* [PATCH net-next v2 3/4] ipip: add x-netns support
From: Nicolas Dichtel @ 2013-08-13 15:51 UTC (permalink / raw)
To: netdev
Cc: davem, ebiederm, bcrl, ravi.mlists, bhutchings, eric.dumazet,
Nicolas Dichtel
In-Reply-To: <1376409072-6414-1-git-send-email-nicolas.dichtel@6wind.com>
This patch allows to switch the netns when packet is encapsulated or
decapsulated. In other word, the encapsulated packet is received in a netns,
where the lookup is done to find the tunnel. Once the tunnel is found, the
packet is decapsulated and injecting into the corresponding interface which
stands to another netns.
When one of the two netns is removed, the tunnel is destroyed.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/net/ip_tunnels.h | 2 +-
net/ipv4/ip_gre.c | 4 ++--
net/ipv4/ip_tunnel.c | 43 ++++++++++++++++++++++++++++---------------
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipip.c | 3 +--
5 files changed, 33 insertions(+), 21 deletions(-)
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index c6acd9f8f877..5a76f2bef822 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -102,7 +102,7 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head);
int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
struct rtnl_link_ops *ops, char *devname);
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn);
+void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops);
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
const struct iphdr *tnl_params, const u8 protocol);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 1f6eab66f7ce..bc3a76521deb 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -534,7 +534,7 @@ static int __net_init ipgre_init_net(struct net *net)
static void __net_exit ipgre_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipgre_link_ops);
}
static struct pernet_operations ipgre_net_ops = {
@@ -767,7 +767,7 @@ static int __net_init ipgre_tap_init_net(struct net *net)
static void __net_exit ipgre_tap_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipgre_tap_ops);
}
static struct pernet_operations ipgre_tap_net_ops = {
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index a351a003ee6b..a4d9126c7b51 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -350,7 +350,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
struct flowi4 fl4;
struct rtable *rt;
- rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+ rt = ip_route_output_tunnel(tunnel->net, &fl4,
tunnel->parms.iph.protocol,
iph->daddr, iph->saddr,
tunnel->parms.o_key,
@@ -365,7 +365,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
}
if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+ tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
@@ -654,7 +654,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
}
- err = iptunnel_xmit(dev_net(dev), rt, skb,
+ err = iptunnel_xmit(tunnel->net, rt, skb,
fl4.saddr, fl4.daddr, protocol,
ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
@@ -821,11 +821,10 @@ static void ip_tunnel_dev_free(struct net_device *dev)
void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
{
- struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn;
- itn = net_generic(net, tunnel->ip_tnl_net_id);
+ itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);
if (itn->fb_tunnel_dev != dev) {
ip_tunnel_del(netdev_priv(dev));
@@ -855,6 +854,10 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
rtnl_lock();
itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
+ /* FB netdevice is special: we have one, and only one per netns.
+ * Allowing to move it to another netns is clearly unsafe.
+ */
+ itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
rtnl_unlock();
if (IS_ERR(itn->fb_tunnel_dev))
@@ -864,28 +867,39 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
}
EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
-static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head)
+static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
+ struct rtnl_link_ops *ops)
{
+ struct net *net = dev_net(itn->fb_tunnel_dev);
+ struct net_device *dev, *aux;
int h;
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == ops)
+ unregister_netdevice_queue(dev, head);
+
for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
struct ip_tunnel *t;
struct hlist_node *n;
struct hlist_head *thead = &itn->tunnels[h];
hlist_for_each_entry_safe(t, n, thead, hash_node)
- unregister_netdevice_queue(t->dev, head);
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(t->dev), net))
+ unregister_netdevice_queue(t->dev, head);
}
if (itn->fb_tunnel_dev)
unregister_netdevice_queue(itn->fb_tunnel_dev, head);
}
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn)
+void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
{
LIST_HEAD(list);
rtnl_lock();
- ip_tunnel_destroy(itn, &list);
+ ip_tunnel_destroy(itn, &list, ops);
unregister_netdevice_many(&list);
rtnl_unlock();
}
@@ -929,23 +943,21 @@ EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p)
{
- struct ip_tunnel *t, *nt;
- struct net *net = dev_net(dev);
+ struct ip_tunnel *t;
struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct net *net = tunnel->net;
struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
if (dev == itn->fb_tunnel_dev)
return -EINVAL;
- nt = netdev_priv(dev);
-
t = ip_tunnel_find(itn, p, dev->type);
if (t) {
if (t->dev != dev)
return -EEXIST;
} else {
- t = nt;
+ t = tunnel;
if (dev->type != ARPHRD_ETHER) {
unsigned int nflags = 0;
@@ -984,6 +996,7 @@ int ip_tunnel_init(struct net_device *dev)
}
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
iph->ihl = 5;
@@ -994,8 +1007,8 @@ EXPORT_SYMBOL_GPL(ip_tunnel_init);
void ip_tunnel_uninit(struct net_device *dev)
{
- struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct net *net = tunnel->net;
struct ip_tunnel_net *itn;
itn = net_generic(net, tunnel->ip_tnl_net_id);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 79b263da4168..e805e7b3030e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -318,7 +318,7 @@ static int __net_init vti_init_net(struct net *net)
static void __net_exit vti_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &vti_link_ops);
}
static struct pernet_operations vti_net_ops = {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 51fc2a1dcdd3..87bd2952c733 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -286,7 +286,6 @@ static void ipip_tunnel_setup(struct net_device *dev)
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_LLTX;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
@@ -437,7 +436,7 @@ static int __net_init ipip_init_net(struct net *net)
static void __net_exit ipip_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipip_link_ops);
}
static struct pernet_operations ipip_net_ops = {
--
1.8.2.1
^ permalink raw reply related
* [PATCH net-next v2 2/4] ipv4 tunnels: use net_eq() helper to check netns
From: Nicolas Dichtel @ 2013-08-13 15:51 UTC (permalink / raw)
To: netdev
Cc: davem, ebiederm, bcrl, ravi.mlists, bhutchings, eric.dumazet,
Nicolas Dichtel
In-Reply-To: <1376409072-6414-1-git-send-email-nicolas.dichtel@6wind.com>
It's better to use available helpers for these tests.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/ipv4/ip_tunnel.c | 4 ++--
net/ipv6/sit.c | 6 +++---
2 files changed, 5 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index fbc1094964bf..a351a003ee6b 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -461,7 +461,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
skb->dev = tunnel->dev;
}
- if (tunnel->net != dev_net(tunnel->dev))
+ if (!net_eq(tunnel->net, dev_net(tunnel->dev)))
skb_scrub_packet(skb);
gro_cells_receive(&tunnel->gro_cells, skb);
@@ -614,7 +614,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
- if (tunnel->net != dev_net(dev))
+ if (!net_eq(tunnel->net, dev_net(dev)))
skb_scrub_packet(skb);
if (tunnel->err_count > 0) {
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index a3437a4cd07e..f18f842ac893 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -621,7 +621,7 @@ static int ipip6_rcv(struct sk_buff *skb)
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
- if (tunnel->net != dev_net(tunnel->dev))
+ if (!net_eq(tunnel->net, dev_net(tunnel->dev)))
skb_scrub_packet(skb);
netif_rx(skb);
@@ -860,7 +860,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
tunnel->err_count = 0;
}
- if (tunnel->net != dev_net(dev))
+ if (!net_eq(tunnel->net, dev_net(dev)))
skb_scrub_packet(skb);
/*
@@ -1589,7 +1589,7 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
- if (dev_net(t->dev) != net)
+ if (!net_eq(dev_net(t->dev), net))
unregister_netdevice_queue(t->dev,
head);
t = rtnl_dereference(t->next);
--
1.8.2.1
^ permalink raw reply related
* [PATCH net-next v2 4/4] ip6tnl: add x-netns support
From: Nicolas Dichtel @ 2013-08-13 15:51 UTC (permalink / raw)
To: netdev
Cc: davem, ebiederm, bcrl, ravi.mlists, bhutchings, eric.dumazet,
Nicolas Dichtel
In-Reply-To: <1376409072-6414-1-git-send-email-nicolas.dichtel@6wind.com>
This patch allows to switch the netns when packet is encapsulated or
decapsulated. In other word, the encapsulated packet is received in a netns,
where the lookup is done to find the tunnel. Once the tunnel is found, the
packet is decapsulated and injecting into the corresponding interface which
stands to another netns.
When one of the two netns is removed, the tunnel is destroyed.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/net/ip6_tunnel.h | 1 +
net/ipv6/ip6_gre.c | 5 +++++
net/ipv6/ip6_tunnel.c | 41 +++++++++++++++++++++++++++++++----------
3 files changed, 37 insertions(+), 10 deletions(-)
diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 4da5de10d1d4..2265b0bf97e5 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -36,6 +36,7 @@ struct __ip6_tnl_parm {
struct ip6_tnl {
struct ip6_tnl __rcu *next; /* next tunnel in list */
struct net_device *dev; /* virtual device associated with tunnel */
+ struct net *net; /* netns for packet i/o */
struct __ip6_tnl_parm parms; /* tunnel configuration parameters */
struct flowi fl; /* flowi template for xmit */
struct dst_entry *dst_cache; /* cached dst */
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index ecd60733e5e2..f2d0a42f8057 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -335,6 +335,7 @@ static struct ip6_tnl *ip6gre_tunnel_locate(struct net *net,
dev->rtnl_link_ops = &ip6gre_link_ops;
nt->dev = dev;
+ nt->net = dev_net(dev);
ip6gre_tnl_link_config(nt, 1);
if (register_netdevice(dev) < 0)
@@ -1255,6 +1256,7 @@ static int ip6gre_tunnel_init(struct net_device *dev)
tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
memcpy(dev->dev_addr, &tunnel->parms.laddr, sizeof(struct in6_addr));
@@ -1275,6 +1277,7 @@ static void ip6gre_fb_tunnel_init(struct net_device *dev)
struct ip6_tnl *tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
tunnel->hlen = sizeof(struct ipv6hdr) + 4;
@@ -1450,6 +1453,7 @@ static int ip6gre_tap_init(struct net_device *dev)
tunnel = netdev_priv(dev);
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
ip6gre_tnl_link_config(tunnel, 1);
@@ -1501,6 +1505,7 @@ static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
eth_hw_addr_random(dev);
nt->dev = dev;
+ nt->net = dev_net(dev);
ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
/* Can use a lockless transmit, unless we generate output sequences */
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 1e55866cead7..cc3bb201b8b0 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -315,6 +315,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
t = netdev_priv(dev);
t->parms = *p;
+ t->net = dev_net(dev);
err = ip6_tnl_create2(dev);
if (err < 0)
goto failed_free;
@@ -374,7 +375,7 @@ static void
ip6_tnl_dev_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
@@ -741,7 +742,7 @@ int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
if ((p->flags & IP6_TNL_F_CAP_RCV) ||
((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
@@ -827,6 +828,9 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
+ if (!net_eq(t->net, dev_net(t->dev)))
+ skb_scrub_packet(skb);
+
netif_rx(skb);
rcu_read_unlock();
@@ -895,7 +899,7 @@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t)
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
if (p->flags & IP6_TNL_F_CAP_XMIT) {
struct net_device *ldev = NULL;
@@ -945,8 +949,8 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
int encap_limit,
__u32 *pmtu)
{
- struct net *net = dev_net(dev);
struct ip6_tnl *t = netdev_priv(dev);
+ struct net *net = t->net;
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct ipv6_tel_txoption opt;
@@ -996,6 +1000,9 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
goto tx_err_dst_release;
}
+ if (!net_eq(t->net, dev_net(dev)))
+ skb_scrub_packet(skb);
+
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
@@ -1202,7 +1209,7 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
- struct rt6_info *rt = rt6_lookup(dev_net(dev),
+ struct rt6_info *rt = rt6_lookup(t->net,
&p->raddr, &p->laddr,
p->link, strict);
@@ -1251,7 +1258,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
{
- struct net *net = dev_net(t->dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
@@ -1463,7 +1470,6 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
dev->mtu-=8;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
}
@@ -1479,6 +1485,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
struct ip6_tnl *t = netdev_priv(dev);
t->dev = dev;
+ t->net = dev_net(dev);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
@@ -1596,9 +1603,9 @@ static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[])
{
- struct ip6_tnl *t;
+ struct ip6_tnl *t = netdev_priv(dev);
struct __ip6_tnl_parm p;
- struct net *net = dev_net(dev);
+ struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
@@ -1699,14 +1706,24 @@ static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
{
+ struct net *net = dev_net(ip6n->fb_tnl_dev);
+ struct net_device *dev, *aux;
int h;
struct ip6_tnl *t;
LIST_HEAD(list);
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == &ip6_link_ops)
+ unregister_netdevice_queue(dev, &list);
+
for (h = 0; h < HASH_SIZE; h++) {
t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t != NULL) {
- unregister_netdevice_queue(t->dev, &list);
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(t->dev), net))
+ unregister_netdevice_queue(t->dev, &list);
t = rtnl_dereference(t->next);
}
}
@@ -1732,6 +1749,10 @@ static int __net_init ip6_tnl_init_net(struct net *net)
if (!ip6n->fb_tnl_dev)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
+ /* FB netdevice is special: we have one, and only one per netns.
+ * Allowing to move it to another netns is clearly unsafe.
+ */
+ ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
--
1.8.2.1
^ permalink raw reply related
* [PATCH net-next v2 1/4] dev: move skb_scrub_packet() after eth_type_trans()
From: Nicolas Dichtel @ 2013-08-13 15:51 UTC (permalink / raw)
To: netdev
Cc: davem, ebiederm, bcrl, ravi.mlists, bhutchings, eric.dumazet,
Nicolas Dichtel
In-Reply-To: <1376409072-6414-1-git-send-email-nicolas.dichtel@6wind.com>
skb_scrub_packet() was called before eth_type_trans() to let eth_type_trans()
set pkt_type.
In fact, we should force pkt_type to PACKET_HOST, so move the call after
eth_type_trans().
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
net/core/dev.c | 6 +++---
net/ipv4/ip_tunnel.c | 7 ++++---
2 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 58eb802584b9..1ed2b66a10a6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1691,13 +1691,13 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
kfree_skb(skb);
return NET_RX_DROP;
}
- skb_scrub_packet(skb);
skb->protocol = eth_type_trans(skb, dev);
/* eth_type_trans() can set pkt_type.
- * clear pkt_type _after_ calling eth_type_trans()
+ * call skb_scrub_packet() after it to clear pkt_type _after_ calling
+ * eth_type_trans().
*/
- skb->pkt_type = PACKET_HOST;
+ skb_scrub_packet(skb);
return netif_rx(skb);
}
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 9fdf8a6d95f3..fbc1094964bf 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -454,15 +454,16 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- if (tunnel->net != dev_net(tunnel->dev))
- skb_scrub_packet(skb);
-
if (tunnel->dev->type == ARPHRD_ETHER) {
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
} else {
skb->dev = tunnel->dev;
}
+
+ if (tunnel->net != dev_net(tunnel->dev))
+ skb_scrub_packet(skb);
+
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
--
1.8.2.1
^ permalink raw reply related
* [PATCH net-next v2 0/4] ipip/ip6tnl: allow to switch netns during encap/decap
From: Nicolas Dichtel @ 2013-08-13 15:51 UTC (permalink / raw)
To: netdev; +Cc: davem, ebiederm, bcrl, ravi.mlists, bhutchings, eric.dumazet
In-Reply-To: <20130704.145621.2060744817757546493.davem@davemloft.net>
This serie is a follow up of the previous serie witch adds this functionality
for sit tunnels.
The goal is to add x-netns support for the module ipip and ip6_tunnel, ie the
encapsulation addresses and the network device are not owned by the same
namespace.
Note that the two first patches are cleanup.
Example to configure an ipip tunnel:
modprobe ipip
ip netns add netns1
ip link add ipip1 type ipip remote 10.16.0.121 local 10.16.0.249
ip l s ipip1 netns netns1
ip netns exec netns1 ip l s lo up
ip netns exec netns1 ip l s ipip1 up
ip netns exec netns1 ip a a dev ipip1 192.168.2.123 remote 192.168.2.121
or an ip6_tunnel:
modprobe ip6_tunnel
ip netns add netns1
ip link add ip6tnl1 type ip6tnl remote 2001:660:3008:c1c3::121 local 2001:660:3008:c1c3::123
ip l s ip6tnl1 netns netns1
ip netns exec netns1 ip l s lo up
ip netns exec netns1 ip l s ip6tnl1 up
ip netns exec netns1 ip a a dev ip6tnl1 192.168.1.123 remote 192.168.1.121
ip netns exec netns1 ip -6 a a dev ip6tnl1 2001:1235::123 remote 2001:1235::121
v2: remove the patch 1/3 of the v1 serie (already included)
use net_eq()
add patch 1/4 and 2/4
include/net/ip6_tunnel.h | 1 +
include/net/ip_tunnels.h | 2 +-
net/core/dev.c | 6 +++---
net/ipv4/ip_gre.c | 4 ++--
net/ipv4/ip_tunnel.c | 52 ++++++++++++++++++++++++++++++------------------
net/ipv4/ip_vti.c | 2 +-
net/ipv4/ipip.c | 3 +--
net/ipv6/ip6_gre.c | 5 +++++
net/ipv6/ip6_tunnel.c | 41 ++++++++++++++++++++++++++++----------
net/ipv6/sit.c | 6 +++---
10 files changed, 81 insertions(+), 41 deletions(-)
Comments are welcome.
Regards,
Nicolas
^ permalink raw reply
* question about drivers/net/ethernet/sgi
From: Julia Lawall @ 2013-08-13 15:43 UTC (permalink / raw)
To: ralf, linux-mips, netdev
The files in drivers/net/ethernet/sgi (meth.c and ioc3-eth.c) both use
alloc_skb. Is there a reason why they do not use netdev_alloc_skb, like
most other ethernet drivers?
thanks,
julia
^ permalink raw reply
* Re: [PATCH net-next 1/3] net/usb/r8152: support aggregation
From: Oliver Neukum @ 2013-08-13 15:17 UTC (permalink / raw)
To: hayeswang; +Cc: netdev, linux-kernel, linux-usb
In-Reply-To: <9E410853D1BD483E9479C175D5E72EB6@realtek.com.tw>
On Tue, 2013-08-13 at 20:32 +0800, hayeswang wrote:
> Oliver Neukum [mailto:oneukum@suse.de]
> > Sent: Tuesday, August 13, 2013 4:49 PM
> > To: Hayeswang
> > Cc: netdev@vger.kernel.org; linux-kernel@vger.kernel.org;
> > linux-usb@vger.kernel.org
> > Subject: Re: [PATCH net-next 1/3] net/usb/r8152: support aggregation
> >
> [...]
> > > + len_used = 0;
> > > + rx_desc = agg->head;
> > > + rx_data = agg->head;
> > > + smp_wmb();
> > > + pkt_len = le32_to_cpu(rx_desc->opts1) & RX_LEN_MASK;
> > > + len_used += sizeof(struct rx_desc) + pkt_len;
> > > +
> > > + while (urb->actual_length >= len_used) {
> > > + if (pkt_len < ETH_ZLEN)
> > > + break;
> > > +
> > > + pkt_len -= 4; /* CRC */
> > > + rx_data += sizeof(struct rx_desc);
> > > +
> > > + skb = netdev_alloc_skb_ip_align(netdev,
> > > pkt_len);
> > > + if (!skb) {
> > > + stats->rx_dropped++;
> > > + break;
> > > + }
> > > + memcpy(skb->data, rx_data, pkt_len);
> > > + skb_put(skb, pkt_len);
> > > + skb->protocol = eth_type_trans(skb, netdev);
> > > + netif_rx(skb);
> > > + stats->rx_packets++;
> > > + stats->rx_bytes += pkt_len;
> > > +
> > > + rx_data = rx_agg_align(rx_data +
> > pkt_len + 4);
> > > + rx_desc = (struct rx_desc *)rx_data;
> > > + smp_wmb();
> >
> > Against what is the memory barrier?
>
> Excuse me. I don't understand your question. Do you mean the function should not
> be used here?
I don't understand what problem the function is supposed to fix. As long
as I don't understand it I cannot say for sure whether it is correct.
There seems no obvious reason for a memory barrier, but there may be a
hidden reason I don't see.
