Merge branch 'net-gso-restore-outer-ip-ids-correctly'

Richard Gobert says:

====================
net: gso: restore outer ip ids correctly

GRO currently ignores outer IPv4 header IDs for encapsulated packets
that have their don't-fragment flag set. GSO, however, always assumes
that outer IP IDs are incrementing. This results in GSO mangling the
outer IDs when they aren't incrementing. For example, GSO mangles the
outer IDs of IPv6 packets that were converted to IPv4, which must
have an ID of 0 according to RFC 6145, sect. 5.1.

GRO+GSO is supposed to be entirely transparent by default. GSO already
correctly restores inner IDs and IDs of non-encapsulated packets. The
tx-tcp-mangleid-segmentation feature can be enabled to allow the
mangling of such IDs so that TSO can be used.

This series fixes outer ID restoration for encapsulated packets when
tx-tcp-mangleid-segmentation is disabled. It also allows GRO to merge
packets with fixed IDs that don't have their don't-fragment flag set.

v1: https://lore.kernel.org/netdev/20250814114030.7683-1-richardbgobert@gmail.com/
v2: https://lore.kernel.org/netdev/20250819063223.5239-1-richardbgobert@gmail.com/
v3: https://lore.kernel.org/netdev/20250821073047.2091-1-richardbgobert@gmail.com/
v4: https://lore.kernel.org/netdev/20250901113826.6508-1-richardbgobert@gmail.com/
v5: https://lore.kernel.org/netdev/20250915113933.3293-1-richardbgobert@gmail.com/
v6: https://lore.kernel.org/netdev/20250916144841.4884-1-richardbgobert@gmail.com/
v7: https://lore.kernel.org/netdev/20250922084103.4764-1-richardbgobert@gmail.com/
====================

Link: https://patch.msgid.link/20250923085908.4687-1-richardbgobert@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 26 insertions, 23 deletions

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1c54d44805fa..1b85454116f6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5320,13 +5320,18 @@ void skb_warn_bad_offload(const struct sk_buff *skb);
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
-	netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT;
+	netdev_features_t feature;
+
+	if (gso_type & (SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_FIXEDID_INNER))
+		gso_type |= __SKB_GSO_TCP_FIXEDID;
+
+	feature = ((netdev_features_t)gso_type << NETIF_F_GSO_SHIFT) & NETIF_F_GSO_MASK;
 
 	/* check flags correspondence */
 	BUILD_BUG_ON(SKB_GSO_TCPV4   != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
-	BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(__SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 78ecfa7d00d0..fb3fec9affaa 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -674,7 +674,7 @@ enum {
 	/* This indicates the tcp segment has CWR set. */
 	SKB_GSO_TCP_ECN = 1 << 2,
 
-	SKB_GSO_TCP_FIXEDID = 1 << 3,
+	__SKB_GSO_TCP_FIXEDID = 1 << 3,
 
 	SKB_GSO_TCPV6 = 1 << 4,
 
@@ -707,6 +707,12 @@ enum {
 	SKB_GSO_FRAGLIST = 1 << 18,
 
 	SKB_GSO_TCP_ACCECN = 1 << 19,
+
+	/* These indirectly map onto the same netdev feature.
+	 * If NETIF_F_TSO_MANGLEID is set it may mangle both inner and outer IDs.
+	 */
+	SKB_GSO_TCP_FIXEDID = 1 << 30,
+	SKB_GSO_TCP_FIXEDID_INNER = 1 << 31,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/include/net/gro.h b/include/net/gro.h
index a0fca7ac6e7e..e3affb2e2ca8 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -71,14 +71,11 @@ struct napi_gro_cb {
 		/* Free the skb? */
 		u8	free:2;
 
-		/* Used in foo-over-udp, set in udp[46]_gro_receive */
-		u8	is_ipv6:1;
-
 		/* Used in GRE, set in fou/gue_gro_receive */
 		u8	is_fou:1;
 
 		/* Used to determine if ipid_offset can be ignored */
-		u8	ip_fixedid:1;
+		u8	ip_fixedid:2;
 
 		/* Number of gro_receive callbacks this packet already went through */
 		u8 recursion_counter:4;
@@ -445,29 +442,25 @@ static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb,
 }
 
 static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2,
-				 struct sk_buff *p, bool outer)
+				 struct sk_buff *p, bool inner)
 {
 	const u32 id = ntohl(*(__be32 *)&iph->id);
 	const u32 id2 = ntohl(*(__be32 *)&iph2->id);
 	const u16 ipid_offset = (id >> 16) - (id2 >> 16);
 	const u16 count = NAPI_GRO_CB(p)->count;
-	const u32 df = id & IP_DF;
-	int flush;
 
 	/* All fields must match except length and checksum. */
-	flush = (iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | (df ^ (id2 & IP_DF));
-
-	if (flush | (outer && df))
-		return flush;
+	if ((iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | ((id ^ id2) & IP_DF))
+		return true;
 
 	/* When we receive our second frame we can make a decision on if we
 	 * continue this flow as an atomic flow with a fixed ID or if we use
 	 * an incrementing ID.
 	 */
-	if (count == 1 && df && !ipid_offset)
-		NAPI_GRO_CB(p)->ip_fixedid = true;
+	if (count == 1 && !ipid_offset)
+		NAPI_GRO_CB(p)->ip_fixedid |= 1 << inner;
 
-	return ipid_offset ^ (count * !NAPI_GRO_CB(p)->ip_fixedid);
+	return ipid_offset ^ (count * !(NAPI_GRO_CB(p)->ip_fixedid & (1 << inner)));
 }
 
 static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2)
@@ -482,7 +475,7 @@ static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr
 
 static inline int __gro_receive_network_flush(const void *th, const void *th2,
 					      struct sk_buff *p, const u16 diff,
-					      bool outer)
+					      bool inner)
 {
 	const void *nh = th - diff;
 	const void *nh2 = th2 - diff;
@@ -490,19 +483,18 @@ static inline int __gro_receive_network_flush(const void *th, const void *th2,
 	if (((struct iphdr *)nh)->version == 6)
 		return ipv6_gro_flush(nh, nh2);
 	else
-		return inet_gro_flush(nh, nh2, p, outer);
+		return inet_gro_flush(nh, nh2, p, inner);
 }
 
 static inline int gro_receive_network_flush(const void *th, const void *th2,
 					    struct sk_buff *p)
 {
-	const bool encap_mark = NAPI_GRO_CB(p)->encap_mark;
 	int off = skb_transport_offset(p);
 	int flush;
 
-	flush = __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->network_offset, encap_mark);
-	if (encap_mark)
-		flush |= __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->inner_network_offset, false);
+	flush = __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->network_offset, false);
+	if (NAPI_GRO_CB(p)->encap_mark)
+		flush |= __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->inner_network_offset, true);
 
 	return flush;
 }