From d7d49dc77c8db113393a31aced3f0562f4afd439 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 26 Aug 2020 19:48:51 +0300 Subject: ipv4: nexthop: Reduce allocation size of 'struct nh_group' The struct looks as follows: struct nh_group { struct nh_group *spare; /* spare group for removals */ u16 num_nh; bool mpath; bool fdb_nh; bool has_v4; struct nh_grp_entry nh_entries[]; }; But its offset within 'struct nexthop' is also taken into account to determine the allocation size. Instead, use struct_size() to allocate only the required number of bytes. Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 134e92382275..d13730ff9aeb 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -133,12 +133,9 @@ static struct nexthop *nexthop_alloc(void) static struct nh_group *nexthop_grp_alloc(u16 num_nh) { - size_t sz = offsetof(struct nexthop, nh_grp) - + sizeof(struct nh_group) - + sizeof(struct nh_grp_entry) * num_nh; struct nh_group *nhg; - nhg = kzalloc(sz, GFP_KERNEL); + nhg = kzalloc(struct_size(nhg, nh_entries, num_nh), GFP_KERNEL); if (nhg) nhg->num_nh = num_nh; -- cgit From 33d80996b85283f90474d531920e40ccc2aab918 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 26 Aug 2020 19:48:52 +0300 Subject: ipv4: nexthop: Use nla_put_be32() for NHA_GATEWAY The code correctly uses nla_get_be32() to get the payload of the attribute, but incorrectly uses nla_put_u32() to add the attribute to the payload. This results in the following warning: net/ipv4/nexthop.c:279:59: warning: incorrect type in argument 3 (different base types) net/ipv4/nexthop.c:279:59: expected unsigned int [usertype] value net/ipv4/nexthop.c:279:59: got restricted __be32 [usertype] ipv4 Suppress the warning by using nla_put_be32(). Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index d13730ff9aeb..0823643a7dec 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -276,7 +276,7 @@ static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh, case AF_INET: fib_nh = &nhi->fib_nh; if (fib_nh->fib_nh_gw_family && - nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) + nla_put_be32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4)) goto nla_put_failure; break; -- cgit From 233c63785cd92e12d61b283d0eaeafc867fc45f5 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 26 Aug 2020 19:48:53 +0300 Subject: ipv4: nexthop: Remove unnecessary rtnl_dereference() The pointer is not RCU protected, so remove the unnecessary rtnl_dereference(). This suppresses the following warning: net/ipv4/nexthop.c:1101:24: error: incompatible types in comparison expression (different address spaces): net/ipv4/nexthop.c:1101:24: struct rb_node [noderef] __rcu * net/ipv4/nexthop.c:1101:24: struct rb_node * Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 0823643a7dec..1b736e3e1baa 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1098,7 +1098,7 @@ static int insert_nexthop(struct net *net, struct nexthop *new_nh, while (1) { struct nexthop *nh; - next = rtnl_dereference(*pp); + next = *pp; if (!next) break; -- cgit From 863b25581ce9e6f27dd9acc210356ca35ffe30a2 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 26 Aug 2020 19:48:54 +0300 Subject: ipv4: nexthop: Correctly update nexthop group when removing a nexthop Each nexthop group contains an indication if it has IPv4 nexthops ('has_v4'). Its purpose is to prevent IPv6 routes from using groups with IPv4 nexthops. However, the indication is not updated when a nexthop is removed. This results in the kernel wrongly rejecting IPv6 routes from pointing to groups that only contain IPv6 nexthops. Example: # ip nexthop replace id 1 via 192.0.2.2 dev dummy10 # ip nexthop replace id 2 via 2001:db8:1::2 dev dummy10 # ip nexthop replace id 10 group 1/2 # ip nexthop del id 1 # ip route replace 2001:db8:10::/64 nhid 10 Error: IPv6 routes can not use an IPv4 nexthop. Solve this by updating the indication according to the new set of member nexthops. Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 1b736e3e1baa..5199a2815df6 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -797,7 +797,7 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, return; } - newg->has_v4 = nhg->has_v4; + newg->has_v4 = false; newg->mpath = nhg->mpath; newg->fdb_nh = nhg->fdb_nh; newg->num_nh = nhg->num_nh; @@ -806,12 +806,18 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge, nhges = nhg->nh_entries; new_nhges = newg->nh_entries; for (i = 0, j = 0; i < nhg->num_nh; ++i) { + struct nh_info *nhi; + /* current nexthop getting removed */ if (nhg->nh_entries[i].nh == nh) { newg->num_nh--; continue; } + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + newg->has_v4 = true; + list_del(&nhges[i].nh_list); new_nhges[j].nh_parent = nhges[i].nh_parent; new_nhges[j].nh = nhges[i].nh; -- cgit From 885a3b15791d8255a642cc157decac31f767ddd6 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 26 Aug 2020 19:48:56 +0300 Subject: ipv4: nexthop: Correctly update nexthop group when replacing a nexthop Each nexthop group contains an indication if it has IPv4 nexthops ('has_v4'). Its purpose is to prevent IPv6 routes from using groups with IPv4 nexthops. However, the indication is not updated when a nexthop is replaced. This results in the kernel wrongly rejecting IPv6 routes from pointing to groups that only contain IPv6 nexthops. Example: # ip nexthop replace id 1 via 192.0.2.2 dev dummy10 # ip nexthop replace id 10 group 1 # ip nexthop replace id 1 via 2001:db8:1::2 dev dummy10 # ip route replace 2001:db8:10::/64 nhid 10 Error: IPv6 routes can not use an IPv4 nexthop. Solve this by iterating over all the nexthop groups that the replaced nexthop is a member of and potentially update their IPv4 indication according to the new set of member nexthops. Avoid wasting cycles by only performing the update in case an IPv4 nexthop is replaced by an IPv6 nexthop. Signed-off-by: Ido Schimmel Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/nexthop.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'net') diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index 5199a2815df6..bf9d4cd2d6e5 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -964,6 +964,23 @@ static int replace_nexthop_grp(struct net *net, struct nexthop *old, return 0; } +static void nh_group_v4_update(struct nh_group *nhg) +{ + struct nh_grp_entry *nhges; + bool has_v4 = false; + int i; + + nhges = nhg->nh_entries; + for (i = 0; i < nhg->num_nh; i++) { + struct nh_info *nhi; + + nhi = rtnl_dereference(nhges[i].nh->nh_info); + if (nhi->family == AF_INET) + has_v4 = true; + } + nhg->has_v4 = has_v4; +} + static int replace_nexthop_single(struct net *net, struct nexthop *old, struct nexthop *new, struct netlink_ext_ack *extack) @@ -987,6 +1004,21 @@ static int replace_nexthop_single(struct net *net, struct nexthop *old, rcu_assign_pointer(old->nh_info, newi); rcu_assign_pointer(new->nh_info, oldi); + /* When replacing an IPv4 nexthop with an IPv6 nexthop, potentially + * update IPv4 indication in all the groups using the nexthop. + */ + if (oldi->family == AF_INET && newi->family == AF_INET6) { + struct nh_grp_entry *nhge; + + list_for_each_entry(nhge, &old->grp_list, nh_list) { + struct nexthop *nhp = nhge->nh_parent; + struct nh_group *nhg; + + nhg = rtnl_dereference(nhp->nh_grp); + nh_group_v4_update(nhg); + } + } + return 0; } -- cgit