Merge tag 'drm-next-2023-06-29' of git://anongit.freedesktop.org/drm/drm

Pull drm updates from Dave Airlie:
 "There is one set of patches to misc for a i915 gsc/mei proxy driver.

  Otherwise it's mostly amdgpu/i915/msm, lots of hw enablement and lots
  of refactoring.

  core:
   - replace strlcpy with strscpy
   - EDID changes to support further conversion to struct drm_edid
   - Move i915 DSC parameter code to common DRM helpers
   - Add Colorspace functionality

  aperture:
   - ignore framebuffers with non-primary devices

  fbdev:
   - use fbdev i/o helpers
   - add Kconfig options for fb_ops helpers
   - use new fb io helpers directly in drivers

  sysfs:
   - export DRM connector ID

  scheduler:
   - Avoid an infinite loop

  ttm:
   - store function table in .rodata
   - Add query for TTM mem limit
   - Add NUMA awareness to pools
   - Export ttm_pool_fini()

  bridge:
   - fsl-ldb: support i.MX6SX
   - lt9211, lt9611: remove blanking packets
   - tc358768: implement input bus formats, devm cleanups
   - ti-snd65dsi86: implement wait_hpd_asserted
   - analogix: fix endless probe loop
   - samsung-dsim: support swapped clock, fix enabling, support var
     clock
   - display-connector: Add support for external power supply
   - imx: Fix module linking
   - tc358762: Support reset GPIO

  panel:
   - nt36523: Support Lenovo J606F
   - st7703: Support Anbernic RG353V-V2
   - InnoLux G070ACE-L01 support
   - boe-tv101wum-nl6: Improve initialization
   - sharp-ls043t1le001: Mode fixes
   - simple: BOE EV121WXM-N10-1850, S6D7AA0
   - Ampire AM-800480L1TMQW-T00H
   - Rocktech RK043FN48H
   - Starry himax83102-j02
   - Starry ili9882t

  amdgpu:
   - add new ctx query flag to handle reset better
   - add new query/set shadow buffer for rdna3
   - DCN 3.2/3.1.x/3.0.x updates
   - Enable DC_FP on loongarch
   - PCIe fix for RDNA2
   - improve DC FAMS/SubVP support for better power management
   - partition support for lots of engines
   - Take NUMA into account when allocating memory
   - Add new DRM_AMDGPU_WERROR config parameter to help with CI
   - Initial SMU13 overdrive support
   - Add support for new colorspace KMS API
   - W=1 fixes

  amdkfd:
   - Query TTM mem limit rather than hardcoding it
   - GC 9.4.3 partition support
   - Handle NUMA for partitions
   - Add debugger interface for enabling gdb
   - Add KFD event age tracking

  radeon:
   - Fix possible UAF

  i915:
   - new getparam for PXP support
   - GSC/MEI proxy driver
   - Meteorlake display enablement
   - avoid clearing preallocated framebuffers with TTM
   - implement framebuffer mmap support
   - Disable sampler indirect state in bindless heap
   - Enable fdinfo for GuC backends
   - GuC loading and firmware table handling fixes
   - Various refactors for multi-tile enablement
   - Define MOCS and PAT tables for MTL
   - GSC/MEI support for Meteorlake
   - PMU multi-tile support
   - Large driver kernel doc cleanup
   - Allow VRR toggling and arbitrary refresh rates
   - Support async flips on linear buffers on display ver 12+
   - Expose CRTC CTM property on ILK/SNB/VLV
   - New debugfs for display clock frequencies
   - Hotplug refactoring
   - Display refactoring
   - I915_GEM_CREATE_EXT_SET_PAT for Mesa on Meteorlake
   - Use large rings for compute contexts
   - HuC loading for MTL
   - Allow user to set cache at BO creation
   - MTL powermanagement enhancements
   - Switch to dedicated workqueues to stop using flush_scheduled_work()
   - Move display runtime init under display/
   - Remove 10bit gamma on desktop gen3 parts, they don't support it

  habanalabs:
   - uapi: return 0 for user queries if there was a h/w or f/w error
   - Add pci health check when we lose connection with the firmware.
     This can be used to distinguish between pci link down and firmware
     getting stuck.
   - Add more info to the error print when TPC interrupt occur.
   - Firmware fixes

  msm:
   - Adreno A660 bindings
   - SM8350 MDSS bindings fix
   - Added support for DPU on sm6350 and sm6375 platforms
   - Implemented tearcheck support to support vsync on SM150 and newer
     platforms
   - Enabled missing features (DSPP, DSC, split display) on sc8180x,
     sc8280xp, sm8450
   - Added support for DSI and 28nm DSI PHY on MSM8226 platform
   - Added support for DSI on sm6350 and sm6375 platforms
   - Added support for display controller on MSM8226 platform
   - A690 GPU support
   - Move cmdstream dumping out of fence signaling path
   - a610 support
   - Support for a6xx devices without GMU

  nouveau:
   - NULL ptr before deref fixes

  armada:
   - implement fbdev emulation as client

  sun4i:
   - fix mipi-dsi dotclock
   - release clocks

  vc4:
   - rgb range toggle property
   - BT601 / BT2020 HDMI support

  vkms:
   - convert to drmm helpers
   - add reflection and rotation support
   - fix rgb565 conversion

  gma500:
   - fix iomem access

  shmobile:
   - support renesas soc platform
   - enable fbdev

  mxsfb:
   - Add support for i.MX93 LCDIF

  stm:
   - dsi: Use devm_ helper
   - ltdc: Fix potential invalid pointer deref

  renesas:
   - Group drivers in renesas subdirectory to prepare for new platform
   - Drop deprecated R-Car H3 ES1.x support

  meson:
   - Add support for MIPI DSI displays

  virtio:
   - add sync object support

  mediatek:
   - Add display binding document for MT6795"

