Skip to contentSkip to conversation

netfilter: nft_fwd_netdev: use recursion counter in neigh egress path

PATCH In review Weiming Shi 2 participants 4 messages Apr 9

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 netfilter: nft_fwd_netdev: use recursion counter in neigh egress path

nft_fwd_neigh can be used in egress chains (NF_NETDEV_EGRESS). When the forwarding rule targets the same device or two devices forward to each other, neigh_xmit() triggers dev_queue_xmit() which re-enters nf_hook_egress(), causing infinite recursion and stack overflow.

Move the nf_get_nf_dup_skb_recursion() accessor and NF_RECURSION_LIMIT to the shared header nf_dup_netdev.h as a static inline, so that nft_fwd_netdev can use the recursion counter directly without exported function call overhead. Guard neigh_xmit() with the same recursion limit already used in nf_do_netdev_egress().

Fixes f87b9464d152 ("netfilter: nft_fwd_netdev: Support egress hook")
---
 include/net/netfilter/nf_dup_netdev.h | 13 +++++++++++++
 net/netfilter/nf_dup_netdev.c         | 16 ----------------
 net/netfilter/nft_fwd_netdev.c        |  7 +++++++
 3 files changed, 20 insertions(+), 16 deletions(-)
include/net/netfilter/nf_dup_netdev.h +13 -0
index b175d271aec9..609bcf422a9b 100644
@@ -3,10 +3,23 @@
 #define _NF_DUP_NETDEV_H_
 
 #include <net/netfilter/nf_tables.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
 
 void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 
+#define NF_RECURSION_LIMIT	2
+
+static inline u8 *nf_get_nf_dup_skb_recursion(void)
+{
+#ifndef CONFIG_PREEMPT_RT
+	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
+#else
+	return &current->net_xmit.nf_dup_skb_recursion;
+#endif
+}
+
 struct nft_offload_ctx;
 struct nft_flow_rule;
 
net/netfilter/nf_dup_netdev.c +0 -16
index fab8b9011098..a958a1b0c5be 100644
@@ -13,22 +13,6 @@
 #include <net/netfilter/nf_tables_offload.h>
 #include <net/netfilter/nf_dup_netdev.h>
 
-#define NF_RECURSION_LIMIT	2
-
-#ifndef CONFIG_PREEMPT_RT
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
-}
-#else
-
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return &current->net_xmit.nf_dup_skb_recursion;
-}
-
-#endif
-
 static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
 				enum nf_dev_hooks hook)
 {
net/netfilter/nft_fwd_netdev.c +7 -0
index 152a9fb4d23a..492bb599a499 100644
@@ -141,13 +141,20 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
+	if (*nf_get_nf_dup_skb_recursion() > NF_RECURSION_LIMIT) {
+		verdict = NF_DROP;
+		goto out;
+	}
+
 	dev = dev_get_by_index_rcu(nft_net(pkt), oif);
 	if (dev == NULL)
 		return;
 
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
+	(*nf_get_nf_dup_skb_recursion())++;
 	neigh_xmit(neigh_table, dev, addr, skb);
+	(*nf_get_nf_dup_skb_recursion())--;
 out:
 	regs->verdict.code = verdict;
 }
Signature · 1 line
2.43.0
#1 lore raw
Quoted 5 lines · Weiming Shi

nft_fwd_neigh can be used in egress chains (NF_NETDEV_EGRESS). When the forwarding rule targets the same device or two devices forward to each other, neigh_xmit() triggers dev_queue_xmit() which re-enters nf_hook_egress(), causing infinite recursion and stack overflow.

Quoted 7 lines

Move the nf_get_nf_dup_skb_recursion() accessor and NF_RECURSION_LIMIT to the shared header nf_dup_netdev.h as a static inline, so that nft_fwd_netdev can use the recursion counter directly without exported function call overhead. Guard neigh_xmit() with the same recursion limit already used in nf_do_netdev_egress().

Fixes f87b9464d152 ("netfilter: nft_fwd_netdev: Support egress hook")

I would just restrict this "feature", I don't see a point in allowing this from egress?

