diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/bridge/Kconfig | 13 | ||||
-rw-r--r-- | net/bridge/Makefile | 2 | ||||
-rw-r--r-- | net/bridge/br_device.c | 23 | ||||
-rw-r--r-- | net/bridge/br_forward.c | 150 | ||||
-rw-r--r-- | net/bridge/br_if.c | 4 | ||||
-rw-r--r-- | net/bridge/br_input.c | 39 | ||||
-rw-r--r-- | net/bridge/br_multicast.c | 1304 | ||||
-rw-r--r-- | net/bridge/br_private.h | 168 | ||||
-rw-r--r-- | net/bridge/br_stp.c | 2 | ||||
-rw-r--r-- | net/bridge/br_stp_if.c | 1 | ||||
-rw-r--r-- | net/bridge/br_sysfs_br.c | 281 | ||||
-rw-r--r-- | net/bridge/br_sysfs_if.c | 18 | ||||
-rw-r--r-- | net/core/dev.c | 171 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 59 | ||||
-rw-r--r-- | net/mac80211/main.c | 6 | ||||
-rw-r--r-- | net/mac80211/work.c | 1 |
16 files changed, 2126 insertions, 116 deletions
diff --git a/net/bridge/Kconfig b/net/bridge/Kconfig index e143ca67888..19a6b9629c5 100644 --- a/net/bridge/Kconfig +++ b/net/bridge/Kconfig @@ -31,3 +31,16 @@ config BRIDGE will be called bridge. If unsure, say N. + +config BRIDGE_IGMP_SNOOPING + bool "IGMP snooping" + depends on BRIDGE + default y + ---help--- + If you say Y here, then the Ethernet bridge will be able selectively + forward multicast traffic based on IGMP traffic received from each + port. + + Say N to exclude this support and reduce the binary size. + + If unsure, say Y. diff --git a/net/bridge/Makefile b/net/bridge/Makefile index f444c12cde5..d0359ea8ee7 100644 --- a/net/bridge/Makefile +++ b/net/bridge/Makefile @@ -12,4 +12,6 @@ bridge-$(CONFIG_SYSFS) += br_sysfs_if.o br_sysfs_br.o bridge-$(CONFIG_BRIDGE_NETFILTER) += br_netfilter.o +bridge-$(CONFIG_BRIDGE_IGMP_SNOOPING) += br_multicast.o + obj-$(CONFIG_BRIDGE_NF_EBTABLES) += netfilter/ diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index 1a99c4e04e8..eb7062d2e9e 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -25,6 +25,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct net_bridge *br = netdev_priv(dev); const unsigned char *dest = skb->data; struct net_bridge_fdb_entry *dst; + struct net_bridge_mdb_entry *mdst; + + BR_INPUT_SKB_CB(skb)->brdev = dev; dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; @@ -32,13 +35,21 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_reset_mac_header(skb); skb_pull(skb, ETH_HLEN); - if (dest[0] & 1) - br_flood_deliver(br, skb); - else if ((dst = __br_fdb_get(br, dest)) != NULL) + if (dest[0] & 1) { + if (br_multicast_rcv(br, NULL, skb)) + goto out; + + mdst = br_mdb_get(br, skb); + if (mdst || BR_INPUT_SKB_CB(skb)->mrouters_only) + br_multicast_deliver(mdst, skb); + else + br_flood_deliver(br, skb); + } else if ((dst = __br_fdb_get(br, dest)) != NULL) br_deliver(dst->dst, skb); else br_flood_deliver(br, skb); +out: return NETDEV_TX_OK; } @@ -49,6 +60,7 @@ static int br_dev_open(struct net_device *dev) br_features_recompute(br); netif_start_queue(dev); br_stp_enable_bridge(br); + br_multicast_open(br); return 0; } @@ -59,7 +71,10 @@ static void br_dev_set_multicast_list(struct net_device *dev) static int br_dev_stop(struct net_device *dev) { - br_stp_disable_bridge(netdev_priv(dev)); + struct net_bridge *br = netdev_priv(dev); + + br_stp_disable_bridge(br); + br_multicast_stop(br); netif_stop_queue(dev); diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index bc1704ac6cd..d61e6f74112 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -11,6 +11,7 @@ * 2 of the License, or (at your option) any later version. */ +#include <linux/err.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/skbuff.h> @@ -103,51 +104,152 @@ void br_forward(const struct net_bridge_port *to, struct sk_buff *skb) kfree_skb(skb); } -/* called under bridge lock */ -static void br_flood(struct net_bridge *br, struct sk_buff *skb, +static int deliver_clone(struct net_bridge_port *prev, struct sk_buff *skb, + void (*__packet_hook)(const struct net_bridge_port *p, + struct sk_buff *skb)) +{ + skb = skb_clone(skb, GFP_ATOMIC); + if (!skb) { + struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; + + dev->stats.tx_dropped++; + return -ENOMEM; + } + + __packet_hook(prev, skb); + return 0; +} + +static struct net_bridge_port *maybe_deliver( + struct net_bridge_port *prev, struct net_bridge_port *p, + struct sk_buff *skb, void (*__packet_hook)(const struct net_bridge_port *p, struct sk_buff *skb)) { + int err; + + if (!should_deliver(p, skb)) + return prev; + + if (!prev) + goto out; + + err = deliver_clone(prev, skb, __packet_hook); + if (err) + return ERR_PTR(err); + +out: + return p; +} + +/* called under bridge lock */ +static void br_flood(struct net_bridge *br, struct sk_buff *skb, + struct sk_buff *skb0, + void (*__packet_hook)(const struct net_bridge_port *p, + struct sk_buff *skb)) +{ struct net_bridge_port *p; struct net_bridge_port *prev; prev = NULL; list_for_each_entry_rcu(p, &br->port_list, list) { - if (should_deliver(p, skb)) { - if (prev != NULL) { - struct sk_buff *skb2; - - if ((skb2 = skb_clone(skb, GFP_ATOMIC)) == NULL) { - br->dev->stats.tx_dropped++; - kfree_skb(skb); - return; - } - - __packet_hook(prev, skb2); - } - - prev = p; - } + prev = maybe_deliver(prev, p, skb, __packet_hook); + if (IS_ERR(prev)) + goto out; } - if (prev != NULL) { + if (!prev) + goto out; + + if (skb0) + deliver_clone(prev, skb, __packet_hook); + else __packet_hook(prev, skb); - return; - } + return; - kfree_skb(skb); +out: + if (!skb0) + kfree_skb(skb); } /* called with rcu_read_lock */ void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb) { - br_flood(br, skb, __br_deliver); + br_flood(br, skb, NULL, __br_deliver); } /* called under bridge lock */ -void br_flood_forward(struct net_bridge *br, struct sk_buff *skb) +void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, + struct sk_buff *skb2) +{ + br_flood(br, skb, skb2, __br_forward); +} + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +/* called with rcu_read_lock */ +static void br_multicast_flood(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, struct sk_buff *skb0, + void (*__packet_hook)( + const struct net_bridge_port *p, + struct sk_buff *skb)) +{ + struct net_device *dev = BR_INPUT_SKB_CB(skb)->brdev; + struct net_bridge *br = netdev_priv(dev); + struct net_bridge_port *port; + struct net_bridge_port *lport, *rport; + struct net_bridge_port *prev; + struct net_bridge_port_group *p; + struct hlist_node *rp; + + prev = NULL; + + rp = br->router_list.first; + p = mdst ? mdst->ports : NULL; + while (p || rp) { + lport = p ? p->port : NULL; + rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) : + NULL; + + port = (unsigned long)lport > (unsigned long)rport ? + lport : rport; + + prev = maybe_deliver(prev, port, skb, __packet_hook); + if (IS_ERR(prev)) + goto out; + + if ((unsigned long)lport >= (unsigned long)port) + p = p->next; + if ((unsigned long)rport >= (unsigned long)port) + rp = rp->next; + } + + if (!prev) + goto out; + + if (skb0) + deliver_clone(prev, skb, __packet_hook); + else + __packet_hook(prev, skb); + return; + +out: + if (!skb0) + kfree_skb(skb); +} + +/* called with rcu_read_lock */ +void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb) +{ + br_multicast_flood(mdst, skb, NULL, __br_deliver); +} + +/* called with rcu_read_lock */ +void br_multicast_forward(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, struct sk_buff *skb2) { - br_flood(br, skb, __br_forward); + br_multicast_flood(mdst, skb, skb2, __br_forward); } +#endif diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index bc2b1badab8..b6a3872f568 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -147,6 +147,8 @@ static void del_nbp(struct net_bridge_port *p) rcu_assign_pointer(dev->br_port, NULL); + br_multicast_del_port(p); + kobject_uevent(&p->kobj, KOBJ_REMOVE); kobject_del(&p->kobj); @@ -207,6 +209,7 @@ static struct net_device *new_bridge_dev(struct net *net, const char *name) br_netfilter_rtable_init(br); br_stp_timer_init(br); + br_multicast_init(br); return dev; } @@ -258,6 +261,7 @@ static struct net_bridge_port *new_nbp(struct net_bridge *br, br_init_port(p); p->state = BR_STATE_DISABLED; br_stp_port_timer_init(p); + br_multicast_add_port(p); return p; } diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index 5ee1a3682bf..53b39851d87 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -20,9 +20,9 @@ /* Bridge group multicast address 802.1d (pg 51). */ const u8 br_group_address[ETH_ALEN] = { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 }; -static void br_pass_frame_up(struct net_bridge *br, struct sk_buff *skb) +static int br_pass_frame_up(struct sk_buff *skb) { - struct net_device *indev, *brdev = br->dev; + struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; brdev->stats.rx_packets++; brdev->stats.rx_bytes += skb->len; @@ -30,8 +30,8 @@ static void br_pass_frame_up(struct net_bridge *br, struct sk_buff *skb) indev = skb->dev; skb->dev = brdev; - NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, - netif_receive_skb); + return NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_IN, skb, indev, NULL, + netif_receive_skb); } /* note: already called with rcu_read_lock (preempt_disabled) */ @@ -41,6 +41,7 @@ int br_handle_frame_finish(struct sk_buff *skb) struct net_bridge_port *p = rcu_dereference(skb->dev->br_port); struct net_bridge *br; struct net_bridge_fdb_entry *dst; + struct net_bridge_mdb_entry *mdst; struct sk_buff *skb2; if (!p || p->state == BR_STATE_DISABLED) @@ -50,9 +51,15 @@ int br_handle_frame_finish(struct sk_buff *skb) br = p->br; br_fdb_update(br, p, eth_hdr(skb)->h_source); + if (is_multicast_ether_addr(dest) && + br_multicast_rcv(br, p, skb)) + goto drop; + if (p->state == BR_STATE_LEARNING) goto drop; + BR_INPUT_SKB_CB(skb)->brdev = br->dev; + /* The packet skb2 goes to the local host (NULL to skip). */ skb2 = NULL; @@ -62,27 +69,35 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; if (is_multicast_ether_addr(dest)) { + mdst = br_mdb_get(br, skb); + if (mdst || BR_INPUT_SKB_CB(skb)->mrouters_only) { + if ((mdst && !hlist_unhashed(&mdst->mglist)) || + br_multicast_is_router(br)) + skb2 = skb; + br_multicast_forward(mdst, skb, skb2); + skb = NULL; + if (!skb2) + goto out; + } else + skb2 = skb; + br->dev->stats.multicast++; - skb2 = skb; } else if ((dst = __br_fdb_get(br, dest)) && dst->is_local) { skb2 = skb; /* Do not forward the packet since it's local. */ skb = NULL; } - if (skb2 == skb) - skb2 = skb_clone(skb, GFP_ATOMIC); - - if (skb2) - br_pass_frame_up(br, skb2); - if (skb) { if (dst) br_forward(dst->dst, skb); else - br_flood_forward(br, skb); + br_flood_forward(br, skb, skb2); } + if (skb2) + return br_pass_frame_up(skb2); + out: return 0; drop: diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c new file mode 100644 index 00000000000..2559fb53983 --- /dev/null +++ b/net/bridge/br_multicast.c @@ -0,0 +1,1304 @@ +/* + * Bridge multicast support. + * + * Copyright (c) 2010 Herbert Xu <herbert@gondor.apana.org.au> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the Free + * Software Foundation; either version 2 of the License, or (at your option) + * any later version. + * + */ + +#include <linux/err.h> +#include <linux/if_ether.h> +#include <linux/igmp.h> +#include <linux/jhash.h> +#include <linux/kernel.h> +#include <linux/log2.h> +#include <linux/netdevice.h> +#include <linux/netfilter_bridge.h> +#include <linux/random.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/timer.h> +#include <net/ip.h> + +#include "br_private.h" + +static inline int br_ip_hash(struct net_bridge_mdb_htable *mdb, __be32 ip) +{ + return jhash_1word(mdb->secret, (u32)ip) & (mdb->max - 1); +} + +static struct net_bridge_mdb_entry *__br_mdb_ip_get( + struct net_bridge_mdb_htable *mdb, __be32 dst, int hash) +{ + struct net_bridge_mdb_entry *mp; + struct hlist_node *p; + + hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + if (dst == mp->addr) + return mp; + } + + return NULL; +} + +static struct net_bridge_mdb_entry *br_mdb_ip_get( + struct net_bridge_mdb_htable *mdb, __be32 dst) +{ + return __br_mdb_ip_get(mdb, dst, br_ip_hash(mdb, dst)); +} + +struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, + struct sk_buff *skb) +{ + struct net_bridge_mdb_htable *mdb = br->mdb; + + if (!mdb || br->multicast_disabled) + return NULL; + + switch (skb->protocol) { + case htons(ETH_P_IP): + if (BR_INPUT_SKB_CB(skb)->igmp) + break; + return br_mdb_ip_get(mdb, ip_hdr(skb)->daddr); + } + + return NULL; +} + +static void br_mdb_free(struct rcu_head *head) +{ + struct net_bridge_mdb_htable *mdb = + container_of(head, struct net_bridge_mdb_htable, rcu); + struct net_bridge_mdb_htable *old = mdb->old; + + mdb->old = NULL; + kfree(old->mhash); + kfree(old); +} + +static int br_mdb_copy(struct net_bridge_mdb_htable *new, + struct net_bridge_mdb_htable *old, + int elasticity) +{ + struct net_bridge_mdb_entry *mp; + struct hlist_node *p; + int maxlen; + int len; + int i; + + for (i = 0; i < old->max; i++) + hlist_for_each_entry(mp, p, &old->mhash[i], hlist[old->ver]) + hlist_add_head(&mp->hlist[new->ver], + &new->mhash[br_ip_hash(new, mp->addr)]); + + if (!elasticity) + return 0; + + maxlen = 0; + for (i = 0; i < new->max; i++) { + len = 0; + hlist_for_each_entry(mp, p, &new->mhash[i], hlist[new->ver]) + len++; + if (len > maxlen) + maxlen = len; + } + + return maxlen > elasticity ? -EINVAL : 0; +} + +static void br_multicast_free_pg(struct rcu_head *head) +{ + struct net_bridge_port_group *p = + container_of(head, struct net_bridge_port_group, rcu); + + kfree(p); +} + +static void br_multicast_free_group(struct rcu_head *head) +{ + struct net_bridge_mdb_entry *mp = + container_of(head, struct net_bridge_mdb_entry, rcu); + + kfree(mp); +} + +static void br_multicast_group_expired(unsigned long data) +{ + struct net_bridge_mdb_entry *mp = (void *)data; + struct net_bridge *br = mp->br; + struct net_bridge_mdb_htable *mdb; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || timer_pending(&mp->timer)) + goto out; + + if (!hlist_unhashed(&mp->mglist)) + hlist_del_init(&mp->mglist); + + if (mp->ports) + goto out; + + mdb = br->mdb; + hlist_del_rcu(&mp->hlist[mdb->ver]); + mdb->size--; + + del_timer(&mp->query_timer); + call_rcu_bh(&mp->rcu, br_multicast_free_group); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_multicast_del_pg(struct net_bridge *br, + struct net_bridge_port_group *pg) +{ + struct net_bridge_mdb_htable *mdb = br->mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group **pp; + + mp = br_mdb_ip_get(mdb, pg->addr); + if (WARN_ON(!mp)) + return; + + for (pp = &mp->ports; (p = *pp); pp = &p->next) { + if (p != pg) + continue; + + *pp = p->next; + hlist_del_init(&p->mglist); + del_timer(&p->timer); + del_timer(&p->query_timer); + call_rcu_bh(&p->rcu, br_multicast_free_pg); + + if (!mp->ports && hlist_unhashed(&mp->mglist) && + netif_running(br->dev)) + mod_timer(&mp->timer, jiffies); + + return; + } + + WARN_ON(1); +} + +static void br_multicast_port_group_expired(unsigned long data) +{ + struct net_bridge_port_group *pg = (void *)data; + struct net_bridge *br = pg->port->br; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || timer_pending(&pg->timer) || + hlist_unhashed(&pg->mglist)) + goto out; + + br_multicast_del_pg(br, pg); + +out: + spin_unlock(&br->multicast_lock); +} + +static int br_mdb_rehash(struct net_bridge_mdb_htable **mdbp, int max, + int elasticity) +{ + struct net_bridge_mdb_htable *old = *mdbp; + struct net_bridge_mdb_htable *mdb; + int err; + + mdb = kmalloc(sizeof(*mdb), GFP_ATOMIC); + if (!mdb) + return -ENOMEM; + + mdb->max = max; + mdb->old = old; + + mdb->mhash = kzalloc(max * sizeof(*mdb->mhash), GFP_ATOMIC); + if (!mdb->mhash) { + kfree(mdb); + return -ENOMEM; + } + + mdb->size = old ? old->size : 0; + mdb->ver = old ? old->ver ^ 1 : 0; + + if (!old || elasticity) + get_random_bytes(&mdb->secret, sizeof(mdb->secret)); + else + mdb->secret = old->secret; + + if (!old) + goto out; + + err = br_mdb_copy(mdb, old, elasticity); + if (err) { + kfree(mdb->mhash); + kfree(mdb); + return err; + } + + call_rcu_bh(&mdb->rcu, br_mdb_free); + +out: + rcu_assign_pointer(*mdbp, mdb); + + return 0; +} + +static struct sk_buff *br_multicast_alloc_query(struct net_bridge *br, + __be32 group) +{ + struct sk_buff *skb; + struct igmphdr *ih; + struct ethhdr *eth; + struct iphdr *iph; + + skb = netdev_alloc_skb_ip_align(br->dev, sizeof(*eth) + sizeof(*iph) + + sizeof(*ih) + 4); + if (!skb) + goto out; + + skb->protocol = htons(ETH_P_IP); + + skb_reset_mac_header(skb); + eth = eth_hdr(skb); + + memcpy(eth->h_source, br->dev->dev_addr, 6); + eth->h_dest[0] = 1; + eth->h_dest[1] = 0; + eth->h_dest[2] = 0x5e; + eth->h_dest[3] = 0; + eth->h_dest[4] = 0; + eth->h_dest[5] = 1; + eth->h_proto = htons(ETH_P_IP); + skb_put(skb, sizeof(*eth)); + + skb_set_network_header(skb, skb->len); + iph = ip_hdr(skb); + + iph->version = 4; + iph->ihl = 6; + iph->tos = 0xc0; + iph->tot_len = htons(sizeof(*iph) + sizeof(*ih) + 4); + iph->id = 0; + iph->frag_off = htons(IP_DF); + iph->ttl = 1; + iph->protocol = IPPROTO_IGMP; + iph->saddr = 0; + iph->daddr = htonl(INADDR_ALLHOSTS_GROUP); + ((u8 *)&iph[1])[0] = IPOPT_RA; + ((u8 *)&iph[1])[1] = 4; + ((u8 *)&iph[1])[2] = 0; + ((u8 *)&iph[1])[3] = 0; + ip_send_check(iph); + skb_put(skb, 24); + + skb_set_transport_header(skb, skb->len); + ih = igmp_hdr(skb); + ih->type = IGMP_HOST_MEMBERSHIP_QUERY; + ih->code = (group ? br->multicast_last_member_interval : + br->multicast_query_response_interval) / + (HZ / IGMP_TIMER_SCALE); + ih->group = group; + ih->csum = 0; + ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); + skb_put(skb, sizeof(*ih)); + + __skb_pull(skb, sizeof(*eth)); + +out: + return skb; +} + +static void br_multicast_send_group_query(struct net_bridge_mdb_entry *mp) +{ + struct net_bridge *br = mp->br; + struct sk_buff *skb; + + skb = br_multicast_alloc_query(br, mp->addr); + if (!skb) + goto timer; + + netif_rx(skb); + +timer: + if (++mp->queries_sent < br->multicast_last_member_count) + mod_timer(&mp->query_timer, + jiffies + br->multicast_last_member_interval); +} + +static void br_multicast_group_query_expired(unsigned long data) +{ + struct net_bridge_mdb_entry *mp = (void *)data; + struct net_bridge *br = mp->br; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || hlist_unhashed(&mp->mglist) || + mp->queries_sent >= br->multicast_last_member_count) + goto out; + + br_multicast_send_group_query(mp); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_multicast_send_port_group_query(struct net_bridge_port_group *pg) +{ + struct net_bridge_port *port = pg->port; + struct net_bridge *br = port->br; + struct sk_buff *skb; + + skb = br_multicast_alloc_query(br, pg->addr); + if (!skb) + goto timer; + + br_deliver(port, skb); + +timer: + if (++pg->queries_sent < br->multicast_last_member_count) + mod_timer(&pg->query_timer, + jiffies + br->multicast_last_member_interval); +} + +static void br_multicast_port_group_query_expired(unsigned long data) +{ + struct net_bridge_port_group *pg = (void *)data; + struct net_bridge_port *port = pg->port; + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || hlist_unhashed(&pg->mglist) || + pg->queries_sent >= br->multicast_last_member_count) + goto out; + + br_multicast_send_port_group_query(pg); + +out: + spin_unlock(&br->multicast_lock); +} + +static struct net_bridge_mdb_entry *br_multicast_get_group( + struct net_bridge *br, struct net_bridge_port *port, __be32 group, + int hash) +{ + struct net_bridge_mdb_htable *mdb = br->mdb; + struct net_bridge_mdb_entry *mp; + struct hlist_node *p; + unsigned count = 0; + unsigned max; + int elasticity; + int err; + + hlist_for_each_entry(mp, p, &mdb->mhash[hash], hlist[mdb->ver]) { + count++; + if (unlikely(group == mp->addr)) { + return mp; + } + } + + elasticity = 0; + max = mdb->max; + + if (unlikely(count > br->hash_elasticity && count)) { + if (net_ratelimit()) + printk(KERN_INFO "%s: Multicast hash table " + "chain limit reached: %s\n", + br->dev->name, port ? port->dev->name : + br->dev->name); + + elasticity = br->hash_elasticity; + } + + if (mdb->size >= max) { + max *= 2; + if (unlikely(max >= br->hash_max)) { + printk(KERN_WARNING "%s: Multicast hash table maximum " + "reached, disabling snooping: %s, %d\n", + br->dev->name, port ? port->dev->name : + br->dev->name, + max); + err = -E2BIG; +disable: + br->multicast_disabled = 1; + goto err; + } + } + + if (max > mdb->max || elasticity) { + if (mdb->old) { + if (net_ratelimit()) + printk(KERN_INFO "%s: Multicast hash table " + "on fire: %s\n", + br->dev->name, port ? port->dev->name : + br->dev->name); + err = -EEXIST; + goto err; + } + + err = br_mdb_rehash(&br->mdb, max, elasticity); + if (err) { + printk(KERN_WARNING "%s: Cannot rehash multicast " + "hash table, disabling snooping: " + "%s, %d, %d\n", + br->dev->name, port ? port->dev->name : + br->dev->name, + mdb->size, err); + goto disable; + } + + err = -EAGAIN; + goto err; + } + + return NULL; + +err: + mp = ERR_PTR(err); + return mp; +} + +static struct net_bridge_mdb_entry *br_multicast_new_group( + struct net_bridge *br, struct net_bridge_port *port, __be32 group) +{ + struct net_bridge_mdb_htable *mdb = br->mdb; + struct net_bridge_mdb_entry *mp; + int hash; + + if (!mdb) { + if (br_mdb_rehash(&br->mdb, BR_HASH_SIZE, 0)) + return NULL; + goto rehash; + } + + hash = br_ip_hash(mdb, group); + mp = br_multicast_get_group(br, port, group, hash); + switch (PTR_ERR(mp)) { + case 0: + break; + + case -EAGAIN: +rehash: + mdb = br->mdb; + hash = br_ip_hash(mdb, group); + break; + + default: + goto out; + } + + mp = kzalloc(sizeof(*mp), GFP_ATOMIC); + if (unlikely(!mp)) + goto out; + + mp->br = br; + mp->addr = group; + setup_timer(&mp->timer, br_multicast_group_expired, + (unsigned long)mp); + setup_timer(&mp->query_timer, br_multicast_group_query_expired, + (unsigned long)mp); + + hlist_add_head_rcu(&mp->hlist[mdb->ver], &mdb->mhash[hash]); + mdb->size++; + +out: + return mp; +} + +static int br_multicast_add_group(struct net_bridge *br, + struct net_bridge_port *port, __be32 group) +{ + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + struct net_bridge_port_group **pp; + unsigned long now = jiffies; + int err; + + if (ipv4_is_local_multicast(group)) + return 0; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (port && port->state == BR_STATE_DISABLED)) + goto out; + + mp = br_multicast_new_group(br, port, group); + err = PTR_ERR(mp); + if (unlikely(IS_ERR(mp) || !mp)) + goto err; + + if (!port) { + hlist_add_head(&mp->mglist, &br->mglist); + mod_timer(&mp->timer, now + br->multicast_membership_interval); + goto out; + } + + for (pp = &mp->ports; (p = *pp); pp = &p->next) { + if (p->port == port) + goto found; + if ((unsigned long)p->port < (unsigned long)port) + break; + } + + p = kzalloc(sizeof(*p), GFP_ATOMIC); + err = -ENOMEM; + if (unlikely(!p)) + goto err; + + p->addr = group; + p->port = port; + p->next = *pp; + hlist_add_head(&p->mglist, &port->mglist); + setup_timer(&p->timer, br_multicast_port_group_expired, + (unsigned long)p); + setup_timer(&p->query_timer, br_multicast_port_group_query_expired, + (unsigned long)p); + + rcu_assign_pointer(*pp, p); + +found: + mod_timer(&p->timer, now + br->multicast_membership_interval); +out: + err = 0; + +err: + spin_unlock(&br->multicast_lock); + return err; +} + +static void br_multicast_router_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (port->multicast_router != 1 || + timer_pending(&port->multicast_router_timer) || + hlist_unhashed(&port->rlist)) + goto out; + + hlist_del_init_rcu(&port->rlist); + +out: + spin_unlock(&br->multicast_lock); +} + +static void br_multicast_local_router_expired(unsigned long data) +{ +} + +static void br_multicast_send_query(struct net_bridge *br, + struct net_bridge_port *port, u32 sent) +{ + unsigned long time; + struct sk_buff *skb; + + if (!netif_running(br->dev) || br->multicast_disabled || + timer_pending(&br->multicast_querier_timer)) + return; + + skb = br_multicast_alloc_query(br, 0); + if (!skb) + goto timer; + + if (port) { + __skb_push(skb, sizeof(struct ethhdr)); + skb->dev = port->dev; + NF_HOOK(PF_BRIDGE, NF_BR_LOCAL_OUT, skb, NULL, skb->dev, + dev_queue_xmit); + } else + netif_rx(skb); + +timer: + time = jiffies; + time += sent < br->multicast_startup_query_count ? + br->multicast_startup_query_interval : + br->multicast_query_interval; + mod_timer(port ? &port->multicast_query_timer : + &br->multicast_query_timer, time); +} + +static void br_multicast_port_query_expired(unsigned long data) +{ + struct net_bridge_port *port = (void *)data; + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (port && (port->state == BR_STATE_DISABLED || + port->state == BR_STATE_BLOCKING)) + goto out; + + if (port->multicast_startup_queries_sent < + br->multicast_startup_query_count) + port->multicast_startup_queries_sent++; + + br_multicast_send_query(port->br, port, + port->multicast_startup_queries_sent); + +out: + spin_unlock(&br->multicast_lock); +} + +void br_multicast_add_port(struct net_bridge_port *port) +{ + port->multicast_router = 1; + + setup_timer(&port->multicast_router_timer, br_multicast_router_expired, + (unsigned long)port); + setup_timer(&port->multicast_query_timer, + br_multicast_port_query_expired, (unsigned long)port); +} + +void br_multicast_del_port(struct net_bridge_port *port) +{ + del_timer_sync(&port->multicast_router_timer); +} + +static void __br_multicast_enable_port(struct net_bridge_port *port) +{ + port->multicast_startup_queries_sent = 0; + + if (try_to_del_timer_sync(&port->multicast_query_timer) >= 0 || + del_timer(&port->multicast_query_timer)) + mod_timer(&port->multicast_query_timer, jiffies); +} + +void br_multicast_enable_port(struct net_bridge_port *port) +{ + struct net_bridge *br = port->br; + + spin_lock(&br->multicast_lock); + if (br->multicast_disabled || !netif_running(br->dev)) + goto out; + + __br_multicast_enable_port(port); + +out: + spin_unlock(&br->multicast_lock); +} + +void br_multicast_disable_port(struct net_bridge_port *port) +{ + struct net_bridge *br = port->br; + struct net_bridge_port_group *pg; + struct hlist_node *p, *n; + + spin_lock(&br->multicast_lock); + hlist_for_each_entry_safe(pg, p, n, &port->mglist, mglist) + br_multicast_del_pg(br, pg); + + if (!hlist_unhashed(&port->rlist)) + hlist_del_init_rcu(&port->rlist); + del_timer(&port->multicast_router_timer); + del_timer(&port->multicast_query_timer); + spin_unlock(&br->multicast_lock); +} + +static int br_multicast_igmp3_report(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + struct igmpv3_report *ih; + struct igmpv3_grec *grec; + int i; + int len; + int num; + int type; + int err = 0; + __be32 group; + + if (!pskb_may_pull(skb, sizeof(*ih))) + return -EINVAL; + + ih = igmpv3_report_hdr(skb); + num = ntohs(ih->ngrec); + len = sizeof(*ih); + + for (i = 0; i < num; i++) { + len += sizeof(*grec); + if (!pskb_may_pull(skb, len)) + return -EINVAL; + + grec = (void *)(skb->data + len); + group = grec->grec_mca; + type = grec->grec_type; + + len += grec->grec_nsrcs * 4; + if (!pskb_may_pull(skb, len)) + return -EINVAL; + + /* We treat this as an IGMPv2 report for now. */ + switch (type) { + case IGMPV3_MODE_IS_INCLUDE: + case IGMPV3_MODE_IS_EXCLUDE: + case IGMPV3_CHANGE_TO_INCLUDE: + case IGMPV3_CHANGE_TO_EXCLUDE: + case IGMPV3_ALLOW_NEW_SOURCES: + case IGMPV3_BLOCK_OLD_SOURCES: + break; + + default: + continue; + } + + err = br_multicast_add_group(br, port, group); + if (err) + break; + } + + return err; +} + +static void br_multicast_add_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + struct hlist_node *p; + struct hlist_node **h; + + for (h = &br->router_list.first; + (p = *h) && + (unsigned long)container_of(p, struct net_bridge_port, rlist) > + (unsigned long)port; + h = &p->next) + ; + + port->rlist.pprev = h; + port->rlist.next = p; + rcu_assign_pointer(*h, &port->rlist); + if (p) + p->pprev = &port->rlist.next; +} + +static void br_multicast_mark_router(struct net_bridge *br, + struct net_bridge_port *port) +{ + unsigned long now = jiffies; + + if (!port) { + if (br->multicast_router == 1) + mod_timer(&br->multicast_router_timer, + now + br->multicast_querier_interval); + return; + } + + if (port->multicast_router != 1) + return; + + if (!hlist_unhashed(&port->rlist)) + goto timer; + + br_multicast_add_router(br, port); + +timer: + mod_timer(&port->multicast_router_timer, + now + br->multicast_querier_interval); +} + +static void br_multicast_query_received(struct net_bridge *br, + struct net_bridge_port *port, + __be32 saddr) +{ + if (saddr) + mod_timer(&br->multicast_querier_timer, + jiffies + br->multicast_querier_interval); + else if (timer_pending(&br->multicast_querier_timer)) + return; + + br_multicast_mark_router(br, port); +} + +static int br_multicast_query(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + struct igmphdr *ih = igmp_hdr(skb); + struct net_bridge_mdb_entry *mp; + struct igmpv3_query *ih3; + struct net_bridge_port_group *p; + struct net_bridge_port_group **pp; + unsigned long max_delay; + unsigned long now = jiffies; + __be32 group; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (port && port->state == BR_STATE_DISABLED)) + goto out; + + br_multicast_query_received(br, port, iph->saddr); + + group = ih->group; + + if (skb->len == sizeof(*ih)) { + max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); + + if (!max_delay) { + max_delay = 10 * HZ; + group = 0; + } + } else { + if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) + return -EINVAL; + + ih3 = igmpv3_query_hdr(skb); + if (ih3->nsrcs) + return 0; + + max_delay = ih3->code ? 1 : + IGMPV3_MRC(ih3->code) * (HZ / IGMP_TIMER_SCALE); + } + + if (!group) + goto out; + + mp = br_mdb_ip_get(br->mdb, group); + if (!mp) + goto out; + + max_delay *= br->multicast_last_member_count; + + if (!hlist_unhashed(&mp->mglist) && + (timer_pending(&mp->timer) ? + time_after(mp->timer.expires, now + max_delay) : + try_to_del_timer_sync(&mp->timer) >= 0)) + mod_timer(&mp->timer, now + max_delay); + + for (pp = &mp->ports; (p = *pp); pp = &p->next) { + if (timer_pending(&p->timer) ? + time_after(p->timer.expires, now + max_delay) : + try_to_del_timer_sync(&p->timer) >= 0) + mod_timer(&mp->timer, now + max_delay); + } + +out: + spin_unlock(&br->multicast_lock); + return 0; +} + +static void br_multicast_leave_group(struct net_bridge *br, + struct net_bridge_port *port, + __be32 group) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct net_bridge_port_group *p; + unsigned long now; + unsigned long time; + + if (ipv4_is_local_multicast(group)) + return; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || + (port && port->state == BR_STATE_DISABLED) || + timer_pending(&br->multicast_querier_timer)) + goto out; + + mdb = br->mdb; + mp = br_mdb_ip_get(mdb, group); + if (!mp) + goto out; + + now = jiffies; + time = now + br->multicast_last_member_count * + br->multicast_last_member_interval; + + if (!port) { + if (!hlist_unhashed(&mp->mglist) && + (timer_pending(&mp->timer) ? + time_after(mp->timer.expires, time) : + try_to_del_timer_sync(&mp->timer) >= 0)) { + mod_timer(&mp->timer, time); + + mp->queries_sent = 0; + mod_timer(&mp->query_timer, now); + } + + goto out; + } + + for (p = mp->ports; p; p = p->next) { + if (p->port != port) + continue; + + if (!hlist_unhashed(&p->mglist) && + (timer_pending(&p->timer) ? + time_after(p->timer.expires, time) : + try_to_del_timer_sync(&p->timer) >= 0)) { + mod_timer(&p->timer, time); + + p->queries_sent = 0; + mod_timer(&p->query_timer, now); + } + + break; + } + +out: + spin_unlock(&br->multicast_lock); +} + +static int br_multicast_ipv4_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + struct sk_buff *skb2 = skb; + struct iphdr *iph; + struct igmphdr *ih; + unsigned len; + unsigned offset; + int err; + + BR_INPUT_SKB_CB(skb)->igmp = 0; + BR_INPUT_SKB_CB(skb)->mrouters_only = 0; + + /* We treat OOM as packet loss for now. */ + if (!pskb_may_pull(skb, sizeof(*iph))) + return -EINVAL; + + iph = ip_hdr(skb); + + if (iph->ihl < 5 || iph->version != 4) + return -EINVAL; + + if (!pskb_may_pull(skb, ip_hdrlen(skb))) + return -EINVAL; + + iph = ip_hdr(skb); + + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + return -EINVAL; + + if (iph->protocol != IPPROTO_IGMP) + return 0; + + len = ntohs(iph->tot_len); + if (skb->len < len || len < ip_hdrlen(skb)) + return -EINVAL; + + if (skb->len > len) { + skb2 = skb_clone(skb, GFP_ATOMIC); + if (!skb2) + return -ENOMEM; + + err = pskb_trim_rcsum(skb2, len); + if (err) + return err; + } + + len -= ip_hdrlen(skb2); + offset = skb_network_offset(skb2) + ip_hdrlen(skb2); + __skb_pull(skb2, offset); + skb_reset_transport_header(skb2); + + err = -EINVAL; + if (!pskb_may_pull(skb2, sizeof(*ih))) + goto out; + + iph = ip_hdr(skb2); + + switch (skb2->ip_summed) { + case CHECKSUM_COMPLETE: + if (!csum_fold(skb2->csum)) + break; + /* fall through */ + case CHECKSUM_NONE: + skb2->csum = 0; + if (skb_checksum_complete(skb2)) + return -EINVAL; + } + + err = 0; + + BR_INPUT_SKB_CB(skb)->igmp = 1; + ih = igmp_hdr(skb2); + + switch (ih->type) { + case IGMP_HOST_MEMBERSHIP_REPORT: + case IGMPV2_HOST_MEMBERSHIP_REPORT: + BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + err = br_multicast_add_group(br, port, ih->group); + break; + case IGMPV3_HOST_MEMBERSHIP_REPORT: + err = br_multicast_igmp3_report(br, port, skb2); + break; + case IGMP_HOST_MEMBERSHIP_QUERY: + err = br_multicast_query(br, port, skb2); + break; + case IGMP_HOST_LEAVE_MESSAGE: + br_multicast_leave_group(br, port, ih->group); + break; + } + +out: + __skb_push(skb2, offset); + if (skb2 != skb) + kfree_skb(skb2); + return err; +} + +int br_multicast_rcv(struct net_bridge *br, struct net_bridge_port *port, + struct sk_buff *skb) +{ + if (br->multicast_disabled) + return 0; + + switch (skb->protocol) { + case htons(ETH_P_IP): + return br_multicast_ipv4_rcv(br, port, skb); + } + + return 0; +} + +static void br_multicast_query_expired(unsigned long data) +{ + struct net_bridge *br = (void *)data; + + spin_lock(&br->multicast_lock); + if (br->multicast_startup_queries_sent < + br->multicast_startup_query_count) + br->multicast_startup_queries_sent++; + + br_multicast_send_query(br, NULL, br->multicast_startup_queries_sent); + + spin_unlock(&br->multicast_lock); +} + +void br_multicast_init(struct net_bridge *br) +{ + br->hash_elasticity = 4; + br->hash_max = 512; + + br->multicast_router = 1; + br->multicast_last_member_count = 2; + br->multicast_startup_query_count = 2; + + br->multicast_last_member_interval = HZ; + br->multicast_query_response_interval = 10 * HZ; + br->multicast_startup_query_interval = 125 * HZ / 4; + br->multicast_query_interval = 125 * HZ; + br->multicast_querier_interval = 255 * HZ; + br->multicast_membership_interval = 260 * HZ; + + spin_lock_init(&br->multicast_lock); + setup_timer(&br->multicast_router_timer, + br_multicast_local_router_expired, 0); + setup_timer(&br->multicast_querier_timer, + br_multicast_local_router_expired, 0); + setup_timer(&br->multicast_query_timer, br_multicast_query_expired, + (unsigned long)br); +} + +void br_multicast_open(struct net_bridge *br) +{ + br->multicast_startup_queries_sent = 0; + + if (br->multicast_disabled) + return; + + mod_timer(&br->multicast_query_timer, jiffies); +} + +void br_multicast_stop(struct net_bridge *br) +{ + struct net_bridge_mdb_htable *mdb; + struct net_bridge_mdb_entry *mp; + struct hlist_node *p, *n; + u32 ver; + int i; + + del_timer_sync(&br->multicast_router_timer); + del_timer_sync(&br->multicast_querier_timer); + del_timer_sync(&br->multicast_query_timer); + + spin_lock_bh(&br->multicast_lock); + mdb = br->mdb; + if (!mdb) + goto out; + + br->mdb = NULL; + + ver = mdb->ver; + for (i = 0; i < mdb->max; i++) { + hlist_for_each_entry_safe(mp, p, n, &mdb->mhash[i], + hlist[ver]) { + del_timer(&mp->timer); + del_timer(&mp->query_timer); + call_rcu_bh(&mp->rcu, br_multicast_free_group); + } + } + + if (mdb->old) { + spin_unlock_bh(&br->multicast_lock); + synchronize_rcu_bh(); + spin_lock_bh(&br->multicast_lock); + WARN_ON(mdb->old); + } + + mdb->old = mdb; + call_rcu_bh(&mdb->rcu, br_mdb_free); + +out: + spin_unlock_bh(&br->multicast_lock); +} + +int br_multicast_set_router(struct net_bridge *br, unsigned long val) +{ + int err = -ENOENT; + + spin_lock_bh(&br->multicast_lock); + if (!netif_running(br->dev)) + goto unlock; + + switch (val) { + case 0: + case 2: + del_timer(&br->multicast_router_timer); + /* fall through */ + case 1: + br->multicast_router = val; + err = 0; + break; + + default: + err = -EINVAL; + break; + } + +unlock: + spin_unlock_bh(&br->multicast_lock); + + return err; +} + +int br_multicast_set_port_router(struct net_bridge_port *p, unsigned long val) +{ + struct net_bridge *br = p->br; + int err = -ENOENT; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev) || p->state == BR_STATE_DISABLED) + goto unlock; + + switch (val) { + case 0: + case 1: + case 2: + p->multicast_router = val; + err = 0; + + if (val < 2 && !hlist_unhashed(&p->rlist)) + hlist_del_init_rcu(&p->rlist); + + if (val == 1) + break; + + del_timer(&p->multicast_router_timer); + + if (val == 0) + break; + + br_multicast_add_router(br, p); + break; + + default: + err = -EINVAL; + break; + } + +unlock: + spin_unlock(&br->multicast_lock); + + return err; +} + +int br_multicast_toggle(struct net_bridge *br, unsigned long val) +{ + struct net_bridge_port *port; + int err = -ENOENT; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev)) + goto unlock; + + err = 0; + if (br->multicast_disabled == !val) + goto unlock; + + br->multicast_disabled = !val; + if (br->multicast_disabled) + goto unlock; + + if (br->mdb) { + if (br->mdb->old) { + err = -EEXIST; +rollback: + br->multicast_disabled = !!val; + goto unlock; + } + + err = br_mdb_rehash(&br->mdb, br->mdb->max, + br->hash_elasticity); + if (err) + goto rollback; + } + + br_multicast_open(br); + list_for_each_entry(port, &br->port_list, list) { + if (port->state == BR_STATE_DISABLED || + port->state == BR_STATE_BLOCKING) + continue; + + __br_multicast_enable_port(port); + } + +unlock: + spin_unlock(&br->multicast_lock); + + return err; +} + +int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val) +{ + int err = -ENOENT; + u32 old; + + spin_lock(&br->multicast_lock); + if (!netif_running(br->dev)) + goto unlock; + + err = -EINVAL; + if (!is_power_of_2(val)) + goto unlock; + if (br->mdb && val < br->mdb->size) + goto unlock; + + err = 0; + + old = br->hash_max; + br->hash_max = val; + + if (br->mdb) { + if (br->mdb->old) { + err = -EEXIST; +rollback: + br->hash_max = old; + goto unlock; + } + + err = br_mdb_rehash(&br->mdb, br->hash_max, + br->hash_elasticity); + if (err) + goto rollback; + } + +unlock: + spin_unlock(&br->multicast_lock); + + return err; +} diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 1f0c4f44b76..9191198c4f1 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -57,6 +57,41 @@ struct net_bridge_fdb_entry unsigned char is_static; }; +struct net_bridge_port_group { + struct net_bridge_port *port; + struct net_bridge_port_group *next; + struct hlist_node mglist; + struct rcu_head rcu; + struct timer_list timer; + struct timer_list query_timer; + __be32 addr; + u32 queries_sent; +}; + +struct net_bridge_mdb_entry +{ + struct hlist_node hlist[2]; + struct hlist_node mglist; + struct net_bridge *br; + struct net_bridge_port_group *ports; + struct rcu_head rcu; + struct timer_list timer; + struct timer_list query_timer; + __be32 addr; + u32 queries_sent; +}; + +struct net_bridge_mdb_htable +{ + struct hlist_head *mhash; + struct rcu_head rcu; + struct net_bridge_mdb_htable *old; + u32 size; + u32 max; + u32 secret; + u32 ver; +}; + struct net_bridge_port { struct net_bridge *br; @@ -84,6 +119,15 @@ struct net_bridge_port unsigned long flags; #define BR_HAIRPIN_MODE 0x00000001 + +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + u32 multicast_startup_queries_sent; + unsigned char multicast_router; + struct timer_list multicast_router_timer; + struct timer_list multicast_query_timer; + struct hlist_head mglist; + struct hlist_node rlist; +#endif }; struct net_bridge @@ -124,6 +168,35 @@ struct net_bridge unsigned char topology_change; unsigned char topology_change_detected; +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + unsigned char multicast_router; + + u8 multicast_disabled:1; + + u32 hash_elasticity; + u32 hash_max; + + u32 multicast_last_member_count; + u32 multicast_startup_queries_sent; + u32 multicast_startup_query_count; + + unsigned long multicast_last_member_interval; + unsigned long multicast_membership_interval; + unsigned long multicast_querier_interval; + unsigned long multicast_query_interval; + unsigned long multicast_query_response_interval; + unsigned long multicast_startup_query_interval; + + spinlock_t multicast_lock; + struct net_bridge_mdb_htable *mdb; + struct hlist_head router_list; + struct hlist_head mglist; + + struct timer_list multicast_router_timer; + struct timer_list multicast_querier_timer; + struct timer_list multicast_query_timer; +#endif + struct timer_list hello_timer; struct timer_list tcn_timer; struct timer_list topology_change_timer; @@ -131,6 +204,14 @@ struct net_bridge struct kobject *ifobj; }; +struct br_input_skb_cb { + struct net_device *brdev; + int igmp; + int mrouters_only; +}; + +#define BR_INPUT_SKB_CB(__skb) ((struct br_input_skb_cb *)(__skb)->cb) + extern struct notifier_block br_device_notifier; extern const u8 br_group_address[ETH_ALEN]; @@ -174,7 +255,8 @@ extern void br_forward(const struct net_bridge_port *to, struct sk_buff *skb); extern int br_forward_finish(struct sk_buff *skb); extern void br_flood_deliver(struct net_bridge *br, struct sk_buff *skb); -extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb); +extern void br_flood_forward(struct net_bridge *br, struct sk_buff *skb, + struct sk_buff *skb2); /* br_if.c */ extern void br_port_carrier_check(struct net_bridge_port *p); @@ -197,6 +279,90 @@ extern struct sk_buff *br_handle_frame(struct net_bridge_port *p, extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); extern int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, void __user *arg); +/* br_multicast.c */ +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +extern int br_multicast_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb); +extern struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, + struct sk_buff *skb); +extern void br_multicast_add_port(struct net_bridge_port *port); +extern void br_multicast_del_port(struct net_bridge_port *port); +extern void br_multicast_enable_port(struct net_bridge_port *port); +extern void br_multicast_disable_port(struct net_bridge_port *port); +extern void br_multicast_init(struct net_bridge *br); +extern void br_multicast_open(struct net_bridge *br); +extern void br_multicast_stop(struct net_bridge *br); +extern void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb); +extern void br_multicast_forward(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, struct sk_buff *skb2); +extern int br_multicast_set_router(struct net_bridge *br, unsigned long val); +extern int br_multicast_set_port_router(struct net_bridge_port *p, + unsigned long val); +extern int br_multicast_toggle(struct net_bridge *br, unsigned long val); +extern int br_multicast_set_hash_max(struct net_bridge *br, unsigned long val); +#else +static inline int br_multicast_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + return 0; +} + +static inline struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge *br, + struct sk_buff *skb) +{ + return NULL; +} + +static inline void br_multicast_add_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_del_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_enable_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_disable_port(struct net_bridge_port *port) +{ +} + +static inline void br_multicast_init(struct net_bridge *br) +{ +} + +static inline void br_multicast_open(struct net_bridge *br) +{ +} + +static inline void br_multicast_stop(struct net_bridge *br) +{ +} + +static inline void br_multicast_deliver(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb) +{ +} + +static inline void br_multicast_forward(struct net_bridge_mdb_entry *mdst, + struct sk_buff *skb, + struct sk_buff *skb2) +{ +} +#endif + +static inline bool br_multicast_is_router(struct net_bridge *br) +{ + return br->multicast_router == 2 || + (br->multicast_router == 1 && + timer_pending(&br->multicast_router_timer)); +} + /* br_netfilter.c */ #ifdef CONFIG_BRIDGE_NETFILTER extern int br_netfilter_init(void); diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index fd3f8d6c099..edcf14b560f 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -386,6 +386,8 @@ static void br_make_forwarding(struct net_bridge_port *p) else p->state = BR_STATE_LEARNING; + br_multicast_enable_port(p); + br_log_state(p); if (br->forward_delay != 0) diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c index 9a52ac5b452..d527119e9f5 100644 --- a/net/bridge/br_stp_if.c +++ b/net/bridge/br_stp_if.c @@ -108,6 +108,7 @@ void br_stp_disable_port(struct net_bridge_port *p) del_timer(&p->hold_timer); br_fdb_delete_by_port(br, p, 0); + br_multicast_disable_port(p); br_configuration_update(br); diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index bee4f300d0c..dd321e39e62 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -345,6 +345,273 @@ static ssize_t store_flush(struct device *d, } static DEVICE_ATTR(flush, S_IWUSR, NULL, store_flush); +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +static ssize_t show_multicast_router(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", br->multicast_router); +} + +static ssize_t store_multicast_router(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_router); +} +static DEVICE_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, + store_multicast_router); + +static ssize_t show_multicast_snooping(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%d\n", !br->multicast_disabled); +} + +static ssize_t store_multicast_snooping(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_toggle); +} +static DEVICE_ATTR(multicast_snooping, S_IRUGO | S_IWUSR, + show_multicast_snooping, store_multicast_snooping); + +static ssize_t show_hash_elasticity(struct device *d, + struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->hash_elasticity); +} + +static int set_elasticity(struct net_bridge *br, unsigned long val) +{ + br->hash_elasticity = val; + return 0; +} + +static ssize_t store_hash_elasticity(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_elasticity); +} +static DEVICE_ATTR(hash_elasticity, S_IRUGO | S_IWUSR, show_hash_elasticity, + store_hash_elasticity); + +static ssize_t show_hash_max(struct device *d, struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->hash_max); +} + +static ssize_t store_hash_max(struct device *d, struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, br_multicast_set_hash_max); +} +static DEVICE_ATTR(hash_max, S_IRUGO | S_IWUSR, show_hash_max, + store_hash_max); + +static ssize_t show_multicast_last_member_count(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->multicast_last_member_count); +} + +static int set_last_member_count(struct net_bridge *br, unsigned long val) +{ + br->multicast_last_member_count = val; + return 0; +} + +static ssize_t store_multicast_last_member_count(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_last_member_count); +} +static DEVICE_ATTR(multicast_last_member_count, S_IRUGO | S_IWUSR, + show_multicast_last_member_count, + store_multicast_last_member_count); + +static ssize_t show_multicast_startup_query_count( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%u\n", br->multicast_startup_query_count); +} + +static int set_startup_query_count(struct net_bridge *br, unsigned long val) +{ + br->multicast_startup_query_count = val; + return 0; +} + +static ssize_t store_multicast_startup_query_count( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_startup_query_count); +} +static DEVICE_ATTR(multicast_startup_query_count, S_IRUGO | S_IWUSR, + show_multicast_startup_query_count, + store_multicast_startup_query_count); + +static ssize_t show_multicast_last_member_interval( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_last_member_interval)); +} + +static int set_last_member_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_last_member_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t store_multicast_last_member_interval( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_last_member_interval); +} +static DEVICE_ATTR(multicast_last_member_interval, S_IRUGO | S_IWUSR, + show_multicast_last_member_interval, + store_multicast_last_member_interval); + +static ssize_t show_multicast_membership_interval( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_membership_interval)); +} + +static int set_membership_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_membership_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t store_multicast_membership_interval( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_membership_interval); +} +static DEVICE_ATTR(multicast_membership_interval, S_IRUGO | S_IWUSR, + show_multicast_membership_interval, + store_multicast_membership_interval); + +static ssize_t show_multicast_querier_interval(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_querier_interval)); +} + +static int set_querier_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_querier_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t store_multicast_querier_interval(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_querier_interval); +} +static DEVICE_ATTR(multicast_querier_interval, S_IRUGO | S_IWUSR, + show_multicast_querier_interval, + store_multicast_querier_interval); + +static ssize_t show_multicast_query_interval(struct device *d, + struct device_attribute *attr, + char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf(buf, "%lu\n", + jiffies_to_clock_t(br->multicast_query_interval)); +} + +static int set_query_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_query_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t store_multicast_query_interval(struct device *d, + struct device_attribute *attr, + const char *buf, size_t len) +{ + return store_bridge_parm(d, buf, len, set_query_interval); +} +static DEVICE_ATTR(multicast_query_interval, S_IRUGO | S_IWUSR, + show_multicast_query_interval, + store_multicast_query_interval); + +static ssize_t show_multicast_query_response_interval( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf( + buf, "%lu\n", + jiffies_to_clock_t(br->multicast_query_response_interval)); +} + +static int set_query_response_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_query_response_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t store_multicast_query_response_interval( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_query_response_interval); +} +static DEVICE_ATTR(multicast_query_response_interval, S_IRUGO | S_IWUSR, + show_multicast_query_response_interval, + store_multicast_query_response_interval); + +static ssize_t show_multicast_startup_query_interval( + struct device *d, struct device_attribute *attr, char *buf) +{ + struct net_bridge *br = to_bridge(d); + return sprintf( + buf, "%lu\n", + jiffies_to_clock_t(br->multicast_startup_query_interval)); +} + +static int set_startup_query_interval(struct net_bridge *br, unsigned long val) +{ + br->multicast_startup_query_interval = clock_t_to_jiffies(val); + return 0; +} + +static ssize_t store_multicast_startup_query_interval( + struct device *d, struct device_attribute *attr, const char *buf, + size_t len) +{ + return store_bridge_parm(d, buf, len, set_startup_query_interval); +} +static DEVICE_ATTR(multicast_startup_query_interval, S_IRUGO | S_IWUSR, + show_multicast_startup_query_interval, + store_multicast_startup_query_interval); +#endif + static struct attribute *bridge_attrs[] = { &dev_attr_forward_delay.attr, &dev_attr_hello_time.attr, @@ -364,6 +631,20 @@ static struct attribute *bridge_attrs[] = { &dev_attr_gc_timer.attr, &dev_attr_group_addr.attr, &dev_attr_flush.attr, +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + &dev_attr_multicast_router.attr, + &dev_attr_multicast_snooping.attr, + &dev_attr_hash_elasticity.attr, + &dev_attr_hash_max.attr, + &dev_attr_multicast_last_member_count.attr, + &dev_attr_multicast_startup_query_count.attr, + &dev_attr_multicast_last_member_interval.attr, + &dev_attr_multicast_membership_interval.attr, + &dev_attr_multicast_querier_interval.attr, + &dev_attr_multicast_query_interval.attr, + &dev_attr_multicast_query_response_interval.attr, + &dev_attr_multicast_startup_query_interval.attr, +#endif NULL }; diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c index 820643a3ba9..696596cd338 100644 --- a/net/bridge/br_sysfs_if.c +++ b/net/bridge/br_sysfs_if.c @@ -159,6 +159,21 @@ static ssize_t store_hairpin_mode(struct net_bridge_port *p, unsigned long v) static BRPORT_ATTR(hairpin_mode, S_IRUGO | S_IWUSR, show_hairpin_mode, store_hairpin_mode); +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING +static ssize_t show_multicast_router(struct net_bridge_port *p, char *buf) +{ + return sprintf(buf, "%d\n", p->multicast_router); +} + +static ssize_t store_multicast_router(struct net_bridge_port *p, + unsigned long v) +{ + return br_multicast_set_port_router(p, v); +} +static BRPORT_ATTR(multicast_router, S_IRUGO | S_IWUSR, show_multicast_router, + store_multicast_router); +#endif + static struct brport_attribute *brport_attrs[] = { &brport_attr_path_cost, &brport_attr_priority, @@ -176,6 +191,9 @@ static struct brport_attribute *brport_attrs[] = { &brport_attr_hold_timer, &brport_attr_flush, &brport_attr_hairpin_mode, +#ifdef CONFIG_BRIDGE_IGMP_SNOOPING + &brport_attr_multicast_router, +#endif NULL }; diff --git a/net/core/dev.c b/net/core/dev.c index eb7f1a4fefc..e5972f7f7e1 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1113,19 +1113,7 @@ void dev_load(struct net *net, const char *name) } EXPORT_SYMBOL(dev_load); -/** - * dev_open - prepare an interface for use. - * @dev: device to open - * - * Takes a device from down to up state. The device's private open - * function is invoked and then the multicast lists are loaded. Finally - * the device is moved into the up state and a %NETDEV_UP message is - * sent to the netdev notifier chain. - * - * Calling this function on an active interface is a nop. On a failure - * a negative errno code is returned. - */ -int dev_open(struct net_device *dev) +static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; int ret; @@ -1133,13 +1121,6 @@ int dev_open(struct net_device *dev) ASSERT_RTNL(); /* - * Is it already up? - */ - - if (dev->flags & IFF_UP) - return 0; - - /* * Is it even present? */ if (!netif_device_present(dev)) @@ -1187,36 +1168,57 @@ int dev_open(struct net_device *dev) * Wakeup transmit queue engine */ dev_activate(dev); - - /* - * ... and announce new interface. - */ - call_netdevice_notifiers(NETDEV_UP, dev); } return ret; } -EXPORT_SYMBOL(dev_open); /** - * dev_close - shutdown an interface. - * @dev: device to shutdown + * dev_open - prepare an interface for use. + * @dev: device to open * - * This function moves an active device into down state. A - * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device - * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier - * chain. + * Takes a device from down to up state. The device's private open + * function is invoked and then the multicast lists are loaded. Finally + * the device is moved into the up state and a %NETDEV_UP message is + * sent to the netdev notifier chain. + * + * Calling this function on an active interface is a nop. On a failure + * a negative errno code is returned. */ -int dev_close(struct net_device *dev) +int dev_open(struct net_device *dev) +{ + int ret; + + /* + * Is it already up? + */ + if (dev->flags & IFF_UP) + return 0; + + /* + * Open device + */ + ret = __dev_open(dev); + if (ret < 0) + return ret; + + /* + * ... and announce new interface. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_UP, dev); + + return ret; +} +EXPORT_SYMBOL(dev_open); + +static int __dev_close(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; - ASSERT_RTNL(); + ASSERT_RTNL(); might_sleep(); - if (!(dev->flags & IFF_UP)) - return 0; - /* * Tell people we are going down, so that they can * prepare to death, when device is still operating. @@ -1252,14 +1254,34 @@ int dev_close(struct net_device *dev) dev->flags &= ~IFF_UP; /* - * Tell people we are down + * Shutdown NET_DMA */ - call_netdevice_notifiers(NETDEV_DOWN, dev); + net_dmaengine_put(); + + return 0; +} + +/** + * dev_close - shutdown an interface. + * @dev: device to shutdown + * + * This function moves an active device into down state. A + * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device + * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier + * chain. + */ +int dev_close(struct net_device *dev) +{ + if (!(dev->flags & IFF_UP)) + return 0; + + __dev_close(dev); /* - * Shutdown NET_DMA + * Tell people we are down */ - net_dmaengine_put(); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_DOWN, dev); return 0; } @@ -4299,18 +4321,10 @@ unsigned dev_get_flags(const struct net_device *dev) } EXPORT_SYMBOL(dev_get_flags); -/** - * dev_change_flags - change device settings - * @dev: device - * @flags: device state flags - * - * Change settings on device based state flags. The flags are - * in the userspace exported format. - */ -int dev_change_flags(struct net_device *dev, unsigned flags) +int __dev_change_flags(struct net_device *dev, unsigned int flags) { - int ret, changes; int old_flags = dev->flags; + int ret; ASSERT_RTNL(); @@ -4341,17 +4355,12 @@ int dev_change_flags(struct net_device *dev, unsigned flags) ret = 0; if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */ - ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev); + ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev); if (!ret) dev_set_rx_mode(dev); } - if (dev->flags & IFF_UP && - ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | - IFF_VOLATILE))) - call_netdevice_notifiers(NETDEV_CHANGE, dev); - if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; @@ -4370,11 +4379,47 @@ int dev_change_flags(struct net_device *dev, unsigned flags) dev_set_allmulti(dev, inc); } - /* Exclude state transition flags, already notified */ - changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING); + return ret; +} + +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) +{ + unsigned int changes = dev->flags ^ old_flags; + + if (changes & IFF_UP) { + if (dev->flags & IFF_UP) + call_netdevice_notifiers(NETDEV_UP, dev); + else + call_netdevice_notifiers(NETDEV_DOWN, dev); + } + + if (dev->flags & IFF_UP && + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) + call_netdevice_notifiers(NETDEV_CHANGE, dev); +} + +/** + * dev_change_flags - change device settings + * @dev: device + * @flags: device state flags + * + * Change settings on device based state flags. The flags are + * in the userspace exported format. + */ +int dev_change_flags(struct net_device *dev, unsigned flags) +{ + int ret, changes; + int old_flags = dev->flags; + + ret = __dev_change_flags(dev, flags); + if (ret < 0) + return ret; + + changes = old_flags ^ dev->flags; if (changes) rtmsg_ifinfo(RTM_NEWLINK, dev, changes); + __dev_notify_flags(dev, old_flags); return ret; } EXPORT_SYMBOL(dev_change_flags); @@ -4865,6 +4910,10 @@ static void rollback_registered_many(struct list_head *head) */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); + /* * Flush the unicast and multicast chains */ @@ -5091,7 +5140,9 @@ int register_netdevice(struct net_device *dev) * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); out: return ret; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 4dd4c3cdc44..d1472a42332 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -549,6 +549,19 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } +static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, + const struct ifinfomsg *ifm) +{ + unsigned int flags = ifm->ifi_flags; + + /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ + if (ifm->ifi_change) + flags = (flags & ifm->ifi_change) | + (dev->flags & ~ifm->ifi_change); + + return flags; +} + static void copy_rtnl_link_stats(struct rtnl_link_stats *a, const struct net_device_stats *b) { @@ -904,13 +917,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, } if (ifm->ifi_flags || ifm->ifi_change) { - unsigned int flags = ifm->ifi_flags; - - /* bugwards compatibility: ifi_change == 0 is treated as ~0 */ - if (ifm->ifi_change) - flags = (flags & ifm->ifi_change) | - (dev->flags & ~ifm->ifi_change); - err = dev_change_flags(dev, flags); + err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm)); if (err < 0) goto errout; } @@ -1053,6 +1060,26 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) return 0; } +int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm) +{ + unsigned int old_flags; + int err; + + old_flags = dev->flags; + if (ifm && (ifm->ifi_flags || ifm->ifi_change)) { + err = __dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm)); + if (err < 0) + return err; + } + + dev->rtnl_link_state = RTNL_LINK_INITIALIZED; + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + + __dev_notify_flags(dev, old_flags); + return 0; +} +EXPORT_SYMBOL(rtnl_configure_link); + struct net_device *rtnl_create_link(struct net *src_net, struct net *net, char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { @@ -1074,6 +1101,7 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, dev_net_set(dev, net); dev->rtnl_link_ops = ops; + dev->rtnl_link_state = RTNL_LINK_INITIALIZING; dev->real_num_tx_queues = real_num_queues; if (strchr(dev->name, '%')) { @@ -1203,7 +1231,7 @@ replay: if (!(nlh->nlmsg_flags & NLM_F_CREATE)) return -ENODEV; - if (ifm->ifi_index || ifm->ifi_flags || ifm->ifi_change) + if (ifm->ifi_index) return -EOPNOTSUPP; if (tb[IFLA_MAP] || tb[IFLA_MASTER] || tb[IFLA_PROTINFO]) return -EOPNOTSUPP; @@ -1234,9 +1262,15 @@ replay: err = ops->newlink(net, dev, tb, data); else err = register_netdevice(dev); - if (err < 0 && !IS_ERR(dev)) + if (err < 0 && !IS_ERR(dev)) { free_netdev(dev); + goto out; + } + err = rtnl_configure_link(dev, ifm); + if (err < 0) + unregister_netdevice(dev); +out: put_net(dest_net); return err; } @@ -1425,17 +1459,14 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi struct net_device *dev = ptr; switch (event) { - case NETDEV_UNREGISTER: - rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); - break; case NETDEV_UP: case NETDEV_DOWN: - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); - break; + case NETDEV_PRE_UP: case NETDEV_POST_INIT: case NETDEV_REGISTER: case NETDEV_CHANGE: case NETDEV_GOING_DOWN: + case NETDEV_UNREGISTER: case NETDEV_UNREGISTER_BATCH: break; default: diff --git a/net/mac80211/main.c b/net/mac80211/main.c index ec8f767ba95..06c33b68d8e 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -558,8 +558,12 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) debugfs_hw_add(local); + /* + * if the driver doesn't specify a max listen interval we + * use 5 which should be a safe default + */ if (local->hw.max_listen_interval == 0) - local->hw.max_listen_interval = 1; + local->hw.max_listen_interval = 5; local->hw.conf.listen_interval = local->hw.max_listen_interval; diff --git a/net/mac80211/work.c b/net/mac80211/work.c index 7e708d5c88b..1e1ea3007b0 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -869,6 +869,7 @@ static void ieee80211_work_work(struct work_struct *work) break; case IEEE80211_WORK_ABORT: rma = WORK_ACT_TIMEOUT; + break; case IEEE80211_WORK_DIRECT_PROBE: rma = ieee80211_direct_probe(wk); break; |