Merge tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "Highlights:
   - AMD adds some more upcoming HW platforms
   - Intel made Meteorlake stable and started adding Lunarlake
   - nouveau has a bunch of display rework in prepartion for the NVIDIA
     GSP firmware support
   - msm adds a7xx support
   - habanalabs has finished migration to accel subsystem

  Detail summary:

  kernel:
   - add initial vmemdup-user-array

  core:
   - fix platform remove() to return void
   - drm_file owner updated to reflect owner
   - move size calcs to drm buddy allocator
   - let GPUVM build as a module
   - allow variable number of run-queues in scheduler

  edid:
   - handle bad h/v sync_end in EDIDs

  panfrost:
   - add Boris as maintainer

  fbdev:
   - use fb_ops helpers more
   - only allow logo use from fbcon
   - rename fb_pgproto to pgprot_framebuffer
   - add HPD state to drm_connector_oob_hotplug_event
   - convert to fbdev i/o mem helpers

  i915:
   - Enable meteorlake by default
   - Early Xe2 LPD/Lunarlake display enablement
   - Rework subplatforms into IP version checks
   - GuC based TLB invalidation for Meteorlake
   - Display rework for future Xe driver integration
   - LNL FBC features
   - LNL display feature capability reads
   - update recommended fw versions for DG2+
   - drop fastboot module parameter
   - added deviceid for Arrowlake-S
   - drop preproduction workarounds
   - don't disable preemption for resets
   - cleanup inlines in headers
   - PXP firmware loading fix
   - Fix sg list lengths
   - DSC PPS state readout/verification
   - Add more RPL P/U PCI IDs
   - Add new DG2-G12 stepping
   - DP enhanced framing support to state checker
   - Improve shared link bandwidth management
   - stop using GEM macros in display code
   - refactor related code into display code
   - locally enable W=1 warnings
   - remove PSR watchdog timers on LNL

  amdgpu:
   - RAS/FRU EEPROM updatse
   - IP discovery updatses
   - GC 11.5 support
   - DCN 3.5 support
   - VPE 6.1 support
   - NBIO 7.11 support
   - DML2 support
   - lots of IP updates
   - use flexible arrays for bo list handling
   - W=1 fixes
   - Enable seamless boot in more cases
   - Enable context type property for HDMI
   - Rework GPUVM TLB flushing
   - VCN IB start/size alignment fixes

  amdkfd:
   - GC 10/11 fixes
   - GC 11.5 support
   - use partial migration in GPU faults

  radeon:
   - W=1 Fixes
   - fix some possible buffer overflow/NULL derefs

  nouveau:
   - update uapi for NO_PREFETCH
   - scheduler/fence fixes
   - rework suspend/resume for GSP-RM
   - rework display in preparation for GSP-RM

  habanalabs:
   - uapi: expose tsc clock
   - uapi: block access to eventfd through control device
   - uapi: force dma-buf export to PAGE_SIZE alignments
   - complete move to accel subsystem
   - move firmware interface include files
   - perform hard reset on PCIe AXI drain event
   - optimise user interrupt handling

  msm:
   - DP: use existing helpers for DPCD
   - DPU: interrupts reworked
   - gpu: a7xx (a730/a740) support
   - decouple msm_drv from kms for headless devices

  mediatek:
   - MT8188 dsi/dp/edp support
   - DDP GAMMA - 12 bit LUT support
   - connector dynamic selection capability

  rockchip:
   - rv1126 mipi-dsi/vop support
   - add planar formats

  ast:
   - rename constants

  panels:
   - Mitsubishi AA084XE01
   - JDI LPM102A188A
   - LTK050H3148W-CTA6

  ivpu:
   - power management fixes

  qaic:
   - add detach slice bo api

  komeda:
   - add NV12 writeback

  tegra:
   - support NVSYNC/NHSYNC
   - host1x suspend fixes

  ili9882t:
   - separate into own driver"

* tag 'drm-next-2023-10-31-1' of git://anongit.freedesktop.org/drm/drm: (1803 commits)
  drm/amdgpu: Remove unused variables from amdgpu_show_fdinfo
  drm/amdgpu: Remove duplicate fdinfo fields
  drm/amd/amdgpu: avoid to disable gfxhub interrupt when driver is unloaded
  drm/amdgpu: Add EXT_COHERENT support for APU and NUMA systems
  drm/amdgpu: Retrieve CE count from ce_count_lo_chip in EccInfo table
  drm/amdgpu: Identify data parity error corrected in replay mode
  drm/amdgpu: Fix typo in IP discovery parsing
  drm/amd/display: fix S/G display enablement
  drm/amdxcp: fix amdxcp unloads incompletely
  drm/amd/amdgpu: fix the GPU power print error in pm info
  drm/amdgpu: Use pcie domain of xcc acpi objects
  drm/amd: check num of link levels when update pcie param
  drm/amdgpu: Add a read to GFX v9.4.3 ring test
  drm/amd/pm: call smu_cmn_get_smc_version in is_mode1_reset_supported.
  drm/amdgpu: get RAS poison status from DF v4_6_2
  drm/amdgpu: Use discovery table's subrevision
  drm/amd/display: 3.2.256
  drm/amd/display: add interface to query SubVP status
  drm/amd/display: Read before writing Backlight Mode Set Register
  drm/amd/display: Disable SYMCLK32_SE RCO on DCN314
  ...

9 files changed, 151 insertions, 44 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index f477eda6a2b8..ad21c613fec8 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -150,7 +150,7 @@ extern "C" {
  */
 #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 explicitly
+ * 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.
@@ -163,6 +163,14 @@ extern "C" {
  * 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)
 
 struct drm_amdgpu_gem_create_in  {
 	/** the requested memory size */
@@ -241,9 +249,9 @@ union drm_amdgpu_bo_list {
 /* unknown cause */
 #define AMDGPU_CTX_UNKNOWN_RESET	3
 
-/* indicate gpu reset occured after ctx created */
+/* indicate gpu reset occurred after ctx created */
 #define AMDGPU_CTX_QUERY2_FLAGS_RESET    (1<<0)
-/* indicate vram lost occured after ctx created */
+/* 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)
@@ -586,7 +594,8 @@ struct drm_amdgpu_gem_va {
  */
 #define AMDGPU_HW_IP_VCN_ENC      7
 #define AMDGPU_HW_IP_VCN_JPEG     8
-#define AMDGPU_HW_IP_NUM          9
+#define AMDGPU_HW_IP_VPE          9
+#define AMDGPU_HW_IP_NUM          10
 
 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1
 
@@ -797,6 +806,8 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
 	#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
@@ -895,6 +906,8 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
 	#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
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
@@ -1220,6 +1233,20 @@ 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;
+};
+
 /*
  * Supported GPU families
  */
@@ -1238,6 +1265,7 @@ struct drm_amdgpu_info_video_caps {
 #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 */
 
 #if defined(__cplusplus)
 }
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 794c1d857677..de723566c5ae 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -1134,6 +1134,26 @@ extern "C" {
 #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)
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 8db7fd3f743e..3151f1fc7ebb 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -323,6 +323,8 @@ extern "C" {
  * 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
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index ea1b639bcb28..128d09138ceb 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -1032,13 +1032,25 @@ struct drm_mode_crtc_page_flip_target {
 	__u64 user_data;
 };
 
-/* create a dumb scanout buffer */
+/**
+ * struct drm_mode_create_dumb - Create a KMS dumb buffer for scanout.
+ * @height: buffer height in pixels
+ * @width: buffer width in pixels
+ * @bpp: bits per pixel
+ * @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.
+ */
 struct drm_mode_create_dumb {
 	__u32 height;
 	__u32 width;
 	__u32 bpp;
 	__u32 flags;
-	/* handle, pitch, size will be returned */
+
 	__u32 handle;
 	__u32 pitch;
 	__u64 size;
diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h
index e6436f3e8ea6..347c7b62e60e 100644
--- a/include/uapi/drm/habanalabs_accel.h
+++ b/include/uapi/drm/habanalabs_accel.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
  *
- * Copyright 2016-2022 HabanaLabs, Ltd.
+ * Copyright 2016-2023 HabanaLabs, Ltd.
  * All Rights Reserved.
  *
  */
@@ -8,8 +8,7 @@
 #ifndef HABANALABS_H_
 #define HABANALABS_H_
 
