net: gro: minor optimization for dev_gro_receive()

While inspecting some perf report, I noticed that the compiler
emits suboptimal code for the napi CB initialization, fetching
and storing multiple times the memory for flags bitfield.
This is with gcc 10.3.1, but I observed the same with older compiler
versions.

We can help the compiler to do a nicer work clearing several
fields at once using an u32 alias. The generated code is quite
smaller, with the same number of conditional.

Before:
objdump -t net/core/gro.o | grep " F .text"
0000000000000bb0 l     F .text	0000000000000357 dev_gro_receive

After:
0000000000000bb0 l     F .text	000000000000033c dev_gro_receive

v1  -> v2:
 - use struct_group (Alexander and Alex)

RFC -> v1:
 - use __struct_group to delimit the zeroed area (Alexander)
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/gro.h

@@ -29,14 +29,17 @@ struct napi_gro_cb {
 	/* Number of segments aggregated. */
 	u16	count;
 
-	/* Start offset for remote checksum offload */
-	u16	gro_remcsum_start;
+	/* Used in ipv6_gro_receive() and foo-over-udp */
+	u16	proto;
 
 	/* jiffies when first packet was created/queued */
 	unsigned long age;
 
-	/* Used in ipv6_gro_receive() and foo-over-udp */
-	u16	proto;
+	/* portion of the cb set to zero at every gro iteration */
+	struct_group(zeroed,
+
+		/* Start offset for remote checksum offload */
+		u16	gro_remcsum_start;
 
 		/* This is non-zero if the packet may be of the same flow. */
 		u8	same_flow:1;
@@ -69,6 +72,7 @@ struct napi_gro_cb {
 
 		/* GRO is done by frag_list pointer chaining. */
 		u8	is_flist:1;
+	);
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;

net/core/gro.c

@@ -459,29 +459,22 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 		skb_set_network_header(skb, skb_gro_offset(skb));
 		skb_reset_mac_len(skb);
-		NAPI_GRO_CB(skb)->same_flow = 0;
+		BUILD_BUG_ON(sizeof_field(struct napi_gro_cb, zeroed) != sizeof(u32));
+		BUILD_BUG_ON(!IS_ALIGNED(offsetof(struct napi_gro_cb, zeroed),
+					 sizeof(u32))); /* Avoid slow unaligned acc */
+		*(u32 *)&NAPI_GRO_CB(skb)->zeroed = 0;
 		NAPI_GRO_CB(skb)->flush = skb_is_gso(skb) || skb_has_frag_list(skb);
-		NAPI_GRO_CB(skb)->free = 0;
-		NAPI_GRO_CB(skb)->encap_mark = 0;
-		NAPI_GRO_CB(skb)->recursion_counter = 0;
-		NAPI_GRO_CB(skb)->is_fou = 0;
 		NAPI_GRO_CB(skb)->is_atomic = 1;
-		NAPI_GRO_CB(skb)->gro_remcsum_start = 0;
 
 		/* Setup for GRO checksum validation */
 		switch (skb->ip_summed) {
 		case CHECKSUM_COMPLETE:
 			NAPI_GRO_CB(skb)->csum = skb->csum;
 			NAPI_GRO_CB(skb)->csum_valid = 1;
-			NAPI_GRO_CB(skb)->csum_cnt = 0;
 			break;
 		case CHECKSUM_UNNECESSARY:
 			NAPI_GRO_CB(skb)->csum_cnt = skb->csum_level + 1;
-			NAPI_GRO_CB(skb)->csum_valid = 0;
 			break;
-		default:
-			NAPI_GRO_CB(skb)->csum_cnt = 0;
-			NAPI_GRO_CB(skb)->csum_valid = 0;
 		}
 
 		pp = INDIRECT_CALL_INET(ptype->callbacks.gro_receive,