diff options
Diffstat (limited to 'include/uapi')
| -rw-r--r-- | include/uapi/drm/amdgpu_drm.h | 317 | ||||
| -rw-r--r-- | include/uapi/drm/asahi_drm.h | 1194 | ||||
| -rw-r--r-- | include/uapi/drm/drm.h | 4 | ||||
| -rw-r--r-- | include/uapi/drm/drm_fourcc.h | 45 | ||||
| -rw-r--r-- | include/uapi/drm/nova_drm.h | 101 | ||||
| -rw-r--r-- | include/uapi/drm/panthor_drm.h | 23 | ||||
| -rw-r--r-- | include/uapi/drm/virtgpu_drm.h | 6 | ||||
| -rw-r--r-- | include/uapi/drm/xe_drm.h | 6 | ||||
| -rw-r--r-- | include/uapi/linux/blktrace_api.h | 2 | ||||
| -rw-r--r-- | include/uapi/linux/cec-funcs.h | 40 | ||||
| -rw-r--r-- | include/uapi/linux/fscrypt.h | 6 | ||||
| -rw-r--r-- | include/uapi/linux/futex.h | 9 | ||||
| -rw-r--r-- | include/uapi/linux/io_uring.h | 12 | ||||
| -rw-r--r-- | include/uapi/linux/kfd_ioctl.h | 5 | ||||
| -rw-r--r-- | include/uapi/linux/media/amlogic/c3-isp-config.h | 564 | ||||
| -rw-r--r-- | include/uapi/linux/perf_event.h | 657 | ||||
| -rw-r--r-- | include/uapi/linux/pidfd.h | 18 | ||||
| -rw-r--r-- | include/uapi/linux/prctl.h | 7 | ||||
| -rw-r--r-- | include/uapi/linux/stat.h | 8 | ||||
| -rw-r--r-- | include/uapi/linux/taskstats.h | 47 | ||||
| -rw-r--r-- | include/uapi/linux/ublk_cmd.h | 128 | ||||
| -rw-r--r-- | include/uapi/linux/videodev2.h | 18 | ||||
| -rw-r--r-- | include/uapi/linux/virtio_gpu.h | 3 |
23 files changed, 2847 insertions, 373 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/asahi_drm.h b/include/uapi/drm/asahi_drm.h new file mode 100644 index 000000000000..de67f1c603af --- /dev/null +++ b/include/uapi/drm/asahi_drm.h @@ -0,0 +1,1194 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright (C) The Asahi Linux Contributors + * Copyright (C) 2018-2023 Collabora Ltd. + * Copyright (C) 2014-2018 Broadcom + */ +#ifndef _ASAHI_DRM_H_ +#define _ASAHI_DRM_H_ + +#include "drm.h" + +#if defined(__cplusplus) +extern "C" { +#endif + +/** + * DOC: Introduction to the Asahi UAPI + * + * This documentation describes the Asahi IOCTLs. + * + * Just a few generic rules about the data passed to the Asahi IOCTLs (cribbed + * from Panthor): + * + * - Structures must be aligned on 64-bit/8-byte. If the object is not + * naturally aligned, a padding field must be added. + * - Fields must be explicitly aligned to their natural type alignment with + * pad[0..N] fields. + * - All padding fields will be checked by the driver to make sure they are + * zeroed. + * - Flags can be added, but not removed/replaced. + * - New fields can be added to the main structures (the structures + * directly passed to the ioctl). Those fields can be added at the end of + * the structure, or replace existing padding fields. Any new field being + * added must preserve the behavior that existed before those fields were + * added when a value of zero is passed. + * - New fields can be added to indirect objects (objects pointed by the + * main structure), iff those objects are passed a size to reflect the + * size known by the userspace driver (see + * drm_asahi_cmd_header::size). + * - If the kernel driver is too old to know some fields, those will be + * ignored if zero, and otherwise rejected (and so will be zero on output). + * - If userspace is too old to know some fields, those will be zeroed + * (input) before the structure is parsed by the kernel driver. + * - Each new flag/field addition must come with a driver version update so + * the userspace driver doesn't have to guess which flags are supported. + * - Structures should not contain unions, as this would defeat the + * extensibility of such structures. + * - IOCTLs can't be removed or replaced. New IOCTL IDs should be placed + * at the end of the drm_asahi_ioctl_id enum. + */ + +/** + * enum drm_asahi_ioctl_id - IOCTL IDs + * + * Place new ioctls at the end, don't re-order, don't replace or remove entries. + * + * These IDs are not meant to be used directly. Use the DRM_IOCTL_ASAHI_xxx + * definitions instead. + */ +enum drm_asahi_ioctl_id { + /** @DRM_ASAHI_GET_PARAMS: Query device properties. */ + DRM_ASAHI_GET_PARAMS = 0, + + /** @DRM_ASAHI_GET_TIME: Query device time. */ + DRM_ASAHI_GET_TIME, + + /** @DRM_ASAHI_VM_CREATE: Create a GPU VM address space. */ + DRM_ASAHI_VM_CREATE, + + /** @DRM_ASAHI_VM_DESTROY: Destroy a VM. */ + DRM_ASAHI_VM_DESTROY, + + /** @DRM_ASAHI_VM_BIND: Bind/unbind memory to a VM. */ + DRM_ASAHI_VM_BIND, + + /** @DRM_ASAHI_GEM_CREATE: Create a buffer object. */ + DRM_ASAHI_GEM_CREATE, + + /** + * @DRM_ASAHI_GEM_MMAP_OFFSET: Get offset to pass to mmap() to map a + * given GEM handle. + */ + DRM_ASAHI_GEM_MMAP_OFFSET, + + /** @DRM_ASAHI_GEM_BIND_OBJECT: Bind memory as a special object */ + DRM_ASAHI_GEM_BIND_OBJECT, + + /** @DRM_ASAHI_QUEUE_CREATE: Create a scheduling queue. */ + DRM_ASAHI_QUEUE_CREATE, + + /** @DRM_ASAHI_QUEUE_DESTROY: Destroy a scheduling queue. */ + DRM_ASAHI_QUEUE_DESTROY, + + /** @DRM_ASAHI_SUBMIT: Submit commands to a queue. */ + DRM_ASAHI_SUBMIT, +}; + +#define DRM_ASAHI_MAX_CLUSTERS 64 + +/** + * struct drm_asahi_params_global - Global parameters. + * + * This struct may be queried by drm_asahi_get_params. + */ +struct drm_asahi_params_global { + /** @features: Feature bits from drm_asahi_feature */ + __u64 features; + + /** @gpu_generation: GPU generation, e.g. 13 for G13G */ + __u32 gpu_generation; + + /** @gpu_variant: GPU variant as a character, e.g. 'C' for G13C */ + __u32 gpu_variant; + + /** + * @gpu_revision: GPU revision in BCD, e.g. 0x00 for 'A0' or + * 0x21 for 'C1' + */ + __u32 gpu_revision; + + /** @chip_id: Chip ID in BCD, e.g. 0x8103 for T8103 */ + __u32 chip_id; + + /** @num_dies: Number of dies in the SoC */ + __u32 num_dies; + + /** @num_clusters_total: Number of GPU clusters (across all dies) */ + __u32 num_clusters_total; + + /** + * @num_cores_per_cluster: Number of logical cores per cluster + * (including inactive/nonexistent) + */ + __u32 num_cores_per_cluster; + + /** @max_frequency_khz: Maximum GPU core clock frequency */ + __u32 max_frequency_khz; + + /** @core_masks: Bitmask of present/enabled cores per cluster */ + __u64 core_masks[DRM_ASAHI_MAX_CLUSTERS]; + + /** + * @vm_start: VM range start VMA. Together with @vm_end, this defines + * the window of valid GPU VAs. Userspace is expected to subdivide VAs + * out of this window. + * + * This window contains all virtual addresses that userspace needs to + * know about. There may be kernel-internal GPU VAs outside this range, + * but that detail is not relevant here. + */ + __u64 vm_start; + + /** @vm_end: VM range end VMA */ + __u64 vm_end; + + /** + * @vm_kernel_min_size: Minimum kernel VMA window size. + * + * When creating a VM, userspace is required to carve out a section of + * virtual addresses (within the range given by @vm_start and + * @vm_end). The kernel will allocate various internal structures + * within the specified VA range. + * + * Allowing userspace to choose the VA range for the kernel, rather than + * the kernel reserving VAs and requiring userspace to cope, can assist + * in implementing SVM. + */ + __u64 vm_kernel_min_size; + + /** + * @max_commands_per_submission: Maximum number of supported commands + * per submission. This mirrors firmware limits. Userspace must split up + * larger command buffers, which may require inserting additional + * synchronization. + */ + __u32 max_commands_per_submission; + + /** + * @max_attachments: Maximum number of drm_asahi_attachment's per + * command + */ + __u32 max_attachments; + + /** + * @command_timestamp_frequency_hz: Timebase frequency for timestamps + * written during command execution, specified via drm_asahi_timestamp + * structures. As this rate is controlled by the firmware, it is a + * queryable parameter. + * + * Userspace must divide by this frequency to convert timestamps to + * seconds, rather than hardcoding a particular firmware's rate. + */ + __u64 command_timestamp_frequency_hz; +}; + +/** + * enum drm_asahi_feature - Feature bits + * + * This covers only features that userspace cannot infer from the architecture + * version. Most features don't need to be here. + */ +enum drm_asahi_feature { + /** + * @DRM_ASAHI_FEATURE_SOFT_FAULTS: GPU has "soft fault" enabled. Shader + * loads of unmapped memory will return zero. Shader stores to unmapped + * memory will be silently discarded. Note that only shader load/store + * is affected. Other hardware units are not affected, notably including + * texture sampling. + * + * Soft fault is set when initializing the GPU and cannot be runtime + * toggled. Therefore, it is exposed as a feature bit and not a + * userspace-settable flag on the VM. When soft fault is enabled, + * userspace can speculate memory accesses more aggressively. + */ + DRM_ASAHI_FEATURE_SOFT_FAULTS = (1UL) << 0, +}; + +/** + * struct drm_asahi_get_params - Arguments passed to DRM_IOCTL_ASAHI_GET_PARAMS + */ +struct drm_asahi_get_params { + /** @param_group: Parameter group to fetch (MBZ) */ + __u32 param_group; + + /** @pad: MBZ */ + __u32 pad; + + /** @pointer: User pointer to write parameter struct */ + __u64 pointer; + + /** + * @size: Size of the user buffer. In case of older userspace, this may + * be less than sizeof(struct drm_asahi_params_global). The kernel will + * not write past the length specified here, allowing extensibility. + */ + __u64 size; +}; + +/** + * struct drm_asahi_vm_create - Arguments passed to DRM_IOCTL_ASAHI_VM_CREATE + */ +struct drm_asahi_vm_create { + /** + * @kernel_start: Start of the kernel-reserved address range. See + * drm_asahi_params_global::vm_kernel_min_size. + * + * Both @kernel_start and @kernel_end must be within the range of + * valid VAs given by drm_asahi_params_global::vm_start and + * drm_asahi_params_global::vm_end. The size of the kernel range + * (@kernel_end - @kernel_start) must be at least + * drm_asahi_params_global::vm_kernel_min_size. + * + * Userspace must not bind any memory on this VM into this reserved + * range, it is for kernel use only. + */ + __u64 kernel_start; + + /** + * @kernel_end: End of the kernel-reserved address range. See + * @kernel_start. + */ + __u64 kernel_end; + + /** @vm_id: Returned VM ID */ + __u32 vm_id; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_asahi_vm_destroy - Arguments passed to DRM_IOCTL_ASAHI_VM_DESTROY + */ +struct drm_asahi_vm_destroy { + /** @vm_id: VM ID to be destroyed */ + __u32 vm_id; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * enum drm_asahi_gem_flags - Flags for GEM creation + */ +enum drm_asahi_gem_flags { + /** + * @DRM_ASAHI_GEM_WRITEBACK: BO should be CPU-mapped as writeback. + * + * Map as writeback instead of write-combine. This optimizes for CPU + * reads. + */ + DRM_ASAHI_GEM_WRITEBACK = (1L << 0), + + /** + * @DRM_ASAHI_GEM_VM_PRIVATE: BO is private to this GPU VM (no exports). + */ + DRM_ASAHI_GEM_VM_PRIVATE = (1L << 1), +}; + +/** + * struct drm_asahi_gem_create - Arguments passed to DRM_IOCTL_ASAHI_GEM_CREATE + */ +struct drm_asahi_gem_create { + /** @size: Size of the BO */ + __u64 size; + + /** @flags: Combination of drm_asahi_gem_flags flags. */ + __u32 flags; + + /** + * @vm_id: VM ID to assign to the BO, if DRM_ASAHI_GEM_VM_PRIVATE is set + */ + __u32 vm_id; + + /** @handle: Returned GEM handle for the BO */ + __u32 handle; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_asahi_gem_mmap_offset - Arguments passed to + * DRM_IOCTL_ASAHI_GEM_MMAP_OFFSET + */ +struct drm_asahi_gem_mmap_offset { + /** @handle: Handle for the object being mapped. */ + __u32 handle; + + /** @flags: Must be zero */ + __u32 flags; + + /** @offset: The fake offset to use for subsequent mmap call */ + __u64 offset; +}; + +/** + * enum drm_asahi_bind_flags - Flags for GEM binding + */ +enum drm_asahi_bind_flags { + /** + * @DRM_ASAHI_BIND_UNBIND: Instead of binding a GEM object to the range, + * simply unbind the GPU VMA range. + */ + DRM_ASAHI_BIND_UNBIND = (1L << 0), + + /** @DRM_ASAHI_BIND_READ: Map BO with GPU read permission */ + DRM_ASAHI_BIND_READ = (1L << 1), + + /** @DRM_ASAHI_BIND_WRITE: Map BO with GPU write permission */ + DRM_ASAHI_BIND_WRITE = (1L << 2), + + /** + * @DRM_ASAHI_BIND_SINGLE_PAGE: Map a single page of the BO repeatedly + * across the VA range. + * + * This is useful to fill a VA range with scratch pages or zero pages. + * It is intended as a mechanism to accelerate sparse. + */ + DRM_ASAHI_BIND_SINGLE_PAGE = (1L << 3), +}; + +/** + * struct drm_asahi_gem_bind_op - Description of a single GEM bind operation. + */ +struct drm_asahi_gem_bind_op { + /** @flags: Combination of drm_asahi_bind_flags flags. */ + __u32 flags; + + /** @handle: GEM object to bind (except for UNBIND) */ + __u32 handle; + + /** + * @offset: Offset into the object (except for UNBIND). + * + * For a regular bind, this is the beginning of the region of the GEM + * object to bind. + * + * For a single-page bind, this is the offset to the single page that + * will be repeatedly bound. + * + * Must be page-size aligned. + */ + __u64 offset; + + /** + * @range: Number of bytes to bind/unbind to @addr. + * + * Must be page-size aligned. + */ + __u64 range; + + /** + * @addr: Address to bind to. + * + * Must be page-size aligned. + */ + __u64 addr; +}; + +/** + * struct drm_asahi_vm_bind - Arguments passed to + * DRM_IOCTL_ASAHI_VM_BIND + */ +struct drm_asahi_vm_bind { + /** @vm_id: The ID of the VM to bind to */ + __u32 vm_id; + + /** @num_binds: number of binds in this IOCTL. */ + __u32 num_binds; + + /** + * @stride: Stride in bytes between consecutive binds. This allows + * extensibility of drm_asahi_gem_bind_op. + */ + __u32 stride; + + /** @pad: MBZ */ + __u32 pad; + + /** + * @userptr: User pointer to an array of @num_binds structures of type + * @drm_asahi_gem_bind_op and size @stride bytes. + */ + __u64 userptr; +}; + +/** + * enum drm_asahi_bind_object_op - Special object bind operation + */ +enum drm_asahi_bind_object_op { + /** @DRM_ASAHI_BIND_OBJECT_OP_BIND: Bind a BO as a special GPU object */ + DRM_ASAHI_BIND_OBJECT_OP_BIND = 0, + + /** @DRM_ASAHI_BIND_OBJECT_OP_UNBIND: Unbind a special GPU object */ + DRM_ASAHI_BIND_OBJECT_OP_UNBIND = 1, +}; + +/** + * enum drm_asahi_bind_object_flags - Special object bind flags + */ +enum drm_asahi_bind_object_flags { + /** + * @DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS: Map a BO as a timestamp + * buffer. + */ + DRM_ASAHI_BIND_OBJECT_USAGE_TIMESTAMPS = (1L << 0), +}; + +/** + * struct drm_asahi_gem_bind_object - Arguments passed to + * DRM_IOCTL_ASAHI_GEM_BIND_OBJECT + */ +struct drm_asahi_gem_bind_object { + /** @op: Bind operation (enum drm_asahi_bind_object_op) */ + __u32 op; + + /** @flags: Combination of drm_asahi_bind_object_flags flags. */ + __u32 flags; + + /** @handle: GEM object to bind/unbind (BIND) */ + __u32 handle; + + /** @vm_id: The ID of the VM to operate on (MBZ currently) */ + __u32 vm_id; + + /** @offset: Offset into the object (BIND only) */ + __u64 offset; + + /** @range: Number of bytes to bind/unbind (BIND only) */ + __u64 range; + + /** @object_handle: Object handle (out for BIND, in for UNBIND) */ + __u32 object_handle; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * enum drm_asahi_cmd_type - Command type + */ +enum drm_asahi_cmd_type { + /** + * @DRM_ASAHI_CMD_RENDER: Render command, executing on the render + * subqueue. Combined vertex and fragment operation. + * + * Followed by a @drm_asahi_cmd_render payload. + */ + DRM_ASAHI_CMD_RENDER = 0, + + /** + * @DRM_ASAHI_CMD_COMPUTE: Compute command on the compute subqueue. + * + * Followed by a @drm_asahi_cmd_compute payload. + */ + DRM_ASAHI_CMD_COMPUTE = 1, + + /** + * @DRM_ASAHI_SET_VERTEX_ATTACHMENTS: Software command to set + * attachments for subsequent vertex shaders in the same submit. + * + * Followed by (possibly multiple) @drm_asahi_attachment payloads. + */ + DRM_ASAHI_SET_VERTEX_ATTACHMENTS = 2, + + /** + * @DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS: Software command to set + * attachments for subsequent fragment shaders in the same submit. + * + * Followed by (possibly multiple) @drm_asahi_attachment payloads. + */ + DRM_ASAHI_SET_FRAGMENT_ATTACHMENTS = 3, + + /** + * @DRM_ASAHI_SET_COMPUTE_ATTACHMENTS: Software command to set + * attachments for subsequent compute shaders in the same submit. + * + * Followed by (possibly multiple) @drm_asahi_attachment payloads. + */ + DRM_ASAHI_SET_COMPUTE_ATTACHMENTS = 4, +}; + +/** + * enum drm_asahi_priority - Scheduling queue priority. + * + * These priorities are forwarded to the firmware to influence firmware + * scheduling. The exact policy is ultimately decided by firmware, but + * these enums allow userspace to communicate the intentions. + */ +enum drm_asahi_priority { + /** @DRM_ASAHI_PRIORITY_LOW: Low priority queue. */ + DRM_ASAHI_PRIORITY_LOW = 0, + + /** @DRM_ASAHI_PRIORITY_MEDIUM: Medium priority queue. */ + DRM_ASAHI_PRIORITY_MEDIUM = 1, + + /** + * @DRM_ASAHI_PRIORITY_HIGH: High priority queue. + * + * Reserved for future extension. + */ + DRM_ASAHI_PRIORITY_HIGH = 2, + + /** + * @DRM_ASAHI_PRIORITY_REALTIME: Real-time priority queue. + * + * Reserved for future extension. + */ + DRM_ASAHI_PRIORITY_REALTIME = 3, +}; + +/** + * struct drm_asahi_queue_create - Arguments passed to + * DRM_IOCTL_ASAHI_QUEUE_CREATE + */ +struct drm_asahi_queue_create { + /** @flags: MBZ */ + __u32 flags; + + /** @vm_id: The ID of the VM this queue is bound to */ + __u32 vm_id; + + /** @priority: One of drm_asahi_priority */ + __u32 priority; + + /** @queue_id: The returned queue ID */ + __u32 queue_id; + + /** + * @usc_exec_base: GPU base address for all USC binaries (shaders) on + * this queue. USC addresses are 32-bit relative to this 64-bit base. + * + * This sets the following registers on all queue commands: + * + * USC_EXEC_BASE_TA (vertex) + * USC_EXEC_BASE_ISP (fragment) + * USC_EXEC_BASE_CP (compute) + * + * While the hardware lets us configure these independently per command, + * we do not have a use case for this. Instead, we expect userspace to + * fix a 4GiB VA carveout for USC memory and pass its base address here. + */ + __u64 usc_exec_base; +}; + +/** + * struct drm_asahi_queue_destroy - Arguments passed to + * DRM_IOCTL_ASAHI_QUEUE_DESTROY + */ +struct drm_asahi_queue_destroy { + /** @queue_id: The queue ID to be destroyed */ + __u32 queue_id; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * enum drm_asahi_sync_type - Sync item type + */ +enum drm_asahi_sync_type { + /** @DRM_ASAHI_SYNC_SYNCOBJ: Binary sync object */ + DRM_ASAHI_SYNC_SYNCOBJ = 0, + + /** @DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ: Timeline sync object */ + DRM_ASAHI_SYNC_TIMELINE_SYNCOBJ = 1, +}; + +/** + * struct drm_asahi_sync - Sync item + */ +struct drm_asahi_sync { + /** @sync_type: One of drm_asahi_sync_type */ + __u32 sync_type; + + /** @handle: The sync object handle */ + __u32 handle; + + /** @timeline_value: Timeline value for timeline sync objects */ + __u64 timeline_value; +}; + +/** + * define DRM_ASAHI_BARRIER_NONE - Command index for no barrier + * + * This special value may be passed in to drm_asahi_command::vdm_barrier or + * drm_asahi_command::cdm_barrier to indicate that the respective subqueue + * should not wait on any previous work. + */ +#define DRM_ASAHI_BARRIER_NONE (0xFFFFu) + +/** + * struct drm_asahi_cmd_header - Top level command structure + * + * This struct is core to the command buffer definition and therefore is not + * extensible. + */ +struct drm_asahi_cmd_header { + /** @cmd_type: One of drm_asahi_cmd_type */ + __u16 cmd_type; + + /** + * @size: Size of this command, not including this header. + * + * For hardware commands, this enables extensibility of commands without + * requiring extra command types. Passing a command that is shorter + * than expected is explicitly allowed for backwards-compatibility. + * Truncated fields will be zeroed. + * + * For the synthetic attachment setting commands, this implicitly + * encodes the number of attachments. These commands take multiple + * fixed-size @drm_asahi_attachment structures as their payload, so size + * equals number of attachments * sizeof(struct drm_asahi_attachment). + */ + __u16 size; + + /** + * @vdm_barrier: VDM (render) command index to wait on. + * + * Barriers are indices relative to the beginning of a given submit. A + * barrier of 0 waits on commands submitted to the respective subqueue + * in previous submit ioctls. A barrier of N waits on N previous + * commands on the subqueue within the current submit ioctl. As a + * special case, passing @DRM_ASAHI_BARRIER_NONE avoids waiting on any + * commands in the subqueue. + * + * Examples: + * + * 0: This waits on all previous work. + * + * NONE: This does not wait for anything on this subqueue. + * + * 1: This waits on the first render command in the submit. + * This is valid only if there are multiple render commands in the + * same submit. + * + * Barriers are valid only for hardware commands. Synthetic software + * commands to set attachments must pass NONE here. + */ + __u16 vdm_barrier; + + /** + * @cdm_barrier: CDM (compute) command index to wait on. + * + * See @vdm_barrier, and replace VDM/render with CDM/compute. + */ + __u16 cdm_barrier; +}; + +/** + * struct drm_asahi_submit - Arguments passed to DRM_IOCTL_ASAHI_SUBMIT + */ +struct drm_asahi_submit { + /** + * @syncs: An optional pointer to an array of drm_asahi_sync. The first + * @in_sync_count elements are in-syncs, then the remaining + * @out_sync_count elements are out-syncs. Using a single array with + * explicit partitioning simplifies handling. + */ + __u64 syncs; + + /** + * @cmdbuf: Pointer to the command buffer to submit. + * + * This is a flat command buffer. By design, it contains no CPU + * pointers, which makes it suitable for a virtgpu wire protocol without + * requiring any serializing/deserializing step. + * + * It consists of a series of commands. Each command begins with a + * fixed-size @drm_asahi_cmd_header header and is followed by a + * variable-length payload according to the type and size in the header. + * + * The combined count of "real" hardware commands must be nonzero and at + * most drm_asahi_params_global::max_commands_per_submission. + */ + __u64 cmdbuf; + + /** @flags: Flags for command submission (MBZ) */ + __u32 flags; + + /** @queue_id: The queue ID to be submitted to */ + __u32 queue_id; + + /** + * @in_sync_count: Number of sync objects to wait on before starting + * this job. + */ + __u32 in_sync_count; + + /** + * @out_sync_count: Number of sync objects to signal upon completion of + * this job. + */ + __u32 out_sync_count; + + /** @cmdbuf_size: Command buffer size in bytes */ + __u32 cmdbuf_size; + + /** @pad: MBZ */ + __u32 pad; +}; + +/** + * struct drm_asahi_attachment - Describe an "attachment". + * + * Attachments are any memory written by shaders, notably including render + * target attachments written by the end-of-tile program. This is purely a hint + * about the accessed memory regions. It is optional to specify, which is + * fortunate as it cannot be specified precisely with bindless access anyway. + * But where possible, it's probably a good idea for userspace to include these + * hints, forwarded to the firmware. + * + * This struct is implicitly sized and therefore is not extensible. + */ +struct drm_asahi_attachment { + /** @pointer: Base address of the attachment */ + __u64 pointer; + + /** @size: Size of the attachment in bytes */ + __u64 size; + + /** @pad: MBZ */ + __u32 pad; + + /** @flags: MBZ */ + __u32 flags; +}; + +enum drm_asahi_render_flags { + /** + * @DRM_ASAHI_RENDER_VERTEX_SCRATCH: A vertex stage shader uses scratch + * memory. + */ + DRM_ASAHI_RENDER_VERTEX_SCRATCH = (1U << 0), + + /** + * @DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES: Process even empty tiles. + * This must be set when clearing render targets. + */ + DRM_ASAHI_RENDER_PROCESS_EMPTY_TILES = (1U << 1), + + /** + * @DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING: Run vertex stage on a single + * cluster (on multi-cluster GPUs) + * + * This harms performance but can workaround certain sync/coherency + * bugs, and therefore is useful for debugging. + */ + DRM_ASAHI_RENDER_NO_VERTEX_CLUSTERING = (1U << 2), + + /** + * @DRM_ASAHI_RENDER_DBIAS_IS_INT: Use integer depth bias formula. + * + * Graphics specifications contain two alternate formulas for depth + * bias, a float formula used with floating-point depth buffers and an + * integer formula using with unorm depth buffers. This flag specifies + * that the integer formula should be used. If omitted, the float + * formula is used instead. + * + * This corresponds to bit 18 of the relevant hardware control register, + * so we match that here for efficiency. + */ + DRM_ASAHI_RENDER_DBIAS_IS_INT = (1U << 18), +}; + +/** + * struct drm_asahi_zls_buffer - Describe a depth or stencil buffer. + * + * These fields correspond to hardware registers in the ZLS (Z Load/Store) unit. + * There are three hardware registers for each field respectively for loads, + * stores, and partial renders. In practice, it makes sense to set all to the + * same values, except in exceptional cases not yet implemented in userspace, so + * we do not duplicate here for simplicity/efficiency. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_zls_buffer { + /** @base: Base address of the buffer */ + __u64 base; + + /** + * @comp_base: If the load buffer is compressed, address of the + * compression metadata section. + */ + __u64 comp_base; + + /** + * @stride: If layered rendering is enabled, the number of bytes + * between each layer of the buffer. + */ + __u32 stride; + + /** + * @comp_stride: If layered rendering is enabled, the number of bytes + * between each layer of the compression metadata. + */ + __u32 comp_stride; +}; + +/** + * struct drm_asahi_timestamp - Describe a timestamp write. + * + * The firmware can optionally write the GPU timestamp at render pass + * granularities, but it needs to be mapped specially via + * DRM_IOCTL_ASAHI_GEM_BIND_OBJECT. This structure therefore describes where to + * write as a handle-offset pair, rather than a GPU address like normal. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_timestamp { + /** + * @handle: Handle of the timestamp buffer, or 0 to skip this + * timestamp. If nonzero, this must equal the value returned in + * drm_asahi_gem_bind_object::object_handle. + */ + __u32 handle; + + /** @offset: Offset to write into the timestamp buffer */ + __u32 offset; +}; + +/** + * struct drm_asahi_timestamps - Describe timestamp writes. + * + * Each operation that can be timestamped, can be timestamped at the start and + * end. Therefore, drm_asahi_timestamp structs always come in pairs, bundled + * together into drm_asahi_timestamps. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_timestamps { + /** @start: Timestamp recorded at the start of the operation */ + struct drm_asahi_timestamp start; + + /** @end: Timestamp recorded at the end of the operation */ + struct drm_asahi_timestamp end; +}; + +/** + * struct drm_asahi_helper_program - Describe helper program configuration. + * + * The helper program is a compute-like kernel required for various hardware + * functionality. Its most important role is dynamically allocating + * scratch/stack memory for individual subgroups, by partitioning a static + * allocation shared for the whole device. It is supplied by userspace via + * drm_asahi_helper_program and internally dispatched by the hardware as needed. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_helper_program { + /** + * @binary: USC address to the helper program binary. This is a tagged + * pointer with configuration in the bottom bits. + */ + __u32 binary; + + /** @cfg: Additional configuration bits for the helper program. */ + __u32 cfg; + + /** + * @data: Data passed to the helper program. This value is not + * interpreted by the kernel, firmware, or hardware in any way. It is + * simply a sideband for userspace, set with the submit ioctl and read + * via special registers inside the helper program. + * + * In practice, userspace will pass a 64-bit GPU VA here pointing to the + * actual arguments, which presumably don't fit in 64-bits. + */ + __u64 data; +}; + +/** + * struct drm_asahi_bg_eot - Describe a background or end-of-tile program. + * + * The background and end-of-tile programs are dispatched by the hardware at the + * beginning and end of rendering. As the hardware "tilebuffer" is simply local + * memory, these programs are necessary to implement API-level render targets. + * The fragment-like background program is responsible for loading either the + * clear colour or the existing render target contents, while the compute-like + * end-of-tile program stores the tilebuffer contents to memory. + * + * This struct is embedded in other structs and therefore is not extensible. + */ +struct drm_asahi_bg_eot { + /** + * @usc: USC address of the hardware USC words binding resources + * (including images and uniforms) and the program itself. Note this is + * an additional layer of indirection compared to the helper program, + * avoiding the need for a sideband for data. This is a tagged pointer + * with additional configuration in the bottom bits. + */ + __u32 usc; + + /** + * @rsrc_spec: Resource specifier for the program. This is a packed + * hardware data structure describing the required number of registers, + * uniforms, bound textures, and bound samplers. + */ + __u32 rsrc_spec; +}; + +/** + * struct drm_asahi_cmd_render - Command to submit 3D + * + * This command submits a single render pass. The hardware control stream may + * include many draws and subpasses, but within the command, the framebuffer + * dimensions and attachments are fixed. + * + * The hardware requires the firmware to set a large number of Control Registers + * setting up state at render pass granularity before each command rendering 3D. + * The firmware bundles this state into data structures. Unfortunately, we + * cannot expose either any of that directly to userspace, because the + * kernel-firmware ABI is not stable. Although we can guarantee the firmware + * updates in tandem with the kernel, we cannot break old userspace when + * upgrading the firmware and kernel. Therefore, we need to abstract well the + * data structures to avoid tying our hands with future firmwares. + * + * The bulk of drm_asahi_cmd_render therefore consists of values of hardware + * control registers, marshalled via the firmware interface. + * + * The framebuffer/tilebuffer dimensions are also specified here. In addition to + * being passed to the firmware/hardware, the kernel requires these dimensions + * to calculate various essential tiling-related data structures. It is + * unfortunate