* [PATCH 04/16] ipv4: Kill 'rt_src' from 'struct rtable'
From: David Miller @ 2012-07-20 21:25 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/route.c | 34 +++++++++++++++-------------------
net/ipv4/xfrm4_policy.c | 1 -
3 files changed, 15 insertions(+), 21 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 935fa59..85d1093 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -49,7 +49,6 @@ struct rtable {
__u16 rt_type;
__be32 rt_dst; /* Path destination */
- __be32 rt_src; /* Path source */
int rt_route_iif;
int rt_iif;
int rt_oif;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c89d690..fc1199d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1272,7 +1272,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
rth->rt_dst = daddr;
- rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
@@ -1393,7 +1392,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_flags = flags;
rth->rt_type = res->type;
rth->rt_dst = daddr;
- rth->rt_src = saddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
@@ -1561,7 +1559,6 @@ local_input:
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
rth->rt_dst = daddr;
- rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
@@ -1714,7 +1711,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_flags = flags;
rth->rt_type = type;
rth->rt_dst = fl4->daddr;
- rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
@@ -2005,7 +2001,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_dst = ort->rt_dst;
- rt->rt_src = ort->rt_src;
rt->rt_gateway = ort->rt_gateway;
rt->fi = ort->fi;
if (rt->fi)
@@ -2036,7 +2031,7 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-static int rt_fill_info(struct net *net, __be32 src, u8 tos,
+static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
@@ -2055,7 +2050,7 @@ static int rt_fill_info(struct net *net, __be32 src, u8 tos,
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
- r->rtm_tos = tos;
+ r->rtm_tos = fl4->flowi4_tos;
r->rtm_table = RT_TABLE_MAIN;
if (nla_put_u32(skb, RTA_TABLE, RT_TABLE_MAIN))
goto nla_put_failure;
@@ -2082,11 +2077,11 @@ static int rt_fill_info(struct net *net, __be32 src, u8 tos,
goto nla_put_failure;
#endif
if (!rt_is_input_route(rt) &&
- rt->rt_src != src) {
- if (nla_put_be32(skb, RTA_PREFSRC, rt->rt_src))
+ fl4->saddr != src) {
+ if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (rt->rt_dst != rt->rt_gateway &&
+ if (fl4->daddr != rt->rt_gateway &&
nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
goto nla_put_failure;
@@ -2116,7 +2111,7 @@ static int rt_fill_info(struct net *net, __be32 src, u8 tos,
if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
int err = ipmr_get_route(net, skb,
- rt->rt_src, rt->rt_dst,
+ fl4->saddr, fl4->daddr,
r, nowait);
if (err <= 0) {
if (!nowait) {
@@ -2151,6 +2146,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
struct rtmsg *rtm;
struct nlattr *tb[RTA_MAX+1];
struct rtable *rt = NULL;
+ struct flowi4 fl4;
__be32 dst = 0;
__be32 src = 0;
u32 iif;
@@ -2185,6 +2181,13 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
+ memset(&fl4, 0, sizeof(fl4));
+ fl4.daddr = dst;
+ fl4.saddr = src;
+ fl4.flowi4_tos = rtm->rtm_tos;
+ fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
+ fl4.flowi4_mark = mark;
+
if (iif) {
struct net_device *dev;
@@ -2205,13 +2208,6 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (err == 0 && rt->dst.error)
err = -rt->dst.error;
} else {
- struct flowi4 fl4 = {
- .daddr = dst,
- .saddr = src,
- .flowi4_tos = rtm->rtm_tos,
- .flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
- .flowi4_mark = mark,
- };
rt = ip_route_output_key(net, &fl4);
err = 0;
@@ -2226,7 +2222,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(net, src, rtm->rtm_tos, skb,
+ err = rt_fill_info(net, src, &fl4, skb,
NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 2a8d5cf..00d49e4 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -92,7 +92,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
- xdst->u.rt.rt_src = rt->rt_src;
xdst->u.rt.rt_dst = rt->rt_dst;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 05/16] ipv4: Remove 'rt_mark' from 'struct rtable'
From: David Miller @ 2012-07-20 21:25 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/ipmr.c | 2 +-
net/ipv4/route.c | 9 ++-------
net/ipv4/xfrm4_policy.c | 1 -
4 files changed, 3 insertions(+), 10 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 85d1093..757fe40 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -52,7 +52,6 @@ struct rtable {
int rt_route_iif;
int rt_iif;
int rt_oif;
- __u32 rt_mark;
/* Info on neighbour */
__be32 rt_gateway;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 5716c6b..eee3bf6 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1797,7 +1797,7 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
.flowi4_tos = RT_TOS(iph->tos),
.flowi4_oif = rt->rt_oif,
.flowi4_iif = rt->rt_iif,
- .flowi4_mark = rt->rt_mark,
+ .flowi4_mark = skb->mark,
};
struct mr_table *mrt;
int err;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fc1199d..264617c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1275,7 +1275,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
- rth->rt_mark = skb->mark;
rth->rt_pmtu = 0;
rth->rt_gateway = daddr;
rth->fi = NULL;
@@ -1395,7 +1394,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
- rth->rt_mark = skb->mark;
rth->rt_pmtu = 0;
rth->rt_gateway = daddr;
rth->fi = NULL;
@@ -1562,7 +1560,6 @@ local_input:
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
- rth->rt_mark = skb->mark;
rth->rt_pmtu = 0;
rth->rt_gateway = daddr;
rth->fi = NULL;
@@ -1714,7 +1711,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
- rth->rt_mark = fl4->flowi4_mark;
rth->rt_pmtu = 0;
rth->rt_gateway = fl4->daddr;
rth->fi = NULL;
@@ -1994,7 +1990,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
rt->rt_oif = ort->rt_oif;
- rt->rt_mark = ort->rt_mark;
rt->rt_pmtu = ort->rt_pmtu;
rt->rt_genid = rt_genid(net);
@@ -2091,8 +2086,8 @@ static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
if (rtnetlink_put_metrics(skb, metrics) < 0)
goto nla_put_failure;
- if (rt->rt_mark &&
- nla_put_be32(skb, RTA_MARK, rt->rt_mark))
+ if (fl4->flowi4_mark &&
+ nla_put_be32(skb, RTA_MARK, fl4->flowi4_mark))
goto nla_put_failure;
error = rt->dst.error;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 00d49e4..f73ba82 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -82,7 +82,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
xdst->u.rt.rt_iif = fl4->flowi4_iif;
xdst->u.rt.rt_oif = fl4->flowi4_oif;
- xdst->u.rt.rt_mark = fl4->flowi4_mark;
xdst->u.dst.dev = dev;
dev_hold(dev);
--
1.7.10.4
^ permalink raw reply related
* [PATCH 06/16] ipv4: Remove 'rt_dst' from 'struct rtable'
From: David Miller @ 2012-07-20 21:25 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/route.c | 45 +++++++++------------------------------------
net/ipv4/xfrm4_policy.c | 1 -
3 files changed, 9 insertions(+), 38 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 757fe40..6d111bc 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -48,7 +48,6 @@ struct rtable {
unsigned int rt_flags;
__u16 rt_type;
- __be32 rt_dst; /* Path destination */
int rt_route_iif;
int rt_iif;
int rt_oif;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 264617c..85d103f 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -850,7 +850,7 @@ void ip_rt_send_redirect(struct sk_buff *skb)
peer->rate_tokens == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, rt->rt_iif,
- &rt->rt_dst, &rt->rt_gateway);
+ &ip_hdr(skb)->daddr, &rt->rt_gateway);
#endif
}
out_put_peer:
@@ -1132,8 +1132,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-
- if (rt->rt_gateway != rt->rt_dst && mtu > 576)
+ if (rt->rt_gateway != 0 && mtu > 576)
mtu = 576;
}
@@ -1271,7 +1270,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_genid = rt_genid(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
- rth->rt_dst = daddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
@@ -1390,7 +1388,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rth->rt_flags = flags;
rth->rt_type = res->type;
- rth->rt_dst = daddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
@@ -1556,7 +1553,6 @@ local_input:
rth->rt_genid = rt_genid(net);
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
- rth->rt_dst = daddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
@@ -1707,7 +1703,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
- rth->rt_dst = fl4->daddr;
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
@@ -1995,7 +1990,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
- rt->rt_dst = ort->rt_dst;
rt->rt_gateway = ort->rt_gateway;
rt->fi = ort->fi;
if (rt->fi)
@@ -2026,9 +2020,9 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
-static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
- struct sk_buff *skb, u32 pid, u32 seq, int event,
- int nowait, unsigned int flags)
+static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+ struct flowi4 *fl4, struct sk_buff *skb, u32 pid,
+ u32 seq, int event, int nowait, unsigned int flags)
{
struct rtable *rt = skb_rtable(skb);
struct rtmsg *r;
@@ -2056,7 +2050,7 @@ static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
- if (nla_put_be32(skb, RTA_DST, rt->rt_dst))
+ if (nla_put_be32(skb, RTA_DST, dst))
goto nla_put_failure;
if (src) {
r->rtm_src_len = 32;
@@ -2100,29 +2094,8 @@ static int rt_fill_info(struct net *net, __be32 src, struct flowi4 *fl4,
}
if (rt_is_input_route(rt)) {
-#ifdef CONFIG_IP_MROUTE
- __be32 dst = rt->rt_dst;
-
- if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
- IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
- int err = ipmr_get_route(net, skb,
- fl4->saddr, fl4->daddr,
- r, nowait);
- if (err <= 0) {
- if (!nowait) {
- if (err == 0)
- return 0;
- goto nla_put_failure;
- } else {
- if (err == -EMSGSIZE)
- goto nla_put_failure;
- error = err;
- }
- }
- } else
-#endif
- if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
- goto nla_put_failure;
+ if (nla_put_u32(skb, RTA_IIF, rt->rt_iif))
+ goto nla_put_failure;
}
if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0)
@@ -2217,7 +2190,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, void
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
- err = rt_fill_info(net, src, &fl4, skb,
+ err = rt_fill_info(net, dst, src, &fl4, skb,
NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index f73ba82..6074b69 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -91,7 +91,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
- xdst->u.rt.rt_dst = rt->rt_dst;
xdst->u.rt.rt_gateway = rt->rt_gateway;
xdst->u.rt.rt_pmtu = rt->rt_pmtu;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 07/16] ipv4: Adjust semantics of rt->rt_gateway.
