From b0ab2fabb5b91da99c189db02e91ae10bc8355c5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 26 Jun 2014 09:58:25 +0200 Subject: rtnetlink: allow to register ops without ops->setup set So far, it is assumed that ops->setup is filled up. But there might be case that ops might make sense even without ->setup. In that case, forbid to newlink and dellink. This allows to register simple rtnl link ops containing only ->kind. That allows consistent way of passing device kind (either device-kind or slave-kind) to userspace. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1063996f8317..27acaf7ff6d7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -299,7 +299,12 @@ int __rtnl_link_register(struct rtnl_link_ops *ops) if (rtnl_link_ops_get(ops->kind)) return -EEXIST; - if (!ops->dellink) + /* The check for setup is here because if ops + * does not have that filled up, it is not possible + * to use the ops for creating device. So do not + * fill up dellink as well. That disables rtnl_dellink. + */ + if (ops->setup && !ops->dellink) ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); @@ -1777,7 +1782,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh) return -ENODEV; ops = dev->rtnl_link_ops; - if (!ops) + if (!ops || !ops->dellink) return -EOPNOTSUPP; ops->dellink(dev, &list_kill); @@ -2038,6 +2043,9 @@ replay: return -EOPNOTSUPP; } + if (!ops->setup) + return -EOPNOTSUPP; + if (!ifname[0]) snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); -- cgit v1.2.3 From 5d5eacb34c9e1fdc0a47b885d832eaa4de860dc7 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Thu, 10 Jul 2014 07:01:58 -0400 Subject: bridge: fdb dumping takes a filter device Dumping a bridge fdb dumps every fdb entry held. With this change we are going to filter on selected bridge port. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 27acaf7ff6d7..90a906e7ac26 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2517,6 +2517,7 @@ skip: int ndo_dflt_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, + struct net_device *filter_dev, int idx) { int err; @@ -2547,13 +2548,15 @@ static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) br_dev = netdev_master_upper_dev_get(dev); ops = br_dev->netdev_ops; if (ops->ndo_fdb_dump) - idx = ops->ndo_fdb_dump(skb, cb, dev, idx); + idx = ops->ndo_fdb_dump(skb, cb, dev, NULL, + idx); } if (dev->netdev_ops->ndo_fdb_dump) - idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, idx); + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, + idx); else - idx = ndo_dflt_fdb_dump(skb, cb, dev, idx); + idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); } rcu_read_unlock(); -- cgit v1.2.3 From 5e6d243587990a588143b9da3974833649595587 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Thu, 10 Jul 2014 07:01:59 -0400 Subject: bridge: netlink dump interface at par with brctl Actually better than brctl showmacs because we can filter by bridge port in the kernel. The current bridge netlink interface doesnt scale when you have many bridges each with large fdbs or even bridges with many bridge ports And now for the science non-fiction novel you have all been waiting for.. //lets see what bridge ports we have root@moja-1:/configs/may30-iprt/bridge# ./bridge link show 8: eth1 state DOWN : mtu 1500 master br0 state disabled priority 32 cost 19 17: sw1-p1 state DOWN : mtu 1500 master br0 state disabled priority 32 cost 100 // show all.. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show 33:33:00:00:00:01 dev bond0 self permanent 33:33:00:00:00:01 dev dummy0 self permanent 33:33:00:00:00:01 dev ifb0 self permanent 33:33:00:00:00:01 dev ifb1 self permanent 33:33:00:00:00:01 dev eth0 self permanent 01:00:5e:00:00:01 dev eth0 self permanent 33:33:ff:22:01:01 dev eth0 self permanent 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 33:33:00:00:00:01 dev gretap0 self permanent da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent //filter by bridge root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent // bridge sw1 has no ports attached.. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br sw1 //filter by port root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show brport eth1 02:00:00:12:01:02 vlan 0 master br0 permanent 00:17:42:8a:b4:05 vlan 0 master br0 permanent 00:17:42:8a:b4:07 self permanent 33:33:00:00:00:01 self permanent // filter by port + bridge root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 brport sw1-p1 da:ac:46:27:d9:53 vlan 0 master br0 permanent 33:33:00:00:00:01 self permanent // for shits and giggles (as they say in New Brunswick), lets // change the mac that br0 uses // Note: a magical fdb entry with no brport is added ... root@moja-1:/configs/may30-iprt/bridge# ip link set dev br0 address 02:00:00:12:01:04 // lets see if we can see the unicorn .. root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show 33:33:00:00:00:01 dev bond0 self permanent 33:33:00:00:00:01 dev dummy0 self permanent 33:33:00:00:00:01 dev ifb0 self permanent 33:33:00:00:00:01 dev ifb1 self permanent 33:33:00:00:00:01 dev eth0 self permanent 01:00:5e:00:00:01 dev eth0 self permanent 33:33:ff:22:01:01 dev eth0 self permanent 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 33:33:00:00:00:01 dev gretap0 self permanent 02:00:00:12:01:04 dev br0 vlan 0 master br0 permanent <=== there it is da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent //can we see it if we filter by bridge? root@moja-1:/configs/may30-iprt/bridge# ./bridge fdb show br br0 02:00:00:12:01:02 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:05 dev eth1 vlan 0 master br0 permanent 00:17:42:8a:b4:07 dev eth1 self permanent 33:33:00:00:00:01 dev eth1 self permanent 02:00:00:12:01:04 dev br0 vlan 0 master br0 permanent <=== there it is da:ac:46:27:d9:53 dev sw1-p1 vlan 0 master br0 permanent 33:33:00:00:00:01 dev sw1-p1 self permanent Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 74 ++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 58 insertions(+), 16 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 90a906e7ac26..1f8a59e02c48 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2535,30 +2535,72 @@ EXPORT_SYMBOL(ndo_dflt_fdb_dump); static int rtnl_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb) { - int idx = 0; - struct net *net = sock_net(skb->sk); struct net_device *dev; + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *bdev = NULL; + struct net_device *br_dev = NULL; + const struct net_device_ops *ops = NULL; + const struct net_device_ops *cops = NULL; + struct ifinfomsg *ifm = nlmsg_data(cb->nlh); + struct net *net = sock_net(skb->sk); + int brport_idx = 0; + int br_idx = 0; + int idx = 0; + + if (nlmsg_parse(cb->nlh, sizeof(struct ifinfomsg), tb, IFLA_MAX, + ifla_policy) == 0) { + if (tb[IFLA_MASTER]) + br_idx = nla_get_u32(tb[IFLA_MASTER]); + } + + brport_idx = ifm->ifi_index; + + if (br_idx) { + br_dev = __dev_get_by_index(net, br_idx); + if (!br_dev) + return -ENODEV; + + ops = br_dev->netdev_ops; + bdev = br_dev; + } + + for_each_netdev(net, dev) { + if (brport_idx && (dev->ifindex != brport_idx)) + continue; + + if (!br_idx) { /* user did not specify a specific bridge */ + if (dev->priv_flags & IFF_BRIDGE_PORT) { + br_dev = netdev_master_upper_dev_get(dev); + cops = br_dev->netdev_ops; + } + + bdev = dev; + } else { + if (dev != br_dev && + !(dev->priv_flags & IFF_BRIDGE_PORT)) + continue; + + if (br_dev != netdev_master_upper_dev_get(dev) && + !(dev->priv_flags & IFF_EBRIDGE)) + continue; + + bdev = br_dev; + cops = ops; + } - rcu_read_lock(); - for_each_netdev_rcu(net, dev) { if (dev->priv_flags & IFF_BRIDGE_PORT) { - struct net_device *br_dev; - const struct net_device_ops *ops; - - br_dev = netdev_master_upper_dev_get(dev); - ops = br_dev->netdev_ops; - if (ops->ndo_fdb_dump) - idx = ops->ndo_fdb_dump(skb, cb, dev, NULL, - idx); + if (cops && cops->ndo_fdb_dump) + idx = cops->ndo_fdb_dump(skb, cb, br_dev, dev, + idx); } + idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); if (dev->netdev_ops->ndo_fdb_dump) - idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, dev, NULL, + idx = dev->netdev_ops->ndo_fdb_dump(skb, cb, bdev, dev, idx); - else - idx = ndo_dflt_fdb_dump(skb, cb, dev, NULL, idx); + + cops = NULL; } - rcu_read_unlock(); cb->args[0] = idx; return skb->len; -- cgit v1.2.3 From c835a677331495cf137a7f8a023463afd9f032f8 Mon Sep 17 00:00:00 2001 From: Tom Gundersen Date: Mon, 14 Jul 2014 16:37:24 +0200 Subject: net: set name_assign_type in alloc_netdev() Extend alloc_netdev{,_mq{,s}}() to take name_assign_type as argument, and convert all users to pass NET_NAME_UNKNOWN. Coccinelle patch: @@ expression sizeof_priv, name, setup, txqs, rxqs, count; @@ ( -alloc_netdev_mqs(sizeof_priv, name, setup, txqs, rxqs) +alloc_netdev_mqs(sizeof_priv, name, NET_NAME_UNKNOWN, setup, txqs, rxqs) | -alloc_netdev_mq(sizeof_priv, name, setup, count) +alloc_netdev_mq(sizeof_priv, name, NET_NAME_UNKNOWN, setup, count) | -alloc_netdev(sizeof_priv, name, setup) +alloc_netdev(sizeof_priv, name, NET_NAME_UNKNOWN, setup) ) v9: move comments here from the wrong commit Signed-off-by: Tom Gundersen Reviewed-by: David Herrmann Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1f8a59e02c48..599864322de8 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1828,8 +1828,8 @@ struct net_device *rtnl_create_link(struct net *net, num_rx_queues = ops->get_num_rx_queues(); err = -ENOMEM; - dev = alloc_netdev_mqs(ops->priv_size, ifname, ops->setup, - num_tx_queues, num_rx_queues); + dev = alloc_netdev_mqs(ops->priv_size, ifname, NET_NAME_UNKNOWN, + ops->setup, num_tx_queues, num_rx_queues); if (!dev) goto err; -- cgit v1.2.3 From 5517750f058edd111bcabe5e116056cc63b1f39c Mon Sep 17 00:00:00 2001 From: Tom Gundersen Date: Mon, 14 Jul 2014 16:37:25 +0200 Subject: net: rtnetlink - make create_link take name_assign_type This passes down NET_NAME_USER (or NET_NAME_ENUM) to alloc_netdev(), for any device created over rtnetlink. v9: restore reverse-christmas-tree order of local variables Signed-off-by: Tom Gundersen Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 599864322de8..e9918020dbc9 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1810,7 +1810,8 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) EXPORT_SYMBOL(rtnl_configure_link); struct net_device *rtnl_create_link(struct net *net, - char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) + char *ifname, unsigned char name_assign_type, + const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; struct net_device *dev; @@ -1828,7 +1829,7 @@ struct net_device *rtnl_create_link(struct net *net, num_rx_queues = ops->get_num_rx_queues(); err = -ENOMEM; - dev = alloc_netdev_mqs(ops->priv_size, ifname, NET_NAME_UNKNOWN, + dev = alloc_netdev_mqs(ops->priv_size, ifname, name_assign_type, ops->setup, num_tx_queues, num_rx_queues); if (!dev) goto err; @@ -1894,6 +1895,7 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh) char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct nlattr *linkinfo[IFLA_INFO_MAX+1]; + unsigned char name_assign_type = NET_NAME_USER; int err; #ifdef CONFIG_MODULES @@ -2046,14 +2048,16 @@ replay: if (!ops->setup) return -EOPNOTSUPP; - if (!ifname[0]) + if (!ifname[0]) { snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); + name_assign_type = NET_NAME_ENUM; + } dest_net = rtnl_link_get_net(net, tb); if (IS_ERR(dest_net)) return PTR_ERR(dest_net); - dev = rtnl_create_link(dest_net, ifname, ops, tb); + dev = rtnl_create_link(dest_net, ifname, name_assign_type, ops, tb); if (IS_ERR(dev)) { err = PTR_ERR(dev); goto out; -- cgit v1.2.3 From c8a89c4a1d58230192cf7243520bf7f9899239f4 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Tue, 15 Jul 2014 15:15:20 -0700 Subject: rtnetlink: Drop unnecessary return value from ndo_dflt_fdb_del This change cleans up ndo_dflt_fdb_del to drop the ENOTSUPP return value since that isn't actually returned anywhere in the code. As a result we are able to drop a few lines by just defaulting this to -EINVAL. Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index e9918020dbc9..8d39071f32d7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2392,22 +2392,20 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, struct net_device *dev, const unsigned char *addr) { - int err = -EOPNOTSUPP; + int err = -EINVAL; /* If aging addresses are supported device will need to * implement its own handler for this. */ if (!(ndm->ndm_state & NUD_PERMANENT)) { pr_info("%s: FDB only supports static addresses\n", dev->name); - return -EINVAL; + return err; } if (is_unicast_ether_addr(addr) || is_link_local_ether_addr(addr)) err = dev_uc_del(dev, addr); else if (is_multicast_ether_addr(addr)) err = dev_mc_del(dev, addr); - else - err = -EINVAL; return err; } -- cgit v1.2.3 From 945a36761fd7877660f630bbdeb4ff9ff80d1935 Mon Sep 17 00:00:00 2001 From: Jiri Benc Date: Fri, 8 Aug 2014 16:44:32 +0200 Subject: rtnetlink: fix VF info size Commit 1d8faf48c74b8 ("net/core: Add VF link state control") added new attribute to IFLA_VF_INFO group in rtnl_fill_ifinfo but did not adjust size of the allocated memory in if_nlmsg_size/rtnl_vfinfo_size. As the result, we may trigger warnings in rtnl_getlink and similar functions when many VF links are enabled, as the information does not fit into the allocated skb. Fixes: 1d8faf48c74b8 ("net/core: Add VF link state control") Reported-by: Yulong Pei Signed-off-by: Jiri Benc Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/core/rtnetlink.c') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8d39071f32d7..f0493e3b7471 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -804,7 +804,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + - nla_total_size(sizeof(struct ifla_vf_rate))); + nla_total_size(sizeof(struct ifla_vf_rate)) + + nla_total_size(sizeof(struct ifla_vf_link_state))); return size; } else return 0; -- cgit v1.2.3