1. 22 Jan, 2014 7 commits
  2. 21 Jan, 2014 5 commits
  3. 20 Jan, 2014 22 commits
  4. 19 Jan, 2014 3 commits
  5. 18 Jan, 2014 3 commits
    • David S. Miller's avatar
      Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net · 41804420
      David S. Miller authored
      Conflicts:
      	drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
      	net/ipv4/tcp_metrics.c
      
      Overlapping changes between the "don't create two tcp metrics objects
      with the same key" race fix in net and the addition of the destination
      address in the lookup key in net-next.
      
      Minor overlapping changes in bnx2x driver.
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      41804420
    • Linus Torvalds's avatar
      Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net · 7d0d46da
      Linus Torvalds authored
      Pull networking fixes from David Miller:
      
       1) The value choosen for the new SO_MAX_PACING_RATE socket option on
          parisc was very poorly choosen, let's fix it while we still can.
          From Eric Dumazet.
      
       2) Our generic reciprocal divide was found to handle some edge cases
          incorrectly, part of this is encoded into the BPF as deep as the JIT
          engines themselves.  Just use a real divide throughout for now.
          From Eric Dumazet.
      
       3) Because the initial lookup is lockless, the TCP metrics engine can
          end up creating two entries for the same lookup key.  Fix this by
          doing a second lookup under the lock before we actually create the
          new entry.  From Christoph Paasch.
      
       4) Fix scatter-gather list init in usbnet driver, from Bjørn Mork.
      
       5) Fix unintended 32-bit truncation in cxgb4 driver's bit shifting.
          From Dan Carpenter.
      
       6) Netlink socket dumping uses the wrong socket state for timewait
          sockets.  Fix from Neal Cardwell.
      
       7) Fix netlink memory leak in ieee802154_add_iface(), from Christian
          Engelmayer.
      
       8) Multicast forwarding in ipv4 can overflow the per-rule reference
          counts, causing all multicast traffic to cease.  Fix from Hannes
          Frederic Sowa.
      
       9) via-rhine needs to stop all TX queues when it resets the device,
          from Richard Weinberger.
      
      10) Fix RDS per-cpu accesses broken by the this_cpu_* conversions.  From
          Gerald Schaefer.
      
      * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net:
        s390/bpf,jit: fix 32 bit divisions, use unsigned divide instructions
        parisc: fix SO_MAX_PACING_RATE typo
        ipv6: simplify detection of first operational link-local address on interface
        tcp: metrics: Avoid duplicate entries with the same destination-IP
        net: rds: fix per-cpu helper usage
        e1000e: Fix compilation warning when !CONFIG_PM_SLEEP
        bpf: do not use reciprocal divide
        be2net: add dma_mapping_error() check for dma_map_page()
        bnx2x: Don't release PCI bars on shutdown
        net,via-rhine: Fix tx_timeout handling
        batman-adv: fix batman-adv header overhead calculation
        qlge: Fix vlan netdev features.
        net: avoid reference counter overflows on fib_rules in multicast forwarding
        dm9601: add USB IDs for new dm96xx variants
        MAINTAINERS: add virtio-dev ML for virtio
        ieee802154: Fix memory leak in ieee802154_add_iface()
        net: usbnet: fix SG initialisation
        inet_diag: fix inet_diag_dump_icsk() to use correct state for timewait sockets
        cxgb4: silence shift wrapping static checker warning
      7d0d46da
    • David S. Miller's avatar
      Merge branch 'ixgbevf' · 7b1e46c5
      David S. Miller authored
      Aaron Brown says:
      
      ====================
      Intel Wired LAN Driver Updates
      
      This series contains updates from Emil to ixgbevf.
      
      He cleans up the code by removing the adapter structure as a
      parameter from multiple functions in favor of using the ixgbevf_ring
      structure and moves hot-path specific statistic int the ring
      structure for anticipated performance gains.
      
      He also removes the Tx/Rx counters for checksum offload and adds
      counters for tx_restart_queue and tx_timeout_count.
      
      Next he makes it so that the first tx_buffer structure acts as a
      central storage location for most the skb info we are about to
      transmit, then takes advantage of the dma buffer always being
      present in the first descriptor and mapped as single allowing a
      call to dma_unmap_single which alleviates the need to check for
      DMA mapping in ixgbevf_clean_tx_irq().
      
      Finally he merges the ixgbevf_tx_map call and the ixgbevf_tx_queue
      call into a single function.
      ====================
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      7b1e46c5