Commit 95e26838 authored by David S. Miller's avatar David S. Miller
Browse files

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: default avatarDavid S. Miller <davem@davemloft.net>
parents c3664d91 de5a1f3c

include/net/gro.h

+28 −24
Original line number Diff line number Diff line
@@ -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

+4 −12
Original line number Diff line number Diff line
@@ -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);