* [PATCH net-next] net: vlan: add support for tunnel offload
@ 2018-11-07 10:28 Davide Caratti
2018-11-08 6:23 ` David Miller
0 siblings, 1 reply; 2+ messages in thread
From: Davide Caratti @ 2018-11-07 10:28 UTC (permalink / raw)
To: David S. Miller, Cong Wang, netdev, Flavio Leitner, Florian Westphal
GSO tunneled packets are always segmented in software before they are
transmitted by a VLAN, even when the lower device can offload tunnel
encapsulation and VLAN together (i.e., some bits in NETIF_F_GSO_ENCAP_ALL
mask are set in the lower device 'vlan_features'). If we let VLANs have
the same tunnel offload capabilities as their lower device, throughput
can improve significantly when CPU is limited on the transmitter side.
- set NETIF_F_GSO_ENCAP_ALL bits in the VLAN 'hw_features', to ensure
that 'features' will have those bits zeroed only when the lower device
has no hardware support for tunnel encapsulation.
- for the same reason, copy GSO-related bits of 'hw_enc_features' from
lower device to VLAN, and ensure to update that value when the lower
device changes its features.
- set NETIF_F_HW_CSUM bit in the VLAN 'hw_enc_features' if 'real_dev'
is able to compute checksums at least for a kind of packets, like done
with commit 8403debeead8 ("vlan: Keep NETIF_F_HW_CSUM similar to other
software devices"). This avoids software segmentation due to mismatching
checksum capabilities between VLAN's 'features' and 'hw_enc_features'.
Reported-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: Davide Caratti <dcaratti@redhat.com>
---
net/8021q/vlan.c | 1 +
net/8021q/vlan.h | 12 ++++++++++++
net/8021q/vlan_dev.c | 2 ++
3 files changed, 15 insertions(+)
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 5e9950453955..1b7a375c6616 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -330,6 +330,7 @@ static void vlan_transfer_features(struct net_device *dev,
vlandev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
vlandev->priv_flags |= (vlan->real_dev->priv_flags & IFF_XMIT_DST_RELEASE);
+ vlandev->hw_enc_features = vlan_tnl_features(vlan->real_dev);
netdev_update_features(vlandev);
}
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h
index 44df1c3df02d..c46daf09a501 100644
--- a/net/8021q/vlan.h
+++ b/net/8021q/vlan.h
@@ -92,6 +92,18 @@ static inline struct net_device *vlan_find_dev(struct net_device *real_dev,
return NULL;
}
+static inline netdev_features_t vlan_tnl_features(struct net_device *real_dev)
+{
+ netdev_features_t ret;
+
+ ret = real_dev->hw_enc_features &
+ (NETIF_F_CSUM_MASK | NETIF_F_ALL_TSO | NETIF_F_GSO_ENCAP_ALL);
+
+ if ((ret & NETIF_F_GSO_ENCAP_ALL) && (ret & NETIF_F_CSUM_MASK))
+ return (ret & ~NETIF_F_CSUM_MASK) | NETIF_F_HW_CSUM;
+ return 0;
+}
+
#define vlan_group_for_each_dev(grp, i, dev) \
for ((i) = 0; i < VLAN_PROTO_NUM * VLAN_N_VID; i++) \
if (((dev) = __vlan_group_get_device((grp), (i) / VLAN_N_VID, \
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ff720f1ebf73..b2d9c8f27cd7 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -562,6 +562,7 @@ static int vlan_dev_init(struct net_device *dev)
dev->hw_features = NETIF_F_HW_CSUM | NETIF_F_SG |
NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE |
+ NETIF_F_GSO_ENCAP_ALL |
NETIF_F_HIGHDMA | NETIF_F_SCTP_CRC |
NETIF_F_ALL_FCOE;
@@ -572,6 +573,7 @@ static int vlan_dev_init(struct net_device *dev)
netdev_warn(real_dev, "VLAN features are set incorrectly. Q-in-Q configurations may not work correctly.\n");
dev->vlan_features = real_dev->vlan_features & ~NETIF_F_ALL_FCOE;
+ dev->hw_enc_features = vlan_tnl_features(real_dev);
/* ipv6 shared card related stuff */
dev->dev_id = real_dev->dev_id;
--
2.19.1
^ permalink raw reply related [flat|nested] 2+ messages in thread
* Re: [PATCH net-next] net: vlan: add support for tunnel offload
2018-11-07 10:28 [PATCH net-next] net: vlan: add support for tunnel offload Davide Caratti
@ 2018-11-08 6:23 ` David Miller
0 siblings, 0 replies; 2+ messages in thread
From: David Miller @ 2018-11-08 6:23 UTC (permalink / raw)
To: dcaratti; +Cc: xiyou.wangcong, netdev, fbl, fw
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 7 Nov 2018 11:28:18 +0100
> GSO tunneled packets are always segmented in software before they are
> transmitted by a VLAN, even when the lower device can offload tunnel
> encapsulation and VLAN together (i.e., some bits in NETIF_F_GSO_ENCAP_ALL
> mask are set in the lower device 'vlan_features'). If we let VLANs have
> the same tunnel offload capabilities as their lower device, throughput
> can improve significantly when CPU is limited on the transmitter side.
>
> - set NETIF_F_GSO_ENCAP_ALL bits in the VLAN 'hw_features', to ensure
> that 'features' will have those bits zeroed only when the lower device
> has no hardware support for tunnel encapsulation.
> - for the same reason, copy GSO-related bits of 'hw_enc_features' from
> lower device to VLAN, and ensure to update that value when the lower
> device changes its features.
> - set NETIF_F_HW_CSUM bit in the VLAN 'hw_enc_features' if 'real_dev'
> is able to compute checksums at least for a kind of packets, like done
> with commit 8403debeead8 ("vlan: Keep NETIF_F_HW_CSUM similar to other
> software devices"). This avoids software segmentation due to mismatching
> checksum capabilities between VLAN's 'features' and 'hw_enc_features'.
>
> Reported-by: Flavio Leitner <fbl@redhat.com>
> Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Applied.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2018-11-08 15:57 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-11-07 10:28 [PATCH net-next] net: vlan: add support for tunnel offload Davide Caratti
2018-11-08 6:23 ` David Miller
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).