_data;
+};
+
+/**
+ * struct drm_mode_create_dumb - Create a KMS dumb buffer for scanout.
+ * @height: buffer height in pixels
+ * @width: buffer width in pixels
+ * @bpp: color mode
+ * @flags: must be zero
+ * @handle: buffer object handle
+ * @pitch: number of bytes between two consecutive lines
+ * @size: size of the whole buffer in bytes
+ *
+ * User-space fills @height, @width, @bpp and @flags. If the IOCTL succeeds,
+ * the kernel fills @handle, @pitch and @size.
+ *
+ * The value of @bpp is a color-mode number describing a specific format
+ * or a variant thereof. The value often corresponds to the number of bits
+ * per pixel for most modes, although there are exceptions. Each color mode
+ * maps to a DRM format plus a number of modes with similar pixel layout.
+ * Framebuffer layout is always linear.
+ *
+ * Support for all modes and formats is optional. Even if dumb-buffer
+ * creation with a certain color mode succeeds, it is not guaranteed that
+ * the DRM driver supports any of the related formats. Most drivers support
+ * a color mode of 32 with a format of DRM_FORMAT_XRGB8888 on their primary
+ * plane.
+ *
+ * +------------+------------------------+------------------------+
+ * | Color mode | Framebuffer format     | Compatible formats     |
+ * +============+========================+========================+
+ * |     32     |  * DRM_FORMAT_XRGB8888 |  * DRM_FORMAT_BGRX8888 |
+ * |            |                        |  * DRM_FORMAT_RGBX8888 |
+ * |            |                        |  * DRM_FORMAT_XBGR8888 |
+ * +------------+------------------------+------------------------+
+ * |     24     |  * DRM_FORMAT_RGB888   |  * DRM_FORMAT_BGR888   |
+ * +------------+------------------------+------------------------+
+ * |     16     |  * DRM_FORMAT_RGB565   |  * DRM_FORMAT_BGR565   |
+ * +------------+------------------------+------------------------+
+ * |     15     |  * DRM_FORMAT_XRGB1555 |  * DRM_FORMAT_BGRX1555 |
+ * |            |                        |  * DRM_FORMAT_RGBX1555 |
+ * |            |                        |  * DRM_FORMAT_XBGR1555 |
+ * +------------+------------------------+------------------------+
+ * |      8     |  * DRM_FORMAT_C8       |  * DRM_FORMAT_D8       |
+ * |            |                        |  * DRM_FORMAT_R8       |
+ * +------------+------------------------+------------------------+
+ * |      4     |  * DRM_FORMAT_C4       |  * DRM_FORMAT_D4       |
+ * |            |                        |  * DRM_FORMAT_R4       |
+ * +------------+------------------------+------------------------+
+ * |      2     |  * DRM_FORMAT_C2       |  * DRM_FORMAT_D2       |
+ * |            |                        |  * DRM_FORMAT_R2       |
+ * +------------+------------------------+------------------------+
+ * |      1     |  * DRM_FORMAT_C1       |  * DRM_FORMAT_D1       |
+ * |            |                        |  * DRM_FORMAT_R1       |
+ * +------------+------------------------+------------------------+
+ *
+ * Color modes of 10, 12, 15, 30 and 64 are only supported for use by
+ * legacy user space. Please don't use them in new code. Other modes
+ * are not support.
+ *
+ * Do not attempt to allocate anything but linear framebuffer memory
+ * with single-plane RGB data. Allocation of other framebuffer
+ * layouts requires dedicated ioctls in the respective DRM driver.
+ */
+struct drm_mode_create_dumb {
+	__u32 height;
+	__u32 width;
+	__u32 bpp;
+	__u32 flags;
+
+	__u32 handle;
+	__u32 pitch;
+	__u64 size;
+};
+
+/* set up for mmap of a dumb scanout buffer */
+struct drm_mode_map_dumb {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/**
+	 * Fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+};
+
+struct drm_mode_destroy_dumb {
+	__u32 handle;
+};
+
+/**
+ * DRM_MODE_ATOMIC_TEST_ONLY
+ *
+ * Do not apply the atomic commit, instead check whether the hardware supports
+ * this configuration.
+ *
+ * See &drm_mode_config_funcs.atomic_check for more details on test-only
+ * commits.
+ */
+#define DRM_MODE_ATOMIC_TEST_ONLY 0x0100
+/**
+ * DRM_MODE_ATOMIC_NONBLOCK
+ *
+ * Do not block while applying the atomic commit. The &DRM_IOCTL_MODE_ATOMIC
+ * IOCTL returns immediately instead of waiting for the changes to be applied
+ * in hardware. Note, the driver will still check that the update can be
+ * applied before retuning.
+ */
+#define DRM_MODE_ATOMIC_NONBLOCK  0x0200
+/**
+ * DRM_MODE_ATOMIC_ALLOW_MODESET
+ *
+ * Allow the update to result in temporary or transient visible artifacts while
+ * the update is being applied. Applying the update may also take significantly
+ * more time than a page flip. All visual artifacts will disappear by the time
+ * the update is completed, as signalled through the vblank event's timestamp
+ * (see struct drm_event_vblank).
+ *
+ * This flag must be set when the KMS update might cause visible artifacts.
+ * Without this flag such KMS update will return a EINVAL error. What kind of
+ * update may cause visible artifacts depends on the driver and the hardware.
+ * User-space that needs to know beforehand if an update might cause visible
+ * artifacts can use &DRM_MODE_ATOMIC_TEST_ONLY without
+ * &DRM_MODE_ATOMIC_ALLOW_MODESET to see if it fails.
+ *
+ * To the best of the driver's knowledge, visual artifacts are guaranteed to
+ * not appear when this flag is not set. Some sinks might display visual
+ * artifacts outside of the driver's control.
+ */
+#define DRM_MODE_ATOMIC_ALLOW_MODESET 0x0400
+
+/**
+ * DRM_MODE_ATOMIC_FLAGS
+ *
+ * Bitfield of flags accepted by the &DRM_IOCTL_MODE_ATOMIC IOCTL in
+ * &drm_mode_atomic.flags.
+ */
+#define DRM_MODE_ATOMIC_FLAGS (\
+		DRM_MODE_PAGE_FLIP_EVENT |\
+		DRM_MODE_PAGE_FLIP_ASYNC |\
+		DRM_MODE_ATOMIC_TEST_ONLY |\
+		DRM_MODE_ATOMIC_NONBLOCK |\
+		DRM_MODE_ATOMIC_ALLOW_MODESET)
+
+struct drm_mode_atomic {
+	__u32 flags;
+	__u32 count_objs;
+	__u64 objs_ptr;
+	__u64 count_props_ptr;
+	__u64 props_ptr;
+	__u64 prop_values_ptr;
+	__u64 reserved;
+	__u64 user_data;
+};
+
+struct drm_format_modifier_blob {
+#define FORMAT_BLOB_CURRENT 1
+	/* Version of this blob format */
+	__u32 version;
+
+	/* Flags */
+	__u32 flags;
+
+	/* Number of fourcc formats supported */
+	__u32 count_formats;
+
+	/* Where in this blob the formats exist (in bytes) */
+	__u32 formats_offset;
+
+	/* Number of drm_format_modifiers */
+	__u32 count_modifiers;
+
+	/* Where in this blob the modifiers exist (in bytes) */
+	__u32 modifiers_offset;
+
+	/* __u32 formats[] */
+	/* struct drm_format_modifier modifiers[] */
+};
+
+struct drm_format_modifier {
+	/* Bitmask of formats in get_plane format list this info applies to. The
+	 * offset allows a sliding window of which 64 formats (bits).
+	 *
+	 * Some examples:
+	 * In today's world with < 65 formats, and formats 0, and 2 are
+	 * supported
+	 * 0x0000000000000005
+	 *		  ^-offset = 0, formats = 5
+	 *
+	 * If the number formats grew to 128, and formats 98-102 are
+	 * supported with the modifier:
+	 *
+	 * 0x0000007c00000000 0000000000000000
+	 *		  ^
+	 *		  |__offset = 64, formats = 0x7c00000000
+	 *
+	 */
+	__u64 formats;
+	__u32 offset;
+	__u32 pad;
+
+	/* The modifier that applies to the >get_plane format list bitmask. */
+	__u64 modifier;
+};
+
+/**
+ * struct drm_mode_create_blob - Create New blob property
+ *
+ * Create a new 'blob' data property, copying length bytes from data pointer,
+ * and returning new blob ID.
+ */
+struct drm_mode_create_blob {
+	/** @data: Pointer to data to copy. */
+	__u64 data;
+	/** @length: Length of data to copy. */
+	__u32 length;
+	/** @blob_id: Return: new property ID. */
+	__u32 blob_id;
+};
+
+/**
+ * struct drm_mode_destroy_blob - Destroy user blob
+ * @blob_id: blob_id to destroy
+ *
+ * Destroy a user-created blob property.
+ *
+ * User-space can release blobs as soon as they do not need to refer to them by
+ * their blob object ID.  For instance, if you are using a MODE_ID blob in an
+ * atomic commit and you will not make another commit re-using the same ID, you
+ * can destroy the blob as soon as the commit has been issued, without waiting
+ * for it to complete.
+ */
+struct drm_mode_destroy_blob {
+	__u32 blob_id;
+};
+
+/**
+ * struct drm_mode_create_lease - Create lease
+ *
+ * Lease mode resources, creating another drm_master.
+ *
+ * The @object_ids array must reference at least one CRTC, one connector and
+ * one plane if &DRM_CLIENT_CAP_UNIVERSAL_PLANES is enabled. Alternatively,
+ * the lease can be completely empty.
+ */
+struct drm_mode_create_lease {
+	/** @object_ids: Pointer to array of object ids (__u32) */
+	__u64 object_ids;
+	/** @object_count: Number of object ids */
+	__u32 object_count;
+	/** @flags: flags for new FD (O_CLOEXEC, etc) */
+	__u32 flags;
+
+	/** @lessee_id: Return: unique identifier for lessee. */
+	__u32 lessee_id;
+	/** @fd: Return: file descriptor to new drm_master file */
+	__u32 fd;
+};
+
+/**
+ * struct drm_mode_list_lessees - List lessees
+ *
+ * List lesses from a drm_master.
+ */
+struct drm_mode_list_lessees {
+	/**
+	 * @count_lessees: Number of lessees.
+	 *
+	 * On input, provides length of the array.
+	 * On output, provides total number. No
+	 * more than the input number will be written
+	 * back, so two calls can be used to get
+	 * the size and then the data.
+	 */
+	__u32 count_lessees;
+	/** @pad: Padding. */
+	__u32 pad;
+
+	/**
+	 * @lessees_ptr: Pointer to lessees.
+	 *
+	 * Pointer to __u64 array of lessee ids
+	 */
+	__u64 lessees_ptr;
+};
+
+/**
+ * struct drm_mode_get_lease - Get Lease
+ *
+ * Get leased objects.
+ */
+struct drm_mode_get_lease {
+	/**
+	 * @count_objects: Number of leased objects.
+	 *
+	 * On input, provides length of the array.
+	 * On output, provides total number. No
+	 * more than the input number will be written
+	 * back, so two calls can be used to get
+	 * the size and then the data.
+	 */
+	__u32 count_objects;
+	/** @pad: Padding. */
+	__u32 pad;
+
+	/**
+	 * @objects_ptr: Pointer to objects.
+	 *
+	 * Pointer to __u32 array of object ids.
+	 */
+	__u64 objects_ptr;
+};
+
+/**
+ * struct drm_mode_revoke_lease - Revoke lease
+ */
+struct drm_mode_revoke_lease {
+	/** @lessee_id: Unique ID of lessee */
+	__u32 lessee_id;
+};
+
+/**
+ * struct drm_mode_rect - Two dimensional rectangle.
+ * @x1: Horizontal starting coordinate (inclusive).
+ * @y1: Vertical starting coordinate (inclusive).
+ * @x2: Horizontal ending coordinate (exclusive).
+ * @y2: Vertical ending coordinate (exclusive).
+ *
+ * With drm subsystem using struct drm_rect to manage rectangular area this
+ * export it to user-space.
+ *
+ * Currently used by drm_mode_atomic blob property FB_DAMAGE_CLIPS.
+ */
+struct drm_mode_rect {
+	__s32 x1;
+	__s32 y1;
+	__s32 x2;
+	__s32 y2;
+};
+
+/**
+ * struct drm_mode_closefb
+ * @fb_id: Framebuffer ID.
+ * @pad: Must be zero.
+ */
+struct drm_mode_closefb {
+	__u32 fb_id;
+	__u32 pad;
+};
+
+/*
+ * Put 16-bit ARGB values into a standard 64-bit representation that can be
+ * used for ioctl parameters, inter-driver communication, etc.
+ *
+ * If the component values being provided contain less than 16 bits of
+ * precision, use a conversion ratio to get a better color approximation.
+ * The ratio is computed as (2^16 - 1) / (2^bpc - 1), where bpc and 16 are
+ * the input and output precision, respectively.
+ * Also note bpc must be greater than 0.
+ */
+#define __DRM_ARGB64_PREP(c, shift)					\
+	(((__u64)(c) & __GENMASK(15, 0)) << (shift))
+
+#define __DRM_ARGB64_PREP_BPC(c, shift, bpc)				\
+({									\
+	__u16 mask = __GENMASK((bpc) - 1, 0);				\
+	__u16 conv = __KERNEL_DIV_ROUND_CLOSEST((mask & (c)) *		\
+						__GENMASK(15, 0), mask);\
+	__DRM_ARGB64_PREP(conv, shift);					\
+})
+
+#define DRM_ARGB64_PREP(alpha, red, green, blue)			\
+(									\
+	__DRM_ARGB64_PREP(alpha, 48) |					\
+	__DRM_ARGB64_PREP(red,   32) |					\
+	__DRM_ARGB64_PREP(green, 16) |					\
+	__DRM_ARGB64_PREP(blue,   0)					\
+)
+
+#define DRM_ARGB64_PREP_BPC(alpha, red, green, blue, bpc)		\
+({									\
+	__typeof__(bpc) __bpc = bpc;					\
+	__DRM_ARGB64_PREP_BPC(alpha, 48, __bpc) |			\
+	__DRM_ARGB64_PREP_BPC(red,   32, __bpc) |			\
+	__DRM_ARGB64_PREP_BPC(green, 16, __bpc) |			\
+	__DRM_ARGB64_PREP_BPC(blue,   0, __bpc);			\
+})
+
+/*
+ * Extract the specified color component from a standard 64-bit ARGB value.
+ *
+ * If the requested precision is less than 16 bits, make use of a conversion
+ * ratio calculated as (2^bpc - 1) / (2^16 - 1), where bpc and 16 are the
+ * output and input precision, respectively.
+ *
+ * If speed is more important than accuracy, use DRM_ARGB64_GET*_BPCS()
+ * instead of DRM_ARGB64_GET*_BPC() in order to replace the expensive
+ * division with a simple bit right-shift operation.
+ */
+#define __DRM_ARGB64_GET(c, shift)					\
+	((__u16)(((__u64)(c) >> (shift)) & __GENMASK(15, 0)))
+
+#define __DRM_ARGB64_GET_BPC(c, shift, bpc)				\
+({									\
+	__u16 comp = __DRM_ARGB64_GET(c, shift);			\
+	__KERNEL_DIV_ROUND_CLOSEST(comp * __GENMASK((bpc) - 1, 0),	\
+				   __GENMASK(15, 0));			\
+})
+
+#define __DRM_ARGB64_GET_BPCS(c, shift, bpc)				\
+	(__DRM_ARGB64_GET(c, shift) >> (16 - (bpc)))
+
+#define DRM_ARGB64_GETA(c)		__DRM_ARGB64_GET(c, 48)
+#define DRM_ARGB64_GETR(c)		__DRM_ARGB64_GET(c, 32)
+#define DRM_ARGB64_GETG(c)		__DRM_ARGB64_GET(c, 16)
+#define DRM_ARGB64_GETB(c)		__DRM_ARGB64_GET(c, 0)
+
+#define DRM_ARGB64_GETA_BPC(c, bpc)	__DRM_ARGB64_GET_BPC(c, 48, bpc)
+#define DRM_ARGB64_GETR_BPC(c, bpc)	__DRM_ARGB64_GET_BPC(c, 32, bpc)
+#define DRM_ARGB64_GETG_BPC(c, bpc)	__DRM_ARGB64_GET_BPC(c, 16, bpc)
+#define DRM_ARGB64_GETB_BPC(c, bpc)	__DRM_ARGB64_GET_BPC(c, 0, bpc)
+
+#define DRM_ARGB64_GETA_BPCS(c, bpc)	__DRM_ARGB64_GET_BPCS(c, 48, bpc)
+#define DRM_ARGB64_GETR_BPCS(c, bpc)	__DRM_ARGB64_GET_BPCS(c, 32, bpc)
+#define DRM_ARGB64_GETG_BPCS(c, bpc)	__DRM_ARGB64_GET_BPCS(c, 16, bpc)
+#define DRM_ARGB64_GETB_BPCS(c, bpc)	__DRM_ARGB64_GET_BPCS(c, 0, bpc)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
new file mode 100644
index 000000000..218a3ee86
--- /dev/null
+++ b/include/uapi/drm/drm_ras.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/drm_ras.yaml */
+/* YNL-GEN uapi header */
+/* To regenerate run: tools/net/ynl/ynl-regen.sh */
+
+#ifndef _UAPI_LINUX_DRM_RAS_H
+#define _UAPI_LINUX_DRM_RAS_H
+
+#define DRM_RAS_FAMILY_NAME	"drm-ras"
+#define DRM_RAS_FAMILY_VERSION	1
+
+/*
+ * Type of the node. Currently, only error-counter nodes are supported, which
+ * expose reliability counters for a hardware/software component.
+ */
+enum drm_ras_node_type {
+	DRM_RAS_NODE_TYPE_ERROR_COUNTER = 1,
+};
+
+enum {
+	DRM_RAS_A_NODE_ATTRS_NODE_ID = 1,
+	DRM_RAS_A_NODE_ATTRS_DEVICE_NAME,
+	DRM_RAS_A_NODE_ATTRS_NODE_NAME,
+	DRM_RAS_A_NODE_ATTRS_NODE_TYPE,
+
+	__DRM_RAS_A_NODE_ATTRS_MAX,
+	DRM_RAS_A_NODE_ATTRS_MAX = (__DRM_RAS_A_NODE_ATTRS_MAX - 1)
+};
+
+enum {
+	DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID = 1,
+	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID,
+	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_NAME,
+	DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_VALUE,
+
+	__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX,
+	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
+};
+
+enum {
+	DRM_RAS_CMD_LIST_NODES = 1,
+	DRM_RAS_CMD_GET_ERROR_COUNTER,
+	DRM_RAS_CMD_CLEAR_ERROR_COUNTER,
+
+	__DRM_RAS_CMD_MAX,
+	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
+};
+
+#endif /* _UAPI_LINUX_DRM_RAS_H */
diff --git a/include/uapi/drm/drm_sarea.h b/include/uapi/drm/drm_sarea.h
new file mode 100644
index 000000000..1e38d0283
--- /dev/null
+++ b/include/uapi/drm/drm_sarea.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: MIT */
+/**
+ * \file drm_sarea.h
+ * \brief SAREA definitions
+ *
+ * \author Michel Dänzer <michel@daenzer.net>
+ */
+
+/*
+ * Copyright 2002 Tungsten Graphics, Inc., Cedar Park, Texas.
+ * All Rights Reserved.
+ */
+
+#ifndef _DRM_SAREA_H_
+#define _DRM_SAREA_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* SAREA area needs to be at least a page */
+#if defined(__alpha__)
+#define SAREA_MAX                       0x2000U
+#elif defined(__mips__)
+#define SAREA_MAX                       0x4000U
+#elif defined(__ia64__)
+#define SAREA_MAX                       0x10000U	/* 64kB */
+#else
+/* Intel 830M driver needs at least 8k SAREA */
+#define SAREA_MAX                       0x2000U
+#endif
+
+/** Maximum number of drawables in the SAREA */
+#define SAREA_MAX_DRAWABLES		256
+
+#define SAREA_DRAWABLE_CLAIMED_ENTRY    0x80000000
+
+/** SAREA drawable */
+struct drm_sarea_drawable {
+	unsigned int stamp;
+	unsigned int flags;
+};
+
+/** SAREA frame */
+struct drm_sarea_frame {
+	unsigned int x;
+	unsigned int y;
+	unsigned int width;
+	unsigned int height;
+	unsigned int fullscreen;
+};
+
+/** SAREA */
+struct drm_sarea {
+    /** first thing is always the DRM locking structure */
+	struct drm_hw_lock lock;
+    /** \todo Use readers/writer lock for drm_sarea::drawable_lock */
+	struct drm_hw_lock drawable_lock;
+	struct drm_sarea_drawable drawableTable[SAREA_MAX_DRAWABLES];	/**< drawables */
+	struct drm_sarea_frame frame;	/**< frame */
+	drm_context_t dummy_context;
+};
+
+#ifndef __KERNEL__
+typedef struct drm_sarea_drawable drm_sarea_drawable_t;
+typedef struct drm_sarea_frame drm_sarea_frame_t;
+typedef struct drm_sarea drm_sarea_t;
+#endif
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif				/* _DRM_SAREA_H_ */
diff --git a/include/uapi/drm/ethosu_accel.h b/include/uapi/drm/ethosu_accel.h
new file mode 100644
index 000000000..5b97d59a7
--- /dev/null
+++ b/include/uapi/drm/ethosu_accel.h
@@ -0,0 +1,319 @@
+/* SPDX-License-Identifier: MIT */
+/* Copyright (C) 2025 Arm, Ltd. */
+#ifndef _ETHOSU_DRM_H_
+#define _ETHOSU_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * DOC: IOCTL IDs
+ *
+ * enum drm_ethosu_ioctl_id - IOCTL IDs
+ *
+ * Place new ioctls at the end, don't re-order, don't replace or remove entries.
+ *
+ * These IDs are not meant to be used directly. Use the DRM_IOCTL_ETHOSU_xxx
+ * definitions instead.
+ */
+enum drm_ethosu_ioctl_id {
+	/** @DRM_ETHOSU_DEV_QUERY: Query device information. */
+	DRM_ETHOSU_DEV_QUERY = 0,
+
+	/** @DRM_ETHOSU_BO_CREATE: Create a buffer object. */
+	DRM_ETHOSU_BO_CREATE,
+
+	/** @DRM_ETHOSU_BO_WAIT: Wait on a buffer object's fence. */
+	DRM_ETHOSU_BO_WAIT,
+
+	/**
+	 * @DRM_ETHOSU_BO_MMAP_OFFSET: Get the file offset to pass to
+	 * mmap to map a GEM object.
+	 */
+	DRM_ETHOSU_BO_MMAP_OFFSET,
+
+	/**
+	 * @DRM_ETHOSU_CMDSTREAM_BO_CREATE: Create a command stream buffer
+	 * object.
+	 */
+	DRM_ETHOSU_CMDSTREAM_BO_CREATE,
+
+	/** @DRM_ETHOSU_SUBMIT: Submit a job and BOs to run. */
+	DRM_ETHOSU_SUBMIT,
+
+	DRM_ETHOSU_PERFMON_CREATE,
+	DRM_ETHOSU_PERFMON_DESTROY,
+	DRM_ETHOSU_PERFMON_GET_VALUES,
+	DRM_ETHOSU_PERFMON_SET_GLOBAL,
+};
+
+/**
+ * DOC: IOCTL arguments
+ */
+
+/**
+ * enum drm_ethosu_dev_query_type - Query type
+ *
+ * Place new types at the end, don't re-order, don't remove or replace.
+ */
+enum drm_ethosu_dev_query_type {
+	/** @DRM_ETHOSU_DEV_QUERY_NPU_INFO: Query NPU information. */
+	DRM_ETHOSU_DEV_QUERY_NPU_INFO = 0,
+};
+
+/**
+ * struct drm_ethosu_gpu_info - NPU information
+ *
+ * Structure grouping all queryable information relating to the NPU.
+ */
+struct drm_ethosu_npu_info {
+	/** @id : NPU ID. */
+	__u32 id;
+#define DRM_ETHOSU_ARCH_MAJOR(x)			((x) >> 28)
+#define DRM_ETHOSU_ARCH_MINOR(x)			(((x) >> 20) & 0xff)
+#define DRM_ETHOSU_ARCH_PATCH(x)			(((x) >> 16) & 0xf)
+#define DRM_ETHOSU_PRODUCT_MAJOR(x)		(((x) >> 12) & 0xf)
+#define DRM_ETHOSU_VERSION_MAJOR(x)		(((x) >> 8) & 0xf)
+#define DRM_ETHOSU_VERSION_MINOR(x)		(((x) >> 4) & 0xff)
+#define DRM_ETHOSU_VERSION_STATUS(x)		((x) & 0xf)
+
+	/** @gpu_rev: GPU revision. */
+	__u32 config;
+
+	__u32 sram_size;
+	__u32 pmu_counters;
+};
+
+/**
+ * struct drm_ethosu_dev_query - Arguments passed to DRM_ETHOSU_IOCTL_DEV_QUERY
+ */
+struct drm_ethosu_dev_query {
+	/** @type: the query type (see drm_ethosu_dev_query_type). */
+	__u32 type;
+
+	/**
+	 * @size: size of the type being queried.
+	 *
+	 * If pointer is NULL, size is updated by the driver to provide the
+	 * output structure size. If pointer is not NULL, the driver will
+	 * only copy min(size, actual_structure_size) bytes to the pointer,
+	 * and update the size accordingly. This allows us to extend query
+	 * types without breaking userspace.
+	 */
+	__u32 size;
+
+	/**
+	 * @pointer: user pointer to a query type struct.
+	 *
+	 * Pointer can be NULL, in which case, nothing is copied, but the
+	 * actual structure size is returned. If not NULL, it must point to
+	 * a location that's large enough to hold size bytes.
+	 */
+	__u64 pointer;
+};
+
+/**
+ * enum drm_ethosu_bo_flags - Buffer object flags, passed at creation time.
+ */
+enum drm_ethosu_bo_flags {
+	/**
+	 * @DRM_ETHOSU_BO_NO_MMAP: The buffer object will never be CPU-mapped
+	 * in userspace.
+	 */
+	DRM_ETHOSU_BO_NO_MMAP = (1 << 0),
+};
+
+/**
+ * struct drm_ethosu_bo_create - Arguments passed to DRM_IOCTL_ETHOSU_BO_CREATE.
+ */
+struct drm_ethosu_bo_create {
+	/**
+	 * @size: Requested size for the object
+	 *
+	 * The (page-aligned) allocated size for the object will be returned.
+	 */
+	__u64 size;
+
+	/**
+	 * @flags: Flags. Must be a combination of drm_ethosu_bo_flags flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @handle: Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+};
+
+/**
+ * struct drm_ethosu_bo_mmap_offset - Arguments passed to DRM_IOCTL_ETHOSU_BO_MMAP_OFFSET.
+ */
+struct drm_ethosu_bo_mmap_offset {
+	/** @handle: Handle of the object we want an mmap offset for. */
+	__u32 handle;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+
+	/** @offset: The fake offset to use for subsequent mmap calls. */
+	__u64 offset;
+};
+
+/**
+ * struct drm_ethosu_wait_bo - ioctl argument for waiting for
+ * completion of the last DRM_ETHOSU_SUBMIT on a BO.
+ *
+ * This is useful for cases where multiple processes might be
+ * rendering to a BO and you want to wait for all rendering to be
+ * completed.
+ */
+struct drm_ethosu_bo_wait {
+	__u32 handle;
+	__u32 pad;
+	__s64 timeout_ns;	/* absolute */
+};
+
+struct drm_ethosu_cmdstream_bo_create {
+	/* Size of the data argument. */
+	__u32 size;
+
+	/* Flags, currently must be 0. */
+	__u32 flags;
+
+	/* Pointer to the data. */
+	__u64 data;
+
+	/** Returned GEM handle for the BO. */
+	__u32 handle;
+
+	/* Pad, must be 0. */
+	__u32 pad;
+};
+
+/**
+ * struct drm_ethosu_job - A job to be run on the NPU
+ *
+ * The kernel will schedule the execution of this job taking into account its
+ * dependencies with other jobs. All tasks in the same job will be executed
+ * sequentially on the same core, to benefit from memory residency in SRAM.
+ */
+struct drm_ethosu_job {
+	/** Input: BO handle for cmdstream. */
+	__u32 cmd_bo;
+
+	/** Input: Amount of SRAM to use. */
+	__u32 sram_size;
+
+#define ETHOSU_MAX_REGIONS	8
+	/** Input: Array of BO handles for each region. */
+	__u32 region_bo_handles[ETHOSU_MAX_REGIONS];
+};
+
+/**
+ * struct drm_ethosu_submit - ioctl argument for submitting commands to the NPU.
+ *
+ * The kernel will schedule the execution of these jobs in dependency order.
+ */
+struct drm_ethosu_submit {
+	/** Input: Pointer to an array of struct drm_ethosu_job. */
+	__u64 jobs;
+
+	/** Input: Number of jobs passed in. */
+	__u32 job_count;
+
+	/** Input: Id returned by DRM_ETHOSU_PERFMON_CREATE */
+	__u32 perfmon_id;
+};
+
+#define DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS	8
+#define DRM_ETHOSU_MAX_PERF_COUNTERS \
+	(DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS + 1)
+
+struct drm_ethosu_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u16 counters[DRM_ETHOSU_MAX_PERF_EVENT_COUNTERS];
+};
+
+struct drm_ethosu_perfmon_destroy {
+	__u32 id;
+	__u32 pad;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of (ncounters + 1) u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed.
+ */
+struct drm_ethosu_perfmon_get_values {
+	__u32 id;
+	__u32 pad;
+	__u64 values_ptr;
+};
+
+#define DRM_ETHOSU_PERFMON_CLEAR_GLOBAL    0x0001
+
+/**
+ * struct drm_ethosu_perfmon_set_global - ioctl to define a global performance
+ * monitor
+ *
+ * The global performance monitor will be used for all jobs. If a global
+ * performance monitor is defined, jobs with a self-defined performance
+ * monitor won't be allowed.
+ */
+struct drm_ethosu_perfmon_set_global {
+	__u32 flags;
+	__u32 id;
+};
+
+/**
+ * DRM_IOCTL_ETHOSU() - Build a ethosu IOCTL number
+ * @__access: Access type. Must be R, W or RW.
+ * @__id: One of the DRM_ETHOSU_xxx id.
+ * @__type: Suffix of the type being passed to the IOCTL.
+ *
+ * Don't use this macro directly, use the DRM_IOCTL_ETHOSU_xxx
+ * values instead.
+ *
+ * Return: An IOCTL number to be passed to ioctl() from userspace.
+ */
+#define DRM_IOCTL_ETHOSU(__access, __id, __type) \
+	DRM_IO ## __access(DRM_COMMAND_BASE + DRM_ETHOSU_ ## __id, \
+			   struct drm_ethosu_ ## __type)
+
+enum {
+	DRM_IOCTL_ETHOSU_DEV_QUERY =
+		DRM_IOCTL_ETHOSU(WR, DEV_QUERY, dev_query),
+	DRM_IOCTL_ETHOSU_BO_CREATE =
+		DRM_IOCTL_ETHOSU(WR, BO_CREATE, bo_create),
+	DRM_IOCTL_ETHOSU_BO_WAIT =
+		DRM_IOCTL_ETHOSU(WR, BO_WAIT, bo_wait),
+	DRM_IOCTL_ETHOSU_BO_MMAP_OFFSET =
+		DRM_IOCTL_ETHOSU(WR, BO_MMAP_OFFSET, bo_mmap_offset),
+	DRM_IOCTL_ETHOSU_CMDSTREAM_BO_CREATE =
+		DRM_IOCTL_ETHOSU(WR, CMDSTREAM_BO_CREATE, cmdstream_bo_create),
+	DRM_IOCTL_ETHOSU_SUBMIT =
+		DRM_IOCTL_ETHOSU(WR, SUBMIT, submit),
+	DRM_IOCTL_ETHOSU_PERFMON_CREATE =
+		DRM_IOCTL_ETHOSU(WR, PERFMON_CREATE, perfmon_create),
+	DRM_IOCTL_ETHOSU_PERFMON_DESTROY =
+		DRM_IOCTL_ETHOSU(WR, PERFMON_DESTROY, perfmon_destroy),
+	DRM_IOCTL_ETHOSU_PERFMON_GET_VALUES =
+		DRM_IOCTL_ETHOSU(WR, PERFMON_GET_VALUES, perfmon_get_values),
+	DRM_IOCTL_ETHOSU_PERFMON_SET_GLOBAL =
+		DRM_IOCTL_ETHOSU(WR, PERFMON_SET_GLOBAL, perfmon_set_global),
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _ETHOSU_DRM_H_ */
diff --git a/include/uapi/drm/etnaviv_drm.h b/include/uapi/drm/etnaviv_drm.h
new file mode 100644
index 000000000..af024d904
--- /dev/null
+++ b/include/uapi/drm/etnaviv_drm.h
@@ -0,0 +1,300 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2015 Etnaviv Project
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __ETNAVIV_DRM_H__
+#define __ETNAVIV_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:
+ *  1) Do not use pointers, use __u64 instead for 32 bit / 64 bit
+ *     user/kernel compatibility
+ *  2) Keep fields aligned to their size
+ *  3) Because of how drm_ioctl() works, we can add new fields at
+ *     the end of an ioctl if some care is taken: drm_ioctl() will
+ *     zero out the new fields at the tail of the ioctl, so a zero
+ *     value should have a backwards compatible meaning.  And for
+ *     output params, userspace won't see the newly added output
+ *     fields.. so that has to be somehow ok.
+ */
+
+/* timeouts are specified in clock-monotonic absolute times (to simplify
+ * restarting interrupted ioctls).  The following struct is logically the
+ * same as 'struct timespec' but 32/64b ABI safe.
+ */
+struct drm_etnaviv_timespec {
+	__s64 tv_sec;          /* seconds */
+	__s64 tv_nsec;         /* nanoseconds */
+};
+
+#define ETNAVIV_PARAM_GPU_MODEL                     0x01
+#define ETNAVIV_PARAM_GPU_REVISION                  0x02
+#define ETNAVIV_PARAM_GPU_FEATURES_0                0x03
+#define ETNAVIV_PARAM_GPU_FEATURES_1                0x04
+#define ETNAVIV_PARAM_GPU_FEATURES_2                0x05
+#define ETNAVIV_PARAM_GPU_FEATURES_3                0x06
+#define ETNAVIV_PARAM_GPU_FEATURES_4                0x07
+#define ETNAVIV_PARAM_GPU_FEATURES_5                0x08
+#define ETNAVIV_PARAM_GPU_FEATURES_6                0x09
+#define ETNAVIV_PARAM_GPU_FEATURES_7                0x0a
+#define ETNAVIV_PARAM_GPU_FEATURES_8                0x0b
+#define ETNAVIV_PARAM_GPU_FEATURES_9                0x0c
+#define ETNAVIV_PARAM_GPU_FEATURES_10               0x0d
+#define ETNAVIV_PARAM_GPU_FEATURES_11               0x0e
+#define ETNAVIV_PARAM_GPU_FEATURES_12               0x0f
+
+#define ETNAVIV_PARAM_GPU_STREAM_COUNT              0x10
+#define ETNAVIV_PARAM_GPU_REGISTER_MAX              0x11
+#define ETNAVIV_PARAM_GPU_THREAD_COUNT              0x12
+#define ETNAVIV_PARAM_GPU_VERTEX_CACHE_SIZE         0x13
+#define ETNAVIV_PARAM_GPU_SHADER_CORE_COUNT         0x14
+#define ETNAVIV_PARAM_GPU_PIXEL_PIPES               0x15
+#define ETNAVIV_PARAM_GPU_VERTEX_OUTPUT_BUFFER_SIZE 0x16
+#define ETNAVIV_PARAM_GPU_BUFFER_SIZE               0x17
+#define ETNAVIV_PARAM_GPU_INSTRUCTION_COUNT         0x18
+#define ETNAVIV_PARAM_GPU_NUM_CONSTANTS             0x19
+#define ETNAVIV_PARAM_GPU_NUM_VARYINGS              0x1a
+#define ETNAVIV_PARAM_SOFTPIN_START_ADDR            0x1b
+#define ETNAVIV_PARAM_GPU_PRODUCT_ID                0x1c
+#define ETNAVIV_PARAM_GPU_CUSTOMER_ID               0x1d
+#define ETNAVIV_PARAM_GPU_ECO_ID                    0x1e
+
+#define ETNA_MAX_PIPES 4
+
+struct drm_etnaviv_param {
+	__u32 pipe;           /* in */
+	__u32 param;          /* in, ETNAVIV_PARAM_x */
+	__u64 value;          /* out (get_param) or in (set_param) */
+};
+
+/*
+ * GEM buffers:
+ */
+
+#define ETNA_BO_CACHE_MASK   0x000f0000
+/* cache modes */
+#define ETNA_BO_CACHED       0x00010000
+#define ETNA_BO_WC           0x00020000
+#define ETNA_BO_UNCACHED     0x00040000
+/* map flags */
+#define ETNA_BO_FORCE_MMU    0x00100000
+
+struct drm_etnaviv_gem_new {
+	__u64 size;           /* in */
+	__u32 flags;          /* in, mask of ETNA_BO_x */
+	__u32 handle;         /* out */
+};
+
+struct drm_etnaviv_gem_info {
+	__u32 handle;         /* in */
+	__u32 pad;
+	__u64 offset;         /* out, offset to pass to mmap() */
+};
+
+#define ETNA_PREP_READ        0x01
+#define ETNA_PREP_WRITE       0x02
+#define ETNA_PREP_NOSYNC      0x04
+
+struct drm_etnaviv_gem_cpu_prep {
+	__u32 handle;         /* in */
+	__u32 op;             /* in, mask of ETNA_PREP_x */
+	struct drm_etnaviv_timespec timeout;   /* in */
+};
+
+struct drm_etnaviv_gem_cpu_fini {
+	__u32 handle;         /* in */
+	__u32 flags;          /* in, placeholder for now, no defined values */
+};
+
+/*
+ * Cmdstream Submission:
+ */
+
+/* The value written into the cmdstream is logically:
+ * relocbuf->gpuaddr + reloc_offset
+ *
+ * NOTE that reloc's must be sorted by order of increasing submit_offset,
+ * otherwise EINVAL.
+ */
+struct drm_etnaviv_gem_submit_reloc {
+	__u32 submit_offset;  /* in, offset from submit_bo */
+	__u32 reloc_idx;      /* in, index of reloc_bo buffer */
+	__u64 reloc_offset;   /* in, offset from start of reloc_bo */
+	__u32 flags;          /* in, placeholder for now, no defined values */
+};
+
+/* Each buffer referenced elsewhere in the cmdstream submit (ie. the
+ * cmdstream buffer(s) themselves or reloc entries) has one (and only
+ * one) entry in the submit->bos[] table.
+ *
+ * As a optimization, the current buffer (gpu virtual address) can be
+ * passed back through the 'presumed' field.  If on a subsequent reloc,
+ * userspace passes back a 'presumed' address that is still valid,
+ * then patching the cmdstream for this entry is skipped.  This can
+ * avoid kernel needing to map/access the cmdstream bo in the common
+ * case.
+ * If the submit is a softpin submit (ETNA_SUBMIT_SOFTPIN) the 'presumed'
+ * field is interpreted as the fixed location to map the bo into the gpu
+ * virtual address space. If the kernel is unable to map the buffer at
+ * this location the submit will fail. This means userspace is responsible
+ * for the whole gpu virtual address management.
+ */
+#define ETNA_SUBMIT_BO_READ             0x0001
+#define ETNA_SUBMIT_BO_WRITE            0x0002
+struct drm_etnaviv_gem_submit_bo {
+	__u32 flags;          /* in, mask of ETNA_SUBMIT_BO_x */
+	__u32 handle;         /* in, GEM handle */
+	__u64 presumed;       /* in/out, presumed buffer address */
+};
+
+/* performance monitor request (pmr) */
+#define ETNA_PM_PROCESS_PRE             0x0001
+#define ETNA_PM_PROCESS_POST            0x0002
+struct drm_etnaviv_gem_submit_pmr {
+	__u32 flags;          /* in, when to process request (ETNA_PM_PROCESS_x) */
+	__u8  domain;         /* in, pm domain */
+	__u8  pad;
+	__u16 signal;         /* in, pm signal */
+	__u32 sequence;       /* in, sequence number */
+	__u32 read_offset;    /* in, offset from read_bo */
+	__u32 read_idx;       /* in, index of read_bo buffer */
+};
+
+/* Each cmdstream submit consists of a table of buffers involved, and
+ * one or more cmdstream buffers.  This allows for conditional execution
+ * (context-restore), and IB buffers needed for per tile/bin draw cmds.
+ */
+#define ETNA_SUBMIT_NO_IMPLICIT         0x0001
+#define ETNA_SUBMIT_FENCE_FD_IN         0x0002
+#define ETNA_SUBMIT_FENCE_FD_OUT        0x0004
+#define ETNA_SUBMIT_SOFTPIN             0x0008
+#define ETNA_SUBMIT_FLAGS		(ETNA_SUBMIT_NO_IMPLICIT | \
+					 ETNA_SUBMIT_FENCE_FD_IN | \
+					 ETNA_SUBMIT_FENCE_FD_OUT| \
+					 ETNA_SUBMIT_SOFTPIN)
+#define ETNA_PIPE_3D      0x00
+#define ETNA_PIPE_2D      0x01
+#define ETNA_PIPE_VG      0x02
+struct drm_etnaviv_gem_submit {
+	__u32 fence;          /* out */
+	__u32 pipe;           /* in */
+	__u32 exec_state;     /* in, initial execution state (ETNA_PIPE_x) */
+	__u32 nr_bos;         /* in, number of submit_bo's */
+	__u32 nr_relocs;      /* in, number of submit_reloc's */
+	__u32 stream_size;    /* in, cmdstream size */
+	__u64 bos;            /* in, ptr to array of submit_bo's */
+	__u64 relocs;         /* in, ptr to array of submit_reloc's */
+	__u64 stream;         /* in, ptr to cmdstream */
+	__u32 flags;          /* in, mask of ETNA_SUBMIT_x */
+	__s32 fence_fd;       /* in/out, fence fd (see ETNA_SUBMIT_FENCE_FD_x) */
+	__u64 pmrs;           /* in, ptr to array of submit_pmr's */
+	__u32 nr_pmrs;        /* in, number of submit_pmr's */
+	__u32 pad;
+};
+
+/* The normal way to synchronize with the GPU is just to CPU_PREP on
+ * a buffer if you need to access it from the CPU (other cmdstream
+ * submission from same or other contexts, PAGE_FLIP ioctl, etc, all
+ * handle the required synchronization under the hood).  This ioctl
+ * mainly just exists as a way to implement the gallium pipe_fence
+ * APIs without requiring a dummy bo to synchronize on.
+ */
+#define ETNA_WAIT_NONBLOCK      0x01
+struct drm_etnaviv_wait_fence {
+	__u32 pipe;           /* in */
+	__u32 fence;          /* in */
+	__u32 flags;          /* in, mask of ETNA_WAIT_x */
+	__u32 pad;
+	struct drm_etnaviv_timespec timeout;   /* in */
+};
+
+#define ETNA_USERPTR_READ	0x01
+#define ETNA_USERPTR_WRITE	0x02
+struct drm_etnaviv_gem_userptr {
+	__u64 user_ptr;	/* in, page aligned user pointer */
+	__u64 user_size;	/* in, page aligned user size */
+	__u32 flags;		/* in, flags */
+	__u32 handle;	/* out, non-zero handle */
+};
+
+struct drm_etnaviv_gem_wait {
+	__u32 pipe;				/* in */
+	__u32 handle;				/* in, bo to be waited for */
+	__u32 flags;				/* in, mask of ETNA_WAIT_x  */
+	__u32 pad;
+	struct drm_etnaviv_timespec timeout;	/* in */
+};
+
+/*
+ * Performance Monitor (PM):
+ */
+
+struct drm_etnaviv_pm_domain {
+	__u32 pipe;       /* in */
+	__u8  iter;       /* in/out, select pm domain at index iter */
+	__u8  id;         /* out, id of domain */
+	__u16 nr_signals; /* out, how many signals does this domain provide */
+	char  name[64];   /* out, name of domain */
+};
+
+struct drm_etnaviv_pm_signal {
+	__u32 pipe;       /* in */
+	__u8  domain;     /* in, pm domain index */
+	__u8  pad;
+	__u16 iter;       /* in/out, select pm source at index iter */
+	__u16 id;         /* out, id of signal */
+	char  name[64];   /* out, name of domain */
+};
+
+#define DRM_ETNAVIV_GET_PARAM          0x00
+/* placeholder:
+#define DRM_ETNAVIV_SET_PARAM          0x01
+ */
+#define DRM_ETNAVIV_GEM_NEW            0x02
+#define DRM_ETNAVIV_GEM_INFO           0x03
+#define DRM_ETNAVIV_GEM_CPU_PREP       0x04
+#define DRM_ETNAVIV_GEM_CPU_FINI       0x05
+#define DRM_ETNAVIV_GEM_SUBMIT         0x06
+#define DRM_ETNAVIV_WAIT_FENCE         0x07
+#define DRM_ETNAVIV_GEM_USERPTR        0x08
+#define DRM_ETNAVIV_GEM_WAIT           0x09
+#define DRM_ETNAVIV_PM_QUERY_DOM       0x0a
+#define DRM_ETNAVIV_PM_QUERY_SIG       0x0b
+#define DRM_ETNAVIV_NUM_IOCTLS         0x0c
+
+#define DRM_IOCTL_ETNAVIV_GET_PARAM    DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GET_PARAM, struct drm_etnaviv_param)
+#define DRM_IOCTL_ETNAVIV_GEM_NEW      DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_NEW, struct drm_etnaviv_gem_new)
+#define DRM_IOCTL_ETNAVIV_GEM_INFO     DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_INFO, struct drm_etnaviv_gem_info)
+#define DRM_IOCTL_ETNAVIV_GEM_CPU_PREP DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_CPU_PREP, struct drm_etnaviv_gem_cpu_prep)
+#define DRM_IOCTL_ETNAVIV_GEM_CPU_FINI DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_CPU_FINI, struct drm_etnaviv_gem_cpu_fini)
+#define DRM_IOCTL_ETNAVIV_GEM_SUBMIT   DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_SUBMIT, struct drm_etnaviv_gem_submit)
+#define DRM_IOCTL_ETNAVIV_WAIT_FENCE   DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_WAIT_FENCE, struct drm_etnaviv_wait_fence)
+#define DRM_IOCTL_ETNAVIV_GEM_USERPTR  DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_USERPTR, struct drm_etnaviv_gem_userptr)
+#define DRM_IOCTL_ETNAVIV_GEM_WAIT     DRM_IOW(DRM_COMMAND_BASE + DRM_ETNAVIV_GEM_WAIT, struct drm_etnaviv_gem_wait)
+#define DRM_IOCTL_ETNAVIV_PM_QUERY_DOM DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_PM_QUERY_DOM, struct drm_etnaviv_pm_domain)
+#define DRM_IOCTL_ETNAVIV_PM_QUERY_SIG DRM_IOWR(DRM_COMMAND_BASE + DRM_ETNAVIV_PM_QUERY_SIG, struct drm_etnaviv_pm_signal)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __ETNAVIV_DRM_H__ */
diff --git a/include/uapi/drm/exynos_drm.h b/include/uapi/drm/exynos_drm.h
new file mode 100644
index 000000000..a51aa1c61
--- /dev/null
+++ b/include/uapi/drm/exynos_drm.h
@@ -0,0 +1,424 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/* exynos_drm.h
+ *
+ * Copyright (c) 2011 Samsung Electronics Co., Ltd.
+ * Authors:
+ *	Inki Dae <inki.dae@samsung.com>
+ *	Joonyoung Shim <jy0922.shim@samsung.com>
+ *	Seung-Woo Kim <sw0312.kim@samsung.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+
+#ifndef _UAPI_EXYNOS_DRM_H_
+#define _UAPI_EXYNOS_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * User-desired buffer creation information structure.
+ *
+ * @size: user-desired memory allocation size.
+ *	- this size value would be page-aligned internally.
+ * @flags: user request for setting memory type or cache attributes.
+ * @handle: returned a handle to created gem object.
+ *	- this handle will be set by gem module of kernel side.
+ */
+struct drm_exynos_gem_create {
+	__u64 size;
+	__u32 flags;
+	__u32 handle;
+};
+
+/**
+ * A structure for getting a fake-offset that can be used with mmap.
+ *
+ * @handle: handle of gem object.
+ * @reserved: just padding to be 64-bit aligned.
+ * @offset: a fake-offset of gem object.
+ */
+struct drm_exynos_gem_map {
+	__u32 handle;
+	__u32 reserved;
+	__u64 offset;
+};
+
+/**
+ * A structure to gem information.
+ *
+ * @handle: a handle to gem object created.
+ * @flags: flag value including memory type and cache attribute and
+ *	this value would be set by driver.
+ * @size: size to memory region allocated by gem and this size would
+ *	be set by driver.
+ */
+struct drm_exynos_gem_info {
+	__u32 handle;
+	__u32 flags;
+	__u64 size;
+};
+
+/**
+ * A structure for user connection request of virtual display.
+ *
+ * @connection: indicate whether doing connection or not by user.
+ * @extensions: if this value is 1 then the vidi driver would need additional
+ *	128bytes edid data.
+ * @edid: the edid data pointer from user side.
+ */
+struct drm_exynos_vidi_connection {
+	__u32 connection;
+	__u32 extensions;
+	__u64 edid;
+};
+
+/* memory type definitions. */
+enum e_drm_exynos_gem_mem_type {
+	/* Physically Continuous memory and used as default. */
+	EXYNOS_BO_CONTIG	= 0 << 0,
+	/* Physically Non-Continuous memory. */
+	EXYNOS_BO_NONCONTIG	= 1 << 0,
+	/* non-cachable mapping and used as default. */
+	EXYNOS_BO_NONCACHABLE	= 0 << 1,
+	/* cachable mapping. */
+	EXYNOS_BO_CACHABLE	= 1 << 1,
+	/* write-combine mapping. */
+	EXYNOS_BO_WC		= 1 << 2,
+	EXYNOS_BO_MASK		= EXYNOS_BO_NONCONTIG | EXYNOS_BO_CACHABLE |
+					EXYNOS_BO_WC
+};
+
+struct drm_exynos_g2d_get_ver {
+	__u32	major;
+	__u32	minor;
+};
+
+struct drm_exynos_g2d_cmd {
+	__u32	offset;
+	__u32	data;
+};
+
+enum drm_exynos_g2d_buf_type {
+	G2D_BUF_USERPTR = 1 << 31,
+};
+
+enum drm_exynos_g2d_event_type {
+	G2D_EVENT_NOT,
+	G2D_EVENT_NONSTOP,
+	G2D_EVENT_STOP,		/* not yet */
+};
+
+struct drm_exynos_g2d_userptr {
+	unsigned long userptr;
+	unsigned long size;
+};
+
+struct drm_exynos_g2d_set_cmdlist {
+	__u64					cmd;
+	__u64					cmd_buf;
+	__u32					cmd_nr;
+	__u32					cmd_buf_nr;
+
+	/* for g2d event */
+	__u64					event_type;
+	__u64					user_data;
+};
+
+struct drm_exynos_g2d_exec {
+	__u64					async;
+};
+
+/* Exynos DRM IPP v2 API */
+
+/**
+ * Enumerate available IPP hardware modules.
+ *
+ * @count_ipps: size of ipp_id array / number of ipp modules (set by driver)
+ * @reserved: padding
+ * @ipp_id_ptr: pointer to ipp_id array or NULL
+ */
+struct drm_exynos_ioctl_ipp_get_res {
+	__u32 count_ipps;
+	__u32 reserved;
+	__u64 ipp_id_ptr;
+};
+
+enum drm_exynos_ipp_format_type {
+	DRM_EXYNOS_IPP_FORMAT_SOURCE		= 0x01,
+	DRM_EXYNOS_IPP_FORMAT_DESTINATION	= 0x02,
+};
+
+struct drm_exynos_ipp_format {
+	__u32 fourcc;
+	__u32 type;
+	__u64 modifier;
+};
+
+enum drm_exynos_ipp_capability {
+	DRM_EXYNOS_IPP_CAP_CROP		= 0x01,
+	DRM_EXYNOS_IPP_CAP_ROTATE	= 0x02,
+	DRM_EXYNOS_IPP_CAP_SCALE	= 0x04,
+	DRM_EXYNOS_IPP_CAP_CONVERT	= 0x08,
+};
+
+/**
+ * Get IPP hardware capabilities and supported image formats.
+ *
+ * @ipp_id: id of IPP module to query
+ * @capabilities: bitmask of drm_exynos_ipp_capability (set by driver)
+ * @reserved: padding
+ * @formats_count: size of formats array (in entries) / number of filled
+ *		   formats (set by driver)
+ * @formats_ptr: pointer to formats array or NULL
+ */
+struct drm_exynos_ioctl_ipp_get_caps {
+	__u32 ipp_id;
+	__u32 capabilities;
+	__u32 reserved;
+	__u32 formats_count;
+	__u64 formats_ptr;
+};
+
+enum drm_exynos_ipp_limit_type {
+	/* size (horizontal/vertial) limits, in pixels (min, max, alignment) */
+	DRM_EXYNOS_IPP_LIMIT_TYPE_SIZE		= 0x0001,
+	/* scale ratio (horizonta/vertial), 16.16 fixed point (min, max) */
+	DRM_EXYNOS_IPP_LIMIT_TYPE_SCALE		= 0x0002,
+
+	/* image buffer area */
+	DRM_EXYNOS_IPP_LIMIT_SIZE_BUFFER	= 0x0001 << 16,
+	/* src/dst rectangle area */
+	DRM_EXYNOS_IPP_LIMIT_SIZE_AREA		= 0x0002 << 16,
+	/* src/dst rectangle area when rotation enabled */
+	DRM_EXYNOS_IPP_LIMIT_SIZE_ROTATED	= 0x0003 << 16,
+
+	DRM_EXYNOS_IPP_LIMIT_TYPE_MASK		= 0x000f,
+	DRM_EXYNOS_IPP_LIMIT_SIZE_MASK		= 0x000f << 16,
+};
+
+struct drm_exynos_ipp_limit_val {
+	__u32 min;
+	__u32 max;
+	__u32 align;
+	__u32 reserved;
+};
+
+/**
+ * IPP module limitation.
+ *
+ * @type: limit type (see drm_exynos_ipp_limit_type enum)
+ * @reserved: padding
+ * @h: horizontal limits
+ * @v: vertical limits
+ */
+struct drm_exynos_ipp_limit {
+	__u32 type;
+	__u32 reserved;
+	struct drm_exynos_ipp_limit_val h;
+	struct drm_exynos_ipp_limit_val v;
+};
+
+/**
+ * Get IPP limits for given image format.
+ *
+ * @ipp_id: id of IPP module to query
+ * @fourcc: image format code (see DRM_FORMAT_* in drm_fourcc.h)
+ * @modifier: image format modifier (see DRM_FORMAT_MOD_* in drm_fourcc.h)
+ * @type: source/destination identifier (drm_exynos_ipp_format_flag enum)
+ * @limits_count: size of limits array (in entries) / number of filled entries
+ *		 (set by driver)
+ * @limits_ptr: pointer to limits array or NULL
+ */
+struct drm_exynos_ioctl_ipp_get_limits {
+	__u32 ipp_id;
+	__u32 fourcc;
+	__u64 modifier;
+	__u32 type;
+	__u32 limits_count;
+	__u64 limits_ptr;
+};
+
+enum drm_exynos_ipp_task_id {
+	/* buffer described by struct drm_exynos_ipp_task_buffer */
+	DRM_EXYNOS_IPP_TASK_BUFFER		= 0x0001,
+	/* rectangle described by struct drm_exynos_ipp_task_rect */
+	DRM_EXYNOS_IPP_TASK_RECTANGLE		= 0x0002,
+	/* transformation described by struct drm_exynos_ipp_task_transform */
+	DRM_EXYNOS_IPP_TASK_TRANSFORM		= 0x0003,
+	/* alpha configuration described by struct drm_exynos_ipp_task_alpha */
+	DRM_EXYNOS_IPP_TASK_ALPHA		= 0x0004,
+
+	/* source image data (for buffer and rectangle chunks) */
+	DRM_EXYNOS_IPP_TASK_TYPE_SOURCE		= 0x0001 << 16,
+	/* destination image data (for buffer and rectangle chunks) */
+	DRM_EXYNOS_IPP_TASK_TYPE_DESTINATION	= 0x0002 << 16,
+};
+
+/**
+ * Memory buffer with image data.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_BUFFER
+ * other parameters are same as for AddFB2 generic DRM ioctl
+ */
+struct drm_exynos_ipp_task_buffer {
+	__u32	id;
+	__u32	fourcc;
+	__u32	width, height;
+	__u32	gem_id[4];
+	__u32	offset[4];
+	__u32	pitch[4];
+	__u64	modifier;
+};
+
+/**
+ * Rectangle for processing.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_RECTANGLE
+ * @reserved: padding
+ * @x,@y: left corner in pixels
+ * @w,@h: width/height in pixels
+ */
+struct drm_exynos_ipp_task_rect {
+	__u32	id;
+	__u32	reserved;
+	__u32	x;
+	__u32	y;
+	__u32	w;
+	__u32	h;
+};
+
+/**
+ * Image tranformation description.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_TRANSFORM
+ * @rotation: DRM_MODE_ROTATE_* and DRM_MODE_REFLECT_* values
+ */
+struct drm_exynos_ipp_task_transform {
+	__u32	id;
+	__u32	rotation;
+};
+
+/**
+ * Image global alpha configuration for formats without alpha values.
+ *
+ * @id: must be DRM_EXYNOS_IPP_TASK_ALPHA
+ * @value: global alpha value (0-255)
+ */
+struct drm_exynos_ipp_task_alpha {
+	__u32	id;
+	__u32	value;
+};
+
+enum drm_exynos_ipp_flag {
+	/* generate DRM event after processing */
+	DRM_EXYNOS_IPP_FLAG_EVENT	= 0x01,
+	/* dry run, only check task parameters */
+	DRM_EXYNOS_IPP_FLAG_TEST_ONLY	= 0x02,
+	/* non-blocking processing */
+	DRM_EXYNOS_IPP_FLAG_NONBLOCK	= 0x04,
+};
+
+#define DRM_EXYNOS_IPP_FLAGS (DRM_EXYNOS_IPP_FLAG_EVENT |\
+		DRM_EXYNOS_IPP_FLAG_TEST_ONLY | DRM_EXYNOS_IPP_FLAG_NONBLOCK)
+
+/**
+ * Perform image processing described by array of drm_exynos_ipp_task_*
+ * structures (parameters array).
+ *
+ * @ipp_id: id of IPP module to run the task
+ * @flags: bitmask of drm_exynos_ipp_flag values
+ * @reserved: padding
+ * @params_size: size of parameters array (in bytes)
+ * @params_ptr: pointer to parameters array or NULL
+ * @user_data: (optional) data for drm event
+ */
+struct drm_exynos_ioctl_ipp_commit {
+	__u32 ipp_id;
+	__u32 flags;
+	__u32 reserved;
+	__u32 params_size;
+	__u64 params_ptr;
+	__u64 user_data;
+};
+
+#define DRM_EXYNOS_GEM_CREATE		0x00
+#define DRM_EXYNOS_GEM_MAP		0x01
+/* Reserved 0x03 ~ 0x05 for exynos specific gem ioctl */
+#define DRM_EXYNOS_GEM_GET		0x04
+#define DRM_EXYNOS_VIDI_CONNECTION	0x07
+
+/* G2D */
+#define DRM_EXYNOS_G2D_GET_VER		0x20
+#define DRM_EXYNOS_G2D_SET_CMDLIST	0x21
+#define DRM_EXYNOS_G2D_EXEC		0x22
+
+/* Reserved 0x30 ~ 0x33 for obsolete Exynos IPP ioctls */
+/* IPP - Image Post Processing */
+#define DRM_EXYNOS_IPP_GET_RESOURCES	0x40
+#define DRM_EXYNOS_IPP_GET_CAPS		0x41
+#define DRM_EXYNOS_IPP_GET_LIMITS	0x42
+#define DRM_EXYNOS_IPP_COMMIT		0x43
+
+#define DRM_IOCTL_EXYNOS_GEM_CREATE		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_GEM_CREATE, struct drm_exynos_gem_create)
+#define DRM_IOCTL_EXYNOS_GEM_MAP		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_GEM_MAP, struct drm_exynos_gem_map)
+#define DRM_IOCTL_EXYNOS_GEM_GET	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_GEM_GET,	struct drm_exynos_gem_info)
+
+#define DRM_IOCTL_EXYNOS_VIDI_CONNECTION	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_VIDI_CONNECTION, struct drm_exynos_vidi_connection)
+
+#define DRM_IOCTL_EXYNOS_G2D_GET_VER		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_G2D_GET_VER, struct drm_exynos_g2d_get_ver)
+#define DRM_IOCTL_EXYNOS_G2D_SET_CMDLIST	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_G2D_SET_CMDLIST, struct drm_exynos_g2d_set_cmdlist)
+#define DRM_IOCTL_EXYNOS_G2D_EXEC		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_G2D_EXEC, struct drm_exynos_g2d_exec)
+
+#define DRM_IOCTL_EXYNOS_IPP_GET_RESOURCES	DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_RESOURCES, \
+		struct drm_exynos_ioctl_ipp_get_res)
+#define DRM_IOCTL_EXYNOS_IPP_GET_CAPS		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_CAPS, struct drm_exynos_ioctl_ipp_get_caps)
+#define DRM_IOCTL_EXYNOS_IPP_GET_LIMITS		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_GET_LIMITS, \
+		struct drm_exynos_ioctl_ipp_get_limits)
+#define DRM_IOCTL_EXYNOS_IPP_COMMIT		DRM_IOWR(DRM_COMMAND_BASE + \
+		DRM_EXYNOS_IPP_COMMIT, struct drm_exynos_ioctl_ipp_commit)
+
+/* Exynos specific events */
+#define DRM_EXYNOS_G2D_EVENT		0x80000000
+#define DRM_EXYNOS_IPP_EVENT		0x80000002
+
+struct drm_exynos_g2d_event {
+	struct drm_event	base;
+	__u64			user_data;
+	__u32			tv_sec;
+	__u32			tv_usec;
+	__u32			cmdlist_no;
+	__u32			reserved;
+};
+
+struct drm_exynos_ipp_event {
+	struct drm_event	base;
+	__u64			user_data;
+	__u32			tv_sec;
+	__u32			tv_usec;
+	__u32			ipp_id;
+	__u32			sequence;
+	__u64			reserved;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_EXYNOS_DRM_H_ */
diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h
new file mode 100644
index 000000000..a512dc4cf
--- /dev/null
+++ b/include/uapi/drm/habanalabs_accel.h
@@ -0,0 +1,2368 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+ *
+ * Copyright 2016-2023 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+#ifndef HABANALABS_H_
+#define HABANALABS_H_
+
+#include <drm/drm.h>
+
+/*
+ * Defines that are asic-specific but constitutes as ABI between kernel driver
+ * and userspace
+ */
+#define GOYA_KMD_SRAM_RESERVED_SIZE_FROM_START		0x8000	/* 32KB */
+#define GAUDI_DRIVER_SRAM_RESERVED_SIZE_FROM_START	0x80	/* 128 bytes */
+
+/*
+ * 128 SOBs reserved for collective wait
+ * 16 SOBs reserved for sync stream
+ */
+#define GAUDI_FIRST_AVAILABLE_W_S_SYNC_OBJECT		144
+
+/*
+ * 64 monitors reserved for collective wait
+ * 8 monitors reserved for sync stream
+ */
+#define GAUDI_FIRST_AVAILABLE_W_S_MONITOR		72
+
+/* Max number of elements in timestamps registration buffers */
+#define	TS_MAX_ELEMENTS_NUM				(1 << 20) /* 1MB */
+
+/*
+ * Goya queue Numbering
+ *
+ * The external queues (PCI DMA channels) MUST be before the internal queues
+ * and each group (PCI DMA channels and internal) must be contiguous inside
+ * itself but there can be a gap between the two groups (although not
+ * recommended)
+ */
+
+enum goya_queue_id {
+	GOYA_QUEUE_ID_DMA_0 = 0,
+	GOYA_QUEUE_ID_DMA_1 = 1,
+	GOYA_QUEUE_ID_DMA_2 = 2,
+	GOYA_QUEUE_ID_DMA_3 = 3,
+	GOYA_QUEUE_ID_DMA_4 = 4,
+	GOYA_QUEUE_ID_CPU_PQ = 5,
+	GOYA_QUEUE_ID_MME = 6,	/* Internal queues start here */
+	GOYA_QUEUE_ID_TPC0 = 7,
+	GOYA_QUEUE_ID_TPC1 = 8,
+	GOYA_QUEUE_ID_TPC2 = 9,
+	GOYA_QUEUE_ID_TPC3 = 10,
+	GOYA_QUEUE_ID_TPC4 = 11,
+	GOYA_QUEUE_ID_TPC5 = 12,
+	GOYA_QUEUE_ID_TPC6 = 13,
+	GOYA_QUEUE_ID_TPC7 = 14,
+	GOYA_QUEUE_ID_SIZE
+};
+
+/*
+ * Gaudi queue Numbering
+ * External queues (PCI DMA channels) are DMA_0_*, DMA_1_* and DMA_5_*.
+ * Except one CPU queue, all the rest are internal queues.
+ */
+
+enum gaudi_queue_id {
+	GAUDI_QUEUE_ID_DMA_0_0 = 0,	/* external */
+	GAUDI_QUEUE_ID_DMA_0_1 = 1,	/* external */
+	GAUDI_QUEUE_ID_DMA_0_2 = 2,	/* external */
+	GAUDI_QUEUE_ID_DMA_0_3 = 3,	/* external */
+	GAUDI_QUEUE_ID_DMA_1_0 = 4,	/* external */
+	GAUDI_QUEUE_ID_DMA_1_1 = 5,	/* external */
+	GAUDI_QUEUE_ID_DMA_1_2 = 6,	/* external */
+	GAUDI_QUEUE_ID_DMA_1_3 = 7,	/* external */
+	GAUDI_QUEUE_ID_CPU_PQ = 8,	/* CPU */
+	GAUDI_QUEUE_ID_DMA_2_0 = 9,	/* internal */
+	GAUDI_QUEUE_ID_DMA_2_1 = 10,	/* internal */
+	GAUDI_QUEUE_ID_DMA_2_2 = 11,	/* internal */
+	GAUDI_QUEUE_ID_DMA_2_3 = 12,	/* internal */
+	GAUDI_QUEUE_ID_DMA_3_0 = 13,	/* internal */
+	GAUDI_QUEUE_ID_DMA_3_1 = 14,	/* internal */
+	GAUDI_QUEUE_ID_DMA_3_2 = 15,	/* internal */
+	GAUDI_QUEUE_ID_DMA_3_3 = 16,	/* internal */
+	GAUDI_QUEUE_ID_DMA_4_0 = 17,	/* internal */
+	GAUDI_QUEUE_ID_DMA_4_1 = 18,	/* internal */
+	GAUDI_QUEUE_ID_DMA_4_2 = 19,	/* internal */
+	GAUDI_QUEUE_ID_DMA_4_3 = 20,	/* internal */
+	GAUDI_QUEUE_ID_DMA_5_0 = 21,	/* internal */
+	GAUDI_QUEUE_ID_DMA_5_1 = 22,	/* internal */
+	GAUDI_QUEUE_ID_DMA_5_2 = 23,	/* internal */
+	GAUDI_QUEUE_ID_DMA_5_3 = 24,	/* internal */
+	GAUDI_QUEUE_ID_DMA_6_0 = 25,	/* internal */
+	GAUDI_QUEUE_ID_DMA_6_1 = 26,	/* internal */
+	GAUDI_QUEUE_ID_DMA_6_2 = 27,	/* internal */
+	GAUDI_QUEUE_ID_DMA_6_3 = 28,	/* internal */
+	GAUDI_QUEUE_ID_DMA_7_0 = 29,	/* internal */
+	GAUDI_QUEUE_ID_DMA_7_1 = 30,	/* internal */
+	GAUDI_QUEUE_ID_DMA_7_2 = 31,	/* internal */
+	GAUDI_QUEUE_ID_DMA_7_3 = 32,	/* internal */
+	GAUDI_QUEUE_ID_MME_0_0 = 33,	/* internal */
+	GAUDI_QUEUE_ID_MME_0_1 = 34,	/* internal */
+	GAUDI_QUEUE_ID_MME_0_2 = 35,	/* internal */
+	GAUDI_QUEUE_ID_MME_0_3 = 36,	/* internal */
+	GAUDI_QUEUE_ID_MME_1_0 = 37,	/* internal */
+	GAUDI_QUEUE_ID_MME_1_1 = 38,	/* internal */
+	GAUDI_QUEUE_ID_MME_1_2 = 39,	/* internal */
+	GAUDI_QUEUE_ID_MME_1_3 = 40,	/* internal */
+	GAUDI_QUEUE_ID_TPC_0_0 = 41,	/* internal */
+	GAUDI_QUEUE_ID_TPC_0_1 = 42,	/* internal */
+	GAUDI_QUEUE_ID_TPC_0_2 = 43,	/* internal */
+	GAUDI_QUEUE_ID_TPC_0_3 = 44,	/* internal */
+	GAUDI_QUEUE_ID_TPC_1_0 = 45,	/* internal */
+	GAUDI_QUEUE_ID_TPC_1_1 = 46,	/* internal */
+	GAUDI_QUEUE_ID_TPC_1_2 = 47,	/* internal */
+	GAUDI_QUEUE_ID_TPC_1_3 = 48,	/* internal */
+	GAUDI_QUEUE_ID_TPC_2_0 = 49,	/* internal */
+	GAUDI_QUEUE_ID_TPC_2_1 = 50,	/* internal */
+	GAUDI_QUEUE_ID_TPC_2_2 = 51,	/* internal */
+	GAUDI_QUEUE_ID_TPC_2_3 = 52,	/* internal */
+	GAUDI_QUEUE_ID_TPC_3_0 = 53,	/* internal */
+	GAUDI_QUEUE_ID_TPC_3_1 = 54,	/* internal */
+	GAUDI_QUEUE_ID_TPC_3_2 = 55,	/* internal */
+	GAUDI_QUEUE_ID_TPC_3_3 = 56,	/* internal */
+	GAUDI_QUEUE_ID_TPC_4_0 = 57,	/* internal */
+	GAUDI_QUEUE_ID_TPC_4_1 = 58,	/* internal */
+	GAUDI_QUEUE_ID_TPC_4_2 = 59,	/* internal */
+	GAUDI_QUEUE_ID_TPC_4_3 = 60,	/* internal */
+	GAUDI_QUEUE_ID_TPC_5_0 = 61,	/* internal */
+	GAUDI_QUEUE_ID_TPC_5_1 = 62,	/* internal */
+	GAUDI_QUEUE_ID_TPC_5_2 = 63,	/* internal */
+	GAUDI_QUEUE_ID_TPC_5_3 = 64,	/* internal */
+	GAUDI_QUEUE_ID_TPC_6_0 = 65,	/* internal */
+	GAUDI_QUEUE_ID_TPC_6_1 = 66,	/* internal */
+	GAUDI_QUEUE_ID_TPC_6_2 = 67,	/* internal */
+	GAUDI_QUEUE_ID_TPC_6_3 = 68,	/* internal */
+	GAUDI_QUEUE_ID_TPC_7_0 = 69,	/* internal */
+	GAUDI_QUEUE_ID_TPC_7_1 = 70,	/* internal */
+	GAUDI_QUEUE_ID_TPC_7_2 = 71,	/* internal */
+	GAUDI_QUEUE_ID_TPC_7_3 = 72,	/* internal */
+	GAUDI_QUEUE_ID_NIC_0_0 = 73,	/* internal */
+	GAUDI_QUEUE_ID_NIC_0_1 = 74,	/* internal */
+	GAUDI_QUEUE_ID_NIC_0_2 = 75,	/* internal */
+	GAUDI_QUEUE_ID_NIC_0_3 = 76,	/* internal */
+	GAUDI_QUEUE_ID_NIC_1_0 = 77,	/* internal */
+	GAUDI_QUEUE_ID_NIC_1_1 = 78,	/* internal */
+	GAUDI_QUEUE_ID_NIC_1_2 = 79,	/* internal */
+	GAUDI_QUEUE_ID_NIC_1_3 = 80,	/* internal */
+	GAUDI_QUEUE_ID_NIC_2_0 = 81,	/* internal */
+	GAUDI_QUEUE_ID_NIC_2_1 = 82,	/* internal */
+	GAUDI_QUEUE_ID_NIC_2_2 = 83,	/* internal */
+	GAUDI_QUEUE_ID_NIC_2_3 = 84,	/* internal */
+	GAUDI_QUEUE_ID_NIC_3_0 = 85,	/* internal */
+	GAUDI_QUEUE_ID_NIC_3_1 = 86,	/* internal */
+	GAUDI_QUEUE_ID_NIC_3_2 = 87,	/* internal */
+	GAUDI_QUEUE_ID_NIC_3_3 = 88,	/* internal */
+	GAUDI_QUEUE_ID_NIC_4_0 = 89,	/* internal */
+	GAUDI_QUEUE_ID_NIC_4_1 = 90,	/* internal */
+	GAUDI_QUEUE_ID_NIC_4_2 = 91,	/* internal */
+	GAUDI_QUEUE_ID_NIC_4_3 = 92,	/* internal */
+	GAUDI_QUEUE_ID_NIC_5_0 = 93,	/* internal */
+	GAUDI_QUEUE_ID_NIC_5_1 = 94,	/* internal */
+	GAUDI_QUEUE_ID_NIC_5_2 = 95,	/* internal */
+	GAUDI_QUEUE_ID_NIC_5_3 = 96,	/* internal */
+	GAUDI_QUEUE_ID_NIC_6_0 = 97,	/* internal */
+	GAUDI_QUEUE_ID_NIC_6_1 = 98,	/* internal */
+	GAUDI_QUEUE_ID_NIC_6_2 = 99,	/* internal */
+	GAUDI_QUEUE_ID_NIC_6_3 = 100,	/* internal */
+	GAUDI_QUEUE_ID_NIC_7_0 = 101,	/* internal */
+	GAUDI_QUEUE_ID_NIC_7_1 = 102,	/* internal */
+	GAUDI_QUEUE_ID_NIC_7_2 = 103,	/* internal */
+	GAUDI_QUEUE_ID_NIC_7_3 = 104,	/* internal */
+	GAUDI_QUEUE_ID_NIC_8_0 = 105,	/* internal */
+	GAUDI_QUEUE_ID_NIC_8_1 = 106,	/* internal */
+	GAUDI_QUEUE_ID_NIC_8_2 = 107,	/* internal */
+	GAUDI_QUEUE_ID_NIC_8_3 = 108,	/* internal */
+	GAUDI_QUEUE_ID_NIC_9_0 = 109,	/* internal */
+	GAUDI_QUEUE_ID_NIC_9_1 = 110,	/* internal */
+	GAUDI_QUEUE_ID_NIC_9_2 = 111,	/* internal */
+	GAUDI_QUEUE_ID_NIC_9_3 = 112,	/* internal */
+	GAUDI_QUEUE_ID_SIZE
+};
+
+/*
+ * In GAUDI2 we have two modes of operation in regard to queues:
+ * 1. Legacy mode, where each QMAN exposes 4 streams to the user
+ * 2. F/W mode, where we use F/W to schedule the JOBS to the different queues.
+ *
+ * When in legacy mode, the user sends the queue id per JOB according to
+ * enum gaudi2_queue_id below.
+ *
+ * When in F/W mode, the user sends a stream id per Command Submission. The
+ * stream id is a running number from 0 up to (N-1), where N is the number
+ * of streams the F/W exposes and is passed to the user in
+ * struct hl_info_hw_ip_info
+ */
+
+enum gaudi2_queue_id {
+	GAUDI2_QUEUE_ID_PDMA_0_0 = 0,
+	GAUDI2_QUEUE_ID_PDMA_0_1 = 1,
+	GAUDI2_QUEUE_ID_PDMA_0_2 = 2,
+	GAUDI2_QUEUE_ID_PDMA_0_3 = 3,
+	GAUDI2_QUEUE_ID_PDMA_1_0 = 4,
+	GAUDI2_QUEUE_ID_PDMA_1_1 = 5,
+	GAUDI2_QUEUE_ID_PDMA_1_2 = 6,
+	GAUDI2_QUEUE_ID_PDMA_1_3 = 7,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_0_0 = 8,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_0_1 = 9,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_0_2 = 10,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_0_3 = 11,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_1_0 = 12,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_1_1 = 13,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_1_2 = 14,
+	GAUDI2_QUEUE_ID_DCORE0_EDMA_1_3 = 15,
+	GAUDI2_QUEUE_ID_DCORE0_MME_0_0 = 16,
+	GAUDI2_QUEUE_ID_DCORE0_MME_0_1 = 17,
+	GAUDI2_QUEUE_ID_DCORE0_MME_0_2 = 18,
+	GAUDI2_QUEUE_ID_DCORE0_MME_0_3 = 19,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_0_0 = 20,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_0_1 = 21,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_0_2 = 22,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_0_3 = 23,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_1_0 = 24,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_1_1 = 25,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_1_2 = 26,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_1_3 = 27,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_2_0 = 28,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_2_1 = 29,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_2_2 = 30,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_2_3 = 31,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_3_0 = 32,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_3_1 = 33,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_3_2 = 34,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_3_3 = 35,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_4_0 = 36,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_4_1 = 37,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_4_2 = 38,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_4_3 = 39,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_5_0 = 40,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_5_1 = 41,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_5_2 = 42,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_5_3 = 43,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_6_0 = 44,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_6_1 = 45,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_6_2 = 46,
+	GAUDI2_QUEUE_ID_DCORE0_TPC_6_3 = 47,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_0_0 = 48,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_0_1 = 49,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_0_2 = 50,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_0_3 = 51,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_1_0 = 52,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_1_1 = 53,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_1_2 = 54,
+	GAUDI2_QUEUE_ID_DCORE1_EDMA_1_3 = 55,
+	GAUDI2_QUEUE_ID_DCORE1_MME_0_0 = 56,
+	GAUDI2_QUEUE_ID_DCORE1_MME_0_1 = 57,
+	GAUDI2_QUEUE_ID_DCORE1_MME_0_2 = 58,
+	GAUDI2_QUEUE_ID_DCORE1_MME_0_3 = 59,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_0_0 = 60,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_0_1 = 61,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_0_2 = 62,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_0_3 = 63,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_1_0 = 64,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_1_1 = 65,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_1_2 = 66,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_1_3 = 67,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_2_0 = 68,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_2_1 = 69,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_2_2 = 70,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_2_3 = 71,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_3_0 = 72,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_3_1 = 73,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_3_2 = 74,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_3_3 = 75,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_4_0 = 76,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_4_1 = 77,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_4_2 = 78,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_4_3 = 79,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_5_0 = 80,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_5_1 = 81,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_5_2 = 82,
+	GAUDI2_QUEUE_ID_DCORE1_TPC_5_3 = 83,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_0_0 = 84,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_0_1 = 85,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_0_2 = 86,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_0_3 = 87,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_1_0 = 88,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_1_1 = 89,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_1_2 = 90,
+	GAUDI2_QUEUE_ID_DCORE2_EDMA_1_3 = 91,
+	GAUDI2_QUEUE_ID_DCORE2_MME_0_0 = 92,
+	GAUDI2_QUEUE_ID_DCORE2_MME_0_1 = 93,
+	GAUDI2_QUEUE_ID_DCORE2_MME_0_2 = 94,
+	GAUDI2_QUEUE_ID_DCORE2_MME_0_3 = 95,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_0_0 = 96,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_0_1 = 97,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_0_2 = 98,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_0_3 = 99,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_1_0 = 100,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_1_1 = 101,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_1_2 = 102,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_1_3 = 103,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_2_0 = 104,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_2_1 = 105,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_2_2 = 106,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_2_3 = 107,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_3_0 = 108,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_3_1 = 109,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_3_2 = 110,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_3_3 = 111,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_4_0 = 112,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_4_1 = 113,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_4_2 = 114,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_4_3 = 115,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_5_0 = 116,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_5_1 = 117,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_5_2 = 118,
+	GAUDI2_QUEUE_ID_DCORE2_TPC_5_3 = 119,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_0_0 = 120,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_0_1 = 121,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_0_2 = 122,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_0_3 = 123,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_1_0 = 124,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_1_1 = 125,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_1_2 = 126,
+	GAUDI2_QUEUE_ID_DCORE3_EDMA_1_3 = 127,
+	GAUDI2_QUEUE_ID_DCORE3_MME_0_0 = 128,
+	GAUDI2_QUEUE_ID_DCORE3_MME_0_1 = 129,
+	GAUDI2_QUEUE_ID_DCORE3_MME_0_2 = 130,
+	GAUDI2_QUEUE_ID_DCORE3_MME_0_3 = 131,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_0_0 = 132,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_0_1 = 133,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_0_2 = 134,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_0_3 = 135,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_1_0 = 136,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_1_1 = 137,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_1_2 = 138,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_1_3 = 139,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_2_0 = 140,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_2_1 = 141,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_2_2 = 142,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_2_3 = 143,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_3_0 = 144,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_3_1 = 145,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_3_2 = 146,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_3_3 = 147,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_4_0 = 148,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_4_1 = 149,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_4_2 = 150,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_4_3 = 151,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_5_0 = 152,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_5_1 = 153,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_5_2 = 154,
+	GAUDI2_QUEUE_ID_DCORE3_TPC_5_3 = 155,
+	GAUDI2_QUEUE_ID_NIC_0_0 = 156,
+	GAUDI2_QUEUE_ID_NIC_0_1 = 157,
+	GAUDI2_QUEUE_ID_NIC_0_2 = 158,
+	GAUDI2_QUEUE_ID_NIC_0_3 = 159,
+	GAUDI2_QUEUE_ID_NIC_1_0 = 160,
+	GAUDI2_QUEUE_ID_NIC_1_1 = 161,
+	GAUDI2_QUEUE_ID_NIC_1_2 = 162,
+	GAUDI2_QUEUE_ID_NIC_1_3 = 163,
+	GAUDI2_QUEUE_ID_NIC_2_0 = 164,
+	GAUDI2_QUEUE_ID_NIC_2_1 = 165,
+	GAUDI2_QUEUE_ID_NIC_2_2 = 166,
+	GAUDI2_QUEUE_ID_NIC_2_3 = 167,
+	GAUDI2_QUEUE_ID_NIC_3_0 = 168,
+	GAUDI2_QUEUE_ID_NIC_3_1 = 169,
+	GAUDI2_QUEUE_ID_NIC_3_2 = 170,
+	GAUDI2_QUEUE_ID_NIC_3_3 = 171,
+	GAUDI2_QUEUE_ID_NIC_4_0 = 172,
+	GAUDI2_QUEUE_ID_NIC_4_1 = 173,
+	GAUDI2_QUEUE_ID_NIC_4_2 = 174,
+	GAUDI2_QUEUE_ID_NIC_4_3 = 175,
+	GAUDI2_QUEUE_ID_NIC_5_0 = 176,
+	GAUDI2_QUEUE_ID_NIC_5_1 = 177,
+	GAUDI2_QUEUE_ID_NIC_5_2 = 178,
+	GAUDI2_QUEUE_ID_NIC_5_3 = 179,
+	GAUDI2_QUEUE_ID_NIC_6_0 = 180,
+	GAUDI2_QUEUE_ID_NIC_6_1 = 181,
+	GAUDI2_QUEUE_ID_NIC_6_2 = 182,
+	GAUDI2_QUEUE_ID_NIC_6_3 = 183,
+	GAUDI2_QUEUE_ID_NIC_7_0 = 184,
+	GAUDI2_QUEUE_ID_NIC_7_1 = 185,
+	GAUDI2_QUEUE_ID_NIC_7_2 = 186,
+	GAUDI2_QUEUE_ID_NIC_7_3 = 187,
+	GAUDI2_QUEUE_ID_NIC_8_0 = 188,
+	GAUDI2_QUEUE_ID_NIC_8_1 = 189,
+	GAUDI2_QUEUE_ID_NIC_8_2 = 190,
+	GAUDI2_QUEUE_ID_NIC_8_3 = 191,
+	GAUDI2_QUEUE_ID_NIC_9_0 = 192,
+	GAUDI2_QUEUE_ID_NIC_9_1 = 193,
+	GAUDI2_QUEUE_ID_NIC_9_2 = 194,
+	GAUDI2_QUEUE_ID_NIC_9_3 = 195,
+	GAUDI2_QUEUE_ID_NIC_10_0 = 196,
+	GAUDI2_QUEUE_ID_NIC_10_1 = 197,
+	GAUDI2_QUEUE_ID_NIC_10_2 = 198,
+	GAUDI2_QUEUE_ID_NIC_10_3 = 199,
+	GAUDI2_QUEUE_ID_NIC_11_0 = 200,
+	GAUDI2_QUEUE_ID_NIC_11_1 = 201,
+	GAUDI2_QUEUE_ID_NIC_11_2 = 202,
+	GAUDI2_QUEUE_ID_NIC_11_3 = 203,
+	GAUDI2_QUEUE_ID_NIC_12_0 = 204,
+	GAUDI2_QUEUE_ID_NIC_12_1 = 205,
+	GAUDI2_QUEUE_ID_NIC_12_2 = 206,
+	GAUDI2_QUEUE_ID_NIC_12_3 = 207,
+	GAUDI2_QUEUE_ID_NIC_13_0 = 208,
+	GAUDI2_QUEUE_ID_NIC_13_1 = 209,
+	GAUDI2_QUEUE_ID_NIC_13_2 = 210,
+	GAUDI2_QUEUE_ID_NIC_13_3 = 211,
+	GAUDI2_QUEUE_ID_NIC_14_0 = 212,
+	GAUDI2_QUEUE_ID_NIC_14_1 = 213,
+	GAUDI2_QUEUE_ID_NIC_14_2 = 214,
+	GAUDI2_QUEUE_ID_NIC_14_3 = 215,
+	GAUDI2_QUEUE_ID_NIC_15_0 = 216,
+	GAUDI2_QUEUE_ID_NIC_15_1 = 217,
+	GAUDI2_QUEUE_ID_NIC_15_2 = 218,
+	GAUDI2_QUEUE_ID_NIC_15_3 = 219,
+	GAUDI2_QUEUE_ID_NIC_16_0 = 220,
+	GAUDI2_QUEUE_ID_NIC_16_1 = 221,
+	GAUDI2_QUEUE_ID_NIC_16_2 = 222,
+	GAUDI2_QUEUE_ID_NIC_16_3 = 223,
+	GAUDI2_QUEUE_ID_NIC_17_0 = 224,
+	GAUDI2_QUEUE_ID_NIC_17_1 = 225,
+	GAUDI2_QUEUE_ID_NIC_17_2 = 226,
+	GAUDI2_QUEUE_ID_NIC_17_3 = 227,
+	GAUDI2_QUEUE_ID_NIC_18_0 = 228,
+	GAUDI2_QUEUE_ID_NIC_18_1 = 229,
+	GAUDI2_QUEUE_ID_NIC_18_2 = 230,
+	GAUDI2_QUEUE_ID_NIC_18_3 = 231,
+	GAUDI2_QUEUE_ID_NIC_19_0 = 232,
+	GAUDI2_QUEUE_ID_NIC_19_1 = 233,
+	GAUDI2_QUEUE_ID_NIC_19_2 = 234,
+	GAUDI2_QUEUE_ID_NIC_19_3 = 235,
+	GAUDI2_QUEUE_ID_NIC_20_0 = 236,
+	GAUDI2_QUEUE_ID_NIC_20_1 = 237,
+	GAUDI2_QUEUE_ID_NIC_20_2 = 238,
+	GAUDI2_QUEUE_ID_NIC_20_3 = 239,
+	GAUDI2_QUEUE_ID_NIC_21_0 = 240,
+	GAUDI2_QUEUE_ID_NIC_21_1 = 241,
+	GAUDI2_QUEUE_ID_NIC_21_2 = 242,
+	GAUDI2_QUEUE_ID_NIC_21_3 = 243,
+	GAUDI2_QUEUE_ID_NIC_22_0 = 244,
+	GAUDI2_QUEUE_ID_NIC_22_1 = 245,
+	GAUDI2_QUEUE_ID_NIC_22_2 = 246,
+	GAUDI2_QUEUE_ID_NIC_22_3 = 247,
+	GAUDI2_QUEUE_ID_NIC_23_0 = 248,
+	GAUDI2_QUEUE_ID_NIC_23_1 = 249,
+	GAUDI2_QUEUE_ID_NIC_23_2 = 250,
+	GAUDI2_QUEUE_ID_NIC_23_3 = 251,
+	GAUDI2_QUEUE_ID_ROT_0_0 = 252,
+	GAUDI2_QUEUE_ID_ROT_0_1 = 253,
+	GAUDI2_QUEUE_ID_ROT_0_2 = 254,
+	GAUDI2_QUEUE_ID_ROT_0_3 = 255,
+	GAUDI2_QUEUE_ID_ROT_1_0 = 256,
+	GAUDI2_QUEUE_ID_ROT_1_1 = 257,
+	GAUDI2_QUEUE_ID_ROT_1_2 = 258,
+	GAUDI2_QUEUE_ID_ROT_1_3 = 259,
+	GAUDI2_QUEUE_ID_CPU_PQ = 260,
+	GAUDI2_QUEUE_ID_SIZE
+};
+
+/*
+ * Engine Numbering
+ *
+ * Used in the "busy_engines_mask" field in `struct hl_info_hw_idle'
+ */
+
+enum goya_engine_id {
+	GOYA_ENGINE_ID_DMA_0 = 0,
+	GOYA_ENGINE_ID_DMA_1,
+	GOYA_ENGINE_ID_DMA_2,
+	GOYA_ENGINE_ID_DMA_3,
+	GOYA_ENGINE_ID_DMA_4,
+	GOYA_ENGINE_ID_MME_0,
+	GOYA_ENGINE_ID_TPC_0,
+	GOYA_ENGINE_ID_TPC_1,
+	GOYA_ENGINE_ID_TPC_2,
+	GOYA_ENGINE_ID_TPC_3,
+	GOYA_ENGINE_ID_TPC_4,
+	GOYA_ENGINE_ID_TPC_5,
+	GOYA_ENGINE_ID_TPC_6,
+	GOYA_ENGINE_ID_TPC_7,
+	GOYA_ENGINE_ID_SIZE
+};
+
+enum gaudi_engine_id {
+	GAUDI_ENGINE_ID_DMA_0 = 0,
+	GAUDI_ENGINE_ID_DMA_1,
+	GAUDI_ENGINE_ID_DMA_2,
+	GAUDI_ENGINE_ID_DMA_3,
+	GAUDI_ENGINE_ID_DMA_4,
+	GAUDI_ENGINE_ID_DMA_5,
+	GAUDI_ENGINE_ID_DMA_6,
+	GAUDI_ENGINE_ID_DMA_7,
+	GAUDI_ENGINE_ID_MME_0,
+	GAUDI_ENGINE_ID_MME_1,
+	GAUDI_ENGINE_ID_MME_2,
+	GAUDI_ENGINE_ID_MME_3,
+	GAUDI_ENGINE_ID_TPC_0,
+	GAUDI_ENGINE_ID_TPC_1,
+	GAUDI_ENGINE_ID_TPC_2,
+	GAUDI_ENGINE_ID_TPC_3,
+	GAUDI_ENGINE_ID_TPC_4,
+	GAUDI_ENGINE_ID_TPC_5,
+	GAUDI_ENGINE_ID_TPC_6,
+	GAUDI_ENGINE_ID_TPC_7,
+	GAUDI_ENGINE_ID_NIC_0,
+	GAUDI_ENGINE_ID_NIC_1,
+	GAUDI_ENGINE_ID_NIC_2,
+	GAUDI_ENGINE_ID_NIC_3,
+	GAUDI_ENGINE_ID_NIC_4,
+	GAUDI_ENGINE_ID_NIC_5,
+	GAUDI_ENGINE_ID_NIC_6,
+	GAUDI_ENGINE_ID_NIC_7,
+	GAUDI_ENGINE_ID_NIC_8,
+	GAUDI_ENGINE_ID_NIC_9,
+	GAUDI_ENGINE_ID_SIZE
+};
+
+enum gaudi2_engine_id {
+	GAUDI2_DCORE0_ENGINE_ID_EDMA_0 = 0,
+	GAUDI2_DCORE0_ENGINE_ID_EDMA_1,
+	GAUDI2_DCORE0_ENGINE_ID_MME,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_0,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_1,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_2,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_3,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_4,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_5,
+	GAUDI2_DCORE0_ENGINE_ID_DEC_0,
+	GAUDI2_DCORE0_ENGINE_ID_DEC_1,
+	GAUDI2_DCORE1_ENGINE_ID_EDMA_0,
+	GAUDI2_DCORE1_ENGINE_ID_EDMA_1,
+	GAUDI2_DCORE1_ENGINE_ID_MME,
+	GAUDI2_DCORE1_ENGINE_ID_TPC_0,
+	GAUDI2_DCORE1_ENGINE_ID_TPC_1,
+	GAUDI2_DCORE1_ENGINE_ID_TPC_2,
+	GAUDI2_DCORE1_ENGINE_ID_TPC_3,
+	GAUDI2_DCORE1_ENGINE_ID_TPC_4,
+	GAUDI2_DCORE1_ENGINE_ID_TPC_5,
+	GAUDI2_DCORE1_ENGINE_ID_DEC_0,
+	GAUDI2_DCORE1_ENGINE_ID_DEC_1,
+	GAUDI2_DCORE2_ENGINE_ID_EDMA_0,
+	GAUDI2_DCORE2_ENGINE_ID_EDMA_1,
+	GAUDI2_DCORE2_ENGINE_ID_MME,
+	GAUDI2_DCORE2_ENGINE_ID_TPC_0,
+	GAUDI2_DCORE2_ENGINE_ID_TPC_1,
+	GAUDI2_DCORE2_ENGINE_ID_TPC_2,
+	GAUDI2_DCORE2_ENGINE_ID_TPC_3,
+	GAUDI2_DCORE2_ENGINE_ID_TPC_4,
+	GAUDI2_DCORE2_ENGINE_ID_TPC_5,
+	GAUDI2_DCORE2_ENGINE_ID_DEC_0,
+	GAUDI2_DCORE2_ENGINE_ID_DEC_1,
+	GAUDI2_DCORE3_ENGINE_ID_EDMA_0,
+	GAUDI2_DCORE3_ENGINE_ID_EDMA_1,
+	GAUDI2_DCORE3_ENGINE_ID_MME,
+	GAUDI2_DCORE3_ENGINE_ID_TPC_0,
+	GAUDI2_DCORE3_ENGINE_ID_TPC_1,
+	GAUDI2_DCORE3_ENGINE_ID_TPC_2,
+	GAUDI2_DCORE3_ENGINE_ID_TPC_3,
+	GAUDI2_DCORE3_ENGINE_ID_TPC_4,
+	GAUDI2_DCORE3_ENGINE_ID_TPC_5,
+	GAUDI2_DCORE3_ENGINE_ID_DEC_0,
+	GAUDI2_DCORE3_ENGINE_ID_DEC_1,
+	GAUDI2_DCORE0_ENGINE_ID_TPC_6,
+	GAUDI2_ENGINE_ID_PDMA_0,
+	GAUDI2_ENGINE_ID_PDMA_1,
+	GAUDI2_ENGINE_ID_ROT_0,
+	GAUDI2_ENGINE_ID_ROT_1,
+	GAUDI2_PCIE_ENGINE_ID_DEC_0,
+	GAUDI2_PCIE_ENGINE_ID_DEC_1,
+	GAUDI2_ENGINE_ID_NIC0_0,
+	GAUDI2_ENGINE_ID_NIC0_1,
+	GAUDI2_ENGINE_ID_NIC1_0,
+	GAUDI2_ENGINE_ID_NIC1_1,
+	GAUDI2_ENGINE_ID_NIC2_0,
+	GAUDI2_ENGINE_ID_NIC2_1,
+	GAUDI2_ENGINE_ID_NIC3_0,
+	GAUDI2_ENGINE_ID_NIC3_1,
+	GAUDI2_ENGINE_ID_NIC4_0,
+	GAUDI2_ENGINE_ID_NIC4_1,
+	GAUDI2_ENGINE_ID_NIC5_0,
+	GAUDI2_ENGINE_ID_NIC5_1,
+	GAUDI2_ENGINE_ID_NIC6_0,
+	GAUDI2_ENGINE_ID_NIC6_1,
+	GAUDI2_ENGINE_ID_NIC7_0,
+	GAUDI2_ENGINE_ID_NIC7_1,
+	GAUDI2_ENGINE_ID_NIC8_0,
+	GAUDI2_ENGINE_ID_NIC8_1,
+	GAUDI2_ENGINE_ID_NIC9_0,
+	GAUDI2_ENGINE_ID_NIC9_1,
+	GAUDI2_ENGINE_ID_NIC10_0,
+	GAUDI2_ENGINE_ID_NIC10_1,
+	GAUDI2_ENGINE_ID_NIC11_0,
+	GAUDI2_ENGINE_ID_NIC11_1,
+	GAUDI2_ENGINE_ID_PCIE,
+	GAUDI2_ENGINE_ID_PSOC,
+	GAUDI2_ENGINE_ID_ARC_FARM,
+	GAUDI2_ENGINE_ID_KDMA,
+	GAUDI2_ENGINE_ID_SIZE
+};
+
+/*
+ * ASIC specific PLL index
+ *
+ * Used to retrieve in frequency info of different IPs via HL_INFO_PLL_FREQUENCY under
+ * DRM_IOCTL_HL_INFO IOCTL.
+ * The enums need to be used as an index in struct hl_pll_frequency_info.
