Merge tag 'drm-next-2026-06-17' of https://gitlab.freedesktop.org/drm/kernel

Pull drm updates from Dave Airlie:
 "Highlights:
   - xe: add initial CRI platform support
   - amdgpu: initial HDMI 2.1 FRL support
   - rust: add some new type concepts for device lifetimes
   - scheduler: moves to a fair algorithm and lots of cleanups

  But it's mostly the usual mountain of changes across the board.

  core:
   - add docbook for DRM_IOCTL_SYNCOBJ_EVENTFD
   - change signature of drm_connector_attach_hdr_output_metadata_property
   - dedup counter and timestamp retrieval in vblank code
   - parse AMD VSDB v3 in CTA extension blocks
   - add P230, Y7, XYYY2101010, T430, XVUY210101010 formats
   - don't call drop master on file close if not master
   - use drm_printf_indent in atomic / bridge
   - fix 32b format descriptions
   - docs: fix toctree
   - hdmi: add common TMDS character rates
   - fix drm_syncobj_find_fence leak

  rust:
   - introduce Higher-Ranked lifetime types
   - replace drvdata with scoped registration data
   - add GPUVM immediate mode abstraction for rust GPU drivers
   - introduce DeviceContext type state for drm::Device

  bridge:
   - clarify drm_bridge_get/put
   - create drm_get_bridge_by_endpoint and use it
   - analogix_dp: add panel probing
   - ite-it6211 - use drm audio hdmi helpers

  buddy:
   - add lockdep annotations

  dp:
   - add PR and VRR updates
   - mst: fix buffer overflows
   - add Adaptive Sync SDP decoding support
   - fix OOB reads in dp-mst

  ttm:
   - bump fpfn/lpfn to 64-bit

  scheduler:
   - change default to fair scheduler
   - map runqueue 1:1 with scheduler

  dma-buf:
   - port selftests to kunit
   - convert dma-buf system/heap allocators to module
   - add separate DMABUF_HEAPS_SYSTEM_CC_SHARED Kconfig

  udmabuf:
   - revert hugetlb support
   - fix error with CONFIG_DMA_API_DEBUG

  dma-fence:
   - fix tracepoints lifetime
   - remove unused signal on any support

  ras:
   - add clear error counter netlink command to drm ras

  gpusvm:
   - reject VMAs with VM_IO or VM_PFNMAP when creating SVM ranges
   - use IOVA allocations

  pagemap:
   - use IOVA allocations

  panels:
   - update to use ref counts
   - add support for CSW PNB601LS1-2, LGD LP116WHA-SPB1
   - add support for waveshare panels
   - CMN N116BCN-EA1, CMN N140HCA-EEK, IVO M140NWFQ R5,
   - IVO, R140NWFW R0, BOE NT140*, BOE NV133FHM-N4F,
   - AUO B140*, AUO B133HAN06.6 and AUO B116XTN02.3 eDP panels
   - Surface Pro 12 Panel

  xe:
   - add CRI PCI-IDs
   - debugfs add multi-lrc info
   - engine init cleanup
   - PF fair scheduling auto provisioning
   - system controller support for CRI/Xe3p
   - PXP state machine fixes
   - Reset/wedge/unload corner case fixes
   - Wedge path memory allocation fixes
   - PAT type cleanups
   - Reject unsafe PAT for CPU cached memory
   - OA improvements for CRI device memory
   - kernel doc syntax in xe headers
   - xe_drm.h documentation fixes
   - include guard cleanups
   - VF CCS memory pool
   - i915/xe step unification
   - Xe3p GT tuning fixes
   - forcewake cleanup in GT and GuC
   - admin-only PF mode
   - enable hwmon energy attributes for CRI
   - enable GT_MI_USER_INTERRUPT
   - refactor emit functions
   - oa workarounds
   - multi_queue: allow QUEUE_TIMESTAMP register
   - convert stolen memory to ttm range manager
   - use xe2 style blitter as a feature flag
   - make drm_driver const
   - add/use IRQ page to HW engine definition
   - fix oops when display disabled

  i915:
   - enable PIPEDMC_ERROR interrupt
   - more common display code refactoring
   - restructure DP/HDMI sink format handling
   - eliminate FB usage from lowlevel pinning code
   - panel replay bw optimization
   - integrate sharpness filter into the scaler
   - new fb_pin abstraction for xe/i915 fb transparent handling
   - skip inactive MST connectors on HDCP
   - start switching to display specific registers
   - use polling when irq unavailable
   - Adaptive-sync SDP prep