-#include <linux/types.h>
-#include <linux/ioctl.h>
+#include <drm/drm.h>
 
 /*
  * Defines that are asic-specific but constitutes as ABI between kernel driver
@@ -607,9 +606,9 @@ enum gaudi2_engine_id {
 /*
  * ASIC specific PLL index
  *
- * Used to retrieve in frequency info of different IPs via
- * HL_INFO_PLL_FREQUENCY under HL_IOCTL_INFO IOCTL. The enums need to be
- * used as an index in struct hl_pll_frequency_info
+ * 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 {
@@ -809,6 +808,7 @@ enum hl_server_type {
  * 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
@@ -845,6 +845,7 @@ enum hl_server_type {
 #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_VERSION_MAX_LEN			128
 #define HL_INFO_CARD_NAME_MAX_LEN		16
@@ -884,11 +885,11 @@ enum hl_server_type {
  * @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 Greco and later.
+ *                         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 Greco and later.
+ *                        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.
@@ -990,6 +991,7 @@ struct hl_info_reset_count {
 struct hl_info_time_sync {
 	__u64 device_time;
 	__u64 host_time;
+	__u64 tsc_time;
 };
 
 /**
@@ -1227,6 +1229,20 @@ struct hl_info_fw_err_event {
 };
 
 /**
+ * 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).
@@ -1409,7 +1425,7 @@ union hl_cb_args {
  *
  * HL_CS_CHUNK_FLAGS_USER_ALLOC_CB:
  *      Indicates if the CB was allocated and mapped by userspace
- *      (relevant to greco and above). User allocated CB is a command buffer,
+ *      (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
@@ -1434,7 +1450,7 @@ struct hl_cs_chunk {
 		 * a DRAM address of the internal CB. In Gaudi, this might also
 		 * represent a mapped host address of the CB.
 		 *
-		 * Greco onwards:
+		 * 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.
 		 *
@@ -2147,6 +2163,13 @@ struct hl_debug_args {
 	__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
@@ -2161,8 +2184,7 @@ struct hl_debug_args {
  * definitions of structures in kernel and userspace, e.g. in case of old
  * userspace and new kernel driver
  */
-#define HL_IOCTL_INFO	\
-		_IOWR('H', 0x01, struct hl_info_args)
+#define DRM_IOCTL_HL_INFO	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_INFO, struct hl_info_args)
 
 /*
  * Command Buffer
@@ -2183,8 +2205,7 @@ struct hl_debug_args {
  * and won't be returned to user.
  *
  */
-#define HL_IOCTL_CB		\
-		_IOWR('H', 0x02, union hl_cb_args)
+#define DRM_IOCTL_HL_CB		DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_CB, union hl_cb_args)
 
 /*
  * Command Submission
@@ -2206,7 +2227,7 @@ struct hl_debug_args {
  * internal. The driver will get completion notifications from the device only
  * on JOBS which are enqueued in the external queues.
  *
- * Greco onwards:
+ * 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.
@@ -2236,8 +2257,7 @@ struct hl_debug_args {
  * and only if CS N and CS N-1 are exactly the same (same CBs for the same
  * queues).
  */
-#define HL_IOCTL_CS			\
-		_IOWR('H', 0x03, union hl_cs_args)
+#define DRM_IOCTL_HL_CS		DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_CS, union hl_cs_args)
 
 /*
  * Wait for Command Submission
@@ -2269,9 +2289,7 @@ struct hl_debug_args {
  * HL_WAIT_CS_STATUS_ABORTED     - The CS was aborted, usually because the
  *                                 device was reset (EIO)
  */
-
-#define HL_IOCTL_WAIT_CS			\
-		_IOWR('H', 0x04, union hl_wait_cs_args)
+#define DRM_IOCTL_HL_WAIT_CS	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_WAIT_CS, union hl_wait_cs_args)
 
 /*
  * Memory
@@ -2288,8 +2306,7 @@ struct hl_debug_args {
  * There is an option for the user to specify the requested virtual address.
  *
  */
-#define HL_IOCTL_MEMORY		\
-		_IOWR('H', 0x05, union hl_mem_args)
+#define DRM_IOCTL_HL_MEMORY	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_MEMORY, union hl_mem_args)
 
 /*
  * Debug
@@ -2315,10 +2332,9 @@ struct hl_debug_args {
  * The driver can decide to "kick out" the user if he abuses this interface.
  *
  */
-#define HL_IOCTL_DEBUG		\
-		_IOWR('H', 0x06, struct hl_debug_args)
+#define DRM_IOCTL_HL_DEBUG	DRM_IOWR(DRM_COMMAND_BASE + HL_IOCTL_DEBUG, struct hl_debug_args)
 
