Skip to contentSkip to conversation

tcp: Make GRO completion function inline

PATCH In review Parav Pandit 4 participants 5 messages Jun 11, 2023 – Jul 3, 2023

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 tcp: Make GRO completion function inline

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.

---
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(-)
include/net/tcp.h +18 -1
index 49611af31bb7..e6e0a7125618 100644
@@ -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);
 
net/ipv4/tcp_offload.c +0 -18
index 8311c38267b5..5628d6007d43 100644
@@ -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)
 {
Signature · 1 line
2.26.2
Tested-by Reviewed-by on v1 1/1
#1 lore raw
Quoted 14 lines · Parav Pandit

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.

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

Quoted 6 lines

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?

---

Sorry for the delay. It works fine on bnxt NICs running hardware GRO. No noticeable changes in throughput or CPU utilization running simple netperf. Thanks.

#2 lore raw

From: Michael Chan <[email protected]>
Date: Sat, 1 Jul 2023 16:09:53 -0700

Quoted 20 lines · Parav Pandit
Quoted 19 lines

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.

---
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?

Quoted 8 lines
Quoted 1 line

---

Sorry for the delay. It works fine on bnxt NICs running hardware GRO. No noticeable changes in throughput or CPU utilization running simple netperf. Thanks.

Why is this needed then if it gives nothing? :D

Thanks,
Olek

#3 lore raw
Quoted 26 lines · Alexander Lobakin

From: Michael Chan <[email protected]>
Date: Sat, 1 Jul 2023 16:09:53 -0700

Quoted 22 lines · Parav Pandit
Quoted 20 lines

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.

---
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?

---

Quoted 8 lines
Quoted 6 lines

Sorry for the delay. It works fine on bnxt NICs running hardware GRO. No noticeable changes in throughput or CPU utilization running simple netperf. Thanks.

Why is this needed then if it gives nothing? :D

I only tested at 50G link speed and about 64K aggregation size. At higher speed and smaller aggregation size, perhaps it will show slightly better performance or CPU utilization.

#4 lore raw
In reply to Alexander Lobakin
Quoted 1 line · Alexander Lobakin

Why is this needed then if it gives nothing? :D

It is a question I asked. There are a fair number of trivial sk_buff functions called in the datapath (e.g., skb_add_rx_frag is another). Function calls are not free, so inlining them should *collectively* provide measurable performance bumps as line rates and packet rates increase.