From c82d1707ed3ba7de58161842d62a2b177308982a Mon Sep 17 00:00:00 2001
From: Stoiko Ivanov <s.ivanov@proxmox.com>
Date: Thu, 10 Dec 2020 15:02:49 +0100
Subject: [PATCH] accept-phase: fix conn_count "leak"

When handling new connections in 'accept_connections' the number of
active connections (conn_count) got increased before the callback, which
would eventually decrease it got registered in AnyEvent::Handle->new.

Any error/die before registering the callback would skip the
decrement, and leave the process in an endless loop upon exiting in
wait_end_loop.

This can happen e.g. when the call to getpeername fails, or if the
connection is denied by the ALLOW_FROM/DENY_FROM settings in
'/etc/default/pveproxy' (which is also a simple reproducer for that).

Additionally it can cause a denial of service, by attempting to
connect from a denied ip until the connection count exeeds the maximum
connections of all child-processes.

This patch addresses the issue by incrementing the connection count
before attempting to create the handle, and decrementing it again, if
handle creation fails.

A warning is logged if 'conn_count' turns negative when decrementing
during cleanup on error/eof. In case creating a new handle during
initial accept_connection fails, a warning is logged as well, but
'conn_count' is not decremented.

Reported via our community-forum:
https://forum.proxmox.com/threads/pveproxy-eats-available-ram.79617/

Co-Authored-by: Dominik Csapak <d.csapak@proxmox.com>
Signed-off-by: Stoiko Ivanov <s.ivanov@proxmox.com>
---
 PVE/APIServer/AnyEvent.pm | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/PVE/APIServer/AnyEvent.pm b/PVE/APIServer/AnyEvent.pm
index b8c28ce..be60f2e 100644
--- a/PVE/APIServer/AnyEvent.pm
+++ b/PVE/APIServer/AnyEvent.pm
@@ -157,6 +157,8 @@ sub client_do_disconnect {
 
     &$shutdown_hdl($hdl);
 
+    warn "connection count <= 0!\n" if $self->{conn_count} <= 0;
+
     $self->{conn_count}--;
 
     $self->dprint("CLOSE FH" .  $hdl->{fh}->fileno() . " CONN$self->{conn_count}");
@@ -1489,8 +1491,6 @@ sub accept {
 
     fh_nonblocking $clientfh, 1;
 
-    $self->{conn_count}++;
-
     return $clientfh;
 }
 
@@ -1564,6 +1564,7 @@ sub check_host_access {
 sub accept_connections {
     my ($self) = @_;
 
+    my $handle_creation;
     eval {
 
 	while (my $clientfh = $self->accept()) {
@@ -1571,7 +1572,7 @@ sub accept_connections {
 	    my $reqstate = { keep_alive => $self->{keep_alive} };
 
 	    # stop keep-alive when there are many open connections
-	    if ($self->{conn_count} >= $self->{max_conn_soft_limit}) {
+	    if ($self->{conn_count} + 1 >= $self->{max_conn_soft_limit}) {
 		$reqstate->{keep_alive} = 0;
 	    }
 
@@ -1587,6 +1588,11 @@ sub accept_connections {
 		next;
 	    }
 
+	    # Increment conn_count before creating new handle, since creation
+	    # triggers callbacks, which can potentialy decrement (e.g.
+	    # on_error) conn_count before AnyEvent::Handle->new() returns.
+	    $handle_creation = 1;
+	    $self->{conn_count}++;
 	    $reqstate->{hdl} = AnyEvent::Handle->new(
 		fh => $clientfh,
 		rbuf_max => 64*1024,
@@ -1609,6 +1615,7 @@ sub accept_connections {
 		    if (my $err = $@) { syslog('err', "$err"); }
 		},
 		($self->{tls_ctx} ? (tls => "accept", tls_ctx => $self->{tls_ctx}) : ()));
+	    $handle_creation = 0;
 
 	    $self->dprint("ACCEPT FH" .  $clientfh->fileno() . " CONN$self->{conn_count}");
 
@@ -1618,6 +1625,13 @@ sub accept_connections {
 
     if (my $err = $@) {
 	syslog('err', $err);
+	if ($handle_creation) {
+	    if ($self->{conn_count} <= 0) {
+		warn "connection count <= 0 not decrementing!\n";
+	    } else {
+		$self->{conn_count}--;
+	    }
+	}
 	$self->{end_loop} = 1;
     }
 
-- 
2.39.2