Received-SPF: pass (google.com: domain of linux-kernel+bounces-157438-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
From: Felix Fietkau <nbd@nbd.name>
To: netdev@vger.kernel.org,
	Eric Dumazet <edumazet@google.com>,
	"David S. Miller" <davem@davemloft.net>,
	Jakub Kicinski <kuba@kernel.org>,
	Paolo Abeni <pabeni@redhat.com>,
	David Ahern <dsahern@kernel.org>
Cc: willemdebruijn.kernel@gmail.com,
	linux-kernel@vger.kernel.org
Subject: [PATCH net-next 3/4] net: add code for TCP fraglist GRO
Date: Wed, 24 Apr 2024 20:04:55 +0200
Message-ID: <20240424180458.56211-4-nbd@nbd.name>
In-Reply-To: <20240424180458.56211-1-nbd@nbd.name>
References: <20240424180458.56211-1-nbd@nbd.name>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

This implements fraglist GRO similar to how it's handled in UDP, however
no functional changes are added yet. The next change adds a heuristic for
using fraglist GRO instead of regular GRO.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 include/net/tcp.h        |  3 ++-
 net/ipv4/tcp_offload.c   | 29 +++++++++++++++++++++++++++--
 net/ipv6/tcpv6_offload.c | 11 ++++++++++-
 3 files changed, 39 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b935e1ae4caf..875cda53a7c9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2194,7 +2194,8 @@ void tcp_v4_destroy_sock(struct sock *sk);
 
 struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features);
-struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				bool fraglist);
 INDIRECT_CALLABLE_DECLARE(int tcp4_gro_complete(struct sk_buff *skb, int thoff));
 INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb));
 INDIRECT_CALLABLE_DECLARE(int tcp6_gro_complete(struct sk_buff *skb, int thoff));
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 06dbb2e2b2f3..6294e7a5c099 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -252,7 +252,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	return segs;
 }
 
-struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				bool fraglist)
 {
 	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
@@ -289,6 +290,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 	len = skb_gro_len(skb);
 	flags = tcp_flag_word(th);
 
+	NAPI_GRO_CB(skb)->is_flist = fraglist;
 	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
@@ -308,6 +310,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 found:
 	/* Include the IP ID check below from the inner most IP hdr */
 	flush = NAPI_GRO_CB(p)->flush;
+	flush |= fraglist != NAPI_GRO_CB(p)->is_flist;
 	flush |= (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
 		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
@@ -341,6 +344,19 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
 	flush |= skb_cmp_decrypted(p, skb);
 
+	if (fraglist) {
+		flush |= (__force int)(flags ^ tcp_flag_word(th2));
+		flush |= skb->ip_summed != p->ip_summed;
+		flush |= skb->csum_level != p->csum_level;
+		flush |= !pskb_may_pull(skb, skb_gro_offset(skb));
+		flush |= NAPI_GRO_CB(p)->count >= 64;
+
+		if (flush || skb_gro_receive_list(p, skb))
+			mss = 1;
+
+		goto out_check_final;
+	}
+
 	if (flush || skb_gro_receive(p, skb)) {
 		mss = 1;
 		goto out_check_final;
@@ -399,7 +415,7 @@ struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 		return NULL;
 	}
 
-	return tcp_gro_receive(head, skb);
+	return tcp_gro_receive(head, skb, false);
 }
 
 INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
@@ -407,6 +423,15 @@ INDIRECT_CALLABLE_SCOPE int tcp4_gro_complete(struct sk_buff *skb, int thoff)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
+	if (NAPI_GRO_CB(skb)->is_flist) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV4;
+		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+		__skb_incr_checksum_unnecessary(skb);
+
+		return 0;
+	}
+
 	th->check = ~tcp_v4_check(skb->len - thoff, iph->saddr,
 				  iph->daddr, 0);
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 12fe79cb2c10..239588557dc4 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -24,7 +24,7 @@ struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb)
 		return NULL;
 	}
 
-	return tcp_gro_receive(head, skb);
+	return tcp_gro_receive(head, skb, false);
 }
 
 INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
@@ -32,6 +32,15 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 	const struct ipv6hdr *iph = ipv6_hdr(skb);
 	struct tcphdr *th = tcp_hdr(skb);
 
+	if (NAPI_GRO_CB(skb)->is_flist) {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_FRAGLIST | SKB_GSO_TCPV6;
+		skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+		__skb_incr_checksum_unnecessary(skb);
+
+		return 0;
+	}
+
 	th->check = ~tcp_v6_check(skb->len - thoff, &iph->saddr,
 				  &iph->daddr, 0);
 	skb_shinfo(skb)->gso_type |= SKB_GSO_TCPV6;
-- 
2.44.0