linux.git/net/core/dev.c, branch v2.6.36 Linux kernel source tree net: use rcu_barrier() in rollback_registered_many 2010-09-14T21:27:29+00:00 Eric Dumazet eric.dumazet@gmail.com 2010-09-13T12:24:54+00:00 ef885afbf8a37689afc1d9d545e2f3e7a8276c17 netdev_wait_allrefs() waits that all references to a device vanishes. It currently uses a _very_ pessimistic 250 ms delay between each probe. Some users reported that no more than 4 devices can be dismantled per second, this is a pretty serious problem for some setups. Most of the time, a refcount is about to be released by an RCU callback, that is still in flight because rollback_registered_many() uses a synchronize_rcu() call instead of rcu_barrier(). Problem is visible if number of online cpus is one, because synchronize_rcu() is then a no op. time to remove 50 ipip tunnels on a UP machine : before patch : real 11.910s after patch : real 1.250s Reported-by: Nicolas Dichtel <nicolas.dichtel@6wind.com> Reported-by: Octavian Purdila <opurdila@ixiacom.com> Reported-by: Benjamin LaHaise <bcrl@kvack.org> Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
netdev_wait_allrefs() waits that all references to a device vanishes.

It currently uses a _very_ pessimistic 250 ms delay between each probe.
Some users reported that no more than 4 devices can be dismantled per
second, this is a pretty serious problem for some setups.

Most of the time, a refcount is about to be released by an RCU callback,
that is still in flight because rollback_registered_many() uses a
synchronize_rcu() call instead of rcu_barrier(). Problem is visible if
number of online cpus is one, because synchronize_rcu() is then a no op.

time to remove 50 ipip tunnels on a UP machine :

before patch : real 11.910s
after patch : real 1.250s

Reported-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reported-by: Octavian Purdila <opurdila@ixiacom.com>
Reported-by: Benjamin LaHaise <bcrl@kvack.org>
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: fix tx queue selection for bridged devices implementing select_queue 2010-09-07T20:57:20+00:00 Helmut Schaa helmut.schaa@googlemail.com 2010-09-03T02:39:56+00:00 deabc772f39405054a438d711f408d2d94d26d96 When a net device is implementing the select_queue callback and is part of a bridge, frames coming from the bridge already have a tx queue associated to the socket (introduced in commit a4ee3ce3293dc931fab19beb472a8bde1295aebe, "net: Use sk_tx_queue_mapping for connected sockets"). The call to sk_tx_queue_get will then return the tx queue used by the bridge instead of calling the select_queue callback. In case of mac80211 this broke QoS which is implemented by using the select_queue callback. Furthermore it introduced problems with rt2x00 because frames with the same TID and RA sometimes appeared on different tx queues which the hw cannot handle correctly. Fix this by always calling select_queue first if it is available and only afterwards use the socket tx queue mapping. Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
When a net device is implementing the select_queue callback and is part of
a bridge, frames coming from the bridge already have a tx queue associated
to the socket (introduced in commit a4ee3ce3293dc931fab19beb472a8bde1295aebe,
"net: Use sk_tx_queue_mapping for connected sockets"). The call to
sk_tx_queue_get will then return the tx queue used by the bridge instead
of calling the select_queue callback.

In case of mac80211 this broke QoS which is implemented by using the
select_queue callback. Furthermore it introduced problems with rt2x00
because frames with the same TID and RA sometimes appeared on different
tx queues which the hw cannot handle correctly.

Fix this by always calling select_queue first if it is available and only
afterwards use the socket tx queue mapping.

Signed-off-by: Helmut Schaa <helmut.schaa@googlemail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Fix a memmove bug in dev_gro_receive() 2010-08-18T00:37:28+00:00 Jarek Poplawski jarkao2@gmail.com 2010-08-11T02:02:10+00:00 e5093aec2e6b60c3df2420057ffab9ed4a6d2792 >Xin Xiaohui wrote: > I looked into the code dev_gro_receive(), found the code here: > if the frags[0] is pulled to 0, then the page will be released, > and memmove() frags left. > Is that right? I'm not sure if memmove do right or not, but > frags[0].size is never set after memove at least. what I think > a simple way is not to do anything if we found frags[0].size == 0. > The patch is as followed. ... This version of the patch fixes the bug directly in memmove. Reported-by: "Xin, Xiaohui" <xiaohui.xin@intel.com> Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
>Xin Xiaohui wrote:
> I looked into the code dev_gro_receive(), found the code here:
> if the frags[0] is pulled to 0, then the page will be released,
> and memmove() frags left.
> Is that right? I'm not sure if memmove do right or not, but
> frags[0].size is never set after memove at least. what I think
> a simple way is not to do anything if we found frags[0].size == 0.
> The patch is as followed.
...

This version of the patch fixes the bug directly in memmove.

Reported-by: "Xin, Xiaohui" <xiaohui.xin@intel.com>
Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: disable preemption before call smp_processor_id() 2010-08-08T03:35:43+00:00 Changli Gao xiaosuo@gmail.com 2010-08-08T03:35:43+00:00 cece1945bffcf1a823cdfa36669beae118419351 Although netif_rx() isn't expected to be called in process context with preemption enabled, it'd better handle this case. And this is why get_cpu() is used in the non-RPS #ifdef branch. If tree RCU is selected, rcu_read_lock() won't disable preemption, so preempt_disable() should be called explictly. Signed-off-by: Changli Gao <xiaosuo@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Although netif_rx() isn't expected to be called in process context with
preemption enabled, it'd better handle this case. And this is why get_cpu()
is used in the non-RPS #ifdef branch. If tree RCU is selected,
rcu_read_lock() won't disable preemption, so preempt_disable() should be
called explictly.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: Fix napi_gro_frags vs netpoll path 2010-08-05T20:21:25+00:00 Jarek Poplawski jarkao2@gmail.com 2010-08-05T01:19:11+00:00 ce9e76c8450fc248d3e1fc16ef05e6eb50c02fa5 The netpoll_rx_on() check in __napi_gro_receive() skips part of the "common" GRO_NORMAL path, especially "pull:" in dev_gro_receive(), where at least eth header should be copied for entirely paged skbs. Signed-off-by: Jarek Poplawski <jarkao2@gmail.com> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net> 
The netpoll_rx_on() check in __napi_gro_receive() skips part of the
"common" GRO_NORMAL path, especially "pull:" in dev_gro_receive(),
where at least eth header should be copied for entirely paged skbs.

Signed-off-by: Jarek Poplawski <jarkao2@gmail.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Revert "net: remove zap_completion_queue" 2010-08-03T07:24:04+00:00 David S. Miller davem@davemloft.net 2010-08-03T07:24:04+00:00 3578b0c8abc7bdb4f02152ce5db7e09d484c6866 This reverts commit 15e83ed78864d0625e87a85f09b297c0919a4797. As explained by Johannes Berg, the optimization made here is invalid. Or, at best, incomplete. Not only destructor invocation, but conntract entry releasing must be executed outside of hw IRQ context. So just checking "skb->destructor" is insufficient. Signed-off-by: David S. Miller <davem@davemloft.net> 
This reverts commit 15e83ed78864d0625e87a85f09b297c0919a4797.

As explained by Johannes Berg, the optimization made here is
invalid.  Or, at best, incomplete.

Not only destructor invocation, but conntract entry releasing
must be executed outside of hw IRQ context.

So just checking "skb->destructor" is insufficient.

Signed-off-by: David S. Miller <davem@davemloft.net>
net: cleanup inclusion 2010-08-03T05:45:49+00:00 Changli Gao xiaosuo@gmail.com 2010-08-03T05:45:49+00:00 a427615e0420f179eab801b929111abaadea2ed3 Commit ab95bfe01f9872459c8678572ccadbf646badad0 replaces bridge and macvlan hooks in __netif_receive_skb(), so dev.c doesn't need to include their headers. Signed-off-by: Changli Gao <xiaosuo@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
Commit ab95bfe01f9872459c8678572ccadbf646badad0 replaces bridge and macvlan
hooks in __netif_receive_skb(), so dev.c doesn't need to include their headers.

Signed-off-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
net: ingress filter message limit 2010-08-01T07:33:23+00:00 Stephen Hemminger shemminger@vyatta.com 2010-08-01T07:33:23+00:00 de38483010bae523f533bb6bf9f7b7353772f6eb If user misconfigures ingress and causes a redirection loop, don't overwhelm the log. This is also a error case so make it unlikely. Found by inspection, luckily not in real system. Signed-off-by: Stephen Hemminger <shemminger@vyatta.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
If user misconfigures ingress and causes a redirection loop, don't
overwhelm the log.  This is also a error case so make it unlikely.
Found by inspection, luckily not in real system.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 2010-07-28T04:01:35+00:00 David S. Miller davem@davemloft.net 2010-07-28T04:01:35+00:00 bb7e95c8fd859922c6cf3ebbb3a8546007df1748 Conflicts: drivers/net/bnx2x_main.c Merge bnx2x bug fixes in by hand... :-/ Signed-off-by: David S. Miller <davem@davemloft.net> 
Conflicts:
	drivers/net/bnx2x_main.c

Merge bnx2x bug fixes in by hand... :-/

Signed-off-by: David S. Miller <davem@davemloft.net>
net: dev_forward_skb should call nf_reset 2010-07-26T04:58:46+00:00 Ben Greear greearb@candelatech.com 2010-07-22T09:54:47+00:00 c736eefadb71a01a5e61e0de700f28f6952b4444 With conn-track zones and probably with different network namespaces, the netfilter logic needs to be re-calculated on packet receive. If the netfilter logic is not reset, it will not be recalculated properly. This patch adds the nf_reset logic to dev_forward_skb. Signed-off-by: Ben Greear <greearb@candelatech.com> Signed-off-by: David S. Miller <davem@davemloft.net> 
With conn-track zones and probably with different network
namespaces, the netfilter logic needs to be re-calculated
on packet receive.  If the netfilter logic is not reset,
it will not be recalculated properly.  This patch adds
the nf_reset logic to dev_forward_skb.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: David S. Miller <davem@davemloft.net>