Merge drm-next-2025-05-28 into drm-misc-next

Christian needs a recent drm-next branch to merge fence patches.

Signed-off-by: Maxime Ripard <mripard@kernel.org>

3 files changed, 423 insertions, 0 deletions

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 25d5c6e90a99..45c4fa13499c 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -54,6 +54,9 @@ extern "C" {
 #define DRM_AMDGPU_VM			0x13
 #define DRM_AMDGPU_FENCE_TO_HANDLE	0x14
 #define DRM_AMDGPU_SCHED		0x15
+#define DRM_AMDGPU_USERQ		0x16
+#define DRM_AMDGPU_USERQ_SIGNAL		0x17
+#define DRM_AMDGPU_USERQ_WAIT		0x18
 
 #define DRM_IOCTL_AMDGPU_GEM_CREATE	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_CREATE, union drm_amdgpu_gem_create)
 #define DRM_IOCTL_AMDGPU_GEM_MMAP	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_MMAP, union drm_amdgpu_gem_mmap)
@@ -71,6 +74,9 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_VM		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_VM, union drm_amdgpu_vm)
 #define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
 #define DRM_IOCTL_AMDGPU_SCHED		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched)
+#define DRM_IOCTL_AMDGPU_USERQ		DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ, union drm_amdgpu_userq)
+#define DRM_IOCTL_AMDGPU_USERQ_SIGNAL	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_SIGNAL, struct drm_amdgpu_userq_signal)
+#define DRM_IOCTL_AMDGPU_USERQ_WAIT	DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_USERQ_WAIT, struct drm_amdgpu_userq_wait)
 
 /**
  * DOC: memory domains
@@ -319,6 +325,260 @@ union drm_amdgpu_ctx {
 	union drm_amdgpu_ctx_out out;
 };
 
