| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Sun, 28 Oct 2018 21:02:45 -0700
From: Nitin Hande <nitin.hande@...il.com>
To: daniel@...earbox.net
Cc: Alexei Starovoitov <alexei.starovoitov@...il.com>,
Joe Stringer <joe@...d.net.nz>, Martin Lau <kafai@...com>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
Jesper Dangaard Brouer <brouer@...hat.com>,
John Fastabend <john.fastabend@...il.com>
Subject: [PATCH v2 bpf-next] bpf: Extend the sk_lookup() helper to XDP
hookpoint.
This patch proposes to extend the sk_lookup() BPF API to the
XDP hookpoint. The sk_lookup() helper supports a lookup
on incoming packet to find the corresponding socket that will
receive this packet. Current support for this BPF API is
at the tc hookpoint. This patch will extend this API at XDP
hookpoint. A XDP program can map the incoming packet to the
5-tuple parameter and invoke the API to find the corresponding
socket structure.
Signed-off-by: Nitin Hande <Nitin.Hande@...il.com>
---
v1->v2
- For sockets with reuseport socket option, there was a case
where the sk returned by the helper can vary due to the
absence of skb at XDP hookpoint as compared to TC. v2 removes
that variance by passing NULL for skb from both TC and XDP
hookpoint. As a result, for reuseport sockets, the helper
will now consistently return the same sk from reuse->socks[]
using the hash of the packet after being invoked from either
TC or XDP hookpoint. This also makes the helper stateless,
else there are certain scenarios where upper layer records
skb.
- Add relevant documentation to the helper.
---
include/uapi/linux/bpf.h | 4 ++
net/core/filter.c | 105 ++++++++++++++++++++++++++++++++-------
2 files changed, 90 insertions(+), 19 deletions(-)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 852dc17ab47a..47d606d744cc 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2201,6 +2201,8 @@ union bpf_attr {
* **CONFIG_NET** configuration option.
* Return
* Pointer to *struct bpf_sock*, or NULL in case of failure.
+ * For sockets with reuseport option, *struct bpf_sock*
+ * return is from reuse->socks[] using hash of the packet.
*
* struct bpf_sock *bpf_sk_lookup_udp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u32 netns, u64 flags)
* Description
@@ -2233,6 +2235,8 @@ union bpf_attr {
* **CONFIG_NET** configuration option.
* Return
* Pointer to *struct bpf_sock*, or NULL in case of failure.
+ * For sockets with reuseport option, *struct bpf_sock*
+ * return is from reuse->socks[] using hash of the packet.
*
* int bpf_sk_release(struct bpf_sock *sk)
* Description
diff --git a/net/core/filter.c b/net/core/filter.c
index 35c6933c2622..bc20b5bfcaf1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4825,38 +4825,32 @@ static const struct bpf_func_proto bpf_lwt_seg6_adjust_srh_proto = {
#ifdef CONFIG_INET
static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
- struct sk_buff *skb, u8 family, u8 proto)
+ int dif, int sdif, u8 family, u8 proto)
{
bool refcounted = false;
struct sock *sk = NULL;
- int dif = 0;
-
- if (skb->dev)
- dif = skb->dev->ifindex;
if (family == AF_INET) {
__be32 src4 = tuple->ipv4.saddr;
__be32 dst4 = tuple->ipv4.daddr;
- int sdif = inet_sdif(skb);
if (proto == IPPROTO_TCP)
- sk = __inet_lookup(net, &tcp_hashinfo, skb, 0,
+ sk = __inet_lookup(net, &tcp_hashinfo, NULL, 0,
src4, tuple->ipv4.sport,
dst4, tuple->ipv4.dport,
dif, sdif, &refcounted);
else
sk = __udp4_lib_lookup(net, src4, tuple->ipv4.sport,
dst4, tuple->ipv4.dport,
- dif, sdif, &udp_table, skb);
+ dif, sdif, &udp_table, NULL);
#if IS_ENABLED(CONFIG_IPV6)
} else {
struct in6_addr *src6 = (struct in6_addr *)&tuple->ipv6.saddr;
struct in6_addr *dst6 = (struct in6_addr *)&tuple->ipv6.daddr;
u16 hnum = ntohs(tuple->ipv6.dport);
- int sdif = inet6_sdif(skb);
if (proto == IPPROTO_TCP)
- sk = __inet6_lookup(net, &tcp_hashinfo, skb, 0,
+ sk = __inet6_lookup(net, &tcp_hashinfo, NULL, 0,
src6, tuple->ipv6.sport,
dst6, hnum,
dif, sdif, &refcounted);
@@ -4865,7 +4859,7 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
src6, tuple->ipv6.sport,
dst6, hnum,
dif, sdif,
- &udp_table, skb);
+ &udp_table, NULL);
#endif
}
@@ -4882,31 +4876,33 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
* callers to satisfy BPF_CALL declarations.
