Merge tag 'amd-drm-next-6.5-2023-06-09' of https://gitlab.freedesktop.org/agd5f/linux into drm-next

amd-drm-next-6.5-2023-06-02:

amdgpu:
- SR-IOV fixes
- Warning fixes
- Misc code cleanups and spelling fixes
- DCN 3.2 updates
- Improved DC FAMS support for better power management
- Improved DC SubVP support for better power management
- DCN 3.1.x fixes
- Max IB size query
- DC GPU reset fixes
- RAS updates
- DCN 3.0.x fixes
- S/G display fixes
- CP shadow buffer support
- Implement connector force callback
- Z8 power improvements
- PSP 13.0.10 vbflash support
- Mode2 reset fixes
- Store MQDs in VRAM to improve queue switch latency
- VCN 3.x fixes
- JPEG 3.x fixes
- Enable DC_FP on LoongArch
- GFXOFF fixes
- GC 9.4.3 partition support
- SDMA 4.4.2 partition support
- VCN/JPEG 4.0.3 partition support
- VCN 4.0.3 updates
- NBIO 7.9 updates
- GC 9.4.3 updates
- Take NUMA into account when allocating memory
- Handle NUMA for partitions
- SMU 13.0.6 updates
- GC 9.4.3 RAS updates
- Stop including unused swiotlb.h
- SMU 13.0.7 fixes
- Fix clock output ordering on some APUs
- Clean up DC FPGA code
- GFX9 preemption fixes
- Misc irq fixes
- S0ix fixes
- Add new DRM_AMDGPU_WERROR config parameter to help with CI
- PCIe fix for RDNA2
- kdoc fixes
- Documentation updates

amdkfd:
- Query TTM mem limit rather than hardcoding it
- GC 9.4.3 partition support
- Handle NUMA for partitions

radeon:
- Fix possible double free
- Stop including unused swiotlb.h
- Fix possible division by zero

ttm:
- Add query for TTM mem limit
- Add NUMA awareness to pools
- Export ttm_pool_fini()

UAPI:
- Add new ctx query flag to better handle GPU resets
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22290
- Add new interface to query and set shadow buffer for RDNA3
  Mesa MR: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21986
- Add new INFO query for max IB size
  Proposed userspace: https://gitlab.freedesktop.org/bnieuwenhuizen/mesa/-/commits/ib-rejection-v3

amd-drm-next-6.5-2023-06-09:

amdgpu:
- S0ix fixes
- Initial SMU13 Overdrive support
- kdoc fixes
- Misc clode cleanups
- Flexible array fixes
- Display OTG fixes
- SMU 13.0.6 updates
- Revert some broken clock counter updates
- Misc display fixes
- GFX9 preemption fixes
- Add support for newer EEPROM bad page table format
- Add missing radeon secondary id
- Add support for new colorspace KMS API
- CSA fix
- Stable pstate fixes for APUs
- make vbl interface admin only
- Handle PCI accelerator class

amdkfd:
- Add debugger support for gdb

radeon:
- Fix possible UAF

drm:
- Add Colorspace functionality

UAPI:
- Add debugger interface for enabling gdb
  Proposed userspace: https://github.com/ROCm-Developer-Tools/ROCdbgapi/tree/wip-dbgapi
- Add KMS colorspace API
  Discussion: https://lists.freedesktop.org/archives/dri-devel/2023-June/408128.html

From: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20230609174817.7764-1-alexander.deucher@amd.com

8 files changed, 815 insertions, 33 deletions

diff --git a/include/drm/display/drm_dp.h b/include/drm/display/drm_dp.h
index b046f79f4744..02f2ac4dd2df 100644
--- a/include/drm/display/drm_dp.h
+++ b/include/drm/display/drm_dp.h
@@ -1635,7 +1635,7 @@ enum dp_pixelformat {
  *
  * This enum is used to indicate DP VSC SDP Colorimetry formats.
  * It is based on DP 1.4 spec [Table 2-117: VSC SDP Payload for DB16 through
- * DB18] and a name of enum member follows DRM_MODE_COLORIMETRY definition.
+ * DB18] and a name of enum member follows enum drm_colorimetry definition.
  *
  * @DP_COLORIMETRY_DEFAULT: sRGB (IEC 61966-2-1) or
  *                          ITU-R BT.601 colorimetry format
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index e143fef07de9..d300fde6c1a4 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -30,6 +30,7 @@
 #include <linux/notifier.h>
 #include <drm/drm_mode_object.h>
 #include <drm/drm_util.h>
+#include <drm/drm_property.h>
 
 #include <uapi/drm/drm_mode.h>
 
@@ -424,37 +425,106 @@ enum drm_privacy_screen_status {
 	PRIVACY_SCREEN_ENABLED_LOCKED,
 };
 
-/*
- * This is a consolidated colorimetry list supported by HDMI and
+/**
+ * enum drm_colorspace - color space
+ *
+ * This enum is a consolidated colorimetry list supported by HDMI and
  * DP protocol standard. The respective connectors will register
  * a property with the subset of this list (supported by that
  * respective protocol). Userspace will set the colorspace through
  * a colorspace property which will be created and exposed to
  * userspace.
+ *
+ * DP definitions come from the DP v2.0 spec
+ * HDMI definitions come from the CTA-861-H spec
+ *
+ * A note on YCC and RGB variants:
+ *
+ * Since userspace is not aware of the encoding on the wire
+ * (RGB or YCbCr), drivers are free to pick the appropriate
+ * variant, regardless of what userspace selects. E.g., if
+ * BT2020_RGB is selected by userspace a driver will pick
+ * BT2020_YCC if the encoding on the wire is YUV444 or YUV420.
+  *
+ * @DRM_MODE_COLORIMETRY_DEFAULT:
+ *   Driver specific behavior.
+ * @DRM_MODE_COLORIMETRY_NO_DATA:
+ *   Driver specific behavior.
+ * @DRM_MODE_COLORIMETRY_SMPTE_170M_YCC:
+ *   (HDMI)
+ *   SMPTE ST 170M colorimetry format
+ * @DRM_MODE_COLORIMETRY_BT709_YCC:
+ *   (HDMI, DP)
+ *   ITU-R BT.709 colorimetry format
+ * @DRM_MODE_COLORIMETRY_XVYCC_601:
+ *   (HDMI, DP)
+ *   xvYCC601 colorimetry format
+ * @DRM_MODE_COLORIMETRY_XVYCC_709:
+ *   (HDMI, DP)
+ *   xvYCC709 colorimetry format
+ * @DRM_MODE_COLORIMETRY_SYCC_601:
+ *   (HDMI, DP)
+ *   sYCC601 colorimetry format
+ * @DRM_MODE_COLORIMETRY_OPYCC_601:
+ *   (HDMI, DP)
+ *   opYCC601 colorimetry format
+ * @DRM_MODE_COLORIMETRY_OPRGB:
+ *   (HDMI, DP)
+ *   opRGB colorimetry format
+ * @DRM_MODE_COLORIMETRY_BT2020_CYCC:
+ *   (HDMI, DP)
+ *   ITU-R BT.2020 Y'c C'bc C'rc (constant luminance) colorimetry format
+ * @DRM_MODE_COLORIMETRY_BT2020_RGB:
+ *   (HDMI, DP)
+ *   ITU-R BT.2020 R' G' B' colorimetry format
+ * @DRM_MODE_COLORIMETRY_BT2020_YCC:
+ *   (HDMI, DP)
+ *   ITU-R BT.2020 Y' C'b C'r colorimetry format
+ * @DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65:
+ *   (HDMI)
+ *   SMPTE ST 2113 P3D65 colorimetry format
+ * @DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER:
+ *   (HDMI)
+ *   SMPTE ST 2113 P3DCI colorimetry format
+ * @DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED:
+ *   (DP)
+ *   RGB wide gamut fixed point colorimetry format
+ * @DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT:
+ *   (DP)
+ *   RGB wide gamut floating point
+ *   (scRGB (IEC 61966-2-2)) colorimetry format
