<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux.git/net/sched/act_sample.c, branch v4.15</title>
<subtitle>Linux kernel source tree</subtitle>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/'/>
<entry>
<title>act_sample: get rid of tcf_sample_cleanup_rcu()</title>
<updated>2017-11-30T15:19:17+00:00</updated>
<author>
<name>Cong Wang</name>
<email>xiyou.wangcong@gmail.com</email>
</author>
<published>2017-11-30T00:07:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=90a6ec85351b31449c2c6b5406b5396ac96f191d'/>
<id>90a6ec85351b31449c2c6b5406b5396ac96f191d</id>
<content type='text'>
Similar to commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu"),
TC actions don't need to respect RCU grace period, because it
is either just detached from tc filter (standalone case) or
it is removed together with tc filter (bound case) in which case
RCU grace period is already respected at filter layer.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Reported-by: Eric Dumazet &lt;eric.dumazet@gmail.com&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Cc: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Reviewed-by: Eric Dumazet &lt;edumazet@google.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Similar to commit d7fb60b9cafb ("net_sched: get rid of tcfa_rcu"),
TC actions don't need to respect RCU grace period, because it
is either just detached from tc filter (standalone case) or
it is removed together with tc filter (bound case) in which case
RCU grace period is already respected at filter layer.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Reported-by: Eric Dumazet &lt;eric.dumazet@gmail.com&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Cc: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Reviewed-by: Eric Dumazet &lt;edumazet@google.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>Revert "net_sched: hold netns refcnt for each action"</title>
<updated>2017-11-09T01:03:09+00:00</updated>
<author>
<name>Cong Wang</name>
<email>xiyou.wangcong@gmail.com</email>
</author>
<published>2017-11-06T21:47:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=c7e460ce55724d4e4e22d3126e5c47273819c53a'/>
<id>c7e460ce55724d4e4e22d3126e5c47273819c53a</id>
<content type='text'>
This reverts commit ceffcc5e254b450e6159f173e4538215cebf1b59.
If we hold that refcnt, the netns can never be destroyed until
all actions are destroyed by user, this breaks our netns design
which we expect all actions are destroyed when we destroy the
whole netns.

Cc: Lucas Bates &lt;lucasb@mojatatu.com&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This reverts commit ceffcc5e254b450e6159f173e4538215cebf1b59.
If we hold that refcnt, the netns can never be destroyed until
all actions are destroyed by user, this breaks our netns design
which we expect all actions are destroyed when we destroy the
whole netns.

Cc: Lucas Bates &lt;lucasb@mojatatu.com&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net_sched: hold netns refcnt for each action</title>
<updated>2017-11-03T01:30:38+00:00</updated>
<author>
<name>Cong Wang</name>
<email>xiyou.wangcong@gmail.com</email>
</author>
<published>2017-11-01T17:23:50+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=ceffcc5e254b450e6159f173e4538215cebf1b59'/>
<id>ceffcc5e254b450e6159f173e4538215cebf1b59</id>
<content type='text'>
TC actions have been destroyed asynchronously for a long time,
previously in a RCU callback and now in a workqueue. If we
don't hold a refcnt for its netns, we could use the per netns
data structure, struct tcf_idrinfo, after it has been freed by
netns workqueue.

Hold refcnt to ensure netns destroy happens after all actions
are gone.

Fixes: ddf97ccdd7cb ("net_sched: add network namespace support for tc actions")
Reported-by: Lucas Bates &lt;lucasb@mojatatu.com&gt;
Tested-by: Lucas Bates &lt;lucasb@mojatatu.com&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
TC actions have been destroyed asynchronously for a long time,
previously in a RCU callback and now in a workqueue. If we
don't hold a refcnt for its netns, we could use the per netns
data structure, struct tcf_idrinfo, after it has been freed by
netns workqueue.

Hold refcnt to ensure netns destroy happens after all actions
are gone.