  amdgpu:
   - use drm_display_info for AMD VSDB data
   - Initial HDMI 2.1 FRL support
   - Initial DCN 4.2.1 support
   - GART fixes for non-4k pages
   - GC 11.5.6/SDMA 6.4.0/and other new IPs
   - GFX9/DCE6/Hawaii/SDMA4/GART/Userq fixes
   - Finish support for using multiple SDMA queues for TTM operations
   - SWSMU updates
   - GC 12.1 updates
   - SMU 15.0.8 updates
   - DCN 4.2 updates
   - DC type conversion fixes
   - Enable DC power module
   - Replay/PSR updates
   - SMU 13.x updates
   - Compute queue quantum MQD updates
   - ASPM fix
   - Align VKMS with common implementation
   - DC analog support fixes
   - UVD 3 fixes
   - TCC harvesting fixes for SI
   - GC 11 APU module reload fix
   - NBIO 6.3.2 support
   - IH 7.1 updates
   - DC cursor fixes
   - VCN/JPEG user fence fixes
   - DC support for connectors without DDC
   - Prefer ROM BAR for default VGA device
   - DC bandwidth fixes
   - Add PTL support for profiler
   - Introduce dc_plane_cm and migrate surface update color path
   - Add FRL registers for HDMI 2.1
   - Restructure VM state machine
   - Auxless ALPM support
   - GEM_OP locking/warning fixes
   - switch to system_dfl_wq

  amdkfd:
   - GPUVM TLB flush fix
   - Hotplug fix
   - Boundary check fixes
   - SVM fixes
   - CRIU fixes
   - add profiler API
   - MES 12.1 updates

  msm:
   - core:
     - fix shrinker documentation
     - IFPC enabled for gen8
     - PERFCNTR_CONFIG ioctl support
   - GPU:
     - reworked UBWC handling
     - a810 support
   - MDSS:
     - add support for Milos platform
     - reworked UBWC handling
   - DisplayPort:
     - reworked HPD handling as prep for MST
   - DPU:
     - Milos platform support
     - reworked UBWC handling
   - DSI:
     - Milos platform support

  nova:
   - Hopper/Blackwell enablement (GH100/GB100/GB202)
     - FSP support
     - 32-bit firmware support
     - HAL functions
   - refactor GSP boot/unload
   - GA100 support
   - VBIOS hardening/refactoring
   - Adopt higher order lifetime types

  tyr:
   - define register blocks
   - add shmem backed GEM objects
   - adopt higher order lifetime types
   - move clock cleanup into Drop

  radeon:
   - Hawaii SMU fixes
   - CS parser fix
   - use struct drm_edid instead of edid

  amdxdna:
   - export per-client BO memory via fdinfo
   - AIE4 device support
   - support medium/lower power modes
   - expandable device heap support
   - revert read-only user-pointer BO mappings

  ivpu:
   - support frequency limiting

  panthor:
   - enable GEM shrinker support
   - add eviction and reclaim info to fdinfo

  v3d:
   - enable runtime PM

  mgag200:
   - support XRGB1555 + C8

  ast:
   - support XRGB1555 + C8
   - use constants for lots of registers
   - fix register handling

  imagination:
   - fence handling refactoring

  nouveau:
   - fix sched double call
   - expose VBIOS on GSP-RM systems
   - add GA100 support

  virtio:
   - add VIRTIO_GPU_F_BLOB_ALIGNMENT flag
   - add deferred mapping support

  gud:
   - add RCade Display Adapter

  hibmc:
   - fix no connectors usage

  mediatek:
   - hdmi: convert error handling
   - simplify mtk_crtc allocation

  exynos:
   - move fbdev emulation to drm client buffers
   - use drm format helpers for geometry/size
   - adopt core DMA tracking
   - fix framebuffer offset handling

  renesas:
   - add RZ/T2H SOC support

  versilicon:
   - add cursor plane support

  tegra:
   - use drm client for framebuffer"

