diff options
Diffstat (limited to 'man/man2/select.2')
| -rw-r--r-- | man/man2/select.2 | 765 |
1 files changed, 765 insertions, 0 deletions
diff --git a/man/man2/select.2 b/man/man2/select.2 new file mode 100644 index 000000000..bbf8ea9e0 --- /dev/null +++ b/man/man2/select.2 @@ -0,0 +1,765 @@ +.\" This manpage is copyright (C) 1992 Drew Eckhardt, +.\" copyright (C) 1995 Michael Shields, +.\" copyright (C) 2001 Paul Sheer, +.\" copyright (C) 2006, 2019 Michael Kerrisk <mtk.manpages@gmail.com> +.\" +.\" SPDX-License-Identifier: Linux-man-pages-copyleft +.\" +.\" Modified 1993-07-24 by Rik Faith <faith@cs.unc.edu> +.\" Modified 1995-05-18 by Jim Van Zandt <jrv@vanzandt.mv.com> +.\" Sun Feb 11 14:07:00 MET 1996 Martin Schulze <joey@linux.de> +.\" * layout slightly modified +.\" +.\" Modified Mon Oct 21 23:05:29 EDT 1996 by Eric S. Raymond <esr@thyrsus.com> +.\" Modified Thu Feb 24 01:41:09 CET 2000 by aeb +.\" Modified Thu Feb 9 22:32:09 CET 2001 by bert hubert <ahu@ds9a.nl>, aeb +.\" Modified Mon Nov 11 14:35:00 PST 2002 by Ben Woodard <ben@zork.net> +.\" 2005-03-11, mtk, modified pselect() text (it is now a system +.\" call in Linux 2.6.16. +.\" +.TH select 2 (date) "Linux man-pages (unreleased)" +.SH NAME +select, pselect, FD_CLR, FD_ISSET, FD_SET, FD_ZERO, fd_set \- +synchronous I/O multiplexing +.SH LIBRARY +Standard C library +.RI ( libc ", " \-lc ) +.SH SYNOPSIS +.nf +.B #include <sys/select.h> +.P +.BR typedef " /* ... */ " fd_set; +.P +.BI "int select(int " nfds ", fd_set *_Nullable restrict " readfds , +.BI " fd_set *_Nullable restrict " writefds , +.BI " fd_set *_Nullable restrict " exceptfds , +.BI " struct timeval *_Nullable restrict " timeout ); +.P +.BI "void FD_CLR(int " fd ", fd_set *" set ); +.BI "int FD_ISSET(int " fd ", fd_set *" set ); +.BI "void FD_SET(int " fd ", fd_set *" set ); +.BI "void FD_ZERO(fd_set *" set ); +.P +.BI "int pselect(int " nfds ", fd_set *_Nullable restrict " readfds , +.BI " fd_set *_Nullable restrict " writefds , +.BI " fd_set *_Nullable restrict " exceptfds , +.BI " const struct timespec *_Nullable restrict " timeout , +.BI " const sigset_t *_Nullable restrict " sigmask ); +.fi +.P +.RS -4 +Feature Test Macro Requirements for glibc (see +.BR feature_test_macros (7)): +.RE +.P +.BR pselect (): +.nf + _POSIX_C_SOURCE >= 200112L +.fi +.SH DESCRIPTION +.BR "WARNING" : +.BR select () +can monitor only file descriptors numbers that are less than +.B FD_SETSIZE +(1024)\[em]an unreasonably low limit for many modern applications\[em]and +this limitation will not change. +All modern applications should instead use +.BR poll (2) +or +.BR epoll (7), +which do not suffer this limitation. +.P +.BR select () +allows a program to monitor multiple file descriptors, +waiting until one or more of the file descriptors become "ready" +for some class of I/O operation (e.g., input possible). +A file descriptor is considered ready if it is possible to +perform a corresponding I/O operation (e.g., +.BR read (2), +or a sufficiently small +.BR write (2)) +without blocking. +.\" +.SS fd_set +A structure type that can represent a set of file descriptors. +According to POSIX, +the maximum number of file descriptors in an +.I fd_set +structure is the value of the macro +.BR FD_SETSIZE . +.\" +.SS File descriptor sets +The principal arguments of +.BR select () +are three "sets" of file descriptors (declared with the type +.IR fd_set ), +which allow the caller to wait for three classes of events +on the specified set of file descriptors. +Each of the +.I fd_set +arguments may be specified as NULL if no file descriptors are +to be watched for the corresponding class of events. +.P +.BR "Note well" : +Upon return, each of the file descriptor sets is modified in place +to indicate which file descriptors are currently "ready". +Thus, if using +.BR select () +within a loop, the sets \fImust be reinitialized\fP before each call. +.P +The contents of a file descriptor set can be manipulated +using the following macros: +.TP +.BR FD_ZERO () +This macro