[PATCH net-next] net: avoid indirect calls in L4 checksum calculation

[Matteo Croce]

Commit 283c16a2dfd3 ("indirect call wrappers: helpers to speed-up
indirect calls of builtin") introduces some macros to avoid doing
indirect calls.

Use these helpers to remove two indirect calls in the L4 checksum
calculation for devices which don't have hardware support for it.

As a test I generate packets with pktgen out to a dummy interface
with HW checksumming disabled, to have the checksum calculated in
every sent packet.
The packet rate measured with an i7-6700K CPU and a single pktgen
thread raised from 6143 to 6608 Kpps, an increase by 7.5%

Suggested-by: Davide Caratti <dcaratti@xxxxxxxxxx>
Signed-off-by: Matteo Croce <mcroce@xxxxxxxxxx>
---
 net/core/skbuff.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index e89be6282693..a24a7ef55ce9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -69,6 +69,7 @@
 #include <net/sock.h>
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/sctp/checksum.h>
 #include <net/xfrm.h>
 
 #include <linux/uaccess.h>
@@ -76,9 +77,22 @@
 #include <linux/highmem.h>
 #include <linux/capability.h>
 #include <linux/user_namespace.h>
+#include <linux/indirect_call_wrapper.h>
 
 #include "datagram.h"
 
+#if IS_ENABLED(CONFIG_IP_SCTP)
+#define CSUM_UPDATE(f, ...) \
+	INDIRECT_CALL_2(f, csum_partial_ext, sctp_csum_update, __VA_ARGS__)
+#define CSUM_COMBINE(f, ...) \
+	INDIRECT_CALL_2(f, csum_block_add_ext, sctp_csum_combine, __VA_ARGS__)
+#else
+#define CSUM_UPDATE(f, ...) \
+	INDIRECT_CALL_1(f, csum_partial_ext, __VA_ARGS__)
+#define CSUM_COMBINE(f, ...) \
+	INDIRECT_CALL_1(f, csum_block_add_ext, __VA_ARGS__)
+#endif
+
 struct kmem_cache *skbuff_head_cache __ro_after_init;
 static struct kmem_cache *skbuff_fclone_cache __ro_after_init;
 #ifdef CONFIG_SKB_EXTENSIONS
@@ -2507,7 +2521,7 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 	if (copy > 0) {
 		if (copy > len)
 			copy = len;
-		csum = ops->update(skb->data + offset, copy, csum);
+		csum = CSUM_UPDATE(ops->update, skb->data + offset, copy, csum);
 		if ((len -= copy) == 0)
 			return csum;
 		offset += copy;
@@ -2534,9 +2548,9 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 					      frag->page_offset + offset - start,
 					      copy, p, p_off, p_len, copied) {
 				vaddr = kmap_atomic(p);
-				csum2 = ops->update(vaddr + p_off, p_len, 0);
+				csum2 = CSUM_UPDATE(ops->update, vaddr + p_off, p_len, 0);
 				kunmap_atomic(vaddr);
-				csum = ops->combine(csum, csum2, pos, p_len);
+				csum = CSUM_COMBINE(ops->combine, csum, csum2, pos, p_len);
 				pos += p_len;
 			}
 
@@ -2559,7 +2573,7 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len,
 				copy = len;
 			csum2 = __skb_checksum(frag_iter, offset - start,
 					       copy, 0, ops);
-			csum = ops->combine(csum, csum2, pos, copy);
+			csum = CSUM_COMBINE(ops->combine, csum, csum2, pos, copy);
 			if ((len -= copy) == 0)
 				return csum;
 			offset += copy;
-- 
2.21.0