Linux Ethernet Bridging - Jul 2019 - [Bridge] [PATCH net 2/4] net: bridge: mcast: fix stale ipv6 hdr pointer when handling v6 query

Hi,
In the bridge driver we have a couple of places which call pskb_may_pull
but we've cached skb pointers before that and use them after which can
lead to out-of-bounds/stale pointer use. I've had these in my "to
fix"
list for some time and now we got a report (patch 01) so here they are.
Patches 02-04 are fixes based on code inspection. Also patch 01 was
tested by Martin Weinelt, Martin if you don't mind please add your
tested-by tag to it by replying with Tested-by: name <email>.
I've also briefly tested the set by trying to exercise those code paths.

Thanks,
 Nik

Nikolay Aleksandrov (4):
  net: bridge: mcast: fix stale nsrcs pointer in igmp3/mld2 report
    handling
  net: bridge: mcast: fix stale ipv6 hdr pointer when handling v6 query
  net: bridge: don't cache ether dest pointer on input
  net: bridge: stp: don't cache eth dest pointer before skb pull

 net/bridge/br_input.c     |  8 +++-----
 net/bridge/br_multicast.c | 23 +++++++++++++----------
 net/bridge/br_stp_bpdu.c  |  3 +--
 3 files changed, 17 insertions(+), 17 deletions(-)

-- 
2.21.0

We take a pointer to grec prior to calling pskb_may_pull and use it
afterwards to get nsrcs so record nsrcs before the pull when handling
igmp3 and we get a pointer to nsrcs and call pskb_may_pull when handling
mld2 which again could lead to reading 2 bytes out-of-bounds.

 ================================================================= BUG: KASAN:
use-after-free in br_multicast_rcv+0x480c/0x4ad0 [bridge]
 Read of size 2 at addr ffff8880421302b4 by task ksoftirqd/1/16

 CPU: 1 PID: 16 Comm: ksoftirqd/1 Tainted: G           OE     5.2.0-rc6+ #1
 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.10.2-1 04/01/2014
 Call Trace:
  dump_stack+0x71/0xab
  print_address_description+0x6a/0x280
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  __kasan_report+0x152/0x1aa
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  ? br_multicast_rcv+0x480c/0x4ad0 [bridge]
  kasan_report+0xe/0x20
  br_multicast_rcv+0x480c/0x4ad0 [bridge]
  ? br_multicast_disable_port+0x150/0x150 [bridge]
  ? ktime_get_with_offset+0xb4/0x150
  ? __kasan_kmalloc.constprop.6+0xa6/0xf0
  ? __netif_receive_skb+0x1b0/0x1b0
  ? br_fdb_update+0x10e/0x6e0 [bridge]
  ? br_handle_frame_finish+0x3c6/0x11d0 [bridge]
  br_handle_frame_finish+0x3c6/0x11d0 [bridge]
  ? br_pass_frame_up+0x3a0/0x3a0 [bridge]
  ? virtnet_probe+0x1c80/0x1c80 [virtio_net]
  br_handle_frame+0x731/0xd90 [bridge]
  ? select_idle_sibling+0x25/0x7d0
  ? br_handle_frame_finish+0x11d0/0x11d0 [bridge]
  __netif_receive_skb_core+0xced/0x2d70
  ? virtqueue_get_buf_ctx+0x230/0x1130 [virtio_ring]
  ? do_xdp_generic+0x20/0x20
  ? virtqueue_napi_complete+0x39/0x70 [virtio_net]
  ? virtnet_poll+0x94d/0xc78 [virtio_net]
  ? receive_buf+0x5120/0x5120 [virtio_net]
  ? __netif_receive_skb_one_core+0x97/0x1d0
  __netif_receive_skb_one_core+0x97/0x1d0
  ? __netif_receive_skb_core+0x2d70/0x2d70
  ? _raw_write_trylock+0x100/0x100
  ? __queue_work+0x41e/0xbe0
  process_backlog+0x19c/0x650
  ? _raw_read_lock_irq+0x40/0x40
  net_rx_action+0x71e/0xbc0
  ? __switch_to_asm+0x40/0x70
  ? napi_complete_done+0x360/0x360
  ? __switch_to_asm+0x34/0x70
  ? __switch_to_asm+0x40/0x70
  ? __schedule+0x85e/0x14d0
  __do_softirq+0x1db/0x5f9
  ? takeover_tasklets+0x5f0/0x5f0
  run_ksoftirqd+0x26/0x40
  smpboot_thread_fn+0x443/0x680
  ? sort_range+0x20/0x20
  ? schedule+0x94/0x210
  ? __kthread_parkme+0x78/0xf0
  ? sort_range+0x20/0x20
  kthread+0x2ae/0x3a0
  ? kthread_create_worker_on_cpu+0xc0/0xc0
  ret_from_fork+0x35/0x40