Quoted 92 lines
---
 include/net/netfilter/nf_dup_netdev.h | 13 +++++++++++++
 net/netfilter/nf_dup_netdev.c         | 16 ----------------
 net/netfilter/nft_fwd_netdev.c        |  7 +++++++
 3 files changed, 20 insertions(+), 16 deletions(-)
include/net/netfilter/nf_dup_netdev.h +13 -0
index b175d271aec9..609bcf422a9b 100644
@@ -3,10 +3,23 @@
 #define _NF_DUP_NETDEV_H_
 
 #include <net/netfilter/nf_tables.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
 
 void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 
+#define NF_RECURSION_LIMIT	2
+
+static inline u8 *nf_get_nf_dup_skb_recursion(void)
+{
+#ifndef CONFIG_PREEMPT_RT
+	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
+#else
+	return &current->net_xmit.nf_dup_skb_recursion;
+#endif
+}
+
 struct nft_offload_ctx;
 struct nft_flow_rule;
 
net/netfilter/nf_dup_netdev.c +0 -16
index fab8b9011098..a958a1b0c5be 100644
@@ -13,22 +13,6 @@
 #include <net/netfilter/nf_tables_offload.h>
 #include <net/netfilter/nf_dup_netdev.h>
 
-#define NF_RECURSION_LIMIT	2
-
-#ifndef CONFIG_PREEMPT_RT
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
-}
-#else
-
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return &current->net_xmit.nf_dup_skb_recursion;
-}
-
-#endif
-
 static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
 				enum nf_dev_hooks hook)
 {
net/netfilter/nft_fwd_netdev.c +7 -0
index 152a9fb4d23a..492bb599a499 100644
@@ -141,13 +141,20 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
+	if (*nf_get_nf_dup_skb_recursion() > NF_RECURSION_LIMIT) {
+		verdict = NF_DROP;
+		goto out;
+	}
+
 	dev = dev_get_by_index_rcu(nft_net(pkt), oif);
 	if (dev == NULL)
 		return;
 
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
+	(*nf_get_nf_dup_skb_recursion())++;
 	neigh_xmit(neigh_table, dev, addr, skb);
+	(*nf_get_nf_dup_skb_recursion())--;
 out:
 	regs->verdict.code = verdict;
 }
Signature · 1 line
2.43.0
#2 lore raw
Quoted 12 lines · Pablo Neira Ayuso
Quoted 11 lines · Weiming Shi

nft_fwd_neigh can be used in egress chains (NF_NETDEV_EGRESS). When the forwarding rule targets the same device or two devices forward to each other, neigh_xmit() triggers dev_queue_xmit() which re-enters nf_hook_egress(), causing infinite recursion and stack overflow.

Move the nf_get_nf_dup_skb_recursion() accessor and NF_RECURSION_LIMIT to the shared header nf_dup_netdev.h as a static inline, so that nft_fwd_netdev can use the recursion counter directly without exported function call overhead. Guard neigh_xmit() with the same recursion limit already used in nf_do_netdev_egress().

Quoted 4 lines
Quoted 1 line
Fixes f87b9464d152 ("netfilter: nft_fwd_netdev: Support egress hook")

I would just restrict this "feature", I don't see a point in allowing this from egress?

Hm, actually this can be combined with if0 device, fixing it makes sense.

Quoted 92 lines
Quoted 92 lines
---
 include/net/netfilter/nf_dup_netdev.h | 13 +++++++++++++
 net/netfilter/nf_dup_netdev.c         | 16 ----------------
 net/netfilter/nft_fwd_netdev.c        |  7 +++++++
 3 files changed, 20 insertions(+), 16 deletions(-)
include/net/netfilter/nf_dup_netdev.h +13 -0
index b175d271aec9..609bcf422a9b 100644
@@ -3,10 +3,23 @@
 #define _NF_DUP_NETDEV_H_
 
 #include <net/netfilter/nf_tables.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
 
 void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 
+#define NF_RECURSION_LIMIT	2
+
+static inline u8 *nf_get_nf_dup_skb_recursion(void)
+{
+#ifndef CONFIG_PREEMPT_RT
+	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
+#else
+	return &current->net_xmit.nf_dup_skb_recursion;
+#endif
+}
+
 struct nft_offload_ctx;
 struct nft_flow_rule;
 
net/netfilter/nf_dup_netdev.c +0 -16
index fab8b9011098..a958a1b0c5be 100644
@@ -13,22 +13,6 @@
 #include <net/netfilter/nf_tables_offload.h>
 #include <net/netfilter/nf_dup_netdev.h>
 
-#define NF_RECURSION_LIMIT	2
-
-#ifndef CONFIG_PREEMPT_RT
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
-}
-#else
-
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return &current->net_xmit.nf_dup_skb_recursion;
-}
-
-#endif
-
 static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
 				enum nf_dev_hooks hook)
 {
net/netfilter/nft_fwd_netdev.c +7 -0
index 152a9fb4d23a..492bb599a499 100644
@@ -141,13 +141,20 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
+	if (*nf_get_nf_dup_skb_recursion() > NF_RECURSION_LIMIT) {
+		verdict = NF_DROP;
+		goto out;
+	}
+
 	dev = dev_get_by_index_rcu(nft_net(pkt), oif);
 	if (dev == NULL)
 		return;
 
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
+	(*nf_get_nf_dup_skb_recursion())++;
 	neigh_xmit(neigh_table, dev, addr, skb);
+	(*nf_get_nf_dup_skb_recursion())--;
 out:
 	regs->verdict.code = verdict;
 }
Signature · 1 line
2.43.0
#3 lore raw
Quoted 100 lines · Pablo Neira Ayuso
Quoted 12 lines · Pablo Neira Ayuso
Quoted 11 lines · Weiming Shi

nft_fwd_neigh can be used in egress chains (NF_NETDEV_EGRESS). When the forwarding rule targets the same device or two devices forward to each other, neigh_xmit() triggers dev_queue_xmit() which re-enters nf_hook_egress(), causing infinite recursion and stack overflow.

Move the nf_get_nf_dup_skb_recursion() accessor and NF_RECURSION_LIMIT to the shared header nf_dup_netdev.h as a static inline, so that nft_fwd_netdev can use the recursion counter directly without exported function call overhead. Guard neigh_xmit() with the same recursion limit already used in nf_do_netdev_egress().

Quoted 4 lines
Quoted 1 line
Fixes f87b9464d152 ("netfilter: nft_fwd_netdev: Support egress hook")

I would just restrict this "feature", I don't see a point in allowing this from egress?

Hm, actually this can be combined with if0 device, fixing it makes sense.

Quoted 80 lines
Quoted 80 lines
---
 include/net/netfilter/nf_dup_netdev.h | 13 +++++++++++++
 net/netfilter/nf_dup_netdev.c         | 16 ----------------
 net/netfilter/nft_fwd_netdev.c        |  7 +++++++
 3 files changed, 20 insertions(+), 16 deletions(-)
include/net/netfilter/nf_dup_netdev.h +13 -0
index b175d271aec9..609bcf422a9b 100644
@@ -3,10 +3,23 @@
 #define _NF_DUP_NETDEV_H_
 
 #include <net/netfilter/nf_tables.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
 
 void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 
+#define NF_RECURSION_LIMIT	2
+
+static inline u8 *nf_get_nf_dup_skb_recursion(void)
+{
+#ifndef CONFIG_PREEMPT_RT
+	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
+#else
+	return &current->net_xmit.nf_dup_skb_recursion;
+#endif
+}
+
 struct nft_offload_ctx;
 struct nft_flow_rule;
 
net/netfilter/nf_dup_netdev.c +0 -16
index fab8b9011098..a958a1b0c5be 100644
@@ -13,22 +13,6 @@
 #include <net/netfilter/nf_tables_offload.h>
 #include <net/netfilter/nf_dup_netdev.h>
 
-#define NF_RECURSION_LIMIT	2
-
-#ifndef CONFIG_PREEMPT_RT
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
-}
-#else
-
-static u8 *nf_get_nf_dup_skb_recursion(void)
-{
-	return &current->net_xmit.nf_dup_skb_recursion;
-}
-
-#endif
-
 static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev,
 				enum nf_dev_hooks hook)
 {
net/netfilter/nft_fwd_netdev.c +5 -0
index 152a9fb4d23a..492bb599a499 100644
@@ -141,13 +141,20 @@ static void nft_fwd_neigh_eval(const struct nft_expr *expr,
 		goto out;
 	}
 
+	if (*nf_get_nf_dup_skb_recursion() > NF_RECURSION_LIMIT) {
+		verdict = NF_DROP;
+		goto out;
+	}
+
 	dev = dev_get_by_index_rcu(nft_net(pkt), oif);
 	if (dev == NULL)
 		return;
 
Quoted 12 lines
Quoted 4 lines
Quoted 4 lines
net/netfilter/nft_fwd_netdev.c +1 -0
 	skb->dev = dev;
 	skb_clear_tstamp(skb);
+	(*nf_get_nf_dup_skb_recursion())++;
 	neigh_xmit(neigh_table, dev, addr, skb);
Quoted 8 lines
Quoted 8 lines
net/netfilter/nft_fwd_netdev.c +1 -0
+	(*nf_get_nf_dup_skb_recursion())--;
 out:
 	regs->verdict.code = verdict;
 }
Signature · 1 line
2.43.0

Thanks Pablo. So shall I keep v2 as is, or is there anything else you'd like me to change?