Netdev List
 help / color / mirror / Atom feed
* [PATCH net v2 0/2] net: gso: fraglist segmentation fixes
@ 2026-11-20  4:46 Willem de Bruijn
  2026-11-20  4:46 ` [PATCH net v2 1/2] net: gso: cow head on tcp fraglist fallback to skb_segment Willem de Bruijn
  2026-11-20  4:46 ` [PATCH net v2 2/2] net: gso: fall back to skb_segment when fraglist cannot satisfy checksum Willem de Bruijn
  0 siblings, 2 replies; 3+ messages in thread
From: Willem de Bruijn @ 2026-11-20  4:46 UTC (permalink / raw)
  To: netdev; +Cc: davem, kuba, edumazet, pabeni, horms, Willem de Bruijn

From: Willem de Bruijn <willemb@google.com>

Fix two issues when segmenting SKB_GSO_FRAGLIST packets.

Patch 1 unshares the head before the TCP fallback to skb_segment()
rewrites the TCP checksum field.

Patch 2 falls back to skb_segment() in more cases where
skb_segment_list() produces incorrect checksums: tunnels with outer
checksums, and CHECKSUM_PARTIAL packets sent to a device without
checksum offload.

Testing

Tested in virtme-ng. A sender injects TCP and UDP GSO packets (20
packets of 20 segments of 1000B) over a veth with TSO disabled. The
peer veth has GRO and rx-gro-list enabled, and forwards the fraglist
skbs to a tap device without offloads, in three ways:

- routed
- routed into a vxlan device with udpcsum, over the tap
- bridged

Each for IPv4 and IPv6, and with sender checksum offload enabled
(CHECKSUM_PARTIAL) and disabled (complete checksums): 24 cases.

A reader on the tap verifies the IP, TCP and UDP checksums of every
segment, including inside vxlan. For TCP, a packet socket on the
ingress veth holds clones of the GRO packets, and checks whether their
TCP checksum field was modified in place.

- net/main: 14 of 24 cases fail.
  CHECKSUM_PARTIAL to the tap has incorrect L4 checksums, routed and
  bridged. Vxlan has incorrect outer UDP checksums: with IPv6 inner
  packets always, with IPv4 inner packets only with CHECKSUM_PARTIAL.
- This series without the skb_cow_head() of patch 1: the bridged TCP
  CHECKSUM_PARTIAL cases, IPv4 and IPv6, modify all clones. Routed
  cases are not affected, as ip_forward() unshares the head.
- This series: all 24 cases pass.

Changes
  v1 -> v2
    - new patch 1/2
    - patch 2/2: move the test into helper skb_gso_fraglist_ok()
    - patch 2/2: rebase onto commit 22b7cb932c6a ("udp: check frag_list
      IP family before using skb_segment_list()")
    - patch 2/2: commit message: explain the skb->encapsulation test,
      reference the existing skb_segment() fallback, drop the claim that
      skb_segment() is always safe
  v1: https://lore.kernel.org/netdev/20261111221129.829218-1-willemdebruijn.kernel@gmail.com/

Willem de Bruijn (2):
  net: gso: cow head on tcp fraglist fallback to skb_segment
  net: gso: fall back to skb_segment when fraglist cannot satisfy
    checksum

 include/net/gso.h        | 33 +++++++++++++++++++++++++++++++++
 net/ipv4/tcp_offload.c   | 10 +++++++---
 net/ipv4/udp_offload.c   |  5 +++--
 net/ipv6/tcpv6_offload.c | 11 ++++++++---
 4 files changed, 51 insertions(+), 8 deletions(-)

-- 
2.56.1.750.gf70dc682cf-goog


^ permalink raw reply	[flat|nested] 3+ messages in thread

* [PATCH net v2 1/2] net: gso: cow head on tcp fraglist fallback to skb_segment
  2026-11-20  4:46 [PATCH net v2 0/2] net: gso: fraglist segmentation fixes Willem de Bruijn
@ 2026-11-20  4:46 ` Willem de Bruijn
  2026-11-20  4:46 ` [PATCH net v2 2/2] net: gso: fall back to skb_segment when fraglist cannot satisfy checksum Willem de Bruijn
  1 sibling, 0 replies; 3+ messages in thread
From: Willem de Bruijn @ 2026-11-20  4:46 UTC (permalink / raw)
  To: netdev; +Cc: davem, kuba, edumazet, pabeni, horms, Willem de Bruijn, stable

From: Willem de Bruijn <willemb@google.com>

When tcp4_gso_segment() or tcp6_gso_segment() cannot use
skb_segment_list(), they fall back to tcp_gso_segment(), first resetting
th->check to the pseudo-header sum. This writes to skb->head without
unsharing it. If the skb is cloned, e.g., by a packet socket on a bridge
port, the other holders see the rewritten checksum.

Call skb_cow_head(), like skb_segment_list() and the UDP fallback
already unshare the head with skb_unclone() and __skb_linearize().
skb_header_cloned() is equivalent to skb_cloned() here, as GRO does not
set nohdr on the head of fraglist skbs.

Discovered by an AI code review agent. Reproduced on an unmodified
kernel with bridged veth devices and an AF_PACKET socket, and verified
in virtme-ng.

Fixes: 17bd3bd82f9f ("net: gso: fix tcp fraglist segmentation after pull from frag_list")
Cc: stable@vger.kernel.org
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
 net/ipv4/tcp_offload.c   | 5 +++++
 net/ipv6/tcpv6_offload.c | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index b84fcd07c723..520778c5ca7f 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -106,11 +106,16 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) {
 		struct tcphdr *th = tcp_hdr(skb);
+		int err;
 
 		if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) &&
 		    !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
 			return __tcp4_gso_segment_list(skb, features);
 
+		err = skb_cow_head(skb, 0);
+		if (err < 0)
+			return ERR_PTR(err);
+
 		skb->ip_summed = CHECKSUM_NONE;
 	}
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index eec3778855eb..0914f95f100c 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -178,11 +178,16 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) {
 		struct tcphdr *th = tcp_hdr(skb);
+		int err;
 
 		if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) &&
 		    !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
 			return __tcp6_gso_segment_list(skb, features);
 
+		err = skb_cow_head(skb, 0);
+		if (err < 0)
+			return ERR_PTR(err);
+
 		skb->ip_summed = CHECKSUM_NONE;
 	}
 
-- 
2.56.1.750.gf70dc682cf-goog


^ permalink raw reply related	[flat|nested] 3+ messages in thread

* [PATCH net v2 2/2] net: gso: fall back to skb_segment when fraglist cannot satisfy checksum
  2026-11-20  4:46 [PATCH net v2 0/2] net: gso: fraglist segmentation fixes Willem de Bruijn
  2026-11-20  4:46 ` [PATCH net v2 1/2] net: gso: cow head on tcp fraglist fallback to skb_segment Willem de Bruijn
@ 2026-11-20  4:46 ` Willem de Bruijn
  1 sibling, 0 replies; 3+ messages in thread
From: Willem de Bruijn @ 2026-11-20  4:46 UTC (permalink / raw)
  To: netdev
  Cc: davem, kuba, edumazet, pabeni, horms, Willem de Bruijn, stable,
	Hassan Sultan

From: Willem de Bruijn <willemb@google.com>

skb_segment_list() keeps the original headers and checksum state of the
frag_list members. It ignores the checksum features and does not set up
the SKB_GSO_CB() checksum state. This breaks:

1. Outer tunnel checksums. __skb_udp_tunnel_segment() and
   gre_gso_segment() compute these with gso_make_checksum(), which
   reads stale SKB_GSO_CB() state, and needs an inner payload sum that
   skb_segment_list() does not compute.

2. CHECKSUM_PARTIAL packets, e.g., from veth or tun, sent to a device
   without checksum offload. Unlike skb_segment(), skb_segment_list()
   does not resolve these.

Extend the existing fallback to skb_segment() for modified geometry and
SKB_GSO_DODGY, from
commit 17bd3bd82f9f ("net: gso: fix tcp fraglist segmentation after pull
from frag_list"), to when:

- skb_tnl_header_len() is non-zero: UDP, GRE and MPLS tunnels (case 1).
- the features cannot checksum a CHECKSUM_PARTIAL packet (case 2).
- skb->encapsulation is set: encapsulations not seen by
  skb_tnl_header_len(). For example, ESP with xfrm offload in transport
  mode, as skb_segment_list() does not copy the ESP header and IV to
  the frag_list members. IPIP and SIT are excluded too, for simplicity.

Share this test between TCP and UDP in skb_gso_fraglist_ok().

This moves some correctly handled tunnel traffic to the slower
skb_segment(). Fraglist GRO is off by default.

Discovered through analysis by an LLM. Reproduced on an unmodified
kernel and verified with LLM-generated reproducers in virtme-ng.

Fixes: 9fd1ff5d2ac7 ("udp: Support UDP fraglist GRO/GSO.")
Fixes: bee88cd5bd83 ("net: add support for segmenting TCP fraglist GSO packets")
Cc: stable@vger.kernel.org
Reported-by: Hassan Sultan <hassansultan@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
---
 include/net/gso.h        | 33 +++++++++++++++++++++++++++++++++
 net/ipv4/tcp_offload.c   |  5 ++---
 net/ipv4/udp_offload.c   |  5 +++--
 net/ipv6/tcpv6_offload.c |  6 +++---
 4 files changed, 41 insertions(+), 8 deletions(-)

diff --git a/include/net/gso.h b/include/net/gso.h
index 119fc4c170e1..6cf6a6dee234 100644
--- a/include/net/gso.h
+++ b/include/net/gso.h
@@ -3,6 +3,7 @@
 #ifndef _NET_GSO_H
 #define _NET_GSO_H
 
+#include <linux/netdevice.h>
 #include <linux/skbuff.h>
 
 /* Keeps track of mac header offset relative to skb->head.
@@ -39,6 +40,38 @@ static inline int skb_tnl_header_len(const struct sk_buff *inner_skb)
 		SKB_GSO_CB(inner_skb)->mac_offset;
 }
 
+/**
+ * skb_gso_fraglist_ok - test whether skb_segment_list() can segment an skb
+ * @skb: SKB_GSO_FRAGLIST skb to segment
+ * @features: features for the output path
+ * @hdrlen: transport header length
+ * @proto: network protocol, for checksum offload
+ *
+ * Return: false if the skb must be passed to the more general skb_segment().
+ */
+static inline bool skb_gso_fraglist_ok(const struct sk_buff *skb,
+				       netdev_features_t features,
+				       unsigned int hdrlen, __be16 proto)
+{
+	/* Geometry modified, e.g., by a pull from frag_list */
+	if (skb_pagelen(skb) - hdrlen != skb_shinfo(skb)->gso_size)
+		return false;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_DODGY)
+		return false;
+
+	/* Tunnel headers and outer checksums are not rebuilt */
+	if (skb->encapsulation || skb_tnl_header_len(skb))
+		return false;
+
+	/* Checksums are not resolved in software */
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    !can_checksum_protocol(features, proto))
+		return false;
+
+	return true;
+}
+
 static inline int gso_pskb_expand_head(struct sk_buff *skb, int extra)
 {
 	int new_headroom, headroom;
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 520778c5ca7f..7691be01da4d 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -105,11 +105,10 @@ static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) {
-		struct tcphdr *th = tcp_hdr(skb);
 		int err;
 
-		if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) &&
-		    !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
+		if (skb_gso_fraglist_ok(skb, features, tcp_hdrlen(skb),
+					htons(ETH_P_IP)))
 			return __tcp4_gso_segment_list(skb, features);
 
 		err = skb_cow_head(skb, 0);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b77ae2f00c62..243bd75302d8 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -519,8 +519,9 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 		 * the frag_list skbs still have the IP family we segment for,
 		 * as their network headers are not rebuilt.
 		 */
-		if ((skb_pagelen(gso_skb) - sizeof(*uh) == skb_shinfo(gso_skb)->gso_size) &&
-		    !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_DODGY) &&
+		if (skb_gso_fraglist_ok(gso_skb, features, sizeof(*uh),
+					is_ipv6 ? htons(ETH_P_IPV6) :
+						  htons(ETH_P_IP)) &&
 		    ip_hdr(skb_shinfo(gso_skb)->frag_list)->version == (is_ipv6 ? 6 : 4))
 			return __udp_gso_segment_list(gso_skb, features, is_ipv6);
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 0914f95f100c..71feb92aeac2 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -9,6 +9,7 @@
 #include <linux/skbuff.h>
 #include <net/inet6_hashtables.h>
 #include <net/gro.h>
+#include <net/gso.h>
 #include <net/protocol.h>
 #include <net/tcp.h>
 #include <net/ip6_checksum.h>
@@ -177,11 +178,10 @@ static struct sk_buff *tcp6_gso_segment(struct sk_buff *skb,
 		return ERR_PTR(-EINVAL);
 
 	if (skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST) {
-		struct tcphdr *th = tcp_hdr(skb);
 		int err;
 
-		if ((skb_pagelen(skb) - th->doff * 4 == skb_shinfo(skb)->gso_size) &&
-		    !(skb_shinfo(skb)->gso_type & SKB_GSO_DODGY))
+		if (skb_gso_fraglist_ok(skb, features, tcp_hdrlen(skb),
+					htons(ETH_P_IPV6)))
 			return __tcp6_gso_segment_list(skb, features);
 
 		err = skb_cow_head(skb, 0);
-- 
2.56.1.750.gf70dc682cf-goog


^ permalink raw reply related	[flat|nested] 3+ messages in thread

end of thread, other threads:[~2026-11-20  4:47 UTC | newest]

Thread overview: 3+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-11-20  4:46 [PATCH net v2 0/2] net: gso: fraglist segmentation fixes Willem de Bruijn
2026-11-20  4:46 ` [PATCH net v2 1/2] net: gso: cow head on tcp fraglist fallback to skb_segment Willem de Bruijn
2026-11-20  4:46 ` [PATCH net v2 2/2] net: gso: fall back to skb_segment when fraglist cannot satisfy checksum Willem de Bruijn

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox