[PATCH net-next] gre: fix ERSPAN o_flags race/corruption in xmit and fill_info

[PATCH net-next] gre: fix ERSPAN o_flags race/corruption in xmit and fill_info

[Eric Dumazet]

For IPv4 ERSPAN:
In erspan_xmit(), the driver clears IP_TUNNEL_SEQ_BIT (for version 0)
and IP_TUNNEL_KEY_BIT directly in the shared tunnel->parms.o_flags
structure. Since transmit paths can run locklessly and concurrently,
this leads to a data race.

Furthermore, modifying tunnel->parms.o_flags permanently alters the
tunnel configuration. To work around this, erspan_fill_info() (which
reports config to userspace) was setting IP_TUNNEL_KEY_BIT back. If
erspan_fill_info (running under RTNL) and erspan_xmit (running locklessly)
race, erspan_xmit might see IP_TUNNEL_KEY_BIT set when it shouldn't,
leading to GRE header corruption (injecting a key field into the ERSPAN
GRE header).

Fix this by:
1) Passing flags as an argument to __gre_xmit().
2) Using local flags in erspan_xmit() and passing them to __gre_xmit().
3) Removing the racy modification of t->parms.o_flags in erspan_fill_info().
4) Forcing IP_TUNNEL_KEY_BIT in the reported flags for ERSPAN locally
   in ipgre_fill_info().

For IPv6 ERSPAN:
ip6erspan_tunnel_xmit() was locklessly clearing IP_TUNNEL_KEY_BIT in
t->parms.o_flags even though it does not use these flags for building
the GRE header (it uses local flags). This permanently corrupts the
configuration and races with ip6gre_fill_info() which reads it.

Remove the redundant and racy modification.
This should remove false sharing in a fast path.

Add const qualifiers in ipgre_fill_info(), erspan_fill_info()
and ip6gre_fill_info() to clarify that these methods are not
supposed to write any live parameters.

Fixes: 84e54fe0a5ea ("gre: introduce native tunnel support for ERSPAN")
Fixes: ee496694b9ee ("ip_gre: do not report erspan version on GRE interface")
Fixes: 5a963eb61b7c ("ip6_gre: Add ERSPAN native tunnel support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
I found this issue while working on RTNL-less fill_info().
Sent to net-next since 7.1 was just released.

 net/ipv4/ip_gre.c  | 30 +++++++++++++++---------------
 net/ipv6/ip6_gre.c |  5 ++---
 2 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 208dd48012d963b9df0eddbdda73dd319930e48f..eab6d228d062b97b6f3f9d03418b84bac12b6983 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -475,12 +475,9 @@ static int gre_rcv(struct sk_buff *skb)
 
 static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
 		       const struct iphdr *tnl_params,
-		       __be16 proto)
+		       __be16 proto, const unsigned long *flags)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	IP_TUNNEL_DECLARE_FLAGS(flags);
-
-	ip_tunnel_flags_copy(flags, tunnel->parms.o_flags);
 
 	/* Push GRE header. */
 	gre_build_header(skb, tunnel->tun_hlen,
@@ -692,7 +689,7 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
 					      tunnel->parms.o_flags)))
 		goto free_skb;
 
-	__gre_xmit(skb, dev, tnl_params, skb->protocol);
+	__gre_xmit(skb, dev, tnl_params, skb->protocol, tunnel->parms.o_flags);
 	return NETDEV_TX_OK;
 
 free_skb:
@@ -705,6 +702,7 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 			       struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
+	IP_TUNNEL_DECLARE_FLAGS(flags);
 	bool truncate = false;
 	__be16 proto;
 
@@ -728,10 +726,12 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 		truncate = true;
 	}
 
+	ip_tunnel_flags_copy(flags, tunnel->parms.o_flags);
+
 	/* Push ERSPAN header */
 	if (tunnel->erspan_ver == 0) {
 		proto = htons(ETH_P_ERSPAN);
-		__clear_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.o_flags);
+		__clear_bit(IP_TUNNEL_SEQ_BIT, flags);
 	} else if (tunnel->erspan_ver == 1) {
 		erspan_build_header(skb, ntohl(tunnel->parms.o_key),
 				    tunnel->index,
@@ -746,8 +746,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
 		goto free_skb;
 	}
 
-	__clear_bit(IP_TUNNEL_KEY_BIT, tunnel->parms.o_flags);
-	__gre_xmit(skb, dev, &tunnel->parms.iph, proto);
+	__clear_bit(IP_TUNNEL_KEY_BIT, flags);
+	__gre_xmit(skb, dev, &tunnel->parms.iph, proto, flags);
 	return NETDEV_TX_OK;
 
 free_skb:
@@ -776,7 +776,7 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
 	if (skb_cow_head(skb, dev->needed_headroom))
 		goto free_skb;
 
-	__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB));
+	__gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB), tunnel->parms.o_flags);
 	return NETDEV_TX_OK;
 
 free_skb:
@@ -1554,12 +1554,15 @@ static size_t ipgre_get_size(const struct net_device *dev)
 
 static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct ip_tunnel *t = netdev_priv(dev);
-	struct ip_tunnel_parm_kern *p = &t->parms;
+	const struct ip_tunnel *t = netdev_priv(dev);
+	const struct ip_tunnel_parm_kern *p = &t->parms;
 	IP_TUNNEL_DECLARE_FLAGS(o_flags);
 
 	ip_tunnel_flags_copy(o_flags, p->o_flags);
 
+	if (t->erspan_ver != 0 && !t->collect_md)
+		__set_bit(IP_TUNNEL_KEY_BIT, o_flags);
+
 	if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
 	    nla_put_be16(skb, IFLA_GRE_IFLAGS,
 			 gre_tnl_flags_to_gre_flags(p->i_flags)) ||
@@ -1602,12 +1605,9 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 
 static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct ip_tunnel *t = netdev_priv(dev);
+	const struct ip_tunnel *t = netdev_priv(dev);
 
 	if (t->erspan_ver <= 2) {
-		if (t->erspan_ver != 0 && !t->collect_md)
-			__set_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags);
-
 		if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver))
 			goto nla_put_failure;
 
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 795be59946f7210bfae55d20500d18c83c01ede9..d0701351934ccfcfbac70bb2c2c2a7ccb9b6d779 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -964,7 +964,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 	if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen))
 		goto tx_err;
 
-	__clear_bit(IP_TUNNEL_KEY_BIT, t->parms.o_flags);
 	IPCB(skb)->flags = 0;
 
 	/* For collect_md mode, derive fl6 from the tunnel key,
@@ -2112,8 +2111,8 @@ static size_t ip6gre_get_size(const struct net_device *dev)
 
 static int ip6gre_fill_info(struct sk_buff *skb, const struct net_device *dev)
 {
-	struct ip6_tnl *t = netdev_priv(dev);
-	struct __ip6_tnl_parm *p = &t->parms;
+	const struct ip6_tnl *t = netdev_priv(dev);
+	const struct __ip6_tnl_parm *p = &t->parms;
 	IP_TUNNEL_DECLARE_FLAGS(o_flags);
 
 	ip_tunnel_flags_copy(o_flags, p->o_flags);
-- 
2.54.0.1136.gdb2ca164c4-goog