diff options
author | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-07-15 16:50:46 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@woody.linux-foundation.org> | 2007-07-15 16:50:46 -0700 |
commit | d3502d7f25b22cfc9762bf1781faa9db1bb3be2e (patch) | |
tree | e1d0195704efaafa14caf6965c8f2b6b00cbcb83 /net | |
parent | d2a9a8ded48bec153f08ee87a40626c8d0737f79 (diff) | |
parent | 0a9f2a467d8dacaf7e97469dba99ed2d07287d80 (diff) | |
download | lwn-d3502d7f25b22cfc9762bf1781faa9db1bb3be2e.tar.gz lwn-d3502d7f25b22cfc9762bf1781faa9db1bb3be2e.zip |
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6
* 'master' of master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6: (53 commits)
[TCP]: Verify the presence of RETRANS bit when leaving FRTO
[IPV6]: Call inet6addr_chain notifiers on link down
[NET_SCHED]: Kill CONFIG_NET_CLS_POLICE
[NET_SCHED]: act_api: qdisc internal reclassify support
[NET_SCHED]: sch_dsmark: act_api support
[NET_SCHED]: sch_atm: act_api support
[NET_SCHED]: sch_atm: Lindent
[IPV6]: MSG_ERRQUEUE messages do not pass to connected raw sockets
[IPV4]: Cleanup call to __neigh_lookup()
[NET_SCHED]: Revert "avoid transmit softirq on watchdog wakeup" optimization
[NETFILTER]: nf_conntrack: UDPLITE support
[NETFILTER]: nf_conntrack: mark protocols __read_mostly
[NETFILTER]: x_tables: add connlimit match
[NETFILTER]: Lower *tables printk severity
[NETFILTER]: nf_conntrack: Don't track locally generated special ICMP error
[NETFILTER]: nf_conntrack: Introduces nf_ct_get_tuplepr and uses it
[NETFILTER]: nf_conntrack: make l3proto->prepare() generic and renames it
[NETFILTER]: nf_conntrack: Increment error count on parsing IPv4 header
[NET]: Add ethtool support for NETIF_F_IPV6_CSUM devices.
[AF_IUCV]: Add lock when updating accept_q
...
Diffstat (limited to 'net')
58 files changed, 1993 insertions, 1226 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index abb9900edb3f..cda936b77d22 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -373,10 +373,11 @@ void vlan_setup(struct net_device *new_dev) new_dev->open = vlan_dev_open; new_dev->stop = vlan_dev_stop; new_dev->set_multicast_list = vlan_dev_set_multicast_list; + new_dev->change_rx_flags = vlan_change_rx_flags; new_dev->destructor = free_netdev; new_dev->do_ioctl = vlan_dev_ioctl; - memset(new_dev->broadcast, 0, sizeof(ETH_ALEN)); + memset(new_dev->broadcast, 0, ETH_ALEN); } static void vlan_transfer_operstate(const struct net_device *dev, struct net_device *vlandev) diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 62ce1c519aab..7df5b2935579 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -69,6 +69,7 @@ int vlan_dev_set_vlan_flag(const struct net_device *dev, u32 flag, short flag_val); void vlan_dev_get_realdev_name(const struct net_device *dev, char *result); void vlan_dev_get_vid(const struct net_device *dev, unsigned short *result); +void vlan_change_rx_flags(struct net_device *dev, int change); void vlan_dev_set_multicast_list(struct net_device *vlan_dev); int vlan_check_real_dev(struct net_device *real_dev, unsigned short vlan_id); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index d4a62d1b52b4..4d2aa4dd42ac 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -612,90 +612,6 @@ void vlan_dev_get_vid(const struct net_device *dev, unsigned short *result) *result = VLAN_DEV_INFO(dev)->vlan_id; } -static inline int vlan_dmi_equals(struct dev_mc_list *dmi1, - struct dev_mc_list *dmi2) -{ - return ((dmi1->dmi_addrlen == dmi2->dmi_addrlen) && - (memcmp(dmi1->dmi_addr, dmi2->dmi_addr, dmi1->dmi_addrlen) == 0)); -} - -/** dmi is a single entry into a dev_mc_list, a single node. mc_list is - * an entire list, and we'll iterate through it. - */ -static int vlan_should_add_mc(struct dev_mc_list *dmi, struct dev_mc_list *mc_list) -{ - struct dev_mc_list *idmi; - - for (idmi = mc_list; idmi != NULL; ) { - if (vlan_dmi_equals(dmi, idmi)) { - if (dmi->dmi_users > idmi->dmi_users) - return 1; - else - return 0; - } else { - idmi = idmi->next; - } - } - - return 1; -} - -static inline void vlan_destroy_mc_list(struct dev_mc_list *mc_list) -{ - struct dev_mc_list *dmi = mc_list; - struct dev_mc_list *next; - - while(dmi) { - next = dmi->next; - kfree(dmi); - dmi = next; - } -} - -static void vlan_copy_mc_list(struct dev_mc_list *mc_list, struct vlan_dev_info *vlan_info) -{ - struct dev_mc_list *dmi, *new_dmi; - - vlan_destroy_mc_list(vlan_info->old_mc_list); - vlan_info->old_mc_list = NULL; - - for (dmi = mc_list; dmi != NULL; dmi = dmi->next) { - new_dmi = kmalloc(sizeof(*new_dmi), GFP_ATOMIC); - if (new_dmi == NULL) { - printk(KERN_ERR "vlan: cannot allocate memory. " - "Multicast may not work properly from now.\n"); - return; - } - - /* Copy whole structure, then make new 'next' pointer */ - *new_dmi = *dmi; - new_dmi->next = vlan_info->old_mc_list; - vlan_info->old_mc_list = new_dmi; - } -} - -static void vlan_flush_mc_list(struct net_device *dev) -{ - struct dev_mc_list *dmi = dev->mc_list; - - while (dmi) { - printk(KERN_DEBUG "%s: del %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address from vlan interface\n", - dev->name, - dmi->dmi_addr[0], - dmi->dmi_addr[1], - dmi->dmi_addr[2], - dmi->dmi_addr[3], - dmi->dmi_addr[4], - dmi->dmi_addr[5]); - dev_mc_delete(dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); - dmi = dev->mc_list; - } - - /* dev->mc_list is NULL by the time we get here. */ - vlan_destroy_mc_list(VLAN_DEV_INFO(dev)->old_mc_list); - VLAN_DEV_INFO(dev)->old_mc_list = NULL; -} - int vlan_dev_open(struct net_device *dev) { struct vlan_dev_info *vlan = VLAN_DEV_INFO(dev); @@ -712,6 +628,11 @@ int vlan_dev_open(struct net_device *dev) } memcpy(vlan->real_dev_addr, real_dev->dev_addr, ETH_ALEN); + if (dev->flags & IFF_ALLMULTI) + dev_set_allmulti(real_dev, 1); + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(real_dev, 1); + return 0; } @@ -719,7 +640,11 @@ int vlan_dev_stop(struct net_device *dev) { struct net_device *real_dev = VLAN_DEV_INFO(dev)->real_dev; - vlan_flush_mc_list(dev); + dev_mc_unsync(real_dev, dev); + if (dev->flags & IFF_ALLMULTI) + dev_set_allmulti(real_dev, -1); + if (dev->flags & IFF_PROMISC) + dev_set_promiscuity(real_dev, -1); if (compare_ether_addr(dev->dev_addr, real_dev->dev_addr)) dev_unicast_delete(real_dev, dev->dev_addr, dev->addr_len); @@ -754,68 +679,18 @@ int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) return err; } -/** Taken from Gleb + Lennert's VLAN code, and modified... */ -void vlan_dev_set_multicast_list(struct net_device *vlan_dev) +void vlan_change_rx_flags(struct net_device *dev, int change) { - struct dev_mc_list *dmi; - struct net_device *real_dev; - int inc; - - if (vlan_dev && (vlan_dev->priv_flags & IFF_802_1Q_VLAN)) { - /* Then it's a real vlan device, as far as we can tell.. */ - real_dev = VLAN_DEV_INFO(vlan_dev)->real_dev; - - /* compare the current promiscuity to the last promisc we had.. */ - inc = vlan_dev->promiscuity - VLAN_DEV_INFO(vlan_dev)->old_promiscuity; - if (inc) { - printk(KERN_INFO "%s: dev_set_promiscuity(master, %d)\n", - vlan_dev->name, inc); - dev_set_promiscuity(real_dev, inc); /* found in dev.c */ - VLAN_DEV_INFO(vlan_dev)->old_promiscuity = vlan_dev->promiscuity; - } - - inc = vlan_dev->allmulti - VLAN_DEV_INFO(vlan_dev)->old_allmulti; - if (inc) { - printk(KERN_INFO "%s: dev_set_allmulti(master, %d)\n", - vlan_dev->name, inc); - dev_set_allmulti(real_dev, inc); /* dev.c */ - VLAN_DEV_INFO(vlan_dev)->old_allmulti = vlan_dev->allmulti; - } - - /* looking for addresses to add to master's list */ - for (dmi = vlan_dev->mc_list; dmi != NULL; dmi = dmi->next) { - if (vlan_should_add_mc(dmi, VLAN_DEV_INFO(vlan_dev)->old_mc_list)) { - dev_mc_add(real_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); - printk(KERN_DEBUG "%s: add %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address to master interface\n", - vlan_dev->name, - dmi->dmi_addr[0], - dmi->dmi_addr[1], - dmi->dmi_addr[2], - dmi->dmi_addr[3], - dmi->dmi_addr[4], - dmi->dmi_addr[5]); - } - } + struct net_device *real_dev = VLAN_DEV_INFO(dev)->real_dev; - /* looking for addresses to delete from master's list */ - for (dmi = VLAN_DEV_INFO(vlan_dev)->old_mc_list; dmi != NULL; dmi = dmi->next) { - if (vlan_should_add_mc(dmi, vlan_dev->mc_list)) { - /* if we think we should add it to the new list, then we should really - * delete it from the real list on the underlying device. - */ - dev_mc_delete(real_dev, dmi->dmi_addr, dmi->dmi_addrlen, 0); - printk(KERN_DEBUG "%s: del %.2x:%.2x:%.2x:%.2x:%.2x:%.2x mcast address from master interface\n", - vlan_dev->name, - dmi->dmi_addr[0], - dmi->dmi_addr[1], - dmi->dmi_addr[2], - dmi->dmi_addr[3], - dmi->dmi_addr[4], - dmi->dmi_addr[5]); - } - } + if (change & IFF_ALLMULTI) + dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1); + if (change & IFF_PROMISC) + dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1); +} - /* save multicast list */ - vlan_copy_mc_list(vlan_dev->mc_list, VLAN_DEV_INFO(vlan_dev)); - } +/** Taken from Gleb + Lennert's VLAN code, and modified... */ +void vlan_dev_set_multicast_list(struct net_device *vlan_dev) +{ + dev_mc_sync(VLAN_DEV_INFO(vlan_dev)->real_dev, vlan_dev); } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index ac9984f98e59..4169a2a89a39 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1525,14 +1525,14 @@ static int __init ebtables_init(void) if ((ret = nf_register_sockopt(&ebt_sockopts)) < 0) return ret; - printk(KERN_NOTICE "Ebtables v2.0 registered\n"); + printk(KERN_INFO "Ebtables v2.0 registered\n"); return 0; } static void __exit ebtables_fini(void) { nf_unregister_sockopt(&ebt_sockopts); - printk(KERN_NOTICE "Ebtables v2.0 unregistered\n"); + printk(KERN_INFO "Ebtables v2.0 unregistered\n"); } EXPORT_SYMBOL(ebt_register_table); diff --git a/net/core/dev.c b/net/core/dev.c index 96443055324e..13a0d9f6da54 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -98,6 +98,7 @@ #include <linux/seq_file.h> #include <linux/stat.h> #include <linux/if_bridge.h> +#include <linux/if_macvlan.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> @@ -1813,6 +1814,28 @@ static inline struct sk_buff *handle_bridge(struct sk_buff *skb, #define handle_bridge(skb, pt_prev, ret, orig_dev) (skb) #endif +#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE) +struct sk_buff *(*macvlan_handle_frame_hook)(struct sk_buff *skb) __read_mostly; +EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook); + +static inline struct sk_buff *handle_macvlan(struct sk_buff *skb, + struct packet_type **pt_prev, + int *ret, + struct net_device *orig_dev) +{ + if (skb->dev->macvlan_port == NULL) + return skb; + + if (*pt_prev) { + *ret = deliver_skb(skb, *pt_prev, orig_dev); + *pt_prev = NULL; + } + return macvlan_handle_frame_hook(skb); +} +#else +#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb) +#endif + #ifdef CONFIG_NET_CLS_ACT /* TODO: Maybe we should just force sch_ingress to be compiled in * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions @@ -1920,6 +1943,9 @@ ncls: skb = handle_bridge(skb, &pt_prev, &ret, orig_dev); if (!skb) goto out; + skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev); + if (!skb) + goto out; type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type)&15], list) { @@ -2521,6 +2547,8 @@ static void __dev_set_promiscuity(struct net_device *dev, int inc) { unsigned short old_flags = dev->flags; + ASSERT_RTNL(); + if ((dev->promiscuity += inc) == 0) dev->flags &= ~IFF_PROMISC; else @@ -2535,6 +2563,9 @@ static void __dev_set_promiscuity(struct net_device *dev, int inc) dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), audit_get_loginuid(current->audit_context)); + + if (dev->change_rx_flags) + dev->change_rx_flags(dev, IFF_PROMISC); } } @@ -2573,11 +2604,16 @@ void dev_set_allmulti(struct net_device *dev, int inc) { unsigned short old_flags = dev->flags; + ASSERT_RTNL(); + dev->flags |= IFF_ALLMULTI; if ((dev->allmulti += inc) == 0) dev->flags &= ~IFF_ALLMULTI; - if (dev->flags ^ old_flags) + if (dev->flags ^ old_flags) { + if (dev->change_rx_flags) + dev->change_rx_flags(dev, IFF_ALLMULTI); dev_set_rx_mode(dev); + } } /* @@ -2778,6 +2814,8 @@ int dev_change_flags(struct net_device *dev, unsigned flags) int ret, changes; int old_flags = dev->flags; + ASSERT_RTNL(); + /* * Set the flags on our device. */ @@ -2792,6 +2830,9 @@ int dev_change_flags(struct net_device *dev, unsigned flags) * Load in the correct multicast list now the flags have changed. */ + if (dev->change_rx_flags && (dev->flags ^ flags) & IFF_MULTICAST) + dev->change_rx_flags(dev, IFF_MULTICAST); + dev_set_rx_mode(dev); /* diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index aa38100601fb..235a2a8a0d05 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -102,6 +102,81 @@ int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) return err; } +/** + * dev_mc_sync - Synchronize device's multicast list to another device + * @to: destination device + * @from: source device + * + * Add newly added addresses to the destination device and release + * addresses that have no users left. The source device must be + * locked by netif_tx_lock_bh. + * + * This function is intended to be called from the dev->set_multicast_list + * function of layered software devices. + */ +int dev_mc_sync(struct net_device *to, struct net_device *from) +{ + struct dev_addr_list *da; + int err = 0; + + netif_tx_lock_bh(to); + for (da = from->mc_list; da != NULL; da = da->next) { + if (!da->da_synced) { + err = __dev_addr_add(&to->mc_list, &to->mc_count, + da->da_addr, da->da_addrlen, 0); + if (err < 0) + break; + da->da_synced = 1; + da->da_users++; + } else if (da->da_users == 1) { + __dev_addr_delete(&to->mc_list, &to->mc_count, + da->da_addr, da->da_addrlen, 0); + __dev_addr_delete(&from->mc_list, &from->mc_count, + da->da_addr, da->da_addrlen, 0); + } + } + if (!err) + __dev_set_rx_mode(to); + netif_tx_unlock_bh(to); + + return err; +} +EXPORT_SYMBOL(dev_mc_sync); + + +/** + * dev_mc_unsync - Remove synchronized addresses from the destination + * device + * @to: destination device + * @from: source device + * + * Remove all addresses that were added to the destination device by + * dev_mc_sync(). This function is intended to be called from the + * dev->stop function of layered software devices. + */ +void dev_mc_unsync(struct net_device *to, struct net_device *from) +{ + struct dev_addr_list *da; + + netif_tx_lock_bh(from); + netif_tx_lock_bh(to); + + for (da = from->mc_list; da != NULL; da = da->next) { + if (!da->da_synced) + continue; + __dev_addr_delete(&to->mc_list, &to->mc_count, + da->da_addr, da->da_addrlen, 0); + da->da_synced = 0; + __dev_addr_delete(&from->mc_list, &from->mc_count, + da->da_addr, da->da_addrlen, 0); + } + __dev_set_rx_mode(to); + + netif_tx_unlock_bh(to); + netif_tx_unlock_bh(from); +} +EXPORT_SYMBOL(dev_mc_unsync); + /* * Discard multicast list when a device is downed */ diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 8d5e5a09b576..0b531e98ec33 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -52,6 +52,17 @@ int ethtool_op_set_tx_hw_csum(struct net_device *dev, u32 data) return 0; } + +int ethtool_op_set_tx_ipv6_csum(struct net_device *dev, u32 data) +{ + if (data) + dev->features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM; + else + dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM); + + return 0; +} + u32 ethtool_op_get_sg(struct net_device *dev) { return (dev->features & NETIF_F_SG) != 0; @@ -980,5 +991,6 @@ EXPORT_SYMBOL(ethtool_op_set_sg); EXPORT_SYMBOL(ethtool_op_set_tso); EXPORT_SYMBOL(ethtool_op_set_tx_csum); EXPORT_SYMBOL(ethtool_op_set_tx_hw_csum); +EXPORT_SYMBOL(ethtool_op_set_tx_ipv6_csum); EXPORT_SYMBOL(ethtool_op_set_ufo); EXPORT_SYMBOL(ethtool_op_get_ufo); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index e00767e8ebd9..9ab9d534fbac 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -885,7 +885,7 @@ static int arp_process(struct sk_buff *skb) if (n == NULL && arp->ar_op == htons(ARPOP_REPLY) && inet_addr_type(sip) == RTN_UNICAST) - n = __neigh_lookup(&arp_tbl, &sip, dev, -1); + n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } if (n) { diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index a73cf93cee36..2586df09b9b6 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -14,7 +14,8 @@ #include <net/ip.h> /* Must be called with locally disabled BHs. */ -void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) +static void __inet_twsk_kill(struct inet_timewait_sock *tw, + struct inet_hashinfo *hashinfo) { struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; @@ -47,8 +48,6 @@ void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_hashinfo *hashi inet_twsk_put(tw); } -EXPORT_SYMBOL_GPL(__inet_twsk_kill); - /* * Enter the time wait state. This is called with locally disabled BH. * Essentially we whip up a timewait bucket, copy the relevant info into it diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e981232942a1..d1149aba9351 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1184,7 +1184,7 @@ static int __init arp_tables_init(void) if (ret < 0) goto err4; - printk("arp_tables: (C) 2002 David S. Miller\n"); + printk(KERN_INFO "arp_tables: (C) 2002 David S. Miller\n"); return 0; err4: diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 3c5629938487..64552afd01cb 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -78,21 +78,26 @@ nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) return skb; } -static int -ipv4_prepare(struct sk_buff **pskb, unsigned int hooknum, unsigned int *dataoff, - u_int8_t *protonum) +static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + unsigned int *dataoff, u_int8_t *protonum) { + struct iphdr _iph, *iph; + + iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph); + if (iph == NULL) + return -NF_DROP; + /* Never happen */ - if (ip_hdr(*pskb)->frag_off & htons(IP_OFFSET)) { + if (iph->frag_off & htons(IP_OFFSET)) { if (net_ratelimit()) { - printk(KERN_ERR "ipv4_prepare: Frag of proto %u (hook=%u)\n", - ip_hdr(*pskb)->protocol, hooknum); + printk(KERN_ERR "ipv4_get_l4proto: Frag of proto %u\n", + iph->protocol); } return -NF_DROP; } - *dataoff = skb_network_offset(*pskb) + ip_hdrlen(*pskb); - *protonum = ip_hdr(*pskb)->protocol; + *dataoff = nhoff + (iph->ihl << 2); + *protonum = iph->protocol; return NF_ACCEPT; } @@ -400,14 +405,14 @@ static struct nf_sockopt_ops so_getorigdst = { .get = &getorigdst, }; -struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = { +struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 __read_mostly = { .l3proto = PF_INET, .name = "ipv4", .pkt_to_tuple = ipv4_pkt_to_tuple, .invert_tuple = ipv4_invert_tuple, .print_tuple = ipv4_print_tuple, .print_conntrack = ipv4_print_conntrack, - .prepare = ipv4_prepare, + .get_l4proto = ipv4_get_l4proto, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nfattr = ipv4_tuple_to_nfattr, .nfattr_to_tuple = ipv4_nfattr_to_tuple, diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 0fe8fb0466ef..6593fd2c5b10 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -136,40 +136,22 @@ icmp_error_message(struct sk_buff *skb, unsigned int hooknum) { struct nf_conntrack_tuple innertuple, origtuple; - struct { - struct icmphdr icmp; - struct iphdr ip; - } _in, *inside; struct nf_conntrack_l4proto *innerproto; struct nf_conntrack_tuple_hash *h; - int dataoff; NF_CT_ASSERT(skb->nfct == NULL); - /* Not enough header? */ - inside = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_in), &_in); - if (inside == NULL) - return -NF_ACCEPT; - - /* Ignore ICMP's containing fragments (shouldn't happen) */ - if (inside->ip.frag_off & htons(IP_OFFSET)) { - pr_debug("icmp_error_message: fragment of proto %u\n", - inside->ip.protocol); + /* Are they talking about one of our connections? */ + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + ip_hdrlen(skb) + + sizeof(struct icmphdr), + PF_INET, &origtuple)) { + pr_debug("icmp_error_message: failed to get tuple\n"); return -NF_ACCEPT; } /* rcu_read_lock()ed by nf_hook_slow */ - innerproto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol); - - dataoff = ip_hdrlen(skb) + sizeof(inside->icmp); - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuple(skb, dataoff, dataoff + inside->ip.ihl*4, PF_INET, - inside->ip.protocol, &origtuple, - &nf_conntrack_l3proto_ipv4, innerproto)) { - pr_debug("icmp_error_message: ! get_tuple p=%u", - inside->ip.protocol); - return -NF_ACCEPT; - } + innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum); /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ @@ -183,25 +165,13 @@ icmp_error_message(struct sk_buff *skb, h = nf_conntrack_find_get(&innertuple); if (!h) { - /* Locally generated ICMPs will match inverted if they - haven't been SNAT'ed yet */ - /* FIXME: NAT code has to handle half-done double NAT --RR */ - if (hooknum == NF_IP_LOCAL_OUT) - h = nf_conntrack_find_get(&origtuple); - - if (!h) { - pr_debug("icmp_error_message: no match\n"); - return -NF_ACCEPT; - } - - /* Reverse direction from that found */ - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - *ctinfo += IP_CT_IS_REPLY; - } else { - if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) - *ctinfo += IP_CT_IS_REPLY; + pr_debug("icmp_error_message: no match\n"); + return -NF_ACCEPT; } + if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) + *ctinfo += IP_CT_IS_REPLY; + /* Update skb to refer to this connection */ skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; skb->nfctinfo = *ctinfo; @@ -342,7 +312,7 @@ static struct ctl_table icmp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ -struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = +struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_ICMP, @@ -368,4 +338,3 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = #endif #endif }; -EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_icmp); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 69f9f1ef3ef6..4e5884ac8f29 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1398,7 +1398,9 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag) * waiting for the first ACK and did not get it)... */ if ((tp->frto_counter == 1) && !(flag&FLAG_DATA_ACKED)) { - tp->retrans_out += tcp_skb_pcount(skb); + /* For some reason this R-bit might get cleared? */ + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) + tp->retrans_out += tcp_skb_pcount(skb); /* ...enter this if branch just for the first segment */ flag |= FLAG_DATA_ACKED; } else { diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 86624fabc4bf..f37d5928921a 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -111,6 +111,7 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb, p->snd_una = tp->snd_una; p->snd_cwnd = tp->snd_cwnd; p->snd_wnd = tp->snd_wnd; + p->ssthresh = tcp_current_ssthresh(sk); p->srtt = tp->srtt >> 3; tcp_probe.head = (tcp_probe.head + 1) % bufsize; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 24424c3b7dc0..06012920912a 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2475,6 +2475,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) write_unlock_bh(&idev->lock); __ipv6_ifa_notify(RTM_DELADDR, ifa); + atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifa); in6_ifa_put(ifa); write_lock_bh(&idev->lock); diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 4765a29f98a8..6a6714d154ed 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -604,7 +604,7 @@ static void icmpv6_notify(struct sk_buff *skb, int type, int code, __be32 info) read_lock(&raw_v6_lock); if ((sk = sk_head(&raw_v6_htable[hash])) != NULL) { - while((sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, + while ((sk = __raw_v6_lookup(sk, nexthdr, saddr, daddr, IP6CB(skb)->iif))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 254c769b750a..aeda617246b7 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1497,7 +1497,7 @@ static int __init ip6_tables_init(void) if (ret < 0) goto err5; - printk("ip6_tables: (C) 2000-2006 Netfilter Core Team\n"); + printk(KERN_INFO "ip6_tables: (C) 2000-2006 Netfilter Core Team\n"); return 0; err5: diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index 89e20ab494b8..36df2218b669 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -86,7 +86,7 @@ static int ipv6_print_conntrack(struct seq_file *s, * - Note also special handling of AUTH header. Thanks to IPsec wizards. */ -int nf_ct_ipv6_skip_exthdr(struct sk_buff *skb, int start, u8 *nexthdrp, +int nf_ct_ipv6_skip_exthdr(const struct sk_buff *skb, int start, u8 *nexthdrp, int len) { u8 nexthdr = *nexthdrp; @@ -117,22 +117,25 @@ int nf_ct_ipv6_skip_exthdr(struct sk_buff *skb, int start, u8 *nexthdrp, return start; } -static int -ipv6_prepare(struct sk_buff **pskb, unsigned int hooknum, unsigned int *dataoff, - u_int8_t *protonum) +static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + unsigned int *dataoff, u_int8_t *protonum) { - unsigned int extoff = (u8 *)(ipv6_hdr(*pskb) + 1) - (*pskb)->data; - unsigned char pnum = ipv6_hdr(*pskb)->nexthdr; - int protoff = nf_ct_ipv6_skip_exthdr(*pskb, extoff, &pnum, - (*pskb)->len - extoff); + unsigned int extoff = nhoff + sizeof(struct ipv6hdr); + unsigned char pnum; + int protoff; + + if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr), + &pnum, sizeof(pnum)) != 0) { + pr_debug("ip6_conntrack_core: can't get nexthdr\n"); + return -NF_ACCEPT; + } + protoff = nf_ct_ipv6_skip_exthdr(skb, extoff, &pnum, skb->len - extoff); /* - * (protoff == (*pskb)->len) mean that the packet doesn't have no data + * (protoff == skb->len) mean that the packet doesn't have no data * except of IPv6 & ext headers. but it's tracked anyway. - YK */ - if ((protoff < 0) || (protoff > (*pskb)->len)) { + if ((protoff < 0) || (protoff > skb->len)) { pr_debug("ip6_conntrack_core: can't find proto in pkt\n"); - NF_CT_STAT_INC_ATOMIC(error); - NF_CT_STAT_INC_ATOMIC(invalid); return -NF_ACCEPT; } @@ -370,14 +373,14 @@ static int ipv6_nfattr_to_tuple(struct nfattr *tb[], } #endif -struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = { +struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = { .l3proto = PF_INET6, .name = "ipv6", .pkt_to_tuple = ipv6_pkt_to_tuple, .invert_tuple = ipv6_invert_tuple, .print_tuple = ipv6_print_tuple, .print_conntrack = ipv6_print_conntrack, - .prepare = ipv6_prepare, + .get_l4proto = ipv6_get_l4proto, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) .tuple_to_nfattr = ipv6_tuple_to_nfattr, .nfattr_to_tuple = ipv6_nfattr_to_tuple, diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 9defc7e14554..ab154fb90018 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -136,49 +136,23 @@ icmpv6_error_message(struct sk_buff *skb, { struct nf_conntrack_tuple intuple, origtuple; struct nf_conntrack_tuple_hash *h; - struct icmp6hdr _hdr, *hp; - unsigned int inip6off; struct nf_conntrack_l4proto *inproto; - u_int8_t inprotonum; - unsigned int inprotoff; NF_CT_ASSERT(skb->nfct == NULL); - hp = skb_header_pointer(skb, icmp6off, sizeof(_hdr), &_hdr); - if (hp == NULL) { - pr_debug("icmpv6_error: Can't get ICMPv6 hdr.\n"); - return -NF_ACCEPT; - } - - inip6off = icmp6off + sizeof(_hdr); - if (skb_copy_bits(skb, inip6off+offsetof(struct ipv6hdr, nexthdr), - &inprotonum, sizeof(inprotonum)) != 0) { - pr_debug("icmpv6_error: Can't get nexthdr in inner IPv6 " - "header.\n"); - return -NF_ACCEPT; - } - inprotoff = nf_ct_ipv6_skip_exthdr(skb, - inip6off + sizeof(struct ipv6hdr), - &inprotonum, - skb->len - inip6off - - sizeof(struct ipv6hdr)); - - if ((inprotoff > skb->len) || (inprotonum == NEXTHDR_FRAGMENT)) { - pr_debug("icmpv6_error: Can't get protocol header in ICMPv6 " - "payload.\n"); - return -NF_ACCEPT; - } - - /* rcu_read_lock()ed by nf_hook_slow */ - inproto = __nf_ct_l4proto_find(PF_INET6, inprotonum); - /* Are they talking about one of our connections? */ - if (!nf_ct_get_tuple(skb, inip6off, inprotoff, PF_INET6, inprotonum, - &origtuple, &nf_conntrack_l3proto_ipv6, inproto)) { + if (!nf_ct_get_tuplepr(skb, + skb_network_offset(skb) + + sizeof(struct ipv6hdr) + + sizeof(struct icmp6hdr), + PF_INET6, &origtuple)) { pr_debug("icmpv6_error: Can't get tuple\n"); return -NF_ACCEPT; } + /* rcu_read_lock()ed by nf_hook_slow */ + inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum); + /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ if (!nf_ct_invert_tuple(&intuple, &origtuple, @@ -302,7 +276,7 @@ static struct ctl_table icmpv6_sysctl_table[] = { }; #endif /* CONFIG_SYSCTL */ -struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = +struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly = { .l3proto = PF_INET6, .l4proto = IPPROTO_ICMPV6, @@ -323,5 +297,3 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .ctl_table = icmpv6_sysctl_table, #endif }; - -EXPORT_SYMBOL(nf_conntrack_l4proto_icmpv6); diff --git a/net/iucv/Kconfig b/net/iucv/Kconfig index f8fcc3d10327..16ce9cd4f39e 100644 --- a/net/iucv/Kconfig +++ b/net/iucv/Kconfig @@ -1,13 +1,13 @@ config IUCV - tristate "IUCV support (VM only)" + tristate "IUCV support (S390 - z/VM only)" depends on S390 help - Select this option if you want to use inter-user communication under - VM or VIF sockets. If you run on z/VM, say "Y" to enable a fast + Select this option if you want to use inter-user communication + under VM or VIF. If you run on z/VM, say "Y" to enable a fast communication link between VM guests. config AFIUCV - tristate "AF_IUCV support (VM only)" + tristate "AF_IUCV support (S390 - z/VM only)" depends on IUCV help Select this option if you want to use inter-user communication under diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index d9e9ddb8eac5..53ae14c35f70 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -219,6 +219,7 @@ static struct sock *iucv_sock_alloc(struct socket *sock, int proto, gfp_t prio) sock_init_data(sock, sk); INIT_LIST_HEAD(&iucv_sk(sk)->accept_q); + spin_lock_init(&iucv_sk(sk)->accept_q_lock); skb_queue_head_init(&iucv_sk(sk)->send_skb_q); skb_queue_head_init(&iucv_sk(sk)->backlog_skb_q); iucv_sk(sk)->send_tag = 0; @@ -274,15 +275,25 @@ void iucv_sock_unlink(struct iucv_sock_list *l, struct sock *sk) void iucv_accept_enqueue(struct sock *parent, struct sock *sk) { + unsigned long flags; + struct iucv_sock *par = iucv_sk(parent); + sock_hold(sk); - list_add_tail(&iucv_sk(sk)->accept_q, &iucv_sk(parent)->accept_q); + spin_lock_irqsave(&par->accept_q_lock, flags); + list_add_tail(&iucv_sk(sk)->accept_q, &par->accept_q); + spin_unlock_irqrestore(&par->accept_q_lock, flags); iucv_sk(sk)->parent = parent; parent->sk_ack_backlog++; } void iucv_accept_unlink(struct sock *sk) { + unsigned long flags; + struct iucv_sock *par = iucv_sk(iucv_sk(sk)->parent); + + spin_lock_irqsave(&par->accept_q_lock, flags); list_del_init(&iucv_sk(sk)->accept_q); + spin_unlock_irqrestore(&par->accept_q_lock, flags); iucv_sk(sk)->parent->sk_ack_backlog--; iucv_sk(sk)->parent = NULL; sock_put(sk); @@ -298,8 +309,8 @@ struct sock *iucv_accept_dequeue(struct sock *parent, struct socket *newsock) lock_sock(sk); if (sk->sk_state == IUCV_CLOSED) { - release_sock(sk); iucv_accept_unlink(sk); + release_sock(sk); continue; } @@ -879,6 +890,7 @@ static int iucv_callback_connreq(struct iucv_path *path, /* Find out if this path belongs to af_iucv. */ read_lock(&iucv_sk_list.lock); iucv = NULL; + sk = NULL; sk_for_each(sk, node, &iucv_sk_list.head) if (sk->sk_state == IUCV_LISTEN && !memcmp(&iucv_sk(sk)->src_name, src_name, 8)) { diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index b7333061016d..ad5150b8dfa9 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -1494,7 +1494,10 @@ static void iucv_tasklet_fn(unsigned long ignored) struct iucv_irq_list *p, *n; /* Serialize tasklet, iucv_path_sever and iucv_path_connect. */ - spin_lock(&iucv_table_lock); + if (!spin_trylock(&iucv_table_lock)) { + tasklet_schedule(&iucv_tasklet); + return; + } iucv_active_cpu = smp_processor_id(); spin_lock_irq(&iucv_queue_lock); diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c index 9e3964638bad..a3e01d76d503 100644 --- a/net/mac80211/debugfs_netdev.c +++ b/net/mac80211/debugfs_netdev.c @@ -118,7 +118,7 @@ static ssize_t ieee80211_if_fmt_flags( sdata->u.sta.authenticated ? "AUTH\n" : "", sdata->u.sta.associated ? "ASSOC\n" : "", sdata->u.sta.probereq_poll ? "PROBEREQ POLL\n" : "", - sdata->u.sta.use_protection ? "CTS prot\n" : ""); + sdata->use_protection ? "CTS prot\n" : ""); } __IEEE80211_IF_FILE(flags); diff --git a/net/mac80211/hostapd_ioctl.h b/net/mac80211/hostapd_ioctl.h index 34fa128e9872..52da513f060a 100644 --- a/net/mac80211/hostapd_ioctl.h +++ b/net/mac80211/hostapd_ioctl.h @@ -26,24 +26,16 @@ * mess shall be deleted completely. */ enum { PRISM2_PARAM_IEEE_802_1X = 23, - PRISM2_PARAM_ANTSEL_TX = 24, - PRISM2_PARAM_ANTSEL_RX = 25, /* Instant802 additions */ PRISM2_PARAM_CTS_PROTECT_ERP_FRAMES = 1001, - PRISM2_PARAM_DROP_UNENCRYPTED = 1002, PRISM2_PARAM_PREAMBLE = 1003, PRISM2_PARAM_SHORT_SLOT_TIME = 1006, PRISM2_PARAM_NEXT_MODE = 1008, - PRISM2_PARAM_CLEAR_KEYS = 1009, PRISM2_PARAM_RADIO_ENABLED = 1010, PRISM2_PARAM_ANTENNA_MODE = 1013, PRISM2_PARAM_STAT_TIME = 1016, PRISM2_PARAM_STA_ANTENNA_SEL = 1017, - PRISM2_PARAM_FORCE_UNICAST_RATE = 1018, - PRISM2_PARAM_RATE_CTRL_NUM_UP = 1019, - PRISM2_PARAM_RATE_CTRL_NUM_DOWN = 1020, - PRISM2_PARAM_MAX_RATECTRL_RATE = 1021, PRISM2_PARAM_TX_POWER_REDUCTION = 1022, PRISM2_PARAM_KEY_TX_RX_THRESHOLD = 1024, PRISM2_PARAM_DEFAULT_WEP_ONLY = 1026, diff --git a/net/mac80211/ieee80211.c b/net/mac80211/ieee80211.c index 4e84f24fd439..2ddf4ef4065e 100644 --- a/net/mac80211/ieee80211.c +++ b/net/mac80211/ieee80211.c @@ -24,6 +24,7 @@ #include <linux/compiler.h> #include <linux/bitmap.h> #include <net/cfg80211.h> +#include <asm/unaligned.h> #include "ieee80211_common.h" #include "ieee80211_i.h" @@ -56,6 +57,17 @@ static const unsigned char eapol_header[] = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00, 0x88, 0x8e }; +/* + * For seeing transmitted packets on monitor interfaces + * we have a radiotap header too. + */ +struct ieee80211_tx_status_rtap_hdr { + struct ieee80211_radiotap_header hdr; + __le16 tx_flags; + u8 data_retries; +} __attribute__ ((packed)); + + static inline void ieee80211_include_sequence(struct ieee80211_sub_if_data *sdata, struct ieee80211_hdr *hdr) { @@ -430,7 +442,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_txrx_data *tx) if (!tx->u.tx.rate) return TXRX_DROP; if (tx->u.tx.mode->mode == MODE_IEEE80211G && - tx->local->cts_protect_erp_frames && tx->fragmented && + tx->sdata->use_protection && tx->fragmented && extra.nonerp) { tx->u.tx.last_frag_rate = tx->u.tx.rate; tx->u.tx.probe_last_frag = extra.probe ? 1 : 0; @@ -528,7 +540,7 @@ ieee80211_tx_h_fragment(struct ieee80211_txrx_data *tx) /* reserve enough extra head and tail room for possible * encryption */ frag = frags[i] = - dev_alloc_skb(tx->local->hw.extra_tx_headroom + + dev_alloc_skb(tx->local->tx_headroom + frag_threshold + IEEE80211_ENCRYPT_HEADROOM + IEEE80211_ENCRYPT_TAILROOM); @@ -537,8 +549,8 @@ ieee80211_tx_h_fragment(struct ieee80211_txrx_data *tx) /* Make sure that all fragments use the same priority so * that they end up using the same TX queue */ frag->priority = first->priority; - skb_reserve(frag, tx->local->hw.extra_tx_headroom + - IEEE80211_ENCRYPT_HEADROOM); + skb_reserve(frag, tx->local->tx_headroom + + IEEE80211_ENCRYPT_HEADROOM); fhdr = (struct ieee80211_hdr *) skb_put(frag, hdrlen); memcpy(fhdr, first->data, hdrlen); if (i == num_fragm - 2) @@ -856,8 +868,7 @@ ieee80211_tx_h_misc(struct ieee80211_txrx_data *tx) * for the frame. */ if (mode->mode == MODE_IEEE80211G && (tx->u.tx.rate->flags & IEEE80211_RATE_ERP) && - tx->u.tx.unicast && - tx->local->cts_protect_erp_frames && + tx->u.tx.unicast && tx->sdata->use_protection && !