Merge branch 'net-gro-add-flush-flush_id-checks-and-fix-wrong-offset-in-udp'

Richard Gobert says:

====================
net: gro: add flush/flush_id checks and fix wrong offset in udp

This series fixes a bug in the complete phase of UDP in GRO, in which
socket lookup fails due to using network_header when parsing encapsulated
packets. The fix is to add network_offset and inner_network_offset to
napi_gro_cb and use these offsets for socket lookup.

In addition p->flush/flush_id should be checked in all UDP flows. The
same logic from tcp_gro_receive is applied for all flows in
udp_gro_receive_segment. This prevents packets with mismatching network
headers (flush/flush_id turned on) from merging in UDP GRO.

The original series includes a change to vxlan test which adds the local
parameter to prevent similar future bugs. I plan to submit it separately to
net-next.

This series is part of a previously submitted series to net-next:
https://lore.kernel.org/all/20240408141720.98832-1-richardbgobert@gmail.com/

v3 -> v4:
 - Store network offsets, and use them only in udp_gro_complete flows
 - Correct commit hash used in Fixes tag
 - v3:
 https://lore.kernel.org/netdev/20240424163045.123528-1-richardbgobert@gmail.com/

v2 -> v3:
 - Add network_offsets and fix udp bug in a single commit to make backporting easier
 - Write to inner_network_offset in {inet,ipv6}_gro_receive
 - Use network_offsets union in tcp[46]_gro_complete as well
 - v2:
 https://lore.kernel.org/netdev/20240419153542.121087-1-richardbgobert@gmail.com/

v1 -> v2:
 - Use network_offsets instead of p_poff param as suggested by Willem
 - Check flush before postpull, and for all UDP GRO flows
 - v1:
 https://lore.kernel.org/netdev/20240412152120.115067-1-richardbgobert@gmail.com/
====================

Link: https://lore.kernel.org/r/20240430143555.126083-1-richardbgobert@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

9 files changed, 33 insertions, 5 deletions

diff --git a/include/net/gro.h b/include/net/gro.h
index 50f1e403dbbb..c1d4ca0463a1 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -87,6 +87,15 @@ struct napi_gro_cb {
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
+
+	/* L3 offsets */
+	union {
+		struct {
+			u16 network_offset;
+			u16 inner_network_offset;
+		};
+		u16 network_offsets[2];
+	};
 };
 
 #define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index f00158234505..9404dd551dfd 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -478,6 +478,8 @@ static struct sk_buff *vlan_gro_receive(struct list_head *head,
 	if (unlikely(!vhdr))
 		goto out;
 
+	NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark] = hlen;
+
 	type = vhdr->h_vlan_encapsulated_proto;
 
 	ptype = gro_find_receive_by_type(type);
diff --git a/net/core/gro.c b/net/core/gro.c
index 83f35d99a682..c7901253a1a8 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -371,6 +371,7 @@ static inline void skb_gro_reset_offset(struct sk_buff *skb, u32 nhoff)
 	const skb_frag_t *frag0;
 	unsigned int headlen;
 
+	NAPI_GRO_CB(skb)->network_offset = 0;
 	NAPI_GRO_CB(skb)->data_offset = 0;
 	headlen = skb_headlen(skb);
 	NAPI_GRO_CB(skb)->frag0 = skb->data;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 55bd72997b31..fafb123f798b 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1572,6 +1572,7 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	/* The above will be needed by the transport layer if there is one
 	 * immediately following this IP hdr.
 	 */
+	NAPI_GRO_CB(skb)->inner_network_offset = off;
 
 	/* Note : No need to call skb_gro_postpull_rcsum() here,
 	 * as we already checked checksum over ipv4 header was 0
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 420905be5f30..b32cf2eeeb41 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -532,7 +532,8 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
-	const struct iphdr *iph = ip_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
 	struct net *net = dev_net(skb->dev);
 	int iif, sdif;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 3498dd1d0694..8721fe5beca2 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -471,6 +471,7 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 	struct sk_buff *p;
 	unsigned int ulen;
 	int ret = 0;
+	int flush;
 
 	/* requires non zero csum, for symmetry with GSO */
 	if (!uh->check) {
@@ -504,13 +505,22 @@ static struct sk_buff *udp_gro_receive_segment(struct list_head *head,
 			return p;
 		}
 
+		flush = NAPI_GRO_CB(p)->flush;
+
+		if (NAPI_GRO_CB(p)->flush_id != 1 ||
+		    NAPI_GRO_CB(p)->count != 1 ||
+		    !NAPI_GRO_CB(p)->is_atomic)
+			flush |= NAPI_GRO_CB(p)->flush_id;
+		else
+			NAPI_GRO_CB(p)->is_atomic = false;
+
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot
 		 * leading to excessive truesize values.
 		 * On len mismatch merge the first packet shorter than gso_size,
 		 * otherwise complete the GRO packet.
 		 */
-		if (ulen > ntohs(uh2->len)) {
+		if (ulen > ntohs(uh2->len) || flush) {
 			pp = p;
 		} else {
 			if (NAPI_GRO_CB(skb)->is_flist) {
@@ -718,7 +728,8 @@ EXPORT_SYMBOL(udp_gro_complete);
 
 INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	const struct iphdr *iph = ip_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct iphdr *iph = (struct iphdr *)(skb->data + offset);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
 	/* do fraglist only if there is no outer UDP encap (or we already processed it) */
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index b41e35af69ea..c8b909a9904f 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -237,6 +237,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 		goto out;
 
 	skb_set_network_header(skb, off);
+	NAPI_GRO_CB(skb)->inner_network_offset = off;
 
 	flush += ntohs(iph->payload_len) != skb->len - hlen;
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1a4cccdd40c9..8f7aa8bac1e7 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -272,7 +272,8 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
 struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
-	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset);
 	struct net *net = dev_net(skb->dev);
 	int iif, sdif;
 
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index bbd347de00b4..b41152dd4246 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -164,7 +164,8 @@ flush:
 
 INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff)
 {
-	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
+	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + offset);
 	struct udphdr *uh = (struct udphdr *)(skb->data + nhoff);
 
 	/* do fraglist only if there is no outer UDP encap (or we already processed it) */