HTML rendering created 2025-09-06 byMichael Kerrisk, author ofThe Linux Programming Interface. For details of in-depthLinux/UNIX system programming training courses that I teach, lookhere. Hosting byjambit GmbH. |  |
NAME |SYNOPSIS |DESCRIPTION |RETURN VALUE |ERRORS |CQE ERRORS |COLOPHON | |
io_uring_enter(2) Linux Programmer's Manualio_uring_enter(2)io_uring_enter - initiate and/or complete asynchronous I/O
#include <liburing.h>int io_uring_enter(unsigned intfd, unsigned intto_submit,unsigned intmin_complete, unsigned intflags,sigset_t *sig);int io_uring_enter2(unsigned intfd, unsigned intto_submit,unsigned intmin_complete, unsigned intflags,void *arg, size_tsz);
io_uring_enter(2) is used to initiate and complete I/O using the shared submission and completion queues setup by a call toio_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 toio_uring_enter(2).fd is the file descriptor returned byio_uring_setup(2).to_submit specifies the number of I/Os to submit from the submission queue.flags is a bitmask of the following values:IORING_ENTER_GETEVENTS If this flag is set, then the system call will wait for the specified number of events inmin_complete before returning. This flag can be set along withto_submit to both submit and complete events in a single system call. If this flag is set either the flagIORING_SETUP_DEFER_TASKRUNmust not be set or the thread issuing the syscall must be the thread that created the io_uring associated withfd, or be the thread that enabled the ring originally created withIORING_SETUP_R_DISABLED viaio_uring_register(2) orio_uring_enable_rings(3).IORING_ENTER_SQ_WAKEUP If the ring has been created withIORING_SETUP_SQPOLL,then this flag asks the kernel to wakeup the SQ kernel thread to submit IO.IORING_ENTER_SQ_WAIT If the ring has been created withIORING_SETUP_SQPOLL,then the application has no real insight into when the SQ kernel thread has consumed entries from the SQ ring. This can lead to a situation where the application can no longer get a free SQE entry to submit, without knowing when one will become available as the SQ kernel thread consumes them. If the system call is used with this flag set, then it will wait until at least one entry is free in the SQ ring.IORING_ENTER_EXT_ARG By default,arg is asigset_t pointer. IfIORING_ENTER_EXT_ARGis set (supported since kernel 5.11), thenarg is instead a pointer to astructio_uring_getevents_arg andargsz must be set to the size of this structure. The definition is as follows:struct io_uring_getevents_arg {__u64 sigmask;__u32 sigmask_sz;__u32 pad;__u64 ts;}; which allows passing in both a signal mask as well as pointer to astruct __kernel_timespec timeout value. Ifts is set to a valid pointer, then this time value indicates the timeout for waiting on events. If an application is waiting on events and wishes to stop waiting after a specified amount of time, then this can be accomplished directly in version 5.11 and newer by using this feature.IORING_ENTER_REGISTERED_RING If the ring file descriptor has been registered through use ofIORING_REGISTER_RING_FDS, then setting this flag will tell the kernel that thering_fd passed in is the registered ring offset rather than a normal file descriptor.IORING_ENTER_ABS_TIMER When this flag is set, the timeout argument passed instruct io_uring_getevents_arg will be interpreted as an absolute time of the registered clock (seeIORING_REGISTER_CLOCK)until which the waiting should end. Available since 6.12IORING_ENTER_EXT_ARG_REG When this flag is set,arg is not a pointer to astructio_uring_getevents_arg, but merely an offset into an area of wait regions previously registered withio_uring_register(2) using theIORING_REGISTER_MEM_REGION operation. Available since 6.13IORING_ENTER_NO_IOWAIT When this flag is set, the system call will not mark the waiting task as being in iowait if it is sleeping waiting on events and there are pending requests. This is useful if iowait isn't expected when waiting for events. It can also prevent extra power usage by allowing the CPU to enter lower sleep states. This flag is only available if the kernel supports theIORING_FEAT_NO_IOWAITfeature. Available since 6.15. If the io_uring instance was configured for polling, by specifyingIORING_SETUP_IOPOLLin the call toio_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. Ifmin_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 (whereIORING_SETUP_IOPOLLwas not specified in the call toio_uring_setup(2)), an application may check the completion queue for event completions without entering the kernel at all. 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.sig is a pointer to a signal mask (seesigprocmask(2)); ifsig is not NULL,io_uring_enter(2) first replaces the current signal mask by the one pointed to bysig, then waits for events to become available in the completion queue, and then restores the original signal mask. The followingio_uring_enter(2) call: ret = io_uring_enter(fd, 0, 1, IORING_ENTER_GETEVENTS, &sig); is equivalent toatomically executing the following calls: pthread_sigmask(SIG_SETMASK, &sig, &orig); ret = io_uring_enter(fd, 0, 1, IORING_ENTER_GETEVENTS, NULL); pthread_sigmask(SIG_SETMASK, &orig, NULL); See the description ofpselect(2) for an explanation of why thesig parameter is necessary. Submission queue entries are represented using the following data structure: /* * 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 */ union { __u64 off; /* offset into file */ __u64 addr2; struct { __u32 cmd_op; __u32 __pad1; }; }; union { __u64 addr; /* pointer to buffer or iovecs */ __u64 splice_off_in; struct { __u32 level; __u32 optname; }; }; __u32 len; /* buffer size or number of iovecs */ union { __kernel_rwf_t rw_flags; __u32 fsync_flags; __u16 poll_events; /* compatibility */ __u32 poll32_events; /* word-reversed for BE */ __u32 sync_range_flags; __u32 msg_flags; __u32 timeout_flags; __u32 accept_flags; __u32 cancel_flags; __u32 open_flags; __u32 statx_flags; __u32 fadvise_advice; __u32 splice_flags; __u32 rename_flags; __u32 unlink_flags; __u32 hardlink_flags; __u32 xattr_flags; __u32 msg_ring_flags; __u32 uring_cmd_flags; __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 */ union { /* index into fixed buffers, if used */ __u16 buf_index; /* for grouped buffer selection */ __u16 buf_group; } __attribute__((packed)); /* personality to use, if used */ __u16 personality; union { __s32 