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>

2 files changed, 44 insertions, 16 deletions

diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c
index d5824eadea10..2b1d9f2b3e9e 100644
--- a/tools/testing/selftests/net/gro.c
+++ b/tools/testing/selftests/net/gro.c
@@ -93,6 +93,7 @@ static bool tx_socket = true;
 static int tcp_offset = -1;
 static int total_hdr_len = -1;
 static int ethhdr_proto = -1;
+static bool ipip;
 static const int num_flush_id_cases = 6;
 
 static void vlog(const char *fmt, ...)
@@ -114,7 +115,9 @@ static void setup_sock_filter(int fd)
 	int ipproto_off, opt_ipproto_off;
 	int next_off;
 
-	if (proto == PF_INET)
+	if (ipip)
+		next_off = sizeof(struct iphdr) + offsetof(struct iphdr, protocol);
+	else if (proto == PF_INET)
 		next_off = offsetof(struct iphdr, protocol);
 	else
 		next_off = offsetof(struct ipv6hdr, nexthdr);
@@ -244,7 +247,7 @@ static void fill_datalinklayer(void *buf)
 	eth->h_proto = ethhdr_proto;
 }
 
-static void fill_networklayer(void *buf, int payload_len)
+static void fill_networklayer(void *buf, int payload_len, int protocol)
 {
 	struct ipv6hdr *ip6h = buf;
 	struct iphdr *iph = buf;
@@ -254,7 +257,7 @@ static void fill_networklayer(void *buf, int payload_len)
 
 		ip6h->version = 6;
 		ip6h->payload_len = htons(sizeof(struct tcphdr) + payload_len);
-		ip6h->nexthdr = IPPROTO_TCP;
+		ip6h->nexthdr = protocol;
 		ip6h->hop_limit = 8;
 		if (inet_pton(AF_INET6, addr6_src, &ip6h->saddr) != 1)
 			error(1, errno, "inet_pton source ip6");
@@ -266,7 +269,7 @@ static void fill_networklayer(void *buf, int payload_len)
 		iph->version = 4;
 		iph->ihl = 5;
 		iph->ttl = 8;
-		iph->protocol	= IPPROTO_TCP;
+		iph->protocol	= protocol;
 		iph->tot_len = htons(sizeof(struct tcphdr) +
 				payload_len + sizeof(struct iphdr));
 		iph->frag_off = htons(0x4000); /* DF = 1, MF = 0 */
@@ -313,9 +316,19 @@ static void create_packet(void *buf, int seq_offset, int ack_offset,
 {
 	memset(buf, 0, total_hdr_len);
 	memset(buf + total_hdr_len, 'a', payload_len);
+
 	fill_transportlayer(buf + tcp_offset, seq_offset, ack_offset,
 			    payload_len, fin);
-	fill_networklayer(buf + ETH_HLEN, payload_len);
+
+	if (ipip) {
+		fill_networklayer(buf + ETH_HLEN, payload_len + sizeof(struct iphdr),
+				  IPPROTO_IPIP);
+		fill_networklayer(buf + ETH_HLEN + sizeof(struct iphdr),
+				  payload_len, IPPROTO_TCP);
+	} else {
+		fill_networklayer(buf + ETH_HLEN, payload_len, IPPROTO_TCP);
+	}
+
 	fill_datalinklayer(buf);
 }
 
@@ -416,6 +429,13 @@ static void recompute_packet(char *buf, char *no_ext, int extlen)
 		iph->tot_len = htons(ntohs(iph->tot_len) + extlen);
 		iph->check = 0;
 		iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+
+		if (ipip) {
+			iph += 1;
+			iph->tot_len = htons(ntohs(iph->tot_len) + extlen);
+			iph->check = 0;
+			iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+		}
 	} else {
 		ip6h->payload_len = htons(ntohs(ip6h->payload_len) + extlen);
 	}
@@ -670,7 +690,7 @@ static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase)
 		iph2->id = htons(9);
 		break;
 
-	case 3: /* DF=0, Fixed - should not coalesce */
+	case 3: /* DF=0, Fixed - should coalesce */
 		iph1->frag_off &= ~htons(IP_DF);
 		iph1->id = htons(8);
 