+ * @DRM_MODE_COLORIMETRY_BT601_YCC:
+ *   (DP)
+ *   ITU-R BT.601 colorimetry format
+ *   The DP spec does not say whether this is the 525 or the 625
+ *   line version.
  */
-
-/* For Default case, driver will set the colorspace */
-#define DRM_MODE_COLORIMETRY_DEFAULT			0
-/* CEA 861 Normal Colorimetry options */
-#define DRM_MODE_COLORIMETRY_NO_DATA			0
-#define DRM_MODE_COLORIMETRY_SMPTE_170M_YCC		1
-#define DRM_MODE_COLORIMETRY_BT709_YCC			2
-/* CEA 861 Extended Colorimetry Options */
-#define DRM_MODE_COLORIMETRY_XVYCC_601			3
-#define DRM_MODE_COLORIMETRY_XVYCC_709			4
-#define DRM_MODE_COLORIMETRY_SYCC_601			5
-#define DRM_MODE_COLORIMETRY_OPYCC_601			6
-#define DRM_MODE_COLORIMETRY_OPRGB			7
-#define DRM_MODE_COLORIMETRY_BT2020_CYCC		8
-#define DRM_MODE_COLORIMETRY_BT2020_RGB			9
-#define DRM_MODE_COLORIMETRY_BT2020_YCC			10
-/* Additional Colorimetry extension added as part of CTA 861.G */
-#define DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65		11
-#define DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER		12
-/* Additional Colorimetry Options added for DP 1.4a VSC Colorimetry Format */
-#define DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED		13
-#define DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT		14
-#define DRM_MODE_COLORIMETRY_BT601_YCC			15
+enum drm_colorspace {
+	/* For Default case, driver will set the colorspace */
+	DRM_MODE_COLORIMETRY_DEFAULT 		= 0,
+	/* CEA 861 Normal Colorimetry options */
+	DRM_MODE_COLORIMETRY_NO_DATA		= 0,
+	DRM_MODE_COLORIMETRY_SMPTE_170M_YCC	= 1,
+	DRM_MODE_COLORIMETRY_BT709_YCC		= 2,
+	/* CEA 861 Extended Colorimetry Options */
+	DRM_MODE_COLORIMETRY_XVYCC_601		= 3,
+	DRM_MODE_COLORIMETRY_XVYCC_709		= 4,
+	DRM_MODE_COLORIMETRY_SYCC_601		= 5,
+	DRM_MODE_COLORIMETRY_OPYCC_601		= 6,
+	DRM_MODE_COLORIMETRY_OPRGB		= 7,
+	DRM_MODE_COLORIMETRY_BT2020_CYCC	= 8,
+	DRM_MODE_COLORIMETRY_BT2020_RGB		= 9,
+	DRM_MODE_COLORIMETRY_BT2020_YCC		= 10,
+	/* Additional Colorimetry extension added as part of CTA 861.G */
+	DRM_MODE_COLORIMETRY_DCI_P3_RGB_D65	= 11,
+	DRM_MODE_COLORIMETRY_DCI_P3_RGB_THEATER	= 12,
+	/* Additional Colorimetry Options added for DP 1.4a VSC Colorimetry Format */
+	DRM_MODE_COLORIMETRY_RGB_WIDE_FIXED	= 13,
+	DRM_MODE_COLORIMETRY_RGB_WIDE_FLOAT	= 14,
+	DRM_MODE_COLORIMETRY_BT601_YCC		= 15,
+	/* not a valid value; merely used for counting */
+	DRM_MODE_COLORIMETRY_COUNT
+};
 
 /**
  * enum drm_bus_flags - bus_flags info for &drm_display_info
@@ -914,7 +984,7 @@ struct drm_connector_state {
 	 * colorspace change on Sink. This is most commonly used to switch
 	 * to wider color gamuts like BT2020.
 	 */
-	u32 colorspace;
+	enum drm_colorspace colorspace;
 
 	/**
 	 * @writeback_job: Writeback job for writeback connectors
@@ -1938,8 +2008,10 @@ int drm_connector_attach_hdr_output_metadata_property(struct drm_connector *conn
 bool drm_connector_atomic_hdr_metadata_equal(struct drm_connector_state *old_state,
 					     struct drm_connector_state *new_state);
 int drm_mode_create_aspect_ratio_property(struct drm_device *dev);
-int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector);
-int drm_mode_create_dp_colorspace_property(struct drm_connector *connector);
+int drm_mode_create_hdmi_colorspace_property(struct drm_connector *connector,
+					     u32 supported_colorspaces);
+int drm_mode_create_dp_colorspace_property(struct drm_connector *connector,
+					   u32 supported_colorspaces);
 int drm_mode_create_content_type_property(struct drm_device *dev);
 int drm_mode_create_suggested_offset_properties(struct drm_device *dev);
 
@@ -2022,6 +2094,7 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter);
 
 bool drm_connector_has_possible_encoder(struct drm_connector *connector,
 					struct drm_encoder *encoder);
+const char *drm_get_colorspace_name(enum drm_colorspace colorspace);
 
 /**
  * drm_for_each_connector_iter - connector_list iterator macro
diff --git a/include/drm/ttm/ttm_pool.h b/include/drm/ttm/ttm_pool.h
index 8ce14f9d202a..30a347e5aa11 100644
--- a/include/drm/ttm/ttm_pool.h
+++ b/include/drm/ttm/ttm_pool.h
@@ -61,12 +61,14 @@ struct ttm_pool_type {
  * struct ttm_pool - Pool for all caching and orders
  *
  * @dev: the device we allocate pages for
+ * @nid: which numa node to use
  * @use_dma_alloc: if coherent DMA allocations should be used
  * @use_dma32: if GFP_DMA32 should be used
  * @caching: pools for each caching/order
  */
 struct ttm_pool {
 	struct device *dev;
+	int nid;
 
 	bool use_dma_alloc;
 	bool use_dma32;
@@ -81,7 +83,7 @@ int ttm_pool_alloc(struct ttm_pool *pool, struct ttm_tt *tt,
 void ttm_pool_free(struct ttm_pool *pool, struct ttm_tt *tt);
 
 void ttm_pool_init(struct ttm_pool *pool, struct device *dev,
-		   bool use_dma_alloc, bool use_dma32);
+		   int nid, bool use_dma_alloc, bool use_dma32);
 void ttm_pool_fini(struct ttm_pool *pool);
 
 int ttm_pool_debugfs(struct ttm_pool *pool, struct seq_file *m);
diff --git a/include/drm/ttm/ttm_tt.h b/include/drm/ttm/ttm_tt.h
index 977ca195a536..a4eff85b1f44 100644
--- a/include/drm/ttm/ttm_tt.h
+++ b/include/drm/ttm/ttm_tt.h
@@ -222,7 +222,7 @@ void ttm_tt_mgr_init(unsigned long num_pages, unsigned long num_dma32_pages);
 
 struct ttm_kmap_iter *ttm_kmap_iter_tt_init(struct ttm_kmap_iter_tt *iter_tt,
 					    struct ttm_tt *tt);
-
+unsigned long ttm_tt_pages_limit(void);
 #if IS_ENABLED(CONFIG_AGP)
 #include <linux/agp_backend.h>
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 95f33dadb2be..f368352b3e0f 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -151,6 +151,9 @@
 #define PCI_CLASS_SP_DPIO		0x1100
 #define PCI_CLASS_SP_OTHER		0x1180
 
+#define PCI_BASE_CLASS_ACCELERATOR	0x12
+#define PCI_CLASS_ACCELERATOR_PROCESSING	0x1200
+
 #define PCI_CLASS_OTHERS		0xff
 
 /* Vendors and devices.  Sort key: vendor first, device next. */
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/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 2da5c3ad71bd..1781e7669982 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -38,9 +38,10 @@
  * - 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
  */
 #define KFD_IOCTL_MAJOR_VERSION 1
-#define KFD_IOCTL_MINOR_VERSION 12
+#define KFD_IOCTL_MINOR_VERSION 13
 
 struct kfd_ioctl_get_version_args {
 	__u32 major_version;	/* from KFD */
@@ -110,6 +111,32 @@ 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
@@ -773,6 +800,640 @@ 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 +1548,13 @@ 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