(control->flags & IEEE80211_TXCTL_USE_RTS_CTS)) control->flags |= IEEE80211_TXCTL_USE_CTS_PROTECT; @@ -1118,7 +1129,138 @@ ieee80211_tx_h_ps_buf(struct ieee80211_txrx_data *tx) } -static void inline +/* + * deal with packet injection down monitor interface + * with Radiotap Header -- only called for monitor mode interface + */ + +static ieee80211_txrx_result +__ieee80211_parse_tx_radiotap( + struct ieee80211_txrx_data *tx, + struct sk_buff *skb, struct ieee80211_tx_control *control) +{ + /* + * this is the moment to interpret and discard the radiotap header that + * must be at the start of the packet injected in Monitor mode + * + * Need to take some care with endian-ness since radiotap + * args are little-endian + */ + + struct ieee80211_radiotap_iterator iterator; + struct ieee80211_radiotap_header *rthdr = + (struct ieee80211_radiotap_header *) skb->data; + struct ieee80211_hw_mode *mode = tx->local->hw.conf.mode; + int ret = ieee80211_radiotap_iterator_init(&iterator, rthdr, skb->len); + + /* + * default control situation for all injected packets + * FIXME: this does not suit all usage cases, expand to allow control + */ + + control->retry_limit = 1; /* no retry */ + control->key_idx = -1; /* no encryption key */ + control->flags &= ~(IEEE80211_TXCTL_USE_RTS_CTS | + IEEE80211_TXCTL_USE_CTS_PROTECT); + control->flags |= IEEE80211_TXCTL_DO_NOT_ENCRYPT | + IEEE80211_TXCTL_NO_ACK; + control->antenna_sel_tx = 0; /* default to default antenna */ + + /* + * for every radiotap entry that is present + * (ieee80211_radiotap_iterator_next returns -ENOENT when no more + * entries present, or -EINVAL on error) + */ + + while (!ret) { + int i, target_rate; + + ret = ieee80211_radiotap_iterator_next(&iterator); + + if (ret) + continue; + + /* see if this argument is something we can use */ + switch (iterator.this_arg_index) { + /* + * You must take care when dereferencing iterator.this_arg + * for multibyte types... the pointer is not aligned. Use + * get_unaligned((type *)iterator.this_arg) to dereference + * iterator.this_arg for type "type" safely on all arches. + */ + case IEEE80211_RADIOTAP_RATE: + /* + * radiotap rate u8 is in 500kbps units eg, 0x02=1Mbps + * ieee80211 rate int is in 100kbps units eg, 0x0a=1Mbps + */ + target_rate = (*iterator.this_arg) * 5; + for (i = 0; i < mode->num_rates; i++) { + struct ieee80211_rate *r = &mode->rates[i]; + + if (r->rate > target_rate) + continue; + + control->rate = r; + + if (r->flags & IEEE80211_RATE_PREAMBLE2) + control->tx_rate = r->val2; + else + control->tx_rate = r->val; + + /* end on exact match */ + if (r->rate == target_rate) + i = mode->num_rates; + } + break; + + case IEEE80211_RADIOTAP_ANTENNA: + /* + * radiotap uses 0 for 1st ant, mac80211 is 1 for + * 1st ant + */ + control->antenna_sel_tx = (*iterator.this_arg) + 1; + break; + + case IEEE80211_RADIOTAP_DBM_TX_POWER: + control->power_level = *iterator.this_arg; + break; + + case IEEE80211_RADIOTAP_FLAGS: + if (*iterator.this_arg & IEEE80211_RADIOTAP_F_FCS) { + /* + * this indicates that the skb we have been + * handed has the 32-bit FCS CRC at the end... + * we should react to that by snipping it off + * because it will be recomputed and added + * on transmission + */ + if (skb->len < (iterator.max_length + FCS_LEN)) + return TXRX_DROP; + + skb_trim(skb, skb->len - FCS_LEN); + } + break; + + default: + break; + } + } + + if (ret != -ENOENT) /* ie, if we didn't simply run out of fields */ + return TXRX_DROP; + + /* + * remove the radiotap header + * iterator->max_length was sanity-checked against + * skb->len by iterator init + */ + skb_pull(skb, iterator.max_length); + + return TXRX_CONTINUE; +} + + +static ieee80211_txrx_result inline __ieee80211_tx_prepare(struct ieee80211_txrx_data *tx, struct sk_buff *skb, struct net_device *dev, @@ -1126,6 +1268,9 @@ __ieee80211_tx_prepare(struct ieee80211_txrx_data *tx, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; + struct ieee80211_sub_if_data *sdata; + ieee80211_txrx_result res = TXRX_CONTINUE; + int hdrlen; memset(tx, 0, sizeof(*tx)); @@ -1135,7 +1280,32 @@ __ieee80211_tx_prepare(struct ieee80211_txrx_data *tx, tx->sdata = IEEE80211_DEV_TO_SUB_IF(dev); tx->sta = sta_info_get(local, hdr->addr1); tx->fc = le16_to_cpu(hdr->frame_control); + + /* + * set defaults for things that can be set by + * injected radiotap headers + */ control->power_level = local->hw.conf.power_level; + control->antenna_sel_tx = local->hw.conf.antenna_sel_tx; + if (local->sta_antenna_sel != STA_ANTENNA_SEL_AUTO && tx->sta) + control->antenna_sel_tx = tx->sta->antenna_sel_tx; + + /* process and remove the injection radiotap header */ + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (unlikely(sdata->type == IEEE80211_IF_TYPE_MNTR)) { + if (__ieee80211_parse_tx_radiotap(tx, skb, control) == + TXRX_DROP) { + return TXRX_DROP; + } + /* + * we removed the radiotap header after this point, + * we filled control with what we could use + * set to the actual ieee header now + */ + hdr = (struct ieee80211_hdr *) skb->data; + res = TXRX_QUEUED; /* indication it was monitor packet */ + } + tx->u.tx.control = control; tx->u.tx.unicast = !is_multicast_ether_addr(hdr->addr1); if (is_multicast_ether_addr(hdr->addr1)) @@ -1152,9 +1322,6 @@ __ieee80211_tx_prepare(struct ieee80211_txrx_data *tx, control->flags |= IEEE80211_TXCTL_CLEAR_DST_MASK; tx->sta->clear_dst_mask = 0; } - control->antenna_sel_tx = local->hw.conf.antenna_sel_tx; - if (local->sta_antenna_sel != STA_ANTENNA_SEL_AUTO && tx->sta) - control->antenna_sel_tx = tx->sta->antenna_sel_tx; hdrlen = ieee80211_get_hdrlen(tx->fc); if (skb->len > hdrlen + sizeof(rfc1042_header) + 2) { u8 *pos = &skb->data[hdrlen + sizeof(rfc1042_header)]; @@ -1162,6 +1329,7 @@ __ieee80211_tx_prepare(struct ieee80211_txrx_data *tx, } control->flags |= IEEE80211_TXCTL_FIRST_FRAGMENT; + return res; } static int inline is_ieee80211_device(struct net_device *dev, @@ -1274,7 +1442,7 @@ static int ieee80211_tx(struct net_device *dev, struct sk_buff *skb, struct sta_info *sta; ieee80211_tx_handler *handler; struct ieee80211_txrx_data tx; - ieee80211_txrx_result res = TXRX_DROP; + ieee80211_txrx_result res = TXRX_DROP, res_prepare; int ret, i; WARN_ON(__ieee80211_queue_pending(local, control->queue)); @@ -1284,15 +1452,26 @@ static int ieee80211_tx(struct net_device *dev, struct sk_buff *skb, return 0; } - __ieee80211_tx_prepare(&tx, skb, dev, control); + res_prepare = __ieee80211_tx_prepare(&tx, skb, dev, control); + + if (res_prepare == TXRX_DROP) { + dev_kfree_skb(skb); + return 0; + } + sta = tx.sta; tx.u.tx.mgmt_interface = mgmt; tx.u.tx.mode = local->hw.conf.mode; - for (handler = local->tx_handlers; *handler != NULL; handler++) { - res = (*handler)(&tx); - if (res != TXRX_CONTINUE) - break; + if (res_prepare == TXRX_QUEUED) { /* if it was an injected packet */ + res = TXRX_CONTINUE; + } else { + for (handler = local->tx_handlers; *handler != NULL; + handler++) { + res = (*handler)(&tx); + if (res != TXRX_CONTINUE) + break; + } } skb = tx.skb; /* handlers are allowed to change skb */ @@ -1467,8 +1646,7 @@ static int ieee80211_master_start_xmit(struct sk_buff *skb, } osdata = IEEE80211_DEV_TO_SUB_IF(odev); - headroom = osdata->local->hw.extra_tx_headroom + - IEEE80211_ENCRYPT_HEADROOM; + headroom = osdata->local->tx_headroom + IEEE80211_ENCRYPT_HEADROOM; if (skb_headroom(skb) < headroom) { if (pskb_expand_head(skb, headroom, 0, GFP_ATOMIC)) { dev_kfree_skb(skb); @@ -1494,6 +1672,56 @@ static int ieee80211_master_start_xmit(struct sk_buff *skb, } +int ieee80211_monitor_start_xmit(struct sk_buff *skb, + struct net_device *dev) +{ + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_tx_packet_data *pkt_data; + struct ieee80211_radiotap_header *prthdr = + (struct ieee80211_radiotap_header *)skb->data; + u16 len; + + /* + * there must be a radiotap header at the + * start in this case + */ + if (unlikely(prthdr->it_version)) { + /* only version 0 is supported */ + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + skb->dev = local->mdev; + + pkt_data = (struct ieee80211_tx_packet_data *)skb->cb; + memset(pkt_data, 0, sizeof(*pkt_data)); + pkt_data->ifindex = dev->ifindex; + pkt_data->mgmt_iface = 0; + pkt_data->do_not_encrypt = 1; + + /* above needed because we set skb device to master */ + + /* + * fix up the pointers accounting for the radiotap + * header still being in there. We are being given + * a precooked IEEE80211 header so no need for + * normal processing + */ + len = le16_to_cpu(get_unaligned(&prthdr->it_len)); + skb_set_mac_header(skb, len); + skb_set_network_header(skb, len + sizeof(struct ieee80211_hdr)); + skb_set_transport_header(skb, len + sizeof(struct ieee80211_hdr)); + + /* + * pass the radiotap header up to + * the next stage intact + */ + dev_queue_xmit(skb); + + return NETDEV_TX_OK; +} + + /** * ieee80211_subif_start_xmit - netif start_xmit function for Ethernet-type * subinterfaces (wlan#, WDS, and VLAN interfaces) @@ -1509,8 +1737,8 @@ static int ieee80211_master_start_xmit(struct sk_buff *skb, * encapsulated packet will then be passed to master interface, wlan#.11, for * transmission (through low-level driver). */ -static int ieee80211_subif_start_xmit(struct sk_buff *skb, - struct net_device *dev) +int ieee80211_subif_start_xmit(struct sk_buff *skb, + struct net_device *dev) { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_tx_packet_data *pkt_data; @@ -1619,7 +1847,7 @@ static int ieee80211_subif_start_xmit(struct sk_buff *skb, * build in headroom in __dev_alloc_skb() (linux/skbuff.h) and * alloc_skb() (net/core/skbuff.c) */ - head_need = hdrlen + encaps_len + local->hw.extra_tx_headroom; + head_need = hdrlen + encaps_len + local->tx_headroom; head_need -= skb_headroom(skb); /* We are going to modify skb data, so make a copy of it if happens to @@ -1658,7 +1886,7 @@ static int ieee80211_subif_start_xmit(struct sk_buff *skb, pkt_data = (struct ieee80211_tx_packet_data *)skb->cb; memset(pkt_data, 0, sizeof(struct ieee80211_tx_packet_data)); - pkt_data->ifindex = sdata->dev->ifindex; + pkt_data->ifindex = dev->ifindex; pkt_data->mgmt_iface = (sdata->type == IEEE80211_IF_TYPE_MGMT); pkt_data->do_not_encrypt = no_encrypt; @@ -1706,9 +1934,9 @@ ieee80211_mgmt_start_xmit(struct sk_buff *skb, struct net_device *dev) return 0; } - if (skb_headroom(skb) < sdata->local->hw.extra_tx_headroom) { - if (pskb_expand_head(skb, - sdata->local->hw.extra_tx_headroom, 0, GFP_ATOMIC)) { + if (skb_headroom(skb) < sdata->local->tx_headroom) { + if (pskb_expand_head(skb, sdata->local->tx_headroom, + 0, GFP_ATOMIC)) { dev_kfree_skb(skb); return 0; } @@ -1847,12 +2075,12 @@ struct sk_buff * ieee80211_beacon_get(struct ieee80211_hw *hw, int if_id, bh_len = ap->beacon_head_len; bt_len = ap->beacon_tail_len; - skb = dev_alloc_skb(local->hw.extra_tx_headroom + + skb = dev_alloc_skb(local->tx_headroom + bh_len + bt_len + 256 /* maximum TIM len */); if (!skb) return NULL; - skb_reserve(skb, local->hw.extra_tx_headroom); + skb_reserve(skb, local->tx_headroom); memcpy(skb_put(skb, bh_len), b_head, bh_len); ieee80211_include_sequence(sdata, (struct ieee80211_hdr *)skb->data); @@ -2376,8 +2604,7 @@ static void ieee80211_start_hard_monitor(struct ieee80211_local *local) struct ieee80211_if_init_conf conf; if (local->open_count && local->open_count == local->monitors && - !(local->hw.flags & IEEE80211_HW_MONITOR_DURING_OPER) && - local->ops->add_interface) { + !(local->hw.flags & IEEE80211_HW_MONITOR_DURING_OPER)) { conf.if_id = -1; conf.type = IEEE80211_IF_TYPE_MNTR; conf.mac_addr = NULL; @@ -2420,21 +2647,14 @@ static int ieee80211_open(struct net_device *dev) } ieee80211_start_soft_monitor(local); - if (local->ops->add_interface) { - conf.if_id = dev->ifindex; - conf.type = sdata->type; - conf.mac_addr = dev->dev_addr; - res = local->ops->add_interface(local_to_hw(local), &conf); - if (res) { - if (sdata->type == IEEE80211_IF_TYPE_MNTR) - ieee80211_start_hard_monitor(local); - return res; - } - } else { - if (sdata->type != IEEE80211_IF_TYPE_STA) - return -EOPNOTSUPP; - if (local->open_count > 0) - return -ENOBUFS; + conf.if_id = dev->ifindex; + conf.type = sdata->type; + conf.mac_addr = dev->dev_addr; + res = local->ops->add_interface(local_to_hw(local), &conf); + if (res) { + if (sdata->type == IEEE80211_IF_TYPE_MNTR) + ieee80211_start_hard_monitor(local); + return res; } if (local->open_count == 0) { @@ -2941,34 +3161,6 @@ int ieee80211_radar_status(struct ieee80211_hw *hw, int channel, } EXPORT_SYMBOL(ieee80211_radar_status); -int ieee80211_set_aid_for_sta(struct ieee80211_hw *hw, u8 *peer_address, - u16 aid) -{ - struct sk_buff *skb; - struct ieee80211_msg_set_aid_for_sta *msg; - struct ieee80211_local *local = hw_to_local(hw); - - /* unlikely because if this event only happens for APs, - * which require an open ap device. */ - if (unlikely(!local->apdev)) - return 0; - - skb = dev_alloc_skb(sizeof(struct ieee80211_frame_info) + - sizeof(struct ieee80211_msg_set_aid_for_sta)); - - if (!skb) - return -ENOMEM; - skb_reserve(skb, sizeof(struct ieee80211_frame_info)); - - msg = (struct ieee80211_msg_set_aid_for_sta *) - skb_put(skb, sizeof(struct ieee80211_msg_set_aid_for_sta)); - memcpy(msg->sta_address, peer_address, ETH_ALEN); - msg->aid = aid; - - ieee80211_rx_mgmt(local, skb, NULL, ieee80211_msg_set_aid_for_sta); - return 0; -} -EXPORT_SYMBOL(ieee80211_set_aid_for_sta); static void ap_sta_ps_start(struct net_device *dev, struct sta_info *sta) { @@ -4284,6 +4476,9 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb, struct ieee80211_local *local = hw_to_local(hw); u16 frag, type; u32 msg_type; + struct ieee80211_tx_status_rtap_hdr *rthdr; + struct ieee80211_sub_if_data *sdata; + int monitors; if (!status) { printk(KERN_ERR @@ -4395,27 +4590,100 @@ void ieee80211_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb, local->dot11FailedCount++; } - if (!(status->control.flags & IEEE80211_TXCTL_REQ_TX_STATUS) - || unlikely(!local->apdev)) { + msg_type = (status->flags & IEEE80211_TX_STATUS_ACK) ? + ieee80211_msg_tx_callback_ack : ieee80211_msg_tx_callback_fail; + + /* this was a transmitted frame, but now we want to reuse it */ + skb_orphan(skb); + + if ((status->control.flags & IEEE80211_TXCTL_REQ_TX_STATUS) && + local->apdev) { + if (local->monitors) { + skb2 = skb_clone(skb, GFP_ATOMIC); + } else { + skb2 = skb; + skb = NULL; + } + + if (skb2) + /* Send frame to hostapd */ + ieee80211_rx_mgmt(local, skb2, NULL, msg_type); + + if (!skb) + return; + } + + if (!local->monitors) { dev_kfree_skb(skb); return; } - msg_type = (status->flags & IEEE80211_TX_STATUS_ACK) ? - ieee80211_msg_tx_callback_ack : ieee80211_msg_tx_callback_fail; + /* send frame to monitor interfaces now */ - /* skb was the original skb used for TX. Clone it and give the clone - * to netif_rx(). Free original skb. */ - skb2 = skb_copy(skb, GFP_ATOMIC); - if (!skb2) { + if (skb_headroom(skb) < sizeof(*rthdr)) { + printk(KERN_ERR "ieee80211_tx_status: headroom too small\n"); dev_kfree_skb(skb); return; } - dev_kfree_skb(skb); - skb = skb2; - /* Send frame to hostapd */ - ieee80211_rx_mgmt(local, skb, NULL, msg_type); + rthdr = (struct ieee80211_tx_status_rtap_hdr*) + skb_push(skb, sizeof(*rthdr)); + + memset(rthdr, 0, sizeof(*rthdr)); + rthdr->hdr.it_len = cpu_to_le16(sizeof(*rthdr)); + rthdr->hdr.it_present = + cpu_to_le32((1 << IEEE80211_RADIOTAP_TX_FLAGS) | + (1 << IEEE80211_RADIOTAP_DATA_RETRIES)); + + if (!(status->flags & IEEE80211_TX_STATUS_ACK) && + !is_multicast_ether_addr(hdr->addr1)) + rthdr->tx_flags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_FAIL); + + if ((status->control.flags & IEEE80211_TXCTL_USE_RTS_CTS) && + (status->control.flags & IEEE80211_TXCTL_USE_CTS_PROTECT)) + rthdr->tx_flags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_CTS); + else if (status->control.flags & IEEE80211_TXCTL_USE_RTS_CTS) + rthdr->tx_flags |= cpu_to_le16(IEEE80211_RADIOTAP_F_TX_RTS); + + rthdr->data_retries = status->retry_count; + + read_lock(&local->sub_if_lock); + monitors = local->monitors; + list_for_each_entry(sdata, &local->sub_if_list, list) { + /* + * Using the monitors counter is possibly racy, but + * if the value is wrong we simply either clone the skb + * once too much or forget sending it to one monitor iface + * The latter case isn't nice but fixing the race is much + * more complicated. + */ + if (!monitors || !skb) + goto out; + + if (sdata->type == IEEE80211_IF_TYPE_MNTR) { + if (!netif_running(sdata->dev)) + continue; + monitors--; + if (monitors) + skb2 = skb_clone(skb, GFP_KERNEL); + else + skb2 = NULL; + skb->dev = sdata->dev; + /* XXX: is this sufficient for BPF? */ + skb_set_mac_header(skb, 0); + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->pkt_type = PACKET_OTHERHOST; + skb->protocol = htons(ETH_P_802_2); + memset(skb->cb, 0, sizeof(skb->cb)); + netif_rx(skb); + skb = skb2; + break; + } + } + out: + read_unlock(&local->sub_if_lock); + if (skb) + dev_kfree_skb(skb); } EXPORT_SYMBOL(ieee80211_tx_status); @@ -4619,6 +4887,9 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, ((sizeof(struct ieee80211_local) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); + BUG_ON(!ops->tx); + BUG_ON(!ops->config); + BUG_ON(!ops->add_interface); local->ops = ops; /* for now, mdev needs sub_if_data :/ */ @@ -4647,8 +4918,6 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->short_retry_limit = 7; local->long_retry_limit = 4; local->hw.conf.radio_enabled = 1; - local->rate_ctrl_num_up = RATE_CONTROL_NUM_UP; - local->rate_ctrl_num_down = RATE_CONTROL_NUM_DOWN; local->enabled_modes = (unsigned int) -1; @@ -4712,6 +4981,14 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_workqueue; } + /* + * The hardware needs headroom for sending the frame, + * and we need some headroom for passing the frame to monitor + * interfaces, but never both at the same time. + */ + local->tx_headroom = max(local->hw.extra_tx_headroom, + sizeof(struct ieee80211_tx_status_rtap_hdr)); + debugfs_hw_add(local); local->hw.conf.beacon_int = 1000; diff --git a/net/mac80211/ieee80211_common.h b/net/mac80211/ieee80211_common.h index b9a73e7f5f75..77c6afb7f6a8 100644 --- a/net/mac80211/ieee80211_common.h +++ b/net/mac80211/ieee80211_common.h @@ -47,21 +47,16 @@ enum ieee80211_msg_type { ieee80211_msg_normal = 0, ieee80211_msg_tx_callback_ack = 1, ieee80211_msg_tx_callback_fail = 2, - ieee80211_msg_passive_scan = 3, + /* hole at 3, was ieee80211_msg_passive_scan but unused */ ieee80211_msg_wep_frame_unknown_key = 4, ieee80211_msg_michael_mic_failure = 5, /* hole at 6, was monitor but never sent to userspace */ ieee80211_msg_sta_not_assoc = 7, - ieee80211_msg_set_aid_for_sta = 8 /* used by Intersil MVC driver */, + /* 8 was ieee80211_msg_set_aid_for_sta */ ieee80211_msg_key_threshold_notification = 9, ieee80211_msg_radar = 11, }; -struct ieee80211_msg_set_aid_for_sta { - char sta_address[ETH_ALEN]; - u16 aid; -}; - struct ieee80211_msg_key_notification { int tx_rx_count; char ifname[IFNAMSIZ]; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index af4d14d0b969..055a2a912185 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -99,6 +99,12 @@ struct ieee80211_sta_bss { int probe_resp; unsigned long last_update; + /* during assocation, we save an ERP value from a probe response so + * that we can feed ERP info to the driver when handling the + * association completes. these fields probably won't be up-to-date + * otherwise, you probably don't want to use them. */ + int has_erp_value; + u8 erp_value; }; @@ -235,7 +241,6 @@ struct ieee80211_if_sta { unsigned int authenticated:1; unsigned int associated:1; unsigned int probereq_poll:1; - unsigned int use_protection:1; unsigned int create_ibss:1; unsigned int mixed_cell:1; unsigned int wmm_enabled:1; @@ -278,6 +283,7 @@ struct ieee80211_sub_if_data { int mc_count; unsigned int allmulti:1; unsigned int promisc:1; + unsigned int use_protection:1; /* CTS protect ERP frames */ struct net_device_stats stats; int drop_unencrypted; @@ -392,6 +398,7 @@ struct ieee80211_local { int monitors; struct iw_statistics wstats; u8 wstats_flags; + int tx_headroom; /* required headroom for hardware/radiotap */ enum { IEEE80211_DEV_UNINITIALIZED = 0, @@ -437,7 +444,6 @@ struct ieee80211_local { int *basic_rates[NUM_IEEE80211_MODES]; int rts_threshold; - int cts_protect_erp_frames; int fragmentation_threshold; int short_retry_limit; /* dot11ShortRetryLimit */ int long_retry_limit; /* dot11LongRetryLimit */ @@ -513,8 +519,6 @@ struct ieee80211_local { STA_ANTENNA_SEL_SW_CTRL_DEBUG = 2 } sta_antenna_sel; - int rate_ctrl_num_up, rate_ctrl_num_down; - #ifdef CONFIG_MAC80211_DEBUG_COUNTERS /* TX/RX handler statistics */ unsigned int tx_handlers_drop; @@ -719,6 +723,8 @@ void ieee80211_prepare_rates(struct ieee80211_local *local, struct ieee80211_hw_mode *mode); void ieee80211_tx_set_iswep(struct ieee80211_txrx_data *tx); int ieee80211_if_update_wds(struct net_device *dev, u8 *remote_addr); +int ieee80211_monitor_start_xmit(struct sk_buff *skb, struct net_device *dev); +int ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev); void ieee80211_if_setup(struct net_device *dev); void ieee80211_if_mgmt_setup(struct net_device *dev); int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local, diff --git a/net/mac80211/ieee80211_iface.c b/net/mac80211/ieee80211_iface.c index cf0f32e8c2a2..8532a5ccdd1e 100644 --- a/net/mac80211/ieee80211_iface.c +++ b/net/mac80211/ieee80211_iface.c @@ -157,6 +157,8 @@ void ieee80211_if_set_type(struct net_device *dev, int type) struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); int oldtype = sdata->type; + dev->hard_start_xmit = ieee80211_subif_start_xmit; + sdata->type = type; switch (type) { case IEEE80211_IF_TYPE_WDS: @@ -196,6 +198,7 @@ void ieee80211_if_set_type(struct net_device *dev, int type) } case IEEE80211_IF_TYPE_MNTR: dev->type = ARPHRD_IEEE80211_RADIOTAP; + dev->hard_start_xmit = ieee80211_monitor_start_xmit; break; default: printk(KERN_WARNING "%s: %s: Unknown interface type 0x%x", diff --git a/net/mac80211/ieee80211_ioctl.c b/net/mac80211/ieee80211_ioctl.c index 66e8a976b311..5918dd079e12 100644 --- a/net/mac80211/ieee80211_ioctl.c +++ b/net/mac80211/ieee80211_ioctl.c @@ -345,6 +345,8 @@ static int ieee80211_ioctl_giwrange(struct net_device *dev, { struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct iw_range *range = (struct iw_range *) extra; + struct ieee80211_hw_mode *mode = NULL; + int c = 0; data->length = sizeof(struct iw_range); memset(range, 0, sizeof(struct iw_range)); @@ -378,6 +380,29 @@ static int ieee80211_ioctl_giwrange(struct net_device *dev, range->enc_capa = IW_ENC_CAPA_WPA | IW_ENC_CAPA_WPA2 | IW_ENC_CAPA_CIPHER_TKIP | IW_ENC_CAPA_CIPHER_CCMP; + list_for_each_entry(mode, &local->modes_list, list) { + int i = 0; + + if (!