.\" Copyright (C) 2019 Jens Axboe .\" Copyright (C) 2019 Red Hat, Inc. .\" .\" %%%LICENSE_START(LGPL_V2.1) .\" This file is distributed according to the GNU Lesser General Public License. .\" %%%LICENSE_END .\" .TH IO_URING_ENTER 2 2019-01-22 "Linux" "Linux Programmer's Manual" .SH NAME io_uring_enter \- initiate and/or complete asynchronous I/O .SH SYNOPSIS .nf .BR "#include " .PP .BI "int io_uring_enter(unsigned int " fd ", unsigned int " to_submit , .BI " unsigned int " min_complete ", unsigned int " flags , .BI " sigset_t *" sig ); .fi .PP .SH DESCRIPTION .PP .BR io_uring_enter () is used to initiate and complete I/O using the shared submission and completion queues setup by a call to .BR io_uring_setup (2). A single call can both submit new I/O and wait for completions of I/O initiated by this call or previous calls to .BR io_uring_enter (). .I fd is the file descriptor returned by .BR io_uring_setup (2). .I to_submit specifies the number of I/Os to submit from the submission queue. If the .B IORING_ENTER_GETEVENTS bit is set in .IR flags , then the system call will attempt to wait for .I min_complete event completions before returning. If the io_uring instance was configured for polling, by specifying .B IORING_SETUP_IOPOLL in the call to .BR io_uring_setup (2), then min_complete has a slightly different meaning. Passing a value of 0 instructs the kernel to return any events which are already complete, without blocking. If .I min_complete is a non-zero value, the kernel will still return immediately if any completion events are available. If no event completions are available, then the call will poll either until one or more completions become available, or until the process has exceeded its scheduler time slice. Note that, for interrupt driven I/O (where .B IORING_SETUP_IOPOLL was not specified in the call to .BR io_uring_setup (2)), an application may check the completion queue for event completions without entering the kernel at all. .PP When the system call returns that a certain amount of SQEs have been consumed and submitted, it's safe to reuse SQE entries in the ring. This is true even if the actual IO submission had to be punted to async context, which means that the SQE may in fact not have been submitted yet. If the kernel requires later use of a particular SQE entry, it will have made a private copy of it. .I sig is a pointer to a signal mask (see .BR sigprocmask (2)); if .I sig is not NULL, .BR io_uring_enter () first replaces the current signal mask by the one pointed to by .IR sig , then waits for events to become available in the completion queue, and then restores the original signal mask. The following .BR io_uring_enter () call: .PP .in +4n .EX ret = io_uring_enter(fd, 0, 1, IORING_ENTER_GETEVENTS, &sig); .EE .in .PP is equivalent to .I atomically executing the following calls: .PP .in +4n .EX pthread_sigmask(SIG_SETMASK, &sig, &orig); ret = io_uring_enter(fd, 0, 1, IORING_ENTER_GETEVENTS, NULL); pthread_sigmask(SIG_SETMASK, &orig, NULL); .EE .in .PP See the description of .BR pselect (2) for an explanation of why the .I sig parameter is necessary. Submission queue entries are represented using the following data structure: .PP .in +4n .EX /* * IO submission data structure (Submission Queue Entry) */ struct io_uring_sqe { __u8 opcode; /* type of operation for this sqe */ __u8 flags; /* IOSQE_ flags */ __u16 ioprio; /* ioprio for the request */ __s32 fd; /* file descriptor to do IO on */ __u64 off; /* offset into file */ __u64 addr; /* pointer to buffer or iovecs */ __u32 len; /* buffer size or number of iovecs */ union { __kernel_rwf_t rw_flags; __u32 fsync_flags; __u16 poll_events; __u32 sync_range_flags; __u32 msg_flags; __u32 timeout_flags; }; __u64 user_data; /* data to be passed back at completion time */ union { __u16 buf_index; /* index into fixed buffers, if used */ __u64 __pad2[3]; }; }; .EE .in .PP The .I opcode describes the operation to be performed. It can be one of: .TP .B IORING_OP_NOP Do not perform any I/O. This is useful for testing the performance of the io_uring implementation itself. .TP .B IORING_OP_READV .TP .B IORING_OP_WRITEV Vectored read and write operations, similar to .BR preadv2 (2) and .BR pwritev2 (2). .TP .B IORING_OP_READ_FIXED .TP .B IORING_OP_WRITE_FIXED Read from or write to pre-mapped buffers. See .BR io_uring_register (2) for details on how to setup a context for fixed reads and writes. .TP .B IORING_OP_FSYNC File sync. See also .BR fsync (2). Note that, while I/O is initiated in the order in which it appears in the submission queue, completions are unordered. For example, an application which places a write I/O followed by an fsync in the submission queue cannot expect the fsync to apply to the write. The two operations execute in parallel, so the fsync may complete before the write is issued to the storage. The same is also true for previously issued writes that have not completed prior to the fsync. .TP .B IORING_OP_POLL_ADD Poll the .I fd specified in the submission queue entry for the events specified in the .I poll_events field. Unlike poll or epoll without .BR EPOLLONESHOT , this interface always works in one shot mode. That is, once the poll operation is completed, it will have to be resubmitted. .TP .B IORING_OP_POLL_REMOVE Remove an existing poll request. If found, the .I res field of the .I "struct io_uring_cqe" will contain 0. If not found, .I res will contain .B -ENOENT. .PP The .I flags field is a bit mask. The supported flags are: .TP .B IOSQE_FIXED_FILE When this flag is specified, .I fd is an index into the files array registered with the io_uring instance (see the .B IORING_REGISTER_FILES section of the .BR io_uring_register (2) man page). .TP .B IOSQE_IO_DRAIN When this flag is specified, the SQE will not be started before previously submitted SQEs have