+/* user queue IOCTL operations */
+#define AMDGPU_USERQ_OP_CREATE	1
+#define AMDGPU_USERQ_OP_FREE	2
+
+/* queue priority levels */
+/* low < normal low < normal high < high */
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_MASK  0x3
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_SHIFT 0
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_NORMAL_LOW 0
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_LOW 1
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_NORMAL_HIGH 2
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_PRIORITY_HIGH 3 /* admin only */
+/* for queues that need access to protected content */
+#define AMDGPU_USERQ_CREATE_FLAGS_QUEUE_SECURE  (1 << 2)
+
+/*
+ * This structure is a container to pass input configuration
+ * info for all supported userqueue related operations.
+ * For operation AMDGPU_USERQ_OP_CREATE: user is expected
+ *  to set all fields, excep the parameter 'queue_id'.
+ * For operation AMDGPU_USERQ_OP_FREE: the only input parameter expected
+ *  to be set is 'queue_id', eveything else is ignored.
+ */
+struct drm_amdgpu_userq_in {
+	/** AMDGPU_USERQ_OP_* */
+	__u32	op;
+	/** Queue id passed for operation USERQ_OP_FREE */
+	__u32	queue_id;
+	/** the target GPU engine to execute workload (AMDGPU_HW_IP_*) */
+	__u32   ip_type;
+	/**
+	 * @doorbell_handle: the handle of doorbell GEM object
+	 * associated with this userqueue client.
+	 */
+	__u32   doorbell_handle;
+	/**
+	 * @doorbell_offset: 32-bit offset of the doorbell in the doorbell bo.
+	 * Kernel will generate absolute doorbell offset using doorbell_handle
+	 * and doorbell_offset in the doorbell bo.
+	 */
+	__u32   doorbell_offset;
+	/**
+	 * @flags: flags used for queue parameters
+	 */
+	__u32 flags;
+	/**
+	 * @queue_va: Virtual address of the GPU memory which holds the queue
+	 * object. The queue holds the workload packets.
+	 */
+	__u64   queue_va;
+	/**
+	 * @queue_size: Size of the queue in bytes, this needs to be 256-byte
+	 * aligned.
+	 */
+	__u64   queue_size;
+	/**
+	 * @rptr_va : Virtual address of the GPU memory which holds the ring RPTR.
+	 * This object must be at least 8 byte in size and aligned to 8-byte offset.
+	 */
+	__u64   rptr_va;
+	/**
+	 * @wptr_va : Virtual address of the GPU memory which holds the ring WPTR.
+	 * This object must be at least 8 byte in size and aligned to 8-byte offset.
+	 *
+	 * Queue, RPTR and WPTR can come from the same object, as long as the size
+	 * and alignment related requirements are met.
+	 */
+	__u64   wptr_va;
+	/**
+	 * @mqd: MQD (memory queue descriptor) is a set of parameters which allow
+	 * the GPU to uniquely define and identify a usermode queue.
+	 *
+	 * MQD data can be of different size for different GPU IP/engine and
+	 * their respective versions/revisions, so this points to a __u64 *
+	 * which holds IP specific MQD of this usermode queue.
+	 */
+	__u64 mqd;
+	/**
+	 * @size: size of MQD data in bytes, it must match the MQD structure
+	 * size of the respective engine/revision defined in UAPI for ex, for
+	 * gfx11 workloads, size = sizeof(drm_amdgpu_userq_mqd_gfx11).
+	 */
+	__u64 mqd_size;
+};
+
+/* The structure to carry output of userqueue ops */
+struct drm_amdgpu_userq_out {
+	/**
+	 * For operation AMDGPU_USERQ_OP_CREATE: This field contains a unique
+	 * queue ID to represent the newly created userqueue in the system, otherwise
+	 * it should be ignored.
+	 */
+	__u32	queue_id;
+	__u32 _pad;
+};
+
+union drm_amdgpu_userq {
+	struct drm_amdgpu_userq_in in;
+	struct drm_amdgpu_userq_out out;
+};
+
+/* GFX V11 IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_gfx11 {
+	/**
+	 * @shadow_va: Virtual address of the GPU memory to hold the shadow buffer.
+	 * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+	 */
+	__u64   shadow_va;
+	/**
+	 * @csa_va: Virtual address of the GPU memory to hold the CSA buffer.
+	 * Use AMDGPU_INFO_IOCTL to find the exact size of the object.
+	 */
+	__u64   csa_va;
+};
+
+/* GFX V11 SDMA IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_sdma_gfx11 {
+	/**
+	 * @csa_va: Virtual address of the GPU memory to hold the CSA buffer.
+	 * This must be a from a separate GPU object, and use AMDGPU_INFO IOCTL
+	 * to get the size.
+	 */
+	__u64   csa_va;
+};
+
+/* GFX V11 Compute IP specific MQD parameters */
+struct drm_amdgpu_userq_mqd_compute_gfx11 {
+	/**
+	 * @eop_va: Virtual address of the GPU memory to hold the EOP buffer.
+	 * This must be a from a separate GPU object, and use AMDGPU_INFO IOCTL
