Merge branch 'net-gro-remove-network_header-use-move-p-flush-flush_id-calculations-to-l4'

Richard Gobert says:

====================
net: gro: remove network_header use, move p->{flush/flush_id} calculations to L4

The cb fields network_offset and inner_network_offset are used instead of
skb->network_header throughout GRO.

These fields are then leveraged in the next commit to remove flush_id state
from napi_gro_cb, and stateful code in {ipv6,inet}_gro_receive which may be
unnecessarily complicated due to encapsulation support in GRO. These fields
are checked in L4 instead.

3rd patch adds tests for different flush_id flows in GRO.
====================

Link: https://lore.kernel.org/r/20240509190819.2985-1-richardbgobert@gmail.comSigned-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/gro.h

@@ -36,15 +36,15 @@ struct napi_gro_cb {
 	/* This is non-zero if the packet cannot be merged with the new skb. */
 	u16	flush;
 
-	/* Save the IP ID here and check when we get to the transport layer */
-	u16	flush_id;
-
 	/* Number of segments aggregated. */
 	u16	count;
 
 	/* Used in ipv6_gro_receive() and foo-over-udp and esp-in-udp */
 	u16	proto;
 
+	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
+	__wsum	csum;
+
 /* Used in napi_gro_cb::free */
 #define NAPI_GRO_FREE             1
 #define NAPI_GRO_FREE_STOLEN_HEAD 2
@@ -75,8 +75,8 @@ struct napi_gro_cb {
 		/* Used in GRE, set in fou/gue_gro_receive */
 		u8	is_fou:1;
 
-		/* Used to determine if flush_id can be ignored */
-		u8	is_atomic:1;
+		/* Used to determine if ipid_offset can be ignored */
+		u8	ip_fixedid:1;
 
 		/* Number of gro_receive callbacks this packet already went through */
 		u8 recursion_counter:4;
@@ -85,9 +85,6 @@ struct napi_gro_cb {
 		u8	is_flist:1;
 	);
 
-	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
-	__wsum	csum;
-
 	/* L3 offsets */
 	union {
 		struct {
@@ -181,12 +178,17 @@ static inline void *skb_gro_header(struct sk_buff *skb, unsigned int hlen,
 	return ptr;
 }
 
+static inline int skb_gro_receive_network_offset(const struct sk_buff *skb)
+{
+	return NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark];
+}
+
 static inline void *skb_gro_network_header(const struct sk_buff *skb)
 {
 	if (skb_gro_may_pull(skb, skb_gro_offset(skb)))
-		return skb_gro_header_fast(skb, skb_network_offset(skb));
+		return skb_gro_header_fast(skb, skb_gro_receive_network_offset(skb));
 
-	return skb_network_header(skb);
+	return skb->data + skb_gro_receive_network_offset(skb);
 }
 
 static inline __wsum inet_gro_compute_pseudo(const struct sk_buff *skb,
@@ -437,6 +439,69 @@ static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb,
 					    skb_gro_len(skb), proto, 0));
 }
 
+static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2,
+				 struct sk_buff *p, bool outer)
+{
+	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;
+
+	/* 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;
+
+	return ipid_offset ^ (count * !NAPI_GRO_CB(p)->ip_fixedid);
+}
+
+static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2)
+{
+	/* <Version:4><Traffic_Class:8><Flow_Label:20> */
+	__be32 first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
+
+	/* Flush if Traffic Class fields are different. */
+	return !!((first_word & htonl(0x0FF00000)) |
+		(__force __be32)(iph->hop_limit ^ iph2->hop_limit));
+}
+
+static inline int __gro_receive_network_flush(const void *th, const void *th2,
+					      struct sk_buff *p, const u16 diff,
+					      bool outer)
+{
+	const void *nh = th - diff;
+	const void *nh2 = th2 - diff;
+
+	if (((struct iphdr *)nh)->version == 6)
+		return ipv6_gro_flush(nh, nh2);
+	else
+		return inet_gro_flush(nh, nh2, p, outer);
+}
+
+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);
+
+	return flush;
+}
+
 int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
 int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
 

net/core/gro.c

@@ -358,8 +358,6 @@ static void gro_list_prepare(const struct list_head *head,
 	list_for_each_entry(p, head, list) {
 		unsigned long diffs;
 
-		NAPI_GRO_CB(p)->flush = 0;
-
 		if (hash != skb_get_hash_raw(p)) {
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
@@ -499,7 +497,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 					sizeof(u32))); /* Avoid slow unaligned acc */
 	*(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0;
 	NAPI_GRO_CB(skb)->flush = skb_has_frag_list(skb);
-	NAPI_GRO_CB(skb)->is_atomic = 1;
 	NAPI_GRO_CB(skb)->count = 1;
 	if (unlikely(skb_is_gso(skb))) {
 		NAPI_GRO_CB(skb)->count = skb_shinfo(skb)->gso_segs;

net/ipv4/af_inet.c

@@ -1482,7 +1482,6 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 	struct sk_buff *p;
 	unsigned int hlen;
 	unsigned int off;
-	unsigned int id;
 	int flush = 1;
 	int proto;
 
@@ -1508,13 +1507,10 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 		goto out;
 
 	NAPI_GRO_CB(skb)->proto = proto;
-	id = ntohl(*(__be32 *)&iph->id);
-	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
-	id >>= 16;
+	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (ntohl(*(__be32 *)&iph->id) & ~IP_DF));
 
 	list_for_each_entry(p, head, list) {
 		struct iphdr *iph2;
-		u16 flush_id;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
@@ -1531,48 +1527,9 @@ struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 			NAPI_GRO_CB(p)->same_flow = 0;
 			continue;
 		}
-
-		/* All fields must match except length and checksum. */
-		NAPI_GRO_CB(p)->flush |=
-			(iph->ttl ^ iph2->ttl) |
-			(iph->tos ^ iph2->tos) |
-			((iph->frag_off ^ iph2->frag_off) & htons(IP_DF));
-
-		NAPI_GRO_CB(p)->flush |= flush;
-
-		/* We need to store of the IP ID check to be included later
-		 * when we can verify that this packet does in fact belong
-		 * to a given flow.
-		 */
-		flush_id = (u16)(id - ntohs(iph2->id));
-
-		/* This bit of code makes it much easier for us to identify
-		 * the cases where we are doing atomic vs non-atomic IP ID
-		 * checks.  Specifically an atomic check can return IP ID
-		 * values 0 - 0xFFFF, while a non-atomic check can only
-		 * return 0 or 0xFFFF.
-		 */
-		if (!NAPI_GRO_CB(p)->is_atomic ||
-		    !(iph->frag_off & htons(IP_DF))) {
-			flush_id ^= NAPI_GRO_CB(p)->count;
-			flush_id = flush_id ? 0xFFFF : 0;
-		}
-
-		/* If the previous IP ID value was based on an atomic
-		 * datagram we can overwrite the value and ignore it.
-		 */
-		if (NAPI_GRO_CB(skb)->is_atomic)
-			NAPI_GRO_CB(p)->flush_id = flush_id;
-		else
-			NAPI_GRO_CB(p)->flush_id |= flush_id;
 	}
 
-	NAPI_GRO_CB(skb)->is_atomic = !!(iph->frag_off & htons(IP_DF));
 	NAPI_GRO_CB(skb)->flush |= flush;
-	skb_set_network_header(skb, off);
-	/* 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,

net/ipv4/tcp_offload.c

@@ -313,10 +313,8 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	if (!p)
 		goto out_check_final;
 
-	/* Include the IP ID check below from the inner most IP hdr */
 	th2 = tcp_hdr(p);
-	flush = NAPI_GRO_CB(p)->flush;
-	flush |= (__force int)(flags & TCP_FLAG_CWR);
+	flush = (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
 		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
 	flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
@@ -324,16 +322,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
 		flush |= *(u32 *)((u8 *)th + i) ^
 			 *(u32 *)((u8 *)th2 + i);
 
-	/* When we receive our second frame we can made a decision on if we
-	 * continue this flow as an atomic flow with a fixed ID or if we use
-	 * an incrementing ID.
-	 */
-	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;
+	flush |= gro_receive_network_flush(th, th2, p);
 
 	mss = skb_shinfo(p)->gso_size;
 
@@ -463,7 +452,8 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 
 INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 {
-	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 tcphdr *th = tcp_hdr(skb);
 
 	if (unlikely(NAPI_GRO_CB(skb)->is_flist)) {
@@ -479,7 +469,7 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 				  iph->daddr, 0);
 
 	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV4 |
-			(NAPI_GRO_CB(skb)->is_atomic * SKB_GSO_TCP_FIXEDID);
+			(NAPI_GRO_CB(skb)->ip_fixedid * SKB_GSO_TCP_FIXEDID);
 
 	tcp_gro_complete(skb);
 	return 0;

net/ipv4/udp_offload.c

@@ -478,14 +478,7 @@ 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;
+		flush = gro_receive_network_flush(uh, uh2, p);
 
 		/* Terminate the flow on len mismatch or if it grow "too much".
 		 * Under small packet flood GRO count could elsewhere grow a lot

net/ipv6/ip6_offload.c

@@ -67,7 +67,7 @@ static int ipv6_gro_pull_exthdrs(struct sk_buff *skb, int off, int proto)
 		off += len;
 	}
 
-	skb_gro_pull(skb, off - skb_network_offset(skb));
+	skb_gro_pull(skb, off - skb_gro_receive_network_offset(skb));
 	return proto;
 }
 
@@ -236,7 +236,6 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 	if (unlikely(!iph))
 		goto out;
 
-	skb_set_network_header(skb, off);
 	NAPI_GRO_CB(skb)->inner_network_offset = off;
 
 	flush += ntohs(iph->payload_len) != skb->len - hlen;
@@ -260,7 +259,7 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 	NAPI_GRO_CB(skb)->proto = proto;
 
 	flush--;
-	nlen = skb_network_header_len(skb);
+	nlen = skb_gro_offset(skb) - off;
 
 	list_for_each_entry(p, head, list) {
 		const struct ipv6hdr *iph2;
@@ -291,19 +290,8 @@ INDIRECT_CALLABLE_SCOPE struct sk_buff *ipv6_gro_receive(struct list_head *head,
 				   nlen - sizeof(struct ipv6hdr)))
 				goto not_same_flow;
 		}
-		/* flush if Traffic Class fields are different */
-		NAPI_GRO_CB(p)->flush |= !!((first_word & htonl(0x0FF00000)) |
-			(__force __be32)(iph->hop_limit ^ iph2->hop_limit));
-		NAPI_GRO_CB(p)->flush |= flush;
-
-		/* If the previous IP ID value was based on an atomic
-		 * datagram we can overwrite the value and ignore it.
-		 */
-		if (NAPI_GRO_CB(skb)->is_atomic)
-			NAPI_GRO_CB(p)->flush_id = 0;
 	}
 
-	NAPI_GRO_CB(skb)->is_atomic = true;
 	NAPI_GRO_CB(skb)->flush |= flush;
 
 	skb_gro_postpull_rcsum(skb, iph, nlen);

net/ipv6/tcpv6_offload.c

@@ -72,7 +72,8 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 
 INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 {
-	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 tcphdr *th = tcp_hdr(skb);
 
 	if (unlikely(NAPI_GRO_CB(skb)->is_flist)) {

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 const int num_flush_id_cases = 6;
 
 static void vlog(const char *fmt, ...)
 {
@@ -620,6 +621,113 @@ static void add_ipv6_exthdr(void *buf, void *optpkt, __u8 exthdr_type, char *ext
 	iph->payload_len = htons(ntohs(iph->payload_len) + MIN_EXTHDR_SIZE);
 }
 
+static void fix_ip4_checksum(struct iphdr *iph)
+{
+	iph->check = 0;
+	iph->check = checksum_fold(iph, sizeof(struct iphdr), 0);
+}
+
+static void send_flush_id_case(int fd, struct sockaddr_ll *daddr, int tcase)
+{
+	static char buf1[MAX_HDR_LEN + PAYLOAD_LEN];
+	static char buf2[MAX_HDR_LEN + PAYLOAD_LEN];
+	static char buf3[MAX_HDR_LEN + PAYLOAD_LEN];
+	bool send_three = false;
+	struct iphdr *iph1;
+	struct iphdr *iph2;
+	struct iphdr *iph3;
+
+	iph1 = (struct iphdr *)(buf1 + ETH_HLEN);
+	iph2 = (struct iphdr *)(buf2 + ETH_HLEN);
+	iph3 = (struct iphdr *)(buf3 + ETH_HLEN);
+
+	create_packet(buf1, 0, 0, PAYLOAD_LEN, 0);
+	create_packet(buf2, PAYLOAD_LEN, 0, PAYLOAD_LEN, 0);
+	create_packet(buf3, PAYLOAD_LEN * 2, 0, PAYLOAD_LEN, 0);
+
+	switch (tcase) {
+	case 0: /* DF=1, Incrementing - should coalesce */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(9);
+		break;
+
+	case 1: /* DF=1, Fixed - should coalesce */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(8);
+		break;
+
+	case 2: /* DF=0, Incrementing - should coalesce */
+		iph1->frag_off &= ~htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off &= ~htons(IP_DF);
+		iph2->id = htons(9);
+		break;
+
+	case 3: /* DF=0, Fixed - should not coalesce */
+		iph1->frag_off &= ~htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off &= ~htons(IP_DF);
+		iph2->id = htons(8);
+		break;
+
+	case 4: /* DF=1, two packets incrementing, and one fixed - should
+		 * coalesce only the first two packets
+		 */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(9);
+
+		iph3->frag_off |= htons(IP_DF);
+		iph3->id = htons(9);
+		send_three = true;
+		break;
+
+	case 5: /* DF=1, two packets fixed, and one incrementing - should
+		 * coalesce only the first two packets
+		 */
+		iph1->frag_off |= htons(IP_DF);
+		iph1->id = htons(8);
+
+		iph2->frag_off |= htons(IP_DF);
+		iph2->id = htons(8);
+
+		iph3->frag_off |= htons(IP_DF);
+		iph3->id = htons(9);
+		send_three = true;
+		break;
+	}
+
+	fix_ip4_checksum(iph1);
+	fix_ip4_checksum(iph2);
+	write_packet(fd, buf1, total_hdr_len + PAYLOAD_LEN, daddr);
+	write_packet(fd, buf2, total_hdr_len + PAYLOAD_LEN, daddr);
+
+	if (send_three) {
+		fix_ip4_checksum(iph3);
+		write_packet(fd, buf3, total_hdr_len + PAYLOAD_LEN, daddr);
+	}
+}
+
+static void test_flush_id(int fd, struct sockaddr_ll *daddr, char *fin_pkt)
+{
+	for (int i = 0; i < num_flush_id_cases; i++) {
+		sleep(1);
+		send_flush_id_case(fd, daddr, i);
+		sleep(1);
+		write_packet(fd, fin_pkt, total_hdr_len, daddr);
+	}
+}
+
 static void send_ipv6_exthdr(int fd, struct sockaddr_ll *daddr, char *ext_data1, char *ext_data2)
 {
 	static char buf[MAX_HDR_LEN + PAYLOAD_LEN];
@@ -938,6 +1046,8 @@ static void gro_sender(void)
 			send_fragment4(txfd, &daddr);
 			sleep(1);
 			write_packet(txfd, fin_pkt, total_hdr_len, &daddr);
+
+			test_flush_id(txfd, &daddr, fin_pkt);
 		} else if (proto == PF_INET6) {
 			sleep(1);
 			send_fragment6(txfd, &daddr);
@@ -1064,6 +1174,34 @@ static void gro_receiver(void)
 
 			printf("fragmented ip4 doesn't coalesce: ");
 			check_recv_pkts(rxfd, correct_payload, 2);
+
+			/* is_atomic checks */
+			printf("DF=1, Incrementing - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("DF=1, Fixed - should coalesce: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			check_recv_pkts(rxfd, correct_payload, 1);
+
+			printf("DF=0, Incrementing - should coalesce: ");
+			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=1, 2 Incrementing and one fixed - should coalesce only first 2 packets: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			correct_payload[1] = PAYLOAD_LEN;
+			check_recv_pkts(rxfd, correct_payload, 2);
+
+			printf("DF=1, 2 Fixed and one incrementing - should coalesce only first 2 packets: ");
+			correct_payload[0] = PAYLOAD_LEN * 2;
+			correct_payload[1] = PAYLOAD_LEN;
+			check_recv_pkts(rxfd, correct_payload, 2);
 		} else if (proto == PF_INET6) {
 			/* GRO doesn't check for ipv6 hop limit when flushing.
 			 * Hence no corresponding test to the ipv4 case.