* tag 'drm-next-2026-06-17' of https://gitlab.freedesktop.org/drm/kernel: (1731 commits)
  dma-buf: move system_cc_shared heap under separate Kconfig
  accel/amdxdna: Clear sva pointer after unbind
  agp/amd64: Fix broken error propagation in agp_amd64_probe()
  accel/amdxdna: Require carveout when PASID and force_iova are disabled
  drm/amdkfd: always resume_all after suspend_all
  drm/amdgpu/gfx: move fault and EOP IRQ get/put to hw_init/hw_fini
  drm/amd/display: Consult MCCS FreeSync cap only if requested & supported
  drm/amd/pm: Use strscpy in profile mode parsing
  drm/amdkfd: Fix infinite loop parsing CRAT with zero subtype length
  drm/amdkfd: fix sysfs topology prop length on buffer truncation
  drm/amdgpu: drop retry loop in amdgpu_hmm_range_get_pages
  drm/amd/pm: bound OD parameter parsing to stack array size
  drm/amd/pm: Stop pp_od_clk_voltage emit at PAGE_SIZE
  drm/amdkfd: Unwind debug trap enable on copy_to_user failure
  drm/amdgpu: validate the mes firmware version for gfx12.1
  drm/amdgpu: validate the mes firmware version for gfx12
  drm/amdgpu: compare MES firmware version ucode for gfx11
  drm/amdkfd: Add bounds check for AMDKFD_IOC_WAIT_EVENTS
  drm/amdgpu: restart the CS if some parts of the VM are still invalidated
  drm/amd/display: use unsigned types for local pipe and REG_GET counters
  ...

12 files changed, 285 insertions, 185 deletions

diff --git a/include/uapi/drm/amdxdna_accel.h b/include/uapi/drm/amdxdna_accel.h
index 61d3686fa3b1..51a507561df6 100644
--- a/include/uapi/drm/amdxdna_accel.h
+++ b/include/uapi/drm/amdxdna_accel.h
@@ -18,6 +18,7 @@ extern "C" {
 #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
@@ -29,7 +30,9 @@ extern "C" {
 
 enum amdxdna_device_type {
 	AMDXDNA_DEV_TYPE_UNKNOWN = -1,
-	AMDXDNA_DEV_TYPE_KMQ,
+	AMDXDNA_DEV_TYPE_KMQ = 0,
+	AMDXDNA_DEV_TYPE_UMQ = 1,
+	AMDXDNA_DEV_TYPE_PF = 2,
 };
 
 enum amdxdna_drm_ioctl_id {
@@ -42,7 +45,8 @@ enum amdxdna_drm_ioctl_id {
 	DRM_AMDXDNA_EXEC_CMD,
 	DRM_AMDXDNA_GET_INFO,
 	DRM_AMDXDNA_SET_STATE,
-	DRM_AMDXDNA_GET_ARRAY = 10,
+	DRM_AMDXDNA_WAIT_CMD,
+	DRM_AMDXDNA_GET_ARRAY,
 };
 
 /**
@@ -272,6 +276,21 @@ struct amdxdna_drm_exec_cmd {
 };
 
 /**
+ * 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.
@@ -736,6 +755,10 @@ struct amdxdna_drm_set_power_mode {
 	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
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 27cc159c1d27..bc7ef7684099 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Header for the Direct Rendering Manager
  *
@@ -11,25 +12,6 @@
  * Copyright 1999 Precision Insight, Inc., Cedar Park, Texas.
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * 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 _DRM_H_
@@ -1323,6 +1305,13 @@ extern "C" {
  */
 #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)
 
 /**
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index ac66fa93b5a3..3a4d4dc635bf 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -1,24 +1,6 @@
+/* SPDX-License-Identifier: MIT */
 /*
  * Copyright 2011 Intel Corporation
- *
- * 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 DRM_FOURCC_H
@@ -242,9 +224,9 @@ extern "C" {
  * [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] R:G 32:32 little endian */
-#define DRM_FORMAT_BGR323232F    fourcc_code('B', 'G', 'R', 'F') /* [95:0] R:G:B 32:32:32 little endian */
-#define DRM_FORMAT_ABGR32323232F fourcc_code('A', 'B', '8', 'F') /* [127:0] R:G:B:A 32:32:32:32 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
@@ -264,6 +246,7 @@ extern "C" {
 #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
@@ -379,6 +362,14 @@ extern "C" {
  */
 #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
@@ -396,6 +387,15 @@ extern "C" {
 #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
@@ -451,6 +451,16 @@ extern "C" {
 #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:
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index a4bdc4bd11bc..381a3e857d4e 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -1,27 +1,10 @@
+/* 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
- *
- * 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
- * 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 _DRM_MODE_H
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 5f40fa5b869d..218a3ee86805 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/include/uapi/drm/drm_ras.h
@@ -41,6 +41,7 @@ enum {
 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)
diff --git a/include/uapi/drm/drm_sarea.h b/include/uapi/drm/drm_sarea.h
index a951ced60ebe..1e38d028332d 100644
--- a/include/uapi/drm/drm_sarea.h
+++ b/include/uapi/drm/drm_sarea.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: MIT */
 /**
  * \file drm_sarea.h
  * \brief SAREA definitions
@@ -8,25 +9,6 @@
 /*
  * 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
- * 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 _DRM_SAREA_H_
diff --git a/include/uapi/drm/msm_drm.h b/include/uapi/drm/msm_drm.h
index b99098792371..7f2e594be4eb 100644
--- a/include/uapi/drm/msm_drm.h
+++ b/include/uapi/drm/msm_drm.h
@@ -491,6 +491,52 @@ struct drm_msm_submitqueue_query {
 	__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
@@ -507,6 +553,7 @@ struct drm_msm_submitqueue_query {
 #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)
@@ -521,6 +568,7 @@ struct drm_msm_submitqueue_query {
 #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)
 }
diff --git a/include/uapi/drm/tegra_drm.h b/include/uapi/drm/tegra_drm.h
index 94cfc306d50a..8f21f3a44832 100644
--- a/include/uapi/drm/tegra_drm.h
+++ b/include/uapi/drm/tegra_drm.h
@@ -304,6 +304,7 @@ struct drm_tegra_cmdbuf {
  * struct drm_tegra_reloc - GEM object relocation structure
  */
 struct drm_tegra_reloc {
+	/** @cmdbuf: cmd information */
 	struct {
 		/**
 		 * @cmdbuf.handle:
@@ -321,6 +322,7 @@ struct drm_tegra_reloc {
 		 */
 		__u32 offset;
 	} cmdbuf;
+	/** @target: relocate target information */
 	struct {
 		/**
 		 * @target.handle:
@@ -778,6 +780,9 @@ struct drm_tegra_channel_unmap {
 /* 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.
@@ -830,16 +835,27 @@ struct drm_tegra_submit_buf {
 };
 
 /**
+ * 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.
  */
diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h
index 9debb320c34b..95587e12aed5 100644
--- a/include/uapi/drm/virtgpu_drm.h
+++ b/include/uapi/drm/virtgpu_drm.h
@@ -98,6 +98,7 @@ struct drm_virtgpu_execbuffer {
 #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;
@@ -200,6 +201,10 @@ struct drm_virtgpu_resource_create_blob {
 	__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
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index ae2fda23ce7c..48e9f1fdb78d 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -83,6 +83,7 @@ extern "C" {
  *  - &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
  */
 
@@ -167,7 +168,7 @@ extern "C" {
  * 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
@@ -229,9 +230,9 @@ struct drm_xe_ext_set_property {
 /**
  * struct drm_xe_engine_class_instance - instance of an engine class
  *
- * It is returned as part of the @drm_xe_engine, but it also is used as
- * the input of engine selection for both @drm_xe_exec_queue_create and
- * @drm_xe_query_engine_cycles
+ * 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
@@ -264,7 +265,7 @@ struct drm_xe_engine_class_instance {
  * struct drm_xe_engine - describe hardware engine
  */
 struct drm_xe_engine {
-	/** @instance: The @drm_xe_engine_class_instance */
+	/** @instance: The &struct drm_xe_engine_class_instance */
 	struct drm_xe_engine_class_instance instance;
 
 	/** @reserved: Reserved */
@@ -274,9 +275,9 @@ struct drm_xe_engine {
 /**
  * struct drm_xe_query_engines - describe engines
  *
- * If a query is made with a struct @drm_xe_device_query where .query
+ * 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 in .data.
  */
 struct drm_xe_query_engines {
 	/** @num_engines: number of engines returned in @engines */
@@ -349,7 +350,7 @@ struct drm_xe_mem_region {
 	 * is smaller than @total_size then this is referred to as a
 	 * small BAR system.
 	 *
-	 * On systems without small BAR (full BAR), the probed_size will
+	 * 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.
 	 *
@@ -410,7 +411,7 @@ struct drm_xe_query_mem_regions {
  *      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 creaed with
+ *      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
@@ -705,7 +706,10 @@ struct drm_xe_query_pxp_status {
  *    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
@@ -825,7 +829,7 @@ struct drm_xe_device_query {
  *
  * This ioctl supports setting the following properties via the
  * %DRM_XE_GEM_CREATE_EXTENSION_SET_PROPERTY extension, which uses the
- * generic @drm_xe_ext_set_property struct:
+ * 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
@@ -862,8 +866,7 @@ struct drm_xe_gem_create {
 #define DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM	(1 << 2)
 #define DRM_XE_GEM_CREATE_FLAG_NO_COMPRESSION		(1 << 3)
 	/**
-	 * @flags: Flags, currently a mask of memory instances of where BO can
-	 * be placed
+	 * @flags: Flags for the GEM object, see DRM_XE_GEM_CREATE_FLAG_*
 	 */
 	__u32 flags;
 
