net: skb_shared_info optimization
skb_dma_unmap() is quite expensive for small packets,
because we use two different cache lines from skb_shared_info.
One to access nr_frags, one to access dma_maps[0]
Instead of dma_maps being an array of MAX_SKB_FRAGS + 1 elements,
let dma_head alone in a new dma_head field, close to nr_frags,
to reduce cache lines misses.
Tested on my dev machine (bnx2 & tg3 adapters), nice speedup !
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 74850581..aad484c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -189,6 +189,9 @@
atomic_t dataref;
unsigned short nr_frags;
unsigned short gso_size;
+#ifdef CONFIG_HAS_DMA
+ dma_addr_t dma_head;
+#endif
/* Warning: this field is not always filled in (UFO)! */
unsigned short gso_segs;
unsigned short gso_type;
@@ -198,7 +201,7 @@
struct skb_shared_hwtstamps hwtstamps;
skb_frag_t frags[MAX_SKB_FRAGS];
#ifdef CONFIG_HAS_DMA
- dma_addr_t dma_maps[MAX_SKB_FRAGS + 1];
+ dma_addr_t dma_maps[MAX_SKB_FRAGS];
#endif
/* Intermediate layers must ensure that destructor_arg
* remains valid until skb destructor */