use strict;
use warnings;
-use PVE::Tools qw(run_command);
+use PVE::Tools qw(run_command lock_file);
use PVE::ProcFSTools;
use PVE::INotify;
use File::Basename;
+use IO::Socket::IP;
+use Socket qw(NI_NUMERICHOST NI_NUMERICSERV);
+use POSIX qw(ECONNREFUSED);
+
+use Net::IP;
# host network related utility functions
];
our $ipv4_mask_hash_localnet = {
+ '255.0.0.0' => 8,
+ '255.128.0.0' => 9,
+ '255.192.0.0' => 10,
+ '255.224.0.0' => 11,
+ '255.240.0.0' => 12,
+ '255.248.0.0' => 13,
+ '255.252.0.0' => 14,
+ '255.254.0.0' => 15,
'255.255.0.0' => 16,
'255.255.128.0' => 17,
'255.255.192.0' => 18,
'255.255.255.240' => 28,
'255.255.255.248' => 29,
'255.255.255.252' => 30,
+ '255.255.255.254' => 31,
+ '255.255.255.255' => 32,
};
sub setup_tc_rate_limit {
my ($iface, $rate, $burst, $debug) = @_;
- system("/sbin/tc class del dev $iface parent 1: classid 1:1 >/dev/null 2>&1");
- system("/sbin/tc filter del dev $iface parent ffff: protocol ip prio 50 estimator 1sec 8sec >/dev/null 2>&1");
- system("/sbin/tc qdisc del dev $iface ingress >/dev/null 2>&1");
- system("/sbin/tc qdisc del dev $iface root >/dev/null 2>&1");
+ # these are allowed / expected to fail, e.g. when there is no previous rate limit to remove
+ eval { run_command("/sbin/tc class del dev $iface parent 1: classid 1:1 >/dev/null 2>&1"); };
+ eval { run_command("/sbin/tc filter del dev $iface parent ffff: protocol all pref 50 u32 >/dev/null 2>&1"); };
+ eval { run_command("/sbin/tc qdisc del dev $iface ingress >/dev/null 2>&1"); };
+ eval { run_command("/sbin/tc qdisc del dev $iface root >/dev/null 2>&1"); };
return if !$rate;
- run_command("/sbin/tc qdisc add dev $iface handle ffff: ingress");
-
- # this does not work wit virtio - don't know why (setting "mtu 64kb" does not help)
- #run_command("/sbin/tc filter add dev $iface parent ffff: protocol ip prio 50 u32 match ip src 0.0.0.0/0 police rate ${rate}bps burst ${burst}b drop flowid :1");
- # so we use avrate instead
- run_command("/sbin/tc filter add dev $iface parent ffff: " .
- "protocol ip prio 50 estimator 1sec 8sec " .
- "u32 match ip src 0.0.0.0/0 police avrate ${rate}bps drop flowid :1");
-
# tbf does not work for unknown reason
#$TC qdisc add dev $DEV root tbf rate $RATE latency 100ms burst $BURST
# so we use htb instead
run_command("/sbin/tc class add dev $iface parent 1: classid 1:1 " .
"htb rate ${rate}bps burst ${burst}b");
+ run_command("/sbin/tc qdisc add dev $iface handle ffff: ingress");
+ run_command("/sbin/tc filter add dev $iface parent ffff: " .
+ "prio 50 basic " .
+ "police rate ${rate}bps burst ${burst}b mtu 64kb " .
+ "drop flowid :1");
+
if ($debug) {
print "DEBUG tc settings\n";
system("/sbin/tc qdisc ls dev $iface");
my ($iface, $rate) = @_;
my $debug = 0;
- $rate = int($rate*1024*1024);
+ $rate = int($rate*1024*1024) if $rate;
my $burst = 1024*1024;
setup_tc_rate_limit($iface, $rate, $burst, $debug);
return $mtu;
};
-my $parse_tap_devive_name = sub {
+my $parse_tap_device_name = sub {
my ($iface, $noerr) = @_;
my ($vmid, $devid);
if ($iface =~ m/^tap(\d+)i(\d+)$/) {
$vmid = $1;
$devid = $2;
- } elsif ($iface =~ m/^veth(\d+)\.(\d+)$/) {
+ } elsif ($iface =~ m/^veth(\d+)i(\d+)$/) {
$vmid = $1;
$devid = $2;
} else {
my ($bridge) = @_;
if (! -d "/sys/class/net/$bridge") {
- system("/sbin/brctl addbr $bridge") == 0 ||
- die "can't add bridge '$bridge'\n";
+ system("/sbin/brctl addbr $bridge") == 0 ||
+ die "can't add bridge '$bridge'\n";
+ disable_ipv6($bridge);
}
};
+sub disable_ipv6 {
+ my ($iface) = @_;
+ return if !-d '/proc/sys/net/ipv6'; # ipv6 might be completely disabled
+ my $file = "/proc/sys/net/ipv6/conf/$iface/disable_ipv6";
+ open(my $fh, '>', $file) or die "failed to open $file for writing: $!\n";
+ print {$fh} "1\n" or die "failed to disable link-local ipv6 for $iface\n";
+ close($fh);
+}
+
my $bridge_add_interface = sub {
- my ($bridge, $iface) = @_;
+ my ($bridge, $iface, $tag, $trunks) = @_;
+ # drop link local address (it can't be used when on a bridge anyway)
+ disable_ipv6($iface);
system("/sbin/brctl addif $bridge $iface") == 0 ||
die "can't add interface 'iface' to bridge '$bridge'\n";
+
+ my $vlan_aware = PVE::Tools::file_read_firstline("/sys/class/net/$bridge/bridge/vlan_filtering");
+
+ if ($vlan_aware) {
+ if ($tag) {
+ system({'/sbin/bridge'} 'bridge', 'vlan', 'del', 'dev', $iface, 'vid', '1-4094') == 0
+ or die "failed to remove default vlan tags of $iface\n";
+ system({'/sbin/bridge'} 'bridge', 'vlan', 'add', 'dev', $iface, 'vid', $tag, 'pvid', 'untagged') == 0
+ or die "unable to add vlan $tag to interface $iface\n";
+
+ warn "Caution: Setting VLAN ID 1 on a VLAN aware bridge may be dangerous\n" if $tag == 1;
+ } else {
+ system("/sbin/bridge vlan add dev $iface vid 2-4094") == 0 ||
+ die "unable to add default vlan tags to interface $iface\n" if !$trunks;
+ }
+
+ if ($trunks) {
+ my @trunks_array = split /;/, $trunks;
+ foreach my $trunk (@trunks_array) {
+ system("/sbin/bridge vlan add dev $iface vid $trunk") == 0 ||
+ die "unable to add vlan $trunk to interface $iface\n";
+ }
+ }
+ }
};
my $ovs_bridge_add_port = sub {
- my ($bridge, $iface, $tag, $internal) = @_;
+ my ($bridge, $iface, $tag, $internal, $trunks) = @_;
+
+ $trunks =~ s/;/,/g if $trunks;
my $cmd = "/usr/bin/ovs-vsctl add-port $bridge $iface";
$cmd .= " tag=$tag" if $tag;
+ $cmd .= " trunks=". join(',', $trunks) if $trunks;
+ $cmd .= " vlan_mode=native-untagged" if $tag && $trunks;
+
$cmd .= " -- set Interface $iface type=internal" if $internal;
system($cmd) == 0 ||
die "can't add ovs port '$iface'\n";
+ disable_ipv6($iface);
};
my $activate_interface = sub {
my $bridgemtu = &$read_bridge_mtu($bridge);
eval {
- PVE::Tools::run_command("/sbin/ifconfig $iface 0.0.0.0 promisc up mtu $bridgemtu");
+ disable_ipv6($iface);
+ PVE::Tools::run_command(['/sbin/ip', 'link', 'set', $iface, 'up', 'promisc', 'on', 'mtu', $bridgemtu]);
};
die "interface activation failed\n" if $@;
}
}
# up vethpair
+ disable_ipv6($veth);
+ disable_ipv6($vethpeer);
&$activate_interface($veth);
&$activate_interface($vethpeer);
}
if (-d "/sys/class/net/$veth") {
run_command("/sbin/ip link delete dev $veth", outfunc => sub {}, errfunc => sub {});
}
-
+ eval { tap_unplug($veth) };
}
my $create_firewall_bridge_linux = sub {
- my ($iface, $bridge) = @_;
+ my ($iface, $bridge, $tag, $trunks) = @_;
- my ($vmid, $devid) = &$parse_tap_devive_name($iface);
+ my ($vmid, $devid) = &$parse_tap_device_name($iface);
my ($fwbr, $vethfw, $vethfwpeer) = &$compute_fwbr_names($vmid, $devid);
&$cond_create_bridge($fwbr);
veth_create($vethfw, $vethfwpeer, $bridge);
&$bridge_add_interface($fwbr, $vethfw);
- &$bridge_add_interface($bridge, $vethfwpeer);
+ &$bridge_add_interface($bridge, $vethfwpeer, $tag, $trunks);
- return $fwbr;
+ &$bridge_add_interface($fwbr, $iface);
};
my $create_firewall_bridge_ovs = sub {
- my ($iface, $bridge, $tag) = @_;
+ my ($iface, $bridge, $tag, $trunks) = @_;
- my ($vmid, $devid) = &$parse_tap_devive_name($iface);
+ my ($vmid, $devid) = &$parse_tap_device_name($iface);
my ($fwbr, undef, undef, $ovsintport) = &$compute_fwbr_names($vmid, $devid);
my $bridgemtu = &$read_bridge_mtu($bridge);
&$bridge_add_interface($fwbr, $iface);
- &$ovs_bridge_add_port($bridge, $ovsintport, $tag, 1);
+ &$ovs_bridge_add_port($bridge, $ovsintport, $tag, 1, $trunks);
&$activate_interface($ovsintport);
# set the same mtu for ovs int port
- PVE::Tools::run_command("/sbin/ifconfig $ovsintport mtu $bridgemtu");
+ PVE::Tools::run_command(['/sbin/ip', 'link', 'set', $ovsintport, 'mtu', $bridgemtu]);
&$bridge_add_interface($fwbr, $ovsintport);
};
my $cleanup_firewall_bridge = sub {
my ($iface) = @_;
- my ($vmid, $devid) = &$parse_tap_devive_name($iface, 1);
+ my ($vmid, $devid) = &$parse_tap_device_name($iface, 1);
return if !defined($vmid);
my ($fwbr, $vethfw, $vethfwpeer, $ovsintport) = &$compute_fwbr_names($vmid, $devid);
};
sub tap_plug {
- my ($iface, $bridge, $tag, $firewall) = @_;
+ my ($iface, $bridge, $tag, $firewall, $trunks, $rate) = @_;
#cleanup old port config from any openvswitch bridge
eval {run_command("/usr/bin/ovs-vsctl del-port $iface", outfunc => sub {}, errfunc => sub {}) };
if (-d "/sys/class/net/$bridge/bridge") {
&$cleanup_firewall_bridge($iface); # remove stale devices
- my $newbridge = activate_bridge_vlan($bridge, $tag);
- copy_bridge_config($bridge, $newbridge) if $bridge ne $newbridge;
+ my $vlan_aware = PVE::Tools::file_read_firstline("/sys/class/net/$bridge/bridge/vlan_filtering");
- $newbridge = &$create_firewall_bridge_linux($iface, $newbridge) if $firewall;
+ if (!$vlan_aware) {
+ die "vlan aware feature need to be enabled to use trunks" if $trunks;
+ my $newbridge = activate_bridge_vlan($bridge, $tag);
+ copy_bridge_config($bridge, $newbridge) if $bridge ne $newbridge;
+ $bridge = $newbridge;
+ $tag = undef;
+ }
+
+ if ($firewall) {
+ &$create_firewall_bridge_linux($iface, $bridge, $tag, $trunks);
+ } else {
+ &$bridge_add_interface($bridge, $iface, $tag, $trunks);
+ }
- &$bridge_add_interface($newbridge, $iface);
} else {
&$cleanup_firewall_bridge($iface); # remove stale devices
if ($firewall) {
- &$create_firewall_bridge_ovs($iface, $bridge, $tag);
+ &$create_firewall_bridge_ovs($iface, $bridge, $tag, $trunks);
} else {
- &$ovs_bridge_add_port($bridge, $iface, $tag);
+ &$ovs_bridge_add_port($bridge, $iface, $tag, undef, $trunks);
}
}
+
+ tap_rate_limit($iface, $rate);
}
sub tap_unplug {
}
&$cleanup_firewall_bridge($iface);
+ #cleanup old port config from any openvswitch bridge
+ eval {run_command("/usr/bin/ovs-vsctl del-port $iface", outfunc => sub {}, errfunc => sub {}) };
}
sub copy_bridge_config {
# create vlan on $iface is not already exist
if (! -d "/sys/class/net/$ifacevlan") {
- system("/sbin/vconfig add $iface $tag") == 0 ||
+ system("/sbin/ip link add link $iface name $ifacevlan type vlan id $tag") == 0 ||
die "can't add vlan tag $tag to interface $iface\n";
+
+ # remove ipv6 link-local address before activation
+ disable_ipv6($ifacevlan);
}
# be sure to have the $ifacevlan up
my @ifaces = ();
my $dir = "/sys/class/net/$bridge/brif";
- PVE::Tools::dir_glob_foreach($dir, '((eth|bond)\d+)', sub {
+ PVE::Tools::dir_glob_foreach($dir, '(((eth|bond)\d+|en[^.]+)(\.\d+)?)', sub {
push @ifaces, $_[0];
});
die "no physical interface on bridge '$bridge'\n" if scalar(@ifaces) == 0;
- # add bridgevlan if it doesn't already exist
- if (! -d "/sys/class/net/$bridgevlan") {
- system("/sbin/brctl addbr $bridgevlan") == 0 ||
- die "can't add bridge $bridgevlan\n";
+ lock_network(sub {
+ # add bridgevlan if it doesn't already exist
+ if (! -d "/sys/class/net/$bridgevlan") {
+ system("/sbin/brctl addbr $bridgevlan") == 0 ||
+ die "can't add bridge $bridgevlan\n";
+ }
+
+ # for each physical interface (eth or bridge) bind them to bridge vlan
+ foreach my $iface (@ifaces) {
+ activate_bridge_vlan_slave($bridgevlan, $iface, $tag);
+ }
+
+ #fixme: set other bridge flags
+
+ # remove ipv6 link-local address before activation
+ disable_ipv6($bridgevlan);
+ # be sure to have the bridge up
+ &$activate_interface($bridgevlan);
+ });
+ return $bridgevlan;
+}
+
+sub tcp_ping {
+ my ($host, $port, $timeout) = @_;
+
+ my $refused = 1;
+
+ $timeout = 3 if !$timeout; # sane default
+ if (!$port) {
+ # Net::Ping defaults to the echo port
+ $port = 7;
+ } else {
+ # Net::Ping's port_number() implies service_check(1)
+ $refused = 0;
}
- # for each physical interface (eth or bridge) bind them to bridge vlan
- foreach my $iface (@ifaces) {
- activate_bridge_vlan_slave($bridgevlan, $iface, $tag);
+ my ($sock, $result);
+ eval {
+ $result = PVE::Tools::run_with_timeout($timeout, sub {
+ $sock = IO::Socket::IP->new(PeerHost => $host, PeerPort => $port, Type => SOCK_STREAM);
+ $result = $refused if $! == ECONNREFUSED;
+ });
+ };
+ if ($sock) {
+ $sock->close();
+ $result = 1;
}
+ return $result;
+}
- #fixme: set other bridge flags
+sub IP_from_cidr {
+ my ($cidr, $version) = @_;
- # be sure to have the bridge up
- system("/sbin/ip link set $bridgevlan up") == 0 ||
- die "can't up bridge $bridgevlan\n";
-
- return $bridgevlan;
+ return if $cidr !~ m!^(\S+?)/(\S+)$!;
+ my ($ip, $prefix) = ($1, $2);
+
+ my $ipobj = Net::IP->new($ip, $version);
+ return if !$ipobj;
+
+ $version = $ipobj->version();
+
+ my $binmask = Net::IP::ip_get_mask($prefix, $version);
+ return if !$binmask;
+
+ my $masked_binip = $ipobj->binip() & $binmask;
+ my $masked_ip = Net::IP::ip_bintoip($masked_binip, $version);
+ return Net::IP->new("$masked_ip/$prefix");
+}
+
+sub is_ip_in_cidr {
+ my ($ip, $cidr, $version) = @_;
+
+ my $cidr_obj = IP_from_cidr($cidr, $version);
+ return undef if !$cidr_obj;
+
+ my $ip_obj = Net::IP->new($ip, $version);
+ return undef if !$ip_obj;
+
+ return $cidr_obj->overlaps($ip_obj) == $Net::IP::IP_B_IN_A_OVERLAP;
+}
+
+
+sub get_local_ip_from_cidr {
+ my ($cidr) = @_;
+
+ my $cmd = ['/sbin/ip', 'address', 'show', 'to', $cidr, 'up'];
+
+ my $IPs = [];
+
+ my $code = sub {
+ my $line = shift;
+
+ if ($line =~ m!^\s*inet(?:6)?\s+($PVE::Tools::IPRE)/\d+!) {
+ push @$IPs, $1;
+ }
+ };
+
+ PVE::Tools::run_command($cmd, outfunc => $code);
+
+ return $IPs;
+}
+
+sub addr_to_ip {
+ my ($addr) = @_;
+ my ($err, $host, $port) = Socket::getnameinfo($addr, NI_NUMERICHOST | NI_NUMERICSERV);
+ die "failed to get numerical host address: $err\n" if $err;
+ return ($host, $port) if wantarray;
+ return $host;
+}
+
+sub get_ip_from_hostname {
+ my ($hostname, $noerr) = @_;
+
+ my ($family, $ip);
+
+ eval {
+ my @res = PVE::Tools::getaddrinfo_all($hostname);
+ $family = $res[0]->{family};
+ $ip = addr_to_ip($res[0]->{addr})
+ };
+ if ($@) {
+ die "hostname lookup failed:\n$@" if !$noerr;
+ return undef;
+ }
+
+ if ($ip =~ m/^127\.|^::1$/) {
+ die "hostname lookup failed - got local IP address ($hostname = $ip)\n" if !$noerr;
+ return undef;
+ }
+
+ return wantarray ? ($ip, $family) : $ip;
+}
+
+sub lock_network {
+ my ($code, @param) = @_;
+ my $res = lock_file('/var/lock/pve-network.lck', 10, $code, @param);
+ die $@ if $@;
+ return $res;
}
1;