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.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 11 insertions, 85 deletions

diff --git a/net/core/gro.c b/net/core/gro.c
index e2f84947fb74..b3b43de1a650 100644
--- a/net/core/gro.c
+++ b/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 @@ found_ptype:
 					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;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a7bad18bc8b5..44564d009e95 100644
--- a/net/ipv4/af_inet.c
+++ b/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,
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index c90704befd7b..4b791e74529e 100644
--- a/net/ipv4/tcp_offload.c
+++ b/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 @@ flush:
 
 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;
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index f6d3c442e260..59448a2dbf2c 100644
--- a/net/ipv4/udp_offload.c
+++ b/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
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index c8b909a9904f..bd5aff97d8b1 100644
--- a/net/ipv6/ip6_offload.c
+++ b/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 @@ not_same_flow:
 				   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);
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index d59f58cbd306..23971903e66d 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -72,7 +72,8 @@ flush:
 
 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)) {