<feed xmlns='http://www.w3.org/2005/Atom'>
<title>linux-toradex.git/net/openvswitch/datapath.c, branch v5.9-rc6</title>
<subtitle>Linux kernel for Apalis and Colibri modules</subtitle>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/'/>
<entry>
<title>net: openvswitch: introduce common code for flushing flows</title>
<updated>2020-08-13T22:53:30+00:00</updated>
<author>
<name>Tonghao Zhang</name>
<email>xiangxia.m.yue@gmail.com</email>
</author>
<published>2020-08-12T09:56:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=1f3a090b9033f69de380c03db3ea1a1015c850cf'/>
<id>1f3a090b9033f69de380c03db3ea1a1015c850cf</id>
<content type='text'>
To avoid some issues, for example RCU usage warning and double free,
we should flush the flows under ovs_lock. This patch refactors
table_instance_destroy and introduces table_instance_flow_flush
which can be invoked by __dp_destroy or ovs_flow_tbl_flush.

Fixes: 50b0e61b32ee ("net: openvswitch: fix possible memleak on destroy flow-table")
Reported-by: Johan Knöös &lt;jknoos@google.com&gt;
Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2020-August/050489.html
Signed-off-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Reviewed-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>
To avoid some issues, for example RCU usage warning and double free,
we should flush the flows under ovs_lock. This patch refactors
table_instance_destroy and introduces table_instance_flow_flush
which can be invoked by __dp_destroy or ovs_flow_tbl_flush.

Fixes: 50b0e61b32ee ("net: openvswitch: fix possible memleak on destroy flow-table")
Reported-by: Johan Knöös &lt;jknoos@google.com&gt;
Reported-at: https://mail.openvswitch.org/pipermail/ovs-discuss/2020-August/050489.html
Signed-off-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Reviewed-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: openvswitch: make masks cache size configurable</title>
<updated>2020-08-03T22:17:48+00:00</updated>
<author>
<name>Eelco Chaudron</name>
<email>echaudro@redhat.com</email>
</author>
<published>2020-07-31T12:21:34+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=9bf24f594c6acf676fb8c229f152c21bfb915ddb'/>
<id>9bf24f594c6acf676fb8c229f152c21bfb915ddb</id>
<content type='text'>
This patch makes the masks cache size configurable, or with
a size of 0, disable it.

Reviewed-by: Paolo Abeni &lt;pabeni@redhat.com&gt;
Reviewed-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.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 patch makes the masks cache size configurable, or with
a size of 0, disable it.

Reviewed-by: Paolo Abeni &lt;pabeni@redhat.com&gt;
Reviewed-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net: openvswitch: add masks cache hit counter</title>
<updated>2020-08-03T22:17:48+00:00</updated>
<author>
<name>Eelco Chaudron</name>
<email>echaudro@redhat.com</email>
</author>
<published>2020-07-31T12:20:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=9d2f627b7ec9d5d3246b6cec17f290ee6778c83b'/>
<id>9d2f627b7ec9d5d3246b6cec17f290ee6778c83b</id>
<content type='text'>
Add a counter that counts the number of masks cache hits, and
export it through the megaflow netlink statistics.

Reviewed-by: Paolo Abeni &lt;pabeni@redhat.com&gt;
Reviewed-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.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>
Add a counter that counts the number of masks cache hits, and
export it through the megaflow netlink statistics.

Reviewed-by: Paolo Abeni &lt;pabeni@redhat.com&gt;
Reviewed-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net: openvswitch: fixes potential deadlock in dp cleanup code</title>
<updated>2020-07-24T23:58:38+00:00</updated>
<author>
<name>Eelco Chaudron</name>
<email>echaudro@redhat.com</email>
</author>
<published>2020-07-24T08:20:59+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=a65878d6f00bb2d791348ae90dcc2ede1dbe2b91'/>
<id>a65878d6f00bb2d791348ae90dcc2ede1dbe2b91</id>
<content type='text'>
The previous patch introduced a deadlock, this patch fixes it by making
sure the work is canceled without holding the global ovs lock. This is
done by moving the reorder processing one layer up to the netns level.

Fixes: eac87c413bf9 ("net: openvswitch: reorder masks array based on usage")
Reported-by: syzbot+2c4ff3614695f75ce26c@syzkaller.appspotmail.com
Reported-by: syzbot+bad6507e5db05017b008@syzkaller.appspotmail.com
Reviewed-by: Paolo &lt;pabeni@redhat.com&gt;
Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.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 previous patch introduced a deadlock, this patch fixes it by making
sure the work is canceled without holding the global ovs lock. This is
done by moving the reorder processing one layer up to the netns level.