that our submits are heavier than on vendors with saner + * hardware-software interfaces. The upshot is all of this information is + * readily available to userspace with all current APIs. + * + * It looks odd - but it's not overly burdensome and it ensures we can remain + * compatible with old userspace. + */ +struct drm_asahi_cmd_render { + /** @flags: Combination of drm_asahi_render_flags flags. */ + __u32 flags; + + /** + * @isp_zls_pixels: ISP_ZLS_PIXELS register value. This contains the + * depth/stencil width/height, which may differ from the framebuffer + * width/height. + */ + __u32 isp_zls_pixels; + + /** + * @vdm_ctrl_stream_base: VDM_CTRL_STREAM_BASE register value. GPU + * address to the beginning of the VDM control stream. + */ + __u64 vdm_ctrl_stream_base; + + /** @vertex_helper: Helper program used for the vertex shader */ + struct drm_asahi_helper_program vertex_helper; + + /** @fragment_helper: Helper program used for the fragment shader */ + struct drm_asahi_helper_program fragment_helper; + + /** + * @isp_scissor_base: ISP_SCISSOR_BASE register value. GPU address of an + * array of scissor descriptors indexed in the render pass. + */ + __u64 isp_scissor_base; + + /** + * @isp_dbias_base: ISP_DBIAS_BASE register value. GPU address of an + * array of depth bias values indexed in the render pass. + */ + __u64 isp_dbias_base; + + /** + * @isp_oclqry_base: ISP_OCLQRY_BASE register value. GPU address of an + * array of occlusion query results written by the render pass. + */ + __u64 isp_oclqry_base; + + /** @depth: Depth buffer */ + struct drm_asahi_zls_buffer depth; + + /** @stencil: Stencil buffer */ + struct drm_asahi_zls_buffer stencil; + + /** @zls_ctrl: ZLS_CTRL register value */ + __u64 zls_ctrl; + + /** @ppp_multisamplectl: PPP_MULTISAMPLECTL register value */ + __u64 ppp_multisamplectl; + + /** + * @sampler_heap: Base address of the sampler heap. This heap is used + * for both vertex shaders and fragment shaders. The registers are + * per-stage, but there is no known use case for separate heaps. + */ + __u64 sampler_heap; + + /** @ppp_ctrl: PPP_CTRL register value */ + __u32 ppp_ctrl; + + /** @width_px: Framebuffer width in pixels */ + __u16 width_px; + + /** @height_px: Framebuffer height in pixels */ + __u16 height_px; + + /** @layers: Number of layers in the framebuffer */ + __u16 layers; + + /** @sampler_count: Number of samplers in the sampler heap. */ + __u16 sampler_count; + + /** @utile_width_px: Width of a logical tilebuffer tile in pixels */ + __u8 utile_width_px; + + /** @utile_height_px: Height of a logical tilebuffer tile in pixels */ + __u8 utile_height_px; + + /** @samples: # of samples in the framebuffer. Must be 1, 2, or 4. */ + __u8 samples; + + /** @sample_size_B: # of bytes in the tilebuffer required per sample. */ + __u8 sample_size_B; + + /** + * @isp_merge_upper_x: 32-bit float used in the hardware triangle + * merging. Calculate as: tan(60 deg) * width. + * + * Making these values UAPI avoids requiring floating-point calculations + * in the kernel in the hot path. + */ + __u32 isp_merge_upper_x; + + /** + * @isp_merge_upper_y: 32-bit float. Calculate as: tan(60 deg) * height. + * See @isp_merge_upper_x. + */ + __u32 isp_merge_upper_y; + + /** @bg: Background program run for each tile at the start */ + struct drm_asahi_bg_eot bg; + + /** @eot: End-of-tile program ran for each tile at the end */ + struct drm_asahi_bg_eot eot; + + /** + * @partial_bg: Background program ran at the start of each tile when + * resuming the render pass during a partial render. + */ + struct drm_asahi_bg_eot partial_bg; + + /** + * @partial_eot: End-of-tile program ran at the end of each tile when + * pausing the render pass during a partial render. + */ + struct drm_asahi_bg_eot partial_eot; + + /** + * @isp_bgobjdepth: ISP_BGOBJDEPTH register value. This is the depth + * buffer clear value, encoded in the depth buffer's format: either a + * 32-bit float or a 16-bit unorm (with upper bits zeroed). + */ + __u32 isp_bgobjdepth; + + /** + * @isp_bgobjvals: ISP_BGOBJVALS register value. The bottom 8-bits + * contain the stencil buffer clear value. + */ + __u32 isp_bgobjvals; + + /** @ts_vtx: Timestamps for the vertex portion of the render */ + struct drm_asahi_timestamps ts_vtx; + + /** @ts_frag: Timestamps for the fragment portion of the render */ + struct drm_asahi_timestamps ts_frag; +}; + +/** + * struct drm_asahi_cmd_compute - Command to submit compute + * + * This command submits a control stream consisting of compute dispatches. There + * is essentially no limit on how many compute dispatches may be included in a + * single compute command, although timestamps are at command granularity. + */ +struct drm_asahi_cmd_compute { + /** @flags: MBZ */ + __u32 flags; + + /** @sampler_count: Number of samplers in the sampler heap. */ + __u32 sampler_count; + + /** + * @cdm_ctrl_stream_base: CDM_CTRL_STREAM_BASE register value. GPU + * address to the beginning of the CDM control stream. + */ + __u64 cdm_ctrl_stream_base; + + /** + * @cdm_ctrl_stream_end: GPU base address to the end of the hardware + * control stream. Note this only considers the first contiguous segment + * of the control stream, as the stream might jump elsewhere. + */ + __u64 cdm_ctrl_stream_end; + + /** @sampler_heap: Base address of the sampler heap. */ + __u64 sampler_heap; + + /** @helper: Helper program used for this compute command */ + struct drm_asahi_helper_program helper; + + /** @ts: Timestamps for the compute command */ + struct drm_asahi_timestamps ts; +}; + +/** + * struct drm_asahi_get_time - Arguments passed to DRM_IOCTL_ASAHI_GET_TIME + */ +struct drm_asahi_get_time { + /** @flags: MBZ. */ + __u64 flags; + + /** @gpu_timestamp: On return, the GPU timestamp in nanoseconds. */ + __u64 gpu_timestamp; +}; + +/** + * DRM_IOCTL_ASAHI() - Build an Asahi IOCTL number + * @__access: Access type. Must be R, W or RW. + * @__id: One of the DRM_ASAHI_xxx id. + * @__type: Suffix of the type being passed to the IOCTL. + * + * Don't use this macro directly, use the DRM_IOCTL_ASAHI_xxx + * values instead. + * + * Return: An IOCTL number to be passed to ioctl() from userspace. + */ +#define DRM_IOCTL_ASAHI(__access, __id, __type) \ + DRM_IO ## __access(DRM_COMMAND_BASE + DRM_ASAHI_ ## __id, \ + struct drm_asahi_ ## __type) + +/* Note: this is an enum so that it can be resolved by Rust bindgen. */ +enum { + DRM_IOCTL_ASAHI_GET_PARAMS = DRM_IOCTL_ASAHI(W, GET_PARAMS, get_params), + DRM_IOCTL_ASAHI_GET_TIME = DRM_IOCTL_ASAHI(WR, GET_TIME, get_time), + DRM_IOCTL_ASAHI_VM_CREATE = DRM_IOCTL_ASAHI(WR, VM_CREATE, vm_create), + DRM_IOCTL_ASAHI_VM_DESTROY = DRM_IOCTL_ASAHI(W, VM_DESTROY, vm_destroy), + DRM_IOCTL_ASAHI_VM_BIND = DRM_IOCTL_ASAHI(W, VM_BIND, vm_bind), + DRM_IOCTL_ASAHI_GEM_CREATE = DRM_IOCTL_ASAHI(WR, GEM_CREATE, gem_create), + DRM_IOCTL_ASAHI_GEM_MMAP_OFFSET = DRM_IOCTL_ASAHI(WR, GEM_MMAP_OFFSET, gem_mmap_offset), + DRM_IOCTL_ASAHI_GEM_BIND_OBJECT = DRM_IOCTL_ASAHI(WR, GEM_BIND_OBJECT, gem_bind_object), + DRM_IOCTL_ASAHI_QUEUE_CREATE = DRM_IOCTL_ASAHI(WR, QUEUE_CREATE, queue_create), + DRM_IOCTL_ASAHI_QUEUE_DESTROY = DRM_IOCTL_ASAHI(W, QUEUE_DESTROY, queue_destroy), + DRM_IOCTL_ASAHI_SUBMIT = DRM_IOCTL_ASAHI(W, SUBMIT, submit), +}; + +#if defined(__cplusplus) +} +#endif + +#endif /* _ASAHI_DRM_H_ */ diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h index 7fba37b94401..e63a71d3c607 100644 --- a/include/uapi/drm/drm.h +++ b/include/uapi/drm/drm.h @@ -905,13 +905,17 @@ struct drm_syncobj_destroy { }; #define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_IMPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_FD_TO_HANDLE_FLAGS_TIMELINE (1 << 1) #define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_EXPORT_SYNC_FILE (1 << 0) +#define DRM_SYNCOBJ_HANDLE_TO_FD_FLAGS_TIMELINE (1 << 1) struct drm_syncobj_handle { __u32 handle; __u32 flags; __s32 fd; __u32 pad; + + __u64 point; }; struct drm_syncobj_transfer { diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index e41a3cec6a9e..81202a50dc9e 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -422,6 +422,7 @@ extern "C" { #define DRM_FORMAT_MOD_VENDOR_ALLWINNER 0x09 #define DRM_FORMAT_MOD_VENDOR_AMLOGIC 0x0a #define DRM_FORMAT_MOD_VENDOR_MTK 0x0b +#define DRM_FORMAT_MOD_VENDOR_APPLE 0x0c /* add more to the end as needed */ @@ -1495,6 +1496,50 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier) #define DRM_FORMAT_MOD_MTK_16L_32S_TILE DRM_FORMAT_MOD_MTK(MTK_FMT_MOD_TILE_16L32S) /* + * Apple GPU-tiled layouts. + * + * Apple GPUs support nonlinear tilings with optional lossless compression. + * + * GPU-tiled images are divided into 16KiB tiles: + * + * Bytes per pixel Tile size + * --------------- --------- + * 1 128x128 + * 2 128x64 + * 4 64x64 + * 8 64x32 + * 16 32x32 + * + * Tiles are raster-order. Pixels within a tile are interleaved (Morton order). + * + * Compressed images pad the body to 128-bytes and are immediately followed by a + * metadata section. The metadata section rounds the image dimensions to + * powers-of-two and contains 8 bytes for each 16x16 compression subtile. + * Subtiles are interleaved (Morton order). + * + * All images are 128-byte aligned. + * + * These layouts fundamentally do not have meaningful strides. No matter how we + * specify strides for these layouts, userspace unaware of Apple image layouts + * will be unable to use correctly the specified stride for any purpose. + * Userspace aware of the image layouts do not use strides. The most "correct" + * convention would be setting the image stride to 0. Unfortunately, some + * software assumes the stride is at least (width * bytes per pixel). We + * therefore require that stride equals (width * bytes per pixel). Since the + * stride is arbitrary here, we pick the simplest convention. + * + * Although containing two sections, compressed image layouts are treated in + * software as a single plane. This is modelled after AFBC, a similar + * scheme. Attempting to separate the sections to be "explicit" in DRM would + * only generate more confusion, as software does not treat the image this way. + * + * For detailed information on the hardware image layouts, see + * https://docs.mesa3d.org/drivers/asahi.html#image-layouts + */ +#define DRM_FORMAT_MOD_APPLE_GPU_TILED fourcc_mod_code(APPLE, 1) +#define DRM_FORMAT_MOD_APPLE_GPU_TILED_COMPRESSED fourcc_mod_code(APPLE, 2) + +/* * AMD modifiers * * Memory layout: 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/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h index 97e2c4510e69..ad9a70afea6c 100644 --- a/include/uapi/drm/panthor_drm.h +++ b/include/uapi/drm/panthor_drm.h @@ -127,6 +127,9 @@ enum drm_panthor_ioctl_id { /** @DRM_PANTHOR_TILER_HEAP_DESTROY: Destroy a tiler heap. */ DRM_PANTHOR_TILER_HEAP_DESTROY, + + /** @DRM_PANTHOR_BO_SET_LABEL: Label a BO. */ + DRM_PANTHOR_BO_SET_LABEL, }; /** @@ -978,6 +981,24 @@ struct drm_panthor_tiler_heap_destroy { }; /** + * struct drm_panthor_bo_set_label - Arguments passed to DRM_IOCTL_PANTHOR_BO_SET_LABEL + */ +struct drm_panthor_bo_set_label { + /** @handle: Handle of the buffer object to label. */ + __u32 handle; + + /** @pad: MBZ. */ + __u32 pad; + + /** + * @label: User pointer to a NUL-terminated string + * + * Length cannot be greater than 4096 + */ + __u64 label; +}; + +/** * DRM_IOCTL_PANTHOR() - Build a Panthor IOCTL number * @__access: Access type. Must be R, W or RW. * @__id: One of the DRM_PANTHOR_xxx id. @@ -1019,6 +1040,8 @@ enum { DRM_IOCTL_PANTHOR(WR, TILER_HEAP_CREATE, tiler_heap_create), DRM_IOCTL_PANTHOR_TILER_HEAP_DESTROY = DRM_IOCTL_PANTHOR(WR, TILER_HEAP_DESTROY, tiler_heap_destroy), + DRM_IOCTL_PANTHOR_BO_SET_LABEL = + DRM_IOCTL_PANTHOR(WR, BO_SET_LABEL, bo_set_label), }; #if defined(__cplusplus) diff --git a/include/uapi/drm/virtgpu_drm.h b/include/uapi/drm/virtgpu_drm.h index c2ce71987e9b..9debb320c34b 100644 --- a/include/uapi/drm/virtgpu_drm.h +++ b/include/uapi/drm/virtgpu_drm.h @@ -163,6 +163,12 @@ struct drm_virtgpu_3d_wait { __u32 flags; }; +#define VIRTGPU_DRM_CAPSET_VIRGL 1 +#define VIRTGPU_DRM_CAPSET_VIRGL2 2 +#define VIRTGPU_DRM_CAPSET_GFXSTREAM_VULKAN 3 +#define VIRTGPU_DRM_CAPSET_VENUS 4 +#define VIRTGPU_DRM_CAPSET_CROSS_DOMAIN 5 +#define VIRTGPU_DRM_CAPSET_DRM 6 struct drm_virtgpu_get_caps { __u32 cap_set_id; __u32 cap_set_ver; diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 616916985e3f..9c08738c3b91 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -917,7 +917,11 @@ struct drm_xe_gem_mmap_offset { * struct drm_xe_vm_create - Input of &DRM_IOCTL_XE_VM_CREATE * * The @flags can be: - * - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE + * - %DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE - Map the whole virtual address + * space of the VM to scratch page. A vm_bind would overwrite the scratch + * page mapping. This flag is mutually exclusive with the + * %DRM_XE_VM_CREATE_FLAG_FAULT_MODE flag, with an exception of on x2 and + * xe3 platform. * - %DRM_XE_VM_CREATE_FLAG_LR_MODE - An LR, or Long Running VM accepts * exec submissions to its exec_queues that don't have an upper time * limit on the job execution time. But exec submissions to these diff --git a/include/uapi/linux/blktrace_api.h b/include/uapi/linux/blktrace_api.h index 690621b610e5..1bfb635e309b 100644 --- a/include/uapi/linux/blktrace_api.h +++ b/include/uapi/linux/blktrace_api.h @@ -49,7 +49,7 @@ enum blktrace_act { __BLK_TA_UNPLUG_TIMER, /* queue was unplugged by timer */ __BLK_TA_INSERT, /* insert request */ __BLK_TA_SPLIT, /* bio was split */ - __BLK_TA_BOUNCE, /* bio was bounced */ + __BLK_TA_BOUNCE, /* unused, was: bio was bounced */ __BLK_TA_REMAP, /* bio was remapped */ __BLK_TA_ABORT, /* request aborted */ __BLK_TA_DRV_DATA, /* driver-specific binary data */ diff --git a/include/uapi/linux/cec-funcs.h b/include/uapi/linux/cec-funcs.h index d58fa1cdcb08..189ecf0e13cd 100644 --- a/include/uapi/linux/cec-funcs.h +++ b/include/uapi/linux/cec-funcs.h @@ -14,7 +14,7 @@ static inline void cec_msg_active_source(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_ACTIVE_SOURCE; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -59,7 +59,7 @@ static inline void cec_msg_request_active_source(struct cec_msg *msg, int reply) { msg->len = 2; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REQUEST_ACTIVE_SOURCE; msg->reply = reply ? CEC_MSG_ACTIVE_SOURCE : 0; } @@ -68,7 +68,7 @@ static inline void cec_msg_routing_information(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_ROUTING_INFORMATION; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -86,7 +86,7 @@ static inline void cec_msg_routing_change(struct cec_msg *msg, __u16 new_phys_addr) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_ROUTING_CHANGE; msg->msg[2] = orig_phys_addr >> 8; msg->msg[3] = orig_phys_addr & 0xff; @@ -106,7 +106,7 @@ static inline void cec_ops_routing_change(const struct cec_msg *msg, static inline void cec_msg_set_stream_path(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_SET_STREAM_PATH; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -791,7 +791,7 @@ static inline void cec_msg_report_physical_addr(struct cec_msg *msg, __u16 phys_addr, __u8 prim_devtype) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REPORT_PHYSICAL_ADDR; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -817,7 +817,7 @@ static inline void cec_msg_set_menu_language(struct cec_msg *msg, const char *language) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_SET_MENU_LANGUAGE; memcpy(msg->msg + 2, language, 3); } @@ -850,7 +850,7 @@ static inline void cec_msg_report_features(struct cec_msg *msg, __u8 rc_profile, __u8 dev_features) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REPORT_FEATURES; msg->msg[2] = cec_version; msg->msg[3] = all_device_types; @@ -1092,7 +1092,7 @@ static inline void cec_msg_tuner_step_increment(struct cec_msg *msg) static inline void cec_msg_device_vendor_id(struct cec_msg *msg, __u32 vendor_id) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_DEVICE_VENDOR_ID; msg->msg[2] = vendor_id >> 16; msg->msg[3] = (vendor_id >> 8) & 0xff; @@ -1655,7 +1655,7 @@ static inline void cec_msg_report_current_latency(struct cec_msg *msg, __u8 audio_out_delay) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REPORT_CURRENT_LATENCY; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -1687,7 +1687,7 @@ static inline void cec_msg_request_current_latency(struct cec_msg *msg, __u16 phys_addr) { msg->len = 4; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_REQUEST_CURRENT_LATENCY; msg->msg[2] = phys_addr >> 8; msg->msg[3] = phys_addr & 0xff; @@ -1707,7 +1707,7 @@ static inline void cec_msg_cdc_hec_inquire_state(struct cec_msg *msg, __u16 phys_addr2) { msg->len = 9; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; @@ -1737,7 +1737,7 @@ static inline void cec_msg_cdc_hec_report_state(struct cec_msg *msg, __u16 hec_field) { msg->len = has_field ? 