splice_fd_in; __u32 file_index; __u32 optlen; struct { __u16 addr_len; __u16 __pad3[1]; }; }; union { struct { __u64 addr3; __u64 __pad2[1]; }; __u64 optval; /* * If the ring is initialized with IORING_SETUP_SQE128, then * this field is used for 80 bytes of arbitrary command data */ __u8 cmd[0]; }; }; Theopcode describes the operation to be performed. It can be one of:IORING_OP_NOP Do not perform any I/O. This is useful for testing the performance of the io_uring implementation itself.IORING_OP_READVIORING_OP_WRITEV Vectored read and write operations, similar topreadv2(2) andpwritev2(2). If the file is not seekable,off must be set to zero or -1.IORING_OP_READ_FIXEDIORING_OP_WRITE_FIXED Read from or write to pre-mapped buffers. Seeio_uring_register(2) for details on how to setup a context for fixed reads and writes.IORING_OP_FSYNC File sync. See alsofsync(2). Optionallyoff andlen can be used to specify a range within the file to be synced rather than syncing the entire file, which is the default behavior. 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. To enforce ordering one may utilize linked SQEs,IOSQE_IO_DRAINor wait for the arrival of CQEs of requests which have to be ordered before a given request before submitting its SQE.IORING_OP_POLL_ADD Poll thefd specified in the submission queue entry for the events specified in thepoll_events field. Unlike poll or epoll withoutEPOLLONESHOT, by default this interface always works in one shot mode. That is, once the poll operation is completed, it will have to be resubmitted. IfIORING_POLL_ADD_MULTIis set in the SQElen field, then the poll will work in multi shot mode instead. That means it'll repatedly trigger when the requested event becomes true, and hence multiple CQEs can be generated from this single SQE. The CQEflags field will haveIORING_CQE_F_MORE set on completion if the application should expect further CQE entries from the original request. If this flag isn't set on completion, then the poll request has been terminated and no further events will be generated. This mode is available since 5.13. This command works like an asyncpoll(2) and the completion event result is the returned mask of events. WithoutIORING_POLL_ADD_MULTIand the initial poll operation withIORING_POLL_ADD_MULTIthe operation is level triggered, i.e. if there is data ready or events pending etc. at the time of submission a corresponding CQE will be posted. Potential further completions beyond the first caused by aIORING_POLL_ADD_MULTIare edge triggered.IORING_OP_POLL_REMOVE Remove or update an existing poll request. If found, theres field of thestruct io_uring_cqe will contain 0. If not found,res will contain-ENOENT,or-EALREADYif the poll request was in the process of completing already. IfIORING_POLL_UPDATE_EVENTSis set in the SQElen field, then the request will update an existing poll request with the mask of events passed in with this request. The lookup is based on theuser_data field of the original SQE submitted, and this values is passed in theaddr field of the SQE. IfIORING_POLL_UPDATE_USER_DATAis set in the SQElen field, then the request will update theuser_data of an existing poll request based on the value passed in theoff field. Updating an existing poll is available since 5.13.IORING_OP_EPOLL_CTL Add, remove or modify entries in the interest list ofepoll(7). Seeepoll_ctl(2) for details of the system call.fd holds the file descriptor that represents the epoll instance,off holds the file descriptor to add, remove or modify,len holds the operation (EPOLL_CTL_ADD,EPOLL_CTL_DEL,EPOLL_CTL_MOD) to perform and,addr holds a pointer to theepoll_event structure. Available since 5.6.IORING_OP_SYNC_FILE_RANGE Issue the equivalent of async_file_range(2) on the file descriptor. Thefd field is the file descriptor to sync, theoff field holds the offset in bytes, thelen field holds the length in bytes, and thesync_range_flags field holds the flags for the command. See alsosync_file_range(2) for the general description of the related system call. Available since 5.2.IORING_OP_SENDMSG Issue the equivalent of asendmsg(2) system call.fd must be set to the socket file descriptor,addr must contain a pointer to the msghdr structure, andmsg_flags holds the flags associated with the system call. See alsosendmsg(2) for the general description of the related system call. Available since 5.3. This command also supports the following modifiers inioprio:IORING_RECVSEND_POLL_FIRSTIf set, io_uring will assume the socket is currently full and attempting to send data will be unsuccessful. For this case, io_uring will arm internal poll and trigger a send of the data when there is enough space available. This initial send attempt can be wasteful for the case where the socket is expected to be full, setting this flag will bypass the initial send attempt and go straight to arming poll. If poll does indicate that data can be sent, the operation will proceed.IORING_OP_RECVMSG Works just like IORING_OP_SENDMSG, except forrecvmsg(2) instead. See the description of IORING_OP_SENDMSG. Available since 5.3. This command also supports the following modifiers inioprio:IORING_RECVSEND_POLL_FIRSTIf set, io_uring will assume the socket is currently empty and attempting to receive data will be unsuccessful. For this case, io_uring will arm internal poll and trigger a receive of the data when the socket has data to be read. This initial receive attempt can be wasteful for the case where the socket is expected to be empty, setting this flag will bypass the initial receive attempt and go straight to arming poll. If poll does indicate that data is ready to be received, the operation will proceed.IORING_OP_SEND Issue the equivalent of asend(2) system call.fd must be set to the socket file descriptor,addr must contain a pointer to the buffer,len denotes the length of the buffer to send, andmsg_flags holds the flags associated with the system call. See alsosend(2) for the general description of the related system call. Available since 5.6. This command also supports the following modifiers inioprio:IORING_RECVSEND_POLL_FIRSTIf set, io_uring will assume the socket is currently full and attempting to send data will be unsuccessful. For this case, io_uring will arm internal poll and trigger a send of the data when there is enough space available. This initial send attempt can be wasteful for the case where the socket is expected to be full, setting this flag will bypass the initial send attempt and go straight to arming poll. If poll does indicate that data can be sent, the operation will proceed.IORING_OP_RECV Works just like IORING_OP_SEND, except forrecv(2) instead. See the description of IORING_OP_SEND. Available since 5.6. This command also supports the following modifiers inioprio:IORING_RECVSEND_POLL_FIRSTIf set, io_uring will assume the socket is currently empty and attempting to receive data will be unsuccessful. For this case, io_uring will arm internal poll and trigger a receive of the data when the socket has data to be read. This initial receive attempt can be wasteful for the case where the socket is expected to be empty, setting this flag will bypass the initial receive attempt and go straight to arming poll. If poll does indicate that data is ready to be received, the operation will proceed.IORING_OP_TIMEOUT This command will register a timeout operation. Theaddr field must contain a pointer to a struct __kernel_timespec structure,len must contain 1 to signify one __kernel_timespec structure,timeout_flags may containIORING_TIMEOUT_ABSfor an absolute timeout value, or 0 for a relative timeout.off may contain a completion event count. A timeout will trigger a wakeup event on the completion ring for anyone waiting for events. A timeout condition is met when either the specified timeout expires, or the specified number of events have completed. Either condition will trigger the event. If set to 0, completed events are not counted, which effectively acts like a timer. io_uring timeouts use theCLOCK_MONOTONICas the default clock source. The request will complete with-ETIME if the timeout got completed through expiration of the timer, or0 if the timeout got completed through requests completing on their own. If the timeout was canceled before it expired, the request will complete with-ECANCELED. Available since 5.4. Since 5.15, this command also supports the following modifiers intimeout_flags:IORING_TIMEOUT_BOOTTIMEIf set, then the clocksource used isCLOCK_BOOTTIMEinstead ofCLOCK_MONOTONIC. This clocksource differs in that it includes time elapsed if the system was suspend while having a timeout request in-flight.IORING_TIMEOUT_REALTIMEIf set, then the clocksource used isCLOCK_REALTIMEinstead ofCLOCK_MONOTONIC. Since 5.16,IORING_TIMEOUT_ETIME_SUCCESScan be set intimeout_flags, which will result in the expiration of the timer and subsequent completion with-ETIMEnot being interpreted as an error. This is mostly relevant for linked SQEs, as subsequent requests in the chain would not get canceled by the timeout, if this flag is set. SeeIOSQE_IO_LINKfor more details on linked SQEs. Since 6.4,IORING_TIMEOUT_MULTISHOTcan be set intimeout_flags, which will result in the timer producing multiple consecutive completions like other multi shot operations e.g.IORING_OP_READ_MULTISHOTorIORING_POLL_ADD_MULTI.off must be set to the amount of desired completions.IORING_TIMEOUT_MULTISHOTmust not be used withIORING_TIMEOUT_ABS.IORING_OP_TIMEOUT_REMOVE Iftimeout_flags are zero, then it attempts to remove an existing timeout operation.addr must contain theuser_data field of the previously issued timeout operation. If the specified timeout request is found and canceled successfully, this request will terminate with a result value of0 If the timeout request was found but expiration was already in progress, this request will terminate with a result value of-EBUSYIf the timeout request wasn't found, the request will terminate with a result value of-ENOENT Available since 5.5. Iftimeout_flags containIORING_TIMEOUT_UPDATE, instead of removing an existing operation, it updates it.addr and return values are same as before.addr2 field must contain a pointer to a struct __kernel_timespec structure.timeout_flags may also contain IORING_TIMEOUT_ABS, in which case the value given is an absolute one, not a relative one. Available since 5.11.IORING_OP_ACCEPT Issue the equivalent of anaccept4(2) system call.fd must be set to the socket file descriptor,addr must contain the pointer to the sockaddr structure, andaddr2 must contain a pointer to the socklen_t addrlen field. Flags can be passed using theaccept_flags field. See alsoaccept4(2) for the general description of the related system call. Available since 5.5. If thefile_index field is set to a positive number, the file won't be installed into the normal file table as usual but will be placed into the fixed file table at indexfile_index - 1. In this case, instead of returning a file descriptor, the result will contain either 0 on success or an error. If the index points to a valid empty slot, the installation is guaranteed to not fail. If there is already a file in the slot, it will be replaced, similar toIORING_OP_FILES_UPDATE.Please note that only io_uring has access to such files and no other syscall can use them. SeeIOSQE_FIXED_FILEandIORING_REGISTER_FILES. Available since 5.5.IORING_OP_ASYNC_CANCEL Attempt to cancel an already issued request.addr must contain theuser_data field of the request that should be canceled. The cancelation request will complete with one of the following results codes. If found, theres field of the cqe will contain 0. If not found,res will contain-ENOENT. If found and attempted canceled, theres field will contain-EALREADY. In this case, the request may or may not terminate. In general, requests that are interruptible (like socket IO) will get canceled, while disk IO requests cannot be canceled if already started. Available since 5.5.IORING_OP_LINK_TIMEOUT This request must be linked with another request throughIOSQE_IO_LINKwhich is described below. UnlikeIORING_OP_TIMEOUT,IORING_OP_LINK_TIMEOUTacts on the linked request, not the completion queue. The format of the command is otherwise likeIORING_OP_TIMEOUT, except there's no completion event count as it's tied to a specific request. If used, the timeout specified in the command will cancel the linked command, unless the linked command completes before the timeout. The timeout will complete with-ETIMEif the timer expired and the linked request was attempted canceled, or-ECANCELEDif the timer got canceled because of completion of the linked request. LikeIORING_OP_TIMEOUTthe clock source used isCLOCK_MONOTONIC Available since 5.5.IORING_OP_CONNECT Issue the equivalent of aconnect(2) system call.fd must be set to the socket file descriptor,addr must contain the const pointer to the sockaddr structure, andoff must contain the socklen_t addrlen field. See alsoconnect(2) for the general description of the related system call. Available since 5.5.IORING_OP_FALLOCATE Issue the equivalent of afallocate(2) system call.fd must be set to the file descriptor,len must contain the mode associated with the operation,off must contain the offset on which to operate, andaddr must contain the length. See alsofallocate(2) for the general description of the related system call. Available since 5.6.IORING_OP_FADVISE Issue the equivalent of aposix_fadvise(2) system call.fd must be set to the file descriptor,off must contain the offset on which to operate,len must contain the length, andfadvise_advice must contain the advice associated with the operation. See alsoposix_fadvise(2) for the general description of the related system call. Available since 5.6.IORING_OP_MADVISE Issue the equivalent of amadvise(2) system call.addr must contain the address to operate on,len must contain the length on which to operate, andfadvise_advice must contain the advice associated with the operation. See alsomadvise(2) for the general description of the related system call. Available since 5.6.IORING_OP_OPENAT Issue the equivalent of aopenat(2) system call.fd is thedirfd argument,addr must contain a pointer to the*pathname argument,open_flags should contain any flags passed in, andlen is access mode of the file. See alsoopenat(2) for the general description of the related system call. Available since 5.6. If thefile_index field is set to a positive number, the file won't be installed into the normal file table as usual but will be placed into the fixed file table at indexfile_index - 1. In this case, instead of returning a file descriptor, the result will contain either 0 on success or an error. If the index points to a valid empty slot, the installation is guaranteed to not fail. If there is already a file in the slot, it will be replaced, similar toIORING_OP_FILES_UPDATE.Please note that only io_uring has access to such files and no other syscall can use them. SeeIOSQE_FIXED_FILEandIORING_REGISTER_FILES. Available since 5.15.IORING_OP_OPENAT2 Issue the equivalent of aopenat2(2) system call.fd is thedirfd argument,addr must contain a pointer to the*pathname argument,len should contain the size of the open_how structure, andoff should be set to the address of the open_how structure. See alsoopenat2(2) for the general description of the related system call. Available since 5.6. If thefile_index field is set to a positive number, the file won't be installed into the normal file table as usual but will be placed into the fixed file table at indexfile_index - 1. In this case, instead of returning a file descriptor, the result will contain either 0 on success or an error. If the index points to a valid empty slot, the installation is guaranteed to not fail. If there is already a file in the slot, it will be replaced, similar toIORING_OP_FILES_UPDATE. Please note that only io_uring has access to such files and no other syscall can use them. SeeIOSQE_FIXED_FILEandIORING_REGISTER_FILES. Available since 5.15.IORING_OP_CLOSE Issue the equivalent of aclose(2) system call.fd is the file descriptor to be closed. See alsoclose(2) for the general description of the related system call. Available since 5.6. If thefile_index field is set to a positive number, this command can be used to close files that were direct opened throughIORING_OP_OPENAT,IORING_OP_OPENAT2, orIORING_OP_ACCEPTusing the io_uring specific direct descriptors. Note that only one of the descriptor fields may be set. The direct close feature is available since the 5.15 kernel, where direct descriptors were introduced.IORING_OP_STATX Issue the equivalent of astatx(2) system call.fd is thedirfd argument,addr must contain a pointer to the*pathname string,statx_flags is theflags argument,len should be themask argument, andoff must contain a pointer to thestatxbuf to be filled in. See alsostatx(2) for the general description of the related system call. Available since 5.6.IORING_OP_READIORING_OP_WRITE Issue the equivalent of apread(2) orpwrite(2) system call.fd is the file descriptor to be operated on,addr contains the buffer in question,len contains the length of the IO operation, andoffs contains the read or write offset. Iffd does not refer to a seekable file,off must be set to zero or -1. Ifoffs is set to-1, the offset will use (and advance) the file position, like theread(2) andwrite(2) system calls. These are non-vectored versions of theIORING_OP_READVandIORING_OP_WRITEVopcodes. See alsoread(2) andwrite(2) for the general description of the related system call. Available since 5.6.IORING_OP_SPLICE Issue the equivalent of asplice(2) system call.splice_fd_in is the file descriptor to read from,splice_off_in is an offset to read from,fd is the file descriptor to write to,off is an offset from which to start writing to. A sentinel value of-1is used to pass the equivalent of a NULL for the offsets tosplice(2).len contains the number of bytes to copy.splice_flags contains a bit mask for the flag field associated with the system call. Please note that one of the file descriptors must refer to a pipe. See alsosplice(2) for the general description of the related system call. Available since 5.7.IORING_OP_TEE Issue the equivalent of atee(2) system call.splice_fd_in is the file descriptor to read from,fd is the file descriptor to write to,len contains the number of bytes to copy, andsplice_flags contains a bit mask for the flag field associated with the system call. Please note that both of the file descriptors must refer to a pipe. See alsotee(2) for the general description of the related system call. Available since 5.8.IORING_OP_FILES_UPDATE This command is an alternative to usingIORING_REGISTER_FILES_UPDATEwhich then works in an async fashion, like the rest of the io_uring commands. The arguments passed in are the same.addr must contain a pointer to the array of file descriptors,len must contain the length of the array, andoff must contain the offset at which to operate. Note that the array of file descriptors pointed to inaddr must remain valid until this operation has completed. Available since 5.6.IORING_OP_PROVIDE_BUFFERS This command allows an application to register a group of buffers to be used by