--- AnyEvent/lib/AnyEvent/Handle.pm 2009/08/05 20:50:27 1.172 +++ AnyEvent/lib/AnyEvent/Handle.pm 2011/07/24 13:10:43 1.220 @@ -1,19 +1,6 @@ -package AnyEvent::Handle; - -use Scalar::Util (); -use Carp (); -use Errno qw(EAGAIN EINTR); - -use AnyEvent (); BEGIN { AnyEvent::common_sense } -use AnyEvent::Util qw(WSAEWOULDBLOCK); - =head1 NAME -AnyEvent::Handle - non-blocking I/O on file handles via AnyEvent - -=cut - -our $VERSION = 4.901; +AnyEvent::Handle - non-blocking I/O on streaming handles via AnyEvent =head1 SYNOPSIS @@ -29,7 +16,7 @@ warn "got error $msg\n"; $hdl->destroy; $cv->send; - ); + }; # send some request line $hdl->push_write ("getinfo\015\012"); @@ -45,14 +32,14 @@ =head1 DESCRIPTION -This module is a helper module to make it easier to do event-based I/O on -filehandles. +This is a helper module to make it easier to do event-based I/O on +stream-based filehandles (sockets, pipes, and other stream things). The L tutorial contains some well-documented AnyEvent::Handle examples. -In the following, when the documentation refers to of "bytes" then this -means characters. As sysread and syswrite are used for all I/O, their +In the following, where the documentation refers to "bytes", it means +characters. As sysread and syswrite are used for all I/O, their treatment of characters applies to this module as well. At the very minimum, you should specify C or C, and the @@ -61,11 +48,42 @@ All callbacks will be invoked with the handle object as their first argument. +=cut + +package AnyEvent::Handle; + +use Scalar::Util (); +use List::Util (); +use Carp (); +use Errno qw(EAGAIN EINTR); + +use AnyEvent (); BEGIN { AnyEvent::common_sense } +use AnyEvent::Util qw(WSAEWOULDBLOCK); + +our $VERSION = $AnyEvent::VERSION; + +sub _load_func($) { + my $func = $_[0]; + + unless (defined &$func) { + my $pkg = $func; + do { + $pkg =~ s/::[^:]+$// + or return; + eval "require $pkg"; + } until defined &$func; + } + + \&$func +} + +sub MAX_READ_SIZE() { 131072 } + =head1 METHODS =over 4 -=item $handle = B AnyEvent::TLS fh => $filehandle, key => value... +=item $handle = B AnyEvent::Handle fh => $filehandle, key => value... The constructor supports these arguments (all as C<< key => value >> pairs). @@ -98,33 +116,33 @@ =item on_prepare => $cb->($handle) This (rarely used) callback is called before a new connection is -attempted, but after the file handle has been created. It could be used to -prepare the file handle with parameters required for the actual connect -(as opposed to settings that can be changed when the connection is already -established). +attempted, but after the file handle has been created (you can access that +file handle via C<< $handle->{fh} >>). It could be used to prepare the +file handle with parameters required for the actual connect (as opposed to +settings that can be changed when the connection is already established). The return value of this callback should be the connect timeout value in -seconds (or C<0>, or C, or the empty list, to indicate the default -timeout is to be used). +seconds (or C<0>, or C, or the empty list, to indicate that the +default timeout is to be used). =item on_connect => $cb->($handle, $host, $port, $retry->()) This callback is called when a connection has been successfully established. -The actual numeric host and port (the socket peername) are passed as +The peer's numeric host and port (the socket peername) are passed as parameters, together with a retry callback. -When, for some reason, the handle is not acceptable, then calling -C<$retry> will continue with the next conenction target (in case of -multi-homed hosts or SRV records there can be multiple connection -endpoints). When it is called then the read and write queues, eof status, -tls status and similar properties of the handle are being reset. +If, for some reason, the handle is not acceptable, calling C<$retry> +will continue with the next connection target (in case of multi-homed +hosts or SRV records there can be multiple connection endpoints). At the +time it is called the read and write queues, eof status, tls status and +similar properties of the handle will have been reset. -In most cases, ignoring the C<$retry> parameter is the way to go. +In most cases, you should ignore the C<$retry> parameter. =item on_connect_error => $cb->($handle, $message) -This callback is called when the conenction could not be +This callback is called when the connection could not be established. C<$!> will contain the relevant error code, and C<$message> a message describing it (usually the same as C<"$!">). @@ -137,14 +155,14 @@ This is the error callback, which is called when, well, some error occured, such as not being able to resolve the hostname, failure to -connect or a read error. +connect, or a read error. Some errors are fatal (which is indicated by C<$fatal> being true). On fatal errors the handle object will be destroyed (by a call to C<< -> destroy >>) after invoking the error callback (which means you are free to examine the handle object). Examples of fatal errors are an EOF condition -with active (but unsatisifable) read watchers (C) or I/O errors. In -cases where the other side can close the connection at their will it is +with active (but unsatisfiable) read watchers (C) or I/O errors. In +cases where the other side can close the connection at will, it is often easiest to not report C errors in this callback. AnyEvent::Handle tries to find an appropriate error code for you to check @@ -152,17 +170,17 @@ recommended to always output the C<$message> argument in human-readable error messages (it's usually the same as C<"$!">). -Non-fatal errors can be retried by simply returning, but it is recommended +Non-fatal errors can be retried by returning, but it is recommended to simply ignore this parameter and instead abondon the handle object when this callback is invoked. Examples of non-fatal errors are timeouts C) or badly-formatted data (C). -On callback entrance, the value of C<$!> contains the operating system -error code (or C, C, C, C or +On entry to the callback, the value of C<$!> contains the operating +system error code (or C, C, C, C or C). While not mandatory, it is I recommended to set this callback, as -you will not be notified of errors otherwise. The default simply calls +you will not be notified of errors otherwise. The default just calls C. =item on_read => $cb->($handle) @@ -177,7 +195,10 @@ must not enlarge or modify the read buffer, you can only remove data at the beginning from it. -When an EOF condition is detected then AnyEvent::Handle will first try to +You can also call C<< ->push_read (...) >> or any other function that +modifies the read queue. Or do both. Or ... + +When an EOF condition is detected, AnyEvent::Handle will first try to feed all the remaining data to the queued callbacks and C before calling the C callback. If no progress can be made, then a fatal error will be raised (with C<$!> set to C). @@ -206,7 +227,7 @@ =item on_drain => $cb->($handle) This sets the callback that is called when the write buffer becomes empty -(or when the callback is set and the buffer is empty already). +(or immediately if the buffer is empty already). To append to the write buffer, use the C<< ->push_write >> method. @@ -218,21 +239,37 @@ =item timeout => $fractional_seconds -If non-zero, then this enables an "inactivity" timeout: whenever this many -seconds pass without a successful read or write on the underlying file -handle, the C callback will be invoked (and if that one is -missing, a non-fatal C error will be raised). - -Note that timeout processing is also active when you currently do not have -any outstanding read or write requests: If you plan to keep the connection -idle then you should disable the timout temporarily or ignore the timeout -in the C callback, in which case AnyEvent::Handle will simply -restart the timeout. +=item rtimeout => $fractional_seconds + +=item wtimeout => $fractional_seconds -Zero (the default) disables this timeout. +If non-zero, then these enables an "inactivity" timeout: whenever this +many seconds pass without a successful read or write on the underlying +file handle (or a call to C), the C callback +will be invoked (and if that one is missing, a non-fatal C +error will be raised). + +There are three variants of the timeouts that work independently of each +other, for both read and write (triggered when nothing was read I +written), just read (triggered when nothing was read), and just write: +C, C and C, with corresponding callbacks +C, C and C, and reset functions +C, C, and C. + +Note that timeout processing is active even when you do not have any +outstanding read or write requests: If you plan to keep the connection +idle then you should disable the timeout temporarily or ignore the +timeout in the corresponding C callback, in which case +AnyEvent::Handle will simply restart the timeout. + +Zero (the default) disables the corresponding timeout. =item on_timeout => $cb->($handle) +=item on_rtimeout => $cb->($handle) + +=item on_wtimeout => $cb->($handle) + Called whenever the inactivity timeout passes. If you return from this callback, then the timeout will be reset as if some activity had happened, so this condition is not fatal in any way. @@ -249,16 +286,31 @@ amount of data without a callback ever being called as long as the line isn't finished). +=item wbuf_max => + +If defined, then a fatal error will be raised (with C<$!> set to C) +when the write buffer ever (strictly) exceeds this size. This is useful to +avoid some forms of denial-of-service attacks. + +Although the units of this parameter is bytes, this is the I number +of bytes not yet accepted by the kernel. This can make a difference when +you e.g. use TLS, as TLS typically makes your write data larger (but it +can also make it smaller due to compression). + +As an example of when this limit is useful, take a chat server that sends +chat messages to a client. If the client does not read those in a timely +manner then the send buffer in the server would grow unbounded. + =item autocork => -When disabled (the default), then C will try to immediately -write the data to the handle, if possible. This avoids having to register +When disabled (the default), C will try to immediately +write the data to the handle if possible. This avoids having to register a write watcher and wait for the next event loop iteration, but can be inefficient if you write multiple small chunks (on the wire, this disadvantage is usually avoided by your kernel's nagle algorithm, see C, but this option can save costly syscalls). -When enabled, then writes will always be queued till the next event loop +When enabled, writes will always be queued till the next event loop iteration. This is efficient when you do many small writes per iteration, but less efficient when you do a single write only per iteration (or when the write buffer often is full). It also increases write latency. @@ -272,19 +324,59 @@ In some situations you want as low a delay as possible, which can be accomplishd by setting this option to a true value. -The default is your opertaing system's default behaviour (most likely -enabled), this option explicitly enables or disables it, if possible. +The default is your operating system's default behaviour (most likely +enabled). This option explicitly enables or disables it, if possible. + +=item keepalive => + +Enables (default disable) the SO_KEEPALIVE option on the stream socket: +normally, TCP connections have no time-out once established, so TCP +connections, once established, can stay alive forever even when the other +side has long gone. TCP keepalives are a cheap way to take down long-lived +TCP connections when the other side becomes unreachable. While the default +is OS-dependent, TCP keepalives usually kick in after around two hours, +and, if the other side doesn't reply, take down the TCP connection some 10 +to 15 minutes later. + +It is harmless to specify this option for file handles that do not support +keepalives, and enabling it on connections that are