[PATCH net-next] vxlan: vxlan dev should inherit lowerdev's gso_max_size

[PATCH net-next] vxlan: vxlan dev should inherit lowerdev's gso_max_size

[Felix Manlunas]

vxlan dev currently ignores lowerdev's gso_max_size, which adversely
affects TSO performance of liquidio if it's the lowerdev.  Egress TCP
packets' skb->len often exceed liquidio's advertised gso_max_size.  This
may happen on other NIC drivers.

Fix it by assigning lowerdev's gso_max_size to that of vxlan dev.  Might as
well do likewise for gso_max_segs.

Single flow TSO throughput of liquidio as lowerdev (using iperf3):

    Before the patch:    139 Mbps
    After the patch :   8.68 Gbps
    Percent increase:  6,144 %

Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: Satanand Burla <satananda.burla@cavium.com>
---
 drivers/net/vxlan.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 1e54fb5..714f74f 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2926,6 +2926,11 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 		return -EINVAL;
 	}
 
+	if (lowerdev) {
+		dev->gso_max_size = lowerdev->gso_max_size;
+		dev->gso_max_segs = lowerdev->gso_max_segs;
+	}
+
 	if (conf->mtu) {
 		int max_mtu = ETH_MAX_MTU;
 

Re: [PATCH net-next] vxlan: vxlan dev should inherit lowerdev's gso_max_size

[David Miller]

From: Felix Manlunas <felix.manlunas@cavium.com>
Date: Wed, 29 Mar 2017 17:56:43 -0700

> vxlan dev currently ignores lowerdev's gso_max_size, which adversely
> affects TSO performance of liquidio if it's the lowerdev.  Egress TCP
> packets' skb->len often exceed liquidio's advertised gso_max_size.  This
> may happen on other NIC drivers.
> 
> Fix it by assigning lowerdev's gso_max_size to that of vxlan dev.  Might as
> well do likewise for gso_max_segs.
> 
> Single flow TSO throughput of liquidio as lowerdev (using iperf3):
> 
>     Before the patch:    139 Mbps
>     After the patch :   8.68 Gbps
>     Percent increase:  6,144 %
> 
> Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
> Signed-off-by: Satanand Burla <satananda.burla@cavium.com>

Ok, since this location is exactly when we associate the lowerdev
this is the right way to fix this.

Applied, thank you.