Eric Lee / smarc-fsl-linux-kernel

05 Oct, 2010

1 commit

  • 4e18b3edf   cls_u32: signedness bug ... Browse Code »

    skb_headroom() is unsigned so "skb_headroom(skb) + toff" is also
    unsigned and can't be less than zero. This test was added in 66d50d25:
    "u32: negative offset fix" It was supposed to fix a regression.

    Signed-off-by: Dan Carpenter
    Signed-off-by: David S. Miller

    Dan Carpenter
     

13 Sep, 2010

1 commit

02 Sep, 2010

2 commits

  • 3b2eb6131   net/sched/sch_hfsc.c: initialize parent's cl_cfmin properly in init_vf() ... Browse Code »

    This patch fixes init_vf() function, so on each new backlog period parent's
    cl_cfmin is properly updated (including further propgation towards the root),
    even if the activated leaf has no upperlimit curve defined.

    Signed-off-by: Michal Soltys
    Signed-off-by: David S. Miller

    Michal Soltys
     
  • 0f04cfd09   net sched: fix kernel leak in act_police ... Browse Code »

    While reviewing commit 1c40be12f7d8ca1d387510d39787b12e512a7ce8, I
    audited other users of tc_action_ops->dump for information leaks.

    That commit covered almost all of them but act_police still had a leak.

    opt.limit and opt.capab aren't zeroed out before the structure is
    passed out.

    This patch uses the C99 initializers to zero everything unused out.

    Signed-off-by: Jeff Mahoney
    Acked-by: Jeff Mahoney
    Signed-off-by: David S. Miller

    Jeff Mahoney
     

18 Aug, 2010

1 commit

  • 1c40be12f   net sched: fix some kernel memory leaks ... Browse Code »

    We leak at least 32bits of kernel memory to user land in tc dump,
    because we dont init all fields (capab ?) of the dumped structure.

    Use C99 initializers so that holes and non explicit fields are zeroed.

    Signed-off-by: Eric Dumazet
    Signed-off-by: David S. Miller

    Eric Dumazet
     

11 Aug, 2010

2 commits

10 Aug, 2010

3 commits

08 Aug, 2010

1 commit

  • eb4a5527b   pkt_sched: Fix sch_sfq vs tcf_bind_filter oops ... Browse Code »

    Since there was added ->tcf_chain() method without ->bind_tcf() to
    sch_sfq class options, there is oops when a filter is added with
    the classid parameter.

    Fixes commit 7d2681a6ff4f9ab5e48d02550b4c6338f1638998
    netdev thread: null pointer at cls_api.c

    Signed-off-by: Jarek Poplawski
    Reported-by: Franchoze Eric
    Signed-off-by: David S. Miller

    Jarek Poplawski
     

05 Aug, 2010

4 commits

03 Aug, 2010

2 commits

01 Aug, 2010

2 commits

28 Jul, 2010

1 commit

25 Jul, 2010

1 commit

  • 3b87956ea   net sched: fix race in mirred device removal ... Browse Code »

    This fixes hang when target device of mirred packet classifier
    action is removed.

    If a mirror or redirection action is configured to cause packets
    to go to another device, the classifier holds a ref count, but was assuming
    the adminstrator cleaned up all redirections before removing. The fix
    is to add a notifier and cleanup during unregister.

    The new list is implicitly protected by RTNL mutex because
    it is held during filter add/delete as well as notifier.

    Signed-off-by: Stephen Hemminger
    Acked-by: Jamal Hadi Salim
    Signed-off-by: David S. Miller

    stephen hemminger
     

21 Jul, 2010

1 commit

20 Jul, 2010

1 commit

19 Jul, 2010

1 commit

15 Jul, 2010

1 commit

  • 0eff683f7   net/sched: potential data corruption ... Browse Code »

    The reset_policy() does:
    memset(d->tcfd_defdata, 0, SIMP_MAX_DATA);
    strlcpy(d->tcfd_defdata, defdata, SIMP_MAX_DATA);

    In the original code, the size of d->tcfd_defdata wasn't fixed and if
    strlen(defdata) was less than 31, reset_policy() would cause memory
    corruption.

    Please Note: The original alloc_defdata() assumes defdata is 32
    characters and a NUL terminator while reset_policy() assumes defdata is
    31 characters and a NUL. This patch updates alloc_defdata() to match
    reset_policy() (ie a shorter string). I'm not very familiar with this
    code so please review carefully.

    Signed-off-by: Dan Carpenter
    Acked-by: Jamal Hadi Salim
    Signed-off-by: David S. Miller

    Dan Carpenter
     

13 Jul, 2010

1 commit

  • 70c2efa5a   act_nat: not all of the ICMP packets need an IP header payload ... Browse Code »

    not all of the ICMP packets need an IP header payload, so we check the length
    of the skbs only when the packets should have an IP header payload.

    Based upon analysis and initial patch by Rodrigo Partearroyo González.

    Signed-off-by: Changli Gao
    Acked-by: Herbert Xu
    ----
    net/sched/act_nat.c | 5 ++++-
    1 file changed, 4 insertions(+), 1 deletion(-)
    Signed-off-by: David S. Miller

    Changli Gao
     

01 Jul, 2010

2 commits

  • 504f85c9d   act_nat: use stack variable ... Browse Code »

    act_nat: use stack variable

    structure tc_nat isn't too big for stack, so we can put it in stack.

    Signed-off-by: Changli Gao
    ----
    net/sched/act_nat.c | 31 ++++++++++---------------------
    1 file changed, 10 insertions(+), 21 deletions(-)
    Signed-off-by: David S. Miller

    Changli Gao
     
  • 5acbf7f10   act_mirred: combine duplicate code ... Browse Code »

    act_mirred: combine duplicate code

    tcf_bstats is updated in any way, so we can do it earlier to reduce the size of
    the code.

    Signed-off-by: Changli Gao
    Signed-off-by: Jamal Hadi Salim
    ----
    net/sched/act_mirred.c | 6 ++----
    1 file changed, 2 insertions(+), 4 deletions(-)
    Signed-off-by: David S. Miller

    Changli Gao
     

29 Jun, 2010

1 commit

  • 210d6de78   act_mirred: don't clone skb when skb isn't shared ... Browse Code »

    don't clone skb when skb isn't shared

    When the tcf_action is TC_ACT_STOLEN, and the skb isn't shared, we don't need
    to clone a new skb. As the skb will be freed after this function returns, we
    can use it freely once we get a reference to it.

    Signed-off-by: Changli Gao
    ----
    include/net/sch_generic.h | 11 +++++++++--
    net/sched/act_mirred.c | 6 +++---
    2 files changed, 12 insertions(+), 5 deletions(-)
    Signed-off-by: Jamal Hadi Salim
    Signed-off-by: David S. Miller

    Changli Gao
     

24 Jun, 2010

1 commit

17 Jun, 2010

1 commit

  • fa68a7822   Clear IFF_XMIT_DST_RELEASE for teql interfaces ... Browse Code »

    https://bugzilla.kernel.org/show_bug.cgi?id=16183

    The sch_teql module, which can be used to load balance over a set of
    underlying interfaces, stopped working after 2.6.30 and has been
    broken in all kernels since then for any underlying interface which
    requires the addition of link level headers.

    The problem is that the transmit routine relies on being able to
    access the destination address in the skb in order to do address
    resolution once it has decided which underlying interface it is going
    to transmit through.

    In 2.6.31 the IFF_XMIT_DST_RELEASE flag was introduced, and set by
    default for all interfaces, which causes the destination address to be
    released before the transmit routine for the interface is called.

    The solution is to clear that flag for teql interfaces.

    Signed-off-by: Tom Hughes
    Acked-by: Eric Dumazet
    Signed-off-by: David S. Miller

    Tom Hughes
     

12 Jun, 2010

1 commit

  • c7de2cf05   pkt_sched: gen_kill_estimator() rcu fixes ... Browse Code »

    gen_kill_estimator() API is incomplete or not well documented, since
    caller should make sure an RCU grace period is respected before
    freeing stats_lock.

    This was partially addressed in commit 5d944c640b4
    (gen_estimator: deadlock fix), but same problem exist for all
    gen_kill_estimator() users, if lock they use is not already RCU
    protected.

    A code review shows xt_RATEEST.c, act_api.c, act_police.c have this
    problem. Other are ok because they use qdisc lock, already RCU
    protected.

    Signed-off-by: Eric Dumazet
    Signed-off-by: David S. Miller

    Eric Dumazet
     

07 Jun, 2010

3 commits

03 Jun, 2010

1 commit

  • db2c24175   act_pedit: access skb->data safely ... Browse Code »

    access skb->data safely

    we should use skb_header_pointer() and skb_store_bits() to access skb->data to
    handle small or non-linear skbs.

    Signed-off-by: Changli Gao
    ----
    net/sched/act_pedit.c | 24 ++++++++++++++----------
    1 file changed, 14 insertions(+), 10 deletions(-)
    Signed-off-by: David S. Miller

    Changli Gao
     

02 Jun, 2010

4 commits

  • fbc2e7d9c   cls_u32: use skb_header_pointer() to dereference data safely ... Browse Code »

    use skb_header_pointer() to dereference data safely

    the original skb->data dereference isn't safe, as there isn't any skb->len or
    skb_is_nonlinear() check. skb_header_pointer() is used instead in this patch.
    And when the skb isn't long enough, we terminate the function u32_classify()
    immediately with -1.

    Signed-off-by: Changli Gao
    Signed-off-by: David S. Miller

    Changli Gao
     
  • 33c29dde7   act_nat: fix the wrong checksum when addr isn't in old_addr/mask ... Browse Code »

    fix the wrong checksum when addr isn't in old_addr/mask

    For TCP and UDP packets, when addr isn't in old_addr/mask we don't do SNAT or
    DNAT, and we should not update layer 4 checksum.

    Signed-off-by: Changli Gao
    ----
    net/sched/act_nat.c | 4 ++++
    1 file changed, 4 insertions(+)
    Signed-off-by: David S. Miller

    Changli Gao
     
  • 79640a4ca   net: add additional lock to qdisc to increase throughput ... Browse Code »

    When many cpus compete for sending frames on a given qdisc, the qdisc
    spinlock suffers from very high contention.

    The cpu owning __QDISC_STATE_RUNNING bit has same priority to acquire
    the lock, and cannot dequeue packets fast enough, since it must wait for
    this lock for each dequeued packet.

    One solution to this problem is to force all cpus spinning on a second
    lock before trying to get the main lock, when/if they see
    __QDISC_STATE_RUNNING already set.

    The owning cpu then compete with at most one other cpu for the main
    lock, allowing for higher dequeueing rate.

    Based on a previous patch from Alexander Duyck. I added the heuristic to
    avoid the atomic in fast path, and put the new lock far away from the
    cache line used by the dequeue worker. Also try to release the busylock
    lock as late as possible.

    Tests with following script gave a boost from ~50.000 pps to ~600.000
    pps on a dual quad core machine (E5450 @3.00GHz), tg3 driver.
    (A single netperf flow can reach ~800.000 pps on this platform)

    for j in `seq 0 3`; do
    for i in `seq 0 7`; do
    netperf -H 192.168.0.1 -t UDP_STREAM -l 60 -N -T $i -- -m 6 &
    done
    done

    Signed-off-by: Eric Dumazet
    Acked-by: Alexander Duyck
    Signed-off-by: David S. Miller

    Eric Dumazet
     
  • bc135b23d   net: Define accessors to manipulate QDISC_STATE_RUNNING ... Browse Code »

    Define three helpers to manipulate QDISC_STATE_RUNNIG flag, that a
    second patch will move on another location.

    Signed-off-by: Eric Dumazet
    Signed-off-by: David S. Miller

    Eric Dumazet