Regards
Oliver
^ permalink raw reply
* question about drivers/net/ethernet/nxp/lpc_eth.c
From: Julia Lawall @ 2013-08-13 15:01 UTC (permalink / raw)
To: grant.likely, rob.herring, netdev, linux-kernel, devicetree
I wonder why drivers/net/ethernet/nxp/lpc_eth.c uses dev_alloc_skb in the
function __lpc_handle_recv, rather than netdev_alloc_skb? The difference
seems to be only that with dev_alloc_skb, the dev field of the skb is
initialized to NULL, rather than to a net_device, but this function seems
to have a net_device value available, so I wonder why it is not used?
thanks,
julia
^ permalink raw reply
* [PATCH] phy: micrel: Add definitions for common Micrel PHY registers
From: dinguyen @ 2013-08-13 14:58 UTC (permalink / raw)
To: dinh.linux
Cc: Dinh Nguyen, Shawn Guo, Nicolas Ferre, David S. Miller,
Andrew Victor, Jean-Christophe Plagniol-Villard, netdev,
linux-arm-kernel
From: Dinh Nguyen <dinguyen@altera.com>
Hi Shawn,
Can you apply this patch to your tree for 3.12?
Thanks,
Dinh Nguyen (1):
phy: micrel: Add definitions for common Micrel PHY registers
arch/arm/mach-at91/board-dt-sama5.c | 17 ++++++-----------
arch/arm/mach-imx/mach-imx6q.c | 13 ++++++++-----
include/linux/micrel_phy.h | 6 ++++++
3 files changed, 20 insertions(+), 16 deletions(-)
Cc: Shawn Guo <shawn.guo@linaro.org>
Cc: Nicolas Ferre <nicolas.ferre@atmel.com>
Cc: David S. Miller <davem@davemloft.net>
CC: Andrew Victor <linux@maxim.org.za>
CC: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: netdev@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
--
1.7.9.5
^ permalink raw reply
* [PATCH] phy: micrel: Add definitions for common Micrel PHY registers
From: dinguyen @ 2013-08-13 14:59 UTC (permalink / raw)
To: dinh.linux
Cc: Dinh Nguyen, David S. Miller, Andrew Victor,
Jean-Christophe Plagniol-Villard, Shawn Guo, Nicolas Ferre,
netdev, linux-arm-kernel
In-Reply-To: <1376405940-17141-1-git-send-email-dinguyen@altera.com>
From: Dinh Nguyen <dinguyen@altera.com>
Add defines for common Micrel PHY setups so that other platforms
can use them. Update imx61 and sama5 hardware to use the micrel_phy.h
PHY defines.
Also add support for the KSZ9021RLRN PHY.
Signed-off-by: Dinh Nguyen <dinguyen@altera.com>
Acked-by: Shawn Guo <shawn.guo@linaro.org>
Acked-by: Nicolas Ferre <nicolas.ferre@atmel.com>
Cc: David S. Miller <davem@davemloft.net>
CC: Andrew Victor <linux@maxim.org.za>
CC: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Shawn Guo <shawn.guo@linaro.org>
Cc: Nicolas Ferre <nicolas.ferre@atmel.com>
Cc: netdev@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
---
arch/arm/mach-at91/board-dt-sama5.c | 17 ++++++-----------
arch/arm/mach-imx/mach-imx6q.c | 13 ++++++++-----
include/linux/micrel_phy.h | 6 ++++++
3 files changed, 20 insertions(+), 16 deletions(-)
diff --git a/arch/arm/mach-at91/board-dt-sama5.c b/arch/arm/mach-at91/board-dt-sama5.c
index ad95f6a..bf00d15 100644
--- a/arch/arm/mach-at91/board-dt-sama5.c
+++ b/arch/arm/mach-at91/board-dt-sama5.c
@@ -42,20 +42,15 @@ static int ksz9021rn_phy_fixup(struct phy_device *phy)
{
int value;
-#define GMII_RCCPSR 260
-#define GMII_RRDPSR 261
-#define GMII_ERCR 11
-#define GMII_ERDWR 12
-
/* Set delay values */
- value = GMII_RCCPSR | 0x8000;
- phy_write(phy, GMII_ERCR, value);
+ value = MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW | 0x8000;
+ phy_write(phy, MICREL_KSZ9021_EXTREG_CTRL, value);
value = 0xF2F4;
- phy_write(phy, GMII_ERDWR, value);
- value = GMII_RRDPSR | 0x8000;
- phy_write(phy, GMII_ERCR, value);
+ phy_write(phy, MICREL_KSZ9021_EXTREG_DATA_WRITE, value);
+ value = MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW | 0x8000;
+ phy_write(phy, MICREL_KSZ9021_EXTREG_CTRL, value);
value = 0x2222;
- phy_write(phy, GMII_ERDWR, value);
+ phy_write(phy, MICREL_KSZ9021_EXTREG_DATA_WRITE, value);
return 0;
}
diff --git a/arch/arm/mach-imx/mach-imx6q.c b/arch/arm/mach-imx/mach-imx6q.c
index 7be13f8..c8d7814 100644
--- a/arch/arm/mach-imx/mach-imx6q.c
+++ b/arch/arm/mach-imx/mach-imx6q.c
@@ -103,13 +103,16 @@ static int ksz9021rn_phy_fixup(struct phy_device *phydev)
{
if (IS_BUILTIN(CONFIG_PHYLIB)) {
/* min rx data delay */
- phy_write(phydev, 0x0b, 0x8105);
- phy_write(phydev, 0x0c, 0x0000);
+ phy_write(phydev, MICREL_KSZ9021_EXTREG_CTRL,
+ 0x8000 | MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW);
+ phy_write(phydev, MICREL_KSZ9021_EXTREG_DATA_WRITE, 0x0000);
/* max rx/tx clock delay, min rx/tx control delay */
- phy_write(phydev, 0x0b, 0x8104);
- phy_write(phydev, 0x0c, 0xf0f0);
- phy_write(phydev, 0x0b, 0x104);
+ phy_write(phydev, MICREL_KSZ9021_EXTREG_CTRL,
+ 0x8000 | MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW);
+ phy_write(phydev, MICREL_KSZ9021_EXTREG_DATA_WRITE, 0xf0f0);
+ phy_write(phydev, MICREL_KSZ9021_EXTREG_CTRL,
+ MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW);
}
return 0;
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 8752dbb..ad05ce6 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -17,6 +17,7 @@
#define PHY_ID_KSZ8873MLL 0x000e7237
#define PHY_ID_KSZ9021 0x00221610
+#define PHY_ID_KSZ9021RLRN 0x00221611
#define PHY_ID_KS8737 0x00221720
#define PHY_ID_KSZ8021 0x00221555
#define PHY_ID_KSZ8031 0x00221556
@@ -35,4 +36,9 @@
/* struct phy_device dev_flags definitions */
#define MICREL_PHY_50MHZ_CLK 0x00000001
+#define MICREL_KSZ9021_EXTREG_CTRL 0xB
+#define MICREL_KSZ9021_EXTREG_DATA_WRITE 0xC
+#define MICREL_KSZ9021_RGMII_CLK_CTRL_PAD_SCEW 0x104
+#define MICREL_KSZ9021_RGMII_RX_DATA_PAD_SCEW 0x105
+
#endif /* _MICREL_PHY_H */
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH net-next 2/3] net/usb/r8152: enable tx checksum
From: Sergei Shtylyov @ 2013-08-13 14:39 UTC (permalink / raw)
To: Hayes Wang; +Cc: netdev, linux-kernel, linux-usb
In-Reply-To: <1376378913-879-2-git-send-email-hayeswang@realtek.com>
Hello.
On 08/13/2013 11:28 AM, Hayes Wang wrote:
> Enable tx checksum.
> Signed-off-by: Hayes Wang <hayeswang@realtek.com>
> ---
> drivers/net/usb/r8152.c | 63 +++++++++++++++++++++++++++++++++++++++++++++----
> 1 file changed, 58 insertions(+), 5 deletions(-)
> diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
> index c6c5aa2..5d9d949 100644
> --- a/drivers/net/usb/r8152.c
> +++ b/drivers/net/usb/r8152.c
[...]
> @@ -964,6 +971,51 @@ err1:
> return -ENOMEM;
> }
>
> +static void
> +r8152_tx_csum(struct r8152 *tp, struct tx_desc *desc, struct sk_buff *skb)
> +{
[...]
> + if (ip_protocol == IPPROTO_TCP) {
> + opts2 |= TCP_CS;
> + opts2 |= (skb_transport_offset(skb) & 0x7fff) << 17;
> + } else if (ip_protocol == IPPROTO_UDP) {
> + opts2 |= UDP_CS;
> + } else
> + WARN_ON_ONCE(1);
Stange, why *else if* branch has {} and *else* don't. It should, according
to Documentation/CodingStyle.
> +
> + desc->opts2 = cpu_to_le32(opts2);
> + }
> +}
> +
WBR, Sergei
^ permalink raw reply
* tun always return NETDEV_TX_OK, why?
From: Yannick Koehler @ 2013-08-13 14:39 UTC (permalink / raw)
To: netdev
Hello,
I hit a problem recently with the tun interface, it looks like when
this interface reach its txqueuelen it will then drop the packet and
return NETDEV_TX_OK unconditionally.
That, from my little understanding of the netdev framework, appears
to be wrong and will simply eat up any pending buffer and discard them
until the queue frees itself. That seems to be against the flow
control design in the tx queue system of the kernel.
So, is this a bug or a misunderstanding? Would it be ok for tun to
return NETDEV_TX_BUSY when the txqueuelen is reach and call
netif_stop_queue() so that the layer above stop sending frame to this
interface until it can cope it's current queue content?
--
Yannick Koehler
^ permalink raw reply
* Re: [PATCH 1/2] ipv6: do not disable temp_address when reaching max_address
From: Sergei Shtylyov @ 2013-08-13 14:31 UTC (permalink / raw)
To: Ding Tianhong
Cc: David S. Miller, Alexey Kuznetsov, James Morris,
Hideaki YOSHIFUJI, Netdev, Patrick McHardy
In-Reply-To: <5209CEE2.70908@huawei.com>
Hello.
On 08/13/2013 10:14 AM, Ding Tianhong wrote:
> A LAN user can remotely disable temporary address which may lead
> to privacy violatins and information disclosure.
