ixgbe: Copybreak sooner to avoid get_page/put_page and offset change overhead

This change makes it so that if only the first 256 bytes of a buffer are
used we just copy the data out and leave the offset and page count
unchanged. There are multiple advantages to this. First it allows us to
reuse the page much more in the case of pages larger than 4K. It also
allows us to avoid some expensive atomic operations in the form of
get_page/put_page. In perf I have seen CPU utilization for put_page drop
from 3.5% to 1.8% as a result of this patch when doing small packet routing,
and packet rates increased by about 3%.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1487,9 +1487,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
 	 * we need the header to contain the greater of either ETH_HLEN or
 	 * 60 bytes if the skb->len is less than 60 for skb_pad.
 	 */
-	pull_len = skb_frag_size(frag);
-	if (pull_len > IXGBE_RX_HDR_SIZE)
-		pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);
+	pull_len = ixgbe_get_headlen(va, IXGBE_RX_HDR_SIZE);
 
 	/* align pull length to size of long to optimize memcpy performance */
 	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
@@ -1499,17 +1497,6 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring,
 	frag->page_offset += pull_len;
 	skb->data_len -= pull_len;
 	skb->tail += pull_len;
-
-	/*
-	 * if we sucked the frag empty then we should free it,
-	 * if there are other frags here something is screwed up in hardware
-	 */
-	if (skb_frag_size(frag) == 0) {
-		BUG_ON(skb_shinfo(skb)->nr_frags != 1);
-		skb_shinfo(skb)->nr_frags = 0;
-		__skb_frag_unref(frag);
-		skb->truesize -= ixgbe_rx_bufsz(rx_ring);
-	}
 }
 
 /**
@@ -1575,7 +1562,8 @@ static bool ixgbe_cleanup_headers(struct ixgbe_ring *rx_ring,
 	}
 
 	/* place header in linear portion of buffer */
-	ixgbe_pull_tail(rx_ring, skb);
+	if (skb_is_nonlinear(skb))
+		ixgbe_pull_tail(rx_ring, skb);
 
 #ifdef IXGBE_FCOE
 	/* do not attempt to pad FCoE Frames as this will disrupt DDP */
@@ -1656,6 +1644,20 @@ static bool ixgbe_add_rx_frag(struct ixgbe_ring *rx_ring,
 				   ixgbe_rx_bufsz(rx_ring);
 #endif
 
+	if ((size <= IXGBE_RX_HDR_SIZE) && !skb_is_nonlinear(skb)) {
+		unsigned char *va = page_address(page) + rx_buffer->page_offset;
+
+		memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long)));
+
+		/* we can reuse buffer as-is, just make sure it is local */
+		if (likely(page_to_nid(page) == numa_node_id()))
+			return true;
+
+		/* this page cannot be reused so discard it */
+		put_page(page);
+		return false;
+	}
+
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
 			rx_buffer->page_offset, size, truesize);