X-Git-Url: http://www.git.stargrave.org/?a=blobdiff_plain;f=lib%2FPublicInbox%2FDS.pm;h=1e51dc41c1dbc46cc5d1011ef7d1b2b6ff95ba86;hb=2535900d284028258bea3bb2c1598b675f8f963c;hp=044b991c8c602abbee79a7b947ac3a21bacae50b;hpb=b70cf61f0c1f70621b88fe6420083a576d47f19f;p=public-inbox.git

diff --git a/lib/PublicInbox/DS.pm b/lib/PublicInbox/DS.pm
index 044b991c..1e51dc41 100644
--- a/lib/PublicInbox/DS.pm
+++ b/lib/PublicInbox/DS.pm
@@ -16,9 +16,9 @@
 package PublicInbox::DS;
 use strict;
 use bytes;
-use POSIX ();
+use POSIX qw(WNOHANG);
 use IO::Handle qw();
-use Fcntl qw(FD_CLOEXEC F_SETFD F_GETFD SEEK_SET);
+use Fcntl qw(SEEK_SET :DEFAULT);
 use Time::HiRes qw(clock_gettime CLOCK_MONOTONIC);
 use parent qw(Exporter);
 our @EXPORT_OK = qw(now msg_more);
@@ -28,22 +28,21 @@ use 5.010_001;
 use PublicInbox::Syscall qw(:epoll);
 
 use fields ('sock',              # underlying socket
+            'rbuf',              # scalarref, usually undef
             'wbuf',              # arrayref of coderefs or GLOB refs
             'wbuf_off',  # offset into first element of wbuf to start writing at
             );
 
-use Errno  qw(EAGAIN EINVAL);
+use Errno  qw(EAGAIN EINVAL EEXIST);
 use Carp   qw(croak confess carp);
-use File::Temp qw(tempfile);
-
-our $HAVE_KQUEUE = eval { require IO::KQueue; IO::KQueue->import; 1 };
+require File::Spec;
 
+my $nextq = []; # queue for next_tick
+my $WaitPids = [];               # list of [ pid, callback, callback_arg ]
+my $reap_timer;
 our (
-     $HaveEpoll,                 # Flag -- is epoll available?  initially undefined.
-     $HaveKQueue,
      %DescriptorMap,             # fd (num) -> PublicInbox::DS object
-     $Epoll,                     # Global epoll fd (for epoll mode only)
-     $KQueue,                    # Global kqueue fd ref (for kqueue mode only)
+     $Epoll,                     # Global epoll fd (or DSKQXS ref)
      $_io,                       # IO::Handle for Epoll
      @ToClose,                   # sockets to close when event loop is done
 
@@ -67,6 +66,8 @@ Reset all state
 =cut
 sub Reset {
     %DescriptorMap = ();
+    $WaitPids = [];
+    $reap_timer = undef;
     @ToClose = ();
     $LoopTimeout = -1;  # no timeout by default
     @Timers = ();
@@ -74,13 +75,8 @@ sub Reset {
     $PostLoopCallback = undef;
     $DoneInit = 0;
 
-    # NOTE kqueue is close-on-fork, and we don't account for it, yet
-    # OTOH, we (public-inbox) don't need this sub outside of tests...
-    POSIX::close($$KQueue) if !$_io && $KQueue && $$KQueue >= 0;
-    $KQueue = undef;
-
-    $_io = undef; # close $Epoll
-    $Epoll = undef;
+    $_io = undef; # closes real $Epoll FD
+    $Epoll = undef; # may call DSKQXS::DESTROY
 
     *EventLoop = *FirstTimeEventLoop;
 }
@@ -108,12 +104,6 @@ Returns a timer object which you can call C<< $timer->cancel >> on if you need t
 sub AddTimer {
     my ($class, $secs, $coderef) = @_;
 
-    if (!$secs) {
-        my $timer = bless([0, $coderef], 'PublicInbox::DS::Timer');
-        unshift(@Timers, $timer);
-        return $timer;
-    }
-
     my $fire_time = now() + $secs;
 
     my $timer = bless [$fire_time, $coderef], "PublicInbox::DS::Timer";
@@ -152,21 +142,19 @@ sub _InitPoller
     return if $DoneInit;
     $DoneInit = 1;
 
-    if ($HAVE_KQUEUE) {
-        $KQueue = IO::KQueue->new();
-        $HaveKQueue = defined $KQueue;
-        if ($HaveKQueue) {
-            *EventLoop = *KQueueEventLoop;
-        }
-    }
-    elsif (PublicInbox::Syscall::epoll_defined()) {
-        $Epoll = eval { epoll_create(1024); };
-        $HaveEpoll = defined $Epoll && $Epoll >= 0;
-        if ($HaveEpoll) {
-            set_cloexec($Epoll);
-            *EventLoop = *EpollEventLoop;
+    if (PublicInbox::Syscall::epoll_defined())  {
+        $Epoll = epoll_create();
+        set_cloexec($Epoll) if (defined($Epoll) && $Epoll >= 0);
+    } else {
+        my $cls;
+        for (qw(DSKQXS DSPoll)) {
+            $cls = "PublicInbox::$_";
+            last if eval "require $cls";
         }
+        $cls->import(qw(epoll_ctl epoll_wait));
+        $Epoll = $cls->new;
     }
+    *EventLoop = *EpollEventLoop;
 }
 
 =head2 C<< CLASS->EventLoop() >>
@@ -180,18 +168,28 @@ sub FirstTimeEventLoop {
 
     _InitPoller();
 
-    if ($HaveEpoll) {
-        EpollEventLoop($class);
-    } elsif ($HaveKQueue) {
-        KQueueEventLoop($class);
-    }
+    EventLoop($class);
 }
 
 sub now () { clock_gettime(CLOCK_MONOTONIC) }
 
+sub next_tick () {
+    my $q = $nextq;
+    $nextq = [];
+    for (@$q) {
+        if (ref($_) eq 'CODE') {
+            $_->();
+        } else {
+            $_->event_step;
+        }
+    }
+}
+
 # runs timers and returns milliseconds for next one, or next event loop
 sub RunTimers {
-    return $LoopTimeout unless @Timers;
+    next_tick();
+
+    return ((@$nextq || @ToClose) ? 0 : $LoopTimeout) unless @Timers;
 
     my $now = now();
 
@@ -201,6 +199,9 @@ sub RunTimers {
         $to_run->[1]->($now) if $to_run->[1];
     }
 
+    # timers may enqueue into nextq:
+    return 0 if (@$nextq || @ToClose);
+
     return $LoopTimeout unless @Timers;
 
     # convert time to an even number of milliseconds, adding 1
@@ -218,11 +219,33 @@ sub RunTimers {
     return $timeout;
 }
 
-### The epoll-based event loop. Gets installed as EventLoop if IO::Epoll loads
-### okay.
-sub EpollEventLoop {
-    my $class = shift;
+# We can't use waitpid(-1) safely here since it can hit ``, system(),
+# and other things.  So we scan the $WaitPids list, which is hopefully
+# not too big.
+sub reap_pids {
+    my $tmp = $WaitPids;
+    $WaitPids = [];
+    $reap_timer = undef;
+    foreach my $ary (@$tmp) {
+        my ($pid, $cb, $arg) = @$ary;
+        my $ret = waitpid($pid, WNOHANG);
+        if ($ret == 0) {
+            push @$WaitPids, $ary;
+        } elsif ($cb) {
+            eval { $cb->($arg, $pid) };
+        }
+    }
+    if (@$WaitPids) {
+        # we may not be donea, and we may miss our
+        $reap_timer = AddTimer(undef, 1, \&reap_pids);
+    }
+}
+
+# reentrant SIGCHLD handler (since reap_pids is not reentrant)
+sub enqueue_reap ($) { push @$nextq, \&reap_pids };
 
+sub EpollEventLoop {
+    local $SIG{CHLD} = \&enqueue_reap;
     while (1) {
         my @events;
         my $i;
@@ -241,30 +264,6 @@ sub EpollEventLoop {
     }
 }
 
-### The kqueue-based event loop. Gets installed as EventLoop if IO::KQueue works
-### okay.
-sub KQueueEventLoop {
-    my $class = shift;
-
-    while (1) {
-        my $timeout = RunTimers();
-        my @ret = eval { $KQueue->kevent($timeout) };
-        if (my $err = $@) {
-            # workaround https://rt.cpan.org/Ticket/Display.html?id=116615
-            if ($err =~ /Interrupted system call/) {
-                @ret = ();
-            } else {
-                die $err;
-            }
-        }
-
-        foreach my $kev (@ret) {
-            $DescriptorMap{$kev->[0]}->event_step;
-        }
-        return unless PostEventLoop();
-    }
-}
-
 =head2 C<< CLASS->SetPostLoopCallback( CODEREF ) >>
 
 Sets post loop callback function.  Pass a subref and it will be
@@ -290,17 +289,8 @@ sub PostEventLoop {
     # now we can close sockets that wanted to close during our event processing.
     # (we didn't want to close them during the loop, as we didn't want fd numbers
     #  being reused and confused during the event loop)
-    while (my $sock = shift @ToClose) {
-        my $fd = fileno($sock);
-
-        # close the socket.  (not a PublicInbox::DS close)
-        $sock->close;
-
-        # and now we can finally remove the fd from the map.  see
-        # comment above in ->close.
-        delete $DescriptorMap{$fd};
-    }
-
+    delete($DescriptorMap{fileno($_)}) for @ToClose;
+    @ToClose = (); # let refcounting drop everything all at once
 
     # by default we keep running, unless a postloop callback (either per-object
     # or global) cancels it
@@ -314,17 +304,6 @@ sub PostEventLoop {
     return $keep_running;
 }
 
-# map EPOLL* bits to kqueue EV_* flags for EV_SET
-sub kq_flag ($$) {
-    my ($bit, $ev) = @_;
-    if ($ev & $bit) {
-        my $fl = EV_ADD() | EV_ENABLE();
-        ($ev & EPOLLONESHOT) ? ($fl|EV_ONESHOT()) : $fl;
-    } else {
-        EV_DISABLE();
-    }
-}
-
 #####################################################################
 ### PublicInbox::DS-the-object code
 #####################################################################
@@ -353,21 +332,13 @@ sub new {
 
     _InitPoller();
 
-    if ($HaveEpoll) {
-retry:
-        if (epoll_ctl($Epoll, EPOLL_CTL_ADD, $fd, $ev)) {
-            if ($! == EINVAL && ($ev & EPOLLEXCLUSIVE)) {
-                $ev &= ~EPOLLEXCLUSIVE;
-                goto retry;
-            }
-            die "couldn't add epoll watch for $fd: $!\n";
+    if (epoll_ctl($Epoll, EPOLL_CTL_ADD, $fd, $ev)) {
+        if ($! == EINVAL && ($ev & EPOLLEXCLUSIVE)) {
+            $ev &= ~EPOLLEXCLUSIVE;
+            goto retry;
         }
+        die "couldn't add epoll watch for $fd: $!\n";
     }
-    elsif ($HaveKQueue) {
-        $KQueue->EV_SET($fd, EVFILT_READ(), EV_ADD() | kq_flag(EPOLLIN, $ev));
-        $KQueue->EV_SET($fd, EVFILT_WRITE(), EV_ADD() | kq_flag(EPOLLOUT, $ev));
-    }
-
     Carp::cluck("PublicInbox::DS::new blowing away existing descriptor map for fd=$fd ($DescriptorMap{$fd})")
         if $DescriptorMap{$fd};
 
@@ -380,6 +351,8 @@ retry:
 ### I N S T A N C E   M E T H O D S
 #####################################################################
 
+sub requeue ($) { push @$nextq, $_[0] }
+
 =head2 C<< $obj->close >>
 
 Close the socket.
@@ -396,11 +369,9 @@ sub close {
 
     # if we're using epoll, we have to remove this from our epoll fd so we stop getting
     # notifications about it
-    if ($HaveEpoll) {
-        my $fd = fileno($sock);
-        epoll_ctl($Epoll, EPOLL_CTL_DEL, $fd, 0) and
-            confess("EPOLL_CTL_DEL: $!");
-    }
+    my $fd = fileno($sock);
+    epoll_ctl($Epoll, EPOLL_CTL_DEL, $fd, 0) and
+        confess("EPOLL_CTL_DEL: $!");
 
     # we explicitly don't delete from DescriptorMap here until we
     # actually close the socket, as we might be in the middle of
@@ -438,17 +409,21 @@ sub psendfile ($$$) {
     $written;
 }
 
+sub epbit ($$) { # (sock, default)
+    ref($_[0]) eq 'IO::Socket::SSL' ? PublicInbox::TLS::epollbit() : $_[1];
+}
+
 # returns 1 if done, 0 if incomplete
 sub flush_write ($) {
     my ($self) = @_;
     my $wbuf = $self->{wbuf} or return 1;
-    my $sock = $self->{sock} or return 1;
+    my $sock = $self->{sock};
 
 next_buf:
     while (my $bref = $wbuf->[0]) {
         if (ref($bref) ne 'CODE') {
             my $off = delete($self->{wbuf_off}) // 0;
-            while (1) {
+            while ($sock) {
                 my $w = psendfile($sock, $bref, \$off);
                 if (defined $w) {
                     if ($w == 0) {
@@ -456,8 +431,8 @@ next_buf:
                         goto next_buf;
                     }
                 } elsif ($! == EAGAIN) {
+                    epwait($sock, epbit($sock, EPOLLOUT) | EPOLLONESHOT);
                     $self->{wbuf_off} = $off;
-                    watch($self, EPOLLOUT|EPOLLONESHOT);
                     return 0;
                 } else {
                     return $self->close;
@@ -477,17 +452,25 @@ next_buf:
     1; # all done
 }
 
-sub do_read ($$$$) {
+sub rbuf_idle ($$) {
+    my ($self, $rbuf) = @_;
+    if ($$rbuf eq '') { # who knows how long till we can read again
+        delete $self->{rbuf};
+    } else {
+        $self->{rbuf} = $rbuf;
+    }
+}
+
+sub do_read ($$$;$) {
     my ($self, $rbuf, $len, $off) = @_;
-    my $r = sysread($self->{sock}, $$rbuf, $len, $off);
+    my $r = sysread(my $sock = $self->{sock}, $$rbuf, $len, $off // 0);
     return ($r == 0 ? $self->close : $r) if defined $r;
     # common for clients to break connections without warning,
     # would be too noisy to log here:
-    if (ref($self) eq 'IO::Socket::SSL') {
-        my $ev = PublicInbox::TLS::epollbit() or return $self->close;
-        watch($self, $ev | EPOLLONESHOT);
-    } elsif ($! == EAGAIN) {
-        watch($self, EPOLLIN | EPOLLONESHOT);
+    if ($! == EAGAIN) {
+        epwait($sock, epbit($sock, EPOLLIN) | EPOLLONESHOT);
+        rbuf_idle($self, $rbuf);
+        0;
     } else {
         $self->close;
     }
@@ -505,12 +488,16 @@ sub drop {
 # PerlIO::mmap or PerlIO::scalar if needed
 sub tmpio ($$$) {
     my ($self, $bref, $off) = @_;
-    # open(my $fh, '+>>', undef) doesn't set O_APPEND
-    my ($fh, $path) = eval { tempfile('wbuf-XXXXXXX', TMPDIR => 1) };
-    $fh or return drop($self, "tempfile: $@");
-    open($fh, '+>>', $path) or return drop($self, "open: $!");
+    my $fh; # open(my $fh, '+>>', undef) doesn't set O_APPEND
+    do {
+        my $fn = File::Spec->tmpdir . '/wbuf-' . rand;
+        if (sysopen($fh, $fn, O_RDWR|O_CREAT|O_EXCL|O_APPEND, 0600)) { # likely
+            unlink($fn) or return drop($self, "unlink($fn) $!");
+        } elsif ($! != EEXIST) { # EMFILE/ENFILE/ENOSPC/ENOMEM
+            return drop($self, "open: $!");
+        }
+    } until (defined $fh);
     $fh->autoflush(1);
-    unlink($path) or return drop($self, "unlink: $!");
     my $len = bytes::length($$bref) - $off;
     $fh->write($$bref, $len, $off) or return drop($self, "write ($len): $!");
     $fh
@@ -537,7 +524,8 @@ sub write {
     my $sock = $self->{sock} or return 1;
     my $ref = ref $data;
     my $bref = $ref ? $data : \$data;
-    if (my $wbuf = $self->{wbuf}) { # already buffering, can't write more...
+    my $wbuf = $self->{wbuf};
+    if ($wbuf && scalar(@$wbuf)) { # already buffering, can't write more...
         if ($ref eq 'CODE') {
             push @$wbuf, $bref;
         } else {
@@ -559,14 +547,20 @@ sub write {
 
         if (defined $written) {
             return 1 if $written == $to_write;
+            requeue($self); # runs: event_step -> flush_write
         } elsif ($! == EAGAIN) {
+            epwait($sock, epbit($sock, EPOLLOUT) | EPOLLONESHOT);
             $written = 0;
         } else {
             return $self->close;
         }
+
+        # deal with EAGAIN or partial write:
         my $tmpio = tmpio($self, $bref, $written) or return 0;
-        $self->{wbuf} = [ $tmpio ];
-        watch($self, EPOLLOUT|EPOLLONESHOT);
+
+        # wbuf may be an empty array if we're being called inside
+        # ->flush_write via CODE bref:
+        push @{$self->{wbuf} ||= []}, $tmpio;
         return 0;
     }
 }
@@ -585,28 +579,20 @@ sub msg_more ($$) {
             # queue up the unwritten substring:
             my $tmpio = tmpio($self, \($_[1]), $n) or return 0;
             $self->{wbuf} = [ $tmpio ];
-            watch($self, EPOLLOUT|EPOLLONESHOT);
+            epwait($sock, EPOLLOUT|EPOLLONESHOT);
             return 0;
         }
     }
-    $self->write(\($_[1]));
-}
 
-sub watch ($$) {
-    my ($self, $ev) = @_;
-    my $sock = $self->{sock} or return;
-    my $fd = fileno($sock);
-    if ($HaveEpoll) {
-        epoll_ctl($Epoll, EPOLL_CTL_MOD, $fd, $ev) and
-            confess("EPOLL_CTL_MOD $!");
-    } elsif ($HaveKQueue) {
-        $KQueue->EV_SET($fd, EVFILT_READ(), kq_flag(EPOLLIN, $ev));
-        $KQueue->EV_SET($fd, EVFILT_WRITE(), kq_flag(EPOLLOUT, $ev));
-    }
-    0;
+    # don't redispatch into NNTPdeflate::write
+    PublicInbox::DS::write($self, \($_[1]));
 }
 
-sub watch_in1 ($) { watch($_[0], EPOLLIN | EPOLLONESHOT) }
+sub epwait ($$) {
+    my ($sock, $ev) = @_;
+    epoll_ctl($Epoll, EPOLL_CTL_MOD, fileno($sock), $ev) and
+        confess("EPOLL_CTL_MOD $!");
+}
 
 # return true if complete, false if incomplete (or failure)
 sub accept_tls_step ($) {
@@ -614,11 +600,46 @@ sub accept_tls_step ($) {
     my $sock = $self->{sock} or return;
     return 1 if $sock->accept_SSL;
     return $self->close if $! != EAGAIN;
-    if (my $ev = PublicInbox::TLS::epollbit()) {
-        unshift @{$self->{wbuf} ||= []}, \&accept_tls_step;
-        return watch($self, $ev | EPOLLONESHOT);
+    epwait($sock, PublicInbox::TLS::epollbit() | EPOLLONESHOT);
+    unshift @{$self->{wbuf} ||= []}, \&accept_tls_step;
+    0;
+}
+
+# return true if complete, false if incomplete (or failure)
+sub shutdn_tls_step ($) {
+    my ($self) = @_;
+    my $sock = $self->{sock} or return;
+    return $self->close if $sock->stop_SSL(SSL_fast_shutdown => 1);
+    return $self->close if $! != EAGAIN;
+    epwait($sock, PublicInbox::TLS::epollbit() | EPOLLONESHOT);
+    unshift @{$self->{wbuf} ||= []}, \&shutdn_tls_step;
+    0;
+}
+
+# don't bother with shutdown($sock, 2), we don't fork+exec w/o CLOEXEC
+# or fork w/o exec, so no inadvertant socket sharing
+sub shutdn ($) {
+    my ($self) = @_;
+    my $sock = $self->{sock} or return;
+    if (ref($sock) eq 'IO::Socket::SSL') {
+        shutdn_tls_step($self);
+    } else {
+	$self->close;
+    }
+}
+
+# must be called with eval, PublicInbox::DS may not be loaded (see t/qspawn.t)
+sub dwaitpid ($$$) {
+    my ($pid, $cb, $arg) = @_;
+    my $chld = $SIG{CHLD};
+    if (defined($chld) && $chld eq \&enqueue_reap) {
+        push @$WaitPids, [ $pid, $cb, $arg ];
+
+        # We could've just missed our SIGCHLD, cover it, here:
+        requeue(\&reap_pids);
+    } else {
+        die "Not in EventLoop\n";
     }
-    drop($self, 'BUG? EAGAIN but '.PublicInbox::TLS::err());
 }
 
 package PublicInbox::DS::Timer;