-#define HL_COMMAND_START	0x01
-#define HL_COMMAND_END		0x07
+#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
index 7000e5910a1d..218edb0a96f8 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -38,13 +38,13 @@ extern "C" {
  */
 
 /**
- * DOC: uevents generated by i915 on it's device node
+ * 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,
+ *	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
+ *	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
diff --git a/include/uapi/drm/ivpu_accel.h b/include/uapi/drm/ivpu_accel.h
index a58a14c9f222..262db0c3beee 100644
--- a/include/uapi/drm/ivpu_accel.h
+++ b/include/uapi/drm/ivpu_accel.h
@@ -69,8 +69,20 @@ extern "C" {
 #define DRM_IVPU_CONTEXT_PRIORITY_FOCUS	    2
 #define DRM_IVPU_CONTEXT_PRIORITY_REALTIME  3
 
-#define DRM_IVPU_CAP_METRIC_STREAMER	    1
-#define DRM_IVPU_CAP_DMA_MEMORY_RANGE       2
+/**
+ * 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
 
 /**
  * struct drm_ivpu_param - Get/Set VPU parameters
@@ -123,6 +135,8 @@ struct drm_ivpu_param {
 	 * %DRM_IVPU_PARAM_SKU:
 	 * VPU SKU ID (read-only)
 	 *
+	 * %DRM_IVPU_PARAM_CAPABILITIES:
+	 * Supported capabilities (read-only)
 	 */
 	__u32 param;
 
diff --git a/include/uapi/drm/qaic_accel.h b/include/uapi/drm/qaic_accel.h
index 2d348744a853..43ac5d864512 100644
--- a/include/uapi/drm/qaic_accel.h
+++ b/include/uapi/drm/qaic_accel.h
@@ -242,12 +242,12 @@ struct qaic_attach_slice_entry {
  * @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: In. Total length of the BO.
- *	  If BO is imported (DMABUF/PRIME) then this size
- *	  should not exceed the size of DMABUF provided.
- *	  If BO is allocated using DRM_IOCTL_QAIC_CREATE_BO
- *	  then this size should be exactly same as the size
- *	  provided during DRM_IOCTL_QAIC_CREATE_BO.
+ * @size: In. Total length of BO being used. This should not exceed base
+ *	  size of BO (struct drm_gem_object.base)
+ *	  For BOs being allocated using DRM_IOCTL_QAIC_CREATE_BO, size of
+ *	  BO requested is PAGE_SIZE aligned then allocated hence allocated
+ *	  BO size maybe bigger. This size should not exceed the new
+ *	  PAGE_SIZE aligned BO size.
  * @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.
@@ -372,6 +372,16 @@ struct qaic_perf_stats_entry {
 	__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
@@ -380,6 +390,7 @@ struct qaic_perf_stats_entry {
 #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)
@@ -389,6 +400,7 @@ struct qaic_perf_stats_entry {
 #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)
 }
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index eeb2fdcbdcb7..f0ed68974c54 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -405,6 +405,7 @@ struct kfd_ioctl_acquire_vm_args {
 #define KFD_IOC_ALLOC_MEM_FLAGS_AQL_QUEUE_MEM	(1 << 27)
 #define KFD_IOC_ALLOC_MEM_FLAGS_COHERENT	(1 << 26)
 #define KFD_IOC_ALLOC_MEM_FLAGS_UNCACHED	(1 << 25)
+#define KFD_IOC_ALLOC_MEM_FLAGS_EXT_COHERENT	(1 << 24)
 
 /* Allocate memory for later SVM (shared virtual memory) mapping.
  *
@@ -659,6 +660,8 @@ enum kfd_mmio_remap {
 #define KFD_IOCTL_SVM_FLAG_GPU_READ_MOSTLY     0x00000020
 /* Keep GPU memory mapping always valid as if XNACK is disable */
 #define KFD_IOCTL_SVM_FLAG_GPU_ALWAYS_MAPPED   0x00000040
+/* Fine grained coherency between all devices using device-scope atomics */
+#define KFD_IOCTL_SVM_FLAG_EXT_COHERENT        0x00000080
 
 /**
  * kfd_ioctl_svm_op - SVM ioctl operations