xen-netback: remove unconditional __pskb_pull_tail() in guest Tx path

Unconditionally pulling 128 bytes into the linear area is not required
for:

- security: Every protocol demux starts with pskb_may_pull() to pull
  frag data into the linear area, if necessary, before looking at
  headers.

- performance: Netback has already grant copied up-to 128 bytes from
  the first slot of a packet into the linear area. The first slot
  normally contain all the IPv4/IPv6 and TCP/UDP headers.

The unconditional pull would often copy frag data unnecessarily.  This
is a performance problem when running on a version of Xen where grant
unmap avoids TLB flushes for pages which are not accessed.  TLB
flushes can now be avoided for > 99% of unmaps (it was 0% before).

Grant unmap TLB flush avoidance will be available in a future version
of Xen (probably 4.6).

Signed-off-by: Malcolm Crossley <malcolm.crossley@citrix.com>
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Ian Campbell <ian.campbell@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/xen-netback/netback.c

@@ -82,6 +82,16 @@ MODULE_PARM_DESC(max_queues,
 static unsigned int fatal_skb_slots = FATAL_SKB_SLOTS_DEFAULT;
 module_param(fatal_skb_slots, uint, 0444);
 
+/* The amount to copy out of the first guest Tx slot into the skb's
+ * linear area.  If the first slot has more data, it will be mapped
+ * and put into the first frag.
+ *
+ * This is sized to avoid pulling headers from the frags for most
+ * TCP/IP packets.
+ */
+#define XEN_NETBACK_TX_COPY_LEN 128
+
+
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
 			       u8 status);
 
@@ -125,13 +135,6 @@ static inline struct xenvif_queue *ubuf_to_queue(const struct ubuf_info *ubuf)
 			    pending_tx_info[0]);
 }
 
-/* This is a miniumum size for the linear area to avoid lots of
- * calls to __pskb_pull_tail() as we set up checksum offsets. The
- * value 128 was chosen as it covers all IPv4 and most likely
- * IPv6 headers.
- */
-#define PKT_PROT_LEN 128
-
 static u16 frag_get_pending_idx(skb_frag_t *frag)
 {
 	return (u16)frag->page_offset;
@@ -1446,9 +1449,9 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 		index = pending_index(queue->pending_cons);
 		pending_idx = queue->pending_ring[index];
 
-		data_len = (txreq.size > PKT_PROT_LEN &&
+		data_len = (txreq.size > XEN_NETBACK_TX_COPY_LEN &&
 			    ret < XEN_NETBK_LEGACY_SLOTS_MAX) ?
-			PKT_PROT_LEN : txreq.size;
+			XEN_NETBACK_TX_COPY_LEN : txreq.size;
 
 		skb = xenvif_alloc_skb(data_len);
 		if (unlikely(skb == NULL)) {
@@ -1653,11 +1656,6 @@ static int xenvif_tx_submit(struct xenvif_queue *queue)
 			}
 		}
 
-		if (skb_is_nonlinear(skb) && skb_headlen(skb) < PKT_PROT_LEN) {
-			int target = min_t(int, skb->len, PKT_PROT_LEN);
-			__pskb_pull_tail(skb, target - skb_headlen(skb));
-		}
-
 		skb->dev      = queue->vif->dev;
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb_reset_network_header(skb);