[ovs-dev] [PATCH net v2] openvswitch: meter: fix race when getting now_ms.

We have observed meters working unexpected if traffic is 3+Gbit/s
with multiple connections.

now_ms is not pretected by meter->lock, we may get a negative
long_delta_ms when another cpu updated meter->used, then:
    delta_ms = (u32)long_delta_ms;
which will be a large value.

    band->bucket += delta_ms * band->rate;
then we get a wrong band->bucket.

OpenVswitch userspace datapath has fixed the same issue[1] some
time ago, and we port the implementation to kernel datapath.

[1] https://patchwork.ozlabs.org/project/openvswitch/patch/20191025114436.9746-1-i.maximets@ovn.org/

Fixes: 96fbc13d7e77 ("openvswitch: Add meter infrastructure")
Signed-off-by: Tao Liu <redacted>
Suggested-by: Ilya Maximets <i.maximets@ovn.org>
---
Changelog:
v2: just set negative long_delta_ms to zero in case of race for meter lock.
v1: make now_ms protected by meter lock.
---
 net/openvswitch/meter.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c
index 96b524c..896b8f5 100644
--- a/net/openvswitch/meter.c
+++ b/net/openvswitch/meter.c

@@ -611,6 +611,14 @@ bool ovs_meter_execute(struct datapath *dp, struct sk_buff *skb,
 	spin_lock(&meter->lock);
 
 	long_delta_ms = (now_ms - meter->used); /* ms */
+	if (long_delta_ms < 0) {
+		/* This condition means that we have several threads fighting
+		 * for a meter lock, and the one who received the packets a
+		 * bit later wins. Assuming that all racing threads received
+		 * packets at the same time to avoid overflow.
+		 */
+		long_delta_ms = 0;
+	}
 
 	/* Make sure delta_ms will not be too large, so that bucket will not
 	 * wrap around below.

-- 
1.8.3.1

On 5/13/21 3:08 PM, Tao Liu wrote:

We have observed meters working unexpected if traffic is 3+Gbit/s
with multiple connections.

now_ms is not pretected by meter->lock, we may get a negative
long_delta_ms when another cpu updated meter->used, then:
    delta_ms = (u32)long_delta_ms;
which will be a large value.

    band->bucket += delta_ms * band->rate;
then we get a wrong band->bucket.

OpenVswitch userspace datapath has fixed the same issue[1] some
time ago, and we port the implementation to kernel datapath.

[1] https://patchwork.ozlabs.org/project/openvswitch/patch/20191025114436.9746-1-i.maximets@ovn.org/

Fixes: 96fbc13d7e77 ("openvswitch: Add meter infrastructure")
Signed-off-by: Tao Liu <redacted>
Suggested-by: Ilya Maximets <i.maximets@ovn.org>
---
Changelog:
v2: just set negative long_delta_ms to zero in case of race for meter lock.
v1: make now_ms protected by meter lock.
---

Thanks!
I didn't test it, but the change looks good to me.

Reviewed-by: Ilya Maximets <i.maximets@ovn.org>

Hello:

This patch was applied to netdev/net.git (refs/heads/master):

On Thu, 13 May 2021 21:08:00 +0800 you wrote:

We have observed meters working unexpected if traffic is 3+Gbit/s
with multiple connections.

now_ms is not pretected by meter->lock, we may get a negative
long_delta_ms when another cpu updated meter->used, then:
    delta_ms = (u32)long_delta_ms;
which will be a large value.

[...]

Here is the summary with links:
  - [ovs-dev,net,v2] openvswitch: meter: fix race when getting now_ms.
    https://git.kernel.org/netdev/net/c/e4df1b0c2435

You are awesome, thank you!
--
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html