* tag 'drm-next-2023-06-29' of git://anongit.freedesktop.org/drm/drm: (1791 commits)
  drm/i915: Fix a NULL vs IS_ERR() bug
  drm/i915: make i915_drm_client_fdinfo() reference conditional again
  drm/i915/huc: Fix missing error code in intel_huc_init()
  drm/i915/gsc: take a wakeref for the proxy-init-completion check
  drm/msm/a6xx: Add A610 speedbin support
  drm/msm/a6xx: Add A619_holi speedbin support
  drm/msm/a6xx: Use adreno_is_aXYZ macros in speedbin matching
  drm/msm/a6xx: Use "else if" in GPU speedbin rev matching
  drm/msm/a6xx: Fix some A619 tunables
  drm/msm/a6xx: Add A610 support
  drm/msm/a6xx: Add support for A619_holi
  drm/msm/adreno: Disable has_cached_coherent in GMU wrapper configurations
  drm/msm/a6xx: Introduce GMU wrapper support
  drm/msm/a6xx: Move CX GMU power counter enablement to hw_init
  drm/msm/a6xx: Extend and explain UBWC config
  drm/msm/a6xx: Remove both GBIF and RBBM GBIF halt on hw init
  drm/msm/a6xx: Add a helper for software-resetting the GPU
  drm/msm/a6xx: Improve a6xx_bus_clear_pending_transactions()
  drm/msm/a6xx: Move a6xx_bus_clear_pending_transactions to a6xx_gpu
  drm/msm/a6xx: Move force keepalive vote removal to a6xx_gmu_force_off()
  ...

7 files changed, 867 insertions, 5 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index b6eb90df5d05..79b14828d542 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -245,6 +245,8 @@ union drm_amdgpu_bo_list {
 /* 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
@@ -592,6 +594,7 @@ struct drm_amdgpu_gem_va {
 #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;
@@ -708,6 +711,15 @@ struct drm_amdgpu_cs_chunk_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
  *
@@ -876,6 +888,8 @@ struct drm_amdgpu_cs_chunk_data {
 	#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
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
@@ -1126,6 +1140,14 @@ struct drm_amdgpu_info_device {
 	__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;
 };
 
 struct drm_amdgpu_info_hw_ip {
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index de703c6be969..8db7fd3f743e 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -658,6 +658,49 @@ extern "C" {
 #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)
+
+/*
  * 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
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 46becedf5b2f..43691058d28f 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -834,6 +834,11 @@ 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];
 };
diff --git a/include/uapi/drm/habanalabs_accel.h b/include/uapi/drm/habanalabs_accel.h
index d9ef1b151d04..e6436f3e8ea6 100644
--- a/include/uapi/drm/habanalabs_accel.h
+++ b/include/uapi/drm/habanalabs_accel.h
@@ -787,18 +787,28 @@ enum hl_server_type {
  *                            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.
  */
 #define HL_INFO_HW_IP_INFO			0
 #define HL_INFO_HW_EVENTS			1
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index dba7c5a5b25e..7000e5910a1d 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -280,7 +280,16 @@ enum drm_i915_pmu_engine_sample {
 #define I915_PMU_ENGINE_SEMA(class, instance) \
 	__I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
 
-#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
+/*
+ * 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)
@@ -290,6 +299,12 @@ enum drm_i915_pmu_engine_sample {
 
 #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
@@ -659,7 +674,8 @@ typedef struct drm_i915_irq_wait {
  * 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 authenticated and running.
+ *  * 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
 
@@ -771,6 +787,25 @@ typedef struct drm_i915_irq_wait {
  */
 #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
+
 /* Must be kept compact -- no holes and well documented */
 
 /**
@@ -2096,6 +2131,21 @@ struct drm_i915_gem_context_param {
  *
  * -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
 /* Must be kept compact -- no holes and well documented */
@@ -3630,9 +3680,13 @@ struct drm_i915_gem_create_ext {
 	 *
 	 * 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;
 };
 
@@ -3747,6 +3801,43 @@ struct drm_i915_gem_create_ext_protected_content {
 	__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
 
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 2da5c3ad71bd..eeb2fdcbdcb7 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -38,9 +38,11 @@
  * - 1.10 - Add SMI profiler event log
  * - 1.11 - Add unified memory for ctx save/restore area
  * - 1.12 - Add DMA buf export ioctl
+ * - 1.13 - Add debugger API
+ * - 1.14 - Update kfd_event_data
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 12
+#define KFD_IOCTL_MINOR_VERSION 14
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -110,6 +112,32 @@ struct kfd_ioctl_get_available_memory_args {
 	__u32 pad;
 };
 