clears (removes all file descriptors from) +.IR set . +It should be employed as the first step in initializing a file descriptor set. +.TP +.BR FD_SET () +This macro adds the file descriptor +.I fd +to +.IR set . +Adding a file descriptor that is already present in the set is a no-op, +and does not produce an error. +.TP +.BR FD_CLR () +This macro removes the file descriptor +.I fd +from +.IR set . +Removing a file descriptor that is not present in the set is a no-op, +and does not produce an error. +.TP +.BR FD_ISSET () +.BR select () +modifies the contents of the sets according to the rules +described below. +After calling +.BR select (), +the +.BR FD_ISSET () +macro +can be used to test if a file descriptor is still present in a set. +.BR FD_ISSET () +returns nonzero if the file descriptor +.I fd +is present in +.IR set , +and zero if it is not. +.\" +.SS Arguments +The arguments of +.BR select () +are as follows: +.TP +.I readfds +The file descriptors in this set are watched to see if they are +ready for reading. +A file descriptor is ready for reading if a read operation will not +block; in particular, a file descriptor is also ready on end-of-file. +.IP +After +.BR select () +has returned, \fIreadfds\fP will be +cleared of all file descriptors except for those that are ready for reading. +.TP +.I writefds +The file descriptors in this set are watched to see if they are +ready for writing. +A file descriptor is ready for writing if a write operation will not block. +However, even if a file descriptor indicates as writable, +a large write may still block. +.IP +After +.BR select () +has returned, \fIwritefds\fP will be +cleared of all file descriptors except for those that are ready for writing. +.TP +.I exceptfds +The file descriptors in this set are watched for "exceptional conditions". +For examples of some exceptional conditions, see the discussion of +.B POLLPRI +in +.BR poll (2). +.IP +After +.BR select () +has returned, +\fIexceptfds\fP will be cleared of all file descriptors except for those +for which an exceptional condition has occurred. +.TP +.I nfds +This argument should be set to the highest-numbered file descriptor in any +of the three sets, plus 1. +The indicated file descriptors in each set are checked, up to this limit +(but see BUGS). +.TP +.I timeout +The +.I timeout +argument is a +.I timeval +structure (shown below) that specifies the interval that +.BR select () +should block waiting for a file descriptor to become ready. +The call will block until either: +.RS +.IP \[bu] 3 +a file descriptor becomes ready; +.IP \[bu] +the call is interrupted by a signal handler; or +.IP \[bu] +the timeout expires. +.RE +.IP +Note that the +.I timeout +interval will be rounded up to the system clock granularity, +and kernel scheduling delays mean that the blocking interval +may overrun by a small amount. +.IP +If both fields of the +.I timeval +structure are zero, then +.BR select () +returns immediately. +(This is useful for polling.) +.IP +If +.I timeout +is specified as NULL, +.BR select () +blocks indefinitely waiting for a file descriptor to become ready. +.\" +.SS pselect() +The +.BR pselect () +system call allows an application to safely wait until either +a file descriptor becomes ready or until a signal is caught. +.P +The operation of +.BR select () +and +.BR pselect () +is identical, other than these three differences: +.IP \[bu] 3 +.BR select () +uses a timeout that is a +.I struct timeval +(with seconds and microseconds), while +.BR pselect () +uses a +.I struct timespec +(with seconds and nanoseconds). +.IP \[bu] +.BR select () +may update the +.I timeout +argument to indicate how much time was left. +.BR pselect () +does not change this argument. +.IP \[bu] +.BR select () +has no +.I sigmask +argument, and behaves as +.BR pselect () +called with NULL +.IR sigmask . +.P +.I sigmask +is a pointer to a signal mask (see +.BR sigprocmask (2)); +if it is not NULL, then +.BR pselect () +first replaces the current signal mask by the one pointed