[PATCH net-net] openvswitch: Optimize operation for key comparison

From: Baowen Zheng <redacted>

In the current implement when comparing two flow keys, we will return
result after comparing the whole key from start to end.

In our optimization, we will return result in the first none-zero
comparison, then we will improve the flow table looking up efficiency.

Signed-off-by: Baowen Zheng <redacted>
Signed-off-by: Louis Peens <redacted>
Signed-off-by: Simon Horman <redacted>
---
 net/openvswitch/flow_table.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index c89c8da99f1a..d4a2db0b2299 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c

@@ -670,13 +670,13 @@ static bool cmp_key(const struct sw_flow_key *key1,
 {
 	const long *cp1 = (const long *)((const u8 *)key1 + key_start);
 	const long *cp2 = (const long *)((const u8 *)key2 + key_start);
-	long diffs = 0;
 	int i;
 
 	for (i = key_start; i < key_end; i += sizeof(long))
-		diffs |= *cp1++ ^ *cp2++;
+		if (*cp1++ ^ *cp2++)
+			return false;
 
-	return diffs == 0;
+	return true;
 }
 
 static bool flow_cmp_masked_key(const struct sw_flow *flow,

-- 
2.20.1

Hello:

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

On Tue, 29 Jun 2021 09:22:11 +0200 you wrote:

From: Baowen Zheng <redacted>

In the current implement when comparing two flow keys, we will return
result after comparing the whole key from start to end.

In our optimization, we will return result in the first none-zero
comparison, then we will improve the flow table looking up efficiency.

[...]

Here is the summary with links:
  - [net-net] openvswitch: Optimize operation for key comparison
    https://git.kernel.org/netdev/net/c/b18114476a14

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