(local->enabled_modes & (1 << mode->mode)) || + (local->hw_modes & local->enabled_modes & + (1 << MODE_IEEE80211G) && mode->mode == MODE_IEEE80211B)) + continue; + + while (i < mode->num_channels && c < IW_MAX_FREQUENCIES) { + struct ieee80211_channel *chan = &mode->channels[i]; + + if (chan->flag & IEEE80211_CHAN_W_SCAN) { + range->freq[c].i = chan->chan; + range->freq[c].m = chan->freq * 100000; + range->freq[c].e = 1; + c++; + } + i++; + } + } + range->num_channels = c; + range->num_frequency = c; + IW_EVENT_CAPA_SET_KERNEL(range->event_capa); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWTHRSPY); IW_EVENT_CAPA_SET(range->event_capa, SIOCGIWAP); @@ -838,6 +863,44 @@ static int ieee80211_ioctl_giwscan(struct net_device *dev, } +static int ieee80211_ioctl_siwrate(struct net_device *dev, + struct iw_request_info *info, + struct iw_param *rate, char *extra) +{ + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_hw_mode *mode; + int i; + u32 target_rate = rate->value / 100000; + struct ieee80211_sub_if_data *sdata; + + sdata = IEEE80211_DEV_TO_SUB_IF(dev); + if (!sdata->bss) + return -ENODEV; + mode = local->oper_hw_mode; + /* target_rate = -1, rate->fixed = 0 means auto only, so use all rates + * target_rate = X, rate->fixed = 1 means only rate X + * target_rate = X, rate->fixed = 0 means all rates <= X */ + sdata->bss->max_ratectrl_rateidx = -1; + sdata->bss->force_unicast_rateidx = -1; + if (rate->value < 0) + return 0; + for (i=0; i< mode->num_rates; i++) { + struct ieee80211_rate *rates = &mode->rates[i]; + int this_rate = rates->rate; + + if (mode->mode == MODE_ATHEROS_TURBO || + mode->mode == MODE_ATHEROS_TURBOG) + this_rate *= 2; + if (target_rate == this_rate) { + sdata->bss->max_ratectrl_rateidx = i; + if (rate->fixed) + sdata->bss->force_unicast_rateidx = i; + break; + } + } + return 0; +} + static int ieee80211_ioctl_giwrate(struct net_device *dev, struct iw_request_info *info, struct iw_param *rate, char *extra) @@ -993,118 +1056,6 @@ static int ieee80211_ioctl_giwretry(struct net_device *dev, return 0; } -static int ieee80211_ioctl_clear_keys(struct net_device *dev) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_key_conf key; - int i; - u8 addr[ETH_ALEN]; - struct ieee80211_key_conf *keyconf; - struct ieee80211_sub_if_data *sdata; - struct sta_info *sta; - - memset(addr, 0xff, ETH_ALEN); - read_lock(&local->sub_if_lock); - list_for_each_entry(sdata, &local->sub_if_list, list) { - for (i = 0; i < NUM_DEFAULT_KEYS; i++) { - keyconf = NULL; - if (sdata->keys[i] && - !sdata->keys[i]->force_sw_encrypt && - local->ops->set_key && - (keyconf = ieee80211_key_data2conf(local, - sdata->keys[i]))) - local->ops->set_key(local_to_hw(local), - DISABLE_KEY, addr, - keyconf, 0); - kfree(keyconf); - ieee80211_key_free(sdata->keys[i]); - sdata->keys[i] = NULL; - } - sdata->default_key = NULL; - } - read_unlock(&local->sub_if_lock); - - spin_lock_bh(&local->sta_lock); - list_for_each_entry(sta, &local->sta_list, list) { - keyconf = NULL; - if (sta->key && !sta->key->force_sw_encrypt && - local->ops->set_key && - (keyconf = ieee80211_key_data2conf(local, sta->key))) - local->ops->set_key(local_to_hw(local), DISABLE_KEY, - sta->addr, keyconf, sta->aid); - kfree(keyconf); - ieee80211_key_free(sta->key); - sta->key = NULL; - } - spin_unlock_bh(&local->sta_lock); - - memset(&key, 0, sizeof(key)); - if (local->ops->set_key && - local->ops->set_key(local_to_hw(local), REMOVE_ALL_KEYS, - NULL, &key, 0)) - printk(KERN_DEBUG "%s: failed to remove hwaccel keys\n", - dev->name); - - return 0; -} - - -static int -ieee80211_ioctl_force_unicast_rate(struct net_device *dev, - struct ieee80211_sub_if_data *sdata, - int rate) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_hw_mode *mode; - int i; - - if (sdata->type != IEEE80211_IF_TYPE_AP) - return -ENOENT; - - if (rate == 0) { - sdata->u.ap.force_unicast_rateidx = -1; - return 0; - } - - mode = local->oper_hw_mode; - for (i = 0; i < mode->num_rates; i++) { - if (mode->rates[i].rate == rate) { - sdata->u.ap.force_unicast_rateidx = i; - return 0; - } - } - return -EINVAL; -} - - -static int -ieee80211_ioctl_max_ratectrl_rate(struct net_device *dev, - struct ieee80211_sub_if_data *sdata, - int rate) -{ - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); - struct ieee80211_hw_mode *mode; - int i; - - if (sdata->type != IEEE80211_IF_TYPE_AP) - return -ENOENT; - - if (rate == 0) { - sdata->u.ap.max_ratectrl_rateidx = -1; - return 0; - } - - mode = local->oper_hw_mode; - for (i = 0; i < mode->num_rates; i++) { - if (mode->rates[i].rate == rate) { - sdata->u.ap.max_ratectrl_rateidx = i; - return 0; - } - } - return -EINVAL; -} - - static void ieee80211_key_enable_hwaccel(struct ieee80211_local *local, struct ieee80211_key *key) { @@ -1228,24 +1179,11 @@ static int ieee80211_ioctl_prism2_param(struct net_device *dev, sdata->ieee802_1x = value; break; - case PRISM2_PARAM_ANTSEL_TX: - local->hw.conf.antenna_sel_tx = value; - if (ieee80211_hw_config(local)) - ret = -EINVAL; - break; - - case PRISM2_PARAM_ANTSEL_RX: - local->hw.conf.antenna_sel_rx = value; - if (ieee80211_hw_config(local)) - ret = -EINVAL; - break; - case PRISM2_PARAM_CTS_PROTECT_ERP_FRAMES: - local->cts_protect_erp_frames = value; - break; - - case PRISM2_PARAM_DROP_UNENCRYPTED: - sdata->drop_unencrypted = value; + if (sdata->type != IEEE80211_IF_TYPE_AP) + ret = -ENOENT; + else + sdata->use_protection = value; break; case PRISM2_PARAM_PREAMBLE: @@ -1274,10 +1212,6 @@ static int ieee80211_ioctl_prism2_param(struct net_device *dev, local->next_mode = value; break; - case PRISM2_PARAM_CLEAR_KEYS: - ret = ieee80211_ioctl_clear_keys(dev); - break; - case PRISM2_PARAM_RADIO_ENABLED: ret = ieee80211_ioctl_set_radio_enabled(dev, value); break; @@ -1292,22 +1226,6 @@ static int ieee80211_ioctl_prism2_param(struct net_device *dev, local->sta_antenna_sel = value; break; - case PRISM2_PARAM_FORCE_UNICAST_RATE: - ret = ieee80211_ioctl_force_unicast_rate(dev, sdata, value); - break; - - case PRISM2_PARAM_MAX_RATECTRL_RATE: - ret = ieee80211_ioctl_max_ratectrl_rate(dev, sdata, value); - break; - - case PRISM2_PARAM_RATE_CTRL_NUM_UP: - local->rate_ctrl_num_up = value; - break; - - case PRISM2_PARAM_RATE_CTRL_NUM_DOWN: - local->rate_ctrl_num_down = value; - break; - case PRISM2_PARAM_TX_POWER_REDUCTION: if (value < 0) ret = -EINVAL; @@ -1387,20 +1305,8 @@ static int ieee80211_ioctl_get_prism2_param(struct net_device *dev, *param = sdata->ieee802_1x; break; - case PRISM2_PARAM_ANTSEL_TX: - *param = local->hw.conf.antenna_sel_tx; - break; - - case PRISM2_PARAM_ANTSEL_RX: - *param = local->hw.conf.antenna_sel_rx; - break; - case PRISM2_PARAM_CTS_PROTECT_ERP_FRAMES: - *param = local->cts_protect_erp_frames; - break; - - case PRISM2_PARAM_DROP_UNENCRYPTED: - *param = sdata->drop_unencrypted; + *param = sdata->use_protection; break; case PRISM2_PARAM_PREAMBLE: @@ -1426,14 +1332,6 @@ static int ieee80211_ioctl_get_prism2_param(struct net_device *dev, *param = local->sta_antenna_sel; break; - case PRISM2_PARAM_RATE_CTRL_NUM_UP: - *param = local->rate_ctrl_num_up; - break; - - case PRISM2_PARAM_RATE_CTRL_NUM_DOWN: - *param = local->rate_ctrl_num_down; - break; - case PRISM2_PARAM_TX_POWER_REDUCTION: *param = local->hw.conf.tx_power_reduction; break; @@ -1801,7 +1699,7 @@ static const iw_handler ieee80211_handler[] = (iw_handler) NULL, /* SIOCGIWNICKN */ (iw_handler) NULL, /* -- hole -- */ (iw_handler) NULL, /* -- hole -- */ - (iw_handler) NULL, /* SIOCSIWRATE */ + (iw_handler) ieee80211_ioctl_siwrate, /* SIOCSIWRATE */ (iw_handler) ieee80211_ioctl_giwrate, /* SIOCGIWRATE */ (iw_handler) ieee80211_ioctl_siwrts, /* SIOCSIWRTS */ (iw_handler) ieee80211_ioctl_giwrts, /* SIOCGIWRTS */ diff --git a/net/mac80211/ieee80211_sta.c b/net/mac80211/ieee80211_sta.c index 91b545c144c1..ba2bf8f0a347 100644 --- a/net/mac80211/ieee80211_sta.c +++ b/net/mac80211/ieee80211_sta.c @@ -76,33 +76,36 @@ static int ieee80211_sta_config_auth(struct net_device *dev, /* Parsed Information Elements */ struct ieee802_11_elems { + /* pointers to IEs */ u8 *ssid; - u8 ssid_len; u8 *supp_rates; - u8 supp_rates_len; u8 *fh_params; - u8 fh_params_len; u8 *ds_params; - u8 ds_params_len; u8 *cf_params; - u8 cf_params_len; u8 *tim; - u8 tim_len; u8 *ibss_params; - u8 ibss_params_len; u8 *challenge; - u8 challenge_len; u8 *wpa; - u8 wpa_len; u8 *rsn; - u8 rsn_len; u8 *erp_info; - u8 erp_info_len; u8 *ext_supp_rates; - u8 ext_supp_rates_len; u8 *wmm_info; - u8 wmm_info_len; u8 *wmm_param; + + /* length of them, respectively */ + u8 ssid_len; + u8 supp_rates_len; + u8 fh_params_len; + u8 ds_params_len; + u8 cf_params_len; + u8 tim_len; + u8 ibss_params_len; + u8 challenge_len; + u8 wpa_len; + u8 rsn_len; + u8 erp_info_len; + u8 ext_supp_rates_len; + u8 wmm_info_len; u8 wmm_param_len; }; @@ -311,6 +314,25 @@ static void ieee80211_sta_wmm_params(struct net_device *dev, } +static void ieee80211_handle_erp_ie(struct net_device *dev, u8 erp_value) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_if_sta *ifsta = &sdata->u.sta; + int use_protection = (erp_value & WLAN_ERP_USE_PROTECTION) != 0; + + if (use_protection != sdata->use_protection) { + if (net_ratelimit()) { + printk(KERN_DEBUG "%s: CTS protection %s (BSSID=" + MAC_FMT ")\n", + dev->name, + use_protection ? "enabled" : "disabled", + MAC_ARG(ifsta->bssid)); + } + sdata->use_protection = use_protection; + } +} + + static void ieee80211_sta_send_associnfo(struct net_device *dev, struct ieee80211_if_sta *ifsta) { @@ -366,6 +388,7 @@ static void ieee80211_set_associated(struct net_device *dev, struct ieee80211_if_sta *ifsta, int assoc) { union iwreq_data wrqu; + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (ifsta->associated == assoc) return; @@ -374,9 +397,18 @@ static void ieee80211_set_associated(struct net_device *dev, if (assoc) { struct ieee80211_sub_if_data *sdata; + struct ieee80211_sta_bss *bss; sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->type != IEEE80211_IF_TYPE_STA) return; + + bss = ieee80211_rx_bss_get(dev, ifsta->bssid); + if (bss) { + if (bss->has_erp_value) + ieee80211_handle_erp_ie(dev, bss->erp_value); + ieee80211_rx_bss_put(dev, bss); + } + netif_carrier_on(dev); ifsta->prev_bssid_set = 1; memcpy(ifsta->prev_bssid, sdata->u.sta.bssid, ETH_ALEN); @@ -384,6 +416,7 @@ static void ieee80211_set_associated(struct net_device *dev, ieee80211_sta_send_associnfo(dev, ifsta); } else { netif_carrier_off(dev); + sdata->use_protection = 0; memset(wrqu.ap_addr.sa_data, 0, ETH_ALEN); } wrqu.ap_addr.sa_family = ARPHRD_ETHER; @@ -1174,6 +1207,18 @@ static void ieee80211_rx_mgmt_assoc_resp(struct net_device *dev, return; } + /* it probably doesn't, but if the frame includes an ERP value then + * update our stored copy */ + if (elems.erp_info && elems.erp_info_len >= 1) { + struct ieee80211_sta_bss *bss + = ieee80211_rx_bss_get(dev, ifsta->bssid); + if (bss) { + bss->erp_value = elems.erp_info[0]; + bss->has_erp_value = 1; + ieee80211_rx_bss_put(dev, bss); + } + } + printk(KERN_DEBUG "%s: associated\n", dev->name); ifsta->aid = aid; ifsta->ap_capab = capab_info; @@ -1496,6 +1541,12 @@ static void ieee80211_rx_bss_info(struct net_device *dev, return; } + /* save the ERP value so that it is available at association time */ + if (elems.erp_info && elems.erp_info_len >= 1) { + bss->erp_value = elems.erp_info[0]; + bss->has_erp_value = 1; + } + bss->beacon_int = le16_to_cpu(mgmt->u.beacon.beacon_int); bss->capability = le16_to_cpu(mgmt->u.beacon.capab_info); if (elems.ssid && elems.ssid_len <= IEEE80211_MAX_SSID_LEN) { @@ -1611,10 +1662,8 @@ static void ieee80211_rx_mgmt_beacon(struct net_device *dev, size_t len, struct ieee80211_rx_status *rx_status) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sub_if_data *sdata; struct ieee80211_if_sta *ifsta; - int use_protection; size_t baselen; struct ieee802_11_elems elems; @@ -1638,23 +1687,8 @@ static void ieee80211_rx_mgmt_beacon(struct net_device *dev, &elems) == ParseFailed) return; - use_protection = 0; - if (elems.erp_info && elems.erp_info_len >= 1) { - use_protection = - (elems.erp_info[0] & ERP_INFO_USE_PROTECTION) != 0; - } - - if (use_protection != !!ifsta->use_protection) { - if (net_ratelimit()) { - printk(KERN_DEBUG "%s: CTS protection %s (BSSID=" - MAC_FMT ")\n", - dev->name, - use_protection ? "enabled" : "disabled", - MAC_ARG(ifsta->bssid)); - } - ifsta->use_protection = use_protection ? 1 : 0; - local->cts_protect_erp_frames = use_protection; - } + if (elems.erp_info && elems.erp_info_len >= 1) + ieee80211_handle_erp_ie(dev, elems.erp_info[0]); if (elems.wmm_param && ifsta->wmm_enabled) { ieee80211_sta_wmm_params(dev, ifsta, elems.wmm_param, diff --git a/net/mac80211/rc80211_simple.c b/net/mac80211/rc80211_simple.c index 5ae7fc454665..f6780d63b342 100644 --- a/net/mac80211/rc80211_simple.c +++ b/net/mac80211/rc80211_simple.c @@ -187,9 +187,13 @@ static void rate_control_simple_tx_status(void *priv, struct net_device *dev, } #endif - if (per_failed > local->rate_ctrl_num_down) { + /* + * XXX: Make these configurable once we have an + * interface to the rate control algorithms + */ + if (per_failed > RATE_CONTROL_NUM_DOWN) { rate_control_rate_dec(local, sta); - } else if (per_failed < local->rate_ctrl_num_up) { + } else if (per_failed < RATE_CONTROL_NUM_UP) { rate_control_rate_inc(local, sta); } srctrl->tx_avg_rate_sum += status->control.rate->rate; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index df5e8dab871d..3ac39f1ec775 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -102,6 +102,16 @@ config NF_CT_PROTO_SCTP If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NF_CT_PROTO_UDPLITE + tristate 'UDP-Lite protocol connection tracking support (EXPERIMENTAL)' + depends on EXPERIMENTAL && NF_CONNTRACK + help + With this option enabled, the layer 3 independent connection + tracking code will be able to do state tracking on UDP-Lite + connections. + + To compile it as a module, choose M here. If unsure, say N. + config NF_CONNTRACK_AMANDA tristate "Amanda backup protocol support" depends on NF_CONNTRACK @@ -423,6 +433,13 @@ config NETFILTER_XT_MATCH_CONNBYTES If you want to compile it as a module, say M here and read <file:Documentation/kbuild/modules.txt>. If unsure, say `N'. +config NETFILTER_XT_MATCH_CONNLIMIT + tristate '"connlimit" match support"' + depends on NETFILTER_XTABLES + ---help--- + This match allows you to match against the number of parallel + connections to a server per client IP address (or address block). + config NETFILTER_XT_MATCH_CONNMARK tristate '"connmark" connection mark match support' depends on NETFILTER_XTABLES diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 58b4245a1723..0c054bf27973 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -16,6 +16,7 @@ obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o # SCTP protocol connection tracking obj-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o obj-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o +obj-$(CONFIG_NF_CT_PROTO_UDPLITE) += nf_conntrack_proto_udplite.o # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o @@ -52,6 +53,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o # matches obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o +obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNMARK) += xt_connmark.o obj-$(CONFIG_NETFILTER_XT_MATCH_CONNTRACK) += xt_conntrack.o obj-$(CONFIG_NETFILTER_XT_MATCH_DCCP) += xt_dccp.o diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 3d1411012a2c..8cce814f6bee 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -113,6 +113,36 @@ nf_ct_get_tuple(const struct sk_buff *skb, } EXPORT_SYMBOL_GPL(nf_ct_get_tuple); +int nf_ct_get_tuplepr(const struct sk_buff *skb, + unsigned int nhoff, + u_int16_t l3num, + struct nf_conntrack_tuple *tuple) +{ + struct nf_conntrack_l3proto *l3proto; + struct nf_conntrack_l4proto *l4proto; + unsigned int protoff; + u_int8_t protonum; + int ret; + + rcu_read_lock(); + + l3proto = __nf_ct_l3proto_find(l3num); + ret = l3proto->get_l4proto(skb, nhoff, &protoff, &protonum); + if (ret != NF_ACCEPT) { + rcu_read_unlock(); + return 0; + } + + l4proto = __nf_ct_l4proto_find(l3num, protonum); + + ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, tuple, + l3proto, l4proto); + + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr); + int nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, const struct nf_conntrack_tuple *orig, @@ -622,9 +652,12 @@ nf_conntrack_in(int pf, unsigned int hooknum, struct sk_buff **pskb) /* rcu_read_lock()ed by nf_hook_slow */ l3proto = __nf_ct_l3proto_find((u_int16_t)pf); - - if ((ret = l3proto->prepare(pskb, hooknum, &dataoff, &protonum)) <= 0) { + ret = l3proto->get_l4proto(*pskb, skb_network_offset(*pskb), + &dataoff, &protonum); + if (ret <= 0) { pr_debug("not prepared to track yet or error occured\n"); + NF_CT_STAT_INC_ATOMIC(error); + NF_CT_STAT_INC_ATOMIC(invalid); return -ret; } diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c index b1bfa207a850..991c52c9a28b 100644 --- a/net/netfilter/nf_conntrack_l3proto_generic.c +++ b/net/netfilter/nf_conntrack_l3proto_generic.c @@ -61,22 +61,21 @@ static int generic_print_conntrack(struct seq_file *s, return 0; } -static int -generic_prepare(struct sk_buff **pskb, unsigned int hooknum, - unsigned int *dataoff, u_int8_t *protonum) +static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, + unsigned int *dataoff, u_int8_t *protonum) { /* Never track !!! */ return -NF_ACCEPT; } -struct nf_conntrack_l3proto nf_conntrack_l3proto_generic = { +struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = { .l3proto = PF_UNSPEC, .name = "unknown", .pkt_to_tuple = generic_pkt_to_tuple, .invert_tuple = generic_invert_tuple, .print_tuple = generic_print_tuple, .print_conntrack = generic_print_conntrack, - .prepare = generic_prepare, + .get_l4proto = generic_get_l4proto, }; EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic); diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 6faf1bed7224..d8b501878d9f 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -98,7 +98,7 @@ static struct ctl_table generic_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ -struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = +struct nf_conntrack_l4proto nf_conntrack_l4proto_generic __read_mostly = { .l3proto = PF_UNSPEC, .l4proto = 0, diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 771c4c29936e..bdbead8a7a83 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -261,7 +261,7 @@ static void gre_destroy(struct nf_conn *ct) } /* protocol helper struct */ -static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { +static struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 __read_mostly = { .l3proto = AF_INET, .l4proto = IPPROTO_GRE, .name = "gre", diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index debfe61378a1..04192acc7c40 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -601,7 +601,7 @@ static struct ctl_table sctp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif -struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { +static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_SCTP, .name = "sctp", @@ -622,7 +622,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = { #endif }; -struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = { +static struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 __read_mostly = { .l3proto = PF_INET6, .l4proto = IPPROTO_SCTP, .name = "sctp", diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 1c8206e6560a..87ad3ccf8aff 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1372,7 +1372,7 @@ static struct ctl_table tcp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ -struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = +struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_TCP, @@ -1401,7 +1401,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 = }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_tcp4); -struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 = +struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 __read_mostly = { .l3proto = PF_INET6, .l4proto = IPPROTO_TCP, diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index 3620ecc095fd..13d94a025723 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -191,7 +191,7 @@ static struct ctl_table udp_compat_sysctl_table[] = { #endif /* CONFIG_NF_CONNTRACK_PROC_COMPAT */ #endif /* CONFIG_SYSCTL */ -struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = +struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 __read_mostly = { .l3proto = PF_INET, .l4proto = IPPROTO_UDP, @@ -218,7 +218,7 @@ struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 = }; EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udp4); -struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 = +struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 __read_mostly = { .l3proto = PF_INET6, .l4proto = IPPROTO_UDP, diff --git a/net/netfilter/nf_conntrack_proto_udplite.c b/net/netfilter/nf_conntrack_proto_udplite.c new file mode 100644 index 000000000000..93e747b5396e --- /dev/null +++ b/net/netfilter/nf_conntrack_proto_udplite.c @@ -0,0 +1,266 @@ +/* (C) 1999-2001 Paul `Rusty' Russell + * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org> + * (C) 2007 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/timer.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/udp.h> +#include <linux/seq_file.h> +#include <linux/skbuff.h> +#include <linux/ipv6.h> +#include <net/ip6_checksum.h> +#include <net/checksum.h> + +#include <linux/netfilter.h> +#include <linux/netfilter_ipv4.h> +#include <linux/netfilter_ipv6.h> +#include <net/netfilter/nf_conntrack_l4proto.h> +#include <net/netfilter/nf_conntrack_ecache.h> + +static unsigned int nf_ct_udplite_timeout __read_mostly = 30*HZ; +static unsigned int nf_ct_udplite_timeout_stream __read_mostly = 180*HZ; + +static int udplite_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct nf_conntrack_tuple *tuple) +{ + struct udphdr _hdr, *hp; + + hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hp == NULL) + return 0; + + tuple->src.u.udp.port = hp->source; + tuple->dst.u.udp.port = hp->dest; + return 1; +} + +static int udplite_invert_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) +{ + tuple->src.u.udp.port = orig->dst.u.udp.port; + tuple->dst.u.udp.port = orig->src.u.udp.port; + return 1; +} + +/* Print out the per-protocol part of the tuple. */ +static int udplite_print_tuple(struct seq_file *s, + const struct nf_conntrack_tuple *tuple) +{ + return seq_printf(s, "sport=%hu dport=%hu ", + ntohs(tuple->src.u.udp.port), + ntohs(tuple->dst.u.udp.port)); +} + +/* Print out the private part of the conntrack. */ +static int udplite_print_conntrack(struct seq_file *s, + const struct nf_conn *conntrack) +{ + return 0; +} + +/* Returns verdict for packet, and may modify conntracktype */ +static int udplite_packet(struct nf_conn *conntrack, + const struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + int pf, + unsigned int hooknum) +{ + /* If we've seen traffic both ways, this is some kind of UDP + stream. Extend timeout. */ + if (test_bit(IPS_SEEN_REPLY_BIT, &conntrack->status)) { + nf_ct_refresh_acct(conntrack, ctinfo, skb, + nf_ct_udplite_timeout_stream); + /* Also, more likely to be important, and not a probe */ + if (!test_and_set_bit(IPS_ASSURED_BIT, &conntrack->status)) + nf_conntrack_event_cache(IPCT_STATUS, skb); + } else + nf_ct_refresh_acct(conntrack, ctinfo, skb, + nf_ct_udplite_timeout); + + return NF_ACCEPT; +} + +/* Called when a new connection for this protocol found. */ +static int udplite_new(struct nf_conn *conntrack, const struct sk_buff *skb, + unsigned int dataoff) +{ + return 1; +} + +static int udplite_error(struct sk_buff *skb, unsigned int dataoff, + enum ip_conntrack_info *ctinfo, + int pf, + unsigned int hooknum) +{ + unsigned int udplen = skb->len - dataoff; + struct udphdr _hdr, *hdr; + unsigned int cscov; + + /* Header is too small? */ + hdr = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr); + if (hdr == NULL) { + if (LOG_INVALID(IPPROTO_UDPLITE)) + nf_log_packet(pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: short packet "); + return -NF_ACCEPT; + } + + cscov = ntohs(hdr->len); + if (cscov == 0) + cscov = udplen; + else if (cscov < sizeof(*hdr) || cscov > udplen) { + if (LOG_INVALID(IPPROTO_UDPLITE)) + nf_log_packet(pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: invalid checksum coverage "); + return -NF_ACCEPT; + } + + /* UDPLITE mandates checksums */ + if (!hdr->check) { + if (LOG_INVALID(IPPROTO_UDPLITE)) + nf_log_packet(pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: checksum missing "); + return -NF_ACCEPT; + } + + /* Checksum invalid? Ignore. */ + if (nf_conntrack_checksum && !skb_csum_unnecessary(skb) && + ((pf == PF_INET && hooknum == NF_IP_PRE_ROUTING) || + (pf == PF_INET6 && hooknum == NF_IP6_PRE_ROUTING))) { + if (pf == PF_INET) { + struct iphdr *iph = ip_hdr(skb); + + skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, + udplen, IPPROTO_UDPLITE, 0); + } else { + struct ipv6hdr *ipv6h = ipv6_hdr(skb); + __wsum hsum = skb_checksum(skb, 0, dataoff, 0); + + skb->csum = ~csum_unfold( + csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + udplen, IPPROTO_UDPLITE, + csum_sub(0, hsum))); + } + + skb->ip_summed = CHECKSUM_NONE; + if (__skb_checksum_complete_head(skb, dataoff + cscov)) { + if (LOG_INVALID(IPPROTO_UDPLITE)) + nf_log_packet(pf, 0, skb, NULL, NULL, NULL, + "nf_ct_udplite: bad UDPLite " + "checksum "); + return -NF_ACCEPT; + } + skb->ip_summed = CHECKSUM_UNNECESSARY; + } + + return NF_ACCEPT; +} + +#ifdef CONFIG_SYSCTL +static unsigned int udplite_sysctl_table_users; +static struct ctl_table_header *udplite_sysctl_header; +static struct ctl_table udplite_sysctl_table[] = { + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nf_conntrack_udplite_timeout", + .data = &nf_ct_udplite_timeout, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nf_conntrack_udplite_timeout_stream", + .data = &nf_ct_udplite_timeout_stream, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + }, + { + .ctl_name = 0 + } +}; +#endif /* CONFIG_SYSCTL */ + +static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 __read_mostly = +{ + .l3proto = PF_INET, + .l4proto = IPPROTO_UDPLITE, + .name = "udplite", + .pkt_to_tuple = udplite_pkt_to_tuple, + .invert_tuple = udplite_invert_tuple, + .print_tuple = udplite_print_tuple, + .print_conntrack = udplite_print_conntrack, + .packet = udplite_packet, + .new = udplite_new, + .error = udplite_error, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple, +#endif +#ifdef CONFIG_SYSCTL + .ctl_table_users = &udplite_sysctl_table_users, + .ctl_table_header = &udplite_sysctl_header, + .ctl_table = udplite_sysctl_table, +#endif +}; + +static struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 __read_mostly = +{ + .l3proto = PF_INET6, + .l4proto = IPPROTO_UDPLITE, + .name = "udplite", + .pkt_to_tuple = udplite_pkt_to_tuple, + .invert_tuple = udplite_invert_tuple, + .print_tuple = udplite_print_tuple, + .print_conntrack = udplite_print_conntrack, + .packet = udplite_packet, + .new = udplite_new, + .error = udplite_error, +#if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) + .tuple_to_nfattr = nf_ct_port_tuple_to_nfattr, + .nfattr_to_tuple = nf_ct_port_nfattr_to_tuple, +#endif +#ifdef CONFIG_SYSCTL + .ctl_table_users = &udplite_sysctl_table_users, + .ctl_table_header = &udplite_sysctl_header, + .ctl_table = udplite_sysctl_table, +#endif +}; + +static int __init nf_conntrack_proto_udplite_init(void) +{ + int err; + + err = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udplite4); + if (err < 0) + goto err1; + err = nf_conntrack_l4proto_register(&nf_conntrack_l4proto_udplite6); + if (err < 0) + goto err2; + return 0; +err2: + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udplite4); +err1: + return err; +} + +static void __exit nf_conntrack_proto_udplite_exit(void) +{ + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udplite6); + nf_conntrack_l4proto_unregister(&nf_conntrack_l4proto_udplite4); +} + +module_init(nf_conntrack_proto_udplite_init); +module_exit(nf_conntrack_proto_udplite_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c new file mode 100644 index 000000000000..3335dd5be962 --- /dev/null +++ b/net/netfilter/xt_connlimit.c @@ -0,0 +1,313 @@ +/* + * netfilter module to limit the number of parallel tcp + * connections per IP address. + * (c) 2000 Gerd Knorr <kraxel@bytesex.org> + * Nov 2002: Martin Bene <martin.bene@icomedias.com>: + * only ignore TIME_WAIT or gone connections + * Copyright © Jan Engelhardt <jengelh@gmx.de>, 2007 + * + * based on ... + * + * Kernel module to match connection tracking information. + * GPL (C) 1999 Rusty Russell (rusty@rustcorp.com.au). + */ +#include <linux/in.h> +#include <linux/in6.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/jhash.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/random.h> +#include <linux/skbuff.h> +#include <linux/spinlock.h> +#include <linux/netfilter/nf_conntrack_tcp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_connlimit.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_core.h> +#include <net/netfilter/nf_conntrack_tuple.h> + +/* we will save the tuples of all connections we care about */ +struct xt_connlimit_conn { + struct list_head list; + struct nf_conntrack_tuple tuple; +}; + +struct xt_connlimit_data { + struct list_head iphash[256]; + spinlock_t lock; +}; + +static u_int32_t connlimit_rnd; +static bool connlimit_rnd_inited; + +static inline unsigned int connlimit_iphash(u_int32_t addr) +{ + if (unlikely(!connlimit_rnd_inited)) { + get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd)); + connlimit_rnd_inited = true; + } + return jhash_1word(addr, connlimit_rnd) & 0xFF; +} + +static inline unsigned int +connlimit_iphash6(const union nf_conntrack_address *addr, + const union nf_conntrack_address *mask) +{ + union nf_conntrack_address res; + unsigned int i; + + if (unlikely(!connlimit_rnd_inited)) { + get_random_bytes(&connlimit_rnd, sizeof(connlimit_rnd)); + connlimit_rnd_inited = true; + } + + for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) + res.ip6[i] = addr->ip6[i] & mask->ip6[i]; + + return jhash2(res.ip6, ARRAY_SIZE(res.ip6), connlimit_rnd) & 0xFF; +} + +static inline bool already_closed(const struct nf_conn *conn) +{ + u_int16_t proto = conn->tuplehash[0].tuple.dst.protonum; + + if (proto == IPPROTO_TCP) + return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT; + else + return 0; +} + +static inline unsigned int +same_source_net(const union nf_conntrack_address *addr, + const union nf_conntrack_address *mask, + const union nf_conntrack_address *u3, unsigned int family) +{ + if (family == AF_INET) { + return (addr->ip & mask->ip) == (u3->ip & mask->ip); + } else { + union nf_conntrack_address lh, rh; + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(addr->ip6); ++i) { + lh.ip6[i] = addr->ip6[i] & mask->ip6[i]; + rh.ip6[i] = u3->ip6[i] & mask->ip6[i]; + } + + return memcmp(&lh.ip6, &rh.ip6, sizeof(lh.ip6)) == 0; + } +} + +static int count_them(struct xt_connlimit_data *data, + const struct nf_conntrack_tuple *tuple, + const union nf_conntrack_address *addr, + const union nf_conntrack_address *mask, + const struct xt_match *match) +{ + struct nf_conntrack_tuple_hash *found; + struct xt_connlimit_conn *conn; + struct xt_connlimit_conn *tmp; + struct nf_conn *found_ct; + struct list_head *hash; + bool addit = true; + int matches = 0; + + + if (match->family == AF_INET6) + hash = &data->iphash[connlimit_iphash6(addr, mask)]; + else + hash = &data->iphash[connlimit_iphash(addr->ip & mask->ip)]; + + read_lock_bh(&nf_conntrack_lock); + + /* check the saved connections */ + list_for_each_entry_safe(conn, tmp, hash, list) { + found = __nf_conntrack_find(&conn->tuple, NULL); + found_ct = NULL; + + if (found != NULL) + found_ct = nf_ct_tuplehash_to_ctrack(found); + + if (found_ct != NULL && + nf_ct_tuple_equal(&conn->tuple, tuple) && + !already_closed(found_ct)) + /* + * Just to be sure we have it only once in the list. + * We should not see tuples twice unless someone hooks + * this into a table without "-p tcp --syn". + */ + addit = false; + + if (found == NULL) { + /* this one is gone */ + list_del(&conn->list); + kfree(conn); + continue; + } + + if (already_closed(found_ct)) { + /* + * we do not care about connections which are + * closed already -> ditch it + */ + list_del(&conn->list); + kfree(conn); + continue; + } + + if (same_source_net(addr, mask, &conn->tuple.src.u3, + match->family)) + /* same source network -> be counted! */ + ++matches; + } + + read_unlock_bh(&nf_conntrack_lock); + + if (addit) { + /* save the new connection in our list */ + conn = kzalloc(sizeof(*conn), GFP_ATOMIC); + if (conn == NULL) + return -ENOMEM; + conn->tuple = *tuple; + list_add(&conn->list, hash); + ++matches; + } + + return matches; +} + +static bool connlimit_match(const struct sk_buff *skb, + const struct net_device *in, + const struct net_device *out, + const struct xt_match *match, + const void *matchinfo, int offset, + unsigned int protoff, bool *hotdrop) +{ + const struct xt_connlimit_info *info = matchinfo; + union nf_conntrack_address addr, mask; + struct nf_conntrack_tuple tuple; + const struct nf_conntrack_tuple *tuple_ptr = &tuple; + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct; + int connections; + + ct = nf_ct_get(skb, &ctinfo); + if (ct != NULL) + tuple_ptr = &ct->tuplehash[0].tuple; + else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + match->family, &tuple)) + goto hotdrop; + + if (match->family == AF_INET6) { + const struct ipv6hdr *iph = ipv6_hdr(skb); + memcpy(&addr.ip6, &iph->saddr, sizeof(iph->saddr)); + memcpy(&mask.ip6, info->v6_mask, sizeof(info->v6_mask)); + } else { + const struct iphdr *iph = ip_hdr(skb); + addr.ip = iph->saddr; + mask.ip = info->v4_mask; + } + + spin_lock_bh(&info->data->lock); + connections = count_them(info->data, tuple_ptr, &addr, &mask, match); + spin_unlock_bh(&info->data->lock); + + if (connections < 0) { + /* kmalloc failed, drop it entirely */ + *hotdrop = true; + return false; + } + + return (connections > info->limit) ^ info->inverse; + + hotdrop: + *hotdrop = true; + return false; +} + +static bool connlimit_check(const char *tablename, const void *ip, + const struct xt_match *match, void *matchinfo, + unsigned int hook_mask) +{ + struct xt_connlimit_info *info = matchinfo; + unsigned int i; + + if (nf_ct_l3proto_try_module_get(match->family) < 0) { + printk(KERN_WARNING "cannot load conntrack support for " + "address family %u\n", match->family); + return false; + } + + /* init private data */ + info->data = kmalloc(sizeof(struct xt_connlimit_data), GFP_KERNEL); + if (info->data == NULL) { + nf_ct_l3proto_module_put(match->family); + return false; + } + + spin_lock_init(&info->data->lock); + for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) + INIT_LIST_HEAD(&info->data->iphash[i]); + + return true; +} + +static void connlimit_destroy(const struct xt_match *match, void *matchinfo) +{ + struct xt_connlimit_info *info = matchinfo; + struct xt_connlimit_conn *conn; + struct xt_connlimit_conn *tmp; + struct list_head *hash = info->data->iphash; + unsigned int i; + + nf_ct_l3proto_module_put(match->family); + + for (i = 0; i < ARRAY_SIZE(info->data->iphash); ++i) { + list_for_each_entry_safe(conn, tmp, &hash[i], list) { + list_del(&conn->list); + kfree(conn); + } + } + + kfree(info->data); +} + +static struct xt_match connlimit_reg[] __read_mostly = { + { + .name = "connlimit", + .family = AF_INET, + .checkentry = connlimit_check, + .match = connlimit_match, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_destroy, + .me = THIS_MODULE, + }, + { + .name = "connlimit", + .family = AF_INET6, + .checkentry = connlimit_check, + .match = connlimit_match, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_destroy, + .me = THIS_MODULE, + }, +}; + +static int __init xt_connlimit_init(void) +{ + return xt_register_matches(connlimit_reg, ARRAY_SIZE(connlimit_reg)); +} + +static void __exit xt_connlimit_exit(void) +{ + xt_unregister_matches(connlimit_reg, ARRAY_SIZE(connlimit_reg)); +} + +module_init(xt_connlimit_init); +module_exit(xt_connlimit_exit); +MODULE_AUTHOR("Jan Engelhardt <jengelh@gmx.de>"); +MODULE_DESCRIPTION("netfilter xt_connlimit match module"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("ipt_connlimit"); +MODULE_ALIAS("ip6t_connlimit"); diff --git a/net/rfkill/rfkill-input.c b/net/rfkill/rfkill-input.c index e5c840c30284..230e35c59786 100644 --- a/net/rfkill/rfkill-input.c +++ b/net/rfkill/rfkill-input.c @@ -55,7 +55,7 @@ static void rfkill_task_handler(struct work_struct *work) static void rfkill_schedule_toggle(struct rfkill_task *task) { - unsigned int flags; + unsigned long flags; spin_lock_irqsave(&task->lock, flags); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index b4662888bdbd..d3f7c3f9407a 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -472,12 +472,12 @@ config NET_ACT_SIMP config NET_CLS_POLICE bool "Traffic Policing (obsolete)" - depends on NET_CLS_ACT!=y + select NET_CLS_ACT + select NET_ACT_POLICE ---help--- Say Y here if you want to do traffic policing, i.e. strict - bandwidth limiting. This option is obsoleted by the traffic - policer implemented as action, it stays here for compatibility - reasons. + bandwidth limiting. This option is obsolete and just selects + the option replacing it. It will be removed in the future. config NET_CLS_IND bool "Incoming device classification" diff --git a/net/sched/Makefile b/net/sched/Makefile index 020767a204d4..b67c36f65cf2 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -8,7 +8,6 @@ obj-$(CONFIG_NET_SCHED) += sch_api.o sch_blackhole.o obj-$(CONFIG_NET_CLS) += cls_api.o obj-$(CONFIG_NET_CLS_ACT) += act_api.o obj-$(CONFIG_NET_ACT_POLICE) += act_police.o -obj-$(CONFIG_NET_CLS_POLICE) += act_police.o obj-$(CONFIG_NET_ACT_GACT) += act_gact.o obj-$(CONFIG_NET_ACT_MIRRED) += act_mirred.o obj-$(CONFIG_NET_ACT_IPT) += act_ipt.o diff --git a/net/sched/act_police.c b/net/sched/act_police.c index d20403890877..bf90e60f8411 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -50,7 +50,6 @@ struct tc_police_compat /* Each policer is serialized by its individual spinlock */ -#ifdef CONFIG_NET_CLS_ACT static int tcf_act_police_walker(struct sk_buff *skb, struct netlink_callback *cb, int type, struct tc_action *a) { @@ -96,9 +95,8 @@ rtattr_failure: nlmsg_trim(skb, r); goto done; } -#endif -void tcf_police_destroy(struct tcf_police *p) +static void tcf_police_destroy(struct tcf_police *p) { unsigned int h = tcf_hash(p->tcf_index, POL_TAB_MASK); struct tcf_common **p1p; @@ -121,7 +119,6 @@ void tcf_police_destroy(struct tcf_police *p) BUG_TRAP(0); } -#ifdef CONFIG_NET_CLS_ACT static int tcf_act_police_locate(struct rtattr *rta, struct rtattr *est, struct tc_action *a, int ovr, int bind) { @@ -247,10 +244,19 @@ failure: static int tcf_act_police_cleanup(struct tc_action *a, int bind) { struct tcf_police *p = a->priv; + int ret = 0; - if (p != NULL) - return tcf_police_release(p, bind); - return 0; + if (p != NULL) { + if (bind) + p->tcf_bindcnt--; + + p->tcf_refcnt--; + if (p->tcf_refcnt <= 0 && !p->tcf_bindcnt) { + tcf_police_destroy(p); + ret = 1; + } + } + return ret; } static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, @@ -372,229 +378,3 @@ police_cleanup_module(void) module_init(police_init_module); module_exit(police_cleanup_module); - -#else /* CONFIG_NET_CLS_ACT */ - -static struct tcf_common *tcf_police_lookup(u32 index) -{ - struct tcf_hashinfo *hinfo = &police_hash_info; - struct tcf_common *p; - - read_lock(hinfo->lock); - for (p = hinfo->htab[tcf_hash(index, hinfo->hmask)]; p; - p = p->tcfc_next) { - if (p->tcfc_index == index) - break; - } - read_unlock(hinfo->lock); - - return p; -} - -static u32 tcf_police_new_index(void) -{ - u32 *idx_gen = &police_idx_gen; - u32 val = *idx_gen; - - do { - if (++val == 0) - val = 1; - } while (tcf_police_lookup(val)); - - return (*idx_gen = val); -} - -struct tcf_police *tcf_police_locate(struct rtattr *rta, struct rtattr *est) -{ - unsigned int h; - struct tcf_police *police; - struct rtattr *tb[TCA_POLICE_MAX]; - struct tc_police *parm; - int size; - - if (rtattr_parse_nested(tb, TCA_POLICE_MAX, rta) < 0) - return NULL; - - if (tb[TCA_POLICE_TBF-1] == NULL) - return NULL; - size = RTA_PAYLOAD(tb[TCA_POLICE_TBF-1]); - if (size != sizeof(*parm) && size != sizeof(struct tc_police_compat)) - return NULL; - - parm = RTA_DATA(tb[TCA_POLICE_TBF-1]); - - if (parm->index) { - struct tcf_common *pc; - - pc = tcf_police_lookup(parm->index); - if (pc) { - police = to_police(pc); - police->tcf_refcnt++; - return police; - } - } - police = kzalloc(sizeof(*police), GFP_KERNEL); - if (unlikely(!police)) - return NULL; - - police->tcf_refcnt = 1; - spin_lock_init(&police->tcf_lock); - if (parm->rate.rate) { - police->tcfp_R_tab = - qdisc_get_rtab(&parm->rate, tb[TCA_POLICE_RATE-1]); - if (police->tcfp_R_tab == NULL) - goto failure; - if (parm->peakrate.rate) { - police->tcfp_P_tab = - qdisc_get_rtab(&parm->peakrate, - tb[TCA_POLICE_PEAKRATE-1]); - if (police->tcfp_P_tab == NULL) - goto failure; - } - } - if (tb[TCA_POLICE_RESULT-1]) { - if (RTA_PAYLOAD(tb[TCA_POLICE_RESULT-1]) != sizeof(u32)) - goto failure; - police->tcfp_result = *(u32*)RTA_DATA(tb[TCA_POLICE_RESULT-1]); - } - if (tb[TCA_POLICE_AVRATE-1]) { - if (RTA_PAYLOAD(tb[TCA_POLICE_AVRATE-1]) != sizeof(u32)) - goto failure; - police->tcfp_ewma_rate = - *(u32*)RTA_DATA(tb[TCA_POLICE_AVRATE-1]); - } - police->tcfp_toks = police->tcfp_burst = parm->burst; - police->tcfp_mtu = parm->mtu; - if (police->tcfp_mtu == 0) { - police->tcfp_mtu = ~0; - if (police->tcfp_R_tab) - police->tcfp_mtu = 255<<police->tcfp_R_tab->rate.cell_log; - } - if (police->tcfp_P_tab) - police->tcfp_ptoks = L2T_P(police, police->tcfp_mtu); - police->tcfp_t_c = psched_get_time(); - police->tcf_index = parm->index ? parm->index : - tcf_police_new_index(); - police->tcf_action = parm->action; - if (est) - gen_new_estimator(&police->tcf_bstats, &police->tcf_rate_est, - &police->tcf_lock, est); - h = tcf_hash(police->tcf_index, POL_TAB_MASK); - write_lock_bh(&police_lock); - police->tcf_next = tcf_police_ht[h]; - tcf_police_ht[h] = &police->common; - write_unlock_bh(&police_lock); - return police; - -failure: - if (police->tcfp_R_tab) - qdisc_put_rtab(police->tcfp_R_tab); - kfree(police); - return NULL; -} - -int tcf_police(struct sk_buff *skb, struct tcf_police *police) -{ - psched_time_t now; - long toks; - long ptoks = 0; - - spin_lock(&police->tcf_lock); - - police->tcf_bstats.bytes += skb->len; - police->tcf_bstats.packets++; - - if (police->tcfp_ewma_rate && - police->tcf_rate_est.bps >= police->tcfp_ewma_rate) { - police->tcf_qstats.overlimits++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; - } - if (skb->len <= police->tcfp_mtu) { - if (police->tcfp_R_tab == NULL) { - spin_unlock(&police->tcf_lock); - return police->tcfp_result; - } - - now = psched_get_time(); - toks = psched_tdiff_bounded(now, police->tcfp_t_c, - police->tcfp_burst); - if (police->tcfp_P_tab) { - ptoks = toks + police->tcfp_ptoks; - if (ptoks > (long)L2T_P(police, police->tcfp_mtu)) - ptoks = (long)L2T_P(police, police->tcfp_mtu); - ptoks -= L2T_P(police, skb->len); - } - toks += police->tcfp_toks; - if (toks > (long)police->tcfp_burst) - toks = police->tcfp_burst; - toks -= L2T(police, skb->len); - if ((toks|ptoks) >= 0) { - police->tcfp_t_c = now; - police->tcfp_toks = toks; - police->tcfp_ptoks = ptoks; - spin_unlock(&police->tcf_lock); - return police->tcfp_result; - } - } - - police->tcf_qstats.overlimits++; - spin_unlock(&police->tcf_lock); - return police->tcf_action; -} -EXPORT_SYMBOL(tcf_police); - -int tcf_police_dump(struct sk_buff *skb, struct tcf_police *police) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_police opt; - - opt.index = police->tcf_index; - opt.action = police->tcf_action; - opt.mtu = police->tcfp_mtu; - opt.burst = police->tcfp_burst; - if (police->tcfp_R_tab) - opt.rate = police->tcfp_R_tab->rate; - else - memset(&opt.rate, 0, sizeof(opt.rate)); - if (police->tcfp_P_tab) - opt.peakrate = police->tcfp_P_tab->rate; - else - memset(&opt.peakrate, 0, sizeof(opt.peakrate)); - RTA_PUT(skb, TCA_POLICE_TBF, sizeof(opt), &opt); - if (police->tcfp_result) - RTA_PUT(skb, TCA_POLICE_RESULT, sizeof(int), - &police->tcfp_result); - if (police->tcfp_ewma_rate) - RTA_PUT(skb, TCA_POLICE_AVRATE, 4, &police->tcfp_ewma_rate); - return skb->len; - -rtattr_failure: - nlmsg_trim(skb, b); - return -1; -} - -int tcf_police_dump_stats(struct sk_buff *skb, struct tcf_police *police) -{ - struct gnet_dump d; - - if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, - TCA_XSTATS, &police->tcf_lock, - &d) < 0) - goto errout; - - if (gnet_stats_copy_basic(&d, &police->tcf_bstats) < 0 || - gnet_stats_copy_rate_est(&d, &police->tcf_rate_est) < 0 || - gnet_stats_copy_queue(&d, &police->tcf_qstats) < 0) - goto errout; - - if (gnet_stats_finish_copy(&d) < 0) - goto errout; - - return 0; - -errout: - return -1; -} - -#endif /* CONFIG_NET_CLS_ACT */ diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 36b72aab1bde..5f0fbca7393f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -458,11 +458,6 @@ tcf_exts_destroy(struct tcf_proto *tp, struct tcf_exts *exts) tcf_action_destroy(exts->action, TCA_ACT_UNBIND); exts->action = NULL; } -#elif defined CONFIG_NET_CLS_POLICE - if (exts->police) { - tcf_police_release(exts->police, TCA_ACT_UNBIND); - exts->police = NULL; - } #endif } @@ -496,17 +491,6 @@ tcf_exts_validate(struct tcf_proto *tp, struct rtattr **tb, exts->action = act; } } -#elif defined CONFIG_NET_CLS_POLICE - if (map->police && tb[map->police-1]) { - struct tcf_police *p; - - p = tcf_police_locate(tb[map->police-1], rate_tlv); - if (p == NULL) - return -EINVAL; - - exts->police = p; - } else if (map->action && tb[map->action-1]) - return -EOPNOTSUPP; #else if ((map->action && tb[map->action-1]) || (map->police && tb[map->police-1])) @@ -529,15 +513,6 @@ tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst, if (act) tcf_action_destroy(act, TCA_ACT_UNBIND); } -#elif defined CONFIG_NET_CLS_POLICE - if (src->police) { - struct tcf_police *p; - tcf_tree_lock(tp); - p = xchg(&dst->police, src->police); - tcf_tree_unlock(tp); - if (p) - tcf_police_release(p, TCA_ACT_UNBIND); - } #endif } @@ -566,17 +541,6 @@ tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts, p_rta->rta_len = skb_tail_pointer(skb) - (u8 *)p_rta; } } -#elif defined CONFIG_NET_CLS_POLICE - if (map->police && exts->police) { - struct rtattr *p_rta = (struct rtattr *)skb_tail_pointer(skb); - - RTA_PUT(skb, map->police, 0, NULL); - - if (tcf_police_dump(skb, exts->police) < 0) - goto rtattr_failure; - - p_rta->rta_len = skb_tail_pointer(skb) - (u8 *)p_rta; - } #endif return 0; rtattr_failure: __attribute__ ((unused)) @@ -591,10 +555,6 @@ tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts, if (exts->action) if (tcf_action_copy_stats(skb, exts->action, 1) < 0) goto rtattr_failure; -#elif defined CONFIG_NET_CLS_POLICE - if (exts->police) - if (tcf_police_dump_stats(skb, exts->police) < 0) - goto rtattr_failure; #endif return 0; rtattr_failure: __attribute__ ((unused)) diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 77961e2314dc..8dbe36912ecb 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -782,9 +782,6 @@ static int __init init_u32(void) #ifdef CONFIG_CLS_U32_PERF printk(" Performance counters on\n"); #endif -#ifdef CONFIG_NET_CLS_POLICE - printk(" OLD policer on \n"); -#endif #ifdef CONFIG_NET_CLS_IND printk(" input device check on \n"); #endif diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index d92ea26982c5..13c09bc32aa3 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -278,11 +278,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) wd->qdisc->flags &= ~TCQ_F_THROTTLED; smp_wmb(); - if (spin_trylock(&dev->queue_lock)) { - qdisc_run(dev); - spin_unlock(&dev->queue_lock); - } else - netif_schedule(dev); + netif_schedule(dev); return HRTIMER_NORESTART; } @@ -1149,47 +1145,57 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) to this qdisc, (optionally) tests for protocol and asks specific classifiers. */ +int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp, + struct tcf_result *res) +{ + __be16 protocol = skb->protocol; + int err = 0; + + for (; tp; tp = tp->next) { + if ((tp->protocol == protocol || + tp->protocol == htons(ETH_P_ALL)) && + (err = tp->classify(skb, tp, res)) >= 0) { +#ifdef CONFIG_NET_CLS_ACT + if (err != TC_ACT_RECLASSIFY && skb->tc_verd) + skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0); +#endif + return err; + } + } + return -1; +} +EXPORT_SYMBOL(tc_classify_compat); + int tc_classify(struct sk_buff *skb, struct tcf_proto *tp, - struct tcf_result *res) + struct tcf_result *res) { int err = 0; - __be16 protocol = skb->protocol; + __be16 protocol; #ifdef CONFIG_NET_CLS_ACT struct tcf_proto *otp = tp; reclassify: #endif protocol = skb->protocol; - for ( ; tp; tp = tp->next) { - if ((tp->protocol == protocol || - tp->protocol == htons(ETH_P_ALL)) && - (err = tp->classify(skb, tp, res)) >= 0) { + err = tc_classify_compat(skb, tp, res); #ifdef CONFIG_NET_CLS_ACT - if ( TC_ACT_RECLASSIFY == err) { - __u32 verd = (__u32) G_TC_VERD(skb->tc_verd); - tp = otp; - - if (MAX_REC_LOOP < verd++) { - printk("rule prio %d protocol %02x reclassify is buggy packet dropped\n", - tp->prio&0xffff, ntohs(tp->protocol)); - return TC_ACT_SHOT; - } - skb->tc_verd = SET_TC_VERD(skb->tc_verd,verd); - goto reclassify; - } else { - if (skb->tc_verd) - skb->tc_verd = SET_TC_VERD(skb->tc_verd,0); - return err; - } -#else - - return err; -#endif + if (err == TC_ACT_RECLASSIFY) { + u32 verd = G_TC_VERD(skb->tc_verd); + tp = otp; + + if (verd++ >= MAX_REC_LOOP) { + printk("rule prio %u protocol %02x reclassify loop, " + "packet dropped\n", + tp->prio&0xffff, ntohs(tp->protocol)); + return TC_ACT_SHOT; } - + skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); + goto reclassify; } - return -1; +#endif + return err; } +EXPORT_SYMBOL(tc_classify); void tcf_destroy(struct tcf_proto *tp) { @@ -1256,4 +1262,3 @@ EXPORT_SYMBOL(qdisc_get_rtab); EXPORT_SYMBOL(qdisc_put_rtab); EXPORT_SYMBOL(register_qdisc); EXPORT_SYMBOL(unregister_qdisc); -EXPORT_SYMBOL(tc_classify); diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 54b92d22796c..417ec8fb7f1a 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -2,7 +2,6 @@ /* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - #include <linux/module.h> #include <linux/init.h> #include <linux/string.h> @@ -11,12 +10,11 @@ #include <linux/atmdev.h> #include <linux/atmclip.h> #include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ +#include <linux/file.h> /* for fput */ #include <net/netlink.h> #include <net/pkt_sched.h> - -extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ +extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ #if 0 /* control */ #define DPRINTK(format,args...) printk(KERN_DEBUG format,##args) @@ -30,7 +28,6 @@ extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ #define D2PRINTK(format,args...) #endif - /* * The ATM queuing discipline provides a framework for invoking classifiers * (aka "filters"), which in turn select classes of this queuing discipline. @@ -52,16 +49,15 @@ extern struct socket *sockfd_lookup(int fd, int *err); /* @@@ fix this */ * - should lock the flow while there is data in the queue (?) */ - #define PRIV(sch) qdisc_priv(sch) #define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - struct atm_flow_data { - struct Qdisc *q; /* FIFO, TBF, etc. */ + struct Qdisc *q; /* FIFO, TBF, etc. */ struct tcf_proto *filter_list; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc,struct sk_buff *skb); /* chaining */ + struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ + void (*old_pop)(struct atm_vcc *vcc, + struct sk_buff * skb); /* chaining */ struct atm_qdisc_data *parent; /* parent qdisc */ struct socket *sock; /* for closing */ u32 classid; /* x:y type ID */ @@ -82,76 +78,74 @@ struct atm_qdisc_data { struct tasklet_struct task; /* requeue tasklet */ }; - /* ------------------------- Class/flow operations ------------------------- */ - -static int find_flow(struct atm_qdisc_data *qdisc,struct atm_flow_data *flow) +static int find_flow(struct atm_qdisc_data *qdisc, struct atm_flow_data *flow) { struct atm_flow_data *walk; - DPRINTK("find_flow(qdisc %p,flow %p)\n",qdisc,flow); + DPRINTK("find_flow(qdisc %p,flow %p)\n", qdisc, flow); for (walk = qdisc->flows; walk; walk = walk->next) - if (walk == flow) return 1; + if (walk == flow) + return 1; DPRINTK("find_flow: not found\n"); return 0; } - -static __inline__ struct atm_flow_data *lookup_flow(struct Qdisc *sch, - u32 classid) +static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; for (flow = p->flows; flow; flow = flow->next) - if (flow->classid == classid) break; + if (flow->classid == classid) + break; return flow; } - -static int atm_tc_graft(struct Qdisc *sch,unsigned long arg, - struct Qdisc *new,struct Qdisc **old) +static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, + struct Qdisc *new, struct Qdisc **old) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) arg; - - DPRINTK("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n",sch, - p,flow,new,old); - if (!find_flow(p,flow)) return -EINVAL; - if (!new) new = &noop_qdisc; - *old = xchg(&flow->q,new); - if (*old) qdisc_reset(*old); + struct atm_flow_data *flow = (struct atm_flow_data *)arg; + + DPRINTK("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", + sch, p, flow, new, old); + if (!find_flow(p, flow)) + return -EINVAL; + if (!new) + new = &noop_qdisc; + *old = xchg(&flow->q, new); + if (*old) + qdisc_reset(*old); return 0; } - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch,unsigned long cl) +static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) { - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; - DPRINTK("atm_tc_leaf(sch %p,flow %p)\n",sch,flow); + DPRINTK("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); return flow ? flow->q : NULL; } - -static unsigned long atm_tc_get(struct Qdisc *sch,u32 classid) +static unsigned long atm_tc_get(struct Qdisc *sch, u32 classid) { - struct atm_qdisc_data *p __attribute__((unused)) = PRIV(sch); + struct atm_qdisc_data *p __maybe_unused = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_get(sch %p,[qdisc %p],classid %x)\n",sch,p,classid); - flow = lookup_flow(sch,classid); - if (flow) flow->ref++; - DPRINTK("atm_tc_get: flow %p\n",flow); - return (unsigned long) flow; + DPRINTK("atm_tc_get(sch %p,[qdisc %p],classid %x)\n", sch, p, classid); + flow = lookup_flow(sch, classid); + if (flow) + flow->ref++; + DPRINTK("atm_tc_get: flow %p\n", flow); + return (unsigned long)flow; } - static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) + unsigned long parent, u32 classid) { - return atm_tc_get(sch,classid); + return atm_tc_get(sch, classid); } /* @@ -159,72 +153,75 @@ static unsigned long atm_tc_bind_filter(struct Qdisc *sch, * requested (atm_tc_destroy, etc.). The assumption here is that we never drop * anything that still seems to be in use. */ - static void atm_tc_put(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; struct atm_flow_data **prev; - DPRINTK("atm_tc_put(sch %p,[qdisc %p],flow %p)\n",sch,p,flow); - if (--flow->ref) return; + DPRINTK("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); + if (--flow->ref) + return; DPRINTK("atm_tc_put: destroying\n"); for (prev = &p->flows; *prev; prev = &(*prev)->next) - if (*prev == flow) break; + if (*prev == flow) + break; if (!*prev) { - printk(KERN_CRIT "atm_tc_put: class %p not found\n",flow); + printk(KERN_CRIT "atm_tc_put: class %p not found\n", flow); return; } *prev = flow->next; - DPRINTK("atm_tc_put: qdisc %p\n",flow->q); + DPRINTK("atm_tc_put: qdisc %p\n", flow->q); qdisc_destroy(flow->q); tcf_destroy_chain(flow->filter_list); if (flow->sock) { DPRINTK("atm_tc_put: f_count %d\n", - file_count(flow->sock->file)); + file_count(flow->sock->file)); flow->vcc->pop = flow->old_pop; sockfd_put(flow->sock); } - if (flow->excess) atm_tc_put(sch,(unsigned long) flow->excess); - if (flow != &p->link) kfree(flow); + if (flow->excess) + atm_tc_put(sch, (unsigned long)flow->excess); + if (flow != &p->link) + kfree(flow); /* * If flow == &p->link, the qdisc no longer works at this point and * needs to be removed. (By the caller of atm_tc_put.) */ } - -static void sch_atm_pop(struct atm_vcc *vcc,struct sk_buff *skb) +static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) { struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - D2PRINTK("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n",vcc,skb,p); - VCC2FLOW(vcc)->old_pop(vcc,skb); + D2PRINTK("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); + VCC2FLOW(vcc)->old_pop(vcc, skb); tasklet_schedule(&p->task); } static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ + 0xaa, /* DSAP: non-ISO */ + 0xaa, /* SSAP: non-ISO */ + 0x03, /* Ctrl: Unnumbered Information Command PDU */ + 0x00, /* OUI: EtherType */ 0x00, 0x00, - 0x08, 0x00 }; /* Ethertype IP (0800) */ + 0x08, 0x00 +}; /* Ethertype IP (0800) */ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct rtattr **tca, unsigned long *arg) + struct rtattr **tca, unsigned long *arg) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) *arg; + struct atm_flow_data *flow = (struct atm_flow_data *)*arg; struct atm_flow_data *excess = NULL; - struct rtattr *opt = tca[TCA_OPTIONS-1]; + struct rtattr *opt = tca[TCA_OPTIONS - 1]; struct rtattr *tb[TCA_ATM_MAX]; struct socket *sock; - int fd,error,hdr_len; + int fd, error, hdr_len; void *hdr; DPRINTK("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n",sch,p,classid,parent,flow,opt); + "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); /* * The concept of parents doesn't apply for this qdisc. */ @@ -237,33 +234,36 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, * class needs to be removed and a new one added. (This may be changed * later.) */ - if (flow) return -EBUSY; + if (flow) + return -EBUSY; if (opt == NULL || rtattr_parse_nested(tb, TCA_ATM_MAX, opt)) return -EINVAL; - if (!tb[TCA_ATM_FD-1] || RTA_PAYLOAD(tb[TCA_ATM_FD-1]) < sizeof(fd)) + if (!tb[TCA_ATM_FD - 1] || RTA_PAYLOAD(tb[TCA_ATM_FD - 1]) < sizeof(fd)) return -EINVAL; - fd = *(int *) RTA_DATA(tb[TCA_ATM_FD-1]); - DPRINTK("atm_tc_change: fd %d\n",fd); - if (tb[TCA_ATM_HDR-1]) { - hdr_len = RTA_PAYLOAD(tb[TCA_ATM_HDR-1]); - hdr = RTA_DATA(tb[TCA_ATM_HDR-1]); - } - else { + fd = *(int *)RTA_DATA(tb[TCA_ATM_FD - 1]); + DPRINTK("atm_tc_change: fd %d\n", fd); + if (tb[TCA_ATM_HDR - 1]) { + hdr_len = RTA_PAYLOAD(tb[TCA_ATM_HDR - 1]); + hdr = RTA_DATA(tb[TCA_ATM_HDR - 1]); + } else { hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ + hdr = NULL; /* default LLC/SNAP for IP */ } - if (!tb[TCA_ATM_EXCESS-1]) excess = NULL; + if (!tb[TCA_ATM_EXCESS - 1]) + excess = NULL; else { - if (RTA_PAYLOAD(tb[TCA_ATM_EXCESS-1]) != sizeof(u32)) + if (RTA_PAYLOAD(tb[TCA_ATM_EXCESS - 1]) != sizeof(u32)) return -EINVAL; - excess = (struct atm_flow_data *) atm_tc_get(sch, - *(u32 *) RTA_DATA(tb[TCA_ATM_EXCESS-1])); - if (!excess) return -ENOENT; + excess = (struct atm_flow_data *) + atm_tc_get(sch, *(u32 *)RTA_DATA(tb[TCA_ATM_EXCESS - 1])); + if (!excess) + return -ENOENT; } DPRINTK("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->rta_type,RTA_PAYLOAD(opt),hdr_len); - if (!(sock = sockfd_lookup(fd,&error))) return error; /* f_count++ */ - DPRINTK("atm_tc_change: f_count %d\n",file_count(sock->file)); + opt->rta_type, RTA_PAYLOAD(opt), hdr_len); + if (!(sock = sockfd_lookup(fd, &error))) + return error; /* f_count++ */ + DPRINTK("atm_tc_change: f_count %d\n", file_count(sock->file)); if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { error = -EPROTOTYPE; goto err_out; @@ -276,37 +276,37 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, error = -EINVAL; goto err_out; } - if (find_flow(p,flow)) { + if (find_flow(p, flow)) { error = -EEXIST; goto err_out; } - } - else { + } else { int i; unsigned long cl; for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle,0x8000 | i); - if (!(cl = atm_tc_get(sch,classid))) break; - atm_tc_put(sch,cl); + classid = TC_H_MAKE(sch->handle, 0x8000 | i); + if (!(cl = atm_tc_get(sch, classid))) + break; + atm_tc_put(sch, cl); } } - DPRINTK("atm_tc_change: new id %x\n",classid); - flow = kmalloc(sizeof(struct atm_flow_data)+hdr_len,GFP_KERNEL); - DPRINTK("atm_tc_change: flow %p\n",flow); + DPRINTK("atm_tc_change: new id %x\n", classid); + flow = kmalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); + DPRINTK("atm_tc_change: flow %p\n", flow); if (!flow) { error = -ENOBUFS; goto err_out; } - memset(flow,0,sizeof(*flow)); + memset(flow, 0, sizeof(*flow)); flow->filter_list = NULL; - if (!(flow->q = qdisc_create_dflt(sch->dev,&pfifo_qdisc_ops,classid))) + if (!(flow->q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops, classid))) flow->q = &noop_qdisc; - DPRINTK("atm_tc_change: qdisc %p\n",flow->q); + DPRINTK("atm_tc_change: qdisc %p\n", flow->q); flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ + flow->vcc = ATM_SD(sock); /* speedup */ flow->vcc->user_back = flow; - DPRINTK("atm_tc_change: vcc %p\n",flow->vcc); + DPRINTK("atm_tc_change: vcc %p\n", flow->vcc); flow->old_pop = flow->vcc->pop; flow->parent = p; flow->vcc->pop = sch_atm_pop; @@ -317,50 +317,53 @@ static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, p->link.next = flow; flow->hdr_len = hdr_len; if (hdr) - memcpy(flow->hdr,hdr,hdr_len); + memcpy(flow->hdr, hdr, hdr_len); else - memcpy(flow->hdr,llc_oui_ip,sizeof(llc_oui_ip)); - *arg = (unsigned long) flow; + memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); + *arg = (unsigned long)flow; return 0; err_out: - if (excess) atm_tc_put(sch,(unsigned long) excess); + if (excess) + atm_tc_put(sch, (unsigned long)excess); sockfd_put(sock); return error; } - -static int atm_tc_delete(struct Qdisc *sch,unsigned long arg) +static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) arg; + struct atm_flow_data *flow = (struct atm_flow_data *)arg; - DPRINTK("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n",sch,p,flow); - if (!find_flow(PRIV(sch),flow)) return -EINVAL; - if (flow->filter_list || flow == &p->link) return -EBUSY; + DPRINTK("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); + if (!find_flow(PRIV(sch), flow)) + return -EINVAL; + if (flow->filter_list || flow == &p->link) + return -EBUSY; /* * Reference count must be 2: one for "keepalive" (set at class * creation), and one for the reference held when calling delete. */ if (flow->ref < 2) { - printk(KERN_ERR "atm_tc_delete: flow->ref == %d\n",flow->ref); + printk(KERN_ERR "atm_tc_delete: flow->ref == %d\n", flow->ref); return -EINVAL; } - if (flow->ref > 2) return -EBUSY; /* catch references via excess, etc.*/ - atm_tc_put(sch,arg); + if (flow->ref > 2) + return -EBUSY; /* catch references via excess, etc. */ + atm_tc_put(sch, arg); return 0; } - -static void atm_tc_walk(struct Qdisc *sch,struct qdisc_walker *walker) +static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n",sch,p,walker); - if (walker->stop) return; + DPRINTK("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); + if (walker->stop) + return; for (flow = p->flows; flow; flow = flow->next) { if (walker->count >= walker->skip) - if (walker->fn(sch,(unsigned long) flow,walker) < 0) { + if (walker->fn(sch, (unsigned long)flow, walker) < 0) { walker->stop = 1; break; } @@ -368,73 +371,71 @@ static void atm_tc_walk(struct Qdisc *sch,struct qdisc_walker *walker) } } - -static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch,unsigned long cl) +static struct tcf_proto **atm_tc_find_tcf(struct Qdisc *sch, unsigned long cl) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; - DPRINTK("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n",sch,p,flow); + DPRINTK("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); return flow ? &flow->filter_list : &p->link.filter_list; } - /* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb,struct Qdisc *sch) +static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = NULL ; /* @@@ */ + struct atm_flow_data *flow = NULL; /* @@@ */ struct tcf_result res; int result; int ret = NET_XMIT_POLICED; - D2PRINTK("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); - result = TC_POLICE_OK; /* be nice to gcc */ + D2PRINTK("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + result = TC_POLICE_OK; /* be nice to gcc */ if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *) atm_tc_get(sch,skb->priority))) + !(flow = (struct atm_flow_data *)atm_tc_get(sch, skb->priority))) for (flow = p->flows; flow; flow = flow->next) if (flow->filter_list) { - result = tc_classify(skb,flow->filter_list, - &res); - if (result < 0) continue; - flow = (struct atm_flow_data *) res.class; - if (!flow) flow = lookup_flow(sch,res.classid); + result = tc_classify_compat(skb, + flow->filter_list, + &res); + if (result < 0) + continue; + flow = (struct atm_flow_data *)res.class; + if (!flow) + flow = lookup_flow(sch, res.classid); break; } - if (!flow) flow = &p->link; + if (!flow) + flow = &p->link; else { if (flow->vcc) ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-)*/ -#ifdef CONFIG_NET_CLS_POLICE + /*@@@ looks good ... but it's not supposed to work :-) */ +#ifdef CONFIG_NET_CLS_ACT switch (result) { - case TC_POLICE_SHOT: - kfree_skb(skb); - break; - case TC_POLICE_RECLASSIFY: - if (flow->excess) flow = flow->excess; - else { - ATM_SKB(skb)->atm_options |= - ATM_ATMOPT_CLP; - break; - } - /* fall through */ - case TC_POLICE_OK: - /* fall through */ - default: - break; + case TC_ACT_QUEUED: + case TC_ACT_STOLEN: + kfree_skb(skb); + return NET_XMIT_SUCCESS; + case TC_ACT_SHOT: + kfree_skb(skb); + goto drop; + case TC_POLICE_RECLASSIFY: + if (flow->excess) + flow = flow->excess; + else + ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; + break; } #endif } - if ( -#ifdef CONFIG_NET_CLS_POLICE - result == TC_POLICE_SHOT || -#endif - (ret = flow->q->enqueue(skb,flow->q)) != 0) { + + if ((ret = flow->q->enqueue(skb, flow->q)) != 0) { +drop: __maybe_unused sch->qstats.drops++; - if (flow) flow->qstats.drops++; + if (flow) + flow->qstats.drops++; return ret; } sch->bstats.bytes += skb->len; @@ -458,7 +459,6 @@ static int atm_tc_enqueue(struct sk_buff *skb,struct Qdisc *sch) return NET_XMIT_BYPASS; } - /* * Dequeue packets and send them over ATM. Note that we quite deliberately * avoid checking net_device's flow control here, simply because sch_atm @@ -466,167 +466,163 @@ static int atm_tc_enqueue(struct sk_buff *skb,struct Qdisc *sch) * non-ATM interfaces. */ - static void sch_atm_dequeue(unsigned long data) { - struct Qdisc *sch = (struct Qdisc *) data; + struct Qdisc *sch = (struct Qdisc *)data; struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; struct sk_buff *skb; - D2PRINTK("sch_atm_dequeue(sch %p,[qdisc %p])\n",sch,p); + D2PRINTK("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); for (flow = p->link.next; flow; flow = flow->next) /* * If traffic is properly shaped, this won't generate nasty * little bursts. Otherwise, it may ... (but that's okay) */ while ((skb = flow->q->dequeue(flow->q))) { - if (!atm_may_send(flow->vcc,skb->truesize)) { - (void) flow->q->ops->requeue(skb,flow->q); + if (!atm_may_send(flow->vcc, skb->truesize)) { + (void)flow->q->ops->requeue(skb, flow->q); break; } - D2PRINTK("atm_tc_dequeue: sending on class %p\n",flow); + D2PRINTK("atm_tc_dequeue: sending on class %p\n", flow); /* remove any LL header somebody else has attached */ skb_pull(skb, skb_network_offset(skb)); if (skb_headroom(skb) < flow->hdr_len) { struct sk_buff *new; - new = skb_realloc_headroom(skb,flow->hdr_len); + new = skb_realloc_headroom(skb, flow->hdr_len); dev_kfree_skb(skb); - if (!new) continue; + if (!new) + continue; skb = new; } D2PRINTK("sch_atm_dequeue: ip %p, data %p\n", skb_network_header(skb), skb->data); ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb,flow->hdr_len),flow->hdr, - flow->hdr_len); + memcpy(skb_push(skb, flow->hdr_len), flow->hdr, + flow->hdr_len); atomic_add(skb->truesize, &sk_atm(flow->vcc)->sk_wmem_alloc); /* atm.atm_options are already set by atm_tc_enqueue */ - (void) flow->vcc->send(flow->vcc,skb); + flow->vcc->send(flow->vcc, skb); } } - static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct sk_buff *skb; - D2PRINTK("atm_tc_dequeue(sch %p,[qdisc %p])\n",sch,p); + D2PRINTK("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); tasklet_schedule(&p->task); skb = p->link.q->dequeue(p->link.q); - if (skb) sch->q.qlen--; + if (skb) + sch->q.qlen--; return skb; } - -static int atm_tc_requeue(struct sk_buff *skb,struct Qdisc *sch) +static int atm_tc_requeue(struct sk_buff *skb, struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); int ret; - D2PRINTK("atm_tc_requeue(skb %p,sch %p,[qdisc %p])\n",skb,sch,p); - ret = p->link.q->ops->requeue(skb,p->link.q); + D2PRINTK("atm_tc_requeue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); + ret = p->link.q->ops->requeue(skb, p->link.q); if (!ret) { - sch->q.qlen++; - sch->qstats.requeues++; - } else { + sch->q.qlen++; + sch->qstats.requeues++; + } else { sch->qstats.drops++; p->link.qstats.drops++; } return ret; } - static unsigned int atm_tc_drop(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; unsigned int len; - DPRINTK("atm_tc_drop(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("atm_tc_drop(sch %p,[qdisc %p])\n", sch, p); for (flow = p->flows; flow; flow = flow->next) if (flow->q->ops->drop && (len = flow->q->ops->drop(flow->q))) return len; return 0; } - -static int atm_tc_init(struct Qdisc *sch,struct rtattr *opt) +static int atm_tc_init(struct Qdisc *sch, struct rtattr *opt) { struct atm_qdisc_data *p = PRIV(sch); - DPRINTK("atm_tc_init(sch %p,[qdisc %p],opt %p)\n",sch,p,opt); + DPRINTK("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); p->flows = &p->link; - if(!(p->link.q = qdisc_create_dflt(sch->dev,&pfifo_qdisc_ops, - sch->handle))) + if (!(p->link.q = qdisc_create_dflt(sch->dev, &pfifo_qdisc_ops, + sch->handle))) p->link.q = &noop_qdisc; - DPRINTK("atm_tc_init: link (%p) qdisc %p\n",&p->link,p->link.q); + DPRINTK("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); p->link.filter_list = NULL; p->link.vcc = NULL; p->link.sock = NULL; p->link.classid = sch->handle; p->link.ref = 1; p->link.next = NULL; - tasklet_init(&p->task,sch_atm_dequeue,(unsigned long) sch); + tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } - static void atm_tc_reset(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_reset(sch %p,[qdisc %p])\n",sch,p); - for (flow = p->flows; flow; flow = flow->next) qdisc_reset(flow->q); + DPRINTK("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); + for (flow = p->flows; flow; flow = flow->next) + qdisc_reset(flow->q); sch->q.qlen = 0; } - static void atm_tc_destroy(struct Qdisc *sch) { struct atm_qdisc_data *p = PRIV(sch); struct atm_flow_data *flow; - DPRINTK("atm_tc_destroy(sch %p,[qdisc %p])\n",sch,p); + DPRINTK("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); /* races ? */ while ((flow = p->flows)) { tcf_destroy_chain(flow->filter_list); flow->filter_list = NULL; if (flow->ref > 1) - printk(KERN_ERR "atm_destroy: %p->ref = %d\n",flow, - flow->ref); - atm_tc_put(sch,(unsigned long) flow); + printk(KERN_ERR "atm_destroy: %p->ref = %d\n", flow, + flow->ref); + atm_tc_put(sch, (unsigned long)flow); if (p->flows == flow) { printk(KERN_ERR "atm_destroy: putting flow %p didn't " - "kill it\n",flow); - p->flows = flow->next; /* brute force */ + "kill it\n", flow); + p->flows = flow->next; /* brute force */ break; } } tasklet_kill(&p->task); } - static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) + struct sk_buff *skb, struct tcmsg *tcm) { struct atm_qdisc_data *p = PRIV(sch); - struct atm_flow_data *flow = (struct atm_flow_data *) cl; + struct atm_flow_data *flow = (struct atm_flow_data *)cl; unsigned char *b = skb_tail_pointer(skb); struct rtattr *rta; DPRINTK("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch,p,flow,skb,tcm); - if (!find_flow(p,flow)) return -EINVAL; + sch, p, flow, skb, tcm); + if (!find_flow(p, flow)) + return -EINVAL; tcm->tcm_handle = flow->classid; tcm->tcm_info = flow->q->handle; - rta = (struct rtattr *) b; - RTA_PUT(skb,TCA_OPTIONS,0,NULL); - RTA_PUT(skb,TCA_ATM_HDR,flow->hdr_len,flow->hdr); + rta = (struct rtattr *)b; + RTA_PUT(skb, TCA_OPTIONS, 0, NULL); + RTA_PUT(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr); if (flow->vcc) { struct sockaddr_atmpvc pvc; int state; @@ -635,16 +631,16 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; pvc.sap_addr.vci = flow->vcc->vci; - RTA_PUT(skb,TCA_ATM_ADDR,sizeof(pvc),&pvc); + RTA_PUT(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc); state = ATM_VF2VS(flow->vcc->flags); - RTA_PUT(skb,TCA_ATM_STATE,sizeof(state),&state); + RTA_PUT(skb, TCA_ATM_STATE, sizeof(state), &state); } if (flow->excess) - RTA_PUT(skb,TCA_ATM_EXCESS,sizeof(u32),&flow->classid); + RTA_PUT(skb, TCA_ATM_EXCESS, sizeof(u32), &flow->classid); else { static u32 zero; - RTA_PUT(skb,TCA_ATM_EXCESS,sizeof(zero),&zero); + RTA_PUT(skb, TCA_ATM_EXCESS, sizeof(zero), &zero); } rta->rta_len = skb_tail_pointer(skb) - b; return skb->len; @@ -655,9 +651,9 @@ rtattr_failure: } static int atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) + struct gnet_dump *d) { - struct atm_flow_data *flow = (struct atm_flow_data *) arg; + struct atm_flow_data *flow = (struct atm_flow_data *)arg; flow->qstats.qlen = flow->q->q.qlen; @@ -674,38 +670,35 @@ static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) } static struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .get = atm_tc_get, - .put = atm_tc_put, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_chain = atm_tc_find_tcf, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, + .graft = atm_tc_graft, + .leaf = atm_tc_leaf, + .get = atm_tc_get, + .put = atm_tc_put, + .change = atm_tc_change, + .delete = atm_tc_delete, + .walk = atm_tc_walk, + .tcf_chain = atm_tc_find_tcf, + .bind_tcf = atm_tc_bind_filter, + .unbind_tcf = atm_tc_put, + .dump = atm_tc_dump_class, + .dump_stats = atm_tc_dump_class_stats, }; static struct Qdisc_ops atm_qdisc_ops = { - .next = NULL, - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .requeue = atm_tc_requeue, - .drop = atm_tc_drop, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .change = NULL, - .dump = atm_tc_dump, - .owner = THIS_MODULE, + .cl_ops = &atm_class_ops, + .id = "atm", + .priv_size = sizeof(struct atm_qdisc_data), + .enqueue = atm_tc_enqueue, + .dequeue = atm_tc_dequeue, + .requeue = atm_tc_requeue, + .drop = atm_tc_drop, + .init = atm_tc_init, + .reset = atm_tc_reset, + .destroy = atm_tc_destroy, + .dump = atm_tc_dump, + .owner = THIS_MODULE, }; - static int __init atm_init(void) { return register_qdisc(&atm_qdisc_ops); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index b184c3545145..e38c2839b25c 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -82,7 +82,7 @@ struct cbq_class unsigned char priority2; /* priority to be used after overlimit */ unsigned char ewma_log; /* time constant for idle time calculation */ unsigned char ovl_strategy; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT unsigned char police; #endif @@ -154,7 +154,7 @@ struct cbq_sched_data struct cbq_class *active[TC_CBQ_MAXPRIO+1]; /* List of all classes with backlog */ -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT struct cbq_class *rx_class; #endif struct cbq_class *tx_class; @@ -196,7 +196,7 @@ cbq_class_lookup(struct cbq_sched_data *q, u32 classid) return NULL; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT static struct cbq_class * cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) @@ -247,7 +247,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 2+n. Apply classifier. */ - if (!head->filter_list || (result = tc_classify(skb, head->filter_list, &res)) < 0) + if (!head->filter_list || + (result = tc_classify_compat(skb, head->filter_list, &res)) < 0) goto fallback; if ((cl = (void*)res.class) == NULL) { @@ -267,15 +268,8 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) *qerr = NET_XMIT_SUCCESS; case TC_ACT_SHOT: return NULL; - } -#elif defined(CONFIG_NET_CLS_POLICE) - switch (result) { - case TC_POLICE_RECLASSIFY: + case TC_ACT_RECLASSIFY: return cbq_reclassify(skb, cl); - case TC_POLICE_SHOT: - return NULL; - default: - break; } #endif if (cl->level == 0) @@ -389,7 +383,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; struct cbq_class *cl = cbq_classify(skb, sch, &ret); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT q->rx_class = cl; #endif if (cl == NULL) { @@ -399,7 +393,7 @@ cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT cl->q->__parent = sch; #endif if ((ret = cl->q->enqueue(skb, cl->q)) == NET_XMIT_SUCCESS) { @@ -434,7 +428,7 @@ cbq_requeue(struct sk_buff *skb, struct Qdisc *sch) cbq_mark_toplevel(q, cl); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT q->rx_class = cl; cl->q->__parent = sch; #endif @@ -669,9 +663,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) return HRTIMER_NORESTART; } - -#ifdef CONFIG_NET_CLS_POLICE - +#ifdef CONFIG_NET_CLS_ACT static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) { int len = skb->len; @@ -1364,7 +1356,7 @@ static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl) return 0; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT static int cbq_set_police(struct cbq_class *cl, struct tc_cbq_police *p) { cl->police = p->police; @@ -1532,7 +1524,7 @@ rtattr_failure: return -1; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); @@ -1558,7 +1550,7 @@ static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) cbq_dump_rate(skb, cl) < 0 || cbq_dump_wrr(skb, cl) < 0 || cbq_dump_ovl(skb, cl) < 0 || -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT cbq_dump_police(skb, cl) < 0 || #endif cbq_dump_fopt(skb, cl) < 0) @@ -1653,7 +1645,7 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, cl->classid)) == NULL) return -ENOBUFS; } else { -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (cl->police == TC_POLICE_RECLASSIFY) new->reshape_fail = cbq_reshape_fail; #endif @@ -1718,7 +1710,7 @@ cbq_destroy(struct Qdisc* sch) struct cbq_class *cl; unsigned h; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT q->rx_class = NULL; #endif /* @@ -1747,7 +1739,7 @@ static void cbq_put(struct Qdisc *sch, unsigned long arg) struct cbq_class *cl = (struct cbq_class*)arg; if (--cl->refcnt == 0) { -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT struct cbq_sched_data *q = qdisc_priv(sch); spin_lock_bh(&sch->dev->queue_lock); @@ -1795,7 +1787,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t RTA_PAYLOAD(tb[TCA_CBQ_WRROPT-1]) < sizeof(struct tc_cbq_wrropt)) return -EINVAL; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (tb[TCA_CBQ_POLICE-1] && RTA_PAYLOAD(tb[TCA_CBQ_POLICE-1]) < sizeof(struct tc_cbq_police)) return -EINVAL; @@ -1838,7 +1830,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t if (tb[TCA_CBQ_OVL_STRATEGY-1]) cbq_set_overlimit(cl, RTA_DATA(tb[TCA_CBQ_OVL_STRATEGY-1])); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (tb[TCA_CBQ_POLICE-1]) cbq_set_police(cl, RTA_DATA(tb[TCA_CBQ_POLICE-1])); #endif @@ -1931,7 +1923,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct rtattr **t cl->overlimit = cbq_ovl_classic; if (tb[TCA_CBQ_OVL_STRATEGY-1]) cbq_set_overlimit(cl, RTA_DATA(tb[TCA_CBQ_OVL_STRATEGY-1])); -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (tb[TCA_CBQ_POLICE-1]) cbq_set_police(cl, RTA_DATA(tb[TCA_CBQ_POLICE-1])); #endif @@ -1975,7 +1967,7 @@ static int cbq_delete(struct Qdisc *sch, unsigned long arg) q->tx_class = NULL; q->tx_borrowed = NULL; } -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (q->rx_class == cl) q->rx_class = NULL; #endif diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 4d2c233a8611..60f89199e3da 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -237,25 +237,23 @@ static int dsmark_enqueue(struct sk_buff *skb,struct Qdisc *sch) D2PRINTK("result %d class 0x%04x\n", result, res.classid); switch (result) { -#ifdef CONFIG_NET_CLS_POLICE - case TC_POLICE_SHOT: - kfree_skb(skb); - sch->qstats.drops++; - return NET_XMIT_POLICED; -#if 0 - case TC_POLICE_RECLASSIFY: - /* FIXME: what to do here ??? */ +#ifdef CONFIG_NET_CLS_ACT + case TC_ACT_QUEUED: + case TC_ACT_STOLEN: + kfree_skb(skb); + return NET_XMIT_SUCCESS; + case TC_ACT_SHOT: + kfree_skb(skb); + sch->qstats.drops++; + return NET_XMIT_BYPASS; #endif -#endif - case TC_POLICE_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - case TC_POLICE_UNSPEC: - /* fall through */ - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; + case TC_ACT_OK: + skb->tc_index = TC_H_MIN(res.classid); + break; + default: + if (p->default_index != NO_DEFAULT_INDEX) + skb->tc_index = p->default_index; + break; } } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 874452c41a01..55e7e4530f43 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1174,9 +1174,6 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) case TC_ACT_SHOT: return NULL; } -#elif defined(CONFIG_NET_CLS_POLICE) - if (result == TC_POLICE_SHOT) - return NULL; #endif if ((cl = (struct hfsc_class *)res.class) == NULL) { if ((cl = hfsc_find_class(res.classid, sch)) == NULL) diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index b417a95df322..246a2f9765f1 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -249,9 +249,6 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, case TC_ACT_SHOT: return NULL; } -#elif defined(CONFIG_NET_CLS_POLICE) - if (result == TC_POLICE_SHOT) - return HTB_DIRECT; #endif if ((cl = (void *)res.class) == NULL) { if (res.classid == sch->handle) diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index cd0aab6a2a7c..51f16b0af198 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -164,31 +164,12 @@ static int ingress_enqueue(struct sk_buff *skb,struct Qdisc *sch) result = TC_ACT_OK; break; } -/* backward compat */ -#else -#ifdef CONFIG_NET_CLS_POLICE - switch (result) { - case TC_POLICE_SHOT: - result = NF_DROP; - sch->qstats.drops++; - break; - case TC_POLICE_RECLASSIFY: /* DSCP remarking here ? */ - case TC_POLICE_OK: - case TC_POLICE_UNSPEC: - default: - sch->bstats.packets++; - sch->bstats.bytes += skb->len; - result = NF_ACCEPT; - break; - } - #else D2PRINTK("Overriding result to ACCEPT\n"); result = NF_ACCEPT; sch->bstats.packets++; sch->bstats.bytes += skb->len; #endif -#endif return result; } diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 22e431dace54..8c2639af4c6a 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -125,7 +125,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) if (skb->len > q->max_size) { sch->qstats.drops++; -#ifdef CONFIG_NET_CLS_POLICE +#ifdef CONFIG_NET_CLS_ACT if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch)) #endif kfree_skb(skb); diff --git a/net/wireless/Makefile b/net/wireless/Makefile index 3a96ae60271c..092116e390b6 100644 --- a/net/wireless/Makefile +++ b/net/wireless/Makefile @@ -1,4 +1,4 @@ obj-$(CONFIG_WIRELESS_EXT) += wext.o obj-$(CONFIG_CFG80211) += cfg80211.o -cfg80211-y += core.o sysfs.o +cfg80211-y += core.o sysfs.o radiotap.o diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c new file mode 100644 index 000000000000..68c11d099917 --- /dev/null +++ b/net/wireless/radiotap.c @@ -0,0 +1,257 @@ +/* + * Radiotap parser + * + * Copyright 2007 Andy Green <andy@warmcat.com> + */ + +#include <net/cfg80211.h> +#include <net/ieee80211_radiotap.h> +#include <asm/unaligned.h> + +/* function prototypes and related defs are in include/net/cfg80211.h */ + +/** + * ieee80211_radiotap_iterator_init - radiotap parser iterator initialization + * @iterator: radiotap_iterator to initialize + * @radiotap_header: radiotap header to parse + * @max_length: total length we can parse into (eg, whole packet length) + * + * Returns: 0 or a negative error code if there is a problem. + * + * This function initializes an opaque iterator struct which can then + * be passed to ieee80211_radiotap_iterator_next() to visit every radiotap + * argument which is present in the header. It knows about extended + * present headers and handles them. + * + * How to use: + * call __ieee80211_radiotap_iterator_init() to init a semi-opaque iterator + * struct ieee80211_radiotap_iterator (no need to init the struct beforehand) + * checking for a good 0 return code. Then loop calling + * __ieee80211_radiotap_iterator_next()... it returns either 0, + * -ENOENT if there are no more args to parse, or -EINVAL if there is a problem. + * The iterator's @this_arg member points to the start of the argument + * associated with the current argument index that is present, which can be + * found in the iterator's @this_arg_index member. This arg index corresponds + * to the IEEE80211_RADIOTAP_... defines. + * + * Radiotap header length: + * You can find the CPU-endian total radiotap header length in + * iterator->max_length after executing ieee80211_radiotap_iterator_init() + * successfully. + * + * Alignment Gotcha: + * You must take care when dereferencing iterator.this_arg + * for multibyte types... the pointer is not aligned. Use + * get_unaligned((type *)iterator.this_arg) to dereference + * iterator.this_arg for type "type" safely on all arches. + * + * Example code: + * See Documentation/networking/radiotap-headers.txt + */ + +int ieee80211_radiotap_iterator_init( + struct ieee80211_radiotap_iterator *iterator, + struct ieee80211_radiotap_header *radiotap_header, + int max_length) +{ + /* Linux only supports version 0 radiotap format */ + if (radiotap_header->it_version) + return -EINVAL; + + /* sanity check for allowed length and radiotap length field */ + if (max_length < le16_to_cpu(get_unaligned(&radiotap_header->it_len))) + return -EINVAL; + + iterator->rtheader = radiotap_header; + iterator->max_length = le16_to_cpu(get_unaligned( + &radiotap_header->it_len)); + iterator->arg_index = 0; + iterator->bitmap_shifter = le32_to_cpu(get_unaligned( + &radiotap_header->it_present)); + iterator->arg = (u8 *)radiotap_header + sizeof(*radiotap_header); + iterator->this_arg = NULL; + + /* find payload start allowing for extended bitmap(s) */ + + if (unlikely(iterator->bitmap_shifter & (1<<IEEE80211_RADIOTAP_EXT))) { + while (le32_to_cpu(get_unaligned((__le32 *)iterator->arg)) & + (1<<IEEE80211_RADIOTAP_EXT)) { + iterator->arg += sizeof(u32); + + /* + * check for insanity where the present bitmaps + * keep claiming to extend up to or even beyond the + * stated radiotap header length + */ + + if (((ulong)iterator->arg - + (ulong)iterator->rtheader) > iterator->max_length) + return -EINVAL; + } + + iterator->arg += sizeof(u32); + + /* + * no need to check again for blowing past stated radiotap + * header length, because ieee80211_radiotap_iterator_next + * checks it before it is dereferenced + */ + } + + /* we are all initialized happily */ + + return 0; +} +EXPORT_SYMBOL(ieee80211_radiotap_iterator_init); + + +/** + * ieee80211_radiotap_iterator_next - return next radiotap parser iterator arg + * @iterator: radiotap_iterator to move to next arg (if any) + * + * Returns: 0 if there is an argument to handle, + * -ENOENT if there are no more args or -EINVAL + * if there is something else wrong. + * + * This function provides the next radiotap arg index (IEEE80211_RADIOTAP_*) + * in @this_arg_index and sets @this_arg to point to the + * payload for the field. It takes care of alignment handling and extended + * present fields. @this_arg can be changed by the caller (eg, + * incremented to move inside a compound argument like + * IEEE80211_RADIOTAP_CHANNEL). The args pointed to are in + * little-endian format whatever the endianess of your CPU. + * + * Alignment Gotcha: + * You must take care when dereferencing iterator.this_arg + * for multibyte types... the pointer is not aligned. Use + * get_unaligned((type *)iterator.this_arg) to dereference + * iterator.this_arg for type "type" safely on all arches. + */ + +int ieee80211_radiotap_iterator_next( + struct ieee80211_radiotap_iterator *iterator) +{ + + /* + * small length lookup table for all radiotap types we heard of + * starting from b0 in the bitmap, so we can walk the payload + * area of the radiotap header + * + * There is a requirement to pad args, so that args + * of a given length must begin at a boundary of that length + * -- but note that compound args are allowed (eg, 2 x u16 + * for IEEE80211_RADIOTAP_CHANNEL) so total arg length is not + * a reliable indicator of alignment requirement. + * + * upper nybble: content alignment for arg + * lower nybble: content length for arg + */ + + static const u8 rt_sizes[] = { + [IEEE80211_RADIOTAP_TSFT] = 0x88, + [IEEE80211_RADIOTAP_FLAGS] = 0x11, + [IEEE80211_RADIOTAP_RATE] = 0x11, + [IEEE80211_RADIOTAP_CHANNEL] = 0x24, + [IEEE80211_RADIOTAP_FHSS] = 0x22, + [IEEE80211_RADIOTAP_DBM_ANTSIGNAL] = 0x11, + [IEEE80211_RADIOTAP_DBM_ANTNOISE] = 0x11, + [IEEE80211_RADIOTAP_LOCK_QUALITY] = 0x22, + [IEEE80211_RADIOTAP_TX_ATTENUATION] = 0x22, + [IEEE80211_RADIOTAP_DB_TX_ATTENUATION] = 0x22, + [IEEE80211_RADIOTAP_DBM_TX_POWER] = 0x11, + [IEEE80211_RADIOTAP_ANTENNA] = 0x11, + [IEEE80211_RADIOTAP_DB_ANTSIGNAL] = 0x11, + [IEEE80211_RADIOTAP_DB_ANTNOISE] = 0x11 + /* + * add more here as they are defined in + * include/net/ieee80211_radiotap.h + */ + }; + + /* + * for every radiotap entry we can at + * least skip (by knowing the length)... + */ + + while (iterator->arg_index < sizeof(rt_sizes)) { + int hit = 0; + int pad; + + if (!(iterator->bitmap_shifter & 1)) + goto next_entry; /* arg not present */ + + /* + * arg is present, account for alignment padding + * 8-bit args can be at any alignment + * 16-bit args must start on 16-bit boundary + * 32-bit args must start on 32-bit boundary + * 64-bit args must start on 64-bit boundary + * + * note that total arg size can differ from alignment of + * elements inside arg, so we use upper nybble of length + * table to base alignment on + * + * also note: these alignments are ** relative to the + * start of the radiotap header **. There is no guarantee + * that the radiotap header itself is aligned on any + * kind of boundary. + * + * the above is why get_unaligned() is used to dereference + * multibyte elements from the radiotap area + */ + + pad = (((ulong)iterator->arg) - + ((ulong)iterator->rtheader)) & + ((rt_sizes[iterator->arg_index] >> 4) - 1); + + if (pad) + iterator->arg += + (rt_sizes[iterator->arg_index] >> 4) - pad; + + /* + * this is what we will return to user, but we need to + * move on first so next call has something fresh to test + */ + iterator->this_arg_index = iterator->arg_index; + iterator->this_arg = iterator->arg; + hit = 1; + + /* internally move on the size of this arg */ + iterator->arg += rt_sizes[iterator->arg_index] & 0x0f; + + /* + * check for insanity where we are given a bitmap that + * claims to have more arg content than the length of the + * radiotap section. We will normally end up equalling this + * max_length on the last arg, never exceeding it. + */ + + if (((ulong)iterator->arg - (ulong)iterator->rtheader) > + iterator->max_length) + return -EINVAL; + + next_entry: + iterator->arg_index++; + if (unlikely((iterator->arg_index & 31) == 0)) { + /* completed current u32 bitmap */ + if (iterator->bitmap_shifter & 1) { + /* b31 was set, there is more */ + /* move to next u32 bitmap */ + iterator->bitmap_shifter = le32_to_cpu( + get_unaligned(iterator->next_bitmap)); + iterator->next_bitmap++; + } else + /* no more bitmaps: end */ + iterator->arg_index = sizeof(rt_sizes); + } else /* just try the next bit */ + iterator->bitmap_shifter >>= 1; + + /* if we found a valid arg earlier, return it now */ + if (hit) + return 0; + } + + /* we don't know how to handle any more args, we're done */ + return -ENOENT; +} +EXPORT_SYMBOL(ieee80211_radiotap_iterator_next); |