[PATCH net] net/sched: act_skbmod: Fix headroom COW leading to page cache corruption

[PATCH net] net/sched: act_skbmod: Fix headroom COW leading to page cache corruption

[Muhammad Bilal]

tcf_skbmod_act() calls skb_ensure_writable(skb, max_edit_len) to ensure
the modified packet header is writable before rewriting Ethernet addresses
or setting ECN bits.

However, skb_ensure_writable() only pulls and COWs memory starting from
skb->data onwards. At ingress or on forwarded packets, the Ethernet
header (or network header) may reside in the headroom at a negative
offset (skb_mac_offset(skb) < 0).

Because skb_cow() is omitted for negative offsets, writes via
ether_addr_copy() or INET_ECN_set_ce() modify shared headroom in-place
on cloned SKBs (e.g., cloned by tc mirred, bpf_clone_redirect, or
packet capture sockets). This can result in silent packet corruption
and page cache corruption.

Fix this by ensuring that if the target header starts at a negative
offset in the headroom, skb_cow(skb, -offset) is called to unshare the
headroom before ensuring writability across the header span.

Fixes: 86da71b57383 ("net_sched: Introduce skbmod action")
Signed-off-by: Muhammad Bilal <meatuni001@gmail.com>
---
 net/sched/act_skbmod.c | 37 ++++++++++++++++++++++++-------------
 1 file changed, 24 insertions(+), 13 deletions(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index a8e2b83ebae5..cd2a6e974e6f 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -22,13 +22,24 @@
 
 static struct tc_action_ops act_skbmod_ops;
 
+static int skbmod_ensure_writable(struct sk_buff *skb, int offset, int len)
+{
+	if (offset < 0) {
+		if (skb_cow(skb, -offset))
+			return -ENOMEM;
+		if (offset + len > 0)
+			return skb_ensure_writable(skb, offset + len);
+		return 0;
+	}
+	return skb_ensure_writable(skb, offset + len);
+}
+
 TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb,
 				     const struct tc_action *a,
 				     struct tcf_result *res)
 {
 	struct tcf_skbmod *d = to_skbmod(a);
 	struct tcf_skbmod_params *p;
-	int max_edit_len, err;
 	u64 flags;
 
 	tcf_lastuse_update(&d->tcf_tm);
@@ -38,7 +49,6 @@ TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb,
 	if (unlikely(p->action == TC_ACT_SHOT))
 		goto drop;
 
-	max_edit_len = skb_mac_header_len(skb);
 	flags = p->flags;
 
 	/* tcf_skbmod_init() guarantees "flags" to be one of the following:
@@ -52,19 +62,20 @@ TC_INDIRECT_SCOPE int tcf_skbmod_act(struct sk_buff *skb,
 		switch (skb_protocol(skb, true)) {
 		case cpu_to_be16(ETH_P_IP):
 		case cpu_to_be16(ETH_P_IPV6):
-			max_edit_len += skb_network_header_len(skb);
+			if (skbmod_ensure_writable(skb, skb_network_offset(skb),
+						   skb_network_header_len(skb)))
+				goto drop;
 			break;
 		default:
 			goto out;
 		}
-	} else if (!skb->dev || skb->dev->type != ARPHRD_ETHER) {
-		goto out;
-	}
-
-	err = skb_ensure_writable(skb, max_edit_len);
-	if (unlikely(err)) /* best policy is to drop on the floor */
-		goto drop;
+	} else {
+		if (!skb->dev || skb->dev->type != ARPHRD_ETHER)
+			goto out;
 
+		if (skbmod_ensure_writable(skb, skb_mac_offset(skb), ETH_HLEN))
+			goto drop;
+	}
 	if (flags & SKBMOD_F_DMAC)
 		ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
 	if (flags & SKBMOD_F_SMAC)
-- 
2.43.0

[PATCH net] net/sched: act_nat: Fix missing headroom COW and integer underflow in header rewriting

[Muhammad Bilal]

tcf_nat_act() accesses and rewrites IPv4, TCP, UDP, and ICMP headers
based on noff = skb_network_offset(skb).

When the network header resides in the headroom (noff < 0), two issues
occur:
1. sizeof(*iph) + noff can evaluate to a negative value or underflow
   when passed to functions expecting unsigned lengths, such as
   pskb_may_pull() and skb_try_make_writable().
2. skb_try_make_writable() only evaluates writability from skb->data
   forwards and does not invoke skb_cow() on the headroom. When modifying
   cloned SKBs (e.g. from packet sockets, tc mirred, or BPF redirects),
   in-place header modification via iph->saddr / iph->daddr mutates
   shared headroom data directly, leading to packet corruption and page
   cache corruption.

Fix this by introducing a helper nat_ensure_writable() that validates
headroom using skb_cow(skb, -offset) when offset is negative before
ensuring writability across the modified header length.

Fixes: b4219952356b ("[PKT_SCHED]: Add stateless NAT")
Signed-off-by: Muhammad Bilal <meatuni001@gmail.com>
---
 net/sched/act_nat.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 28cb48419616..1bf5d55b3dc4 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -112,6 +112,18 @@ static struct tc_action_ops act_nat_ops;
 
 static const struct rhashtable_params tcf_nat_ht_params;
 
+static int nat_ensure_writable(struct sk_buff *skb, int offset, size_t len)
+{
+	if (offset < 0) {
+		if (skb_cow(skb, -offset))
+			return -ENOMEM;
+		if (offset + (int)len > 0)
+			return skb_ensure_writable(skb, offset + len);
+		return 0;
+	}
+	return skb_ensure_writable(skb, offset + len);
+}
+
 TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
 				  const struct tc_action *a,
 				  struct tcf_result *res)
@@ -142,7 +154,7 @@ TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
 	egress = parms->flags & TCA_NAT_FLAG_EGRESS;
 
 	noff = skb_network_offset(skb);
-	if (!pskb_may_pull(skb, sizeof(*iph) + noff))
+	if (nat_ensure_writable(skb, noff, sizeof(*iph)))
 		goto drop;
 
 	iph = ip_hdr(skb);
@@ -153,9 +165,6 @@ TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
 		addr = iph->daddr;
 
 	if (!((old_addr ^ addr) & mask)) {
-		if (skb_try_make_writable(skb, sizeof(*iph) + noff))
-			goto drop;
-
 		new_addr &= mask;
 		new_addr |= addr & ~mask;
 
@@ -180,8 +189,7 @@ TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
 	{
 		struct tcphdr *tcph;
 
-		if (!pskb_may_pull(skb, ihl + sizeof(*tcph) + noff) ||
-		    skb_try_make_writable(skb, ihl + sizeof(*tcph) + noff))
+		if (nat_ensure_writable(skb, noff, ihl + sizeof(*tcph)))
 			goto drop;
 
 		tcph = (void *)(skb_network_header(skb) + ihl);
@@ -193,8 +201,7 @@ TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
 	{
 		struct udphdr *udph;
 
-		if (!pskb_may_pull(skb, ihl + sizeof(*udph) + noff) ||
-		    skb_try_make_writable(skb, ihl + sizeof(*udph) + noff))
+		if (nat_ensure_writable(skb, noff, ihl + sizeof(*udph)))
 			goto drop;
 
 		udph = (void *)(skb_network_header(skb) + ihl);
@@ -209,19 +216,19 @@ TC_INDIRECT_SCOPE int tcf_nat_act(struct sk_buff *skb,
 	{
 		struct icmphdr *icmph;
 
-		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + noff))
+		if (nat_ensure_writable(skb, noff, ihl + sizeof(*icmph)))
 			goto drop;
 
 		icmph = (void *)(skb_network_header(skb) + ihl);
 
 		if (!icmp_is_err(icmph->type))
 			break;
 
-		if (!pskb_may_pull(skb, ihl + sizeof(*icmph) + sizeof(*iph) +
-					noff))
+		if (nat_ensure_writable(skb, noff,
+					ihl + sizeof(*icmph) + sizeof(*iph)))
 			goto drop;
 
 		icmph = (void *)(skb_network_header(skb) + ihl);
 		iph = (void *)(icmph + 1);
 		if (egress)
 			addr = iph->daddr;
 		else
 			addr = iph->saddr;
 
 		if ((old_addr ^ addr) & mask)
 			break;
-
-		if (skb_try_make_writable(skb, ihl + sizeof(*icmph) +
-					  sizeof(*iph) + noff))
-			goto drop;
 
 		icmph = (void *)(skb_network_header(skb) + ihl);
 		iph = (void *)(icmph + 1);
-- 
2.43.0

[PATCH net] net/sched: act_csum: Fix missing headroom COW and integer underflow in header rewriting

[Muhammad Bilal]

tcf_csum_skb_nextlayer() and tcf_csum_ipv4() access and rewrite IP and L4
headers based on ntkoff = skb_network_offset(skb).

When the network header resides in the headroom (ntkoff < 0):
1. hl + ntkoff or sizeof(*iph) + ntkoff can evaluate to a negative value
   or underflow when passed to functions expecting unsigned lengths, such
   as pskb_may_pull() and skb_try_make_writable().
2. skb_try_make_writable() only evaluates writability from skb->data
   forwards and does not invoke skb_cow() on the headroom. When modifying
   cloned SKBs (e.g. from packet sockets, tc mirred, or BPF redirects),
   updating headers via ip_send_check() or L4 checksum replacements mutates
   shared headroom data directly, leading to packet corruption and page
   cache corruption.

Fix this by introducing a helper csum_ensure_writable() that validates
headroom using skb_cow(skb, -offset) when offset is negative before
ensuring writability across the modified header length.

Fixes: eb4d40654505 ("net/sched: add ACT_CSUM action to update packets checksums")
Signed-off-by: Muhammad Bilal <meatuni001@gmail.com>
---
 net/sched/act_csum.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index a8e2b83ebae5..cd2a6e974e6f 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -124,6 +124,18 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	return err;
 }
 
+static int csum_ensure_writable(struct sk_buff *skb, int offset, size_t len)
+{
+	if (offset < 0) {
+		if (skb_cow(skb, -offset))
+			return -ENOMEM;
+		if (offset + (int)len > 0)
+			return skb_ensure_writable(skb, offset + len);
+		return 0;
+	}
+	return skb_ensure_writable(skb, offset + len);
+}
+
 /**
  * tcf_csum_skb_nextlayer - Get next layer pointer
  * @skb: sk_buff to use
@@ -139,8 +151,7 @@ static void *tcf_csum_skb_nextlayer(struct sk_buff *skb,
 	int ntkoff = skb_network_offset(skb);
 	int hl = ihl + jhl;
 
-	if (!pskb_may_pull(skb, ipl + ntkoff) || (ipl < hl) ||
-	    skb_try_make_writable(skb, hl + ntkoff))
+	if (ipl < hl || csum_ensure_writable(skb, ntkoff, max_t(unsigned int, ipl, hl)))
 		return NULL;
 	else
 		return (void *)(skb_network_header(skb) + ihl);
@@ -437,8 +448,8 @@ static int tcf_csum_ipv4(struct sk_buff *skb, u32 update_flags)
 	}
 
 	if (update_flags & TCA_CSUM_UPDATE_FLAG_IPV4HDR) {
-		if (skb_try_make_writable(skb, sizeof(*iph) + ntkoff))
+		if (csum_ensure_writable(skb, ntkoff, sizeof(*iph)))
 			goto fail;
 
 		ip_send_check(ip_hdr(skb));
 	}
-- 
2.43.0