potentially long-lived +is usually a good idea. + +=item oobinline => + +BSD majorly fucked up the implementation of TCP urgent data. The result +is that almost no OS implements TCP according to the specs, and every OS +implements it slightly differently. + +If you want to handle TCP urgent data, then setting this flag (the default +is enabled) gives you the most portable way of getting urgent data, by +putting it into the stream. + +Since BSD emulation of OOB data on top of TCP's urgent data can have +security implications, AnyEvent::Handle sets this flag automatically +unless explicitly specified. Note that setting this flag after +establishing a connection I be a bit too late (data loss could +already have occured on BSD systems), but at least it will protect you +from most attacks. =item read_size => -The default read block size (the amount of bytes this module will -try to read during each loop iteration, which affects memory -requirements). Default: C<8192>. +The initial read block size, the number of bytes this module will try to +read during each loop iteration. Each handle object will consume at least +this amount of memory for the read buffer as well, so when handling many +connections requirements). See also C. Default: C<2048>. + +=item max_read_size => + +The maximum read buffer size used by the dynamic adjustment +algorithm: Each time AnyEvent::Handle can read C bytes in +one go it will double C up to the maximum given by this +option. Default: C<131072> or C, whichever is higher. =item low_water_mark => -Sets the amount of bytes (default: C<0>) that make up an "empty" write -buffer: If the write reaches this size or gets even samller it is +Sets the number of bytes (default: C<0>) that make up an "empty" write +buffer: If the buffer reaches this size or gets even samller it is considered empty. Sometimes it can be beneficial (for performance reasons) to add data to @@ -294,7 +386,7 @@ =item linger => -If non-zero (default: C<3600>), then the destructor of the +If this is non-zero (default: C<3600>), the destructor of the AnyEvent::Handle object will check whether there is still outstanding write data and will install a watcher that will write this data to the socket. No errors will be reported (this mostly matches how the operating @@ -311,13 +403,13 @@ Apart from being useful in error messages, this string is also used in TLS peername verification (see C in L). This -verification will be skipped when C is not specified or +verification will be skipped when C is not specified or is C. =item tls => "accept" | "connect" | Net::SSLeay::SSL object When this parameter is given, it enables TLS (SSL) mode, that means -AnyEvent will start a TLS handshake as soon as the conenction has been +AnyEvent will start a TLS handshake as soon as the connection has been established and will transparently encrypt/decrypt data afterwards. All TLS protocol errors will be signalled as C, with an @@ -347,13 +439,14 @@ happens when one uses a stylish C<< tls => 1 >> and is surprised about the segmentation fault. -See the C<< ->starttls >> method for when need to start TLS negotiation later. +Use the C<< ->starttls >> method if you need to start TLS negotiation later. =item tls_ctx => $anyevent_tls Use the given C object to create the new TLS connection -(unless a connection object was specified directly). If this parameter is -missing, then AnyEvent::Handle will use C. +(unless a connection object was specified directly). If this +parameter is missing (or C), then AnyEvent::Handle will use +C. Instead of an object, you can also specify a hash reference with C<< key => value >> pairs. Those will be passed to L to create a @@ -372,9 +465,9 @@ callback is in effect, instead, the error message will be passed to C. Without this callback, handshake failures lead to C being -called, as normal. +called as usual. -Note that you cannot call C right again in this callback. If you +Note that you cannot just call C again in this callback. If you need to do that, start an zero-second timer instead whose callback can then call C<< ->starttls >> again. @@ -432,6 +525,8 @@ sub { my ($fh, $host, $port, $retry) = @_; + delete $self->{_connect}; # no longer needed + if ($fh) { $self->{fh} = $fh; @@ -440,7 +535,7 @@ $self->{on_connect} and $self->{on_connect}($self, $host, $port, sub { - delete @$self{qw(fh _tw _ww _rw _eof _queue rbuf _wbuf tls _tls_rbuf _tls_wbuf)}; + delete @$self{qw(fh _tw _rtw _wtw _ww _rw _eof _queue rbuf _wbuf tls _tls_rbuf _tls_wbuf)}; $self->{_skip_drain_rbuf} = 1; &$retry; }); @@ -448,7 +543,7 @@ } else { if ($self->{on_connect_error}) { $self->{on_connect_error}($self, "$!"); - $self->destroy; + $self->destroy if $self; } else { $self->_error ($!, 1); } @@ -458,7 +553,7 @@ local $self->{fh} = $_[0]; $self->{on_prepare} - ? $self->{on_prepare}->($self) + ? $self->{on_prepare}->($self) : () } ); @@ -474,17 +569,35 @@ sub _start { my ($self) = @_; + # too many clueless people try to use udp and similar sockets + # with AnyEvent::Handle, do them a favour. + my $type = getsockopt $self->{fh}, Socket::SOL_SOCKET (), Socket::SO_TYPE (); + Carp::croak "AnyEvent::Handle: only stream sockets supported, anything else will NOT work!" + if Socket::SOCK_STREAM () != (unpack "I", $type) && defined $type; + AnyEvent::Util::fh_nonblocking $self->{fh}, 1; - $self->{_activity} = AnyEvent->now; - $self->_timeout; + $self->{_activity} = + $self->{_ractivity} = + $self->{_wactivity} = AE::now; + + $self->{read_size} ||= 2048; + $self->{max_read_size} = $self->{read_size} + if $self->{read_size} > ($self->{max_read_size} || MAX_READ_SIZE); + + $self->timeout (delete $self->{timeout} ) if $self->{timeout}; + $self->rtimeout (delete $self->{rtimeout} ) if $self->{rtimeout}; + $self->wtimeout (delete $self->{wtimeout} ) if $self->{wtimeout}; - $self->no_delay (delete $self->{no_delay}) if exists $self->{no_delay}; + $self->no_delay (delete $self->{no_delay} ) if exists $self->{no_delay} && $self->{no_delay}; + $self->keepalive (delete $self->{keepalive}) if exists $self->{keepalive} && $self->{keepalive}; - $self->starttls (delete $self->{tls}, delete $self->{tls_ctx}) + $self->oobinline (exists $self->{oobinline} ? delete $self->{oobinline} : 1); + + $self->starttls (delete $self->{tls}, delete $self->{tls_ctx}) if $self->{tls}; - $self->on_drain (delete $self->{on_drain}) if $self->{on_drain}; + $self->on_drain (delete $self->{on_drain} ) if $self->{on_drain}; $self->start_read if $self->{on_read} || @{ $self->{_queue} }; @@ -492,15 +605,6 @@ $self->_drain_wbuf; } -#sub _shutdown { -# my ($self) = @_; -# -# delete @$self{qw(_tw _rw _ww fh wbuf on_read _queue)}; -# $self->{_eof} = 1; # tell starttls et. al to stop trying -# -# &_freetls; -#} - sub _error { my ($self, $errno, $fatal, $message) = @_; @@ -510,7 +614,7 @@ if ($self->{on_error}) { $self->{on_error}($self, $fatal, $message); $self->destroy if $fatal; - } elsif ($self->{fh}) { + } elsif ($self->{fh} || $self->{connect}) { $self->destroy; Carp::croak "AnyEvent::Handle uncaught error: $message"; } @@ -546,15 +650,17 @@ =item $handle->on_timeout ($cb) -Replace the current C callback, or disables the callback (but -not the timeout) if C<$cb> = C. See the C constructor -argument and method. +=item $handle->on_rtimeout ($cb) + +=item $handle->on_wtimeout ($cb) + +Replace the current C, C or C +callback, or disables the callback (but not the timeout) if C<$cb> = +C. See the C constructor argument and method. =cut -sub on_timeout { - $_[0]{on_timeout} = $_[1]; -} +# see below =item $handle->autocork ($boolean) @@ -577,9 +683,57 @@ sub no_delay { $_[0]{no_delay} = $_[1]; + setsockopt $_[0]{fh}, Socket::IPPROTO_TCP (), Socket::TCP_NODELAY (), int $_[1] + if $_[0]{fh}; +} + +=item $handle->keepalive ($boolean) + +Enables or disables the C setting (see constructor argument of +the same name for details). + +=cut + +sub keepalive { + $_[0]{keepalive} = $_[1]; + + eval { + local $SIG{__DIE__}; + setsockopt $_[0]{fh}, Socket::SOL_SOCKET (), Socket::SO_KEEPALIVE (), int $_[1] + if $_[0]{fh}; + }; +} + +=item $handle->oobinline ($boolean) + +Enables or disables the C setting (see constructor argument of +the same name for details). + +=cut + +sub oobinline { + $_[0]{oobinline} = $_[1]; + eval { local $SIG{__DIE__}; - setsockopt $_[0]{fh}, &Socket::IPPROTO_TCP, &Socket::TCP_NODELAY, int $_[1] + setsockopt $_[0]{fh}, Socket::SOL_SOCKET (), Socket::SO_OOBINLINE (), int $_[1] + if $_[0]{fh}; + }; +} + +=item $handle->keepalive ($boolean) + +Enables or disables the C setting (see constructor argument of +the same name for details). + +=cut + +sub keepalive { + $_[0]{keepalive} = $_[1]; + + eval { + local $SIG{__DIE__}; + setsockopt $_[0]{fh}, Socket::SOL_SOCKET (), Socket::SO_KEEPALIVE (), int $_[1] if $_[0]{fh}; }; } @@ -600,7 +754,7 @@ =cut -sub on_starttls { +sub on_stoptls { $_[0]{on_stoptls} = $_[1]; } @@ -608,64 +762,109 @@ Configures the C setting (C disables it). +=item $handle->wbuf_max ($max_octets) + +Configures the C setting (C disables it). + =cut sub rbuf_max { $_[0]{rbuf_max} = $_[1]; } +sub wbuf_max { + $_[0]{wbuf_max} = $_[1]; +} + ############################################################################# =item $handle->timeout ($seconds) +=item $handle->rtimeout ($seconds) + +=item $handle->wtimeout ($seconds) + Configures (or disables) the inactivity timeout. +The timeout will be checked instantly, so this method might destroy the +handle before it returns. + +=item $handle->timeout_reset + +=item $handle->rtimeout_reset + +=item $handle->wtimeout_reset + +Reset the activity timeout, as if data was received or sent. + +These methods are cheap to call. + =cut -sub timeout { - my ($self, $timeout) = @_; +for my $dir ("", "r", "w") { + my $timeout = "${dir}timeout"; + my $tw = "_${dir}tw"; + my $on_timeout = "on_${dir}timeout"; + my $activity = "_${dir}activity"; + my $cb; - $self->{timeout} = $timeout; - $self->_timeout; -} + *$on_timeout = sub { + $_[0]{$on_timeout} = $_[1]; + }; -# reset the timeout watcher, as neccessary -# also check for time-outs -sub _timeout { - my ($self) = @_; + *$timeout = sub { + my ($self, $new_value) = @_; + + $new_value >= 0 + or Carp::croak "AnyEvent::Handle->$timeout called with negative timeout ($new_value), caught"; - if ($self->{timeout} && $self->{fh}) { - my $NOW = AnyEvent->now; + $self->{$timeout} = $new_value; + delete $self->{$tw}; &$cb; + }; - # when would the timeout trigger? - my $after = $self->{_activity} + $self->{timeout} - $NOW; + *{"${dir}timeout_reset"} = sub { + $_[0]{$activity} = AE::now; + }; - # now or in the past already? - if ($after <= 0) { - $self->{_activity} = $NOW; + # main workhorse: + # reset the timeout watcher, as neccessary + # also check for time-outs + $cb = sub { + my ($self) = @_; + + if ($self->{$timeout} && $self->{fh}) { + my $NOW = AE::now; + + # when would the timeout trigger? + my $after = $self->{$activity} + $self->{$timeout} - $NOW; + + # now or in the past already? + if ($after <= 0) { + $self->{$activity} = $NOW; - if ($self->{on_timeout}) { - $self->{on_timeout}($self); - } else { - $self->_error (Errno::ETIMEDOUT); - } + if ($self->{$on_timeout}) { + $self->{$on_timeout}($self); + } else { + $self->_error (Errno::ETIMEDOUT); + } - # callback could have changed timeout value, optimise - return unless $self->{timeout}; + # callback could have changed timeout value, optimise + return unless $self->{$timeout}; - # calculate new after - $after = $self->{timeout}; - } + # calculate new after + $after = $self->{$timeout}; + } - Scalar::Util::weaken $self; - return unless $self; # ->error could have destroyed $self + Scalar::Util::weaken $self; + return unless $self; # ->error could have destroyed $self - $self->{_tw} ||= AnyEvent->timer (after => $after, cb => sub { - delete $self->{_tw}; - $self->_timeout; - }); - } else { - delete $self->{_tw}; + $self->{$tw} ||= AE::timer $after, 0, sub { + delete $self->{$tw}; + $cb->($self); + }; + } else { + delete $self->{$tw}; + } } } @@ -691,6 +890,9 @@ Sets the C callback or clears it (see the description of C in the constructor). +This