completed, and new SQEs will not be started before this one completes. .TP .B IOSQE_IO_LINK When this flag is specified, it forms a link with the next SQE in the submission ring. That next SQE will not be started before this one completes. This, in effect, forms a chain of SQEs, which can be arbitrarily long. The tail of the chain is denoted by the first SQE that does not have this flag set. This flag has no effect on previous SQE submissions, nor does it impact SQEs that are outside of the chain tail. This means that multiple chains can be executing in parallel, or chains and individual SQEs. Only members inside the chain are serialized. .PP .I ioprio specifies the I/O priority. See .BR ioprio_get (2) for a description of Linux I/O priorities. .I fd specifies the file descriptor against which the operation will be performed, with the exception noted above. If the operation is one of .B IORING_OP_READ_FIXED or .BR IORING_OP_WRITE_FIXED , .I addr and .I len must fall within the buffer located at .I buf_index in the fixed buffer array. If the operation is either .B IORING_OP_READV or .BR IORING_OP_WRITEV , then .I addr points to an iovec array of .I len entries. .IR rw_flags , specified for read and write operations, contains a bitwise OR of per-I/O flags, as described in the .BR preadv2 (2) man page. The .I fsync_flags bit mask may contain either 0, for a normal file integrity sync, or .B IORING_FSYNC_DATASYNC to provide data sync only semantics. See the descriptions of .B O_SYNC and .B O_DSYNC in the .BR open (2) manual page for more information. The bits that may be set in .I poll_events are defined in \fI\fP, and documented in .BR poll (2). .I user_data is an application-supplied value that will be copied into the completion queue entry (see below). .I buf_index is an index into an array of fixed buffers, and is only valid if fixed buffers were registered .PP Once the submission queue entry is initialized, I/O is submitted by placing the index of the submission queue entry into the tail of the submission queue. After one or more indexes are added to the queue, and the queue tail is advanced, the .BR io_uring_enter (2) system call can be invoked to initiate the I/O. Completions use the following data structure: .PP .in +4n .EX /* * IO completion data structure (Completion Queue Entry) */ struct io_uring_cqe { __u64 user_data; /* sqe->data submission passed back */ __s32 res; /* result code for this event */ __u32 flags; }; .EE .in .PP .I user_data is copied from the field of the same name in the submission queue entry. The primary use case is to store data that the application will need to access upon completion of this particular I/O. The .I flags is reserved for future use. .I res is the operation-specific result. .PP For read and write opcodes, the return values match those documented in the .BR preadv2 (2) and .BR pwritev2 (2) man pages. Return codes for the io_uring-specific opcodes are documented in the description of the opcodes above. .PP .SH RETURN VALUE .BR io_uring_enter () returns the number of I/Os successfully consumed. This can be zero if .I to_submit was zero or if the submission queue was empty. The errors below that refer to an error in a submission queue entry will be returned though a completion queue entry, rather than through the system call itself. Errors that occur not on behalf of a submission queue entry are returned via the system call directly. On such an error, -1 is returned and .I errno is set appropriately. .PP .SH ERRORS .TP .B EAGAIN The kernel was unable to allocate memory for the request. .TP .B EBADF The .I fd field in the submission queue entry is invalid, or the .B IOSQE_FIXED_FILE flag was set in the submission queue entry, but no files were registered with the io_uring instance. .TP .B EFAULT buffer is outside of the process' accessible address space .TP .B EFAULT .B IORING_OP_READ_FIXED or .B IORING_OP_WRITE_FIXED was specified in the .I opcode field of the submission queue entry, but either buffers were not registered for this io_uring instance, or the address range described by .I addr and .I len does not fit within the buffer registered at .IR buf_index . .TP .B EINVAL The .I index member of the submission queue entry is invalid. .TP .B EINVAL The .I flags field or .I opcode in a submission queue entry is invalid. .TP .B EINVAL .B IORING_OP_NOP was specified in the submission queue entry, but the io_uring context was setup for polling .RB ( IORING_SETUP_IOPOLL was specified in the call to io_uring_setup). .TP .B EINVAL .B IORING_OP_READV or .B IORING_OP_WRITEV was specified in the submission queue entry, but the io_uring instance has fixed buffers registered. .TP .B EINVAL .B IORING_OP_READ_FIXED or .B IORING_OP_WRITE_FIXED was specified in the submission queue entry, and the .I buf_index is invalid. .TP .B EINVAL .BR IORING_OP_READV , .BR IORING_OP_WRITEV , .BR IORING_OP_READ_FIXED , .B IORING_OP_WRITE_FIXED or .B IORING_OP_FSYNC was specified in the submission queue entry, but the io_uring instance was configured for IOPOLLing, or any of .IR addr , .IR ioprio , .IR off , .IR len , or .I buf_index was set in the submission queue entry. .TP .B EINVAL .B IORING_OP_POLL_ADD or .B IORING_OP_POLL_REMOVE was specified in the .I opcode field of the submission queue entry, but the io_uring instance was configured for busy-wait polling .RB ( IORING_SETUP_IOPOLL ), or any of .IR ioprio , .IR off , .IR len , or .I buf_index was non-zero in the submission queue entry. .TP .B EINVAL .B IORING_OP_POLL_ADD was specified in the .I opcode field of the submission queue entry, and the .I addr field was non-zero. .TP .B ENXIO The io_uring instance is in the process of being torn down. .TP .B EOPNOTSUPP .I fd does not refer to an io_uring instance. .TP .B EOPNOTSUPP .I opcode is valid, but not supported by this kernel.