After an lwt prog pushed an IPv6 header, bpf_lwt_xmit_reroute() hands
skb->sk to ip6_dst_lookup_flow(). When the flow has no source address,
the lookup reads inet6_sk(sk)->srcprefs, and inet6_sk() is NULL for
example when:
- skb->sk is a request_sock, e.g. for a SYN-ACK.
- skb->sk is an IPv4 socket, the IPv6 header was pushed on an IPv4
packet.
KASAN: null-ptr-deref in range [0x0000000000000040-0x0000000000000047]
RIP: 0010:ip6_route_output_flags+0x279/0x4c0
Call Trace:
ip6_dst_lookup_tail.constprop.0+0x26e/0x1050
ip6_dst_lookup_flow+0x101/0x1e0
bpf_lwt_xmit_reroute+0xc18/0x18b0
bpf_xmit+0x28f/0x400
lwtunnel_xmit+0x2a7/0x620
ip_finish_output2+0xa67/0x1f80
__ip_finish_output+0x510/0x7e0
ip_finish_output+0x2f/0x320
ip_output+0x171/0x3e0
ip_push_pending_frames+0x200/0x260
raw_sendmsg+0x114c/0x3680
inet_sendmsg+0xdf/0x100
__sys_sendto+0x3ef/0x500
__x64_sys_sendto+0xe0/0x1b0
x64_sys_call+0x1375/0x27e0
do_syscall_64+0xe7/0x630
entry_SYSCALL_64_after_hwframe+0x76/0x7e
Pass the full socket, and no socket if it is not an IPv6 one while the
flow has no source address.
Fixes: 3bd0b15281af ("bpf: add handling of BPF_LWT_REROUTE to lwt_bpf.c")
Signed-off-by: Jiayuan Chen
---
net/core/lwt_bpf.c | 6 +++++-
1 file changed, 5 insertions(+), 1 deletion(-)
diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index 72c86ff2a847..33f710d92106 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -278,7 +278,11 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb)
fl6.daddr = iph6->daddr;
fl6.saddr = iph6->saddr;
- dst = ip6_dst_lookup_flow(net, skb->sk, &fl6, NULL);
+ if (ipv6_addr_any(&fl6.saddr) &&
+ sk && sk->sk_family != AF_INET6)
+ sk = NULL;
+
+ dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
goto err;
--
2.43.0
Add a test where an lwt_xmit prog pushes an IPv6 header with a ::
source on an IPv4 packet and reroutes. On an unfixed kernel this
dereferences inet6_sk() of the IPv4 socket and crashes; here reaching
the end is the pass.
Signed-off-by: Jiayuan Chen
---
.../selftests/bpf/prog_tests/lwt_reroute.c | 20 ++++++++++++++--
.../selftests/bpf/progs/test_lwt_reroute.c | 24 +++++++++++++++++++
2 files changed, 42 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
index 6c50c0f63f43..01387c0f1b19 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
@@ -18,8 +18,8 @@
*
* ip route add 10.0.0.0/24 encap bpf xmit sec "" dev link_err
*
- * Here is statically defined to test_lwt_reroute.bpf.o, and it contains
- * a single test program entry. This program sets packet mark by last byte of
+ * Here is statically defined to test_lwt_reroute.bpf.o.
+ * The lwt_xmit program sets packet mark by last byte of
* the IPv4 daddr. For example, a packet going to 1.2.3.4 will receive a skb
* mark 4. A packet will only be marked once, and IP x.x.x.0 will be skipped
* to avoid route loop. We didn't use generated BPF skeleton since the
@@ -42,6 +42,7 @@
* --------------------------------
* 1. Reroute to a running tun device
* 2. Reroute to a device where qdisc drop
+ * 3. Reroute an IPv4 packet with a pushed IPv6 header
*
* For case 1, ping packets should be received by the tun device.
*
@@ -241,11 +242,26 @@ static void test_lwt_reroute_qdisc_dropped(void)
close(tun_fd);
}
+static void test_lwt_reroute_push6(void)
+{
+ SYS(out, "ip link add link_err type dummy");
+ SYS(out, "ip link set lo up");
+ SYS(out, "ip addr add dev lo " LOCAL_SRC "/32");
+ SYS(out, "ip link set link_err up");
+ SYS(out, "ip route add %s dev link_err encap bpf xmit obj %s sec push6_zerosrc",
+ TEST_CIDR, BPF_OBJECT);
+
+ ping_once("10.0.0.2");
+out:
+ return;
+}
+
static void *test_lwt_reroute_run(void *arg)
{
netns_delete();
RUN_TEST(lwt_reroute_normal_xmit);
RUN_TEST(lwt_reroute_qdisc_dropped);
+ RUN_TEST(lwt_reroute_push6);
return NULL;
}
diff --git a/tools/testing/selftests/bpf/progs/test_lwt_reroute.c b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
index 1dc64351929c..c969962926e6 100644
--- a/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
+++ b/tools/testing/selftests/bpf/progs/test_lwt_reroute.c
@@ -4,7 +4,9 @@
#include
#include
#include
+#include
#include
+#include
/* This function extracts the last byte of the daddr, and uses it
* as output dev index.
@@ -33,4 +35,26 @@ int test_lwt_reroute(struct __sk_buff *skb)
return BPF_LWT_REROUTE;
}
+SEC("push6_zerosrc")
+int test_lwt_reroute_push6(struct __sk_buff *skb)
+{
+ struct ipv6hdr h = {};
+
+ h.version = 6;
+ h.payload_len = bpf_htons(skb->len);
+ h.nexthdr = IPPROTO_IPIP;
+ h.hop_limit = 64;
+ /* 2001:db8::3, a fake address */
+ h.daddr.s6_addr[0] = 0x20;
+ h.daddr.s6_addr[1] = 0x01;
+ h.daddr.s6_addr[2] = 0x0d;
+ h.daddr.s6_addr[3] = 0xb8;
+ h.daddr.s6_addr[15] = 0x03;
+
+ if (bpf_lwt_push_encap(skb, BPF_LWT_ENCAP_IP, &h, sizeof(h)))
+ return BPF_DROP;
+
+ return BPF_LWT_REROUTE;
+}
+
char _license[] SEC("license") = "GPL";
--
2.43.0