diff options
author | David S. Miller <davem@davemloft.net> | 2018-09-25 20:29:38 -0700 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2018-09-25 20:29:38 -0700 |
commit | 105bc1306e9b29c2aa2783b9524f7aec9b5a5b1f (patch) | |
tree | a3350d692a612e9536033e203200bd8eb8c47f48 /net/core/flow_dissector.c | |
parent | 3475372ff60e4181d3845ed605958daf71c3e3b8 (diff) | |
parent | d0e13a1488ad30dc3c2c9347b931cb10f892e3a4 (diff) |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next
Daniel Borkmann says:
====================
pull-request: bpf-next 2018-09-25
The following pull-request contains BPF updates for your *net-next* tree.
The main changes are:
1) Allow for RX stack hardening by implementing the kernel's flow
dissector in BPF. Idea was originally presented at netconf 2017 [0].
Quote from merge commit:
[...] Because of the rigorous checks of the BPF verifier, this
provides significant security guarantees. In particular, the BPF
flow dissector cannot get inside of an infinite loop, as with
CVE-2013-4348, because BPF programs are guaranteed to terminate.
It cannot read outside of packet bounds, because all memory accesses
are checked. Also, with BPF the administrator can decide which
protocols to support, reducing potential attack surface. Rarely
encountered protocols can be excluded from dissection and the
program can be updated without kernel recompile or reboot if a
bug is discovered. [...]
Also, a sample flow dissector has been implemented in BPF as part
of this work, from Petar and Willem.
[0] http://vger.kernel.org/netconf2017_files/rx_hardening_and_udp_gso.pdf
2) Add support for bpftool to list currently active attachment
points of BPF networking programs providing a quick overview
similar to bpftool's perf subcommand, from Yonghong.
3) Fix a verifier pruning instability bug where a union member
from the register state was not cleared properly leading to
branches not being pruned despite them being valid candidates,
from Alexei.
4) Various smaller fast-path optimizations in XDP's map redirect
code, from Jesper.
5) Enable to recognize BPF_MAP_TYPE_REUSEPORT_SOCKARRAY maps
in bpftool, from Roman.
6) Remove a duplicate check in libbpf that probes for function
storage, from Taeung.
7) Fix an issue in test_progs by avoid checking for errno since
on success its value should not be checked, from Mauricio.
8) Fix unused variable warning in bpf_getsockopt() helper when
CONFIG_INET is not configured, from Anders.
9) Fix a compilation failure in the BPF sample code's use of
bpf_flow_keys, from Prashant.
10) Minor cleanups in BPF code, from Yue and Zhong.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/core/flow_dissector.c')
-rw-r--r-- | net/core/flow_dissector.c | 140 |
1 files changed, 140 insertions, 0 deletions
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 1e745db44cc3..676f3ad629f9 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -25,6 +25,9 @@ #include <net/flow_dissector.h> #include <scsi/fc/fc_fcoe.h> #include <uapi/linux/batadv_packet.h> +#include <linux/bpf.h> + +static DEFINE_MUTEX(flow_dissector_mutex); static void dissector_set_key(struct flow_dissector *flow_dissector, enum flow_dissector_key_id key_id) @@ -62,6 +65,44 @@ void skb_flow_dissector_init(struct flow_dissector *flow_dissector, } EXPORT_SYMBOL(skb_flow_dissector_init); +int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, + struct bpf_prog *prog) +{ + struct bpf_prog *attached; + struct net *net; + + net = current->nsproxy->net_ns; + mutex_lock(&flow_dissector_mutex); + attached = rcu_dereference_protected(net->flow_dissector_prog, + lockdep_is_held(&flow_dissector_mutex)); + if (attached) { + /* Only one BPF program can be attached at a time */ + mutex_unlock(&flow_dissector_mutex); + return -EEXIST; + } + rcu_assign_pointer(net->flow_dissector_prog, prog); + mutex_unlock(&flow_dissector_mutex); + return 0; +} + +int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +{ + struct bpf_prog *attached; + struct net *net; + + net = current->nsproxy->net_ns; + mutex_lock(&flow_dissector_mutex); + attached = rcu_dereference_protected(net->flow_dissector_prog, + lockdep_is_held(&flow_dissector_mutex)); + if (!attached) { + mutex_unlock(&flow_dissector_mutex); + return -ENOENT; + } + bpf_prog_put(attached); + RCU_INIT_POINTER(net->flow_dissector_prog, NULL); + mutex_unlock(&flow_dissector_mutex); + return 0; +} /** * skb_flow_get_be16 - extract be16 entity * @skb: sk_buff to extract from @@ -588,6 +629,60 @@ static bool skb_flow_dissect_allowed(int *num_hdrs) return (*num_hdrs <= MAX_FLOW_DISSECT_HDRS); } +static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, + struct flow_dissector *flow_dissector, + void *target_container) +{ + struct flow_dissector_key_control *key_control; + struct flow_dissector_key_basic *key_basic; + struct flow_dissector_key_addrs *key_addrs; + struct flow_dissector_key_ports *key_ports; + + key_control = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_CONTROL, + target_container); + key_control->thoff = flow_keys->thoff; + if (flow_keys->is_frag) + key_control->flags |= FLOW_DIS_IS_FRAGMENT; + if (flow_keys->is_first_frag) + key_control->flags |= FLOW_DIS_FIRST_FRAG; + if (flow_keys->is_encap) + key_control->flags |= FLOW_DIS_ENCAPSULATION; + + key_basic = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_BASIC, + target_container); + key_basic->n_proto = flow_keys->n_proto; + key_basic->ip_proto = flow_keys->ip_proto; + + if (flow_keys->addr_proto == ETH_P_IP && + dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) { + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV4_ADDRS, + target_container); + key_addrs->v4addrs.src = flow_keys->ipv4_src; + key_addrs->v4addrs.dst = flow_keys->ipv4_dst; + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + } else if (flow_keys->addr_proto == ETH_P_IPV6 && + dissector_uses_key(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS)) { + key_addrs = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_IPV6_ADDRS, + target_container); + memcpy(&key_addrs->v6addrs, &flow_keys->ipv6_src, + sizeof(key_addrs->v6addrs)); + key_control->addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; + } + + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_PORTS)) { + key_ports = skb_flow_dissector_target(flow_dissector, + FLOW_DISSECTOR_KEY_PORTS, + target_container); + key_ports->src = flow_keys->sport; + key_ports->dst = flow_keys->dport; + } +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -619,6 +714,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; + struct bpf_prog *attached = NULL; int num_hdrs = 0; u8 ip_proto = 0; bool ret; @@ -658,6 +754,50 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); + rcu_read_lock(); + if (skb) { + if (skb->dev) + attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog); + else if (skb->sk) + attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog); + else + WARN_ON_ONCE(1); + } + if (attached) { + /* Note that even though the const qualifier is discarded + * throughout the execution of the BPF program, all changes(the + * control block) are reverted after the BPF program returns. + * Therefore, __skb_flow_dissect does not alter the skb. + */ + struct bpf_flow_keys flow_keys = {}; + struct bpf_skb_data_end cb_saved; + struct bpf_skb_data_end *cb; + u32 result; + + cb = (struct bpf_skb_data_end *)skb->cb; + + /* Save Control Block */ + memcpy(&cb_saved, cb, sizeof(cb_saved)); + memset(cb, 0, sizeof(cb_saved)); + + /* Pass parameters to the BPF program */ + cb->qdisc_cb.flow_keys = &flow_keys; + flow_keys.nhoff = nhoff; + + bpf_compute_data_pointers((struct sk_buff *)skb); + result = BPF_PROG_RUN(attached, skb); + + /* Restore state */ + memcpy(cb, &cb_saved, sizeof(cb_saved)); + + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, + target_container); + key_control->thoff = min_t(u16, key_control->thoff, skb->len); + rcu_read_unlock(); + return result == BPF_OK; + } + rcu_read_unlock(); + if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { struct ethhdr *eth = eth_hdr(skb); |