10 : 8; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_REPORT_STATE; @@ -1782,7 +1782,7 @@ static inline void cec_msg_cdc_hec_set_state(struct cec_msg *msg, __u16 phys_addr5) { msg->len = 10; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_INQUIRE_STATE; @@ -1832,7 +1832,7 @@ static inline void cec_msg_cdc_hec_set_state_adjacent(struct cec_msg *msg, __u8 hec_set_state) { msg->len = 8; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_SET_STATE_ADJACENT; @@ -1857,7 +1857,7 @@ static inline void cec_msg_cdc_hec_request_deactivation(struct cec_msg *msg, __u16 phys_addr3) { msg->len = 11; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_REQUEST_DEACTIVATION; @@ -1884,7 +1884,7 @@ static inline void cec_ops_cdc_hec_request_deactivation(const struct cec_msg *ms static inline void cec_msg_cdc_hec_notify_alive(struct cec_msg *msg) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_NOTIFY_ALIVE; @@ -1899,7 +1899,7 @@ static inline void cec_ops_cdc_hec_notify_alive(const struct cec_msg *msg, static inline void cec_msg_cdc_hec_discover(struct cec_msg *msg) { msg->len = 5; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HEC_DISCOVER; @@ -1916,7 +1916,7 @@ static inline void cec_msg_cdc_hpd_set_state(struct cec_msg *msg, __u8 hpd_state) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HPD_SET_STATE; @@ -1938,7 +1938,7 @@ static inline void cec_msg_cdc_hpd_report_state(struct cec_msg *msg, __u8 hpd_error) { msg->len = 6; - msg->msg[0] |= 0xf; /* broadcast */ + msg->msg[0] |= CEC_LOG_ADDR_BROADCAST; msg->msg[1] = CEC_MSG_CDC_MESSAGE; /* msg[2] and msg[3] (phys_addr) are filled in by the CEC framework */ msg->msg[4] = CEC_MSG_CDC_HPD_REPORT_STATE; diff --git a/include/uapi/linux/fscrypt.h b/include/uapi/linux/fscrypt.h index 7a8f4c290187..3aff99f2696a 100644 --- a/include/uapi/linux/fscrypt.h +++ b/include/uapi/linux/fscrypt.h @@ -119,7 +119,7 @@ struct fscrypt_key_specifier { */ struct fscrypt_provisioning_key_payload { __u32 type; - __u32 __reserved; + __u32 flags; __u8 raw[]; }; @@ -128,7 +128,9 @@ struct fscrypt_add_key_arg { struct fscrypt_key_specifier key_spec; __u32 raw_size; __u32 key_id; - __u32 __reserved[8]; +#define FSCRYPT_ADD_KEY_FLAG_HW_WRAPPED 0x00000001 + __u32 flags; + __u32 __reserved[7]; __u8 raw[]; }; diff --git a/include/uapi/linux/futex.h b/include/uapi/linux/futex.h index d2ee625ea189..7e2744ec8933 100644 --- a/include/uapi/linux/futex.h +++ b/include/uapi/linux/futex.h @@ -63,7 +63,7 @@ #define FUTEX2_SIZE_U32 0x02 #define FUTEX2_SIZE_U64 0x03 #define FUTEX2_NUMA 0x04 - /* 0x08 */ +#define FUTEX2_MPOL 0x08 /* 0x10 */ /* 0x20 */ /* 0x40 */ @@ -75,6 +75,13 @@ #define FUTEX_32 FUTEX2_SIZE_U32 /* historical accident :-( */ /* + * When FUTEX2_NUMA doubles the futex word, the second word is a node value. + * The special value -1 indicates no-node. This is the same value as + * NUMA_NO_NODE, except that value is not ABI, this is. + */ +#define FUTEX_NO_NODE (-1) + +/* * Max numbers of elements in a futex_waitv array */ #define FUTEX_WAITV_MAX 128 diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 8f1fc12bac46..cfd17e382082 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -73,6 +73,7 @@ struct io_uring_sqe { __u32 futex_flags; __u32 install_fd_flags; __u32 nop_flags; + __u32 pipe_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -93,6 +94,10 @@ struct io_uring_sqe { __u16 addr_len; __u16 __pad3[1]; }; + struct { + __u8 write_stream; + __u8 __pad4[3]; + }; }; union { struct { @@ -283,6 +288,7 @@ enum io_uring_op { IORING_OP_EPOLL_WAIT, IORING_OP_READV_FIXED, IORING_OP_WRITEV_FIXED, + IORING_OP_PIPE, /* this goes last, obviously */ IORING_OP_LAST, @@ -988,12 +994,16 @@ struct io_uring_zcrx_offsets { __u64 __resv[2]; }; +enum io_uring_zcrx_area_flags { + IORING_ZCRX_AREA_DMABUF = 1, +}; + struct io_uring_zcrx_area_reg { __u64 addr; __u64 len; __u64 rq_area_token; __u32 flags; - __u32 __resv1; + __u32 dmabuf_fd; __u64 __resv2[2]; }; 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) * diff --git a/include/uapi/linux/media/amlogic/c3-isp-config.h b/include/uapi/linux/media/amlogic/c3-isp-config.h new file mode 100644 index 000000000000..ed085ea62a57 --- /dev/null +++ b/include/uapi/linux/media/amlogic/c3-isp-config.h @@ -0,0 +1,564 @@ +/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */ +/* + * Copyright (C) 2024 Amlogic, Inc. All rights reserved + */ + +#ifndef _UAPI_C3_ISP_CONFIG_H_ +#define _UAPI_C3_ISP_CONFIG_H_ + +#include <linux/types.h> + +/* + * Frames are split into zones of almost equal width and height - a zone is a + * rectangular tile of a frame. The metering blocks within the ISP collect + * aggregated statistics per zone. + */ +#define C3_ISP_AE_MAX_ZONES (17 * 15) +#define C3_ISP_AF_MAX_ZONES (17 * 15) +#define C3_ISP_AWB_MAX_ZONES (32 * 24) + +/* The maximum number of point on the diagonal of the frame for statistics */ +#define C3_ISP_AE_MAX_PT_NUM 18 +#define C3_ISP_AF_MAX_PT_NUM 18 +#define C3_ISP_AWB_MAX_PT_NUM 33 + +/** + * struct c3_isp_awb_zone_stats - AWB statistics of a zone + * + * AWB zone stats is aligned with 8 bytes + * + * @rg: the ratio of R / G in a zone + * @bg: the ratio of B / G in a zone + * @pixel_sum: the total number of pixels used in a zone + */ +struct c3_isp_awb_zone_stats { + __u16 rg; + __u16 bg; + __u32 pixel_sum; +}; + +/** + * struct c3_isp_awb_stats - Auto white balance statistics information. + * + * AWB statistical information of all zones. + * + * @stats: array of auto white balance statistics + */ +struct c3_isp_awb_stats { + struct c3_isp_awb_zone_stats stats[C3_ISP_AWB_MAX_ZONES]; +} __attribute__((aligned(16))); + +/** + * struct c3_isp_ae_zone_stats - AE statistics of a zone + * + * AE zone stats is aligned with 8 bytes. + * This is a 5-bin histogram and the total sum is normalized to 0xffff. + * So hist2 = 0xffff - (hist0 + hist1 + hist3 + hist4) + * + * @hist0: the global normalized pixel count for bin 0 + * @hist1: the global normalized pixel count for bin 1 + * @hist3: the global normalized pixel count for bin 3 + * @hist4: the global normalized pixel count for bin 4 + */ +struct c3_isp_ae_zone_stats { + __u16 hist0; + __u16 hist1; + __u16 hist3; + __u16 hist4; +}; + +/** + * struct c3_isp_ae_stats - Exposure statistics information + * + * AE statistical information consists of all blocks information and a 1024-bin + * histogram. + * + * @stats: array of auto exposure block statistics + * @reserved: undefined buffer space + * @hist: a 1024-bin histogram for the entire image + */ +struct c3_isp_ae_stats { + struct c3_isp_ae_zone_stats stats[C3_ISP_AE_MAX_ZONES]; + __u32 reserved[2]; + __u32 hist[1024]; +} __attribute__((aligned(16))); + +/** + * struct c3_isp_af_zone_stats - AF statistics of a zone + * + * AF zone stats is aligned with 8 bytes. + * The zonal accumulated contrast metrics are stored in floating point format + * with 16 bits mantissa and 5 or 6 bits exponent. Apart from contrast metrics + * we accumulate squared image and quartic image data over the zone. + * + * @i2_mat: the mantissa of zonal squared image pixel sum + * @i4_mat: the mantissa of zonal quartic image pixel sum + * @e4_mat: the mantissa of zonal multi-directional quartic edge sum + * @e4_exp: the exponent of zonal multi-directional quartic edge sum + * @i2_exp: the exponent of zonal squared image pixel sum + * @i4_exp: the exponent of zonal quartic image pixel sum + */ +struct c3_isp_af_zone_stats { + __u16 i2_mat; + __u16 i4_mat; + __u16 e4_mat; + __u16 e4_exp : 5; + __u16 i2_exp : 5; + __u16 i4_exp : 6; +}; + +/** + * struct c3_isp_af_stats - Auto Focus statistics information + * + * AF statistical information of each zone + * + * @stats: array of auto focus block statistics + * @reserved: undefined buffer space + */ +struct c3_isp_af_stats { + struct c3_isp_af_zone_stats stats[C3_ISP_AF_MAX_ZONES]; + __u32 reserved[2]; +} __attribute__((aligned(16))); + +/** + * struct c3_isp_stats_info - V4L2_META_FMT_C3ISP_STATS + * + * Contains ISP statistics + * + * @awb: auto white balance stats + * @ae: auto exposure stats + * @af: auto focus stats + */ +struct c3_isp_stats_info { + struct c3_isp_awb_stats awb; + struct c3_isp_ae_stats ae; + struct c3_isp_af_stats af; +}; + +/** + * enum c3_isp_params_buffer_version - C3 ISP parameters block versioning + * + * @C3_ISP_PARAMS_BUFFER_V0: First version of C3 ISP parameters block + */ +enum c3_isp_params_buffer_version { + C3_ISP_PARAMS_BUFFER_V0, +}; + +/** + * enum c3_isp_params_block_type - Enumeration of C3 ISP parameter blocks + * + * Each block configures a specific processing block of the C3 ISP. + * The block type allows the driver to correctly interpret the parameters block + * data. + * + * @C3_ISP_PARAMS_BLOCK_AWB_GAINS: White balance gains + * @C3_ISP_PARAMS_BLOCK_AWB_CONFIG: AWB statistic format configuration for all + * blocks that control how stats are generated + * @C3_ISP_PARAMS_BLOCK_AE_CONFIG: AE statistic format configuration for all + * blocks that control how stats are generated + * @C3_ISP_PARAMS_BLOCK_AF_CONFIG: AF statistic format configuration for all + * blocks that control how stats are generated + * @C3_ISP_PARAMS_BLOCK_PST_GAMMA: post gamma parameters + * @C3_ISP_PARAMS_BLOCK_CCM: Color correction matrix parameters + * @C3_ISP_PARAMS_BLOCK_CSC: Color space conversion parameters + * @C3_ISP_PARAMS_BLOCK_BLC: Black level correction parameters + * @C3_ISP_PARAMS_BLOCK_SENTINEL: First non-valid block index + */ +enum c3_isp_params_block_type { + C3_ISP_PARAMS_BLOCK_AWB_GAINS, + C3_ISP_PARAMS_BLOCK_AWB_CONFIG, + C3_ISP_PARAMS_BLOCK_AE_CONFIG, + C3_ISP_PARAMS_BLOCK_AF_CONFIG, + C3_ISP_PARAMS_BLOCK_PST_GAMMA, + C3_ISP_PARAMS_BLOCK_CCM, + C3_ISP_PARAMS_BLOCK_CSC, + C3_ISP_PARAMS_BLOCK_BLC, + C3_ISP_PARAMS_BLOCK_SENTINEL +}; + +#define C3_ISP_PARAMS_BLOCK_FL_DISABLE (1U << 0) +#define C3_ISP_PARAMS_BLOCK_FL_ENABLE (1U << 1) + +/** + * struct c3_isp_params_block_header - C3 ISP parameter block header + * + * This structure represents the common part of all the ISP configuration + * blocks. Each parameters block shall embed an instance of this structure type + * as its first member, followed by the block-specific configuration data. The + * driver inspects this common header to discern the block type and its size and + * properly handle the block content by casting it to the correct block-specific + * type. + * + * The @type field is one of the values enumerated by + * :c:type:`c3_isp_params_block_type` and specifies how the data should be + * interpreted by the driver. The @size field specifies the size of the + * parameters block and is used by the driver for validation purposes. The + * @flags field is a bitmask of per-block flags C3_ISP_PARAMS_FL*. + * + * When userspace wants to disable an ISP block the + * C3_ISP_PARAMS_BLOCK_FL_DISABLED bit should be set in the @flags field. In + * this case userspace may optionally omit the remainder of the configuration + * block, which will be ignored by the driver. + * + * When a new configuration of an ISP block needs to be applied userspace + * shall fully populate the ISP block and omit setting the + * C3_ISP_PARAMS_BLOCK_FL_DISABLED bit in the @flags field. + * + * Userspace is responsible for correctly populating the parameters block header + * fields (@type, @flags and @size) and the block-specific parameters. + * + * For example: + * + * .. code-block:: c + * + * void populate_pst_gamma(struct c3_isp_params_block_header *block) { + * struct c3_isp_params_pst_gamma *gamma = + * (struct c3_isp_params_pst_gamma *)block; + * + * gamma->header.type = C3_ISP_PARAMS_BLOCK_PST_GAMMA; + * gamma->header.flags = C3_ISP_PARAMS_BLOCK_FL_ENABLE; + * gamma->header.size = sizeof(*gamma); + * + * for (unsigned int i = 0; i < 129; i++) + * gamma->pst_gamma_lut[i] = i; + * } + * + * @type: The parameters block type from :c:type:`c3_isp_params_block_type` + * @flags: A bitmask of block flags + * @size: Size (in bytes) of the parameters block, including this header + */ +struct c3_isp_params_block_header { + __u16 type; + __u16 flags; + __u32 size; +}; + +/** + * struct c3_isp_params_awb_gains - Gains for auto-white balance + * + * This struct allows users to configure the gains for white balance. + * There are four gain settings corresponding to each colour channel in + * the bayer domain. All of the gains are stored in Q4.8 format. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AWB_GAINS + * from :c:type:`c3_isp_params_block_type` + * + * @header: The C3 ISP parameters block header + * @gr_gain: Multiplier for Gr channel (Q4.8 format) + * @r_gain: Multiplier for R channel (Q4.8 format) + * @b_gain: Multiplier for B channel (Q4.8 format) + * @gb_gain: Multiplier for Gb channel (Q4.8 format) + */ +struct c3_isp_params_awb_gains { + struct c3_isp_params_block_header header; + __u16 gr_gain; + __u16 r_gain; + __u16 b_gain; + __u16 gb_gain; +} __attribute__((aligned(8))); + +/** + * enum c3_isp_params_awb_tap_points - Tap points for the AWB statistics + * @C3_ISP_AWB_STATS_TAP_OFE: immediately after the optical frontend block + * @C3_ISP_AWB_STATS_TAP_GE: immediately after the green equal block + * @C3_ISP_AWB_STATS_TAP_BEFORE_WB: immediately before the white balance block + * @C3_ISP_AWB_STATS_TAP_AFTER_WB: immediately after the white balance block + */ +enum c3_isp_params_awb_tap_points { + C3_ISP_AWB_STATS_TAP_OFE = 0, + C3_ISP_AWB_STATS_TAP_GE, + C3_ISP_AWB_STATS_TAP_BEFORE_WB, + C3_ISP_AWB_STATS_TAP_AFTER_WB, +}; + +/** + * struct c3_isp_params_awb_config - Stats settings for auto-white balance + * + * This struct allows the configuration of the statistics generated for auto + * white balance. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AWB_CONFIG + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @tap_point: the tap point from enum c3_isp_params_awb_tap_point + * @satur_vald: AWB statistic over saturation control + * value: 0: disable, 1: enable + * @horiz_zones_num: active number of hotizontal zones [0..32] + * @vert_zones_num: active number of vertical zones [0..24] + * @rg_min: minimum R/G ratio (Q4.8 format) + * @rg_max: maximum R/G ratio (Q4.8 format) + * @bg_min: minimum B/G ratio (Q4.8 format) + * @bg_max: maximum B/G ratio (Q4.8 format) + * @rg_low: R/G ratio trim low (Q4.8 format) + * @rg_high: R/G ratio trim hight (Q4.8 format) + * @bg_low: B/G ratio trim low (Q4.8 format) + * @bg_high: B/G ratio trim high (Q4.8 format) + * @zone_weight: array of weights for AWB statistics zones [0..15] + * @horiz_coord: the horizontal coordinate of points on the diagonal [0..2888] + * @vert_coord: the vertical coordinate of points on the diagonal [0..2240] + */ +struct c3_isp_params_awb_config { + struct c3_isp_params_block_header header; + __u8 tap_point; + __u8 satur_vald; + __u8 horiz_zones_num; + __u8 vert_zones_num; + __u16 rg_min; + __u16 rg_max; + __u16 bg_min; + __u16 bg_max; + __u16 rg_low; + __u16 rg_high; + __u16 bg_low; + __u16 bg_high; + __u8 zone_weight[C3_ISP_AWB_MAX_ZONES]; + __u16 horiz_coord[C3_ISP_AWB_MAX_PT_NUM]; + __u16 vert_coord[C3_ISP_AWB_MAX_PT_NUM]; +} __attribute__((aligned(8))); + +/** + * enum c3_isp_params_ae_tap_points - Tap points for the AE statistics + * @C3_ISP_AE_STATS_TAP_GE: immediately after the green equal block + * @C3_ISP_AE_STATS_TAP_MLS: immediately after the mesh lens shading block + */ +enum c3_isp_params_ae_tap_points { + C3_ISP_AE_STATS_TAP_GE = 0, + C3_ISP_AE_STATS_TAP_MLS, +}; + +/** + * struct c3_isp_params_ae_config - Stats settings for auto-exposure + * + * This struct allows the configuration of the statistics generated for + * auto exposure. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AE_CONFIG + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @horiz_zones_num: active number of horizontal zones [0..17] + * @vert_zones_num: active number of vertical zones [0..15] + * @tap_point: the tap point from enum c3_isp_params_ae_tap_point + * @zone_weight: array of weights for AE statistics zones [0..15] + * @horiz_coord: the horizontal coordinate of points on the diagonal [0..2888] + * @vert_coord: the vertical coordinate of points on the diagonal [0..2240] + * @reserved: applications must zero this array + */ +struct c3_isp_params_ae_config { + struct c3_isp_params_block_header header; + __u8 tap_point; + __u8 horiz_zones_num; + __u8 vert_zones_num; + __u8 zone_weight[C3_ISP_AE_MAX_ZONES]; + __u16 horiz_coord[C3_ISP_AE_MAX_PT_NUM]; + __u16 vert_coord[C3_ISP_AE_MAX_PT_NUM]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * enum c3_isp_params_af_tap_points - Tap points for the AF statistics + * @C3_ISP_AF_STATS_TAP_SNR: immediately after the spatial noise reduce block + * @C3_ISP_AF_STATS_TAP_DMS: immediately after the demosaic block + */ +enum c3_isp_params_af_tap_points { + C3_ISP_AF_STATS_TAP_SNR = 0, + C3_ISP_AF_STATS_TAP_DMS, +}; + +/** + * struct c3_isp_params_af_config - Stats settings for auto-focus + * + * This struct allows the configuration of the statistics generated for + * auto focus. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_AF_CONFIG + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @tap_point: the tap point from enum c3_isp_params_af_tap_point + * @horiz_zones_num: active number of hotizontal zones [0..17] + * @vert_zones_num: active number of vertical zones [0..15] + * @reserved: applications must zero this array + * @horiz_coord: the horizontal coordinate of points on the diagonal [0..2888] + * @vert_coord: the vertical coordinate of points on the diagonal [0..2240] + */ +struct c3_isp_params_af_config { + struct c3_isp_params_block_header header; + __u8 tap_point; + __u8 horiz_zones_num; + __u8 vert_zones_num; + __u8 reserved[5]; + __u16 horiz_coord[C3_ISP_AF_MAX_PT_NUM]; + __u16 vert_coord[C3_ISP_AF_MAX_PT_NUM]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_pst_gamma - Post gamma configuration + * + * This struct allows the configuration of the look up table for + * post gamma. The gamma curve consists of 129 points, so need to + * set lut[129]. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_PST_GAMMA + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @lut: lookup table for P-Stitch gamma [0..1023] + * @reserved: applications must zero this array + */ +struct c3_isp_params_pst_gamma { + struct c3_isp_params_block_header header; + __u16 lut[129]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_ccm - ISP CCM configuration + * + * This struct allows the configuration of the matrix for + * color correction. The matrix consists of 3 x 3 points, + * so need to set matrix[3][3]. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_CCM + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @matrix: a 3 x 3 matrix used for color correction, + * the value of matrix[x][y] is orig_value x 256. [-4096..4095] + * @reserved: applications must zero this array + */ +struct c3_isp_params_ccm { + struct c3_isp_params_block_header header; + __s16 matrix[3][3]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_csc - ISP Color Space Conversion configuration + * + * This struct allows the configuration of the matrix for color space + * conversion. The matrix consists of 3 x 3 points, so need to set matrix[3][3]. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_CSC + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @matrix: a 3x3 matrix used for the color space conversion, + * the value of matrix[x][y] is orig_value x 256. [-4096..4095] + * @reserved: applications must zero this array + */ +struct c3_isp_params_csc { + struct c3_isp_params_block_header header; + __s16 matrix[3][3]; + __u16 reserved[3]; +} __attribute__((aligned(8))); + +/** + * struct c3_isp_params_blc - ISP Black Level Correction configuration + * + * This struct allows the configuration of the block level offset for each + * color channel. + * + * header.type should be set to C3_ISP_PARAMS_BLOCK_BLC + * from :c:type:`c3_isp_params_block_type` + * + * @header: the C3 ISP parameters block header + * @gr_ofst: Gr blc offset (Q4.12 format) + * @r_ofst: R blc offset (Q4.12 format) + * @b_ofst: B blc offset (Q4.12 format) + * @gb_ofst: Gb blc offset(Q4.12 format) + */ +struct c3_isp_params_blc { + struct c3_isp_params_block_header header; + __u16 gr_ofst; + __u16 r_ofst; + __u16 b_ofst; + __u16 gb_ofst; +}; + +/** + * define C3_ISP_PARAMS_MAX_SIZE - Maximum size of all C3 ISP Parameters + * + * Though the parameters for the C3 ISP are passed as optional blocks, the + * driver still needs to know the absolute maximum size so that it can allocate + * a buffer sized appropriately to accommodate userspace attempting to set all + * possible parameters in a single frame. + */ +#define C3_ISP_PARAMS_MAX_SIZE \ + (sizeof(struct c3_isp_params_awb_gains) + \ + sizeof(struct c3_isp_params_awb_config) + \ + sizeof(struct c3_isp_params_ae_config) + \ + sizeof(struct c3_isp_params_af_config) + \ + sizeof(struct c3_isp_params_pst_gamma) + \ + sizeof(struct c3_isp_params_ccm) + \ + sizeof(struct c3_isp_params_csc) + \ + sizeof(struct c3_isp_params_blc)) + +/** + * struct c3_isp_params_cfg - C3 ISP configuration parameters + * + * This struct contains the configuration parameters of the C3 ISP + * algorithms, serialized by userspace into an opaque data buffer. Each + * configuration parameter block is represented by a block-specific structure + * which contains a :c:type:`c3_isp_param_block_header` entry as first + * member. Userspace populates the @data buffer with configuration parameters + * for the blocks that it intends to configure. As a consequence, the data + * buffer effective size changes according to the number of ISP blocks that + * userspace intends to configure. + * + * The parameters buffer is versioned by the @version field to allow modifying + * and extending its definition. Userspace should populate the @version field to + * inform the driver about the version it intends to use. The driver will parse + * and handle the @data buffer according to the data layout specific to the + * indicated revision and return an error if the desired revision is not + * supported. + * + * For each ISP block that userspace wants to configure, a block-specific + * structure is appended to the @data buffer, one after the other without gaps + * in between nor overlaps. Userspace shall populate the @total_size field with + * the effective size, in bytes, of the @data buffer. + * + * The expected memory layout of the parameters buffer is:: + * + * +-------------------- struct c3_isp_params_cfg ---- ------------------+ + * | version = C3_ISP_PARAM_BUFFER_V0; | + * | data_size = sizeof(struct c3_isp_params_awb_gains) + | + * | sizeof(struct c3_isp_params_awb_config); | + * | +------------------------- data ---------------------------------+ | + * | | +------------ struct c3_isp_params_awb_gains) ------------------+ | + * | | | +--------- struct c3_isp_params_block_header header -----+ | | | + * | | | | type = C3_ISP_PARAMS_BLOCK_AWB_GAINS; | | | | + * | | | | flags = C3_ISP_PARAMS_BLOCK_FL_NONE; | | | | + * | | | | size = sizeof(struct c3_isp_params_awb_gains); | | | | + * | | | +---------------------------------------------------------+ | | | + * | | | gr_gain = ...; | | | + * | | | r_gain = ...; | | | + * | | | b_gain = ...; | | | + * | | | gb_gain = ...; | | | + * | | +------------------ struct c3_isp_params_awb_config ----------+ | | + * | | | +---------- struct c3_isp_param_block_header header ------+ | | | + * | | | | type = C3_ISP_PARAMS_BLOCK_AWB_CONFIG; | | | | + * | | | | flags = C3_ISP_PARAMS_BLOCK_FL_NONE; | | | | + * | | | | size = sizeof(struct c3_isp_params_awb_config) | | | | + * | | | +---------------------------------------------------------+ | | | + * | | | tap_point = ...; | | | + * | | | satur_vald = ...; | | | + * | | | horiz_zones_num = ...; | | | + * | | | vert_zones_num = ...; | | | + * | | +-------------------------------------------------------------+ | | + * | +-----------------------------------------------------------------+ | + * +---------------------------------------------------------------------+ + * + * @version: The C3 ISP parameters buffer version + * @data_size: The C3 ISP configuration data effective size, excluding this + * header + * @data: The C3 ISP configuration blocks data + */ +struct c3_isp_params_cfg { + __u32 version; + __u32 data_size; + __u8 data[C3_ISP_PARAMS_MAX_SIZE]; +}; + +#endif diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 5fc753c23734..78a362b80027 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -39,18 +39,21 @@ enum perf_type_id { /* * attr.config layout for type PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE + * * PERF_TYPE_HARDWARE: 0xEEEEEEEE000000AA * AA: hardware event ID * EEEEEEEE: PMU type ID + * * PERF_TYPE_HW_CACHE: 0xEEEEEEEE00DDCCBB * BB: hardware cache ID * CC: hardware cache op ID * DD: hardware cache op result ID * EEEEEEEE: PMU type ID - * If the PMU type ID is 0, the PERF_TYPE_RAW will be applied. + * + * If the PMU type ID is 0, PERF_TYPE_RAW will be applied. */ -#define PERF_PMU_TYPE_SHIFT 32 -#define PERF_HW_EVENT_MASK 0xffffffff +#define PERF_PMU_TYPE_SHIFT 32 +#define PERF_HW_EVENT_MASK 0xffffffff /* * Generalized performance event event_id types, used by the @@ -112,7 +115,7 @@ enum perf_hw_cache_op_result_id { /* * Special "software" events provided by the kernel, even if the hardware * does not support performance events. These events measure various - * physical and sw events of the kernel (and allow the profiling of them as + * physical and SW events of the kernel (and allow the profiling of them as * well): */ enum perf_sw_ids { @@ -167,8 +170,9 @@ enum perf_event_sample_format { }; #define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) + /* - * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set + * Values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set. * * If the user does not pass priv level information via branch_sample_type, * the kernel uses the event's priv level. Branch and event priv levels do @@ -178,20 +182,20 @@ enum perf_event_sample_format { * of branches and therefore it supersedes all the other types. */ enum perf_branch_sample_type_shift { - PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ - PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ - PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ - - PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ - PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ - PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ - PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ - PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ - PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ - PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ + PERF_SAMPLE_BRANCH_USER_SHIFT = 0, /* user branches */ + PERF_SAMPLE_BRANCH_KERNEL_SHIFT = 1, /* kernel branches */ + PERF_SAMPLE_BRANCH_HV_SHIFT = 2, /* hypervisor branches */ + + PERF_SAMPLE_BRANCH_ANY_SHIFT = 3, /* any branch types */ + PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT = 4, /* any call branch */ + PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT = 5, /* any return branch */ + PERF_SAMPLE_BRANCH_IND_CALL_SHIFT = 6, /* indirect calls */ + PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT = 7, /* transaction aborts */ + PERF_SAMPLE_BRANCH_IN_TX_SHIFT = 8, /* in transaction */ + PERF_SAMPLE_BRANCH_NO_TX_SHIFT = 9, /* not in transaction */ PERF_SAMPLE_BRANCH_COND_SHIFT = 10, /* conditional branches */ - PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* call/ret stack */ + PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT = 11, /* CALL/RET stack */ PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT = 12, /* indirect jumps */ PERF_SAMPLE_BRANCH_CALL_SHIFT = 13, /* direct call */ @@ -210,96 +214,95 @@ enum perf_branch_sample_type_shift { }; enum perf_branch_sample_type { - PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, - PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, - PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, + PERF_SAMPLE_BRANCH_USER = 1U << PERF_SAMPLE_BRANCH_USER_SHIFT, + PERF_SAMPLE_BRANCH_KERNEL = 1U << PERF_SAMPLE_BRANCH_KERNEL_SHIFT, + PERF_SAMPLE_BRANCH_HV = 1U << PERF_SAMPLE_BRANCH_HV_SHIFT, - PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, - PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, - PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, - PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, - PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, - PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, - PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, + PERF_SAMPLE_BRANCH_ANY = 1U << PERF_SAMPLE_BRANCH_ANY_SHIFT, + PERF_SAMPLE_BRANCH_ANY_CALL = 1U << PERF_SAMPLE_BRANCH_ANY_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ANY_RETURN = 1U << PERF_SAMPLE_BRANCH_ANY_RETURN_SHIFT, + PERF_SAMPLE_BRANCH_IND_CALL = 1U << PERF_SAMPLE_BRANCH_IND_CALL_SHIFT, + PERF_SAMPLE_BRANCH_ABORT_TX = 1U << PERF_SAMPLE_BRANCH_ABORT_TX_SHIFT, + PERF_SAMPLE_BRANCH_IN_TX = 1U << PERF_SAMPLE_BRANCH_IN_TX_SHIFT, + PERF_SAMPLE_BRANCH_NO_TX = 1U << PERF_SAMPLE_BRANCH_NO_TX_SHIFT, + PERF_SAMPLE_BRANCH_COND = 1U << PERF_SAMPLE_BRANCH_COND_SHIFT, - PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, - PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, - PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, + PERF_SAMPLE_BRANCH_CALL_STACK = 1U << PERF_SAMPLE_BRANCH_CALL_STACK_SHIFT, + PERF_SAMPLE_BRANCH_IND_JUMP = 1U << PERF_SAMPLE_BRANCH_IND_JUMP_SHIFT, + PERF_SAMPLE_BRANCH_CALL = 1U << PERF_SAMPLE_BRANCH_CALL_SHIFT, - PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, - PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, + PERF_SAMPLE_BRANCH_NO_FLAGS = 1U << PERF_SAMPLE_BRANCH_NO_FLAGS_SHIFT, + PERF_SAMPLE_BRANCH_NO_CYCLES = 1U << PERF_SAMPLE_BRANCH_NO_CYCLES_SHIFT, - PERF_SAMPLE_BRANCH_TYPE_SAVE = - 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_TYPE_SAVE = 1U << PERF_SAMPLE_BRANCH_TYPE_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, + PERF_SAMPLE_BRANCH_HW_INDEX = 1U << PERF_SAMPLE_BRANCH_HW_INDEX_SHIFT, - PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, + PERF_SAMPLE_BRANCH_PRIV_SAVE = 1U << PERF_SAMPLE_BRANCH_PRIV_SAVE_SHIFT, - PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, + PERF_SAMPLE_BRANCH_COUNTERS = 1U << PERF_SAMPLE_BRANCH_COUNTERS_SHIFT, - PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, + PERF_SAMPLE_BRANCH_MAX = 1U << PERF_SAMPLE_BRANCH_MAX_SHIFT, }; /* - * Common flow change classification + * Common control flow change classifications: */ enum { - PERF_BR_UNKNOWN = 0, /* unknown */ - PERF_BR_COND = 1, /* conditional */ - PERF_BR_UNCOND = 2, /* unconditional */ - PERF_BR_IND = 3, /* indirect */ - PERF_BR_CALL = 4, /* function call */ - PERF_BR_IND_CALL = 5, /* indirect function call */ - PERF_BR_RET = 6, /* function return */ - PERF_BR_SYSCALL = 7, /* syscall */ - PERF_BR_SYSRET = 8, /* syscall return */ - PERF_BR_COND_CALL = 9, /* conditional function call */ - PERF_BR_COND_RET = 10, /* conditional function return */ - PERF_BR_ERET = 11, /* exception return */ - PERF_BR_IRQ = 12, /* irq */ - PERF_BR_SERROR = 13, /* system error */ - PERF_BR_NO_TX = 14, /* not in transaction */ - PERF_BR_EXTEND_ABI = 15, /* extend ABI */ + PERF_BR_UNKNOWN = 0, /* Unknown */ + PERF_BR_COND = 1, /* Conditional */ + PERF_BR_UNCOND = 2, /* Unconditional */ + PERF_BR_IND = 3, /* Indirect */ + PERF_BR_CALL = 4, /* Function call */ + PERF_BR_IND_CALL = 5, /* Indirect function call */ + PERF_BR_RET = 6, /* Function return */ + PERF_BR_SYSCALL = 7, /* Syscall */ + PERF_BR_SYSRET = 8, /* Syscall return */ + PERF_BR_COND_CALL = 9, /* Conditional function call */ + PERF_BR_COND_RET = 10, /* Conditional function return */ + PERF_BR_ERET = 11, /* Exception return */ + PERF_BR_IRQ = 12, /* IRQ */ + PERF_BR_SERROR = 13, /* System error */ + PERF_BR_NO_TX = 14, /* Not in transaction */ + PERF_BR_EXTEND_ABI = 15, /* Extend ABI */ PERF_BR_MAX, }; /* - * Common branch speculation outcome classification + * Common branch speculation outcome classifications: */ enum { - PERF_BR_SPEC_NA = 0, /* Not available */ - PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ - PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ - PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ + PERF_BR_SPEC_NA = 0, /* Not available */ + PERF_BR_SPEC_WRONG_PATH = 1, /* Speculative but on wrong path */ + PERF_BR_NON_SPEC_CORRECT_PATH = 2, /* Non-speculative but on correct path */ + PERF_BR_SPEC_CORRECT_PATH = 3, /* Speculative and on correct path */ PERF_BR_SPEC_MAX, }; enum { - PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ - PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ - PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ - PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ - PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ - PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ - PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ - PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ + PERF_BR_NEW_FAULT_ALGN = 0, /* Alignment fault */ + PERF_BR_NEW_FAULT_DATA = 1, /* Data fault */ + PERF_BR_NEW_FAULT_INST = 2, /* Inst fault */ + PERF_BR_NEW_ARCH_1 = 3, /* Architecture specific */ + PERF_BR_NEW_ARCH_2 = 4, /* Architecture specific */ + PERF_BR_NEW_ARCH_3 = 5, /* Architecture specific */ + PERF_BR_NEW_ARCH_4 = 6, /* Architecture specific */ + PERF_BR_NEW_ARCH_5 = 7, /* Architecture specific */ PERF_BR_NEW_MAX, }; enum { - PERF_BR_PRIV_UNKNOWN = 0, - PERF_BR_PRIV_USER = 1, - PERF_BR_PRIV_KERNEL = 2, - PERF_BR_PRIV_HV = 3, + PERF_BR_PRIV_UNKNOWN = 0, + PERF_BR_PRIV_USER = 1, + PERF_BR_PRIV_KERNEL = 2, + PERF_BR_PRIV_HV = 3, }; -#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 -#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 -#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 -#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 -#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 +#define PERF_BR_ARM64_FIQ PERF_BR_NEW_ARCH_1 +#define PERF_BR_ARM64_DEBUG_HALT PERF_BR_NEW_ARCH_2 +#define PERF_BR_ARM64_DEBUG_EXIT PERF_BR_NEW_ARCH_3 +#define PERF_BR_ARM64_DEBUG_INST PERF_BR_NEW_ARCH_4 +#define PERF_BR_ARM64_DEBUG_DATA PERF_BR_NEW_ARCH_5 #define PERF_SAMPLE_BRANCH_PLM_ALL \ (PERF_SAMPLE_BRANCH_USER|\ @@ -310,9 +313,9 @@ enum { * Values to determine ABI of the registers dump. */ enum perf_sample_regs_abi { - PERF_SAMPLE_REGS_ABI_NONE = 0, - PERF_SAMPLE_REGS_ABI_32 = 1, - PERF_SAMPLE_REGS_ABI_64 = 2, + PERF_SAMPLE_REGS_ABI_NONE = 0, + PERF_SAMPLE_REGS_ABI_32 = 1, + PERF_SAMPLE_REGS_ABI_64 = 2, }; /* @@ -320,21 +323,21 @@ enum perf_sample_regs_abi { * abort events. Multiple bits can be set. */ enum { - PERF_TXN_ELISION = (1 << 0), /* From elision */ - PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ - PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ - PERF_TXN_ASYNC = (1 << 3), /* Instruction not related */ - PERF_TXN_RETRY = (1 << 4), /* Retry possible */ - PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ - PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ - PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ + PERF_TXN_ELISION = (1 << 0), /* From elision */ + PERF_TXN_TRANSACTION = (1 << 1), /* From transaction */ + PERF_TXN_SYNC = (1 << 2), /* Instruction is related */ + PERF_TXN_ASYNC = (1 << 3), /* Instruction is not related */ + PERF_TXN_RETRY = (1 << 4), /* Retry possible */ + PERF_TXN_CONFLICT = (1 << 5), /* Conflict abort */ + PERF_TXN_CAPACITY_WRITE = (1 << 6), /* Capacity write abort */ + PERF_TXN_CAPACITY_READ = (1 << 7), /* Capacity read abort */ - PERF_TXN_MAX = (1 << 8), /* non-ABI */ + PERF_TXN_MAX = (1 << 8), /* non-ABI */ - /* bits 32..63 are reserved for the abort code */ + /* Bits 32..63 are reserved for the abort code */ - PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), - PERF_TXN_ABORT_SHIFT = 32, + PERF_TXN_ABORT_MASK = (0xffffffffULL << 32), + PERF_TXN_ABORT_SHIFT = 32, }; /* @@ -369,24 +372,22 @@ enum perf_event_read_format { PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; -#define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ -#define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ -#define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ -#define PERF_ATTR_SIZE_VER3 96 /* add: sample_regs_user */ - /* add: sample_stack_user */ -#define PERF_ATTR_SIZE_VER4 104 /* add: sample_regs_intr */ -#define PERF_ATTR_SIZE_VER5 112 /* add: aux_watermark */ -#define PERF_ATTR_SIZE_VER6 120 /* add: aux_sample_size */ -#define PERF_ATTR_SIZE_VER7 128 /* add: sig_data */ -#define PERF_ATTR_SIZE_VER8 136 /* add: config3 */ +#define PERF_ATTR_SIZE_VER0 64 /* Size of first published 'struct perf_event_attr' */ +#define PERF_ATTR_SIZE_VER1 72 /* Add: config2 */ +#define PERF_ATTR_SIZE_VER2 80 /* Add: branch_sample_type */ +#define PERF_ATTR_SIZE_VER3 96 /* Add: sample_regs_user */ + /* Add: sample_stack_user */ +#define PERF_ATTR_SIZE_VER4 104 /* Add: sample_regs_intr */ +#define PERF_ATTR_SIZE_VER5 112 /* Add: aux_watermark */ +#define PERF_ATTR_SIZE_VER6 120 /* Add: aux_sample_size */ +#define PERF_ATTR_SIZE_VER7 128 /* Add: sig_data */ +#define PERF_ATTR_SIZE_VER8 136 /* Add: config3 */ /* - * Hardware event_id to monitor via a performance monitoring event: - * - * @sample_max_stack: Max number of frame pointers in a callchain, - * should be < /proc/sys/kernel/perf_event_max_stack - * Max number of entries of branch stack - * should be < hardware limit + * 'struct perf_event_attr' contains various attributes that define + * a performance event - most of them hardware related configuration + * details, but also a lot of behavioral switches and values implemented + * by the kernel. */ struct perf_event_attr { @@ -396,7 +397,7 @@ struct perf_event_attr { __u32 type; /* - * Size of the attr structure, for fwd/bwd compat. + * Size of the attr structure, for forward/backwards compatibility. */ __u32 size; @@ -451,21 +452,21 @@ struct perf_event_attr { comm_exec : 1, /* flag comm events that are due to an exec */ use_clockid : 1, /* use @clockid for time fields */ context_switch : 1, /* context switch data */ - write_backward : 1, /* Write ring buffer from end to beginning */ + write_backward : 1, /* write ring buffer from end to beginning */ namespaces : 1, /* include namespaces data */ ksymbol : 1, /* include ksymbol events */ - bpf_event : 1, /* include bpf events */ + bpf_event : 1, /* include BPF events */ aux_output : 1, /* generate AUX records instead of events */ cgroup : 1, /* include cgroup events */ text_poke : 1, /* include text poke events */ - build_id : 1, /* use build id in mmap2 events */ + build_id : 1, /* use build ID in mmap2 events */ inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ __reserved_1 : 26; union { - __u32 wakeup_events; /* wakeup every n events */ + __u32 wakeup_events; /* wake up every n events */ __u32 wakeup_watermark; /* bytes before wakeup */ }; @@ -474,13 +475,13 @@ struct perf_event_attr { __u64 bp_addr; __u64 kprobe_func; /* for perf_kprobe */ __u64 uprobe_path; /* for perf_uprobe */ - __u64 config1; /* extension of config */ + __u64 config1; /* extension of config */ }; union { __u64 bp_len; - __u64 kprobe_addr; /* when kprobe_func == NULL */ + __u64 kprobe_addr; /* when kprobe_func == NULL */ __u64 probe_offset; /* for perf_[k,u]probe */ - __u64 config2; /* extension of config1 */ + __u64 config2; /* extension of config1 */ }; __u64 branch_sample_type; /* enum perf_branch_sample_type */ @@ -510,7 +511,16 @@ struct perf_event_attr { * Wakeup watermark for AUX area */ __u32 aux_watermark; + + /* + * Max number of frame pointers in a callchain, should be + * lower than /proc/sys/kernel/perf_event_max_stack. + * + * Max number of entries of branch stack should be lower + * than the hardware limit. + */ __u16 sample_max_stack; + __u16 __reserved_2; __u32 aux_sample_size; @@ -537,7 +547,7 @@ struct perf_event_attr { /* * Structure used by below PERF_EVENT_IOC_QUERY_BPF command - * to query bpf programs attached to the same perf tracepoint + * to query BPF programs attached to the same perf tracepoint * as the given perf event. */ struct perf_event_query_bpf { @@ -559,21 +569,21 @@ struct perf_event_query_bpf { /* * Ioctls that can be done on a perf event fd: */ -#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) -#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) -#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) -#define PERF_EVENT_IOC_RESET _IO ('$', 3) -#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64) -#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) -#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *) -#define PERF_EVENT_IOC_ID _IOR('$', 7, __u64 *) -#define PERF_EVENT_IOC_SET_BPF _IOW('$', 8, __u32) -#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW('$', 9, __u32) +#define PERF_EVENT_IOC_ENABLE _IO ('$', 0) +#define PERF_EVENT_IOC_DISABLE _IO ('$', 1) +#define PERF_EVENT_IOC_REFRESH _IO ('$', 2) +#define PERF_EVENT_IOC_RESET _IO ('$', 3) +#define PERF_EVENT_IOC_PERIOD _IOW ('$', 4, __u64) +#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5) +#define PERF_EVENT_IOC_SET_FILTER _IOW ('$', 6, char *) +#define PERF_EVENT_IOC_ID _IOR ('$', 7, __u64 *) +#define PERF_EVENT_IOC_SET_BPF _IOW ('$', 8, __u32) +#define PERF_EVENT_IOC_PAUSE_OUTPUT _IOW ('$', 9, __u32) #define PERF_EVENT_IOC_QUERY_BPF _IOWR('$', 10, struct perf_event_query_bpf *) -#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW('$', 11, struct perf_event_attr *) +#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES _IOW ('$', 11, struct perf_event_attr *) enum perf_event_ioc_flags { - PERF_IOC_FLAG_GROUP = 1U << 0, + PERF_IOC_FLAG_GROUP = 1U << 0, }; /* @@ -584,7 +594,7 @@ struct perf_event_mmap_page { __u32 compat_version; /* lowest version this is compat with */ /* - * Bits needed to read the hw events in user-space. + * Bits needed to read the HW events in user-space. * * u32 seq, time_mult, time_shift, index, width; * u64 count, enabled, running; @@ -622,7 +632,7 @@ struct perf_event_mmap_page { __u32 index; /* hardware event identifier */ __s64 offset; /* add to hardware event value */ __u64 time_enabled; /* time event active */ - __u64 time_running; /* time event on cpu */ + __u64 time_running; /* time event on CPU */ union { __u64 capabilities; struct { @@ -650,7 +660,7 @@ struct perf_event_mmap_page { /* * If cap_usr_time the below fields can be used to compute the time - * delta since time_enabled (in ns) using rdtsc or similar. + * delta since time_enabled (in ns) using RDTSC or similar. * * u64 quot, rem; * u64 delta; @@ -723,7 +733,7 @@ struct perf_event_mmap_page { * after reading this value. * * When the mapping is PROT_WRITE the @data_tail value should be - * written by userspace to reflect the last read data, after issueing + * written by user-space to reflect the last read data, after issuing * an smp_mb() to separate the data read from the ->data_tail store. * In this case the kernel will not over-write unread data. * @@ -739,7 +749,7 @@ struct perf_event_mmap_page { /* * AUX area is defined by aux_{offset,size} fields that should be set - * by the userspace, so that + * by the user-space, so that * * aux_offset >= data_offset + data_size * @@ -813,7 +823,7 @@ struct perf_event_mmap_page { * Indicates that thread was preempted in TASK_RUNNING state. * * PERF_RECORD_MISC_MMAP_BUILD_ID: - * Indicates that mmap2 event carries build id data. + * Indicates that mmap2 event carries build ID data. */ #define PERF_RECORD_MISC_EXACT_IP (1 << 14) #define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14) @@ -824,26 +834,26 @@ struct perf_event_mmap_page { #define PERF_RECORD_MISC_EXT_RESERVED (1 << 15) struct perf_event_header { - __u32 type; - __u16 misc; - __u16 size; + __u32 type; + __u16 misc; + __u16 size; }; struct perf_ns_link_info { - __u64 dev; - __u64 ino; + __u64 dev; + __u64 ino; }; enum { - NET_NS_INDEX = 0, - UTS_NS_INDEX = 1, - IPC_NS_INDEX = 2, - PID_NS_INDEX = 3, - USER_NS_INDEX = 4, - MNT_NS_INDEX = 5, - CGROUP_NS_INDEX = 6, - - NR_NAMESPACES, /* number of available namespaces */ + NET_NS_INDEX = 0, + UTS_NS_INDEX = 1, + IPC_NS_INDEX = 2, + PID_NS_INDEX = 3, + USER_NS_INDEX = 4, + MNT_NS_INDEX = 5, + CGROUP_NS_INDEX = 6, + + NR_NAMESPACES, /* number of available namespaces */ }; enum perf_event_type { @@ -859,11 +869,11 @@ enum perf_event_type { * optional fields being ignored. * * struct sample_id { - * { u32 pid, tid; } && PERF_SAMPLE_TID - * { u64 time; } && PERF_SAMPLE_TIME - * { u64 id; } && PERF_SAMPLE_ID - * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID - * { u32 cpu, res; } && PERF_SAMPLE_CPU + * { u32 pid, tid; } && PERF_SAMPLE_TID + * { u64 time; } && PERF_SAMPLE_TIME + * { u64 id; } && PERF_SAMPLE_ID + * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID + * { u32 cpu, res; } && PERF_SAMPLE_CPU * { u64 id; } && PERF_SAMPLE_IDENTIFIER * } && perf_event_attr::sample_id_all * @@ -874,7 +884,7 @@ enum perf_event_type { /* * The MMAP events record the PROT_EXEC mappings so that we can - * correlate userspace IPs to code. They have the following structure: + * correlate user-space IPs to code. They have the following structure: * * struct { * struct perf_event_header header; @@ -884,7 +894,7 @@ enum perf_event_type { * u64 len; * u64 pgoff; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP = 1, @@ -894,7 +904,7 @@ enum perf_event_type { * struct perf_event_header header; * u64 id; * u64 lost; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_LOST = 2, @@ -905,7 +915,7 @@ enum perf_event_type { * * u32 pid, tid; * char comm[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_COMM = 3, @@ -916,7 +926,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_EXIT = 4, @@ -927,7 +937,7 @@ enum perf_event_type { * u64 time; * u64 id; * u64 stream_id; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_THROTTLE = 5, @@ -939,7 +949,7 @@ enum perf_event_type { * u32 pid, ppid; * u32 tid, ptid; * u64 time; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_FORK = 7, @@ -950,7 +960,7 @@ enum perf_event_type { * u32 pid, tid; * * struct read_format values; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_READ = 8, @@ -1005,12 +1015,12 @@ enum perf_event_type { * { u64 counters; } cntr[nr] && PERF_SAMPLE_BRANCH_COUNTERS * } && PERF_SAMPLE_BRANCH_STACK * - * { u64 abi; # enum perf_sample_regs_abi - * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER + * { u64 abi; # enum perf_sample_regs_abi + * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_USER * - * { u64 size; - * char data[size]; - * u64 dyn_size; } && PERF_SAMPLE_STACK_USER + * { u64 size; + * char data[size]; + * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * * { union perf_sample_weight * { @@ -1035,10 +1045,11 @@ enum perf_event_type { * { u64 abi; # enum perf_sample_regs_abi * u64 regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR * { u64 phys_addr;} && PERF_SAMPLE_PHYS_ADDR - * { u64 size; - * char data[size]; } && PERF_SAMPLE_AUX + * { u64 cgroup;} && PERF_SAMPLE_CGROUP * { u64 data_page_size;} && PERF_SAMPLE_DATA_PAGE_SIZE * { u64 code_page_size;} && PERF_SAMPLE_CODE_PAGE_SIZE + * { u64 size; + * char data[size]; } && PERF_SAMPLE_AUX * }; */ PERF_RECORD_SAMPLE = 9, @@ -1070,7 +1081,7 @@ enum perf_event_type { * }; * u32 prot, flags; * char filename[]; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_MMAP2 = 10, @@ -1079,12 +1090,12 @@ enum perf_event_type { * Records that new data landed in the AUX buffer part. * * struct { - * struct perf_event_header header; + * struct perf_event_header header; * - * u64 aux_offset; - * u64 aux_size; + * u64 aux_offset; + * u64 aux_size; * u64 flags; - * struct sample_id sample_id; + * struct sample_id sample_id; * }; */ PERF_RECORD_AUX = 11, @@ -1167,7 +1178,7 @@ enum perf_event_type { PERF_RECORD_KSYMBOL = 17, /* - * Record bpf events: + * Record BPF events: * enum perf_bpf_event_type { * PERF_BPF_EVENT_UNKNOWN = 0, * PERF_BPF_EVENT_PROG_LOAD = 1, @@ -1245,181 +1256,181 @@ enum perf_record_ksymbol_type { #define PERF_RECORD_KSYMBOL_FLAGS_UNREGISTER (1 << 0) enum perf_bpf_event_type { - PERF_BPF_EVENT_UNKNOWN = 0, - PERF_BPF_EVENT_PROG_LOAD = 1, - PERF_BPF_EVENT_PROG_UNLOAD = 2, - PERF_BPF_EVENT_MAX, /* non-ABI */ + PERF_BPF_EVENT_UNKNOWN = 0, + PERF_BPF_EVENT_PROG_LOAD = 1, + PERF_BPF_EVENT_PROG_UNLOAD = 2, + PERF_BPF_EVENT_MAX, /* non-ABI */ }; -#define PERF_MAX_STACK_DEPTH 127 -#define PERF_MAX_CONTEXTS_PER_STACK 8 +#define PERF_MAX_STACK_DEPTH 127 +#define PERF_MAX_CONTEXTS_PER_STACK 8 enum perf_callchain_context { - PERF_CONTEXT_HV = (__u64)-32, - PERF_CONTEXT_KERNEL = (__u64)-128, - PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_HV = (__u64)-32, + PERF_CONTEXT_KERNEL = (__u64)-128, + PERF_CONTEXT_USER = (__u64)-512, - PERF_CONTEXT_GUEST = (__u64)-2048, - PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, - PERF_CONTEXT_GUEST_USER = (__u64)-2560, + PERF_CONTEXT_GUEST = (__u64)-2048, + PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, + PERF_CONTEXT_GUEST_USER = (__u64)-2560, - PERF_CONTEXT_MAX = (__u64)-4095, + PERF_CONTEXT_MAX = (__u64)-4095, }; /** * PERF_RECORD_AUX::flags bits */ -#define PERF_AUX_FLAG_TRUNCATED 0x01 /* record was truncated to fit */ -#define PERF_AUX_FLAG_OVERWRITE 0x02 /* snapshot from overwrite mode */ -#define PERF_AUX_FLAG_PARTIAL 0x04 /* record contains gaps */ -#define PERF_AUX_FLAG_COLLISION 0x08 /* sample collided with another */ +#define PERF_AUX_FLAG_TRUNCATED 0x0001 /* Record was truncated to fit */ +#define PERF_AUX_FLAG_OVERWRITE 0x0002 /* Snapshot from overwrite mode */ +#define PERF_AUX_FLAG_PARTIAL 0x0004 /* Record contains gaps */ +#define PERF_AUX_FLAG_COLLISION 0x0008 /* Sample collided with another */ #define PERF_AUX_FLAG_PMU_FORMAT_TYPE_MASK 0xff00 /* PMU specific trace format type */ /* CoreSight PMU AUX buffer formats */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ -#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_CORESIGHT 0x0000 /* Default for backward compatibility */ +#define PERF_AUX_FLAG_CORESIGHT_FORMAT_RAW 0x0100 /* Raw format of the source */ -#define PERF_FLAG_FD_NO_GROUP (1UL << 0) -#define PERF_FLAG_FD_OUTPUT (1UL << 1) -#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup id, per-cpu mode only */ -#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ +#define PERF_FLAG_FD_NO_GROUP (1UL << 0) +#define PERF_FLAG_FD_OUTPUT (1UL << 1) +#define PERF_FLAG_PID_CGROUP (1UL << 2) /* pid=cgroup ID, per-CPU mode only */ +#define PERF_FLAG_FD_CLOEXEC (1UL << 3) /* O_CLOEXEC */ #if defined(__LITTLE_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_op:5, /* type of opcode */ - mem_lvl:14, /* memory hierarchy level */ - mem_snoop:5, /* snoop mode */ - mem_lock:2, /* lock instr */ - mem_dtlb:7, /* tlb access */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_remote:1, /* remote */ - mem_snoopx:2, /* snoop mode, ext */ - mem_blk:3, /* access blocked */ - mem_hops:3, /* hop level */ - mem_rsvd:18; + __u64 mem_op : 5, /* Type of opcode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_snoop : 5, /* Snoop mode */ + mem_lock : 2, /* Lock instr */ + mem_dtlb : 7, /* TLB access */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_remote : 1, /* Remote */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_blk : 3, /* Access blocked */ + mem_hops : 3, /* Hop level */ + mem_rsvd : 18; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:18, - mem_hops:3, /* hop level */ - mem_blk:3, /* access blocked */ - mem_snoopx:2, /* snoop mode, ext */ - mem_remote:1, /* remote */ - mem_lvl_num:4, /* memory hierarchy level number */ - mem_dtlb:7, /* tlb access */ - mem_lock:2, /* lock instr */ - mem_snoop:5, /* snoop mode */ - mem_lvl:14, /* memory hierarchy level */ - mem_op:5; /* type of opcode */ + __u64 mem_rsvd : 18, + mem_hops : 3, /* Hop level */ + mem_blk : 3, /* Access blocked */ + mem_snoopx : 2, /* Snoop mode, ext */ + mem_remote : 1, /* Remote */ + mem_lvl_num : 4, /* Memory hierarchy level number */ + mem_dtlb : 7, /* TLB access */ + mem_lock : 2, /* Lock instr */ + mem_snoop : 5, /* Snoop mode */ + mem_lvl : 14, /* Memory hierarchy level */ + mem_op : 5; /* Type of opcode */ }; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif -/* type of opcode (load/store/prefetch,code) */ -#define PERF_MEM_OP_NA 0x01 /* not available */ -#define PERF_MEM_OP_LOAD 0x02 /* load instruction */ -#define PERF_MEM_OP_STORE 0x04 /* store instruction */ -#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */ -#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */ -#define PERF_MEM_OP_SHIFT 0 +/* Type of memory opcode: */ +#define PERF_MEM_OP_NA 0x0001 /* Not available */ +#define PERF_MEM_OP_LOAD 0x0002 /* Load instruction */ +#define PERF_MEM_OP_STORE 0x0004 /* Store instruction */ +#define PERF_MEM_OP_PFETCH 0x0008 /* Prefetch */ +#define PERF_MEM_OP_EXEC 0x0010 /* Code (execution) */ +#define PERF_MEM_OP_SHIFT 0 /* - * PERF_MEM_LVL_* namespace being depricated to some extent in the + * The PERF_MEM_LVL_* namespace is being deprecated to some extent in * favour of newer composite PERF_MEM_{LVLNUM_,REMOTE_,SNOOPX_} fields. - * Supporting this namespace inorder to not break defined ABIs. + * We support this namespace in order to not break defined ABIs. * - * memory hierarchy (memory level, hit or miss) + * Memory hierarchy (memory level, hit or miss) */ -#define PERF_MEM_LVL_NA 0x01 /* not available */ -#define PERF_MEM_LVL_HIT 0x02 /* hit level */ -#define PERF_MEM_LVL_MISS 0x04 /* miss level */ -#define PERF_MEM_LVL_L1 0x08 /* L1 */ -#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */ -#define PERF_MEM_LVL_L2 0x20 /* L2 */ -#define PERF_MEM_LVL_L3 0x40 /* L3 */ -#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */ -#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */ -#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */ -#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */ -#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */ -#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ -#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ -#define PERF_MEM_LVL_SHIFT 5 - -#define PERF_MEM_REMOTE_REMOTE 0x01 /* Remote */ -#define PERF_MEM_REMOTE_SHIFT 37 - -#define PERF_MEM_LVLNUM_L1 0x01 /* L1 */ -#define PERF_MEM_LVLNUM_L2 0x02 /* L2 */ -#define PERF_MEM_LVLNUM_L3 0x03 /* L3 */ -#define PERF_MEM_LVLNUM_L4 0x04 /* L4 */ -#define PERF_MEM_LVLNUM_L2_MHB 0x05 /* L2 Miss Handling Buffer */ -#define PERF_MEM_LVLNUM_MSC 0x06 /* Memory-side Cache */ -/* 0x7 available */ -#define PERF_MEM_LVLNUM_UNC 0x08 /* Uncached */ -#define PERF_MEM_LVLNUM_CXL 0x09 /* CXL */ -#define PERF_MEM_LVLNUM_IO 0x0a /* I/O */ -#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */ -#define PERF_MEM_LVLNUM_LFB 0x0c /* LFB / L1 Miss Handling Buffer */ -#define PERF_MEM_LVLNUM_RAM 0x0d /* RAM */ -#define PERF_MEM_LVLNUM_PMEM 0x0e /* PMEM */ -#define PERF_MEM_LVLNUM_NA 0x0f /* N/A */ - -#define PERF_MEM_LVLNUM_SHIFT 33 - -/* snoop mode */ -#define PERF_MEM_SNOOP_NA 0x01 /* not available */ -#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */ -#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */ -#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */ -#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */ -#define PERF_MEM_SNOOP_SHIFT 19 - -#define PERF_MEM_SNOOPX_FWD 0x01 /* forward */ -#define PERF_MEM_SNOOPX_PEER 0x02 /* xfer from peer */ -#define PERF_MEM_SNOOPX_SHIFT 38 - -/* locked instruction */ -#define PERF_MEM_LOCK_NA 0x01 /* not available */ -#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */ -#define PERF_MEM_LOCK_SHIFT 24 +#define PERF_MEM_LVL_NA 0x0001 /* Not available */ +#define PERF_MEM_LVL_HIT 0x0002 /* Hit level */ +#define PERF_MEM_LVL_MISS 0x0004 /* Miss level */ +#define PERF_MEM_LVL_L1 0x0008 /* L1 */ +#define PERF_MEM_LVL_LFB 0x0010 /* Line Fill Buffer */ +#define PERF_MEM_LVL_L2 0x0020 /* L2 */ +#define PERF_MEM_LVL_L3 0x0040 /* L3 */ +#define PERF_MEM_LVL_LOC_RAM 0x0080 /* Local DRAM */ +#define PERF_MEM_LVL_REM_RAM1 0x0100 /* Remote DRAM (1 hop) */ +#define PERF_MEM_LVL_REM_RAM2 0x0200 /* Remote DRAM (2 hops) */ +#define PERF_MEM_LVL_REM_CCE1 0x0400 /* Remote Cache (1 hop) */ +#define PERF_MEM_LVL_REM_CCE2 0x0800 /* Remote Cache (2 hops) */ +#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */ +#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */ +#define PERF_MEM_LVL_SHIFT 5 + +#define PERF_MEM_REMOTE_REMOTE 0x0001 /* Remote */ +#define PERF_MEM_REMOTE_SHIFT 37 + +#define PERF_MEM_LVLNUM_L1 0x0001 /* L1 */ +#define PERF_MEM_LVLNUM_L2 0x0002 /* L2 */ +#define PERF_MEM_LVLNUM_L3 0x0003 /* L3 */ +#define PERF_MEM_LVLNUM_L4 0x0004 /* L4 */ +#define PERF_MEM_LVLNUM_L2_MHB 0x0005 /* L2 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_MSC 0x0006 /* Memory-side Cache */ +/* 0x007 available */ +#define PERF_MEM_LVLNUM_UNC 0x0008 /* Uncached */ +#define PERF_MEM_LVLNUM_CXL 0x0009 /* CXL */ +#define PERF_MEM_LVLNUM_IO 0x000a /* I/O */ +#define PERF_MEM_LVLNUM_ANY_CACHE 0x000b /* Any cache */ +#define PERF_MEM_LVLNUM_LFB 0x000c /* LFB / L1 Miss Handling Buffer */ +#define PERF_MEM_LVLNUM_RAM 0x000d /* RAM */ +#define PERF_MEM_LVLNUM_PMEM 0x000e /* PMEM */ +#define PERF_MEM_LVLNUM_NA 0x000f /* N/A */ + +#define PERF_MEM_LVLNUM_SHIFT 33 + +/* Snoop mode */ +#define PERF_MEM_SNOOP_NA 0x0001 /* Not available */ +#define PERF_MEM_SNOOP_NONE 0x0002 /* No snoop */ +#define PERF_MEM_SNOOP_HIT 0x0004 /* Snoop hit */ +#define PERF_MEM_SNOOP_MISS 0x0008 /* Snoop miss */ +#define PERF_MEM_SNOOP_HITM 0x0010 /* Snoop hit modified */ +#define PERF_MEM_SNOOP_SHIFT 19 + +#define PERF_MEM_SNOOPX_FWD 0x0001 /* Forward */ +#define PERF_MEM_SNOOPX_PEER 0x0002 /* Transfer from peer */ +#define PERF_MEM_SNOOPX_SHIFT 38 + +/* Locked instruction */ +#define PERF_MEM_LOCK_NA 0x0001 /* Not available */ +#define PERF_MEM_LOCK_LOCKED 0x0002 /* Locked transaction */ +#define PERF_MEM_LOCK_SHIFT 24 /* TLB access */ -#define PERF_MEM_TLB_NA 0x01 /* not available */ -#define PERF_MEM_TLB_HIT 0x02 /* hit level */ -#define PERF_MEM_TLB_MISS 0x04 /* miss level */ -#define PERF_MEM_TLB_L1 0x08 /* L1 */ -#define PERF_MEM_TLB_L2 0x10 /* L2 */ -#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/ -#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ -#define PERF_MEM_TLB_SHIFT 26 +#define PERF_MEM_TLB_NA 0x0001 /* Not available */ +#define PERF_MEM_TLB_HIT 0x0002 /* Hit level */ +#define PERF_MEM_TLB_MISS 0x0004 /* Miss level */ +#define PERF_MEM_TLB_L1 0x0008 /* L1 */ +#define PERF_MEM_TLB_L2 0x0010 /* L2 */ +#define PERF_MEM_TLB_WK 0x0020 /* Hardware Walker*/ +#define PERF_MEM_TLB_OS 0x0040 /* OS fault handler */ +#define PERF_MEM_TLB_SHIFT 26 /* Access blocked */ -#define PERF_MEM_BLK_NA 0x01 /* not available */ -#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ -#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ -#define PERF_MEM_BLK_SHIFT 40 - -/* hop level */ -#define PERF_MEM_HOPS_0 0x01 /* remote core, same node */ -#define PERF_MEM_HOPS_1 0x02 /* remote node, same socket */ -#define PERF_MEM_HOPS_2 0x03 /* remote socket, same board */ -#define PERF_MEM_HOPS_3 0x04 /* remote board */ +#define PERF_MEM_BLK_NA 0x0001 /* Not available */ +#define PERF_MEM_BLK_DATA 0x0002 /* Data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x0004 /* Address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + +/* Hop level */ +#define PERF_MEM_HOPS_0 0x0001 /* Remote core, same node */ +#define PERF_MEM_HOPS_1 0x0002 /* Remote node, same socket */ +#define PERF_MEM_HOPS_2 0x0003 /* Remote socket, same board */ +#define PERF_MEM_HOPS_3 0x0004 /* Remote board */ /* 5-7 available */ -#define PERF_MEM_HOPS_SHIFT 43 +#define PERF_MEM_HOPS_SHIFT 43 #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) /* - * single taken branch record layout: + * Layout of single taken branch records: * * from: source instruction (may not always be a branch insn) * to: branch target @@ -1438,37 +1449,37 @@ union perf_mem_data_src { struct