diff options
Diffstat (limited to 'include/uapi/linux/io_uring.h')
| -rw-r--r-- | include/uapi/linux/io_uring.h | 327 |
1 files changed, 320 insertions, 7 deletions
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 994bf7af0efe..b5b23c0d5283 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -50,7 +50,7 @@ struct io_uring_sqe { }; __u32 len; /* buffer size or number of iovecs */ union { - __kernel_rwf_t rw_flags; + __u32 rw_flags; __u32 fsync_flags; __u16 poll_events; /* compatibility */ __u32 poll32_events; /* word-reversed for BE */ @@ -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 */ @@ -87,17 +88,26 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + __u32 zcrx_ifq_idx; __u32 optlen; struct { __u16 addr_len; __u16 __pad3[1]; }; + struct { + __u8 write_stream; + __u8 __pad4[3]; + }; }; union { struct { __u64 addr3; __u64 __pad2[1]; }; + struct { + __u64 attr_ptr; /* pointer to attribute information */ + __u64 attr_type_mask; /* bit mask of attributes */ + }; __u64 optval; /* * If the ring is initialized with IORING_SETUP_SQE128, then @@ -107,6 +117,18 @@ struct io_uring_sqe { }; }; +/* sqe->attr_type_mask flags */ +#define IORING_RW_ATTR_FLAG_PI (1U << 0) +/* PI attribute information */ +struct io_uring_attr_pi { + __u16 flags; + __u16 app_tag; + __u32 len; + __u64 addr; + __u64 seed; + __u64 rsvd; +}; + /* * If sqe->file_index is set to this for opcodes that instantiate a new * direct descriptor (like openat/openat2/accept), then io_uring will allocate @@ -200,6 +222,21 @@ enum io_uring_sqe_flags_bit { */ #define IORING_SETUP_NO_SQARRAY (1U << 16) +/* Use hybrid poll in iopoll process */ +#define IORING_SETUP_HYBRID_IOPOLL (1U << 17) + +/* + * Allow both 16b and 32b CQEs. If a 32b CQE is posted, it will have + * IORING_CQE_F_32 set in cqe->flags. + */ +#define IORING_SETUP_CQE_MIXED (1U << 18) + +/* + * Allow both 64b and 128b SQEs. If a 128b SQE is posted, it will have + * a 128b opcode. + */ +#define IORING_SETUP_SQE_MIXED (1U << 19) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -257,6 +294,15 @@ enum io_uring_op { IORING_OP_FUTEX_WAITV, IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, + IORING_OP_BIND, + IORING_OP_LISTEN, + IORING_OP_RECV_ZC, + IORING_OP_EPOLL_WAIT, + IORING_OP_READV_FIXED, + IORING_OP_WRITEV_FIXED, + IORING_OP_PIPE, + IORING_OP_NOP128, + IORING_OP_URING_CMD128, /* this goes last, obviously */ IORING_OP_LAST, @@ -266,9 +312,13 @@ enum io_uring_op { * sqe->uring_cmd_flags top 8bits aren't available for userspace * IORING_URING_CMD_FIXED use registered buffer; pass this flag * along with setting sqe->buf_index. + * IORING_URING_CMD_MULTISHOT must be used with buffer select, like other + * multishot commands. Not compatible with + * IORING_URING_CMD_FIXED, for now. */ #define IORING_URING_CMD_FIXED (1U << 0) -#define IORING_URING_CMD_MASK IORING_URING_CMD_FIXED +#define IORING_URING_CMD_MULTISHOT (1U << 1) +#define IORING_URING_CMD_MASK (IORING_URING_CMD_FIXED | IORING_URING_CMD_MULTISHOT) /* @@ -359,13 +409,17 @@ enum io_uring_op { * result will be the number of buffers send, with * the starting buffer ID in cqe->flags as per * usual for provided buffer usage. The buffers - * will be contigious from the starting buffer ID. + * will be contiguous from the starting buffer ID. + * + * IORING_SEND_VECTORIZED If set, SEND[_ZC] will take a pointer to a io_vec + * to allow vectorized send operations. */ #define IORING_RECVSEND_POLL_FIRST (1U << 0) #define IORING_RECV_MULTISHOT (1U << 1) #define IORING_RECVSEND_FIXED_BUF (1U << 2) #define IORING_SEND_ZC_REPORT_USAGE (1U << 3) #define IORING_RECVSEND_BUNDLE (1U << 4) +#define IORING_SEND_VECTORIZED (1U << 5) /* * cqe.res for IORING_CQE_F_NOTIF if @@ -414,12 +468,17 @@ enum io_uring_msg_ring_flags { * IORING_NOP_INJECT_RESULT Inject result from sqe->result */ #define IORING_NOP_INJECT_RESULT (1U << 0) +#define IORING_NOP_FILE (1U << 1) +#define IORING_NOP_FIXED_FILE (1U << 2) +#define IORING_NOP_FIXED_BUFFER (1U << 3) +#define IORING_NOP_TW (1U << 4) +#define IORING_NOP_CQE32 (1U << 5) /* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { - __u64 user_data; /* sqe->data submission passed back */ + __u64 user_data; /* sqe->user_data value passed back */ __s32 res; /* result code for this event */ __u32 flags; @@ -438,11 +497,31 @@ struct io_uring_cqe { * IORING_CQE_F_SOCK_NONEMPTY If set, more data to read after socket recv * IORING_CQE_F_NOTIF Set for notification CQEs. Can be used to distinct * them from sends. + * IORING_CQE_F_BUF_MORE If set, the buffer ID set in the completion will get + * more completions. In other words, the buffer is being + * partially consumed, and will be used by the kernel for + * more completions. This is only set for buffers used via + * the incremental buffer consumption, as provided by + * a ring buffer setup with IOU_PBUF_RING_INC. For any + * other provided buffer type, all completions with a + * buffer passed back is automatically returned to the + * application. + * IORING_CQE_F_SKIP If set, then the application/liburing must ignore this + * CQE. It's only purpose is to fill a gap in the ring, + * if a large CQE is attempted posted when the ring has + * just a single small CQE worth of space left before + * wrapping. + * IORING_CQE_F_32 If set, this is a 32b/big-cqe posting. Use with rings + * setup in a mixed CQE mode, where both 16b and 32b + * CQEs may be posted to the CQ ring. */ #define IORING_CQE_F_BUFFER (1U << 0) #define IORING_CQE_F_MORE (1U << 1) #define IORING_CQE_F_SOCK_NONEMPTY (1U << 2) #define IORING_CQE_F_NOTIF (1U << 3) +#define IORING_CQE_F_BUF_MORE (1U << 4) +#define IORING_CQE_F_SKIP (1U << 5) +#define IORING_CQE_F_32 (1U << 15) #define IORING_CQE_BUFFER_SHIFT 16 @@ -505,6 +584,9 @@ struct io_cqring_offsets { #define IORING_ENTER_SQ_WAIT (1U << 2) #define IORING_ENTER_EXT_ARG (1U << 3) #define IORING_ENTER_REGISTERED_RING (1U << 4) +#define IORING_ENTER_ABS_TIMER (1U << 5) +#define IORING_ENTER_EXT_ARG_REG (1U << 6) +#define IORING_ENTER_NO_IOWAIT (1U << 7) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -540,6 +622,9 @@ struct io_uring_params { #define IORING_FEAT_LINKED_FILE (1U << 12) #define IORING_FEAT_REG_REG_RING (1U << 13) #define IORING_FEAT_RECVSEND_BUNDLE (1U << 14) +#define IORING_FEAT_MIN_TIMEOUT (1U << 15) +#define IORING_FEAT_RW_ATTR (1U << 16) +#define IORING_FEAT_NO_IOWAIT (1U << 17) /* * io_uring_register(2) opcodes and arguments @@ -593,6 +678,28 @@ enum io_uring_register_op { IORING_REGISTER_NAPI = 27, IORING_UNREGISTER_NAPI = 28, + IORING_REGISTER_CLOCK = 29, + + /* clone registered buffers from source ring to current ring */ + IORING_REGISTER_CLONE_BUFFERS = 30, + + /* send MSG_RING without having a ring */ + IORING_REGISTER_SEND_MSG_RING = 31, + + /* register a netdev hw rx queue for zerocopy */ + IORING_REGISTER_ZCRX_IFQ = 32, + + /* resize CQ ring */ + IORING_REGISTER_RESIZE_RINGS = 33, + + IORING_REGISTER_MEM_REGION = 34, + + /* query various aspects of io_uring, see linux/io_uring/query.h */ + IORING_REGISTER_QUERY = 35, + + /* auxiliary zcrx configuration, see enum zcrx_ctrl_op */ + IORING_REGISTER_ZCRX_CTRL = 36, + /* this goes last */ IORING_REGISTER_LAST, @@ -613,6 +720,31 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +enum { + /* initialise with user provided memory pointed by user_addr */ + IORING_MEM_REGION_TYPE_USER = 1, +}; + +struct io_uring_region_desc { + __u64 user_addr; + __u64 size; + __u32 flags; + __u32 id; + __u64 mmap_offset; + __u64 __resv[4]; +}; + +enum { + /* expose the region as registered wait arguments */ + IORING_MEM_REGION_REG_WAIT_ARG = 1, +}; + +struct io_uring_mem_region_reg { + __u64 region_uptr; /* struct io_uring_region_desc * */ + __u64 flags; + __u64 __resv[2]; +}; + /* * Register a fully sparse file space, rather than pass in an array of all * -1 file descriptors. @@ -673,6 +805,25 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_clock_register { + __u32 clockid; + __u32 __resv[3]; +}; + +enum { + IORING_REGISTER_SRC_REGISTERED = (1U << 0), + IORING_REGISTER_DST_REPLACE = (1U << 1), +}; + +struct io_uring_clone_buffers { + __u32 src_fd; + __u32 flags; + __u32 src_off; + __u32 dst_off; + __u32 nr; + __u32 pad[3]; +}; + struct io_uring_buf { __u64 addr; __u32 len; @@ -705,9 +856,17 @@ struct io_uring_buf_ring { * mmap(2) with the offset set as: * IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT) * to get a virtual mapping for the ring. + * IOU_PBUF_RING_INC: If set, buffers consumed from this buffer ring can be + * consumed incrementally. Normally one (or more) buffers + * are fully consumed. With incremental consumptions, it's + * feasible to register big ranges of buffers, and each + * use of it will consume only as much as it needs. This + * requires that both the kernel and application keep + * track of where the current read/recv index is at. */ enum io_uring_register_pbuf_ring_flags { IOU_PBUF_RING_MMAP = 1, + IOU_PBUF_RING_INC = 2, }; /* argument for IORING_(UN)REGISTER_PBUF_RING */ @@ -726,12 +885,40 @@ struct io_uring_buf_status { __u32 resv[8]; }; +enum io_uring_napi_op { + /* register/ungister backward compatible opcode */ + IO_URING_NAPI_REGISTER_OP = 0, + + /* opcodes to update napi_list when static tracking is used */ + IO_URING_NAPI_STATIC_ADD_ID = 1, + IO_URING_NAPI_STATIC_DEL_ID = 2 +}; + +enum io_uring_napi_tracking_strategy { + /* value must be 0 for backward compatibility */ + IO_URING_NAPI_TRACKING_DYNAMIC = 0, + IO_URING_NAPI_TRACKING_STATIC = 1, + IO_URING_NAPI_TRACKING_INACTIVE = 255 +}; + /* argument for IORING_(UN)REGISTER_NAPI */ struct io_uring_napi { __u32 busy_poll_to; __u8 prefer_busy_poll; - __u8 pad[3]; - __u64 resv; + + /* a io_uring_napi_op value */ + __u8 opcode; + __u8 pad[2]; + + /* + * for IO_URING_NAPI_REGISTER_OP, it is a + * io_uring_napi_tracking_strategy value. + * + * for IO_URING_NAPI_STATIC_ADD_ID/IO_URING_NAPI_STATIC_DEL_ID + * it is the napi id to add/del from napi_list. + */ + __u32 op_param; + __u32 resv; }; /* @@ -753,10 +940,33 @@ enum io_uring_register_restriction_op { IORING_RESTRICTION_LAST }; +enum { + IORING_REG_WAIT_TS = (1U << 0), +}; + +/* + * Argument for io_uring_enter(2) with + * IORING_GETEVENTS | IORING_ENTER_EXT_ARG_REG set, where the actual argument + * is an index into a previously registered fixed wait region described by + * the below structure. + */ +struct io_uring_reg_wait { + struct __kernel_timespec ts; + __u32 min_wait_usec; + __u32 flags; + __u64 sigmask; + __u32 sigmask_sz; + __u32 pad[3]; + __u64 pad2[2]; +}; + +/* + * Argument for io_uring_enter(2) with IORING_GETEVENTS | IORING_ENTER_EXT_ARG + */ struct io_uring_getevents_arg { __u64 sigmask; __u32 sigmask_sz; - __u32 pad; + __u32 min_wait_usec; __u64 ts; }; @@ -798,6 +1008,109 @@ enum io_uring_socket_op { SOCKET_URING_OP_SIOCOUTQ, SOCKET_URING_OP_GETSOCKOPT, SOCKET_URING_OP_SETSOCKOPT, + SOCKET_URING_OP_TX_TIMESTAMP, + SOCKET_URING_OP_GETSOCKNAME, +}; + +/* + * SOCKET_URING_OP_TX_TIMESTAMP definitions + */ + +#define IORING_TIMESTAMP_HW_SHIFT 16 +/* The cqe->flags bit from which the timestamp type is stored */ +#define IORING_TIMESTAMP_TYPE_SHIFT (IORING_TIMESTAMP_HW_SHIFT + 1) +/* The cqe->flags flag signifying whether it's a hardware timestamp */ +#define IORING_CQE_F_TSTAMP_HW ((__u32)1 << IORING_TIMESTAMP_HW_SHIFT) + +struct io_timespec { + __u64 tv_sec; + __u64 tv_nsec; +}; + +/* Zero copy receive refill queue entry */ +struct io_uring_zcrx_rqe { + __u64 off; + __u32 len; + __u32 __pad; +}; + +struct io_uring_zcrx_cqe { + __u64 off; + __u64 __pad; +}; + +/* The bit from which area id is encoded into offsets */ +#define IORING_ZCRX_AREA_SHIFT 48 +#define IORING_ZCRX_AREA_MASK (~(((__u64)1 << IORING_ZCRX_AREA_SHIFT) - 1)) + +struct io_uring_zcrx_offsets { + __u32 head; + __u32 tail; + __u32 rqes; + __u32 __resv2; + __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 dmabuf_fd; + __u64 __resv2[2]; +}; + +enum zcrx_reg_flags { + ZCRX_REG_IMPORT = 1, +}; + +/* + * Argument for IORING_REGISTER_ZCRX_IFQ + */ +struct io_uring_zcrx_ifq_reg { + __u32 if_idx; + __u32 if_rxq; + __u32 rq_entries; + __u32 flags; + + __u64 area_ptr; /* pointer to struct io_uring_zcrx_area_reg */ + __u64 region_ptr; /* struct io_uring_region_desc * */ + + struct io_uring_zcrx_offsets offsets; + __u32 zcrx_id; + __u32 __resv2; + __u64 __resv[3]; +}; + +enum zcrx_ctrl_op { + ZCRX_CTRL_FLUSH_RQ, + ZCRX_CTRL_EXPORT, + + __ZCRX_CTRL_LAST, +}; + +struct zcrx_ctrl_flush_rq { + __u64 __resv[6]; +}; + +struct zcrx_ctrl_export { + __u32 zcrx_fd; + __u32 __resv1[11]; +}; + +struct zcrx_ctrl { + __u32 zcrx_id; + __u32 op; /* see enum zcrx_ctrl_op */ + __u64 __resv[2]; + + union { + struct zcrx_ctrl_export zc_export; + struct zcrx_ctrl_flush_rq zc_flush; + }; }; #ifdef __cplusplus |