diff options
author | Jason Wang <jasowang@redhat.com> | 2018-01-16 16:31:02 +0800 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-01-17 15:32:10 -0500 |
commit | aff3d70a07fffc0abb53663e4a4acb059d2f36af (patch) | |
tree | 6274d9253d5cd93105e5759e616212876ceb2ec9 | |
parent | cd5681d7d8903bf43a571aaf96cf6d2e2e00118c (diff) | |
download | linux-aff3d70a07fffc0abb53663e4a4acb059d2f36af.tar.bz2 |
tun: allow to attach ebpf socket filter
This patch allows userspace to attach eBPF filter to tun. This will
allow to implement VM dataplane filtering in a more efficient way
compared to cBPF filter by allowing either qemu or libvirt to
attach eBPF filter to tun.
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
-rw-r--r-- | drivers/net/tun.c | 38 | ||||
-rw-r--r-- | include/uapi/linux/if_tun.h | 1 |
2 files changed, 35 insertions, 4 deletions
diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 76197ede22a9..170a3e89b5af 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -239,6 +239,12 @@ struct tun_struct { struct tun_pcpu_stats __percpu *pcpu_stats; struct bpf_prog __rcu *xdp_prog; struct tun_prog __rcu *steering_prog; + struct tun_prog __rcu *filter_prog; +}; + +struct veth { + __be16 h_vlan_proto; + __be16 h_vlan_TCI; }; bool tun_is_xdp_buff(void *ptr) @@ -1036,12 +1042,25 @@ static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) #endif } +static unsigned int run_ebpf_filter(struct tun_struct *tun, + struct sk_buff *skb, + int len) +{ + struct tun_prog *prog = rcu_dereference(tun->filter_prog); + + if (prog) + len = bpf_prog_run_clear_cb(prog->prog, skb); + + return len; +} + /* Net device start xmit */ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); int txq = skb->queue_mapping; struct tun_file *tfile; + int len = skb->len; rcu_read_lock(); tfile = rcu_dereference(tun->tfiles[txq]); @@ -1067,6 +1086,15 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) sk_filter(tfile->socket.sk, skb)) goto drop; + len = run_ebpf_filter(tun, skb, len); + + /* Trim extra bytes since we may insert vlan proto & TCI + * in tun_put_user(). + */ + len -= skb_vlan_tag_present(skb) ? sizeof(struct veth) : 0; + if (len <= 0 || pskb_trim(skb, len)) + goto drop; + if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC))) goto drop; @@ -2054,10 +2082,7 @@ static ssize_t tun_put_user(struct tun_struct *tun, if (vlan_hlen) { int ret; - struct { - __be16 h_vlan_proto; - __be16 h_vlan_TCI; - } veth; + struct veth veth; veth.h_vlan_proto = skb->vlan_proto; veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb)); @@ -2225,6 +2250,7 @@ static void tun_free_netdev(struct net_device *dev) tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); __tun_set_ebpf(tun, &tun->steering_prog, NULL); + __tun_set_ebpf(tun, &tun->filter_prog, NULL); } static void tun_setup(struct net_device *dev) @@ -3019,6 +3045,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, ret = tun_set_ebpf(tun, &tun->steering_prog, argp); break; + case TUNSETFILTEREBPF: + ret = tun_set_ebpf(tun, &tun->filter_prog, argp); + break; + default: ret = -EINVAL; break; diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h index fb38c1797131..ee432cd3018c 100644 --- a/include/uapi/linux/if_tun.h +++ b/include/uapi/linux/if_tun.h @@ -58,6 +58,7 @@ #define TUNSETVNETBE _IOW('T', 222, int) #define TUNGETVNETBE _IOR('T', 223, int) #define TUNSETSTEERINGEBPF _IOR('T', 224, int) +#define TUNSETFILTEREBPF _IOR('T', 225, int) /* TUNSETIFF ifr flags */ #define IFF_TUN 0x0001 |