method may invoke callbacks (and therefore the handle might be +destroyed after it returns). + =cut sub on_drain { @@ -704,9 +906,12 @@ =item $handle->push_write ($data) -Queues the given scalar to be written. You can push as much data as you -want (only limited by the available memory), as C -buffers it independently of the kernel. +Queues the given scalar to be written. You can push as much data as +you want (only limited by the available memory and C), as +C buffers it independently of the kernel. + +This method may invoke callbacks (and therefore the handle might be +destroyed after it returns). =cut @@ -723,7 +928,7 @@ if (defined $len) { substr $self->{wbuf}, 0, $len, ""; - $self->{_activity} = AnyEvent->now; + $self->{_activity} = $self->{_wactivity} = AE::now; $self->{on_drain}($self) if $self->{low_water_mark} >= (length $self->{wbuf}) + (length $self->{_tls_wbuf}) @@ -739,13 +944,21 @@ $cb->() unless $self->{autocork}; # if still data left in wbuf, we need to poll - $self->{_ww} = AnyEvent->io (fh => $self->{fh}, poll => "w", cb => $cb) + $self->{_ww} = AE::io $self->{fh}, 1, $cb if length $self->{wbuf}; + + if ( + defined $self->{wbuf_max} + && $self->{wbuf_max} < length $self->{wbuf} + ) { + $self->_error (Errno::ENOSPC, 1), return; + } }; } our %WH; +# deprecated sub register_write_type($$) { $WH{$_[0]} = $_[1]; } @@ -756,23 +969,30 @@ if (@_ > 1) { my $type = shift; - @_ = ($WH{$type} or Carp::croak "unsupported type passed to AnyEvent::Handle::push_write") + @_ = ($WH{$type} ||= _load_func "$type\::anyevent_write_type" + or Carp::croak "unsupported/unloadable type '$type' passed to AnyEvent::Handle::push_write") ->($self, @_); } + # we downgrade here to avoid hard-to-track-down bugs, + # and diagnose the problem earlier and better. + if ($self->{tls}) { - $self->{_tls_wbuf} .= $_[0]; + utf8::downgrade $self->{_tls_wbuf} .= $_[0]; &_dotls ($self) if $self->{fh}; } else { - $self->{wbuf} .= $_[0]; + utf8::downgrade $self->{wbuf} .= $_[0]; $self->_drain_wbuf if $self->{fh}; } } =item $handle->push_write (type => @args) -Instead of formatting your data yourself, you can also let this module do -the job by specifying a type and type-specific arguments. +Instead of formatting your data yourself, you can also let this module +do the job by specifying a type and type-specific arguments. You +can also specify the (fully qualified) name of a package, in which +case AnyEvent tries to load the package and then expects to find the +C function inside (see "custom write types", below). Predefined types are (if you have ideas for additional types, feel free to drop by and tell us): @@ -839,13 +1059,17 @@ =cut +sub json_coder() { + eval { require JSON::XS; JSON::XS->new->utf8 } + || do { require JSON; JSON->new->utf8 } +} + register_write_type json => sub { my ($self, $ref) = @_; - require JSON; + my $json = $self->{json} ||= json_coder; - $self->{json} ? $self->{json}->encode ($ref) - : JSON::encode_json ($ref) + $json->encode ($ref) }; =item storable => $reference @@ -873,7 +1097,7 @@ C to C<0>). This method is a shorthand for just that, and replaces the C callback with: - sub { shutdown $_[0]{fh}, 1 } # for push_shutdown + sub { shutdown $_[0]{fh}, 1 } This simply shuts down the write side and signals an EOF condition to the the peer. @@ -881,6 +1105,9 @@ You can rely on the normal read queue and C handling afterwards. This is the cleanest way to close a connection. +This method may invoke callbacks (and therefore the handle might be +destroyed after it returns). + =cut sub push_shutdown { @@ -890,17 +1117,37 @@ $self->on_drain (sub { shutdown $_[0]{fh}, 1 }); } -=item AnyEvent::Handle::register_write_type type => $coderef->($handle, @args) +=item custom write types - Package::anyevent_write_type $handle, @args + +Instead of one of the predefined types, you can also specify the name of +a package. AnyEvent will try to load the package and then expects to find +a function named C inside. If it isn't found, it +progressively tries to load the parent package until it either finds the +function (good) or runs out of packages (bad). -This function (not method) lets you add your own types to C. -Whenever the given C is used, C will invoke the code -reference with the handle object and the remaining arguments. +Whenever the given C is used, C will the function with +the handle object and the remaining arguments. -The code reference is supposed to return a single octet string that will -be appended to the write buffer. +The function is supposed to return a single octet string that will be +appended to the write buffer, so you cna mentally treat this function as a +"arguments to on-the-wire-format" converter. -Note that this is a function, and all types registered this way will be -global, so try to use unique names. +Example: implement a custom write type C that joins the remaining +arguments using the first one. + + $handle->push_write (My::Type => " ", 1,2,3); + + # uses the following package, which can be defined in the "My::Type" or in + # the "My" modules to be auto-loaded, or just about anywhere when the + # My::Type::anyevent_write_type is defined before invoking it. + + package My::Type; + + sub anyevent_write_type { + my ($handle, $delim, @args) = @_; + + join $delim, @args + } =cut @@ -919,13 +1166,14 @@ In the simple case, you just install an C callback and whenever new data arrives, it will be called. You can then remove some data (if -enough is there) from the read buffer (C<< $handle->rbuf >>). Or you cna +enough is there) from the read buffer (C<< $handle->rbuf >>). Or you can leave the data there if you want to accumulate more (e.g. when only a -partial message has been received so far). +partial message has been received so far), or change the read queue with +e.g. C. In the more complex case, you want to queue multiple callbacks. In this case, AnyEvent::Handle will call the first queued callback each time new -data arrives (also the first time it is queued) and removes it when it has +data arrives (also the first time it is queued) and remove it when it has done its job (see C, below). This way you can, for example, push three line-reads, followed by reading @@ -1066,6 +1314,9 @@ the new callback is C). See the description of C in the constructor. +This method may invoke callbacks (and therefore the handle might be +destroyed after it returns). + =cut sub on_read { @@ -1077,17 +1328,18 @@ =item $handle->rbuf -Returns the read buffer (as a modifiable lvalue). - -You can access the read buffer directly as the C<< ->{rbuf} >> -member, if you want. However, the only operation allowed on the -read buffer (apart from looking at it) is removing data from its -beginning. Otherwise modifying or appending to it is not allowed and will -lead to hard-to-track-down bugs. - -NOTE: The read buffer should only be used or modified if the C, -C or C methods are used. The other read methods -automatically manage the read buffer. +Returns the read buffer (as a modifiable lvalue). You can also access the +read buffer directly as the C<< ->{rbuf} >> member, if you want (this is +much faster, and no less clean). + +The only operation allowed on the read buffer (apart from looking at it) +is removing data from its beginning. Otherwise modifying or appending to +it is not allowed and will lead to hard-to-track-down bugs. + +NOTE: The read buffer should only be used or modified in the C +callback or when C or C are used with a single +callback (i.e. untyped). Typed C and C methods +will manage the read buffer on their own. =cut @@ -1114,6 +1366,9 @@ interested in (which can be none at all) and return a true value. After returning true, it will be removed from the queue. +These methods may invoke callbacks (and therefore the handle might be +destroyed after it returns). + =cut our %RH; @@ -1129,7 +1384,8 @@ if (@_) { my $type = shift; - $cb = ($RH{$type} or Carp::croak "unsupported type passed to AnyEvent::Handle::push_read") + $cb = ($RH{$type} ||= _load_func "$type\::anyevent_read_type" + or Carp::croak "unsupported/unloadable type '$type' passed to AnyEvent::Handle::push_read") ->($self, $cb, @_); } @@ -1144,11 +1400,11 @@ if (@_) { my $type = shift; - $cb = ($RH{$type} or Carp::croak "unsupported type passed to AnyEvent::Handle::unshift_read") + $cb = ($RH{$type} ||= _load_func "$type\::anyevent_read_type" + or Carp::croak "unsupported/unloadable type '$type' passed to AnyEvent::Handle::unshift_read") ->($self, $cb, @_); } - unshift @{ $self->{_queue} }, $cb; $self->_drain_rbuf; } @@ -1159,7 +1415,9 @@ Instead of providing a callback that parses the data itself you can chose between a number of predefined parsing formats, for chunks of data, lines -etc. +etc. You can also specify the (fully qualified) name of a package, in +which case AnyEvent tries to load the package and then expects to find the +C function inside (see "custom read types", below). Predefined types are (if you have ideas for additional types, feel free to drop by and tell us): @@ -1261,10 +1519,10 @@ unconditionally. This is useful to skip large amounts of data that you know cannot be matched, so that the C<$accept> or C<$reject> regex do not have to start matching from the beginning. This is purely an optimisation -and is usually worth only when you expect more than a few kilobytes. +and is usually worth it only when you expect more than a few kilobytes. Example: expect a http header, which ends at C<\015\012\015\012>. Since we -expect the header to be very large (it isn't in practise, but...), we use +expect the header to be very large (it isn't in practice, but...), we use a skip regex to skip initial portions. The skip regex is tricky in that it only accepts something not ending in either \015 or \012, as these are required for the accept regex. @@ -1287,13 +1545,13 @@ # accept if ($$rbuf =~ $accept) { $data .= substr $$rbuf, 0, $+[0], ""; - $cb->($self, $data); + $cb->($_[0], $data); return 1; } # reject if ($reject && $$rbuf =~ $reject) { - $self->_error (Errno::EBADMSG); + $_[0]->_error (Errno::EBADMSG); } # skip @@ -1319,20 +1577,20 @@ sub { unless ($_[0]{rbuf} =~ s/^(0|[1-9][0-9]*)://) { if ($_[0]{rbuf} =~ /[^0-9]/) { - $self->_error (Errno::EBADMSG); + $_[0]->_error (Errno::EBADMSG); } return; } my $len = $1; - $self->unshift_read (chunk => $len, sub { + $_[0]->unshift_read (chunk => $len, sub { my $string = $_[1]; $_[0]->unshift_read (chunk => 1, sub { if ($_[1] eq ",") { $cb->($_[0], $string); } else { - $self->_error (Errno::EBADMSG); + $_[0]->_error (Errno::EBADMSG); } }); }); @@ -1409,34 +1667,32 @@ register_read_type json => sub { my ($self, $cb) = @_; - my $json = $self->{json} ||= - eval { require JSON::XS; JSON::XS->new->utf8 } - || do { require JSON; JSON->new->utf8 }; + my $json = $self->{json} ||= json_coder; my $data; my $rbuf = \$self->{rbuf}; sub { - my $ref = eval { $json->incr_parse ($self->{rbuf}) }; + my $ref = eval { $json->incr_parse ($_[0]{rbuf}) }; if ($ref) { - $self->{rbuf} = $json->incr_text; + $_[0]{rbuf} = $json->incr_text; $json->incr_text = ""; - $cb->($self, $ref); + $cb->($_[0], $ref); 1 } elsif ($@) { # error case $json->incr_skip; - $self->{rbuf} = $json->incr_text; + $_[0]{rbuf} = $json->incr_text; $json->incr_text = ""; - $self->_error (Errno::EBADMSG); + $_[0]->_error (Errno::EBADMSG); () } else { - $self->{rbuf} = ""; + $_[0]{rbuf} = ""; () } @@ -1479,7 +1735,7 @@ if (my $ref = eval { Storable::thaw ($_[1]) }) { $cb->($_[0], $ref); } else { - $self->_error (Errno::EBADMSG); + $_[0]->_error (Errno::EBADMSG); } }); } @@ -1490,25 +1746,28 @@ =back -=item AnyEvent::Handle::register_read_type type => $coderef->($handle, $cb, @args) - -This function (not method) lets you add your own types to C. +=item custom read types - Package::anyevent_read_type $handle, $cb, @args -Whenever the given C is used, C will invoke the code -reference with the handle object, the callback and the remaining -arguments. +Instead of one of the predefined types, you can also specify the name +of a package. AnyEvent will try to load the package and then expects to +find a function named C inside. If