+struct kfd_dbg_device_info_entry {
+	__u64 exception_status;
+	__u64 lds_base;
+	__u64 lds_limit;
+	__u64 scratch_base;
+	__u64 scratch_limit;
+	__u64 gpuvm_base;
+	__u64 gpuvm_limit;
+	__u32 gpu_id;
+	__u32 location_id;
+	__u32 vendor_id;
+	__u32 device_id;
+	__u32 revision_id;
+	__u32 subsystem_vendor_id;
+	__u32 subsystem_device_id;
+	__u32 fw_version;
+	__u32 gfx_target_version;
+	__u32 simd_count;
+	__u32 max_waves_per_simd;
+	__u32 array_count;
+	__u32 simd_arrays_per_engine;
+	__u32 num_xcc;
+	__u32 capability;
+	__u32 debug_prop;
+};
+
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
 #define KFD_IOC_CACHE_POLICY_COHERENT 0
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
@@ -293,12 +321,20 @@ struct kfd_hsa_hw_exception_data {
 	__u32 gpu_id;
 };
 
+/* hsa signal event data */
+struct kfd_hsa_signal_event_data {
+	__u64 last_event_age;	/* to and from KFD */
+};
+
 /* Event data */
 struct kfd_event_data {
 	union {
+		/* From KFD */
 		struct kfd_hsa_memory_exception_data memory_exception_data;
 		struct kfd_hsa_hw_exception_data hw_exception_data;
-	};				/* From KFD */
+		/* To and From KFD */
+		struct kfd_hsa_signal_event_data signal_event_data;
+	};
 	__u64 kfd_event_data_ext;	/* pointer to an extension structure
 					   for future exception types */
 	__u32 event_id;		/* to KFD */
@@ -773,6 +809,640 @@ struct kfd_ioctl_set_xnack_mode_args {
 	__s32 xnack_enabled;
 };
 
+/* Wave launch override modes */
+enum kfd_dbg_trap_override_mode {
+	KFD_DBG_TRAP_OVERRIDE_OR = 0,
+	KFD_DBG_TRAP_OVERRIDE_REPLACE = 1
+};
+
+/* Wave launch overrides */
+enum kfd_dbg_trap_mask {
+	KFD_DBG_TRAP_MASK_FP_INVALID = 1,
+	KFD_DBG_TRAP_MASK_FP_INPUT_DENORMAL = 2,
+	KFD_DBG_TRAP_MASK_FP_DIVIDE_BY_ZERO = 4,
+	KFD_DBG_TRAP_MASK_FP_OVERFLOW = 8,
+	KFD_DBG_TRAP_MASK_FP_UNDERFLOW = 16,
+	KFD_DBG_TRAP_MASK_FP_INEXACT = 32,
+	KFD_DBG_TRAP_MASK_INT_DIVIDE_BY_ZERO = 64,
+	KFD_DBG_TRAP_MASK_DBG_ADDRESS_WATCH = 128,
+	KFD_DBG_TRAP_MASK_DBG_MEMORY_VIOLATION = 256,
+	KFD_DBG_TRAP_MASK_TRAP_ON_WAVE_START = (1 << 30),
+	KFD_DBG_TRAP_MASK_TRAP_ON_WAVE_END = (1 << 31)
+};
+
+/* Wave launch modes */
+enum kfd_dbg_trap_wave_launch_mode {
+	KFD_DBG_TRAP_WAVE_LAUNCH_MODE_NORMAL = 0,
+	KFD_DBG_TRAP_WAVE_LAUNCH_MODE_HALT = 1,
+	KFD_DBG_TRAP_WAVE_LAUNCH_MODE_DEBUG = 3
+};
+
+/* Address watch modes */
+enum kfd_dbg_trap_address_watch_mode {
+	KFD_DBG_TRAP_ADDRESS_WATCH_MODE_READ = 0,
+	KFD_DBG_TRAP_ADDRESS_WATCH_MODE_NONREAD = 1,
+	KFD_DBG_TRAP_ADDRESS_WATCH_MODE_ATOMIC = 2,
+	KFD_DBG_TRAP_ADDRESS_WATCH_MODE_ALL = 3
+};
+
+/* Additional wave settings */
+enum kfd_dbg_trap_flags {
+	KFD_DBG_TRAP_FLAG_SINGLE_MEM_OP = 1,
+};
+
+/* Trap exceptions */
+enum kfd_dbg_trap_exception_code {
+	EC_NONE = 0,
+	/* per queue */
+	EC_QUEUE_WAVE_ABORT = 1,
+	EC_QUEUE_WAVE_TRAP = 2,
+	EC_QUEUE_WAVE_MATH_ERROR = 3,
+	EC_QUEUE_WAVE_ILLEGAL_INSTRUCTION = 4,
+	EC_QUEUE_WAVE_MEMORY_VIOLATION = 5,
+	EC_QUEUE_WAVE_APERTURE_VIOLATION = 6,
+	EC_QUEUE_PACKET_DISPATCH_DIM_INVALID = 16,
+	EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID = 17,
+	EC_QUEUE_PACKET_DISPATCH_CODE_INVALID = 18,
+	EC_QUEUE_PACKET_RESERVED = 19,
+	EC_QUEUE_PACKET_UNSUPPORTED = 20,
+	EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID = 21,
+	EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID = 22,
+	EC_QUEUE_PACKET_VENDOR_UNSUPPORTED = 23,
+	EC_QUEUE_PREEMPTION_ERROR = 30,
+	EC_QUEUE_NEW = 31,
+	/* per device */
+	EC_DEVICE_QUEUE_DELETE = 32,
+	EC_DEVICE_MEMORY_VIOLATION = 33,
+	EC_DEVICE_RAS_ERROR = 34,
+	EC_DEVICE_FATAL_HALT = 35,
+	EC_DEVICE_NEW = 36,
+	/* per process */
+	EC_PROCESS_RUNTIME = 48,
+	EC_PROCESS_DEVICE_REMOVE = 49,
+	EC_MAX
+};
+
+/* Mask generated by ecode in kfd_dbg_trap_exception_code */
+#define KFD_EC_MASK(ecode)	(1ULL << (ecode - 1))
+
+/* Masks for exception code type checks below */
+#define KFD_EC_MASK_QUEUE	(KFD_EC_MASK(EC_QUEUE_WAVE_ABORT) |	\
+				 KFD_EC_MASK(EC_QUEUE_WAVE_TRAP) |	\
+				 KFD_EC_MASK(EC_QUEUE_WAVE_MATH_ERROR) |	\
+				 KFD_EC_MASK(EC_QUEUE_WAVE_ILLEGAL_INSTRUCTION) |	\
+				 KFD_EC_MASK(EC_QUEUE_WAVE_MEMORY_VIOLATION) |	\
+				 KFD_EC_MASK(EC_QUEUE_WAVE_APERTURE_VIOLATION) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_DIM_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_GROUP_SEGMENT_SIZE_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_CODE_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_RESERVED) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_UNSUPPORTED) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_WORK_GROUP_SIZE_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_DISPATCH_REGISTER_INVALID) |	\
+				 KFD_EC_MASK(EC_QUEUE_PACKET_VENDOR_UNSUPPORTED)	|	\
+				 KFD_EC_MASK(EC_QUEUE_PREEMPTION_ERROR)	|	\
+				 KFD_EC_MASK(EC_QUEUE_NEW))
+#define KFD_EC_MASK_DEVICE	(KFD_EC_MASK(EC_DEVICE_QUEUE_DELETE) |		\
+				 KFD_EC_MASK(EC_DEVICE_RAS_ERROR) |		\
+				 KFD_EC_MASK(EC_DEVICE_FATAL_HALT) |		\
+				 KFD_EC_MASK(EC_DEVICE_MEMORY_VIOLATION) |	\
+				 KFD_EC_MASK(EC_DEVICE_NEW))
+#define KFD_EC_MASK_PROCESS	(KFD_EC_MASK(EC_PROCESS_RUNTIME) |	\
+				 KFD_EC_MASK(EC_PROCESS_DEVICE_REMOVE))
+
+/* Checks for exception code types for KFD search */
+#define KFD_DBG_EC_TYPE_IS_QUEUE(ecode)					\
+			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_QUEUE))
+#define KFD_DBG_EC_TYPE_IS_DEVICE(ecode)				\
+			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_DEVICE))
+#define KFD_DBG_EC_TYPE_IS_PROCESS(ecode)				\
+			(!!(KFD_EC_MASK(ecode) & KFD_EC_MASK_PROCESS))
+
+
+/* Runtime enable states */
+enum kfd_dbg_runtime_state {
+	DEBUG_RUNTIME_STATE_DISABLED = 0,
+	DEBUG_RUNTIME_STATE_ENABLED = 1,
+	DEBUG_RUNTIME_STATE_ENABLED_BUSY = 2,
+	DEBUG_RUNTIME_STATE_ENABLED_ERROR = 3
+};
+
+/* Runtime enable status */
+struct kfd_runtime_info {
+	__u64 r_debug;
+	__u32 runtime_state;
+	__u32 ttmp_setup;
+};
+
+/* Enable modes for runtime enable */
+#define KFD_RUNTIME_ENABLE_MODE_ENABLE_MASK	1
+#define KFD_RUNTIME_ENABLE_MODE_TTMP_SAVE_MASK	2
+
+/**
+ * kfd_ioctl_runtime_enable_args - Arguments for runtime enable
+ *
+ * Coordinates debug exception signalling and debug device enablement with runtime.
+ *
+ * @r_debug - pointer to user struct for sharing information between ROCr and the debuggger
+ * @mode_mask - mask to set mode
+ *	KFD_RUNTIME_ENABLE_MODE_ENABLE_MASK - enable runtime for debugging, otherwise disable
+ *	KFD_RUNTIME_ENABLE_MODE_TTMP_SAVE_MASK - enable trap temporary setup (ignore on disable)
+ * @capabilities_mask - mask to notify runtime on what KFD supports
+ *
+ * Return - 0 on SUCCESS.
+ *	  - EBUSY if runtime enable call already pending.
+ *	  - EEXIST if user queues already active prior to call.
+ *	    If process is debug enabled, runtime enable will enable debug devices and
+ *	    wait for debugger process to send runtime exception EC_PROCESS_RUNTIME
+ *	    to unblock - see kfd_ioctl_dbg_trap_args.
+ *
+ */
+struct kfd_ioctl_runtime_enable_args {
+	__u64 r_debug;
+	__u32 mode_mask;
+	__u32 capabilities_mask;
+};
+
+/* Queue information */
+struct kfd_queue_snapshot_entry {
+	__u64 exception_status;
+	__u64 ring_base_address;
+	__u64 write_pointer_address;
+	__u64 read_pointer_address;
+	__u64 ctx_save_restore_address;
+	__u32 queue_id;
+	__u32 gpu_id;
+	__u32 ring_size;
+	__u32 queue_type;
+	__u32 ctx_save_restore_area_size;
+	__u32 reserved;
+};
+
+/* Queue status return for suspend/resume */
+#define KFD_DBG_QUEUE_ERROR_BIT		30
+#define KFD_DBG_QUEUE_INVALID_BIT	31
+#define KFD_DBG_QUEUE_ERROR_MASK	(1 << KFD_DBG_QUEUE_ERROR_BIT)
+#define KFD_DBG_QUEUE_INVALID_MASK	(1 << KFD_DBG_QUEUE_INVALID_BIT)
+
+/* Context save area header information */
+struct kfd_context_save_area_header {
+	struct {
+		__u32 control_stack_offset;
+		__u32 control_stack_size;
+		__u32 wave_state_offset;
+		__u32 wave_state_size;
+	} wave_state;
+	__u32 debug_offset;
+	__u32 debug_size;
+	__u64 err_payload_addr;
+	__u32 err_event_id;
+	__u32 reserved1;
+};
+
+/*
+ * Debug operations
+ *
+ * For specifics on usage and return values, see documentation per operation
+ * below.  Otherwise, generic error returns apply:
+ *	- ESRCH if the process to debug does not exist.
+ *
+ *	- EINVAL (with KFD_IOC_DBG_TRAP_ENABLE exempt) if operation
+ *		 KFD_IOC_DBG_TRAP_ENABLE has not succeeded prior.
+ *		 Also returns this error if GPU hardware scheduling is not supported.
+ *
+ *	- EPERM (with KFD_IOC_DBG_TRAP_DISABLE exempt) if target process is not
+ *		 PTRACE_ATTACHED.  KFD_IOC_DBG_TRAP_DISABLE is exempt to allow
+ *		 clean up of debug mode as long as process is debug enabled.
+ *
+ *	- EACCES if any DBG_HW_OP (debug hardware operation) is requested when
+ *		 AMDKFD_IOC_RUNTIME_ENABLE has not succeeded prior.
+ *
+ *	- ENODEV if any GPU does not support debugging on a DBG_HW_OP call.
+ *
+ *	- Other errors may be returned when a DBG_HW_OP occurs while the GPU
+ *	  is in a fatal state.
+ *
+ */
+enum kfd_dbg_trap_operations {
+	KFD_IOC_DBG_TRAP_ENABLE = 0,
+	KFD_IOC_DBG_TRAP_DISABLE = 1,
+	KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT = 2,
+	KFD_IOC_DBG_TRAP_SET_EXCEPTIONS_ENABLED = 3,
+	KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE = 4,  /* DBG_HW_OP */
+	KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE = 5,      /* DBG_HW_OP */
+	KFD_IOC_DBG_TRAP_SUSPEND_QUEUES = 6,		/* DBG_HW_OP */
+	KFD_IOC_DBG_TRAP_RESUME_QUEUES = 7,		/* DBG_HW_OP */
+	KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH = 8,	/* DBG_HW_OP */
+	KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH = 9,	/* DBG_HW_OP */
+	KFD_IOC_DBG_TRAP_SET_FLAGS = 10,
+	KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT = 11,
+	KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO = 12,
+	KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT = 13,
+	KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT = 14
+};
+
+/**
+ * kfd_ioctl_dbg_trap_enable_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_ENABLE.
+ *
+ *     Enables debug session for target process. Call @op KFD_IOC_DBG_TRAP_DISABLE in
+ *     kfd_ioctl_dbg_trap_args to disable debug session.
+ *
+ *     @exception_mask (IN)	- exceptions to raise to the debugger
+ *     @rinfo_ptr      (IN)	- pointer to runtime info buffer (see kfd_runtime_info)
+ *     @rinfo_size     (IN/OUT)	- size of runtime info buffer in bytes
+ *     @dbg_fd	       (IN)	- fd the KFD will nofify the debugger with of raised
+ *				  exceptions set in exception_mask.
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *		Copies KFD saved kfd_runtime_info to @rinfo_ptr on enable.
+ *		Size of kfd_runtime saved by the KFD returned to @rinfo_size.
+ *            - EBADF if KFD cannot get a reference to dbg_fd.
+ *            - EFAULT if KFD cannot copy runtime info to rinfo_ptr.
+ *            - EINVAL if target process is already debug enabled.
+ *
+ */
+struct kfd_ioctl_dbg_trap_enable_args {
+	__u64 exception_mask;
+	__u64 rinfo_ptr;
+	__u32 rinfo_size;
+	__u32 dbg_fd;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_send_runtime_event_args
+ *
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_SEND_RUNTIME_EVENT.
+ *     Raises exceptions to runtime.
+ *
+ *     @exception_mask (IN) - exceptions to raise to runtime
+ *     @gpu_id	       (IN) - target device id
+ *     @queue_id       (IN) - target queue id
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *	      - ENODEV if gpu_id not found.
+ *		If exception_mask contains EC_PROCESS_RUNTIME, unblocks pending
+ *		AMDKFD_IOC_RUNTIME_ENABLE call - see kfd_ioctl_runtime_enable_args.
+ *		All other exceptions are raised to runtime through err_payload_addr.
+ *		See kfd_context_save_area_header.
+ */
+struct kfd_ioctl_dbg_trap_send_runtime_event_args {
+	__u64 exception_mask;
+	__u32 gpu_id;
+	__u32 queue_id;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_set_exceptions_enabled_args
+ *
+ *     Arguments for KFD_IOC_SET_EXCEPTIONS_ENABLED
+ *     Set new exceptions to be raised to the debugger.
+ *
+ *     @exception_mask (IN) - new exceptions to raise the debugger
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ */
+struct kfd_ioctl_dbg_trap_set_exceptions_enabled_args {
+	__u64 exception_mask;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_set_wave_launch_override_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_OVERRIDE
+ *     Enable HW exceptions to raise trap.
+ *
+ *     @override_mode	     (IN)     - see kfd_dbg_trap_override_mode
+ *     @enable_mask	     (IN/OUT) - reference kfd_dbg_trap_mask.
+ *					IN is the override modes requested to be enabled.
+ *					OUT is referenced in Return below.
+ *     @support_request_mask (IN/OUT) - reference kfd_dbg_trap_mask.
+ *					IN is the override modes requested for support check.
+ *					OUT is referenced in Return below.
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *		Previous enablement is returned in @enable_mask.
+ *		Actual override support is returned in @support_request_mask.
+ *	      - EINVAL if override mode is not supported.
+ *	      - EACCES if trap support requested is not actually supported.
+ *		i.e. enable_mask (IN) is not a subset of support_request_mask (OUT).
+ *		Otherwise it is considered a generic error (see kfd_dbg_trap_operations).
+ */
+struct kfd_ioctl_dbg_trap_set_wave_launch_override_args {
+	__u32 override_mode;
+	__u32 enable_mask;
+	__u32 support_request_mask;
+	__u32 pad;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_set_wave_launch_mode_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_SET_WAVE_LAUNCH_MODE
+ *     Set wave launch mode.
+ *
+ *     @mode (IN) - see kfd_dbg_trap_wave_launch_mode
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ */
+struct kfd_ioctl_dbg_trap_set_wave_launch_mode_args {
+	__u32 launch_mode;
+	__u32 pad;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_suspend_queues_ags
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_SUSPEND_QUEUES
+ *     Suspend queues.
+ *
+ *     @exception_mask	(IN) - raised exceptions to clear
+ *     @queue_array_ptr (IN) - pointer to array of queue ids (u32 per queue id)
+ *			       to suspend
+ *     @num_queues	(IN) - number of queues to suspend in @queue_array_ptr
+ *     @grace_period	(IN) - wave time allowance before preemption
+ *			       per 1K GPU clock cycle unit
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Destruction of a suspended queue is blocked until the queue is
+ *     resumed.  This allows the debugger to access queue information and
+ *     the its context save area without running into a race condition on
+ *     queue destruction.
+ *     Automatically copies per queue context save area header information
+ *     into the save area base
+ *     (see kfd_queue_snapshot_entry and kfd_context_save_area_header).
+ *
+ *     Return - Number of queues suspended on SUCCESS.
+ *	.	KFD_DBG_QUEUE_ERROR_MASK and KFD_DBG_QUEUE_INVALID_MASK masked
+ *		for each queue id in @queue_array_ptr array reports unsuccessful
+ *		suspend reason.
+ *		KFD_DBG_QUEUE_ERROR_MASK = HW failure.
+ *		KFD_DBG_QUEUE_INVALID_MASK = queue does not exist, is new or
+ *		is being destroyed.
+ */
+struct kfd_ioctl_dbg_trap_suspend_queues_args {
+	__u64 exception_mask;
+	__u64 queue_array_ptr;
+	__u32 num_queues;
+	__u32 grace_period;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_resume_queues_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_RESUME_QUEUES
+ *     Resume queues.
+ *
+ *     @queue_array_ptr (IN) - pointer to array of queue ids (u32 per queue id)
+ *			       to resume
+ *     @num_queues	(IN) - number of queues to resume in @queue_array_ptr
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - Number of queues resumed on SUCCESS.
+ *		KFD_DBG_QUEUE_ERROR_MASK and KFD_DBG_QUEUE_INVALID_MASK mask
+ *		for each queue id in @queue_array_ptr array reports unsuccessful
+ *		resume reason.
+ *		KFD_DBG_QUEUE_ERROR_MASK = HW failure.
+ *		KFD_DBG_QUEUE_INVALID_MASK = queue does not exist.
+ */
+struct kfd_ioctl_dbg_trap_resume_queues_args {
+	__u64 queue_array_ptr;
+	__u32 num_queues;
+	__u32 pad;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_set_node_address_watch_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_SET_NODE_ADDRESS_WATCH
+ *     Sets address watch for device.
+ *
+ *     @address	(IN)  - watch address to set
+ *     @mode    (IN)  - see kfd_dbg_trap_address_watch_mode
+ *     @mask    (IN)  - watch address mask
+ *     @gpu_id  (IN)  - target gpu to set watch point
+ *     @id      (OUT) - watch id allocated
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *		Allocated watch ID returned to @id.
+ *	      - ENODEV if gpu_id not found.
+ *	      - ENOMEM if watch IDs can be allocated
+ */
+struct kfd_ioctl_dbg_trap_set_node_address_watch_args {
+	__u64 address;
+	__u32 mode;
+	__u32 mask;
+	__u32 gpu_id;
+	__u32 id;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_clear_node_address_watch_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_CLEAR_NODE_ADDRESS_WATCH
+ *     Clear address watch for device.
+ *
+ *     @gpu_id  (IN)  - target device to clear watch point
+ *     @id      (IN) - allocated watch id to clear
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *	      - ENODEV if gpu_id not found.
+ *	      - EINVAL if watch ID has not been allocated.
+ */
+struct kfd_ioctl_dbg_trap_clear_node_address_watch_args {
+	__u32 gpu_id;
+	__u32 id;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_set_flags_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_SET_FLAGS
+ *     Sets flags for wave behaviour.
+ *
+ *     @flags (IN/OUT) - IN = flags to enable, OUT = flags previously enabled
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *	      - EACCESS if any debug device does not allow flag options.
+ */
+struct kfd_ioctl_dbg_trap_set_flags_args {
+	__u32 flags;
+	__u32 pad;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_query_debug_event_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_QUERY_DEBUG_EVENT
+ *
+ *     Find one or more raised exceptions. This function can return multiple
+ *     exceptions from a single queue or a single device with one call. To find
+ *     all raised exceptions, this function must be called repeatedly until it
+ *     returns -EAGAIN. Returned exceptions can optionally be cleared by
+ *     setting the corresponding bit in the @exception_mask input parameter.
+ *     However, clearing an exception prevents retrieving further information
+ *     about it with KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO.
+ *
+ *     @exception_mask (IN/OUT) - exception to clear (IN) and raised (OUT)
+ *     @gpu_id	       (OUT)    - gpu id of exceptions raised
+ *     @queue_id       (OUT)    - queue id of exceptions raised
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on raised exception found
+ *              Raised exceptions found are returned in @exception mask
+ *              with reported source id returned in @gpu_id or @queue_id.
+ *            - EAGAIN if no raised exception has been found
+ */
+struct kfd_ioctl_dbg_trap_query_debug_event_args {
+	__u64 exception_mask;
+	__u32 gpu_id;
+	__u32 queue_id;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_query_exception_info_args
+ *
+ *     Arguments KFD_IOC_DBG_TRAP_QUERY_EXCEPTION_INFO
+ *     Get additional info on raised exception.
+ *
+ *     @info_ptr	(IN)	 - pointer to exception info buffer to copy to
+ *     @info_size	(IN/OUT) - exception info buffer size (bytes)
+ *     @source_id	(IN)     - target gpu or queue id
+ *     @exception_code	(IN)     - target exception
+ *     @clear_exception	(IN)     - clear raised @exception_code exception
+ *				   (0 = false, 1 = true)
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *              If @exception_code is EC_DEVICE_MEMORY_VIOLATION, copy @info_size(OUT)
+ *		bytes of memory exception data to @info_ptr.
+ *              If @exception_code is EC_PROCESS_RUNTIME, copy saved
+ *              kfd_runtime_info to @info_ptr.
+ *              Actual required @info_ptr size (bytes) is returned in @info_size.
+ */
+struct kfd_ioctl_dbg_trap_query_exception_info_args {
+	__u64 info_ptr;
+	__u32 info_size;
+	__u32 source_id;
+	__u32 exception_code;
+	__u32 clear_exception;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_get_queue_snapshot_args
+ *
+ *     Arguments KFD_IOC_DBG_TRAP_GET_QUEUE_SNAPSHOT
+ *     Get queue information.
+ *
+ *     @exception_mask	 (IN)	  - exceptions raised to clear
+ *     @snapshot_buf_ptr (IN)	  - queue snapshot entry buffer (see kfd_queue_snapshot_entry)
+ *     @num_queues	 (IN/OUT) - number of queue snapshot entries
+ *         The debugger specifies the size of the array allocated in @num_queues.
+ *         KFD returns the number of queues that actually existed. If this is
+ *         larger than the size specified by the debugger, KFD will not overflow
+ *         the array allocated by the debugger.
+ *
+ *     @entry_size	 (IN/OUT) - size per entry in bytes
+ *         The debugger specifies sizeof(struct kfd_queue_snapshot_entry) in
+ *         @entry_size. KFD returns the number of bytes actually populated per
+ *         entry. The debugger should use the KFD_IOCTL_MINOR_VERSION to determine,
+ *         which fields in struct kfd_queue_snapshot_entry are valid. This allows
+ *         growing the ABI in a backwards compatible manner.
+ *         Note that entry_size(IN) should still be used to stride the snapshot buffer in the
+ *         event that it's larger than actual kfd_queue_snapshot_entry.
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *              Copies @num_queues(IN) queue snapshot entries of size @entry_size(IN)
+ *              into @snapshot_buf_ptr if @num_queues(IN) > 0.
+ *              Otherwise return @num_queues(OUT) queue snapshot entries that exist.
+ */
+struct kfd_ioctl_dbg_trap_queue_snapshot_args {
+	__u64 exception_mask;
+	__u64 snapshot_buf_ptr;
+	__u32 num_queues;
+	__u32 entry_size;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_get_device_snapshot_args
+ *
+ *     Arguments for KFD_IOC_DBG_TRAP_GET_DEVICE_SNAPSHOT
+ *     Get device information.
+ *
+ *     @exception_mask	 (IN)	  - exceptions raised to clear
+ *     @snapshot_buf_ptr (IN)	  - pointer to snapshot buffer (see kfd_dbg_device_info_entry)
+ *     @num_devices	 (IN/OUT) - number of debug devices to snapshot
+ *         The debugger specifies the size of the array allocated in @num_devices.
+ *         KFD returns the number of devices that actually existed. If this is
+ *         larger than the size specified by the debugger, KFD will not overflow
+ *         the array allocated by the debugger.
+ *
+ *     @entry_size	 (IN/OUT) - size per entry in bytes
+ *         The debugger specifies sizeof(struct kfd_dbg_device_info_entry) in
+ *         @entry_size. KFD returns the number of bytes actually populated. The
+ *         debugger should use KFD_IOCTL_MINOR_VERSION to determine, which fields
+ *         in struct kfd_dbg_device_info_entry are valid. This allows growing the
+ *         ABI in a backwards compatible manner.
+ *         Note that entry_size(IN) should still be used to stride the snapshot buffer in the
+ *         event that it's larger than actual kfd_dbg_device_info_entry.
+ *
+ *     Generic errors apply (see kfd_dbg_trap_operations).
+ *     Return - 0 on SUCCESS.
+ *              Copies @num_devices(IN) device snapshot entries of size @entry_size(IN)
+ *              into @snapshot_buf_ptr if @num_devices(IN) > 0.
+ *              Otherwise return @num_devices(OUT) queue snapshot entries that exist.
+ */
+struct kfd_ioctl_dbg_trap_device_snapshot_args {
+	__u64 exception_mask;
+	__u64 snapshot_buf_ptr;
+	__u32 num_devices;
+	__u32 entry_size;
+};
+
+/**
+ * kfd_ioctl_dbg_trap_args
+ *
+ * Arguments to debug target process.
+ *
+ *     @pid - target process to debug
+ *     @op  - debug operation (see kfd_dbg_trap_operations)
+ *
+ *     @op determines which union struct args to use.
+ *     Refer to kern docs for each kfd_ioctl_dbg_trap_*_args struct.
+ */
+struct kfd_ioctl_dbg_trap_args {
+	__u32 pid;
+	__u32 op;
+
+	union {
+		struct kfd_ioctl_dbg_trap_enable_args enable;
+		struct kfd_ioctl_dbg_trap_send_runtime_event_args send_runtime_event;
+		struct kfd_ioctl_dbg_trap_set_exceptions_enabled_args set_exceptions_enabled;
+		struct kfd_ioctl_dbg_trap_set_wave_launch_override_args launch_override;
+		struct kfd_ioctl_dbg_trap_set_wave_launch_mode_args launch_mode;
+		struct kfd_ioctl_dbg_trap_suspend_queues_args suspend_queues;
+		struct kfd_ioctl_dbg_trap_resume_queues_args resume_queues;
+		struct kfd_ioctl_dbg_trap_set_node_address_watch_args set_node_address_watch;
+		struct kfd_ioctl_dbg_trap_clear_node_address_watch_args clear_node_address_watch;
+		struct kfd_ioctl_dbg_trap_set_flags_args set_flags;
+		struct kfd_ioctl_dbg_trap_query_debug_event_args query_debug_event;
+		struct kfd_ioctl_dbg_trap_query_exception_info_args query_exception_info;
+		struct kfd_ioctl_dbg_trap_queue_snapshot_args queue_snapshot;
+		struct kfd_ioctl_dbg_trap_device_snapshot_args device_snapshot;
+	};
+};
+
 #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)
@@ -887,7 +1557,13 @@ struct kfd_ioctl_set_xnack_mode_args {
 #define AMDKFD_IOC_EXPORT_DMABUF		\
 		AMDKFD_IOWR(0x24, struct kfd_ioctl_export_dmabuf_args)
 
+#define AMDKFD_IOC_RUNTIME_ENABLE		\
+		AMDKFD_IOWR(0x25, struct kfd_ioctl_runtime_enable_args)
+
+#define AMDKFD_IOC_DBG_TRAP			\
+		AMDKFD_IOWR(0x26, struct kfd_ioctl_dbg_trap_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x25
+#define AMDKFD_COMMAND_END		0x27
 
 #endif
diff --git a/include/uapi/linux/kfd_sysfs.h b/include/uapi/linux/kfd_sysfs.h
index 3e330f368917..a51b7331e0b4 100644
--- a/include/uapi/linux/kfd_sysfs.h
+++ b/include/uapi/linux/kfd_sysfs.h
@@ -43,6 +43,11 @@
 #define HSA_CAP_DOORBELL_TYPE_2_0		0x2
 #define HSA_CAP_AQL_QUEUE_DOUBLE_MAP		0x00004000
 
+#define HSA_CAP_TRAP_DEBUG_SUPPORT              0x00008000
+#define HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_TRAP_OVERRIDE_SUPPORTED  0x00010000
+#define HSA_CAP_TRAP_DEBUG_WAVE_LAUNCH_MODE_SUPPORTED           0x00020000
+#define HSA_CAP_TRAP_DEBUG_PRECISE_MEMORY_OPERATIONS_SUPPORTED  0x00040000
+
 /* Old buggy user mode depends on this being 0 */
 #define HSA_CAP_RESERVED_WAS_SRAM_EDCSUPPORTED	0x00080000
 
@@ -53,8 +58,18 @@
 #define HSA_CAP_SRAM_EDCSUPPORTED		0x04000000
 #define HSA_CAP_SVMAPI_SUPPORTED		0x08000000
 #define HSA_CAP_FLAGS_COHERENTHOSTACCESS	0x10000000
+#define HSA_CAP_TRAP_DEBUG_FIRMWARE_SUPPORTED   0x20000000
 #define HSA_CAP_RESERVED			0xe00f8000
 
+/* debug_prop bits in node properties */
+#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_MASK     0x0000000f
+#define HSA_DBG_WATCH_ADDR_MASK_LO_BIT_SHIFT    0
+#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT_MASK     0x000003f0
+#define HSA_DBG_WATCH_ADDR_MASK_HI_BIT_SHIFT    4
+#define HSA_DBG_DISPATCH_INFO_ALWAYS_VALID      0x00000400
+#define HSA_DBG_WATCHPOINTS_EXCLUSIVE           0x00000800
+#define HSA_DBG_RESERVED                0xfffffffffffff000ull
+
 /* Heap types in memory properties */
 #define HSA_MEM_HEAP_TYPE_SYSTEM	0
 #define HSA_MEM_HEAP_TYPE_FB_PUBLIC	1