diff options
| author | Eric Dumazet <edumazet@google.com> | 2014-10-05 18:38:35 -0700 |
|---|---|---|
| committer | David S. Miller <davem@davemloft.net> | 2014-10-07 13:22:11 -0400 |
| commit | 0287587884b15041203b3a362d485e1ab1f24445 (patch) | |
| tree | 675ae57663c1ba3ee8768e65e7fb0e6d0259e04c /net/ipv6 | |
| parent | fe971b95c22578456ff7198537827841c726d3f7 (diff) | |
net: better IFF_XMIT_DST_RELEASE support
Testing xmit_more support with netperf and connected UDP sockets,
I found strange dst refcount false sharing.
Current handling of IFF_XMIT_DST_RELEASE is not optimal.
Dropping dst in validate_xmit_skb() is certainly too late in case
packet was queued by cpu X but dequeued by cpu Y
The logical point to take care of drop/force is in __dev_queue_xmit()
before even taking qdisc lock.
As Julian Anastasov pointed out, need for skb_dst() might come from some
packet schedulers or classifiers.
This patch adds new helper to cleanly express needs of various drivers
or qdiscs/classifiers.
Drivers that need skb_dst() in their ndo_start_xmit() should call
following helper in their setup instead of the prior :
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
->
netif_keep_dst(dev);
Instead of using a single bit, we use two bits, one being
eventually rebuilt in bonding/team drivers.
The other one, is permanent and blocks IFF_XMIT_DST_RELEASE being
rebuilt in bonding/team. Eventually, we could add something
smarter later.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6')
| -rw-r--r-- | net/ipv6/ip6_gre.c | 2 | ||||
| -rw-r--r-- | net/ipv6/ip6_tunnel.c | 2 | ||||
| -rw-r--r-- | net/ipv6/ip6_vti.c | 2 | ||||
| -rw-r--r-- | net/ipv6/sit.c | 2 |
4 files changed, 4 insertions, 4 deletions
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 74b677916a70..de3b1c86b8d3 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -1242,7 +1242,7 @@ static void ip6gre_tunnel_setup(struct net_device *dev) dev->flags |= IFF_NOARP; dev->iflink = 0; dev->addr_len = sizeof(struct in6_addr); - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + netif_keep_dst(dev); } static int ip6gre_tunnel_init(struct net_device *dev) diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d3e8888ad611..9409887fb664 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1493,7 +1493,7 @@ static void ip6_tnl_dev_setup(struct net_device *dev) dev->mtu -= 8; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + netif_keep_dst(dev); /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 5833a2244467..d440bb585524 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -807,7 +807,7 @@ static void vti6_dev_setup(struct net_device *dev) dev->mtu = ETH_DATA_LEN; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + netif_keep_dst(dev); } /** diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 0d4e27466f82..6eab37cf5345 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -1364,7 +1364,7 @@ static void ipip6_tunnel_setup(struct net_device *dev) dev->hard_header_len = LL_MAX_HEADER + t_hlen; dev->mtu = ETH_DATA_LEN - t_hlen; dev->flags = IFF_NOARP; - dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; + netif_keep_dst(dev); dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_LLTX; |