@@ -888,7 +891,7 @@ struct drm_xe_gem_create {
 #define DRM_XE_GEM_CPU_CACHING_WC                      2
 	/**
 	 * @cpu_caching: The CPU caching mode to select for this object. If
-	 * mmaping the object the mode selected here will also be used. The
+	 * 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
@@ -931,7 +934,7 @@ struct drm_xe_gem_create {
  *
  *     err = ioctl(fd, DRM_IOCTL_XE_GEM_MMAP_OFFSET, &mmo);
  *     map = mmap(NULL, size, PROT_WRITE, MAP_SHARED, fd, mmo.offset);
- *     map[i] = 0xdeadbeaf; // issue barrier
+ *     map[i] = 0xdeadbeef; // issue barrier
  */
 struct drm_xe_gem_mmap_offset {
 	/** @extensions: Pointer to the first extension struct, if any */
@@ -958,8 +961,8 @@ struct drm_xe_gem_mmap_offset {
  *  - %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 of on x2 and
- *    xe3 platform.
+ *    %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
@@ -1045,7 +1048,7 @@ struct drm_xe_vm_destroy {
  *    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 are only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO
+ *    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
@@ -1061,6 +1064,7 @@ struct drm_xe_vm_destroy {
  *    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
@@ -1109,7 +1113,7 @@ struct drm_xe_vm_bind_op {
 	 *	ppGTT WT -> COH_NONE
 	 *	ppGTT WB -> COH_AT_LEAST_1WAY
 	 *
-	 * In practice UC/WC/WT should only ever used for scanout surfaces on
+	 * 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
@@ -1199,10 +1203,10 @@ struct drm_xe_vm_bind_op {
 /**
  * struct drm_xe_vm_bind - Input of &DRM_IOCTL_XE_VM_BIND
  *
- * Below is an example of a minimal use of @drm_xe_vm_bind to
+ * 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 @drm_xe_sync.
+ * provided for &struct drm_xe_sync.
  *
  * .. code-block:: C
  *
@@ -1355,7 +1359,7 @@ struct drm_xe_vm_get_property {
  *
  * This ioctl supports setting the following properties via the
  * %DRM_XE_EXEC_QUEUE_EXTENSION_SET_PROPERTY extension, which uses the
- * generic @drm_xe_ext_set_property struct:
+ * 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.
@@ -1366,7 +1370,7 @@ struct drm_xe_vm_get_property {
  *    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
- *    (%XE_PXP_HWDRM_DEFAULT_SESSION) will be started, if isn't already running.
+ *    (%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
@@ -1390,9 +1394,9 @@ struct drm_xe_vm_get_property {
  *    enable render color cache keying on BTP+BTI instead of just BTI
  *    (only valid for render queues).
  *
- * The example below shows how to use @drm_xe_exec_queue_create to create
+ * 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.
+ * %DRM_XE_ENGINE_CLASS_RENDER.
  *
  * .. code-block:: C
  *
@@ -1402,23 +1406,25 @@ struct drm_xe_vm_get_property {
  *     struct drm_xe_exec_queue_create exec_queue_create = {
  *          .extensions = 0,
  *          .vm_id = vm,
- *          .num_bb_per_exec = 1,
- *          .num_eng_per_bb = 1,
+ *          .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,
+ * 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,
- *          .num_bb_per_exec = 1,
- *          .num_eng_per_bb = 1,
+ *          .width = 1,
+ *          .num_placements = 1,
  *          .instances = to_user_pointer(&instance),
  *     };
  *     ioctl(fd, DRM_IOCTL_XE_EXEC_QUEUE_CREATE, &exec_queue_create);
@@ -1515,7 +1521,7 @@ struct drm_xe_exec_queue_get_property {
  * and the @flags can be:
  *  - %DRM_XE_SYNC_FLAG_SIGNAL
  *
- * A minimal use of @drm_xe_sync looks like this:
+ * A minimal use of &struct drm_xe_sync looks like this:
  *
  * .. code-block:: C
  *
@@ -1546,7 +1552,7 @@ struct drm_xe_sync {
 #define DRM_XE_SYNC_TYPE_SYNCOBJ		0x0
 #define DRM_XE_SYNC_TYPE_TIMELINE_SYNCOBJ	0x1
 #define DRM_XE_SYNC_TYPE_USER_FENCE		0x2
-	/** @type: Type of the this sync object */
+	/** @type: Type of this sync object */
 	__u32 type;
 
 #define DRM_XE_SYNC_FLAG_SIGNAL	(1 << 0)
@@ -1559,9 +1565,9 @@ struct drm_xe_sync {
 