it isn't found, it +progressively tries to load the parent package until it either finds the +function (good) or runs out of packages (bad). + +Whenever this type is used, C will invoke the function with the +handle object, the original callback and the remaining arguments. + +The function is supposed to return a callback (usually a closure) that +works as a plain read callback (see C<< ->push_read ($cb) >>), so you can +mentally treat the function as a "configurable read type to read callback" +converter. + +It should invoke the original callback when it is done reading (remember +to pass C<$handle> as first argument as all other callbacks do that, +although there is no strict requirement on this). -The code reference is supposed to return a callback (usually a closure) -that works as a plain read callback (see C<< ->push_read ($cb) >>). - -It should invoke the passed callback when it is done reading (remember to -pass C<$handle> as first argument as all other callbacks do that). - -Note that this is a function, and all types registered this way will be -global, so try to use unique names. - -For examples, see the source of this module (F, -search for C)). +For examples, see the source of this module (F, search for C)). =item $handle->stop_read @@ -1524,29 +1783,38 @@ will automatically C for you when neither C is set nor there are any read requests in the queue. -These methods will have no effect when in TLS mode (as TLS doesn't support -half-duplex connections). +In older versions of this module (<= 5.3), these methods had no effect, +as TLS does not support half-duplex connections. In current versions they +work as expected, as this behaviour is required to avoid certain resource +attacks, where the program would be forced to read (and buffer) arbitrary +amounts of data before being able to send some data. The drawback is that +some readings of the the SSL/TLS specifications basically require this +attack to be working, as SSL/TLS implementations might stall sending data +during a rehandshake. + +As a guideline, during the initial handshake, you should not stop reading, +and as a client, it might cause problems, depending on your applciation. =cut sub stop_read { my ($self) = @_; - delete $self->{_rw} unless $self->{tls}; + delete $self->{_rw}; } sub start_read { my ($self) = @_; - unless ($self->{_rw} || $self->{_eof}) { + unless ($self->{_rw} || $self->{_eof} || !$self->{fh}) { Scalar::Util::weaken $self; - $self->{_rw} = AnyEvent->io (fh => $self->{fh}, poll => "r", cb => sub { + $self->{_rw} = AE::io $self->{fh}, 0, sub { my $rbuf = \($self->{tls} ? my $buf : $self->{rbuf}); - my $len = sysread $self->{fh}, $$rbuf, $self->{read_size} || 8192, length $$rbuf; + my $len = sysread $self->{fh}, $$rbuf, $self->{read_size}, length $$rbuf; if ($len > 0) { - $self->{_activity} = AnyEvent->now; + $self->{_activity} = $self->{_ractivity} = AE::now; if ($self->{tls}) { Net::SSLeay::BIO_write ($self->{_rbio}, $$rbuf); @@ -1556,6 +1824,12 @@ $self->_drain_rbuf; } + if ($len == $self->{read_size}) { + $self->{read_size} *= 2; + $self->{read_size} = $self->{max_read_size} || MAX_READ_SIZE + if $self->{read_size} > ($self->{max_read_size} || MAX_READ_SIZE); + } + } elsif (defined $len) { delete $self->{_rw}; $self->{_eof} = 1; @@ -1564,7 +1838,7 @@ } elsif ($! != EAGAIN && $! != EINTR && $! != WSAEWOULDBLOCK) { return $self->_error ($!, 1); } - }); + }; } } @@ -1641,6 +1915,7 @@ while (length ($tmp = Net::SSLeay::BIO_read ($self->{_wbio}))) { $self->{wbuf} .= $tmp; $self->_drain_wbuf; + $self->{tls} or return; # tls session might have gone away in callback } $self->{_on_starttls} @@ -1672,8 +1947,11 @@ when this function returns. Due to bugs in OpenSSL, it might or might not be possible to do multiple -handshakes on the same stream. Best do not attempt to use the stream after -stopping TLS. +handshakes on the same stream. It is best to not attempt to use the +stream after stopping TLS. + +This method may invoke callbacks (and therefore the handle might be +destroyed after it returns). =cut @@ -1695,7 +1973,7 @@ $ERROR_SYSCALL = Net::SSLeay::ERROR_SYSCALL (); $ERROR_WANT_READ = Net::SSLeay::ERROR_WANT_READ (); - $tls = $self->{tls}; + $tls = delete $self->{tls}; $ctx = $self->{tls_ctx}; local $Carp::CarpLevel = 1; # skip ourselves when creating a new context or session @@ -1734,7 +2012,8 @@ $self->{_rbio} = Net::SSLeay::BIO_new (Net::SSLeay::BIO_s_mem ()); $self->{_wbio} = Net::SSLeay::BIO_new (Net::SSLeay::BIO_s_mem ()); - Net::SSLeay::BIO_write ($self->{_rbio}, delete $self->{rbuf}); + Net::SSLeay::BIO_write ($self->{_rbio}, $self->{rbuf}); + $self->{rbuf} = ""; Net::SSLeay::set_bio ($tls, $self->{_rbio}, $self->{_wbio}); @@ -1749,15 +2028,18 @@ Shuts down the SSL connection - this makes a proper EOF handshake by sending a close notify to the other side, but since OpenSSL doesn't -support non-blocking shut downs, it is not guarenteed that you can re-use +support non-blocking shut downs, it is not guaranteed that you can re-use the stream afterwards. +This method may invoke callbacks (and therefore the handle might be +destroyed after it returns). + =cut sub stoptls { my ($self) = @_; - if ($self->{tls}) { + if ($self->{tls} && $self->{fh}) { Net::SSLeay::shutdown ($self->{tls}); &_dotls; @@ -1779,6 +2061,19 @@ delete @$self{qw(_rbio _wbio _tls_wbuf _on_starttls)}; } +=item $handle->resettls + +This rarely-used method simply resets and TLS state on the handle, usually +causing data loss. + +One case where it may be useful is when you want to skip over the data in +the stream but you are not interested in interpreting it, so data loss is +no concern. + +=cut + +*resettls = \&_freetls; + sub DESTROY { my ($self) = @_; @@ -1792,18 +2087,18 @@ my @linger; - push @linger, AnyEvent->io (fh => $fh, poll => "w", cb => sub { + push @linger, AE::io $fh, 1, sub { my $len = syswrite $fh, $wbuf, length $wbuf; if ($len > 0) { substr $wbuf, 0, $len, ""; - } else { + } elsif (defined $len || ($! != EAGAIN && $! != EINTR && $! != WSAEWOULDBLOCK)) { @linger = (); # end } - }); - push @linger, AnyEvent->timer (after => $linger, cb => sub { + }; + push @linger, AE::timer $linger, 0, sub { @linger = (); - }); + }; } } @@ -1844,6 +2139,29 @@ #nop } +=item $handle->destroyed + +Returns false as long as the handle hasn't been destroyed by a call to C<< +->destroy >>, true otherwise. + +Can be useful to decide whether the handle is still valid after some +callback possibly destroyed the handle. For example, C<< ->push_write >>, +C<< ->starttls >> and other methods can call user callbacks, which in turn +can destroy the handle, so work can be avoided by checking sometimes: + + $hdl->starttls ("accept"); + return if $hdl->destroyed; + $hdl->push_write (... + +Note that the call to C will silently be ignored if the handle +has been destroyed, so often you can just ignore the possibility of the +handle being destroyed. + +=cut + +sub destroyed { 0 } +sub AnyEvent::Handle::destroyed::destroyed { 1 } + =item AnyEvent::Handle::TLS_CTX This function creates and returns the AnyEvent::TLS object used by default @@ -1880,15 +2198,95 @@ from within all other callbacks, you need to explicitly call the C<< ->destroy >> method. +=item Why is my C callback never called? + +Probably because your C callback is being called instead: When +you have outstanding requests in your read queue, then an EOF is +considered an error as you clearly expected some data. + +To avoid this, make sure you have an empty read queue whenever your handle +is supposed to be "idle" (i.e. connection closes are O.K.). You cna set +an C handler that simply pushes the first read requests in the +queue. + +See also the next question, which explains this in a bit more detail. + +=item How can I serve requests in a loop? + +Most protocols consist of some setup phase (authentication for example) +followed by a request handling phase, where the server waits for requests +and handles them, in a loop. + +There are two important variants: The first (traditional, better) variant +handles requests until the server gets some QUIT command, causing it to +close the connection first (highly desirable for a busy TCP server). A +client dropping the connection is an error, which means this variant can +detect an unexpected detection close. + +To handle this case, always make sure you have a on-empty read queue, by +pushing the "read request start" handler on it: + + # we assume a request starts with a single line + my @start_request; @start_request = (line => sub { + my ($hdl, $line) = @_; + + ... handle request + + # push next request read, possibly from a nested callback + $hdl->push_read (@start_request); + }); + + # auth done, now go into request handling loop + # now push the first @start_request + $hdl->push_read (@start_request); + +By always having an outstanding C, the handle always expects +some data and raises the C error when the connction is dropped +unexpectedly. + +The second variant is a protocol where the client can drop the connection +at any time. For TCP, this means that the server machine may run out of +sockets easier, and in general, it means you cnanot distinguish a protocl +failure/client crash from a normal connection close. Nevertheless, these +kinds of protocols are common (and sometimes even the best solution to the +problem). + +Having an outstanding read request at all times is possible if you ignore +C errors, but this doesn't help with when the client drops the +connection during a request, which would still be an error. + +A better solution is to push the initial request read in an C +callback. This avoids an error, as when the server doesn't expect data +(i.e. is idly waiting for the next request, an EOF will not raise an +error, but simply result in an C callback. It is also a bit slower +and simpler: + + # auth done, now go into request handling loop + $hdl->on_read (sub { + my ($hdl) = @_; + + # called each time we receive data but the read queue is empty + # simply start read the request + + $hdl->push_read (line => sub { + my ($hdl, $line) = @_; + + ... handle request + + # do nothing special when the request has been handled, just + # let the request queue go empty. + }); + }); + =item I get different callback invocations in TLS mode/Why can't I pause reading? Unlike, say, TCP, TLS connections do not consist of two independent -communication channels, one for each direction. Or put differently. The +communication channels, one for each direction. Or put differently, the read and write directions are not independent of each other: you cannot write data unless you are also prepared to read, and vice versa. -This can mean than, in TLS mode, you might get C or C +This means that, in TLS mode, you might get C or C callback invocations when you are not expecting any read data - the reason is that AnyEvent::Handle always reads in TLS mode. @@ -1910,9 +2308,13 @@ my $data = delete $_[0]{rbuf}; }); +Note that this example removes the C member from the handle object, +which is not normally allowed by the API. It is expressly permitted in +this case only, as the handle object needs to be destroyed afterwards. + The reason to use C is that TCP connections, due to latencies and packets loss, might get closed quite violently with an error, when in -fact, all data has been received. +fact all data has been received. It is usually better to use acknowledgements when transferring data, to make sure the other side hasn't just died and you got the data @@ -1939,7 +2341,7 @@ =item I want to contact a TLS/SSL server, I don't care about security. If your TLS server is a pure TLS server (e.g. HTTPS) that only speaks TLS, -simply connect to it and then create the AnyEvent::Handle with the C +connect to it and then create the AnyEvent::Handle with the C parameter: tcp_connect $host, $port, sub { @@ -2049,7 +2451,7 @@ are free to use in subclasses. Of course, new versions of AnyEvent::Handle may introduce more "public" -member variables, but thats just life, at least it is documented. +member variables, but that's just life. At least it is documented. =back