diff options
Diffstat (limited to 'include/uapi/linux/io_uring.h')
| -rw-r--r-- | include/uapi/linux/io_uring.h | 204 |
1 files changed, 189 insertions, 15 deletions
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 7bd10201a02b..e11c82638527 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -72,6 +72,7 @@ struct io_uring_sqe { __u32 waitid_flags; __u32 futex_flags; __u32 install_fd_flags; + __u32 nop_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -97,6 +98,10 @@ struct io_uring_sqe { __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 @@ -106,6 +111,18 @@ 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 @@ -115,7 +132,7 @@ struct io_uring_sqe { */ #define IORING_FILE_INDEX_ALLOC (~0U) -enum { +enum io_uring_sqe_flags_bit { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, IOSQE_IO_LINK_BIT, @@ -199,6 +216,9 @@ enum { */ #define IORING_SETUP_NO_SQARRAY (1U << 16) +/* Use hybrid poll in iopoll process */ +#define IORING_SETUP_HYBRID_IOPOLL (1U << 17) + enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, @@ -256,6 +276,8 @@ enum io_uring_op { IORING_OP_FUTEX_WAITV, IORING_OP_FIXED_FD_INSTALL, IORING_OP_FTRUNCATE, + IORING_OP_BIND, + IORING_OP_LISTEN, /* this goes last, obviously */ IORING_OP_LAST, @@ -351,11 +373,20 @@ enum io_uring_op { * 0 is reported if zerocopy was actually possible. * IORING_NOTIF_USAGE_ZC_COPIED if data was copied * (at least partially). + * + * IORING_RECVSEND_BUNDLE Used with IOSQE_BUFFER_SELECT. If set, send or + * recv will grab as many buffers from the buffer + * group ID given and send them all. The completion + * 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. */ #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) /* * cqe.res for IORING_CQE_F_NOTIF if @@ -370,11 +401,13 @@ enum io_uring_op { * accept flags stored in sqe->ioprio */ #define IORING_ACCEPT_MULTISHOT (1U << 0) +#define IORING_ACCEPT_DONTWAIT (1U << 1) +#define IORING_ACCEPT_POLL_FIRST (1U << 2) /* * IORING_OP_MSG_RING command types, stored in sqe->addr */ -enum { +enum io_uring_msg_ring_flags { IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ IORING_MSG_SEND_FD, /* send a registered fd to another ring */ }; @@ -397,10 +430,20 @@ enum { #define IORING_FIXED_FD_NO_CLOEXEC (1U << 0) /* + * IORING_OP_NOP flags (sqe->nop_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) + +/* * 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; @@ -419,15 +462,23 @@ 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. */ #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) -enum { - IORING_CQE_BUFFER_SHIFT = 16, -}; +#define IORING_CQE_BUFFER_SHIFT 16 /* * Magic offsets for the application to mmap the data it needs @@ -488,6 +539,8 @@ 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) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -522,11 +575,14 @@ struct io_uring_params { #define IORING_FEAT_CQE_SKIP (1U << 11) #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) /* * io_uring_register(2) opcodes and arguments */ -enum { +enum io_uring_register_op { IORING_REGISTER_BUFFERS = 0, IORING_UNREGISTER_BUFFERS = 1, IORING_REGISTER_FILES = 2, @@ -575,6 +631,21 @@ enum { 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, + + /* 32 reserved for zc rx */ + + /* resize CQ ring */ + IORING_REGISTER_RESIZE_RINGS = 33, + + IORING_REGISTER_MEM_REGION = 34, + /* this goes last */ IORING_REGISTER_LAST, @@ -583,7 +654,7 @@ enum { }; /* io-wq worker categories */ -enum { +enum io_wq_type { IO_WQ_BOUND, IO_WQ_UNBOUND, }; @@ -595,6 +666,31 @@ 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. @@ -655,6 +751,25 @@ 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; @@ -687,9 +802,17 @@ 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. - */ -enum { + * 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 */ @@ -708,18 +831,46 @@ 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; }; /* * io_uring_restriction->opcode values */ -enum { +enum io_uring_register_restriction_op { /* Allow an io_uring_register(2) opcode */ IORING_RESTRICTION_REGISTER_OP = 0, @@ -735,10 +886,33 @@ enum { 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; }; @@ -775,7 +949,7 @@ struct io_uring_recvmsg_out { /* * Argument for IORING_OP_URING_CMD when file is a socket */ -enum { +enum io_uring_socket_op { SOCKET_URING_OP_SIOCINQ = 0, SOCKET_URING_OP_SIOCOUTQ, SOCKET_URING_OP_GETSOCKOPT, |