From: David Miller @ 2012-07-20 21:25 UTC (permalink / raw)
To: netdev
In order to allow prefixed routes, we have to adjust how rt_gateway
is set and interpreted.
The new interpretation is:
1) rt_gateway == 0, destination is on-link, nexthop is iph->daddr
2) rt_gateway != 0, destination requires a nexthop gateway
Abstract the fetching of the proper nexthop value using a new
inline helper, rt_nexthop(), as suggested by Joe Perches.
Signed-off-by: David S. Miller <davem@davemloft.net>
Tested-by: Vijay Subramanian <subramanian.vijay@gmail.com>
---
include/net/route.h | 7 +++++++
net/ipv4/arp.c | 3 +--
net/ipv4/inet_connection_sock.c | 4 ++--
net/ipv4/ip_gre.c | 2 +-
net/ipv4/ip_output.c | 2 +-
net/ipv4/ipip.c | 2 +-
net/ipv4/netfilter/ipt_MASQUERADE.c | 5 +++--
net/ipv4/route.c | 17 +++++++++--------
8 files changed, 25 insertions(+), 17 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 6d111bc..3c1eeab 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -70,6 +70,13 @@ static inline bool rt_is_output_route(const struct rtable *rt)
return rt->rt_route_iif == 0;
}
+static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
+{
+ if (rt->rt_gateway)
+ return rt->rt_gateway;
+ return daddr;
+}
+
struct ip_rt_acct {
__u32 o_bytes;
__u32 o_packets;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index c38293f..a0124eb 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -475,8 +475,7 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb)
return 1;
}
- paddr = skb_rtable(skb)->rt_gateway;
-
+ paddr = rt_nexthop(skb_rtable(skb), ip_hdr(skb)->daddr);
if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr,
paddr, dev))
return 0;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index c7a4de0..0a290d7 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -389,7 +389,7 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_gateway)
goto route_err;
return &rt->dst;
@@ -422,7 +422,7 @@ struct dst_entry *inet_csk_route_child_sock(struct sock *sk,
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
- if (opt && opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+ if (opt && opt->opt.is_strictroute && rt->rt_gateway)
goto route_err;
return &rt->dst;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 42c44b1..b062a98 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -766,7 +766,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
- dst = rt->rt_gateway;
+ dst = rt_nexthop(rt, old_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index c528f84..4494015 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -371,7 +371,7 @@ int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl)
skb_dst_set_noref(skb, &rt->dst);
packet_routed:
- if (inet_opt && inet_opt->opt.is_strictroute && fl4->daddr != rt->rt_gateway)
+ if (inet_opt && inet_opt->opt.is_strictroute && rt->rt_gateway)
goto no_route;
/* OK, we know where to send it, allocate and build IP header. */
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 2c2c35b..99af1f0 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -487,7 +487,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
dev->stats.tx_fifo_errors++;
goto tx_error;
}
- dst = rt->rt_gateway;
+ dst = rt_nexthop(rt, old_iph->daddr);
}
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 2f210c7..cbb6a1a 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -52,7 +52,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
struct nf_nat_ipv4_range newrange;
const struct nf_nat_ipv4_multi_range_compat *mr;
const struct rtable *rt;
- __be32 newsrc;
+ __be32 newsrc, nh;
NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING);
@@ -70,7 +70,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par)
mr = par->targinfo;
rt = skb_rtable(skb);
- newsrc = inet_select_addr(par->out, rt->rt_gateway, RT_SCOPE_UNIVERSE);
+ nh = rt_nexthop(rt, ip_hdr(skb)->daddr);
+ newsrc = inet_select_addr(par->out, nh, RT_SCOPE_UNIVERSE);
if (!newsrc) {
pr_info("%s ate my IP address\n", par->out->name);
return NF_DROP;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85d103f..d1d5796 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1085,8 +1085,9 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
else
- src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
- RT_SCOPE_UNIVERSE);
+ src = inet_select_addr(rt->dst.dev,
+ rt_nexthop(rt, iph->daddr),
+ RT_SCOPE_UNIVERSE);
rcu_read_unlock();
}
memcpy(addr, &src, 4);
@@ -1132,7 +1133,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
- if (rt->rt_gateway != 0 && mtu > 576)
+ if (rt->rt_gateway && mtu > 576)
mtu = 576;
}
@@ -1274,7 +1275,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
rth->rt_pmtu = 0;
- rth->rt_gateway = daddr;
+ rth->rt_gateway = 0;
rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
@@ -1392,7 +1393,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
rth->rt_pmtu = 0;
- rth->rt_gateway = daddr;
+ rth->rt_gateway = 0;
rth->fi = NULL;
rth->dst.input = ip_forward;
@@ -1557,7 +1558,7 @@ local_input:
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
rth->rt_pmtu = 0;
- rth->rt_gateway = daddr;
+ rth->rt_gateway = 0;
rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
@@ -1707,7 +1708,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
rth->rt_pmtu = 0;
- rth->rt_gateway = fl4->daddr;
+ rth->rt_gateway = 0;
rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2070,7 +2071,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
if (nla_put_be32(skb, RTA_PREFSRC, fl4->saddr))
goto nla_put_failure;
}
- if (fl4->daddr != rt->rt_gateway &&
+ if (rt->rt_gateway &&
nla_put_be32(skb, RTA_GATEWAY, rt->rt_gateway))
goto nla_put_failure;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 08/16] net: Document dst->obsolete better.
From: David Miller @ 2012-07-20 21:25 UTC (permalink / raw)
To: netdev
Add a big comment explaining how the field works, and use defines
instead of magic constants for the values assigned to it.
Suggested by Joe Perches.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/dst.h | 14 +++++++++++++-
net/core/dst.c | 4 ++--
net/decnet/dn_route.c | 4 ++--
net/ipv4/route.c | 5 +++--
net/ipv6/route.c | 4 ++--
net/sctp/transport.c | 2 +-
net/xfrm/xfrm_policy.c | 23 ++++++++++++-----------
7 files changed, 35 insertions(+), 21 deletions(-)
diff --git a/include/net/dst.h b/include/net/dst.h
index 5161046..0df661a 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -65,7 +65,19 @@ struct dst_entry {
unsigned short pending_confirm;
short error;
+
+ /* A non-zero value of dst->obsolete forces by-hand validation
+ * of the route entry. Positive values are set by the generic
+ * dst layer to indicate that the entry has been forcefully
+ * destroyed.
+ *
+ * Negative values are used by the implementation layer code to
+ * force invocation of the dst_ops->check() method.
+ */
short obsolete;
+#define DST_OBSOLETE_NONE 0
+#define DST_OBSOLETE_DEAD 2
+#define DST_OBSOLETE_FORCE_CHK -1
unsigned short header_len; /* more space at head required */
unsigned short trailer_len; /* space to reserve at tail */
#ifdef CONFIG_IP_ROUTE_CLASSID
@@ -359,7 +371,7 @@ extern struct dst_entry *dst_destroy(struct dst_entry *dst);
static inline void dst_free(struct dst_entry *dst)
{
- if (dst->obsolete > 1)
+ if (dst->obsolete > 0)
return;
if (!atomic_read(&dst->__refcnt)) {
dst = dst_destroy(dst);
diff --git a/net/core/dst.c b/net/core/dst.c
index 07bacff..069d51d 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -94,7 +94,7 @@ loop:
* But we do not have state "obsoleted, but
* referenced by parent", so it is right.
*/
- if (dst->obsolete > 1)
+ if (dst->obsolete > 0)
continue;
___dst_free(dst);
@@ -202,7 +202,7 @@ static void ___dst_free(struct dst_entry *dst)
*/
if (dst->dev == NULL || !(dst->dev->flags&IFF_UP))
dst->input = dst->output = dst_discard;
- dst->obsolete = 2;
+ dst->obsolete = DST_OBSOLETE_DEAD;
}
void __dst_free(struct dst_entry *dst)
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 47de90d..23cc11d 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1176,7 +1176,7 @@ make_route:
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
- rt = dst_alloc(&dn_dst_ops, dev_out, 1, 0, DST_HOST);
+ rt = dst_alloc(&dn_dst_ops, dev_out, 1, DST_OBSOLETE_NONE, DST_HOST);
if (rt == NULL)
goto e_nobufs;
@@ -1444,7 +1444,7 @@ static int dn_route_input_slow(struct sk_buff *skb)
}
make_route:
- rt = dst_alloc(&dn_dst_ops, out_dev, 0, 0, DST_HOST);
+ rt = dst_alloc(&dn_dst_ops, out_dev, 0, DST_OBSOLETE_NONE, DST_HOST);
if (rt == NULL)
goto e_nobufs;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d1d5796..50d2498 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1221,7 +1221,7 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
static struct rtable *rt_dst_alloc(struct net_device *dev,
bool nopolicy, bool noxfrm)
{
- return dst_alloc(&ipv4_dst_ops, dev, 1, -1,
+ return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
DST_HOST | DST_NOCACHE |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
@@ -1969,9 +1969,10 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
- struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0);
struct rtable *ort = (struct rtable *) dst_orig;
+ struct rtable *rt;
+ rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
if (rt) {
struct dst_entry *new = &rt->dst;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 84f6564..cf02cb9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -281,7 +281,7 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
struct fib6_table *table)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
- 0, 0, flags);
+ 0, DST_OBSOLETE_NONE, flags);
if (rt) {
struct dst_entry *dst = &rt->dst;
@@ -985,7 +985,7 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
struct rt6_info *rt, *ort = (struct rt6_info *) dst_orig;
struct dst_entry *new = NULL;
- rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, 0, 0);
+ rt = dst_alloc(&ip6_dst_blackhole_ops, ort->dst.dev, 1, DST_OBSOLETE_NONE, 0);
if (rt) {
new = &rt->dst;
diff --git a/net/sctp/transport.c b/net/sctp/transport.c
index a6b7ee9..ec3a12b 100644
--- a/net/sctp/transport.c
+++ b/net/sctp/transport.c
@@ -216,7 +216,7 @@ void sctp_transport_set_owner(struct sctp_transport *transport,
void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk)
{
/* If we don't have a fresh route, look one up */
- if (!transport->dst || transport->dst->obsolete > 1) {
+ if (!transport->dst || transport->dst->obsolete) {
dst_release(transport->dst);
transport->af_specific->get_dst(transport, &transport->saddr,
&transport->fl, sk);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 65bd1ca5..c5a5165 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1350,7 +1350,7 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
default:
BUG();
}
- xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
+ xdst = dst_alloc(dst_ops, NULL, 0, DST_OBSOLETE_NONE, 0);
if (likely(xdst)) {
struct dst_entry *dst = &xdst->u.dst;
@@ -1477,7 +1477,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
dst1->xfrm = xfrm[i];
xdst->xfrm_genid = xfrm[i]->genid;
- dst1->obsolete = -1;
+ dst1->obsolete = DST_OBSOLETE_FORCE_CHK;
dst1->flags |= DST_HOST;
dst1->lastuse = now;
@@ -2219,12 +2219,13 @@ EXPORT_SYMBOL(__xfrm_route_forward);
static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie)
{
/* Code (such as __xfrm4_bundle_create()) sets dst->obsolete
- * to "-1" to force all XFRM destinations to get validated by
- * dst_ops->check on every use. We do this because when a
- * normal route referenced by an XFRM dst is obsoleted we do
- * not go looking around for all parent referencing XFRM dsts
- * so that we can invalidate them. It is just too much work.
- * Instead we make the checks here on every use. For example:
+ * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to
+ * get validated by dst_ops->check on every use. We do this
+ * because when a normal route referenced by an XFRM dst is
+ * obsoleted we do not go looking around for all parent
+ * referencing XFRM dsts so that we can invalidate them. It
+ * is just too much work. Instead we make the checks here on
+ * every use. For example:
*
* XFRM dst A --> IPv4 dst X
*
@@ -2234,9 +2235,9 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie)
* stale_bundle() check.
*
* When a policy's bundle is pruned, we dst_free() the XFRM
- * dst which causes it's ->obsolete field to be set to a
- * positive non-zero integer. If an XFRM dst has been pruned
- * like this, we want to force a new route lookup.
+ * dst which causes it's ->obsolete field to be set to
+ * DST_OBSOLETE_DEAD. If an XFRM dst has been pruned like
+ * this, we want to force a new route lookup.
*/
if (dst->obsolete < 0 && !stale_bundle(dst))
return dst;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 09/16] ipv4: Kill routes during PMTU/redirect updates.
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
Mark them obsolete so there will be a re-lookup to fetch the
FIB nexthop exception info.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/dst.h | 1 +
net/ipv4/route.c | 41 +++++++++++++++++++++++++++++------------
2 files changed, 30 insertions(+), 12 deletions(-)
diff --git a/include/net/dst.h b/include/net/dst.h
index 0df661a..baf5978 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -78,6 +78,7 @@ struct dst_entry {
#define DST_OBSOLETE_NONE 0
#define DST_OBSOLETE_DEAD 2
#define DST_OBSOLETE_FORCE_CHK -1
+#define DST_OBSOLETE_KILL -2
unsigned short header_len; /* more space at head required */
unsigned short trailer_len; /* space to reserve at tail */
#ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 50d2498..d52f769 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -673,7 +673,8 @@ out_unlock:
return;
}
-static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4)
+static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4,
+ bool kill_route)
{
__be32 new_gw = icmp_hdr(skb)->un.gateway;
__be32 old_gw = ip_hdr(skb)->saddr;
@@ -728,8 +729,8 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
update_or_create_fnhe(nh, fl4->daddr, new_gw,
0, 0);
}
- rt->rt_gateway = new_gw;
- rt->rt_flags |= RTCF_REDIRECTED;
+ if (kill_route)
+ rt->dst.obsolete = DST_OBSOLETE_KILL;
call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
}
neigh_release(n);
@@ -760,7 +761,7 @@ static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buf
rt = (struct rtable *) dst;
ip_rt_build_flow_key(&fl4, sk, skb);
- __ip_do_redirect(rt, skb, &fl4);
+ __ip_do_redirect(rt, skb, &fl4, true);
}
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
@@ -919,7 +920,7 @@ out: kfree_skb(skb);
return 0;
}
-static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
+static u32 __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
{
struct fib_result res;
@@ -932,8 +933,7 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
update_or_create_fnhe(nh, fl4->daddr, 0, mtu,
jiffies + ip_rt_mtu_expires);
}
- rt->rt_pmtu = mtu;
- dst_set_expires(&rt->dst, ip_rt_mtu_expires);
+ return mtu;
}
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
@@ -943,7 +943,14 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb);
- __ip_rt_update_pmtu(rt, &fl4, mtu);
+ mtu = __ip_rt_update_pmtu(rt, &fl4, mtu);
+
+ if (!rt->rt_pmtu) {
+ dst->obsolete = DST_OBSOLETE_KILL;
+ } else {
+ rt->rt_pmtu = mtu;
+ dst_set_expires(&rt->dst, ip_rt_mtu_expires);
+ }
}
void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
@@ -989,7 +996,7 @@ void ipv4_redirect(struct sk_buff *skb, struct net *net,
RT_TOS(iph->tos), protocol, mark, flow_flags);
rt = __ip_route_output_key(net, &fl4);
if (!IS_ERR(rt)) {
- __ip_do_redirect(rt, skb, &fl4);
+ __ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
}
}
@@ -1004,7 +1011,7 @@ void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk)
__build_flow_key(&fl4, sk, iph, 0, 0, 0, 0, 0);
rt = __ip_route_output_key(sock_net(sk), &fl4);
if (!IS_ERR(rt)) {
- __ip_do_redirect(rt, skb, &fl4);
+ __ip_do_redirect(rt, skb, &fl4, false);
ip_rt_put(rt);
}
}
@@ -1014,7 +1021,15 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
struct rtable *rt = (struct rtable *) dst;
- if (rt_is_expired(rt))
+ /* All IPV4 dsts are created with ->obsolete set to the value
+ * DST_OBSOLETE_FORCE_CHK which forces validation calls down
+ * into this function always.
+ *
+ * When a PMTU/redirect information update invalidates a
+ * route, this is indicated by setting obsolete to
+ * DST_OBSOLETE_KILL.
+ */
+ if (dst->obsolete == DST_OBSOLETE_KILL || rt_is_expired(rt))
return NULL;
return dst;
}
@@ -1186,8 +1201,10 @@ restart:
dst_set_expires(&rt->dst, diff);
}
}
- if (gw)
+ if (gw) {
+ rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_gateway = gw;
+ }
fnhe->fnhe_stamp = jiffies;
break;
}
--
1.7.10.4
^ permalink raw reply related
* [PATCH 10/16] ipv4: Cache output routes in fib_info nexthops.
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
If we have an output route that lacks nexthop exceptions, we can cache
it in the FIB info nexthop.
Such routes will have DST_HOST cleared because such routes refer to a
family of destinations, rather than just one.
The sequence of the handling of exceptions during route lookup is
adjusted to make the logic work properly.
Before we allocate the route, we lookup the exception.
Then we know if we will cache this route or not, and therefore whether
DST_HOST should be set on the allocated route.
Then we use DST_HOST to key off whether we should store the resulting
route, during rt_set_nexthop(), in the FIB nexthop cache.
With help from Eric Dumazet.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/ip_fib.h | 2 +
net/ipv4/fib_semantics.c | 2 +
net/ipv4/route.c | 140 ++++++++++++++++++++++++++++++++--------------
3 files changed, 101 insertions(+), 43 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 2daf096..fb62c59 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -46,6 +46,7 @@ struct fib_config {
};
struct fib_info;
+struct rtable;
struct fib_nh_exception {
struct fib_nh_exception __rcu *fnhe_next;
@@ -80,6 +81,7 @@ struct fib_nh {
__be32 nh_gw;
__be32 nh_saddr;
int nh_saddr_genid;
+ struct rtable *nh_rth_output;
struct fnhe_hash_bucket *nh_exceptions;
};
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 2b57d76..83d0f42 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -171,6 +171,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
dev_put(nexthop_nh->nh_dev);
if (nexthop_nh->nh_exceptions)
free_nh_exceptions(nexthop_nh);
+ if (nexthop_nh->nh_rth_output)
+ dst_release(&nexthop_nh->nh_rth_output->dst);
} endfor_nexthops(fi);
release_net(fi->fib_net);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d52f769..8a02600 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1158,8 +1158,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
return mtu;
}
-static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
- struct fib_info *fi)
+static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
{
if (fi->fib_metrics != (u32 *) dst_default_metrics) {
rt->fi = fi;
@@ -1168,50 +1167,83 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
}
-static void rt_bind_exception(struct rtable *rt, struct fib_nh *nh, __be32 daddr)
+static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
{
struct fnhe_hash_bucket *hash = nh->nh_exceptions;
struct fib_nh_exception *fnhe;
u32 hval;
+ if (!hash)
+ return NULL;
+
hval = fnhe_hashfun(daddr);
-restart:
for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
- __be32 fnhe_daddr, gw;
- unsigned long expires;
- unsigned int seq;
- u32 pmtu;
-
- seq = read_seqbegin(&fnhe_seqlock);
- fnhe_daddr = fnhe->fnhe_daddr;
- gw = fnhe->fnhe_gw;
- pmtu = fnhe->fnhe_pmtu;
- expires = fnhe->fnhe_expires;
- if (read_seqretry(&fnhe_seqlock, seq))
- goto restart;
- if (daddr != fnhe_daddr)
- continue;
- if (pmtu) {
- unsigned long diff = expires - jiffies;
+ if (fnhe->fnhe_daddr == daddr)
+ return fnhe;
+ }
+ return NULL;
+}
- if (time_before(jiffies, expires)) {
- rt->rt_pmtu = pmtu;
- dst_set_expires(&rt->dst, diff);
- }
- }
- if (gw) {
- rt->rt_flags |= RTCF_REDIRECTED;
- rt->rt_gateway = gw;
+static void rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
+ __be32 daddr)
+{
+ __be32 fnhe_daddr, gw;
+ unsigned long expires;
+ unsigned int seq;
+ u32 pmtu;
+
+restart:
+ seq = read_seqbegin(&fnhe_seqlock);
+ fnhe_daddr = fnhe->fnhe_daddr;
+ gw = fnhe->fnhe_gw;
+ pmtu = fnhe->fnhe_pmtu;
+ expires = fnhe->fnhe_expires;
+ if (read_seqretry(&fnhe_seqlock, seq))
+ goto restart;
+
+ if (daddr != fnhe_daddr)
+ return;
+
+ if (pmtu) {
+ unsigned long diff = expires - jiffies;
+
+ if (time_before(jiffies, expires)) {
+ rt->rt_pmtu = pmtu;
+ dst_set_expires(&rt->dst, diff);
}
- fnhe->fnhe_stamp = jiffies;
- break;
+ }
+ if (gw) {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ rt->rt_gateway = gw;
+ }
+ fnhe->fnhe_stamp = jiffies;
+}
+
+static inline void rt_release_rcu(struct rcu_head *head)
+{
+ struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+ dst_release(dst);
+}
+
+static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
+{
+ struct rtable *orig, *prev, **p = &nh->nh_rth_output;
+
+ orig = *p;
+
+ prev = cmpxchg(p, orig, rt);
+ if (prev == orig) {
+ dst_clone(&rt->dst);
+ if (orig)
+ call_rcu_bh(&orig->dst.rcu_head, rt_release_rcu);
}
}
-static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
+static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
const struct fib_result *res,
+ struct fib_nh_exception *fnhe,
struct fib_info *fi, u16 type, u32 itag)
{
if (fi) {
@@ -1219,12 +1251,15 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
if (nh->nh_gw && nh->nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = nh->nh_gw;
- if (unlikely(nh->nh_exceptions))
- rt_bind_exception(rt, nh, fl4->daddr);
- rt_init_metrics(rt, fl4, fi);
+ if (unlikely(fnhe))
+ rt_bind_exception(rt, fnhe, daddr);
+ rt_init_metrics(rt, fi);
#ifdef CONFIG_IP_ROUTE_CLASSID
- rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
+ rt->dst.tclassid = nh->nh_tclassid;
#endif
+ if (!(rt->dst.flags & DST_HOST) &&
+ rt_is_output_route(rt))
+ rt_cache_route(nh, rt);
}
#ifdef CONFIG_IP_ROUTE_CLASSID
@@ -1236,10 +1271,10 @@ static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
}
static struct rtable *rt_dst_alloc(struct net_device *dev,
- bool nopolicy, bool noxfrm)
+ bool nopolicy, bool noxfrm, bool will_cache)
{
return dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK,
- DST_HOST | DST_NOCACHE |
+ (will_cache ? 0 : DST_HOST) | DST_NOCACHE |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
}
@@ -1276,7 +1311,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
goto e_err;
}
rth = rt_dst_alloc(dev_net(dev)->loopback_dev,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
if (!rth)
goto e_nobufs;
@@ -1349,6 +1384,7 @@ static int __mkroute_input(struct sk_buff *skb,
__be32 daddr, __be32 saddr, u32 tos,
struct rtable **result)
{
+ struct fib_nh_exception *fnhe;
struct rtable *rth;
int err;
struct in_device *out_dev;
@@ -1395,9 +1431,13 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
+ fnhe = NULL;
+ if (res->fi)
+ fnhe = find_exception(&FIB_RES_NH(*res), daddr);
+
rth = rt_dst_alloc(out_dev->dev,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(out_dev, NOXFRM));
+ IN_DEV_CONF_GET(out_dev, NOXFRM), false);
if (!rth) {
err = -ENOBUFS;
goto cleanup;
@@ -1416,7 +1456,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
- rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
+ rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
*result = rth;
err = 0;
@@ -1558,7 +1598,7 @@ brd_input:
local_input:
rth = rt_dst_alloc(net->loopback_dev,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
if (!rth)
goto e_nobufs;
@@ -1672,6 +1712,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
unsigned int flags)
{
struct fib_info *fi = res->fi;
+ struct fib_nh_exception *fnhe;
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
@@ -1710,9 +1751,22 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
fi = NULL;
}
+ fnhe = NULL;
+ if (fi) {
+ fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
+ if (!fnhe) {
+ rth = FIB_RES_NH(*res).nh_rth_output;
+ if (rth &&
+ rth->dst.obsolete == DST_OBSOLETE_FORCE_CHK) {
+ dst_use(&rth->dst, jiffies);
+ return rth;
+ }
+ }
+ }
rth = rt_dst_alloc(dev_out,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(in_dev, NOXFRM));
+ IN_DEV_CONF_GET(in_dev, NOXFRM),
+ fi && !fnhe);
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -1749,7 +1803,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
#endif
}
- rt_set_nexthop(rth, fl4, res, fi, type, 0);
+ rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0);
if (fl4->flowi4_flags & FLOWI_FLAG_RT_NOCACHE)
rth->dst.flags |= DST_NOCACHE;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 11/16] ipv4: Cache input routes in fib_info nexthops.
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
Caching input routes is slightly simpler than output routes, since we
don't need to be concerned with nexthop exceptions. (locally
destined, and routed packets, never trigger PMTU events or redirects
that will be processed by us).
However, we have to elide caching for the DIRECTSRC and non-zero itag
cases.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/ip_fib.h | 1 +
net/ipv4/fib_semantics.c | 2 ++
net/ipv4/route.c | 55 ++++++++++++++++++++++++++++++++++++----------
3 files changed, 46 insertions(+), 12 deletions(-)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index fb62c59..e69c3a4 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -82,6 +82,7 @@ struct fib_nh {
__be32 nh_saddr;
int nh_saddr_genid;
struct rtable *nh_rth_output;
+ struct rtable *nh_rth_input;
struct fnhe_hash_bucket *nh_exceptions;
};
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 83d0f42..e55171f 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -173,6 +173,8 @@ static void free_fib_info_rcu(struct rcu_head *head)
free_nh_exceptions(nexthop_nh);
if (nexthop_nh->nh_rth_output)
dst_release(&nexthop_nh->nh_rth_output->dst);
+ if (nexthop_nh->nh_rth_input)
+ dst_release(&nexthop_nh->nh_rth_input->dst);
} endfor_nexthops(fi);
release_net(fi->fib_net);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 8a02600..97cca8a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1231,6 +1231,9 @@ static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
{
struct rtable *orig, *prev, **p = &nh->nh_rth_output;
+ if (rt_is_input_route(rt))
+ p = &nh->nh_rth_input;
+
orig = *p;
prev = cmpxchg(p, orig, rt);
@@ -1241,6 +1244,11 @@ static void rt_cache_route(struct fib_nh *nh, struct rtable *rt)
}
}
+static bool rt_cache_valid(struct rtable *rt)
+{
+ return (rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK);
+}
+
static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
const struct fib_result *res,
struct fib_nh_exception *fnhe,
@@ -1257,8 +1265,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
- if (!(rt->dst.flags & DST_HOST) &&
- rt_is_output_route(rt))
+ if (!(rt->dst.flags & DST_HOST))
rt_cache_route(nh, rt);
}
@@ -1384,11 +1391,11 @@ static int __mkroute_input(struct sk_buff *skb,
__be32 daddr, __be32 saddr, u32 tos,
struct rtable **result)
{
- struct fib_nh_exception *fnhe;
struct rtable *rth;
int err;
struct in_device *out_dev;
unsigned int flags = 0;
+ bool do_cache;
u32 itag;
/* get a working reference to the output device */
@@ -1431,13 +1438,21 @@ static int __mkroute_input(struct sk_buff *skb,
}
}
- fnhe = NULL;
- if (res->fi)
- fnhe = find_exception(&FIB_RES_NH(*res), daddr);
+ do_cache = false;
+ if (res->fi) {
+ if (!(flags & RTCF_DIRECTSRC) && !itag) {
+ rth = FIB_RES_NH(*res).nh_rth_input;
+ if (rt_cache_valid(rth)) {
+ dst_use(&rth->dst, jiffies);
+ goto out;
+ }
+ do_cache = true;
+ }
+ }
rth = rt_dst_alloc(out_dev->dev,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(out_dev, NOXFRM), false);
+ IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache);
if (!rth) {
err = -ENOBUFS;
goto cleanup;
@@ -1456,8 +1471,8 @@ static int __mkroute_input(struct sk_buff *skb,
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
- rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag);
-
+ rt_set_nexthop(rth, daddr, res, NULL, res->fi, res->type, itag);
+out:
*result = rth;
err = 0;
cleanup:
@@ -1509,6 +1524,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
struct rtable *rth;
int err = -EINVAL;
struct net *net = dev_net(dev);
+ bool do_cache;
/* IP on this device is disabled. */
@@ -1522,6 +1538,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr))
goto martian_source;
+ res.fi = NULL;
if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
goto brd_input;
@@ -1597,8 +1614,20 @@ brd_input:
RT_CACHE_STAT_INC(in_brd);
local_input:
+ do_cache = false;
+ if (res.fi) {
+ if (!(flags & RTCF_DIRECTSRC) && !itag) {
+ rth = FIB_RES_NH(res).nh_rth_input;
+ if (rt_cache_valid(rth)) {
+ dst_use(&rth->dst, jiffies);
+ goto set_and_out;
+ }
+ do_cache = true;
+ }
+ }
+
rth = rt_dst_alloc(net->loopback_dev,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
+ IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache);
if (!rth)
goto e_nobufs;
@@ -1622,6 +1651,9 @@ local_input:
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
+ if (do_cache)
+ rt_cache_route(&FIB_RES_NH(res), rth);
+set_and_out:
skb_dst_set(skb, &rth->dst);
err = 0;
goto out;
@@ -1756,8 +1788,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
fnhe = find_exception(&FIB_RES_NH(*res), fl4->daddr);
if (!fnhe) {
rth = FIB_RES_NH(*res).nh_rth_output;
- if (rth &&
- rth->dst.obsolete == DST_OBSOLETE_FORCE_CHK) {
+ if (rt_cache_valid(rth)) {
dst_use(&rth->dst, jiffies);
return rth;
}
--
1.7.10.4
^ permalink raw reply related
* [PATCH 12/16] ipv4: Kill FLOWI_FLAG_RT_NOCACHE and associated code.
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/flow.h | 1 -
include/net/inet_connection_sock.h | 3 +--
net/dccp/ipv4.c | 2 +-
net/ipv4/inet_connection_sock.c | 5 +----
net/ipv4/route.c | 3 ---
net/ipv4/tcp_ipv4.c | 4 ++--
6 files changed, 5 insertions(+), 13 deletions(-)
diff --git a/include/net/flow.h b/include/net/flow.h
index ce9cb76..e1dd508 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -21,7 +21,6 @@ struct flowi_common {
__u8 flowic_flags;
#define FLOWI_FLAG_ANYSRC 0x01
#define FLOWI_FLAG_CAN_SLEEP 0x02
-#define FLOWI_FLAG_RT_NOCACHE 0x04
__u32 flowic_secid;
};
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 2cf44b4..5ee66f5 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -250,8 +250,7 @@ extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
extern struct dst_entry* inet_csk_route_req(struct sock *sk,
struct flowi4 *fl4,
- const struct request_sock *req,
- bool nocache);
+ const struct request_sock *req);
extern struct dst_entry* inet_csk_route_child_sock(struct sock *sk,
struct sock *newsk,
const struct request_sock *req);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index ab4f44c..25428d0 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -508,7 +508,7 @@ static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
struct dst_entry *dst;
struct flowi4 fl4;
- dst = inet_csk_route_req(sk, &fl4, req, false);
+ dst = inet_csk_route_req(sk, &fl4, req);
if (dst == NULL)
goto out;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 0a290d7..db0cf17 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -368,8 +368,7 @@ EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
struct dst_entry *inet_csk_route_req(struct sock *sk,
struct flowi4 *fl4,
- const struct request_sock *req,
- bool nocache)
+ const struct request_sock *req)
{
struct rtable *rt;
const struct inet_request_sock *ireq = inet_rsk(req);
@@ -377,8 +376,6 @@ struct dst_entry *inet_csk_route_req(struct sock *sk,
struct net *net = sock_net(sk);
int flags = inet_sk_flowi_flags(sk);
- if (nocache)
- flags |= FLOWI_FLAG_RT_NOCACHE;
flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark,
RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE,
sk->sk_protocol,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 97cca8a..7e1c0ed 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1836,9 +1836,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0);
- if (fl4->flowi4_flags & FLOWI_FLAG_RT_NOCACHE)
- rth->dst.flags |= DST_NOCACHE;
-
return rth;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1d8b75a..59110ca 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -824,7 +824,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
struct sk_buff * skb;
/* First, grab a route. */
- if (!dst && (dst = inet_csk_route_req(sk, &fl4, req, nocache)) == NULL)
+ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
return -1;
skb = tcp_make_synack(sk, dst, req, rvp);
@@ -1378,7 +1378,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
*/
if (tmp_opt.saw_tstamp &&
tcp_death_row.sysctl_tw_recycle &&
- (dst = inet_csk_route_req(sk, &fl4, req, want_cookie)) != NULL &&
+ (dst = inet_csk_route_req(sk, &fl4, req)) != NULL &&
fl4.daddr == saddr) {
if (!tcp_peer_is_proven(req, dst, true)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSPASSIVEREJECTED);
--
1.7.10.4
^ permalink raw reply related
* [PATCH 13/16] ipv4: Dirty less cache lines in route caching paths.
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
Don't bother incrementing dst->__use and setting dst->lastuse,
they are completely pointless and just slow things down.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
net/ipv4/route.c | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7e1c0ed..b870777 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1443,7 +1443,7 @@ static int __mkroute_input(struct sk_buff *skb,
if (!(flags & RTCF_DIRECTSRC) && !itag) {
rth = FIB_RES_NH(*res).nh_rth_input;
if (rt_cache_valid(rth)) {
- dst_use(&rth->dst, jiffies);
+ dst_hold(&rth->dst);
goto out;
}
do_cache = true;
@@ -1619,7 +1619,7 @@ local_input:
if (!(flags & RTCF_DIRECTSRC) && !itag) {
rth = FIB_RES_NH(res).nh_rth_input;
if (rt_cache_valid(rth)) {
- dst_use(&rth->dst, jiffies);
+ dst_hold(&rth->dst);
goto set_and_out;
}
do_cache = true;
@@ -1789,7 +1789,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
if (!fnhe) {
rth = FIB_RES_NH(*res).nh_rth_output;
if (rt_cache_valid(rth)) {
- dst_use(&rth->dst, jiffies);
+ dst_hold(&rth->dst);
return rth;
}
}
--
1.7.10.4
^ permalink raw reply related
* [PATCH 14/16] ipv4: Kill rt->rt_oif
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
Never actually used.
It was being set on output routes to the original OIF specified in the
flow key used for the lookup.
Adjust the only user, ipmr_rt_fib_lookup(), for greater correctness of
the flowi4_oif and flowi4_iif values, thanks to feedback from Julian
Anastasov.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/ipmr.c | 7 +++++--
net/ipv4/route.c | 5 -----
net/ipv4/xfrm4_policy.c | 1 -
4 files changed, 5 insertions(+), 9 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 3c1eeab..e789a92 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -50,7 +50,6 @@ struct rtable {
int rt_route_iif;
int rt_iif;
- int rt_oif;
/* Info on neighbour */
__be32 rt_gateway;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index eee3bf6..8eec8f4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1795,8 +1795,11 @@ static struct mr_table *ipmr_rt_fib_lookup(struct net *net, struct sk_buff *skb)
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowi4_tos = RT_TOS(iph->tos),
- .flowi4_oif = rt->rt_oif,
- .flowi4_iif = rt->rt_iif,
+ .flowi4_oif = (rt_is_output_route(rt) ?
+ skb->dev->ifindex : 0),
+ .flowi4_iif = (rt_is_output_route(rt) ?
+ net->loopback_dev->ifindex :
+ skb->dev->ifindex),
.flowi4_mark = skb->mark,
};
struct mr_table *mrt;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index b870777..a280b6a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1332,7 +1332,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_type = RTN_MULTICAST;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
- rth->rt_oif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->fi = NULL;
@@ -1463,7 +1462,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_type = res->type;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
- rth->rt_oif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->fi = NULL;
@@ -1642,7 +1640,6 @@ local_input:
rth->rt_type = res.type;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
- rth->rt_oif = 0;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->fi = NULL;
@@ -1808,7 +1805,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_type = type;
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
- rth->rt_oif = orig_oif;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
rth->fi = NULL;
@@ -2085,7 +2081,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
- rt->rt_oif = ort->rt_oif;
rt->rt_pmtu = ort->rt_pmtu;
rt->rt_genid = rt_genid(net);
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6074b69..3c99b4c 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -81,7 +81,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
xdst->u.rt.rt_iif = fl4->flowi4_iif;
- xdst->u.rt.rt_oif = fl4->flowi4_oif;
xdst->u.dst.dev = dev;
dev_hold(dev);
--
1.7.10.4
^ permalink raw reply related
* [PATCH 15/16] ipv4: Turn rt->rt_route_iif into rt->rt_is_input.
From: David Miller @ 2012-07-20 21:26 UTC (permalink / raw)
To: netdev
That is this value's only use, as a boolean to indicate whether
a route is an input route or not.
So implement it that way, using a u16 gap present in the struct
already.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 6 +++---
net/ipv4/route.c | 10 +++++-----
net/ipv4/xfrm4_policy.c | 2 +-
3 files changed, 9 insertions(+), 9 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index e789a92..4bafe0b 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -47,8 +47,8 @@ struct rtable {
int rt_genid;
unsigned int rt_flags;
__u16 rt_type;
+ __u16 rt_is_input;
- int rt_route_iif;
int rt_iif;
/* Info on neighbour */
@@ -61,12 +61,12 @@ struct rtable {
static inline bool rt_is_input_route(const struct rtable *rt)
{
- return rt->rt_route_iif != 0;
+ return rt->rt_is_input != 0;
}
static inline bool rt_is_output_route(const struct rtable *rt)
{
- return rt->rt_route_iif == 0;
+ return rt->rt_is_input == 0;
}
static inline __be32 rt_nexthop(const struct rtable *rt, __be32 daddr)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a280b6a..fac4c4a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1330,7 +1330,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_genid = rt_genid(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
- rth->rt_route_iif = dev->ifindex;
+ rth->rt_is_input= 1;
rth->rt_iif = dev->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
@@ -1460,7 +1460,7 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rth->rt_flags = flags;
rth->rt_type = res->type;
- rth->rt_route_iif = in_dev->dev->ifindex;
+ rth->rt_is_input = 1;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
@@ -1638,7 +1638,7 @@ local_input:
rth->rt_genid = rt_genid(net);
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
- rth->rt_route_iif = dev->ifindex;
+ rth->rt_is_input = 1;
rth->rt_iif = dev->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
@@ -1803,7 +1803,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
- rth->rt_route_iif = 0;
+ rth->rt_is_input = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
@@ -2079,7 +2079,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
if (new->dev)
dev_hold(new->dev);
- rt->rt_route_iif = ort->rt_route_iif;
+ rt->rt_is_input = ort->rt_is_input;
rt->rt_iif = ort->rt_iif;
rt->rt_pmtu = ort->rt_pmtu;
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 3c99b4c..c628184 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -79,7 +79,6 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
struct rtable *rt = (struct rtable *)xdst->route;
const struct flowi4 *fl4 = &fl->u.ip4;
- xdst->u.rt.rt_route_iif = fl4->flowi4_iif;
xdst->u.rt.rt_iif = fl4->flowi4_iif;
xdst->u.dst.dev = dev;
@@ -87,6 +86,7 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
/* Sheit... I remember I did this right. Apparently,
* it was magically lost, so this code needs audit */
+ xdst->u.rt.rt_is_input = rt->rt_is_input;
xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST |
RTCF_LOCAL);
xdst->u.rt.rt_type = rt->rt_type;
--
1.7.10.4
^ permalink raw reply related
* [PATCH 16/16] ipv4: Kill rt->fi
From: David Miller @ 2012-07-20 21:27 UTC (permalink / raw)
To: netdev
It's not really needed.
We only grabbed a reference to the fib_info for the sake of fib_info
local metrics.
However, fib_info objects are freed using RCU, as are therefore their
private metrics (if any).
We would have triggered a route cache flush if we eliminated a
reference to a fib_info object in the routing tables.
Therefore, any existing cached routes will first check and see that
they have been invalidated before an errant reference to these
metric values would occur.
Signed-off-by: David S. Miller <davem@davemloft.net>
---
include/net/route.h | 1 -
net/ipv4/route.c | 32 +-------------------------------
2 files changed, 1 insertion(+), 32 deletions(-)
diff --git a/include/net/route.h b/include/net/route.h
index 4bafe0b..60d611d 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -56,7 +56,6 @@ struct rtable {
/* Miscellaneous cached information */
u32 rt_pmtu;
- struct fib_info *fi; /* for client ref to shared metrics */
};
static inline bool rt_is_input_route(const struct rtable *rt)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index fac4c4a..9add088 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -141,7 +141,6 @@ static int ip_rt_min_advmss __read_mostly = 256;
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
static unsigned int ipv4_mtu(const struct dst_entry *dst);
-static void ipv4_dst_destroy(struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
@@ -171,7 +170,6 @@ static struct dst_ops ipv4_dst_ops = {
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
- .destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
@@ -1034,17 +1032,6 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
return dst;
}
-static void ipv4_dst_destroy(struct dst_entry *dst)
-{
- struct rtable *rt = (struct rtable *) dst;
-
- if (rt->fi) {
- fib_info_put(rt->fi);
- rt->fi = NULL;
- }
-}
-
-
static void ipv4_link_failure(struct sk_buff *skb)
{
struct rtable *rt;
@@ -1158,15 +1145,6 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
return mtu;
}
-static void rt_init_metrics(struct rtable *rt, struct fib_info *fi)
-{
- if (fi->fib_metrics != (u32 *) dst_default_metrics) {
- rt->fi = fi;
- atomic_inc(&fi->fib_clntref);
- }
- dst_init_metrics(&rt->dst, fi->fib_metrics, true);
-}
-
static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
{
struct fnhe_hash_bucket *hash = nh->nh_exceptions;
@@ -1261,7 +1239,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
rt->rt_gateway = nh->nh_gw;
if (unlikely(fnhe))
rt_bind_exception(rt, fnhe, daddr);
- rt_init_metrics(rt, fi);
+ dst_init_metrics(&rt->dst, fi->fib_metrics, true);
#ifdef CONFIG_IP_ROUTE_CLASSID
rt->dst.tclassid = nh->nh_tclassid;
#endif
@@ -1334,7 +1312,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
rth->rt_iif = dev->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
- rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
@@ -1464,7 +1441,6 @@ static int __mkroute_input(struct sk_buff *skb,
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
- rth->fi = NULL;
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
@@ -1642,7 +1618,6 @@ local_input:
rth->rt_iif = dev->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
- rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
@@ -1807,7 +1782,6 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_pmtu = 0;
rth->rt_gateway = 0;
- rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
@@ -2052,7 +2026,6 @@ static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
- .destroy = ipv4_dst_destroy,
.check = ipv4_blackhole_dst_check,
.mtu = ipv4_blackhole_mtu,
.default_advmss = ipv4_default_advmss,
@@ -2087,9 +2060,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
- rt->fi = ort->fi;
- if (rt->fi)
- atomic_inc(&rt->fi->fib_clntref);
dst_free(new);
}
--
1.7.10.4
^ permalink raw reply related
* [PATCH RFT] net: Fix Neptune ethernet driver to check dma mapping error
From: Shuah Khan @ 2012-07-20 21:27 UTC (permalink / raw)
To: davem, mcarlson, bhutchings, eric.dumazet, mchan
Cc: netdev, LKML, shuahkhan, stable
Request for testing, since I don't have the hardware to test.
--------------------------------------------------------------------
Fix Neptune ethernet driver to check dma mapping error after map_page()
interface returns.
Signed-off-by: Shuah Khan <shuah.khan@hp.com>
Cc: <stable@vger.kernel.org>
---
drivers/net/ethernet/sun/niu.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 8c726b7..60d5c03 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -3335,6 +3335,10 @@ static int niu_rbr_add_page(struct niu *np, struct rx_ring_info *rp,
addr = np->ops->map_page(np->device, page, 0,
PAGE_SIZE, DMA_FROM_DEVICE);
+ if (!addr) {
+ __free_page(page);
+ return -ENOMEM;
+ }
niu_hash_page(rp, page, addr);
if (rp->rbr_blocks_per_page > 1)
--
1.7.9.5
^ permalink raw reply related
* Re: [PATCH RFT] net: Fix Neptune ethernet driver to check dma mapping error
From: David Miller @ 2012-07-20 21:30 UTC (permalink / raw)
To: shuah.khan
Cc: mcarlson, bhutchings, eric.dumazet, mchan, netdev, linux-kernel,
shuahkhan, stable
In-Reply-To: <1342819679.5434.50.camel@lorien2>
From: Shuah Khan <shuah.khan@hp.com>
Date: Fri, 20 Jul 2012 15:27:59 -0600
> Request for testing, since I don't have the hardware to test.
This is not how you post a patch.
> --------------------------------------------------------------------
When you put those "---..." there, GIT is going to eliminate everything
afterwards from the commit mesage when I apply this. Yet afterwards
is what your commit message actually is.
You therefore should do things the other way around, provide the commit
message text, then the "---..." line, then your comments you don't want
in the final commit message.
^ permalink raw reply
* Re: [PATCH] net: ethernet: davinci_emac: add pm_runtime support
From: Mark A. Greer @ 2012-07-20 21:30 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-omap, linux-arm-kernel, nsekhar, khilman
In-Reply-To: <20120720.112301.1733694549621760738.davem@davemloft.net>
On Fri, Jul 20, 2012 at 11:23:01AM -0700, David Miller wrote:
> From: "Mark A. Greer" <mgreer@animalcreek.com>
> Date: Thu, 19 Jul 2012 15:22:57 -0700
>
> > From: "Mark A. Greer" <mgreer@animalcreek.com>
> >
> > Add pm_runtime support to the TI Davinci EMAC driver.
> >
> > CC: Sekhar Nori <nsekhar@ti.com>
> > CC: Kevin Hilman <khilman@ti.com>
> > Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
>
> This patch doesn't apply at all to net-next
My apologies. I'll fix & resubmit in a bit.
Mark
^ permalink raw reply
* Re: [PATCH RFT] net: Fix Neptune ethernet driver to check dma mapping error
From: Shuah Khan @ 2012-07-20 21:36 UTC (permalink / raw)
To: David Miller
Cc: mcarlson, bhutchings, eric.dumazet, mchan, netdev, linux-kernel,
stable
In-Reply-To: <20120720.143005.135422510157595877.davem@davemloft.net>
On Fri, 2012-07-20 at 14:30 -0700, David Miller wrote:
> From: Shuah Khan <shuah.khan@hp.com>
> Date: Fri, 20 Jul 2012 15:27:59 -0600
>
> > Request for testing, since I don't have the hardware to test.
>
> This is not how you post a patch.
>
> > --------------------------------------------------------------------
>
> When you put those "---..." there, GIT is going to eliminate everything
> afterwards from the commit mesage when I apply this. Yet afterwards
> is what your commit message actually is.
>
> You therefore should do things the other way around, provide the commit
> message text, then the "---..." line, then your comments you don't want
> in the final commit message.
Thanks. I had it reversed in my head for some reason. Maybe not enough
coffee :) Will resend the patch now.
-- Shuah
^ permalink raw reply
* Re: [PATCH] net: ethernet: davinci_emac: add pm_runtime support
From: Mark A. Greer @ 2012-07-20 21:42 UTC (permalink / raw)
To: Sekhar Nori
Cc: netdev, linux-omap, linux-arm-kernel, Kevin Hilman, David Miller,
davinci-linux-open-source@linux.davincidsp.com
In-Reply-To: <50095B8C.3050502@ti.com>
On Fri, Jul 20, 2012 at 06:52:20PM +0530, Sekhar Nori wrote:
> + Dave Miller and DaVinci list
>
> Hi Mark,
>
> On 7/20/2012 3:52 AM, Mark A. Greer wrote:
> > From: "Mark A. Greer" <mgreer@animalcreek.com>
> >
> > Add pm_runtime support to the TI Davinci EMAC driver.
> >
> > CC: Sekhar Nori <nsekhar@ti.com>
> > CC: Kevin Hilman <khilman@ti.com>
> > Signed-off-by: Mark A. Greer <mgreer@animalcreek.com>
>
> Tested on AM18x EVM using NFS root and suspend-to-RAM.
>
> Acked-by: Sekhar Nori <nsekhar@ti.com>
Thanks for testing, Sekhar.
Mark
^ permalink raw reply
* [net-next 0/6][pull request] Intel Wired LAN Driver Updates
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem; +Cc: Jeff Kirsher, netdev, gospo, sassmann
This series contains updates to ethtool, e1000, e1000e and igb with
regards to the new MDI ethtool support patches submitted earlier.
The following are changes since commit fa0afcd10951afad2022dda09777d2bf70cdab3d:
atl1c: fix issue of io access mode for AR8152 v2.1
and are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-next master
Bruce W Allan (1):
e1000e: implement 82577/579 MDI setting support
Jesse Brandeburg (5):
ethtool.h: MDI setting support
igb: implement 580 MDI setting support
e1000: configure and read MDI settings
e1000e: implement MDI/MDI-X control
igb: update to allow reading/setting MDI state
drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 34 +++++++++++++++++++
drivers/net/ethernet/intel/e1000/e1000_main.c | 4 +++
drivers/net/ethernet/intel/e1000e/ethtool.c | 39 +++++++++++++++++++---
drivers/net/ethernet/intel/e1000e/phy.c | 31 +++++++++++++++--
drivers/net/ethernet/intel/igb/e1000_phy.c | 29 ++++++++++++++--
drivers/net/ethernet/intel/igb/e1000_phy.h | 5 +--
drivers/net/ethernet/intel/igb/igb_ethtool.c | 37 ++++++++++++++++++++
drivers/net/ethernet/intel/igb/igb_main.c | 4 +++
include/linux/ethtool.h | 17 ++++++----
9 files changed, 184 insertions(+), 16 deletions(-)
--
1.7.10.4
^ permalink raw reply
* [net-next 2/6] e1000e: implement 82577/579 MDI setting support
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem
Cc: Bruce W Allan, netdev, gospo, sassmann, Jesse Brandeburg,
Jeff Kirsher
In-Reply-To: <1342820631-19738-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Bruce W Allan <bruce.w.allan@intel.com>
in order for e1000e to support MDI setting support via
ethtool this code is needed to allow setting the MDI state
via software.
This is in regards to the related ethtool patch and
fixes bugzilla.kernel.org bug 11998
Signed-off-by: Bruce W Allan <bruce.w.allan@intel.com>
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/phy.c | 31 +++++++++++++++++++++++++++++--
1 file changed, 29 insertions(+), 2 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c
index b860d4f..fc62a3f 100644
--- a/drivers/net/ethernet/intel/e1000e/phy.c
+++ b/drivers/net/ethernet/intel/e1000e/phy.c
@@ -84,8 +84,9 @@ static const u16 e1000_igp_2_cable_length_table[] = {
#define I82577_PHY_STATUS2_SPEED_1000MBPS 0x0200
/* I82577 PHY Control 2 */
-#define I82577_PHY_CTRL2_AUTO_MDIX 0x0400
-#define I82577_PHY_CTRL2_FORCE_MDI_MDIX 0x0200
+#define I82577_PHY_CTRL2_MANUAL_MDIX 0x0200
+#define I82577_PHY_CTRL2_AUTO_MDI_MDIX 0x0400
+#define I82577_PHY_CTRL2_MDIX_CFG_MASK 0x0600
/* I82577 PHY Diagnostics Status */
#define I82577_DSTATUS_CABLE_LENGTH 0x03FC
@@ -702,6 +703,32 @@ s32 e1000_copper_link_setup_82577(struct e1000_hw *hw)
if (ret_val)
return ret_val;
+ /* Set MDI/MDIX mode */
+ ret_val = e1e_rphy(hw, I82577_PHY_CTRL_2, &phy_data);
+ if (ret_val)
+ return ret_val;
+ phy_data &= ~I82577_PHY_CTRL2_MDIX_CFG_MASK;
+ /*
+ * Options:
+ * 0 - Auto (default)
+ * 1 - MDI mode
+ * 2 - MDI-X mode
+ */
+ switch (hw->phy.mdix) {
+ case 1:
+ break;
+ case 2:
+ phy_data |= I82577_PHY_CTRL2_MANUAL_MDIX;
+ break;
+ case 0:
+ default:
+ phy_data |= I82577_PHY_CTRL2_AUTO_MDI_MDIX;
+ break;
+ }
+ ret_val = e1e_wphy(hw, I82577_PHY_CTRL_2, phy_data);
+ if (ret_val)
+ return ret_val;
+
return e1000_set_master_slave_mode(hw);
}
--
1.7.10.4
^ permalink raw reply related
* [net-next 1/6] ethtool.h: MDI setting support
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem
Cc: Jesse Brandeburg, netdev, gospo, sassmann, Ben Hutchings,
Jeff Kirsher
In-Reply-To: <1342820631-19738-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
This change modifies the core ethtool struct to allow a driver to
support setting of MDI/MDI-X state for twisted pair wiring. This
change uses a previously reserved u8 and should not change any
binary compatibility of ethtool.
Also as per Ben Hutchings' suggestion, the capabilities are
stored in a separate byte so the driver can report if it supports
changing settings.
see thread: http://kerneltrap.org/mailarchive/linux-netdev/2010/11/17/6289820/thread
see ethtool patches titled:
ethtool: allow setting MDI-X state
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Ben Hutchings <bhutchings@solarflare.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
include/linux/ethtool.h | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 21eff41..fcb4f8e 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -45,8 +45,10 @@ struct ethtool_cmd {
* bits) in Mbps. Please use
* ethtool_cmd_speed()/_set() to
* access it */
- __u8 eth_tp_mdix;
- __u8 reserved2;
+ __u8 eth_tp_mdix; /* twisted pair MDI-X status */
+ __u8 eth_tp_mdix_ctrl; /* twisted pair MDI-X control, when set,
+ * link should be renegotiated if necessary
+ */
__u32 lp_advertising; /* Features the link partner advertises */
__u32 reserved[2];
};
@@ -1229,10 +1231,13 @@ struct ethtool_ops {
#define AUTONEG_DISABLE 0x00
#define AUTONEG_ENABLE 0x01
-/* Mode MDI or MDI-X */
-#define ETH_TP_MDI_INVALID 0x00
-#define ETH_TP_MDI 0x01
-#define ETH_TP_MDI_X 0x02
+/* MDI or MDI-X status/control - if MDI/MDI_X/AUTO is set then
+ * the driver is required to renegotiate link
+ */
+#define ETH_TP_MDI_INVALID 0x00 /* status: unknown; control: unsupported */
+#define ETH_TP_MDI 0x01 /* status: MDI; control: force MDI */
+#define ETH_TP_MDI_X 0x02 /* status: MDI-X; control: force MDI-X */
+#define ETH_TP_MDI_AUTO 0x03 /* control: auto-select */
/* Wake-On-Lan options. */
#define WAKE_PHY (1 << 0)
--
1.7.10.4
^ permalink raw reply related
* [net-next 3/6] igb: implement 580 MDI setting support
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem; +Cc: Jesse Brandeburg, netdev, gospo, sassmann, Jeff Kirsher
In-Reply-To: <1342820631-19738-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
In order for igb to support MDI setting support via
ethtool this code is needed to allow setting the MDI state
via software.
This is in regards to the related ethtool patch
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/e1000_phy.c | 29 ++++++++++++++++++++++++++--
drivers/net/ethernet/intel/igb/e1000_phy.h | 5 +++--
2 files changed, 30 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 7be98b6..3404bc7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -464,6 +464,32 @@ s32 igb_copper_link_setup_82580(struct e1000_hw *hw)
phy_data |= I82580_CFG_ENABLE_DOWNSHIFT;
ret_val = phy->ops.write_reg(hw, I82580_CFG_REG, phy_data);
+ if (ret_val)
+ goto out;
+
+ /* Set MDI/MDIX mode */
+ ret_val = phy->ops.read_reg(hw, I82580_PHY_CTRL_2, &phy_data);
+ if (ret_val)
+ goto out;
+ phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK;
+ /*
+ * Options:
+ * 0 - Auto (default)
+ * 1 - MDI mode
+ * 2 - MDI-X mode
+ */
+ switch (hw->phy.mdix) {
+ case 1:
+ break;
+ case 2:
+ phy_data |= I82580_PHY_CTRL2_MANUAL_MDIX;
+ break;
+ case 0:
+ default:
+ phy_data |= I82580_PHY_CTRL2_AUTO_MDI_MDIX;
+ break;
+ }
+ ret_val = hw->phy.ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data);
out:
return ret_val;
@@ -2246,8 +2272,7 @@ s32 igb_phy_force_speed_duplex_82580(struct e1000_hw *hw)
if (ret_val)
goto out;
- phy_data &= ~I82580_PHY_CTRL2_AUTO_MDIX;
- phy_data &= ~I82580_PHY_CTRL2_FORCE_MDI_MDIX;
+ phy_data &= ~I82580_PHY_CTRL2_MDIX_CFG_MASK;
ret_val = phy->ops.write_reg(hw, I82580_PHY_CTRL_2, phy_data);
if (ret_val)
diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h
index 34e4061..6ac3299 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.h
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.h
@@ -111,8 +111,9 @@ s32 igb_check_polarity_m88(struct e1000_hw *hw);
#define I82580_PHY_STATUS2_SPEED_100MBPS 0x0100
/* I82580 PHY Control 2 */
-#define I82580_PHY_CTRL2_AUTO_MDIX 0x0400
-#define I82580_PHY_CTRL2_FORCE_MDI_MDIX 0x0200
+#define I82580_PHY_CTRL2_MANUAL_MDIX 0x0200
+#define I82580_PHY_CTRL2_AUTO_MDI_MDIX 0x0400
+#define I82580_PHY_CTRL2_MDIX_CFG_MASK 0x0600
/* I82580 PHY Diagnostics Status */
#define I82580_DSTATUS_CABLE_LENGTH 0x03FC
--
1.7.10.4
^ permalink raw reply related
* [net-next 5/6] e1000e: implement MDI/MDI-X control
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem
Cc: Jesse Brandeburg, netdev, gospo, sassmann, bruce.w.allan,
n.poppelier, bastien, jsveiga, Jeff Kirsher
In-Reply-To: <1342820631-19738-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
Some users report issues with link failing when connected to certain
switches. This gives the user the ability to control the MDI state
from the driver, allowing users to work around some improperly
behaving switches.
Current get_settings behavior slightly changes in that now when link
is down get_settings will return the MDI state of the last link
because get_settings needs to succeed to allow the set to work even
when link is down.
Forcing in this driver is for now only allowed when auto-neg is
enabled.
This is in regards to the related ethtool app patch and
bugzilla.kernel.org bug 11998
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: bruce.w.allan@intel.com
CC: n.poppelier@xs4all.nl
CC: bastien@durel.org
CC: jsveiga@it.eng.br
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000e/ethtool.c | 39 ++++++++++++++++++++++++---
1 file changed, 35 insertions(+), 4 deletions(-)
diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c
index 105d554..9b1e082 100644
--- a/drivers/net/ethernet/intel/e1000e/ethtool.c
+++ b/drivers/net/ethernet/intel/e1000e/ethtool.c
@@ -192,8 +192,7 @@ static int e1000_get_settings(struct net_device *netdev,
hw->mac.autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
/* MDI-X => 2; MDI =>1; Invalid =>0 */
- if ((hw->phy.media_type == e1000_media_type_copper) &&
- netif_carrier_ok(netdev))
+ if (hw->phy.media_type == e1000_media_type_copper)
ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
ETH_TP_MDI;
else
@@ -241,6 +240,10 @@ static int e1000_set_spd_dplx(struct e1000_adapter *adapter, u32 spd, u8 dplx)
default:
goto err_inval;
}
+
+ /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+ adapter->hw.phy.mdix = AUTO_ALL_MODES;
+
return 0;
err_inval:
@@ -264,6 +267,22 @@ static int e1000_set_settings(struct net_device *netdev,
return -EINVAL;
}
+ /*
+ * MDI setting is only allowed when autoneg enabled because
+ * some hardware doesn't allow MDI setting when speed or
+ * duplex is forced.
+ */
+ if (ecmd->eth_tp_mdix_ctrl) {
+ if (hw->phy.media_type != e1000_media_type_copper)
+ return -EOPNOTSUPP;
+
+ if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+ (ecmd->autoneg != AUTONEG_ENABLE)) {
+ e_err("forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+ return -EINVAL;
+ }
+ }
+
while (test_and_set_bit(__E1000_RESETTING, &adapter->state))
usleep_range(1000, 2000);
@@ -282,20 +301,32 @@ static int e1000_set_settings(struct net_device *netdev,
hw->fc.requested_mode = e1000_fc_default;
} else {
u32 speed = ethtool_cmd_speed(ecmd);
+ /* calling this overrides forced MDI setting */
if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
clear_bit(__E1000_RESETTING, &adapter->state);
return -EINVAL;
}
}
+ /* MDI-X => 2; MDI => 1; Auto => 3 */
+ if (ecmd->eth_tp_mdix_ctrl) {
+ /*
+ * fix up the value for auto (3 => 0) as zero is mapped
+ * internally to auto
+ */
+ if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ hw->phy.mdix = AUTO_ALL_MODES;
+ else
+ hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+ }
+
/* reset the link */
if (netif_running(adapter->netdev)) {
e1000e_down(adapter);
e1000e_up(adapter);
- } else {
+ } else
e1000e_reset(adapter);
- }
clear_bit(__E1000_RESETTING, &adapter->state);
return 0;
--
1.7.10.4
^ permalink raw reply related
* [net-next 4/6] e1000: configure and read MDI settings
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem; +Cc: Jesse Brandeburg, netdev, gospo, sassmann, Tushar Dave,
Jeff Kirsher
In-Reply-To: <1342820631-19738-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
This is the implementation in e1000 to allow ethtool to force
MDI state, allowing users to work around some improperly
behaving switches.
Current get_settings behavior slightly changes in that now when link is down
get_settings will return the MDI state of the last link because get_settings
needs to succeed to allow the set to work even when link is down.
Forcing in this driver is for now only allowed when auto-neg is enabled.
To use must have the matching version of ethtool app that supports
this functionality.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Tushar Dave <tushar.n.dave@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/e1000/e1000_ethtool.c | 34 ++++++++++++++++++++++
drivers/net/ethernet/intel/e1000/e1000_main.c | 4 +++
2 files changed, 38 insertions(+)
diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
index 3103f0b..1d96bda 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c
@@ -174,6 +174,15 @@ static int e1000_get_settings(struct net_device *netdev,
ecmd->autoneg = ((hw->media_type == e1000_media_type_fiber) ||
hw->autoneg) ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+ /* MDI-X => 1; MDI => 0 */
+ if (hw->media_type == e1000_media_type_copper)
+ ecmd->eth_tp_mdix = (!!adapter->phy_info.mdix_mode ?
+ ETH_TP_MDI_X :
+ ETH_TP_MDI);
+ else
+ ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+
return 0;
}
@@ -183,6 +192,22 @@ static int e1000_set_settings(struct net_device *netdev,
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
+ /*
+ * MDI setting is only allowed when autoneg enabled because
+ * some hardware doesn't allow MDI setting when speed or
+ * duplex is forced.
+ */
+ if (ecmd->eth_tp_mdix_ctrl) {
+ if (hw->media_type != e1000_media_type_copper)
+ return -EOPNOTSUPP;
+
+ if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+ (ecmd->autoneg != AUTONEG_ENABLE)) {
+ e_err(drv, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+ return -EINVAL;
+ }
+ }
+
while (test_and_set_bit(__E1000_RESETTING, &adapter->flags))
msleep(1);
@@ -199,12 +224,21 @@ static int e1000_set_settings(struct net_device *netdev,
ecmd->advertising = hw->autoneg_advertised;
} else {
u32 speed = ethtool_cmd_speed(ecmd);
+ /* calling this overrides forced MDI setting */
if (e1000_set_spd_dplx(adapter, speed, ecmd->duplex)) {
clear_bit(__E1000_RESETTING, &adapter->flags);
return -EINVAL;
}
}
+ /* MDI-X => 2; MDI => 1; Auto => 3 */
+ if (ecmd->eth_tp_mdix_ctrl) {
+ if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ hw->mdix = AUTO_ALL_MODES;
+ else
+ hw->mdix = ecmd->eth_tp_mdix_ctrl;
+ }
+
/* reset the link */
if (netif_running(adapter->netdev)) {
diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c
index 3bfbb8d..0ae2fcf 100644
--- a/drivers/net/ethernet/intel/e1000/e1000_main.c
+++ b/drivers/net/ethernet/intel/e1000/e1000_main.c
@@ -4939,6 +4939,10 @@ int e1000_set_spd_dplx(struct e1000_adapter *adapter, u32 spd, u8 dplx)
default:
goto err_inval;
}
+
+ /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+ hw->mdix = AUTO_ALL_MODES;
+
return 0;
err_inval:
--
1.7.10.4
^ permalink raw reply related
* [net-next 6/6] igb: update to allow reading/setting MDI state
From: Jeff Kirsher @ 2012-07-20 21:43 UTC (permalink / raw)
To: davem
Cc: Jesse Brandeburg, netdev, gospo, sassmann, Carolyn Wyborny,
Jeff Kirsher
In-Reply-To: <1342820631-19738-1-git-send-email-jeffrey.t.kirsher@intel.com>
From: Jesse Brandeburg <jesse.brandeburg@intel.com>
This is the implementation for igb to allow forcing MDI state
via ethtool, allowing users to work around some improperly
behaving switches.
get_settings will now return the MDI state of the last link
because get_settings needs to succeed to allow the set to work even
when link is down.
Forcing in this driver is for now only allowed when auto-neg is
enabled.
Signed-off-by: Jesse Brandeburg <jesse.brandeburg@intel.com>
CC: Carolyn Wyborny <carolyn.wyborny@intel.com>
Tested-by: Jeff Pieper <jeffrey.e.pieper@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
drivers/net/ethernet/intel/igb/igb_ethtool.c | 37 ++++++++++++++++++++++++++
drivers/net/ethernet/intel/igb/igb_main.c | 4 +++
2 files changed, 41 insertions(+)
diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c
index a19c84c..bc3c5b4 100644
--- a/drivers/net/ethernet/intel/igb/igb_ethtool.c
+++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c
@@ -198,6 +198,14 @@ static int igb_get_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
}
ecmd->autoneg = hw->mac.autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE;
+
+ /* MDI-X => 2; MDI =>1; Invalid =>0 */
+ if (hw->phy.media_type == e1000_media_type_copper)
+ ecmd->eth_tp_mdix = hw->phy.is_mdix ? ETH_TP_MDI_X :
+ ETH_TP_MDI;
+ else
+ ecmd->eth_tp_mdix = ETH_TP_MDI_INVALID;
+
return 0;
}
@@ -214,6 +222,22 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
return -EINVAL;
}
+ /*
+ * MDI setting is only allowed when autoneg enabled because
+ * some hardware doesn't allow MDI setting when speed or
+ * duplex is forced.
+ */
+ if (ecmd->eth_tp_mdix_ctrl) {
+ if (hw->phy.media_type != e1000_media_type_copper)
+ return -EOPNOTSUPP;
+
+ if ((ecmd->eth_tp_mdix_ctrl != ETH_TP_MDI_AUTO) &&
+ (ecmd->autoneg != AUTONEG_ENABLE)) {
+ dev_err(&adapter->pdev->dev, "forcing MDI/MDI-X state is not supported when link speed and/or duplex are forced\n");
+ return -EINVAL;
+ }
+ }
+
while (test_and_set_bit(__IGB_RESETTING, &adapter->state))
msleep(1);
@@ -227,12 +251,25 @@ static int igb_set_settings(struct net_device *netdev, struct ethtool_cmd *ecmd)
hw->fc.requested_mode = e1000_fc_default;
} else {
u32 speed = ethtool_cmd_speed(ecmd);
+ /* calling this overrides forced MDI setting */
if (igb_set_spd_dplx(adapter, speed, ecmd->duplex)) {
clear_bit(__IGB_RESETTING, &adapter->state);
return -EINVAL;
}
}
+ /* MDI-X => 2; MDI => 1; Auto => 3 */
+ if (ecmd->eth_tp_mdix_ctrl) {
+ /*
+ * fix up the value for auto (3 => 0) as zero is mapped
+ * internally to auto
+ */
+ if (ecmd->eth_tp_mdix_ctrl == ETH_TP_MDI_AUTO)
+ hw->phy.mdix = AUTO_ALL_MODES;
+ else
+ hw->phy.mdix = ecmd->eth_tp_mdix_ctrl;
+ }
+
/* reset the link */
if (netif_running(adapter->netdev)) {
igb_down(adapter);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8adeca9..4df7848 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6675,6 +6675,10 @@ int igb_set_spd_dplx(struct igb_adapter *adapter, u32 spd, u8 dplx)
default:
goto err_inval;
}
+
+ /* clear MDI, MDI(-X) override is only allowed when autoneg enabled */
+ adapter->hw.phy.mdix = AUTO_ALL_MODES;
+
return 0;
err_inval:
--
1.7.10.4
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox