Merge branch 'gro-minor-opts'

Paolo Abeni says:

====================
gro: a couple of minor optimization

This series collects a couple of small optimizations for the GRO engine,
reducing slightly the number of cycles for dev_gro_receive().
The delta is within noise range in tput tests, but with big TCP coming
every cycle saved from the GRO engine will count - I hope ;)

v1 -> v2:
 - a few cleanup suggested from Alexander(s)
 - moved away the more controversial 3rd patch
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 32 insertions, 36 deletions

diff --git a/include/net/gro.h b/include/net/gro.h
index 8f75802d50fd..a765fedda5c4 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -29,46 +29,50 @@ 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;
+		/* This is non-zero if the packet may be of the same flow. */
+		u8	same_flow:1;
 
-	/* Used in tunnel GRO receive */
-	u8	encap_mark:1;
+		/* Used in tunnel GRO receive */
+		u8	encap_mark:1;
 
-	/* GRO checksum is valid */
-	u8	csum_valid:1;
+		/* GRO checksum is valid */
+		u8	csum_valid:1;
 
-	/* Number of checksums via CHECKSUM_UNNECESSARY */
-	u8	csum_cnt:3;
+		/* Number of checksums via CHECKSUM_UNNECESSARY */
+		u8	csum_cnt:3;
 
-	/* Free the skb? */
-	u8	free:2;
+		/* Free the skb? */
+		u8	free:2;
 #define NAPI_GRO_FREE		  1
 #define NAPI_GRO_FREE_STOLEN_HEAD 2
 
-	/* Used in foo-over-udp, set in udp[46]_gro_receive */
-	u8	is_ipv6:1;
+		/* Used in foo-over-udp, set in udp[46]_gro_receive */
+		u8	is_ipv6:1;
 
-	/* Used in GRE, set in fou/gue_gro_receive */
-	u8	is_fou:1;
+		/* Used in GRE, set in fou/gue_gro_receive */
+		u8	is_fou:1;
 
-	/* Used to determine if flush_id can be ignored */
-	u8	is_atomic:1;
+		/* Used to determine if flush_id can be ignored */
+		u8	is_atomic:1;
 
-	/* Number of gro_receive callbacks this packet already went through */
-	u8 recursion_counter:4;
+		/* Number of gro_receive callbacks this packet already went through */
+		u8 recursion_counter:4;
 
-	/* GRO is done by frag_list pointer chaining. */
-	u8	is_flist:1;
+		/* GRO is done by frag_list pointer chaining. */
+		u8	is_flist:1;
+	);
 
 	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
 	__wsum	csum;
diff --git a/net/core/gro.c b/net/core/gro.c
index a11b286d1495..ee5e7e889d8b 100644
--- a/net/core/gro.c
+++ b/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,
@@ -634,7 +627,6 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 
 	skb->encapsulation = 0;
 	skb_shinfo(skb)->gso_type = 0;
-	skb->truesize = SKB_TRUESIZE(skb_end_offset(skb));
 	if (unlikely(skb->slow_gro)) {
 		skb_orphan(skb);
 		skb_ext_reset(skb);