 The buggy address belongs to the page:
 page:ffffea0001084c00 refcount:0 mapcount:-128 mapping:0000000000000000
index:0x0
 flags: 0xffffc000000000()
 raw: 00ffffc000000000 ffffea0000cfca08 ffffea0001098608 0000000000000000
 raw: 0000000000000000 0000000000000003 00000000ffffff7f 0000000000000000
 page dumped because: kasan: bad access detected

 Memory state around the buggy address:
 ffff888042130180: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff888042130200: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 > ffff888042130280: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
                                     ^
 ffff888042130300: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ffff888042130380: ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff ff
 ================================================================= Disabling
lock debugging due to kernel taint

Fixes: bc8c20acaea1 ("bridge: multicast: treat igmpv3 report with INCLUDE
and no sources as a leave")
Reported-by: Martin Weinelt <martin at linuxlounge.net>
Signed-off-by: Nikolay Aleksandrov <nikolay at cumulusnetworks.com>
---
 net/bridge/br_multicast.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index de22c8fbbb15..f37897e7b97b 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -911,6 +911,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge
*br,
 	int type;
 	int err = 0;
 	__be32 group;
+	u16 nsrcs;
 
 	ih = igmpv3_report_hdr(skb);
 	num = ntohs(ih->ngrec);
@@ -924,8 +925,9 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge
*br,
 		grec = (void *)(skb->data + len - sizeof(*grec));
 		group = grec->grec_mca;
 		type = grec->grec_type;
+		nsrcs = ntohs(grec->grec_nsrcs);
 
-		len += ntohs(grec->grec_nsrcs) * 4;
+		len += nsrcs * 4;
 		if (!ip_mc_may_pull(skb, len))
 			return -EINVAL;
 
@@ -946,7 +948,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge
*br,
 		src = eth_hdr(skb)->h_source;
 		if ((type == IGMPV3_CHANGE_TO_INCLUDE ||
 		     type == IGMPV3_MODE_IS_INCLUDE) &&
-		    ntohs(grec->grec_nsrcs) == 0) {
+		    nsrcs == 0) {
 			br_ip4_multicast_leave_group(br, port, group, vid, src);
 		} else {
 			err = br_ip4_multicast_add_group(br, port, group, vid,
@@ -983,7 +985,8 @@ static int br_ip6_multicast_mld2_report(struct net_bridge
*br,
 	len = skb_transport_offset(skb) + sizeof(*icmp6h);
 
 	for (i = 0; i < num; i++) {
-		__be16 *nsrcs, _nsrcs;
+		__be16 *_nsrcs, __nsrcs;
+		u16 nsrcs;
 
 		nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs);
 
@@ -991,12 +994,13 @@ static int br_ip6_multicast_mld2_report(struct net_bridge
*br,
 		    nsrcs_offset + sizeof(_nsrcs))
 			return -EINVAL;
 
-		nsrcs = skb_header_pointer(skb, nsrcs_offset,
-					   sizeof(_nsrcs), &_nsrcs);
-		if (!nsrcs)
+		_nsrcs = skb_header_pointer(skb, nsrcs_offset,
+					    sizeof(__nsrcs), &__nsrcs);
+		if (!_nsrcs)
 			return -EINVAL;
 
-		grec_len = struct_size(grec, grec_src, ntohs(*nsrcs));
+		nsrcs = ntohs(*_nsrcs);
+		grec_len = struct_size(grec, grec_src, nsrcs);
 
 		if (!ipv6_mc_may_pull(skb, len + grec_len))
 			return -EINVAL;
@@ -1021,7 +1025,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge
*br,
 		src = eth_hdr(skb)->h_source;
 		if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE ||
 		     grec->grec_type == MLD2_MODE_IS_INCLUDE) &&
-		    ntohs(*nsrcs) == 0) {
+		    nsrcs == 0) {
 			br_ip6_multicast_leave_group(br, port, &grec->grec_mca,
 						     vid, src);
 		} else {
-- 
2.21.0

We get a pointer to the ipv6 hdr in br_ip6_multicast_query but we may
call pskb_may_pull afterwards and end up using a stale pointer.
So use the header directly, it's just 1 place where it's needed.

Fixes: 08b202b67264 ("bridge br_multicast: IPv6 MLD support.")
Signed-off-by: Nikolay Aleksandrov <nikolay at cumulusnetworks.com>
---
 net/bridge/br_multicast.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index f37897e7b97b..3d8deac2353d 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1279,7 +1279,6 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 				  u16 vid)
 {
 	unsigned int transport_len = ipv6_transport_len(skb);
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct mld_msg *mld;
 	struct net_bridge_mdb_entry *mp;
 	struct mld2_query *mld2q;
@@ -1323,7 +1322,7 @@ static int br_ip6_multicast_query(struct net_bridge *br,
 
 	if (is_general_query) {
 		saddr.proto = htons(ETH_P_IPV6);
-		saddr.u.ip6 = ip6h->saddr;
+		saddr.u.ip6 = ipv6_hdr(skb)->saddr;
 
 		br_multicast_query_received(br, port, &br->ip6_other_query,
 					    &saddr, max_delay);
-- 
2.21.0

We would cache ether dst pointer on input in br_handle_frame_finish but
after the neigh suppress code that could lead to a stale pointer since
both ipv4 and ipv6 suppress code do pskb_may_pull. This means we have to
always reload it after the suppress code so there's no point in having
it cached just retrieve it directly.

Fixes: 057658cb33fbf ("bridge: suppress arp pkts on BR_NEIGH_SUPPRESS
ports")
Fixes: ed842faeb2bd ("bridge: suppress nd pkts on BR_NEIGH_SUPPRESS
ports")
Signed-off-by: Nikolay Aleksandrov <nikolay at cumulusnetworks.com>
---
 net/bridge/br_input.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index 21b74e7a7b2f..52c712984cc7 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -74,7 +74,6 @@ int br_handle_frame_finish(struct net *net, struct sock *sk,
struct sk_buff *skb
 	struct net_bridge_fdb_entry *dst = NULL;
 	struct net_bridge_mdb_entry *mdst;
 	bool local_rcv, mcast_hit = false;
-	const unsigned char *dest;
 	struct net_bridge *br;
 	u16 vid = 0;
 
@@ -92,10 +91,9 @@ int br_handle_frame_finish(struct net *net, struct sock *sk,
struct sk_buff *skb
 		br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false);
 
 	local_rcv = !!(br->dev->flags & IFF_PROMISC);
-	dest = eth_hdr(skb)->h_dest;
-	if (is_multicast_ether_addr(dest)) {
+	if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) {
 		/* by definition the broadcast is also a multicast address */
-		if (is_broadcast_ether_addr(dest)) {
+		if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) {
 			pkt_type = BR_PKT_BROADCAST;
 			local_rcv = true;
 		} else {
@@ -145,7 +143,7 @@ int br_handle_frame_finish(struct net *net, struct sock *sk,
struct sk_buff *skb
 		}
 		break;
 	case BR_PKT_UNICAST:
-		dst = br_fdb_find_rcu(br, dest, vid);
+		dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid);
 	default:
 		break;
 	}
-- 
2.21.0

Don't cache eth dest pointer before calling pskb_may_pull.

Fixes: cf0f02d04a83 ("[BRIDGE]: use llc for receiving STP packets")
Signed-off-by: Nikolay Aleksandrov <nikolay at cumulusnetworks.com>
---
 net/bridge/br_stp_bpdu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/br_stp_bpdu.c b/net/bridge/br_stp_bpdu.c
index 68a6922b4141..7796dd9d42d7 100644
--- a/net/bridge/br_stp_bpdu.c
+++ b/net/bridge/br_stp_bpdu.c
@@ -143,7 +143,6 @@ void br_send_tcn_bpdu(struct net_bridge_port *p)
 void br_stp_rcv(const struct stp_proto *proto, struct sk_buff *skb,
 		struct net_device *dev)
 {
-	const unsigned char *dest = eth_hdr(skb)->h_dest;
 	struct net_bridge_port *p;
 	struct net_bridge *br;
 	const unsigned char *buf;
@@ -172,7 +171,7 @@ void br_stp_rcv(const struct stp_proto *proto, struct
sk_buff *skb,
 	if (p->state == BR_STATE_DISABLED)
 		goto out;
 
-	if (!ether_addr_equal(dest, br->group_addr))
+	if (!ether_addr_equal(eth_hdr(skb)->h_dest, br->group_addr))
 		goto out;
 
 	if (p->flags & BR_BPDU_GUARD) {
-- 
2.21.0

From: Nikolay Aleksandrov <nikolay at cumulusnetworks.com>
Date: Tue,  2 Jul 2019 15:00:17 +0300
> In the bridge driver we have a couple of places which call pskb_may_pull
> but we've cached skb pointers before that and use them after which can
> lead to out-of-bounds/stale pointer use. I've had these in my "to
fix"
> list for some time and now we got a report (patch 01) so here they are.
> Patches 02-04 are fixes based on code inspection. Also patch 01 was
> tested by Martin Weinelt, Martin if you don't mind please add your
> tested-by tag to it by replying with Tested-by: name <email>.
> I've also briefly tested the set by trying to exercise those code
paths.
Series applied, thanks.