[PATCH net-next] tcp: Make GRO completion function inline

[Parav Pandit <parav@nvidia.com>]

At 100G link speed, with 1500 MTU, at 8.2 mpps, if device does GRO for
64K message size, currently it results in ~190k calls to
tcp_gro_complete() in data path.

Inline this small routine to avoid above number of function calls.

Suggested-by: David Ahern <dsahern@kernel.org>
Signed-off-by: Parav Pandit <parav@nvidia.com>

---
This patch is untested as I do not have the any of the 3 hw devices
calling this routine.

qede, bnxt and bnx2x maintainers,

Can you please verify it with your devices if it reduces cpu
utilization marginally or it stays same or has some side effects?

---
 include/net/tcp.h      | 19 ++++++++++++++++++-
 net/ipv4/tcp_offload.c | 18 ------------------
 2 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 49611af31bb7..e6e0a7125618 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -40,6 +40,7 @@
 #include <net/inet_ecn.h>
 #include <net/dst.h>
 #include <net/mptcp.h>
+#include <net/gro.h>
 
 #include <linux/seq_file.h>
 #include <linux/memcontrol.h>
@@ -2043,7 +2044,23 @@ 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));
 INDIRECT_CALLABLE_DECLARE(struct sk_buff *tcp6_gro_receive(struct list_head *head, struct sk_buff *skb));
-void tcp_gro_complete(struct sk_buff *skb);
+
+static inline void tcp_gro_complete(struct sk_buff *skb)
+{
+	struct tcphdr *th = tcp_hdr(skb);
+
+	skb->csum_start = (unsigned char *)th - skb->head;
+	skb->csum_offset = offsetof(struct tcphdr, check);
+	skb->ip_summed = CHECKSUM_PARTIAL;
+
+	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
+
+	if (th->cwr)
+		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
+
+	if (skb->encapsulation)
+		skb->inner_transport_header = skb->transport_header;
+}
 
 void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
 
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 8311c38267b5..5628d6007d43 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -296,24 +296,6 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 	return pp;
 }
 
-void tcp_gro_complete(struct sk_buff *skb)
-{
-	struct tcphdr *th = tcp_hdr(skb);
-
-	skb->csum_start = (unsigned char *)th - skb->head;
-	skb->csum_offset = offsetof(struct tcphdr, check);
-	skb->ip_summed = CHECKSUM_PARTIAL;
-
-	skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count;
-
-	if (th->cwr)
-		skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN;
-
-	if (skb->encapsulation)
-		skb->inner_transport_header = skb->transport_header;
-}
-EXPORT_SYMBOL(tcp_gro_complete);
-
 INDIRECT_CALLABLE_SCOPE
 struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
-- 
2.26.2