to by +.IR sigmask , +then does the "select" function, and then restores the original +signal mask. +(If +.I sigmask +is NULL, +the signal mask is not modified during the +.BR pselect () +call.) +.P +Other than the difference in the precision of the +.I timeout +argument, the following +.BR pselect () +call: +.P +.in +4n +.EX +ready = pselect(nfds, &readfds, &writefds, &exceptfds, + timeout, &sigmask); +.EE +.in +.P +is equivalent to +.I atomically +executing the following calls: +.P +.in +4n +.EX +sigset_t origmask; +\& +pthread_sigmask(SIG_SETMASK, &sigmask, &origmask); +ready = select(nfds, &readfds, &writefds, &exceptfds, timeout); +pthread_sigmask(SIG_SETMASK, &origmask, NULL); +.EE +.in +.P +The reason that +.BR pselect () +is needed is that if one wants to wait for either a signal +or for a file descriptor to become ready, then +an atomic test is needed to prevent race conditions. +(Suppose the signal handler sets a global flag and +returns. +Then a test of this global flag followed by a call of +.BR select () +could hang indefinitely if the signal arrived just after the test +but just before the call. +By contrast, +.BR pselect () +allows one to first block signals, handle the signals that have come in, +then call +.BR pselect () +with the desired +.IR sigmask , +avoiding the race.) +.SS The timeout +The +.I timeout +argument for +.BR select () +is a structure of the following type: +.P +.in +4n +.EX +struct timeval { + time_t tv_sec; /* seconds */ + suseconds_t tv_usec; /* microseconds */ +}; +.EE +.in +.P +The corresponding argument for +.BR pselect () +is a +.BR timespec (3) +structure. +.P +On Linux, +.BR select () +modifies +.I timeout +to reflect the amount of time not slept; most other implementations +do not do this. +(POSIX.1 permits either behavior.) +This causes problems both when Linux code which reads +.I timeout +is ported to other operating systems, and when code is ported to Linux +that reuses a \fIstruct timeval\fP for multiple +.BR select ()s +in a loop without reinitializing it. +Consider +.I timeout +to be undefined after +.BR select () +returns. +.\" .P - it is rumored that: +.\" On BSD, when a timeout occurs, the file descriptor bits are not changed. +.\" - it is certainly true that: +.\" Linux follows SUSv2 and sets the bit masks to zero upon a timeout. +.SH RETURN VALUE +On success, +.BR select () +and +.BR pselect () +return the number of file descriptors contained in the three returned +descriptor sets (that is, the total number of bits that are set in +.IR readfds , +.IR writefds , +.IR exceptfds ). +The return value may be zero if the timeout expired before any +file descriptors became ready. +.P +On error, \-1 is returned, and +.I errno +is set to indicate the error; +the file descriptor sets are unmodified, +and +.I timeout +becomes undefined. +.SH ERRORS +.TP +.B EBADF +An invalid file descriptor was given in one of the sets. +(Perhaps a file descriptor that was already closed, +or one on which an error has occurred.) +However, see BUGS. +.TP +.B EINTR +A signal was caught; see +.BR signal (7). +.TP +.B EINVAL +.I nfds +is negative or exceeds the +.B RLIMIT_NOFILE +resource limit (see +.BR getrlimit (2)). +.TP +.B EINVAL +The value contained within +.I timeout +is invalid. +.TP +.B ENOMEM +Unable to allocate memory for internal tables. +.SH VERSIONS +On some other UNIX systems, +.\" Darwin, according to a report by Jeremy Sequoia, relayed by Josh Triplett +.BR select () +can fail with the error +.B EAGAIN +if the system fails to allocate kernel-internal resources, rather than +.B ENOMEM +as Linux does. +POSIX specifies this error for +.BR poll (2), +but not for +.BR select (). +Portable programs may wish to check for +.B EAGAIN +and loop, just as with +.BR EINTR . +.SH STANDARDS +POSIX.1-2008. +.SH HISTORY +.TP +.BR select () +POSIX.1-2001, 4.4BSD (first appeared in 4.2BSD). +.IP +Generally portable to/from +non-BSD systems supporting clones of the BSD socket layer (including +System\ V variants). +However, note that the System\ V variant typically +sets the timeout variable before returning, but the BSD variant does not. +.TP +.BR pselect () +Linux 2.6.16. +POSIX.1g, POSIX.1-2001. +.IP +Prior to this, +it was emulated in glibc (but see BUGS). +.TP +.B fd_set +POSIX.1-2001. +.SH NOTES +The following header also provides the +.I fd_set +type: +.IR <sys/time.h> . +.P +An +.I fd_set +is a fixed size buffer. +Executing +.BR FD_CLR () +or +.BR FD_SET () +with a value of +.I fd +that is negative or is equal to or larger than +.B FD_SETSIZE +will result +in undefined behavior. +Moreover, POSIX requires +.I fd +to be a valid file descriptor. +.P +The operation of +.BR select () +and +.BR pselect () +is not affected by the +.B O_NONBLOCK +flag. +.\" +.SS The self-pipe trick +On systems that lack +.BR pselect (), +reliable (and more portable) signal trapping can be achieved +using the self-pipe trick. +In this technique, +a signal handler writes a byte to a pipe whose other end +is monitored by +.BR select () +in the main program. +(To avoid possibly blocking when writing to a pipe that may be full +or reading from a pipe that may be empty, +nonblocking I/O is used when reading from and writing to the pipe.) +.\" +.SS Emulating usleep(3) +Before the advent of +.BR usleep (3), +some code employed a call to +.BR select () +with all three sets empty, +.I nfds +zero, and a non-NULL +.I timeout +as a fairly portable way to sleep with subsecond precision. +.\" +.SS Correspondence between select() and poll() notifications +Within the Linux kernel source, +.\" fs/select.c +we find the following definitions which show the correspondence +between the readable, writable, and exceptional condition notifications of +.BR select () +and the event notifications provided by +.BR poll (2) +and +.BR epoll (7): +.P +.in +4n +.EX +#define POLLIN_SET (EPOLLRDNORM | EPOLLRDBAND | EPOLLIN | + EPOLLHUP | EPOLLERR) + /* Ready for reading */ +#define POLLOUT_SET (EPOLLWRBAND | EPOLLWRNORM | EPOLLOUT | + EPOLLERR) + /* Ready for writing */ +#define POLLEX_SET (EPOLLPRI) + /* Exceptional condition */ +.EE +.in +.\" +.SS Multithreaded applications +If a file descriptor being monitored by +.BR select () +is closed in another thread, the result is unspecified. +On some UNIX systems, +.BR select () +unblocks and returns, with an indication that the file descriptor is ready +(a subsequent I/O operation will likely fail with an error, +unless another process reopens the file descriptor between the time +.BR select () +returned and the I/O operation is performed). +On Linux (and some other systems), +closing the file descriptor in another thread has no effect on +.BR select (). +In summary, any application that relies on a particular behavior +in this scenario must be considered buggy. +.\" +.SS C library/kernel differences +The Linux kernel allows file descriptor sets of arbitrary size, +determining the length of the sets to be checked from the value of +.IR nfds . +However, in the glibc implementation, the +.I fd_set +type is fixed in size. +See also BUGS. +.P +The +.BR pselect () +interface described in this page is implemented by glibc. +The underlying Linux system call is named +.BR pselect6 (). +This system call has somewhat different behavior from the glibc +wrapper function. +.P +The Linux +.BR pselect6 () +system call modifies its +.I timeout +argument. +However, the glibc wrapper function hides this behavior +by using a local variable for the timeout argument that +is passed to the system call. +Thus, the glibc +.BR pselect () +function does not modify its +.I timeout +argument; +this is the behavior required by POSIX.1-2001. +.P +The final argument of the +.BR pselect6 () +system call is not a +.I "sigset_t\ *" +pointer, but is instead a structure of the form: +.P +.in +4n +.EX +struct { + const kernel_sigset_t *ss; /* Pointer to signal set */ + size_t ss_len; /* Size (in bytes) of object + pointed to by \[aq]ss\[aq] */ +}; +.EE +.in +.P +This allows the system call to obtain both +a pointer to the signal set and its size, +while allowing for the fact that most architectures +support a maximum of 6 arguments to a system call. +See +.BR sigprocmask (2) +for a discussion of the difference between the kernel and libc +notion of the signal set. +.