> The reason is that the linux kernel uses the 'ipv6.max_addresses'
> option to specify how many ipv6 addresses and interface may have.
> The 'ipv6.regen_max_retry' (default value 3) option specifies
> how many times the kernel will try to create a new address.
> But the kernel is not distinguish between the event of reaching
> max_addresses for an interface and failing to generate a new address.
> the kernel disable the temporary address after regenerate a new
> address 'regen_max_retry' times.
> According RFC4941 3.3.7:
> ---------------------------------------
> If DAD indicates the address is already in use,
> the node must generate a new randomized interface
> identifier as described in section 3.2 above, and
> repeat the previous steps as appropriate up to
> TEMP_IDGEN_RETRIES times.
> If after TEMP_IDGEN_RETRIES consecutive attempts no
> non-unique address was generated, the node must log
> a system error and must not attempt to generate
> temporary address for that interface.
> ------------------------------------------
> RFC4941 3.3.7 specifies that disabling the temp_address must happen
> upon the address is already in use, not reach the max_address,
> So we have to check the return err and distinguish the correct retry path.
> This fixes CVE-2013-0343
> Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
> Tested-by: Wang Weidong <wangweidong1@huawei.com>
> Cc: David S. Miller <davem@davemloft.net>
> ---
> net/ipv6/addrconf.c | 25 +++++++++++++++++++++----
> 1 file changed, 21 insertions(+), 4 deletions(-)
> diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
> index da4241c..99f9fd5 100644
> --- a/net/ipv6/addrconf.c
> +++ b/net/ipv6/addrconf.c
> @@ -1134,10 +1134,27 @@ retry:
[...]
> + if (PTR_ERR(ift) == -EEXIST) {
> + pr_info("%s: retry temporary address regeneration\n", __func__);
> + tmpaddr = &addr;
> + write_lock(&idev->lock);
> + goto retry;
> + } else
> + goto out;
According to CodingStyle, both arms of the *if* statement should have {}
if one has it.
WBR, Sergei
^ permalink raw reply
* Re: the congestion window rfc2001
From: Yuchung Cheng @ 2013-08-13 14:29 UTC (permalink / raw)
To: Dong Fang; +Cc: netdev
In-Reply-To: <520AC2AD.1030306@gmail.com>
Please ask those questions on more relevant list such as
tcpm@ietf.org. This list is for discussing Linux kernel networking
development, not generic TCP protocol.
On Tue, Aug 13, 2013 at 4:35 PM, Dong Fang <yp.fangdong@gmail.com> wrote:
> hi, all
>
>
> http://tools.ietf.org/html/rfc2001
>
>
> 1. When the third duplicate ACK in a row is received, set ssthresh
> to one-half the current congestion window, cwnd, but no less
> than two segments. Retransmit the missing segment. Set cwnd =
> ssthresh + 3 times the segment size. This inflates the
> -- what is the meaning of '3'
>
> congestion window by the number of segments that have left the
> network and which the other end has cached (3).
>
> 2. Each time another duplicate ACK arrives, increment cwnd by the
> segment size. This inflates the congestion window for the
> additional segment that has left the network.
> -- why do this
>
> Transmit a packet, if allowed by the new value of cwnd.
>
> 3. When the next ACK arrives that acknowledges new data, set cwnd
> to ssthresh (the value set in step 1). This ACK should be the
> acknowledgment of the retransmission from step 1, one round-trip
> time after the retransmission. Additionally, this ACK should
> acknowledge all the intermediate segments sent between the lost
> packet and the receipt of the first duplicate ACK. This step is
> congestion avoidance, since TCP is down to one-half the rate it
> was at when the packet was lost.
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* RE: [PATCH net v5 0/5] bnx2x: fixes
From: Dmitry Kravkov @ 2013-08-13 14:16 UTC (permalink / raw)
To: Benjamin Poirier, Ariel Elior
Cc: davem@davemloft.net, netdev@vger.kernel.org, Eilon Greenstein
In-Reply-To: <20130813140715.GA4394@d2.synalogic.ca>
> -----Original Message-----
> From: netdev-owner@vger.kernel.org [mailto:netdev-
> owner@vger.kernel.org] On Behalf Of Benjamin Poirier
> Sent: Tuesday, August 13, 2013 5:07 PM
> To: Ariel Elior
> Cc: Dmitry Kravkov; davem@davemloft.net; netdev@vger.kernel.org; Eilon
> Greenstein
> Subject: Re: [PATCH net v5 0/5] bnx2x: fixes
>
> On 2013/08/13 12:38, Ariel Elior wrote:
> > > I'm confused. Wasn't "[PATCH net v4 1/6] bnx2x: properly initialize
> > > statistic counters" supposed to fix a race condition? According to
> > > earlier communication with Ariel:
> > > In this issue a race condition at driver startup causes a second
> > > statistics query to be sent before the first one completes,
> > > resulting in a firmware assert and a stuck chip. A patch was
> > > sent upstream fixing this:
> > > http://patchwork.ozlabs.org/patch/264810/
> >
> > As I explicitly mentioned in the communique which you quoted above,
> the patch was sent but not yet accepted.
> > This is precisely the upstream process - patches are being sent, reviewed
> and sometimes rejected and revised.
> > If you have further questions please address them to me - the technical
> forum is no place for this kind of discussion.
> > Thanks,
> > Ariel
> >
>
> It's a technical question about a patch which was sent upstream. Where
> should the discussion happen if not upstream?
>
> Let me rephrase my question:
>
> I'm confused. I thought that "[PATCH net v4 1/6] bnx2x: properly initialize
> statistic counters" was meant to fix a race condition at driver startup which
> causes a second statistics query to be sent before the first one completes,
> resulting in a firmware assert and a stuck chip. Am I mistaken and there is no
> such race condition, or is it addressed by the other patches in this series?
>
There is such condition, but it's not caused by wrongly initialized counted -
the initialization done in a correct way. Patch "[PATCH net v5 1/5] bnx2x: protect
different statistics flows" - prevents from two outstanding queries to be sent
simultaneously.
Thanks
Dmitry
^ permalink raw reply
* Re: [PATCH net v5 0/5] bnx2x: fixes
From: Benjamin Poirier @ 2013-08-13 14:07 UTC (permalink / raw)
To: Ariel Elior
Cc: Dmitry Kravkov, davem@davemloft.net, netdev@vger.kernel.org,
Eilon Greenstein
In-Reply-To: <6AE768456CEC4B4A9B2248CB6B87EB3E1BEB957E@SJEXCHMB05.corp.ad.broadcom.com>
On 2013/08/13 12:38, Ariel Elior wrote:
> > I'm confused. Wasn't "[PATCH net v4 1/6] bnx2x: properly initialize
> > statistic counters" supposed to fix a race condition? According to
> > earlier communication with Ariel:
> > In this issue a race condition at driver startup causes a second
> > statistics query to be sent before the first one completes,
> > resulting in a firmware assert and a stuck chip. A patch was
> > sent upstream fixing this:
> > http://patchwork.ozlabs.org/patch/264810/
>
> As I explicitly mentioned in the communique which you quoted above, the patch was sent but not yet accepted.
> This is precisely the upstream process - patches are being sent, reviewed and sometimes rejected and revised.
> If you have further questions please address them to me - the technical forum is no place for this kind of discussion.
> Thanks,
> Ariel
>
It's a technical question about a patch which was sent upstream. Where
should the discussion happen if not upstream?
Let me rephrase my question:
I'm confused. I thought that "[PATCH net v4 1/6] bnx2x: properly
initialize statistic counters" was meant to fix a race condition at
driver startup which causes a second statistics query to be sent before
the first one completes, resulting in a firmware assert and a stuck
chip. Am I mistaken and there is no such race condition, or is it
addressed by the other patches in this series?
^ permalink raw reply
* Quick Blind TCP Connection Spoofing with SYN Cookies
From: Jakob Lell @ 2013-08-13 13:57 UTC (permalink / raw)
To: full-disclosure-yjGSz5NhYZxwCIiogXJnzFpr/1R2p/CL
Cc: oss-security-ZwoEplunGu1jrUoiu81ncdBPR1lH4CV8,
netdev-u79uwXL29TY76Z2rM5mHXA
[-- Attachment #1: Type: text/plain, Size: 23401 bytes --]
Advisory location:
http://www.jakoblell.com/blog/2013/08/13/quick-blind-tcp-connection-spoofing-with-syn-cookies/
Quick Blind TCP Connection Spoofing with SYN Cookies
Abstract:
TCP uses 32 bit Seq/Ack numbers in order to make sure that both sides of
a connection can actually receive packets from each other. Additionally,
these numbers make it relatively hard to spoof the source address
because successful spoofing requires guessing the correct initial
sequence number (ISN) which is generated by the server in a
non-guessable way. It is commonly known that a 32 bit number can be
brute forced in a couple of hours given a fast (gigabit) network
connection. This article shows that the effort required for guessing a
valid ISN can be reduced from hours to minutes if the server uses TCP
SYN Cookies (a widely used defense mechanism against SYN-Flooding DOS
Attacks), which are enabled by default for various Linux distributions
including Ubuntu and Debian.
I. Repetition of TCP Basics
A TCP Connection is initiated with a three-way handshake:
SYN: The Client sends a SYN packet to the server in order to initiate a
connection. The SYN packet contains an initial sequence number (ISN)
generated by the client.
SYN-ACK: The server acknowledges the connection request by the client.
The SYN-ACK Packet contains an ISN generated by the server. It also
confirms the ISN from the client in the ack field of the TCP header so
that the client can verify that the SYN-ACK packet actually comes from
the server and isn't spoofed.
ACK: In the final ACK packet of the three-way handshake the client
confirms that it has received the ISN generated by the server. That way
the server knows that the client has actually received the SYN-ACK
packet from the server and thus the connection request isn't spoofed.
After this three-way handshake, the TCP connection is established and
both sides can send data to each other. The initial sequence numbers
make sure that the other side can actually receive the packets and thus
prevent IP spoofing given that the attacker can't receive packets sent
to the spoofed IP address.
Since the initial sequence numbers are only 32-bit values, it is not
impossible to blindly spoof a connection by brute-forcing the ISN. If we
need to send 3 packets to the server (one SYN packet to initiate the
connection, one ACK packet to finish the three-way handshake and one
payload packet), we will have to send 3*2^32 packets per successfully
spoofed connection at an average. Given a packet rate of 300,000 packets
per second (which can easily be achieved with a gigabit connection),
sending this packets requires some 12 hours.
One long-known weakness of the original TCP protocol design is that an
attacker can spoof a high number of SYN packets to a server. The server
then has to send (and maybe even retransmit) a SYN-ACK packet to each of
the spoofed IP addresses and keep track the half-open connection so that
it can handle an ACK packet. Remembering a high number of bogus
half-open connections can lead to resource exhaustion and make the
server unresponsive to legitimate clients. This attack is called SYN
Flooding and it can lead to DOS even if the attacker only uses a
fraction of the network bandwidth available to the server.
II. Description of the SYN Cookie approach
In order to protect servers against SYN-Flooding attacks, Daniel J.
Bernstein suggested the technique of TCP Syn Cookies in 1996. The main
idea of the approach is not to keep track of incoming SYN packets and
instead encode the required information in the ISN generated by the
server. Once the server receives an ACK packet, he can check whether the
Ack number from the client actually matches the server-generated ISN,
which can easily be recalculated when receiving the ACK-packet. This
allows processing the ACK packet without remembering anything about the
initial SYN request issued by the client.
Since the server doesn't keep track of half-open connections, it can't
remember any detail of the SYN packet sent by the client. Since the
initial SYN packet contains the maximum segment size (MSS) of the
client, the server encodes the MSS using 3 bits (via a table with 8
hard-coded MSS values). In order to make sure that half-open connections
expire after a certain time, the server also encodes a
slowly-incrementing (typically about once a minute) counter to the ISN.
Other options of the initial SYN packet are typically ignored (although
recent Linux kernels do support some options by encoding them via TCP
Timestamps [1]). When receiving an ACK packet, the kernel extracts the
counter value from the SYN Cookie and checks whether it is one of the
last 4 valid values.
The original approach of Bernstein [2] only encodes the counter and the
MSS value in the first 8 bits of the ISN thus leaving only 24 bits for
the cryptographically generated (non-guessable) value which needs to be
guessed for spoofing a connection. This can easily be brute forced
within relatively short time given the speed of modern network hardware.
In order to mitigate this attack, Bernstein suggests[3]:
# Add another number to the cookie: a 32-bit server-selected secret
function of the client address and server address (but not the current
time). This forces the attacker to guess 32 bits instead of 24.
This is implemented in recent Linux kernels and it does indeed make
guessing the ISN more costly than a simple implementation without this
additional secret function. However, as we will see in the next section,
it does not require the attacker to guess the full 32 bit ISN.
The following function shows the generation of the SYN Cookies in the
Linux Kernel 3.10.1 (file net/ipv4/syncookies.c):
#define COOKIEBITS 24 /* Upper bits store count */
#define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
static __u32 secure_tcp_syn_cookie(__be32 saddr, __be32 daddr, __be16 sport,
__be16 dport, __u32 sseq, __u32 count,
__u32 data)
{
/*
* Compute the secure sequence number.
* The output should be:
* HASH(sec1,saddr,sport,daddr,dport,sec1) + sseq + (count * 2^24)
* + (HASH(sec2,saddr,sport,daddr,dport,count,sec2) % 2^24).
* Where sseq is their sequence number and count increases every
* minute by 1.
* As an extra hack, we add a small "data" value that encodes the
* MSS into the second hash value.
*/
return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
sseq + (count << COOKIEBITS) +
((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
& COOKIEMASK));
}
The value sseq is the sequence number generated by the client and is
therefore directly known to the attacker. The data is an integer between
0 and 7, which encodes one of 8 possible MSS values. The count value is
just a timestamp which is increased once a minute and it is encoded in
the upper 8 bits of the generated cookie. However, since the first hash
value is not known to the attacker, the timestamp value must be guessed
by the attacker as well.
The following two functions show how the SYN Cookies are verified when
receiving an ACK packet:
#define COUNTER_TRIES 4
/*
* This retrieves the small "data" value from the syncookie.
* If the syncookie is bad, the data returned will be out of
* range. This must be checked by the caller.
*
* The count value used to generate the cookie must be within
* "maxdiff" if the current (passed-in) "count". The return value
* is (__u32)-1 if this test fails.
*/
static __u32 check_tcp_syn_cookie(__u32 cookie, __be32 saddr, __be32 daddr,
__be16 sport, __be16 dport, __u32 sseq,
__u32 count, __u32 maxdiff)
{
__u32 diff;
/* Strip away the layers from the cookie */
cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
/* Cookie is now reduced to (count * 2^24) ^ (hash % 2^24) */
diff = (count - (cookie >> COOKIEBITS)) & ((__u32) - 1 >> COOKIEBITS);
if (diff >= maxdiff)
return (__u32)-1;
return (cookie -
cookie_hash(saddr, daddr, sport, dport, count - diff, 1))
& COOKIEMASK; /* Leaving the data behind */
}
/*
* Check if a ack sequence number is a valid syncookie.
* Return the decoded mss if it is, or 0 if not.
*/
static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
{
const struct iphdr *iph = ip_hdr(skb);
const struct tcphdr *th = tcp_hdr(skb);
__u32 seq = ntohl(th->seq) - 1;
__u32 mssind = check_tcp_syn_cookie(cookie, iph->saddr, iph->daddr,
th->source, th->dest, seq,
jiffies / (HZ * 60),
COUNTER_TRIES);
return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
}
First of all, the server removes the first hash value and the ISN chosen
by the client. This is easily possible because the hash only depends on
a server secret and the source/destination address/port and doesn't
change over time. Then the upper 8 bits contain the count value and if
this counter is one of the last four valid counter values, it is
accepted. At that point the counter used for generating the SYN Cookie
is known and the server can therefore calculate the second hash and
subtract it from the cookie. The remaining value is the encoded MSS
value. The Cookie is only accepted if this encoded MSS value is actually
a number between 0 and 7.
III. Reduced cost of guessing due to multiple valid ISNs
Since the kernel encodes a counter and the MSS value in the ISN, there
must be one valid ISN for every combination of a valid counter value and
a valid MSS value. In current implementations there are 4 valid counter
values and 8 possible MSS values. This gives a total of 32 valid
combinations which will be accepted by the server at any given time.
Each of this 32 combination results in one valid ISN and if the attacker
guesses any one of them, the kernel will accept the ACK packet. This
reduces the effort needed to successfully guess a valid ISN by the
factor 32.
Since the server doesn't remember that he has received a SYN packet when
using SYN Cookies, there is no need to actually send the initial SYN
packet. If we start the connection by sending an ACK packet and guess
one of the 32 valid ISNs, the kernel will process the ACK packet without
noticing that he has never received a SYN packet from the client and
responded with a SYN-Ack packet.
IV. Combination of ACK-Packet and Payload
Although the TCP standard assumes that the three-way handshake is
completed before any data is sent, it is also possible to add data to
the final ACK packet of the handshake [4]. This means that guessing an
ISN and spoofing a full tcp connection with some payload data (such as
an http request) can be reduced to sending out only one single packet.
So the average number of packets required per successfully spoofed
connection can be reduced to 2^32 / 32 (because the server accepts 32
different ISNs at a time). At a packet rate of 300,000 pps (which can
easily be achieved with gigabit ethernet) this amount of packets can be
sent out in no more than 8 minutes (compared to the 12 hours calculated
in section I).
V. Possible real-life applications of TCP Connection spoofing
Many application developers assume that TCP makes sure that the client
IP address is actually correct and can't easily be spoofed. Being able
to spoof the source address obviously creates significant problems when
using the IP address for authentication e.g. for legacy protocols like
RSH. Even if RSH has widely been replaced by more secure alternatives
like SSH by now, there are still some applications where the IP address
is used for authentication. For instance it is still common to have
administrative interfaces which can only be accessed from certain IP
addresses. Another widespread usage of IP addresses for authentication
is that many web applications bind the session ID to a specific IP
address. If the session ID can be stolen by other means, an attacker can
use the method described here to bypass this IP address verification.
Aside from actually using IP addresses for authenticating requests, it
is also quite common to log IP addresses, which may then be used to
track down initiators of objectionable requests such as exploits,
abusive blog comments or illegal file sharing traffic. Using the
technique described here may allow planting false evidence in the logged
IP addresses.
Being able to spoof IP addresses also allows bypassing SPF e.g. when
sending spear phishing mails in order to give the phishing mails the
additional credibility of a valid SPF sender address, which may help to
bypass email filtering software.
An obvious limitation of the technique described here is that when
spoofing the IP address, you can only send a request (which may result
in persistent changes on the server) but not receive any responses sent
by the server. For many protocols it is however possible to guess the
size of the server responses, send matching ACK packets and transmit
multiple payload packets in order to spoof a more complex protocol
interaction with the server.
VI. POC Exploit and real-life performance measures
This section describes the steps needed to actually carry out the attack
and contains full POC code. For my experimental setup the server used
the IP address 192.168.1.11 and port 1234. The attacker system was
located in the same local subnet and the spoofed IP address was
192.168.1.217.
First of all, even if SYN Cookies are enabled in
/proc/sys/net/ipv4/tcp_syncookies (which is the default for various
linux distributions), the system will still use a traditional backlog
queue for storing half-open connections and only fall back to using SYN
Cookies if the backlog queue overflows. The main reason for this is that
storing information about connection requests allows full support of TCP
Options and arbitrary MSS values (which don't have to be reduced to one
of 8 predefined values). The backlog queue size is 2048 by default and
can be adjusted via /proc/sys/net/ipv4/tcp_max_syn_backlog. So in order
to actually carry out the spoofing attack, we have to intentionally
overflow the backlog queue by doing a Syn-Flooding attack. This can be
done e.g. with the hping3 command:
hping3 -i u100 -p 1234 -S -a 192.168.1.216 -q 192.168.1.11
Experiments have shown that running hping3 in parallel to the actual ISN
brute-forcing does significantly reduce the packet rate even if hping3
is configured to use only a small fraction of the packet rate of the ISN
brute-forcing tool. In order to achieve the maximum packet rate
possible, it is therefore more efficient to run hping3 in regular short
intervals. The following command sends out 3000 SYN packets in a short
burst once a second:
while true;do time hping3 -i u1 -c 3000 -S -q -p 1234 -a 192.168.1.216
192.168.1.11;sleep 1;done
The source IP address used for this SYN-Flooding attack should not
respond with a RST packet or return an ICMP Destination Host Unreachable
message so that the queue entries aren't freed before they time out. On
linux you can easily add another IP address to a network interface and
block all traffic coming to this IP address in order to prevent it from
responding with RST packets:
ifconfig eth0:1 inet 192.168.1.216 netmask 255.255.255.0 up
iptables -I INPUT --dst 192.168.1.216 -j DROP
I've used the same commands to set up the IP address 192.168.1.217,
which is the IP address I wanted to spoof. This makes sure that sending
responses to the spoofed address won't lead to a RST packet or an ICMP
Destination Host Unreachable packet, which may lead to a premature
termination of the connection and the processing of the spoofed request
in the server software.
ifconfig eth0:2 inet 192.168.1.217 netmask 255.255.255.0 up
iptables -I INPUT --dst 192.168.1.217 -j DROP
In a real world attack, the same goal can also be achieved by issuing a
(D)DOS attack against the spoofed IP address.
Once the system is in SYN-Cookie mode, it is necessary to spoof a high
number of ACK packets with a payload in order to guess one of the 32
valid ISNs. I initially wanted to do this with scapy but this failed due
to the utterly low performance of scapy (less then 10k packets per
second). So I went on to create a pcap file in scapy, which can then be
sent out with a patched version of tcpreplay in a loop. The patched
tcpreplay just increases the ack field of the tcp header by 31337 for
each repetition of the loop. Using an uneven number makes sure that it
reaches all 2^32 possible values without repetitions. In theory you
could just linearly try all possible ISNs. However, the counter value in
the 8 upper bits of the ISN only changes once a minute and is linearly
incremented for a given combination of source and destination
address/port. Therefore a linear search will likely be in an incorrect
range and not create any hit within a long time. So it is advisable to
increment the guessed ISN by a larger number so that it traverses the
full ISN space relatively quickly.
The attached script create_packet.py creates a single ACK packet with
some payload data.
The next step is to patch and compile tcpreplay. Here are the commands
needed on an Ubuntu 12.04 amd64 system:
apt-get install build-essential libpcap-dev
ln -s lib/x86_64-linux-gnu /usr/lib64 # Quick workaround for a bug in
the build system of tcpreplay
wget -O tcpreplay-3.4.4.tar.gz
http://prdownloads.sourceforge.net/tcpreplay/tcpreplay-3.4.4.tar.gz?download
tar xzvf tcpreplay-3.4.4.tar.gz
cd tcpreplay-3.4.4
cat ../tcpreplay_patch.txt | patch -p1
./configure
make
cp src/tcpreplay-edit ../
After compiling a patched version of tcpreplay, you can use the
following commands to actually send out packets in an infinite loop:
python create_packet.py
while true;do time ./tcpreplay-edit -i eth0 -t -C -K -l 500000000 -q
ack_with_payload.pcap;done
VII. Experimental results
I've tested this setup in a local network between a 3 year old notebook
(HP 6440b, i5-430M CPU and Marvell 88E8072 gigabit NIC) as the client
and a desktop computer as the server. With a small test payload, the
achievable packet rate is some 280,000 packets per seconds, which leads
to some 73% CPU usage of the tcpreplay process (18% user and 55% sys in
the output of time). According to [5] it may be expected that the packet
rate can at least be doubled given a fast system with a decent Intel
gigabit network card. Obviously the actual packet rate also depends on
the size of the payload data. During a 10.5 hour overnight run I
successfully spoofed 64 connections, which is about one successful spoof
every 10 minutes. This is a little bit less than the expected value of
79 spoofed connections (once every 8 minutes). There are several
possible explanations for this deviation:
* The tcpreplay process takes some time to print the statistics in the
end. During that time no packets are sent. I've only used the statistics
output of tcpreplay for measuring the packet rate and so the measured
packet rate may be a little bit off.
* When going to the maximum packet rate achievable with your hardware,
there may be packet loss (especially if you don't use any kind of
congestion control).
* Last but not least the spoofing is a statistical process. The standard
deviation is approximately the square root of the expected number of
spoofed connections and it is not particularly unlikely to be off by one
or two standard deviations from the expected value. For this experiment
the standard deviation is sqrt(79) = 8.89 and the measured number of
spoofed connections was off by 1.68 standard deviations, which is well
within the expected statistical variation.
VIII. Possible mitigation options
The simplification of TCP Connection Spoofing described here is an
inherent problem of TCP SYN Cookies and so there won't be a simple patch
which just solves the issue and makes the Spoofing Attack as hard as it
is without SYN Cookies. It is only possible to gradually increase the
required effort for successfully spoofing a connection e.g. by only
accepting the last two instead of four counter values (which will lead
to a 60-120s timeout between the initial SYN and the final ACK packet of
the three-way handshake during a SYN Flooding attack) or by disallowing
the combination of the final ACK packet with payload data (which will
double the number of packets the attacker has to send). However, even
with this two mitigation options in place, the spoofing attack is still
about an order of magnitude easier with SYN Cookies than it is without
SYN Cookies and it would still be very inadvisable to assume that the
source IP address of TCP connections can't be spoofed. It may also be
possible to use the lower bits of the TCP timestamp option (which is
currently used in order to support TCP Options with SYN Cookies) for
encoding the MSS and counter values. However, this can only provide
effective protection against a spoofing attack if the server refuses
clients which don't support TCP timestamps during a SYN Flooding Attack,
which will break compatibility with some standard-conform TCP
implementations.
It is obviously possible to disable SYN Cookies (and increase the
backlog queue size in /proc/sys/net/ipv4/tcp_max_syn_backlog) in order
to make the spoofing attack as hard as possible and force an attacker to
brute force the full 32 bit ISN space. However, disabling SYN Cookies
may require a significant amount of CPU Time and Memory during a SYN
Flooding Attack. Moreover, the spoofing is still not impossible even
without SYN Cookies and it will likely succeed within a couple of hours
with a gigabit ethernet connection.
Given the limitations of the other mitigation options my suggestion is
to solve the problem on a higher level and make sure that the security
of applications doesn't rely on the impossible of spoofing the source
address of TCP connections. This obviously means that you should never
rely on source IP addresses for authentication. For web applications it
is also possible to mitigate the issue by using secure CSRF tokens for
all actions which cause persistent changes on the server and not
processing the request unless it uses a valid CSRF token. In that case
the IP address of the request using the CSRF token may be spoofed but
the IP address to which the token has been sent to can't be spoofed
since the attacker will need to receive the CSRF token so that he can
use it. When logging IP addresses used for certain actions such as blog
comments or account registrations, the IP address to which the CSRF
token has been sent to should be logged additionally to (or instead of)
the IP address using the token.
References:
[1]: http://lwn.net/Articles/277146/
[2]: http://cr.yp.to/syncookies.html Section "What are SYN cookies?"
[3]: http://cr.yp.to/syncookies.html Section "Blind connection forgery"
[4]: http://www.thice.nl/creating-ack-get-packets-with-scapy/
[5]:
http://wiki.networksecuritytoolkit.org/nstwiki/index.php/LAN_Ethernet_Maximum_Rates,_Generation,_Capturing_%26_Monitoring#pktgen:_UDP_60_Byte_Packets
[-- Attachment #2: create_packet.py --]
[-- Type: text/x-python, Size: 794 bytes --]
#!/usr/bin/python
# Change log level to suppress annoying IPv6 error
import logging
logging.getLogger("scapy.runtime").setLevel(logging.ERROR)
from scapy.all import *
import time
# Adjust MAC addresses of sender and recipient of this packet accordingly, the dst MAC
# should be the MAC of the gateway to use when the target is not on your local subnet
ether=Ether(src="40:eb:60:9f:42:a0",dst="e8:40:f2:d1:b3:a2")
# Set up source and destination IP addresses
ip=IP(src="192.168.1.217", dst="192.168.1.11")
# Assemble an ACK packet with "Hello World\n" as a payload
pkt = ether/ip/TCP(sport=31337, dport=1234, flags="A", seq=43, ack=1337) / ("Hello World\n")
# Write the packet to a pcap file, which can then be sent using a patched version of tcpreplay
wrpcap("ack_with_payload.pcap",pkt)
[-- Attachment #3: tcpreplay_patch.txt --]
[-- Type: text/plain, Size: 1578 bytes --]
diff -u -r tcpreplay-3.4.4/src/send_packets.c tcpreplay-3.4.4.patched/src/send_packets.c
--- tcpreplay-3.4.4/src/send_packets.c 2010-04-05 02:58:02.000000000 +0200
+++ tcpreplay-3.4.4.patched/src/send_packets.c 2013-08-06 10:56:51.757048452 +0200
@@ -81,6 +81,9 @@
void
send_packets(pcap_t *pcap, int cache_file_idx)
{
+ static u_int32_t ack_bruteforce_offset = 1;
+ uint32_t* ack;
+ uint32_t orig_ack;
struct timeval last = { 0, 0 }, last_print_time = { 0, 0 }, print_delta, now;
COUNTER packetnum = 0;
struct pcap_pkthdr pkthdr;
@@ -154,6 +157,9 @@
#endif
#if defined TCPREPLAY && defined TCPREPLAY_EDIT
+ ack = (uint32_t*)(pktdata + 14 + 20 + 8);
+ orig_ack = *ack;
+ *ack = htonl(ntohl(*ack) + ack_bruteforce_offset);
pkthdr_ptr = &pkthdr;
if (tcpedit_packet(tcpedit, &pkthdr_ptr, &pktdata, sp->cache_dir) == -1) {
errx(-1, "Error editing packet #" COUNTER_SPEC ": %s", packetnum, tcpedit_geterr(tcpedit));
@@ -176,7 +182,7 @@
/* write packet out on network */
if (sendpacket(sp, pktdata, pktlen) < (int)pktlen)
warnx("Unable to send packet: %s", sendpacket_geterr(sp));
-
+ *ack = orig_ack;
/*
* track the time of the "last packet sent". Again, because of OpenBSD
* we have to do a mempcy rather then assignment.
