On 16-02-24 12:58 PM, Daniel Borkmann wrote:
On 02/24/2016 01:49 PM, Jamal Hadi Salim wrote:
Yes, a bit of that ++.
I am between two worlds: There are people who do user space packet
processing that claim they do so because they can quickly prototype
without compiling the kernel. My goal
On 16-02-24 12:48 PM, Daniel Borkmann wrote:
On 02/24/2016 01:49 PM, Jamal Hadi Salim wrote:
Drivers do set the hash. My use case is slightly different.
I have a NIC which has an embedded cavium processor. This thing
strips off the TLV and uses the hash to select the host MSI.
Only thing we
On 16-02-24 12:37 PM, Daniel Borkmann wrote:
On 02/23/2016 01:49 PM, Jamal Hadi Salim wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
[...]
+static const struct nla_policy ife_policy[TCA_IFE_MAX + 1] = {
+[TCA_IFE_PARMS] = {.len = sizeof(struct tc_ife)},
+[TCA_IFE_DMAC] =
On 16-02-24 12:21 PM, Cong Wang wrote:
On Wed, Feb 24, 2016 at 5:19 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
[..]
Did you mean something else or am i missing the obvious?
I am looking at the call sites for tcf_action_destroy():
-tc_dump_tfilter() has access to *net
-tcf_exts_
On 16-02-23 02:03 PM, John Fastabend wrote:
In the initial implementation the only way to stop a rule from being
inserted into the hardware table was via the device feature flag.
However this doesn't work well when working on an end host system
where packets are expect to hit both the hardware
into the core code and removes it from the
driver specific case.
Signed-off-by: John Fastabend <john.r.fastab...@intel.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
cheers,
jamal
in one function lift
the current check into a helper routine tc_should_offload().
Signed-off-by: John Fastabend <john.r.fastab...@intel.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
cheers,
jamal
On 16-02-23 05:23 PM, Cong Wang wrote:
On Tue, Feb 23, 2016 at 5:14 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
It doesnt seem neccessary to have hinfo in tc_action. Quick scan:
__tcf_hash_release() seems to be the only other place that uses it.
And the callers to that appear c
On 16-02-23 04:44 PM, Cong Wang wrote:
On Tue, Feb 23, 2016 at 4:49 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
+#define MODULE_ALIAS_IFE_META(metan) MODULE_ALIAS("ifemeta"
__stringify_1(metan))
+
+int get_meta_u32(struct sk_buff *skb, struct tcf_meta_info *mi);
+
On 16-02-23 11:12 AM, Daniel Borkmann wrote:
On 02/23/2016 03:39 PM, Jamal Hadi Salim wrote:
My question was rather: should the kernel enforce the IDs and only
allow what the kernel dictates (and not in/out of tree modules)? If
yes, then there would be no need for a module parameter
On 16-02-23 10:34 AM, Daniel Borkmann wrote:
On 02/23/2016 03:28 PM, Jamal Hadi Salim wrote:
[..]
These are basic metadata. The question to ask is what could one use
skb->hash for. Today it is used to select a cpu to balance to.
Right, but that happens before you decode that informat
On 16-02-24 12:46 AM, Simon Horman wrote:
On Tue, Feb 23, 2016 at 05:12:34PM +0100, Daniel Borkmann wrote:
From my point of view the test should be weather the encapsulation might
reasonably be expected to be used outside of the context of tc. If so then
it makes sense to use a netdev to
On 16-02-23 08:32 AM, Daniel Borkmann wrote:
On 02/23/2016 01:49 PM, Jamal Hadi Salim wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
This action allows for a sending side to encapsulate arbitrary metadata
which is decapsulated by the receiving end.
The sender runs in encodin
On 16-02-23 08:20 AM, Daniel Borkmann wrote:
On 02/23/2016 01:09 PM, Jamal Hadi Salim wrote:
On 16-02-22 11:47 AM, Daniel Borkmann wrote:
[...]
So, basically this is a L2 encap with TLVs, right?
And as TLVs you have skb->mark, skb->priority, skb->hash,
skb->queue_mapping
that
On 16-02-22 06:57 PM, Cong Wang wrote:
[..]
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 8c4e3ff..342be6c 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -7,6 +7,8 @@
#include
#include
+#include
+#include
struct tcf_common {
struct
netns in the latter patch.
Cc: Jamal Hadi Salim <j...@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
cheers,
jamal
From: Jamal Hadi Salim <j...@mojatatu.com>
Example usage:
Set the skb priority using skbedit then allow it to be encoded
sudo tc qdisc add dev $ETH root handle 1: prio
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flow
From: Jamal Hadi Salim <j...@mojatatu.com>
Example usage:
Set the skb using skbedit then allow it to be encoded
sudo tc qdisc add dev $ETH root handle 1: prio
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flowid 1:2 \
action skbedit mark 17 \
acti
From: Jamal Hadi Salim <j...@mojatatu.com>
This action allows for a sending side to encapsulate arbitrary metadata
which is decapsulated by the receiving end.
The sender runs in encoding mode and the receiver in decode mode.
Both sender and receiver must specify the same ethertype.
At some
From: Jamal Hadi Salim <j...@mojatatu.com>
hard code static value of 10 for qmap
mark of 12
prio of 13
and hashid of 11
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flowid 1:2 \
action ife encode \
type 0xDEAD \
use mark 12 \
use prio 13 \
use
From: Jamal Hadi Salim <j...@mojatatu.com>
As agreed at netconf in Seville, here's the patch finally (1 year
was just too long to wait).
Described in netdev01 paper:
"Distributing Linux Traffic Control Classifier-Action Subsystem"
Authors: Jamal Hadi Sal
From: Jamal Hadi Salim <j...@mojatatu.com>
Example usage:
allow skb hash to be encoded as metadata
sudo tc qdisc add dev $ETH root handle 1: prio
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flow
On 16-02-23 02:00 AM, Cong Wang wrote:
On Mon, Feb 22, 2016 at 5:21 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
As agreed at netconf in Seville, here's the patch finally (1 year
was just too long to wait).
Described in ne
On 16-02-22 04:03 PM, John Fastabend wrote:
On 16-02-22 05:21 AM, Jamal Hadi Salim wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
hard code static value of 10 for qmap
mark of 12
prio of 13
and hashid of 11
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip prot
Hi Daniel,
On 16-02-22 11:47 AM, Daniel Borkmann wrote:
Hi Jamal,
On 02/22/2016 02:21 PM, Jamal Hadi Salim wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
As agreed at netconf in Seville, here's the patch finally (1 year
was just too long to wait).
Described in netdev01
On 16-02-20 07:46 PM, Cong Wang wrote:
On Sat, Feb 20, 2016 at 10:36 AM, Daniel Borkmann wrote:
Do you see a way to reduce the code duplication needed across all
the action modules? I.e. that each of them now needs to register
a new per netns subsystem, etc. In other
From: Jamal Hadi Salim <j...@mojatatu.com>
Example usage:
Set the skb using skbedit then allow it to be encoded
sudo tc qdisc add dev $ETH root handle 1: prio
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flowid 1:2 \
action skbedit mark 17 \
acti
From: Jamal Hadi Salim <j...@mojatatu.com>
hard code static value of 10 for qmap
mark of 12
prio of 13
and hashid of 11
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flowid 1:2 \
action ife encode \
type 0xDEAD \
use mark 12 \
use prio 13 \
use
From: Jamal Hadi Salim <j...@mojatatu.com>
Example usage:
allow skb hash to be encoded as metadata
sudo tc qdisc add dev $ETH root handle 1: prio
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flow
From: Jamal Hadi Salim <j...@mojatatu.com>
Example usage:
Set the skb priority using skbedit then allow it to be encoded
sudo tc qdisc add dev $ETH root handle 1: prio
sudo tc filter add dev $ETH parent 1: protocol ip prio 10 \
u32 match ip protocol 1 0xff flow
From: Jamal Hadi Salim <j...@mojatatu.com>
This action allows for a sending side to encapsulate arbitrary metadata
which is decapsulated by the receiving end.
The sender runs in encoding mode and the receiver in decode mode.
Both sender and receiver must specify the same ethertype.
At some
From: Jamal Hadi Salim <j...@mojatatu.com>
As agreed at netconf in Seville, here's the patch finally (1 year
was just too long to wait).
Described in netdev01 paper:
"Distributing Linux Traffic Control Classifier-Action Subsystem"
Authors: Jamal Hadi Sal
On 16-02-18 10:24 AM, John Fastabend wrote:
On 16-02-18 04:14 AM, Jamal Hadi Salim wrote:
On 16-02-17 06:07 PM, John Fastabend wrote:
[...]
IMO, it would be better at this early stage to enforce the correct
behavior for future generations.
To follow the netlink semantics which a lot
From: Jamal Hadi Salim <j...@mojatatu.com>
Signed-off-by: Jamal Hadi Salim <j...@mojatatu.com>
---
net/sched/sch_api.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index af1acf0..de1e176 100644
--- a/net/sched/sch_api
From: Jamal Hadi Salim <j...@mojatatu.com>
actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
will ask for the packet to be reclassified. We then need to restart
the classification with the new proto
From: Jamal Hadi Salim <j...@mojatatu.com>
v3:
Cong says this needs to go to -net. And to put back the removed new line
v2:
Use Daniel's suggestion on when to set the skb proto
v1:
fix compile error found by build bot when CONFIG_NET_CLS_ACT was off
Jamal Hadi Salim (1):
net_sch
On 16-02-18 06:53 AM, Daniel Borkmann wrote:
On 02/17/2016 06:27 PM, Cong Wang wrote:
const struct tcf_proto *old_tp = tp;
int limit = 0;
-
Why remove this empty line? I think it is still useful. :)
Also your patch should be targeted to -net instead of -net-next, since it
On 16-02-17 06:07 PM, John Fastabend wrote:
[...]
Actually thinking about this a bit more I wrote this thinking
that there existed some hardware that actually cared if it was
a new rule or an existing rule. For me it doesn't matter I do
the same thing in the new/replace cases I just write
On 16-02-17 06:19 AM, Jamal Hadi Salim wrote:
Thats how the original code was (and what i tested). I dont have time
to test right now but i will send an update with your suggestion.
My setup was still running so I managed to test it with IFE
cheers,
jamal
x that NEW with REPLACE
in patch 3.
For this patch:
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
cheers,
jamal
From: Jamal Hadi Salim <j...@mojatatu.com>
v2:
Use Daniel's suggestion on when to set the skb proto
v1:
fix compile error found by build bot when CONFIG_NET_CLS_ACT was off
Jamal Hadi Salim (1):
net_sched fix: reclassification needs to consider ether protocol
changes
net/sched/sch
From: Jamal Hadi Salim <j...@mojatatu.com>
actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
will ask for the packet to be reclassified. We then need to restart
the classification with the new proto
On 16-02-16 10:20 AM, Daniel Borkmann wrote:
On 02/16/2016 01:37 PM, Jamal Hadi Salim wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
wi
On 16-02-17 12:18 AM, John Fastabend wrote:
This adds initial support for offloading the u32 tc classifier. This
initial implementation only implements a few base matches and actions
to illustrate the use of the infrastructure patches.
However it is an interesting subset because it handles the
u32. I think most of unsigned ints should be u32.
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
tab...@intel.com>
Acked-by: Jiri Pirko <j...@mellanox.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
On 16-02-17 12:18 AM, John Fastabend wrote:
This is a helper function drivers can use to learn if the
action type is a drop action.
Signed-off-by: John Fastabend <john.r.fastab...@intel.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
cheers,
jamal
On 16-02-17 12:17 AM, John Fastabend wrote:
This patch allows netdev drivers to consume cls_u32 offloads via
the ndo_setup_tc ndo op.
This works aligns with how network drivers have been doing qdisc
offloads for mqprio.
This one i have comments on.
Signed-off-by: John Fastabend
ndo ops or grow the signature of the
callback.
Signed-off-by: John Fastabend <john.r.fastab...@intel.com>
Acked-by: Jiri Pirko <j...@mellanox.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
com>
CC: Jeff Kirsher <jeffrey.t.kirs...@intel.com>
CC: Bruce Allan <bruce.w.al...@intel.com>
CC: Jesse Brandeburg <jesse.brandeb...@intel.com>
CC: Don Skidmore <donald.c.skidm...@intel.com>
Signed-off-by: John Fastabend <john.r.fastab...@intel.com>
Acked-by: Jiri Pir
From: Jamal Hadi Salim <j...@mojatatu.com>
actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
will ask for the packet to be reclassified. We then need to restart
the classification with the new proto
On 16-02-15 03:59 PM, Daniel Borkmann wrote:
On 02/15/2016 08:49 PM, Jamal Hadi Salim wrote:
From: Jamal Hadi Salim <j...@mojatatu.com>
actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
wi
From: Jamal Hadi Salim <j...@mojatatu.com>
actions could change the etherproto in particular with ethernet
tunnelled data. Typically such actions, after peeling the outer header,
will ask for the packet to be reclassified. We then need to restart
the classification with the new proto
On 16-02-09 03:40 AM, David Miller wrote:
From: Eric Dumazet
Date: Mon, 08 Feb 2016 14:57:40 -0800
Whole point of TLV is that it allows us to add new fields at the end of
the structures.
...
Look at iproute2, you were the one adding in 2004 code to cope with
On 16-02-09 06:24 AM, Fastabend, John R wrote:
On 2/4/2016 5:12 AM, Jamal Hadi Salim wrote:
On 16-02-03 01:48 PM, Fastabend, John R wrote:
Basically most hardware (or i should say driver implementations of
mostly TCAMS) allow you to add exactly the same filter as many times
as you want
On 16-02-03 01:48 PM, Fastabend, John R wrote:
BTW: For the record John, I empathize with you that we need to
move. Please have patience - we are close; lets just get this resolved
in Seville. I like your patches a lot and would love to just have
your patches pushed in, but the challenges with
On 16-02-03 05:26 AM, John Fastabend wrote:
On 16-02-03 02:07 AM, Amir Vadai" wrote:
On Wed, Feb 03, 2016 at 01:29:59AM -0800, John Fastabend wrote:
This adds initial support for offloading the u32 tc classifier. This
initial implementation only implements a few base matches and actions
to
On 16-02-03 05:31 AM, Or Gerlitz wrote:
On 2/3/2016 12:21 PM, John Fastabend wrote:
Thanks, we will need at least a v2 to fixup some build errors
with various compile flags caught by build_bot and missed by me.
Hi John,
You didn't mark that as RFC... but we said this direction/approach yet
to
Sorry for not being as responsive as i would like to be
(theman calls and i have to go).
This looks like a good (tc workshop) candidate discussion, if still
active by netdev11 time.
On 15-12-30 12:50 PM, John Fastabend wrote:
Hi,
This is a first take at removing the qdisc lock on the xmit
On 15-12-16 10:50 AM, Eric Dumazet wrote:
On Wed, 2015-12-16 at 07:43 -0800, Stephen Hemminger wrote:
I see no security checks in the diag infrastructure.
Up until now diag has been read-only access and therefore has been
allowed for all users.
It is still allowed to all users.
Only the
Hi Igor,
On 15-12-11 04:55 AM, Igor Gavrilov wrote:
Improved CTTUPLE macro with code from sched/act_connmark.c, so it be
able to get unNATed addresses from nf_conntrack.
1) Question: Have you tested the patch or you just cutnpasted
from connmark.c? By inspection the patch looks ok
On 15-12-08 02:33 AM, John Fastabend wrote:
On 15-12-02 04:15 PM, Tom Herbert wrote:
Just keying off the last statement there...
I think BPF programs are going to be hard to translate into hardware
for most devices. The problem is the BPF programs in general lack
structure. A parse graph
On 15-12-08 09:23 AM, Jamal Hadi Salim wrote:
On 15-12-08 02:33 AM, John Fastabend wrote:
;-> I feel a little vindicated with this discussion.
Of course you can implement hardware using BPF!
BTW - Just to be clear; I am not arguing for what that paper
preaches. What the paper preac
On 10/15/15 00:32, Cong Wang wrote:
On Wed, Oct 14, 2015 at 5:11 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
On 10/12/15 14:38, Cong Wang wrote:
When the bottom qdisc decides to, for example, drop some packet,
it calls qdisc_tree_decrease_qlen() to update the queue length
for a
On 10/15/15 00:15, Cong Wang wrote:
On Wed, Oct 14, 2015 at 4:56 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
On 10/12/15 14:38, Cong Wang wrote:
Remove nearly duplicated code and prepare for the following patch.
Cong - like Dave, I dont see equivalence in some of these
c
On 10/15/15 00:21, Cong Wang wrote:
On Wed, Oct 14, 2015 at 5:25 AM, Jamal Hadi Salim <j...@mojatatu.com> wrote:
On 10/12/15 14:38, Cong Wang wrote:
It is odd to see qlen!=0 but backlog==0, for a real example:
Backlog is a transient stat so a lot of times it should be 0. Only when
t
On 10/12/15 14:38, Cong Wang wrote:
Remove nearly duplicated code and prepare for the following patch.
Cong - like Dave, I dont see equivalence in some of these
changes.
Example not sure how the qfq grafting invocation of
qfq_purge_queue fits in. There are a few others.
cheers,
jamal
--
On 10/12/15 14:38, Cong Wang wrote:
When the bottom qdisc decides to, for example, drop some packet,
it calls qdisc_tree_decrease_qlen() to update the queue length
for all its ancestors, we need to update the backlog too to
keep the stats on root qdisc accurate.
There is more than one change
, overlimits 123575834
requeues 0)
backlog 0b 72p requeues 0
So we need to update backlog too when we update qlen.
Cc: Jamal Hadi Salim <j...@mojatatu.com>
Signed-off-by: Cong Wang <cw...@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com>
---
--
To unsubscribe fr
Never mind. Mirred is speacial because it points to other netdevs.
So:
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
Thanks Cong.
cheers,
jamal
On 10/05/15 07:58, Jamal Hadi Salim wrote:
Hi Cong,
I am wondering if making the bindcount or refcount atomic would help?
How does this b
Hi Cong,
I am wondering if making the bindcount or refcount atomic would help?
How does this bug get created? i.e the RTNL is still around.
Why is this specific to mirred only?
cheers,
jamal
On 10/01/15 14:37, Cong Wang wrote:
After commit 1ce87720d456 ("net: sched: make cls_u32 lockless")
On 10/01/15 14:37, Cong Wang wrote:
Align with other tc actions.
Cc: Jamal Hadi Salim <j...@mojatatu.com>
Signed-off-by: Cong Wang <cw...@twopensource.com>
Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
cheers,
jama
tp->root allocation into fw_init()")
Reported-by: Akshat Kakkar <akshat.1...@gmail.com>
Cc: Jamal Hadi Salim <j...@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com>
Acked-by: Jamal Hadi Salim <j...@mojatatu.com>
--
To unsubscribe from this
Hi Daniel,
On 09/17/15 09:13, Daniel Borkmann wrote:
Hmm, I don't really agree. With cls_bpf you have non-linear
classifications as opposed to walking a chain of classifiers:
A chain of classifiers is a better description today (non-linear would
be an appropriate description before cls_bpf
On 09/17/15 11:19, Alexei Starovoitov wrote:
misread as bpf program now executes the actions and bypasses
tcf_exts_exec() ? Well, that may be interesting idea for
the future,
And above is precisely why i raised the concern. You are already
bypassing tcf_exts_exec with that patch. It is a big
On 09/14/15 18:04, Cong Wang wrote:
That is exactly the original code. But it is not readable at all,
at least I still missed it when I touched the tp->init() part. :(
Having a boolean doesn't harm anything.
The default should really be no head alloced (given that is the
main use case).
The
On 09/16/15 02:05, Alexei Starovoitov wrote:
From: Daniel Borkmann
Often cls_bpf classifier is used with single action drop attached.
Optimize this use case and let cls_bpf return both classid and action.
For backwards compatibility reasons enable this feature under
On 09/11/15 20:00, Cong Wang wrote:
On Fri, Sep 11, 2015 at 3:24 PM, Akshat Kakkar wrote:
Hmm, I didn't know that before either. Looks like my tp->init change
breaks it.
Could you try the following patch?
I would just make init() empty for this classifier (return
On 09/02/15 02:22, Cong Wang wrote:
(Why not Cc'ing Jamal for net_sched pathes?)
On Tue, Sep 1, 2015 at 9:34 AM, Daniel Borkmann wrote:
From: John Fastabend
Add a new ->preclassify() op to allow multiqueue queuing disciplines
to call
On 08/28/15 19:20, David Miller wrote:
But HTB definitely should be allowed.
Problem with most non-work conserving schedulers is what the meaning
of default resources means; example, for HTB:
What is the default bandwidth you allocate to a class of users?
cheers,
jamal
--
To unsubscribe
On 08/28/15 00:23, David Miller wrote:
If a default qdisc like HTB is choosen, we invoke the -init() function
and we change the HTB -init() function to do something reasonable
if a NULL set of configuration attributes is given. ie. make HTB use
some defaults.
That may work. Or to reduce
] http://thread.gmane.org/gmane.linux.network/321960/
Reported-by: Jamal Hadi Salim j...@mojatatu.com
Signed-off-by: Daniel Borkmann dan...@iogearbox.net
Cc: Michael Tuexen tue...@fh-muenster.de
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe from this list: send
On 07/20/15 15:40, Alex Gartrell wrote:
We have an application that invokes tc to delete the root every time the
config changes. As a result we stress the cleanup code and were seeing the
following panic:
crash bt
PID: 630839 TASK: 8823c990d280 CPU: 14 COMMAND: tc
[... snip
On 07/14/15 06:29, Daniel Borkmann wrote:
On 07/14/2015 12:26 AM, Alexei Starovoitov wrote:
On 7/13/15 1:55 PM, Daniel Borkmann wrote:
On 07/13/2015 10:17 PM, Alexei Starovoitov wrote:
...
We cannot check tc actions from pktgen, since they can be added
dynamically.
So I see three options:
1
On 07/10/15 20:10, Alexei Starovoitov wrote:
TC actions need to check for very unlikely event skb-users != 1,
otherwise subsequent pskb_may_pull/pskb_expand_head will crash.
When skb_shared() just drop the packet, since in the middle of actions
it's too late to call skb_share_check(), since
In the newer kernels this message is extremely noisy. After a quick
discussion with Daniel it seems to me it will be very hard to get
existing apps that nobody is going to update to continue to work
(i.e no forward compat). And newer apps that desire to play in both
older kernels and new
before/after the change?
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On 07/06/15 02:41, Eric Dumazet wrote:
As mentioned by Alexei last week in Budapest, it is a bit weird
to take a spinlock in order to drop a packet in a tc filter...
Lets add percpu infra for tc actions and use it for gact mirred.
Before changes, my host with 8 RX queues was handling 5 Mpps
queue capability to ifb device
Signed-off-by: Eric Dumazet eduma...@google.com
Looks good to me ;-
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cant wait for the multi queue ifb.
cheers,
jamal
--
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to majord
() is renamed to qdisc_qstats_cpu_drop()
Signed-off-by: Eric Dumazet eduma...@google.com
Cc: Alexei Starovoitov a...@plumgrid.com
Cc: Jamal Hadi Salim j...@mojatatu.com
Cc: John Fastabend john.fastab...@gmail.com
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe from
On 07/02/15 09:07, Eric Dumazet wrote:
First step for gact RCU operation :
Instead of testing if tcfg_pval is zero or not, just make it 1.
No change in behavior, but slightly faster code.
Signed-off-by: Eric Dumazet eduma...@google.com
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers
-by: Eric Dumazet eduma...@google.com
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
On 07/02/15 09:07, Eric Dumazet wrote:
Third step for gact RCU operation :
Following patch will get rid of spinlock protection,
so we need to read tcfg_ptype once.
Signed-off-by: Eric Dumazet eduma...@google.com
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe
, vlan and skbedit.
CCing the respective authors.
Signed-off-by: Eric Dumazet eduma...@google.com
Cc: Alexei Starovoitov a...@plumgrid.com
Cc: Jamal Hadi Salim j...@mojatatu.com
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe from this list: send the line
On 07/02/15 16:59, Eric Dumazet wrote:
On Thu, 2015-07-02 at 09:35 -0700, John Fastabend wrote:
Point is to not dirty cache line for every packet ?
Doing the test means we attempt dirtying only ~HZ times per second,
which really matters to handle millions of packets per second.
My tests
-by: Eric Dumazet eduma...@google.com
Acked-by: Jamal Hadi Salim j...@mojatatu.com
cheers,
jamal
--
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Trying to catchup with email and i am noticing my last
received email was on the 21st. Anyone else having problems
(feel like i am asking the question if you cant hear me
please raise your hand ;-).
cheers,
jamal
--
To unsubscribe from this list: send the line unsubscribe netdev in
the body of
From: Jamal Hadi Salim h...@mojatatu.com
Fix typo in the validation rules for flower's attributes
Signed-off-by: Jamal Hadi Salim j...@mojatatu.com
---
net/sched/cls_flower.c |4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/net/sched/cls_flower.c b/net/sched
On 06/25/15 08:03, David Miller wrote:
I'm pretty sure you're just not subscribed to the list.
I never unsubscribed. Ive resubscribed.
cheers,
jamal
--
To unsubscribe from this list: send the line unsubscribe netdev in
the body of a message to majord...@vger.kernel.org
More majordomo info
On 06/16/15 17:11, Jiri Pirko wrote:
Tue, Jun 16, 2015 at 06:47:47PM CEST, sfel...@gmail.com wrote:
On Mon, Jun 15, 2015 at 11:04 PM, Jiri Pirko j...@resnulli.us wrote:
So what we need is a unique mark for device ports within a fwding
group, such as a bridge.
Yep, have a group of netdevs,
901 - 1000 of 1060 matches
Mail list logo