* [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation
@ 2014-06-03 23:53 Simon Horman
2014-06-04 10:13 ` Thomas Graf
2014-06-05 22:05 ` David Miller
0 siblings, 2 replies; 4+ messages in thread
From: Simon Horman @ 2014-06-03 23:53 UTC (permalink / raw)
To: David Miller, netdev-u79uwXL29TY76Z2rM5mHXA
Cc: dev-yBygre7rU0TnMu66kgdUjQ, YAMAMOTO Takashi
If an MPLS packet requires segmentation then use mpls_features
to determine if the software implementation should be used.
As no driver advertises MPLS GSO segmentation this will always be
the case.
I had not noticed that this was necessary before as software MPLS GSO
segmentation was already being used in my test environment. I believe that
the reason for that is the skbs in question always had fragments and the
driver I used does not advertise NETIF_F_FRAGLIST (which seems to be the
case for most drivers). Thus software segmentation was activated by
skb_gso_ok().
This introduces the overhead of an extra call to skb_network_protocol()
in the case where where CONFIG_NET_MPLS_GSO is set and
skb->ip_summed == CHECKSUM_NONE.
Thanks to Jesse Gross for prompting me to investigate this.
Signed-off-by: Simon Horman <horms-/R6kz+dDXgpPR4JQBCEnsQ@public.gmane.org>
Acked-by: YAMAMOTO Takashi <yamamoto-jCdQPDEk3idL9jVzuh4AOg@public.gmane.org>
---
v5
* As suggested by Yamamoto-san
- Remove unused tmp variable
- Do not use unlikely() for MPLS ethertype check
* Added Ack from Yamamoto-san
v4.2
* As suggested by Eric Dumazet
- Use htons() instead of cpu_to_be16()
- Refactor code to pass type to net_mpls_features.
v4.1
* Following fedback from Thomas Graff and Jesse Gross
- Use ethertype of packet to detect MPLS rather than
relying on mac_len indicating a gap between the end of L2
and the beginning of L3. That assumption seems to
be broken by the GRE GSO code.
- Move mpls_features handling into harmonize_features()
This allows an existing call in there to skb_network_protocol()
to be leveraged.
- Removed acks as the patch has now changed in a material way
v4
* As suggested by YAMAMOTO Takashi
- Correct typos in comment
* Added Ack from YAMAMOTO Takashi
v3
* As requested by David Miller
- Do not mark net_mpls_features as inline
- Correct alignment of parameters
v2
* Added Ack from Jesse Gross
* Removed duplicate 'Thus' from changelog
---
net/core/dev.c | 28 +++++++++++++++++++++++++++-
1 file changed, 27 insertions(+), 1 deletion(-)
diff --git a/net/core/dev.c b/net/core/dev.c
index 0355ca5..f726bfb 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2498,13 +2498,39 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features)
return 0;
}
+/* If MPLS offload request, verify we are testing hardware MPLS features
+ * instead of standard features for the netdev.
+ */
+#ifdef CONFIG_NET_MPLS_GSO
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+ netdev_features_t features,
+ __be16 type)
+{
+ if (type == htons(ETH_P_MPLS_UC) || type == htons(ETH_P_MPLS_MC))
+ features &= skb->dev->mpls_features;
+
+ return features;
+}
+#else
+static netdev_features_t net_mpls_features(struct sk_buff *skb,
+ netdev_features_t features,
+ __be16 type)
+{
+ return features;
+}
+#endif
+
static netdev_features_t harmonize_features(struct sk_buff *skb,
netdev_features_t features)
{
int tmp;
+ __be16 type;
+
+ type = skb_network_protocol(skb, &tmp);
+ features = net_mpls_features(skb, features, type);
if (skb->ip_summed != CHECKSUM_NONE &&
- !can_checksum_protocol(features, skb_network_protocol(skb, &tmp))) {
+ !can_checksum_protocol(features, type)) {
features &= ~NETIF_F_ALL_CSUM;
} else if (illegal_highdma(skb->dev, skb)) {
features &= ~NETIF_F_SG;
--
2.0.0.rc2
^ permalink raw reply related [flat|nested] 4+ messages in thread
* Re: [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation
2014-06-03 23:53 [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation Simon Horman
@ 2014-06-04 10:13 ` Thomas Graf
2014-06-05 22:05 ` David Miller
1 sibling, 0 replies; 4+ messages in thread
From: Thomas Graf @ 2014-06-04 10:13 UTC (permalink / raw)
To: Simon Horman; +Cc: David Miller, netdev, Jesse Gross, YAMAMOTO Takashi, dev
On 06/04/14 at 08:53am, Simon Horman wrote:
> If an MPLS packet requires segmentation then use mpls_features
> to determine if the software implementation should be used.
