From 475abbf1ef67fdf35eed0720adcf59ed25ad924e Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 2 Aug 2017 09:56:01 +0200 Subject: ipv4: fib: Set offload indication according to nexthop flags We're going to have capable drivers indicate route offload using the nexthop flags, but for non-multipath routes these flags aren't dumped to user space. Instead, set the offload indication in the route message flags. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Acked-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4/fib_semantics.c') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index b8d18171cca3..f62dc2463280 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1342,6 +1342,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev)) rtm->rtm_flags |= RTNH_F_DEAD; } + if (fi->fib_nh->nh_flags & RTNH_F_OFFLOAD) + rtm->rtm_flags |= RTNH_F_OFFLOAD; #ifdef CONFIG_IP_ROUTE_CLASSID if (fi->fib_nh[0].nh_tclassid && nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) -- cgit From 04b1d4e50e82536c12da00ee04a77510c459c844 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Thu, 3 Aug 2017 13:28:11 +0200 Subject: net: core: Make the FIB notification chain generic The FIB notification chain is currently soley used by IPv4 code. However, we're going to introduce IPv6 FIB offload support, which requires these notification as well. As explained in commit c3852ef7f2f8 ("ipv4: fib: Replay events when registering FIB notifier"), upon registration to the chain, the callee receives a full dump of the FIB tables and rules by traversing all the net namespaces. The integrity of the dump is ensured by a per-namespace sequence counter that is incremented whenever a change to the tables or rules occurs. In order to allow more address families to use the chain, each family is expected to register its fib_notifier_ops in its pernet init. These operations allow the common code to read the family's sequence counter as well as dump its tables and rules in the given net namespace. Additionally, a 'family' parameter is added to sent notifications, so that listeners could distinguish between the different families. Implement the common code that allows listeners to register to the chain and for address families to register their fib_notifier_ops. Subsequent patches will implement these operations in IPv6. In the future, ipmr and ip6mr will be extended to provide these notifications as well. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net/ipv4/fib_semantics.c') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f62dc2463280..632b454ce77c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -44,6 +44,7 @@ #include #include #include +#include #include "fib_lookup.h" @@ -1451,14 +1452,14 @@ static int call_fib_nh_notifiers(struct fib_nh *fib_nh, if (IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) break; - return call_fib_notifiers(dev_net(fib_nh->nh_dev), event_type, - &info.info); + return call_fib4_notifiers(dev_net(fib_nh->nh_dev), event_type, + &info.info); case FIB_EVENT_NH_DEL: if ((in_dev && IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) && fib_nh->nh_flags & RTNH_F_LINKDOWN) || (fib_nh->nh_flags & RTNH_F_DEAD)) - return call_fib_notifiers(dev_net(fib_nh->nh_dev), - event_type, &info.info); + return call_fib4_notifiers(dev_net(fib_nh->nh_dev), + event_type, &info.info); default: break; } -- cgit From 9620fef27ed2cdb37bf6fd028f32bea2ef5119a8 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 18 Aug 2017 12:08:07 -0700 Subject: ipv4: convert dst_metrics.refcnt from atomic_t to refcount_t refcount_t type and corresponding API should be used instead of atomic_t when the variable is used as a reference counter. This allows to avoid accidental refcounter overflows that might lead to use-after-free situations. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/ipv4/fib_semantics.c') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d521caf57385..394d800db50c 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -220,7 +220,7 @@ static void free_fib_info_rcu(struct rcu_head *head) } endfor_nexthops(fi); m = fi->fib_metrics; - if (m != &dst_default_metrics && atomic_dec_and_test(&m->refcnt)) + if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) kfree(m); kfree(fi); } @@ -1090,7 +1090,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, kfree(fi); return ERR_PTR(err); } - atomic_set(&fi->fib_metrics->refcnt, 1); + refcount_set(&fi->fib_metrics->refcnt, 1); } else { fi->fib_metrics = (struct dst_metrics *)&dst_default_metrics; } -- cgit From 5f9ae3d9e7e4ad6db0491abc7c4ae5452dbeadd8 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Wed, 23 Aug 2017 10:07:26 +0800 Subject: ipv4: do metrics match when looking up and deleting a route Now when ipv4 route inserts a fib_info, it memcmp fib_metrics. It means ipv4 route identifies one route also with metrics. But when removing a route, it tries to find the route without caring about the metrics. It will cause that the route with right metrics can't be removed. Thomas noticed this issue when doing the testing: 1. add: # ip route append 192.168.7.0/24 dev v window 1000 # ip route append 192.168.7.0/24 dev v window 1001 # ip route append 192.168.7.0/24 dev v window 1002 # ip route append 192.168.7.0/24 dev v window 1003 2. delete: # ip route delete 192.168.7.0/24 dev v window 1002 3. show: 192.168.7.0/24 proto boot scope link window 1001 192.168.7.0/24 proto boot scope link window 1002 192.168.7.0/24 proto boot scope link window 1003 The one with window 1002 wasn't deleted but the first one was. This patch is to do metrics match when looking up and deleting one route. Reported-by: Thomas Haller Signed-off-by: Xin Long Acked-by: Hannes Frederic Sowa Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'net/ipv4/fib_semantics.c') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 394d800db50c..57a5d48acee8 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -696,6 +696,40 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, return 0; } +bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi) +{ + struct nlattr *nla; + int remaining; + + if (!cfg->fc_mx) + return true; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla_type(nla); + u32 val; + + if (!type) + continue; + if (type > RTAX_MAX) + return false; + + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + bool ecn_ca = false; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + } else { + val = nla_get_u32(nla); + } + + if (fi->fib_metrics->metrics[type - 1] != val) + return false; + } + + return true; +} + /* * Picture -- cgit