+ */
+
+enum hl_goya_pll_index {
+	HL_GOYA_CPU_PLL = 0,
+	HL_GOYA_IC_PLL,
+	HL_GOYA_MC_PLL,
+	HL_GOYA_MME_PLL,
+	HL_GOYA_PCI_PLL,
+	HL_GOYA_EMMC_PLL,
+	HL_GOYA_TPC_PLL,
+	HL_GOYA_PLL_MAX
+};
+
+enum hl_gaudi_pll_index {
+	HL_GAUDI_CPU_PLL = 0,
+	HL_GAUDI_PCI_PLL,
+	HL_GAUDI_SRAM_PLL,
+	HL_GAUDI_HBM_PLL,
+	HL_GAUDI_NIC_PLL,
+	HL_GAUDI_DMA_PLL,
+	HL_GAUDI_MESH_PLL,
+	HL_GAUDI_MME_PLL,
+	HL_GAUDI_TPC_PLL,
+	HL_GAUDI_IF_PLL,
+	HL_GAUDI_PLL_MAX
+};
+
+enum hl_gaudi2_pll_index {
+	HL_GAUDI2_CPU_PLL = 0,
+	HL_GAUDI2_PCI_PLL,
+	HL_GAUDI2_SRAM_PLL,
+	HL_GAUDI2_HBM_PLL,
+	HL_GAUDI2_NIC_PLL,
+	HL_GAUDI2_DMA_PLL,
+	HL_GAUDI2_MESH_PLL,
+	HL_GAUDI2_MME_PLL,
+	HL_GAUDI2_TPC_PLL,
+	HL_GAUDI2_IF_PLL,
+	HL_GAUDI2_VID_PLL,
+	HL_GAUDI2_MSS_PLL,
+	HL_GAUDI2_PLL_MAX
+};
+
+/**
+ * enum hl_goya_dma_direction - Direction of DMA operation inside a LIN_DMA packet that is
+ *                              submitted to the GOYA's DMA QMAN. This attribute is not relevant
+ *                              to the H/W but the kernel driver use it to parse the packet's
+ *                              addresses and patch/validate them.
+ * @HL_DMA_HOST_TO_DRAM: DMA operation from Host memory to GOYA's DDR.
+ * @HL_DMA_HOST_TO_SRAM: DMA operation from Host memory to GOYA's SRAM.
+ * @HL_DMA_DRAM_TO_SRAM: DMA operation from GOYA's DDR to GOYA's SRAM.
+ * @HL_DMA_SRAM_TO_DRAM: DMA operation from GOYA's SRAM to GOYA's DDR.
+ * @HL_DMA_SRAM_TO_HOST: DMA operation from GOYA's SRAM to Host memory.
+ * @HL_DMA_DRAM_TO_HOST: DMA operation from GOYA's DDR to Host memory.
+ * @HL_DMA_DRAM_TO_DRAM: DMA operation from GOYA's DDR to GOYA's DDR.
+ * @HL_DMA_SRAM_TO_SRAM: DMA operation from GOYA's SRAM to GOYA's SRAM.
+ * @HL_DMA_ENUM_MAX: number of values in enum
+ */
+enum hl_goya_dma_direction {
+	HL_DMA_HOST_TO_DRAM,
+	HL_DMA_HOST_TO_SRAM,
+	HL_DMA_DRAM_TO_SRAM,
+	HL_DMA_SRAM_TO_DRAM,
+	HL_DMA_SRAM_TO_HOST,
+	HL_DMA_DRAM_TO_HOST,
+	HL_DMA_DRAM_TO_DRAM,
+	HL_DMA_SRAM_TO_SRAM,
+	HL_DMA_ENUM_MAX
+};
+
+/**
+ * enum hl_device_status - Device status information.
+ * @HL_DEVICE_STATUS_OPERATIONAL: Device is operational.
+ * @HL_DEVICE_STATUS_IN_RESET: Device is currently during reset.
+ * @HL_DEVICE_STATUS_MALFUNCTION: Device is unusable.
+ * @HL_DEVICE_STATUS_NEEDS_RESET: Device needs reset because auto reset was disabled.
+ * @HL_DEVICE_STATUS_IN_DEVICE_CREATION: Device is operational but its creation is still in
+ *                                       progress.
+ * @HL_DEVICE_STATUS_IN_RESET_AFTER_DEVICE_RELEASE: Device is currently during reset that was
+ *                                                  triggered because the user released the device
+ * @HL_DEVICE_STATUS_LAST: Last status.
+ */
+enum hl_device_status {
+	HL_DEVICE_STATUS_OPERATIONAL,
+	HL_DEVICE_STATUS_IN_RESET,
+	HL_DEVICE_STATUS_MALFUNCTION,
+	HL_DEVICE_STATUS_NEEDS_RESET,
+	HL_DEVICE_STATUS_IN_DEVICE_CREATION,
+	HL_DEVICE_STATUS_IN_RESET_AFTER_DEVICE_RELEASE,
+	HL_DEVICE_STATUS_LAST = HL_DEVICE_STATUS_IN_RESET_AFTER_DEVICE_RELEASE
+};
+
+enum hl_server_type {
+	HL_SERVER_TYPE_UNKNOWN = 0,
+	HL_SERVER_GAUDI_HLS1 = 1,
+	HL_SERVER_GAUDI_HLS1H = 2,
+	HL_SERVER_GAUDI_TYPE1 = 3,
+	HL_SERVER_GAUDI_TYPE2 = 4,
+	HL_SERVER_GAUDI2_HLS2 = 5,
+	HL_SERVER_GAUDI2_TYPE1 = 7
+};
+
+/*
+ * Notifier event values - for the notification mechanism and the HL_INFO_GET_EVENTS command
+ *
+ * HL_NOTIFIER_EVENT_TPC_ASSERT		- Indicates TPC assert event
+ * HL_NOTIFIER_EVENT_UNDEFINED_OPCODE	- Indicates undefined operation code
+ * HL_NOTIFIER_EVENT_DEVICE_RESET	- Indicates device requires a reset
+ * HL_NOTIFIER_EVENT_CS_TIMEOUT		- Indicates CS timeout error
+ * HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE	- Indicates device is unavailable
+ * HL_NOTIFIER_EVENT_USER_ENGINE_ERR	- Indicates device engine in error state
+ * HL_NOTIFIER_EVENT_GENERAL_HW_ERR     - Indicates device HW error
+ * HL_NOTIFIER_EVENT_RAZWI              - Indicates razwi happened
+ * HL_NOTIFIER_EVENT_PAGE_FAULT         - Indicates page fault happened
+ * HL_NOTIFIER_EVENT_CRITICAL_HW_ERR    - Indicates a HW error that requires SW abort and
+ *                                        HW reset
+ * HL_NOTIFIER_EVENT_CRITICAL_FW_ERR    - Indicates a FW error that requires SW abort and
+ *                                        HW reset
+ */
+#define HL_NOTIFIER_EVENT_TPC_ASSERT		(1ULL << 0)
+#define HL_NOTIFIER_EVENT_UNDEFINED_OPCODE	(1ULL << 1)
+#define HL_NOTIFIER_EVENT_DEVICE_RESET		(1ULL << 2)
+#define HL_NOTIFIER_EVENT_CS_TIMEOUT		(1ULL << 3)
+#define HL_NOTIFIER_EVENT_DEVICE_UNAVAILABLE	(1ULL << 4)
+#define HL_NOTIFIER_EVENT_USER_ENGINE_ERR	(1ULL << 5)
+#define HL_NOTIFIER_EVENT_GENERAL_HW_ERR	(1ULL << 6)
+#define HL_NOTIFIER_EVENT_RAZWI			(1ULL << 7)
+#define HL_NOTIFIER_EVENT_PAGE_FAULT		(1ULL << 8)
+#define HL_NOTIFIER_EVENT_CRITICL_HW_ERR	(1ULL << 9)
+#define HL_NOTIFIER_EVENT_CRITICL_FW_ERR	(1ULL << 10)
+
+/* Opcode for management ioctl
+ *
+ * HW_IP_INFO            - Receive information about different IP blocks in the
+ *                         device.
+ * HL_INFO_HW_EVENTS     - Receive an array describing how many times each event
+ *                         occurred since the last hard reset.
+ * HL_INFO_DRAM_USAGE    - Retrieve the dram usage inside the device and of the
+ *                         specific context. This is relevant only for devices
+ *                         where the dram is managed by the kernel driver
+ * HL_INFO_HW_IDLE       - Retrieve information about the idle status of each
+ *                         internal engine.
+ * HL_INFO_DEVICE_STATUS - Retrieve the device's status. This opcode doesn't
+ *                         require an open context.
+ * HL_INFO_DEVICE_UTILIZATION  - Retrieve the total utilization of the device
+ *                               over the last period specified by the user.
+ *                               The period can be between 100ms to 1s, in
+ *                               resolution of 100ms. The return value is a
+ *                               percentage of the utilization rate.
+ * HL_INFO_HW_EVENTS_AGGREGATE - Receive an array describing how many times each
+ *                               event occurred since the driver was loaded.
+ * HL_INFO_CLK_RATE            - Retrieve the current and maximum clock rate
+ *                               of the device in MHz. The maximum clock rate is
+ *                               configurable via sysfs parameter
+ * HL_INFO_RESET_COUNT   - Retrieve the counts of the soft and hard reset
+ *                         operations performed on the device since the last
+ *                         time the driver was loaded.
+ * HL_INFO_TIME_SYNC     - Retrieve the device's time alongside the host's time
+ *                         for synchronization.
+ * HL_INFO_CS_COUNTERS   - Retrieve command submission counters
+ * HL_INFO_PCI_COUNTERS  - Retrieve PCI counters
+ * HL_INFO_CLK_THROTTLE_REASON - Retrieve clock throttling reason
+ * HL_INFO_SYNC_MANAGER  - Retrieve sync manager info per dcore
+ * HL_INFO_TOTAL_ENERGY  - Retrieve total energy consumption
+ * HL_INFO_PLL_FREQUENCY - Retrieve PLL frequency
+ * HL_INFO_POWER         - Retrieve power information
+ * HL_INFO_OPEN_STATS    - Retrieve info regarding recent device open calls
+ * HL_INFO_DRAM_REPLACED_ROWS - Retrieve DRAM replaced rows info
+ * HL_INFO_DRAM_PENDING_ROWS - Retrieve DRAM pending rows num
+ * HL_INFO_LAST_ERR_OPEN_DEV_TIME - Retrieve timestamp of the last time the device was opened
+ *                                  and CS timeout or razwi error occurred.
+ * HL_INFO_CS_TIMEOUT_EVENT - Retrieve CS timeout timestamp and its related CS sequence number.
+ * HL_INFO_RAZWI_EVENT - Retrieve parameters of razwi:
+ *                            Timestamp of razwi.
+ *                            The address which accessing it caused the razwi.
+ *                            Razwi initiator.
+ *                            Razwi cause, was it a page fault or MMU access error.
+ *                            May return 0 even though no new data is available, in that case
+ *                            timestamp will be 0.
+ * HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES - Retrieve valid page sizes for device memory allocation
+ * HL_INFO_SECURED_ATTESTATION - Retrieve attestation report of the boot.
+ * HL_INFO_REGISTER_EVENTFD   - Register eventfd for event notifications.
+ * HL_INFO_UNREGISTER_EVENTFD - Unregister eventfd
+ * HL_INFO_GET_EVENTS         - Retrieve the last occurred events
+ * HL_INFO_UNDEFINED_OPCODE_EVENT - Retrieve last undefined opcode error information.
+ *                                  May return 0 even though no new data is available, in that case
+ *                                  timestamp will be 0.
+ * HL_INFO_ENGINE_STATUS - Retrieve the status of all the h/w engines in the asic.
+ * HL_INFO_PAGE_FAULT_EVENT - Retrieve parameters of captured page fault.
+ *                            May return 0 even though no new data is available, in that case
+ *                            timestamp will be 0.
+ * HL_INFO_USER_MAPPINGS - Retrieve user mappings, captured after page fault event.
+ * HL_INFO_FW_GENERIC_REQ - Send generic request to FW.
+ * HL_INFO_HW_ERR_EVENT   - Retrieve information on the reported HW error.
+ *                          May return 0 even though no new data is available, in that case
+ *                          timestamp will be 0.
+ * HL_INFO_FW_ERR_EVENT   - Retrieve information on the reported FW error.
+ *                          May return 0 even though no new data is available, in that case
+ *                          timestamp will be 0.
+ * HL_INFO_USER_ENGINE_ERR_EVENT - Retrieve the last engine id that reported an error.
+ */
+#define HL_INFO_HW_IP_INFO			0
+#define HL_INFO_HW_EVENTS			1
+#define HL_INFO_DRAM_USAGE			2
+#define HL_INFO_HW_IDLE				3
+#define HL_INFO_DEVICE_STATUS			4
+#define HL_INFO_DEVICE_UTILIZATION		6
+#define HL_INFO_HW_EVENTS_AGGREGATE		7
+#define HL_INFO_CLK_RATE			8
+#define HL_INFO_RESET_COUNT			9
+#define HL_INFO_TIME_SYNC			10
+#define HL_INFO_CS_COUNTERS			11
+#define HL_INFO_PCI_COUNTERS			12
+#define HL_INFO_CLK_THROTTLE_REASON		13
+#define HL_INFO_SYNC_MANAGER			14
+#define HL_INFO_TOTAL_ENERGY			15
+#define HL_INFO_PLL_FREQUENCY			16
+#define HL_INFO_POWER				17
+#define HL_INFO_OPEN_STATS			18
+#define HL_INFO_DRAM_REPLACED_ROWS		21
+#define HL_INFO_DRAM_PENDING_ROWS		22
+#define HL_INFO_LAST_ERR_OPEN_DEV_TIME		23
+#define HL_INFO_CS_TIMEOUT_EVENT		24
+#define HL_INFO_RAZWI_EVENT			25
+#define HL_INFO_DEV_MEM_ALLOC_PAGE_SIZES	26
+#define HL_INFO_SECURED_ATTESTATION		27
+#define HL_INFO_REGISTER_EVENTFD		28
+#define HL_INFO_UNREGISTER_EVENTFD		29
+#define HL_INFO_GET_EVENTS			30
+#define HL_INFO_UNDEFINED_OPCODE_EVENT		31
+#define HL_INFO_ENGINE_STATUS			32
+#define HL_INFO_PAGE_FAULT_EVENT		33
+#define HL_INFO_USER_MAPPINGS			34
+#define HL_INFO_FW_GENERIC_REQ			35
+#define HL_INFO_HW_ERR_EVENT			36
+#define HL_INFO_FW_ERR_EVENT			37
+#define HL_INFO_USER_ENGINE_ERR_EVENT		38
+#define HL_INFO_DEV_SIGNED			40
+
+#define HL_INFO_VERSION_MAX_LEN			128
+#define HL_INFO_CARD_NAME_MAX_LEN		16
+
+/* Maximum buffer size for retrieving engines status */
+#define HL_ENGINES_DATA_MAX_SIZE	SZ_1M
+
+/**
+ * struct hl_info_hw_ip_info - hardware information on various IPs in the ASIC
+ * @sram_base_address: The first SRAM physical base address that is free to be
+ *                     used by the user.
+ * @dram_base_address: The first DRAM virtual or physical base address that is
+ *                     free to be used by the user.
+ * @dram_size: The DRAM size that is available to the user.
+ * @sram_size: The SRAM size that is available to the user.
+ * @num_of_events: The number of events that can be received from the f/w. This
+ *                 is needed so the user can what is the size of the h/w events
+ *                 array he needs to pass to the kernel when he wants to fetch
+ *                 the event counters.
+ * @device_id: PCI device ID of the ASIC.
+ * @module_id: Module ID of the ASIC for mezzanine cards in servers
+ *             (From OCP spec).
+ * @decoder_enabled_mask: Bit-mask that represents which decoders are enabled.
+ * @first_available_interrupt_id: The first available interrupt ID for the user
+ *                                to be used when it works with user interrupts.
+ *                                Relevant for Gaudi2 and later.
+ * @server_type: Server type that the Gaudi ASIC is currently installed in.
+ *               The value is according to enum hl_server_type
+ * @cpld_version: CPLD version on the board.
+ * @psoc_pci_pll_nr: PCI PLL NR value. Needed by the profiler in some ASICs.
+ * @psoc_pci_pll_nf: PCI PLL NF value. Needed by the profiler in some ASICs.
+ * @psoc_pci_pll_od: PCI PLL OD value. Needed by the profiler in some ASICs.
+ * @psoc_pci_pll_div_factor: PCI PLL DIV factor value. Needed by the profiler
+ *                           in some ASICs.
+ * @tpc_enabled_mask: Bit-mask that represents which TPCs are enabled. Relevant
+ *                    for Goya/Gaudi only.
+ * @dram_enabled: Whether the DRAM is enabled.
+ * @security_enabled: Whether security is enabled on device.
+ * @mme_master_slave_mode: Indicate whether the MME is working in master/slave
+ *                         configuration. Relevant for Gaudi2 and later.
+ * @cpucp_version: The CPUCP f/w version.
+ * @card_name: The card name as passed by the f/w.
+ * @tpc_enabled_mask_ext: Bit-mask that represents which TPCs are enabled.
+ *                        Relevant for Gaudi2 and later.
+ * @dram_page_size: The DRAM physical page size.
+ * @edma_enabled_mask: Bit-mask that represents which EDMAs are enabled.
+ *                     Relevant for Gaudi2 and later.
+ * @number_of_user_interrupts: The number of interrupts that are available to the userspace
+ *                             application to use. Relevant for Gaudi2 and later.
+ * @device_mem_alloc_default_page_size: default page size used in device memory allocation.
+ * @revision_id: PCI revision ID of the ASIC.
+ * @tpc_interrupt_id: interrupt id for TPC to use in order to raise events towards the host.
+ * @rotator_enabled_mask: Bit-mask that represents which rotators are enabled.
+ *                        Relevant for Gaudi3 and later.
+ * @engine_core_interrupt_reg_addr: interrupt register address for engine core to use
+ *                                  in order to raise events toward FW.
+ * @reserved_dram_size: DRAM size reserved for driver and firmware.
+ */
+struct hl_info_hw_ip_info {
+	__u64 sram_base_address;
+	__u64 dram_base_address;
+	__u64 dram_size;
+	__u32 sram_size;
+	__u32 num_of_events;
+	__u32 device_id;
+	__u32 module_id;
+	__u32 decoder_enabled_mask;
+	__u16 first_available_interrupt_id;
+	__u16 server_type;
+	__u32 cpld_version;
+	__u32 psoc_pci_pll_nr;
+	__u32 psoc_pci_pll_nf;
+	__u32 psoc_pci_pll_od;
+	__u32 psoc_pci_pll_div_factor;
+	__u8 tpc_enabled_mask;
+	__u8 dram_enabled;
+	__u8 security_enabled;
+	__u8 mme_master_slave_mode;
+	__u8 cpucp_version[HL_INFO_VERSION_MAX_LEN];
+	__u8 card_name[HL_INFO_CARD_NAME_MAX_LEN];
+	__u64 tpc_enabled_mask_ext;
+	__u64 dram_page_size;
+	__u32 edma_enabled_mask;
+	__u16 number_of_user_interrupts;
+	__u8 reserved1;
+	__u8 reserved2;
+	__u64 reserved3;
+	__u64 device_mem_alloc_default_page_size;
+	__u64 reserved4;
+	__u64 reserved5;
+	__u32 reserved6;
+	__u8 reserved7;
+	__u8 revision_id;
+	__u16 tpc_interrupt_id;
+	__u32 rotator_enabled_mask;
+	__u32 reserved9;
+	__u64 engine_core_interrupt_reg_addr;
+	__u64 reserved_dram_size;
+};
+
+struct hl_info_dram_usage {
+	__u64 dram_free_mem;
+	__u64 ctx_dram_mem;
+};
+
+#define HL_BUSY_ENGINES_MASK_EXT_SIZE	4
+
+struct hl_info_hw_idle {
+	__u32 is_idle;
+	/*
+	 * Bitmask of busy engines.
+	 * Bits definition is according to `enum <chip>_engine_id'.
+	 */
+	__u32 busy_engines_mask;
+
+	/*
+	 * Extended Bitmask of busy engines.
+	 * Bits definition is according to `enum <chip>_engine_id'.
+	 */
+	__u64 busy_engines_mask_ext[HL_BUSY_ENGINES_MASK_EXT_SIZE];
+};
+
+struct hl_info_device_status {
+	__u32 status;
+	__u32 pad;
+};
+
+struct hl_info_device_utilization {
+	__u32 utilization;
+	__u32 pad;
+};
+
+struct hl_info_clk_rate {
+	__u32 cur_clk_rate_mhz;
+	__u32 max_clk_rate_mhz;
+};
+
+struct hl_info_reset_count {
+	__u32 hard_reset_cnt;
+	__u32 soft_reset_cnt;
+};
+
+struct hl_info_time_sync {
+	__u64 device_time;
+	__u64 host_time;
+	__u64 tsc_time;
+};
+
+/**
+ * struct hl_info_pci_counters - pci counters
+ * @rx_throughput: PCI rx throughput KBps
+ * @tx_throughput: PCI tx throughput KBps
+ * @replay_cnt: PCI replay counter
+ */
+struct hl_info_pci_counters {
+	__u64 rx_throughput;
+	__u64 tx_throughput;
+	__u64 replay_cnt;
+};
+
+enum hl_clk_throttling_type {
+	HL_CLK_THROTTLE_TYPE_POWER,
+	HL_CLK_THROTTLE_TYPE_THERMAL,
+	HL_CLK_THROTTLE_TYPE_MAX
+};
+
+/* clk_throttling_reason masks */
+#define HL_CLK_THROTTLE_POWER		(1 << HL_CLK_THROTTLE_TYPE_POWER)
+#define HL_CLK_THROTTLE_THERMAL		(1 << HL_CLK_THROTTLE_TYPE_THERMAL)
+
+/**
+ * struct hl_info_clk_throttle - clock throttling reason
+ * @clk_throttling_reason: each bit represents a clk throttling reason
+ * @clk_throttling_timestamp_us: represents CPU timestamp in microseconds of the start-event
+ * @clk_throttling_duration_ns: the clock throttle time in nanosec
+ */
+struct hl_info_clk_throttle {
+	__u32 clk_throttling_reason;
+	__u32 pad;
+	__u64 clk_throttling_timestamp_us[HL_CLK_THROTTLE_TYPE_MAX];
+	__u64 clk_throttling_duration_ns[HL_CLK_THROTTLE_TYPE_MAX];
+};
+
+/**
+ * struct hl_info_energy - device energy information
+ * @total_energy_consumption: total device energy consumption
+ */
+struct hl_info_energy {
+	__u64 total_energy_consumption;
+};
+
+#define HL_PLL_NUM_OUTPUTS 4
+
+struct hl_pll_frequency_info {
+	__u16 output[HL_PLL_NUM_OUTPUTS];
+};
+
+/**
+ * struct hl_open_stats_info - device open statistics information
+ * @open_counter: ever growing counter, increased on each successful dev open
+ * @last_open_period_ms: duration (ms) device was open last time
+ * @is_compute_ctx_active: Whether there is an active compute context executing
+ * @compute_ctx_in_release: true if the current compute context is being released
+ */
+struct hl_open_stats_info {
+	__u64 open_counter;
+	__u64 last_open_period_ms;
+	__u8 is_compute_ctx_active;
+	__u8 compute_ctx_in_release;
+	__u8 pad[6];
+};
+
+/**
+ * struct hl_power_info - power information
+ * @power: power consumption
+ */
+struct hl_power_info {
+	__u64 power;
+};
+
+/**
+ * struct hl_info_sync_manager - sync manager information
+ * @first_available_sync_object: first available sob
+ * @first_available_monitor: first available monitor
+ * @first_available_cq: first available cq
+ */
+struct hl_info_sync_manager {
+	__u32 first_available_sync_object;
+	__u32 first_available_monitor;
+	__u32 first_available_cq;
+	__u32 reserved;
+};
+
+/**
+ * struct hl_info_cs_counters - command submission counters
+ * @total_out_of_mem_drop_cnt: total dropped due to memory allocation issue
+ * @ctx_out_of_mem_drop_cnt: context dropped due to memory allocation issue
+ * @total_parsing_drop_cnt: total dropped due to error in packet parsing
+ * @ctx_parsing_drop_cnt: context dropped due to error in packet parsing
+ * @total_queue_full_drop_cnt: total dropped due to queue full
+ * @ctx_queue_full_drop_cnt: context dropped due to queue full
+ * @total_device_in_reset_drop_cnt: total dropped due to device in reset
+ * @ctx_device_in_reset_drop_cnt: context dropped due to device in reset
+ * @total_max_cs_in_flight_drop_cnt: total dropped due to maximum CS in-flight
+ * @ctx_max_cs_in_flight_drop_cnt: context dropped due to maximum CS in-flight
+ * @total_validation_drop_cnt: total dropped due to validation error
+ * @ctx_validation_drop_cnt: context dropped due to validation error
+ */
+struct hl_info_cs_counters {
+	__u64 total_out_of_mem_drop_cnt;
+	__u64 ctx_out_of_mem_drop_cnt;
+	__u64 total_parsing_drop_cnt;
+	__u64 ctx_parsing_drop_cnt;
+	__u64 total_queue_full_drop_cnt;
+	__u64 ctx_queue_full_drop_cnt;
+	__u64 total_device_in_reset_drop_cnt;
+	__u64 ctx_device_in_reset_drop_cnt;
+	__u64 total_max_cs_in_flight_drop_cnt;
+	__u64 ctx_max_cs_in_flight_drop_cnt;
+	__u64 total_validation_drop_cnt;
+	__u64 ctx_validation_drop_cnt;
+};
+
+/**
+ * struct hl_info_last_err_open_dev_time - last error boot information.
+ * @timestamp: timestamp of last time the device was opened and error occurred.
+ */
+struct hl_info_last_err_open_dev_time {
+	__s64 timestamp;
+};
+
+/**
+ * struct hl_info_cs_timeout_event - last CS timeout information.
+ * @timestamp: timestamp when last CS timeout event occurred.
+ * @seq: sequence number of last CS timeout event.
+ */
+struct hl_info_cs_timeout_event {
+	__s64 timestamp;
+	__u64 seq;
+};
+
+#define HL_RAZWI_NA_ENG_ID U16_MAX
+#define HL_RAZWI_MAX_NUM_OF_ENGINES_PER_RTR 128
+#define HL_RAZWI_READ		BIT(0)
+#define HL_RAZWI_WRITE		BIT(1)
+#define HL_RAZWI_LBW		BIT(2)
+#define HL_RAZWI_HBW		BIT(3)
+#define HL_RAZWI_RR		BIT(4)
+#define HL_RAZWI_ADDR_DEC	BIT(5)
+
+/**
+ * struct hl_info_razwi_event - razwi information.
+ * @timestamp: timestamp of razwi.
+ * @addr: address which accessing it caused razwi.
+ * @engine_id: engine id of the razwi initiator, if it was initiated by engine that does not
+ *             have engine id it will be set to HL_RAZWI_NA_ENG_ID. If there are several possible
+ *             engines which caused the razwi, it will hold all of them.
+ * @num_of_possible_engines: contains number of possible engine ids. In some asics, razwi indication
+ *                           might be common for several engines and there is no way to get the
+ *                           exact engine. In this way, engine_id array will be filled with all
+ *                           possible engines caused this razwi. Also, there might be possibility
+ *                           in gaudi, where we don't indication on specific engine, in that case
+ *                           the value of this parameter will be zero.
+ * @flags: bitmask for additional data: HL_RAZWI_READ - razwi caused by read operation
+ *                                      HL_RAZWI_WRITE - razwi caused by write operation
+ *                                      HL_RAZWI_LBW - razwi caused by lbw fabric transaction
+ *                                      HL_RAZWI_HBW - razwi caused by hbw fabric transaction
+ *                                      HL_RAZWI_RR - razwi caused by range register
+ *                                      HL_RAZWI_ADDR_DEC - razwi caused by address decode error
+ *         Note: this data is not supported by all asics, in that case the relevant bits will not
+ *               be set.
+ */
+struct hl_info_razwi_event {
+	__s64 timestamp;
+	__u64 addr;
+	__u16 engine_id[HL_RAZWI_MAX_NUM_OF_ENGINES_PER_RTR];
+	__u16 num_of_possible_engines;
+	__u8 flags;
+	__u8 pad[5];
+};
+
+#define MAX_QMAN_STREAMS_INFO		4
+#define OPCODE_INFO_MAX_ADDR_SIZE	8
+/**
+ * struct hl_info_undefined_opcode_event - info about last undefined opcode error
+ * @timestamp: timestamp of the undefined opcode error
+ * @cb_addr_streams: CB addresses (per stream) that are currently exists in the PQ
+ *                   entries. In case all streams array entries are
+ *                   filled with values, it means the execution was in Lower-CP.
+ * @cq_addr: the address of the current handled command buffer
+ * @cq_size: the size of the current handled command buffer
+ * @cb_addr_streams_len: num of streams - actual len of cb_addr_streams array.
+ *                       should be equal to 1 in case of undefined opcode
+ *                       in Upper-CP (specific stream) and equal to 4 incase
+ *                       of undefined opcode in Lower-CP.
+ * @engine_id: engine-id that the error occurred on
+ * @stream_id: the stream id the error occurred on. In case the stream equals to
+ *             MAX_QMAN_STREAMS_INFO it means the error occurred on a Lower-CP.
+ */
+struct hl_info_undefined_opcode_event {
+	__s64 timestamp;
+	__u64 cb_addr_streams[MAX_QMAN_STREAMS_INFO][OPCODE_INFO_MAX_ADDR_SIZE];
+	__u64 cq_addr;
+	__u32 cq_size;
+	__u32 cb_addr_streams_len;
+	__u32 engine_id;
+	__u32 stream_id;
+};
+
+/**
+ * struct hl_info_hw_err_event - info about HW error
+ * @timestamp: timestamp of error occurrence
+ * @event_id: The async event ID (specific to each device type).
+ * @pad: size padding for u64 granularity.
+ */
+struct hl_info_hw_err_event {
+	__s64 timestamp;
+	__u16 event_id;
+	__u16 pad[3];
+};
+
+/* FW error definition for event_type in struct hl_info_fw_err_event */
+enum hl_info_fw_err_type {
+	HL_INFO_FW_HEARTBEAT_ERR,
+	HL_INFO_FW_REPORTED_ERR,
+};
+
+/**
+ * struct hl_info_fw_err_event - info about FW error
+ * @timestamp: time-stamp of error occurrence
+ * @err_type: The type of event as defined in hl_info_fw_err_type.
+ * @event_id: The async event ID (specific to each device type, applicable only when event type is
+ *             HL_INFO_FW_REPORTED_ERR).
+ * @pad: size padding for u64 granularity.
+ */
+struct hl_info_fw_err_event {
+	__s64 timestamp;
+	__u16 err_type;
+	__u16 event_id;
+	__u32 pad;
+};
+
+/**
+ * struct hl_info_engine_err_event - engine error info
+ * @timestamp: time-stamp of error occurrence
+ * @engine_id: engine id who reported the error.
+ * @error_count: Amount of errors reported.
+ * @pad: size padding for u64 granularity.
+ */
+struct hl_info_engine_err_event {
+	__s64 timestamp;
+	__u16 engine_id;
+	__u16 error_count;
+	__u32 pad;
+};
+
+/**
+ * struct hl_info_dev_memalloc_page_sizes - valid page sizes in device mem alloc information.
+ * @page_order_bitmask: bitmap in which a set bit represents the order of the supported page size
+ *                      (e.g. 0x2100000 means that 1MB and 32MB pages are supported).
+ */
+struct hl_info_dev_memalloc_page_sizes {
+	__u64 page_order_bitmask;
+};
+
+#define SEC_PCR_DATA_BUF_SZ	256
+#define SEC_PCR_QUOTE_BUF_SZ	510	/* (512 - 2) 2 bytes used for size */
+#define SEC_SIGNATURE_BUF_SZ	255	/* (256 - 1) 1 byte used for size */
+#define SEC_PUB_DATA_BUF_SZ	510	/* (512 - 2) 2 bytes used for size */
+#define SEC_CERTIFICATE_BUF_SZ	2046	/* (2048 - 2) 2 bytes used for size */
+#define SEC_DEV_INFO_BUF_SZ	5120
+
+/*
+ * struct hl_info_sec_attest - attestation report of the boot
+ * @nonce: number only used once. random number provided by host. this also passed to the quote
+ *         command as a qualifying data.
+ * @pcr_quote_len: length of the attestation quote data (bytes)
+ * @pub_data_len: length of the public data (bytes)
+ * @certificate_len: length of the certificate (bytes)
+ * @pcr_num_reg: number of PCR registers in the pcr_data array
+ * @pcr_reg_len: length of each PCR register in the pcr_data array (bytes)
+ * @quote_sig_len: length of the attestation report signature (bytes)
+ * @pcr_data: raw values of the PCR registers
+ * @pcr_quote: attestation report data structure
+ * @quote_sig: signature structure of the attestation report
+ * @public_data: public key for the signed attestation
+ *		 (outPublic + name + qualifiedName)
+ * @certificate: certificate for the attestation signing key
+ */
+struct hl_info_sec_attest {
+	__u32 nonce;
+	__u16 pcr_quote_len;
+	__u16 pub_data_len;
+	__u16 certificate_len;
+	__u8 pcr_num_reg;
+	__u8 pcr_reg_len;
+	__u8 quote_sig_len;
+	__u8 pcr_data[SEC_PCR_DATA_BUF_SZ];
+	__u8 pcr_quote[SEC_PCR_QUOTE_BUF_SZ];
+	__u8 quote_sig[SEC_SIGNATURE_BUF_SZ];
+	__u8 public_data[SEC_PUB_DATA_BUF_SZ];
+	__u8 certificate[SEC_CERTIFICATE_BUF_SZ];
+	__u8 pad0[2];
+};
+
+/*
+ * struct hl_info_signed - device information signed by a secured device.
+ * @nonce: number only used once. random number provided by host. this also passed to the quote
+ *         command as a qualifying data.
+ * @pub_data_len: length of the public data (bytes)
+ * @certificate_len: length of the certificate (bytes)
+ * @info_sig_len: length of the attestation signature (bytes)
+ * @public_data: public key info signed info data (outPublic + name + qualifiedName)
+ * @certificate: certificate for the signing key
+ * @info_sig: signature of the info + nonce data.
+ * @dev_info_len: length of device info (bytes)
+ * @dev_info: device info as byte array.
+ */
+struct hl_info_signed {
+	__u32 nonce;
+	__u16 pub_data_len;
+	__u16 certificate_len;
+	__u8 info_sig_len;
+	__u8 public_data[SEC_PUB_DATA_BUF_SZ];
+	__u8 certificate[SEC_CERTIFICATE_BUF_SZ];
+	__u8 info_sig[SEC_SIGNATURE_BUF_SZ];
+	__u16 dev_info_len;
+	__u8 dev_info[SEC_DEV_INFO_BUF_SZ];
+	__u8 pad[2];
+};
+
+/**
+ * struct hl_page_fault_info - page fault information.
+ * @timestamp: timestamp of page fault.
+ * @addr: address which accessing it caused page fault.
+ * @engine_id: engine id which caused the page fault, supported only in gaudi3.
+ */
+struct hl_page_fault_info {
+	__s64 timestamp;
+	__u64 addr;
+	__u16 engine_id;
+	__u8 pad[6];
+};
+
+/**
+ * struct hl_user_mapping - user mapping information.
+ * @dev_va: device virtual address.
+ * @size: virtual address mapping size.
+ */
+struct hl_user_mapping {
+	__u64 dev_va;
+	__u64 size;
+};
+
+enum gaudi_dcores {
+	HL_GAUDI_WS_DCORE,
+	HL_GAUDI_WN_DCORE,
+	HL_GAUDI_EN_DCORE,
+	HL_GAUDI_ES_DCORE
+};
+
+/**
+ * struct hl_info_args - Main structure to retrieve device related information.
+ * @return_pointer: User space address of the relevant structure related to HL_INFO_* operation
+ *                  mentioned in @op.
+ * @return_size: Size of the structure used in @return_pointer, just like "size" in "snprintf", it
+ *               limits how many bytes the kernel can write. For hw_events array, the size should be
+ *               hl_info_hw_ip_info.num_of_events * sizeof(__u32).
+ * @op: Defines which type of information to be retrieved. Refer HL_INFO_* for details.
+ * @dcore_id: DCORE id for which the information is relevant (for Gaudi refer to enum gaudi_dcores).
+ * @ctx_id: Context ID of the user. Currently not in use.
+ * @period_ms: Period value, in milliseconds, for utilization rate in range 100ms - 1000ms in 100 ms
+ *             resolution. Currently not in use.
+ * @pll_index: Index as defined in hl_<asic type>_pll_index enumeration.
+ * @eventfd: event file descriptor for event notifications.
+ * @user_buffer_actual_size: Actual data size which was copied to user allocated buffer by the
+ *                           driver. It is possible for the user to allocate buffer larger than
+ *                           needed, hence updating this variable so user will know the exact amount
+ *                           of bytes copied by the kernel to the buffer.
+ * @sec_attest_nonce: Nonce number used for attestation report.
+ * @array_size: Number of array members copied to user buffer.
+ *              Relevant for HL_INFO_USER_MAPPINGS info ioctl.
+ * @fw_sub_opcode: generic requests sub opcodes.
+ * @pad: Padding to 64 bit.
+ */
+struct hl_info_args {
+	__u64 return_pointer;
+	__u32 return_size;
+	__u32 op;
+
+	union {
+		__u32 dcore_id;
+		__u32 ctx_id;
+		__u32 period_ms;
+		__u32 pll_index;
+		__u32 eventfd;
+		__u32 user_buffer_actual_size;
+		__u32 sec_attest_nonce;
+		__u32 array_size;
+		__u32 fw_sub_opcode;
+	};
+
+	__u32 pad;
+};
+
+/* Opcode to create a new command buffer */
+#define HL_CB_OP_CREATE		0
+/* Opcode to destroy previously created command buffer */
+#define HL_CB_OP_DESTROY	1
+/* Opcode to retrieve information about a command buffer */
+#define HL_CB_OP_INFO		2
+
+/* 2MB minus 32 bytes for 2xMSG_PROT */
+#define HL_MAX_CB_SIZE		(0x200000 - 32)
+
+/* Indicates whether the command buffer should be mapped to the device's MMU */
+#define HL_CB_FLAGS_MAP			0x1
+
+/* Used with HL_CB_OP_INFO opcode to get the device va address for kernel mapped CB */
+#define HL_CB_FLAGS_GET_DEVICE_VA	0x2
+
+struct hl_cb_in {
+	/* Handle of CB or 0 if we want to create one */
+	__u64 cb_handle;
+	/* HL_CB_OP_* */
+	__u32 op;
+
+	/* Size of CB. Maximum size is HL_MAX_CB_SIZE. The minimum size that
+	 * will be allocated, regardless of this parameter's value, is PAGE_SIZE
+	 */
+	__u32 cb_size;
+
+	/* Context ID - Currently not in use */
+	__u32 ctx_id;
+	/* HL_CB_FLAGS_* */
+	__u32 flags;
+};
+
+struct hl_cb_out {
+	union {
+		/* Handle of CB */
+		__u64 cb_handle;
+
+		union {
+			/* Information about CB */
+			struct {
+				/* Usage count of CB */
+				__u32 usage_cnt;
+				__u32 pad;
+			};
+
+			/* CB mapped address to device MMU */
+			__u64 device_va;
+		};
+	};
+};
+
+union hl_cb_args {
+	struct hl_cb_in in;
+	struct hl_cb_out out;
+};
+
+/* HL_CS_CHUNK_FLAGS_ values
+ *
+ * HL_CS_CHUNK_FLAGS_USER_ALLOC_CB:
+ *      Indicates if the CB was allocated and mapped by userspace
+ *      (relevant to Gaudi2 and later). User allocated CB is a command buffer,
+ *      allocated by the user, via malloc (or similar). After allocating the
+ *      CB, the user invokes - “memory ioctl” to map the user memory into a
+ *      device virtual address. The user provides this address via the
+ *      cb_handle field. The interface provides the ability to create a
+ *      large CBs, Which aren’t limited to “HL_MAX_CB_SIZE”. Therefore, it
+ *      increases the PCI-DMA queues throughput. This CB allocation method
+ *      also reduces the use of Linux DMA-able memory pool. Which are limited
+ *      and used by other Linux sub-systems.
+ */
+#define HL_CS_CHUNK_FLAGS_USER_ALLOC_CB 0x1
+
+/*
+ * This structure size must always be fixed to 64-bytes for backward
+ * compatibility
+ */
+struct hl_cs_chunk {
+	union {
+		/* Goya/Gaudi:
+		 * For external queue, this represents a Handle of CB on the
+		 * Host.
+		 * For internal queue in Goya, this represents an SRAM or
+		 * a DRAM address of the internal CB. In Gaudi, this might also
+		 * represent a mapped host address of the CB.
+		 *
+		 * Gaudi2 onwards:
+		 * For H/W queue, this represents either a Handle of CB on the
+		 * Host, or an SRAM, a DRAM, or a mapped host address of the CB.
+		 *
+		 * A mapped host address is in the device address space, after
+		 * a host address was mapped by the device MMU.
+		 */
+		__u64 cb_handle;
+
+		/* Relevant only when HL_CS_FLAGS_WAIT or
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set
+		 * This holds address of array of u64 values that contain
+		 * signal CS sequence numbers. The wait described by
+		 * this job will listen on all those signals
+		 * (wait event per signal)
+		 */
+		__u64 signal_seq_arr;
+
+		/*
+		 * Relevant only when HL_CS_FLAGS_WAIT or
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set
+		 * along with HL_CS_FLAGS_ENCAP_SIGNALS.
+		 * This is the CS sequence which has the encapsulated signals.
+		 */
+		__u64 encaps_signal_seq;
+	};
+
+	/* Index of queue to put the CB on */
+	__u32 queue_index;
+
+	union {
+		/*
+		 * Size of command buffer with valid packets
+		 * Can be smaller then actual CB size
+		 */
+		__u32 cb_size;
+
+		/* Relevant only when HL_CS_FLAGS_WAIT or
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set.
+		 * Number of entries in signal_seq_arr
+		 */
+		__u32 num_signal_seq_arr;
+
+		/* Relevant only when HL_CS_FLAGS_WAIT or
+		 * HL_CS_FLAGS_COLLECTIVE_WAIT is set along
+		 * with HL_CS_FLAGS_ENCAP_SIGNALS
+		 * This set the signals range that the user want to wait for
+		 * out of the whole reserved signals range.
+		 * e.g if the signals range is 20, and user don't want
+		 * to wait for signal 8, so he set this offset to 7, then
+		 * he call the API again with 9 and so on till 20.
+		 */
+		__u32 encaps_signal_offset;
+	};
+
+	/* HL_CS_CHUNK_FLAGS_* */
+	__u32 cs_chunk_flags;
+
+	/* Relevant only when HL_CS_FLAGS_COLLECTIVE_WAIT is set.
+	 * This holds the collective engine ID. The wait described by this job
+	 * will sync with this engine and with all NICs before completion.
+	 */
+	__u32 collective_engine_id;
+
+	/* Align structure to 64 bytes */
+	__u32 pad[10];
+};
+
+/* SIGNAL/WAIT/COLLECTIVE_WAIT flags are mutually exclusive */
+#define HL_CS_FLAGS_FORCE_RESTORE		0x1
+#define HL_CS_FLAGS_SIGNAL			0x2
+#define HL_CS_FLAGS_WAIT			0x4
+#define HL_CS_FLAGS_COLLECTIVE_WAIT		0x8
+
+#define HL_CS_FLAGS_TIMESTAMP			0x20
+#define HL_CS_FLAGS_STAGED_SUBMISSION		0x40
+#define HL_CS_FLAGS_STAGED_SUBMISSION_FIRST	0x80
+#define HL_CS_FLAGS_STAGED_SUBMISSION_LAST	0x100
+#define HL_CS_FLAGS_CUSTOM_TIMEOUT		0x200
+#define HL_CS_FLAGS_SKIP_RESET_ON_TIMEOUT	0x400
+
+/*
+ * The encapsulated signals CS is merged into the existing CS ioctls.
+ * In order to use this feature need to follow the below procedure:
+ * 1. Reserve signals, set the CS type to HL_CS_FLAGS_RESERVE_SIGNALS_ONLY
+ *    the output of this API will be the SOB offset from CFG_BASE.
+ *    this address will be used to patch CB cmds to do the signaling for this
+ *    SOB by incrementing it's value.
+ *    for reverting the reservation use HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY
+ *    CS type, note that this might fail if out-of-sync happened to the SOB
+ *    value, in case other signaling request to the same SOB occurred between
+ *    reserve-unreserve calls.
+ * 2. Use the staged CS to do the encapsulated signaling jobs.
+ *    use HL_CS_FLAGS_STAGED_SUBMISSION and HL_CS_FLAGS_STAGED_SUBMISSION_FIRST
+ *    along with HL_CS_FLAGS_ENCAP_SIGNALS flag, and set encaps_signal_offset
+ *    field. This offset allows app to wait on part of the reserved signals.
+ * 3. Use WAIT/COLLECTIVE WAIT CS along with HL_CS_FLAGS_ENCAP_SIGNALS flag
+ *    to wait for the encapsulated signals.
+ */
+#define HL_CS_FLAGS_ENCAP_SIGNALS		0x800
+#define HL_CS_FLAGS_RESERVE_SIGNALS_ONLY	0x1000
+#define HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY	0x2000
+
+/*
+ * The engine cores CS is merged into the existing CS ioctls.
+ * Use it to control the engine cores mode.
+ */
+#define HL_CS_FLAGS_ENGINE_CORE_COMMAND		0x4000
+
+/*
+ * The flush HBW PCI writes is merged into the existing CS ioctls.
+ * Used to flush all HBW PCI writes.
+ * This is a blocking operation and for this reason the user shall not use
+ * the return sequence number (which will be invalid anyway)
+ */
+#define HL_CS_FLAGS_FLUSH_PCI_HBW_WRITES	0x8000
+
+/*
+ * The engines CS is merged into the existing CS ioctls.
+ * Use it to control engines modes.
+ */
+#define HL_CS_FLAGS_ENGINES_COMMAND		0x10000
+
+#define HL_CS_STATUS_SUCCESS		0
+
+#define HL_MAX_JOBS_PER_CS		512
+
+/*
+ * enum hl_engine_command - engine command
+ *
+ * @HL_ENGINE_CORE_HALT: engine core halt
+ * @HL_ENGINE_CORE_RUN: engine core run
+ * @HL_ENGINE_STALL: user engine/s stall
+ * @HL_ENGINE_RESUME: user engine/s resume
+ */
+enum hl_engine_command {
+	HL_ENGINE_CORE_HALT = 1,
+	HL_ENGINE_CORE_RUN = 2,
+	HL_ENGINE_STALL = 3,
+	HL_ENGINE_RESUME = 4,
+	HL_ENGINE_COMMAND_MAX
+};
+
+struct hl_cs_in {
+
+	union {
+		struct {
+			/* this holds address of array of hl_cs_chunk for restore phase */
+			__u64 chunks_restore;
+
+			/* holds address of array of hl_cs_chunk for execution phase */
+			__u64 chunks_execute;
+		};
+
+		/* Valid only when HL_CS_FLAGS_ENGINE_CORE_COMMAND is set */
+		struct {
+			/* this holds address of array of uint32 for engine_cores */
+			__u64 engine_cores;
+
+			/* number of engine cores in engine_cores array */
+			__u32 num_engine_cores;
+
+			/* the core command to be sent towards engine cores */
+			__u32 core_command;
+		};
+
+		/* Valid only when HL_CS_FLAGS_ENGINES_COMMAND is set */
+		struct {
+			/* this holds address of array of uint32 for engines */
+			__u64 engines;
+
+			/* number of engines in engines array */
+			__u32 num_engines;
+
+			/* the engine command to be sent towards engines */
+			__u32 engine_command;
+		};
+	};
+
+	union {
+		/*
+		 * Sequence number of a staged submission CS
+		 * valid only if HL_CS_FLAGS_STAGED_SUBMISSION is set and
+		 * HL_CS_FLAGS_STAGED_SUBMISSION_FIRST is unset.
+		 */
+		__u64 seq;
+
+		/*
+		 * Encapsulated signals handle id
+		 * Valid for two flows:
+		 * 1. CS with encapsulated signals:
+		 *    when HL_CS_FLAGS_STAGED_SUBMISSION and
+		 *    HL_CS_FLAGS_STAGED_SUBMISSION_FIRST
+		 *    and HL_CS_FLAGS_ENCAP_SIGNALS are set.
+		 * 2. unreserve signals:
+		 *    valid when HL_CS_FLAGS_UNRESERVE_SIGNALS_ONLY is set.
+		 */
+		__u32 encaps_sig_handle_id;
+
+		/* Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */
+		struct {
+			/* Encapsulated signals number */
+			__u32 encaps_signals_count;
+
+			/* Encapsulated signals queue index (stream) */
+			__u32 encaps_signals_q_idx;
+		};
+	};
+
+	/* Number of chunks in restore phase array. Maximum number is
+	 * HL_MAX_JOBS_PER_CS
+	 */
+	__u32 num_chunks_restore;
+
+	/* Number of chunks in execution array. Maximum number is
+	 * HL_MAX_JOBS_PER_CS
+	 */
+	__u32 num_chunks_execute;
+
+	/* timeout in seconds - valid only if HL_CS_FLAGS_CUSTOM_TIMEOUT
+	 * is set
+	 */
+	__u32 timeout;
+
+	/* HL_CS_FLAGS_* */
+	__u32 cs_flags;
+
+	/* Context ID - Currently not in use */
+	__u32 ctx_id;
+	__u8 pad[4];
+};
+
+struct hl_cs_out {
+	union {
+		/*
+		 * seq holds the sequence number of the CS to pass to wait
+		 * ioctl. All values are valid except for 0 and ULLONG_MAX
+		 */
+		__u64 seq;
+
+		/* Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY is set */
+		struct {
+			/* This is the reserved signal handle id */
+			__u32 handle_id;
+
+			/* This is the signals count */
+			__u32 count;
+		};
+	};
+
+	/* HL_CS_STATUS */
+	__u32 status;
+
+	/*
+	 * SOB base address offset
+	 * Valid only when HL_CS_FLAGS_RESERVE_SIGNALS_ONLY or HL_CS_FLAGS_SIGNAL is set
+	 */
+	__u32 sob_base_addr_offset;
+
+	/*
+	 * Count of completed signals in SOB before current signal submission.
+	 * Valid only when (HL_CS_FLAGS_ENCAP_SIGNALS & HL_CS_FLAGS_STAGED_SUBMISSION)
+	 * or HL_CS_FLAGS_SIGNAL is set
+	 */
+	__u16 sob_count_before_submission;
+	__u16 pad[3];
+};
+
+union hl_cs_args {
+	struct hl_cs_in in;
+	struct hl_cs_out out;
+};
+
+#define HL_WAIT_CS_FLAGS_INTERRUPT		0x2
+#define HL_WAIT_CS_FLAGS_INTERRUPT_MASK		0xFFF00000
+#define HL_WAIT_CS_FLAGS_ANY_CQ_INTERRUPT	0xFFF00000
+#define HL_WAIT_CS_FLAGS_ANY_DEC_INTERRUPT	0xFFE00000
+#define HL_WAIT_CS_FLAGS_MULTI_CS		0x4
+#define HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ	0x10
+#define HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT	0x20
+
+#define HL_WAIT_MULTI_CS_LIST_MAX_LEN	32
+
+struct hl_wait_cs_in {
+	union {
+		struct {
+			/*
+			 * In case of wait_cs holds the CS sequence number.
+			 * In case of wait for multi CS hold a user pointer to
+			 * an array of CS sequence numbers
+			 */
+			__u64 seq;
+			/* Absolute timeout to wait for command submission
+			 * in microseconds
+			 */
+			__u64 timeout_us;
+		};
+
+		struct {
+			union {
+				/* User address for completion comparison.
+				 * upon interrupt, driver will compare the value pointed
+				 * by this address with the supplied target value.
+				 * in order not to perform any comparison, set address
+				 * to all 1s.
+				 * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set
+				 */
+				__u64 addr;
+
+				/* cq_counters_handle to a kernel mapped cb which contains
+				 * cq counters.
+				 * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ is set
+				 */
+				__u64 cq_counters_handle;
+			};
+
+			/* Target value for completion comparison */
+			__u64 target;
+		};
+	};
+
+	/* Context ID - Currently not in use */
+	__u32 ctx_id;
+
+	/* HL_WAIT_CS_FLAGS_*
+	 * If HL_WAIT_CS_FLAGS_INTERRUPT is set, this field should include
+	 * interrupt id according to HL_WAIT_CS_FLAGS_INTERRUPT_MASK
+	 *
+	 * in order to wait for any CQ interrupt, set interrupt value to
+	 * HL_WAIT_CS_FLAGS_ANY_CQ_INTERRUPT.
+	 *
+	 * in order to wait for any decoder interrupt, set interrupt value to
+	 * HL_WAIT_CS_FLAGS_ANY_DEC_INTERRUPT.
+	 */
+	__u32 flags;
+
+	union {
+		struct {
+			/* Multi CS API info- valid entries in multi-CS array */
+			__u8 seq_arr_len;
+			__u8 pad[7];
+		};
+
+		/* Absolute timeout to wait for an interrupt in microseconds.
+		 * Relevant only when HL_WAIT_CS_FLAGS_INTERRUPT is set
+		 */
+		__u64 interrupt_timeout_us;
+	};
+
+	/*
+	 * cq counter offset inside the counters cb pointed by cq_counters_handle above.
+	 * upon interrupt, driver will compare the value pointed
+	 * by this address (cq_counters_handle + cq_counters_offset)
+	 * with the supplied target value.
+	 * relevant only when HL_WAIT_CS_FLAGS_INTERRUPT_KERNEL_CQ is set
+	 */
+	__u64 cq_counters_offset;
+
+	/*
+	 * Timestamp_handle timestamps buffer handle.
+	 * relevant only when HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT is set
+	 */
+	__u64 timestamp_handle;
+
+	/*
+	 * Timestamp_offset is offset inside the timestamp buffer pointed by timestamp_handle above.
+	 * upon interrupt, if the cq reached the target value then driver will write
+	 * timestamp to this offset.
+	 * relevant only when HL_WAIT_CS_FLAGS_REGISTER_INTERRUPT is set
+	 */
+	__u64 timestamp_offset;
+};
+
+#define HL_WAIT_CS_STATUS_COMPLETED	0
+#define HL_WAIT_CS_STATUS_BUSY		1
+#define HL_WAIT_CS_STATUS_TIMEDOUT	2
+#define HL_WAIT_CS_STATUS_ABORTED	3
+
+#define HL_WAIT_CS_STATUS_FLAG_GONE		0x1
+#define HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD	0x2
+
+struct hl_wait_cs_out {
+	/* HL_WAIT_CS_STATUS_* */
+	__u32 status;
+	/* HL_WAIT_CS_STATUS_FLAG* */
+	__u32 flags;
+	/*
+	 * valid only if HL_WAIT_CS_STATUS_FLAG_TIMESTAMP_VLD is set
+	 * for wait_cs: timestamp of CS completion
+	 * for wait_multi_cs: timestamp of FIRST CS completion
+	 */
+	__s64 timestamp_nsec;
+	/* multi CS completion bitmap */
+	__u32 cs_completion_map;
+	__u32 pad;
+};
+
+union hl_wait_cs_args {
+	struct hl_wait_cs_in in;
+	struct hl_wait_cs_out out;
+};
+
+/* Opcode to allocate device memory */
+#define HL_MEM_OP_ALLOC			0
+
+/* Opcode to free previously allocated device memory */
+#define HL_MEM_OP_FREE			1
+
+/* Opcode to map host and device memory */
+#define HL_MEM_OP_MAP			2
+
+/* Opcode to unmap previously mapped host and device memory */
+#define HL_MEM_OP_UNMAP			3
+
+/* Opcode to map a hw block */
+#define HL_MEM_OP_MAP_BLOCK		4
+
+/* Opcode to create DMA-BUF object for an existing device memory allocation
+ * and to export an FD of that DMA-BUF back to the caller
+ */
+#define HL_MEM_OP_EXPORT_DMABUF_FD	5
+
+/* Opcode to create timestamps pool for user interrupts registration support
+ * The memory will be allocated by the kernel driver, A timestamp buffer which the user
+ * will get handle to it for mmap, and another internal buffer used by the
+ * driver for registration management
+ * The memory will be freed when the user closes the file descriptor(ctx close)
+ */
+#define HL_MEM_OP_TS_ALLOC		6
+
+/* Memory flags */
+#define HL_MEM_CONTIGUOUS	0x1
+#define HL_MEM_SHARED		0x2
+#define HL_MEM_USERPTR		0x4
+#define HL_MEM_FORCE_HINT	0x8
+#define HL_MEM_PREFETCH		0x40
+
+/**
+ * structure hl_mem_in - structure that handle input args for memory IOCTL
+ * @union arg: union of structures to be used based on the input operation
+ * @op: specify the requested memory operation (one of the HL_MEM_OP_* definitions).
+ * @flags: flags for the memory operation (one of the HL_MEM_* definitions).
+ *         For the HL_MEM_OP_EXPORT_DMABUF_FD opcode, this field holds the DMA-BUF file/FD flags.
+ * @ctx_id: context ID - currently not in use.
+ * @num_of_elements: number of timestamp elements used only with HL_MEM_OP_TS_ALLOC opcode.
+ */
+struct hl_mem_in {
+	union {
+		/**
+		 * structure for device memory allocation (used with the HL_MEM_OP_ALLOC op)
+		 * @mem_size: memory size to allocate
+		 * @page_size: page size to use on allocation. when the value is 0 the default page
+		 *             size will be taken.
+		 */
+		struct {
+			__u64 mem_size;
+			__u64 page_size;
+		} alloc;
+
+		/**
+		 * structure for free-ing device memory (used with the HL_MEM_OP_FREE op)
+		 * @handle: handle returned from HL_MEM_OP_ALLOC
+		 */
+		struct {
+			__u64 handle;
+		} free;
+
+		/**
+		 * structure for mapping device memory (used with the HL_MEM_OP_MAP op)
+		 * @hint_addr: requested virtual address of mapped memory.
+		 *             the driver will try to map the requested region to this hint
+		 *             address, as long as the address is valid and not already mapped.
+		 *             the user should check the returned address of the IOCTL to make
+		 *             sure he got the hint address.
+		 *             passing 0 here means that the driver will choose the address itself.
+		 * @handle: handle returned from HL_MEM_OP_ALLOC.
+		 */
+		struct {
+			__u64 hint_addr;
+			__u64 handle;
+		} map_device;
+
+		/**
+		 * structure for mapping host memory (used with the HL_MEM_OP_MAP op)
+		 * @host_virt_addr: address of allocated host memory.
+		 * @hint_addr: requested virtual address of mapped memory.
+		 *             the driver will try to map the requested region to this hint
+		 *             address, as long as the address is valid and not already mapped.
+		 *             the user should check the returned address of the IOCTL to make
+		 *             sure he got the hint address.
+		 *             passing 0 here means that the driver will choose the address itself.
+		 * @size: size of allocated host memory.
+		 */
+		struct {
+			__u64 host_virt_addr;
+			__u64 hint_addr;
+			__u64 mem_size;
+		} map_host;
+
+		/**
+		 * structure for mapping hw block (used with the HL_MEM_OP_MAP_BLOCK op)
+		 * @block_addr:HW block address to map, a handle and size will be returned
+		 *             to the user and will be used to mmap the relevant block.
+		 *             only addresses from configuration space are allowed.
+		 */
+		struct {
+			__u64 block_addr;
+		} map_block;
+
+		/**
+		 * structure for unmapping host memory (used with the HL_MEM_OP_UNMAP op)
+		 * @device_virt_addr: virtual address returned from HL_MEM_OP_MAP
+		 */
+		struct {
+			__u64 device_virt_addr;
+		} unmap;
+
+		/**
+		 * structure for exporting DMABUF object (used with
+		 * the HL_MEM_OP_EXPORT_DMABUF_FD op)
+		 * @addr: for Gaudi1, the driver expects a physical address
+		 *        inside the device's DRAM. this is because in Gaudi1
+		 *        we don't have MMU that covers the device's DRAM.
+		 *        for all other ASICs, the driver expects a device
+		 *        virtual address that represents the start address of
+		 *        a mapped DRAM memory area inside the device.
+		 *        the address must be the same as was received from the
+		 *        driver during a previous HL_MEM_OP_MAP operation.
+		 * @mem_size: size of memory to export.
+		 * @offset: for Gaudi1, this value must be 0. For all other ASICs,
+		 *          the driver expects an offset inside of the memory area
+		 *          describe by addr. the offset represents the start
+		 *          address of that the exported dma-buf object describes.
+		 */
+		struct {
+			__u64 addr;
+			__u64 mem_size;
+			__u64 offset;
+		} export_dmabuf_fd;
+	};
+
+	__u32 op;
+	__u32 flags;
+	__u32 ctx_id;
+	__u32 num_of_elements;
+};
+
+struct hl_mem_out {
+	union {
+		/*
+		 * Used for HL_MEM_OP_MAP as the virtual address that was
+		 * assigned in the device VA space.
+		 * A value of 0 means the requested operation failed.
+		 */
+		__u64 device_virt_addr;
+
+		/*
+		 * Used in HL_MEM_OP_ALLOC
+		 * This is the assigned handle for the allocated memory
+		 */
+		__u64 handle;
+
+		struct {
+			/*
+			 * Used in HL_MEM_OP_MAP_BLOCK.
+			 * This is the assigned handle for the mapped block
+			 */
+			__u64 block_handle;
+
+			/*
+			 * Used in HL_MEM_OP_MAP_BLOCK
+			 * This is the size of the mapped block
+			 */
+			__u32 block_size;
+
+			__u32 pad;
+		};
+
+		/* Returned in HL_MEM_OP_EXPORT_DMABUF_FD. Represents the
+		 * DMA-BUF object that was created to describe a memory
+		 * allocation on the device's memory space. The FD should be
+		 * passed to the importer driver
+		 */
+		__s32 fd;
+	};
+};
+
+union hl_mem_args {
+	struct hl_mem_in in;
+	struct hl_mem_out out;
+};
+
+#define HL_DEBUG_MAX_AUX_VALUES		10
+
+struct hl_debug_params_etr {
+	/* Address in memory to allocate buffer */
+	__u64 buffer_address;
+
+	/* Size of buffer to allocate */
+	__u64 buffer_size;
+
+	/* Sink operation mode: SW fifo, HW fifo, Circular buffer */
+	__u32 sink_mode;
+	__u32 pad;
+};
+
+struct hl_debug_params_etf {
+	/* Address in memory to allocate buffer */
+	__u64 buffer_address;
+
+	/* Size of buffer to allocate */
+	__u64 buffer_size;
+
+	/* Sink operation mode: SW fifo, HW fifo, Circular buffer */
+	__u32 sink_mode;
+	__u32 pad;
+};
+
+struct hl_debug_params_stm {
+	/* Two bit masks for HW event and Stimulus Port */
+	__u64 he_mask;
+	__u64 sp_mask;
+
+	/* Trace source ID */
+	__u32 id;
+
+	/* Frequency for the timestamp register */
+	__u32 frequency;
+};
+
+struct hl_debug_params_bmon {
+	/* Two address ranges that the user can request to filter */
+	__u64 start_addr0;
+	__u64 addr_mask0;
+
+	__u64 start_addr1;
+	__u64 addr_mask1;
+
+	/* Capture window configuration */
+	__u32 bw_win;
+	__u32 win_capture;
+
+	/* Trace source ID */
+	__u32 id;
+
+	/* Control register */
+	__u32 control;
+
+	/* Two more address ranges that the user can request to filter */
+	__u64 start_addr2;
+	__u64 end_addr2;
+
+	__u64 start_addr3;
+	__u64 end_addr3;
+};
+
+struct hl_debug_params_spmu {
+	/* Event types selection */
+	__u64 event_types[HL_DEBUG_MAX_AUX_VALUES];
+
+	/* Number of event types selection */
+	__u32 event_types_num;
+
+	/* TRC configuration register values */
+	__u32 pmtrc_val;
+	__u32 trc_ctrl_host_val;
+	__u32 trc_en_host_val;
+};
+
+/* Opcode for ETR component */
+#define HL_DEBUG_OP_ETR		0
+/* Opcode for ETF component */
+#define HL_DEBUG_OP_ETF		1
+/* Opcode for STM component */
+#define HL_DEBUG_OP_STM		2
+/* Opcode for FUNNEL component */
+#define HL_DEBUG_OP_FUNNEL	3
+/* Opcode for BMON component */
+#define HL_DEBUG_OP_BMON	4
+/* Opcode for SPMU component */
+#define HL_DEBUG_OP_SPMU	5
+/* Opcode for timestamp (deprecated) */
+#define HL_DEBUG_OP_TIMESTAMP	6
+/* Opcode for setting the device into or out of debug mode. The enable
+ * variable should be 1 for enabling debug mode and 0 for disabling it
+ */
+#define HL_DEBUG_OP_SET_MODE	7
+
+struct hl_debug_args {
+	/*
+	 * Pointer to user input structure.
+	 * This field is relevant to specific opcodes.
+	 */
+	__u64 input_ptr;
+	/* Pointer to user output structure */
+	__u64 output_ptr;
+	/* Size of user input structure */
+	__u32 input_size;
+	/* Size of user output structure */
+	__u32 output_size;
+	/* HL_DEBUG_OP_* */
+	__u32 op;
+	/*
+	 * Register index in the component, taken from the debug_regs_index enum
+	 * in the various ASIC header files
+	 */
+	__u32 reg_idx;
+	/* Enable/disable */
+	__u32 enable;
+	/* Context ID - Currently not in use */
+	__u32 ctx_id;
+};
+
+#define HL_IOCTL_INFO		0x00
+#define HL_IOCTL_CB		0x01
+#define HL_IOCTL_CS		0x02
+#define HL_IOCTL_WAIT_CS	0x03
+#define HL_IOCTL_MEMORY		0x04
+#define HL_IOCTL_DEBUG		0x05
+
+/*
+ * Various information operations such as:
+ * - H/W IP information
+ * - Current dram usage
+ *
+ * The user calls this IOCTL with an opcode that describes the required
+ * information. The user should supply a pointer to a user-allocated memory
+ * chunk, which will be filled by the driver with the requested information.
+ *
+ * The user supplies the maximum amount of size to copy into the user's memory,
+ * in order to prevent data corruption in case of differences between the
+ * definitions of structures in kernel and userspace, e.g. in case of old
+ * userspace and new kernel driver
+ */
+#define DRM_IOCTL_HL_INFO	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_INFO, struct hl_info_args)
+
+/*
+ * Command Buffer
+ * - Request a Command Buffer
+ * - Destroy a Command Buffer
+ *
+ * The command buffers are memory blocks that reside in DMA-able address
+ * space and are physically contiguous so they can be accessed by the device
+ * directly. They are allocated using the coherent DMA API.
+ *
+ * When creating a new CB, the IOCTL returns a handle of it, and the user-space
+ * process needs to use that handle to mmap the buffer so it can access them.
+ *
+ * In some instances, the device must access the command buffer through the
+ * device's MMU, and thus its memory should be mapped. In these cases, user can
+ * indicate the driver that such a mapping is required.
+ * The resulting device virtual address will be used internally by the driver,
+ * and won't be returned to user.
+ *
+ */
+#define DRM_IOCTL_HL_CB		DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_CB, union hl_cb_args)
+
+/*
+ * Command Submission
+ *
+ * To submit work to the device, the user need to call this IOCTL with a set
+ * of JOBS. That set of JOBS constitutes a CS object.
+ * Each JOB will be enqueued on a specific queue, according to the user's input.
+ * There can be more then one JOB per queue.
+ *
+ * The CS IOCTL will receive two sets of JOBS. One set is for "restore" phase
+ * and a second set is for "execution" phase.
+ * The JOBS on the "restore" phase are enqueued only after context-switch
+ * (or if its the first CS for this context). The user can also order the
+ * driver to run the "restore" phase explicitly
+ *
+ * Goya/Gaudi:
+ * There are two types of queues - external and internal. External queues
+ * are DMA queues which transfer data from/to the Host. All other queues are
+ * internal. The driver will get completion notifications from the device only
+ * on JOBS which are enqueued in the external queues.
+ *
+ * Gaudi2 onwards:
+ * There is a single type of queue for all types of engines, either DMA engines
+ * for transfers from/to the host or inside the device, or compute engines.
+ * The driver will get completion notifications from the device for all queues.
+ *
+ * For jobs on external queues, the user needs to create command buffers
+ * through the CB ioctl and give the CB's handle to the CS ioctl. For jobs on
+ * internal queues, the user needs to prepare a "command buffer" with packets
+ * on either the device SRAM/DRAM or the host, and give the device address of
+ * that buffer to the CS ioctl.
+ * For jobs on H/W queues both options of command buffers are valid.
+ *
+ * This IOCTL is asynchronous in regard to the actual execution of the CS. This
+ * means it returns immediately after ALL the JOBS were enqueued on their
+ * relevant queues. Therefore, the user mustn't assume the CS has been completed
+ * or has even started to execute.
+ *
+ * Upon successful enqueue, the IOCTL returns a sequence number which the user
+ * can use with the "Wait for CS" IOCTL to check whether the handle's CS
+ * non-internal JOBS have been completed. Note that if the CS has internal JOBS
+ * which can execute AFTER the external JOBS have finished, the driver might
+ * report that the CS has finished executing BEFORE the internal JOBS have
+ * actually finished executing.
+ *
+ * Even though the sequence number increments per CS, the user can NOT
+ * automatically assume that if CS with sequence number N finished, then CS
+ * with sequence number N-1 also finished. The user can make this assumption if
+ * and only if CS N and CS N-1 are exactly the same (same CBs for the same
+ * queues).
+ */
+#define DRM_IOCTL_HL_CS		DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_CS, union hl_cs_args)
+
+/*
+ * Wait for Command Submission
+ *
+ * The user can call this IOCTL with a handle it received from the CS IOCTL
+ * to wait until the handle's CS has finished executing. The user will wait
+ * inside the kernel until the CS has finished or until the user-requested
+ * timeout has expired.
+ *
+ * If the timeout value is 0, the driver won't sleep at all. It will check
+ * the status of the CS and return immediately
+ *
+ * The return value of the IOCTL is a standard Linux error code. The possible
+ * values are:
+ *
+ * EINTR     - Kernel waiting has been interrupted, e.g. due to OS signal
+ *             that the user process received
+ * ETIMEDOUT - The CS has caused a timeout on the device
+ * EIO       - The CS was aborted (usually because the device was reset)
+ * ENODEV    - The device wants to do hard-reset (so user need to close FD)
+ *
+ * The driver also returns a custom define in case the IOCTL call returned 0.
+ * The define can be one of the following:
+ *
+ * HL_WAIT_CS_STATUS_COMPLETED   - The CS has been completed successfully (0)
+ * HL_WAIT_CS_STATUS_BUSY        - The CS is still executing (0)
+ * HL_WAIT_CS_STATUS_TIMEDOUT    - The CS has caused a timeout on the device
+ *                                 (ETIMEDOUT)
+ * HL_WAIT_CS_STATUS_ABORTED     - The CS was aborted, usually because the
+ *                                 device was reset (EIO)
+ */
+#define DRM_IOCTL_HL_WAIT_CS	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_WAIT_CS, union hl_wait_cs_args)
+
+/*
+ * Memory
+ * - Map host memory to device MMU
+ * - Unmap host memory from device MMU
+ *
+ * This IOCTL allows the user to map host memory to the device MMU
+ *
+ * For host memory, the IOCTL doesn't allocate memory. The user is supposed
+ * to allocate the memory in user-space (malloc/new). The driver pins the
+ * physical pages (up to the allowed limit by the OS), assigns a virtual
+ * address in the device VA space and initializes the device MMU.
+ *
+ * There is an option for the user to specify the requested virtual address.
+ *
+ */
+#define DRM_IOCTL_HL_MEMORY	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_MEMORY, union hl_mem_args)
+
+/*
+ * Debug
+ * - Enable/disable the ETR/ETF/FUNNEL/STM/BMON/SPMU debug traces
+ *
+ * This IOCTL allows the user to get debug traces from the chip.
+ *
+ * Before the user can send configuration requests of the various
+ * debug/profile engines, it needs to set the device into debug mode.
+ * This is because the debug/profile infrastructure is shared component in the
+ * device and we can't allow multiple users to access it at the same time.
+ *
+ * Once a user set the device into debug mode, the driver won't allow other
+ * users to "work" with the device, i.e. open a FD. If there are multiple users
+ * opened on the device, the driver won't allow any user to debug the device.
+ *
+ * For each configuration request, the user needs to provide the register index
+ * and essential data such as buffer address and size.
+ *
+ * Once the user has finished using the debug/profile engines, he should
+ * set the device into non-debug mode, i.e. disable debug mode.
+ *
+ * The driver can decide to "kick out" the user if he abuses this interface.
+ *
+ */
+#define DRM_IOCTL_HL_DEBUG	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_DEBUG, struct hl_debug_args)
+
+#define HL_COMMAND_START	(DRM_COMMAND_BASE + HL_IOCTL_INFO)
+#define HL_COMMAND_END		(DRM_COMMAND_BASE + HL_IOCTL_DEBUG + 1)
+
+#endif /* HABANALABS_H_ */
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
new file mode 100644
index 000000000..535cb68fd
--- /dev/null
+++ b/include/uapi/drm/i915_drm.h
@@ -0,0 +1,3916 @@
+/*
+ * Copyright 2003 Tungsten Graphics, Inc., Cedar Park, Texas.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
+ * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
+ * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _UAPI_I915_DRM_H_
+#define _UAPI_I915_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.
+ */
+
+/**
+ * DOC: uevents generated by i915 on its device node
+ *
+ * I915_L3_PARITY_UEVENT - Generated when the driver receives a parity mismatch
+ *	event from the GPU L3 cache. Additional information supplied is ROW,
+ *	BANK, SUBBANK, SLICE of the affected cacheline. Userspace should keep
+ *	track of these events, and if a specific cache-line seems to have a
+ *	persistent error, remap it with the L3 remapping tool supplied in
+ *	intel-gpu-tools.  The value supplied with the event is always 1.
+ *
+ * I915_ERROR_UEVENT - Generated upon error detection, currently only via
+ *	hangcheck. The error detection event is a good indicator of when things
+ *	began to go badly. The value supplied with the event is a 1 upon error
+ *	detection, and a 0 upon reset completion, signifying no more error
+ *	exists. NOTE: Disabling hangcheck or reset via module parameter will
+ *	cause the related events to not be seen.
+ *
+ * I915_RESET_UEVENT - Event is generated just before an attempt to reset the
+ *	GPU. The value supplied with the event is always 1. NOTE: Disable
+ *	reset via module parameter will cause this event to not be seen.
+ */
+#define I915_L3_PARITY_UEVENT		"L3_PARITY_ERROR"
+#define I915_ERROR_UEVENT		"ERROR"
+#define I915_RESET_UEVENT		"RESET"
+
+/**
+ * struct i915_user_extension - Base class for defining a chain of extensions
+ *
+ * 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 i915_user_extension ext3 {
+ *		.next_extension = 0, // end
+ *		.name = ...,
+ *	};
+ *	struct i915_user_extension ext2 {
+ *		.next_extension = (uintptr_t)&ext3,
+ *		.name = ...,
+ *	};
+ *	struct i915_user_extension ext1 {
+ *		.next_extension = (uintptr_t)&ext2,
+ *		.name = ...,
+ *	};
+ *
+ * Typically the struct i915_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 i915_user_extension {
+	/**
+	 * @next_extension:
+	 *
+	 * Pointer to the next struct i915_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 i915_user_extension.
+	 */
+	__u32 name;
+	/**
+	 * @flags: MBZ
+	 *
+	 * All undefined bits must be zero.
+	 */
+	__u32 flags;
+	/**
+	 * @rsvd: MBZ
+	 *
+	 * Reserved for future use; must be zero.
+	 */
+	__u32 rsvd[4];
+};
+
+/*
+ * MOCS indexes used for GPU surfaces, defining the cacheability of the
+ * surface data and the coherency for this data wrt. CPU vs. GPU accesses.
+ */
+enum i915_mocs_table_index {
+	/*
+	 * Not cached anywhere, coherency between CPU and GPU accesses is
+	 * guaranteed.
+	 */
+	I915_MOCS_UNCACHED,
+	/*
+	 * Cacheability and coherency controlled by the kernel automatically
+	 * based on the DRM_I915_GEM_SET_CACHING IOCTL setting and the current
+	 * usage of the surface (used for display scanout or not).
+	 */
+	I915_MOCS_PTE,
+	/*
+	 * Cached in all GPU caches available on the platform.
+	 * Coherency between CPU and GPU accesses to the surface is not
+	 * guaranteed without extra synchronization.
+	 */
+	I915_MOCS_CACHED,
+};
+
+/**
+ * enum drm_i915_gem_engine_class - uapi engine type enumeration
+ *
+ * Different engines serve different roles, and there may be more than one
+ * engine serving each role.  This enum provides a classification of the role
+ * of the engine, which may be used when requesting operations to be performed
+ * on a certain subset of engines, or for providing information about that
+ * group.
+ */
+enum drm_i915_gem_engine_class {
+	/**
+	 * @I915_ENGINE_CLASS_RENDER:
+	 *
+	 * Render engines support instructions used for 3D, Compute (GPGPU),
+	 * and programmable media workloads.  These instructions fetch data and
+	 * dispatch individual work items to threads that operate in parallel.
+	 * The threads run small programs (called "kernels" or "shaders") on
+	 * the GPU's execution units (EUs).
+	 */
+	I915_ENGINE_CLASS_RENDER	= 0,
+
+	/**
+	 * @I915_ENGINE_CLASS_COPY:
+	 *
+	 * Copy engines (also referred to as "blitters") support instructions
+	 * that move blocks of data from one location in memory to another,
+	 * or that fill a specified location of memory with fixed data.
+	 * Copy engines can perform pre-defined logical or bitwise operations
+	 * on the source, destination, or pattern data.
+	 */
+	I915_ENGINE_CLASS_COPY		= 1,
+
+	/**
+	 * @I915_ENGINE_CLASS_VIDEO:
+	 *
+	 * Video engines (also referred to as "bit stream decode" (BSD) or
+	 * "vdbox") support instructions that perform fixed-function media
+	 * decode and encode.
+	 */
+	I915_ENGINE_CLASS_VIDEO		= 2,
+
+	/**
+	 * @I915_ENGINE_CLASS_VIDEO_ENHANCE:
+	 *
+	 * Video enhancement engines (also referred to as "vebox") support
+	 * instructions related to image enhancement.
+	 */
+	I915_ENGINE_CLASS_VIDEO_ENHANCE	= 3,
+
+	/**
+	 * @I915_ENGINE_CLASS_COMPUTE:
+	 *
+	 * Compute engines support a subset of the instructions available
+	 * on render engines:  compute engines support Compute (GPGPU) and
+	 * programmable media workloads, but do not support the 3D pipeline.
+	 */
+	I915_ENGINE_CLASS_COMPUTE	= 4,
+
+	/* Values in this enum should be kept compact. */
+
+	/**
+	 * @I915_ENGINE_CLASS_INVALID:
+	 *
+	 * Placeholder value to represent an invalid engine class assignment.
+	 */
+	I915_ENGINE_CLASS_INVALID	= -1
+};
+
+/**
+ * struct i915_engine_class_instance - Engine class/instance identifier
+ *
+ * There may be more than one engine fulfilling any role within the system.
+ * Each engine of a class is given a unique instance number and therefore
+ * any engine can be specified by its class:instance tuplet. APIs that allow
+ * access to any engine in the system will use struct i915_engine_class_instance
+ * for this identification.
+ */
+struct i915_engine_class_instance {
+	/**
+	 * @engine_class:
+	 *
+	 * Engine class from enum drm_i915_gem_engine_class
+	 */
+	__u16 engine_class;
+#define I915_ENGINE_CLASS_INVALID_NONE -1
+#define I915_ENGINE_CLASS_INVALID_VIRTUAL -2
+
+	/**
+	 * @engine_instance:
+	 *
+	 * Engine instance.
+	 */
+	__u16 engine_instance;
+};
+
+/**
+ * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
+ *
+ */
+
+enum drm_i915_pmu_engine_sample {
+	I915_SAMPLE_BUSY = 0,
+	I915_SAMPLE_WAIT = 1,
+	I915_SAMPLE_SEMA = 2
+};
+
+#define I915_PMU_SAMPLE_BITS (4)
+#define I915_PMU_SAMPLE_MASK (0xf)
+#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
+#define I915_PMU_CLASS_SHIFT \
+	(I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
+
+#define __I915_PMU_ENGINE(class, instance, sample) \
+	((class) << I915_PMU_CLASS_SHIFT | \
+	(instance) << I915_PMU_SAMPLE_BITS | \
+	(sample))
+
+#define I915_PMU_ENGINE_BUSY(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
+
+#define I915_PMU_ENGINE_WAIT(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
+
+#define I915_PMU_ENGINE_SEMA(class, instance) \
+	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
+
+/*
+ * Top 4 bits of every non-engine counter are GT id.
+ */
+#define __I915_PMU_GT_SHIFT (60)
+
+#define ___I915_PMU_OTHER(gt, x) \
+	(((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \
+	((__u64)(gt) << __I915_PMU_GT_SHIFT))
+
+#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x)
+
+#define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
+#define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
+#define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
+#define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
+#define I915_PMU_SOFTWARE_GT_AWAKE_TIME	__I915_PMU_OTHER(4)
+
+#define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY
+
+#define __I915_PMU_ACTUAL_FREQUENCY(gt)		___I915_PMU_OTHER(gt, 0)
+#define __I915_PMU_REQUESTED_FREQUENCY(gt)	___I915_PMU_OTHER(gt, 1)
+#define __I915_PMU_INTERRUPTS(gt)		___I915_PMU_OTHER(gt, 2)
+#define __I915_PMU_RC6_RESIDENCY(gt)		___I915_PMU_OTHER(gt, 3)
+#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt)	___I915_PMU_OTHER(gt, 4)
+
+/* Each region is a minimum of 16k, and there are at most 255 of them.
+ */
+#define I915_NR_TEX_REGIONS 255	/* table size 2k - maximum due to use
+				 * of chars for next/prev indices */
+#define I915_LOG_MIN_TEX_REGION_SIZE 14
+
+typedef struct _drm_i915_init {
+	enum {
+		I915_INIT_DMA = 0x01,
+		I915_CLEANUP_DMA = 0x02,
+		I915_RESUME_DMA = 0x03
+	} func;
+	unsigned int mmio_offset;
+	int sarea_priv_offset;
+	unsigned int ring_start;
+	unsigned int ring_end;
+	unsigned int ring_size;
+	unsigned int front_offset;
+	unsigned int back_offset;
+	unsigned int depth_offset;
+	unsigned int w;
+	unsigned int h;
+	unsigned int pitch;
+	unsigned int pitch_bits;
+	unsigned int back_pitch;
+	unsigned int depth_pitch;
+	unsigned int cpp;
+	unsigned int chipset;
+} drm_i915_init_t;
+
+typedef struct _drm_i915_sarea {
+	struct drm_tex_region texList[I915_NR_TEX_REGIONS + 1];
+	int last_upload;	/* last time texture was uploaded */
+	int last_enqueue;	/* last time a buffer was enqueued */
+	int last_dispatch;	/* age of the most recently dispatched buffer */
+	int ctxOwner;		/* last context to upload state */
+	int texAge;
+	int pf_enabled;		/* is pageflipping allowed? */
+	int pf_active;
+	int pf_current_page;	/* which buffer is being displayed? */
+	int perf_boxes;		/* performance boxes to be displayed */
+	int width, height;      /* screen size in pixels */
+
+	drm_handle_t front_handle;
+	int front_offset;
+	int front_size;
+
+	drm_handle_t back_handle;
+	int back_offset;
+	int back_size;
+
+	drm_handle_t depth_handle;
+	int depth_offset;
+	int depth_size;
+
+	drm_handle_t tex_handle;
+	int tex_offset;
+	int tex_size;
+	int log_tex_granularity;
+	int pitch;
+	int rotation;           /* 0, 90, 180 or 270 */
+	int rotated_offset;
+	int rotated_size;
+	int rotated_pitch;
+	int virtualX, virtualY;
+
+	unsigned int front_tiled;
+	unsigned int back_tiled;
+	unsigned int depth_tiled;
+	unsigned int rotated_tiled;
+	unsigned int rotated2_tiled;
+
+	int pipeA_x;
+	int pipeA_y;
+	int pipeA_w;
+	int pipeA_h;
+	int pipeB_x;
+	int pipeB_y;
+	int pipeB_w;
+	int pipeB_h;
+
+	/* fill out some space for old userspace triple buffer */
+	drm_handle_t unused_handle;
+	__u32 unused1, unused2, unused3;
+
+	/* buffer object handles for static buffers. May change
+	 * over the lifetime of the client.
+	 */
+	__u32 front_bo_handle;
+	__u32 back_bo_handle;
+	__u32 unused_bo_handle;
+	__u32 depth_bo_handle;
+
+} drm_i915_sarea_t;
+
+/* due to userspace building against these headers we need some compat here */
+#define planeA_x pipeA_x
+#define planeA_y pipeA_y
+#define planeA_w pipeA_w
+#define planeA_h pipeA_h
+#define planeB_x pipeB_x
+#define planeB_y pipeB_y
+#define planeB_w pipeB_w
+#define planeB_h pipeB_h
+
+/* Flags for perf_boxes
+ */
+#define I915_BOX_RING_EMPTY    0x1
+#define I915_BOX_FLIP          0x2
+#define I915_BOX_WAIT          0x4
+#define I915_BOX_TEXTURE_LOAD  0x8
+#define I915_BOX_LOST_CONTEXT  0x10
+
+/*
+ * i915 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_I915_INIT		0x00
+#define DRM_I915_FLUSH		0x01
+#define DRM_I915_FLIP		0x02
+#define DRM_I915_BATCHBUFFER	0x03
+#define DRM_I915_IRQ_EMIT	0x04
+#define DRM_I915_IRQ_WAIT	0x05
+#define DRM_I915_GETPARAM	0x06
+#define DRM_I915_SETPARAM	0x07
+#define DRM_I915_ALLOC		0x08
+#define DRM_I915_FREE		0x09
+#define DRM_I915_INIT_HEAP	0x0a
+#define DRM_I915_CMDBUFFER	0x0b
+#define DRM_I915_DESTROY_HEAP	0x0c
+#define DRM_I915_SET_VBLANK_PIPE	0x0d
+#define DRM_I915_GET_VBLANK_PIPE	0x0e
+#define DRM_I915_VBLANK_SWAP	0x0f
+#define DRM_I915_HWS_ADDR	0x11
+#define DRM_I915_GEM_INIT	0x13
+#define DRM_I915_GEM_EXECBUFFER	0x14
+#define DRM_I915_GEM_PIN	0x15
+#define DRM_I915_GEM_UNPIN	0x16
+#define DRM_I915_GEM_BUSY	0x17
+#define DRM_I915_GEM_THROTTLE	0x18
+#define DRM_I915_GEM_ENTERVT	0x19
+#define DRM_I915_GEM_LEAVEVT	0x1a
+#define DRM_I915_GEM_CREATE	0x1b
+#define DRM_I915_GEM_PREAD	0x1c
+#define DRM_I915_GEM_PWRITE	0x1d
+#define DRM_I915_GEM_MMAP	0x1e
+#define DRM_I915_GEM_SET_DOMAIN	0x1f
+#define DRM_I915_GEM_SW_FINISH	0x20
+#define DRM_I915_GEM_SET_TILING	0x21
+#define DRM_I915_GEM_GET_TILING	0x22
+#define DRM_I915_GEM_GET_APERTURE 0x23
+#define DRM_I915_GEM_MMAP_GTT	0x24
+#define DRM_I915_GET_PIPE_FROM_CRTC_ID	0x25
+#define DRM_I915_GEM_MADVISE	0x26
+#define DRM_I915_OVERLAY_PUT_IMAGE	0x27
+#define DRM_I915_OVERLAY_ATTRS	0x28
+#define DRM_I915_GEM_EXECBUFFER2	0x29
+#define DRM_I915_GEM_EXECBUFFER2_WR	DRM_I915_GEM_EXECBUFFER2
+#define DRM_I915_GET_SPRITE_COLORKEY	0x2a
+#define DRM_I915_SET_SPRITE_COLORKEY	0x2b
+#define DRM_I915_GEM_WAIT	0x2c
+#define DRM_I915_GEM_CONTEXT_CREATE	0x2d
+#define DRM_I915_GEM_CONTEXT_DESTROY	0x2e
+#define DRM_I915_GEM_SET_CACHING	0x2f
+#define DRM_I915_GEM_GET_CACHING	0x30
+#define DRM_I915_REG_READ		0x31
+#define DRM_I915_GET_RESET_STATS	0x32
+#define DRM_I915_GEM_USERPTR		0x33
+#define DRM_I915_GEM_CONTEXT_GETPARAM	0x34
+#define DRM_I915_GEM_CONTEXT_SETPARAM	0x35
+#define DRM_I915_PERF_OPEN		0x36
+#define DRM_I915_PERF_ADD_CONFIG	0x37
+#define DRM_I915_PERF_REMOVE_CONFIG	0x38
+#define DRM_I915_QUERY			0x39
+#define DRM_I915_GEM_VM_CREATE		0x3a
+#define DRM_I915_GEM_VM_DESTROY		0x3b
+#define DRM_I915_GEM_CREATE_EXT		0x3c
+/* Must be kept compact -- no holes */
+
+#define DRM_IOCTL_I915_INIT		DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT, drm_i915_init_t)
+#define DRM_IOCTL_I915_FLUSH		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLUSH)
+#define DRM_IOCTL_I915_FLIP		DRM_IO ( DRM_COMMAND_BASE + DRM_I915_FLIP)
+#define DRM_IOCTL_I915_BATCHBUFFER	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_BATCHBUFFER, drm_i915_batchbuffer_t)
+#define DRM_IOCTL_I915_IRQ_EMIT         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_IRQ_EMIT, drm_i915_irq_emit_t)
+#define DRM_IOCTL_I915_IRQ_WAIT         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_IRQ_WAIT, drm_i915_irq_wait_t)
+#define DRM_IOCTL_I915_GETPARAM         DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GETPARAM, drm_i915_getparam_t)
+#define DRM_IOCTL_I915_SETPARAM         DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SETPARAM, drm_i915_setparam_t)
+#define DRM_IOCTL_I915_ALLOC            DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_ALLOC, drm_i915_mem_alloc_t)
+#define DRM_IOCTL_I915_FREE             DRM_IOW( DRM_COMMAND_BASE + DRM_I915_FREE, drm_i915_mem_free_t)
+#define DRM_IOCTL_I915_INIT_HEAP        DRM_IOW( DRM_COMMAND_BASE + DRM_I915_INIT_HEAP, drm_i915_mem_init_heap_t)
+#define DRM_IOCTL_I915_CMDBUFFER	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_CMDBUFFER, drm_i915_cmdbuffer_t)
+#define DRM_IOCTL_I915_DESTROY_HEAP	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_DESTROY_HEAP, drm_i915_mem_destroy_heap_t)
+#define DRM_IOCTL_I915_SET_VBLANK_PIPE	DRM_IOW( DRM_COMMAND_BASE + DRM_I915_SET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
+#define DRM_IOCTL_I915_GET_VBLANK_PIPE	DRM_IOR( DRM_COMMAND_BASE + DRM_I915_GET_VBLANK_PIPE, drm_i915_vblank_pipe_t)
+#define DRM_IOCTL_I915_VBLANK_SWAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_VBLANK_SWAP, drm_i915_vblank_swap_t)
+#define DRM_IOCTL_I915_HWS_ADDR		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_HWS_ADDR, struct drm_i915_gem_init)
+#define DRM_IOCTL_I915_GEM_INIT		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_INIT, struct drm_i915_gem_init)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER, struct drm_i915_gem_execbuffer)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_EXECBUFFER2_WR	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_EXECBUFFER2_WR, struct drm_i915_gem_execbuffer2)
+#define DRM_IOCTL_I915_GEM_PIN		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_PIN, struct drm_i915_gem_pin)
+#define DRM_IOCTL_I915_GEM_UNPIN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_UNPIN, struct drm_i915_gem_unpin)
+#define DRM_IOCTL_I915_GEM_BUSY		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_BUSY, struct drm_i915_gem_busy)
+#define DRM_IOCTL_I915_GEM_SET_CACHING		DRM_IOW(DRM_COMMAND_BASE + DRM_I915_GEM_SET_CACHING, struct drm_i915_gem_caching)
+#define DRM_IOCTL_I915_GEM_GET_CACHING		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_GET_CACHING, struct drm_i915_gem_caching)
+#define DRM_IOCTL_I915_GEM_THROTTLE	DRM_IO ( DRM_COMMAND_BASE + DRM_I915_GEM_THROTTLE)
+#define DRM_IOCTL_I915_GEM_ENTERVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_ENTERVT)
+#define DRM_IOCTL_I915_GEM_LEAVEVT	DRM_IO(DRM_COMMAND_BASE + DRM_I915_GEM_LEAVEVT)
+#define DRM_IOCTL_I915_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE, struct drm_i915_gem_create)
+#define DRM_IOCTL_I915_GEM_CREATE_EXT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_CREATE_EXT, struct drm_i915_gem_create_ext)
+#define DRM_IOCTL_I915_GEM_PREAD	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PREAD, struct drm_i915_gem_pread)
+#define DRM_IOCTL_I915_GEM_PWRITE	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_PWRITE, struct drm_i915_gem_pwrite)
+#define DRM_IOCTL_I915_GEM_MMAP		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP, struct drm_i915_gem_mmap)
+#define DRM_IOCTL_I915_GEM_MMAP_GTT	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_gtt)
+#define DRM_IOCTL_I915_GEM_MMAP_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MMAP_GTT, struct drm_i915_gem_mmap_offset)
+#define DRM_IOCTL_I915_GEM_SET_DOMAIN	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SET_DOMAIN, struct drm_i915_gem_set_domain)
+#define DRM_IOCTL_I915_GEM_SW_FINISH	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_SW_FINISH, struct drm_i915_gem_sw_finish)
+#define DRM_IOCTL_I915_GEM_SET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_SET_TILING, struct drm_i915_gem_set_tiling)
+#define DRM_IOCTL_I915_GEM_GET_TILING	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_GET_TILING, struct drm_i915_gem_get_tiling)
+#define DRM_IOCTL_I915_GEM_GET_APERTURE	DRM_IOR  (DRM_COMMAND_BASE + DRM_I915_GEM_GET_APERTURE, struct drm_i915_gem_get_aperture)
+#define DRM_IOCTL_I915_GET_PIPE_FROM_CRTC_ID DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_PIPE_FROM_CRTC_ID, struct drm_i915_get_pipe_from_crtc_id)
+#define DRM_IOCTL_I915_GEM_MADVISE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_MADVISE, struct drm_i915_gem_madvise)
+#define DRM_IOCTL_I915_OVERLAY_PUT_IMAGE	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_OVERLAY_PUT_IMAGE, struct drm_intel_overlay_put_image)
+#define DRM_IOCTL_I915_OVERLAY_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_OVERLAY_ATTRS, struct drm_intel_overlay_attrs)
+#define DRM_IOCTL_I915_SET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_SET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GET_SPRITE_COLORKEY DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GET_SPRITE_COLORKEY, struct drm_intel_sprite_colorkey)
+#define DRM_IOCTL_I915_GEM_WAIT		DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_WAIT, struct drm_i915_gem_wait)
+#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create)
+#define DRM_IOCTL_I915_GEM_CONTEXT_CREATE_EXT	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_CREATE, struct drm_i915_gem_context_create_ext)
+#define DRM_IOCTL_I915_GEM_CONTEXT_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_DESTROY, struct drm_i915_gem_context_destroy)
+#define DRM_IOCTL_I915_REG_READ			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_REG_READ, struct drm_i915_reg_read)
+#define DRM_IOCTL_I915_GET_RESET_STATS		DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GET_RESET_STATS, struct drm_i915_reset_stats)
+#define DRM_IOCTL_I915_GEM_USERPTR			DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_USERPTR, struct drm_i915_gem_userptr)
+#define DRM_IOCTL_I915_GEM_CONTEXT_GETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_GETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_GEM_CONTEXT_SETPARAM	DRM_IOWR (DRM_COMMAND_BASE + DRM_I915_GEM_CONTEXT_SETPARAM, struct drm_i915_gem_context_param)
+#define DRM_IOCTL_I915_PERF_OPEN	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_OPEN, struct drm_i915_perf_open_param)
+#define DRM_IOCTL_I915_PERF_ADD_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_ADD_CONFIG, struct drm_i915_perf_oa_config)
+#define DRM_IOCTL_I915_PERF_REMOVE_CONFIG	DRM_IOW(DRM_COMMAND_BASE + DRM_I915_PERF_REMOVE_CONFIG, __u64)
+#define DRM_IOCTL_I915_QUERY			DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_QUERY, struct drm_i915_query)
+#define DRM_IOCTL_I915_GEM_VM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_I915_GEM_VM_CREATE, struct drm_i915_gem_vm_control)
+#define DRM_IOCTL_I915_GEM_VM_DESTROY	DRM_IOW (DRM_COMMAND_BASE + DRM_I915_GEM_VM_DESTROY, struct drm_i915_gem_vm_control)
+
+/* Allow drivers to submit batchbuffers directly to hardware, relying
+ * on the security mechanisms provided by hardware.
+ */
+typedef struct drm_i915_batchbuffer {
+	int start;		/* agp offset */
+	int used;		/* nr bytes in use */
+	int DR1;		/* hw flags for GFX_OP_DRAWRECT_INFO */
+	int DR4;		/* window origin for GFX_OP_DRAWRECT_INFO */
+	int num_cliprects;	/* mulitpass with multiple cliprects? */
+	struct drm_clip_rect __user *cliprects;	/* pointer to userspace cliprects */
+} drm_i915_batchbuffer_t;
+
+/* As above, but pass a pointer to userspace buffer which can be
+ * validated by the kernel prior to sending to hardware.
