1. 09 Dec, 2012 4 commits
    • Alexander Duyck's avatar
      net: Handle encapsulated offloads before fragmentation or handing to lower dev · fc70fb64
      Alexander Duyck authored
      This change allows the VXLAN to enable Tx checksum offloading even on
      devices that do not support encapsulated checksum offloads. The
      advantage to this is that it allows for the lower device to change due
      to routing table changes without impacting features on the VXLAN itself.
      Signed-off-by: default avatarAlexander Duyck <alexander.h.duyck@intel.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      fc70fb64
    • Joseph Gasparakis's avatar
      net: Add support for hardware-offloaded encapsulation · 6a674e9c
      Joseph Gasparakis authored
      This patch adds support in the kernel for offloading in the NIC Tx and Rx
      checksumming for encapsulated packets (such as VXLAN and IP GRE).
      
      For Tx encapsulation offload, the driver will need to set the right bits
      in netdev->hw_enc_features. The protocol driver will have to set the
      skb->encapsulation bit and populate the inner headers, so the NIC driver will
      use those inner headers to calculate the csum in hardware.
      
      For Rx encapsulation offload, the driver will need to set again the
      skb->encapsulation flag and the skb->ip_csum to CHECKSUM_UNNECESSARY.
      In that case the protocol driver should push the decapsulated packet up
      to the stack, again with CHECKSUM_UNNECESSARY. In ether case, the protocol
      driver should set the skb->encapsulation flag back to zero. Finally the
      protocol driver should have NETIF_F_RXCSUM flag set in its features.
      Signed-off-by: default avatarJoseph Gasparakis <joseph.gasparakis@intel.com>
      Signed-off-by: default avatarPeter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
      Signed-off-by: default avatarAlexander Duyck <alexander.h.duyck@intel.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      6a674e9c
    • françois romieu's avatar
      r8169: workaround for missing extended GigaMAC registers · 9ecb9aab
      françois romieu authored
      GigaMAC registers have been reported left unitialized in several
      situations:
      - after cold boot from power-off state
      - after S3 resume
      
      Tweaking rtl_hw_phy_config takes care of both.
      
      This patch removes an excess entry (",") at the end of the exgmac_reg
      array as well.
      Signed-off-by: default avatarFrancois Romieu <romieu@fr.zoreil.com>
      Signed-off-by: default avatarWang YanQing <udknight@gmail.com>
      Cc: Hayes Wang <hayeswang@realtek.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      9ecb9aab
    • David S. Miller's avatar
      Merge branch 'tipc_net-next_v2' of git://git.kernel.org/pub/scm/linux/kernel/git/paulg/linux · ba501666
      David S. Miller authored
      Paul Gortmaker says:
      
      ====================
      Changes since v1:
      	-get rid of essentially unused variable spotted by
      	 Neil Horman (patch #2)
      
      	-drop patch #3; defer it for 3.9 content, so Neil,
      	 Jon and Ying can discuss its specifics at their
      	 leisure while net-next is closed.  (It had no
      	 direct dependencies to the rest of the series, and
      	 was just an optimization)
      
      	-fix indentation of accept() code directly in place
      	 vs. forking it out to a separate function (was patch
      	 #10, now patch #9).
      
      Rebuilt and re-ran tests just to ensure nothing odd happened.
      
      Original v1 text follows, updated pull information follows that.
      
                 ---------
      
      Here is another batch of TIPC changes.  The most interesting
      thing is probably the non-blocking socket connect - I'm told
      there were several users looking forward to seeing this.
      
      Also there were some resource limitation changes that had
      the right intent back in 2005, but were now apparently causing
      needless limitations to people's real use cases; those have
      been relaxed/removed.
      
      There is a lockdep splat fix, but no need for a stable backport,
      since it is virtually impossible to trigger in mainline; you
      have to essentially modify code to force the probabilities
      in your favour to see it.
      
      The rest can largely be categorized as general cleanup of things
      seen in the process of getting the above changes done.
      
      Tested between 64 and 32 bit nodes with the test suite.  I've
      also compile tested all the individual commits on the chain.
      
      I'd originally figured on this queue not being ready for 3.8, but
      the extended stabilization window of 3.7 has changed that.  On
      the other hand, this can still be 3.9 material, if that simply
      works better for folks - no problem for me to defer it to 2013.
      If anyone spots any problems then I'll definitely defer it,
      rather than rush a last minute respin.
      ===================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      ba501666
  2. 07 Dec, 2012 36 commits