 		/**
 		 * @addr: Address of user fence. When sync is passed in via exec
-		 * IOCTL this is a GPU address in the VM. When sync passed in via
+		 * 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 users responsibility that this address is present and
+		 * the user's responsibility that this address is present and
 		 * mapped when the user fence is signalled. Must be qword
 		 * aligned.
 		 */
@@ -1581,10 +1587,10 @@ struct drm_xe_sync {
 /**
  * struct drm_xe_exec - Input of &DRM_IOCTL_XE_EXEC
  *
- * This is an example to use @drm_xe_exec for execution of the object
- * at BIND_ADDRESS (see example in @drm_xe_vm_bind) by an exec_queue
- * (see example in @drm_xe_exec_queue_create). It can be synchronized
- * by using the example provided for @drm_xe_sync.
+ * 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
  *
@@ -1651,7 +1657,6 @@ struct drm_xe_exec {
  *
  * and the @flags can be:
  *  - %DRM_XE_UFENCE_WAIT_FLAG_ABSTIME
- *  - %DRM_XE_UFENCE_WAIT_FLAG_SOFT_OP
  *
  * The @mask values can be for example:
  *  - 0xffu for u8
@@ -1664,7 +1669,7 @@ struct drm_xe_wait_user_fence {
 	__u64 extensions;
 
 	/**
-	 * @addr: user pointer address to wait on, must qword aligned
+	 * @addr: user pointer address to wait on, must be qword aligned
 	 */
 	__u64 addr;
 
@@ -1695,9 +1700,9 @@ struct drm_xe_wait_user_fence {
 	 * Without DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flag set (relative timeout)
 	 * it contains timeout expressed in nanoseconds to wait (fence will
 	 * expire at now() + timeout).
-	 * When DRM_XE_UFENCE_WAIT_FLAG_ABSTIME flat is set (absolute timeout) wait
-	 * will end at timeout (uses system MONOTONIC_CLOCK).
-	 * Passing negative timeout leads to neverending wait.
+	 * 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).
@@ -1741,7 +1746,7 @@ enum drm_xe_observation_op {
 };
 
 /**
- * struct drm_xe_observation_param - Input of &DRM_XE_OBSERVATION
+ * 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
@@ -1751,25 +1756,25 @@ enum drm_xe_observation_op {
 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 */
+	/** @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 */
+	/** @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 ioctl's
+ * enum drm_xe_observation_ioctls - Observation stream fd ioctls
  *
  * Information exchanged between userspace and kernel for observation fd
- * ioctl's is stream type specific
+ * 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 a observation stream */
+	/** @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 */
@@ -1812,7 +1817,7 @@ struct drm_xe_oa_unit {
 	/** @oa_unit_id: OA unit ID */
 	__u32 oa_unit_id;
 
-	/** @oa_unit_type: OA unit type of @drm_xe_oa_unit_type */
+	/** @oa_unit_type: OA unit type of &enum drm_xe_oa_unit_type */
 	__u32 oa_unit_type;
 
 	/** @capabilities: OA capabilities bit-mask */
@@ -1875,7 +1880,7 @@ struct drm_xe_query_oa_units {
 	/** @pad: MBZ */
 	__u32 pad;
 	/**
-	 * @oa_units: struct @drm_xe_oa_unit array returned for this device.
+	 * @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
 	 */
@@ -1902,24 +1907,24 @@ enum drm_xe_oa_format_type {
 };
 
 /**
- * enum drm_xe_oa_property_id - OA stream property id's
+ * enum drm_xe_oa_property_id - OA stream property IDs
  *
- * Stream params are specified as a chain of @drm_xe_ext_set_property
- * struct's, with @property values from enum @drm_xe_oa_property_id and
- * @drm_xe_user_extension base.name set to @DRM_XE_OA_EXTENSION_SET_PROPERTY.
- * @param field in struct @drm_xe_observation_param points to the first
- * @drm_xe_ext_set_property struct.
+ * 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
+ * %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_query_oa_units'. Defaults to 0 if not provided.
+	 * 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,
 
@@ -1932,7 +1937,7 @@ enum drm_xe_oa_property_id {
 
 	/**
 	 * @DRM_XE_OA_PROPERTY_OA_METRIC_SET: OA metrics defining contents of OA
-	 * reports, previously added via @DRM_XE_OBSERVATION_OP_ADD_CONFIG.
+	 * reports, previously added via %DRM_XE_OBSERVATION_OP_ADD_CONFIG.
 	 */
 	DRM_XE_OA_PROPERTY_OA_METRIC_SET,
 
@@ -1940,7 +1945,7 @@ enum drm_xe_oa_property_id {
 	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
+	 * 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.
 	 */
@@ -1957,19 +1962,19 @@ enum drm_xe_oa_property_id {
 
 	/**
 	 * @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).
+	 * 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.
+	 * 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.
+	 * pass along with %DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID or will default to 0.
 	 */
 	DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE,
 
@@ -1981,16 +1986,16 @@ enum drm_xe_oa_property_id {
 
 	/**
 	 * @DRM_XE_OA_PROPERTY_NUM_SYNCS: Number of syncs in the sync array
-	 * specified in @DRM_XE_OA_PROPERTY_SYNCS
+	 * 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
+	 * @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
+	 * %DRM_XE_SYNC_TYPE_USER_FENCE, addr is a user pointer, similar
 	 * to the VM bind case.
 	 */
 	DRM_XE_OA_PROPERTY_SYNCS,
@@ -2013,15 +2018,15 @@ enum drm_xe_oa_property_id {
 /**
  * struct drm_xe_oa_config - OA metric configuration
  *
- * Multiple OA configs can be added using @DRM_XE_OBSERVATION_OP_ADD_CONFIG. A
+ * 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.
+ * %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" */
+	/** @uuid: String formatted like "%08x-%04x-%04x-%04x-%012x" */
 	char uuid[36];
 
 	/** @n_regs: Number of regs in @regs_ptr */
@@ -2036,7 +2041,7 @@ struct drm_xe_oa_config {
 
 /**
  * struct drm_xe_oa_stream_status - OA stream status returned from
- * @DRM_XE_OBSERVATION_IOCTL_STATUS observation stream fd ioctl. Userspace can
+ * %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().
  */
@@ -2057,7 +2062,7 @@ struct drm_xe_oa_stream_status {
 
 /**
  * struct drm_xe_oa_stream_info - OA stream info returned from
- * @DRM_XE_OBSERVATION_IOCTL_INFO observation stream fd ioctl
+ * %DRM_XE_OBSERVATION_IOCTL_INFO observation stream fd ioctl
  */
 struct drm_xe_oa_stream_info {
 	/** @extensions: Pointer to the first extension struct, if any */
@@ -2094,27 +2099,27 @@ enum drm_xe_pxp_session_type {
  * 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
- * @drm_xe_ext_set_property structures with @property set to these
- * properties' enums and @value set to the corresponding values of these
- * properties. @drm_xe_user_extension base.name should be set to
- * @DRM_XE_EU_STALL_EXTENSION_SET_PROPERTY.
+ * &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
+ * 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
+	 * @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
+	 * GPU cycles from sampling_rates in &struct drm_xe_query_eu_stall
 	 */
 	DRM_XE_EU_STALL_PROP_SAMPLE_RATE,
 
@@ -2129,9 +2134,9 @@ enum drm_xe_eu_stall_property_id {
 /**
  * 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.
+ * 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 */
@@ -2183,7 +2188,7 @@ struct drm_xe_query_eu_stall {
  *         .start = 0x100000,
  *         .range = 0x2000,
  *         .type = DRM_XE_MEM_RANGE_ATTR_ATOMIC,
- *         .atomic_val = DRM_XE_ATOMIC_DEVICE,
+ *         .atomic.val = DRM_XE_ATOMIC_DEVICE,
  *    };
  *
  *    ioctl(fd, DRM_IOCTL_XE_MADVISE, &madvise);
@@ -2242,7 +2247,7 @@ struct drm_xe_madvise {
 
 			/**
 			 * @preferred_mem_loc.region_instance : Region instance.
-			 * MBZ if @devmem_fd <= &DRM_XE_PREFERRED_LOC_DEFAULT_DEVICE.
+			 * 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.
@@ -2369,24 +2374,19 @@ struct drm_xe_madvise {
 };
 
 /**
- * struct drm_xe_mem_range_attr - Output of &DRM_IOCTL_XE_VM_QUERY_MEM_RANGES_ATTRS
+ * 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_RANGES_ATTRS ioctl. It describes memory attributes of
- * a memory ranges within a user specified address range in a VM.
+ * 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 ranges
- *
- * @extensions: Pointer to the first extension struct, if any
- * @start: Start address of the memory range
- * @end: End address of the virtual memory range
- *
+ * ioctl to retrieve attributes for each memory range.
  */
 struct drm_xe_mem_range_attr {
-	 /** @extensions: Pointer to the first extension struct, if any */
+	/** @extensions: Pointer to the first extension struct, if any */
 	__u64 extensions;
 
 	/** @start: start of the memory range */
@@ -2413,7 +2413,7 @@ struct drm_xe_mem_range_attr {
 		__u32 reserved;
 	} atomic;
 
-	 /** @pat_index: Page attribute table index */
+	/** @pat_index: Page attribute table index */
 	struct {
 		/** @pat_index.val: PAT index */
 		__u32 val;
@@ -2427,7 +2427,7 @@ struct drm_xe_mem_range_attr {
 };
 
 /**
- * struct drm_xe_vm_query_mem_range_attr - Input of &DRM_IOCTL_XE_VM_QUERY_MEM_ATTRIBUTES
+ * 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
@@ -2435,15 +2435,15 @@ struct drm_xe_mem_range_attr {
  * page attribute table (PAT) index, and preferred memory location.
  *
  * Userspace first calls the ioctl with @num_mem_ranges = 0,
- * @sizeof_mem_ranges_attr = 0 and @vector_of_vma_mem_attr = NULL to retrieve
+ * @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_ranges_attr = 0 and @vector_of_vma_mem_attr = NULL followed by
- * Second ioctl call.
+ * @sizeof_mem_range_attr = 0 and @vector_of_mem_attr = NULL followed by
+ * second ioctl call.
  *
  * Example:
  *
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index e72359370857..9584b5aab727 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -48,9 +48,10 @@
  * - 1.20 - Trap handler support for expert scheduling mode available
  * - 1.21 - Debugger support to subscribe to LDS out-of-address exceptions
  * - 1.22 - Add queue creation with metadata ring base address
+ * - 1.23 - Add profiler control ioctl to enable/disable profiler on a process
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 22
+#define KFD_IOCTL_MINOR_VERSION 23
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -1558,6 +1559,36 @@ struct kfd_ioctl_dbg_trap_args {
 	};
 };
 
+#define KFD_IOC_PROFILER_VERSION_NUM 1
+enum kfd_profiler_ops {
+	KFD_IOC_PROFILER_PMC = 0,
+	KFD_IOC_PROFILER_VERSION = 2,
+	KFD_IOC_PROFILER_PTL_CONTROL = 3,
+};
+
+/**
+ * Enables/Disables GPU Specific profiler settings
+ */
+struct kfd_ioctl_pmc_settings {
+	__u32 gpu_id;             /* This is the user_gpu_id */
+	__u32 lock;               /* Lock GPU for Profiling */
+	__u32 perfcount_enable;   /* Force Perfcount Enable for queues on GPU */
+};
+
+struct kfd_ioctl_ptl_control {
+	__u32 gpu_id; /* user_gpu_id */
+	__u32 enable; /* set 1 to enable PTL, set 0 to disable PTL */
+};
+
+struct kfd_ioctl_profiler_args {
+	__u32 op;						/* kfd_profiler_op */
+	union {
+		struct kfd_ioctl_pmc_settings  pmc;
+		struct kfd_ioctl_ptl_control   ptl;
+		__u32 version;				/* KFD_IOC_PROFILER_VERSION_NUM */
+	};
+};
+
 #define AMDKFD_IOCTL_BASE 'K'
 #define AMDKFD_IO(nr)			_IO(AMDKFD_IOCTL_BASE, nr)
 #define AMDKFD_IOR(nr, type)		_IOR(AMDKFD_IOCTL_BASE, nr, type)
@@ -1681,7 +1712,10 @@ struct kfd_ioctl_dbg_trap_args {
 #define AMDKFD_IOC_CREATE_PROCESS		\
 		AMDKFD_IO(0x27)
 
+#define AMDKFD_IOC_PROFILER			\
+		AMDKFD_IOWR(0x28, struct kfd_ioctl_profiler_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x28
+#define AMDKFD_COMMAND_END		0x29
 
 #endif
diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h
index be109777d10d..4f530d90058c 100644
--- a/include/uapi/linux/virtio_gpu.h
+++ b/include/uapi/linux/virtio_gpu.h
@@ -64,6 +64,14 @@
  * context_init and multiple timelines
  */
 #define VIRTIO_GPU_F_CONTEXT_INIT        4
+/*
+ * The device provides a valid blob_alignment
+ * field in its configuration and both
+ * VIRTIO_GPU_CMD_RESOURCE_CREATE_BLOB and
+ * VIRTIO_GPU_CMD_RESOURCE_MAP_BLOB requests
+ * must be aligned to that value.
+ */
+#define VIRTIO_GPU_F_BLOB_ALIGNMENT      5
 
 enum virtio_gpu_ctrl_type {
 	VIRTIO_GPU_UNDEFINED = 0,
@@ -365,6 +373,7 @@ struct virtio_gpu_config {
 	__le32 events_clear;
 	__le32 num_scanouts;
 	__le32 num_capsets;
+	__le32 blob_alignment;
 };
 
 /* simple formats for fbcon/X use */