\" +.SS Historical glibc details +glibc 2.0 provided an incorrect version of +.BR pselect () +that did not take a +.I sigmask +argument. +.P +From glibc 2.1 to glibc 2.2.1, +one must define +.B _GNU_SOURCE +in order to obtain the declaration of +.BR pselect () +from +.IR <sys/select.h> . +.SH BUGS +POSIX allows an implementation to define an upper limit, +advertised via the constant +.BR FD_SETSIZE , +on the range of file descriptors that can be specified +in a file descriptor set. +The Linux kernel imposes no fixed limit, but the glibc implementation makes +.I fd_set +a fixed-size type, with +.B FD_SETSIZE +defined as 1024, and the +.BR FD_* () +macros operating according to that limit. +To monitor file descriptors greater than 1023, use +.BR poll (2) +or +.BR epoll (7) +instead. +.P +The implementation of the +.I fd_set +arguments as value-result arguments is a design error that is avoided in +.BR poll (2) +and +.BR epoll (7). +.P +According to POSIX, +.BR select () +should check all specified file descriptors in the three file descriptor sets, +up to the limit +.IR nfds\-1 . +However, the current implementation ignores any file descriptor in +these sets that is greater than the maximum file descriptor number +that the process currently has open. +According to POSIX, any such file descriptor that is specified in one +of the sets should result in the error +.BR EBADF . +.P +Starting with glibc 2.1, glibc provided an emulation of +.BR pselect () +that was implemented using +.BR sigprocmask (2) +and +.BR select (). +This implementation remained vulnerable to the very race condition that +.BR pselect () +was designed to prevent. +Modern versions of glibc use the (race-free) +.BR pselect () +system call on kernels where it is provided. +.P +On Linux, +.BR select () +may report a socket file descriptor as "ready for reading", while +nevertheless a subsequent read blocks. +This could for example +happen when data has arrived but upon examination has the wrong +checksum and is discarded. +There may be other circumstances +in which a file descriptor is spuriously reported as ready. +.\" Stevens discusses a case where accept can block after select +.\" returns successfully because of an intervening RST from the client. +Thus it may be safer to use +.B O_NONBLOCK +on sockets that should not block. +.\" Maybe the kernel should have returned EIO in such a situation? +.P +On Linux, +.BR select () +also modifies +.I timeout +if the call is interrupted by a signal handler (i.e., the +.B EINTR +error return). +This is not permitted by POSIX.1. +The Linux +.BR pselect () +system call has the same behavior, +but the glibc wrapper hides this behavior by internally copying the +.I timeout +to a local variable and passing that variable to the system call. +.SH EXAMPLES +.\" SRC BEGIN (select.c) +.EX +#include <stdio.h> +#include <stdlib.h> +#include <sys/select.h> +\& +int +main(void) +{ + int retval; + fd_set rfds; + struct timeval tv; +\& + /* Watch stdin (fd 0) to see when it has input. */ +\& + FD_ZERO(&rfds); + FD_SET(0, &rfds); +\& + /* Wait up to five seconds. */ +\& + tv.tv_sec = 5; + tv.tv_usec = 0; +\& + retval = select(1, &rfds, NULL, NULL, &tv); + /* Don\[aq]t rely on the value of tv now! */ +\& + if (retval == \-1) + perror("select()"); + else if (retval) + printf("Data is available now.\en"); + /* FD_ISSET(0, &rfds) will be true. */ + else + printf("No data within five seconds.\en"); +\& + exit(EXIT_SUCCESS); +} +.EE +.\" SRC END +.SH SEE ALSO +.BR accept (2), +.BR connect (2), +.BR poll (2), +.BR read (2), +.BR recv (2), +.BR restart_syscall (2), +.BR send (2), +.BR sigprocmask (2), +.BR write (2), +.BR timespec (3), +.BR epoll (7), +.BR time (7) +.P +For a tutorial with discussion and examples, see +.BR select_tut (2). |