aoe: for performance support larger packet payloads

tAdd adds the ability to work with large packets composed of a number of
segments, using the scatter gather feature of the block layer (biovecs)
and the network layer (skb frag array).  The motivation is the performance
gained by using a packet data payload greater than a page size and by
using the network card's scatter gather feature.

Users of the out-of-tree aoe driver already had these changes, but since
early 2011, they have complained of increased memory utilization and
higher CPU utilization during heavy writes.[1] The commit below appears
related, as it disables scatter gather on non-IP protocols inside the
harmonize_features function, even when the NIC supports sg.

  commit f01a5236bd4b140198fbcc550f085e8361fd73fa
  Author: Jesse Gross <jesse@nicira.com>
  Date:   Sun Jan 9 06:23:31 2011 +0000

      net offloading: Generalize netif_get_vlan_features().

With that regression in place, transmits always linearize sg AoE packets,
but in-kernel users did not have this patch.  Before 2.6.38, though, these
changes were working to allow sg to increase performance.

1. http://www.spinics.net/lists/linux-mm/msg15184.html

Signed-off-by: Ed Cashin <ecashin@coraid.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 9 insertions, 4 deletions

diff --git a/drivers/block/aoe/aoenet.c b/drivers/block/aoe/aoenet.c
index 4d3bc0d49df5..07878076e43c 100644
--- a/drivers/block/aoe/aoenet.c
+++ b/drivers/block/aoe/aoenet.c
@@ -102,7 +102,9 @@ static int
 aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt, struct net_device *orig_dev)
 {
 	struct aoe_hdr *h;
+	struct aoe_atahdr *ah;
 	u32 n;
+	int sn;
 
 	if (dev_net(ifp) != &init_net)
 		goto exit;
@@ -110,13 +112,16 @@ aoenet_rcv(struct sk_buff *skb, struct net_device *ifp, struct packet_type *pt,
 	skb = skb_share_check(skb, GFP_ATOMIC);
 	if (skb == NULL)
 		return 0;
-	if (skb_linearize(skb))
-		goto exit;
 	if (!is_aoe_netif(ifp))
 		goto exit;
 	skb_push(skb, ETH_HLEN);	/* (1) */
-
-	h = (struct aoe_hdr *) skb_mac_header(skb);
+	sn = sizeof(*h) + sizeof(*ah);
+	if (skb->len >= sn) {
+		sn -= skb_headlen(skb);
+		if (sn > 0 && !__pskb_pull_tail(skb, sn))
+			goto exit;
+	}
+	h = (struct aoe_hdr *) skb->data;
 	n = get_unaligned_be32(&h->tag);
 	if ((h->verfl & AOEFL_RSP) == 0 || (n & 1<<31))
 		goto exit;