summaryrefslogtreecommitdiffstats
path: root/include/linux/etherdevice.h
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2008-11-23 23:24:32 -0800
committerDavid S. Miller <davem@davemloft.net>2008-11-23 23:24:32 -0800
commit1f87e235e6fb92c2968b52b9191de04f1aff8e77 (patch)
treeab774d239c61b6c206ef07398828533cdd01915e /include/linux/etherdevice.h
parent70eb1bfd52e97120eddf9b5aaabfe1ecdf4eb663 (diff)
downloadlinux-1f87e235e6fb92c2968b52b9191de04f1aff8e77.tar.gz
linux-1f87e235e6fb92c2968b52b9191de04f1aff8e77.tar.bz2
linux-1f87e235e6fb92c2968b52b9191de04f1aff8e77.zip
eth: Declare an optimized compare_ether_addr_64bits() function
Linus mentioned we could try to perform long word operations, even on potentially unaligned addresses, on x86 at least. David mentioned the HAVE_EFFICIENT_UNALIGNED_ACCESS test to handle this on all arches that have efficient unailgned accesses. I tried this idea and got nice assembly on 32 bits: 158: 33 82 38 01 00 00 xor 0x138(%edx),%eax 15e: 33 8a 34 01 00 00 xor 0x134(%edx),%ecx 164: c1 e0 10 shl $0x10,%eax 167: 09 c1 or %eax,%ecx 169: 74 0b je 176 <eth_type_trans+0x87> And very nice assembly on 64 bits of course (one xor, one shl) Nice oprofile improvement in eth_type_trans(), 0.17 % instead of 0.41 %, expected since we remove 8 instructions on a fast path. This patch implements a compare_ether_addr_64bits() function, that uses the CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS ifdef to efficiently perform the 6 bytes comparison on all capable arches. Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'include/linux/etherdevice.h')
-rw-r--r--include/linux/etherdevice.h42
1 files changed, 42 insertions, 0 deletions
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 0e5e97060034..1cb0f0b90926 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -27,6 +27,7 @@
#include <linux/if_ether.h>
#include <linux/netdevice.h>
#include <linux/random.h>
+#include <asm/unaligned.h>
#ifdef __KERNEL__
extern __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
@@ -140,6 +141,47 @@ static inline unsigned compare_ether_addr(const u8 *addr1, const u8 *addr2)
BUILD_BUG_ON(ETH_ALEN != 6);
return ((a[0] ^ b[0]) | (a[1] ^ b[1]) | (a[2] ^ b[2])) != 0;
}
+
+static inline unsigned long zap_last_2bytes(unsigned long value)
+{
+#ifdef __BIG_ENDIAN
+ return value >> 16;
+#else
+ return value << 16;
+#endif
+}
+
+/**
+ * compare_ether_addr_64bits - Compare two Ethernet addresses
+ * @addr1: Pointer to an array of 8 bytes
+ * @addr2: Pointer to an other array of 8 bytes
+ *
+ * Compare two ethernet addresses, returns 0 if equal.
+ * Same result than "memcmp(addr1, addr2, ETH_ALEN)" but without conditional
+ * branches, and possibly long word memory accesses on CPU allowing cheap
+ * unaligned memory reads.
+ * arrays = { byte1, byte2, byte3, byte4, byte6, byte7, pad1, pad2}
+ *
+ * Please note that alignment of addr1 & addr2 is only guaranted to be 16 bits.
+ */
+
+static inline unsigned compare_ether_addr_64bits(const u8 addr1[6+2],
+ const u8 addr2[6+2])
+{
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+ unsigned long fold = ((*(unsigned long *)addr1) ^
+ (*(unsigned long *)addr2));
+
+ if (sizeof(fold) == 8)
+ return zap_last_2bytes(fold) != 0;
+
+ fold |= zap_last_2bytes((*(unsigned long *)(addr1 + 4)) ^
+ (*(unsigned long *)(addr2 + 4)));
+ return fold != 0;
+#else
+ return compare_ether_addr(addr1, addr2);
+#endif
+}
#endif /* __KERNEL__ */
#endif /* _LINUX_ETHERDEVICE_H */