commands that read/receive data. Using buffers in this manner can eliminate the need to separate the poll + read, which provides a convenient point in time to allocate a buffer for a given request. It's often infeasible to have as many buffers available as pending reads or receive. With this feature, the application can have its pool of buffers ready in the kernel, and when the file or socket is ready to read/receive data, a buffer can be selected for the operation.fd must contain the number of buffers to provide,addr must contain the starting address to add buffers from,len must contain the length of each buffer to add from the range,buf_group must contain the group ID of this range of buffers, andoff must contain the starting buffer ID of this range of buffers. With that set, the kernel adds buffers starting with the memory address inaddr, each with a length oflen. Hence the application should providelen * fd worth of memory inaddr. Buffers are grouped by the group ID, and each buffer within this group will be identical in size according to the above arguments. This allows the application to provide different groups of buffers, and this is often used to have differently sized buffers available depending on what the expectations are of the individual request. When submitting a request that should use a provided buffer, theIOSQE_BUFFER_SELECTflag must be set, andbuf_group must be set to the desired buffer group ID where the buffer should be selected from. Available since 5.7.IORING_OP_REMOVE_BUFFERS Remove buffers previously registered withIORING_OP_PROVIDE_BUFFERS.fd must contain the number of buffers to remove, andbuf_group must contain the buffer group ID from which to remove the buffers. Available since 5.7.IORING_OP_SHUTDOWN Issue the equivalent of ashutdown(2) system call.fd is the file descriptor to the socket being shutdown, andlen must be set to thehow argument. No no other fields should be set. Available since 5.11.IORING_OP_RENAMEAT Issue the equivalent of arenameat2(2) system call.fd should be set to theolddirfd,addr should be set to theoldpath,len should be set to thenewdirfd,addr should be set to theoldpath,addr2 should be set to thenewpath, and finallyrename_flags should be set to theflags passed in torenameat2(2). Available since 5.11.IORING_OP_UNLINKAT Issue the equivalent of aunlinkat(2) system call.fd should be set to thedirfd,addr should be set to thepathname, andunlink_flags should be set to theflags being passed in tounlinkat(2). Available since 5.11.IORING_OP_MKDIRAT Issue the equivalent of amkdirat(2) system call.fd should be set to thedirfd,addr should be set to thepathname, andlen should be set to themode being passed in tomkdirat(2). Available since 5.15.IORING_OP_SYMLINKAT Issue the equivalent of asymlinkat(2) system call.fd should be set to thenewdirfd,addr should be set to thetarget andaddr2 should be set to thelinkpath being passed in tosymlinkat(2). Available since 5.15.IORING_OP_LINKAT Issue the equivalent of alinkat(2) system call.fd should be set to theolddirfd,addr should be set to theoldpath,len should be set to thenewdirfd,addr2 should be set to thenewpath, andhardlink_flags should be set to theflags being passed in tolinkat(2). Available since 5.15.IORING_OP_MSG_RING Send a message to an io_uring.fd must be set to a file descriptor of a ring that the application has access to,len can be set to any 32-bit value that the application wishes to pass on, andoff should be set any 64-bit value that the application wishes to send. On the target ring, a CQE will be posted with theres field matching thelen set, and auser_data field matching theoff value being passed in. This request type can be used to either just wake or interrupt anyone waiting for completions on the target ring, or it can be used to pass messages via the two fields. Available since 5.18.IORING_OP_SOCKET Issue the equivalent of asocket(2) system call.fd must contain the communication domain,off must contain the communication type,len must contain the protocol, andrw_flags is currently unused and must be set to zero. See alsosocket(2) for the general description of the related system call. Available since 5.19. If thefile_index field is set to a positive number, the file won't be installed into the normal file table as usual but will be placed into the fixed file table at indexfile_index - 1. In this case, instead of returning a file descriptor, the result will contain either 0 on success or an error. If the index points to a valid empty slot, the installation is guaranteed to not fail. If there is already a file in the slot, it will be replaced, similar toIORING_OP_FILES_UPDATE. Please note that only io_uring has access to such files and no other syscall can use them. SeeIOSQE_FIXED_FILEandIORING_REGISTER_FILES. Available since 5.19.IORING_OP_URING_CMD Issues an asynchronous, per-file private operation, similar toioctl(2). Further information may be found in the dedicated man page ofIORING_OP_URING_CMD. Available since 5.19.IORING_OP_SEND_ZC Issue the zerocopy equivalent of asend(2) system call. Similar toIORING_OP_SEND, but tries to avoid making intermediate copies of data. Zerocopy execution is not guaranteed and may fall back to copying. The request may also fail with-EOPNOTSUPP, when a protocol doesn't support zerocopy, in which case users are recommended to use copying sends instead. Theflags field of the firststruct io_uring_cqe may likely containIORING_CQE_F_MORE, which means that there will be a second completion event / notification for the request, with theuser_data field set to the same value. The user must not modify the data buffer until the notification is posted. The first cqe follows the usual rules and so itsres field will contain the number of bytes sent or a negative error code. The notification'sres field will be set to zero and theflags field will containIORING_CQE_F_NOTIF. The two step model is needed because the kernel may hold on to buffers for a long time, e.g. waiting for a TCP ACK, and having a separate cqe for request completions allows userspace to push more data without extra delays. Note, notifications are only responsible for controlling the lifetime of the buffers, and as such don't mean anything about whether the data has atually been sent out or received by the other end. Even errored requests may generate a notification, and the user must check forIORING_CQE_F_MORErather than relying on the result.fd must be set to the socket file descriptor,addr must contain a pointer to the buffer,len denotes the length of the buffer to send, andmsg_flags holds the flags associated with the system call. Whenaddr2 is non-zero it points to the address of the target withaddr_len specifying its size, turning the request into asendto(2) system call equivalent. Available since 6.0. This command also supports the following modifiers inioprio:IORING_RECVSEND_POLL_FIRSTIf set, io_uring will assume the socket is currently full and attempting to send data will be unsuccessful. For this case, io_uring will arm internal poll and trigger a send of the data when there is enough space available. This initial send attempt can be wasteful for the case where the socket is expected to be full, setting this flag will bypass the initial send attempt and go straight to arming poll. If poll does indicate that data can be sent, the operation will proceed.IORING_RECVSEND_FIXED_BUFIf set, instructs io_uring to use a pre-mapped buffer. Thebuf_index field should contain an index into an array of fixed buffers. Seeio_uring_register(2) for details on how to setup a context for fixed buffer I/O.IORING_OP_SENDMSG_ZC Issue the zerocopy equivalent of asendmsg(2) system call. Works just likeIORING_OP_SENDMSG, but likeIORING_OP_SEND_ZCsupportsIORING_RECVSEND_FIXED_BUF. For additional notes regarding zero copy seeIORING_OP_SEND_ZC. Available since 6.1IORING_OP_WAITID Issue the equivalent of awaitid(2) system call.len must contain the idtype being queried/waited for andfd must contain the 'pid' (or id) being waited for.file_index is the 'options' being set (the child state changes to wait for).addr2 is a pointer to siginfo_t, if any, being filled in. See alsowaitid(2) for the general description of the related system call. Available since 6.5.IORING_OP_SETXATTRIORING_OP_GETXATTRIORING_OP_FSETXATTRIORING_OP_FGETXATTR Issue the equivalent of asetxattr(2) orgetxattr(2) orfsetxattr(2) orfgetxattr(2) system call.addr must contain a pointer to a buffer containing the name of the extended attribute.addr2 must contain a pointer to a buffer of maximum lengthlen, in which the value of the extended attribute is to be placed or is read from. Additional flags maybe provided inxattr_flags. Forsetxattr(2) orgetxattr(2)addr3 must contain a pointer to the path of the file. Forfsetxattr(2) orfgetxattr(2)fd must contain the file descriptor of the file. Available since 5.19.IORING_OP_BIND Issues the equivalent of thebind(2) system call.fd must contain the file descriptor of the socket,addr must contain a pointer to the sockaddr struct containing the address to assign andaddr2 must contain the length of the address. Available since 6.11.IORING_OP_LISTEN Issues the equivalent of thelisten(2) system call.fd must contain the file descriptor of the socket andaddr must contain the backlog parameter, i.e. the maximum amount of pending queued connections. Available since 6.11.IORING_OP_FTRUNCATE Issues the equivalent of theftruncate(2) system call.fd must contain the file descriptor of the file to truncate andoff must contain the length to which the file will be truncated. Available since 6.9.IORING_OP_READ_MULTISHOT LikeIORING_OP_READ, but similar to requests prepared withio_uring_prep_multishot_accept(3) additional reads and thus CQEs will be performed based on this single SQE once there is more data available. Is restricted to pollable files and will fall back to single shot if the file does not supportNOWAIT. Like other multishot type requests, the application should look at the CQE flags and see ifIORING_CQE_F_MOREis set on completion as an indication of whether or not the read request will generate further CQEs. Available since 6.7.IORING_OP_FUTEX_WAIT Issues the equivalent of thefutex_wait(2) system call.addr must hold a pointer to the futex,addr2 must hold the value to which the futex has to be changed so this caller tofutex_wait(2) can be woken by a call tofutex_wake(2),addr3 must hold the bitmask of thisfutex_wait(2) caller. For a caller offutex_wake(2) to wake a waiter additionally the bitmask of the waiter and waker must have at least one set bit in common.fd must contain additional flags passed in. Available since 6.7.IORING_OP_FUTEX_WAKE Issues the equivalent of thefutex_wake(2) system call.addr must hold a pointer to the futex,addr2 must hold the maximum number of waiters waiting on this futex to wake,addr3 must hold the bitmask of thisfutex_wake(2) call. To wake a waiter additionally the bitmask of the waiter and waker must have at least one set bit in common.fd must contain additional flags passed in. Available since 6.7.IORING_OP_FUTEX_WAITV Issues the equivalent of thefutex_waitv(2) system call.addr must hold a pointer to the futexv struct,len must hold the length of the futexv struct, which may not be 0 and must be smaller thanFUTEX_WAITV_MAX(as of 6.11 == 128). Available since 6.7.IORING_OP_FIXED_FD_INSTALL This operation is used to insert a registered file into the regular process file table. Consequentlyfd must contain the file index andIOSQE_FIXED_FILEmust be set. The resulting regular fd is returned via cqe->res. Additional flags may be passed in viainstall_fd_flags. Currently supported flags are:IORING_FIXED_FD_NO_CLOEXEC, which overrides a potentially setO_CLOEXECflag set on the initial file. Available since 6.8. Theflags field is a bit mask. The supported flags are:IOSQE_FIXED_FILE When this flag is specified,fd is an index into the files array registered with the io_uring instance (see theIORING_REGISTER_FILESsection of theio_uring_register(2) man page). Note that this isn't always available for all commands. If used on a command that doesn't support fixed files, the SQE will error with-EBADF. Available since 5.1.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. Available since 5.2.IOSQE_IO_LINK When this flag is specified, the SQE forms a link with the next SQE in the submission ring. That next SQE will not be started before the previous request 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. Chains are not supported across submission boundaries. Even if the last SQE in a submission has this flag set, it will still terminate the current chain. 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. A chain of SQEs will be broken if any request in that chain ends in error. io_uring considers any unexpected result an error. This means that, eg, a short read will also terminate the remainder of the chain. If a chain of SQE links is broken, the remaining unstarted part of the chain will be terminated and completed with-ECANCELEDas the error code. Available since 5.3.IOSQE_IO_HARDLINK Like IOSQE_IO_LINK, but it doesn't sever regardless of the completion result. Note that the link will still sever if we fail submitting the parent request, hard links are only resilient in the presence of completion results for requests that did submit correctly.IOSQE_IO_HARDLINK impliesIOSQE_IO_LINK. Available since 5.5.IOSQE_ASYNC Normal operation for io_uring is to try and issue an sqe as non-blocking first, and if that fails, execute it in an async manner. To support more efficient overlapped operation of requests that the application knows/assumes will always (or most of the time) block, the application can ask for an sqe to be issued async from the start. Available since 5.6.IOSQE_BUFFER_SELECT Used in conjunction with theIORING_OP_PROVIDE_BUFFERS command, which registers a pool of buffers to be used by commands that read or receive data. When buffers are registered for this use case, and this flag is set in the command, io_uring will grab a buffer from this pool when the request is ready to receive or read data. If successful, the resulting CQE will haveIORING_CQE_F_BUFFER set in the flags part of the struct, and the upperIORING_CQE_BUFFER_SHIFTbits will contain the ID of the selected buffers. This allows the application to know exactly which buffer was selected for the operation. If no buffers are available and this flag is set, then the request will fail with-ENOBUFSas the error code. Once a buffer has been used, it is no longer available in the kernel pool. The application must re-register the given buffer again when it is ready to recycle it (eg has completed using it). Available since 5.7.IOSQE_CQE_SKIP_SUCCESS Don't generate a CQE if the request completes successfully. If the request fails, an appropriate CQE will be posted as usual and if there is noIOSQE_IO_HARDLINK,CQEs for all linked requests will be omitted. The notion of failure/success is opcode specific and is the same as with breaking chains ofIOSQE_IO_LINK. One special case is when the request has a linked timeout, then the CQE generation for the linked timeout is decided solely by whether it hasIOSQE_CQE_SKIP_SUCCESSset, regardless whether it timed out or was canceled. In other words, if a linked timeout has the flag set, it's guaranteed to not post a CQE. The semantics are chosen to accommodate several use cases. First, when all but the last request of a normal link without linked timeouts are marked with the flag, only one CQE per link is posted. Additionally, it enables suppression of CQEs in cases where the side effects of a successfully executed operation is enough for userspace to know the state of the system. One such example would be writing to a synchronisation file. This flag is incompatible withIOSQE_IO_DRAIN. Using both of them in a single ring is undefined behavior, even when they are not used together in a single request. Currently, after the first request withIOSQE_CQE_SKIP_SUCCESS, all subsequent requests marked with drain will be failed at submission time. Note that the error reporting is best effort only, and restrictions may change in the future. Available since 5.17.ioprio specifies the I/O priority. Seeioprio_get(2) for a description of Linux I/O priorities.fd specifies the file descriptor against which the operation will be performed, with the exception noted above. If the operation is one ofIORING_OP_READ_FIXEDorIORING_OP_WRITE_FIXED,addr andlen must fall within the buffer located atbuf_index in the fixed buffer array. If the operation is eitherIORING_OP_READVorIORING_OP_WRITEV, thenaddr points to an iovec array oflen entries.rw_flags, specified for read and write operations, contains a bitwise OR of per-I/O flags, as described in thepreadv2(2) man page. Thefsync_flags bit mask may contain either 0, for a normal file integrity sync, orIORING_FSYNC_DATASYNCto provide data sync only semantics. See the descriptions ofO_SYNCandO_DSYNCin theopen(2) manual page for more information. The bits that may be set inpoll_events are defined in<poll.h>, and documented inpoll(2).user_data is an application-supplied value that will be copied into the completion queue entry (see below).buf_index is an index into an array of fixed buffers, and is only valid if fixed buffers were registered.personality is the credentials id to use for this operation. Seeio_uring_register(2) for how to register personalities with io_uring. If set to 0, the current personality of the submitting task is used. 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, theio_uring_enter(2) system call can be invoked to initiate the I/O. Completions use the following data structure: /* * 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; };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. Theflags is used for certain commands, likeIORING_OP_POLL_ADDor in conjunction withIOSQE_BUFFER_SELECTorIORING_OP_MSG_RING, see those entries for details.res is the operation-specific result, but io_uring-specific errors (e.g. flags or opcode invalid) are returned through this field. They are described in sectionCQE ERRORS. For read and write opcodes, the return values matcherrno values documented in thepreadv2(2) andpwritev2(2) man pages, withres holding the equivalent of-errno for error cases, or the transferred number of bytes in case the operation is successful. Hence both error and success return can be found in that field in the CQE. For other request types, the return values are documented in the matching man page for that type, or in the opcodes section above for io_uring-specific opcodes.io_uring_enter(2) returns the number of I/Os successfully consumed. This can be zero ifto_submit was zero or if the submission queue was empty. Note that if the ring was created withIORING_SETUP_SQPOLLspecified, then the return value will generally be the same asto_submit as submission happens outside the context of the system call. The errors related to a submission queue entry will be returned through a completion queue entry (see sectionCQE ERRORS), 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, a negative error code is returned. The caller should not rely onerrno variable.
These are the errors returned byio_uring_enter(2) system call.EAGAINThe kernel was unable to allocate memory for the request, or otherwise ran out of resources to handle it. The application should wait for some completions and try again.EBADFfd is not a valid file descriptor.EBADFDfd is a valid file descriptor, but the io_uring ring is not in the right state (enabled). Seeio_uring_register(2) for details on how to enable the ring.EBADRAt least one CQE was dropped even with theIORING_FEAT_NODROPfeature, and there are no otherwise available CQEs. This clears the error state and so with no other changes the next call toio_uring_enter(2) will not have this error. This error should be extremely rare and indicates the machine is running critically low on memory. It may be reasonable for the application to terminate running unless it is able to safely handle any CQE being lost.EBUSYIf theIORING_FEAT_NODROPfeature flag is set, thenEBUSY will be returned if there were overflow entries,IORING_ENTER_GETEVENTSflag is set and not all of the overflow entries were able to be flushed to the CQ ring. WithoutIORING_FEAT_NODROPthe application is attempting to overcommit the number of requests it can have pending. The application should wait for some completions and try again. May occur if the application tries to queue more requests than we have room for in the CQ ring, or if the application attempts to wait for more events without having reaped the ones already present in the CQ ring.EEXISTThe thread submitting the work is invalid. This may occur ifIORING_ENTER_GETEVENTSandIORING_SETUP_DEFER_TASKRUNis set, but the submitting thread is not the thread that initially created or enabled the io_uring associated withfd.EINVALSome bits in theflags argument are invalid.EFAULTAn invalid user space address was specified for thesig argument.ENXIOThe io_uring instance is in the process of being torn down.EOPNOTSUPPfd does not refer to an io_uring instance.EINTRThe operation was interrupted by a delivery of a signal before it could complete; seesignal(7). Can happen while waiting for events withIORING_ENTER_GETEVENTS.EOWNERDEAD The ring has been setup withIORING_SETUP_SQPOLLand the sq poll kernel thread has been killed.
These io_uring-specific errors are returned as a negative value in theres field of the completion queue entry.EACCESTheflags field oropcode in a submission queue entry is not allowed due to registered restrictions. Seeio_uring_register(2) for details on how restrictions work.EBADFThefd field in the submission queue entry is invalid, or theIOSQE_FIXED_FILEflag was set in the submission queue entry, but no files were registered with the io_uring instance.EFAULTbuffer is outside of the process' accessible address spaceEFAULT IORING_OP_READ_FIXEDorIORING_OP_WRITE_FIXEDwas specified in theopcode field of the submission queue entry, but either buffers were not registered for this io_uring instance, or the address range described byaddr andlen does not fit within the buffer registered atbuf_index.EINVALTheflags field oropcode in a submission queue entry is invalid.EINVALThebuf_index member of the submission queue entry is invalid.EINVALThepersonality field in a submission queue entry is invalid.EINVAL IORING_OP_NOPwas specified in the submission queue entry, but the io_uring context was setup for polling (IORING_SETUP_IOPOLLwas specified in the call to io_uring_setup).EINVAL IORING_OP_READVorIORING_OP_WRITEVwas specified in the submission queue entry, but the io_uring instance has fixed buffers registered.EINVAL IORING_OP_READ_FIXEDorIORING_OP_WRITE_FIXEDwas specified in the submission queue entry, and thebuf_index is invalid.EINVAL IORING_OP_READV,IORING_OP_WRITEV,IORING_OP_READ_FIXED,IORING_OP_WRITE_FIXEDorIORING_OP_FSYNCwas specified in the submission queue entry, but the io_uring instance was configured for IOPOLLing, or any ofaddr,ioprio,off,len, orbuf_index was set in the submission queue entry.EINVAL IORING_OP_POLL_ADDorIORING_OP_POLL_REMOVEwas specified in theopcode field of the submission queue entry, but the io_uring instance was configured for busy-wait polling (IORING_SETUP_IOPOLL), or any ofioprio,off,len, orbuf_index was non-zero in the submission queue entry.EINVAL IORING_OP_POLL_ADDwas specified in theopcode field of the submission queue entry, and theaddr field was non-zero.EOPNOTSUPPopcode is valid, but not supported by this kernel.EOPNOTSUPPIOSQE_BUFFER_SELECTwas set in theflags field of the submission queue entry, but theopcode doesn't support buffer selection.EINVAL IORING_OP_TIMEOUTwas specified, buttimeout_flags specified more than one clock source orIORING_TIMEOUT_MULTISHOTwas set alongsideIORING_TIMEOUT_ABS.
This page is part of theliburing (A library for io_uring) project. Information about the project can be found at ⟨https://github.com/axboe/liburing⟩. If you have a bug report for this manual page, send it to io-uring@vger.kernel.org. This page was obtained from the project's upstream Git repository ⟨https://github.com/axboe/liburing⟩ on 2025-08-11. (At that time, the date of the most recent commit that was found in the repository was 2025-08-02.) If you discover any rendering problems in this HTML version of the page, or you believe there is a better or more up-to-date source for the page, or you have corrections or improvements to the information in this COLOPHON (which isnot part of the original manual page), send a mail to man-pages@man7.orgLinux 2019-01-22io_uring_enter(2)Pages that refer to this page:io_uring_enter2(2), io_uring_enter(2), io_uring_register(2), io_uring_setup(2), syscalls(2), io_uring_prep_send_zc(3), io_uring_prep_send_zc_fixed(3), io_uring_register_ring_fd(3), io_uring_set_iowait(3), io_uring(7)
HTML rendering created 2025-09-06 byMichael Kerrisk, author ofThe Linux Programming Interface. For details of in-depthLinux/UNIX system programming training courses that I teach, lookhere. Hosting byjambit GmbH. | |