@@ -205,7 +211,7 @@
}
}
} /* while */
-
+ ack_bruteforce_offset += 31337;
if (options.enable_file_cache) {
options.file_cache[cache_file_idx].cached = TRUE;
}
^ permalink raw reply
* [PATCH net] tun: compare with 0 instead of total_len
From: Weiping Pan @ 2013-08-13 13:46 UTC (permalink / raw)
To: netdev
Since we set "len = total_len" in the beginning of tun_get_user(),
so we should compare the new len with 0, instead of total_len,
or the if statement always returns false.
Signed-off-by: Weiping Pan <wpan@redhat.com>
---
drivers/net/tun.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index db690a3..5a8ee1c 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1074,7 +1074,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
u32 rxhash;
if (!(tun->flags & TUN_NO_PI)) {
- if ((len -= sizeof(pi)) > total_len)
+ if ((len -= sizeof(pi)) < 0)
return -EINVAL;
if (memcpy_fromiovecend((void *)&pi, iv, 0, sizeof(pi)))
@@ -1083,7 +1083,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
}
if (tun->flags & TUN_VNET_HDR) {
- if ((len -= tun->vnet_hdr_sz) > total_len)
+ if ((len -= tun->vnet_hdr_sz) < 0)
return -EINVAL;
if (memcpy_fromiovecend((void *)&gso, iv, offset, sizeof(gso)))
--
1.7.4
^ permalink raw reply related
* [PATCH 1/2] netfilter: export xt_rpfilter.h to userland
From: Nicolas Dichtel @ 2013-08-13 13:05 UTC (permalink / raw)
To: netfilter-devel; +Cc: pablo, netdev, Nicolas Dichtel
This file contains the API for the match "rpfilter", hence it should be exported
to userland.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/linux/netfilter/xt_rpfilter.h | 23 -----------------------
include/uapi/linux/netfilter/Kbuild | 1 +
include/uapi/linux/netfilter/xt_rpfilter.h | 23 +++++++++++++++++++++++
3 files changed, 24 insertions(+), 23 deletions(-)
delete mode 100644 include/linux/netfilter/xt_rpfilter.h
create mode 100644 include/uapi/linux/netfilter/xt_rpfilter.h
diff --git a/include/linux/netfilter/xt_rpfilter.h b/include/linux/netfilter/xt_rpfilter.h
deleted file mode 100644
index 8358d4f71952..000000000000
--- a/include/linux/netfilter/xt_rpfilter.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _XT_RPATH_H
-#define _XT_RPATH_H
-
-#include <linux/types.h>
-
-enum {
- XT_RPFILTER_LOOSE = 1 << 0,
- XT_RPFILTER_VALID_MARK = 1 << 1,
- XT_RPFILTER_ACCEPT_LOCAL = 1 << 2,
- XT_RPFILTER_INVERT = 1 << 3,
-#ifdef __KERNEL__
- XT_RPFILTER_OPTION_MASK = XT_RPFILTER_LOOSE |
- XT_RPFILTER_VALID_MARK |
- XT_RPFILTER_ACCEPT_LOCAL |
- XT_RPFILTER_INVERT,
-#endif
-};
-
-struct xt_rpfilter_info {
- __u8 flags;
-};
-
-#endif
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 41115776d76f..dc00927ffd62 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -68,6 +68,7 @@ header-y += xt_quota.h
header-y += xt_rateest.h
header-y += xt_realm.h
header-y += xt_recent.h
+header-y += xt_rpfilter.h
header-y += xt_sctp.h
header-y += xt_set.h
header-y += xt_socket.h
diff --git a/include/uapi/linux/netfilter/xt_rpfilter.h b/include/uapi/linux/netfilter/xt_rpfilter.h
new file mode 100644
index 000000000000..8358d4f71952
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_rpfilter.h
@@ -0,0 +1,23 @@
+#ifndef _XT_RPATH_H
+#define _XT_RPATH_H
+
+#include <linux/types.h>
+
+enum {
+ XT_RPFILTER_LOOSE = 1 << 0,
+ XT_RPFILTER_VALID_MARK = 1 << 1,
+ XT_RPFILTER_ACCEPT_LOCAL = 1 << 2,
+ XT_RPFILTER_INVERT = 1 << 3,
+#ifdef __KERNEL__
+ XT_RPFILTER_OPTION_MASK = XT_RPFILTER_LOOSE |
+ XT_RPFILTER_VALID_MARK |
+ XT_RPFILTER_ACCEPT_LOCAL |
+ XT_RPFILTER_INVERT,
+#endif
+};
+
+struct xt_rpfilter_info {
+ __u8 flags;
+};
+
+#endif
--
1.8.2.1
^ permalink raw reply related
* [PATCH 2/2] netfilter: export xt_HMARK.h to userland
From: Nicolas Dichtel @ 2013-08-13 13:05 UTC (permalink / raw)
To: netfilter-devel; +Cc: pablo, netdev, Nicolas Dichtel
In-Reply-To: <1376399139-4181-1-git-send-email-nicolas.dichtel@6wind.com>
This file contains the API for the target "HMARK", hence it should be exported
to userland.
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
---
include/linux/netfilter/xt_HMARK.h | 50 ---------------------------------
include/uapi/linux/netfilter/Kbuild | 1 +
include/uapi/linux/netfilter/xt_HMARK.h | 50 +++++++++++++++++++++++++++++++++
3 files changed, 51 insertions(+), 50 deletions(-)
delete mode 100644 include/linux/netfilter/xt_HMARK.h
create mode 100644 include/uapi/linux/netfilter/xt_HMARK.h
diff --git a/include/linux/netfilter/xt_HMARK.h b/include/linux/netfilter/xt_HMARK.h
deleted file mode 100644
index 826fc5807577..000000000000
--- a/include/linux/netfilter/xt_HMARK.h
+++ /dev/null
@@ -1,50 +0,0 @@
-#ifndef XT_HMARK_H_
-#define XT_HMARK_H_
-
-#include <linux/types.h>
-
-enum {
- XT_HMARK_SADDR_MASK,
- XT_HMARK_DADDR_MASK,
- XT_HMARK_SPI,
- XT_HMARK_SPI_MASK,
- XT_HMARK_SPORT,
- XT_HMARK_DPORT,
- XT_HMARK_SPORT_MASK,
- XT_HMARK_DPORT_MASK,
- XT_HMARK_PROTO_MASK,
- XT_HMARK_RND,
- XT_HMARK_MODULUS,
- XT_HMARK_OFFSET,
- XT_HMARK_CT,
- XT_HMARK_METHOD_L3,
- XT_HMARK_METHOD_L3_4,
-};
-#define XT_HMARK_FLAG(flag) (1 << flag)
-
-union hmark_ports {
- struct {
- __u16 src;
- __u16 dst;
- } p16;
- struct {
- __be16 src;
- __be16 dst;
- } b16;
- __u32 v32;
- __be32 b32;
-};
-
-struct xt_hmark_info {
- union nf_inet_addr src_mask;
- union nf_inet_addr dst_mask;
- union hmark_ports port_mask;
- union hmark_ports port_set;
- __u32 flags;
- __u16 proto_mask;
- __u32 hashrnd;
- __u32 hmodulus;
- __u32 hoffset; /* Mark offset to start from */
-};
-
-#endif /* XT_HMARK_H_ */
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index dc00927ffd62..174915420d3f 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/include/uapi/linux/netfilter/Kbuild
@@ -22,6 +22,7 @@ header-y += xt_CONNMARK.h
header-y += xt_CONNSECMARK.h
header-y += xt_CT.h
header-y += xt_DSCP.h
+header-y += xt_HMARK.h
header-y += xt_IDLETIMER.h
header-y += xt_LED.h
header-y += xt_LOG.h
diff --git a/include/uapi/linux/netfilter/xt_HMARK.h b/include/uapi/linux/netfilter/xt_HMARK.h
new file mode 100644
index 000000000000..826fc5807577
--- /dev/null
+++ b/include/uapi/linux/netfilter/xt_HMARK.h
@@ -0,0 +1,50 @@
+#ifndef XT_HMARK_H_
+#define XT_HMARK_H_
+
+#include <linux/types.h>
+
+enum {
+ XT_HMARK_SADDR_MASK,
+ XT_HMARK_DADDR_MASK,
+ XT_HMARK_SPI,
+ XT_HMARK_SPI_MASK,
+ XT_HMARK_SPORT,
+ XT_HMARK_DPORT,
+ XT_HMARK_SPORT_MASK,
+ XT_HMARK_DPORT_MASK,
+ XT_HMARK_PROTO_MASK,
+ XT_HMARK_RND,
+ XT_HMARK_MODULUS,
+ XT_HMARK_OFFSET,
+ XT_HMARK_CT,
+ XT_HMARK_METHOD_L3,
+ XT_HMARK_METHOD_L3_4,
+};
+#define XT_HMARK_FLAG(flag) (1 << flag)
+
+union hmark_ports {
+ struct {
+ __u16 src;
+ __u16 dst;
+ } p16;
+ struct {
+ __be16 src;
+ __be16 dst;
+ } b16;
+ __u32 v32;
+ __be32 b32;
+};
+
+struct xt_hmark_info {
+ union nf_inet_addr src_mask;
+ union nf_inet_addr dst_mask;
+ union hmark_ports port_mask;
+ union hmark_ports port_set;
+ __u32 flags;
+ __u16 proto_mask;
+ __u32 hashrnd;
+ __u32 hmodulus;
+ __u32 hoffset; /* Mark offset to start from */
+};
+
+#endif /* XT_HMARK_H_ */
--
1.8.2.1
^ permalink raw reply related
* [PATCH] ethernet/arc/arc_emac - fix NAPI "work > weight" warning
From: Alexey Brodkin @ 2013-08-13 13:04 UTC (permalink / raw)
To: netdev
Cc: Alexey Brodkin, Vineet Gupta, Mischa Jonker, Arnd Bergmann,
Grant Likely, Rob Herring, Paul Gortmaker, David S. Miller,
linux-kernel
Initially I improperly set a boundary for maximum number of input
packets to process on NAPI poll ("work") so it might be more than
expected amount ("weight").
This was really harmless but seeing WARN_ON_ONCE on every device boot is
not nice. So trivial fix ("<" instead of "<=") is here.
Signed-off-by: Alexey Brodkin <abrodkin@synopsys.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Mischa Jonker <mjonker@synopsys.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Grant Likely <grant.likely@linaro.org>
Cc: Rob Herring <rob.herring@calxeda.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-kernel@vger.kernel.org
---
drivers/net/ethernet/arc/emac_main.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/net/ethernet/arc/emac_main.c b/drivers/net/ethernet/arc/emac_main.c
index f1b121e..55d79cb 100644
--- a/drivers/net/ethernet/arc/emac_main.c
+++ b/drivers/net/ethernet/arc/emac_main.c
@@ -199,7 +199,7 @@ static int arc_emac_rx(struct net_device *ndev, int budget)
struct arc_emac_priv *priv = netdev_priv(ndev);
unsigned int work_done;
- for (work_done = 0; work_done <= budget; work_done++) {
+ for (work_done = 0; work_done < budget; work_done++) {
unsigned int *last_rx_bd = &priv->last_rx_bd;
struct net_device_stats *stats = &priv->stats;
struct buffer_state *rx_buff = &priv->rx_buff[*last_rx_bd];
--
1.8.1.2
^ permalink raw reply related
* Re: [patch net] ipv6: do not create neighbor entries for local delivery
From: Marcelo Ricardo Leitner @ 2013-08-13 12:48 UTC (permalink / raw)
To: Hannes Frederic Sowa
Cc: Debabrata Banerjee, Jiri Pirko, davem@davemloft.net,
netdev@vger.kernel.org, Alexey Kuznetsov, jmorris@namei.org,
yoshfuji@linux-ipv6.org, Patrick McHardy, Banerjee, Debabrata,
Joshua Hunt
In-Reply-To: <20130812222642.GA27385@order.stressinduktion.org>
Em 12-08-2013 19:26, Hannes Frederic Sowa escreveu:
> Hi Marcelo!
>
> On Mon, Aug 12, 2013 at 03:09:19PM -0300, Marcelo Ricardo Leitner wrote:
>> Hannes, would something like this be acceptable? I'm hoping it's not too
>> ugly/hacky... as far as I could track back, input and output routines were
>> merged mainly due code similarity.
>
> Your idea seems sound and I don't think it is very ugly or hacky. It's
> as minimal as a stable-only patch should be. But we could simplify the
> logic a bit. ;) See below.
>
>> TPROXY scenario needs to not create this neighbor entries on INPUT path,
>> while Debabrata ping test needs it on OUTPUT path. This patch limits my
>> previous patch to INPUT only then.
>
> Yes, agreed. I don't see anything which could break because of this patch.
> So I would go with it.
>
>> Initial testing here seems good, TPROXY seems to be working as expected and
>> also the ping6 test.
>>
>> What do you think?
Aye Hannes, thanks! I'll rework the patch based on your points, do some more
testings in here and post it probably only by tomorrow.
Thanks!
Marcelo
>> diff --git a/net/ipv6/route.c b/net/ipv6/route.c
>> index 18ea73c..603f9d9 100644
>> --- a/net/ipv6/route.c
>> +++ b/net/ipv6/route.c
>> @@ -791,7 +791,7 @@ static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort,
>> }
>>
>> static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
>> - struct flowi6 *fl6, int flags)
>> + struct flowi6 *fl6, int flags, int output)
>
> bool input
>
>> {
>> struct fib6_node *fn;
>> struct rt6_info *rt, *nrt;
>> @@ -799,8 +799,11 @@ static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
>> int attempts = 3;
>> int err;
>> int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;
>> + int local = RTF_NONEXTHOP;
>>
>> strict |= flags & RT6_LOOKUP_F_IFACE;
>> + if (!output)
>> + local |= RTF_LOCAL;
>
>
> if (input)
> local |= RTF_LOCAL;
>
>>
>> relookup:
>> read_lock_bh(&table->tb6_lock);
>> @@ -820,7 +823,7 @@ restart:
>> read_unlock_bh(&table->tb6_lock);
>>
>> if (!dst_get_neighbour_raw(&rt->dst)
>> - && !(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_LOCAL)))
>> + && !(rt->rt6i_flags & local))
>> nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
>> else if (!(rt->dst.flags & DST_HOST))
>> nrt = rt6_alloc_clone(rt, &fl6->daddr);
>> @@ -864,7 +867,7 @@ out2:
>> static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
>> struct flowi6 *fl6, int flags)
>> {
>> - return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags);
>> + return ip6_pol_route(net, table, fl6->flowi6_iif, fl6, flags, 0);
>
> true);
>
>
>> }
>>
>> void ip6_route_input(struct sk_buff *skb)
>> @@ -890,7 +893,7 @@ void ip6_route_input(struct sk_buff *skb)
>> static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
>> struct flowi6 *fl6, int flags)
>> {
>> - return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags);
>> + return ip6_pol_route(net, table, fl6->flowi6_oif, fl6, flags, 1);
>
> false);
>
>> }
>>
>> struct dst_entry * ip6_route_output(struct net *net, const struct sock *sk,
>
> Thanks,
>
> Hannes
>
>
^ permalink raw reply
* Re: ipsec smp scalability and cpu use fairness (softirqs)
From: Timo Teras @ 2013-08-13 12:41 UTC (permalink / raw)
To: Steffen Klassert; +Cc: Andrew Collins, netdev
In-Reply-To: <20130813115652.GE26773@secunet.com>
On Tue, 13 Aug 2013 13:56:52 +0200
Steffen Klassert <steffen.klassert@secunet.com> wrote:
> On Tue, Aug 13, 2013 at 02:33:25PM +0300, Timo Teras wrote:
> >
> > I've been now playing with pcrypt. It seems to not give significant
> > boost in throughput. I've setup the cpumaps properly, and top says
> > the work is distributed to appropriate kworkers, but for some reason
> > throughput does not get any better. I've tested with iperf in both
> > udp and tcp modes, with various amounts of threads.
> >
> > Is there any more synchronization points for single SA that might
> > limit throughput? I've been testing with auth hmac(sha1), enc
> > cbc(aes) - according to metric the CPUs are still largely idle
> > instead of processing more data for better throughput. aes-gcm
> > (without pcrypt) achieves better throughput even saturating my test
> > box links.
> >
> > Any pointers what to test, or to pinpoint the bottleneck?
> >
>
> The only pitfall that comes to my mind is that pcrypt must be
> instantiated before inserting the states. Your /proc/crypto
> should show something like:
>
> name : authenc(hmac(sha1),cbc(aes))
> driver : pcrypt(authenc(hmac(sha1-generic),cbc(aes-asm)))
> module : pcrypt
> priority : 2100
> refcnt : 1
> selftest : passed
> type : aead
> async : yes
> blocksize : 16
> ivsize : 16
> maxauthsize : 20
> geniv : <built-in>
>
> pcrypt is now instantiated, e.g. all new IPsec states (that do
> hmac-sha1, cbc-aes) will use it, adding new states increase the
> refcount.
>
> I'll do some tests with current net-next on my own tomorrow and let
> you know about the results.
Yes, I've got pcrypt there. Apparently I had some of the cpu bindings
not right, so now it's looking a lot better. But it seems that
ksoftirqd on one of the CPUs becomes first bottleneck. I'll try to
figure out why.
Thanks on all the info so far, will continue experimenting here too.
^ permalink raw reply
* RE: [PATCH net v5 0/5] bnx2x: fixes
From: Ariel Elior @ 2013-08-13 12:38 UTC (permalink / raw)
To: Benjamin Poirier, Dmitry Kravkov
Cc: davem@davemloft.net, netdev@vger.kernel.org, Eilon Greenstein
In-Reply-To: <20130813123043.GA30192@d2.synalogic.ca>
> I'm confused. Wasn't "[PATCH net v4 1/6] bnx2x: properly initialize
> statistic counters" supposed to fix a race condition? According to
> earlier communication with Ariel:
> In this issue a race condition at driver startup causes a second
> statistics query to be sent before the first one completes,
> resulting in a firmware assert and a stuck chip. A patch was
> sent upstream fixing this:
> http://patchwork.ozlabs.org/patch/264810/
As I explicitly mentioned in the communique which you quoted above, the patch was sent but not yet accepted.
This is precisely the upstream process - patches are being sent, reviewed and sometimes rejected and revised.
If you have further questions please address them to me - the technical forum is no place for this kind of discussion.
Thanks,
Ariel
^ permalink raw reply
* RE: [PATCH net-next 1/3] net/usb/r8152: support aggregation
From: hayeswang @ 2013-08-13 12:32 UTC (permalink / raw)
To: 'Oliver Neukum'; +Cc: netdev, linux-kernel, linux-usb
In-Reply-To: <1376383742.1681.1.camel@linux-fkkt.site>
Oliver Neukum [mailto:oneukum@suse.de]
> Sent: Tuesday, August 13, 2013 4:49 PM
> To: Hayeswang
> Cc: netdev@vger.kernel.org; linux-kernel@vger.kernel.org;
> linux-usb@vger.kernel.org
> Subject: Re: [PATCH net-next 1/3] net/usb/r8152: support aggregation
>
[...]
> > + len_used = 0;
> > + rx_desc = agg->head;
> > + rx_data = agg->head;
> > + smp_wmb();
> > + pkt_len = le32_to_cpu(rx_desc->opts1) & RX_LEN_MASK;
> > + len_used += sizeof(struct rx_desc) + pkt_len;
> > +
> > + while (urb->actual_length >= len_used) {
> > + if (pkt_len < ETH_ZLEN)
> > + break;
> > +
> > + pkt_len -= 4; /* CRC */
> > + rx_data += sizeof(struct rx_desc);
> > +
> > + skb = netdev_alloc_skb_ip_align(netdev,
> > pkt_len);
> > + if (!skb) {
> > + stats->rx_dropped++;
> > + break;
> > + }
> > + memcpy(skb->data, rx_data, pkt_len);
> > + skb_put(skb, pkt_len);
> > + skb->protocol = eth_type_trans(skb, netdev);
> > + netif_rx(skb);
> > + stats->rx_packets++;
> > + stats->rx_bytes += pkt_len;
> > +
> > + rx_data = rx_agg_align(rx_data +
> pkt_len + 4);
> > + rx_desc = (struct rx_desc *)rx_data;
> > + smp_wmb();
>
> Against what is the memory barrier?
Excuse me. I don't understand your question. Do you mean the function should not
be used here?
Best Regards,
Hayes
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox