[PATCH net-next 4/6] net: use core MTU range checking in core net infra

From: Jarod Wilson
Date: Tue Oct 18 2016 - 22:35:33 EST

geneve:
- Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu
- This one isn't quite as straight-forward as others, could use some
closer inspection and testing

macvlan:
- set min/max_mtu

tun:
- set min/max_mtu, remove tun_net_change_mtu

vxlan:
- Merge __vxlan_change_mtu back into vxlan_change_mtu, set min/max_mtu
- This one is also not as straight-forward and could use closer inspection
and testing from vxlan folks

bridge:
- set max_mtu via br_min_mtu()

openvswitch:
- set min/max_mtu, remove internal_dev_change_mtu
- note: max_mtu wasn't checked previously, it's been set to 65535, which
is the largest possible size supported

sch_teql:
- set min/max_mtu (note: max_mtu previously unchecked, used max of 65535)

CC: netdev@xxxxxxxxxxxxxxx
CC: Nicolas Dichtel <nicolas.dichtel@xxxxxxxxx>
CC: Hannes Frederic Sowa <hannes@xxxxxxxxxxxxxxxxxxx>
CC: Tom Herbert <tom@xxxxxxxxxxxxxxx>
CC: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
CC: Alexander Duyck <alexander.h.duyck@xxxxxxxxx>
CC: Paolo Abeni <pabeni@xxxxxxxxxx>
CC: Jiri Benc <jbenc@xxxxxxxxxx>
CC: WANG Cong <xiyou.wangcong@xxxxxxxxx>
CC: Roopa Prabhu <roopa@xxxxxxxxxxxxxxxxxxx>
CC: Pravin B Shelar <pshelar@xxxxxxx>
CC: Sabrina Dubroca <sd@xxxxxxxxxxxxxxx>
CC: Patrick McHardy <kaber@xxxxxxxxx>
CC: Stephen Hemminger <stephen@xxxxxxxxxxxxxxxxxx>
CC: Pravin Shelar <pshelar@xxxxxxxxxx>
Signed-off-by: Jarod Wilson <jarod@xxxxxxxxxx>
---
drivers/net/geneve.c | 48 +++++++++++-----------------
drivers/net/macvlan.c | 6 +++-
drivers/net/tun.c | 20 ++++--------
drivers/net/vxlan.c | 62 ++++++++++++++++++------------------
net/bridge/br_device.c | 9 +++---
net/openvswitch/vport-internal_dev.c | 10 ------
net/sched/sch_teql.c | 5 ++-
7 files changed, 67 insertions(+), 93 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 3c20e87..752bcaa 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1034,39 +1034,18 @@ static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
return geneve_xmit_skb(skb, dev, info);
}

-static int __geneve_change_mtu(struct net_device *dev, int new_mtu, bool strict)
+static int geneve_change_mtu(struct net_device *dev, int new_mtu)
{
- struct geneve_dev *geneve = netdev_priv(dev);
- /* The max_mtu calculation does not take account of GENEVE
- * options, to avoid excluding potentially valid
- * configurations.
+ /* Only possible if called internally, ndo_change_mtu path's new_mtu
+ * is guaranteed to be between dev->min_mtu and dev->max_mtu.
*/
- int max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
-
- if (geneve->remote.sa.sa_family == AF_INET6)
- max_mtu -= sizeof(struct ipv6hdr);
- else
- max_mtu -= sizeof(struct iphdr);
-
- if (new_mtu < 68)
- return -EINVAL;
-
- if (new_mtu > max_mtu) {
- if (strict)
- return -EINVAL;
-
- new_mtu = max_mtu;
- }
+ if (new_mtu > dev->max_mtu)
+ new_mtu = dev->max_mtu;

dev->mtu = new_mtu;
return 0;
}

-static int geneve_change_mtu(struct net_device *dev, int new_mtu)
-{
- return __geneve_change_mtu(dev, new_mtu, true);
-}
-
static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct ip_tunnel_info *info = skb_tunnel_info(skb);
@@ -1170,6 +1149,14 @@ static void geneve_setup(struct net_device *dev)
dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
dev->hw_features |= NETIF_F_GSO_SOFTWARE;

+ /* MTU range: 68 - (something less than 65535) */
+ dev->min_mtu = ETH_MIN_MTU;
+ /* The max_mtu calculation does not take account of GENEVE
+ * options, to avoid excluding potentially valid
+ * configurations. This will be further reduced by IPvX hdr size.
+ */
+ dev->max_mtu = IP_MAX_MTU - GENEVE_BASE_HLEN - dev->hard_header_len;
+
netif_keep_dst(dev);
dev->priv_flags &= ~IFF_TX_SKB_SHARING;
dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
@@ -1285,10 +1272,13 @@ static int geneve_configure(struct net *net, struct net_device *dev,

/* make enough headroom for basic scenario */
encap_len = GENEVE_BASE_HLEN + ETH_HLEN;
- if (remote->sa.sa_family == AF_INET)
+ if (remote->sa.sa_family == AF_INET) {
encap_len += sizeof(struct iphdr);
- else
+ dev->max_mtu -= sizeof(struct iphdr);
+ } else {
encap_len += sizeof(struct ipv6hdr);
+ dev->max_mtu -= sizeof(struct ipv6hdr);
+ }
dev->needed_headroom = encap_len + ETH_HLEN;

if (metadata) {
@@ -1488,7 +1478,7 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
/* openvswitch users expect packet sizes to be unrestricted,
* so set the largest MTU we can.
*/
- err = __geneve_change_mtu(dev, IP_MAX_MTU, false);
+ err = geneve_change_mtu(dev, IP_MAX_MTU);
if (err)
goto err;

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 3234fcd..0e0cb2d 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -777,7 +777,7 @@ static int macvlan_change_mtu(struct net_device *dev, int new_mtu)
{
struct macvlan_dev *vlan = netdev_priv(dev);

- if (new_mtu < 68 || vlan->lowerdev->mtu < new_mtu)
+ if (vlan->lowerdev->mtu < new_mtu)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
@@ -1297,6 +1297,10 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
else if (dev->mtu > lowerdev->mtu)
return -EINVAL;

+ /* MTU range: 68 - lowerdev->max_mtu */
+ dev->min_mtu = ETH_MIN_MTU;
+ dev->max_mtu = lowerdev->max_mtu;
+
if (!tb[IFLA_ADDRESS])
eth_hw_addr_random(dev);

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8093e39..9328568 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -925,18 +925,6 @@ static void tun_net_mclist(struct net_device *dev)
*/
}

-#define MIN_MTU 68
-#define MAX_MTU 65535
-
-static int
-tun_net_change_mtu(struct net_device *dev, int new_mtu)
-{
- if (new_mtu < MIN_MTU || new_mtu + dev->hard_header_len > MAX_MTU)
- return -EINVAL;
- dev->mtu = new_mtu;
- return 0;
-}
-
static netdev_features_t tun_net_fix_features(struct net_device *dev,
netdev_features_t features)
{
@@ -1014,7 +1002,6 @@ static const struct net_device_ops tun_netdev_ops = {
.ndo_open = tun_net_open,
.ndo_stop = tun_net_close,
.ndo_start_xmit = tun_net_xmit,
- .ndo_change_mtu = tun_net_change_mtu,
.ndo_fix_features = tun_net_fix_features,
.ndo_select_queue = tun_select_queue,
#ifdef CONFIG_NET_POLL_CONTROLLER
@@ -1029,7 +1016,6 @@ static const struct net_device_ops tap_netdev_ops = {
.ndo_open = tun_net_open,
.ndo_stop = tun_net_close,
.ndo_start_xmit = tun_net_xmit,
- .ndo_change_mtu = tun_net_change_mtu,
.ndo_fix_features = tun_net_fix_features,
.ndo_set_rx_mode = tun_net_mclist,
.ndo_set_mac_address = eth_mac_addr,
@@ -1062,6 +1048,9 @@ static void tun_flow_uninit(struct tun_struct *tun)
tun_flow_flush(tun);
}

+#define MIN_MTU 68
+#define MAX_MTU 65535
+
/* Initialize net device. */
static void tun_net_init(struct net_device *dev)
{
@@ -1092,6 +1081,9 @@ static void tun_net_init(struct net_device *dev)

break;
}
+
+ dev->min_mtu = MIN_MTU;
+ dev->max_mtu = MAX_MTU - dev->hard_header_len;
}

/* Character device part */
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e7d1668..98207ae 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2367,43 +2367,31 @@ static void vxlan_set_multicast_list(struct net_device *dev)
{
}

-static int __vxlan_change_mtu(struct net_device *dev,
- struct net_device *lowerdev,
- struct vxlan_rdst *dst, int new_mtu, bool strict)
+static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
{
- int max_mtu = IP_MAX_MTU;
-
- if (lowerdev)
- max_mtu = lowerdev->mtu;
+ struct vxlan_dev *vxlan = netdev_priv(dev);
+ struct vxlan_rdst *dst = &vxlan->default_dst;
+ struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
+ dst->remote_ifindex);
+ bool use_ipv6 = false;

if (dst->remote_ip.sa.sa_family == AF_INET6)
- max_mtu -= VXLAN6_HEADROOM;
- else
- max_mtu -= VXLAN_HEADROOM;
-
- if (new_mtu < 68)
- return -EINVAL;
+ use_ipv6 = true;

