diff options
Diffstat (limited to 'include/uapi/drm/amdgpu_drm.h')
| -rw-r--r-- | include/uapi/drm/amdgpu_drm.h | 396 |
1 files changed, 380 insertions, 16 deletions
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index 25d5c6e90a99..9f3090db2f16 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -54,6 +54,10 @@ 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_AMDGPU_GEM_LIST_HANDLES 0x19 #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 +75,10 @@ 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) +#define DRM_IOCTL_AMDGPU_GEM_LIST_HANDLES DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_GEM_LIST_HANDLES, struct drm_amdgpu_gem_list_handles) /** * DOC: memory domains @@ -110,7 +118,7 @@ extern "C" { AMDGPU_GEM_DOMAIN_VRAM | \ AMDGPU_GEM_DOMAIN_GDS | \ AMDGPU_GEM_DOMAIN_GWS | \ - AMDGPU_GEM_DOMAIN_OA | \ + AMDGPU_GEM_DOMAIN_OA | \ AMDGPU_GEM_DOMAIN_DOORBELL) /* Flag that CPU access will be required for the case of VRAM domain */ @@ -319,6 +327,263 @@ 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. + */ + __u16 num_syncobj_handles; + __u16 pad0; + __u32 pad1; + /** + * @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. + */ + __u16 num_syncobj_handles; + __u16 pad0; + /** + * @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 @@ -540,6 +805,21 @@ union drm_amdgpu_wait_fences { #define AMDGPU_GEM_OP_GET_GEM_CREATE_INFO 0 #define AMDGPU_GEM_OP_SET_PLACEMENT 1 +#define AMDGPU_GEM_OP_GET_MAPPING_INFO 2 + +struct drm_amdgpu_gem_vm_entry { + /* Start of mapping (in bytes) */ + __u64 addr; + + /* Size of mapping (in bytes) */ + __u64 size; + + /* Mapping offset */ + __u64 offset; + + /* flags needed to recreate mapping */ + __u64 flags; +}; /* Sets or returns a value associated with a buffer. */ struct drm_amdgpu_gem_op { @@ -547,8 +827,44 @@ struct drm_amdgpu_gem_op { __u32 handle; /** AMDGPU_GEM_OP_* */ __u32 op; - /** Input or return value */ + /** Input or return value. For MAPPING_INFO op: pointer to array of struct drm_amdgpu_gem_vm_entry */ __u64 value; + /** For MAPPING_INFO op: number of mappings (in/out) */ + __u32 num_entries; + + __u32 padding; +}; + +#define AMDGPU_GEM_LIST_HANDLES_FLAG_IS_IMPORT (1 << 0) + +struct drm_amdgpu_gem_list_handles { + /* User pointer to array of drm_amdgpu_gem_bo_info_entry */ + __u64 entries; + + /* Size of entries buffer / Number of handles in process (if larger than size of buffer, must retry) */ + __u32 num_entries; + + __u32 padding; +}; + +struct drm_amdgpu_gem_list_handles_entry { + /* gem handle of buffer object */ + __u32 gem_handle; + + /* Currently just one flag: IS_IMPORT */ + __u32 flags; + + /* Size of bo */ + __u64 size; + + /* Preferred domains for GEM_CREATE */ + __u64 preferred_domains; + + /* GEM_CREATE flags for re-creation of buffer */ + __u64 alloc_flags; + + /* physical start_addr alignment in bytes for some HW requirements */ + __u64 alignment; }; #define AMDGPU_VA_OP_MAP 1 @@ -566,7 +882,7 @@ struct drm_amdgpu_gem_op { #define AMDGPU_VM_PAGE_WRITEABLE (1 << 2) /* executable mapping, new for VI */ #define AMDGPU_VM_PAGE_EXECUTABLE (1 << 3) -/* partially resident texture */ +/* unmapped page of partially resident textures */ #define AMDGPU_VM_PAGE_PRT (1 << 4) /* MTYPE flags use bit 5 to 8 */ #define AMDGPU_VM_MTYPE_MASK (0xf << 5) @@ -599,6 +915,19 @@ 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 @@ -758,10 +1087,11 @@ struct drm_amdgpu_cs_chunk_cp_gfx_shadow { * Query h/w info: Flag that this is integrated (a.h.a. fusion) GPU * */ -#define AMDGPU_IDS_FLAGS_FUSION 0x1 -#define AMDGPU_IDS_FLAGS_PREEMPTION 0x2 -#define AMDGPU_IDS_FLAGS_TMZ 0x4 -#define AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD 0x8 +#define AMDGPU_IDS_FLAGS_FUSION 0x01 +#define AMDGPU_IDS_FLAGS_PREEMPTION 0x02 +#define AMDGPU_IDS_FLAGS_TMZ 0x04 +#define AMDGPU_IDS_FLAGS_CONFORMANT_TRUNC_COORD 0x08 +#define AMDGPU_IDS_FLAGS_GANG_SUBMIT 0x10 /* * Query h/w info: Flag identifying VF/PF/PT mode @@ -940,6 +1270,8 @@ 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 +1425,8 @@ 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 +#define AMDGPU_VRAM_TYPE_HBM4 14 struct drm_amdgpu_info_device { /** PCI Device ID */ @@ -1198,6 +1532,9 @@ 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 { @@ -1214,6 +1551,8 @@ struct drm_amdgpu_info_hw_ip { __u32 available_rings; /** version info: bits 23:16 major, 15:8 minor, 7:0 revision */ __u32 ip_discovery_version; + /* Userq available slots */ + __u32 userq_num_slots; }; struct drm_amdgpu_info_num_handles { @@ -1279,6 +1618,39 @@ 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_compute { + /* EOP size for gfx11 */ + __u32 eop_size; + /* EOP base virtual alignment for gfx11 */ + __u32 eop_alignment; +}; + +struct drm_amdgpu_info_uq_metadata_sdma { + /* context save area size for sdma6 */ + __u32 csa_size; + /* context save area base virtual alignment for sdma6 */ + __u32 csa_alignment; +}; + +struct drm_amdgpu_info_uq_metadata { + union { + struct drm_amdgpu_info_uq_metadata_gfx gfx; + struct drm_amdgpu_info_uq_metadata_compute compute; + struct drm_amdgpu_info_uq_metadata_sdma sdma; + }; +}; + /* * Supported GPU families */ @@ -1298,17 +1670,9 @@ struct drm_amdgpu_info_gpuvm_fault { #define AMDGPU_FAMILY_GC_10_3_6 149 /* GC 10.3.6 */ #define AMDGPU_FAMILY_GC_10_3_7 151 /* GC 10.3.7 */ #define AMDGPU_FAMILY_GC_11_5_0 150 /* GC 11.5.0 */ +#define AMDGPU_FAMILY_GC_11_5_4 154 /* GC 11.5.4 */ #define AMDGPU_FAMILY_GC_12_0_0 152 /* GC 12.0.0 */ -/* FIXME wrong namespace! */ -struct drm_color_ctm_3x4 { - /* - * Conversion matrix with 3x4 dimensions in S31.32 sign-magnitude - * (not two's complement!) format. - */ - __u64 matrix[12]; -}; - #if defined(__cplusplus) } #endif |