*/
static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
- u8 proto, u64 netns_id, u64 flags)
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+ u64 flags)
{
- struct net *caller_net;
struct sock *sk = NULL;
u8 family = AF_UNSPEC;
struct net *net;
+ int sdif;
family = len == sizeof(tuple->ipv4) ? AF_INET : AF_INET6;
if (unlikely(family == AF_UNSPEC || netns_id > U32_MAX || flags))
goto out;
- if (skb->dev)
- caller_net = dev_net(skb->dev);
+ if (family == AF_INET)
+ sdif = inet_sdif(skb);
else
- caller_net = sock_net(skb->sk);
+ sdif = inet6_sdif(skb);
+
if (netns_id) {
net = get_net_ns_by_id(caller_net, netns_id);
if (unlikely(!net))
goto out;
- sk = sk_lookup(net, tuple, skb, family, proto);
+ sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
put_net(net);
} else {
net = caller_net;
- sk = sk_lookup(net, tuple, skb, family, proto);
+ sk = sk_lookup(net, tuple, ifindex, sdif, family, proto);
}
if (sk)
@@ -4915,6 +4911,25 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
return (unsigned long) sk;
}
+static unsigned long
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+ u8 proto, u64 netns_id, u64 flags)
+{
+ struct net *caller_net;
+ int ifindex;
+
+ if (skb->dev) {
+ caller_net = dev_net(skb->dev);
+ ifindex = skb->dev->ifindex;
+ } else {
+ caller_net = sock_net(skb->sk);
+ ifindex = 0;
+ }
+
+ return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex,
+ proto, netns_id, flags);
+}
+
BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
{
@@ -4964,6 +4979,50 @@ static const struct bpf_func_proto bpf_sk_release_proto = {
.ret_type = RET_INTEGER,
.arg1_type = ARG_PTR_TO_SOCKET,
};
+
+BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+ struct net *caller_net = dev_net(ctx->rxq->dev);
+ int ifindex = ctx->rxq->dev->ifindex;
+
+ return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
+ IPPROTO_UDP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
+ .func = bpf_xdp_sk_lookup_udp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
+
+BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
+ struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+ struct net *caller_net = dev_net(ctx->rxq->dev);
+ int ifindex = ctx->rxq->dev->ifindex;
+
+ return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
+ IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
+ .func = bpf_xdp_sk_lookup_tcp,
+ .gpl_only = false,
+ .pkt_access = true,
+ .ret_type = RET_PTR_TO_SOCKET_OR_NULL,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_PTR_TO_MEM,
+ .arg3_type = ARG_CONST_SIZE,
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+};
#endif /* CONFIG_INET */
bool bpf_helper_changes_pkt_data(void *func)
@@ -5214,6 +5273,14 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_xdp_adjust_tail_proto;
case BPF_FUNC_fib_lookup:
return &bpf_xdp_fib_lookup_proto;
+#ifdef CONFIG_INET
+ case BPF_FUNC_sk_lookup_udp:
+ return &bpf_xdp_sk_lookup_udp_proto;
+ case BPF_FUNC_sk_lookup_tcp:
+ return &bpf_xdp_sk_lookup_tcp_proto;
+ case BPF_FUNC_sk_release:
+ return &bpf_sk_release_proto;
+#endif
default:
return bpf_base_func_proto(func_id);
}
--
2.19.1
Powered by blists - more mailing lists