Fixes: eac87c413bf9 ("net: openvswitch: reorder masks array based on usage")
Reported-by: syzbot+2c4ff3614695f75ce26c@syzkaller.appspotmail.com
Reported-by: syzbot+bad6507e5db05017b008@syzkaller.appspotmail.com
Reviewed-by: Paolo &lt;pabeni@redhat.com&gt;
Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net: openvswitch: reorder masks array based on usage</title>
<updated>2020-07-17T17:36:50+00:00</updated>
<author>
<name>Eelco Chaudron</name>
<email>echaudro@redhat.com</email>
</author>
<published>2020-07-15T12:09:28+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=eac87c413bf9794c14d488998a5265ea5b32f04e'/>
<id>eac87c413bf9794c14d488998a5265ea5b32f04e</id>
<content type='text'>
This patch reorders the masks array every 4 seconds based on their
usage count. This greatly reduces the masks per packet hit, and
hence the overall performance. Especially in the OVS/OVN case for
OpenShift.

Here are some results from the OVS/OVN OpenShift test, which use
8 pods, each pod having 512 uperf connections, each connection
sends a 64-byte request and gets a 1024-byte response (TCP).
All uperf clients are on 1 worker node while all uperf servers are
on the other worker node.

Kernel without this patch     :  7.71 Gbps
Kernel with this patch applied: 14.52 Gbps

We also run some tests to verify the rebalance activity does not
lower the flow insertion rate, which does not.

Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.com&gt;
Tested-by: Andrew Theurer &lt;atheurer@redhat.com&gt;
Reviewed-by: Paolo Abeni &lt;pabeni@redhat.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 patch reorders the masks array every 4 seconds based on their
usage count. This greatly reduces the masks per packet hit, and
hence the overall performance. Especially in the OVS/OVN case for
OpenShift.

Here are some results from the OVS/OVN OpenShift test, which use
8 pods, each pod having 512 uperf connections, each connection
sends a 64-byte request and gets a 1024-byte response (TCP).
All uperf clients are on 1 worker node while all uperf servers are
on the other worker node.

Kernel without this patch     :  7.71 Gbps
Kernel with this patch applied: 14.52 Gbps

We also run some tests to verify the rebalance activity does not
lower the flow insertion rate, which does not.

Signed-off-by: Eelco Chaudron &lt;echaudro@redhat.com&gt;
Tested-by: Andrew Theurer &lt;atheurer@redhat.com&gt;
Reviewed-by: Paolo Abeni &lt;pabeni@redhat.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net: openvswitch: ovs_ct_exit to be done under ovs_lock</title>
<updated>2020-04-20T17:53:54+00:00</updated>
<author>
<name>Tonghao Zhang</name>
<email>xiangxia.m.yue@gmail.com</email>
</author>
<published>2020-04-16T18:57:31+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=27de77cec985233bdf6546437b9761853265c505'/>
<id>27de77cec985233bdf6546437b9761853265c505</id>
<content type='text'>
syzbot wrote:
| =============================
| WARNING: suspicious RCU usage
| 5.7.0-rc1+ #45 Not tainted
| -----------------------------
| net/openvswitch/conntrack.c:1898 RCU-list traversed in non-reader section!!
|
| other info that might help us debug this:
| rcu_scheduler_active = 2, debug_locks = 1
| ...
|
| stack backtrace:
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014
| Workqueue: netns cleanup_net
| Call Trace:
| ...
| ovs_ct_exit
| ovs_exit_net
| ops_exit_list.isra.7
| cleanup_net
| process_one_work
| worker_thread

To avoid that warning, invoke the ovs_ct_exit under ovs_lock and add
lockdep_ovsl_is_held as optional lockdep expression.

Link: https://lore.kernel.org/lkml/000000000000e642a905a0cbee6e@google.com
Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit")
Cc: Pravin B Shelar &lt;pshelar@ovn.org&gt;
Cc: Yi-Hung Wei &lt;yihung.wei@gmail.com&gt;
Reported-by: syzbot+7ef50afd3a211f879112@syzkaller.appspotmail.com
Signed-off-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Acked-by: Pravin B Shelar &lt;pshelar@ovn.org&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>
syzbot wrote:
| =============================
| WARNING: suspicious RCU usage
| 5.7.0-rc1+ #45 Not tainted
| -----------------------------
| net/openvswitch/conntrack.c:1898 RCU-list traversed in non-reader section!!
|
| other info that might help us debug this:
| rcu_scheduler_active = 2, debug_locks = 1
| ...
|
| stack backtrace:
| Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.0-0-ga698c8995f-prebuilt.qemu.org 04/01/2014
| Workqueue: netns cleanup_net
| Call Trace:
| ...
| ovs_ct_exit
| ovs_exit_net
| ops_exit_list.isra.7
| cleanup_net
| process_one_work
| worker_thread

To avoid that warning, invoke the ovs_ct_exit under ovs_lock and add
lockdep_ovsl_is_held as optional lockdep expression.

