1. 27 Jan, 2011 2 commits
  2. 26 Jan, 2011 1 commit
    • David S. Miller's avatar
      net: Implement read-only protection and COW'ing of metrics. · 62fa8a84
      David S. Miller authored
      Routing metrics are now copy-on-write.
      
      Initially a route entry points it's metrics at a read-only location.
      If a routing table entry exists, it will point there.  Else it will
      point at the all zero metric place-holder called 'dst_default_metrics'.
      
      The writeability state of the metrics is stored in the low bits of the
      metrics pointer, we have two bits left to spare if we want to store
      more states.
      
      For the initial implementation, COW is implemented simply via kmalloc.
      However future enhancements will change this to place the writable
      metrics somewhere else, in order to increase sharing.  Very likely
      this "somewhere else" will be the inetpeer cache.
      
      Note also that this means that metrics updates may transiently fail
      if we cannot COW the metrics successfully.
      
      But even by itself, this patch should decrease memory usage and
      increase cache locality especially for routing workloads.  In those
      cases the read-only metric copies stay in place and never get written
      to.
      
      TCP workloads where metrics get updated, and those rare cases where
      PMTU triggers occur, will take a very slight performance hit.  But
      that hit will be alleviated when the long-term writable metrics
      move to a more sharable location.
      
      Since the metrics storage went from a u32 array of RTAX_MAX entries to
      what is essentially a pointer, some retooling of the dst_entry layout
      was necessary.
      
      Most importantly, we need to preserve the alignment of the reference
      count so that it doesn't share cache lines with the read-mostly state,
      as per Eric Dumazet's alignment assertion checks.
      
      The only non-trivial bit here is the move of the 'flags' member into
      the writeable cacheline.  This is OK since we are always accessing the
      flags around the same moment when we made a modification to the
      reference count.
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      62fa8a84
  3. 24 Jan, 2011 1 commit
  4. 21 Jan, 2011 2 commits
    • Bruno Randolf's avatar
      cfg80211: Extend channel to frequency mapping for 802.11j · 59eb21a6
      Bruno Randolf authored
      Extend channel to frequency mapping for 802.11j Japan 4.9GHz band, according to
      IEEE802.11 section 17.3.8.3.2 and Annex J. Because there are now overlapping
      channel numbers in the 2GHz and 5GHz band we can't map from channel to
      frequency without knowing the band. This is no problem as in most contexts we
      know the band. In places where we don't know the band (and WEXT compatibility)
      we assume the 2GHz band for channels below 14.
      
      This patch does not implement all channel to frequency mappings defined in
      802.11, it's just an extension for 802.11j 20MHz channels. 5MHz and 10MHz
      channels as well as 802.11y channels have been omitted.
      
      The following drivers have been updated to reflect the API changes:
      iwl-3945, iwl-agn, iwmc3200wifi, libertas, mwl8k, rt2x00, wl1251, wl12xx.
      The drivers have been compile-tested only.
      Signed-off-by: default avatarBruno Randolf <br1@einfach.org>
      Signed-off-by: default avatarBrian Prodoehl <bprodoehl@gmail.com>
      Acked-by: default avatarLuciano Coelho <coelho@ti.com>
      Signed-off-by: default avatarJohn W. Linville <linville@tuxdriver.com>
      59eb21a6
    • Eric Dumazet's avatar
      net_sched: accurate bytes/packets stats/rates · 9190b3b3
      Eric Dumazet authored
      In commit 44b82883 (net_sched: pfifo_head_drop problem), we fixed
      a problem with pfifo_head drops that incorrectly decreased
      sch->bstats.bytes and sch->bstats.packets
      
      Several qdiscs (CHOKe, SFQ, pfifo_head, ...) are able to drop a
      previously enqueued packet, and bstats cannot be changed, so
      bstats/rates are not accurate (over estimated)
      
      This patch changes the qdisc_bstats updates to be done at dequeue() time
      instead of enqueue() time. bstats counters no longer account for dropped
      frames, and rates are more correct, since enqueue() bursts dont have
      effect on dequeue() rate.
      Signed-off-by: default avatarEric Dumazet <eric.dumazet@gmail.com>
      Acked-by: default avatarStephen Hemminger <shemminger@vyatta.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      9190b3b3
  5. 20 Jan, 2011 3 commits
    • Eric Dumazet's avatar
      net_sched: RCU conversion of stab · a2da570d
      Eric Dumazet authored
      This patch converts stab qdisc management to RCU, so that we can perform
      the qdisc_calculate_pkt_len() call before getting qdisc lock.
      
      This shortens the lock's held time in __dev_xmit_skb().
      
      This permits more qdiscs to get TCQ_F_CAN_BYPASS status, avoiding lot of
      cache misses and so reducing latencies.
      Signed-off-by: default avatarEric Dumazet <eric.dumazet@gmail.com>
      CC: Patrick McHardy <kaber@trash.net>
      CC: Jesper Dangaard Brouer <hawk@diku.dk>
      CC: Jarek Poplawski <jarkao2@gmail.com>
      CC: Jamal Hadi Salim <hadi@cyberus.ca>
      CC: Stephen Hemminger <shemminger@vyatta.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      a2da570d
    • Eric Dumazet's avatar
      net_sched: move TCQ_F_THROTTLED flag · fd245a4a
      Eric Dumazet authored
      In commit 37112105 (net: QDISC_STATE_RUNNING dont need atomic bit
      ops) I moved QDISC_STATE_RUNNING flag to __state container, located in
      the cache line containing qdisc lock and often dirtied fields.
      
      I now move TCQ_F_THROTTLED bit too, so that we let first cache line read
      mostly, and shared by all cpus. This should speedup HTB/CBQ for example.
      
      Not using test_bit()/__clear_bit()/__test_and_set_bit allows to use an
      "unsigned int" for __state container, reducing by 8 bytes Qdisc size.
      
      Introduce helpers to hide implementation details.
      Signed-off-by: default avatarEric Dumazet <eric.dumazet@gmail.com>
      CC: Patrick McHardy <kaber@trash.net>
      CC: Jesper Dangaard Brouer <hawk@diku.dk>
      CC: Jarek Poplawski <jarkao2@gmail.com>
      CC: Jamal Hadi Salim <hadi@cyberus.ca>
      CC: Stephen Hemminger <shemminger@vyatta.com>
      Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
      fd245a4a
    • Patrick McHardy's avatar
      netfilter: nf_conntrack: fix linker error with NF_CONNTRACK_TIMESTAMP=n · 2f1e3176
      Patrick McHardy authored
      net/built-in.o: In function `nf_conntrack_init_net':
      net/netfilter/nf_conntrack_core.c:1521:
      	undefined reference to `nf_conntrack_tstamp_init'
      net/netfilter/nf_conntrack_core.c:1531:
      	undefined reference to `nf_conntrack_tstamp_fini'
      
      Add dummy inline functions for the =n case to fix this.
      Reported-by: default avatarJohn Fastabend <john.r.fastabend@intel.com>
      Signed-off-by: default avatarPatrick McHardy <kaber@trash.net>
      2f1e3176
  6. 19 Jan, 2011 6 commits
  7. 18 Jan, 2011 3 commits
  8. 14 Jan, 2011 2 commits
  9. 13 Jan, 2011 1 commit
  10. 12 Jan, 2011 19 commits