+ */
+typedef struct _drm_i915_cmdbuffer {
+	char __user *buf;	/* pointer to userspace command buffer */
+	int sz;			/* nr bytes in buf */
+	int DR1;		/* hw flags for GFX_OP_DRAWRECT_INFO */
+	int DR4;		/* window origin for GFX_OP_DRAWRECT_INFO */
+	int num_cliprects;	/* mulitpass with multiple cliprects? */
+	struct drm_clip_rect __user *cliprects;	/* pointer to userspace cliprects */
+} drm_i915_cmdbuffer_t;
+
+/* Userspace can request & wait on irq's:
+ */
+typedef struct drm_i915_irq_emit {
+	int __user *irq_seq;
+} drm_i915_irq_emit_t;
+
+typedef struct drm_i915_irq_wait {
+	int irq_seq;
+} drm_i915_irq_wait_t;
+
+/*
+ * Different modes of per-process Graphics Translation Table,
+ * see I915_PARAM_HAS_ALIASING_PPGTT
+ */
+#define I915_GEM_PPGTT_NONE	0
+#define I915_GEM_PPGTT_ALIASING	1
+#define I915_GEM_PPGTT_FULL	2
+
+/* Ioctl to query kernel params:
+ */
+#define I915_PARAM_IRQ_ACTIVE            1
+#define I915_PARAM_ALLOW_BATCHBUFFER     2
+#define I915_PARAM_LAST_DISPATCH         3
+#define I915_PARAM_CHIPSET_ID            4
+#define I915_PARAM_HAS_GEM               5
+#define I915_PARAM_NUM_FENCES_AVAIL      6
+#define I915_PARAM_HAS_OVERLAY           7
+#define I915_PARAM_HAS_PAGEFLIPPING	 8
+#define I915_PARAM_HAS_EXECBUF2          9
+#define I915_PARAM_HAS_BSD		 10
+#define I915_PARAM_HAS_BLT		 11
+#define I915_PARAM_HAS_RELAXED_FENCING	 12
+#define I915_PARAM_HAS_COHERENT_RINGS	 13
+#define I915_PARAM_HAS_EXEC_CONSTANTS	 14
+#define I915_PARAM_HAS_RELAXED_DELTA	 15
+#define I915_PARAM_HAS_GEN7_SOL_RESET	 16
+#define I915_PARAM_HAS_LLC     	 	 17
+#define I915_PARAM_HAS_ALIASING_PPGTT	 18
+#define I915_PARAM_HAS_WAIT_TIMEOUT	 19
+#define I915_PARAM_HAS_SEMAPHORES	 20
+#define I915_PARAM_HAS_PRIME_VMAP_FLUSH	 21
+#define I915_PARAM_HAS_VEBOX		 22
+#define I915_PARAM_HAS_SECURE_BATCHES	 23
+#define I915_PARAM_HAS_PINNED_BATCHES	 24
+#define I915_PARAM_HAS_EXEC_NO_RELOC	 25
+#define I915_PARAM_HAS_EXEC_HANDLE_LUT   26
+#define I915_PARAM_HAS_WT     	 	 27
+#define I915_PARAM_CMD_PARSER_VERSION	 28
+#define I915_PARAM_HAS_COHERENT_PHYS_GTT 29
+#define I915_PARAM_MMAP_VERSION          30
+#define I915_PARAM_HAS_BSD2		 31
+#define I915_PARAM_REVISION              32
+#define I915_PARAM_SUBSLICE_TOTAL	 33
+#define I915_PARAM_EU_TOTAL		 34
+#define I915_PARAM_HAS_GPU_RESET	 35
+#define I915_PARAM_HAS_RESOURCE_STREAMER 36
+#define I915_PARAM_HAS_EXEC_SOFTPIN	 37
+#define I915_PARAM_HAS_POOLED_EU	 38
+#define I915_PARAM_MIN_EU_IN_POOL	 39
+#define I915_PARAM_MMAP_GTT_VERSION	 40
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports user defined execution
+ * priorities and the driver will attempt to execute batches in priority order.
+ * The param returns a capability bitmask, nonzero implies that the scheduler
+ * is enabled, with different features present according to the mask.
+ *
+ * The initial priority for each batch is supplied by the context and is
+ * controlled via I915_CONTEXT_PARAM_PRIORITY.
+ */
+#define I915_PARAM_HAS_SCHEDULER	 41
+#define   I915_SCHEDULER_CAP_ENABLED	(1ul << 0)
+#define   I915_SCHEDULER_CAP_PRIORITY	(1ul << 1)
+#define   I915_SCHEDULER_CAP_PREEMPTION	(1ul << 2)
+#define   I915_SCHEDULER_CAP_SEMAPHORES	(1ul << 3)
+#define   I915_SCHEDULER_CAP_ENGINE_BUSY_STATS	(1ul << 4)
+/*
+ * Indicates the 2k user priority levels are statically mapped into 3 buckets as
+ * follows:
+ *
+ * -1k to -1	Low priority
+ * 0		Normal priority
+ * 1 to 1k	Highest priority
+ */
+#define   I915_SCHEDULER_CAP_STATIC_PRIORITY_MAP	(1ul << 5)
+
+/*
+ * Query the status of HuC load.
+ *
+ * The query can fail in the following scenarios with the listed error codes:
+ *  -ENODEV if HuC is not present on this platform,
+ *  -EOPNOTSUPP if HuC firmware usage is disabled,
+ *  -ENOPKG if HuC firmware fetch failed,
+ *  -ENOEXEC if HuC firmware is invalid or mismatched,
+ *  -ENOMEM if i915 failed to prepare the FW objects for transfer to the uC,
+ *  -EIO if the FW transfer or the FW authentication failed.
+ *
+ * If the IOCTL is successful, the returned parameter will be set to one of the
+ * following values:
+ *  * 0 if HuC firmware load is not complete,
+ *  * 1 if HuC firmware is loaded and fully authenticated,
+ *  * 2 if HuC firmware is loaded and authenticated for clear media only
+ */
+#define I915_PARAM_HUC_STATUS		 42
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to opt-out of
+ * synchronisation with implicit fencing on individual objects.
+ * See EXEC_OBJECT_ASYNC.
+ */
+#define I915_PARAM_HAS_EXEC_ASYNC	 43
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports explicit fence support -
+ * both being able to pass in a sync_file fd to wait upon before executing,
+ * and being able to return a new sync_file fd that is signaled when the
+ * current request is complete. See I915_EXEC_FENCE_IN and I915_EXEC_FENCE_OUT.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE	 44
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports the ability to capture
+ * user-specified buffers for post-mortem debugging of GPU hangs. See
+ * EXEC_OBJECT_CAPTURE.
+ */
+#define I915_PARAM_HAS_EXEC_CAPTURE	 45
+
+#define I915_PARAM_SLICE_MASK		 46
+
+/* Assuming it's uniform for each slice, this queries the mask of subslices
+ * per-slice for this system.
+ */
+#define I915_PARAM_SUBSLICE_MASK	 47
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying the batch buffer
+ * as the first execobject as opposed to the last. See I915_EXEC_BATCH_FIRST.
+ */
+#define I915_PARAM_HAS_EXEC_BATCH_FIRST	 48
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * drm_i915_gem_exec_fence structures.  See I915_EXEC_FENCE_ARRAY.
+ */
+#define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
+
+/*
+ * Query whether every context (both per-file default and user created) is
+ * isolated (insofar as HW supports). If this parameter is not true, then
+ * freshly created contexts may inherit values from an existing context,
+ * rather than default HW values. If true, it also ensures (insofar as HW
+ * supports) that all state set by this context will not leak to any other
+ * context.
+ *
+ * As not every engine across every gen support contexts, the returned
+ * value reports the support of context isolation for individual engines by
+ * returning a bitmask of each engine class set to true if that class supports
+ * isolation.
+ */
+#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
+
+/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
+ * registers. This used to be fixed per platform but from CNL onwards, this
+ * might vary depending on the parts.
+ */
+#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
+
+/*
+ * Once upon a time we supposed that writes through the GGTT would be
+ * immediately in physical memory (once flushed out of the CPU path). However,
+ * on a few different processors and chipsets, this is not necessarily the case
+ * as the writes appear to be buffered internally. Thus a read of the backing
+ * storage (physical memory) via a different path (with different physical tags
+ * to the indirect write via the GGTT) will see stale values from before
+ * the GGTT write. Inside the kernel, we can for the most part keep track of
+ * the different read/write domains in use (e.g. set-domain), but the assumption
+ * of coherency is baked into the ABI, hence reporting its true state in this
+ * parameter.
+ *
+ * Reports true when writes via mmap_gtt are immediately visible following an
+ * lfence to flush the WCB.
+ *
+ * Reports false when writes via mmap_gtt are indeterminately delayed in an in
+ * internal buffer and are _not_ immediately visible to third parties accessing
+ * directly via mmap_cpu/mmap_wc. Use of mmap_gtt as part of an IPC
+ * communications channel when reporting false is strongly disadvised.
+ */
+#define I915_PARAM_MMAP_GTT_COHERENT	52
+
+/*
+ * Query whether DRM_I915_GEM_EXECBUFFER2 supports coordination of parallel
+ * execution through use of explicit fence support.
+ * See I915_EXEC_FENCE_OUT and I915_EXEC_FENCE_SUBMIT.
+ */
+#define I915_PARAM_HAS_EXEC_SUBMIT_FENCE 53
+
+/*
+ * Revision of the i915-perf uAPI. The value returned helps determine what
+ * i915-perf features are available. See drm_i915_perf_property_id.
+ */
+#define I915_PARAM_PERF_REVISION	54
+
+/* Query whether DRM_I915_GEM_EXECBUFFER2 supports supplying an array of
+ * timeline syncobj through drm_i915_gem_execbuffer_ext_timeline_fences. See
+ * I915_EXEC_USE_EXTENSIONS.
+ */
+#define I915_PARAM_HAS_EXEC_TIMELINE_FENCES 55
+
+/* Query if the kernel supports the I915_USERPTR_PROBE flag. */
+#define I915_PARAM_HAS_USERPTR_PROBE 56
+
+/*
+ * Frequency of the timestamps in OA reports. This used to be the same as the CS
+ * timestamp frequency, but differs on some platforms.
+ */
+#define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57
+
+/*
+ * Query the status of PXP support in i915.
+ *
+ * The query can fail in the following scenarios with the listed error codes:
+ *     -ENODEV = PXP support is not available on the GPU device or in the
+ *               kernel due to missing component drivers or kernel configs.
+ *
+ * If the IOCTL is successful, the returned parameter will be set to one of
+ * the following values:
+ *     1 = PXP feature is supported and is ready for use.
+ *     2 = PXP feature is supported but should be ready soon (pending
+ *         initialization of non-i915 system dependencies).
+ *
+ * NOTE: When param is supported (positive return values), user space should
+ *       still refer to the GEM PXP context-creation UAPI header specs to be
+ *       aware of possible failure due to system state machine at the time.
+ */
+#define I915_PARAM_PXP_STATUS		 58
+
+/*
+ * Query if kernel allows marking a context to send a Freq hint to SLPC. This
+ * will enable use of the strategies allowed by the SLPC algorithm.
+ */
+#define I915_PARAM_HAS_CONTEXT_FREQ_HINT	59
+
+/* Must be kept compact -- no holes and well documented */
+
+/**
+ * struct drm_i915_getparam - Driver parameter query structure.
+ */
+struct drm_i915_getparam {
+	/** @param: Driver parameter to query. */
+	__s32 param;
+
+	/**
+	 * @value: Address of memory where queried value should be put.
+	 *
+	 * WARNING: Using pointers instead of fixed-size u64 means we need to write
+	 * compat32 code. Don't repeat this mistake.
+	 */
+	int __user *value;
+};
+
+/**
+ * typedef drm_i915_getparam_t - Driver parameter query structure.
+ * See struct drm_i915_getparam.
+ */
+typedef struct drm_i915_getparam drm_i915_getparam_t;
+
+/* Ioctl to set kernel params:
+ */
+#define I915_SETPARAM_USE_MI_BATCHBUFFER_START            1
+#define I915_SETPARAM_TEX_LRU_LOG_GRANULARITY             2
+#define I915_SETPARAM_ALLOW_BATCHBUFFER                   3
+#define I915_SETPARAM_NUM_USED_FENCES                     4
+/* Must be kept compact -- no holes */
+
+typedef struct drm_i915_setparam {
+	int param;
+	int value;
+} drm_i915_setparam_t;
+
+/* A memory manager for regions of shared memory:
+ */
+#define I915_MEM_REGION_AGP 1
+
+typedef struct drm_i915_mem_alloc {
+	int region;
+	int alignment;
+	int size;
+	int __user *region_offset;	/* offset from start of fb or agp */
+} drm_i915_mem_alloc_t;
+
+typedef struct drm_i915_mem_free {
+	int region;
+	int region_offset;
+} drm_i915_mem_free_t;
+
+typedef struct drm_i915_mem_init_heap {
+	int region;
+	int size;
+	int start;
+} drm_i915_mem_init_heap_t;
+
+/* Allow memory manager to be torn down and re-initialized (eg on
+ * rotate):
+ */
+typedef struct drm_i915_mem_destroy_heap {
+	int region;
+} drm_i915_mem_destroy_heap_t;
+
+/* Allow X server to configure which pipes to monitor for vblank signals
+ */
+#define	DRM_I915_VBLANK_PIPE_A	1
+#define	DRM_I915_VBLANK_PIPE_B	2
+
+typedef struct drm_i915_vblank_pipe {
+	int pipe;
+} drm_i915_vblank_pipe_t;
+
+/* Schedule buffer swap at given vertical blank:
+ */
+typedef struct drm_i915_vblank_swap {
+	drm_drawable_t drawable;
+	enum drm_vblank_seq_type seqtype;
+	unsigned int sequence;
+} drm_i915_vblank_swap_t;
+
+typedef struct drm_i915_hws_addr {
+	__u64 addr;
+} drm_i915_hws_addr_t;
+
+struct drm_i915_gem_init {
+	/**
+	 * Beginning offset in the GTT to be managed by the DRM memory
+	 * manager.
+	 */
+	__u64 gtt_start;
+	/**
+	 * Ending offset in the GTT to be managed by the DRM memory
+	 * manager.
+	 */
+	__u64 gtt_end;
+};
+
+struct drm_i915_gem_create {
+	/**
+	 * Requested size for the object.
+	 *
+	 * The (page-aligned) allocated size for the object will be returned.
+	 */
+	__u64 size;
+	/**
+	 * Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+	__u32 pad;
+};
+
+struct drm_i915_gem_pread {
+	/** Handle for the object being read. */
+	__u32 handle;
+	__u32 pad;
+	/** Offset into the object to read from */
+	__u64 offset;
+	/** Length of data to read */
+	__u64 size;
+	/**
+	 * Pointer to write the data into.
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 data_ptr;
+};
+
+struct drm_i915_gem_pwrite {
+	/** Handle for the object being written to. */
+	__u32 handle;
+	__u32 pad;
+	/** Offset into the object to write to */
+	__u64 offset;
+	/** Length of data to write */
+	__u64 size;
+	/**
+	 * Pointer to read the data from.
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 data_ptr;
+};
+
+struct drm_i915_gem_mmap {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/** Offset in the object to map. */
+	__u64 offset;
+	/**
+	 * Length of data to map.
+	 *
+	 * The value will be page-aligned.
+	 */
+	__u64 size;
+	/**
+	 * Returned pointer the data was mapped at.
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 addr_ptr;
+
+	/**
+	 * Flags for extended behaviour.
+	 *
+	 * Added in version 2.
+	 */
+	__u64 flags;
+#define I915_MMAP_WC 0x1
+};
+
+struct drm_i915_gem_mmap_gtt {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 pad;
+	/**
+	 * Fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+};
+
+/**
+ * struct drm_i915_gem_mmap_offset - Retrieve an offset so we can mmap this buffer object.
+ *
+ * This struct is passed as argument to the `DRM_IOCTL_I915_GEM_MMAP_OFFSET` ioctl,
+ * and is used to retrieve the fake offset to mmap an object specified by &handle.
+ *
+ * The legacy way of using `DRM_IOCTL_I915_GEM_MMAP` is removed on gen12+.
+ * `DRM_IOCTL_I915_GEM_MMAP_GTT` is an older supported alias to this struct, but will behave
+ * as setting the &extensions to 0, and &flags to `I915_MMAP_OFFSET_GTT`.
+ */
+struct drm_i915_gem_mmap_offset {
+	/** @handle: Handle for the object being mapped. */
+	__u32 handle;
+	/** @pad: Must be zero */
+	__u32 pad;
+	/**
+	 * @offset: The fake offset to use for subsequent mmap call
+	 *
+	 * This is a fixed-size type for 32/64 compatibility.
+	 */
+	__u64 offset;
+
+	/**
+	 * @flags: Flags for extended behaviour.
+	 *
+	 * It is mandatory that one of the `MMAP_OFFSET` types
+	 * should be included:
+	 *
+	 * - `I915_MMAP_OFFSET_GTT`: Use mmap with the object bound to GTT. (Write-Combined)
+	 * - `I915_MMAP_OFFSET_WC`: Use Write-Combined caching.
+	 * - `I915_MMAP_OFFSET_WB`: Use Write-Back caching.
+	 * - `I915_MMAP_OFFSET_FIXED`: Use object placement to determine caching.
+	 *
+	 * On devices with local memory `I915_MMAP_OFFSET_FIXED` is the only valid
+	 * type. On devices without local memory, this caching mode is invalid.
+	 *
+	 * As caching mode when specifying `I915_MMAP_OFFSET_FIXED`, WC or WB will
+	 * be used, depending on the object placement on creation. WB will be used
+	 * when the object can only exist in system memory, WC otherwise.
+	 */
+	__u64 flags;
+
+#define I915_MMAP_OFFSET_GTT	0
+#define I915_MMAP_OFFSET_WC	1
+#define I915_MMAP_OFFSET_WB	2
+#define I915_MMAP_OFFSET_UC	3
+#define I915_MMAP_OFFSET_FIXED	4
+
+	/**
+	 * @extensions: Zero-terminated chain of extensions.
+	 *
+	 * No current extensions defined; mbz.
+	 */
+	__u64 extensions;
+};
+
+/**
+ * struct drm_i915_gem_set_domain - Adjust the objects write or read domain, in
+ * preparation for accessing the pages via some CPU domain.
+ *
+ * Specifying a new write or read domain will flush the object out of the
+ * previous domain(if required), before then updating the objects domain
+ * tracking with the new domain.
+ *
+ * Note this might involve waiting for the object first if it is still active on
+ * the GPU.
+ *
+ * Supported values for @read_domains and @write_domain:
+ *
+ *	- I915_GEM_DOMAIN_WC: Uncached write-combined domain
+ *	- I915_GEM_DOMAIN_CPU: CPU cache domain
+ *	- I915_GEM_DOMAIN_GTT: Mappable aperture domain
+ *
+ * All other domains are rejected.
+ *
+ * Note that for discrete, starting from DG1, this is no longer supported, and
+ * is instead rejected. On such platforms the CPU domain is effectively static,
+ * where we also only support a single &drm_i915_gem_mmap_offset cache mode,
+ * which can't be set explicitly and instead depends on the object placements,
+ * as per the below.
+ *
+ * Implicit caching rules, starting from DG1:
+ *
+ *	- If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
+ *	  contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
+ *	  mapped as write-combined only.
+ *
+ *	- Everything else is always allocated and mapped as write-back, with the
+ *	  guarantee that everything is also coherent with the GPU.
+ *
+ * Note that this is likely to change in the future again, where we might need
+ * more flexibility on future devices, so making this all explicit as part of a
+ * new &drm_i915_gem_create_ext extension is probable.
+ */
+struct drm_i915_gem_set_domain {
+	/** @handle: Handle for the object. */
+	__u32 handle;
+
+	/** @read_domains: New read domains. */
+	__u32 read_domains;
+
+	/**
+	 * @write_domain: New write domain.
+	 *
+	 * Note that having something in the write domain implies it's in the
+	 * read domain, and only that read domain.
+	 */
+	__u32 write_domain;
+};
+
+struct drm_i915_gem_sw_finish {
+	/** Handle for the object */
+	__u32 handle;
+};
+
+struct drm_i915_gem_relocation_entry {
+	/**
+	 * Handle of the buffer being pointed to by this relocation entry.
+	 *
+	 * It's appealing to make this be an index into the mm_validate_entry
+	 * list to refer to the buffer, but this allows the driver to create
+	 * a relocation list for state buffers and not re-write it per
+	 * exec using the buffer.
+	 */
+	__u32 target_handle;
+
+	/**
+	 * Value to be added to the offset of the target buffer to make up
+	 * the relocation entry.
+	 */
+	__u32 delta;
+
+	/** Offset in the buffer the relocation entry will be written into */
+	__u64 offset;
+
+	/**
+	 * Offset value of the target buffer that the relocation entry was last
+	 * written as.
+	 *
+	 * If the buffer has the same offset as last time, we can skip syncing
+	 * and writing the relocation.  This value is written back out by
+	 * the execbuffer ioctl when the relocation is written.
+	 */
+	__u64 presumed_offset;
+
+	/**
+	 * Target memory domains read by this operation.
+	 */
+	__u32 read_domains;
+
+	/**
+	 * Target memory domains written by this operation.
+	 *
+	 * Note that only one domain may be written by the whole
+	 * execbuffer operation, so that where there are conflicts,
+	 * the application will get -EINVAL back.
+	 */
+	__u32 write_domain;
+};
+
+/** @{
+ * Intel memory domains
+ *
+ * Most of these just align with the various caches in
+ * the system and are used to flush and invalidate as
+ * objects end up cached in different domains.
+ */
+/** CPU cache */
+#define I915_GEM_DOMAIN_CPU		0x00000001
+/** Render cache, used by 2D and 3D drawing */
+#define I915_GEM_DOMAIN_RENDER		0x00000002
+/** Sampler cache, used by texture engine */
+#define I915_GEM_DOMAIN_SAMPLER		0x00000004
+/** Command queue, used to load batch buffers */
+#define I915_GEM_DOMAIN_COMMAND		0x00000008
+/** Instruction cache, used by shader programs */
+#define I915_GEM_DOMAIN_INSTRUCTION	0x00000010
+/** Vertex address cache */
+#define I915_GEM_DOMAIN_VERTEX		0x00000020
+/** GTT domain - aperture and scanout */
+#define I915_GEM_DOMAIN_GTT		0x00000040
+/** WC domain - uncached access */
+#define I915_GEM_DOMAIN_WC		0x00000080
+/** @} */
+
+struct drm_i915_gem_exec_object {
+	/**
+	 * User's handle for a buffer to be bound into the GTT for this
+	 * operation.
+	 */
+	__u32 handle;
+
+	/** Number of relocations to be performed on this buffer */
+	__u32 relocation_count;
+	/**
+	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
+	 * the relocations to be performed in this buffer.
+	 */
+	__u64 relocs_ptr;
+
+	/** Required alignment in graphics aperture */
+	__u64 alignment;
+
+	/**
+	 * Returned value of the updated offset of the object, for future
+	 * presumed_offset writes.
+	 */
+	__u64 offset;
+};
+
+/* DRM_IOCTL_I915_GEM_EXECBUFFER was removed in Linux 5.13 */
+struct drm_i915_gem_execbuffer {
+	/**
+	 * List of buffers to be validated with their relocations to be
+	 * performend on them.
+	 *
+	 * This is a pointer to an array of struct drm_i915_gem_validate_entry.
+	 *
+	 * These buffers must be listed in an order such that all relocations
+	 * a buffer is performing refer to buffers that have already appeared
+	 * in the validate list.
+	 */
+	__u64 buffers_ptr;
+	__u32 buffer_count;
+
+	/** Offset in the batchbuffer to start execution from. */
+	__u32 batch_start_offset;
+	/** Bytes used in batchbuffer from batch_start_offset */
+	__u32 batch_len;
+	__u32 DR1;
+	__u32 DR4;
+	__u32 num_cliprects;
+	/** This is a struct drm_clip_rect *cliprects */
+	__u64 cliprects_ptr;
+};
+
+struct drm_i915_gem_exec_object2 {
+	/**
+	 * User's handle for a buffer to be bound into the GTT for this
+	 * operation.
+	 */
+	__u32 handle;
+
+	/** Number of relocations to be performed on this buffer */
+	__u32 relocation_count;
+	/**
+	 * Pointer to array of struct drm_i915_gem_relocation_entry containing
+	 * the relocations to be performed in this buffer.
+	 */
+	__u64 relocs_ptr;
+
+	/** Required alignment in graphics aperture */
+	__u64 alignment;
+
+	/**
+	 * When the EXEC_OBJECT_PINNED flag is specified this is populated by
+	 * the user with the GTT offset at which this object will be pinned.
+	 *
+	 * When the I915_EXEC_NO_RELOC flag is specified this must contain the
+	 * presumed_offset of the object.
+	 *
+	 * During execbuffer2 the kernel populates it with the value of the
+	 * current GTT offset of the object, for future presumed_offset writes.
+	 *
+	 * See struct drm_i915_gem_create_ext for the rules when dealing with
+	 * alignment restrictions with I915_MEMORY_CLASS_DEVICE, on devices with
+	 * minimum page sizes, like DG2.
+	 */
+	__u64 offset;
+
+#define EXEC_OBJECT_NEEDS_FENCE		 (1<<0)
+#define EXEC_OBJECT_NEEDS_GTT		 (1<<1)
+#define EXEC_OBJECT_WRITE		 (1<<2)
+#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3)
+#define EXEC_OBJECT_PINNED		 (1<<4)
+#define EXEC_OBJECT_PAD_TO_SIZE		 (1<<5)
+/* The kernel implicitly tracks GPU activity on all GEM objects, and
+ * synchronises operations with outstanding rendering. This includes
+ * rendering on other devices if exported via dma-buf. However, sometimes
+ * this tracking is too coarse and the user knows better. For example,
+ * if the object is split into non-overlapping ranges shared between different
+ * clients or engines (i.e. suballocating objects), the implicit tracking
+ * by kernel assumes that each operation affects the whole object rather
+ * than an individual range, causing needless synchronisation between clients.
+ * The kernel will also forgo any CPU cache flushes prior to rendering from
+ * the object as the client is expected to be also handling such domain
+ * tracking.
+ *
+ * The kernel maintains the implicit tracking in order to manage resources
+ * used by the GPU - this flag only disables the synchronisation prior to
+ * rendering with this object in this execbuf.
+ *
+ * Opting out of implicit synhronisation requires the user to do its own
+ * explicit tracking to avoid rendering corruption. See, for example,
+ * I915_PARAM_HAS_EXEC_FENCE to order execbufs and execute them asynchronously.
+ */
+#define EXEC_OBJECT_ASYNC		(1<<6)
+/* Request that the contents of this execobject be copied into the error
+ * state upon a GPU hang involving this batch for post-mortem debugging.
+ * These buffers are recorded in no particular order as "user" in
+ * /sys/class/drm/cardN/error. Query I915_PARAM_HAS_EXEC_CAPTURE to see
+ * if the kernel supports this flag.
+ */
+#define EXEC_OBJECT_CAPTURE		(1<<7)
+/* All remaining bits are MBZ and RESERVED FOR FUTURE USE */
+#define __EXEC_OBJECT_UNKNOWN_FLAGS -(EXEC_OBJECT_CAPTURE<<1)
+	__u64 flags;
+
+	union {
+		__u64 rsvd1;
+		__u64 pad_to_size;
+	};
+	__u64 rsvd2;
+};
+
+/**
+ * struct drm_i915_gem_exec_fence - An input or output fence for the execbuf
+ * ioctl.
+ *
+ * The request will wait for input fence to signal before submission.
+ *
+ * The returned output fence will be signaled after the completion of the
+ * request.
+ */
+struct drm_i915_gem_exec_fence {
+	/** @handle: User's handle for a drm_syncobj to wait on or signal. */
+	__u32 handle;
+
+	/**
+	 * @flags: Supported flags are:
+	 *
+	 * I915_EXEC_FENCE_WAIT:
+	 * Wait for the input fence before request submission.
+	 *
+	 * I915_EXEC_FENCE_SIGNAL:
+	 * Return request completion fence as output
+	 */
+	__u32 flags;
+#define I915_EXEC_FENCE_WAIT            (1<<0)
+#define I915_EXEC_FENCE_SIGNAL          (1<<1)
+#define __I915_EXEC_FENCE_UNKNOWN_FLAGS (-(I915_EXEC_FENCE_SIGNAL << 1))
+};
+
+/**
+ * struct drm_i915_gem_execbuffer_ext_timeline_fences - Timeline fences
+ * for execbuf ioctl.
+ *
+ * This structure describes an array of drm_syncobj and associated points for
+ * timeline variants of drm_syncobj. It is invalid to append this structure to
+ * the execbuf if I915_EXEC_FENCE_ARRAY is set.
+ */
+struct drm_i915_gem_execbuffer_ext_timeline_fences {
+#define DRM_I915_GEM_EXECBUFFER_EXT_TIMELINE_FENCES 0
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+
+	/**
+	 * @fence_count: Number of elements in the @handles_ptr & @value_ptr
+	 * arrays.
+	 */
+	__u64 fence_count;
+
+	/**
+	 * @handles_ptr: Pointer to an array of struct drm_i915_gem_exec_fence
+	 * of length @fence_count.
+	 */
+	__u64 handles_ptr;
+
+	/**
+	 * @values_ptr: Pointer to an array of u64 values of length
+	 * @fence_count.
+	 * Values must be 0 for a binary drm_syncobj. A Value of 0 for a
+	 * timeline drm_syncobj is invalid as it turns a drm_syncobj into a
+	 * binary one.
+	 */
+	__u64 values_ptr;
+};
+
+/**
+ * struct drm_i915_gem_execbuffer2 - Structure for DRM_I915_GEM_EXECBUFFER2
+ * ioctl.
+ */
+struct drm_i915_gem_execbuffer2 {
+	/** @buffers_ptr: Pointer to a list of gem_exec_object2 structs */
+	__u64 buffers_ptr;
+
+	/** @buffer_count: Number of elements in @buffers_ptr array */
+	__u32 buffer_count;
+
+	/**
+	 * @batch_start_offset: Offset in the batchbuffer to start execution
+	 * from.
+	 */
+	__u32 batch_start_offset;
+
+	/**
+	 * @batch_len: Length in bytes of the batch buffer, starting from the
+	 * @batch_start_offset. If 0, length is assumed to be the batch buffer
+	 * object size.
+	 */
+	__u32 batch_len;
+
+	/** @DR1: deprecated */
+	__u32 DR1;
+
+	/** @DR4: deprecated */
+	__u32 DR4;
+
+	/** @num_cliprects: See @cliprects_ptr */
+	__u32 num_cliprects;
+
+	/**
+	 * @cliprects_ptr: Kernel clipping was a DRI1 misfeature.
+	 *
+	 * It is invalid to use this field if I915_EXEC_FENCE_ARRAY or
+	 * I915_EXEC_USE_EXTENSIONS flags are not set.
+	 *
+	 * If I915_EXEC_FENCE_ARRAY is set, then this is a pointer to an array
+	 * of &drm_i915_gem_exec_fence and @num_cliprects is the length of the
+	 * array.
+	 *
+	 * If I915_EXEC_USE_EXTENSIONS is set, then this is a pointer to a
+	 * single &i915_user_extension and num_cliprects is 0.
+	 */
+	__u64 cliprects_ptr;
+
+	/** @flags: Execbuf flags */
+	__u64 flags;
+#define I915_EXEC_RING_MASK              (0x3f)
+#define I915_EXEC_DEFAULT                (0<<0)
+#define I915_EXEC_RENDER                 (1<<0)
+#define I915_EXEC_BSD                    (2<<0)
+#define I915_EXEC_BLT                    (3<<0)
+#define I915_EXEC_VEBOX                  (4<<0)
+
+/* Used for switching the constants addressing mode on gen4+ RENDER ring.
+ * Gen6+ only supports relative addressing to dynamic state (default) and
+ * absolute addressing.
+ *
+ * These flags are ignored for the BSD and BLT rings.
+ */
+#define I915_EXEC_CONSTANTS_MASK 	(3<<6)
+#define I915_EXEC_CONSTANTS_REL_GENERAL (0<<6) /* default */
+#define I915_EXEC_CONSTANTS_ABSOLUTE 	(1<<6)
+#define I915_EXEC_CONSTANTS_REL_SURFACE (2<<6) /* gen4/5 only */
+
+/** Resets the SO write offset registers for transform feedback on gen7. */
+#define I915_EXEC_GEN7_SOL_RESET	(1<<8)
+
+/** Request a privileged ("secure") batch buffer. Note only available for
+ * DRM_ROOT_ONLY | DRM_MASTER processes.
+ */
+#define I915_EXEC_SECURE		(1<<9)
+
+/** Inform the kernel that the batch is and will always be pinned. This
+ * negates the requirement for a workaround to be performed to avoid
+ * an incoherent CS (such as can be found on 830/845). If this flag is
+ * not passed, the kernel will endeavour to make sure the batch is
+ * coherent with the CS before execution. If this flag is passed,
+ * userspace assumes the responsibility for ensuring the same.
+ */
+#define I915_EXEC_IS_PINNED		(1<<10)
+
+/** Provide a hint to the kernel that the command stream and auxiliary
+ * state buffers already holds the correct presumed addresses and so the
+ * relocation process may be skipped if no buffers need to be moved in
+ * preparation for the execbuffer.
+ */
+#define I915_EXEC_NO_RELOC		(1<<11)
+
+/** Use the reloc.handle as an index into the exec object array rather
+ * than as the per-file handle.
+ */
+#define I915_EXEC_HANDLE_LUT		(1<<12)
+
+/** Used for switching BSD rings on the platforms with two BSD rings */
+#define I915_EXEC_BSD_SHIFT	 (13)
+#define I915_EXEC_BSD_MASK	 (3 << I915_EXEC_BSD_SHIFT)
+/* default ping-pong mode */
+#define I915_EXEC_BSD_DEFAULT	 (0 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING1	 (1 << I915_EXEC_BSD_SHIFT)
+#define I915_EXEC_BSD_RING2	 (2 << I915_EXEC_BSD_SHIFT)
+
+/** Tell the kernel that the batchbuffer is processed by
+ *  the resource streamer.
+ */
+#define I915_EXEC_RESOURCE_STREAMER     (1<<15)
+
+/* Setting I915_EXEC_FENCE_IN implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_IN		(1<<16)
+
+/* Setting I915_EXEC_FENCE_OUT causes the ioctl to return a sync_file fd
+ * in the upper_32_bits(rsvd2) upon success. Ownership of the fd is given
+ * to the caller, and it should be close() after use. (The fd is a regular
+ * file descriptor and will be cleaned up on process termination. It holds
+ * a reference to the request, but nothing else.)
+ *
+ * The sync_file fd can be combined with other sync_file and passed either
+ * to execbuf using I915_EXEC_FENCE_IN, to atomic KMS ioctls (so that a flip
+ * will only occur after this request completes), or to other devices.
+ *
+ * Using I915_EXEC_FENCE_OUT requires use of
+ * DRM_IOCTL_I915_GEM_EXECBUFFER2_WR ioctl so that the result is written
+ * back to userspace. Failure to do so will cause the out-fence to always
+ * be reported as zero, and the real fence fd to be leaked.
+ */
+#define I915_EXEC_FENCE_OUT		(1<<17)
+
+/*
+ * Traditionally the execbuf ioctl has only considered the final element in
+ * the execobject[] to be the executable batch. Often though, the client
+ * will known the batch object prior to construction and being able to place
+ * it into the execobject[] array first can simplify the relocation tracking.
+ * Setting I915_EXEC_BATCH_FIRST tells execbuf to use element 0 of the
+ * execobject[] as the * batch instead (the default is to use the last
+ * element).
+ */
+#define I915_EXEC_BATCH_FIRST		(1<<18)
+
+/* Setting I915_FENCE_ARRAY implies that num_cliprects and cliprects_ptr
+ * define an array of i915_gem_exec_fence structures which specify a set of
+ * dma fences to wait upon or signal.
+ */
+#define I915_EXEC_FENCE_ARRAY   (1<<19)
+
+/*
+ * Setting I915_EXEC_FENCE_SUBMIT implies that lower_32_bits(rsvd2) represent
+ * a sync_file fd to wait upon (in a nonblocking manner) prior to executing
+ * the batch.
+ *
+ * Returns -EINVAL if the sync_file fd cannot be found.
+ */
+#define I915_EXEC_FENCE_SUBMIT		(1 << 20)
+
+/*
+ * Setting I915_EXEC_USE_EXTENSIONS implies that
+ * drm_i915_gem_execbuffer2.cliprects_ptr is treated as a pointer to an linked
+ * list of i915_user_extension. Each i915_user_extension node is the base of a
+ * larger structure. The list of supported structures are listed in the
+ * drm_i915_gem_execbuffer_ext enum.
+ */
+#define I915_EXEC_USE_EXTENSIONS	(1 << 21)
+#define __I915_EXEC_UNKNOWN_FLAGS (-(I915_EXEC_USE_EXTENSIONS << 1))
+
+	/** @rsvd1: Context id */
+	__u64 rsvd1;
+
+	/**
+	 * @rsvd2: in and out sync_file file descriptors.
+	 *
+	 * When I915_EXEC_FENCE_IN or I915_EXEC_FENCE_SUBMIT flag is set, the
+	 * lower 32 bits of this field will have the in sync_file fd (input).
+	 *
+	 * When I915_EXEC_FENCE_OUT flag is set, the upper 32 bits of this
+	 * field will have the out sync_file fd (output).
+	 */
+	__u64 rsvd2;
+};
+
+#define I915_EXEC_CONTEXT_ID_MASK	(0xffffffff)
+#define i915_execbuffer2_set_context_id(eb2, context) \
+	(eb2).rsvd1 = context & I915_EXEC_CONTEXT_ID_MASK
+#define i915_execbuffer2_get_context_id(eb2) \
+	((eb2).rsvd1 & I915_EXEC_CONTEXT_ID_MASK)
+
+struct drm_i915_gem_pin {
+	/** Handle of the buffer to be pinned. */
+	__u32 handle;
+	__u32 pad;
+
+	/** alignment required within the aperture */
+	__u64 alignment;
+
+	/** Returned GTT offset of the buffer. */
+	__u64 offset;
+};
+
+struct drm_i915_gem_unpin {
+	/** Handle of the buffer to be unpinned. */
+	__u32 handle;
+	__u32 pad;
+};
+
+struct drm_i915_gem_busy {
+	/** Handle of the buffer to check for busy */
+	__u32 handle;
+
+	/** Return busy status
+	 *
+	 * A return of 0 implies that the object is idle (after
+	 * having flushed any pending activity), and a non-zero return that
+	 * the object is still in-flight on the GPU. (The GPU has not yet
+	 * signaled completion for all pending requests that reference the
+	 * object.) An object is guaranteed to become idle eventually (so
+	 * long as no new GPU commands are executed upon it). Due to the
+	 * asynchronous nature of the hardware, an object reported
+	 * as busy may become idle before the ioctl is completed.
+	 *
+	 * Furthermore, if the object is busy, which engine is busy is only
+	 * provided as a guide and only indirectly by reporting its class
+	 * (there may be more than one engine in each class). There are race
+	 * conditions which prevent the report of which engines are busy from
+	 * being always accurate.  However, the converse is not true. If the
+	 * object is idle, the result of the ioctl, that all engines are idle,
+	 * is accurate.
+	 *
+	 * The returned dword is split into two fields to indicate both
+	 * the engine classes on which the object is being read, and the
+	 * engine class on which it is currently being written (if any).
+	 *
+	 * The low word (bits 0:15) indicate if the object is being written
+	 * to by any engine (there can only be one, as the GEM implicit
+	 * synchronisation rules force writes to be serialised). Only the
+	 * engine class (offset by 1, I915_ENGINE_CLASS_RENDER is reported as
+	 * 1 not 0 etc) for the last write is reported.
+	 *
+	 * The high word (bits 16:31) are a bitmask of which engines classes
+	 * are currently reading from the object. Multiple engines may be
+	 * reading from the object simultaneously.
+	 *
+	 * The value of each engine class is the same as specified in the
+	 * I915_CONTEXT_PARAM_ENGINES context parameter and via perf, i.e.
+	 * I915_ENGINE_CLASS_RENDER, I915_ENGINE_CLASS_COPY, etc.
+	 * Some hardware may have parallel execution engines, e.g. multiple
+	 * media engines, which are mapped to the same class identifier and so
+	 * are not separately reported for busyness.
+	 *
+	 * Caveat emptor:
+	 * Only the boolean result of this query is reliable; that is whether
+	 * the object is idle or busy. The report of which engines are busy
+	 * should be only used as a heuristic.
+	 */
+	__u32 busy;
+};
+
+/**
+ * struct drm_i915_gem_caching - Set or get the caching for given object
+ * handle.
+ *
+ * Allow userspace to control the GTT caching bits for a given object when the
+ * object is later mapped through the ppGTT(or GGTT on older platforms lacking
+ * ppGTT support, or if the object is used for scanout). Note that this might
+ * require unbinding the object from the GTT first, if its current caching value
+ * doesn't match.
+ *
+ * Note that this all changes on discrete platforms, starting from DG1, the
+ * set/get caching is no longer supported, and is now rejected.  Instead the CPU
+ * caching attributes(WB vs WC) will become an immutable creation time property
+ * for the object, along with the GTT caching level. For now we don't expose any
+ * new uAPI for this, instead on DG1 this is all implicit, although this largely
+ * shouldn't matter since DG1 is coherent by default(without any way of
+ * controlling it).
+ *
+ * Implicit caching rules, starting from DG1:
+ *
+ *     - If any of the object placements (see &drm_i915_gem_create_ext_memory_regions)
+ *       contain I915_MEMORY_CLASS_DEVICE then the object will be allocated and
+ *       mapped as write-combined only.
+ *
+ *     - Everything else is always allocated and mapped as write-back, with the
+ *       guarantee that everything is also coherent with the GPU.
+ *
+ * Note that this is likely to change in the future again, where we might need
+ * more flexibility on future devices, so making this all explicit as part of a
+ * new &drm_i915_gem_create_ext extension is probable.
+ *
+ * Side note: Part of the reason for this is that changing the at-allocation-time CPU
+ * caching attributes for the pages might be required(and is expensive) if we
+ * need to then CPU map the pages later with different caching attributes. This
+ * inconsistent caching behaviour, while supported on x86, is not universally
+ * supported on other architectures. So for simplicity we opt for setting
+ * everything at creation time, whilst also making it immutable, on discrete
+ * platforms.
+ */
+struct drm_i915_gem_caching {
+	/**
+	 * @handle: Handle of the buffer to set/get the caching level.
+	 */
+	__u32 handle;
+
+	/**
+	 * @caching: The GTT caching level to apply or possible return value.
+	 *
+	 * The supported @caching values:
+	 *
+	 * I915_CACHING_NONE:
+	 *
+	 * GPU access is not coherent with CPU caches.  Default for machines
+	 * without an LLC. This means manual flushing might be needed, if we
+	 * want GPU access to be coherent.
+	 *
+	 * I915_CACHING_CACHED:
+	 *
+	 * GPU access is coherent with CPU caches and furthermore the data is
+	 * cached in last-level caches shared between CPU cores and the GPU GT.
+	 *
+	 * I915_CACHING_DISPLAY:
+	 *
+	 * Special GPU caching mode which is coherent with the scanout engines.
+	 * Transparently falls back to I915_CACHING_NONE on platforms where no
+	 * special cache mode (like write-through or gfdt flushing) is
+	 * available. The kernel automatically sets this mode when using a
+	 * buffer as a scanout target.  Userspace can manually set this mode to
+	 * avoid a costly stall and clflush in the hotpath of drawing the first
+	 * frame.
+	 */
+#define I915_CACHING_NONE		0
+#define I915_CACHING_CACHED		1
+#define I915_CACHING_DISPLAY		2
+	__u32 caching;
+};
+
+#define I915_TILING_NONE	0
+#define I915_TILING_X		1
+#define I915_TILING_Y		2
+/*
+ * Do not add new tiling types here.  The I915_TILING_* values are for
+ * de-tiling fence registers that no longer exist on modern platforms.  Although
+ * the hardware may support new types of tiling in general (e.g., Tile4), we
+ * do not need to add them to the uapi that is specific to now-defunct ioctls.
+ */
+#define I915_TILING_LAST	I915_TILING_Y
+
+#define I915_BIT_6_SWIZZLE_NONE		0
+#define I915_BIT_6_SWIZZLE_9		1
+#define I915_BIT_6_SWIZZLE_9_10		2
+#define I915_BIT_6_SWIZZLE_9_11		3
+#define I915_BIT_6_SWIZZLE_9_10_11	4
+/* Not seen by userland */
+#define I915_BIT_6_SWIZZLE_UNKNOWN	5
+/* Seen by userland. */
+#define I915_BIT_6_SWIZZLE_9_17		6
+#define I915_BIT_6_SWIZZLE_9_10_17	7
+
+struct drm_i915_gem_set_tiling {
+	/** Handle of the buffer to have its tiling state updated */
+	__u32 handle;
+
+	/**
+	 * Tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+	 * I915_TILING_Y).
+	 *
+	 * This value is to be set on request, and will be updated by the
+	 * kernel on successful return with the actual chosen tiling layout.
+	 *
+	 * The tiling mode may be demoted to I915_TILING_NONE when the system
+	 * has bit 6 swizzling that can't be managed correctly by GEM.
+	 *
+	 * Buffer contents become undefined when changing tiling_mode.
+	 */
+	__u32 tiling_mode;
+
+	/**
+	 * Stride in bytes for the object when in I915_TILING_X or
+	 * I915_TILING_Y.
+	 */
+	__u32 stride;
+
+	/**
+	 * Returned address bit 6 swizzling required for CPU access through
+	 * mmap mapping.
+	 */
+	__u32 swizzle_mode;
+};
+
+struct drm_i915_gem_get_tiling {
+	/** Handle of the buffer to get tiling state for. */
+	__u32 handle;
+
+	/**
+	 * Current tiling mode for the object (I915_TILING_NONE, I915_TILING_X,
+	 * I915_TILING_Y).
+	 */
+	__u32 tiling_mode;
+
+	/**
+	 * Returned address bit 6 swizzling required for CPU access through
+	 * mmap mapping.
+	 */
+	__u32 swizzle_mode;
+
+	/**
+	 * Returned address bit 6 swizzling required for CPU access through
+	 * mmap mapping whilst bound.
+	 */
+	__u32 phys_swizzle_mode;
+};
+
+struct drm_i915_gem_get_aperture {
+	/** Total size of the aperture used by i915_gem_execbuffer, in bytes */
+	__u64 aper_size;
+
+	/**
+	 * Available space in the aperture used by i915_gem_execbuffer, in
+	 * bytes
+	 */
+	__u64 aper_available_size;
+};
+
+struct drm_i915_get_pipe_from_crtc_id {
+	/** ID of CRTC being requested **/
+	__u32 crtc_id;
+
+	/** pipe of requested CRTC **/
+	__u32 pipe;
+};
+
+#define I915_MADV_WILLNEED 0
+#define I915_MADV_DONTNEED 1
+#define __I915_MADV_PURGED 2 /* internal state */
+
+struct drm_i915_gem_madvise {
+	/** Handle of the buffer to change the backing store advice */
+	__u32 handle;
+
+	/* Advice: either the buffer will be needed again in the near future,
+	 *         or won't be and could be discarded under memory pressure.
+	 */
+	__u32 madv;
+
+	/** Whether the backing store still exists. */
+	__u32 retained;
+};
+
+/* flags */
+#define I915_OVERLAY_TYPE_MASK 		0xff
+#define I915_OVERLAY_YUV_PLANAR 	0x01
+#define I915_OVERLAY_YUV_PACKED 	0x02
+#define I915_OVERLAY_RGB		0x03
+
+#define I915_OVERLAY_DEPTH_MASK		0xff00
+#define I915_OVERLAY_RGB24		0x1000
+#define I915_OVERLAY_RGB16		0x2000
+#define I915_OVERLAY_RGB15		0x3000
+#define I915_OVERLAY_YUV422		0x0100
+#define I915_OVERLAY_YUV411		0x0200
+#define I915_OVERLAY_YUV420		0x0300
+#define I915_OVERLAY_YUV410		0x0400
+
+#define I915_OVERLAY_SWAP_MASK		0xff0000
+#define I915_OVERLAY_NO_SWAP		0x000000
+#define I915_OVERLAY_UV_SWAP		0x010000
+#define I915_OVERLAY_Y_SWAP		0x020000
+#define I915_OVERLAY_Y_AND_UV_SWAP	0x030000
+
+#define I915_OVERLAY_FLAGS_MASK		0xff000000
+#define I915_OVERLAY_ENABLE		0x01000000
+
+struct drm_intel_overlay_put_image {
+	/* various flags and src format description */
+	__u32 flags;
+	/* source picture description */
+	__u32 bo_handle;
+	/* stride values and offsets are in bytes, buffer relative */
+	__u16 stride_Y; /* stride for packed formats */
+	__u16 stride_UV;
+	__u32 offset_Y; /* offset for packet formats */
+	__u32 offset_U;
+	__u32 offset_V;
+	/* in pixels */
+	__u16 src_width;
+	__u16 src_height;
+	/* to compensate the scaling factors for partially covered surfaces */
+	__u16 src_scan_width;
+	__u16 src_scan_height;
+	/* output crtc description */
+	__u32 crtc_id;
+	__u16 dst_x;
+	__u16 dst_y;
+	__u16 dst_width;
+	__u16 dst_height;
+};
+
+/* flags */
+#define I915_OVERLAY_UPDATE_ATTRS	(1<<0)
+#define I915_OVERLAY_UPDATE_GAMMA	(1<<1)
+#define I915_OVERLAY_DISABLE_DEST_COLORKEY	(1<<2)
+struct drm_intel_overlay_attrs {
+	__u32 flags;
+	__u32 color_key;
+	__s32 brightness;
+	__u32 contrast;
+	__u32 saturation;
+	__u32 gamma0;
+	__u32 gamma1;
+	__u32 gamma2;
+	__u32 gamma3;
+	__u32 gamma4;
+	__u32 gamma5;
+};
+
+/*
+ * Intel sprite handling
+ *
+ * Color keying works with a min/mask/max tuple.  Both source and destination
+ * color keying is allowed.
+ *
+ * Source keying:
+ * Sprite pixels within the min & max values, masked against the color channels
+ * specified in the mask field, will be transparent.  All other pixels will
+ * be displayed on top of the primary plane.  For RGB surfaces, only the min
+ * and mask fields will be used; ranged compares are not allowed.
+ *
+ * Destination keying:
+ * Primary plane pixels that match the min value, masked against the color
+ * channels specified in the mask field, will be replaced by corresponding
+ * pixels from the sprite plane.
+ *
+ * Note that source & destination keying are exclusive; only one can be
+ * active on a given plane.
+ */
+
+#define I915_SET_COLORKEY_NONE		(1<<0) /* Deprecated. Instead set
+						* flags==0 to disable colorkeying.
+						*/
+#define I915_SET_COLORKEY_DESTINATION	(1<<1)
+#define I915_SET_COLORKEY_SOURCE	(1<<2)
+struct drm_intel_sprite_colorkey {
+	__u32 plane_id;
+	__u32 min_value;
+	__u32 channel_mask;
+	__u32 max_value;
+	__u32 flags;
+};
+
+struct drm_i915_gem_wait {
+	/** Handle of BO we shall wait on */
+	__u32 bo_handle;
+	__u32 flags;
+	/** Number of nanoseconds to wait, Returns time remaining. */
+	__s64 timeout_ns;
+};
+
+struct drm_i915_gem_context_create {
+	__u32 ctx_id; /* output: id of new context*/
+	__u32 pad;
+};
+
+/**
+ * struct drm_i915_gem_context_create_ext - Structure for creating contexts.
+ */
+struct drm_i915_gem_context_create_ext {
+	/** @ctx_id: Id of the created context (output) */
+	__u32 ctx_id;
+
+	/**
+	 * @flags: Supported flags are:
+	 *
+	 * I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS:
+	 *
+	 * Extensions may be appended to this structure and driver must check
+	 * for those. See @extensions.
+	 *
+	 * I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE
+	 *
+	 * Created context will have single timeline.
+	 */
+	__u32 flags;
+#define I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS	(1u << 0)
+#define I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE	(1u << 1)
+#define I915_CONTEXT_CREATE_FLAGS_UNKNOWN \
+	(-(I915_CONTEXT_CREATE_FLAGS_SINGLE_TIMELINE << 1))
+
+	/**
+	 * @extensions: Zero-terminated chain of extensions.
+	 *
+	 * I915_CONTEXT_CREATE_EXT_SETPARAM:
+	 * Context parameter to set or query during context creation.
+	 * See struct drm_i915_gem_context_create_ext_setparam.
+	 *
+	 * I915_CONTEXT_CREATE_EXT_CLONE:
+	 * This extension has been removed. On the off chance someone somewhere
+	 * has attempted to use it, never re-use this extension number.
+	 */
+	__u64 extensions;
+#define I915_CONTEXT_CREATE_EXT_SETPARAM 0
+#define I915_CONTEXT_CREATE_EXT_CLONE 1
+};
+
+/**
+ * struct drm_i915_gem_context_param - Context parameter to set or query.
+ */
+struct drm_i915_gem_context_param {
+	/** @ctx_id: Context id */
+	__u32 ctx_id;
+
+	/** @size: Size of the parameter @value */
+	__u32 size;
+
+	/** @param: Parameter to set or query */
+	__u64 param;
+#define I915_CONTEXT_PARAM_BAN_PERIOD	0x1
+/* I915_CONTEXT_PARAM_NO_ZEROMAP has been removed.  On the off chance
+ * someone somewhere has attempted to use it, never re-use this context
+ * param number.
+ */
+#define I915_CONTEXT_PARAM_NO_ZEROMAP	0x2
+#define I915_CONTEXT_PARAM_GTT_SIZE	0x3
+#define I915_CONTEXT_PARAM_NO_ERROR_CAPTURE	0x4
+#define I915_CONTEXT_PARAM_BANNABLE	0x5
+#define I915_CONTEXT_PARAM_PRIORITY	0x6
+#define   I915_CONTEXT_MAX_USER_PRIORITY	1023 /* inclusive */
+#define   I915_CONTEXT_DEFAULT_PRIORITY		0
+#define   I915_CONTEXT_MIN_USER_PRIORITY	-1023 /* inclusive */
+	/*
+	 * When using the following param, value should be a pointer to
+	 * drm_i915_gem_context_param_sseu.
+	 */
+#define I915_CONTEXT_PARAM_SSEU		0x7
+
+/*
+ * Not all clients may want to attempt automatic recover of a context after
+ * a hang (for example, some clients may only submit very small incremental
+ * batches relying on known logical state of previous batches which will never
+ * recover correctly and each attempt will hang), and so would prefer that
+ * the context is forever banned instead.
+ *
+ * If set to false (0), after a reset, subsequent (and in flight) rendering
+ * from this context is discarded, and the client will need to create a new
+ * context to use instead.
+ *
+ * If set to true (1), the kernel will automatically attempt to recover the
+ * context by skipping the hanging batch and executing the next batch starting
+ * from the default context state (discarding the incomplete logical context
+ * state lost due to the reset).
+ *
+ * On creation, all new contexts are marked as recoverable.
+ */
+#define I915_CONTEXT_PARAM_RECOVERABLE	0x8
+
+	/*
+	 * The id of the associated virtual memory address space (ppGTT) of
+	 * this context. Can be retrieved and passed to another context
+	 * (on the same fd) for both to use the same ppGTT and so share
+	 * address layouts, and avoid reloading the page tables on context
+	 * switches between themselves.
+	 *
+	 * See DRM_I915_GEM_VM_CREATE and DRM_I915_GEM_VM_DESTROY.
+	 */
+#define I915_CONTEXT_PARAM_VM		0x9
+
+/*
+ * I915_CONTEXT_PARAM_ENGINES:
+ *
+ * Bind this context to operate on this subset of available engines. Henceforth,
+ * the I915_EXEC_RING selector for DRM_IOCTL_I915_GEM_EXECBUFFER2 operates as
+ * an index into this array of engines; I915_EXEC_DEFAULT selecting engine[0]
+ * and upwards. Slots 0...N are filled in using the specified (class, instance).
+ * Use
+ *	engine_class: I915_ENGINE_CLASS_INVALID,
+ *	engine_instance: I915_ENGINE_CLASS_INVALID_NONE
+ * to specify a gap in the array that can be filled in later, e.g. by a
+ * virtual engine used for load balancing.
+ *
+ * Setting the number of engines bound to the context to 0, by passing a zero
+ * sized argument, will revert back to default settings.
+ *
+ * See struct i915_context_param_engines.
+ *
+ * Extensions:
+ *   i915_context_engines_load_balance (I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE)
+ *   i915_context_engines_bond (I915_CONTEXT_ENGINES_EXT_BOND)
+ *   i915_context_engines_parallel_submit (I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT)
+ */
+#define I915_CONTEXT_PARAM_ENGINES	0xa
+
+/*
+ * I915_CONTEXT_PARAM_PERSISTENCE:
+ *
+ * Allow the context and active rendering to survive the process until
+ * completion. Persistence allows fire-and-forget clients to queue up a
+ * bunch of work, hand the output over to a display server and then quit.
+ * If the context is marked as not persistent, upon closing (either via
+ * an explicit DRM_I915_GEM_CONTEXT_DESTROY or implicitly from file closure
+ * or process termination), the context and any outstanding requests will be
+ * cancelled (and exported fences for cancelled requests marked as -EIO).
+ *
+ * By default, new contexts allow persistence.
+ */
+#define I915_CONTEXT_PARAM_PERSISTENCE	0xb
+
+/* This API has been removed.  On the off chance someone somewhere has
+ * attempted to use it, never re-use this context param number.
+ */
+#define I915_CONTEXT_PARAM_RINGSIZE	0xc
+
+/*
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT:
+ *
+ * Mark that the context makes use of protected content, which will result
+ * in the context being invalidated when the protected content session is.
+ * Given that the protected content session is killed on suspend, the device
+ * is kept awake for the lifetime of a protected context, so the user should
+ * make sure to dispose of them once done.
+ * This flag can only be set at context creation time and, when set to true,
+ * must be preceded by an explicit setting of I915_CONTEXT_PARAM_RECOVERABLE
+ * to false. This flag can't be set to true in conjunction with setting the
+ * I915_CONTEXT_PARAM_BANNABLE flag to false. Creation example:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_gem_context_create_ext_setparam p_protected = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_PROTECTED_CONTENT,
+ *			.value = 1,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext_setparam p_norecover = {
+ *		.base = {
+ *			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ *			.next_extension = to_user_pointer(&p_protected),
+ *		},
+ *		.param = {
+ *			.param = I915_CONTEXT_PARAM_RECOVERABLE,
+ *			.value = 0,
+ *		}
+ *	};
+ *	struct drm_i915_gem_context_create_ext create = {
+ *		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ *		.extensions = to_user_pointer(&p_norecover);
+ *	};
+ *
+ *	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * In addition to the normal failure cases, setting this flag during context
+ * creation can result in the following errors:
+ *
+ * -ENODEV: feature not available
+ * -EPERM: trying to mark a recoverable or not bannable context as protected
+ * -ENXIO: A dependency such as a component driver or firmware is not yet
+ *         loaded so user space may need to attempt again. Depending on the
+ *         device, this error may be reported if protected context creation is
+ *         attempted very early after kernel start because the internal timeout
+ *         waiting for such dependencies is not guaranteed to be larger than
+ *         required (numbers differ depending on system and kernel config):
+ *            - ADL/RPL: dependencies may take up to 3 seconds from kernel start
+ *                       while context creation internal timeout is 250 milisecs
+ *            - MTL: dependencies may take up to 8 seconds from kernel start
+ *                   while context creation internal timeout is 250 milisecs
+ *         NOTE: such dependencies happen once, so a subsequent call to create a
+ *         protected context after a prior successful call will not experience
+ *         such timeouts and will not return -ENXIO (unless the driver is reloaded,
+ *         or, depending on the device, resumes from a suspended state).
+ * -EIO: The firmware did not succeed in creating the protected context.
+ */
+#define I915_CONTEXT_PARAM_PROTECTED_CONTENT    0xd
+
+/*
+ * I915_CONTEXT_PARAM_LOW_LATENCY:
+ *
+ * Mark this context as a low latency workload which requires aggressive GT
+ * frequency scaling. Use I915_PARAM_HAS_CONTEXT_FREQ_HINT to check if the kernel
+ * supports this per context flag.
+ */
+#define I915_CONTEXT_PARAM_LOW_LATENCY		0xe
+
+/*
+ * I915_CONTEXT_PARAM_CONTEXT_IMAGE:
+ *
+ * Allows userspace to provide own context images.
+ *
+ * Note that this is a debug API not available on production kernel builds.
+ */
+#define I915_CONTEXT_PARAM_CONTEXT_IMAGE	0xf
+/* Must be kept compact -- no holes and well documented */
+
+	/** @value: Context parameter value to be set or queried */
+	__u64 value;
+};
+
+/*
+ * Context SSEU programming
+ *
+ * It may be necessary for either functional or performance reason to configure
+ * a context to run with a reduced number of SSEU (where SSEU stands for Slice/
+ * Sub-slice/EU).
+ *
+ * This is done by configuring SSEU configuration using the below
+ * @struct drm_i915_gem_context_param_sseu for every supported engine which
+ * userspace intends to use.
+ *
+ * Not all GPUs or engines support this functionality in which case an error
+ * code -ENODEV will be returned.
+ *
+ * Also, flexibility of possible SSEU configuration permutations varies between
+ * GPU generations and software imposed limitations. Requesting such a
+ * combination will return an error code of -EINVAL.
+ *
+ * NOTE: When perf/OA is active the context's SSEU configuration is ignored in
+ * favour of a single global setting.
+ */
+struct drm_i915_gem_context_param_sseu {
+	/*
+	 * Engine class & instance to be configured or queried.
+	 */
+	struct i915_engine_class_instance engine;
+
+	/*
+	 * Unknown flags must be cleared to zero.
+	 */
+	__u32 flags;
+#define I915_CONTEXT_SSEU_FLAG_ENGINE_INDEX (1u << 0)
+
+	/*
+	 * Mask of slices to enable for the context. Valid values are a subset
+	 * of the bitmask value returned for I915_PARAM_SLICE_MASK.
+	 */
+	__u64 slice_mask;
+
+	/*
+	 * Mask of subslices to enable for the context. Valid values are a
+	 * subset of the bitmask value return by I915_PARAM_SUBSLICE_MASK.
+	 */
+	__u64 subslice_mask;
+
+	/*
+	 * Minimum/Maximum number of EUs to enable per subslice for the
+	 * context. min_eus_per_subslice must be inferior or equal to
+	 * max_eus_per_subslice.
+	 */
+	__u16 min_eus_per_subslice;
+	__u16 max_eus_per_subslice;
+
+	/*
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 rsvd;
+};
+
+/**
+ * DOC: Virtual Engine uAPI
+ *
+ * Virtual engine is a concept where userspace is able to configure a set of
+ * physical engines, submit a batch buffer, and let the driver execute it on any
+ * engine from the set as it sees fit.
+ *
+ * This is primarily useful on parts which have multiple instances of a same
+ * class engine, like for example GT3+ Skylake parts with their two VCS engines.
+ *
+ * For instance userspace can enumerate all engines of a certain class using the
+ * previously described `Engine Discovery uAPI`_. After that userspace can
+ * create a GEM context with a placeholder slot for the virtual engine (using
+ * `I915_ENGINE_CLASS_INVALID` and `I915_ENGINE_CLASS_INVALID_NONE` for class
+ * and instance respectively) and finally using the
+ * `I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE` extension place a virtual engine in
+ * the same reserved slot.
+ *
+ * Example of creating a virtual engine and submitting a batch buffer to it:
+ *
+ * .. code-block:: C
+ *
+ * 	I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(virtual, 2) = {
+ * 		.base.name = I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE,
+ * 		.engine_index = 0, // Place this virtual engine into engine map slot 0
+ * 		.num_siblings = 2,
+ * 		.engines = { { I915_ENGINE_CLASS_VIDEO, 0 },
+ * 			     { I915_ENGINE_CLASS_VIDEO, 1 }, },
+ * 	};
+ * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 1) = {
+ * 		.engines = { { I915_ENGINE_CLASS_INVALID,
+ * 			       I915_ENGINE_CLASS_INVALID_NONE } },
+ * 		.extensions = to_user_pointer(&virtual), // Chains after load_balance extension
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
+ * 		.base = {
+ * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * 		},
+ * 		.param = {
+ * 			.param = I915_CONTEXT_PARAM_ENGINES,
+ * 			.value = to_user_pointer(&engines),
+ * 			.size = sizeof(engines),
+ * 		},
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext create = {
+ * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * 		.extensions = to_user_pointer(&p_engines);
+ * 	};
+ *
+ * 	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * 	// Now we have created a GEM context with its engine map containing a
+ * 	// single virtual engine. Submissions to this slot can go either to
+ * 	// vcs0 or vcs1, depending on the load balancing algorithm used inside
+ * 	// the driver. The load balancing is dynamic from one batch buffer to
+ * 	// another and transparent to userspace.
+ *
+ * 	...
+ * 	execbuf.rsvd1 = ctx_id;
+ * 	execbuf.flags = 0; // Submits to index 0 which is the virtual engine
+ * 	gem_execbuf(drm_fd, &execbuf);
+ */
+
+/*
+ * i915_context_engines_load_balance:
+ *
+ * Enable load balancing across this set of engines.
+ *
+ * Into the I915_EXEC_DEFAULT slot [0], a virtual engine is created that when
+ * used will proxy the execbuffer request onto one of the set of engines
+ * in such a way as to distribute the load evenly across the set.
+ *
+ * The set of engines must be compatible (e.g. the same HW class) as they
+ * will share the same logical GPU context and ring.
+ *
+ * To intermix rendering with the virtual engine and direct rendering onto
+ * the backing engines (bypassing the load balancing proxy), the context must
+ * be defined to use a single timeline for all engines.
+ */
+struct i915_context_engines_load_balance {
+	struct i915_user_extension base;
+
+	__u16 engine_index;
+	__u16 num_siblings;
+	__u32 flags; /* all undefined flags must be zero */
+
+	__u64 mbz64; /* reserved for future use; must be zero */
+
+	struct i915_engine_class_instance engines[];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_LOAD_BALANCE(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 num_siblings; \
+	__u32 flags; \
+	__u64 mbz64; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/*
+ * i915_context_engines_bond:
+ *
+ * Constructed bonded pairs for execution within a virtual engine.
+ *
+ * All engines are equal, but some are more equal than others. Given
+ * the distribution of resources in the HW, it may be preferable to run
+ * a request on a given subset of engines in parallel to a request on a
+ * specific engine. We enable this selection of engines within a virtual
+ * engine by specifying bonding pairs, for any given master engine we will
+ * only execute on one of the corresponding siblings within the virtual engine.
+ *
+ * To execute a request in parallel on the master engine and a sibling requires
+ * coordination with a I915_EXEC_FENCE_SUBMIT.
+ */
+struct i915_context_engines_bond {
+	struct i915_user_extension base;
+
+	struct i915_engine_class_instance master;
+
+	__u16 virtual_index; /* index of virtual engine in ctx->engines[] */
+	__u16 num_bonds;
+
+	__u64 flags; /* all undefined flags must be zero */
+	__u64 mbz64[4]; /* reserved for future use; must be zero */
+
+	struct i915_engine_class_instance engines[];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_ENGINES_BOND(name__, N__) struct { \
+	struct i915_user_extension base; \
+	struct i915_engine_class_instance master; \
+	__u16 virtual_index; \
+	__u16 num_bonds; \
+	__u64 flags; \
+	__u64 mbz64[4]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
+ * struct i915_context_engines_parallel_submit - Configure engine for
+ * parallel submission.
+ *
+ * Setup a slot in the context engine map to allow multiple BBs to be submitted
+ * in a single execbuf IOCTL. Those BBs will then be scheduled to run on the GPU
+ * in parallel. Multiple hardware contexts are created internally in the i915 to
+ * run these BBs. Once a slot is configured for N BBs only N BBs can be
+ * submitted in each execbuf IOCTL and this is implicit behavior e.g. The user
+ * doesn't tell the execbuf IOCTL there are N BBs, the execbuf IOCTL knows how
+ * many BBs there are based on the slot's configuration. The N BBs are the last
+ * N buffer objects or first N if I915_EXEC_BATCH_FIRST is set.
+ *
+ * The default placement behavior is to create implicit bonds between each
+ * context if each context maps to more than 1 physical engine (e.g. context is
+ * a virtual engine). Also we only allow contexts of same engine class and these
+ * contexts must be in logically contiguous order. Examples of the placement
+ * behavior are described below. Lastly, the default is to not allow BBs to be
+ * preempted mid-batch. Rather insert coordinated preemption points on all
+ * hardware contexts between each set of BBs. Flags could be added in the future
+ * to change both of these default behaviors.
+ *
+ * Returns -EINVAL if hardware context placement configuration is invalid or if
+ * the placement configuration isn't supported on the platform / submission
+ * interface.
+ * Returns -ENODEV if extension isn't supported on the platform / submission
+ * interface.
+ *
+ * .. code-block:: none
+ *
+ *	Examples syntax:
+ *	CS[X] = generic engine of same class, logical instance X
+ *	INVALID = I915_ENGINE_CLASS_INVALID, I915_ENGINE_CLASS_INVALID_NONE
+ *
+ *	Example 1 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=1,
+ *		     engines=CS[0],CS[1])
+ *
+ *	Results in the following valid placement:
+ *	CS[0], CS[1]
+ *
+ *	Example 2 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[2],CS[1],CS[3])
+ *
+ *	Results in the following valid placements:
+ *	CS[0], CS[1]
+ *	CS[2], CS[3]
+ *
+ *	This can be thought of as two virtual engines, each containing two
+ *	engines thereby making a 2D array. However, there are bonds tying the
+ *	entries together and placing restrictions on how they can be scheduled.
+ *	Specifically, the scheduler can choose only vertical columns from the 2D
+ *	array. That is, CS[0] is bonded to CS[1] and CS[2] to CS[3]. So if the
+ *	scheduler wants to submit to CS[0], it must also choose CS[1] and vice
+ *	versa. Same for CS[2] requires also using CS[3].
+ *	VE[0] = CS[0], CS[2]
+ *	VE[1] = CS[1], CS[3]
+ *
+ *	Example 3 pseudo code:
+ *	set_engines(INVALID)
+ *	set_parallel(engine_index=0, width=2, num_siblings=2,
+ *		     engines=CS[0],CS[1],CS[1],CS[3])
+ *
+ *	Results in the following valid and invalid placements:
+ *	CS[0], CS[1]
+ *	CS[1], CS[3] - Not logically contiguous, return -EINVAL
+ */
+struct i915_context_engines_parallel_submit {
+	/**
+	 * @base: base user extension.
+	 */
+	struct i915_user_extension base;
+
+	/**
+	 * @engine_index: slot for parallel engine
+	 */
+	__u16 engine_index;
+
+	/**
+	 * @width: number of contexts per parallel engine or in other words the
+	 * number of batches in each submission
+	 */
+	__u16 width;
+
+	/**
+	 * @num_siblings: number of siblings per context or in other words the
+	 * number of possible placements for each submission
+	 */
+	__u16 num_siblings;
+
+	/**
+	 * @mbz16: reserved for future use; must be zero
+	 */
+	__u16 mbz16;
+
+	/**
+	 * @flags: all undefined flags must be zero, currently not defined flags
+	 */
+	__u64 flags;
+
+	/**
+	 * @mbz64: reserved for future use; must be zero
+	 */
+	__u64 mbz64[3];
+
+	/**
+	 * @engines: 2-d array of engine instances to configure parallel engine
+	 *
+	 * length = width (i) * num_siblings (j)
+	 * index = j + i * num_siblings
+	 */
+	struct i915_engine_class_instance engines[];
+
+} __packed;
+
+#define I915_DEFINE_CONTEXT_ENGINES_PARALLEL_SUBMIT(name__, N__) struct { \
+	struct i915_user_extension base; \
+	__u16 engine_index; \
+	__u16 width; \
+	__u16 num_siblings; \
+	__u16 mbz16; \
+	__u64 flags; \
+	__u64 mbz64[3]; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+/**
+ * DOC: Context Engine Map uAPI
+ *
+ * Context engine map is a new way of addressing engines when submitting batch-
+ * buffers, replacing the existing way of using identifiers like `I915_EXEC_BLT`
+ * inside the flags field of `struct drm_i915_gem_execbuffer2`.
+ *
+ * To use it created GEM contexts need to be configured with a list of engines
+ * the user is intending to submit to. This is accomplished using the
+ * `I915_CONTEXT_PARAM_ENGINES` parameter and `struct
+ * i915_context_param_engines`.
+ *
+ * For such contexts the `I915_EXEC_RING_MASK` field becomes an index into the
+ * configured map.
+ *
+ * Example of creating such context and submitting against it:
+ *
+ * .. code-block:: C
+ *
+ * 	I915_DEFINE_CONTEXT_PARAM_ENGINES(engines, 2) = {
+ * 		.engines = { { I915_ENGINE_CLASS_RENDER, 0 },
+ * 			     { I915_ENGINE_CLASS_COPY, 0 } }
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext_setparam p_engines = {
+ * 		.base = {
+ * 			.name = I915_CONTEXT_CREATE_EXT_SETPARAM,
+ * 		},
+ * 		.param = {
+ * 			.param = I915_CONTEXT_PARAM_ENGINES,
+ * 			.value = to_user_pointer(&engines),
+ * 			.size = sizeof(engines),
+ * 		},
+ * 	};
+ * 	struct drm_i915_gem_context_create_ext create = {
+ * 		.flags = I915_CONTEXT_CREATE_FLAGS_USE_EXTENSIONS,
+ * 		.extensions = to_user_pointer(&p_engines);
+ * 	};
+ *
+ * 	ctx_id = gem_context_create_ext(drm_fd, &create);
+ *
+ * 	// We have now created a GEM context with two engines in the map:
+ * 	// Index 0 points to rcs0 while index 1 points to bcs0. Other engines
+ * 	// will not be accessible from this context.
+ *
+ * 	...
+ * 	execbuf.rsvd1 = ctx_id;
+ * 	execbuf.flags = 0; // Submits to index 0, which is rcs0 for this context
+ * 	gem_execbuf(drm_fd, &execbuf);
+ *
+ * 	...
+ * 	execbuf.rsvd1 = ctx_id;
+ * 	execbuf.flags = 1; // Submits to index 0, which is bcs0 for this context
+ * 	gem_execbuf(drm_fd, &execbuf);
+ */
+
+struct i915_context_param_engines {
+	__u64 extensions; /* linked chain of extension blocks, 0 terminates */
+#define I915_CONTEXT_ENGINES_EXT_LOAD_BALANCE 0 /* see i915_context_engines_load_balance */
+#define I915_CONTEXT_ENGINES_EXT_BOND 1 /* see i915_context_engines_bond */
+#define I915_CONTEXT_ENGINES_EXT_PARALLEL_SUBMIT 2 /* see i915_context_engines_parallel_submit */
+	struct i915_engine_class_instance engines[];
+} __attribute__((packed));
+
+#define I915_DEFINE_CONTEXT_PARAM_ENGINES(name__, N__) struct { \
+	__u64 extensions; \
+	struct i915_engine_class_instance engines[N__]; \
+} __attribute__((packed)) name__
+
+struct i915_gem_context_param_context_image {
+	/** @engine: Engine class & instance to be configured. */
+	struct i915_engine_class_instance engine;
+
+	/** @flags: One of the supported flags or zero. */
+	__u32 flags;
+#define I915_CONTEXT_IMAGE_FLAG_ENGINE_INDEX (1u << 0)
+
+	/** @size: Size of the image blob pointed to by @image. */
+	__u32 size;
+
+	/** @mbz: Must be zero. */
+	__u32 mbz;
+
+	/** @image: Userspace memory containing the context image. */
+	__u64 image;
+} __attribute__((packed));
+
+/**
+ * struct drm_i915_gem_context_create_ext_setparam - Context parameter
+ * to set or query during context creation.
+ */
+struct drm_i915_gem_context_create_ext_setparam {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+
+	/**
+	 * @param: Context parameter to set or query.
+	 * See struct drm_i915_gem_context_param.
+	 */
+	struct drm_i915_gem_context_param param;
+};
+
+struct drm_i915_gem_context_destroy {
+	__u32 ctx_id;
+	__u32 pad;
+};
+
+/**
+ * struct drm_i915_gem_vm_control - Structure to create or destroy VM.
+ *
+ * DRM_I915_GEM_VM_CREATE -
+ *
+ * Create a new virtual memory address space (ppGTT) for use within a context
+ * on the same file. Extensions can be provided to configure exactly how the
+ * address space is setup upon creation.
+ *
+ * The id of new VM (bound to the fd) for use with I915_CONTEXT_PARAM_VM is
+ * returned in the outparam @id.
+ *
+ * An extension chain maybe provided, starting with @extensions, and terminated
+ * by the @next_extension being 0. Currently, no extensions are defined.
+ *
+ * DRM_I915_GEM_VM_DESTROY -
+ *
+ * Destroys a previously created VM id, specified in @vm_id.
+ *
+ * No extensions or flags are allowed currently, and so must be zero.
+ */
+struct drm_i915_gem_vm_control {
+	/** @extensions: Zero-terminated chain of extensions. */
+	__u64 extensions;
+
+	/** @flags: reserved for future usage, currently MBZ */
+	__u32 flags;
+
+	/** @vm_id: Id of the VM created or to be destroyed */
+	__u32 vm_id;
+};
+
+struct drm_i915_reg_read {
+	/*
+	 * Register offset.
+	 * For 64bit wide registers where the upper 32bits don't immediately
+	 * follow the lower 32bits, the offset of the lower 32bits must
+	 * be specified
+	 */
+	__u64 offset;
+#define I915_REG_READ_8B_WA (1ul << 0)
+
+	__u64 val; /* Return value */
+};
+
+/* Known registers:
+ *
+ * Render engine timestamp - 0x2358 + 64bit - gen7+
+ * - Note this register returns an invalid value if using the default
+ *   single instruction 8byte read, in order to workaround that pass
+ *   flag I915_REG_READ_8B_WA in offset field.
+ *
+ */
+
+/*
+ * struct drm_i915_reset_stats - Return global reset and other context stats
+ *
+ * Driver keeps few stats for each contexts and also global reset count.
+ * This struct can be used to query those stats.
+ */
+struct drm_i915_reset_stats {
+	/** @ctx_id: ID of the requested context */
+	__u32 ctx_id;
+
+	/** @flags: MBZ */
+	__u32 flags;
+
+	/** @reset_count: All resets since boot/module reload, for all contexts */
+	__u32 reset_count;
+
+	/** @batch_active: Number of batches lost when active in GPU, for this context */
+	__u32 batch_active;
+
+	/** @batch_pending: Number of batches lost pending for execution, for this context */
+	__u32 batch_pending;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * struct drm_i915_gem_userptr - Create GEM object from user allocated memory.
+ *
+ * Userptr objects have several restrictions on what ioctls can be used with the
+ * object handle.
+ */
+struct drm_i915_gem_userptr {
+	/**
+	 * @user_ptr: The pointer to the allocated memory.
+	 *
+	 * Needs to be aligned to PAGE_SIZE.
+	 */
+	__u64 user_ptr;
+
+	/**
+	 * @user_size:
+	 *
+	 * The size in bytes for the allocated memory. This will also become the
+	 * object size.
+	 *
+	 * Needs to be aligned to PAGE_SIZE, and should be at least PAGE_SIZE,
+	 * or larger.
+	 */
+	__u64 user_size;
+
+	/**
+	 * @flags:
+	 *
+	 * Supported flags:
+	 *
+	 * I915_USERPTR_READ_ONLY:
+	 *
+	 * Mark the object as readonly, this also means GPU access can only be
+	 * readonly. This is only supported on HW which supports readonly access
+	 * through the GTT. If the HW can't support readonly access, an error is
+	 * returned.
+	 *
+	 * I915_USERPTR_PROBE:
+	 *
+	 * Probe the provided @user_ptr range and validate that the @user_ptr is
+	 * indeed pointing to normal memory and that the range is also valid.
+	 * For example if some garbage address is given to the kernel, then this
+	 * should complain.
+	 *
+	 * Returns -EFAULT if the probe failed.
+	 *
+	 * Note that this doesn't populate the backing pages, and also doesn't
+	 * guarantee that the object will remain valid when the object is
+	 * eventually used.
+	 *
+	 * The kernel supports this feature if I915_PARAM_HAS_USERPTR_PROBE
+	 * returns a non-zero value.
+	 *
+	 * I915_USERPTR_UNSYNCHRONIZED:
+	 *
+	 * NOT USED. Setting this flag will result in an error.
+	 */
+	__u32 flags;
+#define I915_USERPTR_READ_ONLY 0x1
+#define I915_USERPTR_PROBE 0x2
+#define I915_USERPTR_UNSYNCHRONIZED 0x80000000
+	/**
+	 * @handle: Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+};
+
+enum drm_i915_oa_format {
+	I915_OA_FORMAT_A13 = 1,	    /* HSW only */
+	I915_OA_FORMAT_A29,	    /* HSW only */
+	I915_OA_FORMAT_A13_B8_C8,   /* HSW only */
+	I915_OA_FORMAT_B4_C8,	    /* HSW only */
+	I915_OA_FORMAT_A45_B8_C8,   /* HSW only */
+	I915_OA_FORMAT_B4_C8_A16,   /* HSW only */
+	I915_OA_FORMAT_C4_B8,	    /* HSW+ */
+
+	/* Gen8+ */
+	I915_OA_FORMAT_A12,
+	I915_OA_FORMAT_A12_B8_C8,
+	I915_OA_FORMAT_A32u40_A4u32_B8_C8,
+
+	/* DG2 */
+	I915_OAR_FORMAT_A32u40_A4u32_B8_C8,
+	I915_OA_FORMAT_A24u40_A14u32_B8_C8,
+
+	/* MTL OAM */
+	I915_OAM_FORMAT_MPEC8u64_B8_C8,
+	I915_OAM_FORMAT_MPEC8u32_B8_C8,
+
+	I915_OA_FORMAT_MAX	    /* non-ABI */
+};
+
+enum drm_i915_perf_property_id {
+	/**
+	 * Open the stream for a specific context handle (as used with
+	 * execbuffer2). A stream opened for a specific context this way
+	 * won't typically require root privileges.
+	 *
+	 * This property is available in perf revision 1.
+	 */
+	DRM_I915_PERF_PROP_CTX_HANDLE = 1,
+
+	/**
+	 * A value of 1 requests the inclusion of raw OA unit reports as
+	 * part of stream samples.
+	 *
+	 * This property is available in perf revision 1.
+	 */
+	DRM_I915_PERF_PROP_SAMPLE_OA,
+
+	/**
+	 * The value specifies which set of OA unit metrics should be
+	 * configured, defining the contents of any OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
+	 */
+	DRM_I915_PERF_PROP_OA_METRICS_SET,
+
+	/**
+	 * The value specifies the size and layout of OA unit reports.
+	 *
+	 * This property is available in perf revision 1.
+	 */
+	DRM_I915_PERF_PROP_OA_FORMAT,
+
+	/**
+	 * Specifying this property implicitly requests periodic OA unit
+	 * sampling and (at least on Haswell) the sampling frequency is derived
+	 * from this exponent as follows:
+	 *
+	 *   80ns * 2^(period_exponent + 1)
+	 *
+	 * This property is available in perf revision 1.
+	 */
+	DRM_I915_PERF_PROP_OA_EXPONENT,
+
+	/**
+	 * Specifying this property is only valid when specify a context to
+	 * filter with DRM_I915_PERF_PROP_CTX_HANDLE. Specifying this property
+	 * will hold preemption of the particular context we want to gather
+	 * performance data about. The execbuf2 submissions must include a
+	 * drm_i915_gem_execbuffer_ext_perf parameter for this to apply.
+	 *
+	 * This property is available in perf revision 3.
+	 */
+	DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+
+	/**
+	 * Specifying this pins all contexts to the specified SSEU power
+	 * configuration for the duration of the recording.
+	 *
+	 * This parameter's value is a pointer to a struct
+	 * drm_i915_gem_context_param_sseu.
+	 *
+	 * This property is available in perf revision 4.
+	 */
+	DRM_I915_PERF_PROP_GLOBAL_SSEU,
+
+	/**
+	 * This optional parameter specifies the timer interval in nanoseconds
+	 * at which the i915 driver will check the OA buffer for available data.
+	 * Minimum allowed value is 100 microseconds. A default value is used by
+	 * the driver if this parameter is not specified. Note that larger timer
+	 * values will reduce cpu consumption during OA perf captures. However,
+	 * excessively large values would potentially result in OA buffer
+	 * overwrites as captures reach end of the OA buffer.
+	 *
+	 * This property is available in perf revision 5.
+	 */
+	DRM_I915_PERF_PROP_POLL_OA_PERIOD,
+
+	/**
+	 * Multiple engines may be mapped to the same OA unit. The OA unit is
+	 * identified by class:instance of any engine mapped to it.
+	 *
+	 * This parameter specifies the engine class and must be passed along
+	 * with DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_CLASS,
+
+	/**
+	 * This parameter specifies the engine instance and must be passed along
+	 * with DRM_I915_PERF_PROP_OA_ENGINE_CLASS.
+	 *
+	 * This property is available in perf revision 6.
+	 */
+	DRM_I915_PERF_PROP_OA_ENGINE_INSTANCE,
+
+	DRM_I915_PERF_PROP_MAX /* non-ABI */
+};
+
+struct drm_i915_perf_open_param {
+	__u32 flags;
+#define I915_PERF_FLAG_FD_CLOEXEC	(1<<0)
+#define I915_PERF_FLAG_FD_NONBLOCK	(1<<1)
+#define I915_PERF_FLAG_DISABLED		(1<<2)
+
+	/** The number of u64 (id, value) pairs */
+	__u32 num_properties;
+
+	/**
+	 * Pointer to array of u64 (id, value) pairs configuring the stream
+	 * to open.
+	 */
+	__u64 properties_ptr;
+};
+
+/*
+ * Enable data capture for a stream that was either opened in a disabled state
+ * via I915_PERF_FLAG_DISABLED or was later disabled via
+ * I915_PERF_IOCTL_DISABLE.
+ *
+ * It is intended to be cheaper to disable and enable a stream than it may be
+ * to close and re-open a stream with the same configuration.
+ *
+ * It's undefined whether any pending data for the stream will be lost.
+ *
+ * This ioctl is available in perf revision 1.
+ */
+#define I915_PERF_IOCTL_ENABLE	_IO('i', 0x0)
+
+/*
+ * Disable data capture for a stream.
+ *
+ * It is an error to try and read a stream that is disabled.
+ *
+ * This ioctl is available in perf revision 1.
+ */
+#define I915_PERF_IOCTL_DISABLE	_IO('i', 0x1)
+
+/*
+ * Change metrics_set captured by a stream.
+ *
+ * If the stream is bound to a specific context, the configuration change
+ * will performed inline with that context such that it takes effect before
+ * the next execbuf submission.
+ *
+ * Returns the previously bound metrics set id, or a negative error code.
+ *
+ * This ioctl is available in perf revision 2.
+ */
+#define I915_PERF_IOCTL_CONFIG	_IO('i', 0x2)
+
+/*
+ * Common to all i915 perf records
+ */
+struct drm_i915_perf_record_header {
+	__u32 type;
+	__u16 pad;
+	__u16 size;
+};
+
+enum drm_i915_perf_record_type {
+
+	/**
+	 * Samples are the work horse record type whose contents are extensible
+	 * and defined when opening an i915 perf stream based on the given
+	 * properties.
+	 *
+	 * Boolean properties following the naming convention
+	 * DRM_I915_PERF_SAMPLE_xyz_PROP request the inclusion of 'xyz' data in
+	 * every sample.
+	 *
+	 * The order of these sample properties given by userspace has no
+	 * affect on the ordering of data within a sample. The order is
+	 * documented here.
+	 *
+	 * struct {
+	 *     struct drm_i915_perf_record_header header;
+	 *
+	 *     { u32 oa_report[]; } && DRM_I915_PERF_PROP_SAMPLE_OA
+	 * };
+	 */
+	DRM_I915_PERF_RECORD_SAMPLE = 1,
+
+	/*
+	 * Indicates that one or more OA reports were not written by the
+	 * hardware. This can happen for example if an MI_REPORT_PERF_COUNT
+	 * command collides with periodic sampling - which would be more likely
+	 * at higher sampling frequencies.
+	 */
+	DRM_I915_PERF_RECORD_OA_REPORT_LOST = 2,
+
+	/**
+	 * An error occurred that resulted in all pending OA reports being lost.
+	 */
+	DRM_I915_PERF_RECORD_OA_BUFFER_LOST = 3,
+
+	DRM_I915_PERF_RECORD_MAX /* non-ABI */
+};
+
+/**
+ * struct drm_i915_perf_oa_config
+ *
+ * Structure to upload perf dynamic configuration into the kernel.
+ */
+struct drm_i915_perf_oa_config {
+	/**
+	 * @uuid:
+	 *
+	 * String formatted like "%\08x-%\04x-%\04x-%\04x-%\012x"
+	 */
+	char uuid[36];
+
+	/**
+	 * @n_mux_regs:
+	 *
+	 * Number of mux regs in &mux_regs_ptr.
+	 */
+	__u32 n_mux_regs;
+
+	/**
+	 * @n_boolean_regs:
+	 *
+	 * Number of boolean regs in &boolean_regs_ptr.
+	 */
+	__u32 n_boolean_regs;
+
+	/**
+	 * @n_flex_regs:
+	 *
+	 * Number of flex regs in &flex_regs_ptr.
+	 */
+	__u32 n_flex_regs;
+
+	/**
+	 * @mux_regs_ptr:
+	 *
+	 * Pointer to tuples of u32 values (register address, value) for mux
+	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
+	 * &n_mux_regs).
+	 */
+	__u64 mux_regs_ptr;
+
+	/**
+	 * @boolean_regs_ptr:
+	 *
+	 * Pointer to tuples of u32 values (register address, value) for mux
+	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
+	 * &n_boolean_regs).
+	 */
+	__u64 boolean_regs_ptr;
+
+	/**
+	 * @flex_regs_ptr:
+	 *
+	 * Pointer to tuples of u32 values (register address, value) for mux
+	 * registers.  Expected length of buffer is (2 * sizeof(u32) *
+	 * &n_flex_regs).
+	 */
+	__u64 flex_regs_ptr;
+};
+
+/**
+ * struct drm_i915_query_item - An individual query for the kernel to process.
+ *
+ * The behaviour is determined by the @query_id. Note that exactly what
+ * @data_ptr is also depends on the specific @query_id.
+ */
+struct drm_i915_query_item {
+	/**
+	 * @query_id:
+	 *
+	 * The id for this query.  Currently accepted query IDs are:
+	 *  - %DRM_I915_QUERY_TOPOLOGY_INFO (see struct drm_i915_query_topology_info)
+	 *  - %DRM_I915_QUERY_ENGINE_INFO (see struct drm_i915_engine_info)
+	 *  - %DRM_I915_QUERY_PERF_CONFIG (see struct drm_i915_query_perf_config)
+	 *  - %DRM_I915_QUERY_MEMORY_REGIONS (see struct drm_i915_query_memory_regions)
+	 *  - %DRM_I915_QUERY_HWCONFIG_BLOB (see `GuC HWCONFIG blob uAPI`)
+	 *  - %DRM_I915_QUERY_GEOMETRY_SUBSLICES (see struct drm_i915_query_topology_info)
+	 *  - %DRM_I915_QUERY_GUC_SUBMISSION_VERSION (see struct drm_i915_query_guc_submission_version)
+	 */
+	__u64 query_id;
+#define DRM_I915_QUERY_TOPOLOGY_INFO		1
+#define DRM_I915_QUERY_ENGINE_INFO		2
+#define DRM_I915_QUERY_PERF_CONFIG		3
+#define DRM_I915_QUERY_MEMORY_REGIONS		4
+#define DRM_I915_QUERY_HWCONFIG_BLOB		5
+#define DRM_I915_QUERY_GEOMETRY_SUBSLICES	6
+#define DRM_I915_QUERY_GUC_SUBMISSION_VERSION	7
+/* Must be kept compact -- no holes and well documented */
+
+	/**
+	 * @length:
+	 *
+	 * When set to zero by userspace, this is filled with the size of the
+	 * data to be written at the @data_ptr pointer. The kernel sets this
+	 * value to a negative value to signal an error on a particular query
+	 * item.
+	 */
+	__s32 length;
+
+	/**
+	 * @flags:
+	 *
+	 * When &query_id == %DRM_I915_QUERY_TOPOLOGY_INFO, must be 0.
+	 *
+	 * When &query_id == %DRM_I915_QUERY_PERF_CONFIG, must be one of the
+	 * following:
+	 *
+	 *	- %DRM_I915_QUERY_PERF_CONFIG_LIST
+	 *      - %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID
+	 *      - %DRM_I915_QUERY_PERF_CONFIG_FOR_UUID
+	 *
+	 * When &query_id == %DRM_I915_QUERY_GEOMETRY_SUBSLICES must contain
+	 * a struct i915_engine_class_instance that references a render engine.
+	 */
+	__u32 flags;
+#define DRM_I915_QUERY_PERF_CONFIG_LIST          1
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID 2
+#define DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID   3
+
+	/**
+	 * @data_ptr:
+	 *
+	 * Data will be written at the location pointed by @data_ptr when the
+	 * value of @length matches the length of the data to be written by the
+	 * kernel.
+	 */
+	__u64 data_ptr;
+};
+
+/**
+ * struct drm_i915_query - Supply an array of struct drm_i915_query_item for the
+ * kernel to fill out.
+ *
+ * Note that this is generally a two step process for each struct
+ * drm_i915_query_item in the array:
+ *
+ * 1. Call the DRM_IOCTL_I915_QUERY, giving it our array of struct
+ *    drm_i915_query_item, with &drm_i915_query_item.length set to zero. The
+ *    kernel will then fill in the size, in bytes, which tells userspace how
+ *    memory it needs to allocate for the blob(say for an array of properties).
+ *
+ * 2. Next we call DRM_IOCTL_I915_QUERY again, this time with the
+ *    &drm_i915_query_item.data_ptr equal to our newly allocated blob. Note that
+ *    the &drm_i915_query_item.length should still be the same as what the
+ *    kernel previously set. At this point the kernel can fill in the blob.
+ *
+ * Note that for some query items it can make sense for userspace to just pass
+ * in a buffer/blob equal to or larger than the required size. In this case only
+ * a single ioctl call is needed. For some smaller query items this can work
+ * quite well.
+ *
+ */
+struct drm_i915_query {
+	/** @num_items: The number of elements in the @items_ptr array */
+	__u32 num_items;
+
+	/**
+	 * @flags: Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/**
+	 * @items_ptr:
+	 *
+	 * Pointer to an array of struct drm_i915_query_item. The number of
+	 * array elements is @num_items.
+	 */
+	__u64 items_ptr;
+};
+
+/**
+ * struct drm_i915_query_topology_info
+ *
+ * Describes slice/subslice/EU information queried by
+ * %DRM_I915_QUERY_TOPOLOGY_INFO
+ */
+struct drm_i915_query_topology_info {
+	/**
+	 * @flags:
+	 *
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u16 flags;
+
+	/**
+	 * @max_slices:
+	 *
+	 * The number of bits used to express the slice mask.
+	 */
+	__u16 max_slices;
+
+	/**
+	 * @max_subslices:
+	 *
+	 * The number of bits used to express the subslice mask.
+	 */
+	__u16 max_subslices;
+
+	/**
+	 * @max_eus_per_subslice:
+	 *
+	 * The number of bits in the EU mask that correspond to a single
+	 * subslice's EUs.
+	 */
+	__u16 max_eus_per_subslice;
+
+	/**
+	 * @subslice_offset:
+	 *
+	 * Offset in data[] at which the subslice masks are stored.
+	 */
+	__u16 subslice_offset;
+
+	/**
+	 * @subslice_stride:
+	 *
+	 * Stride at which each of the subslice masks for each slice are
+	 * stored.
+	 */
+	__u16 subslice_stride;
+
+	/**
+	 * @eu_offset:
+	 *
+	 * Offset in data[] at which the EU masks are stored.
+	 */
+	__u16 eu_offset;
+
+	/**
+	 * @eu_stride:
+	 *
+	 * Stride at which each of the EU masks for each subslice are stored.
+	 */
+	__u16 eu_stride;
+
+	/**
+	 * @data:
+	 *
+	 * Contains 3 pieces of information :
+	 *
+	 * - The slice mask with one bit per slice telling whether a slice is
+	 *   available. The availability of slice X can be queried with the
+	 *   following formula :
+	 *
+	 *   .. code:: c
+	 *
+	 *      (data[X / 8] >> (X % 8)) & 1
+	 *
+	 *   Starting with Xe_HP platforms, Intel hardware no longer has
+	 *   traditional slices so i915 will always report a single slice
+	 *   (hardcoded slicemask = 0x1) which contains all of the platform's
+	 *   subslices.  I.e., the mask here does not reflect any of the newer
+	 *   hardware concepts such as "gslices" or "cslices" since userspace
+	 *   is capable of inferring those from the subslice mask.
+	 *
+	 * - The subslice mask for each slice with one bit per subslice telling
+	 *   whether a subslice is available.  Starting with Gen12 we use the
+	 *   term "subslice" to refer to what the hardware documentation
+	 *   describes as a "dual-subslices."  The availability of subslice Y
+	 *   in slice X can be queried with the following formula :
+	 *
+	 *   .. code:: c
+	 *
+	 *      (data[subslice_offset + X * subslice_stride + Y / 8] >> (Y % 8)) & 1
+	 *
+	 * - The EU mask for each subslice in each slice, with one bit per EU
+	 *   telling whether an EU is available. The availability of EU Z in
+	 *   subslice Y in slice X can be queried with the following formula :
+	 *
+	 *   .. code:: c
+	 *
+	 *      (data[eu_offset +
+	 *            (X * max_subslices + Y) * eu_stride +
+	 *            Z / 8
+	 *       ] >> (Z % 8)) & 1
+	 */
+	__u8 data[];
+};
+
+/**
+ * DOC: Engine Discovery uAPI
+ *
+ * Engine discovery uAPI is a way of enumerating physical engines present in a
+ * GPU associated with an open i915 DRM file descriptor. This supersedes the old
+ * way of using `DRM_IOCTL_I915_GETPARAM` and engine identifiers like
+ * `I915_PARAM_HAS_BLT`.