>
> As no driver advertises MPLS GSO segmentation this will always be
> the case.
>
> I had not noticed that this was necessary before as software MPLS GSO
> segmentation was already being used in my test environment. I believe that
> the reason for that is the skbs in question always had fragments and the
> driver I used does not advertise NETIF_F_FRAGLIST (which seems to be the
> case for most drivers). Thus software segmentation was activated by
> skb_gso_ok().
>
> This introduces the overhead of an extra call to skb_network_protocol()
> in the case where where CONFIG_NET_MPLS_GSO is set and
> skb->ip_summed == CHECKSUM_NONE.
>
> Thanks to Jesse Gross for prompting me to investigate this.
>
> Signed-off-by: Simon Horman <horms@verge.net.au>
> Acked-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
LGTM
Acked-by: Thomas Graf <tgraf@suug.ch>
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation
2014-06-03 23:53 [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation Simon Horman
2014-06-04 10:13 ` Thomas Graf
@ 2014-06-05 22:05 ` David Miller
2014-06-06 7:16 ` Simon Horman
1 sibling, 1 reply; 4+ messages in thread
From: David Miller @ 2014-06-05 22:05 UTC (permalink / raw)
To: horms; +Cc: netdev, jesse, tgraf, yamamoto, dev
From: Simon Horman <horms@verge.net.au>
Date: Wed, 4 Jun 2014 08:53:17 +0900
> If an MPLS packet requires segmentation then use mpls_features
> to determine if the software implementation should be used.
>
> As no driver advertises MPLS GSO segmentation this will always be
> the case.
>
> I had not noticed that this was necessary before as software MPLS GSO
> segmentation was already being used in my test environment. I believe that
> the reason for that is the skbs in question always had fragments and the
> driver I used does not advertise NETIF_F_FRAGLIST (which seems to be the
> case for most drivers). Thus software segmentation was activated by
> skb_gso_ok().
>
> This introduces the overhead of an extra call to skb_network_protocol()
> in the case where where CONFIG_NET_MPLS_GSO is set and
> skb->ip_summed == CHECKSUM_NONE.
>
> Thanks to Jesse Gross for prompting me to investigate this.
>
> Signed-off-by: Simon Horman <horms@verge.net.au>
> Acked-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
Applied to net-next, thanks Simon.
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation
2014-06-05 22:05 ` David Miller
@ 2014-06-06 7:16 ` Simon Horman
0 siblings, 0 replies; 4+ messages in thread
From: Simon Horman @ 2014-06-06 7:16 UTC (permalink / raw)
To: David Miller; +Cc: netdev, jesse, tgraf, yamamoto, dev
On Thu, Jun 05, 2014 at 03:05:42PM -0700, David Miller wrote:
> From: Simon Horman <horms@verge.net.au>
> Date: Wed, 4 Jun 2014 08:53:17 +0900
>
> > If an MPLS packet requires segmentation then use mpls_features
> > to determine if the software implementation should be used.
> >
> > As no driver advertises MPLS GSO segmentation this will always be
> > the case.
> >
> > I had not noticed that this was necessary before as software MPLS GSO
> > segmentation was already being used in my test environment. I believe that
> > the reason for that is the skbs in question always had fragments and the
> > driver I used does not advertise NETIF_F_FRAGLIST (which seems to be the
> > case for most drivers). Thus software segmentation was activated by
> > skb_gso_ok().
> >
> > This introduces the overhead of an extra call to skb_network_protocol()
> > in the case where where CONFIG_NET_MPLS_GSO is set and
> > skb->ip_summed == CHECKSUM_NONE.
> >
> > Thanks to Jesse Gross for prompting me to investigate this.
> >
> > Signed-off-by: Simon Horman <horms@verge.net.au>
> > Acked-by: YAMAMOTO Takashi <yamamoto@valinux.co.jp>
>
> Applied to net-next, thanks Simon.
Thanks!
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2014-06-06 7:16 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-06-03 23:53 [PATCH v5 net-next] MPLS: Use mpls_features to activate software MPLS GSO segmentation Simon Horman
2014-06-04 10:13 ` Thomas Graf
2014-06-05 22:05 ` David Miller
2014-06-06 7:16 ` Simon Horman
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.