diff options
Diffstat (limited to 'include/uapi/linux/io_uring.h')
| -rw-r--r-- | include/uapi/linux/io_uring.h | 268 |
1 files changed, 260 insertions, 8 deletions
diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index c45b5e9a9387..2df3225b562f 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -10,6 +10,11 @@ #include <linux/fs.h> #include <linux/types.h> +#include <linux/time_types.h> + +#ifdef __cplusplus +extern "C" { +#endif /* * IO submission data structure (Submission Queue Entry) @@ -22,6 +27,10 @@ struct io_uring_sqe { union { __u64 off; /* offset into file */ __u64 addr2; + struct { + __u32 cmd_op; + __u32 __pad1; + }; }; union { __u64 addr; /* pointer to buffer or iovecs */ @@ -45,6 +54,9 @@ struct io_uring_sqe { __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; + __u32 xattr_flags; + __u32 msg_ring_flags; + __u32 uring_cmd_flags; }; __u64 user_data; /* data to be passed back at completion time */ /* pack this to avoid bogus arm OABI complaints */ @@ -59,10 +71,33 @@ struct io_uring_sqe { union { __s32 splice_fd_in; __u32 file_index; + struct { + __u16 addr_len; + __u16 __pad3[1]; + }; + }; + union { + struct { + __u64 addr3; + __u64 __pad2[1]; + }; + /* + * If the ring is initialized with IORING_SETUP_SQE128, then + * this field is used for 80 bytes of arbitrary command data + */ + __u8 cmd[0]; }; - __u64 __pad2[2]; }; +/* + * 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 + * an available direct descriptor instead of having the application pass one + * in. The picked direct descriptor will be returned in cqe->res, or -ENFILE + * if the space is full. + */ +#define IORING_FILE_INDEX_ALLOC (~0U) + enum { IOSQE_FIXED_FILE_BIT, IOSQE_IO_DRAIN_BIT, @@ -70,6 +105,7 @@ enum { IOSQE_IO_HARDLINK_BIT, IOSQE_ASYNC_BIT, IOSQE_BUFFER_SELECT_BIT, + IOSQE_CQE_SKIP_SUCCESS_BIT, }; /* @@ -87,6 +123,8 @@ enum { #define IOSQE_ASYNC (1U << IOSQE_ASYNC_BIT) /* select buffer from sqe->buf_group */ #define IOSQE_BUFFER_SELECT (1U << IOSQE_BUFFER_SELECT_BIT) +/* don't post CQE if request succeeded */ +#define IOSQE_CQE_SKIP_SUCCESS (1U << IOSQE_CQE_SKIP_SUCCESS_BIT) /* * io_uring_setup() flags @@ -98,8 +136,36 @@ enum { #define IORING_SETUP_CLAMP (1U << 4) /* clamp SQ/CQ ring sizes */ #define IORING_SETUP_ATTACH_WQ (1U << 5) /* attach to existing wq */ #define IORING_SETUP_R_DISABLED (1U << 6) /* start with ring disabled */ +#define IORING_SETUP_SUBMIT_ALL (1U << 7) /* continue submit on error */ +/* + * Cooperative task running. When requests complete, they often require + * forcing the submitter to transition to the kernel to complete. If this + * flag is set, work will be done when the task transitions anyway, rather + * than force an inter-processor interrupt reschedule. This avoids interrupting + * a task running in userspace, and saves an IPI. + */ +#define IORING_SETUP_COOP_TASKRUN (1U << 8) +/* + * If COOP_TASKRUN is set, get notified if task work is available for + * running and a kernel transition would be needed to run it. This sets + * IORING_SQ_TASKRUN in the sq ring flags. Not valid with COOP_TASKRUN. + */ +#define IORING_SETUP_TASKRUN_FLAG (1U << 9) +#define IORING_SETUP_SQE128 (1U << 10) /* SQEs are 128 byte */ +#define IORING_SETUP_CQE32 (1U << 11) /* CQEs are 32 byte */ +/* + * Only one task is allowed to submit requests + */ +#define IORING_SETUP_SINGLE_ISSUER (1U << 12) -enum { +/* + * Defer running task work to get events. + * Rather than running bits of task work whenever the task transitions + * try to do it just before it is needed. + */ +#define IORING_SETUP_DEFER_TASKRUN (1U << 13) + +enum io_uring_op { IORING_OP_NOP, IORING_OP_READV, IORING_OP_WRITEV, @@ -140,12 +206,29 @@ enum { IORING_OP_MKDIRAT, IORING_OP_SYMLINKAT, IORING_OP_LINKAT, + IORING_OP_MSG_RING, + IORING_OP_FSETXATTR, + IORING_OP_SETXATTR, + IORING_OP_FGETXATTR, + IORING_OP_GETXATTR, + IORING_OP_SOCKET, + IORING_OP_URING_CMD, + IORING_OP_SEND_ZC, + IORING_OP_SENDMSG_ZC, /* this goes last, obviously */ IORING_OP_LAST, }; /* + * sqe->uring_cmd_flags + * IORING_URING_CMD_FIXED use registered buffer; pass this flag + * along with setting sqe->buf_index. + */ +#define IORING_URING_CMD_FIXED (1U << 0) + + +/* * sqe->fsync_flags */ #define IORING_FSYNC_DATASYNC (1U << 0) @@ -177,10 +260,67 @@ enum { * * IORING_POLL_UPDATE Update existing poll request, matching * sqe->addr as the old user_data field. + * + * IORING_POLL_LEVEL Level triggered poll. */ #define IORING_POLL_ADD_MULTI (1U << 0) #define IORING_POLL_UPDATE_EVENTS (1U << 1) #define IORING_POLL_UPDATE_USER_DATA (1U << 2) +#define IORING_POLL_ADD_LEVEL (1U << 3) + +/* + * ASYNC_CANCEL flags. + * + * IORING_ASYNC_CANCEL_ALL Cancel all requests that match the given key + * IORING_ASYNC_CANCEL_FD Key off 'fd' for cancelation rather than the + * request 'user_data' + * IORING_ASYNC_CANCEL_ANY Match any request + * IORING_ASYNC_CANCEL_FD_FIXED 'fd' passed in is a fixed descriptor + */ +#define IORING_ASYNC_CANCEL_ALL (1U << 0) +#define IORING_ASYNC_CANCEL_FD (1U << 1) +#define IORING_ASYNC_CANCEL_ANY (1U << 2) +#define IORING_ASYNC_CANCEL_FD_FIXED (1U << 3) + +/* + * send/sendmsg and recv/recvmsg flags (sqe->ioprio) + * + * IORING_RECVSEND_POLL_FIRST If set, instead of first attempting to send + * or receive and arm poll if that yields an + * -EAGAIN result, arm poll upfront and skip + * the initial transfer attempt. + * + * IORING_RECV_MULTISHOT Multishot recv. Sets IORING_CQE_F_MORE if + * the handler will continue to report + * CQEs on behalf of the same SQE. + * + * IORING_RECVSEND_FIXED_BUF Use registered buffers, the index is stored in + * the buf_index field. + */ +#define IORING_RECVSEND_POLL_FIRST (1U << 0) +#define IORING_RECV_MULTISHOT (1U << 1) +#define IORING_RECVSEND_FIXED_BUF (1U << 2) + +/* + * accept flags stored in sqe->ioprio + */ +#define IORING_ACCEPT_MULTISHOT (1U << 0) + +/* + * IORING_OP_MSG_RING command types, stored in sqe->addr + */ +enum { + IORING_MSG_DATA, /* pass sqe->len as 'res' and off as user_data */ + IORING_MSG_SEND_FD, /* send a registered fd to another ring */ +}; + +/* + * IORING_OP_MSG_RING flags (sqe->msg_ring_flags) + * + * IORING_MSG_RING_CQE_SKIP Don't post a CQE to the target ring. Not + * applicable for IORING_MSG_DATA, obviously. + */ +#define IORING_MSG_RING_CQE_SKIP (1U << 0) /* * IO completion data structure (Completion Queue Entry) @@ -189,6 +329,12 @@ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; + + /* + * If the ring is initialized with IORING_SETUP_CQE32, then this field + * contains 16-bytes of padding, doubling the size of the CQE. + */ + __u64 big_cqe[]; }; /* @@ -196,9 +342,14 @@ struct io_uring_cqe { * * IORING_CQE_F_BUFFER If set, the upper 16 bits are the buffer ID * IORING_CQE_F_MORE If set, parent SQE will generate more CQE entries + * 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. */ #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) enum { IORING_CQE_BUFFER_SHIFT = 16, @@ -231,6 +382,7 @@ struct io_sqring_offsets { */ #define IORING_SQ_NEED_WAKEUP (1U << 0) /* needs io_uring_enter wakeup */ #define IORING_SQ_CQ_OVERFLOW (1U << 1) /* CQ ring is overflown */ +#define IORING_SQ_TASKRUN (1U << 2) /* task should enter the kernel */ struct io_cqring_offsets { __u32 head; @@ -254,10 +406,11 @@ struct io_cqring_offsets { /* * io_uring_enter(2) flags */ -#define IORING_ENTER_GETEVENTS (1U << 0) -#define IORING_ENTER_SQ_WAKEUP (1U << 1) -#define IORING_ENTER_SQ_WAIT (1U << 2) -#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_GETEVENTS (1U << 0) +#define IORING_ENTER_SQ_WAKEUP (1U << 1) +#define IORING_ENTER_SQ_WAIT (1U << 2) +#define IORING_ENTER_EXT_ARG (1U << 3) +#define IORING_ENTER_REGISTERED_RING (1U << 4) /* * Passed in for io_uring_setup(2). Copied back with updated info on success @@ -289,6 +442,8 @@ struct io_uring_params { #define IORING_FEAT_EXT_ARG (1U << 8) #define IORING_FEAT_NATIVE_WORKERS (1U << 9) #define IORING_FEAT_RSRC_TAGS (1U << 10) +#define IORING_FEAT_CQE_SKIP (1U << 11) +#define IORING_FEAT_LINKED_FILE (1U << 12) /* * io_uring_register(2) opcodes and arguments @@ -321,6 +476,20 @@ enum { /* set/get max number of io-wq workers */ IORING_REGISTER_IOWQ_MAX_WORKERS = 19, + /* register/unregister io_uring fd with the ring */ + IORING_REGISTER_RING_FDS = 20, + IORING_UNREGISTER_RING_FDS = 21, + + /* register ring based provide buffer group */ + IORING_REGISTER_PBUF_RING = 22, + IORING_UNREGISTER_PBUF_RING = 23, + + /* sync cancelation API */ + IORING_REGISTER_SYNC_CANCEL = 24, + + /* register a range of fixed file slots for automatic slot allocation */ + IORING_REGISTER_FILE_ALLOC_RANGE = 25, + /* this goes last */ IORING_REGISTER_LAST }; @@ -338,9 +507,15 @@ struct io_uring_files_update { __aligned_u64 /* __s32 * */ fds; }; +/* + * Register a fully sparse file space, rather than pass in an array of all + * -1 file descriptors. + */ +#define IORING_RSRC_REGISTER_SPARSE (1U << 0) + struct io_uring_rsrc_register { __u32 nr; - __u32 resv; + __u32 flags; __u64 resv2; __aligned_u64 data; __aligned_u64 tags; @@ -361,6 +536,19 @@ struct io_uring_rsrc_update2 { __u32 resv2; }; +struct io_uring_notification_slot { + __u64 tag; + __u64 resv[3]; +}; + +struct io_uring_notification_register { + __u32 nr_slots; + __u32 resv; + __u64 resv2; + __u64 data; + __u64 resv3; +}; + /* Skip updating fd indexes set to this value in the fd table */ #define IORING_REGISTER_FILES_SKIP (-2) @@ -378,7 +566,7 @@ struct io_uring_probe { __u8 ops_len; /* length of ops[] array below */ __u16 resv; __u32 resv2[3]; - struct io_uring_probe_op ops[0]; + struct io_uring_probe_op ops[]; }; struct io_uring_restriction { @@ -392,6 +580,38 @@ struct io_uring_restriction { __u32 resv2[3]; }; +struct io_uring_buf { + __u64 addr; + __u32 len; + __u16 bid; + __u16 resv; +}; + +struct io_uring_buf_ring { + union { + /* + * To avoid spilling into more pages than we need to, the + * ring tail is overlaid with the io_uring_buf->resv field. + */ + struct { + __u64 resv1; + __u32 resv2; + __u16 resv3; + __u16 tail; + }; + struct io_uring_buf bufs[0]; + }; +}; + +/* argument for IORING_(UN)REGISTER_PBUF_RING */ +struct io_uring_buf_reg { + __u64 ring_addr; + __u32 ring_entries; + __u16 bgid; + __u16 pad; + __u64 resv[3]; +}; + /* * io_uring_restriction->opcode values */ @@ -418,4 +638,36 @@ struct io_uring_getevents_arg { __u64 ts; }; +/* + * Argument for IORING_REGISTER_SYNC_CANCEL + */ +struct io_uring_sync_cancel_reg { + __u64 addr; + __s32 fd; + __u32 flags; + struct __kernel_timespec timeout; + __u64 pad[4]; +}; + +/* + * Argument for IORING_REGISTER_FILE_ALLOC_RANGE + * The range is specified as [off, off + len) + */ +struct io_uring_file_index_range { + __u32 off; + __u32 len; + __u64 resv; +}; + +struct io_uring_recvmsg_out { + __u32 namelen; + __u32 controllen; + __u32 payloadlen; + __u32 flags; +}; + +#ifdef __cplusplus +} +#endif + #endif |