+	 * to get the size.
+	 */
+	__u64   eop_va;
+};
+
+/* userq signal/wait ioctl */
+struct drm_amdgpu_userq_signal {
+	/**
+	 * @queue_id: Queue handle used by the userq fence creation function
+	 * to retrieve the WPTR.
+	 */
+	__u32	queue_id;
+	__u32	pad;
+	/**
+	 * @syncobj_handles: The list of syncobj handles submitted by the user queue
+	 * job to be signaled.
+	 */
+	__u64	syncobj_handles;
+	/**
+	 * @num_syncobj_handles: A count that represents the number of syncobj handles in
+	 * @syncobj_handles.
+	 */
+	__u64	num_syncobj_handles;
+	/**
+	 * @bo_read_handles: The list of BO handles that the submitted user queue job
+	 * is using for read only. This will update BO fences in the kernel.
+	 */
+	__u64	bo_read_handles;
+	/**
+	 * @bo_write_handles: The list of BO handles that the submitted user queue job
+	 * is using for write only. This will update BO fences in the kernel.
+	 */
+	__u64	bo_write_handles;
+	/**
+	 * @num_bo_read_handles: A count that represents the number of read BO handles in
+	 * @bo_read_handles.
+	 */
+	__u32	num_bo_read_handles;
+	/**
+	 * @num_bo_write_handles: A count that represents the number of write BO handles in
+	 * @bo_write_handles.
+	 */
+	__u32	num_bo_write_handles;
+};
+
+struct drm_amdgpu_userq_fence_info {
+	/**
+	 * @va: A gpu address allocated for each queue which stores the
+	 * read pointer (RPTR) value.
+	 */
+	__u64	va;
+	/**
+	 * @value: A 64 bit value represents the write pointer (WPTR) of the
+	 * queue commands which compared with the RPTR value to signal the
+	 * fences.
+	 */
+	__u64	value;
+};
+
+struct drm_amdgpu_userq_wait {
+	/**
+	 * @waitq_id: Queue handle used by the userq wait IOCTL to retrieve the
+	 * wait queue and maintain the fence driver references in it.
+	 */
+	__u32	waitq_id;
+	__u32	pad;
+	/**
+	 * @syncobj_handles: The list of syncobj handles submitted by the user queue
+	 * job to get the va/value pairs.
+	 */
+	__u64	syncobj_handles;
+	/**
+	 * @syncobj_timeline_handles: The list of timeline syncobj handles submitted by
+	 * the user queue job to get the va/value pairs at given @syncobj_timeline_points.
+	 */
+	__u64	syncobj_timeline_handles;
+	/**
+	 * @syncobj_timeline_points: The list of timeline syncobj points submitted by the
+	 * user queue job for the corresponding @syncobj_timeline_handles.
+	 */
+	__u64	syncobj_timeline_points;
+	/**
+	 * @bo_read_handles: The list of read BO handles submitted by the user queue
+	 * job to get the va/value pairs.
+	 */
+	__u64	bo_read_handles;
+	/**
+	 * @bo_write_handles: The list of write BO handles submitted by the user queue
+	 * job to get the va/value pairs.
+	 */
+	__u64	bo_write_handles;
+	/**
+	 * @num_syncobj_timeline_handles: A count that represents the number of timeline
+	 * syncobj handles in @syncobj_timeline_handles.
+	 */
+	__u16	num_syncobj_timeline_handles;
+	/**
+	 * @num_fences: This field can be used both as input and output. As input it defines
+	 * the maximum number of fences that can be returned and as output it will specify
+	 * how many fences were actually returned from the ioctl.
+	 */
+	__u16	num_fences;
+	/**
+	 * @num_syncobj_handles: A count that represents the number of syncobj handles in
+	 * @syncobj_handles.
+	 */
+	__u32	num_syncobj_handles;
+	/**
+	 * @num_bo_read_handles: A count that represents the number of read BO handles in
+	 * @bo_read_handles.
+	 */
+	__u32	num_bo_read_handles;
+	/**
+	 * @num_bo_write_handles: A count that represents the number of write BO handles in
+	 * @bo_write_handles.
+	 */
+	__u32	num_bo_write_handles;
+	/**
+	 * @out_fences: The field is a return value from the ioctl containing the list of
+	 * address/value pairs to wait for.
+	 */
+	__u64	out_fences;
+};
+
 /* vm ioctl */
 #define AMDGPU_VM_OP_RESERVE_VMID	1
 #define AMDGPU_VM_OP_UNRESERVE_VMID	2
@@ -599,6 +859,19 @@ struct drm_amdgpu_gem_va {
 	__u64 offset_in_bo;
 	/** Specify mapping size. Must be correctly aligned. */
 	__u64 map_size;
+	/**
+	 * vm_timeline_point is a sequence number used to add new timeline point.
+	 */
+	__u64 vm_timeline_point;
+	/**
+	 * The vm page table update fence is installed in given vm_timeline_syncobj_out
+	 * at vm_timeline_point.
+	 */
+	__u32 vm_timeline_syncobj_out;
+	/** the number of syncobj handles in @input_fence_syncobj_handles */
+	__u32 num_syncobj_handles;
+	/** Array of sync object handle to wait for given input fences */
+	__u64 input_fence_syncobj_handles;
 };
 