- if (new_mtu > max_mtu) {
- if (strict)
+ /* We re-check this, because users *could* alter the mtu of the
+ * lower device after we've initialized dev->max_mtu.
+ */
+ if (lowerdev) {
+ dev->max_mtu = lowerdev->mtu -
+ (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
+ if (new_mtu > dev->max_mtu)
return -EINVAL;
-
- new_mtu = max_mtu;
}

dev->mtu = new_mtu;
return 0;
}

-static int vxlan_change_mtu(struct net_device *dev, int new_mtu)
-{
- struct vxlan_dev *vxlan = netdev_priv(dev);
- struct vxlan_rdst *dst = &vxlan->default_dst;
- struct net_device *lowerdev = __dev_get_by_index(vxlan->net,
- dst->remote_ifindex);
- return __vxlan_change_mtu(dev, lowerdev, dst, new_mtu, true);
-}
-
static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
@@ -2795,6 +2783,10 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
vxlan_ether_setup(dev);
}

+ /* MTU range: 68 - 65535 */
+ dev->min_mtu = 68;
+ dev->max_mtu = IP_MAX_MTU;
+
vxlan->net = src_net;

dst->remote_vni = conf->vni;
@@ -2837,8 +2829,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
}
#endif

- if (!conf->mtu)
- dev->mtu = lowerdev->mtu - (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
+ if (!conf->mtu) {
+ dev->mtu = lowerdev->mtu -
+ (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
+ dev->max_mtu = dev->mtu;
+ }

needed_headroom = lowerdev->hard_header_len;
} else if (vxlan_addr_multicast(&dst->remote_ip)) {
@@ -2847,9 +2842,14 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
}

if (conf->mtu) {
- err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false);
- if (err)
- return err;
+ if (lowerdev)
+ dev->max_mtu = lowerdev->mtu;
+ dev->max_mtu -= (use_ipv6 ? VXLAN6_HEADROOM : VXLAN_HEADROOM);
+
+ dev->mtu = conf->mtu;
+
+ if (conf->mtu > dev->max_mtu)
+ dev->mtu = dev->max_mtu;
}

if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA)
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 89a687f..81fc79a 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -184,17 +184,15 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,

static int br_change_mtu(struct net_device *dev, int new_mtu)
{
+#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
struct net_bridge *br = netdev_priv(dev);
- if (new_mtu < 68 || new_mtu > br_min_mtu(br))
- return -EINVAL;
-
- dev->mtu = new_mtu;

-#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* remember the MTU in the rtable for PMTU */
dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
#endif

+ dev->mtu = new_mtu;
+
return 0;
}

@@ -390,6 +388,7 @@ void br_dev_setup(struct net_device *dev)
dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
NETIF_F_HW_VLAN_STAG_TX;
dev->vlan_features = COMMON_FEATURES;
+ dev->max_mtu = br_min_mtu(br);

br->dev = dev;
spin_lock_init(&br->lock);
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index e7da290..d5d6cae 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -89,15 +89,6 @@ static const struct ethtool_ops internal_dev_ethtool_ops = {
.get_link = ethtool_op_get_link,
};

-static int internal_dev_change_mtu(struct net_device *netdev, int new_mtu)
-{
- if (new_mtu < 68)
- return -EINVAL;
-
- netdev->mtu = new_mtu;
- return 0;
-}
-
static void internal_dev_destructor(struct net_device *dev)
{
struct vport *vport = ovs_internal_dev_get_vport(dev);
@@ -148,7 +139,6 @@ static const struct net_device_ops internal_dev_netdev_ops = {
.ndo_stop = internal_dev_stop,
.ndo_start_xmit = internal_dev_xmit,
.ndo_set_mac_address = eth_mac_addr,
- .ndo_change_mtu = internal_dev_change_mtu,
.ndo_get_stats64 = internal_get_stats,
.ndo_set_rx_headroom = internal_set_rx_headroom,
};
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index 2cd9b44..b019636 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -418,9 +418,6 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu)
struct teql_master *m = netdev_priv(dev);
struct Qdisc *q;

- if (new_mtu < 68)
- return -EINVAL;
-
q = m->slaves;
if (q) {
do {
@@ -460,6 +457,8 @@ static __init void teql_master_setup(struct net_device *dev)
dev->netdev_ops = &teql_netdev_ops;
dev->type = ARPHRD_VOID;
dev->mtu = 1500;
+ dev->min_mtu = 68;
+ dev->max_mtu = 65535;
dev->tx_queue_len = 100;
dev->flags = IFF_NOARP;
dev->hard_header_len = LL_MAX_HEADER;
--
2.10.0