Re: [E1000-devel] [PATCH 01/21] net: slight optimization of addr compare for some modules

[Ding Tianhong <dingtianhong@huawei.com>]

On 2013/12/24 1:20, Alexander Duyck wrote:
> On 12/22/2013 09:09 PM, Ding Tianhong wrote:
>> Use the recently added and possibly more efficient
>> ether_addr_equal_unaligned to instead of memcmp.
>>
>> Cc: "David S. Miller" <davem@davemloft.net>
>> Cc: netdev@vger.kernel.org
>> Cc: linux-kernel@vger.kernel.org
>> Cc: e1000-devel@lists.sourceforge.net
>> Signed-off-by: Ding Tianhong <dingtianhong@huawei.com>
>> ---
>>  drivers/net/bonding/bond_3ad.c                        |  2 +-
>>  drivers/net/ethernet/3com/3c509.c                     |  3 +--
>>  drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c        | 10 ++++------
>>  drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c     |  2 +-
>>  drivers/net/ethernet/broadcom/bnx2x/bnx2x_vfpf.c      |  2 +-
>>  drivers/net/ethernet/chelsio/cxgb3/cxgb3_offload.c    |  2 +-
>>  drivers/net/ethernet/chelsio/cxgb3/l2t.c              |  2 +-
>>  drivers/net/ethernet/cisco/enic/enic_pp.c             |  2 +-
>>  drivers/net/ethernet/emulex/benet/be_main.c           |  2 +-
>>  drivers/net/ethernet/intel/igbvf/netdev.c             |  2 +-
>>  drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c        |  3 +--
>>  drivers/net/ethernet/mellanox/mlx4/en_netdev.c        |  4 ++--
>>  drivers/net/ethernet/mellanox/mlx4/resource_tracker.c |  2 +-
>>  drivers/net/ethernet/micrel/ksz884x.c                 |  9 ++++-----
>>  drivers/net/ethernet/neterion/vxge/vxge-main.c        |  2 +-
>>  drivers/net/ethernet/packetengines/yellowfin.c        |  8 ++------
>>  drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c    |  2 +-
>>  drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c        |  4 ++--
>>  drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c        |  4 ++--
>>  drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c      |  4 ++--
>>  drivers/net/ethernet/renesas/sh_eth.c                 |  2 +-
>>  drivers/net/ethernet/seeq/sgiseeq.c                   |  2 +-
>>  drivers/net/ethernet/sun/sunvnet.c                    |  2 +-
>>  drivers/net/ethernet/ti/cpsw_ale.c                    |  2 +-
>>  drivers/net/fddi/skfp/fplustm.c                       |  3 ++-
>>  drivers/net/plip/plip.c                               |  2 +-
>>  net/caif/cfrfml.c                                     |  2 +-
>>  27 files changed, 39 insertions(+), 47 deletions(-)
> 
> What is it you are trying to optimize for, size or speed?  Most of these
> calls are in slow path.  Replacing the memcmp with an inline operation
> may provide little to no gain in terms of speed and in many cases as you
> might actually be increasing the resultant driver size.
> 
> Also I would recommend reviewing the addresses you are comparing.  It is
> likely that you could use ether_addr_equal or compare_ether_addr in many
> cases as I suspect a number of spots are using 16b aligned MAC addresses
> for both operands.
> 
> Thanks,
> 
> Alex
> 
> .

Yes, as the title said, slight optimization, and I think there will be no
negative effect for these places. The patchset still have many problem, 
many places should use the ether_addr_equal as you said, I will fix it later.
Thank you for reviewing the patch.


Regards
Ding


>