perf_branch_entry { __u64 from; __u64 to; - __u64 mispred:1, /* target mispredicted */ - predicted:1,/* target predicted */ - in_tx:1, /* in transaction */ - abort:1, /* transaction abort */ - cycles:16, /* cycle count to last branch */ - type:4, /* branch type */ - spec:2, /* branch speculation info */ - new_type:4, /* additional branch type */ - priv:3, /* privilege level */ - reserved:31; + __u64 mispred : 1, /* target mispredicted */ + predicted : 1, /* target predicted */ + in_tx : 1, /* in transaction */ + abort : 1, /* transaction abort */ + cycles : 16, /* cycle count to last branch */ + type : 4, /* branch type */ + spec : 2, /* branch speculation info */ + new_type : 4, /* additional branch type */ + priv : 3, /* privilege level */ + reserved : 31; }; /* Size of used info bits in struct perf_branch_entry */ #define PERF_BRANCH_ENTRY_INFO_BITS_MAX 33 union perf_sample_weight { - __u64 full; + __u64 full; #if defined(__LITTLE_ENDIAN_BITFIELD) struct { - __u32 var1_dw; - __u16 var2_w; - __u16 var3_w; + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; }; #elif defined(__BIG_ENDIAN_BITFIELD) struct { - __u16 var3_w; - __u16 var2_w; - __u32 var1_dw; + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; }; #else -#error "Unknown endianness" +# error "Unknown endianness" #endif }; diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 2970ef44655a..c27a4e238e4b 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -12,7 +12,7 @@ #define PIDFD_THREAD O_EXCL #ifdef __KERNEL__ #include <linux/sched.h> -#define PIDFD_CLONE CLONE_PIDFD +#define PIDFD_STALE CLONE_PIDFD #endif /* Flags for pidfd_send_signal(). */ @@ -25,10 +25,24 @@ #define PIDFD_INFO_CREDS (1UL << 1) /* Always returned, even if not requested */ #define PIDFD_INFO_CGROUPID (1UL << 2) /* Always returned if available, even if not requested */ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ +#define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ /* + * Values for @coredump_mask in pidfd_info. + * Only valid if PIDFD_INFO_COREDUMP is set in @mask. + * + * Note, the @PIDFD_COREDUMP_ROOT flag indicates that the generated + * coredump should be treated as sensitive and access should only be + * granted to privileged users. + */ +#define PIDFD_COREDUMPED (1U << 0) /* Did crash and... */ +#define PIDFD_COREDUMP_SKIP (1U << 1) /* coredumping generation was skipped. */ +#define PIDFD_COREDUMP_USER (1U << 2) /* coredump was done as the user. */ +#define PIDFD_COREDUMP_ROOT (1U << 3) /* coredump was done as root. */ + +/* * The concept of process and threads in userland and the kernel is a confusing * one - within the kernel every thread is a 'task' with its own individual PID, * however from userland's point of view threads are grouped by a single PID, @@ -92,6 +106,8 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; + __u32 coredump_mask; + __u32 __spare1; }; #define PIDFS_IOCTL_MAGIC 0xFF diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 15c18ef4eb11..43dec6eed559 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -364,4 +364,11 @@ struct prctl_mm_map { # define PR_TIMER_CREATE_RESTORE_IDS_ON 1 # define PR_TIMER_CREATE_RESTORE_IDS_GET 2 +/* FUTEX hash management */ +#define PR_FUTEX_HASH 78 +# define PR_FUTEX_HASH_SET_SLOTS 1 +# define FH_FLAG_IMMUTABLE (1ULL << 0) +# define PR_FUTEX_HASH_GET_SLOTS 2 +# define PR_FUTEX_HASH_GET_IMMUTABLE 3 + #endif /* _LINUX_PRCTL_H */ diff --git a/include/uapi/linux/stat.h b/include/uapi/linux/stat.h index f78ee3670dd5..1686861aae20 100644 --- a/include/uapi/linux/stat.h +++ b/include/uapi/linux/stat.h @@ -182,8 +182,12 @@ struct statx { /* File offset alignment for direct I/O reads */ __u32 stx_dio_read_offset_align; - /* 0xb8 */ - __u64 __spare3[9]; /* Spare space for future expansion */ + /* Optimised max atomic write unit in bytes */ + __u32 stx_atomic_write_unit_max_opt; + __u32 __spare2[1]; + + /* 0xc0 */ + __u64 __spare3[8]; /* Spare space for future expansion */ /* 0x100 */ }; diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index 95762232e018..5929030d4e8b 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 15 +#define TASKSTATS_VERSION 16 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -72,8 +72,6 @@ struct taskstats { */ __u64 cpu_count __attribute__((aligned(8))); __u64 cpu_delay_total; - __u64 cpu_delay_max; - __u64 cpu_delay_min; /* Following four fields atomically updated using task->delays->lock */ @@ -82,14 +80,10 @@ struct taskstats { */ __u64 blkio_count; __u64 blkio_delay_total; - __u64 blkio_delay_max; - __u64 blkio_delay_min; /* Delay waiting for page fault I/O (swap in only) */ __u64 swapin_count; __u64 swapin_delay_total; - __u64 swapin_delay_max; - __u64 swapin_delay_min; /* cpu "wall-clock" running time * On some architectures, value will adjust for cpu time stolen @@ -172,14 +166,11 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; - __u64 freepages_delay_max; - __u64 freepages_delay_min; + /* Delay waiting for thrashing page */ __u64 thrashing_count; __u64 thrashing_delay_total; - __u64 thrashing_delay_max; - __u64 thrashing_delay_min; /* v10: 64-bit btime to avoid overflow */ __u64 ac_btime64; /* 64-bit begin time */ @@ -187,8 +178,6 @@ struct taskstats { /* v11: Delay waiting for memory compact */ __u64 compact_count; __u64 compact_delay_total; - __u64 compact_delay_max; - __u64 compact_delay_min; /* v12 begin */ __u32 ac_tgid; /* thread group ID */ @@ -210,15 +199,37 @@ struct taskstats { /* v13: Delay waiting for write-protect copy */ __u64 wpcopy_count; __u64 wpcopy_delay_total; - __u64 wpcopy_delay_max; - __u64 wpcopy_delay_min; /* v14: Delay waiting for IRQ/SOFTIRQ */ __u64 irq_count; __u64 irq_delay_total; - __u64 irq_delay_max; - __u64 irq_delay_min; - /* v15: add Delay max */ + + /* v15: add Delay max and Delay min */ + + /* v16: move Delay max and Delay min to the end of taskstat */ + __u64 cpu_delay_max; + __u64 cpu_delay_min; + + __u64 blkio_delay_max; + __u64 blkio_delay_min; + + __u64 swapin_delay_max; + __u64 swapin_delay_min; + + __u64 freepages_delay_max; + __u64 freepages_delay_min; + + __u64 thrashing_delay_max; + __u64 thrashing_delay_min; + + __u64 compact_delay_max; + __u64 compact_delay_min; + + __u64 wpcopy_delay_max; + __u64 wpcopy_delay_min; + + __u64 irq_delay_max; + __u64 irq_delay_min; }; diff --git a/include/uapi/linux/ublk_cmd.h b/include/uapi/linux/ublk_cmd.h index 583b86681c93..56c7e3fc666f 100644 --- a/include/uapi/linux/ublk_cmd.h +++ b/include/uapi/linux/ublk_cmd.h @@ -51,6 +51,10 @@ _IOR('u', 0x13, struct ublksrv_ctrl_cmd) #define UBLK_U_CMD_DEL_DEV_ASYNC \ _IOR('u', 0x14, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_UPDATE_SIZE \ + _IOWR('u', 0x15, struct ublksrv_ctrl_cmd) +#define UBLK_U_CMD_QUIESCE_DEV \ + _IOWR('u', 0x16, struct ublksrv_ctrl_cmd) /* * 64bits are enough now, and it should be easy to extend in case of @@ -211,6 +215,63 @@ */ #define UBLK_F_USER_RECOVERY_FAIL_IO (1ULL << 9) +/* + * Resizing a block device is possible with UBLK_U_CMD_UPDATE_SIZE + * New size is passed in cmd->data[0] and is in units of sectors + */ +#define UBLK_F_UPDATE_SIZE (1ULL << 10) + +/* + * request buffer is registered automatically to uring_cmd's io_uring + * context before delivering this io command to ublk server, meantime + * it is un-registered automatically when completing this io command. + * + * For using this feature: + * + * - ublk server has to create sparse buffer table on the same `io_ring_ctx` + * for issuing `UBLK_IO_FETCH_REQ` and `UBLK_IO_COMMIT_AND_FETCH_REQ`. + * If uring_cmd isn't issued on same `io_ring_ctx`, it is ublk server's + * responsibility to unregister the buffer by issuing `IO_UNREGISTER_IO_BUF` + * manually, otherwise this ublk request won't complete. + * + * - ublk server passes auto buf register data via uring_cmd's sqe->addr, + * `struct ublk_auto_buf_reg` is populated from sqe->addr, please see + * the definition of ublk_sqe_addr_to_auto_buf_reg() + * + * - pass buffer index from `ublk_auto_buf_reg.index` + * + * - all reserved fields in `ublk_auto_buf_reg` need to be zeroed + * + * - pass flags from `ublk_auto_buf_reg.flags` if needed + * + * This way avoids extra cost from two uring_cmd, but also simplifies backend + * implementation, such as, the dependency on IO_REGISTER_IO_BUF and + * IO_UNREGISTER_IO_BUF becomes not necessary. + * + * If wrong data or flags are provided, both IO_FETCH_REQ and + * IO_COMMIT_AND_FETCH_REQ are failed, for the latter, the ublk IO request + * won't be completed until new IO_COMMIT_AND_FETCH_REQ command is issued + * successfully + */ +#define UBLK_F_AUTO_BUF_REG (1ULL << 11) + +/* + * Control command `UBLK_U_CMD_QUIESCE_DEV` is added for quiescing device, + * which state can be transitioned to `UBLK_S_DEV_QUIESCED` or + * `UBLK_S_DEV_FAIL_IO` finally, and it needs ublk server cooperation for + * handling `UBLK_IO_RES_ABORT` correctly. + * + * Typical use case is for supporting to upgrade ublk server application, + * meantime keep ublk block device persistent during the period. + * + * This feature is only available when UBLK_F_USER_RECOVERY is enabled. + * + * Note, this command returns -EBUSY in case that all IO commands are being + * handled by ublk server and not completed in specified time period which + * is passed from the control command parameter. + */ +#define UBLK_F_QUIESCE (1ULL << 12) + /* device state */ #define UBLK_S_DEV_DEAD 0 #define UBLK_S_DEV_LIVE 1 @@ -297,6 +358,17 @@ struct ublksrv_ctrl_dev_info { #define UBLK_IO_F_FUA (1U << 13) #define UBLK_IO_F_NOUNMAP (1U << 15) #define UBLK_IO_F_SWAP (1U << 16) +/* + * For UBLK_F_AUTO_BUF_REG & UBLK_AUTO_BUF_REG_FALLBACK only. + * + * This flag is set if auto buffer register is failed & ublk server passes + * UBLK_AUTO_BUF_REG_FALLBACK, and ublk server need to register buffer + * manually for handling the delivered IO command if this flag is observed + * + * ublk server has to check this flag if UBLK_AUTO_BUF_REG_FALLBACK is + * passed in. + */ +#define UBLK_IO_F_NEED_REG_BUF (1U << 17) /* * io cmd is described by this structure, and stored in share memory, indexed @@ -331,6 +403,62 @@ static inline __u32 ublksrv_get_flags(const struct ublksrv_io_desc *iod) return iod->op_flags >> 8; } +/* + * If this flag is set, fallback by completing the uring_cmd and setting + * `UBLK_IO_F_NEED_REG_BUF` in case of auto-buf-register failure; + * otherwise the client ublk request is failed silently + * + * If ublk server passes this flag, it has to check if UBLK_IO_F_NEED_REG_BUF + * is set in `ublksrv_io_desc.op_flags`. If UBLK_IO_F_NEED_REG_BUF is set, + * ublk server needs to register io buffer manually for handling IO command. + */ +#define UBLK_AUTO_BUF_REG_FALLBACK (1 << 0) +#define UBLK_AUTO_BUF_REG_F_MASK UBLK_AUTO_BUF_REG_FALLBACK + +struct ublk_auto_buf_reg { + /* index for registering the delivered request buffer */ + __u16 index; + __u8 flags; + __u8 reserved0; + + /* + * io_ring FD can be passed via the reserve field in future for + * supporting to register io buffer to external io_uring + */ + __u32 reserved1; +}; + +/* + * For UBLK_F_AUTO_BUF_REG, auto buffer register data is carried via + * uring_cmd's sqe->addr: + * + * - bit0 ~ bit15: buffer index + * - bit16 ~ bit23: flags + * - bit24 ~ bit31: reserved0 + * - bit32 ~ bit63: reserved1 + */ +static inline struct ublk_auto_buf_reg ublk_sqe_addr_to_auto_buf_reg( + __u64 sqe_addr) +{ + struct ublk_auto_buf_reg reg = { + .index = sqe_addr & 0xffff, + .flags = (sqe_addr >> 16) & 0xff, + .reserved0 = (sqe_addr >> 24) & 0xff, + .reserved1 = sqe_addr >> 32, + }; + + return reg; +} + +static inline __u64 +ublk_auto_buf_reg_to_sqe_addr(const struct ublk_auto_buf_reg *buf) +{ + __u64 addr = buf->index | (__u64)buf->flags << 16 | (__u64)buf->reserved0 << 24 | + (__u64)buf->reserved1 << 32; + + return addr; +} + /* issued to ublk driver via /dev/ublkcN */ struct ublksrv_io_cmd { __u16 q_id; diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h index c8cb2796130f..9e3b366d5fc7 100644 --- a/include/uapi/linux/videodev2.h +++ b/include/uapi/linux/videodev2.h @@ -153,10 +153,18 @@ enum v4l2_buf_type { V4L2_BUF_TYPE_SDR_OUTPUT = 12, V4L2_BUF_TYPE_META_CAPTURE = 13, V4L2_BUF_TYPE_META_OUTPUT = 14, + /* + * Note: V4L2_TYPE_IS_VALID and V4L2_TYPE_IS_OUTPUT must + * be updated if a new type is added. + */ /* Deprecated, do not use */ V4L2_BUF_TYPE_PRIVATE = 0x80, }; +#define V4L2_TYPE_IS_VALID(type) \ + ((type) >= V4L2_BUF_TYPE_VIDEO_CAPTURE &&\ + (type) <= V4L2_BUF_TYPE_META_OUTPUT) + #define V4L2_TYPE_IS_MULTIPLANAR(type) \ ((type) == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) @@ -164,14 +172,14 @@ enum v4l2_buf_type { #define V4L2_TYPE_IS_OUTPUT(type) \ ((type) == V4L2_BUF_TYPE_VIDEO_OUTPUT \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE \ - || (type) == V4L2_BUF_TYPE_VIDEO_OVERLAY \ || (type) == V4L2_BUF_TYPE_VIDEO_OUTPUT_OVERLAY \ || (type) == V4L2_BUF_TYPE_VBI_OUTPUT \ || (type) == V4L2_BUF_TYPE_SLICED_VBI_OUTPUT \ || (type) == V4L2_BUF_TYPE_SDR_OUTPUT \ || (type) == V4L2_BUF_TYPE_META_OUTPUT) -#define V4L2_TYPE_IS_CAPTURE(type) (!V4L2_TYPE_IS_OUTPUT(type)) +#define V4L2_TYPE_IS_CAPTURE(type) \ + (V4L2_TYPE_IS_VALID(type) && !V4L2_TYPE_IS_OUTPUT(type)) enum v4l2_tuner_type { V4L2_TUNER_RADIO = 1, @@ -643,8 +651,10 @@ struct v4l2_pix_format { /* two planes -- one Y, one Cr + Cb interleaved */ #define V4L2_PIX_FMT_NV12 v4l2_fourcc('N', 'V', '1', '2') /* 12 Y/CbCr 4:2:0 */ #define V4L2_PIX_FMT_NV21 v4l2_fourcc('N', 'V', '2', '1') /* 12 Y/CrCb 4:2:0 */ +#define V4L2_PIX_FMT_NV15 v4l2_fourcc('N', 'V', '1', '5') /* 15 Y/CbCr 4:2:0 10-bit packed */ #define V4L2_PIX_FMT_NV16 v4l2_fourcc('N', 'V', '1', '6') /* 16 Y/CbCr 4:2:2 */ #define V4L2_PIX_FMT_NV61 v4l2_fourcc('N', 'V', '6', '1') /* 16 Y/CrCb 4:2:2 */ +#define V4L2_PIX_FMT_NV20 v4l2_fourcc('N', 'V', '2', '0') /* 20 Y/CbCr 4:2:2 10-bit packed */ #define V4L2_PIX_FMT_NV24 v4l2_fourcc('N', 'V', '2', '4') /* 24 Y/CbCr 4:4:4 */ #define V4L2_PIX_FMT_NV42 v4l2_fourcc('N', 'V', '4', '2') /* 24 Y/CrCb 4:4:4 */ #define V4L2_PIX_FMT_P010 v4l2_fourcc('P', '0', '1', '0') /* 24 Y/CbCr 4:2:0 10-bit per component */ @@ -858,6 +868,10 @@ struct v4l2_pix_format { #define V4L2_META_FMT_RK_ISP1_STAT_3A v4l2_fourcc('R', 'K', '1', 'S') /* Rockchip ISP1 3A Statistics */ #define V4L2_META_FMT_RK_ISP1_EXT_PARAMS v4l2_fourcc('R', 'K', '1', 'E') /* Rockchip ISP1 3a Extensible Parameters */ +/* Vendor specific - used for C3_ISP */ +#define V4L2_META_FMT_C3ISP_PARAMS v4l2_fourcc('C', '3', 'P', 'M') /* Amlogic C3 ISP Parameters */ +#define V4L2_META_FMT_C3ISP_STATS v4l2_fourcc('C', '3', 'S', 'T') /* Amlogic C3 ISP Statistics */ + /* Vendor specific - used for RaspberryPi PiSP */ #define V4L2_META_FMT_RPI_BE_CFG v4l2_fourcc('R', 'P', 'B', 'C') /* PiSP BE configuration */ #define V4L2_META_FMT_RPI_FE_CFG v4l2_fourcc('R', 'P', 'F', 'C') /* PiSP FE configuration */ diff --git a/include/uapi/linux/virtio_gpu.h b/include/uapi/linux/virtio_gpu.h index bf2c9cabd207..be109777d10d 100644 --- a/include/uapi/linux/virtio_gpu.h +++ b/include/uapi/linux/virtio_gpu.h @@ -309,8 +309,9 @@ struct virtio_gpu_cmd_submit { #define VIRTIO_GPU_CAPSET_VIRGL 1 #define VIRTIO_GPU_CAPSET_VIRGL2 2 -/* 3 is reserved for gfxstream */ +#define VIRTIO_GPU_CAPSET_GFXSTREAM_VULKAN 3 #define VIRTIO_GPU_CAPSET_VENUS 4 +#define VIRTIO_GPU_CAPSET_CROSS_DOMAIN 5 #define VIRTIO_GPU_CAPSET_DRM 6 /* VIRTIO_GPU_CMD_GET_CAPSET_INFO */ |