Fixes: ddf97ccdd7cb ("net_sched: add network namespace support for tc actions")
Reported-by: Lucas Bates &lt;lucasb@mojatatu.com&gt;
Tested-by: Lucas Bates &lt;lucasb@mojatatu.com&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>MAINTAINERS: Update Yotam's E-mail</title>
<updated>2017-11-01T03:19:03+00:00</updated>
<author>
<name>Yotam Gigi</name>
<email>yotam.gi@gmail.com</email>
</author>
<published>2017-10-30T09:41:36+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=f1fd20c36181f526ed2fbd0707b6957f907ee64b'/>
<id>f1fd20c36181f526ed2fbd0707b6957f907ee64b</id>
<content type='text'>
For the time being I will be available in my private mail. Update both the
MAINTAINERS file and the individual modules MODULE_AUTHOR directive with
the new address.

Signed-off-by: Yotam Gigi &lt;yotam.gi@gmail.com&gt;
Signed-off-by: Yuval Mintz &lt;yuvalm@mellanox.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
For the time being I will be available in my private mail. Update both the
MAINTAINERS file and the individual modules MODULE_AUTHOR directive with
the new address.

Signed-off-by: Yotam Gigi &lt;yotam.gi@gmail.com&gt;
Signed-off-by: Yuval Mintz &lt;yuvalm@mellanox.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net_sched: fix call_rcu() race on act_sample module removal</title>
<updated>2017-10-29T13:49:31+00:00</updated>
<author>
<name>Cong Wang</name>
<email>xiyou.wangcong@gmail.com</email>
</author>
<published>2017-10-27T01:24:41+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=46e235c15ca44f34cb79f4dbec909b8c51999dc1'/>
<id>46e235c15ca44f34cb79f4dbec909b8c51999dc1</id>
<content type='text'>
Similar to commit c78e1746d3ad
("net: sched: fix call_rcu() race on classifier module unloads"),
we need to wait for flying RCU callback tcf_sample_cleanup_rcu().

Cc: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Cc: Daniel Borkmann &lt;daniel@iogearbox.net&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: "Paul E. McKenney" &lt;paulmck@linux.vnet.ibm.com&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Similar to commit c78e1746d3ad
("net: sched: fix call_rcu() race on classifier module unloads"),
we need to wait for flying RCU callback tcf_sample_cleanup_rcu().

Cc: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Cc: Daniel Borkmann &lt;daniel@iogearbox.net&gt;
Cc: Jiri Pirko &lt;jiri@resnulli.us&gt;
Cc: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Cc: "Paul E. McKenney" &lt;paulmck@linux.vnet.ibm.com&gt;
Signed-off-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net/sched: Change act_api and act_xxx modules to use IDR</title>
<updated>2017-08-30T21:38:51+00:00</updated>
<author>
<name>Chris Mi</name>
<email>chrism@mellanox.com</email>
</author>
<published>2017-08-30T06:31:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=65a206c01e8e7ffe971477a36419422099216eff'/>
<id>65a206c01e8e7ffe971477a36419422099216eff</id>
<content type='text'>
Typically, each TC filter has its own action. All the actions of the
same type are saved in its hash table. But the hash buckets are too
small that it degrades to a list. And the performance is greatly
affected. For example, it takes about 0m11.914s to insert 64K rules.
If we convert the hash table to IDR, it only takes about 0m1.500s.
The improvement is huge.

But please note that the test result is based on previous patch that
cls_flower uses IDR.

Signed-off-by: Chris Mi &lt;chrism@mellanox.com&gt;
Signed-off-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Acked-by: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Typically, each TC filter has its own action. All the actions of the
same type are saved in its hash table. But the hash buckets are too
small that it degrades to a list. And the performance is greatly
affected. For example, it takes about 0m11.914s to insert 64K rules.
If we convert the hash table to IDR, it only takes about 0m1.500s.
The improvement is huge.

But please note that the test result is based on previous patch that
cls_flower uses IDR.

Signed-off-by: Chris Mi &lt;chrism@mellanox.com&gt;
Signed-off-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Acked-by: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>netlink: pass extended ACK struct to parsing functions</title>
<updated>2017-04-13T17:58:22+00:00</updated>
<author>
<name>Johannes Berg</name>
<email>johannes.berg@intel.com</email>
</author>
<published>2017-04-12T12:34:07+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=fceb6435e85298f747fee938415057af837f5a8a'/>
<id>fceb6435e85298f747fee938415057af837f5a8a</id>
<content type='text'>
Pass the new extended ACK reporting struct to all of the generic
netlink parsing functions. For now, pass NULL in almost all callers
(except for some in the core.)

Signed-off-by: Johannes Berg &lt;johannes.berg@intel.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Pass the new extended ACK reporting struct to all of the generic
netlink parsing functions. For now, pass NULL in almost all callers
(except for some in the core.)

Signed-off-by: Johannes Berg &lt;johannes.berg@intel.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net/sched: act_psample: Remove unnecessary ASSERT_RTNL</title>
<updated>2017-02-01T19:10:03+00:00</updated>
<author>
<name>Yotam Gigi</name>
<email>yotamg@mellanox.com</email>
</author>
<published>2017-01-31T09:33:54+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=f3b20313aef93f9cfda76fec2c05625f88510f18'/>
<id>f3b20313aef93f9cfda76fec2c05625f88510f18</id>
<content type='text'>
The ASSERT_RTNL is not necessary in the init function, as it does not
touch any rtnl protected structures, as opposed to the mirred action which
does have to hold a net device.

Reported-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Reviewed-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Signed-off-by: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The ASSERT_RTNL is not necessary in the init function, as it does not
touch any rtnl protected structures, as opposed to the mirred action which
does have to hold a net device.

Reported-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Reviewed-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Signed-off-by: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net/sched: act_sample: Fix error path in init</title>
<updated>2017-02-01T19:10:03+00:00</updated>
<author>
<name>Yotam Gigi</name>
<email>yotamg@mellanox.com</email>
</author>
<published>2017-01-31T09:33:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=cadb9c9fdbc6a624d57b5ecdfd412b5800848703'/>
<id>cadb9c9fdbc6a624d57b5ecdfd412b5800848703</id>
<content type='text'>
Fix error path of in sample init, by releasing the tc hash in case of
failure in psample_group creation.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Reported-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Reviewed-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Signed-off-by: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Fix error path of in sample init, by releasing the tc hash in case of
failure in psample_group creation.

Fixes: 5c5670fae430 ("net/sched: Introduce sample tc action")
Reported-by: Cong Wang &lt;xiyou.wangcong@gmail.com&gt;
Reviewed-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Signed-off-by: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net/sched: Introduce sample tc action</title>
<updated>2017-01-24T18:44:28+00:00</updated>
<author>
<name>Yotam Gigi</name>
<email>yotamg@mellanox.com</email>
</author>
<published>2017-01-23T10:07:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.tavy.me/linux.git/commit/?id=5c5670fae43027778e84b9d9ff3b9d91a10a8131'/>
<id>5c5670fae43027778e84b9d9ff3b9d91a10a8131</id>
<content type='text'>
This action allows the user to sample traffic matched by tc classifier.
The sampling consists of choosing packets randomly and sampling them using
the psample module. The user can configure the psample group number, the
sampling rate and the packet's truncation (to save kernel-user traffic).

Example:
To sample ingress traffic from interface eth1, one may use the commands:

tc qdisc add dev eth1 handle ffff: ingress

tc filter add dev eth1 parent ffff: \
	   matchall action sample rate 12 group 4

Where the first command adds an ingress qdisc and the second starts
sampling randomly with an average of one sampled packet per 12 packets on
dev eth1 to psample group 4.

Signed-off-by: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Acked-by: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Reviewed-by: Simon Horman &lt;simon.horman@netronome.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
This action allows the user to sample traffic matched by tc classifier.
The sampling consists of choosing packets randomly and sampling them using
the psample module. The user can configure the psample group number, the
sampling rate and the packet's truncation (to save kernel-user traffic).

Example:
To sample ingress traffic from interface eth1, one may use the commands:

tc qdisc add dev eth1 handle ffff: ingress

tc filter add dev eth1 parent ffff: \
	   matchall action sample rate 12 group 4

Where the first command adds an ingress qdisc and the second starts
sampling randomly with an average of one sampled packet per 12 packets on
dev eth1 to psample group 4.

Signed-off-by: Yotam Gigi &lt;yotamg@mellanox.com&gt;
Signed-off-by: Jiri Pirko &lt;jiri@mellanox.com&gt;
Acked-by: Jamal Hadi Salim &lt;jhs@mojatatu.com&gt;
Reviewed-by: Simon Horman &lt;simon.horman@netronome.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
</feed>