+ *
+ * The need for this interface came starting with Icelake and newer GPUs, which
+ * started to establish a pattern of having multiple engines of a same class,
+ * where not all instances were always completely functionally equivalent.
+ *
+ * Entry point for this uapi is `DRM_IOCTL_I915_QUERY` with the
+ * `DRM_I915_QUERY_ENGINE_INFO` as the queried item id.
+ *
+ * Example for getting the list of engines:
+ *
+ * .. code-block:: C
+ *
+ * 	struct drm_i915_query_engine_info *info;
+ * 	struct drm_i915_query_item item = {
+ * 		.query_id = DRM_I915_QUERY_ENGINE_INFO;
+ * 	};
+ * 	struct drm_i915_query query = {
+ * 		.num_items = 1,
+ * 		.items_ptr = (uintptr_t)&item,
+ * 	};
+ * 	int err, i;
+ *
+ * 	// First query the size of the blob we need, this needs to be large
+ * 	// enough to hold our array of engines. The kernel will fill out the
+ * 	// item.length for us, which is the number of bytes we need.
+ * 	//
+ *	// Alternatively a large buffer can be allocated straightaway enabling
+ * 	// querying in one pass, in which case item.length should contain the
+ * 	// length of the provided buffer.
+ * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * 	if (err) ...
+ *
+ * 	info = calloc(1, item.length);
+ * 	// Now that we allocated the required number of bytes, we call the ioctl
+ * 	// again, this time with the data_ptr pointing to our newly allocated
+ * 	// blob, which the kernel can then populate with info on all engines.
+ *	item.data_ptr = (uintptr_t)&info;
+ *
+ * 	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ * 	if (err) ...
+ *
+ * 	// We can now access each engine in the array
+ * 	for (i = 0; i < info->num_engines; i++) {
+ * 		struct drm_i915_engine_info einfo = info->engines[i];
+ * 		u16 class = einfo.engine.class;
+ * 		u16 instance = einfo.engine.instance;
+ * 		....
+ * 	}
+ *
+ * 	free(info);
+ *
+ * Each of the enumerated engines, apart from being defined by its class and
+ * instance (see `struct i915_engine_class_instance`), also can have flags and
+ * capabilities defined as documented in i915_drm.h.
+ *
+ * For instance video engines which support HEVC encoding will have the
+ * `I915_VIDEO_CLASS_CAPABILITY_HEVC` capability bit set.
+ *
+ * Engine discovery only fully comes to its own when combined with the new way
+ * of addressing engines when submitting batch buffers using contexts with
+ * engine maps configured.
+ */
+
+/**
+ * struct drm_i915_engine_info
+ *
+ * Describes one engine and its capabilities as known to the driver.
+ */
+struct drm_i915_engine_info {
+	/** @engine: Engine class and instance. */
+	struct i915_engine_class_instance engine;
+
+	/** @rsvd0: Reserved field. */
+	__u32 rsvd0;
+
+	/** @flags: Engine flags. */
+	__u64 flags;
+#define I915_ENGINE_INFO_HAS_LOGICAL_INSTANCE		(1 << 0)
+
+	/** @capabilities: Capabilities of this engine. */
+	__u64 capabilities;
+#define I915_VIDEO_CLASS_CAPABILITY_HEVC		(1 << 0)
+#define I915_VIDEO_AND_ENHANCE_CLASS_CAPABILITY_SFC	(1 << 1)
+
+	/** @logical_instance: Logical instance of engine */
+	__u16 logical_instance;
+
+	/** @rsvd1: Reserved fields. */
+	__u16 rsvd1[3];
+	/** @rsvd2: Reserved fields. */
+	__u64 rsvd2[3];
+};
+
+/**
+ * struct drm_i915_query_engine_info
+ *
+ * Engine info query enumerates all engines known to the driver by filling in
+ * an array of struct drm_i915_engine_info structures.
+ */
+struct drm_i915_query_engine_info {
+	/** @num_engines: Number of struct drm_i915_engine_info structs following. */
+	__u32 num_engines;
+
+	/** @rsvd: MBZ */
+	__u32 rsvd[3];
+
+	/** @engines: Marker for drm_i915_engine_info structures. */
+	struct drm_i915_engine_info engines[];
+};
+
+/**
+ * struct drm_i915_query_perf_config
+ *
+ * Data written by the kernel with query %DRM_I915_QUERY_PERF_CONFIG and
+ * %DRM_I915_QUERY_GEOMETRY_SUBSLICES.
+ */
+struct drm_i915_query_perf_config {
+	union {
+		/**
+		 * @n_configs:
+		 *
+		 * When &drm_i915_query_item.flags ==
+		 * %DRM_I915_QUERY_PERF_CONFIG_LIST, i915 sets this fields to
+		 * the number of configurations available.
+		 */
+		__u64 n_configs;
+
+		/**
+		 * @config:
+		 *
+		 * When &drm_i915_query_item.flags ==
+		 * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_ID, i915 will use the
+		 * value in this field as configuration identifier to decide
+		 * what data to write into config_ptr.
+		 */
+		__u64 config;
+
+		/**
+		 * @uuid:
+		 *
+		 * When &drm_i915_query_item.flags ==
+		 * %DRM_I915_QUERY_PERF_CONFIG_DATA_FOR_UUID, i915 will use the
+		 * value in this field as configuration identifier to decide
+		 * what data to write into config_ptr.
+		 *
+		 * String formatted like "%08x-%04x-%04x-%04x-%012x"
+		 */
+		char uuid[36];
+	};
+
+	/**
+	 * @flags:
+	 *
+	 * Unused for now. Must be cleared to zero.
+	 */
+	__u32 flags;
+
+	/**
+	 * @data:
+	 *
+	 * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_LIST,
+	 * i915 will write an array of __u64 of configuration identifiers.
+	 *
+	 * When &drm_i915_query_item.flags == %DRM_I915_QUERY_PERF_CONFIG_DATA,
+	 * i915 will write a struct drm_i915_perf_oa_config. If the following
+	 * fields of struct drm_i915_perf_oa_config are not set to 0, i915 will
+	 * write into the associated pointers the values of submitted when the
+	 * configuration was created :
+	 *
+	 *  - &drm_i915_perf_oa_config.n_mux_regs
+	 *  - &drm_i915_perf_oa_config.n_boolean_regs
+	 *  - &drm_i915_perf_oa_config.n_flex_regs
+	 */
+	__u8 data[];
+};
+
+/**
+ * enum drm_i915_gem_memory_class - Supported memory classes
+ */
+enum drm_i915_gem_memory_class {
+	/** @I915_MEMORY_CLASS_SYSTEM: System memory */
+	I915_MEMORY_CLASS_SYSTEM = 0,
+	/** @I915_MEMORY_CLASS_DEVICE: Device local-memory */
+	I915_MEMORY_CLASS_DEVICE,
+};
+
+/**
+ * struct drm_i915_gem_memory_class_instance - Identify particular memory region
+ */
+struct drm_i915_gem_memory_class_instance {
+	/** @memory_class: See enum drm_i915_gem_memory_class */
+	__u16 memory_class;
+
+	/** @memory_instance: Which instance */
+	__u16 memory_instance;
+};
+
+/**
+ * struct drm_i915_memory_region_info - Describes one region as known to the
+ * driver.
+ *
+ * Note this is using both struct drm_i915_query_item and struct drm_i915_query.
+ * For this new query we are adding the new query id DRM_I915_QUERY_MEMORY_REGIONS
+ * at &drm_i915_query_item.query_id.
+ */
+struct drm_i915_memory_region_info {
+	/** @region: The class:instance pair encoding */
+	struct drm_i915_gem_memory_class_instance region;
+
+	/** @rsvd0: MBZ */
+	__u32 rsvd0;
+
+	/**
+	 * @probed_size: Memory probed by the driver
+	 *
+	 * Note that it should not be possible to ever encounter a zero value
+	 * here, also note that no current region type will ever return -1 here.
+	 * Although for future region types, this might be a possibility. The
+	 * same applies to the other size fields.
+	 */
+	__u64 probed_size;
+
+	/**
+	 * @unallocated_size: Estimate of memory remaining
+	 *
+	 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable accounting.
+	 * Without this (or if this is an older kernel) the value here will
+	 * always equal the @probed_size. Note this is only currently tracked
+	 * for I915_MEMORY_CLASS_DEVICE regions (for other types the value here
+	 * will always equal the @probed_size).
+	 */
+	__u64 unallocated_size;
+
+	union {
+		/** @rsvd1: MBZ */
+		__u64 rsvd1[8];
+		struct {
+			/**
+			 * @probed_cpu_visible_size: Memory probed by the driver
+			 * that is CPU accessible.
+			 *
+			 * This will be always be <= @probed_size, and the
+			 * remainder (if there is any) will not be CPU
+			 * accessible.
+			 *
+			 * On systems without small BAR, the @probed_size will
+			 * always equal the @probed_cpu_visible_size, since all
+			 * of it will be CPU accessible.
+			 *
+			 * Note this is only tracked for
+			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
+			 * value here will always equal the @probed_size).
+			 *
+			 * Note that if the value returned here is zero, then
+			 * this must be an old kernel which lacks the relevant
+			 * small-bar uAPI support (including
+			 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS), but on
+			 * such systems we should never actually end up with a
+			 * small BAR configuration, assuming we are able to load
+			 * the kernel module. Hence it should be safe to treat
+			 * this the same as when @probed_cpu_visible_size ==
+			 * @probed_size.
+			 */
+			__u64 probed_cpu_visible_size;
+
+			/**
+			 * @unallocated_cpu_visible_size: Estimate of CPU
+			 * visible memory remaining.
+			 *
+			 * Note this is only tracked for
+			 * I915_MEMORY_CLASS_DEVICE regions (for other types the
+			 * value here will always equal the
+			 * @probed_cpu_visible_size).
+			 *
+			 * Requires CAP_PERFMON or CAP_SYS_ADMIN to get reliable
+			 * accounting.  Without this the value here will always
+			 * equal the @probed_cpu_visible_size. Note this is only
+			 * currently tracked for I915_MEMORY_CLASS_DEVICE
+			 * regions (for other types the value here will also
+			 * always equal the @probed_cpu_visible_size).
+			 *
+			 * If this is an older kernel the value here will be
+			 * zero, see also @probed_cpu_visible_size.
+			 */
+			__u64 unallocated_cpu_visible_size;
+		};
+	};
+};
+
+/**
+ * struct drm_i915_query_memory_regions
+ *
+ * The region info query enumerates all regions known to the driver by filling
+ * in an array of struct drm_i915_memory_region_info structures.
+ *
+ * Example for getting the list of supported regions:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_query_memory_regions *info;
+ *	struct drm_i915_query_item item = {
+ *		.query_id = DRM_I915_QUERY_MEMORY_REGIONS;
+ *	};
+ *	struct drm_i915_query query = {
+ *		.num_items = 1,
+ *		.items_ptr = (uintptr_t)&item,
+ *	};
+ *	int err, i;
+ *
+ *	// First query the size of the blob we need, this needs to be large
+ *	// enough to hold our array of regions. The kernel will fill out the
+ *	// item.length for us, which is the number of bytes we need.
+ *	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ *	if (err) ...
+ *
+ *	info = calloc(1, item.length);
+ *	// Now that we allocated the required number of bytes, we call the ioctl
+ *	// again, this time with the data_ptr pointing to our newly allocated
+ *	// blob, which the kernel can then populate with the all the region info.
+ *	item.data_ptr = (uintptr_t)&info,
+ *
+ *	err = ioctl(fd, DRM_IOCTL_I915_QUERY, &query);
+ *	if (err) ...
+ *
+ *	// We can now access each region in the array
+ *	for (i = 0; i < info->num_regions; i++) {
+ *		struct drm_i915_memory_region_info mr = info->regions[i];
+ *		u16 class = mr.region.class;
+ *		u16 instance = mr.region.instance;
+ *
+ *		....
+ *	}
+ *
+ *	free(info);
+ */
+struct drm_i915_query_memory_regions {
+	/** @num_regions: Number of supported regions */
+	__u32 num_regions;
+
+	/** @rsvd: MBZ */
+	__u32 rsvd[3];
+
+	/** @regions: Info about each supported region */
+	struct drm_i915_memory_region_info regions[];
+};
+
+/**
+ * struct drm_i915_query_guc_submission_version - query GuC submission interface version
+ */
+struct drm_i915_query_guc_submission_version {
+	/** @branch: Firmware branch version. */
+	__u32 branch;
+	/** @major: Firmware major version. */
+	__u32 major;
+	/** @minor: Firmware minor version. */
+	__u32 minor;
+	/** @patch: Firmware patch version. */
+	__u32 patch;
+};
+
+/**
+ * DOC: GuC HWCONFIG blob uAPI
+ *
+ * The GuC produces a blob with information about the current device.
+ * i915 reads this blob from GuC and makes it available via this uAPI.
+ *
+ * The format and meaning of the blob content are documented in the
+ * Programmer's Reference Manual.
+ */
+
+/**
+ * struct drm_i915_gem_create_ext - Existing gem_create behaviour, with added
+ * extension support using struct i915_user_extension.
+ *
+ * Note that new buffer flags should be added here, at least for the stuff that
+ * is immutable. Previously we would have two ioctls, one to create the object
+ * with gem_create, and another to apply various parameters, however this
+ * creates some ambiguity for the params which are considered immutable. Also in
+ * general we're phasing out the various SET/GET ioctls.
+ */
+struct drm_i915_gem_create_ext {
+	/**
+	 * @size: Requested size for the object.
+	 *
+	 * The (page-aligned) allocated size for the object will be returned.
+	 *
+	 * On platforms like DG2/ATS the kernel will always use 64K or larger
+	 * pages for I915_MEMORY_CLASS_DEVICE. The kernel also requires a
+	 * minimum of 64K GTT alignment for such objects.
+	 *
+	 * NOTE: Previously the ABI here required a minimum GTT alignment of 2M
+	 * on DG2/ATS, due to how the hardware implemented 64K GTT page support,
+	 * where we had the following complications:
+	 *
+	 *   1) The entire PDE (which covers a 2MB virtual address range), must
+	 *   contain only 64K PTEs, i.e mixing 4K and 64K PTEs in the same
+	 *   PDE is forbidden by the hardware.
+	 *
+	 *   2) We still need to support 4K PTEs for I915_MEMORY_CLASS_SYSTEM
+	 *   objects.
+	 *
+	 * However on actual production HW this was completely changed to now
+	 * allow setting a TLB hint at the PTE level (see PS64), which is a lot
+	 * more flexible than the above. With this the 2M restriction was
+	 * dropped where we now only require 64K.
+	 */
+	__u64 size;
+
+	/**
+	 * @handle: Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+
+	/**
+	 * @flags: Optional flags.
+	 *
+	 * Supported values:
+	 *
+	 * I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS - Signal to the kernel that
+	 * the object will need to be accessed via the CPU.
+	 *
+	 * Only valid when placing objects in I915_MEMORY_CLASS_DEVICE, and only
+	 * strictly required on configurations where some subset of the device
+	 * memory is directly visible/mappable through the CPU (which we also
+	 * call small BAR), like on some DG2+ systems. Note that this is quite
+	 * undesirable, but due to various factors like the client CPU, BIOS etc
+	 * it's something we can expect to see in the wild. See
+	 * &drm_i915_memory_region_info.probed_cpu_visible_size for how to
+	 * determine if this system applies.
+	 *
+	 * Note that one of the placements MUST be I915_MEMORY_CLASS_SYSTEM, to
+	 * ensure the kernel can always spill the allocation to system memory,
+	 * if the object can't be allocated in the mappable part of
+	 * I915_MEMORY_CLASS_DEVICE.
+	 *
+	 * Also note that since the kernel only supports flat-CCS on objects
+	 * that can *only* be placed in I915_MEMORY_CLASS_DEVICE, we therefore
+	 * don't support I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS together with
+	 * flat-CCS.
+	 *
+	 * Without this hint, the kernel will assume that non-mappable
+	 * I915_MEMORY_CLASS_DEVICE is preferred for this object. Note that the
+	 * kernel can still migrate the object to the mappable part, as a last
+	 * resort, if userspace ever CPU faults this object, but this might be
+	 * expensive, and so ideally should be avoided.
+	 *
+	 * On older kernels which lack the relevant small-bar uAPI support (see
+	 * also &drm_i915_memory_region_info.probed_cpu_visible_size),
+	 * usage of the flag will result in an error, but it should NEVER be
+	 * possible to end up with a small BAR configuration, assuming we can
+	 * also successfully load the i915 kernel module. In such cases the
+	 * entire I915_MEMORY_CLASS_DEVICE region will be CPU accessible, and as
+	 * such there are zero restrictions on where the object can be placed.
+	 */
+#define I915_GEM_CREATE_EXT_FLAG_NEEDS_CPU_ACCESS (1 << 0)
+	__u32 flags;
+
+	/**
+	 * @extensions: The chain of extensions to apply to this object.
+	 *
+	 * This will be useful in the future when we need to support several
+	 * different extensions, and we need to apply more than one when
+	 * creating the object. See struct i915_user_extension.
+	 *
+	 * If we don't supply any extensions then we get the same old gem_create
+	 * behaviour.
+	 *
+	 * For I915_GEM_CREATE_EXT_MEMORY_REGIONS usage see
+	 * struct drm_i915_gem_create_ext_memory_regions.
+	 *
+	 * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see
+	 * struct drm_i915_gem_create_ext_protected_content.
+	 *
+	 * For I915_GEM_CREATE_EXT_SET_PAT usage see
+	 * struct drm_i915_gem_create_ext_set_pat.
+	 */
+#define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0
+#define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1
+#define I915_GEM_CREATE_EXT_SET_PAT 2
+	__u64 extensions;
+};
+
+/**
+ * struct drm_i915_gem_create_ext_memory_regions - The
+ * I915_GEM_CREATE_EXT_MEMORY_REGIONS extension.
+ *
+ * Set the object with the desired set of placements/regions in priority
+ * order. Each entry must be unique and supported by the device.
+ *
+ * This is provided as an array of struct drm_i915_gem_memory_class_instance, or
+ * an equivalent layout of class:instance pair encodings. See struct
+ * drm_i915_query_memory_regions and DRM_I915_QUERY_MEMORY_REGIONS for how to
+ * query the supported regions for a device.
+ *
+ * As an example, on discrete devices, if we wish to set the placement as
+ * device local-memory we can do something like:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_i915_gem_memory_class_instance region_lmem = {
+ *              .memory_class = I915_MEMORY_CLASS_DEVICE,
+ *              .memory_instance = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext_memory_regions regions = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_MEMORY_REGIONS },
+ *              .regions = (uintptr_t)&region_lmem,
+ *              .num_regions = 1,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = 16 * PAGE_SIZE,
+ *              .extensions = (uintptr_t)&regions,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ *
+ * At which point we get the object handle in &drm_i915_gem_create_ext.handle,
+ * along with the final object size in &drm_i915_gem_create_ext.size, which
+ * should account for any rounding up, if required.
+ *
+ * Note that userspace has no means of knowing the current backing region
+ * for objects where @num_regions is larger than one. The kernel will only
+ * ensure that the priority order of the @regions array is honoured, either
+ * when initially placing the object, or when moving memory around due to
+ * memory pressure
+ *
+ * On Flat-CCS capable HW, compression is supported for the objects residing
+ * in I915_MEMORY_CLASS_DEVICE. When such objects (compressed) have other
+ * memory class in @regions and migrated (by i915, due to memory
+ * constraints) to the non I915_MEMORY_CLASS_DEVICE region, then i915 needs to
+ * decompress the content. But i915 doesn't have the required information to
+ * decompress the userspace compressed objects.
+ *
+ * So i915 supports Flat-CCS, on the objects which can reside only on
+ * I915_MEMORY_CLASS_DEVICE regions.
+ */
+struct drm_i915_gem_create_ext_memory_regions {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+
+	/** @pad: MBZ */
+	__u32 pad;
+	/** @num_regions: Number of elements in the @regions array. */
+	__u32 num_regions;
+	/**
+	 * @regions: The regions/placements array.
+	 *
+	 * An array of struct drm_i915_gem_memory_class_instance.
+	 */
+	__u64 regions;
+};
+
+/**
+ * struct drm_i915_gem_create_ext_protected_content - The
+ * I915_OBJECT_PARAM_PROTECTED_CONTENT extension.
+ *
+ * If this extension is provided, buffer contents are expected to be protected
+ * by PXP encryption and require decryption for scan out and processing. This
+ * is only possible on platforms that have PXP enabled, on all other scenarios
+ * using this extension will cause the ioctl to fail and return -ENODEV. The
+ * flags parameter is reserved for future expansion and must currently be set
+ * to zero.
+ *
+ * The buffer contents are considered invalid after a PXP session teardown.
+ *
+ * The encryption is guaranteed to be processed correctly only if the object
+ * is submitted with a context created using the
+ * I915_CONTEXT_PARAM_PROTECTED_CONTENT flag. This will also enable extra checks
+ * at submission time on the validity of the objects involved.
+ *
+ * Below is an example on how to create a protected object:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_protected_content protected_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_PROTECTED_CONTENT },
+ *              .flags = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&protected_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_protected_content {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/** @flags: reserved for future usage, currently MBZ */
+	__u32 flags;
+};
+
+/**
+ * struct drm_i915_gem_create_ext_set_pat - The
+ * I915_GEM_CREATE_EXT_SET_PAT extension.
+ *
+ * If this extension is provided, the specified caching policy (PAT index) is
+ * applied to the buffer object.
+ *
+ * Below is an example on how to create an object with specific caching policy:
+ *
+ * .. code-block:: C
+ *
+ *      struct drm_i915_gem_create_ext_set_pat set_pat_ext = {
+ *              .base = { .name = I915_GEM_CREATE_EXT_SET_PAT },
+ *              .pat_index = 0,
+ *      };
+ *      struct drm_i915_gem_create_ext create_ext = {
+ *              .size = PAGE_SIZE,
+ *              .extensions = (uintptr_t)&set_pat_ext,
+ *      };
+ *
+ *      int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext);
+ *      if (err) ...
+ */
+struct drm_i915_gem_create_ext_set_pat {
+	/** @base: Extension link. See struct i915_user_extension. */
+	struct i915_user_extension base;
+	/**
+	 * @pat_index: PAT index to be set
+	 * PAT index is a bit field in Page Table Entry to control caching
+	 * behaviors for GPU accesses. The definition of PAT index is
+	 * platform dependent and can be found in hardware specifications,
+	 */
+	__u32 pat_index;
+	/** @rsvd: reserved for future use */
+	__u32 rsvd;
+};
+
+/* ID of the protected content session managed by i915 when PXP is active */
+#define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_I915_DRM_H_ */
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
new file mode 100644
index 000000000..264505d54
--- /dev/null
+++ b/include/uapi/drm/ivpu_accel.h
@@ -0,0 +1,564 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2020-2025 Intel Corporation
+ */
+
+#ifndef __UAPI_IVPU_DRM_H__
+#define __UAPI_IVPU_DRM_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_IVPU_GET_PARAM		  0x00
+#define DRM_IVPU_SET_PARAM		  0x01
+#define DRM_IVPU_BO_CREATE		  0x02
+#define DRM_IVPU_BO_INFO		  0x03
+#define DRM_IVPU_SUBMIT			  0x05
+#define DRM_IVPU_BO_WAIT		  0x06
+#define DRM_IVPU_METRIC_STREAMER_START	  0x07
+#define DRM_IVPU_METRIC_STREAMER_STOP	  0x08
+#define DRM_IVPU_METRIC_STREAMER_GET_DATA 0x09
+#define DRM_IVPU_METRIC_STREAMER_GET_INFO 0x0a
+#define DRM_IVPU_CMDQ_CREATE              0x0b
+#define DRM_IVPU_CMDQ_DESTROY             0x0c
+#define DRM_IVPU_CMDQ_SUBMIT              0x0d
+#define DRM_IVPU_BO_CREATE_FROM_USERPTR	  0x0e
+
+#define DRM_IOCTL_IVPU_GET_PARAM                                               \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_GET_PARAM, struct drm_ivpu_param)
+
+#define DRM_IOCTL_IVPU_SET_PARAM                                               \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_IVPU_SET_PARAM, struct drm_ivpu_param)
+
+#define DRM_IOCTL_IVPU_BO_CREATE                                               \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_BO_CREATE, struct drm_ivpu_bo_create)
+
+#define DRM_IOCTL_IVPU_BO_INFO                                                 \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_BO_INFO, struct drm_ivpu_bo_info)
+
+#define DRM_IOCTL_IVPU_SUBMIT                                                  \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_IVPU_SUBMIT, struct drm_ivpu_submit)
+
+#define DRM_IOCTL_IVPU_BO_WAIT                                                 \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_BO_WAIT, struct drm_ivpu_bo_wait)
+
+#define DRM_IOCTL_IVPU_METRIC_STREAMER_START                                   \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_METRIC_STREAMER_START,            \
+		 struct drm_ivpu_metric_streamer_start)
+
+#define DRM_IOCTL_IVPU_METRIC_STREAMER_STOP                                    \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_IVPU_METRIC_STREAMER_STOP,              \
+		struct drm_ivpu_metric_streamer_stop)
+
+#define DRM_IOCTL_IVPU_METRIC_STREAMER_GET_DATA                                \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_METRIC_STREAMER_GET_DATA,         \
+		 struct drm_ivpu_metric_streamer_get_data)
+
+#define DRM_IOCTL_IVPU_METRIC_STREAMER_GET_INFO                                \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_METRIC_STREAMER_GET_INFO,         \
+		 struct drm_ivpu_metric_streamer_get_data)
+
+#define DRM_IOCTL_IVPU_CMDQ_CREATE                                             \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_CMDQ_CREATE, struct drm_ivpu_cmdq_create)
+
+#define DRM_IOCTL_IVPU_CMDQ_DESTROY                                            \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_IVPU_CMDQ_DESTROY, struct drm_ivpu_cmdq_destroy)
+
+#define DRM_IOCTL_IVPU_CMDQ_SUBMIT                                             \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_IVPU_CMDQ_SUBMIT, struct drm_ivpu_cmdq_submit)
+
+#define DRM_IOCTL_IVPU_BO_CREATE_FROM_USERPTR                        \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_IVPU_BO_CREATE_FROM_USERPTR, \
+		 struct drm_ivpu_bo_create_from_userptr)
+
+/**
+ * DOC: contexts
+ *
+ * VPU contexts have private virtual address space, job queues and priority.
+ * Each context is identified by an unique ID. Context is created on open().
+ */
+
+#define DRM_IVPU_PARAM_DEVICE_ID	    0
+#define DRM_IVPU_PARAM_DEVICE_REVISION	    1
+#define DRM_IVPU_PARAM_PLATFORM_TYPE	    2
+#define DRM_IVPU_PARAM_CORE_CLOCK_RATE	    3
+#define DRM_IVPU_PARAM_NUM_CONTEXTS	    4
+#define DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS 5
+#define DRM_IVPU_PARAM_CONTEXT_PRIORITY	    6 /* Deprecated */
+#define DRM_IVPU_PARAM_CONTEXT_ID	    7
+#define DRM_IVPU_PARAM_FW_API_VERSION	    8
+#define DRM_IVPU_PARAM_ENGINE_HEARTBEAT	    9
+#define DRM_IVPU_PARAM_UNIQUE_INFERENCE_ID  10
+#define DRM_IVPU_PARAM_TILE_CONFIG	    11
+#define DRM_IVPU_PARAM_SKU		    12
+#define DRM_IVPU_PARAM_CAPABILITIES	    13
+#define DRM_IVPU_PARAM_PREEMPT_BUFFER_SIZE  14
+
+#define DRM_IVPU_PLATFORM_TYPE_SILICON	    0
+
+/* Deprecated, use DRM_IVPU_JOB_PRIORITY */
+#define DRM_IVPU_CONTEXT_PRIORITY_IDLE	    0
+#define DRM_IVPU_CONTEXT_PRIORITY_NORMAL    1
+#define DRM_IVPU_CONTEXT_PRIORITY_FOCUS	    2
+#define DRM_IVPU_CONTEXT_PRIORITY_REALTIME  3
+
+#define DRM_IVPU_JOB_PRIORITY_DEFAULT  0
+#define DRM_IVPU_JOB_PRIORITY_IDLE     1
+#define DRM_IVPU_JOB_PRIORITY_NORMAL   2
+#define DRM_IVPU_JOB_PRIORITY_FOCUS    3
+#define DRM_IVPU_JOB_PRIORITY_REALTIME 4
+
+/**
+ * DRM_IVPU_CAP_METRIC_STREAMER
+ *
+ * Metric streamer support. Provides sampling of various hardware performance
+ * metrics like DMA bandwidth and cache miss/hits. Can be used for profiling.
+ */
+#define DRM_IVPU_CAP_METRIC_STREAMER	1
+/**
+ * DRM_IVPU_CAP_DMA_MEMORY_RANGE
+ *
+ * Driver has capability to allocate separate memory range
+ * accessible by hardware DMA.
+ */
+#define DRM_IVPU_CAP_DMA_MEMORY_RANGE	2
+/**
+ * DRM_IVPU_CAP_MANAGE_CMDQ
+ *
+ * Driver supports explicit command queue operations like command queue create,
+ * command queue destroy and submit job on specific command queue.
+ */
+#define DRM_IVPU_CAP_MANAGE_CMDQ       3
+/**
+ * DRM_IVPU_CAP_BO_CREATE_FROM_USERPTR
+ *
+ * Driver supports creating buffer objects from user space memory pointers.
+ * This allows creating GEM buffers from existing user memory regions.
+ */
+#define DRM_IVPU_CAP_BO_CREATE_FROM_USERPTR	4
+
+/**
+ * struct drm_ivpu_param - Get/Set VPU parameters
+ */
+struct drm_ivpu_param {
+	/**
+	 * @param:
+	 *
+	 * Supported params:
+	 *
+	 * %DRM_IVPU_PARAM_DEVICE_ID:
+	 * PCI Device ID of the VPU device (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_DEVICE_REVISION:
+	 * VPU device revision (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_PLATFORM_TYPE:
+	 * Returns %DRM_IVPU_PLATFORM_TYPE_SILICON on real hardware or device specific
+	 * platform type when executing on a simulator or emulator (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CORE_CLOCK_RATE:
+	 * Maximum frequency of the NPU data processing unit clock (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_NUM_CONTEXTS:
+	 * Maximum number of simultaneously existing contexts (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CONTEXT_BASE_ADDRESS:
+	 * Lowest VPU virtual address available in the current context (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CONTEXT_ID:
+	 * Current context ID, always greater than 0 (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_FW_API_VERSION:
+	 * Firmware API version array (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_ENGINE_HEARTBEAT:
+	 * Heartbeat value from an engine (read-only).
+	 * Engine ID (i.e. DRM_IVPU_ENGINE_COMPUTE) is given via index.
+	 *
+	 * %DRM_IVPU_PARAM_UNIQUE_INFERENCE_ID:
+	 * Device-unique inference ID (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_TILE_CONFIG:
+	 * VPU tile configuration  (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_SKU:
+	 * VPU SKU ID (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_CAPABILITIES:
+	 * Supported capabilities (read-only)
+	 *
+	 * %DRM_IVPU_PARAM_PREEMPT_BUFFER_SIZE:
+	 * Size of the preemption buffer (read-only)
+	 */
+	__u32 param;
+
+	/** @index: Index for params that have multiple instances */
+	__u32 index;
+
+	/** @value: Param value */
+	__u64 value;
+};
+
+#define DRM_IVPU_BO_SHAVE_MEM  0x00000001
+#define DRM_IVPU_BO_HIGH_MEM   DRM_IVPU_BO_SHAVE_MEM
+#define DRM_IVPU_BO_MAPPABLE   0x00000002
+#define DRM_IVPU_BO_DMA_MEM    0x00000004
+#define DRM_IVPU_BO_READ_ONLY  0x00000008
+
+#define DRM_IVPU_BO_CACHED     0x00000000
+#define DRM_IVPU_BO_UNCACHED   0x00010000
+#define DRM_IVPU_BO_WC	       0x00020000
+#define DRM_IVPU_BO_CACHE_MASK 0x00030000
+
+#define DRM_IVPU_BO_FLAGS \
+	(DRM_IVPU_BO_HIGH_MEM | \
+	 DRM_IVPU_BO_MAPPABLE | \
+	 DRM_IVPU_BO_DMA_MEM | \
+	 DRM_IVPU_BO_READ_ONLY | \
+	 DRM_IVPU_BO_CACHE_MASK)
+
+/**
+ * struct drm_ivpu_bo_create - Create BO backed by SHMEM
+ *
+ * Create GEM buffer object allocated in SHMEM memory.
+ */
+struct drm_ivpu_bo_create {
+	/** @size: The size in bytes of the allocated memory */
+	__u64 size;
+
+	/**
+	 * @flags:
+	 *
+	 * Supported flags:
+	 *
+	 * %DRM_IVPU_BO_HIGH_MEM:
+	 *
+	 * Allocate VPU address from >4GB range.
+	 * Buffer object with vpu address >4GB can be always accessed by the
+	 * VPU DMA engine, but some HW generation may not be able to access
+	 * this memory from then firmware running on the VPU management processor.
+	 * Suitable for input, output and some scratch buffers.
+	 *
+	 * %DRM_IVPU_BO_MAPPABLE:
+	 *
+	 * Buffer object can be mapped using mmap().
+	 *
+	 * %DRM_IVPU_BO_CACHED:
+	 *
+	 * Allocated BO will be cached on host side (WB) and snooped on the VPU side.
+	 * This is the default caching mode.
+	 *
+	 * %DRM_IVPU_BO_UNCACHED:
+	 *
+	 * Not supported. Use DRM_IVPU_BO_WC instead.
+	 *
+	 * %DRM_IVPU_BO_WC:
+	 *
+	 * Allocated BO will use write combining buffer for writes but reads will be
+	 * uncached.
+	 */
+	__u32 flags;
+
+	/** @handle: Returned GEM object handle */
+	__u32 handle;
+
+	/** @vpu_addr: Returned VPU virtual address */
+	__u64 vpu_addr;
+};
+
+/**
+ * struct drm_ivpu_bo_create_from_userptr - Create dma-buf from user pointer
+ *
+ * Create a GEM buffer object from a user pointer to a memory region.
+ */
+struct drm_ivpu_bo_create_from_userptr {
+	/** @user_ptr: User pointer to memory region (must be page aligned) */
+	__u64 user_ptr;
+
+	/** @size: Size of the memory region in bytes (must be page aligned) */
+	__u64 size;
+
+	/**
+	 * @flags:
+	 *
+	 * Supported flags:
+	 *
+	 * %DRM_IVPU_BO_HIGH_MEM:
+	 *
+	 * Allocate VPU address from >4GB range.
+	 *
+	 * %DRM_IVPU_BO_DMA_MEM:
+	 *
+	 * Allocate from DMA memory range accessible by hardware DMA.
+	 *
+	 * %DRM_IVPU_BO_READ_ONLY:
+	 *
+	 * Allocate as a read-only buffer object.
+	 */
+	__u32 flags;
+
+	/** @handle: Returned GEM object handle */
+	__u32 handle;
+
+	/** @vpu_addr: Returned VPU virtual address */
+	__u64 vpu_addr;
+};
+
+/**
+ * struct drm_ivpu_bo_info - Query buffer object info
+ */
+struct drm_ivpu_bo_info {
+	/** @handle: Handle of the queried BO */
+	__u32 handle;
+
+	/** @flags: Returned flags used to create the BO */
+	__u32 flags;
+
+	/** @vpu_addr: Returned VPU virtual address */
+	__u64 vpu_addr;
+
+	/**
+	 * @mmap_offset:
+	 *
+	 * Returned offset to be used in mmap(). 0 in case the BO is not mappable.
+	 */
+	__u64 mmap_offset;
+
+	/** @size: Returned GEM object size, aligned to PAGE_SIZE */
+	__u64 size;
+};
+
+/* drm_ivpu_submit engines */
+#define DRM_IVPU_ENGINE_COMPUTE 0
+#define DRM_IVPU_ENGINE_COPY    1 /* Deprecated */
+
+/**
+ * struct drm_ivpu_submit - Submit commands to the VPU
+ *
+ * Execute a single command buffer on a given VPU engine.
+ * Handles to all referenced buffer objects have to be provided in @buffers_ptr.
+ *
+ * User space may wait on job completion using %DRM_IVPU_BO_WAIT ioctl.
+ */
+struct drm_ivpu_submit {
+	/**
+	 * @buffers_ptr:
+	 *
+	 * A pointer to an u32 array of GEM handles of the BOs required for this job.
+	 * The number of elements in the array must be equal to the value given by @buffer_count.
+	 *
+	 * The first BO is the command buffer. The rest of array has to contain all
+	 * BOs referenced from the command buffer.
+	 */
+	__u64 buffers_ptr;
+
+	/** @buffer_count: Number of elements in the @buffers_ptr */
+	__u32 buffer_count;
+
+	/**
+	 * @engine: Select the engine this job should be executed on
+	 *
+	 * %DRM_IVPU_ENGINE_COMPUTE:
+	 *
+	 * Performs Deep Learning Neural Compute Inference Operations
+	 */
+	__u32 engine;
+
+	/** @flags: Reserved for future use - must be zero */
+	__u32 flags;
+
+	/**
+	 * @commands_offset:
+	 *
+	 * Offset inside the first buffer in @buffers_ptr containing commands
+	 * to be executed. The offset has to be 8-byte aligned.
+	 */
+	__u32 commands_offset;
+
+	/**
+	 * @priority:
+	 *
+	 * Priority to be set for related job command queue, can be one of the following:
+	 * %DRM_IVPU_JOB_PRIORITY_DEFAULT
+	 * %DRM_IVPU_JOB_PRIORITY_IDLE
+	 * %DRM_IVPU_JOB_PRIORITY_NORMAL
+	 * %DRM_IVPU_JOB_PRIORITY_FOCUS
+	 * %DRM_IVPU_JOB_PRIORITY_REALTIME
+	 */
+	__u32 priority;
+};
+
+/**
+ * struct drm_ivpu_cmdq_submit - Submit commands to the VPU using explicit command queue
+ *
+ * Execute a single command buffer on a given command queue.
+ * Handles to all referenced buffer objects have to be provided in @buffers_ptr.
+ *
+ * User space may wait on job completion using %DRM_IVPU_BO_WAIT ioctl.
+ */
+struct drm_ivpu_cmdq_submit {
+	/**
+	 * @buffers_ptr:
+	 *
+	 * A pointer to an u32 array of GEM handles of the BOs required for this job.
+	 * The number of elements in the array must be equal to the value given by @buffer_count.
+	 *
+	 * The first BO is the command buffer. The rest of array has to contain all
+	 * BOs referenced from the command buffer.
+	 */
+	__u64 buffers_ptr;
+
+	/** @buffer_count: Number of elements in the @buffers_ptr */
+	__u32 buffer_count;
+
+	/** @cmdq_id: ID for the command queue where job will be submitted */
+	__u32 cmdq_id;
+
+	/** @flags: Reserved for future use - must be zero */
+	__u32 flags;
+
+	/**
+	 * @commands_offset:
+	 *
+	 * Offset inside the first buffer in @buffers_ptr containing commands
+	 * to be executed. The offset has to be 8-byte aligned.
+	 */
+	__u32 commands_offset;
+	/**
+	 * @preempt_buffer_index:
+	 *
+	 * Index of the preemption buffer in the buffers_ptr array.
+	 */
+	__u32 preempt_buffer_index;
+	__u32 reserved;
+};
+
+/* drm_ivpu_bo_wait job status codes */
+#define DRM_IVPU_JOB_STATUS_SUCCESS 0
+#define DRM_IVPU_JOB_STATUS_ABORTED 256
+
+/**
+ * struct drm_ivpu_bo_wait - Wait for BO to become inactive
+ *
+ * Blocks until a given buffer object becomes inactive.
+ * With @timeout_ms set to 0 returns immediately.
+ */
+struct drm_ivpu_bo_wait {
+	/** @handle: Handle to the buffer object to be waited on */
+	__u32 handle;
+
+	/** @flags: Reserved for future use - must be zero */
+	__u32 flags;
+
+	/** @timeout_ns: Absolute timeout in nanoseconds (may be zero) */
+	__s64 timeout_ns;
+
+	/**
+	 * @job_status:
+	 *
+	 * Job status code which is updated after the job is completed.
+	 * &DRM_IVPU_JOB_STATUS_SUCCESS or device specific error otherwise.
+	 * Valid only if @handle points to a command buffer.
+	 */
+	__u32 job_status;
+
+	/** @pad: Padding - must be zero */
+	__u32 pad;
+};
+
+/**
+ * struct drm_ivpu_metric_streamer_start - Start collecting metric data
+ */
+struct drm_ivpu_metric_streamer_start {
+	/** @metric_group_mask: Indicates metric streamer instance */
+	__u64 metric_group_mask;
+	/** @sampling_period_ns: Sampling period in nanoseconds */
+	__u64 sampling_period_ns;
+	/**
+	 * @read_period_samples:
+	 *
+	 * Number of samples after which user space will try to read the data.
+	 * Reading the data after significantly longer period may cause data loss.
+	 */
+	__u32 read_period_samples;
+	/** @sample_size: Returned size of a single sample in bytes */
+	__u32 sample_size;
+	/** @max_data_size: Returned max @data_size from %DRM_IOCTL_IVPU_METRIC_STREAMER_GET_DATA */
+	__u32 max_data_size;
+};
+
+/**
+ * struct drm_ivpu_metric_streamer_get_data - Copy collected metric data
+ */
+struct drm_ivpu_metric_streamer_get_data {
+	/** @metric_group_mask: Indicates metric streamer instance */
+	__u64 metric_group_mask;
+	/** @buffer_ptr: A pointer to a destination for the copied data */
+	__u64 buffer_ptr;
+	/** @buffer_size: Size of the destination buffer */
+	__u64 buffer_size;
+	/**
+	 * @data_size: Returned size of copied metric data
+	 *
+	 * If the @buffer_size is zero, returns the amount of data ready to be copied.
+	 */
+	__u64 data_size;
+};
+
+/* Command queue flags */
+#define DRM_IVPU_CMDQ_FLAG_TURBO 0x00000001
+
+/**
+ * struct drm_ivpu_cmdq_create - Create command queue for job submission
+ */
+struct drm_ivpu_cmdq_create {
+	/** @cmdq_id: Returned ID of created command queue */
+	__u32 cmdq_id;
+	/**
+	 * @priority:
+	 *
+	 * Priority to be set for related job command queue, can be one of the following:
+	 * %DRM_IVPU_JOB_PRIORITY_DEFAULT
+	 * %DRM_IVPU_JOB_PRIORITY_IDLE
+	 * %DRM_IVPU_JOB_PRIORITY_NORMAL
+	 * %DRM_IVPU_JOB_PRIORITY_FOCUS
+	 * %DRM_IVPU_JOB_PRIORITY_REALTIME
+	 */
+	__u32 priority;
+	/**
+	 * @flags:
+	 *
+	 * Supported flags:
+	 *
+	 * %DRM_IVPU_CMDQ_FLAG_TURBO
+	 *
+	 * Enable low-latency mode for the command queue. The NPU will maximize performance
+	 * when executing jobs from such queue at the cost of increased power usage.
+	 */
+	__u32 flags;
+};
+
+/**
+ * struct drm_ivpu_cmdq_destroy - Destroy a command queue
+ */
+struct drm_ivpu_cmdq_destroy {
+	/** @cmdq_id: ID of command queue to destroy */
+	__u32 cmdq_id;
+};
+
+/**
+ * struct drm_ivpu_metric_streamer_stop - Stop collecting metric data
+ */
+struct drm_ivpu_metric_streamer_stop {
+	/** @metric_group_mask: Indicates metric streamer instance */
+	__u64 metric_group_mask;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __UAPI_IVPU_DRM_H__ */
diff --git a/include/uapi/drm/lima_drm.h b/include/uapi/drm/lima_drm.h
new file mode 100644
index 000000000..1ec58d652
--- /dev/null
+++ b/include/uapi/drm/lima_drm.h
@@ -0,0 +1,176 @@
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
+/* Copyright 2017-2018 Qiang Yu <yuq825@gmail.com> */
+
+#ifndef __LIMA_DRM_H__
+#define __LIMA_DRM_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+enum drm_lima_param_gpu_id {
+	DRM_LIMA_PARAM_GPU_ID_UNKNOWN,
+	DRM_LIMA_PARAM_GPU_ID_MALI400,
+	DRM_LIMA_PARAM_GPU_ID_MALI450,
+};
+
+enum drm_lima_param {
+	DRM_LIMA_PARAM_GPU_ID,
+	DRM_LIMA_PARAM_NUM_PP,
+	DRM_LIMA_PARAM_GP_VERSION,
+	DRM_LIMA_PARAM_PP_VERSION,
+};
+
+/**
+ * get various information of the GPU
+ */
+struct drm_lima_get_param {
+	__u32 param; /* in, value in enum drm_lima_param */
+	__u32 pad;   /* pad, must be zero */
+	__u64 value; /* out, parameter value */
+};
+
+/*
+ * heap buffer dynamically increase backup memory size when GP task fail
+ * due to lack of heap memory. size field of heap buffer is an up bound of
+ * the backup memory which can be set to a fairly large value.
+ */
+#define LIMA_BO_FLAG_HEAP  (1 << 0)
+
+/**
+ * create a buffer for used by GPU
+ */
+struct drm_lima_gem_create {
+	__u32 size;    /* in, buffer size */
+	__u32 flags;   /* in, buffer flags */
+	__u32 handle;  /* out, GEM buffer handle */
+	__u32 pad;     /* pad, must be zero */
+};
+
+/**
+ * get information of a buffer
+ */
+struct drm_lima_gem_info {
+	__u32 handle;  /* in, GEM buffer handle */
+	__u32 va;      /* out, virtual address mapped into GPU MMU */
+	__u64 offset;  /* out, used to mmap this buffer to CPU */
+};
+
+#define LIMA_SUBMIT_BO_READ   0x01
+#define LIMA_SUBMIT_BO_WRITE  0x02
+
+/* buffer information used by one task */
+struct drm_lima_gem_submit_bo {
+	__u32 handle;  /* in, GEM buffer handle */
+	__u32 flags;   /* in, buffer read/write by GPU */
+};
+
+#define LIMA_GP_FRAME_REG_NUM 6
+
+/* frame used to setup GP for each task */
+struct drm_lima_gp_frame {
+	__u32 frame[LIMA_GP_FRAME_REG_NUM];
+};
+
+#define LIMA_PP_FRAME_REG_NUM 23
+#define LIMA_PP_WB_REG_NUM 12
+
+/* frame used to setup mali400 GPU PP for each task */
+struct drm_lima_m400_pp_frame {
+	__u32 frame[LIMA_PP_FRAME_REG_NUM];
+	__u32 num_pp;
+	__u32 wb[3 * LIMA_PP_WB_REG_NUM];
+	__u32 plbu_array_address[4];
+	__u32 fragment_stack_address[4];
+};
+
+/* frame used to setup mali450 GPU PP for each task */
+struct drm_lima_m450_pp_frame {
+	__u32 frame[LIMA_PP_FRAME_REG_NUM];
+	__u32 num_pp;
+	__u32 wb[3 * LIMA_PP_WB_REG_NUM];
+	__u32 use_dlbu;
+	__u32 _pad;
+	union {
+		__u32 plbu_array_address[8];
+		__u32 dlbu_regs[4];
+	};
+	__u32 fragment_stack_address[8];
+};
+
+#define LIMA_PIPE_GP  0x00
+#define LIMA_PIPE_PP  0x01
+
+#define LIMA_SUBMIT_FLAG_EXPLICIT_FENCE (1 << 0)
+
+/**
+ * submit a task to GPU
+ *
+ * User can always merge multi sync_file and drm_syncobj
+ * into one drm_syncobj as in_sync[0], but we reserve
+ * in_sync[1] for another task's out_sync to avoid the
+ * export/import/merge pass when explicit sync.
+ */
+struct drm_lima_gem_submit {
+	__u32 ctx;         /* in, context handle task is submitted to */
+	__u32 pipe;        /* in, which pipe to use, GP/PP */
+	__u32 nr_bos;      /* in, array length of bos field */
+	__u32 frame_size;  /* in, size of frame field */
+	__u64 bos;         /* in, array of drm_lima_gem_submit_bo */
+	__u64 frame;       /* in, GP/PP frame */
+	__u32 flags;       /* in, submit flags */
+	__u32 out_sync;    /* in, drm_syncobj handle used to wait task finish after submission */
+	__u32 in_sync[2];  /* in, drm_syncobj handle used to wait before start this task */
+};
+
+#define LIMA_GEM_WAIT_READ   0x01
+#define LIMA_GEM_WAIT_WRITE  0x02
+
+/**
+ * wait pending GPU task finish of a buffer
+ */
+struct drm_lima_gem_wait {
+	__u32 handle;      /* in, GEM buffer handle */
+	__u32 op;          /* in, CPU want to read/write this buffer */
+	__s64 timeout_ns;  /* in, wait timeout in absulute time */
+};
+
+/**
+ * create a context
+ */
+struct drm_lima_ctx_create {
+	__u32 id;          /* out, context handle */
+	__u32 _pad;        /* pad, must be zero */
+};
+
+/**
+ * free a context
+ */
+struct drm_lima_ctx_free {
+	__u32 id;          /* in, context handle */
+	__u32 _pad;        /* pad, must be zero */
+};
+
+#define DRM_LIMA_GET_PARAM   0x00
+#define DRM_LIMA_GEM_CREATE  0x01
+#define DRM_LIMA_GEM_INFO    0x02
+#define DRM_LIMA_GEM_SUBMIT  0x03
+#define DRM_LIMA_GEM_WAIT    0x04
+#define DRM_LIMA_CTX_CREATE  0x05
+#define DRM_LIMA_CTX_FREE    0x06
+
+#define DRM_IOCTL_LIMA_GET_PARAM DRM_IOWR(DRM_COMMAND_BASE + DRM_LIMA_GET_PARAM, struct drm_lima_get_param)
+#define DRM_IOCTL_LIMA_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_LIMA_GEM_CREATE, struct drm_lima_gem_create)
+#define DRM_IOCTL_LIMA_GEM_INFO DRM_IOWR(DRM_COMMAND_BASE + DRM_LIMA_GEM_INFO, struct drm_lima_gem_info)
+#define DRM_IOCTL_LIMA_GEM_SUBMIT DRM_IOW(DRM_COMMAND_BASE + DRM_LIMA_GEM_SUBMIT, struct drm_lima_gem_submit)
+#define DRM_IOCTL_LIMA_GEM_WAIT DRM_IOW(DRM_COMMAND_BASE + DRM_LIMA_GEM_WAIT, struct drm_lima_gem_wait)
+#define DRM_IOCTL_LIMA_CTX_CREATE DRM_IOR(DRM_COMMAND_BASE + DRM_LIMA_CTX_CREATE, struct drm_lima_ctx_create)
+#define DRM_IOCTL_LIMA_CTX_FREE DRM_IOW(DRM_COMMAND_BASE + DRM_LIMA_CTX_FREE, struct drm_lima_ctx_free)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __LIMA_DRM_H__ */
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
new file mode 100644
index 000000000..3d363f12f
--- /dev/null
+++ b/include/uapi/drm/msm_drm.h
@@ -0,0 +1,577 @@
+/*
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __MSM_DRM_H__
+#define __MSM_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:
+ *  1) Do not use pointers, use __u64 instead for 32 bit / 64 bit
+ *     user/kernel compatibility
+ *  2) Keep fields aligned to their size
+ *  3) Because of how drm_ioctl() works, we can add new fields at
+ *     the end of an ioctl if some care is taken: drm_ioctl() will
+ *     zero out the new fields at the tail of the ioctl, so a zero
+ *     value should have a backwards compatible meaning.  And for
+ *     output params, userspace won't see the newly added output
+ *     fields.. so that has to be somehow ok.
+ */
+
+#define MSM_PIPE_NONE        0x00
+#define MSM_PIPE_2D0         0x01
+#define MSM_PIPE_2D1         0x02
+#define MSM_PIPE_3D0         0x10
+
+/* The pipe-id just uses the lower bits, so can be OR'd with flags in
+ * the upper 16 bits (which could be extended further, if needed, maybe
+ * we extend/overload the pipe-id some day to deal with multiple rings,
+ * but even then I don't think we need the full lower 16 bits).
+ */
+#define MSM_PIPE_ID_MASK     0xffff
+#define MSM_PIPE_ID(x)       ((x) & MSM_PIPE_ID_MASK)
+#define MSM_PIPE_FLAGS(x)    ((x) & ~MSM_PIPE_ID_MASK)
+
+/* timeouts are specified in clock-monotonic absolute times (to simplify
+ * restarting interrupted ioctls).  The following struct is logically the
+ * same as 'struct timespec' but 32/64b ABI safe.
+ */
+struct drm_msm_timespec {
+	__s64 tv_sec;          /* seconds */
+	__s64 tv_nsec;         /* nanoseconds */
+};
+
+/* Below "RO" indicates a read-only param, "WO" indicates write-only, and
+ * "RW" indicates a param that can be both read (GET_PARAM) and written
+ * (SET_PARAM)
+ */
+#define MSM_PARAM_GPU_ID     0x01  /* RO */
+#define MSM_PARAM_GMEM_SIZE  0x02  /* RO */
+#define MSM_PARAM_CHIP_ID    0x03  /* RO */
+#define MSM_PARAM_MAX_FREQ   0x04  /* RO */
+#define MSM_PARAM_TIMESTAMP  0x05  /* RO */
+#define MSM_PARAM_GMEM_BASE  0x06  /* RO */
+#define MSM_PARAM_PRIORITIES 0x07  /* RO: The # of priority levels */
+#define MSM_PARAM_PP_PGTABLE 0x08  /* RO: Deprecated, always returns zero */
+#define MSM_PARAM_FAULTS     0x09  /* RO */
+#define MSM_PARAM_SUSPENDS   0x0a  /* RO */
+#define MSM_PARAM_SYSPROF    0x0b  /* WO: 1 preserves perfcntrs, 2 also disables suspend */
+#define MSM_PARAM_COMM       0x0c  /* WO: override for task->comm */
+#define MSM_PARAM_CMDLINE    0x0d  /* WO: override for task cmdline */
+#define MSM_PARAM_VA_START   0x0e  /* RO: start of valid GPU iova range */
+#define MSM_PARAM_VA_SIZE    0x0f  /* RO: size of valid GPU iova range (bytes) */
+#define MSM_PARAM_HIGHEST_BANK_BIT 0x10 /* RO */
+#define MSM_PARAM_RAYTRACING 0x11 /* RO */
+#define MSM_PARAM_UBWC_SWIZZLE 0x12 /* RO */
+#define MSM_PARAM_MACROTILE_MODE 0x13 /* RO */
+#define MSM_PARAM_UCHE_TRAP_BASE 0x14 /* RO */
+/* PRR (Partially Resident Region) is required for sparse residency: */
+#define MSM_PARAM_HAS_PRR    0x15  /* RO */
+/* MSM_PARAM_EN_VM_BIND is set to 1 to enable VM_BIND ops.
+ *
+ * With VM_BIND enabled, userspace is required to allocate iova and use the
+ * VM_BIND ops for map/unmap ioctls.  MSM_INFO_SET_IOVA and MSM_INFO_GET_IOVA
+ * will be rejected.  (The latter does not have a sensible meaning when a BO
+ * can have multiple and/or partial mappings.)
+ *
+ * With VM_BIND enabled, userspace does not include a submit_bo table in the
+ * SUBMIT ioctl (this will be rejected), the resident set is determined by
+ * the the VM_BIND ops.
+ *
+ * Enabling VM_BIND will fail on devices which do not have per-process pgtables.
+ * And it is not allowed to disable VM_BIND once it has been enabled.
+ *
+ * Enabling VM_BIND should be done (attempted) prior to allocating any BOs or
+ * submitqueues of type MSM_SUBMITQUEUE_VM_BIND.
+ *
+ * Relatedly, when VM_BIND mode is enabled, the kernel will not try to recover
+ * from GPU faults or failed async VM_BIND ops, in particular because it is
+ * difficult to communicate to userspace which op failed so that userspace
+ * could rewind and try again.  When the VM is marked unusable, the SUBMIT
+ * ioctl will throw -EPIPE.
+ */
+#define MSM_PARAM_EN_VM_BIND 0x16  /* WO, once */
+#define MSM_PARAM_AQE	     0x17  /* RO */
+
+/* For backwards compat.  The original support for preemption was based on
+ * a single ring per priority level so # of priority levels equals the #
+ * of rings.  With drm/scheduler providing additional levels of priority,
+ * the number of priorities is greater than the # of rings.  The param is
+ * renamed to better reflect this.
+ */
+#define MSM_PARAM_NR_RINGS   MSM_PARAM_PRIORITIES
+
+struct drm_msm_param {
+	__u32 pipe;           /* in, MSM_PIPE_x */
+	__u32 param;          /* in, MSM_PARAM_x */
+	__u64 value;          /* out (get_param) or in (set_param) */
+	__u32 len;            /* zero for non-pointer params */
+	__u32 pad;            /* must be zero */
+};
+
+/*
+ * GEM buffers:
+ */
+
+#define MSM_BO_SCANOUT       0x00000001     /* scanout capable */
+#define MSM_BO_GPU_READONLY  0x00000002
+/* Private buffers do not need to be explicitly listed in the SUBMIT
+ * ioctl, unless referenced by a drm_msm_gem_submit_cmd.  Private
+ * buffers may NOT be imported/exported or used for scanout (or any
+ * other situation where buffers can be indefinitely pinned, but
+ * cases other than scanout are all kernel owned BOs which are not
+ * visible to userspace).
+ *
+ * In exchange for those constraints, all private BOs associated with
+ * a single context (drm_file) share a single dma_resv, and if there
+ * has been no eviction since the last submit, there are no per-BO
+ * bookeeping to do, significantly cutting the SUBMIT overhead.
+ */
+#define MSM_BO_NO_SHARE      0x00000004
+#define MSM_BO_CACHE_MASK    0x000f0000
+/* cache modes */
+#define MSM_BO_CACHED        0x00010000
+#define MSM_BO_WC            0x00020000
+#define MSM_BO_UNCACHED      0x00040000 /* deprecated, use MSM_BO_WC */
+#define MSM_BO_CACHED_COHERENT 0x080000
+
+#define MSM_BO_FLAGS         (MSM_BO_SCANOUT | \
+                              MSM_BO_GPU_READONLY | \
+                              MSM_BO_NO_SHARE | \
+                              MSM_BO_CACHE_MASK)
+
+struct drm_msm_gem_new {
+	__u64 size;           /* in */
+	__u32 flags;          /* in, mask of MSM_BO_x */
+	__u32 handle;         /* out */
+};
+
+/* Get or set GEM buffer info.  The requested value can be passed
+ * directly in 'value', or for data larger than 64b 'value' is a
+ * pointer to userspace buffer, with 'len' specifying the number of
+ * bytes copied into that buffer.  For info returned by pointer,
+ * calling the GEM_INFO ioctl with null 'value' will return the
+ * required buffer size in 'len'
+ */
+#define MSM_INFO_GET_OFFSET	0x00   /* get mmap() offset, returned by value */
+#define MSM_INFO_GET_IOVA	0x01   /* get iova, returned by value */
+#define MSM_INFO_SET_NAME	0x02   /* set the debug name (by pointer) */
+#define MSM_INFO_GET_NAME	0x03   /* get debug name, returned by pointer */
+#define MSM_INFO_SET_IOVA	0x04   /* set the iova, passed by value */
+#define MSM_INFO_GET_FLAGS	0x05   /* get the MSM_BO_x flags */
+#define MSM_INFO_SET_METADATA	0x06   /* set userspace metadata */
+#define MSM_INFO_GET_METADATA	0x07   /* get userspace metadata */
+
+struct drm_msm_gem_info {
+	__u32 handle;         /* in */
+	__u32 info;           /* in - one of MSM_INFO_* */
+	__u64 value;          /* in or out */
+	__u32 len;            /* in or out */
+	__u32 pad;
+};
+
+#define MSM_PREP_READ        0x01
+#define MSM_PREP_WRITE       0x02
+#define MSM_PREP_NOSYNC      0x04
+#define MSM_PREP_BOOST       0x08
+
+#define MSM_PREP_FLAGS       (MSM_PREP_READ | \
+			      MSM_PREP_WRITE | \
+			      MSM_PREP_NOSYNC | \
+			      MSM_PREP_BOOST | \
+			      0)
+
+struct drm_msm_gem_cpu_prep {
+	__u32 handle;         /* in */
+	__u32 op;             /* in, mask of MSM_PREP_x */
+	struct drm_msm_timespec timeout;   /* in */
+};
+
+struct drm_msm_gem_cpu_fini {
+	__u32 handle;         /* in */
+};
+
+/*
+ * Cmdstream Submission:
+ */
+
+#define MSM_SYNCOBJ_RESET 0x00000001 /* Reset syncobj after wait. */
+#define MSM_SYNCOBJ_FLAGS ( \
+		MSM_SYNCOBJ_RESET | \
+		0)
+
+struct drm_msm_syncobj {
+	__u32 handle;     /* in, syncobj handle. */
+	__u32 flags;      /* in, from MSM_SYNCOBJ_FLAGS */
+	__u64 point;      /* in, timepoint for timeline syncobjs. */
+};
+
+/* The value written into the cmdstream is logically:
+ *
+ *   ((relocbuf->gpuaddr + reloc_offset) << shift) | or
+ *
+ * When we have GPU's w/ >32bit ptrs, it should be possible to deal
+ * with this by emit'ing two reloc entries with appropriate shift
+ * values.  Or a new MSM_SUBMIT_CMD_x type would also be an option.
+ *
+ * NOTE that reloc's must be sorted by order of increasing submit_offset,
+ * otherwise EINVAL.
+ */
+struct drm_msm_gem_submit_reloc {
+	__u32 submit_offset;  /* in, offset from submit_bo */
+#ifdef __cplusplus
+	__u32 _or;            /* in, value OR'd with result */
+#else
+	__u32 or;             /* in, value OR'd with result */
+#endif
+	__s32 shift;          /* in, amount of left shift (can be negative) */
+	__u32 reloc_idx;      /* in, index of reloc_bo buffer */
+	__u64 reloc_offset;   /* in, offset from start of reloc_bo */
+};
+
+/* submit-types:
+ *   BUF - this cmd buffer is executed normally.
+ *   IB_TARGET_BUF - this cmd buffer is an IB target.  Reloc's are
+ *      processed normally, but the kernel does not setup an IB to
+ *      this buffer in the first-level ringbuffer
+ *   CTX_RESTORE_BUF - only executed if there has been a GPU context
+ *      switch since the last SUBMIT ioctl
+ */
+#define MSM_SUBMIT_CMD_BUF             0x0001
+#define MSM_SUBMIT_CMD_IB_TARGET_BUF   0x0002
+#define MSM_SUBMIT_CMD_CTX_RESTORE_BUF 0x0003
+struct drm_msm_gem_submit_cmd {
+	__u32 type;           /* in, one of MSM_SUBMIT_CMD_x */
+	__u32 submit_idx;     /* in, index of submit_bo cmdstream buffer */
+	__u32 submit_offset;  /* in, offset into submit_bo */
+	__u32 size;           /* in, cmdstream size */
+	__u32 pad;
+	__u32 nr_relocs;      /* in, number of submit_reloc's */
+	union {
+		__u64 relocs; /* in, ptr to array of submit_reloc's */
+		__u64 iova;   /* cmdstream address (for VM_BIND contexts) */
+	};
+};
+
+/* Each buffer referenced elsewhere in the cmdstream submit (ie. the
+ * cmdstream buffer(s) themselves or reloc entries) has one (and only
+ * one) entry in the submit->bos[] table.
+ *
+ * As a optimization, the current buffer (gpu virtual address) can be
+ * passed back through the 'presumed' field.  If on a subsequent reloc,
+ * userspace passes back a 'presumed' address that is still valid,
+ * then patching the cmdstream for this entry is skipped.  This can
+ * avoid kernel needing to map/access the cmdstream bo in the common
+ * case.
+ */
+#define MSM_SUBMIT_BO_READ             0x0001
+#define MSM_SUBMIT_BO_WRITE            0x0002
+#define MSM_SUBMIT_BO_DUMP             0x0004
+#define MSM_SUBMIT_BO_NO_IMPLICIT      0x0008
+
+#define MSM_SUBMIT_BO_FLAGS            (MSM_SUBMIT_BO_READ | \
+					MSM_SUBMIT_BO_WRITE | \
+					MSM_SUBMIT_BO_DUMP | \
+					MSM_SUBMIT_BO_NO_IMPLICIT)
+
+struct drm_msm_gem_submit_bo {
+	__u32 flags;          /* in, mask of MSM_SUBMIT_BO_x */
+	__u32 handle;         /* in, GEM handle */
+	__u64 presumed;       /* in/out, presumed buffer address */
+};
+
+/* Valid submit ioctl flags: */
+#define MSM_SUBMIT_NO_IMPLICIT   0x80000000 /* disable implicit sync */
+#define MSM_SUBMIT_FENCE_FD_IN   0x40000000 /* enable input fence_fd */
+#define MSM_SUBMIT_FENCE_FD_OUT  0x20000000 /* enable output fence_fd */
+#define MSM_SUBMIT_SUDO          0x10000000 /* run submitted cmds from RB */
+#define MSM_SUBMIT_SYNCOBJ_IN    0x08000000 /* enable input syncobj */
+#define MSM_SUBMIT_SYNCOBJ_OUT   0x04000000 /* enable output syncobj */
+#define MSM_SUBMIT_FENCE_SN_IN   0x02000000 /* userspace passes in seqno fence */
+#define MSM_SUBMIT_FLAGS                ( \
+		MSM_SUBMIT_NO_IMPLICIT   | \
+		MSM_SUBMIT_FENCE_FD_IN   | \
+		MSM_SUBMIT_FENCE_FD_OUT  | \
+		MSM_SUBMIT_SUDO          | \
+		MSM_SUBMIT_SYNCOBJ_IN    | \
+		MSM_SUBMIT_SYNCOBJ_OUT   | \
+		MSM_SUBMIT_FENCE_SN_IN   | \
+		0)
+
+/* Each cmdstream submit consists of a table of buffers involved, and
+ * one or more cmdstream buffers.  This allows for conditional execution
+ * (context-restore), and IB buffers needed for per tile/bin draw cmds.
+ */
+struct drm_msm_gem_submit {
+	__u32 flags;          /* MSM_PIPE_x | MSM_SUBMIT_x */
+	__u32 fence;          /* out (or in with MSM_SUBMIT_FENCE_SN_IN flag) */
+	__u32 nr_bos;         /* in, number of submit_bo's */
+	__u32 nr_cmds;        /* in, number of submit_cmd's */
+	__u64 bos;            /* in, ptr to array of submit_bo's */
+	__u64 cmds;           /* in, ptr to array of submit_cmd's */
+	__s32 fence_fd;       /* in/out fence fd (see MSM_SUBMIT_FENCE_FD_IN/OUT) */
+	__u32 queueid;        /* in, submitqueue id */
+	__u64 in_syncobjs;    /* in, ptr to array of drm_msm_syncobj */
+	__u64 out_syncobjs;   /* in, ptr to array of drm_msm_syncobj */
+	__u32 nr_in_syncobjs; /* in, number of entries in in_syncobj */
+	__u32 nr_out_syncobjs; /* in, number of entries in out_syncobj. */
+	__u32 syncobj_stride; /* in, stride of syncobj arrays. */
+	__u32 pad;            /*in, reserved for future use, always 0. */
+};
+
+#define MSM_VM_BIND_OP_UNMAP	0
+#define MSM_VM_BIND_OP_MAP	1
+#define MSM_VM_BIND_OP_MAP_NULL	2
+
+#define MSM_VM_BIND_OP_DUMP	1
+#define MSM_VM_BIND_OP_FLAGS ( \
+		MSM_VM_BIND_OP_DUMP | \
+		0)
+
+/**
+ * struct drm_msm_vm_bind_op - bind/unbind op to run
+ */
+struct drm_msm_vm_bind_op {
+	/** @op: one of MSM_VM_BIND_OP_x */
+	__u32 op;
+	/** @handle: GEM object handle, MBZ for UNMAP or MAP_NULL */
+	__u32 handle;
+	/** @obj_offset: Offset into GEM object, MBZ for UNMAP or MAP_NULL */
+	__u64 obj_offset;
+	/** @iova: Address to operate on */
+	__u64 iova;
+	/** @range: Number of bites to to map/unmap */
+	__u64 range;
+	/** @flags: Bitmask of MSM_VM_BIND_OP_FLAG_x */
+	__u32 flags;
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+#define MSM_VM_BIND_FENCE_FD_IN		0x00000001
+#define MSM_VM_BIND_FENCE_FD_OUT	0x00000002
+#define MSM_VM_BIND_FLAGS ( \
+		MSM_VM_BIND_FENCE_FD_IN | \
+		MSM_VM_BIND_FENCE_FD_OUT | \
+		0)
+
+/**
+ * struct drm_msm_vm_bind - Input of &DRM_IOCTL_MSM_VM_BIND
+ */
+struct drm_msm_vm_bind {
+	/** @flags: in, bitmask of MSM_VM_BIND_x */
+	__u32 flags;
+	/** @nr_ops: the number of bind ops in this ioctl */
+	__u32 nr_ops;
+	/** @fence_fd: in/out fence fd (see MSM_VM_BIND_FENCE_FD_IN/OUT) */
+	__s32 fence_fd;
+	/** @queue_id: in, submitqueue id */
+	__u32 queue_id;
+	/** @in_syncobjs: in, ptr to array of drm_msm_syncobj */
+	__u64 in_syncobjs;
+	/** @out_syncobjs: in, ptr to array of drm_msm_syncobj */
+	__u64 out_syncobjs;
+	/** @nr_in_syncobjs: in, number of entries in in_syncobj */
+	__u32 nr_in_syncobjs;
+	/** @nr_out_syncobjs: in, number of entries in out_syncobj */
+	__u32 nr_out_syncobjs;
+	/** @syncobj_stride: in, stride of syncobj arrays */
+	__u32 syncobj_stride;
+	/** @op_stride: sizeof each struct drm_msm_vm_bind_op in @ops */
+	__u32 op_stride;
+	union {
+		/** @op: used if num_ops == 1 */
+		struct drm_msm_vm_bind_op op;
+		/** @ops: userptr to array of drm_msm_vm_bind_op if num_ops > 1 */
+		__u64 ops;
+	};
+};
+
+#define MSM_WAIT_FENCE_BOOST	0x00000001
+#define MSM_WAIT_FENCE_FLAGS	( \
+		MSM_WAIT_FENCE_BOOST | \
+		0)
+
+/* The normal way to synchronize with the GPU is just to CPU_PREP on
+ * a buffer if you need to access it from the CPU (other cmdstream
+ * submission from same or other contexts, PAGE_FLIP ioctl, etc, all
+ * handle the required synchronization under the hood).  This ioctl
+ * mainly just exists as a way to implement the gallium pipe_fence
+ * APIs without requiring a dummy bo to synchronize on.
+ */
+struct drm_msm_wait_fence {
+	__u32 fence;          /* in */
+	__u32 flags;          /* in, bitmask of MSM_WAIT_FENCE_x */
+	struct drm_msm_timespec timeout;   /* in */
+	__u32 queueid;         /* in, submitqueue id */
+};
+
+/* madvise provides a way to tell the kernel in case a buffers contents
+ * can be discarded under memory pressure, which is useful for userspace
+ * bo cache where we want to optimistically hold on to buffer allocate
+ * and potential mmap, but allow the pages to be discarded under memory
+ * pressure.
+ *
+ * Typical usage would involve madvise(DONTNEED) when buffer enters BO
+ * cache, and madvise(WILLNEED) if trying to recycle buffer from BO cache.
+ * In the WILLNEED case, 'retained' indicates to userspace whether the
+ * backing pages still exist.
+ */
+#define MSM_MADV_WILLNEED 0       /* backing pages are needed, status returned in 'retained' */
+#define MSM_MADV_DONTNEED 1       /* backing pages not needed */
+#define __MSM_MADV_PURGED 2       /* internal state */
+
+struct drm_msm_gem_madvise {
+	__u32 handle;         /* in, GEM handle */
+	__u32 madv;           /* in, MSM_MADV_x */
+	__u32 retained;       /* out, whether backing store still exists */
+};
+
+/*
+ * Draw queues allow the user to set specific submission parameter. Command
+ * submissions specify a specific submitqueue to use.  ID 0 is reserved for
+ * backwards compatibility as a "default" submitqueue.
+ *
+ * Because VM_BIND async updates happen on the CPU, they must run on a
+ * virtual queue created with the flag MSM_SUBMITQUEUE_VM_BIND.  If we had
+ * a way to do pgtable updates on the GPU, we could drop this restriction.
+ */
+
+#define MSM_SUBMITQUEUE_ALLOW_PREEMPT	0x00000001
+#define MSM_SUBMITQUEUE_VM_BIND	0x00000002  /* virtual queue for VM_BIND ops */
+
+#define MSM_SUBMITQUEUE_FLAGS		    ( \
+		MSM_SUBMITQUEUE_ALLOW_PREEMPT | \
+		MSM_SUBMITQUEUE_VM_BIND | \
+		0)
+
+/*
+ * The submitqueue priority should be between 0 and MSM_PARAM_PRIORITIES-1,
+ * a lower numeric value is higher priority.
+ */
+struct drm_msm_submitqueue {
+	__u32 flags;   /* in, MSM_SUBMITQUEUE_x */
+	__u32 prio;    /* in, Priority level */
+	__u32 id;      /* out, identifier */
+};
+
+#define MSM_SUBMITQUEUE_PARAM_FAULTS   0
+
+struct drm_msm_submitqueue_query {
+	__u64 data;
+	__u32 id;
+	__u32 param;
+	__u32 len;
+	__u32 pad;
+};
+
+#define MSM_PERFCNTR_STREAM	0x00000001
+#define MSM_PERFCNTR_UPDATE	0x00000002
+#define MSM_PERFCNTR_FLAGS	( \
+		MSM_PERFCNTR_STREAM | \
+		MSM_PERFCNTR_UPDATE | \
+		0)
+
+struct drm_msm_perfcntr_group {
+	char group_name[16];
+	__u32 nr_countables;
+	__u32 pad;         /* mbz */
+	__u64 countables;  /* pointer to an array of nr_countables u32 */
+};
+
+/*
+ * Note, for MSM_PERFCNTR_STREAM, the ioctl returns an fd to read recorded
+ * counters.  This only works because the ioctl is DRM_IOW(), if we returned
+ * a out param in the ioctl struct the copy_to_user() (in drm_ioctl())
+ * could fault, causing us to leak the fd.
+ *
+ * If the ioctl returns with error E2BIG, that means more counters/countables
+ * are requested than are currently available.  If MSM_PERFCNTR_UPDATE flag
+ * is set, drm_msm_perfcntr_group::nr_countables will be updated to return
+ * the actual # of counters available.
+ *
+ * The data read from the has the following format for each sampling period:
+ *
+ *     uint64_t timestamp;  // CP_ALWAYS_ON_COUNTER captured at sample time
+ *     uint32_t seqno;      // increments by 1 each period, reset to 0 on discontinuity
+ *     uint32_t mbz;        // pad out counters to 64b
+ *     struct {
+ *        uint64_t counter[nr_countables];
+ *     } groups[nr_groups];
+ *
+ * The ordering of groups and counters matches the order in PERFCNTR_CONFIG
+ * ioctl.
+ */
+struct drm_msm_perfcntr_config {
+	__u32 flags;         /* bitmask of MSM_PERFCNTR_x */
+	__u32 nr_groups;     /* # of entries in groups array */
+	__u64 groups;        /* pointer to array of drm_msm_perfcntr_group */
+	__u64 period;        /* sampling period in ns */
+	__u32 bufsz_shift;   /* sample buffer size in bytes is 1<<bufsz_shift */
+	__u32 group_stride;  /* sizeof(struct drm_msm_perfcntr_group) */
+};
+
+#define DRM_MSM_GET_PARAM              0x00
+#define DRM_MSM_SET_PARAM              0x01
+#define DRM_MSM_GEM_NEW                0x02
+#define DRM_MSM_GEM_INFO               0x03
+#define DRM_MSM_GEM_CPU_PREP           0x04
+#define DRM_MSM_GEM_CPU_FINI           0x05
+#define DRM_MSM_GEM_SUBMIT             0x06
+#define DRM_MSM_WAIT_FENCE             0x07
+#define DRM_MSM_GEM_MADVISE            0x08
+/* placeholder:
+#define DRM_MSM_GEM_SVM_NEW            0x09
+ */
+#define DRM_MSM_SUBMITQUEUE_NEW        0x0A
+#define DRM_MSM_SUBMITQUEUE_CLOSE      0x0B
+#define DRM_MSM_SUBMITQUEUE_QUERY      0x0C
+#define DRM_MSM_VM_BIND                0x0D
+#define DRM_MSM_PERFCNTR_CONFIG        0x0E
+
+#define DRM_IOCTL_MSM_GET_PARAM        DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GET_PARAM, struct drm_msm_param)
+#define DRM_IOCTL_MSM_SET_PARAM        DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SET_PARAM, struct drm_msm_param)
+#define DRM_IOCTL_MSM_GEM_NEW          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_NEW, struct drm_msm_gem_new)
+#define DRM_IOCTL_MSM_GEM_INFO         DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_INFO, struct drm_msm_gem_info)
+#define DRM_IOCTL_MSM_GEM_CPU_PREP     DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_GEM_CPU_PREP, struct drm_msm_gem_cpu_prep)
+#define DRM_IOCTL_MSM_GEM_CPU_FINI     DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_GEM_CPU_FINI, struct drm_msm_gem_cpu_fini)
+#define DRM_IOCTL_MSM_GEM_SUBMIT       DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_SUBMIT, struct drm_msm_gem_submit)
+#define DRM_IOCTL_MSM_WAIT_FENCE       DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_WAIT_FENCE, struct drm_msm_wait_fence)
+#define DRM_IOCTL_MSM_GEM_MADVISE      DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_GEM_MADVISE, struct drm_msm_gem_madvise)
+#define DRM_IOCTL_MSM_SUBMITQUEUE_NEW    DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_NEW, struct drm_msm_submitqueue)
+#define DRM_IOCTL_MSM_SUBMITQUEUE_CLOSE  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_CLOSE, __u32)
+#define DRM_IOCTL_MSM_SUBMITQUEUE_QUERY  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_SUBMITQUEUE_QUERY, struct drm_msm_submitqueue_query)
+#define DRM_IOCTL_MSM_VM_BIND          DRM_IOWR(DRM_COMMAND_BASE + DRM_MSM_VM_BIND, struct drm_msm_vm_bind)
+#define DRM_IOCTL_MSM_PERFCNTR_CONFIG  DRM_IOW (DRM_COMMAND_BASE + DRM_MSM_PERFCNTR_CONFIG, struct drm_msm_perfcntr_config)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __MSM_DRM_H__ */
diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h
new file mode 100644
index 000000000..c4905b3e4
--- /dev/null
+++ b/include/uapi/drm/nouveau_drm.h
@@ -0,0 +1,587 @@
+/*
+ * Copyright 2005 Stephane Marchesin.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * VA LINUX SYSTEMS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+
+#ifndef __NOUVEAU_DRM_H__
+#define __NOUVEAU_DRM_H__
+
+#define DRM_NOUVEAU_EVENT_NVIF                                       0x80000000
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define NOUVEAU_GETPARAM_PCI_VENDOR      3
+#define NOUVEAU_GETPARAM_PCI_DEVICE      4
+#define NOUVEAU_GETPARAM_BUS_TYPE        5
+#define NOUVEAU_GETPARAM_FB_SIZE         8
+#define NOUVEAU_GETPARAM_AGP_SIZE        9
+#define NOUVEAU_GETPARAM_CHIPSET_ID      11
+#define NOUVEAU_GETPARAM_VM_VRAM_BASE    12
+#define NOUVEAU_GETPARAM_GRAPH_UNITS     13
+#define NOUVEAU_GETPARAM_PTIMER_TIME     14
+#define NOUVEAU_GETPARAM_HAS_BO_USAGE    15
+#define NOUVEAU_GETPARAM_HAS_PAGEFLIP    16
+
+/*
+ * NOUVEAU_GETPARAM_EXEC_PUSH_MAX - query max pushes through getparam
+ *
+ * Query the maximum amount of IBs that can be pushed through a single
+ * &drm_nouveau_exec structure and hence a single &DRM_IOCTL_NOUVEAU_EXEC
+ * ioctl().
+ */
+#define NOUVEAU_GETPARAM_EXEC_PUSH_MAX   17
+
+/*
+ * NOUVEAU_GETPARAM_VRAM_BAR_SIZE - query bar size
+ *
+ * Query the VRAM BAR size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_BAR_SIZE 18
+
+/*
+ * NOUVEAU_GETPARAM_VRAM_USED
+ *
+ * Get remaining VRAM size.
+ */
+#define NOUVEAU_GETPARAM_VRAM_USED 19
+
+/*
+ * NOUVEAU_GETPARAM_HAS_VMA_TILEMODE
+ *
+ * Query whether tile mode and PTE kind are accepted with VM allocs or not.
+ */
+#define NOUVEAU_GETPARAM_HAS_VMA_TILEMODE 20
+
+struct drm_nouveau_getparam {
+	__u64 param;
+	__u64 value;
+};
+
+/*
+ * Those are used to support selecting the main engine used on Kepler.
+ * This goes into drm_nouveau_channel_alloc::tt_ctxdma_handle
+ */
+#define NOUVEAU_FIFO_ENGINE_GR  0x01
+#define NOUVEAU_FIFO_ENGINE_VP  0x02
+#define NOUVEAU_FIFO_ENGINE_PPP 0x04
+#define NOUVEAU_FIFO_ENGINE_BSP 0x08
+#define NOUVEAU_FIFO_ENGINE_CE  0x30
+#define NOUVEAU_FIFO_ENGINE_NVDEC 0x300
+
+struct drm_nouveau_channel_alloc {
+	__u32     fb_ctxdma_handle;
+	__u32     tt_ctxdma_handle;
+
+	__s32     channel;
+	__u32     pushbuf_domains;
+
+	/* Notifier memory */
+	__u32     notifier_handle;
+
+	/* DRM-enforced subchannel assignments */
+	struct {
+		__u32 handle;
+		__u32 grclass;
+	} subchan[8];
+	__u32 nr_subchan;
+};
+
+struct drm_nouveau_channel_free {
+	__s32 channel;
+};
+
+struct drm_nouveau_notifierobj_alloc {
+	__u32 channel;
+	__u32 handle;
+	__u32 size;
+	__u32 offset;
+};
+
+struct drm_nouveau_gpuobj_free {
+	__s32 channel;
+	__u32 handle;
+};
+
+#define NOUVEAU_GEM_DOMAIN_CPU       (1 << 0)
+#define NOUVEAU_GEM_DOMAIN_VRAM      (1 << 1)
+#define NOUVEAU_GEM_DOMAIN_GART      (1 << 2)
+#define NOUVEAU_GEM_DOMAIN_MAPPABLE  (1 << 3)
+#define NOUVEAU_GEM_DOMAIN_COHERENT  (1 << 4)
+/* The BO will never be shared via import or export. */
+#define NOUVEAU_GEM_DOMAIN_NO_SHARE  (1 << 5)
+
+#define NOUVEAU_GEM_TILE_COMP        0x00030000 /* nv50-only */
+#define NOUVEAU_GEM_TILE_LAYOUT_MASK 0x0000ff00
+#define NOUVEAU_GEM_TILE_16BPP       0x00000001
+#define NOUVEAU_GEM_TILE_32BPP       0x00000002
+#define NOUVEAU_GEM_TILE_ZETA        0x00000004
+#define NOUVEAU_GEM_TILE_NONCONTIG   0x00000008
+
+struct drm_nouveau_gem_info {
+	__u32 handle;
+	__u32 domain;
+	__u64 size;
+	__u64 offset;
+	__u64 map_handle;
+	__u32 tile_mode;
+	__u32 tile_flags;
+};
+
+struct drm_nouveau_gem_new {
+	struct drm_nouveau_gem_info info;
+	__u32 channel_hint;
+	__u32 align;
+};
+
+#define NOUVEAU_GEM_MAX_BUFFERS 1024
+struct drm_nouveau_gem_pushbuf_bo_presumed {
+	__u32 valid;
+	__u32 domain;
+	__u64 offset;
+};
+
+struct drm_nouveau_gem_pushbuf_bo {
+	__u64 user_priv;
+	__u32 handle;
+	__u32 read_domains;
+	__u32 write_domains;
+	__u32 valid_domains;
+	struct drm_nouveau_gem_pushbuf_bo_presumed presumed;
+};
+
+#define NOUVEAU_GEM_RELOC_LOW  (1 << 0)
+#define NOUVEAU_GEM_RELOC_HIGH (1 << 1)
+#define NOUVEAU_GEM_RELOC_OR   (1 << 2)
+#define NOUVEAU_GEM_MAX_RELOCS 1024
+struct drm_nouveau_gem_pushbuf_reloc {
+	__u32 reloc_bo_index;
+	__u32 reloc_bo_offset;
+	__u32 bo_index;
+	__u32 flags;
+	__u32 data;
+	__u32 vor;
+	__u32 tor;
+};
+
+#define NOUVEAU_GEM_MAX_PUSH 512
+struct drm_nouveau_gem_pushbuf_push {
+	__u32 bo_index;
+	__u32 pad;
+	__u64 offset;
+	__u64 length;
+#define NOUVEAU_GEM_PUSHBUF_NO_PREFETCH (1 << 23)
+};
+
+struct drm_nouveau_gem_pushbuf {
+	__u32 channel;
+	__u32 nr_buffers;
+	__u64 buffers;
+	__u32 nr_relocs;
+	__u32 nr_push;
+	__u64 relocs;
+	__u64 push;
+	__u32 suffix0;
+	__u32 suffix1;
+#define NOUVEAU_GEM_PUSHBUF_SYNC                                    (1ULL << 0)
+	__u64 vram_available;
+	__u64 gart_available;
+};
+
+#define NOUVEAU_GEM_CPU_PREP_NOWAIT                                  0x00000001
+#define NOUVEAU_GEM_CPU_PREP_WRITE                                   0x00000004
+struct drm_nouveau_gem_cpu_prep {
+	__u32 handle;
+	__u32 flags;
+};
+
+struct drm_nouveau_gem_cpu_fini {
+	__u32 handle;
+};
+
+/**
+ * struct drm_nouveau_sync - sync object
+ *
+ * This structure serves as synchronization mechanism for (potentially)
+ * asynchronous operations such as EXEC or VM_BIND.
+ */
+struct drm_nouveau_sync {
+	/**
+	 * @flags: the flags for a sync object
+	 *
+	 * The first 8 bits are used to determine the type of the sync object.
+	 */
+	__u32 flags;
+#define DRM_NOUVEAU_SYNC_SYNCOBJ 0x0
+#define DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ 0x1
+#define DRM_NOUVEAU_SYNC_TYPE_MASK 0xf
+	/**
+	 * @handle: the handle of the sync object
+	 */
+	__u32 handle;
+	/**
+	 * @timeline_value:
+	 *
+	 * The timeline point of the sync object in case the syncobj is of
+	 * type DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ.
+	 */
+	__u64 timeline_value;
+};
+
+/**
+ * struct drm_nouveau_vm_init - GPU VA space init structure
+ *
+ * Used to initialize the GPU's VA space for a user client, telling the kernel
+ * which portion of the VA space is managed by the UMD and kernel respectively.
+ *
+ * For the UMD to use the VM_BIND uAPI, this must be called before any BOs or
+ * channels are created; if called afterwards DRM_IOCTL_NOUVEAU_VM_INIT fails
+ * with -ENOSYS.
+ */
+struct drm_nouveau_vm_init {
+	/**
+	 * @kernel_managed_addr: start address of the kernel managed VA space
+	 * region
+	 */
+	__u64 kernel_managed_addr;
+	/**
+	 * @kernel_managed_size: size of the kernel managed VA space region in
+	 * bytes
+	 */
+	__u64 kernel_managed_size;
+};
+
+/**
+ * struct drm_nouveau_vm_bind_op - VM_BIND operation
+ *
+ * This structure represents a single VM_BIND operation. UMDs should pass
+ * an array of this structure via struct drm_nouveau_vm_bind's &op_ptr field.
+ */
+struct drm_nouveau_vm_bind_op {
+	/**
+	 * @op: the operation type
+	 *
+	 * Supported values:
+	 *
+	 * %DRM_NOUVEAU_VM_BIND_OP_MAP - Map a GEM object to the GPU's VA
+	 * space. Optionally, the &DRM_NOUVEAU_VM_BIND_SPARSE flag can be
+	 * passed to instruct the kernel to create sparse mappings for the
+	 * given range.
+	 *
+	 * %DRM_NOUVEAU_VM_BIND_OP_UNMAP - Unmap an existing mapping in the
+	 * GPU's VA space. If the region the mapping is located in is a
+	 * sparse region, new sparse mappings are created where the unmapped
+	 * (memory backed) mapping was mapped previously. To remove a sparse
+	 * region the &DRM_NOUVEAU_VM_BIND_SPARSE must be set.
+	 */
+	__u32 op;
+#define DRM_NOUVEAU_VM_BIND_OP_MAP 0x0
+#define DRM_NOUVEAU_VM_BIND_OP_UNMAP 0x1
+	/**
+	 * @flags: the flags for a &drm_nouveau_vm_bind_op
+	 *
+	 * Supported values:
+	 *
+	 * %DRM_NOUVEAU_VM_BIND_SPARSE - Indicates that an allocated VA
+	 * space region should be sparse.
+	 */
+	__u32 flags;
+#define DRM_NOUVEAU_VM_BIND_SPARSE (1 << 8)
+	/**
+	 * @handle: the handle of the DRM GEM object to map
+	 */
+	__u32 handle;
+	/**
+	 * @pad: 32 bit padding, should be 0
+	 */
+	__u32 pad;
+	/**
+	 * @addr:
+	 *
+	 * the address the VA space region or (memory backed) mapping should be mapped to
+	 */
+	__u64 addr;
+	/**
+	 * @bo_offset: the offset within the BO backing the mapping
+	 */
+	__u64 bo_offset;
+	/**
+	 * @range: the size of the requested mapping in bytes
+	 */
+	__u64 range;
+};
+
+/**
+ * struct drm_nouveau_vm_bind - structure for DRM_IOCTL_NOUVEAU_VM_BIND
+ */
+struct drm_nouveau_vm_bind {
+	/**
+	 * @op_count: the number of &drm_nouveau_vm_bind_op
+	 */
+	__u32 op_count;
+	/**
+	 * @flags: the flags for a &drm_nouveau_vm_bind ioctl
+	 *
+	 * Supported values:
+	 *
+	 * %DRM_NOUVEAU_VM_BIND_RUN_ASYNC - Indicates that the given VM_BIND
+	 * operation should be executed asynchronously by the kernel.
+	 *
+	 * If this flag is not supplied the kernel executes the associated
+	 * operations synchronously and doesn't accept any &drm_nouveau_sync
+	 * objects.
+	 */
+	__u32 flags;
+#define DRM_NOUVEAU_VM_BIND_RUN_ASYNC 0x1
+	/**
+	 * @wait_count: the number of wait &drm_nouveau_syncs
+	 */
+	__u32 wait_count;
+	/**
+	 * @sig_count: the number of &drm_nouveau_syncs to signal when finished
+	 */
+	__u32 sig_count;
+	/**
+	 * @wait_ptr: pointer to &drm_nouveau_syncs to wait for
+	 */
+	__u64 wait_ptr;
+	/**
+	 * @sig_ptr: pointer to &drm_nouveau_syncs to signal when finished
+	 */
+	__u64 sig_ptr;
+	/**
+	 * @op_ptr: pointer to the &drm_nouveau_vm_bind_ops to execute
+	 */
+	__u64 op_ptr;
+};
+
+/**
+ * struct drm_nouveau_exec_push - EXEC push operation
+ *
+ * This structure represents a single EXEC push operation. UMDs should pass an
+ * array of this structure via struct drm_nouveau_exec's &push_ptr field.
+ */
+struct drm_nouveau_exec_push {
+	/**
+	 * @va: the virtual address of the push buffer mapping
+	 */
+	__u64 va;
+	/**
+	 * @va_len: the length of the push buffer mapping
+	 */
+	__u32 va_len;
+	/**
+	 * @flags: the flags for this push buffer mapping
+	 */
+	__u32 flags;
+#define DRM_NOUVEAU_EXEC_PUSH_NO_PREFETCH 0x1
+};
+
+/**
+ * struct drm_nouveau_exec - structure for DRM_IOCTL_NOUVEAU_EXEC
+ */
+struct drm_nouveau_exec {
+	/**
+	 * @channel: the channel to execute the push buffer in
+	 */
+	__u32 channel;
+	/**
+	 * @push_count: the number of &drm_nouveau_exec_push ops
+	 */
+	__u32 push_count;
+	/**
+	 * @wait_count: the number of wait &drm_nouveau_syncs
+	 */
+	__u32 wait_count;
+	/**
+	 * @sig_count: the number of &drm_nouveau_syncs to signal when finished
+	 */
+	__u32 sig_count;
+	/**
+	 * @wait_ptr: pointer to &drm_nouveau_syncs to wait for
+	 */
+	__u64 wait_ptr;
+	/**
+	 * @sig_ptr: pointer to &drm_nouveau_syncs to signal when finished
+	 */
+	__u64 sig_ptr;
+	/**
+	 * @push_ptr: pointer to &drm_nouveau_exec_push ops
+	 */
+	__u64 push_ptr;
+};
+
+struct drm_nouveau_get_zcull_info {
+	/**
+	 * @width_align_pixels: required alignment for region widths, in pixels
+	 * (typically #TPC's * 16).
+	 */
+	__u32 width_align_pixels;
+	/**
+	 * @height_align_pixels: required alignment for region heights, in
+	 * pixels (typically 32).
+	 */
+	__u32 height_align_pixels;
+	/**
+	 * @pixel_squares_by_aliquots: the pixel area covered by an aliquot
+	 * (typically #Zcull_banks * 16 * 16).
+	 */
+	__u32 pixel_squares_by_aliquots;
+	/**
+	 * @aliquot_total: the total aliquot pool available in hardware
+	 */
+	__u32 aliquot_total;
+	/**
+	 * @zcull_region_byte_multiplier: the size of an aliquot in bytes, which
+	 * is used for save/restore operations on a region
+	 */
+	__u32 zcull_region_byte_multiplier;
+	/**
+	 * @zcull_region_header_size: the region header size in bytes, which is
+	 * used for save/restore operations on a region
+	 */
+	__u32 zcull_region_header_size;
+	/**
+	 * @zcull_subregion_header_size: the subregion header size in bytes,
+	 * which is used for save/restore operations on a region
+	 */
+	__u32 zcull_subregion_header_size;
+	/**
+	 * @subregion_count: the total number of subregions the hardware
+	 * supports
+	 */
+	__u32 subregion_count;
+	/**
+	 * @subregion_width_align_pixels: required alignment for subregion
+	 * widths, in pixels (typically #TPC's * 16).
+	 */
+	__u32 subregion_width_align_pixels;
+	/**
+	 * @subregion_height_align_pixels: required alignment for subregion
+	 * heights, in pixels
+	 */
+	__u32 subregion_height_align_pixels;
+
+	/**
+	 * @ctxsw_size: the size, in bytes, of a zcull context switching region.
+	 * Will be zero if the kernel does not support zcull context switching.
+	 */
+	__u32 ctxsw_size;
+	/**
+	 * @ctxsw_align: the alignment, in bytes, of a zcull context switching
+	 * region
+	 */
+	__u32 ctxsw_align;
+};
+
+#define DRM_NOUVEAU_GETPARAM           0x00
+#define DRM_NOUVEAU_SETPARAM           0x01 /* deprecated */
+#define DRM_NOUVEAU_CHANNEL_ALLOC      0x02
+#define DRM_NOUVEAU_CHANNEL_FREE       0x03
+#define DRM_NOUVEAU_GROBJ_ALLOC        0x04 /* deprecated */
+#define DRM_NOUVEAU_NOTIFIEROBJ_ALLOC  0x05 /* deprecated */
+#define DRM_NOUVEAU_GPUOBJ_FREE        0x06 /* deprecated */
+#define DRM_NOUVEAU_NVIF               0x07
+#define DRM_NOUVEAU_SVM_INIT           0x08
+#define DRM_NOUVEAU_SVM_BIND           0x09
+#define DRM_NOUVEAU_VM_INIT            0x10
+#define DRM_NOUVEAU_VM_BIND            0x11
+#define DRM_NOUVEAU_EXEC               0x12
+#define DRM_NOUVEAU_GET_ZCULL_INFO     0x13
+#define DRM_NOUVEAU_GEM_NEW            0x40
+#define DRM_NOUVEAU_GEM_PUSHBUF        0x41
+#define DRM_NOUVEAU_GEM_CPU_PREP       0x42
+#define DRM_NOUVEAU_GEM_CPU_FINI       0x43
+#define DRM_NOUVEAU_GEM_INFO           0x44
+
+struct drm_nouveau_svm_init {
+	__u64 unmanaged_addr;
+	__u64 unmanaged_size;
+};
+
+struct drm_nouveau_svm_bind {
+	__u64 header;
+	__u64 va_start;
+	__u64 va_end;
+	__u64 npages;
+	__u64 stride;
+	__u64 result;
+	__u64 reserved0;
+	__u64 reserved1;
+};
+
+#define NOUVEAU_SVM_BIND_COMMAND_SHIFT          0
+#define NOUVEAU_SVM_BIND_COMMAND_BITS           8
+#define NOUVEAU_SVM_BIND_COMMAND_MASK           ((1 << 8) - 1)
+#define NOUVEAU_SVM_BIND_PRIORITY_SHIFT         8
+#define NOUVEAU_SVM_BIND_PRIORITY_BITS          8
+#define NOUVEAU_SVM_BIND_PRIORITY_MASK          ((1 << 8) - 1)
+#define NOUVEAU_SVM_BIND_TARGET_SHIFT           16
+#define NOUVEAU_SVM_BIND_TARGET_BITS            32
+#define NOUVEAU_SVM_BIND_TARGET_MASK            0xffffffff
+
+/*
+ * Below is use to validate ioctl argument, userspace can also use it to make
+ * sure that no bit are set beyond known fields for a given kernel version.
+ */
+#define NOUVEAU_SVM_BIND_VALID_BITS     48
+#define NOUVEAU_SVM_BIND_VALID_MASK     ((1ULL << NOUVEAU_SVM_BIND_VALID_BITS) - 1)
+
+
+/*
+ * NOUVEAU_BIND_COMMAND__MIGRATE: synchronous migrate to target memory.
+ * result: number of page successfuly migrate to the target memory.
+ */
+#define NOUVEAU_SVM_BIND_COMMAND__MIGRATE               0
+
+/*
+ * NOUVEAU_SVM_BIND_HEADER_TARGET__GPU_VRAM: target the GPU VRAM memory.
+ */
+#define NOUVEAU_SVM_BIND_TARGET__GPU_VRAM               (1UL << 31)
+
+
+#define DRM_IOCTL_NOUVEAU_GETPARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GETPARAM, struct drm_nouveau_getparam)
+#define DRM_IOCTL_NOUVEAU_CHANNEL_ALLOC      DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_CHANNEL_ALLOC, struct drm_nouveau_channel_alloc)
+#define DRM_IOCTL_NOUVEAU_CHANNEL_FREE       DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_CHANNEL_FREE, struct drm_nouveau_channel_free)
+
+#define DRM_IOCTL_NOUVEAU_SVM_INIT           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SVM_INIT, struct drm_nouveau_svm_init)
+#define DRM_IOCTL_NOUVEAU_SVM_BIND           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_SVM_BIND, struct drm_nouveau_svm_bind)
+
+#define DRM_IOCTL_NOUVEAU_GEM_NEW            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_NEW, struct drm_nouveau_gem_new)
+#define DRM_IOCTL_NOUVEAU_GEM_PUSHBUF        DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_PUSHBUF, struct drm_nouveau_gem_pushbuf)
+#define DRM_IOCTL_NOUVEAU_GEM_CPU_PREP       DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_CPU_PREP, struct drm_nouveau_gem_cpu_prep)
+#define DRM_IOCTL_NOUVEAU_GEM_CPU_FINI       DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_CPU_FINI, struct drm_nouveau_gem_cpu_fini)
+#define DRM_IOCTL_NOUVEAU_GEM_INFO           DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_INFO, struct drm_nouveau_gem_info)
+
+#define DRM_IOCTL_NOUVEAU_VM_INIT            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_INIT, struct drm_nouveau_vm_init)
+#define DRM_IOCTL_NOUVEAU_VM_BIND            DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_BIND, struct drm_nouveau_vm_bind)
+#define DRM_IOCTL_NOUVEAU_EXEC               DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_EXEC, struct drm_nouveau_exec)
+
+#define DRM_IOCTL_NOUVEAU_GET_ZCULL_INFO     DRM_IOR (DRM_COMMAND_BASE + DRM_NOUVEAU_GET_ZCULL_INFO, struct drm_nouveau_get_zcull_info)
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __NOUVEAU_DRM_H__ */
diff --git a/include/uapi/drm/nova_drm.h b/include/uapi/drm/nova_drm.h
new file mode 100644
index 000000000..3ca90ed9d
--- /dev/null
+++ b/include/uapi/drm/nova_drm.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: MIT */
+
+#ifndef __NOVA_DRM_H__
+#define __NOVA_DRM_H__
+
+#include "drm.h"
+
+/* DISCLAIMER: Do not use, this is not a stable uAPI.
+ *
+ * This uAPI serves only testing purposes as long as this driver is still in
+ * development. It is required to implement and test infrastructure which is
+ * upstreamed in the context of this driver. See also [1].
+ *
+ * [1] https://lore.kernel.org/dri-devel/Zfsj0_tb-0-tNrJy@cassiopeiae/T/#u
+ */
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/*
+ * NOVA_GETPARAM_VRAM_BAR_SIZE
+ *
+ * Query the VRAM BAR size in bytes.
+ */
+#define NOVA_GETPARAM_VRAM_BAR_SIZE	0x1
+
+/**
+ * struct drm_nova_getparam - query GPU and driver metadata
+ */
+struct drm_nova_getparam {
+	/**
+	 * @param: The identifier of the parameter to query.
+	 */
+	__u64 param;
+
+	/**
+	 * @value: The value for the specified parameter.
+	 */
+	__u64 value;
+};
+
+/**
+ * struct drm_nova_gem_create - create a new DRM GEM object
+ */
+struct drm_nova_gem_create {
+	/**
+	 * @handle: The handle of the new DRM GEM object.
+	 */
+	__u32 handle;
+
+	/**
+	 * @pad: 32 bit padding, should be 0.
+	 */
+	__u32 pad;
+
+	/**
+	 * @size: The size of the new DRM GEM object.
+	 */
+	__u64 size;
+};
+
+/**
+ * struct drm_nova_gem_info - query DRM GEM object metadata
+ */
+struct drm_nova_gem_info {
+	/**
+	 * @handle: The handle of the DRM GEM object to query.
+	 */
+	__u32 handle;
+
+	/**
+	 * @pad: 32 bit padding, should be 0.
+	 */
+	__u32 pad;
+
+	/**
+	 * @size: The size of the DRM GEM obejct.
+	 */
+	__u64 size;
+};
+
+#define DRM_NOVA_GETPARAM		0x00
+#define DRM_NOVA_GEM_CREATE		0x01
+#define DRM_NOVA_GEM_INFO		0x02
+
+/* Note: this is an enum so that it can be resolved by Rust bindgen. */
+enum {
+	DRM_IOCTL_NOVA_GETPARAM		= DRM_IOWR(DRM_COMMAND_BASE + DRM_NOVA_GETPARAM,
+						   struct drm_nova_getparam),
+	DRM_IOCTL_NOVA_GEM_CREATE	= DRM_IOWR(DRM_COMMAND_BASE + DRM_NOVA_GEM_CREATE,
+						   struct drm_nova_gem_create),
+	DRM_IOCTL_NOVA_GEM_INFO		= DRM_IOWR(DRM_COMMAND_BASE + DRM_NOVA_GEM_INFO,
+						   struct drm_nova_gem_info),
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __NOVA_DRM_H__ */
diff --git a/include/uapi/drm/omap_drm.h b/include/uapi/drm/omap_drm.h
new file mode 100644
index 000000000..5a142fad4
--- /dev/null
+++ b/include/uapi/drm/omap_drm.h
@@ -0,0 +1,126 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * include/uapi/drm/omap_drm.h
+ *
+ * Copyright (C) 2011 Texas Instruments
+ * Author: Rob Clark <rob@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __OMAP_DRM_H__
+#define __OMAP_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.
+ */
+
+#define OMAP_PARAM_CHIPSET_ID	1	/* ie. 0x3430, 0x4430, etc */
+
+struct drm_omap_param {
+	__u64 param;			/* in */
+	__u64 value;			/* in (set_param), out (get_param) */
+};
+
+/* Scanout buffer, consumable by DSS */
+#define OMAP_BO_SCANOUT		0x00000001
+
+/* Buffer CPU caching mode: cached, write-combining or uncached. */
+#define OMAP_BO_CACHED		0x00000000
+#define OMAP_BO_WC		0x00000002
+#define OMAP_BO_UNCACHED	0x00000004
+#define OMAP_BO_CACHE_MASK	0x00000006
+
+/* Use TILER for the buffer. The TILER container unit can be 8, 16 or 32 bits. */
+#define OMAP_BO_TILED_8		0x00000100
+#define OMAP_BO_TILED_16	0x00000200
+#define OMAP_BO_TILED_32	0x00000300
+#define OMAP_BO_TILED_MASK	0x00000f00
+
+union omap_gem_size {
+	__u32 bytes;		/* (for non-tiled formats) */
+	struct {
+		__u16 width;
+		__u16 height;
+	} tiled;		/* (for tiled formats) */
+};
+
+struct drm_omap_gem_new {
+	union omap_gem_size size;	/* in */
+	__u32 flags;			/* in */
+	__u32 handle;			/* out */
+	__u32 __pad;
+};
+
+/* mask of operations: */
+enum omap_gem_op {
+	OMAP_GEM_READ = 0x01,
+	OMAP_GEM_WRITE = 0x02,
+};
+
+struct drm_omap_gem_cpu_prep {
+	__u32 handle;			/* buffer handle (in) */
+	__u32 op;			/* mask of omap_gem_op (in) */
+};
+
+struct drm_omap_gem_cpu_fini {
+	__u32 handle;			/* buffer handle (in) */
+	__u32 op;			/* mask of omap_gem_op (in) */
+	/* TODO maybe here we pass down info about what regions are touched
+	 * by sw so we can be clever about cache ops?  For now a placeholder,
+	 * set to zero and we just do full buffer flush..
+	 */
+	__u32 nregions;
+	__u32 __pad;
+};
+
+struct drm_omap_gem_info {
+	__u32 handle;			/* buffer handle (in) */
+	__u32 pad;
+	__u64 offset;			/* mmap offset (out) */
+	/* note: in case of tiled buffers, the user virtual size can be
+	 * different from the physical size (ie. how many pages are needed
+	 * to back the object) which is returned in DRM_IOCTL_GEM_OPEN..
+	 * This size here is the one that should be used if you want to
+	 * mmap() the buffer:
+	 */
+	__u32 size;			/* virtual size for mmap'ing (out) */
+	__u32 __pad;
+};
+
+#define DRM_OMAP_GET_PARAM		0x00
+#define DRM_OMAP_SET_PARAM		0x01
+#define DRM_OMAP_GEM_NEW		0x03
+#define DRM_OMAP_GEM_CPU_PREP		0x04	/* Deprecated, to be removed */
+#define DRM_OMAP_GEM_CPU_FINI		0x05	/* Deprecated, to be removed */
+#define DRM_OMAP_GEM_INFO		0x06
+#define DRM_OMAP_NUM_IOCTLS		0x07
+
+#define DRM_IOCTL_OMAP_GET_PARAM	DRM_IOWR(DRM_COMMAND_BASE + DRM_OMAP_GET_PARAM, struct drm_omap_param)
+#define DRM_IOCTL_OMAP_SET_PARAM	DRM_IOW (DRM_COMMAND_BASE + DRM_OMAP_SET_PARAM, struct drm_omap_param)
+#define DRM_IOCTL_OMAP_GEM_NEW		DRM_IOWR(DRM_COMMAND_BASE + DRM_OMAP_GEM_NEW, struct drm_omap_gem_new)
+#define DRM_IOCTL_OMAP_GEM_CPU_PREP	DRM_IOW (DRM_COMMAND_BASE + DRM_OMAP_GEM_CPU_PREP, struct drm_omap_gem_cpu_prep)
+#define DRM_IOCTL_OMAP_GEM_CPU_FINI	DRM_IOW (DRM_COMMAND_BASE + DRM_OMAP_GEM_CPU_FINI, struct drm_omap_gem_cpu_fini)
+#define DRM_IOCTL_OMAP_GEM_INFO		DRM_IOWR(DRM_COMMAND_BASE + DRM_OMAP_GEM_INFO, struct drm_omap_gem_info)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __OMAP_DRM_H__ */
diff --git a/include/uapi/drm/panfrost_drm.h b/include/uapi/drm/panfrost_drm.h
new file mode 100644
index 000000000..50d5337f3
--- /dev/null
+++ b/include/uapi/drm/panfrost_drm.h
@@ -0,0 +1,476 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2014-2018 Broadcom
+ * Copyright © 2019 Collabora ltd.
+ */
+#ifndef _PANFROST_DRM_H_
+#define _PANFROST_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_PANFROST_SUBMIT			0x00
+#define DRM_PANFROST_WAIT_BO			0x01
+#define DRM_PANFROST_CREATE_BO			0x02
+#define DRM_PANFROST_MMAP_BO			0x03
+#define DRM_PANFROST_GET_PARAM			0x04
+#define DRM_PANFROST_GET_BO_OFFSET		0x05
+#define DRM_PANFROST_PERFCNT_ENABLE		0x06
+#define DRM_PANFROST_PERFCNT_DUMP		0x07
+#define DRM_PANFROST_MADVISE			0x08
+#define DRM_PANFROST_SET_LABEL_BO		0x09
+#define DRM_PANFROST_JM_CTX_CREATE		0x0a
+#define DRM_PANFROST_JM_CTX_DESTROY		0x0b
+#define DRM_PANFROST_SYNC_BO			0x0c
+#define DRM_PANFROST_QUERY_BO_INFO		0x0d
+
+#define DRM_IOCTL_PANFROST_SUBMIT		DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_SUBMIT, struct drm_panfrost_submit)
+#define DRM_IOCTL_PANFROST_WAIT_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_WAIT_BO, struct drm_panfrost_wait_bo)
+#define DRM_IOCTL_PANFROST_CREATE_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_CREATE_BO, struct drm_panfrost_create_bo)
+#define DRM_IOCTL_PANFROST_MMAP_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_MMAP_BO, struct drm_panfrost_mmap_bo)
+#define DRM_IOCTL_PANFROST_GET_PARAM		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_GET_PARAM, struct drm_panfrost_get_param)
+#define DRM_IOCTL_PANFROST_GET_BO_OFFSET	DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_GET_BO_OFFSET, struct drm_panfrost_get_bo_offset)
+#define DRM_IOCTL_PANFROST_MADVISE		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_MADVISE, struct drm_panfrost_madvise)
+#define DRM_IOCTL_PANFROST_SET_LABEL_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_SET_LABEL_BO, struct drm_panfrost_set_label_bo)
+#define DRM_IOCTL_PANFROST_JM_CTX_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_JM_CTX_CREATE, struct drm_panfrost_jm_ctx_create)
+#define DRM_IOCTL_PANFROST_JM_CTX_DESTROY	DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_JM_CTX_DESTROY, struct drm_panfrost_jm_ctx_destroy)
+#define DRM_IOCTL_PANFROST_SYNC_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_SYNC_BO, struct drm_panfrost_sync_bo)
+#define DRM_IOCTL_PANFROST_QUERY_BO_INFO	DRM_IOWR(DRM_COMMAND_BASE + DRM_PANFROST_QUERY_BO_INFO, struct drm_panfrost_query_bo_info)
+
+/*
+ * Unstable ioctl(s): only exposed when the unsafe unstable_ioctls module
+ * param is set to true.
+ * All these ioctl(s) are subject to deprecation, so please don't rely on
+ * them for anything but debugging purpose.
+ */
+#define DRM_IOCTL_PANFROST_PERFCNT_ENABLE	DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_PERFCNT_ENABLE, struct drm_panfrost_perfcnt_enable)
+#define DRM_IOCTL_PANFROST_PERFCNT_DUMP		DRM_IOW(DRM_COMMAND_BASE + DRM_PANFROST_PERFCNT_DUMP, struct drm_panfrost_perfcnt_dump)
+
+#define PANFROST_JD_REQ_FS (1 << 0)
+#define PANFROST_JD_REQ_CYCLE_COUNT (1 << 1)
+/**
+ * struct drm_panfrost_submit - ioctl argument for submitting commands to the 3D
+ * engine.
+ *
+ * This asks the kernel to have the GPU execute a render command list.
+ */
+struct drm_panfrost_submit {
+	/**
+	 * @jc: Address to GPU mapping of job descriptor
+	 */
+	__u64 jc;
+	/**
+	 * @in_syncs: An optional array of sync objects to wait on
+	 * before starting this job.
+	 */
+	__u64 in_syncs;
+	/**
+	 * @in_sync_count: Number of sync objects to wait on before
+	 * starting this job.
+	 */
+	__u32 in_sync_count;
+	/**
+	 * @out_sync: An optional sync object to place the completion fence in.
+	 */
+	__u32 out_sync;
+	/**
+	 * @bo_handles: Pointer to a u32 array of the BOs that are
+	 * referenced by the job.
+	 */
+	__u64 bo_handles;
+	/**
+	 * @bo_handle_count: Number of BO handles passed in (size is
+	 * that times 4).
+	 */
+	__u32 bo_handle_count;
+	/**
+	 * @requirements: A combination of PANFROST_JD_REQ_*
+	 */
+	__u32 requirements;
+	/**
+	 * @jm_ctx_handle: JM context handle. Zero if you want to use the
+	 * default context.
+	 */
+	__u32 jm_ctx_handle;
+	/**
+	 * @pad: Padding field. Must be zero.
+	 */
+	__u32 pad;
+};
+
+/**
+ * struct drm_panfrost_wait_bo - ioctl argument for waiting for
+ * completion of the last DRM_PANFROST_SUBMIT on a BO.
+ *
+ * This is useful for cases where multiple processes might be
+ * rendering to a BO and you want to wait for all rendering to be
+ * completed.
+ */
+struct drm_panfrost_wait_bo {
+	/**
+	 * @handle: Handle for the object to wait for.
+	 */
+	__u32 handle;
+	/**
+	 * @pad: Padding, must be zero-filled.
+	 */
+	__u32 pad;
+	/**
+	 * @timeout_ns: absolute number of nanoseconds to wait.
+	 */
+	__s64 timeout_ns;
+};
+
+/* Valid flags to pass to drm_panfrost_create_bo.
+ * PANFROST_BO_WB_MMAP can't be set if PANFROST_BO_HEAP is.
+ */
+#define PANFROST_BO_NOEXEC	1
+#define PANFROST_BO_HEAP	2
+#define PANFROST_BO_WB_MMAP	4
+
+/**
+ * struct drm_panfrost_create_bo - ioctl argument for creating Panfrost BOs.
+ *
+ * The flags argument is a bit mask of PANFROST_BO_* flags.
+ */
+struct drm_panfrost_create_bo {
+	/**
+	 * @size: size of shmem/BO area to create (bytes)
+	 */
+	__u32 size;
+	/**
+	 * @flags: see PANFROST_BO_* flags
+	 */
+	__u32 flags;
+	/**
+	 * @handle: Returned GEM handle for the BO.
+	 */
+	__u32 handle;
+	/**
+	 * @pad: Padding, must be zero-filled.
+	 */
+	__u32 pad;
+	/**
+	 * @offset: Returned offset for the BO in the GPU address space.
+	 * This offset is private to the DRM fd and is valid for the
+	 * lifetime of the GEM handle.
+	 *
+	 * This offset value will always be nonzero, since various HW
+	 * units treat 0 specially.
+	 */
+	__u64 offset;
+};
+
+/**
+ * struct drm_panfrost_mmap_bo - ioctl argument for mapping Panfrost BOs.
+ *
+ * This doesn't actually perform an mmap.  Instead, it returns the
+ * offset you need to use in an mmap on the DRM device node.  This
+ * means that tools like valgrind end up knowing about the mapped
+ * memory.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_panfrost_mmap_bo {
+	/**
+	 * @handle: Handle for the object being mapped.
+	 */
+	__u32 handle;
+	/**
+	 * @flags: currently not used (should be zero)
+	 */
+	__u32 flags;
+	/**
+	 * @offset: offset into the drm node to use for subsequent mmap call.
+	 */
+	__u64 offset;
+};
+
+enum drm_panfrost_param {
+	DRM_PANFROST_PARAM_GPU_PROD_ID,
+	DRM_PANFROST_PARAM_GPU_REVISION,
+	DRM_PANFROST_PARAM_SHADER_PRESENT,
+	DRM_PANFROST_PARAM_TILER_PRESENT,
+	DRM_PANFROST_PARAM_L2_PRESENT,
+	DRM_PANFROST_PARAM_STACK_PRESENT,
+	DRM_PANFROST_PARAM_AS_PRESENT,
+	DRM_PANFROST_PARAM_JS_PRESENT,
+	DRM_PANFROST_PARAM_L2_FEATURES,
+	DRM_PANFROST_PARAM_CORE_FEATURES,
+	DRM_PANFROST_PARAM_TILER_FEATURES,
+	DRM_PANFROST_PARAM_MEM_FEATURES,
+	DRM_PANFROST_PARAM_MMU_FEATURES,
+	DRM_PANFROST_PARAM_THREAD_FEATURES,
+	DRM_PANFROST_PARAM_MAX_THREADS,
+	DRM_PANFROST_PARAM_THREAD_MAX_WORKGROUP_SZ,
+	DRM_PANFROST_PARAM_THREAD_MAX_BARRIER_SZ,
+	DRM_PANFROST_PARAM_COHERENCY_FEATURES,
+	DRM_PANFROST_PARAM_TEXTURE_FEATURES0,
+	DRM_PANFROST_PARAM_TEXTURE_FEATURES1,
+	DRM_PANFROST_PARAM_TEXTURE_FEATURES2,
+	DRM_PANFROST_PARAM_TEXTURE_FEATURES3,
+	DRM_PANFROST_PARAM_JS_FEATURES0,
+	DRM_PANFROST_PARAM_JS_FEATURES1,
+	DRM_PANFROST_PARAM_JS_FEATURES2,
+	DRM_PANFROST_PARAM_JS_FEATURES3,
+	DRM_PANFROST_PARAM_JS_FEATURES4,
+	DRM_PANFROST_PARAM_JS_FEATURES5,
+	DRM_PANFROST_PARAM_JS_FEATURES6,
+	DRM_PANFROST_PARAM_JS_FEATURES7,
+	DRM_PANFROST_PARAM_JS_FEATURES8,
+	DRM_PANFROST_PARAM_JS_FEATURES9,
+	DRM_PANFROST_PARAM_JS_FEATURES10,
+	DRM_PANFROST_PARAM_JS_FEATURES11,
+	DRM_PANFROST_PARAM_JS_FEATURES12,
+	DRM_PANFROST_PARAM_JS_FEATURES13,
+	DRM_PANFROST_PARAM_JS_FEATURES14,
+	DRM_PANFROST_PARAM_JS_FEATURES15,
+	DRM_PANFROST_PARAM_NR_CORE_GROUPS,
+	DRM_PANFROST_PARAM_THREAD_TLS_ALLOC,
+	DRM_PANFROST_PARAM_AFBC_FEATURES,
+	DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP,
+	DRM_PANFROST_PARAM_SYSTEM_TIMESTAMP_FREQUENCY,
+	DRM_PANFROST_PARAM_ALLOWED_JM_CTX_PRIORITIES,
+	DRM_PANFROST_PARAM_SELECTED_COHERENCY,
+};
+
+enum drm_panfrost_gpu_coherency {
+	DRM_PANFROST_GPU_COHERENCY_ACE_LITE = 0,
+	DRM_PANFROST_GPU_COHERENCY_ACE = 1,
+	DRM_PANFROST_GPU_COHERENCY_NONE = 31,
+};
+
+struct drm_panfrost_get_param {
+	__u32 param;
+	__u32 pad;
+	__u64 value;
+};
+
+/*
+ * Returns the offset for the BO in the GPU address space for this DRM fd.
+ * This is the same value returned by drm_panfrost_create_bo, if that was called
+ * from this DRM fd.
+ */
+struct drm_panfrost_get_bo_offset {
+	__u32 handle;
+	__u32 pad;
+	__u64 offset;
+};
+
+struct drm_panfrost_perfcnt_enable {
+	__u32 enable;
+	/*
+	 * On bifrost we have 2 sets of counters, this parameter defines the
+	 * one to track.
+	 */
+	__u32 counterset;
+};
+
+struct drm_panfrost_perfcnt_dump {
+	__u64 buf_ptr;
+};
+
+/* madvise provides a way to tell the kernel in case a buffers contents
+ * can be discarded under memory pressure, which is useful for userspace
+ * bo cache where we want to optimistically hold on to buffer allocate
+ * and potential mmap, but allow the pages to be discarded under memory
+ * pressure.
+ *
+ * Typical usage would involve madvise(DONTNEED) when buffer enters BO
+ * cache, and madvise(WILLNEED) if trying to recycle buffer from BO cache.
+ * In the WILLNEED case, 'retained' indicates to userspace whether the
+ * backing pages still exist.
+ */
+#define PANFROST_MADV_WILLNEED 0	/* backing pages are needed, status returned in 'retained' */
+#define PANFROST_MADV_DONTNEED 1	/* backing pages not needed */
+
+struct drm_panfrost_madvise {
+	__u32 handle;         /* in, GEM handle */
+	__u32 madv;           /* in, PANFROST_MADV_x */
+	__u32 retained;       /* out, whether backing store still exists */
+};
+
+/**
+ * struct drm_panfrost_set_label_bo - ioctl argument for labelling Panfrost BOs.
+ */
+struct drm_panfrost_set_label_bo {
+	/**
+	 * @handle: Handle of the buffer object to label.
+	 */
+	__u32 handle;
+	/**
+	 * @pad: Must be zero.
+	 */
+	__u32 pad;
+	/**
+	 * @label: User pointer to a NUL-terminated string
+	 *
+	 * Length cannot be greater than 4096.
+	 * NULL is permitted and means clear the label.
+	 */
+	__u64 label;
+};
+
+/* Valid flags to pass to drm_panfrost_bo_sync_op */
+#define PANFROST_BO_SYNC_CPU_CACHE_FLUSH			0
+#define PANFROST_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE		1
+
+/**
+ * struct drm_panthor_bo_flush_map_op - BO map sync op
+ */
+struct drm_panfrost_bo_sync_op {
+	/** @handle: Handle of the buffer object to sync. */
+	__u32 handle;
+
+	/** @type: Type of sync operation. */
+	__u32 type;
+
+	/**
+	 * @offset: Offset into the BO at which the sync range starts.
+	 *
+	 * This will be rounded down to the nearest cache line as needed.
+	 */
+	__u32 offset;
+
+	/**
+	 * @size: Size of the range to sync
+	 *
+	 * @size + @offset will be rounded up to the nearest cache line as
+	 * needed.
+	 */
+	__u32 size;
+};
+
+/**
+ * struct drm_panfrost_sync_bo - ioctl argument for syncing BO maps
+ */
+struct drm_panfrost_sync_bo {
+	/** Array of struct drm_panfrost_bo_sync_op */
+	__u64 ops;
+
+	/** Number of BO sync ops */
+	__u32 op_count;
+
+	__u32 pad;
+};
+
+/** BO comes from a different subsystem. */
+#define DRM_PANFROST_BO_IS_IMPORTED (1 << 0)
+
+struct drm_panfrost_query_bo_info {
+	/** Handle of the object being queried. */
+	__u32 handle;
+
+	/** Extra flags that are not coming from the BO_CREATE ioctl(). */
+	__u32 extra_flags;
+
+	/** Flags passed at creation time. */
+	__u32 create_flags;
+
+	/** Will be zero on return. */
+	__u32 pad;
+};
+
+/* Definitions for coredump decoding in user space */
+#define PANFROSTDUMP_MAJOR 1
+#define PANFROSTDUMP_MINOR 0
+
+#define PANFROSTDUMP_MAGIC 0x464E4150 /* PANF */
+
+#define PANFROSTDUMP_BUF_REG 0
+#define PANFROSTDUMP_BUF_BOMAP (PANFROSTDUMP_BUF_REG + 1)
+#define PANFROSTDUMP_BUF_BO (PANFROSTDUMP_BUF_BOMAP + 1)
+#define PANFROSTDUMP_BUF_TRAILER (PANFROSTDUMP_BUF_BO + 1)
+
+/*
+ * This structure is the native endianness of the dumping machine, tools can
+ * detect the endianness by looking at the value in 'magic'.
+ */
+struct panfrost_dump_object_header {
+	__u32 magic;
+	__u32 type;
+	__u32 file_size;
+	__u32 file_offset;
+
+	union {
+		struct {
+			__u64 jc;
+			__u32 gpu_id;
+			__u32 major;
+			__u32 minor;
+			__u64 nbos;
+		} reghdr;
+
+		struct {
+			__u32 valid;
+			__u64 iova;
+			__u32 data[2];
+		} bomap;
+
+		/*
+		 * Force same size in case we want to expand the header
+		 * with new fields and also keep it 512-byte aligned
+		 */
+
+		__u32 sizer[496];
+	};
+};
+
+/* Registers object, an array of these */
+struct panfrost_dump_registers {
+	__u32 reg;
+	__u32 value;
+};
+
+enum drm_panfrost_jm_ctx_priority {
+	/**
+	 * @PANFROST_JM_CTX_PRIORITY_LOW: Low priority context.
+	 */
+	PANFROST_JM_CTX_PRIORITY_LOW = 0,
+
+	/**
+	 * @PANFROST_JM_CTX_PRIORITY_MEDIUM: Medium priority context.
+	 */
+	PANFROST_JM_CTX_PRIORITY_MEDIUM,
+
+	/**
+	 * @PANFROST_JM_CTX_PRIORITY_HIGH: High priority context.
+	 *
+	 * Requires CAP_SYS_NICE or DRM_MASTER.
+	 */
+	PANFROST_JM_CTX_PRIORITY_HIGH,
+};
+
+struct drm_panfrost_jm_ctx_create {
+	/**
+	 * @handle: Handle of the created JM context
+	 */
+	__u32 handle;
+	/**
+	 * @priority: Context priority (see enum drm_panfrost_jm_ctx_priority).
+	 */
+	__u32 priority;
+};
+
+struct drm_panfrost_jm_ctx_destroy {
+	/**
+	 * @handle: Handle of the JM context to destroy.
+	 *
+	 * Must be a valid context handle returned by DRM_IOCTL_PANTHOR_JM_CTX_CREATE.
+	 */
+	__u32 handle;
+	/**
+	 * @pad: Padding field, must be zero.
+	 */
+	__u32 pad;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _PANFROST_DRM_H_ */
diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h
new file mode 100644
index 000000000..a2ff0f4ec
--- /dev/null
+++ b/include/uapi/drm/panthor_drm.h
@@ -0,0 +1,1329 @@
+/* SPDX-License-Identifier: MIT */
+/* Copyright (C) 2023 Collabora ltd. */
+#ifndef _PANTHOR_DRM_H_
+#define _PANTHOR_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * DOC: Introduction
+ *
+ * This documentation describes the Panthor IOCTLs.
+ *
+ * Just a few generic rules about the data passed to the Panthor IOCTLs:
+ *
+ * - Structures must be aligned on 64-bit/8-byte. If the object is not
+ *   naturally aligned, a padding field must be added.
+ * - Fields must be explicitly aligned to their natural type alignment with
+ *   pad[0..N] fields.
+ * - All padding fields will be checked by the driver to make sure they are
+ *   zeroed.
+ * - Flags can be added, but not removed/replaced.
+ * - New fields can be added to the main structures (the structures
+ *   directly passed to the ioctl). Those fields can be added at the end of
+ *   the structure, or replace existing padding fields. Any new field being
+ *   added must preserve the behavior that existed before those fields were
+ *   added when a value of zero is passed.
+ * - New fields can be added to indirect objects (objects pointed by the
+ *   main structure), iff those objects are passed a size to reflect the
+ *   size known by the userspace driver (see drm_panthor_obj_array::stride
+ *   or drm_panthor_dev_query::size).
+ * - If the kernel driver is too old to know some fields, those will be
+ *   ignored if zero, and otherwise rejected (and so will be zero on output).
+ * - If userspace is too old to know some fields, those will be zeroed
+ *   (input) before the structure is parsed by the kernel driver.
+ * - Each new flag/field addition must come with a driver version update so
+ *   the userspace driver doesn't have to trial and error to know which
+ *   flags are supported.
+ * - Structures should not contain unions, as this would defeat the
+ *   extensibility of such structures.
+ * - IOCTLs can't be removed or replaced. New IOCTL IDs should be placed
+ *   at the end of the drm_panthor_ioctl_id enum.
+ */
+
+/**
+ * DOC: MMIO regions exposed to userspace.
+ *
+ * .. c:macro:: DRM_PANTHOR_USER_MMIO_OFFSET
+ *
+ * File offset for all MMIO regions being exposed to userspace. Don't use
+ * this value directly, use DRM_PANTHOR_USER_<name>_OFFSET values instead.
+ * pgoffset passed to mmap2() is an unsigned long, which forces us to use a
+ * different offset on 32-bit and 64-bit systems.
+ *
+ * .. c:macro:: DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET
+ *
+ * File offset for the LATEST_FLUSH_ID register. The Userspace driver controls
+ * GPU cache flushing through CS instructions, but the flush reduction
+ * mechanism requires a flush_id. This flush_id could be queried with an
+ * ioctl, but Arm provides a well-isolated register page containing only this
+ * read-only register, so let's expose this page through a static mmap offset
+ * and allow direct mapping of this MMIO region so we can avoid the
+ * user <-> kernel round-trip.
+ */
+#define DRM_PANTHOR_USER_MMIO_OFFSET_32BIT	(1ull << 43)
+#define DRM_PANTHOR_USER_MMIO_OFFSET_64BIT	(1ull << 56)
+#define DRM_PANTHOR_USER_MMIO_OFFSET		(sizeof(unsigned long) < 8 ? \
+						 DRM_PANTHOR_USER_MMIO_OFFSET_32BIT : \
+						 DRM_PANTHOR_USER_MMIO_OFFSET_64BIT)
+#define DRM_PANTHOR_USER_FLUSH_ID_MMIO_OFFSET	(DRM_PANTHOR_USER_MMIO_OFFSET | 0)
+
+/**
+ * DOC: IOCTL IDs
+ *
+ * enum drm_panthor_ioctl_id - IOCTL IDs
+ *
+ * Place new ioctls at the end, don't re-order, don't replace or remove entries.
+ *
+ * These IDs are not meant to be used directly. Use the DRM_IOCTL_PANTHOR_xxx
+ * definitions instead.
+ */
+enum drm_panthor_ioctl_id {
+	/** @DRM_PANTHOR_DEV_QUERY: Query device information. */
+	DRM_PANTHOR_DEV_QUERY = 0,
+
+	/** @DRM_PANTHOR_VM_CREATE: Create a VM. */
+	DRM_PANTHOR_VM_CREATE,
+
+	/** @DRM_PANTHOR_VM_DESTROY: Destroy a VM. */
+	DRM_PANTHOR_VM_DESTROY,
+
+	/** @DRM_PANTHOR_VM_BIND: Bind/unbind memory to a VM. */
+	DRM_PANTHOR_VM_BIND,
+
+	/** @DRM_PANTHOR_VM_GET_STATE: Get VM state. */
+	DRM_PANTHOR_VM_GET_STATE,
+
+	/** @DRM_PANTHOR_BO_CREATE: Create a buffer object. */
+	DRM_PANTHOR_BO_CREATE,
+
+	/**
+	 * @DRM_PANTHOR_BO_MMAP_OFFSET: Get the file offset to pass to
+	 * mmap to map a GEM object.
+	 */
+	DRM_PANTHOR_BO_MMAP_OFFSET,
+
+	/** @DRM_PANTHOR_GROUP_CREATE: Create a scheduling group. */
+	DRM_PANTHOR_GROUP_CREATE,
+
+	/** @DRM_PANTHOR_GROUP_DESTROY: Destroy a scheduling group. */
+	DRM_PANTHOR_GROUP_DESTROY,
+
+	/**
+	 * @DRM_PANTHOR_GROUP_SUBMIT: Submit jobs to queues belonging
+	 * to a specific scheduling group.
+	 */
+	DRM_PANTHOR_GROUP_SUBMIT,
+
+	/** @DRM_PANTHOR_GROUP_GET_STATE: Get the state of a scheduling group. */
+	DRM_PANTHOR_GROUP_GET_STATE,
+
+	/** @DRM_PANTHOR_TILER_HEAP_CREATE: Create a tiler heap. */
+	DRM_PANTHOR_TILER_HEAP_CREATE,
+
+	/** @DRM_PANTHOR_TILER_HEAP_DESTROY: Destroy a tiler heap. */
+	DRM_PANTHOR_TILER_HEAP_DESTROY,
+
+	/** @DRM_PANTHOR_BO_SET_LABEL: Label a BO. */
+	DRM_PANTHOR_BO_SET_LABEL,
+
+	/**
+	 * @DRM_PANTHOR_SET_USER_MMIO_OFFSET: Set the offset to use as the user MMIO offset.
+	 *
+	 * The default behavior is to pick the MMIO offset based on the size of the pgoff_t
+	 * type seen by the process that manipulates the FD, such that a 32-bit process can
+	 * always map the user MMIO ranges. But this approach doesn't work well for emulators
+	 * like FEX, where the emulator is an 64-bit binary which might be executing 32-bit
+	 * code. In that case, the kernel thinks it's the 64-bit process and assumes
+	 * DRM_PANTHOR_USER_MMIO_OFFSET_64BIT is in use, but the UMD library expects
+	 * DRM_PANTHOR_USER_MMIO_OFFSET_32BIT, because it can't mmap() anything above the
+	 * pgoff_t size.
+	 */
+	DRM_PANTHOR_SET_USER_MMIO_OFFSET,
+
+	/** @DRM_PANTHOR_BO_SYNC: Sync BO data to/from the device */
+	DRM_PANTHOR_BO_SYNC,
+
+	/**
+	 * @DRM_PANTHOR_BO_QUERY_INFO: Query information about a BO.
+	 *
+	 * This is useful for imported BOs.
+	 */
+	DRM_PANTHOR_BO_QUERY_INFO,
+};
+
+/**
+ * DOC: IOCTL arguments
+ */
+
+/**
+ * struct drm_panthor_obj_array - Object array.
+ *
+ * This object is used to pass an array of objects whose size is subject to changes in
+ * future versions of the driver. In order to support this mutability, we pass a stride
+ * describing the size of the object as known by userspace.
+ *
+ * You shouldn't fill drm_panthor_obj_array fields directly. You should instead use
+ * the DRM_PANTHOR_OBJ_ARRAY() macro that takes care of initializing the stride to
+ * the object size.
+ */
+struct drm_panthor_obj_array {
+	/** @stride: Stride of object struct. Used for versioning. */
+	__u32 stride;
+
+	/** @count: Number of objects in the array. */
+	__u32 count;
+
+	/** @array: User pointer to an array of objects. */
+	__u64 array;
+};
+
+/**
+ * DRM_PANTHOR_OBJ_ARRAY() - Initialize a drm_panthor_obj_array field.
+ * @cnt: Number of elements in the array.
+ * @ptr: Pointer to the array to pass to the kernel.
+ *
+ * Macro initializing a drm_panthor_obj_array based on the object size as known
+ * by userspace.
+ */
+#define DRM_PANTHOR_OBJ_ARRAY(cnt, ptr) \
+	{ .stride = sizeof((ptr)[0]), .count = (cnt), .array = (__u64)(uintptr_t)(ptr) }
+
+/**
+ * enum drm_panthor_sync_op_flags - Synchronization operation flags.
+ */
+enum drm_panthor_sync_op_flags {
+	/** @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK: Synchronization handle type mask. */
+	DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK = 0xff,
+
+	/** @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_SYNCOBJ: Synchronization object type. */
+	DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_SYNCOBJ = 0,
+
+	/**
+	 * @DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ: Timeline synchronization
+	 * object type.
+	 */
+	DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ = 1,
+
+	/** @DRM_PANTHOR_SYNC_OP_WAIT: Wait operation. */
+	DRM_PANTHOR_SYNC_OP_WAIT = 0 << 31,
+
+	/** @DRM_PANTHOR_SYNC_OP_SIGNAL: Signal operation. */
+	DRM_PANTHOR_SYNC_OP_SIGNAL = (int)(1u << 31),
+};
+
+/**
+ * struct drm_panthor_sync_op - Synchronization operation.
+ */
+struct drm_panthor_sync_op {
+	/** @flags: Synchronization operation flags. Combination of DRM_PANTHOR_SYNC_OP values. */
+	__u32 flags;
+
+	/** @handle: Sync handle. */
+	__u32 handle;
+
+	/**
+	 * @timeline_value: MBZ if
+	 * (flags & DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_MASK) !=
+	 * DRM_PANTHOR_SYNC_OP_HANDLE_TYPE_TIMELINE_SYNCOBJ.
+	 */
+	__u64 timeline_value;
+};
+
+/**
+ * enum drm_panthor_dev_query_type - Query type
+ *
+ * Place new types at the end, don't re-order, don't remove or replace.
+ */
+enum drm_panthor_dev_query_type {
+	/** @DRM_PANTHOR_DEV_QUERY_GPU_INFO: Query GPU information. */
+	DRM_PANTHOR_DEV_QUERY_GPU_INFO = 0,
+
+	/** @DRM_PANTHOR_DEV_QUERY_CSIF_INFO: Query command-stream interface information. */
+	DRM_PANTHOR_DEV_QUERY_CSIF_INFO,
+
+	/** @DRM_PANTHOR_DEV_QUERY_TIMESTAMP_INFO: Query timestamp information. */
+	DRM_PANTHOR_DEV_QUERY_TIMESTAMP_INFO,
+
+	/**
+	 * @DRM_PANTHOR_DEV_QUERY_GROUP_PRIORITIES_INFO: Query allowed group priorities information.
+	 */
+	DRM_PANTHOR_DEV_QUERY_GROUP_PRIORITIES_INFO,
+
+	/** @DRM_PANTHOR_DEV_QUERY_MMU_INFO: Query MMU information. */
+	DRM_PANTHOR_DEV_QUERY_MMU_INFO,
+};
+
+/**
+ * enum drm_panthor_gpu_coherency: Type of GPU coherency
+ */
+enum drm_panthor_gpu_coherency {
+	/**
+	 * @DRM_PANTHOR_GPU_COHERENCY_ACE_LITE: ACE Lite coherency.
+	 */
+	DRM_PANTHOR_GPU_COHERENCY_ACE_LITE = 0,
+
+	/**
+	 * @DRM_PANTHOR_GPU_COHERENCY_ACE: ACE coherency.
+	 */
+	DRM_PANTHOR_GPU_COHERENCY_ACE = 1,
+
+	/**
+	 * @DRM_PANTHOR_GPU_COHERENCY_NONE: No coherency.
+	 */
+	DRM_PANTHOR_GPU_COHERENCY_NONE = 31,
+};
+
+/**
+ * struct drm_panthor_gpu_info - GPU information
+ *
+ * Structure grouping all queryable information relating to the GPU.
+ */
+struct drm_panthor_gpu_info {
+	/** @gpu_id : GPU ID. */
+	__u32 gpu_id;
+#define DRM_PANTHOR_ARCH_MAJOR(x)		((x) >> 28)
+#define DRM_PANTHOR_ARCH_MINOR(x)		(((x) >> 24) & 0xf)
+#define DRM_PANTHOR_ARCH_REV(x)			(((x) >> 20) & 0xf)
+#define DRM_PANTHOR_PRODUCT_MAJOR(x)		(((x) >> 16) & 0xf)
+#define DRM_PANTHOR_VERSION_MAJOR(x)		(((x) >> 12) & 0xf)
+#define DRM_PANTHOR_VERSION_MINOR(x)		(((x) >> 4) & 0xff)
+#define DRM_PANTHOR_VERSION_STATUS(x)		((x) & 0xf)
+
+	/** @gpu_rev: GPU revision. */
+	__u32 gpu_rev;
+
+	/** @csf_id: Command stream frontend ID. */
+	__u32 csf_id;
+#define DRM_PANTHOR_CSHW_MAJOR(x)		(((x) >> 26) & 0x3f)
+#define DRM_PANTHOR_CSHW_MINOR(x)		(((x) >> 20) & 0x3f)
+#define DRM_PANTHOR_CSHW_REV(x)			(((x) >> 16) & 0xf)
+#define DRM_PANTHOR_MCU_MAJOR(x)		(((x) >> 10) & 0x3f)
+#define DRM_PANTHOR_MCU_MINOR(x)		(((x) >> 4) & 0x3f)
+#define DRM_PANTHOR_MCU_REV(x)			((x) & 0xf)
+
+	/** @l2_features: L2-cache features. */
+	__u32 l2_features;
+
+	/** @tiler_features: Tiler features. */
+	__u32 tiler_features;
+
+	/** @mem_features: Memory features. */
+	__u32 mem_features;
+
+	/** @mmu_features: MMU features. */
+	__u32 mmu_features;
+#define DRM_PANTHOR_MMU_VA_BITS(x)		((x) & 0xff)
+
+	/** @thread_features: Thread features. */
+	__u32 thread_features;
+
+	/** @max_threads: Maximum number of threads. */
+	__u32 max_threads;
+
+	/** @thread_max_workgroup_size: Maximum workgroup size. */
+	__u32 thread_max_workgroup_size;
+
+	/**
+	 * @thread_max_barrier_size: Maximum number of threads that can wait
+	 * simultaneously on a barrier.
+	 */
+	__u32 thread_max_barrier_size;
+
+	/**
+	 * @coherency_features: Coherency features.
+	 *
+	 * Combination of drm_panthor_gpu_coherency flags.
+	 *
+	 * Note that this is just what the coherency protocols supported by the
+	 * GPU, but the actual coherency in place depends on the SoC
+	 * integration and is reflected by
+	 * drm_panthor_gpu_info::selected_coherency.
+	 */
+	__u32 coherency_features;
+
+	/** @texture_features: Texture features. */
+	__u32 texture_features[4];
+
+	/** @as_present: Bitmask encoding the number of address-space exposed by the MMU. */
+	__u32 as_present;
+
+	/**
+	 * @selected_coherency: Coherency selected for this device.
+	 *
+	 * One of drm_panthor_gpu_coherency.
+	 */
+	__u32 selected_coherency;
+
+	/** @shader_present: Bitmask encoding the shader cores exposed by the GPU. */
+	__u64 shader_present;
+
+	/** @l2_present: Bitmask encoding the L2 caches exposed by the GPU. */
+	__u64 l2_present;
+
+	/** @tiler_present: Bitmask encoding the tiler units exposed by the GPU. */
+	__u64 tiler_present;
+
+	/** @core_features: Used to discriminate core variants when they exist. */
+	__u32 core_features;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+
+	/** @gpu_features: Bitmask describing supported GPU-wide features */
+	__u64 gpu_features;
+};
+
+/**
+ * struct drm_panthor_csif_info - Command stream interface information
+ *
+ * Structure grouping all queryable information relating to the command stream interface.
+ */
+struct drm_panthor_csif_info {
+	/** @csg_slot_count: Number of command stream group slots exposed by the firmware. */
+	__u32 csg_slot_count;
+
+	/** @cs_slot_count: Number of command stream slots per group. */
+	__u32 cs_slot_count;
+
+	/** @cs_reg_count: Number of command stream registers. */
+	__u32 cs_reg_count;
+
+	/** @scoreboard_slot_count: Number of scoreboard slots. */
+	__u32 scoreboard_slot_count;
+
+	/**
+	 * @unpreserved_cs_reg_count: Number of command stream registers reserved by
+	 * the kernel driver to call a userspace command stream.
+	 *
+	 * All registers can be used by a userspace command stream, but the
+	 * [cs_slot_count - unpreserved_cs_reg_count .. cs_slot_count] registers are
+	 * used by the kernel when DRM_PANTHOR_IOCTL_GROUP_SUBMIT is called.
+	 */
+	__u32 unpreserved_cs_reg_count;
+
+	/**
+	 * @pad: Padding field, set to zero.
+	 */
+	__u32 pad;
+};
+
+/**
+ * enum drm_panthor_timestamp_info_flags - drm_panthor_timestamp_info.flags
+ */
+enum drm_panthor_timestamp_info_flags {
+	/** @DRM_PANTHOR_TIMESTAMP_GPU: Query GPU time. */
+	DRM_PANTHOR_TIMESTAMP_GPU = 1 << 0,
+
+	/** @DRM_PANTHOR_TIMESTAMP_CPU_NONE: Don't query CPU time. */
+	DRM_PANTHOR_TIMESTAMP_CPU_NONE = 0 << 1,
+
+	/** @DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC: Query CPU time using CLOCK_MONOTONIC. */
+	DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC = 1 << 1,
+
+	/** @DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC_RAW: Query CPU time using CLOCK_MONOTONIC_RAW. */
+	DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC_RAW = 2 << 1,
+
+	/** @DRM_PANTHOR_TIMESTAMP_CPU_TYPE_MASK: Space reserved for CPU clock type. */
+	DRM_PANTHOR_TIMESTAMP_CPU_TYPE_MASK = 7 << 1,
+
+	/** @DRM_PANTHOR_TIMESTAMP_GPU_OFFSET: Query GPU offset. */
+	DRM_PANTHOR_TIMESTAMP_GPU_OFFSET = 1 << 4,
+
+	/** @DRM_PANTHOR_TIMESTAMP_GPU_CYCLE_COUNT: Query GPU cycle count. */
+	DRM_PANTHOR_TIMESTAMP_GPU_CYCLE_COUNT = 1 << 5,
+
+	/** @DRM_PANTHOR_TIMESTAMP_FREQ: Query timestamp frequency. */
+	DRM_PANTHOR_TIMESTAMP_FREQ = 1 << 6,
+
+	/** @DRM_PANTHOR_TIMESTAMP_DURATION: Return duration of time query. */
+	DRM_PANTHOR_TIMESTAMP_DURATION = 1 << 7,
+};
+
+/**
+ * struct drm_panthor_timestamp_info - Timestamp information
+ *
+ * Structure grouping all queryable information relating to the GPU timestamp.
+ */
+struct drm_panthor_timestamp_info {
+	/**
+	 * @timestamp_frequency: The frequency of the timestamp timer or 0 if
+	 * unknown.
+	 */
+	__u64 timestamp_frequency;
+
+	/** @current_timestamp: The current GPU timestamp. */
+	__u64 current_timestamp;
+
+	/** @timestamp_offset: The offset of the GPU timestamp timer. */
+	__u64 timestamp_offset;
+
+	/**
+	 * @flags: Bitmask of drm_panthor_timestamp_info_flags.
+	 *
+	 * If set to 0, then it is interpreted as:
+	 *  DRM_PANTHOR_TIMESTAMP_GPU |
+	 *  DRM_PANTHOR_TIMESTAMP_GPU_OFFSET |
+	 *  DRM_PANTHOR_TIMESTAMP_FREQ
+	 *
+	 * Note: these flags are exclusive to each other (only one can be used):
+	 * - DRM_PANTHOR_TIMESTAMP_CPU_NONE
+	 * - DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC
+	 * - DRM_PANTHOR_TIMESTAMP_CPU_MONOTONIC_RAW
+	 */
+	__u32 flags;
+
+	/** @duration_nsec: Duration of time query. */
+	__u32 duration_nsec;
+
+	/** @cycle_count: Value of GPU_CYCLE_COUNT. */
+	__u64 cycle_count;
+
+	/** @cpu_timestamp_sec: Seconds part of CPU timestamp. */
+	__u64 cpu_timestamp_sec;
+
+	/** @cpu_timestamp_nsec: Nanseconds part of CPU timestamp. */
+	__u64 cpu_timestamp_nsec;
+};
+
+/**
+ * struct drm_panthor_mmu_info - MMU information
+ *
+ * Structure grouping all queryable information relating to the MMU.
+ */
+struct drm_panthor_mmu_info {
+	/** @page_size_bitmap: Allowed page sizes */
+	__u64 page_size_bitmap;
+};
+
+/**
+ * struct drm_panthor_group_priorities_info - Group priorities information
+ *
+ * Structure grouping all queryable information relating to the allowed group priorities.
+ */
+struct drm_panthor_group_priorities_info {
+	/**
+	 * @allowed_mask: Bitmask of the allowed group priorities.
+	 *
+	 * Each bit represents a variant of the enum drm_panthor_group_priority.
+	 */
+	__u8 allowed_mask;
+
+	/** @pad: Padding fields, MBZ. */
+	__u8 pad[3];
+};
+
+/**
+ * struct drm_panthor_dev_query - Arguments passed to DRM_PANTHOR_IOCTL_DEV_QUERY
+ */
+struct drm_panthor_dev_query {
+	/** @type: the query type (see drm_panthor_dev_query_type). */
+	__u32 type;
+
+	/**
+	 * @size: size of the type being queried.
+	 *
+	 * If pointer is NULL, size is updated by the driver to provide the
+	 * output structure size. If pointer is not NULL, the driver will
+	 * only copy min(size, actual_structure_size) bytes to the pointer,
+	 * and update the size accordingly. This allows us to extend query
+	 * types without breaking userspace.
+	 */
+	__u32 size;
+
+	/**
+	 * @pointer: user pointer to a query type struct.
+	 *
+	 * Pointer can be NULL, in which case, nothing is copied, but the
+	 * actual structure size is returned. If not NULL, it must point to
+	 * a location that's large enough to hold size bytes.
+	 */
+	__u64 pointer;
+};
+
+/**
+ * struct drm_panthor_vm_create - Arguments passed to DRM_PANTHOR_IOCTL_VM_CREATE
+ */
+struct drm_panthor_vm_create {
+	/** @flags: VM flags, MBZ. */
+	__u32 flags;
+
+	/** @id: Returned VM ID. */
+	__u32 id;
+
+	/**
+	 * @user_va_range: Size of the VA space reserved for user objects.
+	 *
+	 * The kernel will pick the remaining space to map kernel-only objects to the
+	 * VM (heap chunks, heap context, ring buffers, kernel synchronization objects,
+	 * ...). If the space left for kernel objects is too small, kernel object
+	 * allocation will fail further down the road. One can use
+	 * drm_panthor_gpu_info::mmu_features to extract the total virtual address
+	 * range, and chose a user_va_range that leaves some space to the kernel.
+	 *
+	 * If user_va_range is zero, the kernel will pick a sensible value based on
+	 * TASK_SIZE and the virtual range supported by the GPU MMU (the kernel/user
+	 * split should leave enough VA space for userspace processes to support SVM,
+	 * while still allowing the kernel to map some amount of kernel objects in
+	 * the kernel VA range). The value chosen by the driver will be returned in
+	 * @user_va_range.
+	 *
+	 * User VA space always starts at 0x0, kernel VA space is always placed after
+	 * the user VA range.
+	 */
+	__u64 user_va_range;
+};
+
+/**
+ * struct drm_panthor_vm_destroy - Arguments passed to DRM_PANTHOR_IOCTL_VM_DESTROY
+ */
+struct drm_panthor_vm_destroy {
+	/** @id: ID of the VM to destroy. */
+	__u32 id;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+};
+
+/**
+ * enum drm_panthor_vm_bind_op_flags - VM bind operation flags
+ */
+enum drm_panthor_vm_bind_op_flags {
+	/**
+	 * @DRM_PANTHOR_VM_BIND_OP_MAP_READONLY: Map the memory read-only.
+	 *
+	 * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP.
+	 */
+	DRM_PANTHOR_VM_BIND_OP_MAP_READONLY = 1 << 0,
+
+	/**
+	 * @DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC: Map the memory not-executable.
+	 *
+	 * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP.
+	 */
+	DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC = 1 << 1,
+
+	/**
+	 * @DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED: Map the memory uncached.
+	 *
+	 * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP.
+	 */
+	DRM_PANTHOR_VM_BIND_OP_MAP_UNCACHED = 1 << 2,
+
+	/**
+	 * @DRM_PANTHOR_VM_BIND_OP_MAP_SPARSE: Sparsely map a virtual memory range
+	 *
+	 * Only valid with DRM_PANTHOR_VM_BIND_OP_TYPE_MAP.
+	 *
+	 * When this flag is set, the whole vm_bind range is mapped over a dummy object in a cyclic
+	 * fashion, and all GPU reads from addresses in the range return undefined values. This flag
+	 * being set means drm_panthor_vm_bind_op::bo_offset and drm_panthor_vm_bind_op::bo_handle
+	 * must both be set to 0. DRM_PANTHOR_VM_BIND_OP_MAP_NOEXEC must also be set.
+	 */
+	DRM_PANTHOR_VM_BIND_OP_MAP_SPARSE = 1 << 3,
+
+	/**
+	 * @DRM_PANTHOR_VM_BIND_OP_TYPE_MASK: Mask used to determine the type of operation.
+	 */
+	DRM_PANTHOR_VM_BIND_OP_TYPE_MASK = (int)(0xfu << 28),
+
+	/** @DRM_PANTHOR_VM_BIND_OP_TYPE_MAP: Map operation. */
+	DRM_PANTHOR_VM_BIND_OP_TYPE_MAP = 0 << 28,
+
+	/** @DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP: Unmap operation. */
+	DRM_PANTHOR_VM_BIND_OP_TYPE_UNMAP = 1 << 28,
+
+	/**
+	 * @DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY: No VM operation.
+	 *
+	 * Just serves as a synchronization point on a VM queue.
+	 *
+	 * Only valid if %DRM_PANTHOR_VM_BIND_ASYNC is set in drm_panthor_vm_bind::flags,
+	 * and drm_panthor_vm_bind_op::syncs contains at least one element.
+	 */
+	DRM_PANTHOR_VM_BIND_OP_TYPE_SYNC_ONLY = 2 << 28,
+};
+
+/**
+ * struct drm_panthor_vm_bind_op - VM bind operation
+ */
+struct drm_panthor_vm_bind_op {
+	/** @flags: Combination of drm_panthor_vm_bind_op_flags flags. */
+	__u32 flags;
+
+	/**
+	 * @bo_handle: Handle of the buffer object to map.
+	 * MBZ for unmap or sync-only operations.
+	 */
+	__u32 bo_handle;
+
+	/**
+	 * @bo_offset: Buffer object offset.
+	 * MBZ for unmap or sync-only operations.
+	 */
+	__u64 bo_offset;
+
+	/**
+	 * @va: Virtual address to map/unmap.
+	 * MBZ for sync-only operations.
+	 */
+	__u64 va;
+
+	/**
+	 * @size: Size to map/unmap.
+	 * MBZ for sync-only operations.
+	 */
+	__u64 size;
+
+	/**
+	 * @syncs: Array of struct drm_panthor_sync_op synchronization
+	 * operations.
+	 *
+	 * This array must be empty if %DRM_PANTHOR_VM_BIND_ASYNC is not set on
+	 * the drm_panthor_vm_bind object containing this VM bind operation.
+	 *
+	 * This array shall not be empty for sync-only operations.
+	 */
+	struct drm_panthor_obj_array syncs;
+};
+
+/**
+ * enum drm_panthor_vm_bind_flags - VM bind flags
+ */
+enum drm_panthor_vm_bind_flags {
+	/**
+	 * @DRM_PANTHOR_VM_BIND_ASYNC: VM bind operations are queued to the VM
+	 * queue instead of being executed synchronously.
+	 */
+	DRM_PANTHOR_VM_BIND_ASYNC = 1 << 0,
+};
+
+/**
+ * struct drm_panthor_vm_bind - Arguments passed to DRM_IOCTL_PANTHOR_VM_BIND
+ */
+struct drm_panthor_vm_bind {
+	/** @vm_id: VM targeted by the bind request. */
+	__u32 vm_id;
+
+	/** @flags: Combination of drm_panthor_vm_bind_flags flags. */
+	__u32 flags;
+
+	/** @ops: Array of struct drm_panthor_vm_bind_op bind operations. */
+	struct drm_panthor_obj_array ops;
+};
+
+/**
+ * enum drm_panthor_vm_state - VM states.
+ */
+enum drm_panthor_vm_state {
+	/**
+	 * @DRM_PANTHOR_VM_STATE_USABLE: VM is usable.
+	 *
+	 * New VM operations will be accepted on this VM.
+	 */
+	DRM_PANTHOR_VM_STATE_USABLE,
+
+	/**
+	 * @DRM_PANTHOR_VM_STATE_UNUSABLE: VM is unusable.
+	 *
+	 * Something put the VM in an unusable state (like an asynchronous
+	 * VM_BIND request failing for any reason).
+	 *
+	 * Once the VM is in this state, all new MAP operations will be
+	 * rejected, and any GPU job targeting this VM will fail.
+	 * UNMAP operations are still accepted.
+	 *
+	 * The only way to recover from an unusable VM is to create a new
+	 * VM, and destroy the old one.
+	 */
+	DRM_PANTHOR_VM_STATE_UNUSABLE,
+};
+
+/**
+ * struct drm_panthor_vm_get_state - Get VM state.
+ */
+struct drm_panthor_vm_get_state {
+	/** @vm_id: VM targeted by the get_state request. */
+	__u32 vm_id;
+
+	/**
+	 * @state: state returned by the driver.
+	 *
+	 * Must be one of the enum drm_panthor_vm_state values.
+	 */
+	__u32 state;
+};
+
+/**
+ * enum drm_panthor_bo_flags - Buffer object flags, passed at creation time.
+ */
+enum drm_panthor_bo_flags {
+	/** @DRM_PANTHOR_BO_NO_MMAP: The buffer object will never be CPU-mapped in userspace. */
+	DRM_PANTHOR_BO_NO_MMAP = (1 << 0),
+
+	/**
+	 * @DRM_PANTHOR_BO_WB_MMAP: Force "Write-Back Cacheable" CPU mapping.
+	 *
+	 * CPU map the buffer object in userspace by forcing the "Write-Back
+	 * Cacheable" cacheability attribute. The mapping otherwise uses the
+	 * "Non-Cacheable" attribute if the GPU is not IO coherent.
+	 */
+	DRM_PANTHOR_BO_WB_MMAP = (1 << 1),
+};
+
+/**
+ * struct drm_panthor_bo_create - Arguments passed to DRM_IOCTL_PANTHOR_BO_CREATE.
+ */
+struct drm_panthor_bo_create {
+	/**
+	 * @size: Requested size for the object
+	 *
+	 * The (page-aligned) allocated size for the object will be returned.
+	 */
+	__u64 size;
+
+	/**
+	 * @flags: Flags. Must be a combination of drm_panthor_bo_flags flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @exclusive_vm_id: Exclusive VM this buffer object will be mapped to.
+	 *
+	 * If not zero, the field must refer to a valid VM ID, and implies that:
+	 *  - the buffer object will only ever be bound to that VM
+	 *  - cannot be exported as a PRIME fd
+	 */
+	__u32 exclusive_vm_id;
+
+	/**
+	 * @handle: Returned handle for the object.
+	 *
+	 * Object handles are nonzero.
+	 */
+	__u32 handle;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+};
+
+/**
+ * struct drm_panthor_bo_mmap_offset - Arguments passed to DRM_IOCTL_PANTHOR_BO_MMAP_OFFSET.
+ */
+struct drm_panthor_bo_mmap_offset {
+	/** @handle: Handle of the object we want an mmap offset for. */
+	__u32 handle;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+
+	/** @offset: The fake offset to use for subsequent mmap calls. */
+	__u64 offset;
+};
+
+/**
+ * struct drm_panthor_queue_create - Queue creation arguments.
+ */
+struct drm_panthor_queue_create {
+	/**
+	 * @priority: Defines the priority of queues inside a group. Goes from 0 to 15,
+	 * 15 being the highest priority.
+	 */
+	__u8 priority;
+
+	/** @pad: Padding fields, MBZ. */
+	__u8 pad[3];
+
+	/** @ringbuf_size: Size of the ring buffer to allocate to this queue. */
+	__u32 ringbuf_size;
+};
+
+/**
+ * enum drm_panthor_group_priority - Scheduling group priority
+ */
+enum drm_panthor_group_priority {
+	/** @PANTHOR_GROUP_PRIORITY_LOW: Low priority group. */
+	PANTHOR_GROUP_PRIORITY_LOW = 0,
+
+	/** @PANTHOR_GROUP_PRIORITY_MEDIUM: Medium priority group. */
+	PANTHOR_GROUP_PRIORITY_MEDIUM,
+
+	/**
+	 * @PANTHOR_GROUP_PRIORITY_HIGH: High priority group.
+	 *
+	 * Requires CAP_SYS_NICE or DRM_MASTER.
+	 */
+	PANTHOR_GROUP_PRIORITY_HIGH,
+
+	/**
+	 * @PANTHOR_GROUP_PRIORITY_REALTIME: Realtime priority group.
+	 *
+	 * Requires CAP_SYS_NICE or DRM_MASTER.
+	 */
+	PANTHOR_GROUP_PRIORITY_REALTIME,
+};
+
+/**
+ * struct drm_panthor_group_create - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_CREATE
+ */
+struct drm_panthor_group_create {
+	/** @queues: Array of drm_panthor_queue_create elements. */
+	struct drm_panthor_obj_array queues;
+
+	/**
+	 * @max_compute_cores: Maximum number of cores that can be used by compute
+	 * jobs across CS queues bound to this group.
+	 *
+	 * Must be less or equal to the number of bits set in @compute_core_mask.
+	 */
+	__u8 max_compute_cores;
+
+	/**
+	 * @max_fragment_cores: Maximum number of cores that can be used by fragment
+	 * jobs across CS queues bound to this group.
+	 *
+	 * Must be less or equal to the number of bits set in @fragment_core_mask.
+	 */
+	__u8 max_fragment_cores;
+
+	/**
+	 * @max_tiler_cores: Maximum number of tilers that can be used by tiler jobs
+	 * across CS queues bound to this group.
+	 *
+	 * Must be less or equal to the number of bits set in @tiler_core_mask.
+	 */
+	__u8 max_tiler_cores;
+
+	/** @priority: Group priority (see enum drm_panthor_group_priority). */
+	__u8 priority;
+
+	/** @pad: Padding field, MBZ. */
+	__u32 pad;
+
+	/**
+	 * @compute_core_mask: Mask encoding cores that can be used for compute jobs.
+	 *
+	 * This field must have at least @max_compute_cores bits set.
+	 *
+	 * The bits set here should also be set in drm_panthor_gpu_info::shader_present.
+	 */
+	__u64 compute_core_mask;
+
+	/**
+	 * @fragment_core_mask: Mask encoding cores that can be used for fragment jobs.
+	 *
+	 * This field must have at least @max_fragment_cores bits set.
+	 *
+	 * The bits set here should also be set in drm_panthor_gpu_info::shader_present.
+	 */
+	__u64 fragment_core_mask;
+
+	/**
+	 * @tiler_core_mask: Mask encoding cores that can be used for tiler jobs.
+	 *
+	 * This field must have at least @max_tiler_cores bits set.
+	 *
+	 * The bits set here should also be set in drm_panthor_gpu_info::tiler_present.
+	 */
+	__u64 tiler_core_mask;
+
+	/**
+	 * @vm_id: VM ID to bind this group to.
+	 *
+	 * All submission to queues bound to this group will use this VM.
+	 */
+	__u32 vm_id;
+
+	/**
+	 * @group_handle: Returned group handle. Passed back when submitting jobs or
+	 * destroying a group.
+	 */
+	__u32 group_handle;
+};
+
+/**
+ * struct drm_panthor_group_destroy - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_DESTROY
+ */
+struct drm_panthor_group_destroy {
+	/** @group_handle: Group to destroy */
+	__u32 group_handle;
+
+	/** @pad: Padding field, MBZ. */
+	__u32 pad;
+};
+
+/**
+ * struct drm_panthor_queue_submit - Job submission arguments.
+ *
+ * This is describing the userspace command stream to call from the kernel
+ * command stream ring-buffer. Queue submission is always part of a group
+ * submission, taking one or more jobs to submit to the underlying queues.
+ */
+struct drm_panthor_queue_submit {
+	/** @queue_index: Index of the queue inside a group. */
+	__u32 queue_index;
+
+	/**
+	 * @stream_size: Size of the command stream to execute.
+	 *
+	 * Must be 64-bit/8-byte aligned (the size of a CS instruction)
+	 *
+	 * Can be zero if stream_addr is zero too.
+	 *
+	 * When the stream size is zero, the queue submit serves as a
+	 * synchronization point.
+	 */
+	__u32 stream_size;
+
+	/**
+	 * @stream_addr: GPU address of the command stream to execute.
+	 *
+	 * Must be aligned on 64-byte.
+	 *
+	 * Can be zero is stream_size is zero too.
+	 */
+	__u64 stream_addr;
+
+	/**
+	 * @latest_flush: FLUSH_ID read at the time the stream was built.
+	 *
+	 * This allows cache flush elimination for the automatic
+	 * flush+invalidate(all) done at submission time, which is needed to
+	 * ensure the GPU doesn't get garbage when reading the indirect command
+	 * stream buffers. If you want the cache flush to happen
+	 * unconditionally, pass a zero here.
+	 *
+	 * Ignored when stream_size is zero.
+	 */
+	__u32 latest_flush;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+
+	/** @syncs: Array of struct drm_panthor_sync_op sync operations. */
+	struct drm_panthor_obj_array syncs;
+};
+
+/**
+ * struct drm_panthor_group_submit - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_SUBMIT
+ */
+struct drm_panthor_group_submit {
+	/** @group_handle: Handle of the group to queue jobs to. */
+	__u32 group_handle;
+
+	/** @pad: MBZ. */
+	__u32 pad;
+
+	/** @queue_submits: Array of drm_panthor_queue_submit objects. */
+	struct drm_panthor_obj_array queue_submits;
+};
+
+/**
+ * enum drm_panthor_group_state_flags - Group state flags
+ */
+enum drm_panthor_group_state_flags {
+	/**
+	 * @DRM_PANTHOR_GROUP_STATE_TIMEDOUT: Group had unfinished jobs.
+	 *
+	 * When a group ends up with this flag set, no jobs can be submitted to its queues.
+	 */
+	DRM_PANTHOR_GROUP_STATE_TIMEDOUT = 1 << 0,
+
+	/**
+	 * @DRM_PANTHOR_GROUP_STATE_FATAL_FAULT: Group had fatal faults.
+	 *
+	 * When a group ends up with this flag set, no jobs can be submitted to its queues.
+	 */
+	DRM_PANTHOR_GROUP_STATE_FATAL_FAULT = 1 << 1,
+
+	/**
+	 * @DRM_PANTHOR_GROUP_STATE_INNOCENT: Group was killed during a reset caused by other
+	 * groups.
+	 *
+	 * This flag can only be set if DRM_PANTHOR_GROUP_STATE_TIMEDOUT is set and
+	 * DRM_PANTHOR_GROUP_STATE_FATAL_FAULT is not.
+	 */
+	DRM_PANTHOR_GROUP_STATE_INNOCENT = 1 << 2,
+};
+
+/**
+ * struct drm_panthor_group_get_state - Arguments passed to DRM_IOCTL_PANTHOR_GROUP_GET_STATE
+ *
+ * Used to query the state of a group and decide whether a new group should be created to
+ * replace it.
+ */
+struct drm_panthor_group_get_state {
+	/** @group_handle: Handle of the group to query state on */
+	__u32 group_handle;
+
+	/**
+	 * @state: Combination of DRM_PANTHOR_GROUP_STATE_* flags encoding the
+	 * group state.
+	 */
+	__u32 state;
+
+	/** @fatal_queues: Bitmask of queues that faced fatal faults. */
+	__u32 fatal_queues;
+
+	/** @pad: MBZ */
+	__u32 pad;
+};
+
+/**
+ * struct drm_panthor_tiler_heap_create - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE
+ */
+struct drm_panthor_tiler_heap_create {
+	/** @vm_id: VM ID the tiler heap should be mapped to */
+	__u32 vm_id;
+
+	/** @initial_chunk_count: Initial number of chunks to allocate. Must be at least one. */
+	__u32 initial_chunk_count;
+
+	/**
+	 * @chunk_size: Chunk size.
+	 *
+	 * Must be page-aligned and lie in the [128k:8M] range.
+	 */
+	__u32 chunk_size;
+
+	/**
+	 * @max_chunks: Maximum number of chunks that can be allocated.
+	 *
+	 * Must be at least @initial_chunk_count.
+	 */
+	__u32 max_chunks;
+
+	/**
+	 * @target_in_flight: Maximum number of in-flight render passes.
+	 *
+	 * If the heap has more than tiler jobs in-flight, the FW will wait for render
+	 * passes to finish before queuing new tiler jobs.
+	 */
+	__u32 target_in_flight;
+
+	/** @handle: Returned heap handle. Passed back to DESTROY_TILER_HEAP. */
+	__u32 handle;
+
+	/** @tiler_heap_ctx_gpu_va: Returned heap GPU virtual address returned */
+	__u64 tiler_heap_ctx_gpu_va;
+
+	/**
+	 * @first_heap_chunk_gpu_va: First heap chunk.
+	 *
+	 * The tiler heap is formed of heap chunks forming a single-link list. This
+	 * is the first element in the list.
+	 */
+	__u64 first_heap_chunk_gpu_va;
+};
+
+/**
+ * struct drm_panthor_tiler_heap_destroy - Arguments passed to DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY
+ */
+struct drm_panthor_tiler_heap_destroy {
+	/**
+	 * @handle: Handle of the tiler heap to destroy.
+	 *
+	 * Must be a valid heap handle returned by DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE.
+	 */
+	__u32 handle;
+
+	/** @pad: Padding field, MBZ. */
+	__u32 pad;
+};
+
+/**
+ * struct drm_panthor_bo_set_label - Arguments passed to DRM_IOCTL_PANTHOR_BO_SET_LABEL
+ */
+struct drm_panthor_bo_set_label {
+	/** @handle: Handle of the buffer object to label. */
+	__u32 handle;
+
+	/**  @pad: MBZ. */
+	__u32 pad;
+
+	/**
+	 * @label: User pointer to a NUL-terminated string
+	 *
+	 * Length cannot be greater than 4096
+	 */
+	__u64 label;
+};
+
+/**
+ * struct drm_panthor_set_user_mmio_offset - Arguments passed to
+ * DRM_IOCTL_PANTHOR_SET_USER_MMIO_OFFSET
+ *
+ * This ioctl is only really useful if you want to support userspace
+ * CPU emulation environments where the size of an unsigned long differs
+ * between the host and the guest architectures.
+ */
+struct drm_panthor_set_user_mmio_offset {
+	/**
+	 * @offset: User MMIO offset to use.
+	 *
+	 * Must be either DRM_PANTHOR_USER_MMIO_OFFSET_32BIT or
+	 * DRM_PANTHOR_USER_MMIO_OFFSET_64BIT.
+	 *
+	 * Use DRM_PANTHOR_USER_MMIO_OFFSET (which selects OFFSET_32BIT or
+	 * OFFSET_64BIT based on the size of an unsigned long) unless you
+	 * have a very good reason to overrule this decision.
+	 */
+	__u64 offset;
+};
+
+/**
+ * enum drm_panthor_bo_sync_op_type - BO sync type
+ */
+enum drm_panthor_bo_sync_op_type {
+	/** @DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH: Flush CPU caches. */
+	DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH = 0,
+
+	/** @DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE: Flush and invalidate CPU caches. */
+	DRM_PANTHOR_BO_SYNC_CPU_CACHE_FLUSH_AND_INVALIDATE = 1,
+};
+
+/**
+ * struct drm_panthor_bo_sync_op - BO map sync op
+ */
+struct drm_panthor_bo_sync_op {
+	/** @handle: Handle of the buffer object to sync. */
+	__u32 handle;
+
+	/** @type: Type of operation. */
+	__u32 type;
+
+	/**
+	 * @offset: Offset into the BO at which the sync range starts.
+	 *
+	 * This will be rounded down to the nearest cache line as needed.
+	 */
+	__u64 offset;
+
+	/**
+	 * @size: Size of the range to sync
+	 *
+	 * @size + @offset will be rounded up to the nearest cache line as
+	 * needed.
+	 */
+	__u64 size;
+};
+
+/**
+ * struct drm_panthor_bo_sync - BO map sync request
+ */
+struct drm_panthor_bo_sync {
+	/**
+	 * @ops: Array of struct drm_panthor_bo_sync_op sync operations.
+	 */
+	struct drm_panthor_obj_array ops;
+};
+
+/**
+ * enum drm_panthor_bo_extra_flags - Set of flags returned on a BO_QUERY_INFO request
+ *
+ * Those are flags reflecting BO properties that are not directly coming from the flags
+ * passed are creation time, or information on BOs that were imported from other drivers.
+ */
+enum drm_panthor_bo_extra_flags {
+	/**
+	 * @DRM_PANTHOR_BO_IS_IMPORTED: BO has been imported from an external driver.
+	 *
+	 * Note that imported dma-buf handles are not flagged as imported if they
+	 * where exported by panthor. Only buffers that are coming from other drivers
+	 * (dma heaps, other GPUs, display controllers, V4L, ...).
+	 *
+	 * It's also important to note that all imported BOs are mapped cached and can't
+	 * be considered IO-coherent even if the GPU is. This means they require explicit
+	 * syncs that must go through the DRM_PANTHOR_BO_SYNC ioctl (userland cache
+	 * maintenance is not allowed in that case, because extra operations might be
+	 * needed to make changes visible to the CPU/device, like buffer migration when the
+	 * exporter is a GPU with its own VRAM).
+	 */
+	DRM_PANTHOR_BO_IS_IMPORTED = (1 << 0),
+};
+
+/**
+ * struct drm_panthor_bo_query_info - Query BO info
+ */
+struct drm_panthor_bo_query_info {
+	/** @handle: Handle of the buffer object to query flags on. */
+	__u32 handle;
+
+	/**
+	 * @extra_flags: Combination of enum drm_panthor_bo_extra_flags flags.
+	 */
+	__u32 extra_flags;
+
+	/**
+	 * @create_flags: Flags passed at creation time.
+	 *
+	 * Combination of enum drm_panthor_bo_flags flags.
+	 * Will be zero if the buffer comes from a different driver.
+	 */
+	__u32 create_flags;
+
+	/** @pad: Will be zero on return. */
+	__u32 pad;
+};
+
+/**
+ * DRM_IOCTL_PANTHOR() - Build a Panthor IOCTL number
+ * @__access: Access type. Must be R, W or RW.
+ * @__id: One of the DRM_PANTHOR_xxx id.
+ * @__type: Suffix of the type being passed to the IOCTL.
+ *
+ * Don't use this macro directly, use the DRM_IOCTL_PANTHOR_xxx
+ * values instead.
+ *
+ * Return: An IOCTL number to be passed to ioctl() from userspace.
+ */
+#define DRM_IOCTL_PANTHOR(__access, __id, __type) \
+	DRM_IO ## __access(DRM_COMMAND_BASE + DRM_PANTHOR_ ## __id, \
+			   struct drm_panthor_ ## __type)
+
+enum {
+	DRM_IOCTL_PANTHOR_DEV_QUERY =
+		DRM_IOCTL_PANTHOR(WR, DEV_QUERY, dev_query),
+	DRM_IOCTL_PANTHOR_VM_CREATE =
+		DRM_IOCTL_PANTHOR(WR, VM_CREATE, vm_create),
+	DRM_IOCTL_PANTHOR_VM_DESTROY =
+		DRM_IOCTL_PANTHOR(WR, VM_DESTROY, vm_destroy),
+	DRM_IOCTL_PANTHOR_VM_BIND =
+		DRM_IOCTL_PANTHOR(WR, VM_BIND, vm_bind),
+	DRM_IOCTL_PANTHOR_VM_GET_STATE =
+		DRM_IOCTL_PANTHOR(WR, VM_GET_STATE, vm_get_state),
+	DRM_IOCTL_PANTHOR_BO_CREATE =
+		DRM_IOCTL_PANTHOR(WR, BO_CREATE, bo_create),
+	DRM_IOCTL_PANTHOR_BO_MMAP_OFFSET =
+		DRM_IOCTL_PANTHOR(WR, BO_MMAP_OFFSET, bo_mmap_offset),
+	DRM_IOCTL_PANTHOR_GROUP_CREATE =
+		DRM_IOCTL_PANTHOR(WR, GROUP_CREATE, group_create),
+	DRM_IOCTL_PANTHOR_GROUP_DESTROY =
+		DRM_IOCTL_PANTHOR(WR, GROUP_DESTROY, group_destroy),
+	DRM_IOCTL_PANTHOR_GROUP_SUBMIT =
+		DRM_IOCTL_PANTHOR(WR, GROUP_SUBMIT, group_submit),
+	DRM_IOCTL_PANTHOR_GROUP_GET_STATE =
+		DRM_IOCTL_PANTHOR(WR, GROUP_GET_STATE, group_get_state),
+	DRM_IOCTL_PANTHOR_TILER_HEAP_CREATE =
+		DRM_IOCTL_PANTHOR(WR, TILER_HEAP_CREATE, tiler_heap_create),
+	DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY =
+		DRM_IOCTL_PANTHOR(WR, TILER_HEAP_DESTROY, tiler_heap_destroy),
+	DRM_IOCTL_PANTHOR_BO_SET_LABEL =
+		DRM_IOCTL_PANTHOR(WR, BO_SET_LABEL, bo_set_label),
+	DRM_IOCTL_PANTHOR_SET_USER_MMIO_OFFSET =
+		DRM_IOCTL_PANTHOR(WR, SET_USER_MMIO_OFFSET, set_user_mmio_offset),
+	DRM_IOCTL_PANTHOR_BO_SYNC =
+		DRM_IOCTL_PANTHOR(WR, BO_SYNC, bo_sync),
+	DRM_IOCTL_PANTHOR_BO_QUERY_INFO =
+		DRM_IOCTL_PANTHOR(WR, BO_QUERY_INFO, bo_query_info),
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _PANTHOR_DRM_H_ */
diff --git a/include/uapi/drm/pvr_drm.h b/include/uapi/drm/pvr_drm.h
new file mode 100644
index 000000000..ccf6c2112
--- /dev/null
+++ b/include/uapi/drm/pvr_drm.h
@@ -0,0 +1,1295 @@
+/* SPDX-License-Identifier: (GPL-2.0-only WITH Linux-syscall-note) OR MIT */
+/* Copyright (c) 2023 Imagination Technologies Ltd. */
+
+#ifndef PVR_DRM_UAPI_H
+#define PVR_DRM_UAPI_H
+
+#include "drm.h"
+
+#include <linux/const.h>
+#include <linux/types.h>
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/**
+ * DOC: PowerVR UAPI
+ *
+ * The PowerVR IOCTL argument structs have a few limitations in place, in
+ * addition to the standard kernel restrictions:
+ *
+ *  - All members must be type-aligned.
+ *  - The overall struct must be padded to 64-bit alignment.
+ *  - Explicit padding is almost always required. This takes the form of
+ *    ``_padding_[x]`` members of sufficient size to pad to the next power-of-two
+ *    alignment, where [x] is the offset into the struct in hexadecimal. Arrays
+ *    are never used for alignment. Padding fields must be zeroed; this is
+ *    always checked.
+ *  - Unions may only appear as the last member of a struct.
+ *  - Individual union members may grow in the future. The space between the
+ *    end of a union member and the end of its containing union is considered
+ *    "implicit padding" and must be zeroed. This is always checked.
+ *
+ * In addition to the IOCTL argument structs, the PowerVR UAPI makes use of
+ * DEV_QUERY argument structs. These are used to fetch information about the
+ * device and runtime. These structs are subject to the same rules set out
+ * above.
+ */
+
+/**
+ * struct drm_pvr_obj_array - Container used to pass arrays of objects
+ *
+ * It is not unusual to have to extend objects to pass new parameters, and the DRM
+ * ioctl infrastructure is supporting that by padding ioctl arguments with zeros
+ * when the data passed by userspace is smaller than the struct defined in the
+ * drm_ioctl_desc, thus keeping things backward compatible. This type is just
+ * applying the same concepts to indirect objects passed through arrays referenced
+ * from the main ioctl arguments structure: the stride basically defines the size
+ * of the object passed by userspace, which allows the kernel driver to pad with
+ * zeros when it's smaller than the size of the object it expects.
+ *
+ * Use ``DRM_PVR_OBJ_ARRAY()`` to fill object array fields, unless you
+ * have a very good reason not to.
+ */
+struct drm_pvr_obj_array {
+	/** @stride: Stride of object struct. Used for versioning. */
+	__u32 stride;
+
+	/** @count: Number of objects in the array. */
+	__u32 count;
+
+	/** @array: User pointer to an array of objects. */
+	__u64 array;
+};
+
+/**
+ * DRM_PVR_OBJ_ARRAY() - Helper macro for filling &struct drm_pvr_obj_array.
+ * @cnt: Number of elements pointed to py @ptr.
+ * @ptr: Pointer to start of a C array.
+ *
+ * Return: Literal of type &struct drm_pvr_obj_array.
+ */
+#define DRM_PVR_OBJ_ARRAY(cnt, ptr) \
+	{ .stride = sizeof((ptr)[0]), .count = (cnt), .array = (__u64)(uintptr_t)(ptr) }
+
+/**
+ * DOC: PowerVR IOCTL interface
+ */
+
+/**
+ * PVR_IOCTL() - Build a PowerVR IOCTL number
+ * @_ioctl: An incrementing id for this IOCTL. Added to %DRM_COMMAND_BASE.
+ * @_mode: Must be one of %DRM_IOR, %DRM_IOW or %DRM_IOWR.
+ * @_data: The type of the args struct passed by this IOCTL.
+ *
+ * The struct referred to by @_data must have a ``drm_pvr_ioctl_`` prefix and an
+ * ``_args suffix``. They are therefore omitted from @_data.
+ *
+ * This should only be used to build the constants described below; it should
+ * never be used to call an IOCTL directly.
+ *
+ * Return: An IOCTL number to be passed to ioctl() from userspace.
+ */
+#define PVR_IOCTL(_ioctl, _mode, _data) \
+	_mode(DRM_COMMAND_BASE + (_ioctl), struct drm_pvr_ioctl_##_data##_args)
+
+#define DRM_IOCTL_PVR_DEV_QUERY PVR_IOCTL(0x00, DRM_IOWR, dev_query)
+#define DRM_IOCTL_PVR_CREATE_BO PVR_IOCTL(0x01, DRM_IOWR, create_bo)
+#define DRM_IOCTL_PVR_GET_BO_MMAP_OFFSET PVR_IOCTL(0x02, DRM_IOWR, get_bo_mmap_offset)
+#define DRM_IOCTL_PVR_CREATE_VM_CONTEXT PVR_IOCTL(0x03, DRM_IOWR, create_vm_context)
+#define DRM_IOCTL_PVR_DESTROY_VM_CONTEXT PVR_IOCTL(0x04, DRM_IOW, destroy_vm_context)
+#define DRM_IOCTL_PVR_VM_MAP PVR_IOCTL(0x05, DRM_IOW, vm_map)
+#define DRM_IOCTL_PVR_VM_UNMAP PVR_IOCTL(0x06, DRM_IOW, vm_unmap)
+#define DRM_IOCTL_PVR_CREATE_CONTEXT PVR_IOCTL(0x07, DRM_IOWR, create_context)
+#define DRM_IOCTL_PVR_DESTROY_CONTEXT PVR_IOCTL(0x08, DRM_IOW, destroy_context)
+#define DRM_IOCTL_PVR_CREATE_FREE_LIST PVR_IOCTL(0x09, DRM_IOWR, create_free_list)
+#define DRM_IOCTL_PVR_DESTROY_FREE_LIST PVR_IOCTL(0x0a, DRM_IOW, destroy_free_list)
+#define DRM_IOCTL_PVR_CREATE_HWRT_DATASET PVR_IOCTL(0x0b, DRM_IOWR, create_hwrt_dataset)
+#define DRM_IOCTL_PVR_DESTROY_HWRT_DATASET PVR_IOCTL(0x0c, DRM_IOW, destroy_hwrt_dataset)
+#define DRM_IOCTL_PVR_SUBMIT_JOBS PVR_IOCTL(0x0d, DRM_IOW, submit_jobs)
+
+/**
+ * DOC: PowerVR IOCTL DEV_QUERY interface
+ */
+
+/**
+ * struct drm_pvr_dev_query_gpu_info - Container used to fetch information about
+ * the graphics processor.
+ *
+ * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set
+ * to %DRM_PVR_DEV_QUERY_GPU_INFO_GET.
+ */
+struct drm_pvr_dev_query_gpu_info {
+	/**
+	 * @gpu_id: GPU identifier.
+	 *
+	 * For all currently supported GPUs this is the BVNC encoded as a 64-bit
+	 * value as follows:
+	 *
+	 *    +--------+--------+--------+-------+
+	 *    | 63..48 | 47..32 | 31..16 | 15..0 |
+	 *    +========+========+========+=======+
+	 *    | B      | V      | N      | C     |
+	 *    +--------+--------+--------+-------+
+	 */
+	__u64 gpu_id;
+
+	/**
+	 * @num_phantoms: Number of Phantoms present.
+	 */
+	__u32 num_phantoms;
+
+	/** @_padding_c: Reserved. This field must be zeroed. */
+	__u32 _padding_c;
+};
+
+/**
+ * struct drm_pvr_dev_query_runtime_info - Container used to fetch information
+ * about the graphics runtime.
+ *
+ * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set
+ * to %DRM_PVR_DEV_QUERY_RUNTIME_INFO_GET.
+ */
+struct drm_pvr_dev_query_runtime_info {
+	/**
+	 * @free_list_min_pages: Minimum allowed free list size,
+	 * in PM physical pages.
+	 */
+	__u64 free_list_min_pages;
+
+	/**
+	 * @free_list_max_pages: Maximum allowed free list size,
+	 * in PM physical pages.
+	 */
+	__u64 free_list_max_pages;
+
+	/**
+	 * @common_store_alloc_region_size: Size of the Allocation
+	 * Region within the Common Store used for coefficient and shared
+	 * registers, in dwords.
+	 */
+	__u32 common_store_alloc_region_size;
+
+	/**
+	 * @common_store_partition_space_size: Size of the
+	 * Partition Space within the Common Store for output buffers, in
+	 * dwords.
+	 */
+	__u32 common_store_partition_space_size;
+
+	/**
+	 * @max_coeffs: Maximum coefficients, in dwords.
+	 */
+	__u32 max_coeffs;
+
+	/**
+	 * @cdm_max_local_mem_size_regs: Maximum amount of local
+	 * memory available to a compute kernel, in dwords.
+	 */
+	__u32 cdm_max_local_mem_size_regs;
+};
+
+/**
+ * struct drm_pvr_dev_query_quirks - Container used to fetch information about
+ * hardware fixes for which the device may require support in the user mode
+ * driver.
+ *
+ * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set
+ * to %DRM_PVR_DEV_QUERY_QUIRKS_GET.
+ */
+struct drm_pvr_dev_query_quirks {
+	/**
+	 * @quirks: A userspace address for the hardware quirks __u32 array.
+	 *
+	 * The first @musthave_count items in the list are quirks that the
+	 * client must support for this device. If userspace does not support
+	 * all these quirks then functionality is not guaranteed and client
+	 * initialisation must fail.
+	 * The remaining quirks in the list affect userspace and the kernel or
+	 * firmware. They are disabled by default and require userspace to
+	 * opt-in. The opt-in mechanism depends on the quirk.
+	 */
+	__u64 quirks;
+
+	/** @count: Length of @quirks (number of __u32). */
+	__u16 count;
+
+	/**
+	 * @musthave_count: The number of entries in @quirks that are
+	 * mandatory, starting at index 0.
+	 */
+	__u16 musthave_count;
+
+	/** @_padding_c: Reserved. This field must be zeroed. */
+	__u32 _padding_c;
+};
+
+/**
+ * struct drm_pvr_dev_query_enhancements - Container used to fetch information
+ * about optional enhancements supported by the device that require support in
+ * the user mode driver.
+ *
+ * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set
+ * to %DRM_PVR_DEV_ENHANCEMENTS_GET.
+ */
+struct drm_pvr_dev_query_enhancements {
+	/**
+	 * @enhancements: A userspace address for the hardware enhancements
+	 * __u32 array.
+	 *
+	 * These enhancements affect userspace and the kernel or firmware. They
+	 * are disabled by default and require userspace to opt-in. The opt-in
+	 * mechanism depends on the enhancement.
+	 */
+	__u64 enhancements;
+
+	/** @count: Length of @enhancements (number of __u32). */
+	__u16 count;
+
+	/** @_padding_a: Reserved. This field must be zeroed. */
+	__u16 _padding_a;
+
+	/** @_padding_c: Reserved. This field must be zeroed. */
+	__u32 _padding_c;
+};
+
+/**
+ * enum drm_pvr_heap_id - Array index for heap info data returned by
+ * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET.
+ *
+ * For compatibility reasons all indices will be present in the returned array,
+ * however some heaps may not be present. These are indicated where
+ * &struct drm_pvr_heap.size is set to zero.
+ */
+enum drm_pvr_heap_id {
+	/** @DRM_PVR_HEAP_GENERAL: General purpose heap. */
+	DRM_PVR_HEAP_GENERAL = 0,
+	/** @DRM_PVR_HEAP_PDS_CODE_DATA: PDS code and data heap. */
+	DRM_PVR_HEAP_PDS_CODE_DATA,
+	/** @DRM_PVR_HEAP_USC_CODE: USC code heap. */
+	DRM_PVR_HEAP_USC_CODE,
+	/** @DRM_PVR_HEAP_RGNHDR: Region header heap. Only used if GPU has BRN63142. */
+	DRM_PVR_HEAP_RGNHDR,
+	/** @DRM_PVR_HEAP_VIS_TEST: Visibility test heap. */
+	DRM_PVR_HEAP_VIS_TEST,
+	/** @DRM_PVR_HEAP_TRANSFER_FRAG: Transfer fragment heap. */
+	DRM_PVR_HEAP_TRANSFER_FRAG,
+
+	/**
+	 * @DRM_PVR_HEAP_COUNT: The number of heaps returned by
+	 * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET.
+	 *
+	 * More heaps may be added, so this also serves as the copy limit when
+	 * sent by the caller.
+	 */
+	DRM_PVR_HEAP_COUNT
+	/* Please only add additional heaps above DRM_PVR_HEAP_COUNT! */
+};
+
+/**
+ * struct drm_pvr_heap - Container holding information about a single heap.
+ *
+ * This will always be fetched as an array.
+ */
+struct drm_pvr_heap {
+	/** @base: Base address of heap. */
+	__u64 base;
+
+	/** @size: Size of heap, in bytes. Will be 0 if the heap is not present. */
+	__u64 size;
+
+	/** @flags: Flags for this heap. Currently always 0. */
+	__u32 flags;
+
+	/** @page_size_log2: Log2 of page size. */
+	__u32 page_size_log2;
+};
+
+/**
+ * struct drm_pvr_dev_query_heap_info - Container used to fetch information
+ * about heaps supported by the device driver.
+ *
+ * Please note all driver-supported heaps will be returned up to &heaps.count.
+ * Some heaps will not be present in all devices, which will be indicated by
+ * &struct drm_pvr_heap.size being set to zero.
+ *
+ * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set
+ * to %DRM_PVR_DEV_QUERY_HEAP_INFO_GET.
+ */
+struct drm_pvr_dev_query_heap_info {
+	/**
+	 * @heaps: Array of &struct drm_pvr_heap. If pointer is NULL, the count
+	 * and stride will be updated with those known to the driver version, to
+	 * facilitate allocation by the caller.
+	 */
+	struct drm_pvr_obj_array heaps;
+};
+
+/**
+ * enum drm_pvr_static_data_area_usage - Array index for static data area info
+ * returned by %DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET.
+ *
+ * For compatibility reasons all indices will be present in the returned array,
+ * however some areas may not be present. These are indicated where
+ * &struct drm_pvr_static_data_area.size is set to zero.
+ */
+enum drm_pvr_static_data_area_usage {
+	/**
+	 * @DRM_PVR_STATIC_DATA_AREA_EOT: End of Tile PDS program code segment.
+	 *
+	 * The End of Tile PDS task runs at completion of a tile during a fragment job, and is
+	 * responsible for emitting the tile to the Pixel Back End.
+	 */
+	DRM_PVR_STATIC_DATA_AREA_EOT = 0,
+
+	/**
+	 * @DRM_PVR_STATIC_DATA_AREA_FENCE: MCU fence area, used during cache flush and
+	 * invalidation.
+	 *
+	 * This must point to valid physical memory but the contents otherwise are not used.
+	 */
+	DRM_PVR_STATIC_DATA_AREA_FENCE,
+
+	/**
+	 * @DRM_PVR_STATIC_DATA_AREA_VDM_SYNC: VDM sync program.
+	 *
+	 * The VDM sync program is used to synchronise multiple areas of the GPU hardware.
+	 */
+	DRM_PVR_STATIC_DATA_AREA_VDM_SYNC,
+
+	/**
+	 * @DRM_PVR_STATIC_DATA_AREA_YUV_CSC: YUV coefficients.
+	 *
+	 * Area contains up to 16 slots with stride of 64 bytes. Each is a 3x4 matrix of u16 fixed
+	 * point numbers, with 1 sign bit, 2 integer bits and 13 fractional bits.
+	 *
+	 * The slots are :
+	 * 0 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_RGB_IDENTITY_KHR
+	 * 1 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_IDENTITY_KHR (full range)
+	 * 2 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_IDENTITY_KHR (conformant range)
+	 * 3 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_709_KHR (full range)
+	 * 4 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_709_KHR (conformant range)
+	 * 5 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_601_KHR (full range)
+	 * 6 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_601_KHR (conformant range)
+	 * 7 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_2020_KHR (full range)
+	 * 8 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_2020_KHR (conformant range)
+	 * 9 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_601_KHR (conformant range, 10 bit)
+	 * 10 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_709_KHR (conformant range, 10 bit)
+	 * 11 = VK_SAMPLER_YCBCR_MODEL_CONVERSION_YCBCR_2020_KHR (conformant range, 10 bit)
+	 * 14 = Identity (biased)
+	 * 15 = Identity
+	 */
+	DRM_PVR_STATIC_DATA_AREA_YUV_CSC,
+};
+
+/**
+ * struct drm_pvr_static_data_area - Container holding information about a
+ * single static data area.
+ *
+ * This will always be fetched as an array.
+ */
+struct drm_pvr_static_data_area {
+	/**
+	 * @area_usage: Usage of static data area.
+	 * See &enum drm_pvr_static_data_area_usage.
+	 */
+	__u16 area_usage;
+
+	/**
+	 * @location_heap_id: Array index of heap where this of static data
+	 * area is located. This array is fetched using
+	 * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET.
+	 */
+	__u16 location_heap_id;
+
+	/** @size: Size of static data area. Not present if set to zero. */
+	__u32 size;
+
+	/** @offset: Offset of static data area from start of heap. */
+	__u64 offset;
+};
+
+/**
+ * struct drm_pvr_dev_query_static_data_areas - Container used to fetch
+ * information about the static data areas in heaps supported by the device
+ * driver.
+ *
+ * Please note all driver-supported static data areas will be returned up to
+ * &static_data_areas.count. Some will not be present for all devices which,
+ * will be indicated by &struct drm_pvr_static_data_area.size being set to zero.
+ *
+ * Further, some heaps will not be present either. See &struct
+ * drm_pvr_dev_query_heap_info.
+ *
+ * When fetching this type &struct drm_pvr_ioctl_dev_query_args.type must be set
+ * to %DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET.
+ */
+struct drm_pvr_dev_query_static_data_areas {
+	/**
+	 * @static_data_areas: Array of &struct drm_pvr_static_data_area. If
+	 * pointer is NULL, the count and stride will be updated with those
+	 * known to the driver version, to facilitate allocation by the caller.
+	 */
+	struct drm_pvr_obj_array static_data_areas;
+};
+
+/**
+ * enum drm_pvr_dev_query - For use with &drm_pvr_ioctl_dev_query_args.type to
+ * indicate the type of the receiving container.
+ *
+ * Append only. Do not reorder.
+ */
+enum drm_pvr_dev_query {
+	/**
+	 * @DRM_PVR_DEV_QUERY_GPU_INFO_GET: The dev query args contain a pointer
+	 * to &struct drm_pvr_dev_query_gpu_info.
+	 */
+	DRM_PVR_DEV_QUERY_GPU_INFO_GET = 0,
+
+	/**
+	 * @DRM_PVR_DEV_QUERY_RUNTIME_INFO_GET: The dev query args contain a
+	 * pointer to &struct drm_pvr_dev_query_runtime_info.
+	 */
+	DRM_PVR_DEV_QUERY_RUNTIME_INFO_GET,
+
+	/**
+	 * @DRM_PVR_DEV_QUERY_QUIRKS_GET: The dev query args contain a pointer
+	 * to &struct drm_pvr_dev_query_quirks.
+	 */
+	DRM_PVR_DEV_QUERY_QUIRKS_GET,
+
+	/**
+	 * @DRM_PVR_DEV_QUERY_ENHANCEMENTS_GET: The dev query args contain a
+	 * pointer to &struct drm_pvr_dev_query_enhancements.
+	 */
+	DRM_PVR_DEV_QUERY_ENHANCEMENTS_GET,
+
+	/**
+	 * @DRM_PVR_DEV_QUERY_HEAP_INFO_GET: The dev query args contain a
+	 * pointer to &struct drm_pvr_dev_query_heap_info.
+	 */
+	DRM_PVR_DEV_QUERY_HEAP_INFO_GET,
+
+	/**
+	 * @DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET: The dev query args contain
+	 * a pointer to &struct drm_pvr_dev_query_static_data_areas.
+	 */
+	DRM_PVR_DEV_QUERY_STATIC_DATA_AREAS_GET,
+};
+
+/**
+ * struct drm_pvr_ioctl_dev_query_args - Arguments for %DRM_IOCTL_PVR_DEV_QUERY.
+ */
+struct drm_pvr_ioctl_dev_query_args {
+	/**
+	 * @type: Type of query and output struct. See &enum drm_pvr_dev_query.
+	 */
+	__u32 type;
+
+	/**
+	 * @size: Size of the receiving struct, see @type.
+	 *
+	 * After a successful call this will be updated to the written byte
+	 * length.
+	 * Can also be used to get the minimum byte length (see @pointer).
+	 * This allows additional fields to be appended to the structs in
+	 * future.
+	 */
+	__u32 size;
+
+	/**
+	 * @pointer: Pointer to struct @type.
+	 *
+	 * Must be large enough to contain @size bytes.
+	 * If pointer is NULL, the expected size will be returned in the @size
+	 * field, but no other data will be written.
+	 */
+	__u64 pointer;
+};
+
+/**
+ * DOC: PowerVR IOCTL CREATE_BO interface
+ */
+
+/**
+ * DOC: Flags for CREATE_BO
+ *
+ * We use "device" to refer to the GPU here because of the ambiguity between CPU and GPU in some
+ * fonts.
+ *
+ * Device mapping options
+ *    :DRM_PVR_BO_BYPASS_DEVICE_CACHE: Specify that device accesses to this memory will bypass the
+ *       cache. This is used for buffers that will either be regularly updated by the CPU (eg free
+ *       lists) or will be accessed only once and therefore isn't worth caching (eg partial render
+ *       buffers).
+ *       By default, the device flushes its memory caches after every job, so this is not normally
+ *       required for coherency.
+ *    :DRM_PVR_BO_PM_FW_PROTECT: Specify that only the Parameter Manager (PM) and/or firmware
+ *       processor should be allowed to access this memory when mapped to the device. It is not
+ *       valid to specify this flag with DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS.
+ *
+ * CPU mapping options
+ *    :DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS: Allow userspace to map and access the contents of this
+ *       memory. It is not valid to specify this flag with DRM_PVR_BO_PM_FW_PROTECT.
+ */
+#define DRM_PVR_BO_BYPASS_DEVICE_CACHE _BITULL(0)
+#define DRM_PVR_BO_PM_FW_PROTECT _BITULL(1)
+#define DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS _BITULL(2)
+/* Bits 3..63 are reserved. */
+
+#define DRM_PVR_BO_FLAGS_MASK (DRM_PVR_BO_BYPASS_DEVICE_CACHE | DRM_PVR_BO_PM_FW_PROTECT | \
+			       DRM_PVR_BO_ALLOW_CPU_USERSPACE_ACCESS)
+
+/**
+ * struct drm_pvr_ioctl_create_bo_args - Arguments for %DRM_IOCTL_PVR_CREATE_BO
+ */
+struct drm_pvr_ioctl_create_bo_args {
+	/**
+	 * @size: [IN] Size of buffer object to create. This must be page size
+	 * aligned.
+	 */
+	__u64 size;
+
+	/**
+	 * @handle: [OUT] GEM handle of the new buffer object for use in
+	 * userspace.
+	 */
+	__u32 handle;
+
+	/** @_padding_c: Reserved. This field must be zeroed. */
+	__u32 _padding_c;
+
+	/**
+	 * @flags: [IN] Options which will affect the behaviour of this
+	 * creation operation and future mapping operations on the created
+	 * object. This field must be a valid combination of ``DRM_PVR_BO_*``
+	 * values, with all bits marked as reserved set to zero.
+	 */
+	__u64 flags;
+};
+
+/**
+ * DOC: PowerVR IOCTL GET_BO_MMAP_OFFSET interface
+ */
+
+/**
+ * struct drm_pvr_ioctl_get_bo_mmap_offset_args - Arguments for
+ * %DRM_IOCTL_PVR_GET_BO_MMAP_OFFSET
+ *
+ * Like other DRM drivers, the "mmap" IOCTL doesn't actually map any memory.
+ * Instead, it allocates a fake offset which refers to the specified buffer
+ * object. This offset can be used with a real mmap call on the DRM device
+ * itself.
+ */
+struct drm_pvr_ioctl_get_bo_mmap_offset_args {
+	/** @handle: [IN] GEM handle of the buffer object to be mapped. */
+	__u32 handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+
+	/** @offset: [OUT] Fake offset to use in the real mmap call. */
+	__u64 offset;
+};
+
+/**
+ * DOC: PowerVR IOCTL CREATE_VM_CONTEXT and DESTROY_VM_CONTEXT interfaces
+ */
+
+/**
+ * struct drm_pvr_ioctl_create_vm_context_args - Arguments for
+ * %DRM_IOCTL_PVR_CREATE_VM_CONTEXT
+ */
+struct drm_pvr_ioctl_create_vm_context_args {
+	/** @handle: [OUT] Handle for new VM context. */
+	__u32 handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+};
+
+/**
+ * struct drm_pvr_ioctl_destroy_vm_context_args - Arguments for
+ * %DRM_IOCTL_PVR_DESTROY_VM_CONTEXT
+ */
+struct drm_pvr_ioctl_destroy_vm_context_args {
+	/**
+	 * @handle: [IN] Handle for VM context to be destroyed.
+	 */
+	__u32 handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+};
+
+/**
+ * DOC: PowerVR IOCTL VM_MAP and VM_UNMAP interfaces
+ *
+ * The VM UAPI allows userspace to create buffer object mappings in GPU virtual address space.
+ *
+ * The client is responsible for managing GPU address space. It should allocate mappings within
+ * the heaps returned by %DRM_PVR_DEV_QUERY_HEAP_INFO_GET.
+ *
+ * %DRM_IOCTL_PVR_VM_MAP creates a new mapping. The client provides the target virtual address for
+ * the mapping. Size and offset within the mapped buffer object can be specified, so the client can
+ * partially map a buffer.
+ *
+ * %DRM_IOCTL_PVR_VM_UNMAP removes a mapping. The entire mapping will be removed from GPU address
+ * space only if the size of the mapping matches that known to the driver.
+ */
+
+/**
+ * struct drm_pvr_ioctl_vm_map_args - Arguments for %DRM_IOCTL_PVR_VM_MAP.
+ */
+struct drm_pvr_ioctl_vm_map_args {
+	/**
+	 * @vm_context_handle: [IN] Handle for VM context for this mapping to
+	 * exist in.
+	 */
+	__u32 vm_context_handle;
+
+	/** @flags: [IN] Flags which affect this mapping. Currently always 0. */
+	__u32 flags;
+
+	/**
+	 * @device_addr: [IN] Requested device-virtual address for the mapping.
+	 * This must be non-zero and aligned to the device page size for the
+	 * heap containing the requested address. It is an error to specify an
+	 * address which is not contained within one of the heaps returned by
+	 * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET.
+	 */
+	__u64 device_addr;
+
+	/**
+	 * @handle: [IN] Handle of the target buffer object. This must be a
+	 * valid handle returned by %DRM_IOCTL_PVR_CREATE_BO.
+	 */
+	__u32 handle;
+
+	/** @_padding_14: Reserved. This field must be zeroed. */
+	__u32 _padding_14;
+
+	/**
+	 * @offset: [IN] Offset into the target bo from which to begin the
+	 * mapping.
+	 */
+	__u64 offset;
+
+	/**
+	 * @size: [IN] Size of the requested mapping. Must be aligned to
+	 * the device page size for the heap containing the requested address,
+	 * as well as the host page size. When added to @device_addr, the
+	 * result must not overflow the heap which contains @device_addr (i.e.
+	 * the range specified by @device_addr and @size must be completely
+	 * contained within a single heap specified by
+	 * %DRM_PVR_DEV_QUERY_HEAP_INFO_GET).
+	 */
+	__u64 size;
+};
+
+/**
+ * struct drm_pvr_ioctl_vm_unmap_args - Arguments for %DRM_IOCTL_PVR_VM_UNMAP.
+ */
+struct drm_pvr_ioctl_vm_unmap_args {
+	/**
+	 * @vm_context_handle: [IN] Handle for VM context that this mapping
+	 * exists in.
+	 */
+	__u32 vm_context_handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+
+	/**
+	 * @device_addr: [IN] Device-virtual address at the start of the target
+	 * mapping. This must be non-zero.
+	 */
+	__u64 device_addr;
+
+	/**
+	 * @size: Size in bytes of the target mapping. This must be non-zero.
+	 */
+	__u64 size;
+};
+
+/**
+ * DOC: PowerVR IOCTL CREATE_CONTEXT and DESTROY_CONTEXT interfaces
+ */
+
+/**
+ * enum drm_pvr_ctx_priority - Arguments for
+ * &drm_pvr_ioctl_create_context_args.priority
+ */
+enum drm_pvr_ctx_priority {
+	/** @DRM_PVR_CTX_PRIORITY_LOW: Priority below normal. */
+	DRM_PVR_CTX_PRIORITY_LOW = -512,
+
+	/** @DRM_PVR_CTX_PRIORITY_NORMAL: Normal priority. */
+	DRM_PVR_CTX_PRIORITY_NORMAL = 0,
+
+	/**
+	 * @DRM_PVR_CTX_PRIORITY_HIGH: Priority above normal.
+	 * Note this requires ``CAP_SYS_NICE`` or ``DRM_MASTER``.
+	 */
+	DRM_PVR_CTX_PRIORITY_HIGH = 512,
+};
+
+/**
+ * enum drm_pvr_ctx_type - Arguments for
+ * &struct drm_pvr_ioctl_create_context_args.type
+ */
+enum drm_pvr_ctx_type {
+	/**
+	 * @DRM_PVR_CTX_TYPE_RENDER: Render context.
+	 */
+	DRM_PVR_CTX_TYPE_RENDER = 0,
+
+	/**
+	 * @DRM_PVR_CTX_TYPE_COMPUTE: Compute context.
+	 */
+	DRM_PVR_CTX_TYPE_COMPUTE,
+
+	/**
+	 * @DRM_PVR_CTX_TYPE_TRANSFER_FRAG: Transfer context for fragment data
+	 * master.
+	 */
+	DRM_PVR_CTX_TYPE_TRANSFER_FRAG,
+};
+
+/**
+ * struct drm_pvr_ioctl_create_context_args - Arguments for
+ * %DRM_IOCTL_PVR_CREATE_CONTEXT
+ */
+struct drm_pvr_ioctl_create_context_args {
+	/**
+	 * @type: [IN] Type of context to create.
+	 *
+	 * This must be one of the values defined by &enum drm_pvr_ctx_type.
+	 */
+	__u32 type;
+
+	/** @flags: [IN] Flags for context. */
+	__u32 flags;
+
+	/**
+	 * @priority: [IN] Priority of new context.
+	 *
+	 * This must be one of the values defined by &enum drm_pvr_ctx_priority.
+	 */
+	__s32 priority;
+
+	/** @handle: [OUT] Handle for new context. */
+	__u32 handle;
+
+	/**
+	 * @static_context_state: [IN] Pointer to static context state stream.
+	 */
+	__u64 static_context_state;
+
+	/**
+	 * @static_context_state_len: [IN] Length of static context state, in bytes.
+	 */
+	__u32 static_context_state_len;
+
+	/**
+	 * @vm_context_handle: [IN] Handle for VM context that this context is
+	 * associated with.
+	 */
+	__u32 vm_context_handle;
+
+	/**
+	 * @callstack_addr: [IN] Address for initial call stack pointer. Only valid
+	 * if @type is %DRM_PVR_CTX_TYPE_RENDER, otherwise must be 0.
+	 */
+	__u64 callstack_addr;
+};
+
+/**
+ * struct drm_pvr_ioctl_destroy_context_args - Arguments for
+ * %DRM_IOCTL_PVR_DESTROY_CONTEXT
+ */
+struct drm_pvr_ioctl_destroy_context_args {
+	/**
+	 * @handle: [IN] Handle for context to be destroyed.
+	 */
+	__u32 handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+};
+
+/**
+ * DOC: PowerVR IOCTL CREATE_FREE_LIST and DESTROY_FREE_LIST interfaces
+ */
+
+/**
+ * struct drm_pvr_ioctl_create_free_list_args - Arguments for
+ * %DRM_IOCTL_PVR_CREATE_FREE_LIST
+ *
+ * Free list arguments have the following constraints :
+ *
+ * - @max_num_pages must be greater than zero.
+ * - @grow_threshold must be between 0 and 100.
+ * - @grow_num_pages must be less than or equal to &max_num_pages.
+ * - @initial_num_pages, @max_num_pages and @grow_num_pages must be multiples
+ *   of 4.
+ * - When &grow_num_pages is 0, @initial_num_pages must be equal to
+ *   @max_num_pages.
+ * - When &grow_num_pages is non-zero, @initial_num_pages must be less than
+ *   @max_num_pages.
+ */
+struct drm_pvr_ioctl_create_free_list_args {
+	/**
+	 * @free_list_gpu_addr: [IN] Address of GPU mapping of buffer object
+	 * containing memory to be used by free list.
+	 *
+	 * The mapped region of the buffer object must be at least
+	 * @max_num_pages * ``sizeof(__u32)``.
+	 *
+	 * The buffer object must have been created with
+	 * %DRM_PVR_BO_DEVICE_PM_FW_PROTECT set and
+	 * %DRM_PVR_BO_CPU_ALLOW_USERSPACE_ACCESS not set.
+	 */
+	__u64 free_list_gpu_addr;
+
+	/** @initial_num_pages: [IN] Pages initially allocated to free list. */
+	__u32 initial_num_pages;
+
+	/** @max_num_pages: [IN] Maximum number of pages in free list. */
+	__u32 max_num_pages;
+
+	/** @grow_num_pages: [IN] Pages to grow free list by per request. */
+	__u32 grow_num_pages;
+
+	/**
+	 * @grow_threshold: [IN] Percentage of FL memory used that should
+	 * trigger a new grow request.
+	 */
+	__u32 grow_threshold;
+
+	/**
+	 * @vm_context_handle: [IN] Handle for VM context that the free list buffer
+	 * object is mapped in.
+	 */
+	__u32 vm_context_handle;
+
+	/**
+	 * @handle: [OUT] Handle for created free list.
+	 */
+	__u32 handle;
+};
+
+/**
+ * struct drm_pvr_ioctl_destroy_free_list_args - Arguments for
+ * %DRM_IOCTL_PVR_DESTROY_FREE_LIST
+ */
+struct drm_pvr_ioctl_destroy_free_list_args {
+	/**
+	 * @handle: [IN] Handle for free list to be destroyed.
+	 */
+	__u32 handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+};
+
+/**
+ * DOC: PowerVR IOCTL CREATE_HWRT_DATASET and DESTROY_HWRT_DATASET interfaces
+ */
+
+/**
+ * struct drm_pvr_create_hwrt_geom_data_args - Geometry data arguments used for
+ * &struct drm_pvr_ioctl_create_hwrt_dataset_args.geom_data_args.
+ */
+struct drm_pvr_create_hwrt_geom_data_args {
+	/** @tpc_dev_addr: [IN] Tail pointer cache GPU virtual address. */
+	__u64 tpc_dev_addr;
+
+	/** @tpc_size: [IN] Size of TPC, in bytes. */
+	__u32 tpc_size;
+
+	/** @tpc_stride: [IN] Stride between layers in TPC, in pages */
+	__u32 tpc_stride;
+
+	/** @vheap_table_dev_addr: [IN] VHEAP table GPU virtual address. */
+	__u64 vheap_table_dev_addr;
+
+	/** @rtc_dev_addr: [IN] Render Target Cache virtual address. */
+	__u64 rtc_dev_addr;
+};
+
+/**
+ * struct drm_pvr_create_hwrt_rt_data_args - Render target arguments used for
+ * &struct drm_pvr_ioctl_create_hwrt_dataset_args.rt_data_args.
+ */
+struct drm_pvr_create_hwrt_rt_data_args {
+	/** @pm_mlist_dev_addr: [IN] PM MLIST GPU virtual address. */
+	__u64 pm_mlist_dev_addr;
+
+	/** @macrotile_array_dev_addr: [IN] Macrotile array GPU virtual address. */
+	__u64 macrotile_array_dev_addr;
+
+	/** @region_header_dev_addr: [IN] Region header array GPU virtual address. */
+	__u64 region_header_dev_addr;
+};
+
+#define PVR_DRM_HWRT_FREE_LIST_LOCAL 0
+#define PVR_DRM_HWRT_FREE_LIST_GLOBAL 1U
+
+/**
+ * struct drm_pvr_ioctl_create_hwrt_dataset_args - Arguments for
+ * %DRM_IOCTL_PVR_CREATE_HWRT_DATASET
+ */
+struct drm_pvr_ioctl_create_hwrt_dataset_args {
+	/** @geom_data_args: [IN] Geometry data arguments. */
+	struct drm_pvr_create_hwrt_geom_data_args geom_data_args;
+
+	/**
+	 * @rt_data_args: [IN] Array of render target arguments.
+	 *
+	 * Each entry in this array represents a render target in a double buffered
+	 * setup.
+	 */
+	struct drm_pvr_create_hwrt_rt_data_args rt_data_args[2];
+
+	/**
+	 * @free_list_handles: [IN] Array of free list handles.
+	 *
+	 * free_list_handles[PVR_DRM_HWRT_FREE_LIST_LOCAL] must have initial
+	 * size of at least that reported by
+	 * &drm_pvr_dev_query_runtime_info.free_list_min_pages.
+	 */
+	__u32 free_list_handles[2];
+
+	/** @width: [IN] Width in pixels. */
+	__u32 width;
+
+	/** @height: [IN] Height in pixels. */
+	__u32 height;
+
+	/** @samples: [IN] Number of samples. */
+	__u32 samples;
+
+	/** @layers: [IN] Number of layers. */
+	__u32 layers;
+
+	/** @isp_merge_lower_x: [IN] Lower X coefficient for triangle merging. */
+	__u32 isp_merge_lower_x;
+
+	/** @isp_merge_lower_y: [IN] Lower Y coefficient for triangle merging. */
+	__u32 isp_merge_lower_y;
+
+	/** @isp_merge_scale_x: [IN] Scale X coefficient for triangle merging. */
+	__u32 isp_merge_scale_x;
+
+	/** @isp_merge_scale_y: [IN] Scale Y coefficient for triangle merging. */
+	__u32 isp_merge_scale_y;
+
+	/** @isp_merge_upper_x: [IN] Upper X coefficient for triangle merging. */
+	__u32 isp_merge_upper_x;
+
+	/** @isp_merge_upper_y: [IN] Upper Y coefficient for triangle merging. */
+	__u32 isp_merge_upper_y;
+
+	/**
+	 * @region_header_size: [IN] Size of region header array. This common field is used by
+	 * both render targets in this data set.
+	 *
+	 * The units for this field differ depending on what version of the simple internal
+	 * parameter format the device uses. If format 2 is in use then this is interpreted as the
+	 * number of region headers. For other formats it is interpreted as the size in dwords.
+	 */
+	__u32 region_header_size;
+
+	/**
+	 * @handle: [OUT] Handle for created HWRT dataset.
+	 */
+	__u32 handle;
+};
+
+/**
+ * struct drm_pvr_ioctl_destroy_hwrt_dataset_args - Arguments for
+ * %DRM_IOCTL_PVR_DESTROY_HWRT_DATASET
+ */
+struct drm_pvr_ioctl_destroy_hwrt_dataset_args {
+	/**
+	 * @handle: [IN] Handle for HWRT dataset to be destroyed.
+	 */
+	__u32 handle;
+
+	/** @_padding_4: Reserved. This field must be zeroed. */
+	__u32 _padding_4;
+};
+
+/**
+ * DOC: PowerVR IOCTL SUBMIT_JOBS interface
+ */
+
+/**
+ * DOC: Flags for the drm_pvr_sync_op object.
+ *
+ * .. c:macro:: DRM_PVR_SYNC_OP_HANDLE_TYPE_MASK
+ *
+ *    Handle type mask for the drm_pvr_sync_op::flags field.
+ *
+ * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_SYNCOBJ
+ *
+ *    Indicates the handle passed in drm_pvr_sync_op::handle is a syncobj handle.
+ *    This is the default type.
+ *
+ * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_TIMELINE_SYNCOBJ
+ *
+ *    Indicates the handle passed in drm_pvr_sync_op::handle is a timeline syncobj handle.
+ *
+ * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_SIGNAL
+ *
+ *    Signal operation requested. The out-fence bound to the job will be attached to
+ *    the syncobj whose handle is passed in drm_pvr_sync_op::handle.
+ *
+ * .. c:macro:: DRM_PVR_SYNC_OP_FLAG_WAIT
+ *
+ *    Wait operation requested. The job will wait for this particular syncobj or syncobj
+ *    point to be signaled before being started.
+ *    This is the default operation.
+ */
+#define DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_MASK 0xf
+#define DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_SYNCOBJ 0
+#define DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_TIMELINE_SYNCOBJ 1
+#define DRM_PVR_SYNC_OP_FLAG_SIGNAL _BITULL(31)
+#define DRM_PVR_SYNC_OP_FLAG_WAIT 0
+
+#define DRM_PVR_SYNC_OP_FLAGS_MASK (DRM_PVR_SYNC_OP_FLAG_HANDLE_TYPE_MASK | \
+				    DRM_PVR_SYNC_OP_FLAG_SIGNAL)
+
+/**
+ * struct drm_pvr_sync_op - Object describing a sync operation
+ */
+struct drm_pvr_sync_op {
+	/** @handle: Handle of sync object. */
+	__u32 handle;
+
+	/** @flags: Combination of ``DRM_PVR_SYNC_OP_FLAG_`` flags. */
+	__u32 flags;
+
+	/** @value: Timeline value for this drm_syncobj. MBZ for a binary syncobj. */
+	__u64 value;
+};
+
+/**
+ * DOC: Flags for SUBMIT_JOB ioctl geometry command.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_FIRST
+ *
+ *    Indicates if this the first command to be issued for a render.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_LAST
+ *
+ *    Indicates if this the last command to be issued for a render.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_SINGLE_CORE
+ *
+ *    Forces to use single core in a multi core device.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_GEOM_CMD_FLAGS_MASK
+ *
+ *    Logical OR of all the geometry cmd flags.
+ */
+#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_FIRST _BITULL(0)
+#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_LAST _BITULL(1)
+#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_SINGLE_CORE _BITULL(2)
+#define DRM_PVR_SUBMIT_JOB_GEOM_CMD_FLAGS_MASK                                 \
+	(DRM_PVR_SUBMIT_JOB_GEOM_CMD_FIRST |                                   \
+	 DRM_PVR_SUBMIT_JOB_GEOM_CMD_LAST |                                    \
+	 DRM_PVR_SUBMIT_JOB_GEOM_CMD_SINGLE_CORE)
+
+/**
+ * DOC: Flags for SUBMIT_JOB ioctl fragment command.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_SINGLE_CORE
+ *
+ *    Use single core in a multi core setup.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_DEPTHBUFFER
+ *
+ *    Indicates whether a depth buffer is present.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_STENCILBUFFER
+ *
+ *    Indicates whether a stencil buffer is present.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_PREVENT_CDM_OVERLAP
+ *
+ *    Disallow compute overlapped with this render.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_GET_VIS_RESULTS
+ *
+ *    Indicates whether this render produces visibility results.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_SCRATCHBUFFER
+ *
+ *    Indicates whether partial renders write to a scratch buffer instead of
+ *    the final surface. It also forces the full screen copy expected to be
+ *    present on the last render after all partial renders have completed.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_DISABLE_PIXELMERGE
+ *
+ *    Disable pixel merging for this render.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_FRAG_CMD_FLAGS_MASK
+ *
+ *    Logical OR of all the fragment cmd flags.
+ */
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_SINGLE_CORE _BITULL(0)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_DEPTHBUFFER _BITULL(1)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_STENCILBUFFER _BITULL(2)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_PREVENT_CDM_OVERLAP _BITULL(3)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_SCRATCHBUFFER _BITULL(4)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_GET_VIS_RESULTS _BITULL(5)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_PARTIAL_RENDER _BITULL(6)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_DISABLE_PIXELMERGE _BITULL(7)
+#define DRM_PVR_SUBMIT_JOB_FRAG_CMD_FLAGS_MASK                                 \
+	(DRM_PVR_SUBMIT_JOB_FRAG_CMD_SINGLE_CORE |                             \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_DEPTHBUFFER |                             \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_STENCILBUFFER |                           \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_PREVENT_CDM_OVERLAP |                     \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_SCRATCHBUFFER |                           \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_GET_VIS_RESULTS |                         \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_PARTIAL_RENDER |                          \
+	 DRM_PVR_SUBMIT_JOB_FRAG_CMD_DISABLE_PIXELMERGE)
+
+/**
+ * DOC: Flags for SUBMIT_JOB ioctl compute command.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_PREVENT_ALL_OVERLAP
+ *
+ *    Disallow other jobs overlapped with this compute.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_SINGLE_CORE
+ *
+ *    Forces to use single core in a multi core device.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_FLAGS_MASK
+ *
+ *    Logical OR of all the compute cmd flags.
+ */
+#define DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_PREVENT_ALL_OVERLAP _BITULL(0)
+#define DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_SINGLE_CORE _BITULL(1)
+#define DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_FLAGS_MASK         \
+	(DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_PREVENT_ALL_OVERLAP | \
+	 DRM_PVR_SUBMIT_JOB_COMPUTE_CMD_SINGLE_CORE)
+
+/**
+ * DOC: Flags for SUBMIT_JOB ioctl transfer command.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_SINGLE_CORE
+ *
+ *    Forces job to use a single core in a multi core device.
+ *
+ * .. c:macro:: DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_FLAGS_MASK
+ *
+ *    Logical OR of all the transfer cmd flags.
+ */
+#define DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_SINGLE_CORE _BITULL(0)
+
+#define DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_FLAGS_MASK \
+	DRM_PVR_SUBMIT_JOB_TRANSFER_CMD_SINGLE_CORE
+
+/**
+ * enum drm_pvr_job_type - Arguments for &struct drm_pvr_job.job_type
+ */
+enum drm_pvr_job_type {
+	/** @DRM_PVR_JOB_TYPE_GEOMETRY: Job type is geometry. */
+	DRM_PVR_JOB_TYPE_GEOMETRY = 0,
+
+	/** @DRM_PVR_JOB_TYPE_FRAGMENT: Job type is fragment. */
+	DRM_PVR_JOB_TYPE_FRAGMENT,
+
+	/** @DRM_PVR_JOB_TYPE_COMPUTE: Job type is compute. */
+	DRM_PVR_JOB_TYPE_COMPUTE,
+
+	/** @DRM_PVR_JOB_TYPE_TRANSFER_FRAG: Job type is a fragment transfer. */
+	DRM_PVR_JOB_TYPE_TRANSFER_FRAG,
+};
+
+/**
+ * struct drm_pvr_hwrt_data_ref - Reference HWRT data
+ */
+struct drm_pvr_hwrt_data_ref {
+	/** @set_handle: HWRT data set handle. */
+	__u32 set_handle;
+
+	/** @data_index: Index of the HWRT data inside the data set. */
+	__u32 data_index;
+};
+
+/**
+ * struct drm_pvr_job - Job arguments passed to the %DRM_IOCTL_PVR_SUBMIT_JOBS ioctl
+ */
+struct drm_pvr_job {
+	/**
+	 * @type: [IN] Type of job being submitted
+	 *
+	 * This must be one of the values defined by &enum drm_pvr_job_type.
+	 */
+	__u32 type;
+
+	/**
+	 * @context_handle: [IN] Context handle.
+	 *
+	 * When @job_type is %DRM_PVR_JOB_TYPE_RENDER, %DRM_PVR_JOB_TYPE_COMPUTE or
+	 * %DRM_PVR_JOB_TYPE_TRANSFER_FRAG, this must be a valid handle returned by
+	 * %DRM_IOCTL_PVR_CREATE_CONTEXT. The type of context must be compatible
+	 * with the type of job being submitted.
+	 *
+	 * When @job_type is %DRM_PVR_JOB_TYPE_NULL, this must be zero.
+	 */
+	__u32 context_handle;
+
+	/**
+	 * @flags: [IN] Flags for command.
+	 *
+	 * Those are job-dependent. See all ``DRM_PVR_SUBMIT_JOB_*``.
+	 */
+	__u32 flags;
+
+	/**
+	 * @cmd_stream_len: [IN] Length of command stream, in bytes.
+	 */
+	__u32 cmd_stream_len;
+
+	/**
+	 * @cmd_stream: [IN] Pointer to command stream for command.
+	 *
+	 * The command stream must be u64-aligned.
+	 */
+	__u64 cmd_stream;
+
+	/** @sync_ops: [IN] Fragment sync operations. */
+	struct drm_pvr_obj_array sync_ops;
+
+	/**
+	 * @hwrt: [IN] HWRT data used by render jobs (geometry or fragment).
+	 *
+	 * Must be zero for non-render jobs.
+	 */
+	struct drm_pvr_hwrt_data_ref hwrt;
+};
+
+/**
+ * struct drm_pvr_ioctl_submit_jobs_args - Arguments for %DRM_IOCTL_PVR_SUBMIT_JOB
+ *
+ * If the syscall returns an error it is important to check the value of
+ * @jobs.count. This indicates the index into @jobs.array where the
+ * error occurred.
+ */
+struct drm_pvr_ioctl_submit_jobs_args {
+	/** @jobs: [IN] Array of jobs to submit. */
+	struct drm_pvr_obj_array jobs;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* PVR_DRM_UAPI_H */
diff --git a/include/uapi/drm/qaic_accel.h b/include/uapi/drm/qaic_accel.h
new file mode 100644
index 000000000..c92d0309d
--- /dev/null
+++ b/include/uapi/drm/qaic_accel.h
@@ -0,0 +1,399 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+ *
+ * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef QAIC_ACCEL_H_
+#define QAIC_ACCEL_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* The length(4K) includes len and count fields of qaic_manage_msg */
+#define QAIC_MANAGE_MAX_MSG_LENGTH SZ_4K
+
+/* semaphore flags */
+#define QAIC_SEM_INSYNCFENCE	2
+#define QAIC_SEM_OUTSYNCFENCE	1
+
+/* Semaphore commands */
+#define QAIC_SEM_NOP		0
+#define QAIC_SEM_INIT		1
+#define QAIC_SEM_INC		2
+#define QAIC_SEM_DEC		3
+#define QAIC_SEM_WAIT_EQUAL	4
+#define QAIC_SEM_WAIT_GT_EQ	5 /* Greater than or equal */
+#define QAIC_SEM_WAIT_GT_0	6 /* Greater than 0 */
+
+#define QAIC_TRANS_UNDEFINED			0
+#define QAIC_TRANS_PASSTHROUGH_FROM_USR		1
+#define QAIC_TRANS_PASSTHROUGH_TO_USR		2
+#define QAIC_TRANS_PASSTHROUGH_FROM_DEV		3
+#define QAIC_TRANS_PASSTHROUGH_TO_DEV		4
+#define QAIC_TRANS_DMA_XFER_FROM_USR		5
+#define QAIC_TRANS_DMA_XFER_TO_DEV		6
+#define QAIC_TRANS_ACTIVATE_FROM_USR		7
+#define QAIC_TRANS_ACTIVATE_FROM_DEV		8
+#define QAIC_TRANS_ACTIVATE_TO_DEV		9
+#define QAIC_TRANS_DEACTIVATE_FROM_USR		10
+#define QAIC_TRANS_DEACTIVATE_FROM_DEV		11
+#define QAIC_TRANS_STATUS_FROM_USR		12
+#define QAIC_TRANS_STATUS_TO_USR		13
+#define QAIC_TRANS_STATUS_FROM_DEV		14
+#define QAIC_TRANS_STATUS_TO_DEV		15
+#define QAIC_TRANS_TERMINATE_FROM_DEV		16
+#define QAIC_TRANS_TERMINATE_TO_DEV		17
+#define QAIC_TRANS_DMA_XFER_CONT		18
+#define QAIC_TRANS_VALIDATE_PARTITION_FROM_DEV	19
+#define QAIC_TRANS_VALIDATE_PARTITION_TO_DEV	20
+
+/**
+ * struct qaic_manage_trans_hdr - Header for a transaction in a manage message.
+ * @type: In. Identifies this transaction. See QAIC_TRANS_* defines.
+ * @len: In. Length of this transaction, including this header.
+ */
+struct qaic_manage_trans_hdr {
+	__u32 type;
+	__u32 len;
+};
+
+/**
+ * struct qaic_manage_trans_passthrough - Defines a passthrough transaction.
+ * @hdr: In. Header to identify this transaction.
+ * @data: In. Payload of this transaction. Opaque to the driver. Userspace must
+ *	  encode in little endian and align/pad to 64-bit.
+ */
+struct qaic_manage_trans_passthrough {
+	struct qaic_manage_trans_hdr hdr;
+	__u8 data[];
+};
+
+/**
+ * struct qaic_manage_trans_dma_xfer - Defines a DMA transfer transaction.
+ * @hdr: In. Header to identify this transaction.
+ * @tag: In. Identified this transfer in other transactions. Opaque to the
+ *	 driver.
+ * @pad: Structure padding.
+ * @addr: In. Address of the data to DMA to the device.
+ * @size: In. Length of the data to DMA to the device.
+ */
+struct qaic_manage_trans_dma_xfer {
+	struct qaic_manage_trans_hdr hdr;
+	__u32 tag;
+	__u32 pad;
+	__u64 addr;
+	__u64 size;
+};
+
+/**
+ * struct qaic_manage_trans_activate_to_dev - Defines an activate request.
+ * @hdr: In. Header to identify this transaction.
+ * @queue_size: In. Number of elements for DBC request and response queues.
+ * @eventfd: Unused.
+ * @options: In. Device specific options for this activate.
+ * @pad: Structure padding.  Must be 0.
+ */
+struct qaic_manage_trans_activate_to_dev {
+	struct qaic_manage_trans_hdr hdr;
+	__u32 queue_size;
+	__u32 eventfd;
+	__u32 options;
+	__u32 pad;
+};
+
+/**
+ * struct qaic_manage_trans_activate_from_dev - Defines an activate response.
+ * @hdr: Out. Header to identify this transaction.
+ * @status: Out. Return code of the request from the device.
+ * @dbc_id: Out. Id of the assigned DBC for successful request.
+ * @options: Out. Device specific options for this activate.
+ */
+struct qaic_manage_trans_activate_from_dev {
+	struct qaic_manage_trans_hdr hdr;
+	__u32 status;
+	__u32 dbc_id;
+	__u64 options;
+};
+
+/**
+ * struct qaic_manage_trans_deactivate - Defines a deactivate request.
+ * @hdr: In. Header to identify this transaction.
+ * @dbc_id: In. Id of assigned DBC.
+ * @pad: Structure padding.  Must be 0.
+ */
+struct qaic_manage_trans_deactivate {
+	struct qaic_manage_trans_hdr hdr;
+	__u32 dbc_id;
+	__u32 pad;
+};
+
+/**
+ * struct qaic_manage_trans_status_to_dev - Defines a status request.
+ * @hdr: In. Header to identify this transaction.
+ */
+struct qaic_manage_trans_status_to_dev {
+	struct qaic_manage_trans_hdr hdr;
+};
+
+/**
+ * struct qaic_manage_trans_status_from_dev - Defines a status response.
+ * @hdr: Out. Header to identify this transaction.
+ * @major: Out. NNC protocol version major number.
+ * @minor: Out. NNC protocol version minor number.
+ * @status: Out. Return code from device.
+ * @status_flags: Out. Flags from device.  Bit 0 indicates if CRCs are required.
+ */
+struct qaic_manage_trans_status_from_dev {
+	struct qaic_manage_trans_hdr hdr;
+	__u16 major;
+	__u16 minor;
+	__u32 status;
+	__u64 status_flags;
+};
+
+/**
+ * struct qaic_manage_msg - Defines a message to the device.
+ * @len: In. Length of all the transactions contained within this message.
+ * @count: In. Number of transactions in this message.
+ * @data: In. Address to an array where the transactions can be found.
+ */
+struct qaic_manage_msg {
+	__u32 len;
+	__u32 count;
+	__u64 data;
+};
+
+/**
+ * struct qaic_create_bo - Defines a request to create a buffer object.
+ * @size: In.  Size of the buffer in bytes.
+ * @handle: Out. GEM handle for the BO.
+ * @pad: Structure padding. Must be 0.
+ */
+struct qaic_create_bo {
+	__u64 size;
+	__u32 handle;
+	__u32 pad;
+};
+
+/**
+ * struct qaic_mmap_bo - Defines a request to prepare a BO for mmap().
+ * @handle: In.  Handle of the GEM BO to prepare for mmap().
+ * @pad: Structure padding. Must be 0.
+ * @offset: Out. Offset value to provide to mmap().
+ */
+struct qaic_mmap_bo {
+	__u32 handle;
+	__u32 pad;
+	__u64 offset;
+};
+
+/**
+ * struct qaic_sem - Defines a semaphore command for a BO slice.
+ * @val: In. Only lower 12 bits are valid.
+ * @index: In. Only lower 5 bits are valid.
+ * @presync: In. 1 if presync operation, 0 if postsync.
+ * @cmd: In. One of QAIC_SEM_*.
+ * @flags: In. Bitfield. See QAIC_SEM_INSYNCFENCE and QAIC_SEM_OUTSYNCFENCE
+ * @pad: Structure padding.  Must be 0.
+ */
+struct qaic_sem {
+	__u16 val;
+	__u8  index;
+	__u8  presync;
+	__u8  cmd;
+	__u8  flags;
+	__u16 pad;
+};
+
+/**
+ * struct qaic_attach_slice_entry - Defines a single BO slice.
+ * @size: In. Size of this slice in bytes.
+ * @sem0: In. Semaphore command 0. Must be 0 is not valid.
+ * @sem1: In. Semaphore command 1. Must be 0 is not valid.
+ * @sem2: In. Semaphore command 2. Must be 0 is not valid.
+ * @sem3: In. Semaphore command 3. Must be 0 is not valid.
+ * @dev_addr: In. Device address this slice pushes to or pulls from.
+ * @db_addr: In. Address of the doorbell to ring.
+ * @db_data: In. Data to write to the doorbell.
+ * @db_len: In. Size of the doorbell data in bits - 32, 16, or 8.  0 is for
+ *	    inactive doorbells.
+ * @offset: In. Start of this slice as an offset from the start of the BO.
+ */
+struct qaic_attach_slice_entry {
+	__u64 size;
+	struct qaic_sem	sem0;
+	struct qaic_sem	sem1;
+	struct qaic_sem	sem2;
+	struct qaic_sem	sem3;
+	__u64 dev_addr;
+	__u64 db_addr;
+	__u32 db_data;
+	__u32 db_len;
+	__u64 offset;
+};
+
+/**
+ * struct qaic_attach_slice_hdr - Defines metadata for a set of BO slices.
+ * @count: In. Number of slices for this BO.
+ * @dbc_id: In. Associate the sliced BO with this DBC.
+ * @handle: In. GEM handle of the BO to slice.
+ * @dir: In. Direction of data flow. 1 = DMA_TO_DEVICE, 2 = DMA_FROM_DEVICE
+ * @size: Deprecated. This value is ignored and size of @handle is used instead.
+ */
+struct qaic_attach_slice_hdr {
+	__u32 count;
+	__u32 dbc_id;
+	__u32 handle;
+	__u32 dir;
+	__u64 size;
+};
+
+/**
+ * struct qaic_attach_slice - Defines a set of BO slices.
+ * @hdr: In. Metadata of the set of slices.
+ * @data: In. Pointer to an array containing the slice definitions.
+ */
+struct qaic_attach_slice {
+	struct qaic_attach_slice_hdr hdr;
+	__u64 data;
+};
+
+/**
+ * struct qaic_execute_entry - Defines a BO to submit to the device.
+ * @handle: In. GEM handle of the BO to commit to the device.
+ * @dir: In. Direction of data. 1 = to device, 2 = from device.
+ */
+struct qaic_execute_entry {
+	__u32 handle;
+	__u32 dir;
+};
+
+/**
+ * struct qaic_partial_execute_entry - Defines a BO to resize and submit.
+ * @handle: In. GEM handle of the BO to commit to the device.
+ * @dir: In. Direction of data. 1 = to device, 2 = from device.
+ * @resize: In. New size of the BO.  Must be <= the original BO size.
+ *	    @resize as 0 would be interpreted as no DMA transfer is
+ *	    involved.
+ */
+struct qaic_partial_execute_entry {
+	__u32 handle;
+	__u32 dir;
+	__u64 resize;
+};
+
+/**
+ * struct qaic_execute_hdr - Defines metadata for BO submission.
+ * @count: In. Number of BOs to submit.
+ * @dbc_id: In. DBC to submit the BOs on.
+ */
+struct qaic_execute_hdr {
+	__u32 count;
+	__u32 dbc_id;
+};
+
+/**
+ * struct qaic_execute - Defines a list of BOs to submit to the device.
+ * @hdr: In. BO list metadata.
+ * @data: In. Pointer to an array of BOs to submit.
+ */
+struct qaic_execute {
+	struct qaic_execute_hdr hdr;
+	__u64 data;
+};
+
+/**
+ * struct qaic_wait - Defines a blocking wait for BO execution.
+ * @handle: In. GEM handle of the BO to wait on.
+ * @timeout: In. Maximum time in ms to wait for the BO.
+ * @dbc_id: In. DBC the BO is submitted to.
+ * @pad: Structure padding. Must be 0.
+ */
+struct qaic_wait {
+	__u32 handle;
+	__u32 timeout;
+	__u32 dbc_id;
+	__u32 pad;
+};
+
+/**
+ * struct qaic_perf_stats_hdr - Defines metadata for getting BO perf info.
+ * @count: In. Number of BOs requested.
+ * @pad: Structure padding. Must be 0.
+ * @dbc_id: In. DBC the BO are associated with.
+ */
+struct qaic_perf_stats_hdr {
+	__u16 count;
+	__u16 pad;
+	__u32 dbc_id;
+};
+
+/**
+ * struct qaic_perf_stats - Defines a request for getting BO perf info.
+ * @hdr: In. Request metadata
+ * @data: In. Pointer to array of stats structures that will receive the data.
+ */
+struct qaic_perf_stats {
+	struct qaic_perf_stats_hdr hdr;
+	__u64 data;
+};
+
+/**
+ * struct qaic_perf_stats_entry - Defines a BO perf info.
+ * @handle: In. GEM handle of the BO to get perf stats for.
+ * @queue_level_before: Out. Number of elements in the queue before this BO
+ *			was submitted.
+ * @num_queue_element: Out. Number of elements added to the queue to submit
+ *		       this BO.
+ * @submit_latency_us: Out. Time taken by the driver to submit this BO.
+ * @device_latency_us: Out. Time taken by the device to execute this BO.
+ * @pad: Structure padding. Must be 0.
+ */
+struct qaic_perf_stats_entry {
+	__u32 handle;
+	__u32 queue_level_before;
+	__u32 num_queue_element;
+	__u32 submit_latency_us;
+	__u32 device_latency_us;
+	__u32 pad;
+};
+
+/**
+ * struct qaic_detach_slice - Detaches slicing configuration from BO.
+ * @handle: In. GEM handle of the BO to detach slicing configuration.
+ * @pad: Structure padding. Must be 0.
+ */
+struct qaic_detach_slice {
+	__u32 handle;
+	__u32 pad;
+};
+
+#define DRM_QAIC_MANAGE				0x00
+#define DRM_QAIC_CREATE_BO			0x01
+#define DRM_QAIC_MMAP_BO			0x02
+#define DRM_QAIC_ATTACH_SLICE_BO		0x03
+#define DRM_QAIC_EXECUTE_BO			0x04
+#define DRM_QAIC_PARTIAL_EXECUTE_BO		0x05
+#define DRM_QAIC_WAIT_BO			0x06
+#define DRM_QAIC_PERF_STATS_BO			0x07
+#define DRM_QAIC_DETACH_SLICE_BO		0x08
+
+#define DRM_IOCTL_QAIC_MANAGE			DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_MANAGE, struct qaic_manage_msg)
+#define DRM_IOCTL_QAIC_CREATE_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_CREATE_BO,	struct qaic_create_bo)
+#define DRM_IOCTL_QAIC_MMAP_BO			DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_MMAP_BO, struct qaic_mmap_bo)
+#define DRM_IOCTL_QAIC_ATTACH_SLICE_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_ATTACH_SLICE_BO, struct qaic_attach_slice)
+#define DRM_IOCTL_QAIC_EXECUTE_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_EXECUTE_BO,	struct qaic_execute)
+#define DRM_IOCTL_QAIC_PARTIAL_EXECUTE_BO	DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_PARTIAL_EXECUTE_BO,	struct qaic_execute)
+#define DRM_IOCTL_QAIC_WAIT_BO			DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_WAIT_BO, struct qaic_wait)
+#define DRM_IOCTL_QAIC_PERF_STATS_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_QAIC_PERF_STATS_BO, struct qaic_perf_stats)
+#define DRM_IOCTL_QAIC_DETACH_SLICE_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_QAIC_DETACH_SLICE_BO, struct qaic_detach_slice)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* QAIC_ACCEL_H_ */
diff --git a/include/uapi/drm/qxl_drm.h b/include/uapi/drm/qxl_drm.h
new file mode 100644
index 000000000..880999d2d
--- /dev/null
+++ b/include/uapi/drm/qxl_drm.h
@@ -0,0 +1,158 @@
+/*
+ * Copyright 2013 Red Hat
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef QXL_DRM_H
+#define QXL_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.
+ *
+ * Do not use pointers, use __u64 instead for 32 bit / 64 bit user/kernel
+ * compatibility Keep fields aligned to their size
+ */
+
+#define QXL_GEM_DOMAIN_CPU 0
+#define QXL_GEM_DOMAIN_VRAM 1
+#define QXL_GEM_DOMAIN_SURFACE 2
+
+#define DRM_QXL_ALLOC       0x00
+#define DRM_QXL_MAP         0x01
+#define DRM_QXL_EXECBUFFER  0x02
+#define DRM_QXL_UPDATE_AREA 0x03
+#define DRM_QXL_GETPARAM    0x04
+#define DRM_QXL_CLIENTCAP   0x05
+
+#define DRM_QXL_ALLOC_SURF  0x06
+
+struct drm_qxl_alloc {
+	__u32 size;
+	__u32 handle; /* 0 is an invalid handle */
+};
+
+struct drm_qxl_map {
+	__u64 offset; /* use for mmap system call */
+	__u32 handle;
+	__u32 pad;
+};
+
+/*
+ * dest is the bo we are writing the relocation into
+ * src is bo we are relocating.
+ * *(dest_handle.base_addr + dest_offset) = physical_address(src_handle.addr +
+ * src_offset)
+ */
+#define QXL_RELOC_TYPE_BO 1
+#define QXL_RELOC_TYPE_SURF 2
+
+struct drm_qxl_reloc {
+	__u64 src_offset; /* offset into src_handle or src buffer */
+	__u64 dst_offset; /* offset in dest handle */
+	__u32 src_handle; /* dest handle to compute address from */
+	__u32 dst_handle; /* 0 if to command buffer */
+	__u32 reloc_type;
+	__u32 pad;
+};
+
+struct drm_qxl_command {
+	__u64		command; /* void* */
+	__u64		relocs; /* struct drm_qxl_reloc* */
+	__u32		type;
+	__u32		command_size;
+	__u32		relocs_num;
+	__u32                pad;
+};
+
+struct drm_qxl_execbuffer {
+	__u32		flags;		/* for future use */
+	__u32		commands_num;
+	__u64		commands;	/* struct drm_qxl_command* */
+};
+
+struct drm_qxl_update_area {
+	__u32 handle;
+	__u32 top;
+	__u32 left;
+	__u32 bottom;
+	__u32 right;
+	__u32 pad;
+};
+
+#define QXL_PARAM_NUM_SURFACES 1 /* rom->n_surfaces */
+#define QXL_PARAM_MAX_RELOCS 2
+struct drm_qxl_getparam {
+	__u64 param;
+	__u64 value;
+};
+
+/* these are one bit values */
+struct drm_qxl_clientcap {
+	__u32 index;
+	__u32 pad;
+};
+
+struct drm_qxl_alloc_surf {
+	__u32 format;
+	__u32 width;
+	__u32 height;
+	__s32 stride;
+	__u32 handle;
+	__u32 pad;
+};
+
+#define DRM_IOCTL_QXL_ALLOC \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_QXL_ALLOC, struct drm_qxl_alloc)
+
+#define DRM_IOCTL_QXL_MAP \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_QXL_MAP, struct drm_qxl_map)
+
+#define DRM_IOCTL_QXL_EXECBUFFER \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_QXL_EXECBUFFER,\
+		struct drm_qxl_execbuffer)
+
+#define DRM_IOCTL_QXL_UPDATE_AREA \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_QXL_UPDATE_AREA,\
+		struct drm_qxl_update_area)
+
+#define DRM_IOCTL_QXL_GETPARAM \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_QXL_GETPARAM,\
+		struct drm_qxl_getparam)
+
+#define DRM_IOCTL_QXL_CLIENTCAP \
+	DRM_IOW(DRM_COMMAND_BASE + DRM_QXL_CLIENTCAP,\
+		struct drm_qxl_clientcap)
+
+#define DRM_IOCTL_QXL_ALLOC_SURF \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_QXL_ALLOC_SURF,\
+		struct drm_qxl_alloc_surf)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
new file mode 100644
index 000000000..490a59cc4
--- /dev/null
+++ b/include/uapi/drm/radeon_drm.h
@@ -0,0 +1,1078 @@
+/* radeon_drm.h -- Public header for the radeon driver -*- linux-c -*-
+ *
+ * Copyright 2000 Precision Insight, Inc., Cedar Park, Texas.
+ * Copyright 2000 VA Linux Systems, Inc., Fremont, California.
+ * Copyright 2002 Tungsten Graphics, Inc., Cedar Park, Texas.
+ * All rights reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Authors:
+ *    Kevin E. Martin <martin@valinux.com>
+ *    Gareth Hughes <gareth@valinux.com>
+ *    Keith Whitwell <keith@tungstengraphics.com>
+ */
+
+#ifndef __RADEON_DRM_H__
+#define __RADEON_DRM_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* WARNING: If you change any of these defines, make sure to change the
+ * defines in the X server file (radeon_sarea.h)
+ */
+#ifndef __RADEON_SAREA_DEFINES__
+#define __RADEON_SAREA_DEFINES__
+
+/* Old style state flags, required for sarea interface (1.1 and 1.2
+ * clears) and 1.2 drm_vertex2 ioctl.
+ */
+#define RADEON_UPLOAD_CONTEXT		0x00000001
+#define RADEON_UPLOAD_VERTFMT		0x00000002
+#define RADEON_UPLOAD_LINE		0x00000004
+#define RADEON_UPLOAD_BUMPMAP		0x00000008
+#define RADEON_UPLOAD_MASKS		0x00000010
+#define RADEON_UPLOAD_VIEWPORT		0x00000020
+#define RADEON_UPLOAD_SETUP		0x00000040
+#define RADEON_UPLOAD_TCL		0x00000080
+#define RADEON_UPLOAD_MISC		0x00000100
+#define RADEON_UPLOAD_TEX0		0x00000200
+#define RADEON_UPLOAD_TEX1		0x00000400
+#define RADEON_UPLOAD_TEX2		0x00000800
+#define RADEON_UPLOAD_TEX0IMAGES	0x00001000
+#define RADEON_UPLOAD_TEX1IMAGES	0x00002000
+#define RADEON_UPLOAD_TEX2IMAGES	0x00004000
+#define RADEON_UPLOAD_CLIPRECTS		0x00008000	/* handled client-side */
+#define RADEON_REQUIRE_QUIESCENCE	0x00010000
+#define RADEON_UPLOAD_ZBIAS		0x00020000	/* version 1.2 and newer */
+#define RADEON_UPLOAD_ALL		0x003effff
+#define RADEON_UPLOAD_CONTEXT_ALL       0x003e01ff
+
+/* New style per-packet identifiers for use in cmd_buffer ioctl with
+ * the RADEON_EMIT_PACKET command.  Comments relate new packets to old
+ * state bits and the packet size:
+ */
+#define RADEON_EMIT_PP_MISC                         0	/* context/7 */
+#define RADEON_EMIT_PP_CNTL                         1	/* context/3 */
+#define RADEON_EMIT_RB3D_COLORPITCH                 2	/* context/1 */
+#define RADEON_EMIT_RE_LINE_PATTERN                 3	/* line/2 */
+#define RADEON_EMIT_SE_LINE_WIDTH                   4	/* line/1 */
+#define RADEON_EMIT_PP_LUM_MATRIX                   5	/* bumpmap/1 */
+#define RADEON_EMIT_PP_ROT_MATRIX_0                 6	/* bumpmap/2 */
+#define RADEON_EMIT_RB3D_STENCILREFMASK             7	/* masks/3 */
+#define RADEON_EMIT_SE_VPORT_XSCALE                 8	/* viewport/6 */
+#define RADEON_EMIT_SE_CNTL                         9	/* setup/2 */
+#define RADEON_EMIT_SE_CNTL_STATUS                  10	/* setup/1 */
+#define RADEON_EMIT_RE_MISC                         11	/* misc/1 */
+#define RADEON_EMIT_PP_TXFILTER_0                   12	/* tex0/6 */
+#define RADEON_EMIT_PP_BORDER_COLOR_0               13	/* tex0/1 */
+#define RADEON_EMIT_PP_TXFILTER_1                   14	/* tex1/6 */
+#define RADEON_EMIT_PP_BORDER_COLOR_1               15	/* tex1/1 */
+#define RADEON_EMIT_PP_TXFILTER_2                   16	/* tex2/6 */
+#define RADEON_EMIT_PP_BORDER_COLOR_2               17	/* tex2/1 */
+#define RADEON_EMIT_SE_ZBIAS_FACTOR                 18	/* zbias/2 */
+#define RADEON_EMIT_SE_TCL_OUTPUT_VTX_FMT           19	/* tcl/11 */
+#define RADEON_EMIT_SE_TCL_MATERIAL_EMMISSIVE_RED   20	/* material/17 */
+#define R200_EMIT_PP_TXCBLEND_0                     21	/* tex0/4 */
+#define R200_EMIT_PP_TXCBLEND_1                     22	/* tex1/4 */
+#define R200_EMIT_PP_TXCBLEND_2                     23	/* tex2/4 */
+#define R200_EMIT_PP_TXCBLEND_3                     24	/* tex3/4 */
+#define R200_EMIT_PP_TXCBLEND_4                     25	/* tex4/4 */
+#define R200_EMIT_PP_TXCBLEND_5                     26	/* tex5/4 */
+#define R200_EMIT_PP_TXCBLEND_6                     27	/* /4 */
+#define R200_EMIT_PP_TXCBLEND_7                     28	/* /4 */
+#define R200_EMIT_TCL_LIGHT_MODEL_CTL_0             29	/* tcl/7 */
+#define R200_EMIT_TFACTOR_0                         30	/* tf/7 */
+#define R200_EMIT_VTX_FMT_0                         31	/* vtx/5 */
+#define R200_EMIT_VAP_CTL                           32	/* vap/1 */
+#define R200_EMIT_MATRIX_SELECT_0                   33	/* msl/5 */
+#define R200_EMIT_TEX_PROC_CTL_2                    34	/* tcg/5 */
+#define R200_EMIT_TCL_UCP_VERT_BLEND_CTL            35	/* tcl/1 */
+#define R200_EMIT_PP_TXFILTER_0                     36	/* tex0/6 */
+#define R200_EMIT_PP_TXFILTER_1                     37	/* tex1/6 */
+#define R200_EMIT_PP_TXFILTER_2                     38	/* tex2/6 */
+#define R200_EMIT_PP_TXFILTER_3                     39	/* tex3/6 */
+#define R200_EMIT_PP_TXFILTER_4                     40	/* tex4/6 */
+#define R200_EMIT_PP_TXFILTER_5                     41	/* tex5/6 */
+#define R200_EMIT_PP_TXOFFSET_0                     42	/* tex0/1 */
+#define R200_EMIT_PP_TXOFFSET_1                     43	/* tex1/1 */
+#define R200_EMIT_PP_TXOFFSET_2                     44	/* tex2/1 */
+#define R200_EMIT_PP_TXOFFSET_3                     45	/* tex3/1 */
+#define R200_EMIT_PP_TXOFFSET_4                     46	/* tex4/1 */
+#define R200_EMIT_PP_TXOFFSET_5                     47	/* tex5/1 */
+#define R200_EMIT_VTE_CNTL                          48	/* vte/1 */
+#define R200_EMIT_OUTPUT_VTX_COMP_SEL               49	/* vtx/1 */
+#define R200_EMIT_PP_TAM_DEBUG3                     50	/* tam/1 */
+#define R200_EMIT_PP_CNTL_X                         51	/* cst/1 */
+#define R200_EMIT_RB3D_DEPTHXY_OFFSET               52	/* cst/1 */
+#define R200_EMIT_RE_AUX_SCISSOR_CNTL               53	/* cst/1 */
+#define R200_EMIT_RE_SCISSOR_TL_0                   54	/* cst/2 */
+#define R200_EMIT_RE_SCISSOR_TL_1                   55	/* cst/2 */
+#define R200_EMIT_RE_SCISSOR_TL_2                   56	/* cst/2 */
+#define R200_EMIT_SE_VAP_CNTL_STATUS                57	/* cst/1 */
+#define R200_EMIT_SE_VTX_STATE_CNTL                 58	/* cst/1 */
+#define R200_EMIT_RE_POINTSIZE                      59	/* cst/1 */
+#define R200_EMIT_TCL_INPUT_VTX_VECTOR_ADDR_0       60	/* cst/4 */
+#define R200_EMIT_PP_CUBIC_FACES_0                  61
+#define R200_EMIT_PP_CUBIC_OFFSETS_0                62
+#define R200_EMIT_PP_CUBIC_FACES_1                  63
+#define R200_EMIT_PP_CUBIC_OFFSETS_1                64
+#define R200_EMIT_PP_CUBIC_FACES_2                  65
+#define R200_EMIT_PP_CUBIC_OFFSETS_2                66
+#define R200_EMIT_PP_CUBIC_FACES_3                  67
+#define R200_EMIT_PP_CUBIC_OFFSETS_3                68
+#define R200_EMIT_PP_CUBIC_FACES_4                  69
+#define R200_EMIT_PP_CUBIC_OFFSETS_4                70
+#define R200_EMIT_PP_CUBIC_FACES_5                  71
+#define R200_EMIT_PP_CUBIC_OFFSETS_5                72
+#define RADEON_EMIT_PP_TEX_SIZE_0                   73
+#define RADEON_EMIT_PP_TEX_SIZE_1                   74
+#define RADEON_EMIT_PP_TEX_SIZE_2                   75
+#define R200_EMIT_RB3D_BLENDCOLOR                   76
+#define R200_EMIT_TCL_POINT_SPRITE_CNTL             77
+#define RADEON_EMIT_PP_CUBIC_FACES_0                78
+#define RADEON_EMIT_PP_CUBIC_OFFSETS_T0             79
+#define RADEON_EMIT_PP_CUBIC_FACES_1                80
+#define RADEON_EMIT_PP_CUBIC_OFFSETS_T1             81
+#define RADEON_EMIT_PP_CUBIC_FACES_2                82
+#define RADEON_EMIT_PP_CUBIC_OFFSETS_T2             83
+#define R200_EMIT_PP_TRI_PERF_CNTL                  84
+#define R200_EMIT_PP_AFS_0                          85
+#define R200_EMIT_PP_AFS_1                          86
+#define R200_EMIT_ATF_TFACTOR                       87
+#define R200_EMIT_PP_TXCTLALL_0                     88
+#define R200_EMIT_PP_TXCTLALL_1                     89
+#define R200_EMIT_PP_TXCTLALL_2                     90
+#define R200_EMIT_PP_TXCTLALL_3                     91
+#define R200_EMIT_PP_TXCTLALL_4                     92
+#define R200_EMIT_PP_TXCTLALL_5                     93
+#define R200_EMIT_VAP_PVS_CNTL                      94
+#define RADEON_MAX_STATE_PACKETS                    95
+
+/* Commands understood by cmd_buffer ioctl.  More can be added but
+ * obviously these can't be removed or changed:
+ */
+#define RADEON_CMD_PACKET      1	/* emit one of the register packets above */
+#define RADEON_CMD_SCALARS     2	/* emit scalar data */
+#define RADEON_CMD_VECTORS     3	/* emit vector data */
+#define RADEON_CMD_DMA_DISCARD 4	/* discard current dma buf */
+#define RADEON_CMD_PACKET3     5	/* emit hw packet */
+#define RADEON_CMD_PACKET3_CLIP 6	/* emit hw packet wrapped in cliprects */
+#define RADEON_CMD_SCALARS2     7	/* r200 stopgap */
+#define RADEON_CMD_WAIT         8	/* emit hw wait commands -- note:
+					 *  doesn't make the cpu wait, just
+					 *  the graphics hardware */
+#define RADEON_CMD_VECLINEAR	9       /* another r200 stopgap */
+
+typedef union {
+	int i;
+	struct {
+		unsigned char cmd_type, pad0, pad1, pad2;
+	} header;
+	struct {
+		unsigned char cmd_type, packet_id, pad0, pad1;
+	} packet;
+	struct {
+		unsigned char cmd_type, offset, stride, count;
+	} scalars;
+	struct {
+		unsigned char cmd_type, offset, stride, count;
+	} vectors;
+	struct {
+		unsigned char cmd_type, addr_lo, addr_hi, count;
+	} veclinear;
+	struct {
+		unsigned char cmd_type, buf_idx, pad0, pad1;
+	} dma;
+	struct {
+		unsigned char cmd_type, flags, pad0, pad1;
+	} wait;
+} drm_radeon_cmd_header_t;
+
+#define RADEON_WAIT_2D  0x1
+#define RADEON_WAIT_3D  0x2
+
+/* Allowed parameters for R300_CMD_PACKET3
+ */
+#define R300_CMD_PACKET3_CLEAR		0
+#define R300_CMD_PACKET3_RAW		1
+
+/* Commands understood by cmd_buffer ioctl for R300.
+ * The interface has not been stabilized, so some of these may be removed
+ * and eventually reordered before stabilization.
+ */
+#define R300_CMD_PACKET0		1
+#define R300_CMD_VPU			2	/* emit vertex program upload */
+#define R300_CMD_PACKET3		3	/* emit a packet3 */
+#define R300_CMD_END3D			4	/* emit sequence ending 3d rendering */
+#define R300_CMD_CP_DELAY		5
+#define R300_CMD_DMA_DISCARD		6
+#define R300_CMD_WAIT			7
+#	define R300_WAIT_2D		0x1
+#	define R300_WAIT_3D		0x2
+/* these two defines are DOING IT WRONG - however
+ * we have userspace which relies on using these.
+ * The wait interface is backwards compat new 
+ * code should use the NEW_WAIT defines below
+ * THESE ARE NOT BIT FIELDS
+ */
+#	define R300_WAIT_2D_CLEAN	0x3
+#	define R300_WAIT_3D_CLEAN	0x4
+
+#	define R300_NEW_WAIT_2D_3D	0x3
+#	define R300_NEW_WAIT_2D_2D_CLEAN	0x4
+#	define R300_NEW_WAIT_3D_3D_CLEAN	0x6
+#	define R300_NEW_WAIT_2D_2D_CLEAN_3D_3D_CLEAN	0x8
+
+#define R300_CMD_SCRATCH		8
+#define R300_CMD_R500FP                 9
+
+typedef union {
+	unsigned int u;
+	struct {
+		unsigned char cmd_type, pad0, pad1, pad2;
+	} header;
+	struct {
+		unsigned char cmd_type, count, reglo, reghi;
+	} packet0;
+	struct {
+		unsigned char cmd_type, count, adrlo, adrhi;
+	} vpu;
+	struct {
+		unsigned char cmd_type, packet, pad0, pad1;
+	} packet3;
+	struct {
+		unsigned char cmd_type, packet;
+		unsigned short count;	/* amount of packet2 to emit */
+	} delay;
+	struct {
+		unsigned char cmd_type, buf_idx, pad0, pad1;
+	} dma;
+	struct {
+		unsigned char cmd_type, flags, pad0, pad1;
+	} wait;
+	struct {
+		unsigned char cmd_type, reg, n_bufs, flags;
+	} scratch;
+	struct {
+		unsigned char cmd_type, count, adrlo, adrhi_flags;
+	} r500fp;
+} drm_r300_cmd_header_t;
+
+#define RADEON_FRONT			0x1
+#define RADEON_BACK			0x2
+#define RADEON_DEPTH			0x4
+#define RADEON_STENCIL			0x8
+#define RADEON_CLEAR_FASTZ		0x80000000
+#define RADEON_USE_HIERZ		0x40000000
+#define RADEON_USE_COMP_ZBUF		0x20000000
+
+#define R500FP_CONSTANT_TYPE  (1 << 1)
+#define R500FP_CONSTANT_CLAMP (1 << 2)
+
+/* Primitive types
+ */
+#define RADEON_POINTS			0x1
+#define RADEON_LINES			0x2
+#define RADEON_LINE_STRIP		0x3
+#define RADEON_TRIANGLES		0x4
+#define RADEON_TRIANGLE_FAN		0x5
+#define RADEON_TRIANGLE_STRIP		0x6
+
+/* Vertex/indirect buffer size
+ */
+#define RADEON_BUFFER_SIZE		65536
+
+/* Byte offsets for indirect buffer data
+ */
+#define RADEON_INDEX_PRIM_OFFSET	20
+
+#define RADEON_SCRATCH_REG_OFFSET	32
+
+#define R600_SCRATCH_REG_OFFSET         256
+
+#define RADEON_NR_SAREA_CLIPRECTS	12
+
+/* There are 2 heaps (local/GART).  Each region within a heap is a
+ * minimum of 64k, and there are at most 64 of them per heap.
+ */
+#define RADEON_LOCAL_TEX_HEAP		0
+#define RADEON_GART_TEX_HEAP		1
+#define RADEON_NR_TEX_HEAPS		2
+#define RADEON_NR_TEX_REGIONS		64
+#define RADEON_LOG_TEX_GRANULARITY	16
+
+#define RADEON_MAX_TEXTURE_LEVELS	12
+#define RADEON_MAX_TEXTURE_UNITS	3
+
+#define RADEON_MAX_SURFACES		8
+
+/* Blits have strict offset rules.  All blit offset must be aligned on
+ * a 1K-byte boundary.
+ */
+#define RADEON_OFFSET_SHIFT             10
+#define RADEON_OFFSET_ALIGN             (1 << RADEON_OFFSET_SHIFT)
+#define RADEON_OFFSET_MASK              (RADEON_OFFSET_ALIGN - 1)
+
+#endif				/* __RADEON_SAREA_DEFINES__ */
+
+typedef struct {
+	unsigned int red;
+	unsigned int green;
+	unsigned int blue;
+	unsigned int alpha;
+} radeon_color_regs_t;
+
+typedef struct {
+	/* Context state */
+	unsigned int pp_misc;	/* 0x1c14 */
+	unsigned int pp_fog_color;
+	unsigned int re_solid_color;
+	unsigned int rb3d_blendcntl;
+	unsigned int rb3d_depthoffset;
+	unsigned int rb3d_depthpitch;
+	unsigned int rb3d_zstencilcntl;
+
+	unsigned int pp_cntl;	/* 0x1c38 */
+	unsigned int rb3d_cntl;
+	unsigned int rb3d_coloroffset;
+	unsigned int re_width_height;
+	unsigned int rb3d_colorpitch;
+	unsigned int se_cntl;
+
+	/* Vertex format state */
+	unsigned int se_coord_fmt;	/* 0x1c50 */
+
+	/* Line state */
+	unsigned int re_line_pattern;	/* 0x1cd0 */
+	unsigned int re_line_state;
+
+	unsigned int se_line_width;	/* 0x1db8 */
+
+	/* Bumpmap state */
+	unsigned int pp_lum_matrix;	/* 0x1d00 */
+
+	unsigned int pp_rot_matrix_0;	/* 0x1d58 */
+	unsigned int pp_rot_matrix_1;
+
+	/* Mask state */
+	unsigned int rb3d_stencilrefmask;	/* 0x1d7c */
+	unsigned int rb3d_ropcntl;
+	unsigned int rb3d_planemask;
+
+	/* Viewport state */
+	unsigned int se_vport_xscale;	/* 0x1d98 */
+	unsigned int se_vport_xoffset;
+	unsigned int se_vport_yscale;
+	unsigned int se_vport_yoffset;
+	unsigned int se_vport_zscale;
+	unsigned int se_vport_zoffset;
+
+	/* Setup state */
+	unsigned int se_cntl_status;	/* 0x2140 */
+
+	/* Misc state */
+	unsigned int re_top_left;	/* 0x26c0 */
+	unsigned int re_misc;
+} drm_radeon_context_regs_t;
+
+typedef struct {
+	/* Zbias state */
+	unsigned int se_zbias_factor;	/* 0x1dac */
+	unsigned int se_zbias_constant;
+} drm_radeon_context2_regs_t;
+
+/* Setup registers for each texture unit
+ */
+typedef struct {
+	unsigned int pp_txfilter;
+	unsigned int pp_txformat;
+	unsigned int pp_txoffset;
+	unsigned int pp_txcblend;
+	unsigned int pp_txablend;
+	unsigned int pp_tfactor;
+	unsigned int pp_border_color;
+} drm_radeon_texture_regs_t;
+
+typedef struct {
+	unsigned int start;
+	unsigned int finish;
+	unsigned int prim:8;
+	unsigned int stateidx:8;
+	unsigned int numverts:16;	/* overloaded as offset/64 for elt prims */
+	unsigned int vc_format;	/* vertex format */
+} drm_radeon_prim_t;
+
+typedef struct {
+	drm_radeon_context_regs_t context;
+	drm_radeon_texture_regs_t tex[RADEON_MAX_TEXTURE_UNITS];
+	drm_radeon_context2_regs_t context2;
+	unsigned int dirty;
+} drm_radeon_state_t;
+
+typedef struct {
+	/* The channel for communication of state information to the
+	 * kernel on firing a vertex buffer with either of the
+	 * obsoleted vertex/index ioctls.
+	 */
+	drm_radeon_context_regs_t context_state;
+	drm_radeon_texture_regs_t tex_state[RADEON_MAX_TEXTURE_UNITS];
+	unsigned int dirty;
+	unsigned int vertsize;
+	unsigned int vc_format;
+
+	/* The current cliprects, or a subset thereof.
+	 */
+	struct drm_clip_rect boxes[RADEON_NR_SAREA_CLIPRECTS];
+	unsigned int nbox;
+
+	/* Counters for client-side throttling of rendering clients.
+	 */
+	unsigned int last_frame;
+	unsigned int last_dispatch;
+	unsigned int last_clear;
+
+	struct drm_tex_region tex_list[RADEON_NR_TEX_HEAPS][RADEON_NR_TEX_REGIONS +
+						       1];
+	unsigned int tex_age[RADEON_NR_TEX_HEAPS];
+	int ctx_owner;
+	int pfState;		/* number of 3d windows (0,1,2ormore) */
+	int pfCurrentPage;	/* which buffer is being displayed? */
+	int crtc2_base;		/* CRTC2 frame offset */
+	int tiling_enabled;	/* set by drm, read by 2d + 3d clients */
+} drm_radeon_sarea_t;
+
+/* WARNING: If you change any of these defines, make sure to change the
+ * defines in the Xserver file (xf86drmRadeon.h)
+ *
+ * KW: actually it's illegal to change any of this (backwards compatibility).
+ */
+
+/* Radeon specific ioctls
+ * The device specific ioctl range is 0x40 to 0x79.
+ */
+#define DRM_RADEON_CP_INIT    0x00
+#define DRM_RADEON_CP_START   0x01
+#define DRM_RADEON_CP_STOP    0x02
+#define DRM_RADEON_CP_RESET   0x03
+#define DRM_RADEON_CP_IDLE    0x04
+#define DRM_RADEON_RESET      0x05
+#define DRM_RADEON_FULLSCREEN 0x06
+#define DRM_RADEON_SWAP       0x07
+#define DRM_RADEON_CLEAR      0x08
+#define DRM_RADEON_VERTEX     0x09
+#define DRM_RADEON_INDICES    0x0A
+#define DRM_RADEON_NOT_USED
+#define DRM_RADEON_STIPPLE    0x0C
+#define DRM_RADEON_INDIRECT   0x0D
+#define DRM_RADEON_TEXTURE    0x0E
+#define DRM_RADEON_VERTEX2    0x0F
+#define DRM_RADEON_CMDBUF     0x10
+#define DRM_RADEON_GETPARAM   0x11
+#define DRM_RADEON_FLIP       0x12
+#define DRM_RADEON_ALLOC      0x13
+#define DRM_RADEON_FREE       0x14
+#define DRM_RADEON_INIT_HEAP  0x15
+#define DRM_RADEON_IRQ_EMIT   0x16
+#define DRM_RADEON_IRQ_WAIT   0x17
+#define DRM_RADEON_CP_RESUME  0x18
+#define DRM_RADEON_SETPARAM   0x19
+#define DRM_RADEON_SURF_ALLOC 0x1a
+#define DRM_RADEON_SURF_FREE  0x1b
+/* KMS ioctl */
+#define DRM_RADEON_GEM_INFO		0x1c
+#define DRM_RADEON_GEM_CREATE		0x1d
+#define DRM_RADEON_GEM_MMAP		0x1e
+#define DRM_RADEON_GEM_PREAD		0x21
+#define DRM_RADEON_GEM_PWRITE		0x22
+#define DRM_RADEON_GEM_SET_DOMAIN	0x23
+#define DRM_RADEON_GEM_WAIT_IDLE	0x24
+#define DRM_RADEON_CS			0x26
+#define DRM_RADEON_INFO			0x27
+#define DRM_RADEON_GEM_SET_TILING	0x28
+#define DRM_RADEON_GEM_GET_TILING	0x29
+#define DRM_RADEON_GEM_BUSY		0x2a
+#define DRM_RADEON_GEM_VA		0x2b
+#define DRM_RADEON_GEM_OP		0x2c
+#define DRM_RADEON_GEM_USERPTR		0x2d
+
+#define DRM_IOCTL_RADEON_CP_INIT    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_INIT, drm_radeon_init_t)
+#define DRM_IOCTL_RADEON_CP_START   DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_START)
+#define DRM_IOCTL_RADEON_CP_STOP    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_STOP, drm_radeon_cp_stop_t)
+#define DRM_IOCTL_RADEON_CP_RESET   DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_RESET)
+#define DRM_IOCTL_RADEON_CP_IDLE    DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_IDLE)
+#define DRM_IOCTL_RADEON_RESET      DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_RESET)
+#define DRM_IOCTL_RADEON_FULLSCREEN DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_FULLSCREEN, drm_radeon_fullscreen_t)
+#define DRM_IOCTL_RADEON_SWAP       DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_SWAP)
+#define DRM_IOCTL_RADEON_CLEAR      DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CLEAR, drm_radeon_clear_t)
+#define DRM_IOCTL_RADEON_VERTEX     DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_VERTEX, drm_radeon_vertex_t)
+#define DRM_IOCTL_RADEON_INDICES    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_INDICES, drm_radeon_indices_t)
+#define DRM_IOCTL_RADEON_STIPPLE    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_STIPPLE, drm_radeon_stipple_t)
+#define DRM_IOCTL_RADEON_INDIRECT   DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_INDIRECT, drm_radeon_indirect_t)
+#define DRM_IOCTL_RADEON_TEXTURE    DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_TEXTURE, drm_radeon_texture_t)
+#define DRM_IOCTL_RADEON_VERTEX2    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_VERTEX2, drm_radeon_vertex2_t)
+#define DRM_IOCTL_RADEON_CMDBUF     DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CMDBUF, drm_radeon_cmd_buffer_t)
+#define DRM_IOCTL_RADEON_GETPARAM   DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GETPARAM, drm_radeon_getparam_t)
+#define DRM_IOCTL_RADEON_FLIP       DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_FLIP)
+#define DRM_IOCTL_RADEON_ALLOC      DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_ALLOC, drm_radeon_mem_alloc_t)
+#define DRM_IOCTL_RADEON_FREE       DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_FREE, drm_radeon_mem_free_t)
+#define DRM_IOCTL_RADEON_INIT_HEAP  DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_INIT_HEAP, drm_radeon_mem_init_heap_t)
+#define DRM_IOCTL_RADEON_IRQ_EMIT   DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_IRQ_EMIT, drm_radeon_irq_emit_t)
+#define DRM_IOCTL_RADEON_IRQ_WAIT   DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_IRQ_WAIT, drm_radeon_irq_wait_t)
+#define DRM_IOCTL_RADEON_CP_RESUME  DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_RESUME)
+#define DRM_IOCTL_RADEON_SETPARAM   DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_SETPARAM, drm_radeon_setparam_t)
+#define DRM_IOCTL_RADEON_SURF_ALLOC DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_SURF_ALLOC, drm_radeon_surface_alloc_t)
+#define DRM_IOCTL_RADEON_SURF_FREE  DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_SURF_FREE, drm_radeon_surface_free_t)
+/* KMS */
+#define DRM_IOCTL_RADEON_GEM_INFO	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_INFO, struct drm_radeon_gem_info)
+#define DRM_IOCTL_RADEON_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_CREATE, struct drm_radeon_gem_create)
+#define DRM_IOCTL_RADEON_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_MMAP, struct drm_radeon_gem_mmap)
+#define DRM_IOCTL_RADEON_GEM_PREAD	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_PREAD, struct drm_radeon_gem_pread)
+#define DRM_IOCTL_RADEON_GEM_PWRITE	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_PWRITE, struct drm_radeon_gem_pwrite)
+#define DRM_IOCTL_RADEON_GEM_SET_DOMAIN	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_SET_DOMAIN, struct drm_radeon_gem_set_domain)
+#define DRM_IOCTL_RADEON_GEM_WAIT_IDLE	DRM_IOW(DRM_COMMAND_BASE + DRM_RADEON_GEM_WAIT_IDLE, struct drm_radeon_gem_wait_idle)
+#define DRM_IOCTL_RADEON_CS		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_CS, struct drm_radeon_cs)
+#define DRM_IOCTL_RADEON_INFO		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_INFO, struct drm_radeon_info)
+#define DRM_IOCTL_RADEON_GEM_SET_TILING	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_SET_TILING, struct drm_radeon_gem_set_tiling)
+#define DRM_IOCTL_RADEON_GEM_GET_TILING	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_GET_TILING, struct drm_radeon_gem_get_tiling)
+#define DRM_IOCTL_RADEON_GEM_BUSY	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_BUSY, struct drm_radeon_gem_busy)
+#define DRM_IOCTL_RADEON_GEM_VA		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_VA, struct drm_radeon_gem_va)
+#define DRM_IOCTL_RADEON_GEM_OP		DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_OP, struct drm_radeon_gem_op)
+#define DRM_IOCTL_RADEON_GEM_USERPTR	DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_USERPTR, struct drm_radeon_gem_userptr)
+
+typedef struct drm_radeon_init {
+	enum {
+		RADEON_INIT_CP = 0x01,
+		RADEON_CLEANUP_CP = 0x02,
+		RADEON_INIT_R200_CP = 0x03,
+		RADEON_INIT_R300_CP = 0x04,
+		RADEON_INIT_R600_CP = 0x05
+	} func;
+	unsigned long sarea_priv_offset;
+	int is_pci;
+	int cp_mode;
+	int gart_size;
+	int ring_size;
+	int usec_timeout;
+
+	unsigned int fb_bpp;
+	unsigned int front_offset, front_pitch;
+	unsigned int back_offset, back_pitch;
+	unsigned int depth_bpp;
+	unsigned int depth_offset, depth_pitch;
+
+	unsigned long fb_offset;
+	unsigned long mmio_offset;
+	unsigned long ring_offset;
+	unsigned long ring_rptr_offset;
+	unsigned long buffers_offset;
+	unsigned long gart_textures_offset;
+} drm_radeon_init_t;
+
+typedef struct drm_radeon_cp_stop {
+	int flush;
+	int idle;
+} drm_radeon_cp_stop_t;
+
+typedef struct drm_radeon_fullscreen {
+	enum {
+		RADEON_INIT_FULLSCREEN = 0x01,
+		RADEON_CLEANUP_FULLSCREEN = 0x02
+	} func;
+} drm_radeon_fullscreen_t;
+
+#define CLEAR_X1	0
+#define CLEAR_Y1	1
+#define CLEAR_X2	2
+#define CLEAR_Y2	3
+#define CLEAR_DEPTH	4
+
+typedef union drm_radeon_clear_rect {
+	float f[5];
+	unsigned int ui[5];
+} drm_radeon_clear_rect_t;
+
+typedef struct drm_radeon_clear {
+	unsigned int flags;
+	unsigned int clear_color;
+	unsigned int clear_depth;
+	unsigned int color_mask;
+	unsigned int depth_mask;	/* misnamed field:  should be stencil */
+	drm_radeon_clear_rect_t __user *depth_boxes;
+} drm_radeon_clear_t;
+
+typedef struct drm_radeon_vertex {
+	int prim;
+	int idx;		/* Index of vertex buffer */
+	int count;		/* Number of vertices in buffer */
+	int discard;		/* Client finished with buffer? */
+} drm_radeon_vertex_t;
+
+typedef struct drm_radeon_indices {
+	int prim;
+	int idx;
+	int start;
+	int end;
+	int discard;		/* Client finished with buffer? */
+} drm_radeon_indices_t;
+
+/* v1.2 - obsoletes drm_radeon_vertex and drm_radeon_indices
+ *      - allows multiple primitives and state changes in a single ioctl
+ *      - supports driver change to emit native primitives
+ */
+typedef struct drm_radeon_vertex2 {
+	int idx;		/* Index of vertex buffer */
+	int discard;		/* Client finished with buffer? */
+	int nr_states;
+	drm_radeon_state_t __user *state;
+	int nr_prims;
+	drm_radeon_prim_t __user *prim;
+} drm_radeon_vertex2_t;
+
+/* v1.3 - obsoletes drm_radeon_vertex2
+ *      - allows arbitrarily large cliprect list
+ *      - allows updating of tcl packet, vector and scalar state
+ *      - allows memory-efficient description of state updates
+ *      - allows state to be emitted without a primitive
+ *           (for clears, ctx switches)
+ *      - allows more than one dma buffer to be referenced per ioctl
+ *      - supports tcl driver
+ *      - may be extended in future versions with new cmd types, packets
+ */
+typedef struct drm_radeon_cmd_buffer {
+	int bufsz;
+	char __user *buf;
+	int nbox;
+	struct drm_clip_rect __user *boxes;
+} drm_radeon_cmd_buffer_t;
+
+typedef struct drm_radeon_tex_image {
+	unsigned int x, y;	/* Blit coordinates */
+	unsigned int width, height;
+	const void __user *data;
+} drm_radeon_tex_image_t;
+
+typedef struct drm_radeon_texture {
+	unsigned int offset;
+	int pitch;
+	int format;
+	int width;		/* Texture image coordinates */
+	int height;
+	drm_radeon_tex_image_t __user *image;
+} drm_radeon_texture_t;
+
+typedef struct drm_radeon_stipple {
+	unsigned int __user *mask;
+} drm_radeon_stipple_t;
+
+typedef struct drm_radeon_indirect {
+	int idx;
+	int start;
+	int end;
+	int discard;
+} drm_radeon_indirect_t;
+
+/* enum for card type parameters */
+#define RADEON_CARD_PCI 0
+#define RADEON_CARD_AGP 1
+#define RADEON_CARD_PCIE 2
+
+/* 1.3: An ioctl to get parameters that aren't available to the 3d
+ * client any other way.
+ */
+#define RADEON_PARAM_GART_BUFFER_OFFSET    1	/* card offset of 1st GART buffer */
+#define RADEON_PARAM_LAST_FRAME            2
+#define RADEON_PARAM_LAST_DISPATCH         3
+#define RADEON_PARAM_LAST_CLEAR            4
+/* Added with DRM version 1.6. */
+#define RADEON_PARAM_IRQ_NR                5
+#define RADEON_PARAM_GART_BASE             6	/* card offset of GART base */
+/* Added with DRM version 1.8. */
+#define RADEON_PARAM_REGISTER_HANDLE       7	/* for drmMap() */
+#define RADEON_PARAM_STATUS_HANDLE         8
+#define RADEON_PARAM_SAREA_HANDLE          9
+#define RADEON_PARAM_GART_TEX_HANDLE       10
+#define RADEON_PARAM_SCRATCH_OFFSET        11
+#define RADEON_PARAM_CARD_TYPE             12
+#define RADEON_PARAM_VBLANK_CRTC           13   /* VBLANK CRTC */
+#define RADEON_PARAM_FB_LOCATION           14   /* FB location */
+#define RADEON_PARAM_NUM_GB_PIPES          15   /* num GB pipes */
+#define RADEON_PARAM_DEVICE_ID             16
+#define RADEON_PARAM_NUM_Z_PIPES           17   /* num Z pipes */
+
+typedef struct drm_radeon_getparam {
+	int param;
+	void __user *value;
+} drm_radeon_getparam_t;
+
+/* 1.6: Set up a memory manager for regions of shared memory:
+ */
+#define RADEON_MEM_REGION_GART 1
+#define RADEON_MEM_REGION_FB   2
+
+typedef struct drm_radeon_mem_alloc {
+	int region;
+	int alignment;
+	int size;
+	int __user *region_offset;	/* offset from start of fb or GART */
+} drm_radeon_mem_alloc_t;
+
+typedef struct drm_radeon_mem_free {
+	int region;
+	int region_offset;
+} drm_radeon_mem_free_t;
+
+typedef struct drm_radeon_mem_init_heap {
+	int region;
+	int size;
+	int start;
+} drm_radeon_mem_init_heap_t;
+
+/* 1.6: Userspace can request & wait on irq's:
+ */
+typedef struct drm_radeon_irq_emit {
+	int __user *irq_seq;
+} drm_radeon_irq_emit_t;
+
+typedef struct drm_radeon_irq_wait {
+	int irq_seq;
+} drm_radeon_irq_wait_t;
+
+/* 1.10: Clients tell the DRM where they think the framebuffer is located in
+ * the card's address space, via a new generic ioctl to set parameters
+ */
+
+typedef struct drm_radeon_setparam {
+	unsigned int param;
+	__s64 value;
+} drm_radeon_setparam_t;
+
+#define RADEON_SETPARAM_FB_LOCATION    1	/* determined framebuffer location */
+#define RADEON_SETPARAM_SWITCH_TILING  2	/* enable/disable color tiling */
+#define RADEON_SETPARAM_PCIGART_LOCATION 3	/* PCI Gart Location */
+#define RADEON_SETPARAM_NEW_MEMMAP 4		/* Use new memory map */
+#define RADEON_SETPARAM_PCIGART_TABLE_SIZE 5    /* PCI GART Table Size */
+#define RADEON_SETPARAM_VBLANK_CRTC 6           /* VBLANK CRTC */
+/* 1.14: Clients can allocate/free a surface
+ */
+typedef struct drm_radeon_surface_alloc {
+	unsigned int address;
+	unsigned int size;
+	unsigned int flags;
+} drm_radeon_surface_alloc_t;
+
+typedef struct drm_radeon_surface_free {
+	unsigned int address;
+} drm_radeon_surface_free_t;
+
+#define	DRM_RADEON_VBLANK_CRTC1		1
+#define	DRM_RADEON_VBLANK_CRTC2		2
+
+/*
+ * Kernel modesetting world below.
+ */
+#define RADEON_GEM_DOMAIN_CPU		0x1
+#define RADEON_GEM_DOMAIN_GTT		0x2
+#define RADEON_GEM_DOMAIN_VRAM		0x4
+
+struct drm_radeon_gem_info {
+	__u64	gart_size;
+	__u64	vram_size;
+	__u64	vram_visible;
+};
+
+#define RADEON_GEM_NO_BACKING_STORE	(1 << 0)
+#define RADEON_GEM_GTT_UC		(1 << 1)
+#define RADEON_GEM_GTT_WC		(1 << 2)
+/* BO is expected to be accessed by the CPU */
+#define RADEON_GEM_CPU_ACCESS		(1 << 3)
+/* CPU access is not expected to work for this BO */
+#define RADEON_GEM_NO_CPU_ACCESS	(1 << 4)
+
+struct drm_radeon_gem_create {
+	__u64	size;
+	__u64	alignment;
+	__u32	handle;
+	__u32	initial_domain;
+	__u32	flags;
+};
+
+/*
+ * This is not a reliable API and you should expect it to fail for any
+ * number of reasons and have fallback path that do not use userptr to
+ * perform any operation.
+ */
+#define RADEON_GEM_USERPTR_READONLY	(1 << 0)
+#define RADEON_GEM_USERPTR_ANONONLY	(1 << 1)
+#define RADEON_GEM_USERPTR_VALIDATE	(1 << 2)
+#define RADEON_GEM_USERPTR_REGISTER	(1 << 3)
+
+struct drm_radeon_gem_userptr {
+	__u64		addr;
+	__u64		size;
+	__u32		flags;
+	__u32		handle;
+};
+
+#define RADEON_TILING_MACRO				0x1
+#define RADEON_TILING_MICRO				0x2
+#define RADEON_TILING_SWAP_16BIT			0x4
+#define RADEON_TILING_SWAP_32BIT			0x8
+/* this object requires a surface when mapped - i.e. front buffer */
+#define RADEON_TILING_SURFACE				0x10
+#define RADEON_TILING_MICRO_SQUARE			0x20
+#define RADEON_TILING_EG_BANKW_SHIFT			8
+#define RADEON_TILING_EG_BANKW_MASK			0xf
+#define RADEON_TILING_EG_BANKH_SHIFT			12
+#define RADEON_TILING_EG_BANKH_MASK			0xf
+#define RADEON_TILING_EG_MACRO_TILE_ASPECT_SHIFT	16
+#define RADEON_TILING_EG_MACRO_TILE_ASPECT_MASK		0xf
+#define RADEON_TILING_EG_TILE_SPLIT_SHIFT		24
+#define RADEON_TILING_EG_TILE_SPLIT_MASK		0xf
+#define RADEON_TILING_EG_STENCIL_TILE_SPLIT_SHIFT	28
+#define RADEON_TILING_EG_STENCIL_TILE_SPLIT_MASK	0xf
+
+struct drm_radeon_gem_set_tiling {
+	__u32	handle;
+	__u32	tiling_flags;
+	__u32	pitch;
+};
+
+struct drm_radeon_gem_get_tiling {
+	__u32	handle;
+	__u32	tiling_flags;
+	__u32	pitch;
+};
+
+struct drm_radeon_gem_mmap {
+	__u32	handle;
+	__u32	pad;
+	__u64	offset;
+	__u64	size;
+	__u64	addr_ptr;
+};
+
+struct drm_radeon_gem_set_domain {
+	__u32	handle;
+	__u32	read_domains;
+	__u32	write_domain;
+};
+
+struct drm_radeon_gem_wait_idle {
+	__u32	handle;
+	__u32	pad;
+};
+
+struct drm_radeon_gem_busy {
+	__u32	handle;
+	__u32        domain;
+};
+
+struct drm_radeon_gem_pread {
+	/** Handle for the object being read. */
+	__u32 handle;
+	__u32 pad;
+	/** Offset into the object to read from */
+	__u64 offset;
+	/** Length of data to read */
+	__u64 size;
+	/** Pointer to write the data into. */
+	/* void *, but pointers are not 32/64 compatible */
+	__u64 data_ptr;
+};
+
+struct drm_radeon_gem_pwrite {
+	/** Handle for the object being written to. */
+	__u32 handle;
+	__u32 pad;
+	/** Offset into the object to write to */
+	__u64 offset;
+	/** Length of data to write */
+	__u64 size;
+	/** Pointer to read the data from. */
+	/* void *, but pointers are not 32/64 compatible */
+	__u64 data_ptr;
+};
+
+/* Sets or returns a value associated with a buffer. */
+struct drm_radeon_gem_op {
+	__u32	handle; /* buffer */
+	__u32	op;     /* RADEON_GEM_OP_* */
+	__u64	value;  /* input or return value */
+};
+
+#define RADEON_GEM_OP_GET_INITIAL_DOMAIN	0
+#define RADEON_GEM_OP_SET_INITIAL_DOMAIN	1
+
+#define RADEON_VA_MAP			1
+#define RADEON_VA_UNMAP			2
+
+#define RADEON_VA_RESULT_OK		0
+#define RADEON_VA_RESULT_ERROR		1
+#define RADEON_VA_RESULT_VA_EXIST	2
+
+#define RADEON_VM_PAGE_VALID		(1 << 0)
+#define RADEON_VM_PAGE_READABLE		(1 << 1)
+#define RADEON_VM_PAGE_WRITEABLE	(1 << 2)
+#define RADEON_VM_PAGE_SYSTEM		(1 << 3)
+#define RADEON_VM_PAGE_SNOOPED		(1 << 4)
+
+struct drm_radeon_gem_va {
+	__u32		handle;
+	__u32		operation;
+	__u32		vm_id;
+	__u32		flags;
+	__u64		offset;
+};
+
+#define RADEON_CHUNK_ID_RELOCS	0x01
+#define RADEON_CHUNK_ID_IB	0x02
+#define RADEON_CHUNK_ID_FLAGS	0x03
+#define RADEON_CHUNK_ID_CONST_IB	0x04
+
+/* The first dword of RADEON_CHUNK_ID_FLAGS is a uint32 of these flags: */
+#define RADEON_CS_KEEP_TILING_FLAGS 0x01
+#define RADEON_CS_USE_VM            0x02
+#define RADEON_CS_END_OF_FRAME      0x04 /* a hint from userspace which CS is the last one */
+/* The second dword of RADEON_CHUNK_ID_FLAGS is a uint32 that sets the ring type */
+#define RADEON_CS_RING_GFX          0
+#define RADEON_CS_RING_COMPUTE      1
+#define RADEON_CS_RING_DMA          2
+#define RADEON_CS_RING_UVD          3
+#define RADEON_CS_RING_VCE          4
+/* The third dword of RADEON_CHUNK_ID_FLAGS is a sint32 that sets the priority */
+/* 0 = normal, + = higher priority, - = lower priority */
+
+struct drm_radeon_cs_chunk {
+	__u32		chunk_id;
+	__u32		length_dw;
+	__u64		chunk_data;
+};
+
+/* drm_radeon_cs_reloc.flags */
+#define RADEON_RELOC_PRIO_MASK		(0xf << 0)
+
+struct drm_radeon_cs_reloc {
+	__u32		handle;
+	__u32		read_domains;
+	__u32		write_domain;
+	__u32		flags;
+};
+
+struct drm_radeon_cs {
+	__u32		num_chunks;
+	__u32		cs_id;
+	/* this points to __u64 * which point to cs chunks */
+	__u64		chunks;
+	/* updates to the limits after this CS ioctl */
+	__u64		gart_limit;
+	__u64		vram_limit;
+};
+
+#define RADEON_INFO_DEVICE_ID		0x00
+#define RADEON_INFO_NUM_GB_PIPES	0x01
+#define RADEON_INFO_NUM_Z_PIPES 	0x02
+#define RADEON_INFO_ACCEL_WORKING	0x03
+#define RADEON_INFO_CRTC_FROM_ID	0x04
+#define RADEON_INFO_ACCEL_WORKING2	0x05
+#define RADEON_INFO_TILING_CONFIG	0x06
+#define RADEON_INFO_WANT_HYPERZ		0x07
+#define RADEON_INFO_WANT_CMASK		0x08 /* get access to CMASK on r300 */
+#define RADEON_INFO_CLOCK_CRYSTAL_FREQ	0x09 /* clock crystal frequency */
+#define RADEON_INFO_NUM_BACKENDS	0x0a /* DB/backends for r600+ - need for OQ */
+#define RADEON_INFO_NUM_TILE_PIPES	0x0b /* tile pipes for r600+ */
+#define RADEON_INFO_FUSION_GART_WORKING	0x0c /* fusion writes to GTT were broken before this */
+#define RADEON_INFO_BACKEND_MAP		0x0d /* pipe to backend map, needed by mesa */
+/* virtual address start, va < start are reserved by the kernel */
+#define RADEON_INFO_VA_START		0x0e
+/* maximum size of ib using the virtual memory cs */
+#define RADEON_INFO_IB_VM_MAX_SIZE	0x0f
+/* max pipes - needed for compute shaders */
+#define RADEON_INFO_MAX_PIPES		0x10
+/* timestamp for GL_ARB_timer_query (OpenGL), returns the current GPU clock */
+#define RADEON_INFO_TIMESTAMP		0x11
+/* max shader engines (SE) - needed for geometry shaders, etc. */
+#define RADEON_INFO_MAX_SE		0x12
+/* max SH per SE */
+#define RADEON_INFO_MAX_SH_PER_SE	0x13
+/* fast fb access is enabled */
+#define RADEON_INFO_FASTFB_WORKING	0x14
+/* query if a RADEON_CS_RING_* submission is supported */
+#define RADEON_INFO_RING_WORKING	0x15
+/* SI tile mode array */
+#define RADEON_INFO_SI_TILE_MODE_ARRAY	0x16
+/* query if CP DMA is supported on the compute ring */
+#define RADEON_INFO_SI_CP_DMA_COMPUTE	0x17
+/* CIK macrotile mode array */
+#define RADEON_INFO_CIK_MACROTILE_MODE_ARRAY	0x18
+/* query the number of render backends */
+#define RADEON_INFO_SI_BACKEND_ENABLED_MASK	0x19
+/* max engine clock - needed for OpenCL */
+#define RADEON_INFO_MAX_SCLK		0x1a
+/* version of VCE firmware */
+#define RADEON_INFO_VCE_FW_VERSION	0x1b
+/* version of VCE feedback */
+#define RADEON_INFO_VCE_FB_VERSION	0x1c
+#define RADEON_INFO_NUM_BYTES_MOVED	0x1d
+#define RADEON_INFO_VRAM_USAGE		0x1e
+#define RADEON_INFO_GTT_USAGE		0x1f
+#define RADEON_INFO_ACTIVE_CU_COUNT	0x20
+#define RADEON_INFO_CURRENT_GPU_TEMP	0x21
+#define RADEON_INFO_CURRENT_GPU_SCLK	0x22
+#define RADEON_INFO_CURRENT_GPU_MCLK	0x23
+#define RADEON_INFO_READ_REG		0x24
+#define RADEON_INFO_VA_UNMAP_WORKING	0x25
+#define RADEON_INFO_GPU_RESET_COUNTER	0x26
+
+struct drm_radeon_info {
+	__u32		request;
+	__u32		pad;
+	__u64		value;
+};
+
+/* Those correspond to the tile index to use, this is to explicitly state
+ * the API that is implicitly defined by the tile mode array.
+ */
+#define SI_TILE_MODE_COLOR_LINEAR_ALIGNED	8
+#define SI_TILE_MODE_COLOR_1D			13
+#define SI_TILE_MODE_COLOR_1D_SCANOUT		9
+#define SI_TILE_MODE_COLOR_2D_8BPP		14
+#define SI_TILE_MODE_COLOR_2D_16BPP		15
+#define SI_TILE_MODE_COLOR_2D_32BPP		16
+#define SI_TILE_MODE_COLOR_2D_64BPP		17
+#define SI_TILE_MODE_COLOR_2D_SCANOUT_16BPP	11
+#define SI_TILE_MODE_COLOR_2D_SCANOUT_32BPP	12
+#define SI_TILE_MODE_DEPTH_STENCIL_1D		4
+#define SI_TILE_MODE_DEPTH_STENCIL_2D		0
+#define SI_TILE_MODE_DEPTH_STENCIL_2D_2AA	3
+#define SI_TILE_MODE_DEPTH_STENCIL_2D_4AA	3
+#define SI_TILE_MODE_DEPTH_STENCIL_2D_8AA	2
+
+#define CIK_TILE_MODE_DEPTH_STENCIL_1D		5
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/rocket_accel.h b/include/uapi/drm/rocket_accel.h
new file mode 100644
index 000000000..d0685e372
--- /dev/null
+++ b/include/uapi/drm/rocket_accel.h
@@ -0,0 +1,192 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2024 Tomeu Vizoso
+ */
+#ifndef __DRM_UAPI_ROCKET_ACCEL_H__
+#define __DRM_UAPI_ROCKET_ACCEL_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_ROCKET_CREATE_BO			0x00
+#define DRM_ROCKET_SUBMIT			0x01
+#define DRM_ROCKET_PREP_BO			0x02
+#define DRM_ROCKET_FINI_BO			0x03
+
+#define DRM_IOCTL_ROCKET_CREATE_BO		DRM_IOWR(DRM_COMMAND_BASE + DRM_ROCKET_CREATE_BO, struct drm_rocket_create_bo)
+#define DRM_IOCTL_ROCKET_SUBMIT			DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_SUBMIT, struct drm_rocket_submit)
+#define DRM_IOCTL_ROCKET_PREP_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_PREP_BO, struct drm_rocket_prep_bo)
+#define DRM_IOCTL_ROCKET_FINI_BO		DRM_IOW(DRM_COMMAND_BASE + DRM_ROCKET_FINI_BO, struct drm_rocket_fini_bo)
+
+/**
+ * struct drm_rocket_create_bo - ioctl argument for creating Rocket BOs.
+ *
+ */
+struct drm_rocket_create_bo {
+	/**
+	 * @size: Input: Size of the requested BO.
+	 */
+	__u32 size;
+
+	/**
+	 * @handle: Output: GEM handle for the BO.
+	 */
+	__u32 handle;
+
+	/**
+	 * @dma_address: Output: DMA address for the BO in the NPU address
+	 * space.  This address is private to the DRM fd and is valid for
+	 * the lifetime of the GEM handle.
+	 */
+	__u64 dma_address;
+
+	/**
+	 * @offset: Output: Offset into the drm node to use for subsequent
+	 * mmap call.
+	 */
+	__u64 offset;
+};
+
+/**
+ * struct drm_rocket_prep_bo - ioctl argument for starting CPU ownership of the BO.
+ *
+ * Takes care of waiting for any NPU jobs that might still use the NPU and performs cache
+ * synchronization.
+ */
+struct drm_rocket_prep_bo {
+	/**
+	 * @handle: Input: GEM handle of the buffer object.
+	 */
+	__u32 handle;
+
+	/**
+	 * @reserved: Reserved, must be zero.
+	 */
+	__u32 reserved;
+
+	/**
+	 * @timeout_ns: Input: Amount of time to wait for NPU jobs.
+	 */
+	__s64 timeout_ns;
+};
+
+/**
+ * struct drm_rocket_fini_bo - ioctl argument for finishing CPU ownership of the BO.
+ *
+ * Synchronize caches for NPU access.
+ */
+struct drm_rocket_fini_bo {
+	/**
+	 * @handle: Input: GEM handle of the buffer object.
+	 */
+	__u32 handle;
+
+	/**
+	 * @reserved: Reserved, must be zero.
+	 */
+	__u32 reserved;
+};
+
+/**
+ * struct drm_rocket_task - A task to be run on the NPU
+ *
+ * A task is the smallest unit of work that can be run on the NPU.
+ */
+struct drm_rocket_task {
+	/**
+	 * @regcmd: Input: DMA address to NPU mapping of register command buffer
+	 */
+	__u32 regcmd;
+
+	/**
+	 * @regcmd_count: Input: Number of commands in the register command
+	 * buffer
+	 */
+	__u32 regcmd_count;
+};
+
+/**
+ * struct drm_rocket_job - A job to be run on the NPU
+ *
+ * The kernel will schedule the execution of this job taking into account its
+ * dependencies with other jobs. All tasks in the same job will be executed
+ * sequentially on the same core, to benefit from memory residency in SRAM.
+ */
+struct drm_rocket_job {
+	/**
+	 * @tasks: Input: Pointer to an array of struct drm_rocket_task.
+	 */
+	__u64 tasks;
+
+	/**
+	 * @in_bo_handles: Input: Pointer to a u32 array of the BOs that
+	 * are read by the job.
+	 */
+	__u64 in_bo_handles;
+
+	/**
+	 * @out_bo_handles: Input: Pointer to a u32 array of the BOs that
+	 * are written to by the job.
+	 */
+	__u64 out_bo_handles;
+
+	/**
+	 * @task_count: Input: Number of tasks passed in.
+	 */
+	__u32 task_count;
+
+	/**
+	 * @task_struct_size: Input: Size in bytes of the structs in the
+	 * @tasks field.
+	 */
+	__u32 task_struct_size;
+
+	/**
+	 * @in_bo_handle_count: Input: Number of input BO handles passed in
+	 * (size is that times 4).
+	 */
+	__u32 in_bo_handle_count;
+
+	/**
+	 * @out_bo_handle_count: Input: Number of output BO handles passed in
+	 * (size is that times 4).
+	 */
+	__u32 out_bo_handle_count;
+};
+
+/**
+ * struct drm_rocket_submit - ioctl argument for submitting commands to the NPU.
+ *
+ * The kernel will schedule the execution of these jobs in dependency order.
+ */
+struct drm_rocket_submit {
+	/**
+	 * @jobs: Input: Pointer to an array of struct drm_rocket_job.
+	 */
+	__u64 jobs;
+
+	/**
+	 * @job_count: Input: Number of jobs passed in.
+	 */
+	__u32 job_count;
+
+	/**
+	 * @job_struct_size: Input: Size in bytes of the structs in the
+	 * @jobs field.
+	 */
+	__u32 job_struct_size;
+
+	/**
+	 * @reserved: Reserved, must be zero.
+	 */
+	__u64 reserved;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __DRM_UAPI_ROCKET_ACCEL_H__ */
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
new file mode 100644
index 000000000..8f21f3a44
--- /dev/null
+++ b/include/uapi/drm/tegra_drm.h
@@ -0,0 +1,1076 @@
+/* SPDX-License-Identifier: MIT */
+/* Copyright (c) 2012-2020 NVIDIA Corporation */
+
+#ifndef _UAPI_TEGRA_DRM_H_
+#define _UAPI_TEGRA_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/* Tegra DRM legacy UAPI. Only enabled with STAGING */
+
+#define DRM_TEGRA_GEM_CREATE_TILED     (1 << 0)
+#define DRM_TEGRA_GEM_CREATE_BOTTOM_UP (1 << 1)
+
+/**
+ * struct drm_tegra_gem_create - parameters for the GEM object creation IOCTL
+ */
+struct drm_tegra_gem_create {
+	/**
+	 * @size:
+	 *
+	 * The size, in bytes, of the buffer object to be created.
+	 */
+	__u64 size;
+
+	/**
+	 * @flags:
+	 *
+	 * A bitmask of flags that influence the creation of GEM objects:
+	 *
+	 * DRM_TEGRA_GEM_CREATE_TILED
+	 *   Use the 16x16 tiling format for this buffer.
+	 *
+	 * DRM_TEGRA_GEM_CREATE_BOTTOM_UP
+	 *   The buffer has a bottom-up layout.
+	 */
+	__u32 flags;
+
+	/**
+	 * @handle:
+	 *
+	 * The handle of the created GEM object. Set by the kernel upon
+	 * successful completion of the IOCTL.
+	 */
+	__u32 handle;
+};
+
+/**
+ * struct drm_tegra_gem_mmap - parameters for the GEM mmap IOCTL
+ */
+struct drm_tegra_gem_mmap {
+	/**
+	 * @handle:
+	 *
+	 * Handle of the GEM object to obtain an mmap offset for.
+	 */
+	__u32 handle;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+
+	/**
+	 * @offset:
+	 *
+	 * The mmap offset for the given GEM object. Set by the kernel upon
+	 * successful completion of the IOCTL.
+	 */
+	__u64 offset;
+};
+
+/**
+ * struct drm_tegra_syncpt_read - parameters for the read syncpoint IOCTL
+ */
+struct drm_tegra_syncpt_read {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to read the current value from.
+	 */
+	__u32 id;
+
+	/**
+	 * @value:
+	 *
+	 * The current syncpoint value. Set by the kernel upon successful
+	 * completion of the IOCTL.
+	 */
+	__u32 value;
+};
+
+/**
+ * struct drm_tegra_syncpt_incr - parameters for the increment syncpoint IOCTL
+ */
+struct drm_tegra_syncpt_incr {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to increment.
+	 */
+	__u32 id;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+};
+
+/**
+ * struct drm_tegra_syncpt_wait - parameters for the wait syncpoint IOCTL
+ */
+struct drm_tegra_syncpt_wait {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to wait on.
+	 */
+	__u32 id;
+
+	/**
+	 * @thresh:
+	 *
+	 * Threshold value for which to wait.
+	 */
+	__u32 thresh;
+
+	/**
+	 * @timeout:
+	 *
+	 * Timeout, in milliseconds, to wait.
+	 */
+	__u32 timeout;
+
+	/**
+	 * @value:
+	 *
+	 * The new syncpoint value after the wait. Set by the kernel upon
+	 * successful completion of the IOCTL.
+	 */
+	__u32 value;
+};
+
+#define DRM_TEGRA_NO_TIMEOUT	(0xffffffff)
+
+/**
+ * struct drm_tegra_open_channel - parameters for the open channel IOCTL
+ */
+struct drm_tegra_open_channel {
+	/**
+	 * @client:
+	 *
+	 * The client ID for this channel.
+	 */
+	__u32 client;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+
+	/**
+	 * @context:
+	 *
+	 * The application context of this channel. Set by the kernel upon
+	 * successful completion of the IOCTL. This context needs to be passed
+	 * to the DRM_TEGRA_CHANNEL_CLOSE or the DRM_TEGRA_SUBMIT IOCTLs.
+	 */
+	__u64 context;
+};
+
+/**
+ * struct drm_tegra_close_channel - parameters for the close channel IOCTL
+ */
+struct drm_tegra_close_channel {
+	/**
+	 * @context:
+	 *
+	 * The application context of this channel. This is obtained from the
+	 * DRM_TEGRA_OPEN_CHANNEL IOCTL.
+	 */
+	__u64 context;
+};
+
+/**
+ * struct drm_tegra_get_syncpt - parameters for the get syncpoint IOCTL
+ */
+struct drm_tegra_get_syncpt {
+	/**
+	 * @context:
+	 *
+	 * The application context identifying the channel for which to obtain
+	 * the syncpoint ID.
+	 */
+	__u64 context;
+
+	/**
+	 * @index:
+	 *
+	 * Index of the client syncpoint for which to obtain the ID.
+	 */
+	__u32 index;
+
+	/**
+	 * @id:
+	 *
+	 * The ID of the given syncpoint. Set by the kernel upon successful
+	 * completion of the IOCTL.
+	 */
+	__u32 id;
+};
+
+/**
+ * struct drm_tegra_get_syncpt_base - parameters for the get wait base IOCTL
+ */
+struct drm_tegra_get_syncpt_base {
+	/**
+	 * @context:
+	 *
+	 * The application context identifying for which channel to obtain the
+	 * wait base.
+	 */
+	__u64 context;
+
+	/**
+	 * @syncpt:
+	 *
+	 * ID of the syncpoint for which to obtain the wait base.
+	 */
+	__u32 syncpt;
+
+	/**
+	 * @id:
+	 *
+	 * The ID of the wait base corresponding to the client syncpoint. Set
+	 * by the kernel upon successful completion of the IOCTL.
+	 */
+	__u32 id;
+};
+
+/**
+ * struct drm_tegra_syncpt - syncpoint increment operation
+ */
+struct drm_tegra_syncpt {
+	/**
+	 * @id:
+	 *
+	 * ID of the syncpoint to operate on.
+	 */
+	__u32 id;
+
+	/**
+	 * @incrs:
+	 *
+	 * Number of increments to perform for the syncpoint.
+	 */
+	__u32 incrs;
+};
+
+/**
+ * struct drm_tegra_cmdbuf - structure describing a command buffer
+ */
+struct drm_tegra_cmdbuf {
+	/**
+	 * @handle:
+	 *
+	 * Handle to a GEM object containing the command buffer.
+	 */
+	__u32 handle;
+
+	/**
+	 * @offset:
+	 *
+	 * Offset, in bytes, into the GEM object identified by @handle at
+	 * which the command buffer starts.
+	 */
+	__u32 offset;
+
+	/**
+	 * @words:
+	 *
+	 * Number of 32-bit words in this command buffer.
+	 */
+	__u32 words;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+};
+
+/**
+ * struct drm_tegra_reloc - GEM object relocation structure
+ */
+struct drm_tegra_reloc {
+	/** @cmdbuf: cmd information */
+	struct {
+		/**
+		 * @cmdbuf.handle:
+		 *
+		 * Handle to the GEM object containing the command buffer for
+		 * which to perform this GEM object relocation.
+		 */
+		__u32 handle;
+
+		/**
+		 * @cmdbuf.offset:
+		 *
+		 * Offset, in bytes, into the command buffer at which to
+		 * insert the relocated address.
+		 */
+		__u32 offset;
+	} cmdbuf;
+	/** @target: relocate target information */
+	struct {
+		/**
+		 * @target.handle:
+		 *
+		 * Handle to the GEM object to be relocated.
+		 */
+		__u32 handle;
+
+		/**
+		 * @target.offset:
+		 *
+		 * Offset, in bytes, into the target GEM object at which the
+		 * relocated data starts.
+		 */
+		__u32 offset;
+	} target;
+
+	/**
+	 * @shift:
+	 *
+	 * The number of bits by which to shift relocated addresses.
+	 */
+	__u32 shift;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+};
+
+/**
+ * struct drm_tegra_waitchk - wait check structure
+ */
+struct drm_tegra_waitchk {
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object containing a command stream on which to
+	 * perform the wait check.
+	 */
+	__u32 handle;
+
+	/**
+	 * @offset:
+	 *
+	 * Offset, in bytes, of the location in the command stream to perform
+	 * the wait check on.
+	 */
+	__u32 offset;
+
+	/**
+	 * @syncpt:
+	 *
+	 * ID of the syncpoint to wait check.
+	 */
+	__u32 syncpt;
+
+	/**
+	 * @thresh:
+	 *
+	 * Threshold value for which to check.
+	 */
+	__u32 thresh;
+};
+
+/**
+ * struct drm_tegra_submit - job submission structure
+ */
+struct drm_tegra_submit {
+	/**
+	 * @context:
+	 *
+	 * The application context identifying the channel to use for the
+	 * execution of this job.
+	 */
+	__u64 context;
+
+	/**
+	 * @num_syncpts:
+	 *
+	 * The number of syncpoints operated on by this job. This defines the
+	 * length of the array pointed to by @syncpts.
+	 */
+	__u32 num_syncpts;
+
+	/**
+	 * @num_cmdbufs:
+	 *
+	 * The number of command buffers to execute as part of this job. This
+	 * defines the length of the array pointed to by @cmdbufs.
+	 */
+	__u32 num_cmdbufs;
+
+	/**
+	 * @num_relocs:
+	 *
+	 * The number of relocations to perform before executing this job.
+	 * This defines the length of the array pointed to by @relocs.
+	 */
+	__u32 num_relocs;
+
+	/**
+	 * @num_waitchks:
+	 *
+	 * The number of wait checks to perform as part of this job. This
+	 * defines the length of the array pointed to by @waitchks.
+	 */
+	__u32 num_waitchks;
+
+	/**
+	 * @waitchk_mask:
+	 *
+	 * Bitmask of valid wait checks.
+	 */
+	__u32 waitchk_mask;
+
+	/**
+	 * @timeout:
+	 *
+	 * Timeout, in milliseconds, before this job is cancelled.
+	 */
+	__u32 timeout;
+
+	/**
+	 * @syncpts:
+	 *
+	 * A pointer to an array of &struct drm_tegra_syncpt structures that
+	 * specify the syncpoint operations performed as part of this job.
+	 * The number of elements in the array must be equal to the value
+	 * given by @num_syncpts.
+	 */
+	__u64 syncpts;
+
+	/**
+	 * @cmdbufs:
+	 *
+	 * A pointer to an array of &struct drm_tegra_cmdbuf structures that
+	 * define the command buffers to execute as part of this job. The
+	 * number of elements in the array must be equal to the value given
+	 * by @num_syncpts.
+	 */
+	__u64 cmdbufs;
+
+	/**
+	 * @relocs:
+	 *
+	 * A pointer to an array of &struct drm_tegra_reloc structures that
+	 * specify the relocations that need to be performed before executing
+	 * this job. The number of elements in the array must be equal to the
+	 * value given by @num_relocs.
+	 */
+	__u64 relocs;
+
+	/**
+	 * @waitchks:
+	 *
+	 * A pointer to an array of &struct drm_tegra_waitchk structures that
+	 * specify the wait checks to be performed while executing this job.
+	 * The number of elements in the array must be equal to the value
+	 * given by @num_waitchks.
+	 */
+	__u64 waitchks;
+
+	/**
+	 * @fence:
+	 *
+	 * The threshold of the syncpoint associated with this job after it
+	 * has been completed. Set by the kernel upon successful completion of
+	 * the IOCTL. This can be used with the DRM_TEGRA_SYNCPT_WAIT IOCTL to
+	 * wait for this job to be finished.
+	 */
+	__u32 fence;
+
+	/**
+	 * @reserved:
+	 *
+	 * This field is reserved for future use. Must be 0.
+	 */
+	__u32 reserved[5];
+};
+
+#define DRM_TEGRA_GEM_TILING_MODE_PITCH 0
+#define DRM_TEGRA_GEM_TILING_MODE_TILED 1
+#define DRM_TEGRA_GEM_TILING_MODE_BLOCK 2
+
+/**
+ * struct drm_tegra_gem_set_tiling - parameters for the set tiling IOCTL
+ */
+struct drm_tegra_gem_set_tiling {
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to set the tiling parameters.
+	 */
+	__u32 handle;
+
+	/**
+	 * @mode:
+	 *
+	 * The tiling mode to set. Must be one of:
+	 *
+	 * DRM_TEGRA_GEM_TILING_MODE_PITCH
+	 *   pitch linear format
+	 *
+	 * DRM_TEGRA_GEM_TILING_MODE_TILED
+	 *   16x16 tiling format
+	 *
+	 * DRM_TEGRA_GEM_TILING_MODE_BLOCK
+	 *   16Bx2 tiling format
+	 */
+	__u32 mode;
+
+	/**
+	 * @value:
+	 *
+	 * The value to set for the tiling mode parameter.
+	 */
+	__u32 value;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+};
+
+/**
+ * struct drm_tegra_gem_get_tiling - parameters for the get tiling IOCTL
+ */
+struct drm_tegra_gem_get_tiling {
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to query the tiling parameters.
+	 */
+	__u32 handle;
+
+	/**
+	 * @mode:
+	 *
+	 * The tiling mode currently associated with the GEM object. Set by
+	 * the kernel upon successful completion of the IOCTL.
+	 */
+	__u32 mode;
+
+	/**
+	 * @value:
+	 *
+	 * The tiling mode parameter currently associated with the GEM object.
+	 * Set by the kernel upon successful completion of the IOCTL.
+	 */
+	__u32 value;
+
+	/**
+	 * @pad:
+	 *
+	 * Structure padding that may be used in the future. Must be 0.
+	 */
+	__u32 pad;
+};
+
+#define DRM_TEGRA_GEM_BOTTOM_UP		(1 << 0)
+#define DRM_TEGRA_GEM_FLAGS		(DRM_TEGRA_GEM_BOTTOM_UP)
+
+/**
+ * struct drm_tegra_gem_set_flags - parameters for the set flags IOCTL
+ */
+struct drm_tegra_gem_set_flags {
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to set the flags.
+	 */
+	__u32 handle;
+
+	/**
+	 * @flags:
+	 *
+	 * The flags to set for the GEM object.
+	 */
+	__u32 flags;
+};
+
+/**
+ * struct drm_tegra_gem_get_flags - parameters for the get flags IOCTL
+ */
+struct drm_tegra_gem_get_flags {
+	/**
+	 * @handle:
+	 *
+	 * Handle to the GEM object for which to query the flags.
+	 */
+	__u32 handle;
+
+	/**
+	 * @flags:
+	 *
+	 * The flags currently associated with the GEM object. Set by the
+	 * kernel upon successful completion of the IOCTL.
+	 */
+	__u32 flags;
+};
+
+#define DRM_TEGRA_GEM_CREATE		0x00
+#define DRM_TEGRA_GEM_MMAP		0x01
+#define DRM_TEGRA_SYNCPT_READ		0x02
+#define DRM_TEGRA_SYNCPT_INCR		0x03
+#define DRM_TEGRA_SYNCPT_WAIT		0x04
+#define DRM_TEGRA_OPEN_CHANNEL	        0x05
+#define DRM_TEGRA_CLOSE_CHANNEL	        0x06
+#define DRM_TEGRA_GET_SYNCPT		0x07
+#define DRM_TEGRA_SUBMIT		0x08
+#define DRM_TEGRA_GET_SYNCPT_BASE	0x09
+#define DRM_TEGRA_GEM_SET_TILING	0x0a
+#define DRM_TEGRA_GEM_GET_TILING	0x0b
+#define DRM_TEGRA_GEM_SET_FLAGS		0x0c
+#define DRM_TEGRA_GEM_GET_FLAGS		0x0d
+
+#define DRM_IOCTL_TEGRA_GEM_CREATE DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_CREATE, struct drm_tegra_gem_create)
+#define DRM_IOCTL_TEGRA_GEM_MMAP DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_MMAP, struct drm_tegra_gem_mmap)
+#define DRM_IOCTL_TEGRA_SYNCPT_READ DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SYNCPT_READ, struct drm_tegra_syncpt_read)
+#define DRM_IOCTL_TEGRA_SYNCPT_INCR DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SYNCPT_INCR, struct drm_tegra_syncpt_incr)
+#define DRM_IOCTL_TEGRA_SYNCPT_WAIT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SYNCPT_WAIT, struct drm_tegra_syncpt_wait)
+#define DRM_IOCTL_TEGRA_OPEN_CHANNEL DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_OPEN_CHANNEL, struct drm_tegra_open_channel)
+#define DRM_IOCTL_TEGRA_CLOSE_CHANNEL DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_CLOSE_CHANNEL, struct drm_tegra_close_channel)
+#define DRM_IOCTL_TEGRA_GET_SYNCPT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GET_SYNCPT, struct drm_tegra_get_syncpt)
+#define DRM_IOCTL_TEGRA_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_SUBMIT, struct drm_tegra_submit)
+#define DRM_IOCTL_TEGRA_GET_SYNCPT_BASE DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GET_SYNCPT_BASE, struct drm_tegra_get_syncpt_base)
+#define DRM_IOCTL_TEGRA_GEM_SET_TILING DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_SET_TILING, struct drm_tegra_gem_set_tiling)
+#define DRM_IOCTL_TEGRA_GEM_GET_TILING DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_GET_TILING, struct drm_tegra_gem_get_tiling)
+#define DRM_IOCTL_TEGRA_GEM_SET_FLAGS DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_SET_FLAGS, struct drm_tegra_gem_set_flags)
+#define DRM_IOCTL_TEGRA_GEM_GET_FLAGS DRM_IOWR(DRM_COMMAND_BASE + DRM_TEGRA_GEM_GET_FLAGS, struct drm_tegra_gem_get_flags)
+
+/* New Tegra DRM UAPI */
+
+/*
+ * Reported by the driver in the `capabilities` field.
+ *
+ * DRM_TEGRA_CHANNEL_CAP_CACHE_COHERENT: If set, the engine is cache coherent
+ * with regard to the system memory.
+ */
+#define DRM_TEGRA_CHANNEL_CAP_CACHE_COHERENT (1 << 0)
+
+struct drm_tegra_channel_open {
+	/**
+	 * @host1x_class: [in]
+	 *
+	 * Host1x class of the engine that will be programmed using this
+	 * channel.
+	 */
+	__u32 host1x_class;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @context: [out]
+	 *
+	 * Opaque identifier corresponding to the opened channel.
+	 */
+	__u32 context;
+
+	/**
+	 * @version: [out]
+	 *
+	 * Version of the engine hardware. This can be used by userspace
+	 * to determine how the engine needs to be programmed.
+	 */
+	__u32 version;
+
+	/**
+	 * @capabilities: [out]
+	 *
+	 * Flags describing the hardware capabilities.
+	 */
+	__u32 capabilities;
+	__u32 padding;
+};
+
+struct drm_tegra_channel_close {
+	/**
+	 * @context: [in]
+	 *
+	 * Identifier of the channel to close.
+	 */
+	__u32 context;
+	__u32 padding;
+};
+
+/*
+ * Mapping flags that can be used to influence how the mapping is created.
+ *
+ * DRM_TEGRA_CHANNEL_MAP_READ: create mapping that allows HW read access
+ * DRM_TEGRA_CHANNEL_MAP_WRITE: create mapping that allows HW write access
+ */
+#define DRM_TEGRA_CHANNEL_MAP_READ  (1 << 0)
+#define DRM_TEGRA_CHANNEL_MAP_WRITE (1 << 1)
+#define DRM_TEGRA_CHANNEL_MAP_READ_WRITE (DRM_TEGRA_CHANNEL_MAP_READ | \
+					  DRM_TEGRA_CHANNEL_MAP_WRITE)
+
+struct drm_tegra_channel_map {
+	/**
+	 * @context: [in]
+	 *
+	 * Identifier of the channel to which make memory available for.
+	 */
+	__u32 context;
+
+	/**
+	 * @handle: [in]
+	 *
+	 * GEM handle of the memory to map.
+	 */
+	__u32 handle;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @mapping: [out]
+	 *
+	 * Identifier corresponding to the mapping, to be used for
+	 * relocations or unmapping later.
+	 */
+	__u32 mapping;
+};
+
+struct drm_tegra_channel_unmap {
+	/**
+	 * @context: [in]
+	 *
+	 * Channel identifier of the channel to unmap memory from.
+	 */
+	__u32 context;
+
+	/**
+	 * @mapping: [in]
+	 *
+	 * Mapping identifier of the memory mapping to unmap.
+	 */
+	__u32 mapping;
+};
+
+/* Submission */
+
+/**
+ * define DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT - \
+ *    Select sector layout swizzling for in-memory buffers.
+ *
+ * Specify that bit 39 of the patched-in address should be set to switch
+ * swizzling between Tegra and non-Tegra sector layout on systems that store
+ * surfaces in system memory in non-Tegra sector layout.
+ */
+#define DRM_TEGRA_SUBMIT_RELOC_SECTOR_LAYOUT (1 << 0)
+
+struct drm_tegra_submit_buf {
+	/**
+	 * @mapping: [in]
+	 *
+	 * Identifier of the mapping to use in the submission.
+	 */
+	__u32 mapping;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * Information for relocation patching.
+	 */
+	struct {
+		/**
+		 * @target_offset: [in]
+		 *
+		 * Offset from the start of the mapping of the data whose
+		 * address is to be patched into the gather.
+		 */
+		__u64 target_offset;
+
+		/**
+		 * @gather_offset_words: [in]
+		 *
+		 * Offset in words from the start of the gather data to
+		 * where the address should be patched into.
+		 */
+		__u32 gather_offset_words;
+
+		/**
+		 * @shift: [in]
+		 *
+		 * Number of bits the address should be shifted right before
+		 * patching in.
+		 */
+		__u32 shift;
+	} reloc;
+};
+
+/**
+ * define DRM_TEGRA_SUBMIT_CMD_GATHER_UPTR - \
+ *    Execute Host1x opcodes from user pointer.
+ *
+ * Execute `words` words of Host1x opcodes specified in the `gather_data_ptr`
+ * buffer. Each GATHER_UPTR command uses successive words from the buffer.
+ */
+#define DRM_TEGRA_SUBMIT_CMD_GATHER_UPTR		0
+
+/**
+ * define DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT - \
+ *    Wait for syncpoint (absolute).
+ *
+ * Wait for a syncpoint to reach a value before continuing with further
+ * commands.
+ */
+#define DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT		1
+
+/**
+ * define DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT_RELATIVE - \
+ *    Wait for syncpoint (relative).
+ *
+ * Wait for a syncpoint to reach a value before continuing with further
+ * commands. The threshold is calculated relative to the start of the job.
+ */
+#define DRM_TEGRA_SUBMIT_CMD_WAIT_SYNCPT_RELATIVE	2
+
+struct drm_tegra_submit_cmd_gather_uptr {
+	__u32 words;
+	__u32 reserved[3];
+};
+
+struct drm_tegra_submit_cmd_wait_syncpt {
+	__u32 id;
+	__u32 value;
+	__u32 reserved[2];
+};
+
+struct drm_tegra_submit_cmd {
+	/**
+	 * @type: [in]
+	 *
+	 * Command type to execute. One of the DRM_TEGRA_SUBMIT_CMD*
+	 * defines.
+	 */
+	__u32 type;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	union {
+		struct drm_tegra_submit_cmd_gather_uptr gather_uptr;
+		struct drm_tegra_submit_cmd_wait_syncpt wait_syncpt;
+		__u32 reserved[4];
+	};
+};
+
+struct drm_tegra_submit_syncpt {
+	/**
+	 * @id: [in]
+	 *
+	 * ID of the syncpoint that the job will increment.
+	 */
+	__u32 id;
+
+	/**
+	 * @flags: [in]
+	 *
+	 * Flags.
+	 */
+	__u32 flags;
+
+	/**
+	 * @increments: [in]
+	 *
+	 * Number of times the job will increment this syncpoint.
+	 */
+	__u32 increments;
+
+	/**
+	 * @value: [out]
+	 *
+	 * Value the syncpoint will have once the job has completed all
+	 * its specified syncpoint increments.
+	 *
+	 * Note that the kernel may increment the syncpoint before or after
+	 * the job. These increments are not reflected in this field.
+	 *
+	 * If the job hangs or times out, not all of the increments may
+	 * get executed.
+	 */
+	__u32 value;
+};
+
+struct drm_tegra_channel_submit {
+	/**
+	 * @context: [in]
+	 *
+	 * Identifier of the channel to submit this job to.
+	 */
+	__u32 context;
+
+	/**
+	 * @num_bufs: [in]
+	 *
+	 * Number of elements in the `bufs_ptr` array.
+	 */
+	__u32 num_bufs;
+
+	/**
+	 * @num_cmds: [in]
+	 *
+	 * Number of elements in the `cmds_ptr` array.
+	 */
+	__u32 num_cmds;
+
+	/**
+	 * @gather_data_words: [in]
+	 *
+	 * Number of 32-bit words in the `gather_data_ptr` array.
+	 */
+	__u32 gather_data_words;
+
+	/**
+	 * @bufs_ptr: [in]
+	 *
+	 * Pointer to an array of drm_tegra_submit_buf structures.
+	 */
+	__u64 bufs_ptr;
+
+	/**
+	 * @cmds_ptr: [in]
+	 *
+	 * Pointer to an array of drm_tegra_submit_cmd structures.
+	 */
+	__u64 cmds_ptr;
+
+	/**
+	 * @gather_data_ptr: [in]
+	 *
+	 * Pointer to an array of Host1x opcodes to be used by GATHER_UPTR
+	 * commands.
+	 */
+	__u64 gather_data_ptr;
+
+	/**
+	 * @syncobj_in: [in]
+	 *
+	 * Handle for DRM syncobj that will be waited before submission.
+	 * Ignored if zero.
+	 */
+	__u32 syncobj_in;
+
+	/**
+	 * @syncobj_out: [in]
+	 *
+	 * Handle for DRM syncobj that will have its fence replaced with
+	 * the job's completion fence. Ignored if zero.
+	 */
+	__u32 syncobj_out;
+
+	/**
+	 * @syncpt_incr: [in,out]
+	 *
+	 * Information about the syncpoint the job will increment.
+	 */
+	struct drm_tegra_submit_syncpt syncpt;
+};
+
+struct drm_tegra_syncpoint_allocate {
+	/**
+	 * @id: [out]
+	 *
+	 * ID of allocated syncpoint.
+	 */
+	__u32 id;
+	__u32 padding;
+};
+
+struct drm_tegra_syncpoint_free {
+	/**
+	 * @id: [in]
+	 *
+	 * ID of syncpoint to free.
+	 */
+	__u32 id;
+	__u32 padding;
+};
+
+struct drm_tegra_syncpoint_wait {
+	/**
+	 * @timeout: [in]
+	 *
+	 * Absolute timestamp at which the wait will time out.
+	 */
+	__s64 timeout_ns;
+
+	/**
+	 * @id: [in]
+	 *
+	 * ID of syncpoint to wait on.
+	 */
+	__u32 id;
+
+	/**
+	 * @threshold: [in]
+	 *
+	 * Threshold to wait for.
+	 */
+	__u32 threshold;
+
+	/**
+	 * @value: [out]
+	 *
+	 * Value of the syncpoint upon wait completion.
+	 */
+	__u32 value;
+
+	__u32 padding;
+};
+
+#define DRM_IOCTL_TEGRA_CHANNEL_OPEN DRM_IOWR(DRM_COMMAND_BASE + 0x10, struct drm_tegra_channel_open)
+#define DRM_IOCTL_TEGRA_CHANNEL_CLOSE DRM_IOWR(DRM_COMMAND_BASE + 0x11, struct drm_tegra_channel_close)
+#define DRM_IOCTL_TEGRA_CHANNEL_MAP DRM_IOWR(DRM_COMMAND_BASE + 0x12, struct drm_tegra_channel_map)
+#define DRM_IOCTL_TEGRA_CHANNEL_UNMAP DRM_IOWR(DRM_COMMAND_BASE + 0x13, struct drm_tegra_channel_unmap)
+#define DRM_IOCTL_TEGRA_CHANNEL_SUBMIT DRM_IOWR(DRM_COMMAND_BASE + 0x14, struct drm_tegra_channel_submit)
+
+#define DRM_IOCTL_TEGRA_SYNCPOINT_ALLOCATE DRM_IOWR(DRM_COMMAND_BASE + 0x20, struct drm_tegra_syncpoint_allocate)
+#define DRM_IOCTL_TEGRA_SYNCPOINT_FREE DRM_IOWR(DRM_COMMAND_BASE + 0x21, struct drm_tegra_syncpoint_free)
+#define DRM_IOCTL_TEGRA_SYNCPOINT_WAIT DRM_IOWR(DRM_COMMAND_BASE + 0x22, struct drm_tegra_syncpoint_wait)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/v3d_drm.h b/include/uapi/drm/v3d_drm.h
new file mode 100644
index 000000000..d9b01f4c3
--- /dev/null
+++ b/include/uapi/drm/v3d_drm.h
@@ -0,0 +1,793 @@
+/*
+ * Copyright © 2014-2018 Broadcom
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _V3D_DRM_H_
+#define _V3D_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_V3D_SUBMIT_CL                         0x00
+#define DRM_V3D_WAIT_BO                           0x01
+#define DRM_V3D_CREATE_BO                         0x02
+#define DRM_V3D_MMAP_BO                           0x03
+#define DRM_V3D_GET_PARAM                         0x04
+#define DRM_V3D_GET_BO_OFFSET                     0x05
+#define DRM_V3D_SUBMIT_TFU                        0x06
+#define DRM_V3D_SUBMIT_CSD                        0x07
+#define DRM_V3D_PERFMON_CREATE                    0x08
+#define DRM_V3D_PERFMON_DESTROY                   0x09
+#define DRM_V3D_PERFMON_GET_VALUES                0x0a
+#define DRM_V3D_SUBMIT_CPU                        0x0b
+#define DRM_V3D_PERFMON_GET_COUNTER               0x0c
+#define DRM_V3D_PERFMON_SET_GLOBAL                0x0d
+
+#define DRM_IOCTL_V3D_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CL, struct drm_v3d_submit_cl)
+#define DRM_IOCTL_V3D_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_WAIT_BO, struct drm_v3d_wait_bo)
+#define DRM_IOCTL_V3D_CREATE_BO           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_CREATE_BO, struct drm_v3d_create_bo)
+#define DRM_IOCTL_V3D_MMAP_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_MMAP_BO, struct drm_v3d_mmap_bo)
+#define DRM_IOCTL_V3D_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_PARAM, struct drm_v3d_get_param)
+#define DRM_IOCTL_V3D_GET_BO_OFFSET       DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_GET_BO_OFFSET, struct drm_v3d_get_bo_offset)
+#define DRM_IOCTL_V3D_SUBMIT_TFU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_TFU, struct drm_v3d_submit_tfu)
+#define DRM_IOCTL_V3D_SUBMIT_CSD          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CSD, struct drm_v3d_submit_csd)
+#define DRM_IOCTL_V3D_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_CREATE, \
+						   struct drm_v3d_perfmon_create)
+#define DRM_IOCTL_V3D_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_DESTROY, \
+						   struct drm_v3d_perfmon_destroy)
+#define DRM_IOCTL_V3D_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_VALUES, \
+						   struct drm_v3d_perfmon_get_values)
+#define DRM_IOCTL_V3D_SUBMIT_CPU          DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_SUBMIT_CPU, struct drm_v3d_submit_cpu)
+#define DRM_IOCTL_V3D_PERFMON_GET_COUNTER DRM_IOWR(DRM_COMMAND_BASE + DRM_V3D_PERFMON_GET_COUNTER, \
+						   struct drm_v3d_perfmon_get_counter)
+#define DRM_IOCTL_V3D_PERFMON_SET_GLOBAL  DRM_IOW(DRM_COMMAND_BASE + DRM_V3D_PERFMON_SET_GLOBAL, \
+						   struct drm_v3d_perfmon_set_global)
+
+#define DRM_V3D_SUBMIT_CL_FLUSH_CACHE             0x01
+#define DRM_V3D_SUBMIT_EXTENSION		  0x02
+
+/* struct drm_v3d_extension - ioctl extensions
+ *
+ * Linked-list of generic extensions where the id identify which struct is
+ * pointed by ext_data. Therefore, DRM_V3D_EXT_ID_* is used on id to identify
+ * the extension type.
+ */
+struct drm_v3d_extension {
+	__u64 next;
+	__u32 id;
+#define DRM_V3D_EXT_ID_MULTI_SYNC			0x01
+#define DRM_V3D_EXT_ID_CPU_INDIRECT_CSD		0x02
+#define DRM_V3D_EXT_ID_CPU_TIMESTAMP_QUERY		0x03
+#define DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY	0x04
+#define DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY	0x05
+#define DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY	0x06
+#define DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY	0x07
+	__u32 flags; /* mbz */
+};
+
+/* struct drm_v3d_sem - wait/signal semaphore
+ *
+ * If binary semaphore, it only takes syncobj handle and ignores flags and
+ * point fields. Point is defined for timeline syncobj feature.
+ */
+struct drm_v3d_sem {
+	__u32 handle; /* syncobj */
+	/* rsv below, for future uses */
+	__u32 flags;
+	__u64 point;  /* for timeline sem support */
+	__u64 mbz[2]; /* must be zero, rsv */
+};
+
+/* Enum for each of the V3D queues. */
+enum v3d_queue {
+	V3D_BIN,
+	V3D_RENDER,
+	V3D_TFU,
+	V3D_CSD,
+	V3D_CACHE_CLEAN,
+	V3D_CPU,
+};
+
+/**
+ * struct drm_v3d_multi_sync - ioctl extension to add support multiples
+ * syncobjs for commands submission.
+ *
+ * When an extension of DRM_V3D_EXT_ID_MULTI_SYNC id is defined, it points to
+ * this extension to define wait and signal dependencies, instead of single
+ * in/out sync entries on submitting commands. The field flags is used to
+ * determine the stage to set wait dependencies.
+ */
+struct drm_v3d_multi_sync {
+	struct drm_v3d_extension base;
+	/* Array of wait and signal semaphores */
+	__u64 in_syncs;
+	__u64 out_syncs;
+
+	/* Number of entries */
+	__u32 in_sync_count;
+	__u32 out_sync_count;
+
+	/* set the stage (v3d_queue) to sync */
+	__u32 wait_stage;
+
+	__u32 pad; /* mbz */
+};
+
+/**
+ * struct drm_v3d_submit_cl - ioctl argument for submitting commands to the 3D
+ * engine.
+ *
+ * This asks the kernel to have the GPU execute an optional binner
+ * command list, and a render command list.
+ *
+ * The L1T, slice, L2C, L2T, and GCA caches will be flushed before
+ * each CL executes.  The VCD cache should be flushed (if necessary)
+ * by the submitted CLs.  The TLB writes are guaranteed to have been
+ * flushed by the time the render done IRQ happens, which is the
+ * trigger for out_sync.  Any dirtying of cachelines by the job (only
+ * possible using TMU writes) must be flushed by the caller using the
+ * DRM_V3D_SUBMIT_CL_FLUSH_CACHE_FLAG flag.
+ */
+struct drm_v3d_submit_cl {
+	/* Pointer to the binner command list.
+	 *
+	 * This is the first set of commands executed, which runs the
+	 * coordinate shader to determine where primitives land on the screen,
+	 * then writes out the state updates and draw calls necessary per tile
+	 * to the tile allocation BO.
+	 *
+	 * This BCL will block on any previous BCL submitted on the
+	 * same FD, but not on any RCL or BCLs submitted by other
+	 * clients -- that is left up to the submitter to control
+	 * using in_sync_bcl if necessary.
+	 */
+	__u32 bcl_start;
+
+	/** End address of the BCL (first byte after the BCL) */
+	__u32 bcl_end;
+
+	/* Offset of the render command list.
+	 *
+	 * This is the second set of commands executed, which will either
+	 * execute the tiles that have been set up by the BCL, or a fixed set
+	 * of tiles (in the case of RCL-only blits).
+	 *
+	 * This RCL will block on this submit's BCL, and any previous
+	 * RCL submitted on the same FD, but not on any RCL or BCLs
+	 * submitted by other clients -- that is left up to the
+	 * submitter to control using in_sync_rcl if necessary.
+	 */
+	__u32 rcl_start;
+
+	/** End address of the RCL (first byte after the RCL) */
+	__u32 rcl_end;
+
+	/** An optional sync object to wait on before starting the BCL. */
+	__u32 in_sync_bcl;
+	/** An optional sync object to wait on before starting the RCL. */
+	__u32 in_sync_rcl;
+	/** An optional sync object to place the completion fence in. */
+	__u32 out_sync;
+
+	/* Offset of the tile alloc memory
+	 *
+	 * This is optional on V3D 3.3 (where the CL can set the value) but
+	 * required on V3D 4.1.
+	 */
+	__u32 qma;
+
+	/** Size of the tile alloc memory. */
+	__u32 qms;
+
+	/** Offset of the tile state data array. */
+	__u32 qts;
+
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* DRM_V3D_SUBMIT_* properties */
+	__u32 flags;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+
+	__u32 pad;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+};
+
+/**
+ * struct drm_v3d_wait_bo - ioctl argument for waiting for
+ * completion of the last DRM_V3D_SUBMIT_CL on a BO.
+ *
+ * This is useful for cases where multiple processes might be
+ * rendering to a BO and you want to wait for all rendering to be
+ * completed.
+ */
+struct drm_v3d_wait_bo {
+	__u32 handle;
+	__u32 pad;
+	__u64 timeout_ns;
+};
+
+/**
+ * struct drm_v3d_create_bo - ioctl argument for creating V3D BOs.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_v3d_create_bo {
+	__u32 size;
+	__u32 flags;
+	/** Returned GEM handle for the BO. */
+	__u32 handle;
+	/**
+	 * Returned offset for the BO in the V3D address space.  This offset
+	 * is private to the DRM fd and is valid for the lifetime of the GEM
+	 * handle.
+	 *
+	 * This offset value will always be nonzero, since various HW
+	 * units treat 0 specially.
+	 */
+	__u32 offset;
+};
+
+/**
+ * struct drm_v3d_mmap_bo - ioctl argument for mapping V3D BOs.
+ *
+ * This doesn't actually perform an mmap.  Instead, it returns the
+ * offset you need to use in an mmap on the DRM device node.  This
+ * means that tools like valgrind end up knowing about the mapped
+ * memory.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_v3d_mmap_bo {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 flags;
+	/** offset into the drm node to use for subsequent mmap call. */
+	__u64 offset;
+};
+
+enum drm_v3d_param {
+	DRM_V3D_PARAM_V3D_UIFCFG,
+	DRM_V3D_PARAM_V3D_HUB_IDENT1,
+	DRM_V3D_PARAM_V3D_HUB_IDENT2,
+	DRM_V3D_PARAM_V3D_HUB_IDENT3,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT0,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT1,
+	DRM_V3D_PARAM_V3D_CORE0_IDENT2,
+	DRM_V3D_PARAM_SUPPORTS_TFU,
+	DRM_V3D_PARAM_SUPPORTS_CSD,
+	DRM_V3D_PARAM_SUPPORTS_CACHE_FLUSH,
+	DRM_V3D_PARAM_SUPPORTS_PERFMON,
+	DRM_V3D_PARAM_SUPPORTS_MULTISYNC_EXT,
+	DRM_V3D_PARAM_SUPPORTS_CPU_QUEUE,
+	DRM_V3D_PARAM_MAX_PERF_COUNTERS,
+	DRM_V3D_PARAM_SUPPORTS_SUPER_PAGES,
+	DRM_V3D_PARAM_GLOBAL_RESET_COUNTER,
+	DRM_V3D_PARAM_CONTEXT_RESET_COUNTER,
+};
+
+struct drm_v3d_get_param {
+	__u32 param;
+	__u32 pad;
+	__u64 value;
+};
+
+/**
+ * Returns the offset for the BO in the V3D address space for this DRM fd.
+ * This is the same value returned by drm_v3d_create_bo, if that was called
+ * from this DRM fd.
+ */
+struct drm_v3d_get_bo_offset {
+	__u32 handle;
+	__u32 offset;
+};
+
+struct drm_v3d_submit_tfu {
+	__u32 icfg;
+	__u32 iia;
+	__u32 iis;
+	__u32 ica;
+	__u32 iua;
+	__u32 ioa;
+	__u32 ios;
+	__u32 coef[4];
+	/* First handle is the output BO, following are other inputs.
+	 * 0 for unused.
+	 */
+	__u32 bo_handles[4];
+	/* sync object to block on before running the TFU job.  Each TFU
+	 * job will execute in the order submitted to its FD.  Synchronization
+	 * against rendering jobs requires using sync objects.
+	 */
+	__u32 in_sync;
+	/* Sync object to signal when the TFU job is done. */
+	__u32 out_sync;
+
+	__u32 flags;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+
+	struct {
+		__u32 ioc;
+		__u32 pad;
+	} v71;
+};
+
+/* Submits a compute shader for dispatch.  This job will block on any
+ * previous compute shaders submitted on this fd, and any other
+ * synchronization must be performed with in_sync/out_sync.
+ */
+struct drm_v3d_submit_csd {
+	__u32 cfg[7];
+	__u32 coef[4];
+
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* sync object to block on before running the CSD job.  Each
+	 * CSD job will execute in the order submitted to its FD.
+	 * Synchronization against rendering/TFU jobs or CSD from
+	 * other fds requires using sync objects.
+	 */
+	__u32 in_sync;
+	/* Sync object to signal when the CSD job is done. */
+	__u32 out_sync;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmon_id;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+
+	__u32 flags;
+
+	__u32 pad;
+};
+
+/**
+ * struct drm_v3d_indirect_csd - ioctl extension for the CPU job to create an
+ * indirect CSD
+ *
+ * When an extension of DRM_V3D_EXT_ID_CPU_INDIRECT_CSD id is defined, it
+ * points to this extension to define a indirect CSD submission. It creates a
+ * CPU job linked to a CSD job. The CPU job waits for the indirect CSD
+ * dependencies and, once they are signaled, it updates the CSD job config
+ * before allowing the CSD job execution.
+ */
+struct drm_v3d_indirect_csd {
+	struct drm_v3d_extension base;
+
+	/* Indirect CSD */
+	struct drm_v3d_submit_csd submit;
+
+	/* Handle of the indirect BO, that should be also attached to the
+	 * indirect CSD.
+	 */
+	__u32 indirect;
+
+	/* Offset within the BO where the workgroup counts are stored */
+	__u32 offset;
+
+	/* Workgroups size */
+	__u32 wg_size;
+
+	/* Indices of the uniforms with the workgroup dispatch counts
+	 * in the uniform stream. If the uniform rewrite is not needed,
+	 * the offset must be 0xffffffff.
+	 */
+	__u32 wg_uniform_offsets[3];
+};
+
+/**
+ * struct drm_v3d_timestamp_query - ioctl extension for the CPU job to calculate
+ * a timestamp query
+ *
+ * When an extension DRM_V3D_EXT_ID_TIMESTAMP_QUERY is defined, it points to
+ * this extension to define a timestamp query submission. This CPU job will
+ * calculate the timestamp query and update the query value within the
+ * timestamp BO. Moreover, it will signal the timestamp syncobj to indicate
+ * query availability.
+ */
+struct drm_v3d_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Array of queries' offsets within the timestamp BO for their value */
+	__u64 offsets;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* mbz */
+	__u32 pad;
+};
+
+/**
+ * struct drm_v3d_reset_timestamp_query - ioctl extension for the CPU job to
+ * reset timestamp queries
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY is defined, it
+ * points to this extension to define a reset timestamp submission. This CPU
+ * job will reset the timestamp queries based on value offset of the first
+ * query. Moreover, it will reset the timestamp syncobj to reset query
+ * availability.
+ */
+struct drm_v3d_reset_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Offset of the first query within the timestamp BO for its value */
+	__u32 offset;
+
+	/* Number of queries */
+	__u32 count;
+};
+
+/**
+ * struct drm_v3d_copy_timestamp_query - ioctl extension for the CPU job to copy
+ * query results to a buffer
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY is defined, it
+ * points to this extension to define a copy timestamp query submission. This
+ * CPU job will copy the timestamp queries results to a BO with the offset
+ * and stride defined in the extension.
+ */
+struct drm_v3d_copy_timestamp_query {
+	struct drm_v3d_extension base;
+
+	/* Define if should write to buffer using 64 or 32 bits */
+	__u8 do_64bit;
+
+	/* Define if it can write to buffer even if the query is not available */
+	__u8 do_partial;
+
+	/* Define if it should write availability bit to buffer */
+	__u8 availability_bit;
+
+	/* mbz */
+	__u8 pad;
+
+	/* Offset of the buffer in the BO */
+	__u32 offset;
+
+	/* Stride of the buffer in the BO */
+	__u32 stride;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* Array of queries' offsets within the timestamp BO for their value */
+	__u64 offsets;
+
+	/* Array of timestamp's syncobjs to indicate its availability */
+	__u64 syncs;
+};
+
+/**
+ * struct drm_v3d_reset_performance_query - ioctl extension for the CPU job to
+ * reset performance queries
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY is defined, it
+ * points to this extension to define a reset performance submission. This CPU
+ * job will reset the performance queries by resetting the values of the
+ * performance monitors. Moreover, it will reset the syncobj to reset query
+ * availability.
+ */
+struct drm_v3d_reset_performance_query {
+	struct drm_v3d_extension base;
+
+	/* Array of performance queries's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* Number of performance monitors */
+	__u32 nperfmons;
+
+	/* Array of u64 user-pointers that point to an array of kperfmon_ids */
+	__u64 kperfmon_ids;
+};
+
+/**
+ * struct drm_v3d_copy_performance_query - ioctl extension for the CPU job to copy
+ * performance query results to a buffer
+ *
+ * When an extension DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY is defined, it
+ * points to this extension to define a copy performance query submission. This
+ * CPU job will copy the performance queries results to a BO with the offset
+ * and stride defined in the extension.
+ */
+struct drm_v3d_copy_performance_query {
+	struct drm_v3d_extension base;
+
+	/* Define if should write to buffer using 64 or 32 bits */
+	__u8 do_64bit;
+
+	/* Define if it can write to buffer even if the query is not available */
+	__u8 do_partial;
+
+	/* Define if it should write availability bit to buffer */
+	__u8 availability_bit;
+
+	/* mbz */
+	__u8 pad;
+
+	/* Offset of the buffer in the BO */
+	__u32 offset;
+
+	/* Stride of the buffer in the BO */
+	__u32 stride;
+
+	/* Number of performance monitors */
+	__u32 nperfmons;
+
+	/* Number of performance counters related to this query pool */
+	__u32 ncounters;
+
+	/* Number of queries */
+	__u32 count;
+
+	/* Array of performance queries's syncobjs to indicate its availability */
+	__u64 syncs;
+
+	/* Array of u64 user-pointers that point to an array of kperfmon_ids */
+	__u64 kperfmon_ids;
+};
+
+struct drm_v3d_submit_cpu {
+	/* Pointer to a u32 array of the BOs that are referenced by the job.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_INDIRECT_CSD, it must contain only one BO,
+	 * that contains the workgroup counts.
+	 *
+	 * For DRM_V3D_EXT_ID_TIMESTAMP_QUERY, it must contain only one BO,
+	 * that will contain the timestamp.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_RESET_TIMESTAMP_QUERY, it must contain only
+	 * one BO, that contains the timestamp.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_COPY_TIMESTAMP_QUERY, it must contain two
+	 * BOs. The first is the BO where the timestamp queries will be written
+	 * to. The second is the BO that contains the timestamp.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_RESET_PERFORMANCE_QUERY, it must contain no
+	 * BOs.
+	 *
+	 * For DRM_V3D_EXT_ID_CPU_COPY_PERFORMANCE_QUERY, it must contain one
+	 * BO, where the performance queries will be written.
+	 */
+	__u64 bo_handles;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	__u32 flags;
+
+	/* Pointer to an array of ioctl extensions*/
+	__u64 extensions;
+};
+
+/* The performance counters index represented by this enum are deprecated and
+ * must no longer be used. These counters are only valid for V3D 4.2.
+ *
+ * In order to check for performance counter information,
+ * use DRM_IOCTL_V3D_PERFMON_GET_COUNTER.
+ *
+ * Don't use V3D_PERFCNT_NUM to retrieve the maximum number of performance
+ * counters. You should use DRM_IOCTL_V3D_GET_PARAM with the following
+ * parameter: DRM_V3D_PARAM_MAX_PERF_COUNTERS.
+ */
+enum {
+	V3D_PERFCNT_FEP_VALID_PRIMTS_NO_PIXELS,
+	V3D_PERFCNT_FEP_VALID_PRIMS,
+	V3D_PERFCNT_FEP_EZ_NFCLIP_QUADS,
+	V3D_PERFCNT_FEP_VALID_QUADS,
+	V3D_PERFCNT_TLB_QUADS_STENCIL_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_FAIL,
+	V3D_PERFCNT_TLB_QUADS_STENCILZ_PASS,
+	V3D_PERFCNT_TLB_QUADS_ZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_NONZERO_COV,
+	V3D_PERFCNT_TLB_QUADS_WRITTEN,
+	V3D_PERFCNT_PTB_PRIM_VIEWPOINT_DISCARD,
+	V3D_PERFCNT_PTB_PRIM_CLIP,
+	V3D_PERFCNT_PTB_PRIM_REV,
+	V3D_PERFCNT_QPU_IDLE_CYCLES,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_ACTIVE_CYCLES_FRAG,
+	V3D_PERFCNT_QPU_CYCLES_VALID_INSTR,
+	V3D_PERFCNT_QPU_CYCLES_TMU_STALL,
+	V3D_PERFCNT_QPU_CYCLES_SCOREBOARD_STALL,
+	V3D_PERFCNT_QPU_CYCLES_VARYINGS_STALL,
+	V3D_PERFCNT_QPU_IC_HIT,
+	V3D_PERFCNT_QPU_IC_MISS,
+	V3D_PERFCNT_QPU_UC_HIT,
+	V3D_PERFCNT_QPU_UC_MISS,
+	V3D_PERFCNT_TMU_TCACHE_ACCESS,
+	V3D_PERFCNT_TMU_TCACHE_MISS,
+	V3D_PERFCNT_VPM_VDW_STALL,
+	V3D_PERFCNT_VPM_VCD_STALL,
+	V3D_PERFCNT_BIN_ACTIVE,
+	V3D_PERFCNT_RDR_ACTIVE,
+	V3D_PERFCNT_L2T_HITS,
+	V3D_PERFCNT_L2T_MISSES,
+	V3D_PERFCNT_CYCLE_COUNT,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_VERTEX_COORD_USER,
+	V3D_PERFCNT_QPU_CYCLES_STALLED_FRAGMENT,
+	V3D_PERFCNT_PTB_PRIMS_BINNED,
+	V3D_PERFCNT_AXI_WRITES_WATCH_0,
+	V3D_PERFCNT_AXI_READS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_0,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_0,
+	V3D_PERFCNT_AXI_WRITES_WATCH_1,
+	V3D_PERFCNT_AXI_READS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_READ_STALLS_WATCH_1,
+	V3D_PERFCNT_AXI_WRITE_BYTES_WATCH_1,
+	V3D_PERFCNT_AXI_READ_BYTES_WATCH_1,
+	V3D_PERFCNT_TLB_PARTIAL_QUADS,
+	V3D_PERFCNT_TMU_CONFIG_ACCESSES,
+	V3D_PERFCNT_L2T_NO_ID_STALL,
+	V3D_PERFCNT_L2T_COM_QUE_STALL,
+	V3D_PERFCNT_L2T_TMU_WRITES,
+	V3D_PERFCNT_TMU_ACTIVE_CYCLES,
+	V3D_PERFCNT_TMU_STALLED_CYCLES,
+	V3D_PERFCNT_CLE_ACTIVE,
+	V3D_PERFCNT_L2T_TMU_READS,
+	V3D_PERFCNT_L2T_CLE_READS,
+	V3D_PERFCNT_L2T_VCD_READS,
+	V3D_PERFCNT_L2T_TMUCFG_READS,
+	V3D_PERFCNT_L2T_SLC0_READS,
+	V3D_PERFCNT_L2T_SLC1_READS,
+	V3D_PERFCNT_L2T_SLC2_READS,
+	V3D_PERFCNT_L2T_TMU_W_MISSES,
+	V3D_PERFCNT_L2T_TMU_R_MISSES,
+	V3D_PERFCNT_L2T_CLE_MISSES,
+	V3D_PERFCNT_L2T_VCD_MISSES,
+	V3D_PERFCNT_L2T_TMUCFG_MISSES,
+	V3D_PERFCNT_L2T_SLC0_MISSES,
+	V3D_PERFCNT_L2T_SLC1_MISSES,
+	V3D_PERFCNT_L2T_SLC2_MISSES,
+	V3D_PERFCNT_CORE_MEM_WRITES,
+	V3D_PERFCNT_L2T_MEM_WRITES,
+	V3D_PERFCNT_PTB_MEM_WRITES,
+	V3D_PERFCNT_TLB_MEM_WRITES,
+	V3D_PERFCNT_CORE_MEM_READS,
+	V3D_PERFCNT_L2T_MEM_READS,
+	V3D_PERFCNT_PTB_MEM_READS,
+	V3D_PERFCNT_PSE_MEM_READS,
+	V3D_PERFCNT_TLB_MEM_READS,
+	V3D_PERFCNT_GMP_MEM_READS,
+	V3D_PERFCNT_PTB_W_MEM_WORDS,
+	V3D_PERFCNT_TLB_W_MEM_WORDS,
+	V3D_PERFCNT_PSE_R_MEM_WORDS,
+	V3D_PERFCNT_TLB_R_MEM_WORDS,
+	V3D_PERFCNT_TMU_MRU_HITS,
+	V3D_PERFCNT_COMPUTE_ACTIVE,
+	V3D_PERFCNT_NUM,
+};
+
+#define DRM_V3D_MAX_PERF_COUNTERS                 32
+
+struct drm_v3d_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 counters[DRM_V3D_MAX_PERF_COUNTERS];
+};
+
+struct drm_v3d_perfmon_destroy {
+	__u32 id;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of ncounters u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed  (probably by blocking on the seqno returned by the
+ * last exec that used the perfmon).
+ */
+struct drm_v3d_perfmon_get_values {
+	__u32 id;
+	__u32 pad;
+	__u64 values_ptr;
+};
+
+#define DRM_V3D_PERFCNT_MAX_NAME 64
+#define DRM_V3D_PERFCNT_MAX_CATEGORY 32
+#define DRM_V3D_PERFCNT_MAX_DESCRIPTION 256
+
+/**
+ * struct drm_v3d_perfmon_get_counter - ioctl to get the description of a
+ * performance counter
+ *
+ * As userspace needs to retrieve information about the performance counters
+ * available, this IOCTL allows users to get information about a performance
+ * counter (name, category and description).
+ */
+struct drm_v3d_perfmon_get_counter {
+	/*
+	 * Counter ID
+	 *
+	 * Must be smaller than the maximum number of performance counters, which
+	 * can be retrieve through DRM_V3D_PARAM_MAX_PERF_COUNTERS.
+	 */
+	__u8 counter;
+
+	/* Name of the counter */
+	__u8 name[DRM_V3D_PERFCNT_MAX_NAME];
+
+	/* Category of the counter */
+	__u8 category[DRM_V3D_PERFCNT_MAX_CATEGORY];
+
+	/* Description of the counter */
+	__u8 description[DRM_V3D_PERFCNT_MAX_DESCRIPTION];
+
+	/* mbz */
+	__u8 reserved[7];
+};
+
+#define DRM_V3D_PERFMON_CLEAR_GLOBAL    0x0001
+
+/**
+ * struct drm_v3d_perfmon_set_global - ioctl to define a global performance
+ * monitor
+ *
+ * The global performance monitor will be used for all jobs. If a global
+ * performance monitor is defined, jobs with a self-defined performance
+ * monitor won't be allowed.
+ */
+struct drm_v3d_perfmon_set_global {
+	__u32 flags;
+	__u32 id;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _V3D_DRM_H_ */
diff --git a/include/uapi/drm/vc4_drm.h b/include/uapi/drm/vc4_drm.h
new file mode 100644
index 000000000..2cac6277a
--- /dev/null
+++ b/include/uapi/drm/vc4_drm.h
@@ -0,0 +1,442 @@
+/*
+ * Copyright © 2014-2015 Broadcom
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef _UAPI_VC4_DRM_H_
+#define _UAPI_VC4_DRM_H_
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_VC4_SUBMIT_CL                         0x00
+#define DRM_VC4_WAIT_SEQNO                        0x01
+#define DRM_VC4_WAIT_BO                           0x02
+#define DRM_VC4_CREATE_BO                         0x03
+#define DRM_VC4_MMAP_BO                           0x04
+#define DRM_VC4_CREATE_SHADER_BO                  0x05
+#define DRM_VC4_GET_HANG_STATE                    0x06
+#define DRM_VC4_GET_PARAM                         0x07
+#define DRM_VC4_SET_TILING                        0x08
+#define DRM_VC4_GET_TILING                        0x09
+#define DRM_VC4_LABEL_BO                          0x0a
+#define DRM_VC4_GEM_MADVISE                       0x0b
+#define DRM_VC4_PERFMON_CREATE                    0x0c
+#define DRM_VC4_PERFMON_DESTROY                   0x0d
+#define DRM_VC4_PERFMON_GET_VALUES                0x0e
+
+#define DRM_IOCTL_VC4_SUBMIT_CL           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SUBMIT_CL, struct drm_vc4_submit_cl)
+#define DRM_IOCTL_VC4_WAIT_SEQNO          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_SEQNO, struct drm_vc4_wait_seqno)
+#define DRM_IOCTL_VC4_WAIT_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_WAIT_BO, struct drm_vc4_wait_bo)
+#define DRM_IOCTL_VC4_CREATE_BO           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_CREATE_BO, struct drm_vc4_create_bo)
+#define DRM_IOCTL_VC4_MMAP_BO             DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_MMAP_BO, struct drm_vc4_mmap_bo)
+#define DRM_IOCTL_VC4_CREATE_SHADER_BO    DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_CREATE_SHADER_BO, struct drm_vc4_create_shader_bo)
+#define DRM_IOCTL_VC4_GET_HANG_STATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_HANG_STATE, struct drm_vc4_get_hang_state)
+#define DRM_IOCTL_VC4_GET_PARAM           DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_PARAM, struct drm_vc4_get_param)
+#define DRM_IOCTL_VC4_SET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_SET_TILING, struct drm_vc4_set_tiling)
+#define DRM_IOCTL_VC4_GET_TILING          DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GET_TILING, struct drm_vc4_get_tiling)
+#define DRM_IOCTL_VC4_LABEL_BO            DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_LABEL_BO, struct drm_vc4_label_bo)
+#define DRM_IOCTL_VC4_GEM_MADVISE         DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_GEM_MADVISE, struct drm_vc4_gem_madvise)
+#define DRM_IOCTL_VC4_PERFMON_CREATE      DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_CREATE, struct drm_vc4_perfmon_create)
+#define DRM_IOCTL_VC4_PERFMON_DESTROY     DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_DESTROY, struct drm_vc4_perfmon_destroy)
+#define DRM_IOCTL_VC4_PERFMON_GET_VALUES  DRM_IOWR(DRM_COMMAND_BASE + DRM_VC4_PERFMON_GET_VALUES, struct drm_vc4_perfmon_get_values)
+
+struct drm_vc4_submit_rcl_surface {
+	__u32 hindex; /* Handle index, or ~0 if not present. */
+	__u32 offset; /* Offset to start of buffer. */
+	/*
+	 * Bits for either render config (color_write) or load/store packet.
+	 * Bits should all be 0 for MSAA load/stores.
+	 */
+	__u16 bits;
+
+#define VC4_SUBMIT_RCL_SURFACE_READ_IS_FULL_RES		(1 << 0)
+	__u16 flags;
+};
+
+/**
+ * struct drm_vc4_submit_cl - ioctl argument for submitting commands to the 3D
+ * engine.
+ *
+ * Drivers typically use GPU BOs to store batchbuffers / command lists and
+ * their associated state.  However, because the VC4 lacks an MMU, we have to
+ * do validation of memory accesses by the GPU commands.  If we were to store
+ * our commands in BOs, we'd need to do uncached readback from them to do the
+ * validation process, which is too expensive.  Instead, userspace accumulates
+ * commands and associated state in plain memory, then the kernel copies the
+ * data to its own address space, and then validates and stores it in a GPU
+ * BO.
+ */
+struct drm_vc4_submit_cl {
+	/* Pointer to the binner command list.
+	 *
+	 * This is the first set of commands executed, which runs the
+	 * coordinate shader to determine where primitives land on the screen,
+	 * then writes out the state updates and draw calls necessary per tile
+	 * to the tile allocation BO.
+	 */
+	__u64 bin_cl;
+
+	/* Pointer to the shader records.
+	 *
+	 * Shader records are the structures read by the hardware that contain
+	 * pointers to uniforms, shaders, and vertex attributes.  The
+	 * reference to the shader record has enough information to determine
+	 * how many pointers are necessary (fixed number for shaders/uniforms,
+	 * and an attribute count), so those BO indices into bo_handles are
+	 * just stored as __u32s before each shader record passed in.
+	 */
+	__u64 shader_rec;
+
+	/* Pointer to uniform data and texture handles for the textures
+	 * referenced by the shader.
+	 *
+	 * For each shader state record, there is a set of uniform data in the
+	 * order referenced by the record (FS, VS, then CS).  Each set of
+	 * uniform data has a __u32 index into bo_handles per texture
+	 * sample operation, in the order the QPU_W_TMUn_S writes appear in
+	 * the program.  Following the texture BO handle indices is the actual
+	 * uniform data.
+	 *
+	 * The individual uniform state blocks don't have sizes passed in,
+	 * because the kernel has to determine the sizes anyway during shader
+	 * code validation.
+	 */
+	__u64 uniforms;
+	__u64 bo_handles;
+
+	/* Size in bytes of the binner command list. */
+	__u32 bin_cl_size;
+	/* Size in bytes of the set of shader records. */
+	__u32 shader_rec_size;
+	/* Number of shader records.
+	 *
+	 * This could just be computed from the contents of shader_records and
+	 * the address bits of references to them from the bin CL, but it
+	 * keeps the kernel from having to resize some allocations it makes.
+	 */
+	__u32 shader_rec_count;
+	/* Size in bytes of the uniform state. */
+	__u32 uniforms_size;
+
+	/* Number of BO handles passed in (size is that times 4). */
+	__u32 bo_handle_count;
+
+	/* RCL setup: */
+	__u16 width;
+	__u16 height;
+	__u8 min_x_tile;
+	__u8 min_y_tile;
+	__u8 max_x_tile;
+	__u8 max_y_tile;
+	struct drm_vc4_submit_rcl_surface color_read;
+	struct drm_vc4_submit_rcl_surface color_write;
+	struct drm_vc4_submit_rcl_surface zs_read;
+	struct drm_vc4_submit_rcl_surface zs_write;
+	struct drm_vc4_submit_rcl_surface msaa_color_write;
+	struct drm_vc4_submit_rcl_surface msaa_zs_write;
+	__u32 clear_color[2];
+	__u32 clear_z;
+	__u8 clear_s;
+
+	__u32 pad:24;
+
+#define VC4_SUBMIT_CL_USE_CLEAR_COLOR			(1 << 0)
+/* By default, the kernel gets to choose the order that the tiles are
+ * rendered in.  If this is set, then the tiles will be rendered in a
+ * raster order, with the right-to-left vs left-to-right and
+ * top-to-bottom vs bottom-to-top dictated by
+ * VC4_SUBMIT_CL_RCL_ORDER_INCREASING_*.  This allows overlapping
+ * blits to be implemented using the 3D engine.
+ */
+#define VC4_SUBMIT_CL_FIXED_RCL_ORDER			(1 << 1)
+#define VC4_SUBMIT_CL_RCL_ORDER_INCREASING_X		(1 << 2)
+#define VC4_SUBMIT_CL_RCL_ORDER_INCREASING_Y		(1 << 3)
+	__u32 flags;
+
+	/* Returned value of the seqno of this render job (for the
+	 * wait ioctl).
+	 */
+	__u64 seqno;
+
+	/* ID of the perfmon to attach to this job. 0 means no perfmon. */
+	__u32 perfmonid;
+
+	/* Syncobj handle to wait on. If set, processing of this render job
+	 * will not start until the syncobj is signaled. 0 means ignore.
+	 */
+	__u32 in_sync;
+
+	/* Syncobj handle to export fence to. If set, the fence in the syncobj
+	 * will be replaced with a fence that signals upon completion of this
+	 * render job. 0 means ignore.
+	 */
+	__u32 out_sync;
+
+	__u32 pad2;
+};
+
+/**
+ * struct drm_vc4_wait_seqno - ioctl argument for waiting for
+ * DRM_VC4_SUBMIT_CL completion using its returned seqno.
+ *
+ * timeout_ns is the timeout in nanoseconds, where "0" means "don't
+ * block, just return the status."
+ */
+struct drm_vc4_wait_seqno {
+	__u64 seqno;
+	__u64 timeout_ns;
+};
+
+/**
+ * struct drm_vc4_wait_bo - ioctl argument for waiting for
+ * completion of the last DRM_VC4_SUBMIT_CL on a BO.
+ *
+ * This is useful for cases where multiple processes might be
+ * rendering to a BO and you want to wait for all rendering to be
+ * completed.
+ */
+struct drm_vc4_wait_bo {
+	__u32 handle;
+	__u32 pad;
+	__u64 timeout_ns;
+};
+
+/**
+ * struct drm_vc4_create_bo - ioctl argument for creating VC4 BOs.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_vc4_create_bo {
+	__u32 size;
+	__u32 flags;
+	/** Returned GEM handle for the BO. */
+	__u32 handle;
+	__u32 pad;
+};
+
+/**
+ * struct drm_vc4_mmap_bo - ioctl argument for mapping VC4 BOs.
+ *
+ * This doesn't actually perform an mmap.  Instead, it returns the
+ * offset you need to use in an mmap on the DRM device node.  This
+ * means that tools like valgrind end up knowing about the mapped
+ * memory.
+ *
+ * There are currently no values for the flags argument, but it may be
+ * used in a future extension.
+ */
+struct drm_vc4_mmap_bo {
+	/** Handle for the object being mapped. */
+	__u32 handle;
+	__u32 flags;
+	/** offset into the drm node to use for subsequent mmap call. */
+	__u64 offset;
+};
+
+/**
+ * struct drm_vc4_create_shader_bo - ioctl argument for creating VC4
+ * shader BOs.
+ *
+ * Since allowing a shader to be overwritten while it's also being
+ * executed from would allow privlege escalation, shaders must be
+ * created using this ioctl, and they can't be mmapped later.
+ */
+struct drm_vc4_create_shader_bo {
+	/* Size of the data argument. */
+	__u32 size;
+	/* Flags, currently must be 0. */
+	__u32 flags;
+
+	/* Pointer to the data. */
+	__u64 data;
+
+	/** Returned GEM handle for the BO. */
+	__u32 handle;
+	/* Pad, must be 0. */
+	__u32 pad;
+};
+
+struct drm_vc4_get_hang_state_bo {
+	__u32 handle;
+	__u32 paddr;
+	__u32 size;
+	__u32 pad;
+};
+
+/**
+ * struct drm_vc4_hang_state - ioctl argument for collecting state
+ * from a GPU hang for analysis.
+*/
+struct drm_vc4_get_hang_state {
+	/** Pointer to array of struct drm_vc4_get_hang_state_bo. */
+	__u64 bo;
+	/**
+	 * On input, the size of the bo array.  Output is the number
+	 * of bos to be returned.
+	 */
+	__u32 bo_count;
+
+	__u32 start_bin, start_render;
+
+	__u32 ct0ca, ct0ea;
+	__u32 ct1ca, ct1ea;
+	__u32 ct0cs, ct1cs;
+	__u32 ct0ra0, ct1ra0;
+
+	__u32 bpca, bpcs;
+	__u32 bpoa, bpos;
+
+	__u32 vpmbase;
+
+	__u32 dbge;
+	__u32 fdbgo;
+	__u32 fdbgb;
+	__u32 fdbgr;
+	__u32 fdbgs;
+	__u32 errstat;
+
+	/* Pad that we may save more registers into in the future. */
+	__u32 pad[16];
+};
+
+#define DRM_VC4_PARAM_V3D_IDENT0		0
+#define DRM_VC4_PARAM_V3D_IDENT1		1
+#define DRM_VC4_PARAM_V3D_IDENT2		2
+#define DRM_VC4_PARAM_SUPPORTS_BRANCHES		3
+#define DRM_VC4_PARAM_SUPPORTS_ETC1		4
+#define DRM_VC4_PARAM_SUPPORTS_THREADED_FS	5
+#define DRM_VC4_PARAM_SUPPORTS_FIXED_RCL_ORDER	6
+#define DRM_VC4_PARAM_SUPPORTS_MADVISE		7
+#define DRM_VC4_PARAM_SUPPORTS_PERFMON		8
+
+struct drm_vc4_get_param {
+	__u32 param;
+	__u32 pad;
+	__u64 value;
+};
+
+struct drm_vc4_get_tiling {
+	__u32 handle;
+	__u32 flags;
+	__u64 modifier;
+};
+
+struct drm_vc4_set_tiling {
+	__u32 handle;
+	__u32 flags;
+	__u64 modifier;
+};
+
+/**
+ * struct drm_vc4_label_bo - Attach a name to a BO for debug purposes.
+ */
+struct drm_vc4_label_bo {
+	__u32 handle;
+	__u32 len;
+	__u64 name;
+};
+
+/*
+ * States prefixed with '__' are internal states and cannot be passed to the
+ * DRM_IOCTL_VC4_GEM_MADVISE ioctl.
+ */
+#define VC4_MADV_WILLNEED			0
+#define VC4_MADV_DONTNEED			1
+#define __VC4_MADV_PURGED			2
+#define __VC4_MADV_NOTSUPP			3
+
+struct drm_vc4_gem_madvise {
+	__u32 handle;
+	__u32 madv;
+	__u32 retained;
+	__u32 pad;
+};
+
+enum {
+	VC4_PERFCNT_FEP_VALID_PRIMS_NO_RENDER,
+	VC4_PERFCNT_FEP_VALID_PRIMS_RENDER,
+	VC4_PERFCNT_FEP_CLIPPED_QUADS,
+	VC4_PERFCNT_FEP_VALID_QUADS,
+	VC4_PERFCNT_TLB_QUADS_NOT_PASSING_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_NOT_PASSING_Z_AND_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_PASSING_Z_AND_STENCIL,
+	VC4_PERFCNT_TLB_QUADS_ZERO_COVERAGE,
+	VC4_PERFCNT_TLB_QUADS_NON_ZERO_COVERAGE,
+	VC4_PERFCNT_TLB_QUADS_WRITTEN_TO_COLOR_BUF,
+	VC4_PERFCNT_PLB_PRIMS_OUTSIDE_VIEWPORT,
+	VC4_PERFCNT_PLB_PRIMS_NEED_CLIPPING,
+	VC4_PERFCNT_PSE_PRIMS_REVERSED,
+	VC4_PERFCNT_QPU_TOTAL_IDLE_CYCLES,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_VERTEX_COORD_SHADING,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_FRAGMENT_SHADING,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_EXEC_VALID_INST,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_TMUS,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_SCOREBOARD,
+	VC4_PERFCNT_QPU_TOTAL_CLK_CYCLES_WAITING_VARYINGS,
+	VC4_PERFCNT_QPU_TOTAL_INST_CACHE_HIT,
+	VC4_PERFCNT_QPU_TOTAL_INST_CACHE_MISS,
+	VC4_PERFCNT_QPU_TOTAL_UNIFORM_CACHE_HIT,
+	VC4_PERFCNT_QPU_TOTAL_UNIFORM_CACHE_MISS,
+	VC4_PERFCNT_TMU_TOTAL_TEXT_QUADS_PROCESSED,
+	VC4_PERFCNT_TMU_TOTAL_TEXT_CACHE_MISS,
+	VC4_PERFCNT_VPM_TOTAL_CLK_CYCLES_VDW_STALLED,
+	VC4_PERFCNT_VPM_TOTAL_CLK_CYCLES_VCD_STALLED,
+	VC4_PERFCNT_L2C_TOTAL_L2_CACHE_HIT,
+	VC4_PERFCNT_L2C_TOTAL_L2_CACHE_MISS,
+	VC4_PERFCNT_NUM_EVENTS,
+};
+
+#define DRM_VC4_MAX_PERF_COUNTERS	16
+
+struct drm_vc4_perfmon_create {
+	__u32 id;
+	__u32 ncounters;
+	__u8 events[DRM_VC4_MAX_PERF_COUNTERS];
+};
+
+struct drm_vc4_perfmon_destroy {
+	__u32 id;
+};
+
+/*
+ * Returns the values of the performance counters tracked by this
+ * perfmon (as an array of ncounters u64 values).
+ *
+ * No implicit synchronization is performed, so the user has to
+ * guarantee that any jobs using this perfmon have already been
+ * completed  (probably by blocking on the seqno returned by the
+ * last exec that used the perfmon).
+ */
+struct drm_vc4_perfmon_get_values {
+	__u32 id;
+	__u64 values_ptr;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_VC4_DRM_H_ */
diff --git a/include/uapi/drm/vgem_drm.h b/include/uapi/drm/vgem_drm.h
new file mode 100644
index 000000000..bf66f5db6
--- /dev/null
+++ b/include/uapi/drm/vgem_drm.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright 2016 Intel Corporation
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
+ * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
+ * IN NO EVENT SHALL TUNGSTEN GRAPHICS AND/OR ITS SUPPLIERS BE LIABLE FOR
+ * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+ * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+ * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#ifndef _UAPI_VGEM_DRM_H_
+#define _UAPI_VGEM_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.
+ */
+#define DRM_VGEM_FENCE_ATTACH	0x1
+#define DRM_VGEM_FENCE_SIGNAL	0x2
+
+#define DRM_IOCTL_VGEM_FENCE_ATTACH	DRM_IOWR( DRM_COMMAND_BASE + DRM_VGEM_FENCE_ATTACH, struct drm_vgem_fence_attach)
+#define DRM_IOCTL_VGEM_FENCE_SIGNAL	DRM_IOW( DRM_COMMAND_BASE + DRM_VGEM_FENCE_SIGNAL, struct drm_vgem_fence_signal)
+
+struct drm_vgem_fence_attach {
+	__u32 handle;
+	__u32 flags;
+#define VGEM_FENCE_WRITE	0x1
+	__u32 out_fence;
+	__u32 pad;
+};
+
+struct drm_vgem_fence_signal {
+	__u32 fence;
+	__u32 flags;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_VGEM_DRM_H_ */
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
new file mode 100644
index 000000000..95587e12a
--- /dev/null
+++ b/include/uapi/drm/virtgpu_drm.h
@@ -0,0 +1,281 @@
+/*
+ * Copyright 2013 Red Hat
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ */
+#ifndef VIRTGPU_DRM_H
+#define VIRTGPU_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.
+ *
+ * Do not use pointers, use __u64 instead for 32 bit / 64 bit user/kernel
+ * compatibility Keep fields aligned to their size
+ */
+
+#define DRM_VIRTGPU_MAP         0x01
+#define DRM_VIRTGPU_EXECBUFFER  0x02
+#define DRM_VIRTGPU_GETPARAM    0x03
+#define DRM_VIRTGPU_RESOURCE_CREATE 0x04
+#define DRM_VIRTGPU_RESOURCE_INFO     0x05
+#define DRM_VIRTGPU_TRANSFER_FROM_HOST 0x06
+#define DRM_VIRTGPU_TRANSFER_TO_HOST 0x07
+#define DRM_VIRTGPU_WAIT     0x08
+#define DRM_VIRTGPU_GET_CAPS  0x09
+#define DRM_VIRTGPU_RESOURCE_CREATE_BLOB 0x0a
+#define DRM_VIRTGPU_CONTEXT_INIT 0x0b
+
+#define VIRTGPU_EXECBUF_FENCE_FD_IN	0x01
+#define VIRTGPU_EXECBUF_FENCE_FD_OUT	0x02
+#define VIRTGPU_EXECBUF_RING_IDX	0x04
+#define VIRTGPU_EXECBUF_FLAGS  (\
+		VIRTGPU_EXECBUF_FENCE_FD_IN |\
+		VIRTGPU_EXECBUF_FENCE_FD_OUT |\
+		VIRTGPU_EXECBUF_RING_IDX |\
+		0)
+
+struct drm_virtgpu_map {
+	__u64 offset; /* use for mmap system call */
+	__u32 handle;
+	__u32 pad;
+};
+
+#define VIRTGPU_EXECBUF_SYNCOBJ_RESET		0x01
+#define VIRTGPU_EXECBUF_SYNCOBJ_FLAGS ( \
+		VIRTGPU_EXECBUF_SYNCOBJ_RESET | \
+		0)
+struct drm_virtgpu_execbuffer_syncobj {
+	__u32 handle;
+	__u32 flags;
+	__u64 point;
+};
+
+/* fence_fd is modified on success if VIRTGPU_EXECBUF_FENCE_FD_OUT flag is set. */
+struct drm_virtgpu_execbuffer {
+	__u32 flags;
+	__u32 size;
+	__u64 command; /* void* */
+	__u64 bo_handles;
+	__u32 num_bo_handles;
+	__s32 fence_fd; /* in/out fence fd (see VIRTGPU_EXECBUF_FENCE_FD_IN/OUT) */
+	__u32 ring_idx; /* command ring index (see VIRTGPU_EXECBUF_RING_IDX) */
+	__u32 syncobj_stride; /* size of @drm_virtgpu_execbuffer_syncobj */
+	__u32 num_in_syncobjs;
+	__u32 num_out_syncobjs;
+	__u64 in_syncobjs;
+	__u64 out_syncobjs;
+};
+
+#define VIRTGPU_PARAM_3D_FEATURES 1 /* do we have 3D features in the hw */
+#define VIRTGPU_PARAM_CAPSET_QUERY_FIX 2 /* do we have the capset fix */
+#define VIRTGPU_PARAM_RESOURCE_BLOB 3 /* DRM_VIRTGPU_RESOURCE_CREATE_BLOB */
+#define VIRTGPU_PARAM_HOST_VISIBLE 4 /* Host blob resources are mappable */
+#define VIRTGPU_PARAM_CROSS_DEVICE 5 /* Cross virtio-device resource sharing  */
+#define VIRTGPU_PARAM_CONTEXT_INIT 6 /* DRM_VIRTGPU_CONTEXT_INIT */
+#define VIRTGPU_PARAM_SUPPORTED_CAPSET_IDs 7 /* Bitmask of supported capability set ids */
+#define VIRTGPU_PARAM_EXPLICIT_DEBUG_NAME 8 /* Ability to set debug name from userspace */
+#define VIRTGPU_PARAM_BLOB_ALIGNMENT 9 /* Device alignment requirements for blobs */
+
+struct drm_virtgpu_getparam {
+	__u64 param;
+	__u64 value;
+};
+
+/* NO_BO flags? NO resource flag? */
+/* resource flag for y_0_top */
+struct drm_virtgpu_resource_create {
+	__u32 target;
+	__u32 format;
+	__u32 bind;
+	__u32 width;
+	__u32 height;
+	__u32 depth;
+	__u32 array_size;
+	__u32 last_level;
+	__u32 nr_samples;
+	__u32 flags;
+	__u32 bo_handle; /* if this is set - recreate a new resource attached to this bo ? */
+	__u32 res_handle;  /* returned by kernel */
+	__u32 size;        /* validate transfer in the host */
+	__u32 stride;      /* validate transfer in the host */
+};
+
+struct drm_virtgpu_resource_info {
+	__u32 bo_handle;
+	__u32 res_handle;
+	__u32 size;
+	__u32 blob_mem;
+};
+
+struct drm_virtgpu_3d_box {
+	__u32 x;
+	__u32 y;
+	__u32 z;
+	__u32 w;
+	__u32 h;
+	__u32 d;
+};
+
+struct drm_virtgpu_3d_transfer_to_host {
+	__u32 bo_handle;
+	struct drm_virtgpu_3d_box box;
+	__u32 level;
+	__u32 offset;
+	__u32 stride;
+	__u32 layer_stride;
+};
+
+struct drm_virtgpu_3d_transfer_from_host {
+	__u32 bo_handle;
+	struct drm_virtgpu_3d_box box;
+	__u32 level;
+	__u32 offset;
+	__u32 stride;
+	__u32 layer_stride;
+};
+
+#define VIRTGPU_WAIT_NOWAIT 1 /* like it */
+struct drm_virtgpu_3d_wait {
+	__u32 handle; /* 0 is an invalid handle */
+	__u32 flags;
+};
+
+#define VIRTGPU_DRM_CAPSET_VIRGL 1
+#define VIRTGPU_DRM_CAPSET_VIRGL2 2
+#define VIRTGPU_DRM_CAPSET_GFXSTREAM_VULKAN 3
+#define VIRTGPU_DRM_CAPSET_VENUS 4
+#define VIRTGPU_DRM_CAPSET_CROSS_DOMAIN 5
+#define VIRTGPU_DRM_CAPSET_DRM 6
+struct drm_virtgpu_get_caps {
+	__u32 cap_set_id;
+	__u32 cap_set_ver;
+	__u64 addr;
+	__u32 size;
+	__u32 pad;
+};
+
+struct drm_virtgpu_resource_create_blob {
+#define VIRTGPU_BLOB_MEM_GUEST             0x0001
+#define VIRTGPU_BLOB_MEM_HOST3D            0x0002
+#define VIRTGPU_BLOB_MEM_HOST3D_GUEST      0x0003
+
+#define VIRTGPU_BLOB_FLAG_USE_MAPPABLE     0x0001
+#define VIRTGPU_BLOB_FLAG_USE_SHAREABLE    0x0002
+#define VIRTGPU_BLOB_FLAG_USE_CROSS_DEVICE 0x0004
+	/* zero is invalid blob_mem */
+	__u32 blob_mem;
+	__u32 blob_flags;
+	__u32 bo_handle;
+	__u32 res_handle;
+	__u64 size;
+
+	/*
+	 * for 3D contexts with VIRTGPU_BLOB_MEM_HOST3D_GUEST and
+	 * VIRTGPU_BLOB_MEM_HOST3D otherwise, must be zero.
+	 */
+	__u32 pad;
+	__u32 cmd_size;
+	__u64 cmd;
+	__u64 blob_id;
+
+#define DRM_VIRTGPU_BLOB_FLAG_HINT_DEFER_MAPPING        0x0001
+	__u32 blob_hints;
+	__u32 pad2;
+};
+
+#define VIRTGPU_CONTEXT_PARAM_CAPSET_ID       0x0001
+#define VIRTGPU_CONTEXT_PARAM_NUM_RINGS       0x0002
+#define VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK 0x0003
+#define VIRTGPU_CONTEXT_PARAM_DEBUG_NAME      0x0004
+struct drm_virtgpu_context_set_param {
+	__u64 param;
+	__u64 value;
+};
+
+struct drm_virtgpu_context_init {
+	__u32 num_params;
+	__u32 pad;
+
+	/* pointer to drm_virtgpu_context_set_param array */
+	__u64 ctx_set_params;
+};
+
+/*
+ * Event code that's given when VIRTGPU_CONTEXT_PARAM_POLL_RINGS_MASK is in
+ * effect.  The event size is sizeof(drm_event), since there is no additional
+ * payload.
+ */
+#define VIRTGPU_EVENT_FENCE_SIGNALED 0x90000000
+
+#define DRM_IOCTL_VIRTGPU_MAP \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_MAP, struct drm_virtgpu_map)
+
+#define DRM_IOCTL_VIRTGPU_EXECBUFFER \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_EXECBUFFER,\
+		struct drm_virtgpu_execbuffer)
+
+#define DRM_IOCTL_VIRTGPU_GETPARAM \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_GETPARAM,\
+		struct drm_virtgpu_getparam)
+
+#define DRM_IOCTL_VIRTGPU_RESOURCE_CREATE			\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_CREATE,	\
+		struct drm_virtgpu_resource_create)
+
+#define DRM_IOCTL_VIRTGPU_RESOURCE_INFO \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_INFO, \
+		 struct drm_virtgpu_resource_info)
+
+#define DRM_IOCTL_VIRTGPU_TRANSFER_FROM_HOST \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_TRANSFER_FROM_HOST,	\
+		struct drm_virtgpu_3d_transfer_from_host)
+
+#define DRM_IOCTL_VIRTGPU_TRANSFER_TO_HOST \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_TRANSFER_TO_HOST,	\
+		struct drm_virtgpu_3d_transfer_to_host)
+
+#define DRM_IOCTL_VIRTGPU_WAIT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_WAIT,	\
+		struct drm_virtgpu_3d_wait)
+
+#define DRM_IOCTL_VIRTGPU_GET_CAPS \
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_GET_CAPS, \
+	struct drm_virtgpu_get_caps)
+
+#define DRM_IOCTL_VIRTGPU_RESOURCE_CREATE_BLOB				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_RESOURCE_CREATE_BLOB,	\
+		struct drm_virtgpu_resource_create_blob)
+
+#define DRM_IOCTL_VIRTGPU_CONTEXT_INIT					\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VIRTGPU_CONTEXT_INIT,		\
+		struct drm_virtgpu_context_init)
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
new file mode 100644
index 000000000..7d786a0cc
--- /dev/null
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -0,0 +1,1294 @@
+/* SPDX-License-Identifier: (GPL-2.0 WITH Linux-syscall-note) OR MIT */
+/**************************************************************************
+ *
+ * Copyright © 2009-2023 VMware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#ifndef __VMWGFX_DRM_H__
+#define __VMWGFX_DRM_H__
+
+#include "drm.h"
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+#define DRM_VMW_MAX_SURFACE_FACES 6
+#define DRM_VMW_MAX_MIP_LEVELS 24
+
+
+#define DRM_VMW_GET_PARAM            0
+#define DRM_VMW_ALLOC_DMABUF         1
+#define DRM_VMW_ALLOC_BO             1
+#define DRM_VMW_UNREF_DMABUF         2
+#define DRM_VMW_HANDLE_CLOSE         2
+#define DRM_VMW_CURSOR_BYPASS        3
+/* guarded by DRM_VMW_PARAM_NUM_STREAMS != 0*/
+#define DRM_VMW_CONTROL_STREAM       4
+#define DRM_VMW_CLAIM_STREAM         5
+#define DRM_VMW_UNREF_STREAM         6
+/* guarded by DRM_VMW_PARAM_3D == 1 */
+#define DRM_VMW_CREATE_CONTEXT       7
+#define DRM_VMW_UNREF_CONTEXT        8
+#define DRM_VMW_CREATE_SURFACE       9
+#define DRM_VMW_UNREF_SURFACE        10
+#define DRM_VMW_REF_SURFACE          11
+#define DRM_VMW_EXECBUF              12
+#define DRM_VMW_GET_3D_CAP           13
+#define DRM_VMW_FENCE_WAIT           14
+#define DRM_VMW_FENCE_SIGNALED       15
+#define DRM_VMW_FENCE_UNREF          16
+#define DRM_VMW_FENCE_EVENT          17
+#define DRM_VMW_PRESENT              18
+#define DRM_VMW_PRESENT_READBACK     19
+#define DRM_VMW_UPDATE_LAYOUT        20
+#define DRM_VMW_CREATE_SHADER        21
+#define DRM_VMW_UNREF_SHADER         22
+#define DRM_VMW_GB_SURFACE_CREATE    23
+#define DRM_VMW_GB_SURFACE_REF       24
+#define DRM_VMW_SYNCCPU              25
+#define DRM_VMW_CREATE_EXTENDED_CONTEXT 26
+#define DRM_VMW_GB_SURFACE_CREATE_EXT   27
+#define DRM_VMW_GB_SURFACE_REF_EXT      28
+#define DRM_VMW_MSG                     29
+#define DRM_VMW_MKSSTAT_RESET           30
+#define DRM_VMW_MKSSTAT_ADD             31
+#define DRM_VMW_MKSSTAT_REMOVE          32
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GET_PARAM - get device information.
+ *
+ * DRM_VMW_PARAM_FIFO_OFFSET:
+ * Offset to use to map the first page of the FIFO read-only.
+ * The fifo is mapped using the mmap() system call on the drm device.
+ *
+ * DRM_VMW_PARAM_OVERLAY_IOCTL:
+ * Does the driver support the overlay ioctl.
+ *
+ * DRM_VMW_PARAM_SM4_1
+ * SM4_1 support is enabled.
+ *
+ * DRM_VMW_PARAM_SM5
+ * SM5 support is enabled.
+ *
+ * DRM_VMW_PARAM_GL43
+ * SM5.1+GL4.3 support is enabled.
+ *
+ * DRM_VMW_PARAM_DEVICE_ID
+ * PCI ID of the underlying SVGA device.
+ */
+
+#define DRM_VMW_PARAM_NUM_STREAMS      0
+#define DRM_VMW_PARAM_NUM_FREE_STREAMS 1
+#define DRM_VMW_PARAM_3D               2
+#define DRM_VMW_PARAM_HW_CAPS          3
+#define DRM_VMW_PARAM_FIFO_CAPS        4
+#define DRM_VMW_PARAM_MAX_FB_SIZE      5
+#define DRM_VMW_PARAM_FIFO_HW_VERSION  6
+#define DRM_VMW_PARAM_MAX_SURF_MEMORY  7
+#define DRM_VMW_PARAM_3D_CAPS_SIZE     8
+#define DRM_VMW_PARAM_MAX_MOB_MEMORY   9
+#define DRM_VMW_PARAM_MAX_MOB_SIZE     10
+#define DRM_VMW_PARAM_SCREEN_TARGET    11
+#define DRM_VMW_PARAM_DX               12
+#define DRM_VMW_PARAM_HW_CAPS2         13
+#define DRM_VMW_PARAM_SM4_1            14
+#define DRM_VMW_PARAM_SM5              15
+#define DRM_VMW_PARAM_GL43             16
+#define DRM_VMW_PARAM_DEVICE_ID        17
+
+/**
+ * enum drm_vmw_handle_type - handle type for ref ioctls
+ *
+ */
+enum drm_vmw_handle_type {
+	DRM_VMW_HANDLE_LEGACY = 0,
+	DRM_VMW_HANDLE_PRIME = 1
+};
+
+/**
+ * struct drm_vmw_getparam_arg
+ *
+ * @value: Returned value. //Out
+ * @param: Parameter to query. //In.
+ *
+ * Argument to the DRM_VMW_GET_PARAM Ioctl.
+ */
+
+struct drm_vmw_getparam_arg {
+	__u64 value;
+	__u32 param;
+	__u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CREATE_CONTEXT - Create a host context.
+ *
+ * Allocates a device unique context id, and queues a create context command
+ * for the host. Does not wait for host completion.
+ */
+
+/**
+ * struct drm_vmw_context_arg
+ *
+ * @cid: Device unique context ID.
+ *
+ * Output argument to the DRM_VMW_CREATE_CONTEXT Ioctl.
+ * Input argument to the DRM_VMW_UNREF_CONTEXT Ioctl.
+ */
+
+struct drm_vmw_context_arg {
+	__s32 cid;
+	__u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_UNREF_CONTEXT - Create a host context.
+ *
+ * Frees a global context id, and queues a destroy host command for the host.
+ * Does not wait for host completion. The context ID can be used directly
+ * in the command stream and shows up as the same context ID on the host.
+ */
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CREATE_SURFACE - Create a host suface.
+ *
+ * Allocates a device unique surface id, and queues a create surface command
+ * for the host. Does not wait for host completion. The surface ID can be
+ * used directly in the command stream and shows up as the same surface
+ * ID on the host.
+ */
+
+/**
+ * struct drm_wmv_surface_create_req
+ *
+ * @flags: Surface flags as understood by the host.
+ * @format: Surface format as understood by the host.
+ * @mip_levels: Number of mip levels for each face.
+ * An unused face should have 0 encoded.
+ * @size_addr: Address of a user-space array of sruct drm_vmw_size
+ * cast to an __u64 for 32-64 bit compatibility.
+ * The size of the array should equal the total number of mipmap levels.
+ * @shareable: Boolean whether other clients (as identified by file descriptors)
+ * may reference this surface.
+ * @scanout: Boolean whether the surface is intended to be used as a
+ * scanout.
+ *
+ * Input data to the DRM_VMW_CREATE_SURFACE Ioctl.
+ * Output data from the DRM_VMW_REF_SURFACE Ioctl.
+ */
+
+struct drm_vmw_surface_create_req {
+	__u32 flags;
+	__u32 format;
+	__u32 mip_levels[DRM_VMW_MAX_SURFACE_FACES];
+	__u64 size_addr;
+	__s32 shareable;
+	__s32 scanout;
+};
+
+/**
+ * struct drm_wmv_surface_arg
+ *
+ * @sid: Surface id of created surface or surface to destroy or reference.
+ * @handle_type: Handle type for DRM_VMW_REF_SURFACE Ioctl.
+ *
+ * Output data from the DRM_VMW_CREATE_SURFACE Ioctl.
+ * Input argument to the DRM_VMW_UNREF_SURFACE Ioctl.
+ * Input argument to the DRM_VMW_REF_SURFACE Ioctl.
+ */
+
+struct drm_vmw_surface_arg {
+	__s32 sid;
+	enum drm_vmw_handle_type handle_type;
+};
+
+/**
+ * struct drm_vmw_size ioctl.
+ *
+ * @width - mip level width
+ * @height - mip level height
+ * @depth - mip level depth
+ *
+ * Description of a mip level.
+ * Input data to the DRM_WMW_CREATE_SURFACE Ioctl.
+ */
+
+struct drm_vmw_size {
+	__u32 width;
+	__u32 height;
+	__u32 depth;
+	__u32 pad64;
+};
+
+/**
+ * union drm_vmw_surface_create_arg
+ *
+ * @rep: Output data as described above.
+ * @req: Input data as described above.
+ *
+ * Argument to the DRM_VMW_CREATE_SURFACE Ioctl.
+ */
+
+union drm_vmw_surface_create_arg {
+	struct drm_vmw_surface_arg rep;
+	struct drm_vmw_surface_create_req req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_REF_SURFACE - Reference a host surface.
+ *
+ * Puts a reference on a host surface with a give sid, as previously
+ * returned by the DRM_VMW_CREATE_SURFACE ioctl.
+ * A reference will make sure the surface isn't destroyed while we hold
+ * it and will allow the calling client to use the surface ID in the command
+ * stream.
+ *
+ * On successful return, the Ioctl returns the surface information given
+ * in the DRM_VMW_CREATE_SURFACE ioctl.
+ */
+
+/**
+ * union drm_vmw_surface_reference_arg
+ *
+ * @rep: Output data as described above.
+ * @req: Input data as described above.
+ *
+ * Argument to the DRM_VMW_REF_SURFACE Ioctl.
+ */
+
+union drm_vmw_surface_reference_arg {
+	struct drm_vmw_surface_create_req rep;
+	struct drm_vmw_surface_arg req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_UNREF_SURFACE - Unreference a host surface.
+ *
+ * Clear a reference previously put on a host surface.
+ * When all references are gone, including the one implicitly placed
+ * on creation,
+ * a destroy surface command will be queued for the host.
+ * Does not wait for completion.
+ */
+
+/*************************************************************************/
+/**
+ * DRM_VMW_EXECBUF
+ *
+ * Submit a command buffer for execution on the host, and return a
+ * fence seqno that when signaled, indicates that the command buffer has
+ * executed.
+ */
+
+/**
+ * struct drm_vmw_execbuf_arg
+ *
+ * @commands: User-space address of a command buffer cast to an __u64.
+ * @command-size: Size in bytes of the command buffer.
+ * @throttle-us: Sleep until software is less than @throttle_us
+ * microseconds ahead of hardware. The driver may round this value
+ * to the nearest kernel tick.
+ * @fence_rep: User-space address of a struct drm_vmw_fence_rep cast to an
+ * __u64.
+ * @version: Allows expanding the execbuf ioctl parameters without breaking
+ * backwards compatibility, since user-space will always tell the kernel
+ * which version it uses.
+ * @flags: Execbuf flags.
+ * @imported_fence_fd:  FD for a fence imported from another device
+ *
+ * Argument to the DRM_VMW_EXECBUF Ioctl.
+ */
+
+#define DRM_VMW_EXECBUF_VERSION 2
+
+#define DRM_VMW_EXECBUF_FLAG_IMPORT_FENCE_FD (1 << 0)
+#define DRM_VMW_EXECBUF_FLAG_EXPORT_FENCE_FD (1 << 1)
+
+struct drm_vmw_execbuf_arg {
+	__u64 commands;
+	__u32 command_size;
+	__u32 throttle_us;
+	__u64 fence_rep;
+	__u32 version;
+	__u32 flags;
+	__u32 context_handle;
+	__s32 imported_fence_fd;
+};
+
+/**
+ * struct drm_vmw_fence_rep
+ *
+ * @handle: Fence object handle for fence associated with a command submission.
+ * @mask: Fence flags relevant for this fence object.
+ * @seqno: Fence sequence number in fifo. A fence object with a lower
+ * seqno will signal the EXEC flag before a fence object with a higher
+ * seqno. This can be used by user-space to avoid kernel calls to determine
+ * whether a fence has signaled the EXEC flag. Note that @seqno will
+ * wrap at 32-bit.
+ * @passed_seqno: The highest seqno number processed by the hardware
+ * so far. This can be used to mark user-space fence objects as signaled, and
+ * to determine whether a fence seqno might be stale.
+ * @fd: FD associated with the fence, -1 if not exported
+ * @error: This member should've been set to -EFAULT on submission.
+ * The following actions should be take on completion:
+ * error == -EFAULT: Fence communication failed. The host is synchronized.
+ * Use the last fence id read from the FIFO fence register.
+ * error != 0 && error != -EFAULT:
+ * Fence submission failed. The host is synchronized. Use the fence_seq member.
+ * error == 0: All is OK, The host may not be synchronized.
+ * Use the fence_seq member.
+ *
+ * Input / Output data to the DRM_VMW_EXECBUF Ioctl.
+ */
+
+struct drm_vmw_fence_rep {
+	__u32 handle;
+	__u32 mask;
+	__u32 seqno;
+	__u32 passed_seqno;
+	__s32 fd;
+	__s32 error;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_ALLOC_BO
+ *
+ * Allocate a buffer object that is visible also to the host.
+ * NOTE: The buffer is
+ * identified by a handle and an offset, which are private to the guest, but
+ * useable in the command stream. The guest kernel may translate these
+ * and patch up the command stream accordingly. In the future, the offset may
+ * be zero at all times, or it may disappear from the interface before it is
+ * fixed.
+ *
+ * The buffer object may stay user-space mapped in the guest at all times,
+ * and is thus suitable for sub-allocation.
+ *
+ * Buffer objects are mapped using the mmap() syscall on the drm device.
+ */
+
+/**
+ * struct drm_vmw_alloc_bo_req
+ *
+ * @size: Required minimum size of the buffer.
+ *
+ * Input data to the DRM_VMW_ALLOC_BO Ioctl.
+ */
+
+struct drm_vmw_alloc_bo_req {
+	__u32 size;
+	__u32 pad64;
+};
+#define drm_vmw_alloc_dmabuf_req drm_vmw_alloc_bo_req
+
+/**
+ * struct drm_vmw_bo_rep
+ *
+ * @map_handle: Offset to use in the mmap() call used to map the buffer.
+ * @handle: Handle unique to this buffer. Used for unreferencing.
+ * @cur_gmr_id: GMR id to use in the command stream when this buffer is
+ * referenced. See not above.
+ * @cur_gmr_offset: Offset to use in the command stream when this buffer is
+ * referenced. See note above.
+ *
+ * Output data from the DRM_VMW_ALLOC_BO Ioctl.
+ */
+
+struct drm_vmw_bo_rep {
+	__u64 map_handle;
+	__u32 handle;
+	__u32 cur_gmr_id;
+	__u32 cur_gmr_offset;
+	__u32 pad64;
+};
+#define drm_vmw_dmabuf_rep drm_vmw_bo_rep
+
+/**
+ * union drm_vmw_alloc_bo_arg
+ *
+ * @req: Input data as described above.
+ * @rep: Output data as described above.
+ *
+ * Argument to the DRM_VMW_ALLOC_BO Ioctl.
+ */
+
+union drm_vmw_alloc_bo_arg {
+	struct drm_vmw_alloc_bo_req req;
+	struct drm_vmw_bo_rep rep;
+};
+#define drm_vmw_alloc_dmabuf_arg drm_vmw_alloc_bo_arg
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CONTROL_STREAM - Control overlays, aka streams.
+ *
+ * This IOCTL controls the overlay units of the svga device.
+ * The SVGA overlay units does not work like regular hardware units in
+ * that they do not automaticaly read back the contents of the given dma
+ * buffer. But instead only read back for each call to this ioctl, and
+ * at any point between this call being made and a following call that
+ * either changes the buffer or disables the stream.
+ */
+
+/**
+ * struct drm_vmw_rect
+ *
+ * Defines a rectangle. Used in the overlay ioctl to define
+ * source and destination rectangle.
+ */
+
+struct drm_vmw_rect {
+	__s32 x;
+	__s32 y;
+	__u32 w;
+	__u32 h;
+};
+
+/**
+ * struct drm_vmw_control_stream_arg
+ *
+ * @stream_id: Stearm to control
+ * @enabled: If false all following arguments are ignored.
+ * @handle: Handle to buffer for getting data from.
+ * @format: Format of the overlay as understood by the host.
+ * @width: Width of the overlay.
+ * @height: Height of the overlay.
+ * @size: Size of the overlay in bytes.
+ * @pitch: Array of pitches, the two last are only used for YUV12 formats.
+ * @offset: Offset from start of dma buffer to overlay.
+ * @src: Source rect, must be within the defined area above.
+ * @dst: Destination rect, x and y may be negative.
+ *
+ * Argument to the DRM_VMW_CONTROL_STREAM Ioctl.
+ */
+
+struct drm_vmw_control_stream_arg {
+	__u32 stream_id;
+	__u32 enabled;
+
+	__u32 flags;
+	__u32 color_key;
+
+	__u32 handle;
+	__u32 offset;
+	__s32 format;
+	__u32 size;
+	__u32 width;
+	__u32 height;
+	__u32 pitch[3];
+
+	__u32 pad64;
+	struct drm_vmw_rect src;
+	struct drm_vmw_rect dst;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CURSOR_BYPASS - Give extra information about cursor bypass.
+ *
+ */
+
+#define DRM_VMW_CURSOR_BYPASS_ALL    (1 << 0)
+#define DRM_VMW_CURSOR_BYPASS_FLAGS       (1)
+
+/**
+ * struct drm_vmw_cursor_bypass_arg
+ *
+ * @flags: Flags.
+ * @crtc_id: Crtc id, only used if DMR_CURSOR_BYPASS_ALL isn't passed.
+ * @xpos: X position of cursor.
+ * @ypos: Y position of cursor.
+ * @xhot: X hotspot.
+ * @yhot: Y hotspot.
+ *
+ * Argument to the DRM_VMW_CURSOR_BYPASS Ioctl.
+ */
+
+struct drm_vmw_cursor_bypass_arg {
+	__u32 flags;
+	__u32 crtc_id;
+	__s32 xpos;
+	__s32 ypos;
+	__s32 xhot;
+	__s32 yhot;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CLAIM_STREAM - Claim a single stream.
+ */
+
+/**
+ * struct drm_vmw_context_arg
+ *
+ * @stream_id: Device unique context ID.
+ *
+ * Output argument to the DRM_VMW_CREATE_CONTEXT Ioctl.
+ * Input argument to the DRM_VMW_UNREF_CONTEXT Ioctl.
+ */
+
+struct drm_vmw_stream_arg {
+	__u32 stream_id;
+	__u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_UNREF_STREAM - Unclaim a stream.
+ *
+ * Return a single stream that was claimed by this process. Also makes
+ * sure that the stream has been stopped.
+ */
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GET_3D_CAP
+ *
+ * Read 3D capabilities from the FIFO
+ *
+ */
+
+/**
+ * struct drm_vmw_get_3d_cap_arg
+ *
+ * @buffer: Pointer to a buffer for capability data, cast to an __u64
+ * @size: Max size to copy
+ *
+ * Input argument to the DRM_VMW_GET_3D_CAP_IOCTL
+ * ioctls.
+ */
+
+struct drm_vmw_get_3d_cap_arg {
+	__u64 buffer;
+	__u32 max_size;
+	__u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_FENCE_WAIT
+ *
+ * Waits for a fence object to signal. The wait is interruptible, so that
+ * signals may be delivered during the interrupt. The wait may timeout,
+ * in which case the calls returns -EBUSY. If the wait is restarted,
+ * that is restarting without resetting @cookie_valid to zero,
+ * the timeout is computed from the first call.
+ *
+ * The flags argument to the DRM_VMW_FENCE_WAIT ioctl indicates what to wait
+ * on:
+ * DRM_VMW_FENCE_FLAG_EXEC: All commands ahead of the fence in the command
+ * stream
+ * have executed.
+ * DRM_VMW_FENCE_FLAG_QUERY: All query results resulting from query finish
+ * commands
+ * in the buffer given to the EXECBUF ioctl returning the fence object handle
+ * are available to user-space.
+ *
+ * DRM_VMW_WAIT_OPTION_UNREF: If this wait option is given, and the
+ * fenc wait ioctl returns 0, the fence object has been unreferenced after
+ * the wait.
+ */
+
+#define DRM_VMW_FENCE_FLAG_EXEC   (1 << 0)
+#define DRM_VMW_FENCE_FLAG_QUERY  (1 << 1)
+
+#define DRM_VMW_WAIT_OPTION_UNREF (1 << 0)
+
+/**
+ * struct drm_vmw_fence_wait_arg
+ *
+ * @handle: Fence object handle as returned by the DRM_VMW_EXECBUF ioctl.
+ * @cookie_valid: Must be reset to 0 on first call. Left alone on restart.
+ * @kernel_cookie: Set to 0 on first call. Left alone on restart.
+ * @timeout_us: Wait timeout in microseconds. 0 for indefinite timeout.
+ * @lazy: Set to 1 if timing is not critical. Allow more than a kernel tick
+ * before returning.
+ * @flags: Fence flags to wait on.
+ * @wait_options: Options that control the behaviour of the wait ioctl.
+ *
+ * Input argument to the DRM_VMW_FENCE_WAIT ioctl.
+ */
+
+struct drm_vmw_fence_wait_arg {
+	__u32 handle;
+	__s32  cookie_valid;
+	__u64 kernel_cookie;
+	__u64 timeout_us;
+	__s32 lazy;
+	__s32 flags;
+	__s32 wait_options;
+	__s32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_FENCE_SIGNALED
+ *
+ * Checks if a fence object is signaled..
+ */
+
+/**
+ * struct drm_vmw_fence_signaled_arg
+ *
+ * @handle: Fence object handle as returned by the DRM_VMW_EXECBUF ioctl.
+ * @flags: Fence object flags input to DRM_VMW_FENCE_SIGNALED ioctl
+ * @signaled: Out: Flags signaled.
+ * @sequence: Out: Highest sequence passed so far. Can be used to signal the
+ * EXEC flag of user-space fence objects.
+ *
+ * Input/Output argument to the DRM_VMW_FENCE_SIGNALED and DRM_VMW_FENCE_UNREF
+ * ioctls.
+ */
+
+struct drm_vmw_fence_signaled_arg {
+	 __u32 handle;
+	 __u32 flags;
+	 __s32 signaled;
+	 __u32 passed_seqno;
+	 __u32 signaled_flags;
+	 __u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_FENCE_UNREF
+ *
+ * Unreferences a fence object, and causes it to be destroyed if there are no
+ * other references to it.
+ *
+ */
+
+/**
+ * struct drm_vmw_fence_arg
+ *
+ * @handle: Fence object handle as returned by the DRM_VMW_EXECBUF ioctl.
+ *
+ * Input/Output argument to the DRM_VMW_FENCE_UNREF ioctl..
+ */
+
+struct drm_vmw_fence_arg {
+	 __u32 handle;
+	 __u32 pad64;
+};
+
+
+/*************************************************************************/
+/**
+ * DRM_VMW_FENCE_EVENT
+ *
+ * Queues an event on a fence to be delivered on the drm character device
+ * when the fence has signaled the DRM_VMW_FENCE_FLAG_EXEC flag.
+ * Optionally the approximate time when the fence signaled is
+ * given by the event.
+ */
+
+/*
+ * The event type
+ */
+#define DRM_VMW_EVENT_FENCE_SIGNALED 0x80000000
+
+struct drm_vmw_event_fence {
+	struct drm_event base;
+	__u64 user_data;
+	__u32 tv_sec;
+	__u32 tv_usec;
+};
+
+/*
+ * Flags that may be given to the command.
+ */
+/* Request fence signaled time on the event. */
+#define DRM_VMW_FE_FLAG_REQ_TIME (1 << 0)
+
+/**
+ * struct drm_vmw_fence_event_arg
+ *
+ * @fence_rep: Pointer to fence_rep structure cast to __u64 or 0 if
+ * the fence is not supposed to be referenced by user-space.
+ * @user_info: Info to be delivered with the event.
+ * @handle: Attach the event to this fence only.
+ * @flags: A set of flags as defined above.
+ */
+struct drm_vmw_fence_event_arg {
+	__u64 fence_rep;
+	__u64 user_data;
+	__u32 handle;
+	__u32 flags;
+};
+
+
+/*************************************************************************/
+/**
+ * DRM_VMW_PRESENT
+ *
+ * Executes an SVGA present on a given fb for a given surface. The surface
+ * is placed on the framebuffer. Cliprects are given relative to the given
+ * point (the point disignated by dest_{x|y}).
+ *
+ */
+
+/**
+ * struct drm_vmw_present_arg
+ * @fb_id: framebuffer id to present / read back from.
+ * @sid: Surface id to present from.
+ * @dest_x: X placement coordinate for surface.
+ * @dest_y: Y placement coordinate for surface.
+ * @clips_ptr: Pointer to an array of clip rects cast to an __u64.
+ * @num_clips: Number of cliprects given relative to the framebuffer origin,
+ * in the same coordinate space as the frame buffer.
+ * @pad64: Unused 64-bit padding.
+ *
+ * Input argument to the DRM_VMW_PRESENT ioctl.
+ */
+
+struct drm_vmw_present_arg {
+	__u32 fb_id;
+	__u32 sid;
+	__s32 dest_x;
+	__s32 dest_y;
+	__u64 clips_ptr;
+	__u32 num_clips;
+	__u32 pad64;
+};
+
+
+/*************************************************************************/
+/**
+ * DRM_VMW_PRESENT_READBACK
+ *
+ * Executes an SVGA present readback from a given fb to the dma buffer
+ * currently bound as the fb. If there is no dma buffer bound to the fb,
+ * an error will be returned.
+ *
+ */
+
+/**
+ * struct drm_vmw_present_arg
+ * @fb_id: fb_id to present / read back from.
+ * @num_clips: Number of cliprects.
+ * @clips_ptr: Pointer to an array of clip rects cast to an __u64.
+ * @fence_rep: Pointer to a struct drm_vmw_fence_rep, cast to an __u64.
+ * If this member is NULL, then the ioctl should not return a fence.
+ */
+
+struct drm_vmw_present_readback_arg {
+	 __u32 fb_id;
+	 __u32 num_clips;
+	 __u64 clips_ptr;
+	 __u64 fence_rep;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_UPDATE_LAYOUT - Update layout
+ *
+ * Updates the preferred modes and connection status for connectors. The
+ * command consists of one drm_vmw_update_layout_arg pointing to an array
+ * of num_outputs drm_vmw_rect's.
+ */
+
+/**
+ * struct drm_vmw_update_layout_arg
+ *
+ * @num_outputs: number of active connectors
+ * @rects: pointer to array of drm_vmw_rect cast to an __u64
+ *
+ * Input argument to the DRM_VMW_UPDATE_LAYOUT Ioctl.
+ */
+struct drm_vmw_update_layout_arg {
+	__u32 num_outputs;
+	__u32 pad64;
+	__u64 rects;
+};
+
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CREATE_SHADER - Create shader
+ *
+ * Creates a shader and optionally binds it to a dma buffer containing
+ * the shader byte-code.
+ */
+
+/**
+ * enum drm_vmw_shader_type - Shader types
+ */
+enum drm_vmw_shader_type {
+	drm_vmw_shader_type_vs = 0,
+	drm_vmw_shader_type_ps,
+};
+
+
+/**
+ * struct drm_vmw_shader_create_arg
+ *
+ * @shader_type: Shader type of the shader to create.
+ * @size: Size of the byte-code in bytes.
+ * where the shader byte-code starts
+ * @buffer_handle: Buffer handle identifying the buffer containing the
+ * shader byte-code
+ * @shader_handle: On successful completion contains a handle that
+ * can be used to subsequently identify the shader.
+ * @offset: Offset in bytes into the buffer given by @buffer_handle,
+ *
+ * Input / Output argument to the DRM_VMW_CREATE_SHADER Ioctl.
+ */
+struct drm_vmw_shader_create_arg {
+	enum drm_vmw_shader_type shader_type;
+	__u32 size;
+	__u32 buffer_handle;
+	__u32 shader_handle;
+	__u64 offset;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_UNREF_SHADER - Unreferences a shader
+ *
+ * Destroys a user-space reference to a shader, optionally destroying
+ * it.
+ */
+
+/**
+ * struct drm_vmw_shader_arg
+ *
+ * @handle: Handle identifying the shader to destroy.
+ *
+ * Input argument to the DRM_VMW_UNREF_SHADER ioctl.
+ */
+struct drm_vmw_shader_arg {
+	__u32 handle;
+	__u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_CREATE - Create a host guest-backed surface.
+ *
+ * Allocates a surface handle and queues a create surface command
+ * for the host on the first use of the surface. The surface ID can
+ * be used as the surface ID in commands referencing the surface.
+ */
+
+/**
+ * enum drm_vmw_surface_flags
+ *
+ * @drm_vmw_surface_flag_shareable:     Deprecated - all userspace surfaces are
+ *                                      shareable.
+ * @drm_vmw_surface_flag_scanout:       Whether the surface is a scanout
+ *                                      surface.
+ * @drm_vmw_surface_flag_create_buffer: Create a backup buffer if none is
+ *                                      given.
+ * @drm_vmw_surface_flag_coherent:      Back surface with coherent memory.
+ */
+enum drm_vmw_surface_flags {
+	drm_vmw_surface_flag_shareable = (1 << 0),
+	drm_vmw_surface_flag_scanout = (1 << 1),
+	drm_vmw_surface_flag_create_buffer = (1 << 2),
+	drm_vmw_surface_flag_coherent = (1 << 3),
+};
+
+/**
+ * struct drm_vmw_gb_surface_create_req
+ *
+ * @svga3d_flags:     SVGA3d surface flags for the device.
+ * @format:           SVGA3d format.
+ * @mip_level:        Number of mip levels for all faces.
+ * @drm_surface_flags Flags as described above.
+ * @multisample_count Future use. Set to 0.
+ * @autogen_filter    Future use. Set to 0.
+ * @buffer_handle     Buffer handle of backup buffer. SVGA3D_INVALID_ID
+ *                    if none.
+ * @base_size         Size of the base mip level for all faces.
+ * @array_size        Must be zero for non-DX hardware, and if non-zero
+ *                    svga3d_flags must have proper bind flags setup.
+ *
+ * Input argument to the  DRM_VMW_GB_SURFACE_CREATE Ioctl.
+ * Part of output argument for the DRM_VMW_GB_SURFACE_REF Ioctl.
+ */
+struct drm_vmw_gb_surface_create_req {
+	__u32 svga3d_flags;
+	__u32 format;
+	__u32 mip_levels;
+	enum drm_vmw_surface_flags drm_surface_flags;
+	__u32 multisample_count;
+	__u32 autogen_filter;
+	__u32 buffer_handle;
+	__u32 array_size;
+	struct drm_vmw_size base_size;
+};
+
+/**
+ * struct drm_vmw_gb_surface_create_rep
+ *
+ * @handle:            Surface handle.
+ * @backup_size:       Size of backup buffers for this surface.
+ * @buffer_handle:     Handle of backup buffer. SVGA3D_INVALID_ID if none.
+ * @buffer_size:       Actual size of the buffer identified by
+ *                     @buffer_handle
+ * @buffer_map_handle: Offset into device address space for the buffer
+ *                     identified by @buffer_handle.
+ *
+ * Part of output argument for the DRM_VMW_GB_SURFACE_REF ioctl.
+ * Output argument for the DRM_VMW_GB_SURFACE_CREATE ioctl.
+ */
+struct drm_vmw_gb_surface_create_rep {
+	__u32 handle;
+	__u32 backup_size;
+	__u32 buffer_handle;
+	__u32 buffer_size;
+	__u64 buffer_map_handle;
+};
+
+/**
+ * union drm_vmw_gb_surface_create_arg
+ *
+ * @req: Input argument as described above.
+ * @rep: Output argument as described above.
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_CREATE ioctl.
+ */
+union drm_vmw_gb_surface_create_arg {
+	struct drm_vmw_gb_surface_create_rep rep;
+	struct drm_vmw_gb_surface_create_req req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_REF - Reference a host surface.
+ *
+ * Puts a reference on a host surface with a given handle, as previously
+ * returned by the DRM_VMW_GB_SURFACE_CREATE ioctl.
+ * A reference will make sure the surface isn't destroyed while we hold
+ * it and will allow the calling client to use the surface handle in
+ * the command stream.
+ *
+ * On successful return, the Ioctl returns the surface information given
+ * to and returned from the DRM_VMW_GB_SURFACE_CREATE ioctl.
+ */
+
+/**
+ * struct drm_vmw_gb_surface_reference_arg
+ *
+ * @creq: The data used as input when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_req"
+ * @crep: Additional data output when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_rep"
+ *
+ * Output Argument to the DRM_VMW_GB_SURFACE_REF ioctl.
+ */
+struct drm_vmw_gb_surface_ref_rep {
+	struct drm_vmw_gb_surface_create_req creq;
+	struct drm_vmw_gb_surface_create_rep crep;
+};
+
+/**
+ * union drm_vmw_gb_surface_reference_arg
+ *
+ * @req: Input data as described above at "struct drm_vmw_surface_arg"
+ * @rep: Output data as described above at "struct drm_vmw_gb_surface_ref_rep"
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_REF Ioctl.
+ */
+union drm_vmw_gb_surface_reference_arg {
+	struct drm_vmw_gb_surface_ref_rep rep;
+	struct drm_vmw_surface_arg req;
+};
+
+
+/*************************************************************************/
+/**
+ * DRM_VMW_SYNCCPU - Sync a DMA buffer / MOB for CPU access.
+ *
+ * Idles any previously submitted GPU operations on the buffer and
+ * by default blocks command submissions that reference the buffer.
+ * If the file descriptor used to grab a blocking CPU sync is closed, the
+ * cpu sync is released.
+ * The flags argument indicates how the grab / release operation should be
+ * performed:
+ */
+
+/**
+ * enum drm_vmw_synccpu_flags - Synccpu flags:
+ *
+ * @drm_vmw_synccpu_read: Sync for read. If sync is done for read only, it's a
+ * hint to the kernel to allow command submissions that references the buffer
+ * for read-only.
+ * @drm_vmw_synccpu_write: Sync for write. Block all command submissions
+ * referencing this buffer.
+ * @drm_vmw_synccpu_dontblock: Dont wait for GPU idle, but rather return
+ * -EBUSY should the buffer be busy.
+ * @drm_vmw_synccpu_allow_cs: Allow command submission that touches the buffer
+ * while the buffer is synced for CPU. This is similar to the GEM bo idle
+ * behavior.
+ */
+enum drm_vmw_synccpu_flags {
+	drm_vmw_synccpu_read = (1 << 0),
+	drm_vmw_synccpu_write = (1 << 1),
+	drm_vmw_synccpu_dontblock = (1 << 2),
+	drm_vmw_synccpu_allow_cs = (1 << 3)
+};
+
+/**
+ * enum drm_vmw_synccpu_op - Synccpu operations:
+ *
+ * @drm_vmw_synccpu_grab:    Grab the buffer for CPU operations
+ * @drm_vmw_synccpu_release: Release a previous grab.
+ */
+enum drm_vmw_synccpu_op {
+	drm_vmw_synccpu_grab,
+	drm_vmw_synccpu_release
+};
+
+/**
+ * struct drm_vmw_synccpu_arg
+ *
+ * @op:			     The synccpu operation as described above.
+ * @handle:		     Handle identifying the buffer object.
+ * @flags:		     Flags as described above.
+ */
+struct drm_vmw_synccpu_arg {
+	enum drm_vmw_synccpu_op op;
+	enum drm_vmw_synccpu_flags flags;
+	__u32 handle;
+	__u32 pad64;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_CREATE_EXTENDED_CONTEXT - Create a host context.
+ *
+ * Allocates a device unique context id, and queues a create context command
+ * for the host. Does not wait for host completion.
+ */
+enum drm_vmw_extended_context {
+	drm_vmw_context_legacy,
+	drm_vmw_context_dx
+};
+
+/**
+ * union drm_vmw_extended_context_arg
+ *
+ * @req: Context type.
+ * @rep: Context identifier.
+ *
+ * Argument to the DRM_VMW_CREATE_EXTENDED_CONTEXT Ioctl.
+ */
+union drm_vmw_extended_context_arg {
+	enum drm_vmw_extended_context req;
+	struct drm_vmw_context_arg rep;
+};
+
+/*************************************************************************/
+/*
+ * DRM_VMW_HANDLE_CLOSE - Close a user-space handle and release its
+ * underlying resource.
+ *
+ * Note that this ioctl is overlaid on the deprecated DRM_VMW_UNREF_DMABUF
+ * Ioctl.
+ */
+
+/**
+ * struct drm_vmw_handle_close_arg
+ *
+ * @handle: Handle to close.
+ *
+ * Argument to the DRM_VMW_HANDLE_CLOSE Ioctl.
+ */
+struct drm_vmw_handle_close_arg {
+	__u32 handle;
+	__u32 pad64;
+};
+#define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_CREATE_EXT - Create a host guest-backed surface.
+ *
+ * Allocates a surface handle and queues a create surface command
+ * for the host on the first use of the surface. The surface ID can
+ * be used as the surface ID in commands referencing the surface.
+ *
+ * This new command extends DRM_VMW_GB_SURFACE_CREATE by adding version
+ * parameter and 64 bit svga flag.
+ */
+
+/**
+ * enum drm_vmw_surface_version
+ *
+ * @drm_vmw_surface_gb_v1: Corresponds to current gb surface format with
+ * svga3d surface flags split into 2, upper half and lower half.
+ */
+enum drm_vmw_surface_version {
+	drm_vmw_gb_surface_v1,
+};
+
+/**
+ * struct drm_vmw_gb_surface_create_ext_req
+ *
+ * @base: Surface create parameters.
+ * @version: Version of surface create ioctl.
+ * @svga3d_flags_upper_32_bits: Upper 32 bits of svga3d flags.
+ * @multisample_pattern: Multisampling pattern when msaa is supported.
+ * @quality_level: Precision settings for each sample.
+ * @buffer_byte_stride: Buffer byte stride.
+ * @must_be_zero: Reserved for future usage.
+ *
+ * Input argument to the  DRM_VMW_GB_SURFACE_CREATE_EXT Ioctl.
+ * Part of output argument for the DRM_VMW_GB_SURFACE_REF_EXT Ioctl.
+ */
+struct drm_vmw_gb_surface_create_ext_req {
+	struct drm_vmw_gb_surface_create_req base;
+	enum drm_vmw_surface_version version;
+	__u32 svga3d_flags_upper_32_bits;
+	__u32 multisample_pattern;
+	__u32 quality_level;
+	__u32 buffer_byte_stride;
+	__u32 must_be_zero;
+};
+
+/**
+ * union drm_vmw_gb_surface_create_ext_arg
+ *
+ * @req: Input argument as described above.
+ * @rep: Output argument as described above.
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
+union drm_vmw_gb_surface_create_ext_arg {
+	struct drm_vmw_gb_surface_create_rep rep;
+	struct drm_vmw_gb_surface_create_ext_req req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_REF_EXT - Reference a host surface.
+ *
+ * Puts a reference on a host surface with a given handle, as previously
+ * returned by the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ * A reference will make sure the surface isn't destroyed while we hold
+ * it and will allow the calling client to use the surface handle in
+ * the command stream.
+ *
+ * On successful return, the Ioctl returns the surface information given
+ * to and returned from the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
+
+/**
+ * struct drm_vmw_gb_surface_ref_ext_rep
+ *
+ * @creq: The data used as input when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_ext_req"
+ * @crep: Additional data output when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_rep"
+ *
+ * Output Argument to the DRM_VMW_GB_SURFACE_REF_EXT ioctl.
+ */
+struct drm_vmw_gb_surface_ref_ext_rep {
+	struct drm_vmw_gb_surface_create_ext_req creq;
+	struct drm_vmw_gb_surface_create_rep crep;
+};
+
+/**
+ * union drm_vmw_gb_surface_reference_ext_arg
+ *
+ * @req: Input data as described above at "struct drm_vmw_surface_arg"
+ * @rep: Output data as described above at
+ *       "struct drm_vmw_gb_surface_ref_ext_rep"
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_REF Ioctl.
+ */
+union drm_vmw_gb_surface_reference_ext_arg {
+	struct drm_vmw_gb_surface_ref_ext_rep rep;
+	struct drm_vmw_surface_arg req;
+};
+
+/**
+ * struct drm_vmw_msg_arg
+ *
+ * @send: Pointer to user-space msg string (null terminated).
+ * @receive: Pointer to user-space receive buffer.
+ * @send_only: Boolean whether this is only sending or receiving too.
+ *
+ * Argument to the DRM_VMW_MSG ioctl.
+ */
+struct drm_vmw_msg_arg {
+	__u64 send;
+	__u64 receive;
+	__s32 send_only;
+	__u32 receive_len;
+};
+
+/**
+ * struct drm_vmw_mksstat_add_arg
+ *
+ * @stat: Pointer to user-space stat-counters array, page-aligned.
+ * @info: Pointer to user-space counter-infos array, page-aligned.
+ * @strs: Pointer to user-space stat strings, page-aligned.
+ * @stat_len: Length in bytes of stat-counters array.
+ * @info_len: Length in bytes of counter-infos array.
+ * @strs_len: Length in bytes of the stat strings, terminators included.
+ * @description: Pointer to instance descriptor string; will be truncated
+ *               to MKS_GUEST_STAT_INSTANCE_DESC_LENGTH chars.
+ * @id: Output identifier of the produced record; -1 if error.
+ *
+ * Argument to the DRM_VMW_MKSSTAT_ADD ioctl.
+ */
+struct drm_vmw_mksstat_add_arg {
+	__u64 stat;
+	__u64 info;
+	__u64 strs;
+	__u64 stat_len;
+	__u64 info_len;
+	__u64 strs_len;
+	__u64 description;
+	__u64 id;
+};
+
+/**
+ * struct drm_vmw_mksstat_remove_arg
+ *
+ * @id: Identifier of the record being disposed, originally obtained through
+ *      DRM_VMW_MKSSTAT_ADD ioctl.
+ *
+ * Argument to the DRM_VMW_MKSSTAT_REMOVE ioctl.
+ */
+struct drm_vmw_mksstat_remove_arg {
+	__u64 id;
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
new file mode 100644
index 000000000..509202a7b
--- /dev/null
+++ b/include/uapi/drm/xe_drm.h
@@ -0,0 +1,2625 @@
+/* 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
+ *  - &DRM_IOCTL_XE_OBSERVATION
+ *  - &DRM_IOCTL_XE_MADVISE
+ *  - &DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS
+ *  - &DRM_IOCTL_XE_EXEC_QUEUE_SET_PROPERTY
+ *  - &DRM_IOCTL_XE_VM_GET_PROPERTY
+ */
+
+/*
+ * 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
+#define DRM_XE_OBSERVATION		0x0b
+#define DRM_XE_MADVISE			0x0c
+#define DRM_XE_VM_QUERY_MEM_RANGE_ATTRS	0x0d
+#define DRM_XE_EXEC_QUEUE_SET_PROPERTY	0x0e
+#define DRM_XE_VM_GET_PROPERTY		0x0f
+
+/* 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)
+#define DRM_IOCTL_XE_OBSERVATION		DRM_IOW(DRM_COMMAND_BASE + DRM_XE_OBSERVATION, struct drm_xe_observation_param)
+#define DRM_IOCTL_XE_MADVISE			DRM_IOW(DRM_COMMAND_BASE + DRM_XE_MADVISE, struct drm_xe_madvise)
+#define DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS	DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_QUERY_MEM_RANGE_ATTRS, struct drm_xe_vm_query_mem_range_attr)
+#define DRM_IOCTL_XE_EXEC_QUEUE_SET_PROPERTY	DRM_IOW(DRM_COMMAND_BASE + DRM_XE_EXEC_QUEUE_SET_PROPERTY, struct drm_xe_exec_queue_set_property)
+#define DRM_IOCTL_XE_VM_GET_PROPERTY		DRM_IOWR(DRM_COMMAND_BASE + DRM_XE_VM_GET_PROPERTY, struct drm_xe_vm_get_property)
+
+/**
+ * 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;
+
+	union {
+		/** @value: property value */
+		__u64 value;
+		/** @ptr: pointer to user value */
+		__u64 ptr;
+	};
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_engine_class_instance - instance of an engine class
+ *
+ * It is returned as part of the &struct drm_xe_engine, but it also is used as
+ * the input of engine selection for both &struct drm_xe_exec_queue_create and
+ * &struct 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 &struct 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.
+	 */
+	__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 @cpu_visible_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.
+	 *
+	 * 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_FLAG_HAS_LOW_LATENCY - Flag is set if the device
+ *      has low latency hint support
+ *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR - Flag is set if the
+ *      device has CPU address mirroring support
+ *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_NO_COMPRESSION_HINT - Flag is set if the
+ *      device supports the userspace hint %DRM_XE_GEM_CREATE_FLAG_NO_COMPRESSION.
+ *      This is exposed only on Xe2+.
+ *    - %DRM_XE_QUERY_CONFIG_FLAG_HAS_DISABLE_STATE_CACHE_PERF_FIX - Flag is set
+ *      if a queue can be created with
+ *      %DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX
+ *  - %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_FLAG_HAS_LOW_LATENCY	(1 << 1)
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_CPU_ADDR_MIRROR	(1 << 2)
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_NO_COMPRESSION_HINT (1 << 3)
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_DISABLE_STATE_CACHE_PERF_FIX	(1 << 4)
+	#define DRM_XE_QUERY_CONFIG_FLAG_HAS_PURGING_SUPPORT    (1 << 5)
+#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;
+	/** @ip_ver_major: Graphics/media IP major version on GMD_ID platforms */
+	__u16 ip_ver_major;
+	/** @ip_ver_minor: Graphics/media IP minor version on GMD_ID platforms */
+	__u16 ip_ver_minor;
+	/** @ip_ver_rev: Graphics/media IP revision version on GMD_ID platforms */
+	__u16 ip_ver_rev;
+	/** @pad2: MBZ */
+	__u16 pad2;
+	/** @reserved: Reserved */
+	__u64 reserved[7];
+};
+
+/**
+ * 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_L3_BANK - To query the mask of enabled L3 banks.  This type
+ *    may be omitted if the driver is unable to query the mask from the
+ *    hardware.
+ *  - %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 SIMD8 EUs. This type may be omitted if device
+ *    doesn't have SIMD8 EUs.
+ *  - %DRM_XE_TOPO_SIMD16_EU_PER_DSS - To query the mask of SIMD16 Execution
+ *    Units (EU) available per Dual Sub Slices (DSS). For example a query
+ *    response containing the following in mask:
+ *    ``SIMD16_EU_PER_DSS    ff ff 00 00 00 00 00 00``
+ *    means each DSS has 16 SIMD16 EUs. This type may be omitted if device
+ *    doesn't have SIMD16 EUs.
+ */
+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
+#define DRM_XE_TOPO_DSS_COMPUTE		2
+#define DRM_XE_TOPO_L3_BANK		3
+#define DRM_XE_TOPO_EU_PER_DSS		4
+#define DRM_XE_TOPO_SIMD16_EU_PER_DSS	5
+	/** @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_query_uc_fw_version - query a micro-controller firmware version
+ *
+ * Given a uc_type this will return the branch, major, minor and patch version
+ * of the micro-controller firmware.
+ */
+struct drm_xe_query_uc_fw_version {
+	/** @uc_type: The micro-controller type to query firmware version */
+#define XE_QUERY_UC_TYPE_GUC_SUBMISSION 0
+#define XE_QUERY_UC_TYPE_HUC 1
+	__u16 uc_type;
+
+	/** @pad: MBZ */
+	__u16 pad;
+
+	/** @branch_ver: branch uc fw version */
+	__u32 branch_ver;
+	/** @major_ver: major uc fw version */
+	__u32 major_ver;
+	/** @minor_ver: minor uc fw version */
+	__u32 minor_ver;
+	/** @patch_ver: patch uc fw version */
+	__u32 patch_ver;
+
+	/** @pad2: MBZ */
+	__u32 pad2;
+
+	/** @reserved: Reserved */
+	__u64 reserved;
+};
+
+/**
+ * struct drm_xe_query_pxp_status - query if PXP is ready
+ *
+ * If PXP is enabled and no fatal error has occurred, the status will be set to
+ * one of the following values:
+ * 0: PXP init still in progress
+ * 1: PXP init complete
+ *
+ * If PXP is not enabled or something has gone wrong, the query will be failed
+ * with one of the following error codes:
+ * -ENODEV: PXP not supported or disabled;
+ * -EIO: fatal error occurred during init, so PXP will never be enabled;
+ * -EINVAL: incorrect value provided as part of the query;
+ * -EFAULT: error copying the memory between kernel and userspace.
+ *
+ * The status can only be 0 in the first few seconds after driver load. If
+ * everything works as expected, the status will transition to init complete in
+ * less than 1 second, while in case of errors the driver might take longer to
+ * start returning an error code, but it should still take less than 10 seconds.
+ *
+ * The supported session type bitmask is based on the values in
+ * enum drm_xe_pxp_session_type. TYPE_NONE is always supported and therefore
+ * is not reported in the bitmask.
+ *
+ */
+struct drm_xe_query_pxp_status {
+	/** @status: current PXP status */
+	__u32 status;
+
+	/** @supported_session_types: bitmask of supported PXP session types */
+	__u32 supported_session_types;
+};
+
+/**
+ * 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
+ *  - %DRM_XE_DEVICE_QUERY_UC_FW_VERSION
+ *  - %DRM_XE_DEVICE_QUERY_OA_UNITS
+ *  - %DRM_XE_DEVICE_QUERY_PXP_STATUS
+ *  - %DRM_XE_DEVICE_QUERY_EU_STALL
+ *
+ * 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
+#define DRM_XE_DEVICE_QUERY_UC_FW_VERSION	7
+#define DRM_XE_DEVICE_QUERY_OA_UNITS		8
+#define DRM_XE_DEVICE_QUERY_PXP_STATUS		9
+#define DRM_XE_DEVICE_QUERY_EU_STALL		10
+	/** @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 - Modify the GEM object
+ *    allocation strategy by deferring physical memory allocation
+ *    until the object is either bound to a virtual memory region via
+ *    VM_BIND or accessed by the CPU. As a result, no backing memory is
+ *    reserved at the time of GEM object creation.
+ *  - %DRM_XE_GEM_CREATE_FLAG_SCANOUT - Indicates that the GEM object is
+ *    intended for scanout via the display engine. When set, kernel ensures
+ *    that the allocation is placed in a memory region compatible with the
+ *    display engine requirements. This may impose restrictions on tiling,
+ *    alignment, and memory placement to guarantee proper display functionality.
+ *  - %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.
+ *  - %DRM_XE_GEM_CREATE_FLAG_NO_COMPRESSION - Allows userspace to
+ *    hint that compression (CCS) should be disabled for the buffer being
+ *    created. This can avoid unnecessary memory operations and CCS state
+ *    management.
+ *    On pre-Xe2 platforms, this flag is currently rejected as compression
+ *    control is not supported via PAT index. On Xe2+ platforms, compression
+ *    is controlled via PAT entries. If this flag is set, the driver will reject
+ *    any VM bind that requests a PAT index enabling compression for this BO.
+ *    Note: On dGPU platforms, there is currently no change in behavior with
+ *    this flag, but future improvements may leverage it. The current benefit is
+ *    primarily applicable to iGPU platforms.
+ *
+ * @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.
+ *
+ * This ioctl supports setting the following properties via the
+ * %DRM_XE_GEM_CREATE_EXTENSION_SET_PROPERTY extension, which uses the
+ * generic &struct drm_xe_ext_set_property:
+ *
+ *  - %DRM_XE_GEM_CREATE_SET_PROPERTY_PXP_TYPE - set the type of PXP session
+ *    this object will be used with. Valid values are listed in enum
+ *    drm_xe_pxp_session_type. %DRM_XE_PXP_TYPE_NONE is the default behavior, so
+ *    there is no need to explicitly set that. Objects used with session of type
+ *    %DRM_XE_PXP_TYPE_HWDRM will be marked as invalid if a PXP invalidation
+ *    event occurs after their creation. Attempting to flip an invalid object
+ *    will cause a black frame to be displayed instead. Submissions with invalid
+ *    objects mapped in the VM will be rejected.
+ */
+struct drm_xe_gem_create {
+#define DRM_XE_GEM_CREATE_EXTENSION_SET_PROPERTY	0
+#define   DRM_XE_GEM_CREATE_SET_PROPERTY_PXP_TYPE	0
+	/** @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)
+#define DRM_XE_GEM_CREATE_FLAG_NO_COMPRESSION		(1 << 3)
+	/**
+	 * @flags: Flags for the GEM object, see DRM_XE_GEM_CREATE_FLAG_*
+	 */
+	__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
+	 * mmapping the object the mode selected here will also be used. The
+	 * exception is when mapping system memory (including data evicted
+	 * to system) on discrete GPUs. The caching mode selected will
+	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
+	 * between GPU- and CPU is guaranteed. The caching mode of
+	 * existing CPU-mappings will be updated transparently to
+	 * user-space clients.
+	 */
+	__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
+ *
+ * The @flags can be:
+ *  - %DRM_XE_MMAP_OFFSET_FLAG_PCI_BARRIER - For user to query special offset
+ *    for use in mmap ioctl. Writing to the returned mmap address will generate a
+ *    PCI memory barrier with low overhead (avoiding IOCTL call as well as writing
+ *    to VRAM which would also add overhead), acting like an MI_MEM_FENCE
+ *    instruction.
+ *
+ * Note: The mmap size can be at most 4K, due to HW limitations. As a result
+ * this interface is only supported on CPU architectures that support 4K page
+ * size. The mmap_offset ioctl will detect this and gracefully return an
+ * error, where userspace is expected to have a different fallback method for
+ * triggering a barrier.
+ *
+ * Roughly the usage would be as follows:
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_gem_mmap_offset mmo = {
+ *         .handle = 0, // must be set to 0
+ *         .flags = DRM_XE_MMAP_OFFSET_FLAG_PCI_BARRIER,
+ *     };
+ *
+ *     err = ioctl(fd, DRM_IOCTL_XE_GEM_MMAP_OFFSET, &mmo);
+ *     map = mmap(NULL, size, PROT_WRITE, MAP_SHARED, fd, mmo.offset);
+ *     map[i] = 0xdeadbeef; // issue barrier
+ */
+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;
+
+#define DRM_XE_MMAP_OFFSET_FLAG_PCI_BARRIER     (1 << 0)
+	/** @flags: Flags */
+	__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 - Map the whole virtual address
+ *    space of the VM to scratch page. A vm_bind would overwrite the scratch
+ *    page mapping. This flag is mutually exclusive with the
+ *    %DRM_XE_VM_CREATE_FLAG_FAULT_MODE flag, with an exception on Xe2 and
+ *    Xe3 platforms.
+ *  - %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 sync types DRM_XE_SYNC_TYPE_SYNCOBJ,
+ *    DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ, used as out-syncobjs, that is,
+ *    together with sync flag 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.
+ *  - %DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT - Requires also
+ *    DRM_XE_VM_CREATE_FLAG_FAULT_MODE. This disallows per-VM overcommit
+ *    but only during a &DRM_IOCTL_XE_VM_BIND operation with the
+ *    %DRM_XE_VM_BIND_FLAG_IMMEDIATE flag set. This may be useful for
+ *    user-space naively probing the amount of available memory.
+ */
+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)
+#define DRM_XE_VM_CREATE_FLAG_NO_VM_OVERCOMMIT  (1 << 3)
+	/** @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 - Setup the page tables as read-only
+ *    to ensure write protection
+ *  - %DRM_XE_VM_BIND_FLAG_IMMEDIATE - On a faulting VM, do the
+ *    MAP operation immediately rather than deferring the MAP to the page
+ *    fault handler. This is implied on a non-faulting VM as there is no
+ *    fault handler to defer to.
+ *  - %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.
+ *  - %DRM_XE_VM_BIND_FLAG_CHECK_PXP - If the object is encrypted via PXP,
+ *    reject the binding if the encryption key is no longer valid. This
+ *    flag has no effect on BOs that are not marked as using PXP.
+ *  - %DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR - When the CPU address mirror flag is
+ *    set, no mappings are created rather the range is reserved for CPU address
+ *    mirroring which will be populated on GPU page faults or prefetches. Only
+ *    valid on VMs with DRM_XE_VM_CREATE_FLAG_FAULT_MODE set. The CPU address
+ *    mirror flag is only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
+ *    handle MBZ, and the BO offset MBZ.
+ *  - %DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET - Can be used in combination with
+ *    %DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR to reset madvises when the underlying
+ *    CPU address space range is unmapped (typically with munmap(2) or brk(2)).
+ *    The madvise values set with &DRM_IOCTL_XE_MADVISE are reset to the values
+ *    that were present immediately after the &DRM_IOCTL_XE_VM_BIND.
+ *    The reset GPU virtual address range is the intersection of the range bound
+ *    using &DRM_IOCTL_XE_VM_BIND and the virtual CPU address space range
+ *    unmapped.
+ *    This functionality is present to mimic the behaviour of CPU address space
+ *    madvises set using madvise(2), which are typically reset on unmap.
+ *    Note: free(3) may or may not call munmap(2) and/or brk(2), and may thus
+ *    not invoke autoreset. Neither will stack variables going out of scope.
+ *    Therefore it's recommended to always explicitly reset the madvises when
+ *    freeing the memory backing a region used in a &DRM_IOCTL_XE_MADVISE call.
+ *
+ *  - %DRM_XE_VM_BIND_FLAG_DECOMPRESS - Request on-device decompression for a MAP.
+ *    When set on a MAP bind operation, request the driver schedule an on-device
+ *    in-place decompression (via the migrate/resolve path) for the GPU mapping
+ *    created by this bind. Only valid for DRM_XE_VM_BIND_OP_MAP; usage on
+ *    other ops is rejected. The bind's pat_index must select the device's
+ *    "no-compression" PAT. Only meaningful for VRAM-backed BOs on devices that
+ *    support Flat CCS and the required HW generation XE2+.
+ *
+ * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be:
+ *  - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in
+ *    the memory region advised by madvise.
+ */
+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 be 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. Starting from NVL-P, for
+	 * userptr, svm, madvise and externally imported dma-buf the kernel expects
+	 * either 2WAY or 1WAY and XA @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). Same applies to
+	 * DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR bindings as for such mapping
+	 * there is no actual memory being mapped.
+	 */
+	__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;
+
+		/**
+		 * @cpu_addr_mirror_offset: Offset from GPU @addr to create
+		 * CPU address mirror mappings. MBZ with current level of
+		 * support (e.g. 1 to 1 mapping between GPU and CPU mappings
+		 * only supported).
+		 */
+		__s64 cpu_addr_mirror_offset;
+	};
+
+	/**
+	 * @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)
+#define DRM_XE_VM_BIND_FLAG_DUMPABLE	(1 << 3)
+#define DRM_XE_VM_BIND_FLAG_CHECK_PXP	(1 << 4)
+#define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR	(1 << 5)
+#define DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET	(1 << 6)
+#define DRM_XE_VM_BIND_FLAG_DECOMPRESS (1 << 7)
+	/** @flags: Bind flags */
+	__u32 flags;
+
+#define DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC	-1
+	/**
+	 * @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 &struct 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 &struct 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 xe_vm_fault - Describes faults for %DRM_XE_VM_GET_PROPERTY_FAULTS */
+struct xe_vm_fault {
+	/** @address: Canonical address of the fault */
+	__u64 address;
+	/** @address_precision: Precision of faulted address */
+	__u32 address_precision;
+	/** @access_type: Type of address access that resulted in fault */
+#define FAULT_ACCESS_TYPE_READ		0
+#define FAULT_ACCESS_TYPE_WRITE		1
+#define FAULT_ACCESS_TYPE_ATOMIC	2
+	__u8 access_type;
+	/** @fault_type: Type of fault reported */
+#define FAULT_TYPE_NOT_PRESENT		0
+#define FAULT_TYPE_WRITE_ACCESS		1
+#define FAULT_TYPE_ATOMIC_ACCESS	2
+	__u8 fault_type;
+	/** @fault_level: fault level of the fault */
+#define FAULT_LEVEL_PTE		0
+#define FAULT_LEVEL_PDE		1
+#define FAULT_LEVEL_PDP		2
+#define FAULT_LEVEL_PML4	3
+#define FAULT_LEVEL_PML5	4
+	__u8 fault_level;
+	/** @pad: MBZ */
+	__u8 pad;
+	/** @reserved: MBZ */
+	__u64 reserved[4];
+};
+
+/**
+ * struct drm_xe_vm_get_property - Input of &DRM_IOCTL_XE_VM_GET_PROPERTY
+ *
+ * The user provides a VM and a property to query among DRM_XE_VM_GET_PROPERTY_*,
+ * and sets the values in the vm_id and property members, respectively.  This
+ * determines both the VM to get the property of, as well as the property to
+ * report.
+ *
+ * If size is set to 0, the driver fills it with the required size for the
+ * requested property.  The user is expected here to allocate memory for the
+ * property structure and to provide a pointer to the allocated memory using the
+ * data member.  For some properties, this may be zero, in which case, the
+ * value of the property will be saved to the value member and size will remain
+ * zero on return.
+ *
+ * If size is not zero, then the IOCTL will attempt to copy the requested
+ * property into the data member.
+ *
+ * The IOCTL will return -ENOENT if the VM could not be identified from the
+ * provided VM ID, or -EINVAL if the IOCTL fails for any other reason, such as
+ * providing an invalid size for the given property or if the property data
+ * could not be copied to the memory allocated to the data member.
+ *
+ * The property member can be:
+ *  - %DRM_XE_VM_GET_PROPERTY_FAULTS
+ */
+struct drm_xe_vm_get_property {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @vm_id: The ID of the VM to query the properties of */
+	__u32 vm_id;
+
+#define DRM_XE_VM_GET_PROPERTY_FAULTS		0
+	/** @property: property to get */
+	__u32 property;
+
+	/** @size: Size to allocate for @data */
+	__u32 size;
+
+	/** @pad: MBZ */
+	__u32 pad;
+
+	union {
+		/** @data: Pointer to user-defined array of flexible size and type */
+		__u64 data;
+		/** @value: Return value for scalar queries */
+		__u64 value;
+	};
+
+	/** @reserved: MBZ */
+	__u64 reserved[3];
+};
+
+/**
+ * struct drm_xe_exec_queue_create - Input of &DRM_IOCTL_XE_EXEC_QUEUE_CREATE
+ *
+ * This ioctl supports setting the following properties via the
+ * %DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY extension, which uses the
+ * generic &struct drm_xe_ext_set_property:
+ *
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_PRIORITY - set the queue priority.
+ *    CAP_SYS_NICE is required to set a value above normal.
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_TIMESLICE - set the queue timeslice
+ *    duration in microseconds.
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_PXP_TYPE - set the type of PXP session
+ *    this queue will be used with. Valid values are listed in enum
+ *    drm_xe_pxp_session_type. %DRM_XE_PXP_TYPE_NONE is the default behavior, so
+ *    there is no need to explicitly set that. When a queue of type
+ *    %DRM_XE_PXP_TYPE_HWDRM is created, the PXP default HWDRM session
+ *    (%DRM_XE_PXP_HWDRM_DEFAULT_SESSION) will be started, if it isn't already running.
+ *    The user is expected to query the PXP status via the query ioctl (see
+ *    %DRM_XE_DEVICE_QUERY_PXP_STATUS) and to wait for PXP to be ready before
+ *    attempting to create a queue with this property. When a queue is created
+ *    before PXP is ready, the ioctl will return -EBUSY if init is still in
+ *    progress or -EIO if init failed.
+ *    Given that going into a power-saving state kills PXP HWDRM sessions,
+ *    runtime PM will be blocked while queues of this type are alive.
+ *    All PXP queues will be killed if a PXP invalidation event occurs.
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_GROUP - Create a multi-queue group
+ *    or add secondary queues to a multi-queue group.
+ *    If the extension's 'value' field has %DRM_XE_MULTI_GROUP_CREATE flag set,
+ *    then a new multi-queue group is created with this queue as the primary queue
+ *    (Q0). Otherwise, the queue gets added to the multi-queue group whose primary
+ *    queue's exec_queue_id is specified in the lower 32 bits of the 'value' field.
+ *    All the other non-relevant bits of extension's 'value' field while adding the
+ *    primary or the secondary queues of the group must be set to 0.
+ *  - %DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY - Set the queue
+ *    priority within the multi-queue group. Current valid priority values are 0–2
+ *    (default is 1), with higher values indicating higher priority.
+ *  - %DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX - Set the queue to
+ *    enable render color cache keying on BTP+BTI instead of just BTI
+ *    (only valid for render queues).
+ *
+ * The example below shows how to use &struct 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,
+ *          .width = 1,
+ *          .num_placements = 1,
+ *          .instances = to_user_pointer(&instance),
+ *     };
+ *     ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create);
+ *
+ * Allow users to provide a hint to kernel for cases demanding low latency
+ * profile. Please note it will have impact on power consumption. User can
+ * indicate low latency hint with flag while creating exec queue as
+ * mentioned below:
+ *
+ * .. code-block:: C
+ *
+ *     struct drm_xe_exec_queue_create exec_queue_create = {
+ *          .flags = DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT,
+ *          .extensions = 0,
+ *          .vm_id = vm,
+ *          .width = 1,
+ *          .num_placements = 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_PXP_TYPE		2
+#define   DRM_XE_EXEC_QUEUE_SET_HANG_REPLAY_STATE		3
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_GROUP		4
+#define     DRM_XE_MULTI_GROUP_CREATE				(1ull << 63)
+#define   DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY	5
+#define   DRM_XE_EXEC_QUEUE_SET_DISABLE_STATE_CACHE_PERF_FIX	6
+	/** @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;
+
+#define DRM_XE_EXEC_QUEUE_LOW_LATENCY_HINT	(1 << 0)
+	/** @flags: flags to use for this exec queue */
+	__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 &struct 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 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 is passed in via
+		 * VM bind IOCTL this is a user pointer. In either case, it is
+		 * the user's 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_TYPE_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 &struct drm_xe_exec for execution of the object
+ * at BIND_ADDRESS (see example in &struct drm_xe_vm_bind) by an exec_queue
+ * (see example in &struct drm_xe_exec_queue_create). It can be synchronized
+ * by using the example provided for &struct 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;
+
+#define DRM_XE_MAX_SYNCS 1024
+	/** @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
+ *
+ * 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 be 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 flag is set (absolute timeout) wait
+	 * will end at timeout (uses system CLOCK_MONOTONIC).
+	 * Passing negative timeout leads to never ending 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];
+};
+
+/**
+ * enum drm_xe_observation_type - Observation stream types
+ */
+enum drm_xe_observation_type {
+	/** @DRM_XE_OBSERVATION_TYPE_OA: OA observation stream type */
+	DRM_XE_OBSERVATION_TYPE_OA,
+	/** @DRM_XE_OBSERVATION_TYPE_EU_STALL: EU stall sampling observation stream type */
+	DRM_XE_OBSERVATION_TYPE_EU_STALL,
+};
+
+/**
+ * enum drm_xe_observation_op - Observation stream ops
+ */
+enum drm_xe_observation_op {
+	/** @DRM_XE_OBSERVATION_OP_STREAM_OPEN: Open an observation stream */
+	DRM_XE_OBSERVATION_OP_STREAM_OPEN,
+
+	/** @DRM_XE_OBSERVATION_OP_ADD_CONFIG: Add observation stream config */
+	DRM_XE_OBSERVATION_OP_ADD_CONFIG,
+
+	/** @DRM_XE_OBSERVATION_OP_REMOVE_CONFIG: Remove observation stream config */
+	DRM_XE_OBSERVATION_OP_REMOVE_CONFIG,
+};
+
+/**
+ * struct drm_xe_observation_param - Input of &DRM_IOCTL_XE_OBSERVATION
+ *
+ * The observation layer enables multiplexing observation streams of
+ * multiple types. The actual params for a particular stream operation are
+ * supplied via the @param pointer (use __copy_from_user to get these
+ * params).
+ */
+struct drm_xe_observation_param {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+	/** @observation_type: observation stream type, of &enum drm_xe_observation_type */
+	__u64 observation_type;
+	/** @observation_op: observation stream op, of &enum drm_xe_observation_op */
+	__u64 observation_op;
+	/** @param: Pointer to actual stream params */
+	__u64 param;
+};
+
+/**
+ * enum drm_xe_observation_ioctls - Observation stream fd ioctls
+ *
+ * Information exchanged between userspace and kernel for observation fd
+ * ioctls is stream type specific
+ */
+enum drm_xe_observation_ioctls {
+	/** @DRM_XE_OBSERVATION_IOCTL_ENABLE: Enable data capture for an observation stream */
+	DRM_XE_OBSERVATION_IOCTL_ENABLE = _IO('i', 0x0),
+
+	/** @DRM_XE_OBSERVATION_IOCTL_DISABLE: Disable data capture for an observation stream */
+	DRM_XE_OBSERVATION_IOCTL_DISABLE = _IO('i', 0x1),
+
+	/** @DRM_XE_OBSERVATION_IOCTL_CONFIG: Change observation stream configuration */
+	DRM_XE_OBSERVATION_IOCTL_CONFIG = _IO('i', 0x2),
+
+	/** @DRM_XE_OBSERVATION_IOCTL_STATUS: Return observation stream status */
+	DRM_XE_OBSERVATION_IOCTL_STATUS = _IO('i', 0x3),
+
+	/** @DRM_XE_OBSERVATION_IOCTL_INFO: Return observation stream info */
+	DRM_XE_OBSERVATION_IOCTL_INFO = _IO('i', 0x4),
+};
+
+/**
+ * enum drm_xe_oa_unit_type - OA unit types
+ */
+enum drm_xe_oa_unit_type {
+	/**
+	 * @DRM_XE_OA_UNIT_TYPE_OAG: OAG OA unit. OAR/OAC are considered
+	 * sub-types of OAG. For OAR/OAC, use OAG.
+	 */
+	DRM_XE_OA_UNIT_TYPE_OAG,
+
+	/** @DRM_XE_OA_UNIT_TYPE_OAM: OAM OA unit */
+	DRM_XE_OA_UNIT_TYPE_OAM,
+
+	/** @DRM_XE_OA_UNIT_TYPE_OAM_SAG: OAM_SAG OA unit */
+	DRM_XE_OA_UNIT_TYPE_OAM_SAG,
+
+	/** @DRM_XE_OA_UNIT_TYPE_MERT: MERT OA unit */
+	DRM_XE_OA_UNIT_TYPE_MERT,
+};
+
+/**
+ * struct drm_xe_oa_unit - describe OA unit
+ */
+struct drm_xe_oa_unit {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @oa_unit_id: OA unit ID */
+	__u32 oa_unit_id;
+
+	/** @oa_unit_type: OA unit type of &enum drm_xe_oa_unit_type */
+	__u32 oa_unit_type;
+
+	/** @capabilities: OA capabilities bit-mask */
+	__u64 capabilities;
+#define DRM_XE_OA_CAPS_BASE		(1 << 0)
+#define DRM_XE_OA_CAPS_SYNCS		(1 << 1)
+#define DRM_XE_OA_CAPS_OA_BUFFER_SIZE	(1 << 2)
+#define DRM_XE_OA_CAPS_WAIT_NUM_REPORTS	(1 << 3)
+#define DRM_XE_OA_CAPS_OAM		(1 << 4)
+#define DRM_XE_OA_CAPS_OA_UNIT_GT_ID	(1 << 5)
+
+	/** @oa_timestamp_freq: OA timestamp freq */
+	__u64 oa_timestamp_freq;
+
+	/** @gt_id: gt id for this OA unit */
+	__u16 gt_id;
+
+	/** @reserved1: MBZ */
+	__u16 reserved1[3];
+
+	/** @reserved: MBZ */
+	__u64 reserved[3];
+
+	/** @num_engines: number of engines in @eci array */
+	__u64 num_engines;
+
+	/** @eci: engines attached to this OA unit */
+	struct drm_xe_engine_class_instance eci[];
+};
+
+/**
+ * struct drm_xe_query_oa_units - describe OA units
+ *
+ * If a query is made with a struct drm_xe_device_query where .query
+ * is equal to DRM_XE_DEVICE_QUERY_OA_UNITS, then the reply uses struct
+ * drm_xe_query_oa_units in .data.
+ *
+ * OA unit properties for all OA units can be accessed using a code block
+ * such as the one below:
+ *
+ * .. code-block:: C
+ *
+ *	struct drm_xe_query_oa_units *qoa;
+ *	struct drm_xe_oa_unit *oau;
+ *	u8 *poau;
+ *
+ *	// malloc qoa and issue DRM_XE_DEVICE_QUERY_OA_UNITS. Then:
+ *	poau = (u8 *)&qoa->oa_units[0];
+ *	for (int i = 0; i < qoa->num_oa_units; i++) {
+ *		oau = (struct drm_xe_oa_unit *)poau;
+ *		// Access 'struct drm_xe_oa_unit' fields here
+ *		poau += sizeof(*oau) + oau->num_engines * sizeof(oau->eci[0]);
+ *	}
+ */
+struct drm_xe_query_oa_units {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+	/** @num_oa_units: number of OA units returned in oau[] */
+	__u32 num_oa_units;
+	/** @pad: MBZ */
+	__u32 pad;
+	/**
+	 * @oa_units: &struct drm_xe_oa_unit array returned for this device.
+	 * Written below as a u64 array to avoid problems with nested flexible
+	 * arrays with some compilers
+	 */
+	__u64 oa_units[];
+};
+
+/**
+ * enum drm_xe_oa_format_type - OA format types as specified in PRM/Bspec
+ * 52198/60942
+ */
+enum drm_xe_oa_format_type {
+	/** @DRM_XE_OA_FMT_TYPE_OAG: OAG report format */
+	DRM_XE_OA_FMT_TYPE_OAG,
+	/** @DRM_XE_OA_FMT_TYPE_OAR: OAR report format */
+	DRM_XE_OA_FMT_TYPE_OAR,
+	/** @DRM_XE_OA_FMT_TYPE_OAM: OAM report format */
+	DRM_XE_OA_FMT_TYPE_OAM,
+	/** @DRM_XE_OA_FMT_TYPE_OAC: OAC report format */
+	DRM_XE_OA_FMT_TYPE_OAC,
+	/** @DRM_XE_OA_FMT_TYPE_OAM_MPEC: OAM SAMEDIA or OAM MPEC report format */
+	DRM_XE_OA_FMT_TYPE_OAM_MPEC,
+	/** @DRM_XE_OA_FMT_TYPE_PEC: PEC report format */
+	DRM_XE_OA_FMT_TYPE_PEC,
+};
+
+/**
+ * enum drm_xe_oa_property_id - OA stream property IDs
+ *
+ * Stream params are specified as a chain of &struct drm_xe_ext_set_property
+ * structs, with property values from &enum drm_xe_oa_property_id and
+ * &struct drm_xe_user_extension base.name set to %DRM_XE_OA_EXTENSION_SET_PROPERTY.
+ * The param field in &struct drm_xe_observation_param points to the first
+ * &struct drm_xe_ext_set_property struct.
+ *
+ * Exactly the same mechanism is also used for stream reconfiguration using the
+ * %DRM_XE_OBSERVATION_IOCTL_CONFIG observation stream fd ioctl, though only a
+ * subset of properties below can be specified for stream reconfiguration.
+ */
+enum drm_xe_oa_property_id {
+#define DRM_XE_OA_EXTENSION_SET_PROPERTY	0
+	/**
+	 * @DRM_XE_OA_PROPERTY_OA_UNIT_ID: ID of the OA unit on which to open
+	 * the OA stream, see oa_unit_id in &struct drm_xe_oa_unit.
+	 * Defaults to 0 if not provided.
+	 */
+	DRM_XE_OA_PROPERTY_OA_UNIT_ID = 1,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_SAMPLE_OA: A value of 1 requests inclusion of raw
+	 * OA unit reports or stream samples in a global buffer attached to an
+	 * OA unit.
+	 */
+	DRM_XE_OA_PROPERTY_SAMPLE_OA,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_OA_METRIC_SET: OA metrics defining contents of OA
+	 * reports, previously added via %DRM_XE_OBSERVATION_OP_ADD_CONFIG.
+	 */
+	DRM_XE_OA_PROPERTY_OA_METRIC_SET,
+
+	/** @DRM_XE_OA_PROPERTY_OA_FORMAT: OA counter report format */
+	DRM_XE_OA_PROPERTY_OA_FORMAT,
+	/*
+	 * OA_FORMAT's are specified the same way as in PRM/Bspec 52198/60942,
+	 * in terms of the following quantities: a. &enum drm_xe_oa_format_type
+	 * b. Counter select c. Counter size and d. BC report. Also refer to the
+	 * oa_formats array in drivers/gpu/drm/xe/xe_oa.c.
+	 */
+#define DRM_XE_OA_FORMAT_MASK_FMT_TYPE		(0xffu << 0)
+#define DRM_XE_OA_FORMAT_MASK_COUNTER_SEL	(0xffu << 8)
+#define DRM_XE_OA_FORMAT_MASK_COUNTER_SIZE	(0xffu << 16)
+#define DRM_XE_OA_FORMAT_MASK_BC_REPORT		(0xffu << 24)
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT: Requests periodic OA unit
+	 * sampling with sampling frequency proportional to 2^(period_exponent + 1)
+	 */
+	DRM_XE_OA_PROPERTY_OA_PERIOD_EXPONENT,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_OA_DISABLED: A value of 1 will open the OA
+	 * stream in a DISABLED state (see %DRM_XE_OBSERVATION_IOCTL_ENABLE).
+	 */
+	DRM_XE_OA_PROPERTY_OA_DISABLED,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID: Open the stream for a specific
+	 * exec_queue_id. OA queries can be executed on this exec queue.
+	 */
+	DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE: Optional engine instance to
+	 * pass along with %DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID or will default to 0.
+	 */
+	DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_NO_PREEMPT: Allow preemption and timeslicing
+	 * to be disabled for the stream exec queue.
+	 */
+	DRM_XE_OA_PROPERTY_NO_PREEMPT,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_NUM_SYNCS: Number of syncs in the sync array
+	 * specified in %DRM_XE_OA_PROPERTY_SYNCS
+	 */
+	DRM_XE_OA_PROPERTY_NUM_SYNCS,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_SYNCS: Pointer to &struct drm_xe_sync array
+	 * with array size specified via %DRM_XE_OA_PROPERTY_NUM_SYNCS. OA
+	 * configuration will wait till input fences signal. Output fences
+	 * will signal after the new OA configuration takes effect. For
+	 * %DRM_XE_SYNC_TYPE_USER_FENCE, addr is a user pointer, similar
+	 * to the VM bind case.
+	 */
+	DRM_XE_OA_PROPERTY_SYNCS,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_OA_BUFFER_SIZE: Size of OA buffer to be
+	 * allocated by the driver in bytes. Supported sizes are powers of
+	 * 2 from 128 KiB to 128 MiB. When not specified, a 16 MiB OA
+	 * buffer is allocated by default.
+	 */
+	DRM_XE_OA_PROPERTY_OA_BUFFER_SIZE,
+
+	/**
+	 * @DRM_XE_OA_PROPERTY_WAIT_NUM_REPORTS: Number of reports to wait
+	 * for before unblocking poll or read
+	 */
+	DRM_XE_OA_PROPERTY_WAIT_NUM_REPORTS,
+};
+
+/**
+ * struct drm_xe_oa_config - OA metric configuration
+ *
+ * Multiple OA configs can be added using %DRM_XE_OBSERVATION_OP_ADD_CONFIG. A
+ * particular config can be specified when opening an OA stream using
+ * %DRM_XE_OA_PROPERTY_OA_METRIC_SET property.
+ */
+struct drm_xe_oa_config {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @uuid: String formatted like "%08x-%04x-%04x-%04x-%012x" */
+	char uuid[36];
+
+	/** @n_regs: Number of regs in @regs_ptr */
+	__u32 n_regs;
+
+	/**
+	 * @regs_ptr: Pointer to (register address, value) pairs for OA config
+	 * registers. Expected length of buffer is: (2 * sizeof(u32) * @n_regs).
+	 */
+	__u64 regs_ptr;
+};
+
+/**
+ * struct drm_xe_oa_stream_status - OA stream status returned from
+ * %DRM_XE_OBSERVATION_IOCTL_STATUS observation stream fd ioctl. Userspace can
+ * call the ioctl to query stream status in response to EIO errno from
+ * observation fd read().
+ */
+struct drm_xe_oa_stream_status {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @oa_status: OA stream status (see Bspec 46717/61226) */
+	__u64 oa_status;
+#define DRM_XE_OASTATUS_MMIO_TRG_Q_FULL		(1 << 3)
+#define DRM_XE_OASTATUS_COUNTER_OVERFLOW	(1 << 2)
+#define DRM_XE_OASTATUS_BUFFER_OVERFLOW		(1 << 1)
+#define DRM_XE_OASTATUS_REPORT_LOST		(1 << 0)
+
+	/** @reserved: reserved for future use */
+	__u64 reserved[3];
+};
+
+/**
+ * struct drm_xe_oa_stream_info - OA stream info returned from
+ * %DRM_XE_OBSERVATION_IOCTL_INFO observation stream fd ioctl
+ */
+struct drm_xe_oa_stream_info {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @oa_buf_size: OA buffer size */
+	__u64 oa_buf_size;
+
+	/** @reserved: reserved for future use */
+	__u64 reserved[3];
+};
+
+/**
+ * enum drm_xe_pxp_session_type - Supported PXP session types.
+ *
+ * We currently only support HWDRM sessions, which are used for protected
+ * content that ends up being displayed, but the HW supports multiple types, so
+ * we might extend support in the future.
+ */
+enum drm_xe_pxp_session_type {
+	/** @DRM_XE_PXP_TYPE_NONE: PXP not used */
+	DRM_XE_PXP_TYPE_NONE = 0,
+	/**
+	 * @DRM_XE_PXP_TYPE_HWDRM: HWDRM sessions are used for content that ends
+	 * up on the display.
+	 */
+	DRM_XE_PXP_TYPE_HWDRM = 1,
+};
+
+/* ID of the protected content session managed by Xe when PXP is active */
+#define DRM_XE_PXP_HWDRM_DEFAULT_SESSION 0xf
+
+/**
+ * enum drm_xe_eu_stall_property_id - EU stall sampling input property ids.
+ *
+ * These properties are passed to the driver at open as a chain of
+ * &struct drm_xe_ext_set_property structures with property set to these
+ * properties' enums and value set to the corresponding values of these
+ * properties. &struct drm_xe_user_extension base.name should be set to
+ * %DRM_XE_EU_STALL_EXTENSION_SET_PROPERTY.
+ *
+ * With the file descriptor obtained from open, user space must enable
+ * the EU stall stream fd with %DRM_XE_OBSERVATION_IOCTL_ENABLE before
+ * calling read(). EIO errno from read() indicates HW dropped data
+ * due to full buffer.
+ */
+enum drm_xe_eu_stall_property_id {
+#define DRM_XE_EU_STALL_EXTENSION_SET_PROPERTY		0
+	/**
+	 * @DRM_XE_EU_STALL_PROP_GT_ID: gt_id of the GT on which
+	 * EU stall data will be captured.
+	 */
+	DRM_XE_EU_STALL_PROP_GT_ID = 1,
+
+	/**
+	 * @DRM_XE_EU_STALL_PROP_SAMPLE_RATE: Sampling rate in
+	 * GPU cycles from sampling_rates in &struct drm_xe_query_eu_stall
+	 */
+	DRM_XE_EU_STALL_PROP_SAMPLE_RATE,
+
+	/**
+	 * @DRM_XE_EU_STALL_PROP_WAIT_NUM_REPORTS: Minimum number of
+	 * EU stall data reports to be present in the kernel buffer
+	 * before unblocking a blocked poll or read.
+	 */
+	DRM_XE_EU_STALL_PROP_WAIT_NUM_REPORTS,
+};
+
+/**
+ * struct drm_xe_query_eu_stall - Information about EU stall sampling.
+ *
+ * If a query is made with a &struct drm_xe_device_query where .query
+ * is equal to %DRM_XE_DEVICE_QUERY_EU_STALL, then the reply uses
+ * &struct drm_xe_query_eu_stall in .data.
+ */
+struct drm_xe_query_eu_stall {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @capabilities: EU stall capabilities bit-mask */
+	__u64 capabilities;
+#define DRM_XE_EU_STALL_CAPS_BASE		(1 << 0)
+
+	/** @record_size: size of each EU stall data record */
+	__u64 record_size;
+
+	/** @per_xecore_buf_size: internal per XeCore buffer size */
+	__u64 per_xecore_buf_size;
+
+	/** @reserved: Reserved */
+	__u64 reserved[5];
+
+	/** @num_sampling_rates: Number of sampling rates in @sampling_rates array */
+	__u64 num_sampling_rates;
+
+	/**
+	 * @sampling_rates: Flexible array of sampling rates
+	 * sorted in the fastest to slowest order.
+	 * Sampling rates are specified in GPU clock cycles.
+	 */
+	__u64 sampling_rates[];
+};
+
+/**
+ * struct drm_xe_madvise - Input of &DRM_IOCTL_XE_MADVISE
+ *
+ * This structure is used to set memory attributes for a virtual address range
+ * in a VM. The type of attribute is specified by @type, and the corresponding
+ * union member is used to provide additional parameters for @type.
+ *
+ * Supported attribute types:
+ *  - DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC: Set preferred memory location.
+ *  - DRM_XE_MEM_RANGE_ATTR_ATOMIC: Set atomic access policy.
+ *  - DRM_XE_MEM_RANGE_ATTR_PAT: Set page attribute table index.
+ *  - DRM_XE_VMA_ATTR_PURGEABLE_STATE: Set purgeable state for BOs.
+ *
+ * Example:
+ *
+ * .. code-block:: C
+ *
+ *    struct drm_xe_madvise madvise = {
+ *         .vm_id = vm_id,
+ *         .start = 0x100000,
+ *         .range = 0x2000,
+ *         .type = DRM_XE_MEM_RANGE_ATTR_ATOMIC,
+ *         .atomic.val = DRM_XE_ATOMIC_DEVICE,
+ *    };
+ *
+ *    ioctl(fd, DRM_IOCTL_XE_MADVISE, &madvise);
+ *
+ */
+struct drm_xe_madvise {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @start: start of the virtual address range */
+	__u64 start;
+
+	/** @range: size of the virtual address range */
+	__u64 range;
+
+	/** @vm_id: vm_id of the virtual range */
+	__u32 vm_id;
+
+#define DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC	0
+#define DRM_XE_MEM_RANGE_ATTR_ATOMIC		1
+#define DRM_XE_MEM_RANGE_ATTR_PAT		2
+#define DRM_XE_VMA_ATTR_PURGEABLE_STATE		3
+	/** @type: type of attribute */
+	__u32 type;
+
+	union {
+		/**
+		 * @preferred_mem_loc: preferred memory location
+		 *
+		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_PREFERRED_LOC
+		 *
+		 * Supported values for @preferred_mem_loc.devmem_fd:
+		 *  - DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE: set vram of fault tile as preferred loc
+		 *  - DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM: set smem as preferred loc
+		 *
+		 * Supported values for @preferred_mem_loc.migration_policy:
+		 *  - DRM_XE_MIGRATE_ALL_PAGES
+		 *  - DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES
+		 */
+		struct {
+#define DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE	0
+#define DRM_XE_PREFERRED_LOC_DEFAULT_SYSTEM	-1
+			/**
+			 * @preferred_mem_loc.devmem_fd:
+			 * Device file-descriptor of the device where the
+			 * preferred memory is located, or one of the
+			 * above special values. Please also see
+			 * @preferred_mem_loc.region_instance below.
+			 */
+			__u32 devmem_fd;
+
+#define DRM_XE_MIGRATE_ALL_PAGES		0
+#define DRM_XE_MIGRATE_ONLY_SYSTEM_PAGES	1
+			/** @preferred_mem_loc.migration_policy: Page migration policy */
+			__u16 migration_policy;
+
+			/**
+			 * @preferred_mem_loc.region_instance : Region instance.
+			 * MBZ if @devmem_fd <= %DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE.
+			 * Otherwise should point to the desired device
+			 * VRAM instance of the device indicated by
+			 * @preferred_mem_loc.devmem_fd.
+			 */
+			__u16 region_instance;
+
+			/** @preferred_mem_loc.reserved : Reserved */
+			__u64 reserved;
+		} preferred_mem_loc;
+
+		/**
+		 * @atomic: Atomic access policy
+		 *
+		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_ATOMIC.
+		 *
+		 * Supported values for @atomic.val:
+		 *  - DRM_XE_ATOMIC_UNDEFINED: Undefined or default behaviour.
+		 *    Support both GPU and CPU atomic operations for system allocator.
+		 *    Support GPU atomic operations for normal(bo) allocator.
+		 *  - DRM_XE_ATOMIC_DEVICE: Support GPU atomic operations.
+		 *  - DRM_XE_ATOMIC_GLOBAL: Support both GPU and CPU atomic operations.
+		 *  - DRM_XE_ATOMIC_CPU: Support CPU atomic only, no GPU atomics supported.
+		 */
+		struct {
+#define DRM_XE_ATOMIC_UNDEFINED	0
+#define DRM_XE_ATOMIC_DEVICE	1
+#define DRM_XE_ATOMIC_GLOBAL	2
+#define DRM_XE_ATOMIC_CPU	3
+			/** @atomic.val: value of atomic operation */
+			__u32 val;
+
+			/** @atomic.pad: MBZ */
+			__u32 pad;
+
+			/** @atomic.reserved: Reserved */
+			__u64 reserved;
+		} atomic;
+
+		/**
+		 * @pat_index: Page attribute table index
+		 *
+		 * Used when @type == DRM_XE_MEM_RANGE_ATTR_PAT.
+		 */
+		struct {
+			/** @pat_index.val: PAT index value */
+			__u32 val;
+
+			/** @pat_index.pad: MBZ */
+			__u32 pad;
+
+			/** @pat_index.reserved: Reserved */
+			__u64 reserved;
+		} pat_index;
+
+		/**
+		 * @purge_state_val: Purgeable state configuration
+		 *
+		 * Used when @type == DRM_XE_VMA_ATTR_PURGEABLE_STATE.
+		 *
+		 * Configures the purgeable state of buffer objects in the specified
+		 * virtual address range. This allows applications to hint to the kernel
+		 * about bo's usage patterns for better memory management.
+		 *
+		 * By default all VMAs are in WILLNEED state.
+		 *
+		 * Supported values for @purge_state_val.val:
+		 *  - DRM_XE_VMA_PURGEABLE_STATE_WILLNEED (0): Marks BO as needed.
+		 *    If the BO was previously purged, the kernel sets the __u32 at
+		 *    @retained_ptr to 0 (backing store lost) so the application knows
+		 *    it must recreate the BO.
+		 *
+		 *  - DRM_XE_VMA_PURGEABLE_STATE_DONTNEED (1): Marks BO as not currently
+		 *    needed. Kernel may purge it under memory pressure to reclaim memory.
+		 *    Only applies to non-shared BOs. The kernel sets the __u32 at
+		 *    @retained_ptr to 1 if the backing store still exists (not yet purged),
+		 *    or 0 if it was already purged.
+		 *
+		 *    Important: Once marked as DONTNEED, touching the BO's memory
+		 *    is undefined behavior. It may succeed temporarily (before the
+		 *    kernel purges the backing store) but will suddenly fail once
+		 *    the BO transitions to PURGED state.
+		 *
+		 *    To transition back: use WILLNEED and check @retained_ptr —
+		 *    if 0, backing store was lost and the BO must be recreated.
+		 *
+		 *    The following operations are blocked in DONTNEED state to
+		 *    prevent the BO from being re-mapped after madvise:
+		 *    - New mmap() calls: Fail with -EBUSY
+		 *    - VM_BIND operations: Fail with -EBUSY
+		 *    - New dma-buf exports: Fail with -EBUSY
+		 *    - CPU page faults (existing mmap): Fail with SIGBUS
+		 *    - GPU page faults (fault-mode VMs): Fail with -EACCES
+		 */
+		struct {
+#define DRM_XE_VMA_PURGEABLE_STATE_WILLNEED	0
+#define DRM_XE_VMA_PURGEABLE_STATE_DONTNEED	1
+			/** @purge_state_val.val: value for DRM_XE_VMA_ATTR_PURGEABLE_STATE */
+			__u32 val;
+
+			/** @purge_state_val.pad: MBZ */
+			__u32 pad;
+			/**
+			 * @purge_state_val.retained_ptr: Pointer to a __u32 output
+			 * field for backing store status.
+			 *
+			 * Userspace must initialize the __u32 value at this address
+			 * to 0 before the ioctl. Kernel writes a __u32 after the
+			 * operation:
+			 * - 1 if backing store exists (not purged)
+			 * - 0 if backing store was purged
+			 *
+			 * If userspace fails to initialize to 0, ioctl returns -EINVAL.
+			 * This ensures a safe default (0 = assume purged) if kernel
+			 * cannot write the result.
+			 *
+			 * Similar to i915's drm_i915_gem_madvise.retained field.
+			 */
+			__u64 retained_ptr;
+		} purge_state_val;
+	};
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_mem_range_attr - Output of &DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS
+ *
+ * This structure is provided by userspace and filled by KMD in response to the
+ * DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS ioctl. It describes memory attributes of
+ * memory ranges within a user specified address range in a VM.
+ *
+ * The structure includes information such as atomic access policy,
+ * page attribute table (PAT) index, and preferred memory location.
+ * Userspace allocates an array of these structures and passes a pointer to the
+ * ioctl to retrieve attributes for each memory range.
+ */
+struct drm_xe_mem_range_attr {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @start: start of the memory range */
+	__u64 start;
+
+	/** @end: end of the memory range */
+	__u64 end;
+
+	/** @preferred_mem_loc: preferred memory location */
+	struct {
+		/** @preferred_mem_loc.devmem_fd: fd for preferred loc */
+		__u32 devmem_fd;
+
+		/** @preferred_mem_loc.migration_policy: Page migration policy */
+		__u32 migration_policy;
+	} preferred_mem_loc;
+
+	/** @atomic: Atomic access policy */
+	struct {
+		/** @atomic.val: atomic attribute */
+		__u32 val;
+
+		/** @atomic.reserved: Reserved */
+		__u32 reserved;
+	} atomic;
+
+	/** @pat_index: Page attribute table index */
+	struct {
+		/** @pat_index.val: PAT index */
+		__u32 val;
+
+		/** @pat_index.reserved: Reserved */
+		__u32 reserved;
+	} pat_index;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * struct drm_xe_vm_query_mem_range_attr - Input of &DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS
+ *
+ * This structure is used to query memory attributes of memory regions
+ * within a user specified address range in a VM. It provides detailed
+ * information about each memory range, including atomic access policy,
+ * page attribute table (PAT) index, and preferred memory location.
+ *
+ * Userspace first calls the ioctl with @num_mem_ranges = 0,
+ * @sizeof_mem_range_attr = 0 and @vector_of_mem_attr = NULL to retrieve
+ * the number of memory regions and size of each memory range attribute.
+ * Then, it allocates a buffer of that size and calls the ioctl again to fill
+ * the buffer with memory range attributes.
+ *
+ * If second call fails with -ENOSPC, it means memory ranges changed between
+ * first call and now, retry IOCTL again with @num_mem_ranges = 0,
+ * @sizeof_mem_range_attr = 0 and @vector_of_mem_attr = NULL followed by
+ * second ioctl call.
+ *
+ * Example:
+ *
+ * .. code-block:: C
+ *
+ *    struct drm_xe_vm_query_mem_range_attr query = {
+ *         .vm_id = vm_id,
+ *         .start = 0x100000,
+ *         .range = 0x2000,
+ *     };
+ *
+ *    // First ioctl call to get num of mem regions and sizeof each attribute
+ *    ioctl(fd, DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS, &query);
+ *
+ *    // Allocate buffer for the memory region attributes
+ *    void *ptr = malloc(query.num_mem_ranges * query.sizeof_mem_range_attr);
+ *    void *ptr_start = ptr;
+ *
+ *    query.vector_of_mem_attr = (uintptr_t)ptr;
+ *
+ *    // Second ioctl call to actually fill the memory attributes
+ *    ioctl(fd, DRM_IOCTL_XE_VM_QUERY_MEM_RANGE_ATTRS, &query);
+ *
+ *    // Iterate over the returned memory region attributes
+ *    for (unsigned int i = 0; i < query.num_mem_ranges; ++i) {
+ *       struct drm_xe_mem_range_attr *attr = (struct drm_xe_mem_range_attr *)ptr;
+ *
+ *       // Do something with attr
+ *
+ *       // Move pointer by one entry
+ *       ptr += query.sizeof_mem_range_attr;
+ *     }
+ *
+ *    free(ptr_start);
+ */
+struct drm_xe_vm_query_mem_range_attr {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @vm_id: vm_id of the virtual range */
+	__u32 vm_id;
+
+	/** @num_mem_ranges: number of mem_ranges in range */
+	__u32 num_mem_ranges;
+
+	/** @start: start of the virtual address range */
+	__u64 start;
+
+	/** @range: size of the virtual address range */
+	__u64 range;
+
+	/** @sizeof_mem_range_attr: size of struct drm_xe_mem_range_attr */
+	__u64 sizeof_mem_range_attr;
+
+	/** @vector_of_mem_attr: userptr to array of struct drm_xe_mem_range_attr */
+	__u64 vector_of_mem_attr;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+
+};
+
+/**
+ * struct drm_xe_exec_queue_set_property - exec queue set property
+ *
+ * Sets execution queue properties dynamically.
+ * Currently only %DRM_XE_EXEC_QUEUE_SET_PROPERTY_MULTI_QUEUE_PRIORITY
+ * property can be dynamically set.
+ */
+struct drm_xe_exec_queue_set_property {
+	/** @extensions: Pointer to the first extension struct, if any */
+	__u64 extensions;
+
+	/** @exec_queue_id: Exec queue ID */
+	__u32 exec_queue_id;
+
+	/** @property: property to set */
+	__u32 property;
+
+	/** @value: property value */
+	__u64 value;
+
+	/** @reserved: Reserved */
+	__u64 reserved[2];
+};
+
+/**
+ * DOC: Xe DRM RAS
+ *
+ * The enums and strings defined below map to the attributes of the DRM RAS Netlink Interface.
+ * Refer to Documentation/netlink/specs/drm_ras.yaml for complete interface specification.
+ *
+ * Node Registration
+ * -----------------
+ *
+ * The driver registers DRM RAS nodes for each error severity level.
+ * enum drm_xe_ras_error_severity defines the node-id, while DRM_XE_RAS_ERROR_SEVERITY_NAMES maps
+ * node-id to node-name.
+ *
+ * Error Classification
+ * --------------------
+ *
+ * Each node contains a list of error counters. Each error is identified by a error-id and
+ * an error-name. enum drm_xe_ras_error_component defines the error-id, while
+ * DRM_XE_RAS_ERROR_COMPONENT_NAMES maps error-id to error-name.
+ *
+ * User Interface
+ * --------------
+ *
+ * To retrieve error values of a error counter, userspace applications should
+ * follow the below steps:
+ *
+ * 1. Use command LIST_NODES to enumerate all available nodes
+ * 2. Select node by node-id or node-name
+ * 3. Use command GET_ERROR_COUNTERS to list errors of specific node
+ * 4. Query specific error values using either error-id or error-name
+ *
+ * .. code-block:: C
+ *
+ *	// Lookup tables for ID-to-name resolution
+ *	static const char *nodes[] = DRM_XE_RAS_ERROR_SEVERITY_NAMES;
+ *	static const char *errors[] = DRM_XE_RAS_ERROR_COMPONENT_NAMES;
+ *
+ */
+
+/**
+ * enum drm_xe_ras_error_severity - DRM RAS error severity.
+ */
+enum drm_xe_ras_error_severity {
+	/** @DRM_XE_RAS_ERR_SEV_CORRECTABLE: Correctable Error */
+	DRM_XE_RAS_ERR_SEV_CORRECTABLE = 0,
+	/** @DRM_XE_RAS_ERR_SEV_UNCORRECTABLE: Uncorrectable Error */
+	DRM_XE_RAS_ERR_SEV_UNCORRECTABLE,
+	/** @DRM_XE_RAS_ERR_SEV_MAX: Max severity */
+	DRM_XE_RAS_ERR_SEV_MAX /* non-ABI */
+};
+
+/**
+ * enum drm_xe_ras_error_component - DRM RAS error component.
+ */
+enum drm_xe_ras_error_component {
+	/** @DRM_XE_RAS_ERR_COMP_CORE_COMPUTE: Core Compute Error */
+	DRM_XE_RAS_ERR_COMP_CORE_COMPUTE = 1,
+	/** @DRM_XE_RAS_ERR_COMP_SOC_INTERNAL: SoC Internal Error */
+	DRM_XE_RAS_ERR_COMP_SOC_INTERNAL,
+	/** @DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY: Device Memory Error */
+	DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY,
+	/** @DRM_XE_RAS_ERR_COMP_PCIE: PCIe Subsystem Error */
+	DRM_XE_RAS_ERR_COMP_PCIE,
+	/** @DRM_XE_RAS_ERR_COMP_FABRIC: Fabric Subsystem Error */
+	DRM_XE_RAS_ERR_COMP_FABRIC,
+	/** @DRM_XE_RAS_ERR_COMP_MAX: Max Error */
+	DRM_XE_RAS_ERR_COMP_MAX	/* non-ABI */
+};
+
+/*
+ * Error severity to name mapping.
+ */
+#define DRM_XE_RAS_ERROR_SEVERITY_NAMES {				\
+	[DRM_XE_RAS_ERR_SEV_CORRECTABLE] = "correctable-errors",	\
+	[DRM_XE_RAS_ERR_SEV_UNCORRECTABLE] = "uncorrectable-errors",	\
+}
+
+/*
+ * Error component to name mapping.
+ */
+#define DRM_XE_RAS_ERROR_COMPONENT_NAMES {				\
+	[DRM_XE_RAS_ERR_COMP_CORE_COMPUTE] = "core-compute",		\
+	[DRM_XE_RAS_ERR_COMP_SOC_INTERNAL] = "soc-internal",		\
+	[DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY] = "device-memory",		\
+	[DRM_XE_RAS_ERR_COMP_PCIE] = "pcie",				\
+	[DRM_XE_RAS_ERR_COMP_FABRIC] = "fabric",			\
+}
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* _UAPI_XE_DRM_H_ */