 #define AMDGPU_HW_IP_GFX          0
@@ -940,6 +1213,8 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow {
 #define AMDGPU_INFO_MAX_IBS			0x22
 /* query last page fault info */
 #define AMDGPU_INFO_GPUVM_FAULT			0x23
+/* query FW object size and alignment */
+#define AMDGPU_INFO_UQ_FW_AREAS			0x24
 
 #define AMDGPU_INFO_MMR_SE_INDEX_SHIFT	0
 #define AMDGPU_INFO_MMR_SE_INDEX_MASK	0xff
@@ -1093,6 +1368,7 @@ struct drm_amdgpu_info_vbios {
 #define AMDGPU_VRAM_TYPE_DDR5  10
 #define AMDGPU_VRAM_TYPE_LPDDR4 11
 #define AMDGPU_VRAM_TYPE_LPDDR5 12
+#define AMDGPU_VRAM_TYPE_HBM3E 13
 
 struct drm_amdgpu_info_device {
 	/** PCI Device ID */
@@ -1198,6 +1474,9 @@ struct drm_amdgpu_info_device {
 	__u32 csa_size;
 	/* context save area base virtual alignment for gfx11 */
 	__u32 csa_alignment;
+	/* Userq IP mask (1 << AMDGPU_HW_IP_*) */
+	__u32 userq_ip_mask;
+	__u32 pad;
 };
 
 struct drm_amdgpu_info_hw_ip {
@@ -1216,6 +1495,27 @@ struct drm_amdgpu_info_hw_ip {
 	__u32  ip_discovery_version;
 };
 
+/* GFX metadata BO sizes and alignment info (in bytes) */
+struct drm_amdgpu_info_uq_fw_areas_gfx {
+	/* shadow area size */
+	__u32 shadow_size;
+	/* shadow area base virtual mem alignment */
+	__u32 shadow_alignment;
+	/* context save area size */
+	__u32 csa_size;
+	/* context save area base virtual mem alignment */
+	__u32 csa_alignment;
+};
+
+/* IP specific fw related information used in the
+ * subquery AMDGPU_INFO_UQ_FW_AREAS
+ */
+struct drm_amdgpu_info_uq_fw_areas {
+	union {
+		struct drm_amdgpu_info_uq_fw_areas_gfx gfx;
+	};
+};
+
 struct drm_amdgpu_info_num_handles {
 	/** Max handles as supported by firmware for UVD */
 	__u32  uvd_max_handles;
@@ -1279,6 +1579,23 @@ struct drm_amdgpu_info_gpuvm_fault {
 	__u32 vmhub;
 };
 
+struct drm_amdgpu_info_uq_metadata_gfx {
+	/* shadow area size for gfx11 */
+	__u32 shadow_size;
+	/* shadow area base virtual alignment for gfx11 */
+	__u32 shadow_alignment;
+	/* context save area size for gfx11 */
+	__u32 csa_size;
+	/* context save area base virtual alignment for gfx11 */
+	__u32 csa_alignment;
+};
+
+struct drm_amdgpu_info_uq_metadata {
+	union {
+		struct drm_amdgpu_info_uq_metadata_gfx gfx;
+	};
+};
+
 /*
  * Supported GPU families
  */
diff --git a/include/uapi/drm/nova_drm.h b/include/uapi/drm/nova_drm.h
new file mode 100644
index 000000000000..3ca90ed9d2bb
--- /dev/null
+++ b/include/uapi/drm/nova_drm.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: MIT */
+
+#ifndef __NOVA_DRM_H__
+#define __NOVA_DRM_H__
+
+#include "drm.h"
+
+/* DISCLAIMER: Do not use, this is not a stable uAPI.
+ *
+ * This uAPI serves only testing purposes as long as this driver is still in
+ * development. It is required to implement and test infrastructure which is
+ * upstreamed in the context of this driver. See also [1].
+ *
+ * [1] https://lore.kernel.org/dri-devel/Zfsj0_tb-0-tNrJy@cassiopeiae/T/#u
+ */
+
+#if defined(__cplusplus)
+extern "C" {
+#endif
+
+/*
+ * NOVA_GETPARAM_VRAM_BAR_SIZE
+ *
+ * Query the VRAM BAR size in bytes.
+ */
+#define NOVA_GETPARAM_VRAM_BAR_SIZE	0x1
+
+/**
+ * struct drm_nova_getparam - query GPU and driver metadata
+ */
+struct drm_nova_getparam {
+	/**
+	 * @param: The identifier of the parameter to query.
+	 */
+	__u64 param;
+
+	/**
+	 * @value: The value for the specified parameter.
+	 */
+	__u64 value;
+};
+
+/**
+ * struct drm_nova_gem_create - create a new DRM GEM object
+ */
+struct drm_nova_gem_create {
+	/**
+	 * @handle: The handle of the new DRM GEM object.
+	 */
+	__u32 handle;
+
+	/**
+	 * @pad: 32 bit padding, should be 0.
+	 */
+	__u32 pad;
+
+	/**
+	 * @size: The size of the new DRM GEM object.
+	 */
+	__u64 size;
+};
+
+/**
+ * struct drm_nova_gem_info - query DRM GEM object metadata
+ */
+struct drm_nova_gem_info {
+	/**
+	 * @handle: The handle of the DRM GEM object to query.
+	 */
+	__u32 handle;
+
+	/**
+	 * @pad: 32 bit padding, should be 0.
+	 */
+	__u32 pad;
+
+	/**
+	 * @size: The size of the DRM GEM obejct.
+	 */
+	__u64 size;
+};
+
+#define DRM_NOVA_GETPARAM		0x00
+#define DRM_NOVA_GEM_CREATE		0x01
+#define DRM_NOVA_GEM_INFO		0x02
+
+/* Note: this is an enum so that it can be resolved by Rust bindgen. */
+enum {
+	DRM_IOCTL_NOVA_GETPARAM		= DRM_IOWR(DRM_COMMAND_BASE + DRM_NOVA_GETPARAM,
+						   struct drm_nova_getparam),
+	DRM_IOCTL_NOVA_GEM_CREATE	= DRM_IOWR(DRM_COMMAND_BASE + DRM_NOVA_GEM_CREATE,
+						   struct drm_nova_gem_create),
+	DRM_IOCTL_NOVA_GEM_INFO		= DRM_IOWR(DRM_COMMAND_BASE + DRM_NOVA_GEM_INFO,
+						   struct drm_nova_gem_info),
+};
+
+#if defined(__cplusplus)
+}
+#endif
+
+#endif /* __NOVA_DRM_H__ */
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 1e59344c5673..04c7d283dc7d 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -536,6 +536,8 @@ enum kfd_smi_event {
 	KFD_SMI_EVENT_QUEUE_EVICTION = 9,
 	KFD_SMI_EVENT_QUEUE_RESTORE = 10,
 	KFD_SMI_EVENT_UNMAP_FROM_GPU = 11,
+	KFD_SMI_EVENT_PROCESS_START = 12,
+	KFD_SMI_EVENT_PROCESS_END = 13,
 
 	/*
 	 * max event number, as a flag bit to get events from all processes,
@@ -651,6 +653,9 @@ struct kfd_ioctl_smi_events_args {
 		"%lld -%d @%lx(%lx) %x %d\n", (ns), (pid), (addr), (size),\
 		(node), (unmap_trigger)
 
+#define KFD_EVENT_FMT_PROCESS(pid, task_name)\
+		"%x %s\n", (pid), (task_name)
+
 /**************************************************************************************************
  * CRIU IOCTLs (Checkpoint Restore In Userspace)
  *