@@ -777,7 +797,7 @@ static void send_fragment4(int fd, struct sockaddr_ll *daddr)
 	 */
 	memset(buf + total_hdr_len, 'a', PAYLOAD_LEN * 2);
 	fill_transportlayer(buf + tcp_offset, PAYLOAD_LEN, 0, PAYLOAD_LEN * 2, 0);
-	fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN);
+	fill_networklayer(buf + ETH_HLEN, PAYLOAD_LEN, IPPROTO_TCP);
 	fill_datalinklayer(buf);
 
 	iph->frag_off = htons(0x6000); // DF = 1, MF = 1
@@ -1071,7 +1091,7 @@ static void gro_sender(void)
 		 * and min ipv6hdr size. Like MAX_HDR_SIZE,
 		 * MAX_PAYLOAD is defined with the larger header of the two.
 		 */
-		int offset = proto == PF_INET ? 20 : 0;
+		int offset = (proto == PF_INET && !ipip) ? 20 : 0;
 		int remainder = (MAX_PAYLOAD + offset) % MSS;
 
 		send_large(txfd, &daddr, remainder);
@@ -1188,10 +1208,9 @@ static void gro_receiver(void)
 			correct_payload[0] = PAYLOAD_LEN * 2;
 			check_recv_pkts(rxfd, correct_payload, 1);
 
-			printf("DF=0, Fixed - should not coalesce: ");
-			correct_payload[0] = PAYLOAD_LEN;
-			correct_payload[1] = PAYLOAD_LEN;
-			check_recv_pkts(rxfd, correct_payload, 2);
+			printf("DF=0, Fixed - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
 
 			printf("DF=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: ");
 			correct_payload[0] = PAYLOAD_LEN * 2;
@@ -1222,7 +1241,7 @@ static void gro_receiver(void)
 			check_recv_pkts(rxfd, correct_payload, 2);
 		}
 	} else if (strcmp(testname, "large") == 0) {
-		int offset = proto == PF_INET ? 20 : 0;
+		int offset = (proto == PF_INET && !ipip) ? 20 : 0;
 		int remainder = (MAX_PAYLOAD + offset) % MSS;
 
 		correct_payload[0] = (MAX_PAYLOAD + offset);
@@ -1251,6 +1270,7 @@ static void parse_args(int argc, char **argv)
 		{ "iface", required_argument, NULL, 'i' },
 		{ "ipv4", no_argument, NULL, '4' },
 		{ "ipv6", no_argument, NULL, '6' },
+		{ "ipip", no_argument, NULL, 'e' },
 		{ "rx", no_argument, NULL, 'r' },
 		{ "saddr", required_argument, NULL, 's' },
 		{ "smac", required_argument, NULL, 'S' },
@@ -1260,7 +1280,7 @@ static void parse_args(int argc, char **argv)
 	};
 	int c;
 
-	while ((c = getopt_long(argc, argv, "46d:D:i:rs:S:t:v", opts, NULL)) != -1) {
+	while ((c = getopt_long(argc, argv, "46d:D:ei:rs:S:t:v", opts, NULL)) != -1) {
 		switch (c) {
 		case '4':
 			proto = PF_INET;
@@ -1270,6 +1290,11 @@ static void parse_args(int argc, char **argv)
 			proto = PF_INET6;
 			ethhdr_proto = htons(ETH_P_IPV6);
 			break;
+		case 'e':
+			ipip = true;
+			proto = PF_INET;
+			ethhdr_proto = htons(ETH_P_IP);
+			break;
 		case 'd':
 			addr4_dst = addr6_dst = optarg;
 			break;
@@ -1305,7 +1330,10 @@ int main(int argc, char **argv)
 {
 	parse_args(argc, argv);
 
-	if (proto == PF_INET) {
+	if (ipip) {
+		tcp_offset = ETH_HLEN + sizeof(struct iphdr) * 2;
+		total_hdr_len = tcp_offset + sizeof(struct tcphdr);
+	} else if (proto == PF_INET) {
 		tcp_offset = ETH_HLEN + sizeof(struct iphdr);
 		total_hdr_len = tcp_offset + sizeof(struct tcphdr);
 	} else if (proto == PF_INET6) {
diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 9e3f186bc2a1..4c5144c6f652 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -4,7 +4,7 @@
 readonly SERVER_MAC="aa:00:00:00:00:02"
 readonly CLIENT_MAC="aa:00:00:00:00:01"
 readonly TESTS=("data" "ack" "flags" "tcp" "ip" "large")
-readonly PROTOS=("ipv4" "ipv6")
+readonly PROTOS=("ipv4" "ipv6" "ipip")
 dev=""
 test="all"
 proto="ipv4"