Link: https://lore.kernel.org/lkml/000000000000e642a905a0cbee6e@google.com
Fixes: 11efd5cb04a1 ("openvswitch: Support conntrack zone limit")
Cc: Pravin B Shelar &lt;pshelar@ovn.org&gt;
Cc: Yi-Hung Wei &lt;yihung.wei@gmail.com&gt;
Reported-by: syzbot+7ef50afd3a211f879112@syzkaller.appspotmail.com
Signed-off-by: Tonghao Zhang &lt;xiangxia.m.yue@gmail.com&gt;
Acked-by: Pravin B Shelar &lt;pshelar@ovn.org&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net: Fix typo of SKB_SGO_CB_OFFSET</title>
<updated>2020-03-30T04:53:18+00:00</updated>
<author>
<name>Cambda Zhu</name>
<email>cambda@linux.alibaba.com</email>
</author>
<published>2020-03-26T07:33:14+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=a08e7fd9123d85dfdf8d1dc61dbe321c8359d25f'/>
<id>a08e7fd9123d85dfdf8d1dc61dbe321c8359d25f</id>
<content type='text'>
The SKB_SGO_CB_OFFSET should be SKB_GSO_CB_OFFSET which means the
offset of the GSO in skb cb. This patch fixes the typo.

Fixes: 9207f9d45b0a ("net: preserve IP control block during GSO segmentation")
Signed-off-by: Cambda Zhu &lt;cambda@linux.alibaba.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 SKB_SGO_CB_OFFSET should be SKB_GSO_CB_OFFSET which means the
offset of the GSO in skb cb. This patch fixes the typo.

Fixes: 9207f9d45b0a ("net: preserve IP control block during GSO segmentation")
Signed-off-by: Cambda Zhu &lt;cambda@linux.alibaba.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>openvswitch: add missing attribute validation for hash</title>
<updated>2020-03-03T21:28:48+00:00</updated>
<author>
<name>Jakub Kicinski</name>
<email>kuba@kernel.org</email>
</author>
<published>2020-03-03T05:05:18+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=b5ab1f1be6180a2e975eede18731804b5164a05d'/>
<id>b5ab1f1be6180a2e975eede18731804b5164a05d</id>
<content type='text'>
Add missing attribute validation for OVS_PACKET_ATTR_HASH
to the netlink policy.

Fixes: bd1903b7c459 ("net: openvswitch: add hash info to upcall")
Signed-off-by: Jakub Kicinski &lt;kuba@kernel.org&gt;
Reviewed-by: Greg Rose &lt;gvrose8192@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>
Add missing attribute validation for OVS_PACKET_ATTR_HASH
to the netlink policy.

Fixes: bd1903b7c459 ("net: openvswitch: add hash info to upcall")
Signed-off-by: Jakub Kicinski &lt;kuba@kernel.org&gt;
Reviewed-by: Greg Rose &lt;gvrose8192@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>datapath.c: Use built-in RCU list checking</title>
<updated>2020-02-18T20:46:27+00:00</updated>
<author>
<name>Madhuparna Bhowmik</name>
<email>madhuparnabhowmik10@gmail.com</email>
</author>
<published>2020-02-18T19:58:02+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=53742e69e85d2eb7ed56f58d277bc3e682f8949e'/>
<id>53742e69e85d2eb7ed56f58d277bc3e682f8949e</id>
<content type='text'>
hlist_for_each_entry_rcu() has built-in RCU and lock checking.

Pass cond argument to list_for_each_entry_rcu() to silence
false lockdep warning when CONFIG_PROVE_RCU_LIST is enabled
by default.

Signed-off-by: Madhuparna Bhowmik &lt;madhuparnabhowmik10@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>
hlist_for_each_entry_rcu() has built-in RCU and lock checking.

Pass cond argument to list_for_each_entry_rcu() to silence
false lockdep warning when CONFIG_PROVE_RCU_LIST is enabled
by default.

Signed-off-by: Madhuparna Bhowmik &lt;madhuparnabhowmik10@gmail.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
<entry>
<title>net: openvswitch: use skb_list_walk_safe helper for gso segments</title>
<updated>2020-01-14T19:48:41+00:00</updated>
<author>
<name>Jason A. Donenfeld</name>
<email>Jason@zx2c4.com</email>
</author>
<published>2020-01-13T23:42:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.toradex.cn/cgit/linux-toradex.git/commit/?id=2cec4448db38758832c2edad439f99584bb8fa0d'/>
<id>2cec4448db38758832c2edad439f99584bb8fa0d</id>
<content type='text'>
This is a straight-forward conversion case for the new function, keeping
the flow of the existing code as intact as possible.

Signed-off-by: Jason A. Donenfeld &lt;Jason@zx2c4.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 is a straight-forward conversion case for the new function, keeping
the flow of the existing code as intact as possible.

Signed-off-by: Jason A. Donenfeld &lt;Jason@zx2c4.com&gt;
Signed-off-by: David S. Miller &lt;davem@davemloft.net&gt;
</pre>
</div>
</content>
</entry>
</feed>
