* Re: [RFC] per-containers tcp buffer limitation
From: Daniel Wagner @ 2011-08-25 18:33 UTC (permalink / raw)
To: Stephen Hemminger
Cc: Chris Friesen, Eric W. Biederman, KAMEZAWA Hiroyuki,
Glauber Costa, Linux Containers, netdev, David Miller,
Pavel Emelyanov
In-Reply-To: <20110825084415.3c3094e8@nehalam.ftrdhcpuser.net>
Hi Stephen,
On 08/25/2011 05:44 PM, Stephen Hemminger wrote:
> What about using netfilter (with extensions)? We already have iptables
> module to match on uid or gid. It wouldn't be hard to extend this to
> other bits of meta data like originating and target containers.
>From reading the man pages the "owner" extension of netfilter would only
allow to match on outgoing traffic. Would it be possible to extend this
to also match on incoming traffic? Sorry to be completely ignorant here.
thanks,
daniel
^ permalink raw reply
* Re: [RFC] per-containers tcp buffer limitation
From: Daniel Wagner @ 2011-08-25 18:27 UTC (permalink / raw)
To: Chris Friesen
Cc: Eric W. Biederman, KAMEZAWA Hiroyuki, Glauber Costa,
Linux Containers, netdev, David Miller, Pavel Emelyanov
In-Reply-To: <4E5664B5.6000806@genband.com>
Hi Chris,
On 08/25/2011 05:05 PM, Chris Friesen wrote:
> On 08/25/2011 06:55 AM, Daniel Wagner wrote:
>
>> I'd like to solve a use case where it is necessary to count all bytes
>> transmitted and received by an application [1]. So far I have found two
>> unsatisfying solution for it. The first one is to hook into libc and
>> count the bytes there. I don't think I have to say I don't like this.
>
> Is there any particular reason you can't use LD_PRELOAD to interpose a
> library to do the statistics monitoring?
This is certainly possible to do for any dynamic linked application. I
think it wouldn't work for static linked ones. Currently I don't know if
I have to face such application on the project I am on. The reason why I
am not so a big fan is that using the LD_PRELOAD trick seems very
hackish to me.
As Glauber has argumented in this thread, there are properly quite a few
people who want to control or monitor sockets. It seems I am one of
those. Having this kind of support in cgroups seems like a very neat
solution to me.
thanks,
daniel
^ permalink raw reply
* Re: [RFC] per-containers tcp buffer limitation
From: Glauber Costa @ 2011-08-25 18:11 UTC (permalink / raw)
To: Stephen Hemminger
Cc: Chris Friesen, Daniel Wagner, Eric W. Biederman,
KAMEZAWA Hiroyuki, Linux Containers, netdev, David Miller,
Pavel Emelyanov
In-Reply-To: <20110825084415.3c3094e8@nehalam.ftrdhcpuser.net>
On 08/25/2011 12:44 PM, Stephen Hemminger wrote:
> You seem to have forgotten the work of your forefathers. When appealing
> to history you must understand it first.
>
> What about using netfilter (with extensions)? We already have iptables
> module to match on uid or gid. It wouldn't be hard to extend this to
> other bits of meta data like originating and target containers.
>
> You could also use this to restrict access to ports and hosts on
> a per container basis.
>
Hello Stephen,
I am pretty sure netfilter can provide us with amazing functionality
that will help our containers implementation a lot.
I don't think, however, that memory limitation belongs in there. First
of all, IIRC, we are not dropping packets, re-routing, dealing with any
low level characteristic, etc. We're just controlling buffer size. This
seems orthogonal to the work of netfilter.
Think for instance, in the soft limit: When we hit it, we enter a memory
pressure scenario. How would netfilter handle that?
So I guess cgroup is still better suited for this very specific task we
have in mind here. For most of the others, I have no doubt that
netfilter would come handy.
Thanks for your time!
^ permalink raw reply
* Re: [RFC] per-containers tcp buffer limitation
From: Glauber Costa @ 2011-08-25 18:05 UTC (permalink / raw)
To: KAMEZAWA Hiroyuki
Cc: Eric W. Biederman, Linux Containers, netdev, David Miller,
Pavel Emelyanov
In-Reply-To: <20110825104956.41c4b60e.kamezawa.hiroyu@jp.fujitsu.com>
On 08/24/2011 10:49 PM, KAMEZAWA Hiroyuki wrote:
> On Wed, 24 Aug 2011 22:28:59 -0300
> Glauber Costa<glommer@parallels.com> wrote:
>
>> On 08/24/2011 09:35 PM, Eric W. Biederman wrote:
>>> Glauber Costa<glommer@parallels.com> writes:
>>>
>>>> Hello,
>>>>
>>>> This is a proof of concept of some code I have here to limit tcp send and
>>>> receive buffers per-container (in our case). At this phase, I am more concerned
>>>> in discussing my approach, so please curse my family no further than the 3rd
>>>> generation.
>>>>
>>>> The problem we're trying to attack here, is that buffers can grow and fill
>>>> non-reclaimable kernel memory. When doing containers, we can't afford having a
>>>> malicious container pinning kernel memory at will, therefore exhausting all the
>>>> others.
>>>>
>>>> So here a container will be seen in the host system as a group of tasks, grouped
>>>> in a cgroup. This cgroup will have files allowing us to specify global
>>>> per-cgroup limits on buffers. For that purpose, I created a new sockets cgroup -
>>>> didn't really think any other one of the existing would do here.
>>>>
>>>> As for the network code per-se, I tried to keep the same code that deals with
>>>> memory schedule as a basis and make it per-cgroup.
>>>> You will notice that struct proto now take function pointers to values
>>>> controlling memory pressure and will return per-cgroup data instead of global
>>>> ones. So the current behavior is maintained: after the first threshold is hit,
>>>> we enter memory pressure. After that, allocations are suppressed.
>>>>
>>>> Only tcp code was really touched here. udp had the pointers filled, but we're
>>>> not really controlling anything. But the fact that this lives in generic code,
>>>> makes it easier to do the same for other protocols in the future.
>>>>
>>>> For this patch specifically, I am not touching - just provisioning -
>>>> rmem and wmem specific knobs. I should also #ifdef a lot of this, but hey,
>>>> remember: rfc...
>>>>
>>>> One drawback of this approach I found, is that cgroups does not really work well
>>>> with modules. A lot of the network code is modularized, so this would have to be
>>>> fixed somehow.
>>>>
>>>> Let me know what you think.
>>>
>>> Can you implement this by making the existing network sysctls per
>>> network namespace?
>>>
>>> At a quick skim it looks to me like you can make the existing sysctls
>>> per network namespace and solve the issues you are aiming at solving and
>>> that should make the code much simpler, than your proof of concept code.
>>>
>>> Any implementation of this needs to answer the question how much
>>> overhead does this extra accounting add. I don't have a clue how much
>>> overhead you are adding but you are making structures larger and I
>>> suspect adding at least another cache line miss, so I suspect your
>>> changes will impact real world socket performance.
>>
>> Hi Eric,
>>
>> Thanks for your attention.
>>
>> So, this that you propose was my first implementation. I ended up
>> throwing it away after playing with it for a while.
>>
>> One of the first problems that arise from that, is that the sysctls are
>> a tunable visible from inside the container. Those limits, however, are
>> to be set from the outside world. The code is not much better than that
>> either, and instead of creating new cgroup structures and linking them
>> to the protocol, we end up doing it for net ns. We end up increasing
>> structures just the same...
>>
>> Also, since we're doing resource control, it seems more natural to use
>> cgroups. Now, the fact that there are no correlation whatsoever between
>> cgroups and namespaces does bother me. But that's another story, much
>> more broader and general than this patch.
>>
>
> I think using cgroup makes sense. A question in mind is whehter it is
> better to integrate this kind of 'memory usage' controls to memcg or not.
>
> How do you think ? IMHO, having cgroup per class of object is messy.
> ...
> How about adding
> memory.tcp_mem
> to memcg ?
>
> Or, adding kmem cgroup ?
I don't really care which cgroup do we use. I choosed a new socket one,
because they are usually not like other objects. People love tweaking
network aspects, and it is not hard to imagine people wanting to extend it.
Now, if all of this will ever belong to cgroup, is of course a different
matter.
Between your two suggestions, I like kmem better. It makes it then
absolutely clear that we will handle kernel objects only...
>> About overhead, since this is the first RFC, I did not care about
>> measuring. However, it seems trivial to me to guarantee that at least
>> that it won't impose a significant performance penalty when it is
>> compiled out. If we're moving forward with this implementation, I will
>> include data in the next release so we can discuss in this basis.
>>
>
> IMHO, you should show performance number even if RFC. Then, people will
> see patch with more interests.
Let's call this one pre-RFC then.
^ permalink raw reply
* Re: [RFC] per-containers tcp buffer limitation
From: Glauber Costa @ 2011-08-25 18:02 UTC (permalink / raw)
To: Eric W. Biederman
Cc: KAMEZAWA Hiroyuki, Linux Containers, netdev, David Miller,
Pavel Emelyanov
In-Reply-To: <m14o16qlq1.fsf@fess.ebiederm.org>
On 08/24/2011 11:16 PM, Eric W. Biederman wrote:
> KAMEZAWA Hiroyuki<kamezawa.hiroyu@jp.fujitsu.com> writes:
>
>> On Wed, 24 Aug 2011 22:28:59 -0300
>> Glauber Costa<glommer@parallels.com> wrote:
>>
>>> On 08/24/2011 09:35 PM, Eric W. Biederman wrote:
>>>> Glauber Costa<glommer@parallels.com> writes:
>>> Hi Eric,
>>>
>>> Thanks for your attention.
>>>
>>> So, this that you propose was my first implementation. I ended up
>>> throwing it away after playing with it for a while.
>>>
>>> One of the first problems that arise from that, is that the sysctls are
>>> a tunable visible from inside the container. Those limits, however, are
>>> to be set from the outside world. The code is not much better than that
>>> either, and instead of creating new cgroup structures and linking them
>>> to the protocol, we end up doing it for net ns. We end up increasing
>>> structures just the same...
>
> You don't need to add a netns member to sockets.
But then you have to grow the netns structure itself somehow.
>
> But I do agree that there are odd permission issues with using the
> existing sysctls and making them per namespace.
>
> However almost everything I have seen with memory limits I have found
> very strange. They all seem like a very bad version of disabling memory
> over commits.
More or less. At least from our perspective, the only thing we're really
interested in capping are non-swappable resources. So you could not
overcommit anyway.
For the sockets/tcp case, it is an even easier case. The code as it is
today already allow you to define soft and hard memory limits: I am just
making it container-wide, instead of system-wide.
>>> Also, since we're doing resource control, it seems more natural to use
>>> cgroups. Now, the fact that there are no correlation whatsoever between
>>> cgroups and namespaces does bother me. But that's another story, much
>>> more broader and general than this patch.
>>>
>>
>> I think using cgroup makes sense. A question in mind is whehter it is
>> better to integrate this kind of 'memory usage' controls to memcg or
>> not.
>
> Maybe. When sockets start getting a cgroup member I start wondering,
> how many cgroup members will sockets potentially belong to.
>
>> How do you think ? IMHO, having cgroup per class of object is messy.
>> ...
>> How about adding
>> memory.tcp_mem
>> to memcg ?
>>
>> Or, adding kmem cgroup ?
>>
>>> About overhead, since this is the first RFC, I did not care about
>>> measuring. However, it seems trivial to me to guarantee that at least
>>> that it won't impose a significant performance penalty when it is
>>> compiled out. If we're moving forward with this implementation, I will
>>> include data in the next release so we can discuss in this basis.
>>>
>>
>> IMHO, you should show performance number even if RFC. Then, people will
>> see patch with more interests.
>
> And also compiled out doesn't really count. Cgroups are something you
> want people to compile into distributions for the common case, and you
> don't want to impose a noticeable performance penalty for the common
> case.
Absolutely agreed.
^ permalink raw reply
* Re: Traffic shaping - class ID 16bit limit?
From: Stephen Hemminger @ 2011-08-25 17:10 UTC (permalink / raw)
To: Miroslav Kratochvil; +Cc: netdev
In-Reply-To: <CAO0uZ+_6xC0gymfbu28PRK4SaVgkGaSbbe-PgXvZ4h-cPp8k2A@mail.gmail.com>
On Thu, 25 Aug 2011 19:06:58 +0200
Miroslav Kratochvil <exa.exa@gmail.com> wrote:
> >> Technically the ClassID seems to be "hardcoded" as a 16bit value, but
> >> after some source searching, I haven't found any good reason for it to
> >> be 16-bit only.
> >
> > Granted it was a poor choice in the initial design.
> > It is wired into the API and changing it would be quite painful.
> >
>
> I was feeling something like that would come.
>
> If I get it correctly, the API change would consist of:
>
> - some netlink protocol change
> - slight modification of qdisc_class_hash
> - modifications in all (four?) hierarchical schedulers
> - tiny expansion of userspace tc utility
And all the magic compatiablity layers to make old code
work with new code.
^ permalink raw reply
* Re: Traffic shaping - class ID 16bit limit?
From: Miroslav Kratochvil @ 2011-08-25 17:06 UTC (permalink / raw)
To: Stephen Hemminger; +Cc: netdev
In-Reply-To: <20110825093937.2a8a1457@nehalam.ftrdhcpuser.net>
>> Technically the ClassID seems to be "hardcoded" as a 16bit value, but
>> after some source searching, I haven't found any good reason for it to
>> be 16-bit only.
>
> Granted it was a poor choice in the initial design.
> It is wired into the API and changing it would be quite painful.
>
I was feeling something like that would come.
If I get it correctly, the API change would consist of:
- some netlink protocol change
- slight modification of qdisc_class_hash
- modifications in all (four?) hierarchical schedulers
- tiny expansion of userspace tc utility
which isn't that painful (except for the CBQ part), but I'm probably
missing something, and presumably the change would take some time to
get mainstream -- probably way more time than writing a hfsc clone
that is controlled using some other interface than tc/netlink. :(
(but hey! I have a topic for school work!)
> You might be able to do the same thing by splitting traffic
> into multiple virtual devices (dummy or ifb) and then doing
> another layer.
>
My scenario looks pretty simple, mostly like a big hashing filter
attached at the device root, flowid'ing the stuff to leaf classes.
Could you please provide some simple illustration of splitting that
into multiple devices? I guess that the main problem with this
approach would be that my subclasses usually don't share anything in
common, especially not any pretty IP prefixes that would allow good
splitting.
Anyway, thanks very much for response!
-mk
^ permalink raw reply
* Re: Traffic shaping - class ID 16bit limit?
From: Stephen Hemminger @ 2011-08-25 16:39 UTC (permalink / raw)
To: Miroslav Kratochvil; +Cc: netdev
In-Reply-To: <CAO0uZ+-fv89Z3-9+vh5kN93xe=Uw8b=PSfnAqosOjUBP6PcVNg@mail.gmail.com>
On Thu, 25 Aug 2011 18:28:01 +0200
Miroslav Kratochvil <exa.exa@gmail.com> wrote:
> Technically the ClassID seems to be "hardcoded" as a 16bit value, but
> after some source searching, I haven't found any good reason for it to
> be 16-bit only.
Granted it was a poor choice in the initial design.
It is wired into the API and changing it would be quite painful.
You might be able to do the same thing by splitting traffic
into multiple virtual devices (dummy or ifb) and then doing
another layer.
^ permalink raw reply
* Traffic shaping - class ID 16bit limit?
From: Miroslav Kratochvil @ 2011-08-25 16:28 UTC (permalink / raw)
To: netdev
Hello everyone,
the question is simple: What should I do if I need to have more than
2^16 subclasses of a classful queuing discipline (in, say, hfsc or
htb)?
I bumped into this problem while writing some kind of traffic shaping
software and thinking about scalability. As there still are other ways
to have more than 64k "classes" (like grouping some subclasses into
separate qdiscs), those ways have significant drawbacks (require more
tc-filter rules and decisions, generally more processing power, and
the structure is quite hard to maintain).
Technically the ClassID seems to be "hardcoded" as a 16bit value, but
after some source searching, I haven't found any good reason for it to
be 16-bit only.
I understand that those ID's are usually handled together with another
16bit Qdisc ID, which would add up to a quite big number (possibly
unpleasant on some architectures) if those were both 32bit.
I also completely understand that in most cases of common usage
there's absolutely no need to have this big amount of subclasses, but
on the other hand there's still no reason to have "64k classes enough
for everyone". :D
Of course if there's some obvious method to solve this, or a patch, or
some kind of workaround that I haven't found, please let me know about
it, I will happily use it.
Thanks for any suggestions,
Mirek Kratochvil
^ permalink raw reply
* [PATCH net-next] net_sched: sfb: optimize enqueue on full queue
From: Eric Dumazet @ 2011-08-25 16:21 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In case SFB queue is full (hard limit reached), there is no point
spending time to compute hash and maximum qlen/p_mark.
We instead just early drop packet.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/sched/sch_sfb.c | 13 ++++++++-----
1 file changed, 8 insertions(+), 5 deletions(-)
diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c
index 0a833d0..e83c272 100644
--- a/net/sched/sch_sfb.c
+++ b/net/sched/sch_sfb.c
@@ -287,6 +287,12 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
u32 r, slot, salt, sfbhash;
int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+ if (unlikely(sch->q.qlen >= q->limit)) {
+ sch->qstats.overlimits++;
+ q->stats.queuedrop++;
+ goto drop;
+ }
+
if (q->rehash_interval > 0) {
unsigned long limit = q->rehash_time + q->rehash_interval;
@@ -332,12 +338,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch)
slot ^= 1;
sfb_skb_cb(skb)->hashes[slot] = 0;
- if (unlikely(minqlen >= q->max || sch->q.qlen >= q->limit)) {
+ if (unlikely(minqlen >= q->max)) {
sch->qstats.overlimits++;
- if (minqlen >= q->max)
- q->stats.bucketdrop++;
- else
- q->stats.queuedrop++;
+ q->stats.bucketdrop++;
goto drop;
}
^ permalink raw reply related
* Re: [RFC] per-containers tcp buffer limitation
From: Stephen Hemminger @ 2011-08-25 15:44 UTC (permalink / raw)
To: Chris Friesen
Cc: Daniel Wagner, Eric W. Biederman, KAMEZAWA Hiroyuki,
Glauber Costa, Linux Containers, netdev, David Miller,
Pavel Emelyanov
In-Reply-To: <4E5664B5.6000806@genband.com>
You seem to have forgotten the work of your forefathers. When appealing
to history you must understand it first.
What about using netfilter (with extensions)? We already have iptables
module to match on uid or gid. It wouldn't be hard to extend this to
other bits of meta data like originating and target containers.
You could also use this to restrict access to ports and hosts on
a per container basis.
^ permalink raw reply
* Re: linux-next: build failure after merge of the staging tree
From: Greg KH @ 2011-08-25 15:39 UTC (permalink / raw)
To: Larry Finger
Cc: Stephen Rothwell, linux-next, linux-kernel, wlanfae, Jiri Pirko,
David Miller, netdev
In-Reply-To: <4E55DA8C.10102@lwfinger.net>
On Thu, Aug 25, 2011 at 12:15:56AM -0500, Larry Finger wrote:
> On 08/25/2011 12:02 AM, Stephen Rothwell wrote:
> >Hi Greg,
> >
> >After merging the staging tree, today's linux-next build (x86_64
> >allmodconfig) failed like this:
> >
> >drivers/staging/rtl8192e/rtl_core.c:2917:2: error: unknown field 'ndo_set_multicast_list' specified in initializer
> >
> >Caused by commit 94a799425eee ("From: wlanfae<wlanfae@realtek.com>" -
> >really "[PATCH 1/8] rtl8192e: Import new version of driver from realtek"
> >Larry, that patch was badly imported ...) interacting with commit
> >b81693d9149c ("net: remove ndo_set_multicast_list callback") from the net
> >tree.
> >
> >I applied the following patch (which seems to be what was done to the
> >other drivers in the net tree - there is probably more required):
> >
> >From: Stephen Rothwell<sfr@canb.auug.org.au>
> >Date: Thu, 25 Aug 2011 14:57:55 +1000
> >Subject: [PATCH] rtl8192e: update for ndo_set_multicast_list removal.
> >
> >Signed-off-by: Stephen Rothwell<sfr@canb.auug.org.au>
> >---
> > drivers/staging/rtl8192e/rtl_core.c | 2 +-
> > 1 files changed, 1 insertions(+), 1 deletions(-)
> >
> >diff --git a/drivers/staging/rtl8192e/rtl_core.c b/drivers/staging/rtl8192e/rtl_core.c
> >index f8a13d9..b38f626 100644
> >--- a/drivers/staging/rtl8192e/rtl_core.c
> >+++ b/drivers/staging/rtl8192e/rtl_core.c
> >@@ -2914,7 +2914,7 @@ static const struct net_device_ops rtl8192_netdev_ops = {
> > .ndo_stop = rtl8192_close,
> > .ndo_tx_timeout = rtl8192_tx_timeout,
> > .ndo_do_ioctl = rtl8192_ioctl,
> >- .ndo_set_multicast_list = r8192_set_multicast,
> >+ .ndo_set_rx_mode = r8192_set_multicast,
> > .ndo_set_mac_address = r8192_set_mac_adr,
> > .ndo_validate_addr = eth_validate_addr,
> > .ndo_change_mtu = eth_change_mtu,
>
> Stephan,
>
> Thanks for the notice. It seems that commit b81693d9149c had not
> made it into my copy of staging. I'll look into the issue.
It wouldn't ever make it there, as that's coming from the net-next tree,
so this will have to wait until stuff merges together in Linus's tree.
thanks,
greg k-h
^ permalink raw reply
* RE: [PATCH 3/9] IB: nes: convert to SKB paged frag API.
From: Latif, Faisal @ 2011-08-25 15:33 UTC (permalink / raw)
To: Ian Campbell
Cc: Roland Dreier, Hefty, Sean, Hal Rosenstock,
linux-rdma@vger.kernel.org, netdev@vger.kernel.org
In-Reply-To: <1314260895-15936-3-git-send-email-ian.campbell@citrix.com>
Acked-by: Faisal Latif <faisal.latif@intel.com>
Thanks.
> ---
> drivers/infiniband/hw/nes/nes_nic.c | 21 +++++++++++----------
> 1 files changed, 11 insertions(+), 10 deletions(-)
^ permalink raw reply
* Re: [RFC PATCH v2 0/9] bql: Byte Queue Limits
From: Tom Herbert @ 2011-08-25 15:29 UTC (permalink / raw)
To: Johannes Berg; +Cc: jhs, davem, netdev
In-Reply-To: <1312809524.4372.29.camel@jlt3.sipsolutions.net>
> Well, the wireless case is curious, and has a whole bunch of corner
> cases, since it's not necessarily PtP, it can be PtMP!
>
> But considering the most basic case of us being a client connecting to
> an AP first: yes, the bandwidth will change dynamically, I don't know
> what impact this has on BQL, Tom, maybe you can think about this a bit?
>
BQL is dynamic, and will increase the queue limit more aggressively
than decrease it. So for instance, we can track the largest queue
needed over 30 seconds which should be stable in the presence even in
the presence of fluctuating bandwidth. The thing that worries me is
rather the HW queues conform to the queue characteristics described in
the patch. If transmit completions are random and not regular, BQL
probably can't function well.
If you'd like to bring this up on some wireless devices that would be
great, I don't have easy access to any right now, but I can try to
help otherwise.
> The second big challenge in wireless is the PtMP case: if we're acting
> as an AP, then we typically have four queues for any number of remote
> endpoints with varying bandwidth. I haven't found a good way to handle
> this, we can't have hardware queues per station (most HW is simply not
> capable of that many queues) but technically we would want to make the
> queue limits depend on the peer...
>
> Since I just returned from vacation I have tons of email to dig through
> I'll have to keep this short for now, but I'm definitely interested.
>
> johannes
>
>
^ permalink raw reply
* [PATCH] cassini: init before use in cas_interruptN.
From: Francois Romieu @ 2011-08-25 15:02 UTC (permalink / raw)
To: Thomas Jarosch; +Cc: netdev, David S. Miller
In-Reply-To: <201108251558.45290.thomas.jarosch@intra2net.com>
Signed-off-by: Francois Romieu <romieu@fr.zoreil.com>
Spotted-by: Thomas Jarosch <thomas.jarosch@intra2net.com>
---
David, any opinion regarding the removal of the USE_NAPI #ifdef
in this driver ?
drivers/net/cassini.c | 3 +--
1 files changed, 1 insertions(+), 2 deletions(-)
diff --git a/drivers/net/cassini.c b/drivers/net/cassini.c
index 646c86b..fdb7a17 100644
--- a/drivers/net/cassini.c
+++ b/drivers/net/cassini.c
@@ -2452,14 +2452,13 @@ static irqreturn_t cas_interruptN(int irq, void *dev_id)
struct net_device *dev = dev_id;
struct cas *cp = netdev_priv(dev);
unsigned long flags;
- int ring;
+ int ring = (irq == cp->pci_irq_INTC) ? 2 : 3;
u32 status = readl(cp->regs + REG_PLUS_INTRN_STATUS(ring));
/* check for shared irq */
if (status == 0)
return IRQ_NONE;
- ring = (irq == cp->pci_irq_INTC) ? 2 : 3;
spin_lock_irqsave(&cp->lock, flags);
if (status & INTR_RX_DONE_ALT) { /* handle rx separately */
#ifdef USE_NAPI
--
1.7.4.4
^ permalink raw reply related
* Re: [RFC PATCH v2 0/9] bql: Byte Queue Limits
From: Tom Herbert @ 2011-08-25 15:19 UTC (permalink / raw)
To: jhs; +Cc: davem, netdev, Johannes Berg
In-Reply-To: <1312808784.17202.39.camel@mojatatu>
> For wired connections I think the big deal is in improved
> runtime memory saving (your perf numbers are kinda ok).
> The challenge is going to be with wireless where the underlying
> bandwidth changes (and therefore the optimal queue size varies
> more frequently). The problem with active queue management is
> getting the feedback loop to be more accurate and i think there
> will be challenges with wired devices.
The important characteristic (for us at least) will be reduced latency
for high priority packets (for NICs that don't support qos multiQ. I
do have data showing those benefits, but it's a little old. I will
have something to present at LPC.
> I notice that you dont have any wireless devices;
> but it would be nice for someone to check this out on wireless.
> CCing Johannes - maybe he has some insight.
>
Yeah, these scare me ;-)
> cheers,
> jamal
>
>
>
>
^ permalink raw reply
* Re: [RFC] per-containers tcp buffer limitation
From: Chris Friesen @ 2011-08-25 15:05 UTC (permalink / raw)
To: Daniel Wagner
Cc: Eric W. Biederman, KAMEZAWA Hiroyuki, Glauber Costa,
Linux Containers, netdev, David Miller, Pavel Emelyanov
In-Reply-To: <4E56464B.4070304@monom.org>
On 08/25/2011 06:55 AM, Daniel Wagner wrote:
> I'd like to solve a use case where it is necessary to count all bytes
> transmitted and received by an application [1]. So far I have found two
> unsatisfying solution for it. The first one is to hook into libc and
> count the bytes there. I don't think I have to say I don't like this.
Is there any particular reason you can't use LD_PRELOAD to interpose a
library to do the statistics monitoring?
Chris
--
Chris Friesen
Software Developer
GENBAND
chris.friesen@genband.com
www.genband.com
^ permalink raw reply
* Re: [PATCH 2/9] IB: amso1100: convert to SKB paged frag API.
From: Steve Wise @ 2011-08-25 14:42 UTC (permalink / raw)
To: Ian Campbell
Cc: netdev-u79uwXL29TY76Z2rM5mHXA, Tom Tucker, Roland Dreier,
Sean Hefty, Hal Rosenstock, linux-rdma-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <1314260895-15936-2-git-send-email-ian.campbell-Sxgqhf6Nn4DQT0dZR+AlfA@public.gmane.org>
Acked-by: Steve Wise <swise-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org>
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* cassini driver: Use of uninitialized memory
From: Thomas Jarosch @ 2011-08-25 13:58 UTC (permalink / raw)
To: netdev
Hello,
the interrupt routine of the cassini driver
currently looks like this:
----------------------
static irqreturn_t cas_interruptN(int irq, void *dev_id)
{
struct net_device *dev = dev_id;
struct cas *cp = netdev_priv(dev);
unsigned long flags;
int ring;
u32 status = readl(cp->regs + REG_PLUS_INTRN_STATUS(ring));
...
----------------------
-> "ring" isn't initialized properly and gets used
in REG_PLUS_INTRN_STATUS. Some lines below there's this:
----------------------
ring = (irq == cp->pci_irq_INTC) ? 2 : 3;
----------------------
Should that line be moved before the readl() call
or should "ring" be initialized with zero?
Credit for spotting this goes to cppcheck.
Cheers,
Thomas
^ permalink raw reply
* Re: iwlagn: Random "Time out reading EEPROM".
From: Nicolas de Pesloüan @ 2011-08-25 13:50 UTC (permalink / raw)
To: wwguy
Cc: dhalperi-GmWTxIRN22iJaUV4rX00uodd74u8MsAO@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, wireless
In-Reply-To: <1310740111.13897.13.camel@wwguy-ubuntu>
Le 15/07/2011 16:28, wwguy a écrit :
> the error indicate fail to read data from EEPROM, your 2nd report is
> even more strange, the number at the end the error message indicate the
> index of DWORD driver trying to read from EEPROM.
>
> "Time out reading EEPROM[2]" telling me the first 2 DWORD is reading ok
> but not the 3rd read.
>
> How many PCI-E slots you have in your system, could it possible for you
> to switch to another PCI-E slot, or pull out and re-insert the NIC.
Unfortunately, not. On this laptop, the NIC is not reachable without disassembling the laptop, and I
don't want to... I will double check again, but...
> Also, it is possible to put the NIC into different system and see if you
> are seeing the similar problem?
No, for the exact same reason.
Not that it still happens with 3.0.0-1 from Debian.
[ 15.086244] iwlagn: Intel(R) Wireless WiFi Link AGN driver for Linux, in-tree:
[ 15.086247] iwlagn: Copyright(c) 2003-2011 Intel Corporation
[ 15.086404] iwlagn 0000:05:00.0: PCI INT A -> GSI 18 (level, low) -> IRQ 18
[ 15.086412] iwlagn 0000:05:00.0: setting latency timer to 64
[ 15.086438] iwlagn 0000:05:00.0: Detected Intel(R) WiFi Link 5100 AGN, REV=0x54
[ 15.095859] iwlagn 0000:05:00.0: Time out reading EEPROM[6]
[ 15.095945] iwlagn 0000:05:00.0: Unable to init EEPROM
[ 15.096030] iwlagn 0000:05:00.0: PCI INT A disabled
[ 15.096039] iwlagn: probe of 0000:05:00.0 failed with error -110
modprobe -r iwlagn ; modprobe iwlagn
[ 231.822492] iwlagn: Intel(R) Wireless WiFi Link AGN driver for Linux, in-tree:
[ 231.822495] iwlagn: Copyright(c) 2003-2011 Intel Corporation
[ 231.822581] iwlagn 0000:05:00.0: PCI INT A -> GSI 18 (level, low) -> IRQ 18
[ 231.822591] iwlagn 0000:05:00.0: setting latency timer to 64
[ 231.822621] iwlagn 0000:05:00.0: Detected Intel(R) WiFi Link 5100 AGN, REV=0x54
[ 231.843544] iwlagn 0000:05:00.0: device EEPROM VER=0x11f, CALIB=0x4
[ 231.843546] iwlagn 0000:05:00.0: Device SKU: 0Xb
[ 231.844889] iwlagn 0000:05:00.0: Tunable channels: 13 802.11bg, 24 802.11a channels
[ 231.844961] iwlagn 0000:05:00.0: irq 50 for MSI/MSI-X
[ 231.989424] iwlagn 0000:05:00.0: loaded firmware version 8.83.5.1 build 33692
[ 232.037456] ieee80211 phy0: Selected rate control algorithm 'iwl-agn-rs'
The error is not easy to reproduce, but the fix is perfectly stable. A single unload/reload of
iwlagn is always enough to solve the problem, when it happens. For this reason, it sounds difficult
to consider this a hardware slot problem. Can't this be related to some other PCI components?
00:00.0 Host bridge: Intel Corporation Mobile 4 Series Chipset Memory Controller Hub (rev 07)
00:01.0 PCI bridge: Intel Corporation Mobile 4 Series Chipset PCI Express Graphics Port (rev 07)
00:1a.0 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #4 (rev 03)
00:1a.1 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #5 (rev 03)
00:1a.2 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #6 (rev 03)
00:1a.7 USB Controller: Intel Corporation 82801I (ICH9 Family) USB2 EHCI Controller #2 (rev 03)
00:1b.0 Audio device: Intel Corporation 82801I (ICH9 Family) HD Audio Controller (rev 03)
00:1c.0 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 1 (rev 03)
00:1c.1 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 2 (rev 03)
00:1c.2 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 3 (rev 03)
00:1c.3 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 4 (rev 03)
00:1c.4 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 5 (rev 03)
00:1c.5 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 6 (rev 03)
00:1d.0 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #1 (rev 03)
00:1d.1 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #2 (rev 03)
00:1d.2 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #3 (rev 03)
00:1d.7 USB Controller: Intel Corporation 82801I (ICH9 Family) USB2 EHCI Controller #1 (rev 03)
00:1e.0 PCI bridge: Intel Corporation 82801 Mobile PCI Bridge (rev 93)
00:1f.0 ISA bridge: Intel Corporation ICH9M LPC Interface Controller (rev 03)
00:1f.2 SATA controller: Intel Corporation ICH9M/M-E SATA AHCI Controller (rev 03)
00:1f.3 SMBus: Intel Corporation 82801I (ICH9 Family) SMBus Controller (rev 03)
01:00.0 VGA compatible controller: nVidia Corporation G98 [GeForce 9300M GS] (rev a1)
02:00.0 Ethernet controller: Marvell Technology Group Ltd. 88E8055 PCI-E Gigabit Ethernet Controller
(rev 14)
05:00.0 Network controller: Intel Corporation WiFi Link 5100
09:03.0 FireWire (IEEE 1394): Ricoh Co Ltd R5C832 IEEE 1394 Controller (rev 05)
09:03.1 SD Host controller: Ricoh Co Ltd R5C822 SD/SDIO/MMC/MS/MSPro Host Adapter (rev 22)
09:03.2 System peripheral: Ricoh Co Ltd R5C592 Memory Stick Bus Host Adapter (rev 12)
I'm quite sure I can fix this problem by loading, unloading and reloading iwlagn on every startup...
but I don't really consider this a fix :-/
Nicolas.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: iwlagn: Random "Time out reading EEPROM".
From: Guy, Wey-Yi @ 2011-08-25 13:37 UTC (permalink / raw)
To: Nicolas de Pesloüan
Cc: dhalperi-GmWTxIRN22iJaUV4rX00uodd74u8MsAO@public.gmane.org,
netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, wireless
In-Reply-To: <4E565333.3080007-Re5JQEeQqe8AvxtiuMwx3w@public.gmane.org>
On Thu, 2011-08-25 at 06:50 -0700, Nicolas de Pesloüan wrote:
> Le 15/07/2011 16:28, wwguy a écrit :
>
> > the error indicate fail to read data from EEPROM, your 2nd report is
> > even more strange, the number at the end the error message indicate the
> > index of DWORD driver trying to read from EEPROM.
> >
> > "Time out reading EEPROM[2]" telling me the first 2 DWORD is reading ok
> > but not the 3rd read.
> >
> > How many PCI-E slots you have in your system, could it possible for you
> > to switch to another PCI-E slot, or pull out and re-insert the NIC.
>
> Unfortunately, not. On this laptop, the NIC is not reachable without disassembling the laptop, and I
> don't want to... I will double check again, but...
>
> > Also, it is possible to put the NIC into different system and see if you
> > are seeing the similar problem?
>
> No, for the exact same reason.
>
> Not that it still happens with 3.0.0-1 from Debian.
>
> [ 15.086244] iwlagn: Intel(R) Wireless WiFi Link AGN driver for Linux, in-tree:
> [ 15.086247] iwlagn: Copyright(c) 2003-2011 Intel Corporation
> [ 15.086404] iwlagn 0000:05:00.0: PCI INT A -> GSI 18 (level, low) -> IRQ 18
> [ 15.086412] iwlagn 0000:05:00.0: setting latency timer to 64
> [ 15.086438] iwlagn 0000:05:00.0: Detected Intel(R) WiFi Link 5100 AGN, REV=0x54
> [ 15.095859] iwlagn 0000:05:00.0: Time out reading EEPROM[6]
> [ 15.095945] iwlagn 0000:05:00.0: Unable to init EEPROM
> [ 15.096030] iwlagn 0000:05:00.0: PCI INT A disabled
> [ 15.096039] iwlagn: probe of 0000:05:00.0 failed with error -110
>
> modprobe -r iwlagn ; modprobe iwlagn
>
> [ 231.822492] iwlagn: Intel(R) Wireless WiFi Link AGN driver for Linux, in-tree:
> [ 231.822495] iwlagn: Copyright(c) 2003-2011 Intel Corporation
> [ 231.822581] iwlagn 0000:05:00.0: PCI INT A -> GSI 18 (level, low) -> IRQ 18
> [ 231.822591] iwlagn 0000:05:00.0: setting latency timer to 64
> [ 231.822621] iwlagn 0000:05:00.0: Detected Intel(R) WiFi Link 5100 AGN, REV=0x54
> [ 231.843544] iwlagn 0000:05:00.0: device EEPROM VER=0x11f, CALIB=0x4
> [ 231.843546] iwlagn 0000:05:00.0: Device SKU: 0Xb
> [ 231.844889] iwlagn 0000:05:00.0: Tunable channels: 13 802.11bg, 24 802.11a channels
> [ 231.844961] iwlagn 0000:05:00.0: irq 50 for MSI/MSI-X
> [ 231.989424] iwlagn 0000:05:00.0: loaded firmware version 8.83.5.1 build 33692
> [ 232.037456] ieee80211 phy0: Selected rate control algorithm 'iwl-agn-rs'
>
> The error is not easy to reproduce, but the fix is perfectly stable. A single unload/reload of
> iwlagn is always enough to solve the problem, when it happens. For this reason, it sounds difficult
> to consider this a hardware slot problem. Can't this be related to some other PCI components?
>
> 00:00.0 Host bridge: Intel Corporation Mobile 4 Series Chipset Memory Controller Hub (rev 07)
> 00:01.0 PCI bridge: Intel Corporation Mobile 4 Series Chipset PCI Express Graphics Port (rev 07)
> 00:1a.0 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #4 (rev 03)
> 00:1a.1 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #5 (rev 03)
> 00:1a.2 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #6 (rev 03)
> 00:1a.7 USB Controller: Intel Corporation 82801I (ICH9 Family) USB2 EHCI Controller #2 (rev 03)
> 00:1b.0 Audio device: Intel Corporation 82801I (ICH9 Family) HD Audio Controller (rev 03)
> 00:1c.0 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 1 (rev 03)
> 00:1c.1 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 2 (rev 03)
> 00:1c.2 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 3 (rev 03)
> 00:1c.3 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 4 (rev 03)
> 00:1c.4 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 5 (rev 03)
> 00:1c.5 PCI bridge: Intel Corporation 82801I (ICH9 Family) PCI Express Port 6 (rev 03)
> 00:1d.0 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #1 (rev 03)
> 00:1d.1 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #2 (rev 03)
> 00:1d.2 USB Controller: Intel Corporation 82801I (ICH9 Family) USB UHCI Controller #3 (rev 03)
> 00:1d.7 USB Controller: Intel Corporation 82801I (ICH9 Family) USB2 EHCI Controller #1 (rev 03)
> 00:1e.0 PCI bridge: Intel Corporation 82801 Mobile PCI Bridge (rev 93)
> 00:1f.0 ISA bridge: Intel Corporation ICH9M LPC Interface Controller (rev 03)
> 00:1f.2 SATA controller: Intel Corporation ICH9M/M-E SATA AHCI Controller (rev 03)
> 00:1f.3 SMBus: Intel Corporation 82801I (ICH9 Family) SMBus Controller (rev 03)
> 01:00.0 VGA compatible controller: nVidia Corporation G98 [GeForce 9300M GS] (rev a1)
> 02:00.0 Ethernet controller: Marvell Technology Group Ltd. 88E8055 PCI-E Gigabit Ethernet Controller
> (rev 14)
> 05:00.0 Network controller: Intel Corporation WiFi Link 5100
> 09:03.0 FireWire (IEEE 1394): Ricoh Co Ltd R5C832 IEEE 1394 Controller (rev 05)
> 09:03.1 SD Host controller: Ricoh Co Ltd R5C822 SD/SDIO/MMC/MS/MSPro Host Adapter (rev 22)
> 09:03.2 System peripheral: Ricoh Co Ltd R5C592 Memory Stick Bus Host Adapter (rev 12)
>
> I'm quite sure I can fix this problem by loading, unloading and reloading iwlagn on every startup...
> but I don't really consider this a fix :
not sure how to help since it is not easy to re-produce and it is EEPROM
reading problem, I only can guess it might related to the physical
device.
Thanks
Wey
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: TCP port firewall controlled by UDP packets
From: Pavel Machek @ 2011-08-25 13:19 UTC (permalink / raw)
To: Tonda; +Cc: davem, kuznet, jmorris, yoshfuji, kaber, netdev, linux-kernel
In-Reply-To: <1313106172-18455-1-git-send-email-as@strmilov.cz>
No comments, variables named in czech.
Ok for me but...
But first thing would be description what it is good for...?
Pavel
On Fri 2011-08-12 01:42:52, Tonda wrote:
> If unsure, say N.
> +
> +config TCPFIREWALL
> + tristate "TCP Firewall controlled by UDP queries"
> + depends on m
> diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
> --- a/net/ipv4/Makefile
> +++ b/net/ipv4/Makefile
> @@ -51,3 +51,4 @@
>
> obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
> xfrm4_output.o
> +obj-$(CONFIG_TCPFIREWALL) += tcpfirewall/
> diff --git a/net/ipv4/tcpfirewall/Makefile b/net/ipv4/tcpfirewall/Makefile
> --- a/net/ipv4/tcpfirewall/Makefile
> +++ b/net/ipv4/tcpfirewall/Makefile
> @@ -0,0 +1 @@
> +obj-$(CONFIG_TCPFIREWALL) += tcpfirewall.o
> diff --git a/net/ipv4/tcpfirewall/tcpfirewall.c b/net/ipv4/tcpfirewall/tcpfirewall.c
> --- a/net/ipv4/tcpfirewall/tcpfirewall.c
> +++ b/net/ipv4/tcpfirewall/tcpfirewall.c
> @@ -0,0 +1,451 @@
> +#include <linux/module.h>
> +#include <linux/kernel.h>
> +#include <linux/init.h>
> +#include <linux/skbuff.h>
> +#include <linux/in.h>
> +#include <linux/if_packet.h>
> +#include <linux/tcp.h>
> +#include <linux/udp.h>
> +#include <net/tcp.h>
> +#include <net/udp.h>
> +
> +struct net_protocol {
> + int (*handler)(struct sk_buff *skb);
> + void (*err_handler)(struct sk_buff *skb, u32 info);
> + int (*gso_send_check)(struct sk_buff *skb);
> + struct sk_buff *(*gso_segment)(struct sk_buff *skb,
> + u32 features);
> + struct sk_buff **(*gro_receive)(struct sk_buff **head,
> + struct sk_buff *skb);
> + int (*gro_complete)(struct sk_buff *skb);
> + unsigned int no_policy:1,
> + netns_ok:1;
> +};
> +
> +MODULE_LICENSE("GPL");
> +
> +static unsigned long inet_protos = 0x01234567;
> +
> +struct net_protocol **_inet_protos;
> +
> +module_param(inet_protos, ulong, 0);
> +
> +static int *otviraky;
> +static int *zaviraky;
> +
> +static int pocetotviraku;
> +static int pocetzaviraku;
> +static int stav;
> +static int packetcounter;
> +static int tcpport;
> +static int open;
> +static int firewall;
> +
> +int (*tcpv4recv) (struct sk_buff *skb);
> +int (*udprecv) (struct sk_buff *skb);
> +
> +int udpcontroller(struct sk_buff *skb)
> +{
> + const struct udphdr *uh;
> +
> + if (skb->pkt_type != PACKET_HOST) {
> + kfree_skb(skb);
> + return 0;
> + }
> +
> + if (!pskb_may_pull(skb, sizeof(struct tcphdr))) {
> + kfree_skb(skb);
> + return 0;
> + }
> +
> + uh = udp_hdr(skb);
> +
> + if (pocetotviraku == 0)
> + return udprecv(skb);
> +
> + if (!open) {
> + if (uh->dest == otviraky[stav]) {
> + ++stav;
> + packetcounter = 0;
> +
> + if (stav == pocetotviraku) {
> + open = 1;
> + stav = 0;
> + }
> + } else {
> + if (packetcounter <= 16) {
> + ++packetcounter;
> + if (packetcounter > 16)
> + stav = 0;
> + }
> + }
> + } else {
> + if (uh->dest == zaviraky[stav]) {
> + ++stav;
> + packetcounter = 0;
> +
> + if (stav == pocetzaviraku) {
> + open = 0;
> + stav = 0;
> + }
> + } else {
> + if (packetcounter <= 16) {
> + ++packetcounter;
> + if (packetcounter > 16)
> + stav = 0;
> + }
> + }
> + }
> +
> +
> + return udprecv(skb);
> +}
> +
> +int tcpfirewall(struct sk_buff *skb)
> +{
> + const struct tcphdr *th;
> +
> + if (skb->pkt_type != PACKET_HOST) {
> + kfree_skb(skb);
> + return 0;
> + }
> +
> + if (!pskb_may_pull(skb, sizeof(struct tcphdr))) {
> + kfree_skb(skb);
> + return 0;
> + }
> +
> + th = tcp_hdr(skb);
> +
> + if (th->dest == tcpport) {
> + if (firewall == 1 && !open) {
> + /*tcpv4sendreset(NULL, skb);*/
> + kfree_skb(skb);
> + return 0;
> + }
> + }
> +
> + return tcpv4recv(skb);
> +}
> +
> +static struct net_protocol *zalohatcp;
> +static struct net_protocol *zalohaudp;
> +static struct net_protocol mytcp;
> +static struct net_protocol myudp;
> +
> +static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buffer)
> +{
> + if (!strcmp(attr->name, "firewall")) {
> + if (firewall)
> + buffer[0] = '1';
> + else
> + buffer[0] = '0';
> +
> + buffer[1] = '\n';
> + return 2;
> + }
> +
> + if (!strcmp(attr->name, "tcpport")) {
> + sprintf(buffer, "%d\n", ntohs(tcpport));
> + return strlen(buffer)+1;
> + }
> +
> + if (!strcmp(attr->name, "openers")) {
> + int i;
> + char *znak;
> + if (pocetotviraku == 0)
> + return 0;
> + buffer[0] = '\0';
> + znak = kmalloc(10, GFP_KERNEL);
> + for (i = 0; i < pocetotviraku; ++i) {
> + sprintf(znak, "%d ", ntohs(otviraky[i]));
> + strcat(buffer, znak);
> + }
> + kfree(znak);
> + buffer[strlen(buffer)-1] = '\n';
> + return strlen(buffer);
> + }
> +
> + if (!strcmp(attr->name, "closers")) {
> + int i;
> + char *znak;
> + if (pocetzaviraku == 0)
> + return 0;
> + buffer[0] = '\0';
> + znak = kmalloc(10, GFP_KERNEL);
> + for (i = 0; i < pocetzaviraku; ++i) {
> + sprintf(znak, "%d ", ntohs(zaviraky[i]));
> + strcat(buffer, znak);
> + }
> + kfree(znak);
> + buffer[strlen(buffer)-1] = '\n';
> + return strlen(buffer);
> + }
> +
> + if (!strcmp(attr->name, "open")) {
> + if (open)
> + buffer[0] = '1';
> + else
> + buffer[0] = '0';
> +
> + buffer[1] = '\n';
> + return 2;
> + }
> +
> + if (!strcmp(attr->name, "state")) {
> + sprintf(buffer, "%d\n", stav);
> + return strlen(buffer)+1;
> + }
> +
> + if (!strcmp(attr->name, "counter")) {
> + sprintf(buffer, "%d\n", packetcounter);
> + return strlen(buffer)+1;
> + }
> +
> + return 0;
> +}
> +
> +static ssize_t store(struct kobject *kobj, struct attribute *attr,
> + const char *buffer, size_t size)
> +{
> + int i;
> + char *cislo;
> + if (!strcmp(attr->name, "firewall")) {
> + if (size > 0 && buffer[0] == '1')
> + firewall = 1;
> + else
> + firewall = 0;
> + stav = 0;
> + return size;
> + }
> +
> + if (!strcmp(attr->name, "tcpport")) {
> + cislo = kmalloc(size+1, GFP_KERNEL);
> + for (i = 0; i < size; ++i)
> + cislo[i] = buffer[i];
> + cislo[size] = '\0';
> + if (kstrtoint(cislo, 10, &i) < 0)
> + i = -1;
> + if (i > 0 && i < 65536)
> + tcpport = htons(i);
> + kfree(cislo);
> + stav = 0;
> + return size;
> + }
> +
> + if (!strcmp(attr->name, "openers")) {
> + int udpport, i;
> + int *noveotviraky;
> + int *stareotviraky;
> + cislo = kmalloc(size+1, GFP_KERNEL);
> + for (i = 0; i < size; ++i)
> + cislo[i] = buffer[i];
> + cislo[size] = '\0';
> +
> + if (!strcmp(cislo, "reset") || !strcmp(cislo, "reset\n")) {
> + if (pocetotviraku)
> + kfree(otviraky);
> + pocetotviraku = 0;
> + }
> +
> + if (kstrtoint(cislo, 10, &i) < 0)
> + i = -1;
> + kfree(cislo);
> +
> + if (i > 0 && i < 65536 && (pocetotviraku == 0 ||
> + otviraky[pocetotviraku-1] != i))
> + udpport = htons(i);
> + else
> + return size;
> +
> + if (pocetotviraku < 10) {
> + noveotviraky = kmalloc((pocetotviraku+1)*sizeof(int),
> + GFP_KERNEL);
> +
> + for (i = 0; i < pocetotviraku; ++i)
> + noveotviraky[i] = otviraky[i];
> +
> + noveotviraky[pocetotviraku] = udpport;
> + stareotviraky = otviraky;
> + otviraky = noveotviraky;
> + if (pocetotviraku)
> + kfree(stareotviraky);
> +
> + ++pocetotviraku;
> + }
> + stav = 0;
> + return size;
> + }
> +
> + if (!strcmp(attr->name, "closers")) {
> + int udpport, i;
> + int *novezaviraky;
> + int *starezaviraky;
> + cislo = kmalloc(size+1, GFP_KERNEL);
> + for (i = 0; i < size; ++i)
> + cislo[i] = buffer[i];
> + cislo[size] = '\0';
> +
> + if (!strcmp(cislo, "reset") || !strcmp(cislo, "reset\n")) {
> + if (pocetzaviraku)
> + kfree(zaviraky);
> + pocetzaviraku = 0;
> + }
> +
> + if (kstrtoint(cislo, 10, &i) < 0)
> + i = -1;
> + kfree(cislo);
> +
> + if (i > 0 && i < 65536 && (pocetzaviraku == 0 ||
> + zaviraky[pocetzaviraku-1] != i))
> + udpport = htons(i);
> + else
> + return size;
> +
> + if (pocetzaviraku < 10) {
> + novezaviraky = kmalloc((pocetzaviraku+1)*sizeof(int),
> + GFP_KERNEL);
> +
> + for (i = 0; i < pocetzaviraku; ++i)
> + novezaviraky[i] = zaviraky[i];
> +
> + novezaviraky[pocetzaviraku] = udpport;
> + starezaviraky = zaviraky;
> + zaviraky = novezaviraky;
> + if (pocetzaviraku)
> + kfree(starezaviraky);
> +
> + ++pocetzaviraku;
> + }
> + stav = 0;
> + return size;
> + }
> +
> + if (!strcmp(attr->name, "open")) {
> + if (size > 0 && buffer[0] == '1')
> + open = 1;
> + else
> + open = 0;
> +
> + stav = 0;
> + return size;
> + }
> +
> + return 0;
> +}
> +
> +static const struct sysfs_ops so = {
> + .show = show,
> + .store = store,
> +};
> +
> +static struct kobj_type khid = {
> + .sysfs_ops = &so,
> +};
> +
> +static struct kobject kobj;
> +
> +static const struct attribute fw = {
> + .name = "firewall",
> + .mode = S_IRWXU,
> +};
> +
> +static const struct attribute opn = {
> + .name = "open",
> + .mode = S_IRWXU,
> +};
> +
> +static const struct attribute tcpp = {
> + .name = "tcpport",
> + .mode = S_IRWXU,
> +};
> +
> +static const struct attribute openers = {
> + .name = "openers",
> + .mode = S_IRWXU,
> +};
> +
> +static const struct attribute closers = {
> + .name = "closers",
> + .mode = S_IRWXU,
> +};
> +
> +static const struct attribute stat = {
> + .name = "state",
> + .mode = S_IRUSR,
> +};
> +
> +static const struct attribute counte = {
> + .name = "counter",
> + .mode = S_IRUSR,
> +};
> +
> +static int __init start(void)
> +{
> + if (inet_protos == 0x01234567) {
> + printk(KERN_WARNING "inet_protos parameter was not");
> + printk(KERN_WARNING " specified!\nread its value from");
> + printk(KERN_WARNING " System_map file file, and insert");
> + printk(KERN_WARNING " the module again!\n");
> + return -1;
> + }
> +
> + pocetotviraku = 0;
> + pocetzaviraku = 0;
> + stav = -1;
> + packetcounter = 0;
> + tcpport = 0;
> + open = 1;
> + firewall = 0;
> +
> + memset(&kobj, 0, sizeof(struct kobject));
> +
> + _inet_protos = (struct net_protocol **)inet_protos;
> +
> + kobject_init(&kobj, &khid);
> + if (kobject_add(&kobj, NULL, "tcpfirewall") < 0)
> + printk(KERN_ERR "kobject_add failed");
> +
> + if (sysfs_create_file(&kobj, &fw) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> + if (sysfs_create_file(&kobj, &opn) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> + if (sysfs_create_file(&kobj, &tcpp) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> + if (sysfs_create_file(&kobj, &openers) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> + if (sysfs_create_file(&kobj, &closers) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> + if (sysfs_create_file(&kobj, &stat) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> + if (sysfs_create_file(&kobj, &counte) < 0)
> + printk(KERN_ERR "sysfs_create_file failed");
> +
> + zalohatcp = _inet_protos[IPPROTO_TCP];
> + zalohaudp = _inet_protos[IPPROTO_UDP];
> + mytcp = *zalohatcp;
> + myudp = *zalohaudp;
> + tcpv4recv = mytcp.handler;
> + udprecv = myudp.handler;
> + mytcp.handler = tcpfirewall;
> + myudp.handler = udpcontroller;
> + _inet_protos[IPPROTO_TCP] = &mytcp;
> + _inet_protos[IPPROTO_UDP] = &myudp;
> + return 0;
> +}
> +
> +static void konec(void)
> +{
> + _inet_protos[IPPROTO_TCP] = zalohatcp;
> + _inet_protos[IPPROTO_UDP] = zalohaudp;
> +
> + if (pocetotviraku)
> + kfree(otviraky);
> + if (pocetzaviraku)
> + kfree(zaviraky);
> +
> + kobject_del(&kobj);
> +}
> +
> +module_init(start);
> +module_exit(konec);
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
(english) http://www.livejournal.com/~pavelmachek
(cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html
^ permalink raw reply
* Re: [PATCH net-next v5 1/2] af-packet: Added TPACKET_V3 headers.
From: chetan loke @ 2011-08-25 12:58 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20110824.194308.2024908890526228700.davem@davemloft.net>
On Wed, Aug 24, 2011 at 10:43 PM, David Miller <davem@davemloft.net> wrote:
> Applied.
>
> I would suggest, as a follow-up patch, we add some appropriate
> prefixes to these new datastructures added to if_packet.h as
> these are exposed to userspace.
>
Sure.
> For example "hdr_v1", "bd_ts", "bd_header_u", and "block_desc" are
> just asking for namespace conflicts with something other API in
> userspace or the user's own datastructures.
>
Then just to be consistent, I will prefix it with 'tpacket'.
thanks
Chetan Loke
^ permalink raw reply
* Re: [RFC] per-containers tcp buffer limitation
From: Daniel Wagner @ 2011-08-25 12:55 UTC (permalink / raw)
To: Eric W. Biederman
Cc: Pavel Emelyanov, netdev-u79uwXL29TY76Z2rM5mHXA, Linux Containers,
David Miller
In-Reply-To: <m14o16qlq1.fsf-+imSwln9KH6u2/kzUuoCbdi2O/JbrIOy@public.gmane.org>
Hi
On 08/25/2011 04:16 AM, Eric W. Biederman wrote:
> KAMEZAWA Hiroyuki<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org> writes:
>
>> On Wed, 24 Aug 2011 22:28:59 -0300
>> Glauber Costa<glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org> wrote:
>>
>>> On 08/24/2011 09:35 PM, Eric W. Biederman wrote:
>>>> Glauber Costa<glommer-bzQdu9zFT3WakBO8gow8eQ@public.gmane.org> writes:
>>> Hi Eric,
>>>
>>> Thanks for your attention.
>>>
>>> So, this that you propose was my first implementation. I ended up
>>> throwing it away after playing with it for a while.
>>>
>>> One of the first problems that arise from that, is that the sysctls are
>>> a tunable visible from inside the container. Those limits, however, are
>>> to be set from the outside world. The code is not much better than that
>>> either, and instead of creating new cgroup structures and linking them
>>> to the protocol, we end up doing it for net ns. We end up increasing
>>> structures just the same...
>
> You don't need to add a netns member to sockets.
>
> But I do agree that there are odd permission issues with using the
> existing sysctls and making them per namespace.
>
> However almost everything I have seen with memory limits I have found
> very strange. They all seem like a very bad version of disabling memory
> over commits.
Please apply the same rules for not cursing my family no further then
the 3rd generation for my idea:
I'd like to solve a use case where it is necessary to count all bytes
transmitted and received by an application [1]. So far I have found two
unsatisfying solution for it. The first one is to hook into libc and
count the bytes there. I don't think I have to say I don't like this.
The second idea was to use the trick Google has used for Android [2].
They add a hook into __sock_sendmsg and __sock_recvmsg and then count
the bytes per UID. To get this working all application have to use an
unique UID. So not very nice either.
After reading a bit up on cgroup I think that would be the right place
to count the traffic. Unfortunately, with net_cls I can count the
outgoing traffic but not the incoming one. If I understood Glauber
approach correctly adding some statistic counters would be easy to do.
Of course I don't know the impact of this.
thanks,
daniel
[1]
http://lists.freedesktop.org/archives/systemd-devel/2011-August/003093.html
[2]
http://xf.iksaif.net/dev/android/android-2.6.29-to-2.6.32/0083-uidstat-Adding-uid-stat-driver-to-collect-network-st.patch
^ permalink raw reply
* [patch net-next-2.6] benet: remove bogus "unlikely" on vlan check
From: Jiri Pirko @ 2011-08-25 12:50 UTC (permalink / raw)
To: netdev
Cc: davem, eric.dumazet, sathya.perla, subbu.seetharaman,
ajit.khaparde, ivecera
Use of unlikely in this place is wrong. Remove it.
Signed-off-by: Jiri Pirko <jpirko@redhat.com>
---
drivers/net/ethernet/emulex/benet/be_main.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index fb2eda0..3d55b47 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1139,7 +1139,7 @@ static void be_rx_compl_process(struct be_adapter *adapter,
skb->rxhash = rxcp->rss_hash;
- if (unlikely(rxcp->vlanf))
+ if (rxcp->vlanf)
__vlan_hwaccel_put_tag(skb, rxcp->vlan_tag);
netif_receive_skb(skb);
@@ -1196,7 +1196,7 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter,
if (adapter->netdev->features & NETIF_F_RXHASH)
skb->rxhash = rxcp->rss_hash;
- if (unlikely(rxcp->vlanf))
+ if (rxcp->vlanf)
__vlan_hwaccel_put_tag(skb, rxcp->vlan_tag);
napi_gro_frags(&eq_obj->napi);
--
1.7.6
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox