[patch net-next] team: refine IFF_XMIT_DST_RELEASE capability

Subsystems: networking drivers, team driver, the rest

STALE5141d

3 messages, 3 authors, 2012-07-18 · open the first message on its own page

[patch net-next] team: refine IFF_XMIT_DST_RELEASE capability

From: Jiri Pirko <jiri@resnulli.us>
Date: 2012-07-18 17:39:43

Cloned patch of Eric Dumazet for bonding.

Some workloads greatly benefit of IFF_XMIT_DST_RELEASE capability
on output net device, avoiding dirtying dst refcount.

team currently disables IFF_XMIT_DST_RELEASE unconditionally.

If all ports have the IFF_XMIT_DST_RELEASE bit set, then
team dev can also have it in its priv_flags.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
 drivers/net/team/team.c |    5 +++++
 1 file changed, 5 insertions(+)
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 1a13470..813e131 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -733,12 +733,14 @@ static void __team_compute_features(struct team *team)
 	struct team_port *port;
 	u32 vlan_features = TEAM_VLAN_FEATURES;
 	unsigned short max_hard_header_len = ETH_HLEN;
+	unsigned int flags, dst_release_flag = IFF_XMIT_DST_RELEASE;
 
 	list_for_each_entry(port, &team->port_list, list) {
 		vlan_features = netdev_increment_features(vlan_features,
 					port->dev->vlan_features,
 					TEAM_VLAN_FEATURES);
 
+		dst_release_flag &= port->dev->priv_flags;
 		if (port->dev->hard_header_len > max_hard_header_len)
 			max_hard_header_len = port->dev->hard_header_len;
 	}
@@ -746,6 +748,9 @@ static void __team_compute_features(struct team *team)
 	team->dev->vlan_features = vlan_features;
 	team->dev->hard_header_len = max_hard_header_len;
 
+	flags = team->dev->priv_flags & ~IFF_XMIT_DST_RELEASE;
+	team->dev->priv_flags = flags | dst_release_flag;
+
 	netdev_change_features(team->dev);
 }
 
-- 
1.7.10.4

Re: [patch net-next] team: refine IFF_XMIT_DST_RELEASE capability

From: Eric Dumazet <hidden>
Date: 2012-07-18 18:17:39

On Wed, 2012-07-18 at 19:39 +0200, Jiri Pirko wrote:
Cloned patch of Eric Dumazet for bonding.

Some workloads greatly benefit of IFF_XMIT_DST_RELEASE capability
on output net device, avoiding dirtying dst refcount.

team currently disables IFF_XMIT_DST_RELEASE unconditionally.

If all ports have the IFF_XMIT_DST_RELEASE bit set, then
team dev can also have it in its priv_flags.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
 drivers/net/team/team.c |    5 +++++
 1 file changed, 5 insertions(+)
Acked-by: Eric Dumazet <edumazet@google.com>

Thanks

Re: [patch net-next] team: refine IFF_XMIT_DST_RELEASE capability

From: David Miller <davem@davemloft.net>
Date: 2012-07-18 18:28:58

From: Eric Dumazet <redacted>
Date: Wed, 18 Jul 2012 20:17:34 +0200
On Wed, 2012-07-18 at 19:39 +0200, Jiri Pirko wrote:
quoted
Cloned patch of Eric Dumazet for bonding.

Some workloads greatly benefit of IFF_XMIT_DST_RELEASE capability
on output net device, avoiding dirtying dst refcount.

team currently disables IFF_XMIT_DST_RELEASE unconditionally.

If all ports have the IFF_XMIT_DST_RELEASE bit set, then
team dev can also have it in its priv_flags.

Signed-off-by: Jiri Pirko <jiri@resnulli.us>
---
 drivers/net/team/team.c |    5 +++++
 1 file changed, 5 insertions(+)
Acked-by: Eric Dumazet <edumazet@google.com>
Applied, thanks.
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help