diff options
Diffstat (limited to 'net')
360 files changed, 14949 insertions, 7158 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index c7a581a9689..8970ba139d7 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -18,6 +18,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/capability.h> #include <linux/module.h> #include <linux/netdevice.h> @@ -132,8 +134,6 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) vlan_gvrp_uninit_applicant(real_dev); rcu_assign_pointer(real_dev->vlgrp, NULL); - if (ops->ndo_vlan_rx_register) - ops->ndo_vlan_rx_register(real_dev, NULL); /* Free the group, after all cpu's are done. */ call_rcu(&grp->rcu, vlan_rcu_free); @@ -149,13 +149,13 @@ int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id) const struct net_device_ops *ops = real_dev->netdev_ops; if (real_dev->features & NETIF_F_VLAN_CHALLENGED) { - pr_info("8021q: VLANs not supported on %s\n", name); + pr_info("VLANs not supported on %s\n", name); return -EOPNOTSUPP; } if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) && (!ops->ndo_vlan_rx_add_vid || !ops->ndo_vlan_rx_kill_vid)) { - pr_info("8021q: Device %s has buggy VLAN hw accel\n", name); + pr_info("Device %s has buggy VLAN hw accel\n", name); return -EOPNOTSUPP; } @@ -205,8 +205,6 @@ int register_vlan_dev(struct net_device *dev) grp->nr_vlans++; if (ngrp) { - if (ops->ndo_vlan_rx_register) - ops->ndo_vlan_rx_register(real_dev, ngrp); rcu_assign_pointer(real_dev->vlgrp, ngrp); } if (real_dev->features & NETIF_F_HW_VLAN_FILTER) @@ -344,13 +342,12 @@ static void __vlan_device_event(struct net_device *dev, unsigned long event) case NETDEV_CHANGENAME: vlan_proc_rem_dev(dev); if (vlan_proc_add_dev(dev) < 0) - pr_warning("8021q: failed to change proc name for %s\n", - dev->name); + pr_warn("failed to change proc name for %s\n", + dev->name); break; case NETDEV_REGISTER: if (vlan_proc_add_dev(dev) < 0) - pr_warning("8021q: failed to add proc entry for %s\n", - dev->name); + pr_warn("failed to add proc entry for %s\n", dev->name); break; case NETDEV_UNREGISTER: vlan_proc_rem_dev(dev); @@ -374,7 +371,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, if ((event == NETDEV_UP) && (dev->features & NETIF_F_HW_VLAN_FILTER) && dev->netdev_ops->ndo_vlan_rx_add_vid) { - pr_info("8021q: adding VLAN 0 to HW filter on device %s\n", + pr_info("adding VLAN 0 to HW filter on device %s\n", dev->name); dev->netdev_ops->ndo_vlan_rx_add_vid(dev, 0); } diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index 9da07e30d1a..9fd45f3571f 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -74,6 +74,37 @@ static inline struct vlan_dev_info *vlan_dev_info(const struct net_device *dev) return netdev_priv(dev); } +static inline struct net_device *vlan_group_get_device(struct vlan_group *vg, + u16 vlan_id) +{ + struct net_device **array; + array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; + return array ? array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] : NULL; +} + +static inline void vlan_group_set_device(struct vlan_group *vg, + u16 vlan_id, + struct net_device *dev) +{ + struct net_device **array; + if (!vg) + return; + array = vg->vlan_devices_arrays[vlan_id / VLAN_GROUP_ARRAY_PART_LEN]; + array[vlan_id % VLAN_GROUP_ARRAY_PART_LEN] = dev; +} + +/* Must be invoked with rcu_read_lock or with RTNL. */ +static inline struct net_device *vlan_find_dev(struct net_device *real_dev, + u16 vlan_id) +{ + struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp); + + if (grp) + return vlan_group_get_device(grp, vlan_id); + + return NULL; +} + /* found in vlan_dev.c */ void vlan_dev_set_ingress_priority(const struct net_device *dev, u32 skb_prio, u16 vlan_prio); diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 41495dc2a4c..5f27f8e3025 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -23,6 +23,31 @@ bool vlan_do_receive(struct sk_buff **skbp) return false; skb->dev = vlan_dev; + if (skb->pkt_type == PACKET_OTHERHOST) { + /* Our lower layer thinks this is not local, let's make sure. + * This allows the VLAN to have a different MAC than the + * underlying device, and still route correctly. */ + if (!compare_ether_addr(eth_hdr(skb)->h_dest, + vlan_dev->dev_addr)) + skb->pkt_type = PACKET_HOST; + } + + if (!(vlan_dev_info(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) { + unsigned int offset = skb->data - skb_mac_header(skb); + + /* + * vlan_insert_tag expect skb->data pointing to mac header. + * So change skb->data before calling it and change back to + * original position later + */ + skb_push(skb, offset); + skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci); + if (!skb) + return false; + skb_pull(skb, offset + VLAN_HLEN); + skb_reset_mac_len(skb); + } + skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci); skb->vlan_tci = 0; @@ -31,27 +56,34 @@ bool vlan_do_receive(struct sk_buff **skbp) u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; rx_stats->rx_bytes += skb->len; - - switch (skb->pkt_type) { - case PACKET_BROADCAST: - break; - case PACKET_MULTICAST: + if (skb->pkt_type == PACKET_MULTICAST) rx_stats->rx_multicast++; - break; - case PACKET_OTHERHOST: - /* Our lower layer thinks this is not local, let's make sure. - * This allows the VLAN to have a different MAC than the - * underlying device, and still route correctly. */ - if (!compare_ether_addr(eth_hdr(skb)->h_dest, - vlan_dev->dev_addr)) - skb->pkt_type = PACKET_HOST; - break; - } u64_stats_update_end(&rx_stats->syncp); return true; } +/* Must be invoked with rcu_read_lock or with RTNL. */ +struct net_device *__vlan_find_dev_deep(struct net_device *real_dev, + u16 vlan_id) +{ + struct vlan_group *grp = rcu_dereference_rtnl(real_dev->vlgrp); + + if (grp) { + return vlan_group_get_device(grp, vlan_id); + } else { + /* + * Bonding slaves do not have grp assigned to themselves. + * Grp is assigned to bonding master instead. + */ + if (netif_is_bond_slave(real_dev)) + return __vlan_find_dev_deep(real_dev->master, vlan_id); + } + + return NULL; +} +EXPORT_SYMBOL(__vlan_find_dev_deep); + struct net_device *vlan_dev_real_dev(const struct net_device *dev) { return vlan_dev_info(dev)->real_dev; @@ -64,43 +96,13 @@ u16 vlan_dev_vlan_id(const struct net_device *dev) } EXPORT_SYMBOL(vlan_dev_vlan_id); -/* VLAN rx hw acceleration helper. This acts like netif_{rx,receive_skb}(). */ -int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp, - u16 vlan_tci, int polling) +static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) { - __vlan_hwaccel_put_tag(skb, vlan_tci); - return polling ? netif_receive_skb(skb) : netif_rx(skb); -} -EXPORT_SYMBOL(__vlan_hwaccel_rx); - -gro_result_t vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci, struct sk_buff *skb) -{ - __vlan_hwaccel_put_tag(skb, vlan_tci); - return napi_gro_receive(napi, skb); -} -EXPORT_SYMBOL(vlan_gro_receive); - -gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, - unsigned int vlan_tci) -{ - __vlan_hwaccel_put_tag(napi->skb, vlan_tci); - return napi_gro_frags(napi); -} -EXPORT_SYMBOL(vlan_gro_frags); - -static struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) -{ - if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) { - if (skb_cow(skb, skb_headroom(skb)) < 0) - skb = NULL; - if (skb) { - /* Lifted from Gleb's VLAN code... */ - memmove(skb->data - ETH_HLEN, - skb->data - VLAN_ETH_HLEN, 12); - skb->mac_header += VLAN_HLEN; - } - } + if (skb_cow(skb, skb_headroom(skb)) < 0) + return NULL; + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + skb_reset_mac_len(skb); return skb; } @@ -161,7 +163,7 @@ struct sk_buff *vlan_untag(struct sk_buff *skb) skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); - skb = vlan_check_reorder_header(skb); + skb = vlan_reorder_header(skb); if (unlikely(!skb)) goto err_free; diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 7ea5cf9ea08..934e221c1d0 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -20,6 +20,8 @@ * 2 of the License, or (at your option) any later version. */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/slab.h> #include <linux/skbuff.h> @@ -55,7 +57,7 @@ static int vlan_dev_rebuild_header(struct sk_buff *skb) return arp_find(veth->h_dest, skb); #endif default: - pr_debug("%s: unable to resolve type %X addresses.\n", + pr_debug("%s: unable to resolve type %X addresses\n", dev->name, ntohs(veth->h_vlan_encapsulated_proto)); memcpy(veth->h_source, dev->dev_addr, ETH_ALEN); @@ -528,7 +530,11 @@ static int vlan_dev_init(struct net_device *dev) (1<<__LINK_STATE_DORMANT))) | (1<<__LINK_STATE_PRESENT); - dev->hw_features = NETIF_F_ALL_TX_OFFLOADS; + dev->hw_features = NETIF_F_ALL_CSUM | NETIF_F_SG | + NETIF_F_FRAGLIST | NETIF_F_ALL_TSO | + NETIF_F_HIGHDMA | NETIF_F_SCTP_CSUM | + NETIF_F_ALL_FCOE; + dev->features |= real_dev->vlan_features | NETIF_F_LLTX; dev->gso_max_size = real_dev->gso_max_size; @@ -586,9 +592,13 @@ static void vlan_dev_uninit(struct net_device *dev) static u32 vlan_dev_fix_features(struct net_device *dev, u32 features) { struct net_device *real_dev = vlan_dev_info(dev)->real_dev; + u32 old_features = features; features &= real_dev->features; features &= real_dev->vlan_features; + + features |= old_features & NETIF_F_SOFT_FEATURES; + if (dev_ethtool_get_rx_csum(real_dev)) features |= NETIF_F_RXCSUM; features |= NETIF_F_LLTX; diff --git a/net/8021q/vlanproc.c b/net/8021q/vlanproc.c index d940c49d168..d34b6daf893 100644 --- a/net/8021q/vlanproc.c +++ b/net/8021q/vlanproc.c @@ -17,6 +17,8 @@ * Jan 20, 1998 Ben Greear Initial Version *****************************************************************************/ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/module.h> #include <linux/errno.h> #include <linux/kernel.h> @@ -155,7 +157,7 @@ int __net_init vlan_proc_init(struct net *net) return 0; err: - pr_err("%s: can't create entry in proc filesystem!\n", __func__); + pr_err("can't create entry in proc filesystem!\n"); vlan_proc_cleanup(net); return -ENOBUFS; } @@ -229,7 +231,7 @@ static void *vlan_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; - dev = (struct net_device *)v; + dev = v; if (v == SEQ_START_TOKEN) dev = net_device_entry(&net->dev_base_head); diff --git a/net/Kconfig b/net/Kconfig index 878151c772c..a0731484423 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -322,6 +322,7 @@ source "net/rfkill/Kconfig" source "net/9p/Kconfig" source "net/caif/Kconfig" source "net/ceph/Kconfig" +source "net/nfc/Kconfig" endif # if NET diff --git a/net/Makefile b/net/Makefile index a51d9465e62..acdde4950de 100644 --- a/net/Makefile +++ b/net/Makefile @@ -68,3 +68,4 @@ obj-$(CONFIG_WIMAX) += wimax/ obj-$(CONFIG_DNS_RESOLVER) += dns_resolver/ obj-$(CONFIG_CEPH_LIB) += ceph/ obj-$(CONFIG_BATMAN_ADV) += batman-adv/ +obj-$(CONFIG_NFC) += nfc/ diff --git a/net/TUNABLE b/net/TUNABLE deleted file mode 100644 index 9913211f07a..00000000000 --- a/net/TUNABLE +++ /dev/null @@ -1,50 +0,0 @@ -The following parameters should be tunable at compile time. Some of them -exist as sysctls too. - -This is far from complete - -Item Description ----------------------------------------------------------------------------- -MAX_LINKS Maximum number of netlink minor devices. (1-32) -RIF_TABLE_SIZE Token ring RIF cache size (tunable) -AARP_HASH_SIZE Size of Appletalk hash table (tunable) -AX25_DEF_T1 AX.25 parameters. These are all tunable via -AX25_DEF_T2 SIOCAX25SETPARMS -AX25_DEF_T3 T1-T3,N2 have the meanings in the specification -AX25_DEF_N2 -AX25_DEF_AXDEFMODE 8 = normal 128 is PE1CHL extended -AX25_DEF_IPDEFMODE 'D' - datagram 'V' - virtual connection -AX25_DEF_BACKOFF 'E'xponential 'L'inear -AX25_DEF_NETROM Allow netrom 1=Y -AX25_DF_TEXT Allow PID=Text 1=Y -AX25_DEF_WINDOW Window for normal mode -AX25_DEF_EWINDOW Window for PE1CHL mode -AX25_DEF_DIGI 1 for inband 2 for cross band 3 for both -AX25_DEF_CONMODE Allow connected modes 1=Yes -AX25_ROUTE_MAX AX.25 route cache size - no currently tunable -Unnamed (16) Number of protocol hash slots (tunable) -DEV_NUMBUFFS Number of priority levels (not easily tunable) -Unnamed (300) Maximum packet backlog queue (tunable) -MAX_IOVEC Maximum number of iovecs in a message (tunable) -MIN_WINDOW Offered minimum window (tunable) -MAX_WINDOW Offered maximum window (tunable) -MAX_HEADER Largest physical header (tunable) -MAX_ADDR_LEN Largest physical address (tunable) -SOCK_ARRAY_SIZE IP socket array hash size (tunable) -IP_MAX_MEMBERSHIPS Largest number of groups per socket (BSD style) (tunable) -16 Hard coded constant for amount of room allowed for - cache align and faster forwarding (tunable) -IP_FRAG_TIME Time we hold a fragment for. (tunable) -PORT_MASQ_BEGIN First port reserved for masquerade (tunable) -PORT_MASQ_END Last port used for masquerade (tunable) -MASQUERADE_EXPIRE_TCP_FIN Time we keep a masquerade for after a FIN -MASQUERADE_EXPIRE_UDP Time we keep a UDP masquerade for (tunable) -MAXVIFS Maximum mrouted vifs (1-32) -MFC_LINES Lines in the multicast router cache (tunable) - -NetROM parameters are tunable via an ioctl passing a struct - -4000 Size a Unix domain socket malloc falls back to - (tunable) should be 8K - a bit for 8K machines like - the ALPHA - diff --git a/net/appletalk/aarp.c b/net/appletalk/aarp.c index 50dce798132..1acc69576df 100644 --- a/net/appletalk/aarp.c +++ b/net/appletalk/aarp.c @@ -779,87 +779,87 @@ static int aarp_rcv(struct sk_buff *skb, struct net_device *dev, } switch (function) { - case AARP_REPLY: - if (!unresolved_count) /* Speed up */ - break; - - /* Find the entry. */ - a = __aarp_find_entry(unresolved[hash], dev, &sa); - if (!a || dev != a->dev) - break; + case AARP_REPLY: + if (!unresolved_count) /* Speed up */ + break; - /* We can fill one in - this is good. */ - memcpy(a->hwaddr, ea->hw_src, ETH_ALEN); - __aarp_resolved(&unresolved[hash], a, hash); - if (!unresolved_count) - mod_timer(&aarp_timer, - jiffies + sysctl_aarp_expiry_time); + /* Find the entry. */ + a = __aarp_find_entry(unresolved[hash], dev, &sa); + if (!a || dev != a->dev) break; - case AARP_REQUEST: - case AARP_PROBE: + /* We can fill one in - this is good. */ + memcpy(a->hwaddr, ea->hw_src, ETH_ALEN); + __aarp_resolved(&unresolved[hash], a, hash); + if (!unresolved_count) + mod_timer(&aarp_timer, + jiffies + sysctl_aarp_expiry_time); + break; + + case AARP_REQUEST: + case AARP_PROBE: + + /* + * If it is my address set ma to my address and reply. + * We can treat probe and request the same. Probe + * simply means we shouldn't cache the querying host, + * as in a probe they are proposing an address not + * using one. + * + * Support for proxy-AARP added. We check if the + * address is one of our proxies before we toss the + * packet out. + */ + + sa.s_node = ea->pa_dst_node; + sa.s_net = ea->pa_dst_net; + + /* See if we have a matching proxy. */ + ma = __aarp_proxy_find(dev, &sa); + if (!ma) + ma = &ifa->address; + else { /* We need to make a copy of the entry. */ + da.s_node = sa.s_node; + da.s_net = sa.s_net; + ma = &da; + } + if (function == AARP_PROBE) { /* - * If it is my address set ma to my address and reply. - * We can treat probe and request the same. Probe - * simply means we shouldn't cache the querying host, - * as in a probe they are proposing an address not - * using one. - * - * Support for proxy-AARP added. We check if the - * address is one of our proxies before we toss the - * packet out. + * A probe implies someone trying to get an + * address. So as a precaution flush any + * entries we have for this address. */ + a = __aarp_find_entry(resolved[sa.s_node % + (AARP_HASH_SIZE - 1)], + skb->dev, &sa); - sa.s_node = ea->pa_dst_node; - sa.s_net = ea->pa_dst_net; - - /* See if we have a matching proxy. */ - ma = __aarp_proxy_find(dev, &sa); - if (!ma) - ma = &ifa->address; - else { /* We need to make a copy of the entry. */ - da.s_node = sa.s_node; - da.s_net = sa.s_net; - ma = &da; - } - - if (function == AARP_PROBE) { - /* - * A probe implies someone trying to get an - * address. So as a precaution flush any - * entries we have for this address. - */ - a = __aarp_find_entry(resolved[sa.s_node % - (AARP_HASH_SIZE - 1)], - skb->dev, &sa); - - /* - * Make it expire next tick - that avoids us - * getting into a probe/flush/learn/probe/ - * flush/learn cycle during probing of a slow - * to respond host addr. - */ - if (a) { - a->expires_at = jiffies - 1; - mod_timer(&aarp_timer, jiffies + - sysctl_aarp_tick_time); - } + /* + * Make it expire next tick - that avoids us + * getting into a probe/flush/learn/probe/ + * flush/learn cycle during probing of a slow + * to respond host addr. + */ + if (a) { + a->expires_at = jiffies - 1; + mod_timer(&aarp_timer, jiffies + + sysctl_aarp_tick_time); } + } - if (sa.s_node != ma->s_node) - break; + if (sa.s_node != ma->s_node) + break; - if (sa.s_net && ma->s_net && sa.s_net != ma->s_net) - break; + if (sa.s_net && ma->s_net && sa.s_net != ma->s_net) + break; - sa.s_node = ea->pa_src_node; - sa.s_net = ea->pa_src_net; + sa.s_node = ea->pa_src_node; + sa.s_net = ea->pa_src_net; - /* aarp_my_address has found the address to use for us. - */ - aarp_send_reply(dev, ma, &sa, ea->hw_src); - break; + /* aarp_my_address has found the address to use for us. + */ + aarp_send_reply(dev, ma, &sa, ea->hw_src); + break; } unlock: diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index 956a5302002..b1fe7c35e8d 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -684,192 +684,192 @@ static int atif_ioctl(int cmd, void __user *arg) atif = atalk_find_dev(dev); switch (cmd) { - case SIOCSIFADDR: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (sa->sat_family != AF_APPLETALK) - return -EINVAL; - if (dev->type != ARPHRD_ETHER && - dev->type != ARPHRD_LOOPBACK && - dev->type != ARPHRD_LOCALTLK && - dev->type != ARPHRD_PPP) - return -EPROTONOSUPPORT; - - nr = (struct atalk_netrange *)&sa->sat_zero[0]; - add_route = 1; - - /* - * if this is a point-to-point iface, and we already - * have an iface for this AppleTalk address, then we - * should not add a route - */ - if ((dev->flags & IFF_POINTOPOINT) && - atalk_find_interface(sa->sat_addr.s_net, - sa->sat_addr.s_node)) { - printk(KERN_DEBUG "AppleTalk: point-to-point " - "interface added with " - "existing address\n"); - add_route = 0; - } + case SIOCSIFADDR: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + if (dev->type != ARPHRD_ETHER && + dev->type != ARPHRD_LOOPBACK && + dev->type != ARPHRD_LOCALTLK && + dev->type != ARPHRD_PPP) + return -EPROTONOSUPPORT; + + nr = (struct atalk_netrange *)&sa->sat_zero[0]; + add_route = 1; - /* - * Phase 1 is fine on LocalTalk but we don't do - * EtherTalk phase 1. Anyone wanting to add it go ahead. - */ - if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) - return -EPROTONOSUPPORT; - if (sa->sat_addr.s_node == ATADDR_BCAST || - sa->sat_addr.s_node == 254) - return -EINVAL; - if (atif) { - /* Already setting address */ - if (atif->status & ATIF_PROBE) - return -EBUSY; - - atif->address.s_net = sa->sat_addr.s_net; - atif->address.s_node = sa->sat_addr.s_node; - atrtr_device_down(dev); /* Flush old routes */ - } else { - atif = atif_add_device(dev, &sa->sat_addr); - if (!atif) - return -ENOMEM; - } - atif->nets = *nr; - - /* - * Check if the chosen address is used. If so we - * error and atalkd will try another. - */ - - if (!(dev->flags & IFF_LOOPBACK) && - !(dev->flags & IFF_POINTOPOINT) && - atif_probe_device(atif) < 0) { - atif_drop_device(dev); - return -EADDRINUSE; - } - - /* Hey it worked - add the direct routes */ - sa = (struct sockaddr_at *)&rtdef.rt_gateway; - sa->sat_family = AF_APPLETALK; - sa->sat_addr.s_net = atif->address.s_net; - sa->sat_addr.s_node = atif->address.s_node; - sa = (struct sockaddr_at *)&rtdef.rt_dst; - rtdef.rt_flags = RTF_UP; - sa->sat_family = AF_APPLETALK; - sa->sat_addr.s_node = ATADDR_ANYNODE; - if (dev->flags & IFF_LOOPBACK || - dev->flags & IFF_POINTOPOINT) - rtdef.rt_flags |= RTF_HOST; - - /* Routerless initial state */ - if (nr->nr_firstnet == htons(0) && - nr->nr_lastnet == htons(0xFFFE)) { - sa->sat_addr.s_net = atif->address.s_net; - atrtr_create(&rtdef, dev); - atrtr_set_default(dev); - } else { - limit = ntohs(nr->nr_lastnet); - if (limit - ntohs(nr->nr_firstnet) > 4096) { - printk(KERN_WARNING "Too many routes/" - "iface.\n"); - return -EINVAL; - } - if (add_route) - for (ct = ntohs(nr->nr_firstnet); - ct <= limit; ct++) { - sa->sat_addr.s_net = htons(ct); - atrtr_create(&rtdef, dev); - } - } - dev_mc_add_global(dev, aarp_mcast); - return 0; + /* + * if this is a point-to-point iface, and we already + * have an iface for this AppleTalk address, then we + * should not add a route + */ + if ((dev->flags & IFF_POINTOPOINT) && + atalk_find_interface(sa->sat_addr.s_net, + sa->sat_addr.s_node)) { + printk(KERN_DEBUG "AppleTalk: point-to-point " + "interface added with " + "existing address\n"); + add_route = 0; + } - case SIOCGIFADDR: + /* + * Phase 1 is fine on LocalTalk but we don't do + * EtherTalk phase 1. Anyone wanting to add it go ahead. + */ + if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) + return -EPROTONOSUPPORT; + if (sa->sat_addr.s_node == ATADDR_BCAST || + sa->sat_addr.s_node == 254) + return -EINVAL; + if (atif) { + /* Already setting address */ + if (atif->status & ATIF_PROBE) + return -EBUSY; + + atif->address.s_net = sa->sat_addr.s_net; + atif->address.s_node = sa->sat_addr.s_node; + atrtr_device_down(dev); /* Flush old routes */ + } else { + atif = atif_add_device(dev, &sa->sat_addr); if (!atif) - return -EADDRNOTAVAIL; + return -ENOMEM; + } + atif->nets = *nr; - sa->sat_family = AF_APPLETALK; - sa->sat_addr = atif->address; - break; + /* + * Check if the chosen address is used. If so we + * error and atalkd will try another. + */ - case SIOCGIFBRDADDR: - if (!atif) - return -EADDRNOTAVAIL; + if (!(dev->flags & IFF_LOOPBACK) && + !(dev->flags & IFF_POINTOPOINT) && + atif_probe_device(atif) < 0) { + atif_drop_device(dev); + return -EADDRINUSE; + } - sa->sat_family = AF_APPLETALK; + /* Hey it worked - add the direct routes */ + sa = (struct sockaddr_at *)&rtdef.rt_gateway; + sa->sat_family = AF_APPLETALK; + sa->sat_addr.s_net = atif->address.s_net; + sa->sat_addr.s_node = atif->address.s_node; + sa = (struct sockaddr_at *)&rtdef.rt_dst; + rtdef.rt_flags = RTF_UP; + sa->sat_family = AF_APPLETALK; + sa->sat_addr.s_node = ATADDR_ANYNODE; + if (dev->flags & IFF_LOOPBACK || + dev->flags & IFF_POINTOPOINT) + rtdef.rt_flags |= RTF_HOST; + + /* Routerless initial state */ + if (nr->nr_firstnet == htons(0) && + nr->nr_lastnet == htons(0xFFFE)) { sa->sat_addr.s_net = atif->address.s_net; - sa->sat_addr.s_node = ATADDR_BCAST; - break; - - case SIOCATALKDIFADDR: - case SIOCDIFADDR: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (sa->sat_family != AF_APPLETALK) + atrtr_create(&rtdef, dev); + atrtr_set_default(dev); + } else { + limit = ntohs(nr->nr_lastnet); + if (limit - ntohs(nr->nr_firstnet) > 4096) { + printk(KERN_WARNING "Too many routes/" + "iface.\n"); return -EINVAL; - atalk_dev_down(dev); - break; - - case SIOCSARP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (sa->sat_family != AF_APPLETALK) - return -EINVAL; - /* - * for now, we only support proxy AARP on ELAP; - * we should be able to do it for LocalTalk, too. - */ - if (dev->type != ARPHRD_ETHER) - return -EPROTONOSUPPORT; - - /* - * atif points to the current interface on this network; - * we aren't concerned about its current status (at - * least for now), but it has all the settings about - * the network we're going to probe. Consequently, it - * must exist. - */ - if (!atif) - return -EADDRNOTAVAIL; + } + if (add_route) + for (ct = ntohs(nr->nr_firstnet); + ct <= limit; ct++) { + sa->sat_addr.s_net = htons(ct); + atrtr_create(&rtdef, dev); + } + } + dev_mc_add_global(dev, aarp_mcast); + return 0; + + case SIOCGIFADDR: + if (!atif) + return -EADDRNOTAVAIL; + + sa->sat_family = AF_APPLETALK; + sa->sat_addr = atif->address; + break; + + case SIOCGIFBRDADDR: + if (!atif) + return -EADDRNOTAVAIL; + + sa->sat_family = AF_APPLETALK; + sa->sat_addr.s_net = atif->address.s_net; + sa->sat_addr.s_node = ATADDR_BCAST; + break; + + case SIOCATALKDIFADDR: + case SIOCDIFADDR: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + atalk_dev_down(dev); + break; - nr = (struct atalk_netrange *)&(atif->nets); - /* - * Phase 1 is fine on Localtalk but we don't do - * Ethertalk phase 1. Anyone wanting to add it go ahead. - */ - if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) - return -EPROTONOSUPPORT; + case SIOCSARP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + /* + * for now, we only support proxy AARP on ELAP; + * we should be able to do it for LocalTalk, too. + */ + if (dev->type != ARPHRD_ETHER) + return -EPROTONOSUPPORT; - if (sa->sat_addr.s_node == ATADDR_BCAST || - sa->sat_addr.s_node == 254) - return -EINVAL; + /* + * atif points to the current interface on this network; + * we aren't concerned about its current status (at + * least for now), but it has all the settings about + * the network we're going to probe. Consequently, it + * must exist. + */ + if (!atif) + return -EADDRNOTAVAIL; - /* - * Check if the chosen address is used. If so we - * error and ATCP will try another. - */ - if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0) - return -EADDRINUSE; + nr = (struct atalk_netrange *)&(atif->nets); + /* + * Phase 1 is fine on Localtalk but we don't do + * Ethertalk phase 1. Anyone wanting to add it go ahead. + */ + if (dev->type == ARPHRD_ETHER && nr->nr_phase != 2) + return -EPROTONOSUPPORT; - /* - * We now have an address on the local network, and - * the AARP code will defend it for us until we take it - * down. We don't set up any routes right now, because - * ATCP will install them manually via SIOCADDRT. - */ - break; + if (sa->sat_addr.s_node == ATADDR_BCAST || + sa->sat_addr.s_node == 254) + return -EINVAL; - case SIOCDARP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (sa->sat_family != AF_APPLETALK) - return -EINVAL; - if (!atif) - return -EADDRNOTAVAIL; + /* + * Check if the chosen address is used. If so we + * error and ATCP will try another. + */ + if (atif_proxy_probe_device(atif, &(sa->sat_addr)) < 0) + return -EADDRINUSE; - /* give to aarp module to remove proxy entry */ - aarp_proxy_remove(atif->dev, &(sa->sat_addr)); - return 0; + /* + * We now have an address on the local network, and + * the AARP code will defend it for us until we take it + * down. We don't set up any routes right now, because + * ATCP will install them manually via SIOCADDRT. + */ + break; + + case SIOCDARP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (sa->sat_family != AF_APPLETALK) + return -EINVAL; + if (!atif) + return -EADDRNOTAVAIL; + + /* give to aarp module to remove proxy entry */ + aarp_proxy_remove(atif->dev, &(sa->sat_addr)); + return 0; } return copy_to_user(arg, &atreq, sizeof(atreq)) ? -EFAULT : 0; @@ -884,25 +884,25 @@ static int atrtr_ioctl(unsigned int cmd, void __user *arg) return -EFAULT; switch (cmd) { - case SIOCDELRT: - if (rt.rt_dst.sa_family != AF_APPLETALK) - return -EINVAL; - return atrtr_delete(&((struct sockaddr_at *) - &rt.rt_dst)->sat_addr); - - case SIOCADDRT: { - struct net_device *dev = NULL; - if (rt.rt_dev) { - char name[IFNAMSIZ]; - if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1)) - return -EFAULT; - name[IFNAMSIZ-1] = '\0'; - dev = __dev_get_by_name(&init_net, name); - if (!dev) - return -ENODEV; - } - return atrtr_create(&rt, dev); + case SIOCDELRT: + if (rt.rt_dst.sa_family != AF_APPLETALK) + return -EINVAL; + return atrtr_delete(&((struct sockaddr_at *) + &rt.rt_dst)->sat_addr); + + case SIOCADDRT: { + struct net_device *dev = NULL; + if (rt.rt_dev) { + char name[IFNAMSIZ]; + if (copy_from_user(name, rt.rt_dev, IFNAMSIZ-1)) + return -EFAULT; + name[IFNAMSIZ-1] = '\0'; + dev = __dev_get_by_name(&init_net, name); + if (!dev) + return -ENODEV; } + return atrtr_create(&rt, dev); + } } return -EINVAL; } diff --git a/net/atm/clip.c b/net/atm/clip.c index 1d4be60e139..4bc8c67ecb1 100644 --- a/net/atm/clip.c +++ b/net/atm/clip.c @@ -271,10 +271,8 @@ static const struct neigh_ops clip_neigh_ops = { .family = AF_INET, .solicit = clip_neigh_solicit, .error_report = clip_neigh_error, - .output = dev_queue_xmit, - .connected_output = dev_queue_xmit, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, + .output = neigh_direct_output, + .connected_output = neigh_direct_output, }; static int clip_constructor(struct neighbour *neigh) @@ -364,33 +362,37 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct clip_priv *clip_priv = PRIV(dev); + struct dst_entry *dst = skb_dst(skb); struct atmarp_entry *entry; + struct neighbour *n; struct atm_vcc *vcc; int old; unsigned long flags; pr_debug("(skb %p)\n", skb); - if (!skb_dst(skb)) { + if (!dst) { pr_err("skb_dst(skb) == NULL\n"); dev_kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } - if (!skb_dst(skb)->neighbour) { + n = dst_get_neighbour(dst); + if (!n) { #if 0 - skb_dst(skb)->neighbour = clip_find_neighbour(skb_dst(skb), 1); - if (!skb_dst(skb)->neighbour) { + n = clip_find_neighbour(skb_dst(skb), 1); + if (!n) { dev_kfree_skb(skb); /* lost that one */ dev->stats.tx_dropped++; return 0; } + dst_set_neighbour(dst, n); #endif pr_err("NO NEIGHBOUR !\n"); dev_kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } - entry = NEIGH2ENTRY(skb_dst(skb)->neighbour); + entry = NEIGH2ENTRY(n); if (!entry->vccs) { if (time_after(jiffies, entry->expires)) { /* should be resolved */ @@ -407,7 +409,7 @@ static netdev_tx_t clip_start_xmit(struct sk_buff *skb, } pr_debug("neigh %p, vccs %p\n", entry, entry->vccs); ATM_SKB(skb)->vcc = vcc = entry->vccs->vcc; - pr_debug("using neighbour %p, vcc %p\n", skb_dst(skb)->neighbour, vcc); + pr_debug("using neighbour %p, vcc %p\n", n, vcc); if (entry->vccs->encap) { void *here; diff --git a/net/atm/mpc.c b/net/atm/mpc.c index 3ccca42e6f9..aa972409f09 100644 --- a/net/atm/mpc.c +++ b/net/atm/mpc.c @@ -1005,7 +1005,7 @@ static int mpoa_event_listener(struct notifier_block *mpoa_notifier, struct mpoa_client *mpc; struct lec_priv *priv; - dev = (struct net_device *)dev_ptr; + dev = dev_ptr; if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c index e9aced0ec56..db4a11c61d1 100644 --- a/net/atm/pppoatm.c +++ b/net/atm/pppoatm.c @@ -37,6 +37,7 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/interrupt.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <linux/atm.h> diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index 6c051ad833e..2b68d068eaf 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -5,6 +5,7 @@ config BATMAN_ADV tristate "B.A.T.M.A.N. Advanced Meshing Protocol" depends on NET + select CRC16 default n ---help--- diff --git a/net/batman-adv/aggregation.c b/net/batman-adv/aggregation.c index a8c32030527..69467fe71ff 100644 --- a/net/batman-adv/aggregation.c +++ b/net/batman-adv/aggregation.c @@ -20,28 +20,26 @@ */ #include "main.h" +#include "translation-table.h" #include "aggregation.h" #include "send.h" #include "routing.h" #include "hard-interface.h" -/* calculate the size of the tt information for a given packet */ -static int tt_len(struct batman_packet *batman_packet) -{ - return batman_packet->num_tt * ETH_ALEN; -} - /* return true if new_packet can be aggregated with forw_packet */ -static bool can_aggregate_with(struct batman_packet *new_batman_packet, +static bool can_aggregate_with(const struct batman_packet *new_batman_packet, + struct bat_priv *bat_priv, int packet_len, unsigned long send_time, bool directlink, - struct hard_iface *if_incoming, - struct forw_packet *forw_packet) + const struct hard_iface *if_incoming, + const struct forw_packet *forw_packet) { struct batman_packet *batman_packet = (struct batman_packet *)forw_packet->skb->data; int aggregated_bytes = forw_packet->packet_len + packet_len; + struct hard_iface *primary_if = NULL; + bool res = false; /** * we can aggregate the current packet to this aggregated packet @@ -66,6 +64,10 @@ static bool can_aggregate_with(struct batman_packet *new_batman_packet, * packet */ + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + /* packets without direct link flag and high TTL * are flooded through the net */ if ((!directlink) && @@ -75,8 +77,10 @@ static bool can_aggregate_with(struct batman_packet *new_batman_packet, /* own packets originating non-primary * interfaces leave only that interface */ ((!forw_packet->own) || - (forw_packet->if_incoming->if_num == 0))) - return true; + (forw_packet->if_incoming == primary_if))) { + res = true; + goto out; + } /* if the incoming packet is sent via this one * interface only - we still can aggregate */ @@ -89,16 +93,22 @@ static bool can_aggregate_with(struct batman_packet *new_batman_packet, * (= secondary interface packets in general) */ (batman_packet->flags & DIRECTLINK || (forw_packet->own && - forw_packet->if_incoming->if_num != 0))) - return true; + forw_packet->if_incoming != primary_if))) { + res = true; + goto out; + } } - return false; +out: + if (primary_if) + hardif_free_ref(primary_if); + return res; } /* create a new aggregated packet and add this packet to it */ -static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, - unsigned long send_time, bool direct_link, +static void new_aggregated_packet(const unsigned char *packet_buff, + int packet_len, unsigned long send_time, + bool direct_link, struct hard_iface *if_incoming, int own_packet) { @@ -118,7 +128,7 @@ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, } } - forw_packet_aggr = kmalloc(sizeof(struct forw_packet), GFP_ATOMIC); + forw_packet_aggr = kmalloc(sizeof(*forw_packet_aggr), GFP_ATOMIC); if (!forw_packet_aggr) { if (!own_packet) atomic_inc(&bat_priv->batman_queue_left); @@ -150,7 +160,7 @@ static void new_aggregated_packet(unsigned char *packet_buff, int packet_len, forw_packet_aggr->own = own_packet; forw_packet_aggr->if_incoming = if_incoming; forw_packet_aggr->num_packets = 0; - forw_packet_aggr->direct_link_flags = 0; + forw_packet_aggr->direct_link_flags = NO_FLAGS; forw_packet_aggr->send_time = send_time; /* save packet direct link flag status */ @@ -176,8 +186,7 @@ out: /* aggregate a new packet into the existing aggregation */ static void aggregate(struct forw_packet *forw_packet_aggr, - unsigned char *packet_buff, - int packet_len, + const unsigned char *packet_buff, int packet_len, bool direct_link) { unsigned char *skb_buff; @@ -195,7 +204,7 @@ static void aggregate(struct forw_packet *forw_packet_aggr, void add_bat_packet_to_list(struct bat_priv *bat_priv, unsigned char *packet_buff, int packet_len, - struct hard_iface *if_incoming, char own_packet, + struct hard_iface *if_incoming, int own_packet, unsigned long send_time) { /** @@ -215,6 +224,7 @@ void add_bat_packet_to_list(struct bat_priv *bat_priv, hlist_for_each_entry(forw_packet_pos, tmp_node, &bat_priv->forw_bat_list, list) { if (can_aggregate_with(batman_packet, + bat_priv, packet_len, send_time, direct_link, @@ -253,8 +263,9 @@ void add_bat_packet_to_list(struct bat_priv *bat_priv, } /* unpack the aggregated packets and process them one by one */ -void receive_aggr_bat_packet(struct ethhdr *ethhdr, unsigned char *packet_buff, - int packet_len, struct hard_iface *if_incoming) +void receive_aggr_bat_packet(const struct ethhdr *ethhdr, + unsigned char *packet_buff, int packet_len, + struct hard_iface *if_incoming) { struct batman_packet *batman_packet; int buff_pos = 0; @@ -263,18 +274,20 @@ void receive_aggr_bat_packet(struct ethhdr *ethhdr, unsigned char *packet_buff, batman_packet = (struct batman_packet *)packet_buff; do { - /* network to host order for our 32bit seqno, and the - orig_interval. */ + /* network to host order for our 32bit seqno and the + orig_interval */ batman_packet->seqno = ntohl(batman_packet->seqno); + batman_packet->tt_crc = ntohs(batman_packet->tt_crc); tt_buff = packet_buff + buff_pos + BAT_PACKET_LEN; - receive_bat_packet(ethhdr, batman_packet, - tt_buff, tt_len(batman_packet), - if_incoming); - buff_pos += BAT_PACKET_LEN + tt_len(batman_packet); + receive_bat_packet(ethhdr, batman_packet, tt_buff, if_incoming); + + buff_pos += BAT_PACKET_LEN + + tt_len(batman_packet->tt_num_changes); + batman_packet = (struct batman_packet *) (packet_buff + buff_pos); } while (aggregated_packet(buff_pos, packet_len, - batman_packet->num_tt)); + batman_packet->tt_num_changes)); } diff --git a/net/batman-adv/aggregation.h b/net/batman-adv/aggregation.h index 7e6d72fbf54..216337bb841 100644 --- a/net/batman-adv/aggregation.h +++ b/net/batman-adv/aggregation.h @@ -25,9 +25,11 @@ #include "main.h" /* is there another aggregated packet here? */ -static inline int aggregated_packet(int buff_pos, int packet_len, int num_tt) +static inline int aggregated_packet(int buff_pos, int packet_len, + int tt_num_changes) { - int next_buff_pos = buff_pos + BAT_PACKET_LEN + (num_tt * ETH_ALEN); + int next_buff_pos = buff_pos + BAT_PACKET_LEN + (tt_num_changes * + sizeof(struct tt_change)); return (next_buff_pos <= packet_len) && (next_buff_pos <= MAX_AGGREGATION_BYTES); @@ -35,9 +37,10 @@ static inline int aggregated_packet(int buff_pos, int packet_len, int num_tt) void add_bat_packet_to_list(struct bat_priv *bat_priv, unsigned char *packet_buff, int packet_len, - struct hard_iface *if_incoming, char own_packet, + struct hard_iface *if_incoming, int own_packet, unsigned long send_time); -void receive_aggr_bat_packet(struct ethhdr *ethhdr, unsigned char *packet_buff, - int packet_len, struct hard_iface *if_incoming); +void receive_aggr_bat_packet(const struct ethhdr *ethhdr, + unsigned char *packet_buff, int packet_len, + struct hard_iface *if_incoming); #endif /* _NET_BATMAN_ADV_AGGREGATION_H_ */ diff --git a/net/batman-adv/bat_debugfs.c b/net/batman-adv/bat_debugfs.c index abaeec5f624..d0af9bf69e4 100644 --- a/net/batman-adv/bat_debugfs.c +++ b/net/batman-adv/bat_debugfs.c @@ -50,7 +50,8 @@ static void emit_log_char(struct debug_log *debug_log, char c) debug_log->log_start = debug_log->log_end - log_buff_len; } -static int fdebug_log(struct debug_log *debug_log, char *fmt, ...) +__printf(2, 3) +static int fdebug_log(struct debug_log *debug_log, const char *fmt, ...) { va_list args; static char debug_log_buf[256]; @@ -74,14 +75,14 @@ static int fdebug_log(struct debug_log *debug_log, char *fmt, ...) return 0; } -int debug_log(struct bat_priv *bat_priv, char *fmt, ...) +int debug_log(struct bat_priv *bat_priv, const char *fmt, ...) { va_list args; char tmp_log_buf[256]; va_start(args, fmt); vscnprintf(tmp_log_buf, sizeof(tmp_log_buf), fmt, args); - fdebug_log(bat_priv->debug_log, "[%10u] %s", + fdebug_log(bat_priv->debug_log, "[%10lu] %s", (jiffies / HZ), tmp_log_buf); va_end(args); @@ -114,7 +115,7 @@ static ssize_t log_read(struct file *file, char __user *buf, !(debug_log->log_end - debug_log->log_start)) return -EAGAIN; - if ((!buf) || (count < 0)) + if (!buf) return -EINVAL; if (count == 0) @@ -184,7 +185,7 @@ static int debug_log_setup(struct bat_priv *bat_priv) if (!bat_priv->debug_dir) goto err; - bat_priv->debug_log = kzalloc(sizeof(struct debug_log), GFP_ATOMIC); + bat_priv->debug_log = kzalloc(sizeof(*bat_priv->debug_log), GFP_ATOMIC); if (!bat_priv->debug_log) goto err; diff --git a/net/batman-adv/bat_sysfs.c b/net/batman-adv/bat_sysfs.c index 497a0700cc3..cd15deba60a 100644 --- a/net/batman-adv/bat_sysfs.c +++ b/net/batman-adv/bat_sysfs.c @@ -28,9 +28,31 @@ #include "gateway_client.h" #include "vis.h" -#define to_dev(obj) container_of(obj, struct device, kobj) -#define kobj_to_netdev(obj) to_net_dev(to_dev(obj->parent)) -#define kobj_to_batpriv(obj) netdev_priv(kobj_to_netdev(obj)) +static struct net_device *kobj_to_netdev(struct kobject *obj) +{ + struct device *dev = container_of(obj->parent, struct device, kobj); + return to_net_dev(dev); +} + +static struct bat_priv *kobj_to_batpriv(struct kobject *obj) +{ + struct net_device *net_dev = kobj_to_netdev(obj); + return netdev_priv(net_dev); +} + +#define UEV_TYPE_VAR "BATTYPE=" +#define UEV_ACTION_VAR "BATACTION=" +#define UEV_DATA_VAR "BATDATA=" + +static char *uev_action_str[] = { + "add", + "del", + "change" +}; + +static char *uev_type_str[] = { + "gw" +}; /* Use this, if you have customized show and store functions */ #define BAT_ATTR(_name, _mode, _show, _store) \ @@ -96,7 +118,7 @@ ssize_t show_##_name(struct kobject *kobj, struct attribute *attr, \ static int store_bool_attr(char *buff, size_t count, struct net_device *net_dev, - char *attr_name, atomic_t *attr) + const char *attr_name, atomic_t *attr) { int enabled = -1; @@ -138,16 +160,15 @@ static inline ssize_t __store_bool_attr(char *buff, size_t count, { int ret; - ret = store_bool_attr(buff, count, net_dev, (char *)attr->name, - attr_store); + ret = store_bool_attr(buff, count, net_dev, attr->name, attr_store); if (post_func && ret) post_func(net_dev); return ret; } -static int store_uint_attr(char *buff, size_t count, - struct net_device *net_dev, char *attr_name, +static int store_uint_attr(const char *buff, size_t count, + struct net_device *net_dev, const char *attr_name, unsigned int min, unsigned int max, atomic_t *attr) { unsigned long uint_val; @@ -183,15 +204,15 @@ static int store_uint_attr(char *buff, size_t count, return count; } -static inline ssize_t __store_uint_attr(char *buff, size_t count, +static inline ssize_t __store_uint_attr(const char *buff, size_t count, int min, int max, void (*post_func)(struct net_device *), - struct attribute *attr, + const struct attribute *attr, atomic_t *attr_store, struct net_device *net_dev) { int ret; - ret = store_uint_attr(buff, count, net_dev, (char *)attr->name, + ret = store_uint_attr(buff, count, net_dev, attr->name, min, max, attr_store); if (post_func && ret) post_func(net_dev); @@ -368,7 +389,7 @@ BAT_ATTR_UINT(gw_sel_class, S_IRUGO | S_IWUSR, 1, TQ_MAX_VALUE, static BAT_ATTR(gw_bandwidth, S_IRUGO | S_IWUSR, show_gw_bwidth, store_gw_bwidth); #ifdef CONFIG_BATMAN_ADV_DEBUG -BAT_ATTR_UINT(log_level, S_IRUGO | S_IWUSR, 0, 3, NULL); +BAT_ATTR_UINT(log_level, S_IRUGO | S_IWUSR, 0, 7, NULL); #endif static struct bat_attribute *mesh_attrs[] = { @@ -594,3 +615,60 @@ void sysfs_del_hardif(struct kobject **hardif_obj) kobject_put(*hardif_obj); *hardif_obj = NULL; } + +int throw_uevent(struct bat_priv *bat_priv, enum uev_type type, + enum uev_action action, const char *data) +{ + int ret = -1; + struct hard_iface *primary_if = NULL; + struct kobject *bat_kobj; + char *uevent_env[4] = { NULL, NULL, NULL, NULL }; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + bat_kobj = &primary_if->soft_iface->dev.kobj; + + uevent_env[0] = kmalloc(strlen(UEV_TYPE_VAR) + + strlen(uev_type_str[type]) + 1, + GFP_ATOMIC); + if (!uevent_env[0]) + goto out; + + sprintf(uevent_env[0], "%s%s", UEV_TYPE_VAR, uev_type_str[type]); + + uevent_env[1] = kmalloc(strlen(UEV_ACTION_VAR) + + strlen(uev_action_str[action]) + 1, + GFP_ATOMIC); + if (!uevent_env[1]) + goto out; + + sprintf(uevent_env[1], "%s%s", UEV_ACTION_VAR, uev_action_str[action]); + + /* If the event is DEL, ignore the data field */ + if (action != UEV_DEL) { + uevent_env[2] = kmalloc(strlen(UEV_DATA_VAR) + + strlen(data) + 1, GFP_ATOMIC); + if (!uevent_env[2]) + goto out; + + sprintf(uevent_env[2], "%s%s", UEV_DATA_VAR, data); + } + + ret = kobject_uevent_env(bat_kobj, KOBJ_CHANGE, uevent_env); +out: + kfree(uevent_env[0]); + kfree(uevent_env[1]); + kfree(uevent_env[2]); + + if (primary_if) + hardif_free_ref(primary_if); + + if (ret) + bat_dbg(DBG_BATMAN, bat_priv, "Impossible to send " + "uevent for (%s,%s,%s) event (err: %d)\n", + uev_type_str[type], uev_action_str[action], + (action == UEV_DEL ? "NULL" : data), ret); + return ret; +} diff --git a/net/batman-adv/bat_sysfs.h b/net/batman-adv/bat_sysfs.h index 02f1fa7aadf..a3f75a723c5 100644 --- a/net/batman-adv/bat_sysfs.h +++ b/net/batman-adv/bat_sysfs.h @@ -38,5 +38,7 @@ int sysfs_add_meshif(struct net_device *dev); void sysfs_del_meshif(struct net_device *dev); int sysfs_add_hardif(struct kobject **hardif_obj, struct net_device *dev); void sysfs_del_hardif(struct kobject **hardif_obj); +int throw_uevent(struct bat_priv *bat_priv, enum uev_type type, + enum uev_action action, const char *data); #endif /* _NET_BATMAN_ADV_SYSFS_H_ */ diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index ad2ca925b3e..c1f4bfc09cc 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -26,8 +26,8 @@ /* returns true if the corresponding bit in the given seq_bits indicates true * and curr_seqno is within range of last_seqno */ -uint8_t get_bit_status(unsigned long *seq_bits, uint32_t last_seqno, - uint32_t curr_seqno) +int get_bit_status(const unsigned long *seq_bits, uint32_t last_seqno, + uint32_t curr_seqno) { int32_t diff, word_offset, word_num; @@ -127,10 +127,10 @@ static void bit_reset_window(unsigned long *seq_bits) * 1 if the window was moved (either new or very old) * 0 if the window was not moved/shifted. */ -char bit_get_packet(void *priv, unsigned long *seq_bits, - int32_t seq_num_diff, int8_t set_mark) +int bit_get_packet(void *priv, unsigned long *seq_bits, + int32_t seq_num_diff, int set_mark) { - struct bat_priv *bat_priv = (struct bat_priv *)priv; + struct bat_priv *bat_priv = priv; /* sequence number is slightly older. We already got a sequence number * higher than this one, so we just mark it. */ @@ -190,7 +190,7 @@ char bit_get_packet(void *priv, unsigned long *seq_bits, /* count the hamming weight, how many good packets did we receive? just count * the 1's. */ -int bit_packet_count(unsigned long *seq_bits) +int bit_packet_count(const unsigned long *seq_bits) { int i, hamming = 0; diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 769c246d1fc..9c04422aeb0 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -26,8 +26,8 @@ /* returns true if the corresponding bit in the given seq_bits indicates true * and curr_seqno is within range of last_seqno */ -uint8_t get_bit_status(unsigned long *seq_bits, uint32_t last_seqno, - uint32_t curr_seqno); +int get_bit_status(const unsigned long *seq_bits, uint32_t last_seqno, + uint32_t curr_seqno); /* turn corresponding bit on, so we can remember that we got the packet */ void bit_mark(unsigned long *seq_bits, int32_t n); @@ -35,10 +35,10 @@ void bit_mark(unsigned long *seq_bits, int32_t n); /* receive and process one packet, returns 1 if received seq_num is considered * new, 0 if old */ -char bit_get_packet(void *priv, unsigned long *seq_bits, - int32_t seq_num_diff, int8_t set_mark); +int bit_get_packet(void *priv, unsigned long *seq_bits, + int32_t seq_num_diff, int set_mark); /* count the hamming weight, how many good packets did we receive? */ -int bit_packet_count(unsigned long *seq_bits); +int bit_packet_count(const unsigned long *seq_bits); #endif /* _NET_BATMAN_ADV_BITARRAY_H_ */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 61605a0f3f3..056180ef9e1 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -20,15 +20,22 @@ */ #include "main.h" +#include "bat_sysfs.h" #include "gateway_client.h" #include "gateway_common.h" #include "hard-interface.h" #include "originator.h" +#include "routing.h" #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/udp.h> #include <linux/if_vlan.h> +/* This is the offset of the options field in a dhcp packet starting at + * the beginning of the dhcp header */ +#define DHCP_OPTIONS_OFFSET 240 +#define DHCP_REQUEST 3 + static void gw_node_free_ref(struct gw_node *gw_node) { if (atomic_dec_and_test(&gw_node->refcount)) @@ -86,7 +93,7 @@ static void gw_select(struct bat_priv *bat_priv, struct gw_node *new_gw_node) if (new_gw_node && !atomic_inc_not_zero(&new_gw_node->refcount)) new_gw_node = NULL; - curr_gw_node = bat_priv->curr_gw; + curr_gw_node = rcu_dereference_protected(bat_priv->curr_gw, 1); rcu_assign_pointer(bat_priv->curr_gw, new_gw_node); if (curr_gw_node) @@ -97,40 +104,19 @@ static void gw_select(struct bat_priv *bat_priv, struct gw_node *new_gw_node) void gw_deselect(struct bat_priv *bat_priv) { - gw_select(bat_priv, NULL); + atomic_set(&bat_priv->gw_reselect, 1); } -void gw_election(struct bat_priv *bat_priv) +static struct gw_node *gw_get_best_gw_node(struct bat_priv *bat_priv) { - struct hlist_node *node; - struct gw_node *gw_node, *curr_gw = NULL, *curr_gw_tmp = NULL; struct neigh_node *router; - uint8_t max_tq = 0; + struct hlist_node *node; + struct gw_node *gw_node, *curr_gw = NULL; uint32_t max_gw_factor = 0, tmp_gw_factor = 0; + uint8_t max_tq = 0; int down, up; - /** - * The batman daemon checks here if we already passed a full originator - * cycle in order to make sure we don't choose the first gateway we - * hear about. This check is based on the daemon's uptime which we - * don't have. - **/ - if (atomic_read(&bat_priv->gw_mode) != GW_MODE_CLIENT) - return; - - curr_gw = gw_get_selected_gw_node(bat_priv); - if (curr_gw) - goto out; - rcu_read_lock(); - if (hlist_empty(&bat_priv->gw_list)) { - bat_dbg(DBG_BATMAN, bat_priv, - "Removing selected gateway - " - "no gateway in range\n"); - gw_deselect(bat_priv); - goto unlock; - } - hlist_for_each_entry_rcu(gw_node, node, &bat_priv->gw_list, list) { if (gw_node->deleted) continue; @@ -139,6 +125,9 @@ void gw_election(struct bat_priv *bat_priv) if (!router) continue; + if (!atomic_inc_not_zero(&gw_node->refcount)) + goto next; + switch (atomic_read(&bat_priv->gw_sel_class)) { case 1: /* fast connection */ gw_bandwidth_to_kbit(gw_node->orig_node->gw_flags, @@ -151,8 +140,12 @@ void gw_election(struct bat_priv *bat_priv) if ((tmp_gw_factor > max_gw_factor) || ((tmp_gw_factor == max_gw_factor) && - (router->tq_avg > max_tq))) - curr_gw_tmp = gw_node; + (router->tq_avg > max_tq))) { + if (curr_gw) + gw_node_free_ref(curr_gw); + curr_gw = gw_node; + atomic_inc(&curr_gw->refcount); + } break; default: /** @@ -163,8 +156,12 @@ void gw_election(struct bat_priv *bat_priv) * soon as a better gateway appears which has * $routing_class more tq points) **/ - if (router->tq_avg > max_tq) - curr_gw_tmp = gw_node; + if (router->tq_avg > max_tq) { + if (curr_gw) + gw_node_free_ref(curr_gw); + curr_gw = gw_node; + atomic_inc(&curr_gw->refcount); + } break; } @@ -174,42 +171,81 @@ void gw_election(struct bat_priv *bat_priv) if (tmp_gw_factor > max_gw_factor) max_gw_factor = tmp_gw_factor; + gw_node_free_ref(gw_node); + +next: neigh_node_free_ref(router); } + rcu_read_unlock(); - if (curr_gw != curr_gw_tmp) { - router = orig_node_get_router(curr_gw_tmp->orig_node); - if (!router) - goto unlock; + return curr_gw; +} - if ((curr_gw) && (!curr_gw_tmp)) - bat_dbg(DBG_BATMAN, bat_priv, - "Removing selected gateway - " - "no gateway in range\n"); - else if ((!curr_gw) && (curr_gw_tmp)) - bat_dbg(DBG_BATMAN, bat_priv, - "Adding route to gateway %pM " - "(gw_flags: %i, tq: %i)\n", - curr_gw_tmp->orig_node->orig, - curr_gw_tmp->orig_node->gw_flags, - router->tq_avg); - else - bat_dbg(DBG_BATMAN, bat_priv, - "Changing route to gateway %pM " - "(gw_flags: %i, tq: %i)\n", - curr_gw_tmp->orig_node->orig, - curr_gw_tmp->orig_node->gw_flags, - router->tq_avg); +void gw_election(struct bat_priv *bat_priv) +{ + struct gw_node *curr_gw = NULL, *next_gw = NULL; + struct neigh_node *router = NULL; + char gw_addr[18] = { '\0' }; - neigh_node_free_ref(router); - gw_select(bat_priv, curr_gw_tmp); + /** + * The batman daemon checks here if we already passed a full originator + * cycle in order to make sure we don't choose the first gateway we + * hear about. This check is based on the daemon's uptime which we + * don't have. + **/ + if (atomic_read(&bat_priv->gw_mode) != GW_MODE_CLIENT) + goto out; + + if (!atomic_dec_not_zero(&bat_priv->gw_reselect)) + goto out; + + curr_gw = gw_get_selected_gw_node(bat_priv); + + next_gw = gw_get_best_gw_node(bat_priv); + + if (curr_gw == next_gw) + goto out; + + if (next_gw) { + sprintf(gw_addr, "%pM", next_gw->orig_node->orig); + + router = orig_node_get_router(next_gw->orig_node); + if (!router) { + gw_deselect(bat_priv); + goto out; + } } -unlock: - rcu_read_unlock(); + if ((curr_gw) && (!next_gw)) { + bat_dbg(DBG_BATMAN, bat_priv, + "Removing selected gateway - no gateway in range\n"); + throw_uevent(bat_priv, UEV_GW, UEV_DEL, NULL); + } else if ((!curr_gw) && (next_gw)) { + bat_dbg(DBG_BATMAN, bat_priv, + "Adding route to gateway %pM (gw_flags: %i, tq: %i)\n", + next_gw->orig_node->orig, + next_gw->orig_node->gw_flags, + router->tq_avg); + throw_uevent(bat_priv, UEV_GW, UEV_ADD, gw_addr); + } else { + bat_dbg(DBG_BATMAN, bat_priv, + "Changing route to gateway %pM " + "(gw_flags: %i, tq: %i)\n", + next_gw->orig_node->orig, + next_gw->orig_node->gw_flags, + router->tq_avg); + throw_uevent(bat_priv, UEV_GW, UEV_CHANGE, gw_addr); + } + + gw_select(bat_priv, next_gw); + out: if (curr_gw) gw_node_free_ref(curr_gw); + if (next_gw) + gw_node_free_ref(next_gw); + if (router) + neigh_node_free_ref(router); } void gw_check_election(struct bat_priv *bat_priv, struct orig_node *orig_node) @@ -273,11 +309,10 @@ static void gw_node_add(struct bat_priv *bat_priv, struct gw_node *gw_node; int down, up; - gw_node = kmalloc(sizeof(struct gw_node), GFP_ATOMIC); + gw_node = kzalloc(sizeof(*gw_node), GFP_ATOMIC); if (!gw_node) return; - memset(gw_node, 0, sizeof(struct gw_node)); INIT_HLIST_NODE(&gw_node->list); gw_node->orig_node = orig_node; atomic_set(&gw_node->refcount, 1); @@ -323,7 +358,7 @@ void gw_node_update(struct bat_priv *bat_priv, gw_node->deleted = 0; - if (new_gwflags == 0) { + if (new_gwflags == NO_FLAGS) { gw_node->deleted = jiffies; bat_dbg(DBG_BATMAN, bat_priv, "Gateway %pM removed from gateway list\n", @@ -336,7 +371,7 @@ void gw_node_update(struct bat_priv *bat_priv, goto unlock; } - if (new_gwflags == 0) + if (new_gwflags == NO_FLAGS) goto unlock; gw_node_add(bat_priv, orig_node, new_gwflags); @@ -353,7 +388,7 @@ unlock: void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node) { - return gw_node_update(bat_priv, orig_node, 0); + gw_node_update(bat_priv, orig_node, 0); } void gw_node_purge(struct bat_priv *bat_priv) @@ -361,7 +396,7 @@ void gw_node_purge(struct bat_priv *bat_priv) struct gw_node *gw_node, *curr_gw; struct hlist_node *node, *node_tmp; unsigned long timeout = 2 * PURGE_TIMEOUT * HZ; - char do_deselect = 0; + int do_deselect = 0; curr_gw = gw_get_selected_gw_node(bat_priv); @@ -394,8 +429,8 @@ void gw_node_purge(struct bat_priv *bat_priv) /** * fails if orig_node has no router */ -static int _write_buffer_text(struct bat_priv *bat_priv, - struct seq_file *seq, struct gw_node *gw_node) +static int _write_buffer_text(struct bat_priv *bat_priv, struct seq_file *seq, + const struct gw_node *gw_node) { struct gw_node *curr_gw; struct neigh_node *router; @@ -452,10 +487,9 @@ int gw_client_seq_print_text(struct seq_file *seq, void *offset) } seq_printf(seq, " %-12s (%s/%i) %17s [%10s]: gw_class ... " - "[B.A.T.M.A.N. adv %s%s, MainIF/MAC: %s/%pM (%s)]\n", + "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", "Gateway", "#", TQ_MAX_VALUE, "Nexthop", - "outgoingIF", SOURCE_VERSION, REVISION_VERSION_STR, - primary_if->net_dev->name, + "outgoingIF", SOURCE_VERSION, primary_if->net_dev->name, primary_if->net_dev->dev_addr, net_dev->name); rcu_read_lock(); @@ -480,14 +514,75 @@ out: return ret; } -int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) +static bool is_type_dhcprequest(struct sk_buff *skb, int header_len) +{ + int ret = false; + unsigned char *p; + int pkt_len; + + if (skb_linearize(skb) < 0) + goto out; + + pkt_len = skb_headlen(skb); + + if (pkt_len < header_len + DHCP_OPTIONS_OFFSET + 1) + goto out; + + p = skb->data + header_len + DHCP_OPTIONS_OFFSET; + pkt_len -= header_len + DHCP_OPTIONS_OFFSET + 1; + + /* Access the dhcp option lists. Each entry is made up by: + * - octect 1: option type + * - octect 2: option data len (only if type != 255 and 0) + * - octect 3: option data */ + while (*p != 255 && !ret) { + /* p now points to the first octect: option type */ + if (*p == 53) { + /* type 53 is the message type option. + * Jump the len octect and go to the data octect */ + if (pkt_len < 2) + goto out; + p += 2; + + /* check if the message type is what we need */ + if (*p == DHCP_REQUEST) + ret = true; + break; + } else if (*p == 0) { + /* option type 0 (padding), just go forward */ + if (pkt_len < 1) + goto out; + pkt_len--; + p++; + } else { + /* This is any other option. So we get the length... */ + if (pkt_len < 1) + goto out; + pkt_len--; + p++; + + /* ...and then we jump over the data */ + if (pkt_len < *p) + goto out; + pkt_len -= *p; + p += (*p); + } + } +out: + return ret; +} + +int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb, + struct orig_node *old_gw) { struct ethhdr *ethhdr; struct iphdr *iphdr; struct ipv6hdr *ipv6hdr; struct udphdr *udphdr; struct gw_node *curr_gw; + struct neigh_node *neigh_curr = NULL, *neigh_old = NULL; unsigned int header_len = 0; + int ret = 1; if (atomic_read(&bat_priv->gw_mode) == GW_MODE_OFF) return 0; @@ -509,7 +604,7 @@ int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) /* check for ip header */ switch (ntohs(ethhdr->h_proto)) { case ETH_P_IP: - if (!pskb_may_pull(skb, header_len + sizeof(struct iphdr))) + if (!pskb_may_pull(skb, header_len + sizeof(*iphdr))) return 0; iphdr = (struct iphdr *)(skb->data + header_len); header_len += iphdr->ihl * 4; @@ -520,10 +615,10 @@ int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) break; case ETH_P_IPV6: - if (!pskb_may_pull(skb, header_len + sizeof(struct ipv6hdr))) + if (!pskb_may_pull(skb, header_len + sizeof(*ipv6hdr))) return 0; ipv6hdr = (struct ipv6hdr *)(skb->data + header_len); - header_len += sizeof(struct ipv6hdr); + header_len += sizeof(*ipv6hdr); /* check for udp header */ if (ipv6hdr->nexthdr != IPPROTO_UDP) @@ -534,10 +629,10 @@ int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) return 0; } - if (!pskb_may_pull(skb, header_len + sizeof(struct udphdr))) + if (!pskb_may_pull(skb, header_len + sizeof(*udphdr))) return 0; udphdr = (struct udphdr *)(skb->data + header_len); - header_len += sizeof(struct udphdr); + header_len += sizeof(*udphdr); /* check for bootp port */ if ((ntohs(ethhdr->h_proto) == ETH_P_IP) && @@ -555,7 +650,30 @@ int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb) if (!curr_gw) return 0; + /* If old_gw != NULL then this packet is unicast. + * So, at this point we have to check the message type: if it is a + * DHCPREQUEST we have to decide whether to drop it or not */ + if (old_gw && curr_gw->orig_node != old_gw) { + if (is_type_dhcprequest(skb, header_len)) { + /* If the dhcp packet has been sent to a different gw, + * we have to evaluate whether the old gw is still + * reliable enough */ + neigh_curr = find_router(bat_priv, curr_gw->orig_node, + NULL); + neigh_old = find_router(bat_priv, old_gw, NULL); + if (!neigh_curr || !neigh_old) + goto free_neigh; + if (neigh_curr->tq_avg - neigh_old->tq_avg < + GW_THRESHOLD) + ret = -1; + } + } +free_neigh: + if (neigh_old) + neigh_node_free_ref(neigh_old); + if (neigh_curr) + neigh_node_free_ref(neigh_curr); if (curr_gw) gw_node_free_ref(curr_gw); - return 1; + return ret; } diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 1ce8c6066da..b9b983c07fe 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -31,6 +31,7 @@ void gw_node_update(struct bat_priv *bat_priv, void gw_node_delete(struct bat_priv *bat_priv, struct orig_node *orig_node); void gw_node_purge(struct bat_priv *bat_priv); int gw_client_seq_print_text(struct seq_file *seq, void *offset); -int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb); +int gw_is_target(struct bat_priv *bat_priv, struct sk_buff *skb, + struct orig_node *old_gw); #endif /* _NET_BATMAN_ADV_GATEWAY_CLIENT_H_ */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index 50d3a59a3d7..18661af0bc3 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -61,9 +61,9 @@ static void kbit_to_gw_bandwidth(int down, int up, long *gw_srv_class) /* returns the up and downspeeds in kbit, calculated from the class */ void gw_bandwidth_to_kbit(uint8_t gw_srv_class, int *down, int *up) { - char sbit = (gw_srv_class & 0x80) >> 7; - char dpart = (gw_srv_class & 0x78) >> 3; - char upart = (gw_srv_class & 0x07); + int sbit = (gw_srv_class & 0x80) >> 7; + int dpart = (gw_srv_class & 0x78) >> 3; + int upart = (gw_srv_class & 0x07); if (!gw_srv_class) { *down = 0; @@ -76,10 +76,11 @@ void gw_bandwidth_to_kbit(uint8_t gw_srv_class, int *down, int *up) } static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, - long *up, long *down) + int *up, int *down) { int ret, multi = 1; char *slash_ptr, *tmp_ptr; + long ldown, lup; slash_ptr = strchr(buff, '/'); if (slash_ptr) @@ -96,7 +97,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, *tmp_ptr = '\0'; } - ret = strict_strtoul(buff, 10, down); + ret = strict_strtol(buff, 10, &ldown); if (ret) { bat_err(net_dev, "Download speed of gateway mode invalid: %s\n", @@ -104,7 +105,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, return false; } - *down *= multi; + *down = ldown * multi; /* we also got some upload info */ if (slash_ptr) { @@ -121,7 +122,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, *tmp_ptr = '\0'; } - ret = strict_strtoul(slash_ptr + 1, 10, up); + ret = strict_strtol(slash_ptr + 1, 10, &lup); if (ret) { bat_err(net_dev, "Upload speed of gateway mode invalid: " @@ -129,7 +130,7 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, return false; } - *up *= multi; + *up = lup * multi; } return true; @@ -138,7 +139,8 @@ static bool parse_gw_bandwidth(struct net_device *net_dev, char *buff, ssize_t gw_bandwidth_set(struct net_device *net_dev, char *buff, size_t count) { struct bat_priv *bat_priv = netdev_priv(net_dev); - long gw_bandwidth_tmp = 0, up = 0, down = 0; + long gw_bandwidth_tmp = 0; + int up = 0, down = 0; bool ret; ret = parse_gw_bandwidth(net_dev, buff, &up, &down); @@ -158,12 +160,11 @@ ssize_t gw_bandwidth_set(struct net_device *net_dev, char *buff, size_t count) * speeds, hence we need to calculate it back to show the number * that is going to be propagated **/ - gw_bandwidth_to_kbit((uint8_t)gw_bandwidth_tmp, - (int *)&down, (int *)&up); + gw_bandwidth_to_kbit((uint8_t)gw_bandwidth_tmp, &down, &up); gw_deselect(bat_priv); bat_info(net_dev, "Changing gateway bandwidth from: '%i' to: '%ld' " - "(propagating: %ld%s/%ld%s)\n", + "(propagating: %d%s/%d%s)\n", atomic_read(&bat_priv->gw_bandwidth), gw_bandwidth_tmp, (down > 2048 ? down / 1024 : down), (down > 2048 ? "MBit" : "KBit"), diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index dfbfccc9fe4..db7aacf1e09 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -46,7 +46,7 @@ void hardif_free_rcu(struct rcu_head *rcu) kfree(hard_iface); } -struct hard_iface *hardif_get_by_netdev(struct net_device *net_dev) +struct hard_iface *hardif_get_by_netdev(const struct net_device *net_dev) { struct hard_iface *hard_iface; @@ -64,7 +64,7 @@ out: return hard_iface; } -static int is_valid_iface(struct net_device *net_dev) +static int is_valid_iface(const struct net_device *net_dev) { if (net_dev->flags & IFF_LOOPBACK) return 0; @@ -86,7 +86,7 @@ static int is_valid_iface(struct net_device *net_dev) return 1; } -static struct hard_iface *hardif_get_active(struct net_device *soft_iface) +static struct hard_iface *hardif_get_active(const struct net_device *soft_iface) { struct hard_iface *hard_iface; @@ -138,7 +138,7 @@ static void primary_if_select(struct bat_priv *bat_priv, if (new_hard_iface && !atomic_inc_not_zero(&new_hard_iface->refcount)) new_hard_iface = NULL; - curr_hard_iface = bat_priv->primary_if; + curr_hard_iface = rcu_dereference_protected(bat_priv->primary_if, 1); rcu_assign_pointer(bat_priv->primary_if, new_hard_iface); if (curr_hard_iface) @@ -152,15 +152,9 @@ static void primary_if_select(struct bat_priv *bat_priv, batman_packet->ttl = TTL; primary_if_update_addr(bat_priv); - - /*** - * hacky trick to make sure that we send the TT information via - * our new primary interface - */ - atomic_set(&bat_priv->tt_local_changed, 1); } -static bool hardif_is_iface_up(struct hard_iface *hard_iface) +static bool hardif_is_iface_up(const struct hard_iface *hard_iface) { if (hard_iface->net_dev->flags & IFF_UP) return true; @@ -176,9 +170,9 @@ static void update_mac_addresses(struct hard_iface *hard_iface) hard_iface->net_dev->dev_addr, ETH_ALEN); } -static void check_known_mac_addr(struct net_device *net_dev) +static void check_known_mac_addr(const struct net_device *net_dev) { - struct hard_iface *hard_iface; + const struct hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &hardif_list, list) { @@ -204,8 +198,8 @@ static void check_known_mac_addr(struct net_device *net_dev) int hardif_min_mtu(struct net_device *soft_iface) { - struct bat_priv *bat_priv = netdev_priv(soft_iface); - struct hard_iface *hard_iface; + const struct bat_priv *bat_priv = netdev_priv(soft_iface); + const struct hard_iface *hard_iface; /* allow big frames if all devices are capable to do so * (have MTU > 1500 + BAT_HEADER_LEN) */ int min_mtu = ETH_DATA_LEN; @@ -285,7 +279,8 @@ static void hardif_deactivate_interface(struct hard_iface *hard_iface) update_min_mtu(hard_iface->soft_iface); } -int hardif_enable_interface(struct hard_iface *hard_iface, char *iface_name) +int hardif_enable_interface(struct hard_iface *hard_iface, + const char *iface_name) { struct bat_priv *bat_priv; struct batman_packet *batman_packet; @@ -336,10 +331,11 @@ int hardif_enable_interface(struct hard_iface *hard_iface, char *iface_name) batman_packet = (struct batman_packet *)(hard_iface->packet_buff); batman_packet->packet_type = BAT_PACKET; batman_packet->version = COMPAT_VERSION; - batman_packet->flags = 0; + batman_packet->flags = NO_FLAGS; batman_packet->ttl = 2; batman_packet->tq = TQ_MAX_VALUE; - batman_packet->num_tt = 0; + batman_packet->tt_num_changes = 0; + batman_packet->ttvn = 0; hard_iface->if_num = bat_priv->num_ifaces; bat_priv->num_ifaces++; @@ -458,7 +454,7 @@ static struct hard_iface *hardif_add_interface(struct net_device *net_dev) dev_hold(net_dev); - hard_iface = kmalloc(sizeof(struct hard_iface), GFP_ATOMIC); + hard_iface = kmalloc(sizeof(*hard_iface), GFP_ATOMIC); if (!hard_iface) { pr_err("Can't add interface (%s): out of memory\n", net_dev->name); @@ -522,7 +518,7 @@ void hardif_remove_interfaces(void) static int hard_if_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct net_device *net_dev = (struct net_device *)ptr; + struct net_device *net_dev = ptr; struct hard_iface *hard_iface = hardif_get_by_netdev(net_dev); struct hard_iface *primary_if = NULL; struct bat_priv *bat_priv; @@ -567,7 +563,7 @@ static int hard_if_event(struct notifier_block *this, break; default: break; - }; + } hardif_put: hardif_free_ref(hard_iface); @@ -658,6 +654,14 @@ static int batman_skb_recv(struct sk_buff *skb, struct net_device *dev, case BAT_VIS: ret = recv_vis_packet(skb, hard_iface); break; + /* Translation table query (request or response) */ + case BAT_TT_QUERY: + ret = recv_tt_query(skb, hard_iface); + break; + /* Roaming advertisement */ + case BAT_ROAM_ADV: + ret = recv_roam_adv(skb, hard_iface); + break; default: ret = NET_RX_DROP; } diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index 64265991460..442eacbc9e3 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -22,17 +22,21 @@ #ifndef _NET_BATMAN_ADV_HARD_INTERFACE_H_ #define _NET_BATMAN_ADV_HARD_INTERFACE_H_ -#define IF_NOT_IN_USE 0 -#define IF_TO_BE_REMOVED 1 -#define IF_INACTIVE 2 -#define IF_ACTIVE 3 -#define IF_TO_BE_ACTIVATED 4 -#define IF_I_WANT_YOU 5 +enum hard_if_state { + IF_NOT_IN_USE, + IF_TO_BE_REMOVED, + IF_INACTIVE, + IF_ACTIVE, + IF_TO_BE_ACTIVATED, + IF_I_WANT_YOU +}; extern struct notifier_block hard_if_notifier; -struct hard_iface *hardif_get_by_netdev(struct net_device *net_dev); -int hardif_enable_interface(struct hard_iface *hard_iface, char *iface_name); +struct hard_iface* +hardif_get_by_netdev(const struct net_device *net_dev); +int hardif_enable_interface(struct hard_iface *hard_iface, + const char *iface_name); void hardif_disable_interface(struct hard_iface *hard_iface); void hardif_remove_interfaces(void); int hardif_min_mtu(struct net_device *soft_iface); diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index c5213d8f2cc..2a172505f51 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -46,15 +46,16 @@ struct hashtable_t *hash_new(int size) { struct hashtable_t *hash; - hash = kmalloc(sizeof(struct hashtable_t), GFP_ATOMIC); + hash = kmalloc(sizeof(*hash), GFP_ATOMIC); if (!hash) return NULL; - hash->table = kmalloc(sizeof(struct element_t *) * size, GFP_ATOMIC); + hash->table = kmalloc(sizeof(*hash->table) * size, GFP_ATOMIC); if (!hash->table) goto free_hash; - hash->list_locks = kmalloc(sizeof(spinlock_t) * size, GFP_ATOMIC); + hash->list_locks = kmalloc(sizeof(*hash->list_locks) * size, + GFP_ATOMIC); if (!hash->list_locks) goto free_table; diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 434822b2747..dd5c9fd7a90 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -28,12 +28,12 @@ * compare 2 element datas for their keys, * return 0 if same and not 0 if not * same */ -typedef int (*hashdata_compare_cb)(struct hlist_node *, void *); +typedef int (*hashdata_compare_cb)(const struct hlist_node *, const void *); /* the hashfunction, should return an index * based on the key in the data of the first * argument and the size the second */ -typedef int (*hashdata_choose_cb)(void *, int); +typedef int (*hashdata_choose_cb)(const void *, int); typedef void (*hashdata_free_cb)(struct hlist_node *, void *); struct hashtable_t { @@ -80,7 +80,7 @@ static inline void hash_delete(struct hashtable_t *hash, static inline int hash_add(struct hashtable_t *hash, hashdata_compare_cb compare, hashdata_choose_cb choose, - void *data, struct hlist_node *data_node) + const void *data, struct hlist_node *data_node) { int index; struct hlist_head *head; diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index fa22ba2bb83..ac3520e057c 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -46,7 +46,7 @@ static int bat_socket_open(struct inode *inode, struct file *file) nonseekable_open(inode, file); - socket_client = kmalloc(sizeof(struct socket_client), GFP_KERNEL); + socket_client = kmalloc(sizeof(*socket_client), GFP_KERNEL); if (!socket_client) return -ENOMEM; @@ -310,7 +310,7 @@ static void bat_socket_add_packet(struct socket_client *socket_client, { struct socket_packet *socket_packet; - socket_packet = kmalloc(sizeof(struct socket_packet), GFP_ATOMIC); + socket_packet = kmalloc(sizeof(*socket_packet), GFP_ATOMIC); if (!socket_packet) return; diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 0a7cee0076f..b0f9068ade5 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -58,9 +58,8 @@ static int __init batman_init(void) register_netdevice_notifier(&hard_if_notifier); - pr_info("B.A.T.M.A.N. advanced %s%s (compatibility version %i) " - "loaded\n", SOURCE_VERSION, REVISION_VERSION_STR, - COMPAT_VERSION); + pr_info("B.A.T.M.A.N. advanced %s (compatibility version %i) " + "loaded\n", SOURCE_VERSION, COMPAT_VERSION); return 0; } @@ -84,8 +83,10 @@ int mesh_init(struct net_device *soft_iface) spin_lock_init(&bat_priv->forw_bat_list_lock); spin_lock_init(&bat_priv->forw_bcast_list_lock); - spin_lock_init(&bat_priv->tt_lhash_lock); - spin_lock_init(&bat_priv->tt_ghash_lock); + spin_lock_init(&bat_priv->tt_changes_list_lock); + spin_lock_init(&bat_priv->tt_req_list_lock); + spin_lock_init(&bat_priv->tt_roam_list_lock); + spin_lock_init(&bat_priv->tt_buff_lock); spin_lock_init(&bat_priv->gw_list_lock); spin_lock_init(&bat_priv->vis_hash_lock); spin_lock_init(&bat_priv->vis_list_lock); @@ -96,14 +97,14 @@ int mesh_init(struct net_device *soft_iface) INIT_HLIST_HEAD(&bat_priv->forw_bcast_list); INIT_HLIST_HEAD(&bat_priv->gw_list); INIT_HLIST_HEAD(&bat_priv->softif_neigh_vids); + INIT_LIST_HEAD(&bat_priv->tt_changes_list); + INIT_LIST_HEAD(&bat_priv->tt_req_list); + INIT_LIST_HEAD(&bat_priv->tt_roam_list); if (originator_init(bat_priv) < 1) goto err; - if (tt_local_init(bat_priv) < 1) - goto err; - - if (tt_global_init(bat_priv) < 1) + if (tt_init(bat_priv) < 1) goto err; tt_local_add(soft_iface, soft_iface->dev_addr); @@ -111,6 +112,7 @@ int mesh_init(struct net_device *soft_iface) if (vis_init(bat_priv) < 1) goto err; + atomic_set(&bat_priv->gw_reselect, 0); atomic_set(&bat_priv->mesh_state, MESH_ACTIVE); goto end; @@ -137,8 +139,7 @@ void mesh_free(struct net_device *soft_iface) gw_node_purge(bat_priv); originator_free(bat_priv); - tt_local_free(bat_priv); - tt_global_free(bat_priv); + tt_free(bat_priv); softif_neigh_purge(bat_priv); @@ -155,9 +156,9 @@ void dec_module_count(void) module_put(THIS_MODULE); } -int is_my_mac(uint8_t *addr) +int is_my_mac(const uint8_t *addr) { - struct hard_iface *hard_iface; + const struct hard_iface *hard_iface; rcu_read_lock(); list_for_each_entry_rcu(hard_iface, &hardif_list, list) { @@ -182,8 +183,4 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_SUPPORTED_DEVICE(DRIVER_DEVICE); -#ifdef REVISION_VERSION -MODULE_VERSION(SOURCE_VERSION "-" REVISION_VERSION); -#else MODULE_VERSION(SOURCE_VERSION); -#endif diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index 148b49e0264..a6df61a6933 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -27,8 +27,9 @@ #define DRIVER_DESC "B.A.T.M.A.N. advanced" #define DRIVER_DEVICE "batman-adv" -#define SOURCE_VERSION "next" - +#ifndef SOURCE_VERSION +#define SOURCE_VERSION "2011.3.0" +#endif /* B.A.T.M.A.N. parameters */ @@ -42,15 +43,25 @@ * -> TODO: check influence on TQ_LOCAL_WINDOW_SIZE */ #define PURGE_TIMEOUT 200 #define TT_LOCAL_TIMEOUT 3600 /* in seconds */ - +#define TT_CLIENT_ROAM_TIMEOUT 600 /* sliding packet range of received originator messages in squence numbers * (should be a multiple of our word size) */ #define TQ_LOCAL_WINDOW_SIZE 64 +#define TT_REQUEST_TIMEOUT 3 /* seconds we have to keep pending tt_req */ + #define TQ_GLOBAL_WINDOW_SIZE 5 #define TQ_LOCAL_BIDRECT_SEND_MINIMUM 1 #define TQ_LOCAL_BIDRECT_RECV_MINIMUM 1 #define TQ_TOTAL_BIDRECT_LIMIT 1 +#define TT_OGM_APPEND_MAX 3 /* number of OGMs sent with the last tt diff */ + +#define ROAMING_MAX_TIME 20 /* Time in which a client can roam at most + * ROAMING_MAX_COUNT times */ +#define ROAMING_MAX_COUNT 5 + +#define NO_FLAGS 0 + #define NUM_WORDS (TQ_LOCAL_WINDOW_SIZE / WORD_BIT_SIZE) #define LOG_BUF_LEN 8192 /* has to be a power of 2 */ @@ -72,13 +83,27 @@ #define RESET_PROTECTION_MS 30000 #define EXPECTED_SEQNO_RANGE 65536 -#define MESH_INACTIVE 0 -#define MESH_ACTIVE 1 -#define MESH_DEACTIVATING 2 +enum mesh_state { + MESH_INACTIVE, + MESH_ACTIVE, + MESH_DEACTIVATING +}; #define BCAST_QUEUE_LEN 256 #define BATMAN_QUEUE_LEN 256 +enum uev_action { + UEV_ADD = 0, + UEV_DEL, + UEV_CHANGE +}; + +enum uev_type { + UEV_GW = 0 +}; + +#define GW_THRESHOLD 50 + /* * Debug Messages */ @@ -89,10 +114,12 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt /* all messages related to routing / flooding / broadcasting / etc */ -#define DBG_BATMAN 1 -/* route or tt entry added / changed / deleted */ -#define DBG_ROUTES 2 -#define DBG_ALL 3 +enum dbg_level { + DBG_BATMAN = 1 << 0, + DBG_ROUTES = 1 << 1, /* route added / changed / deleted */ + DBG_TT = 1 << 2, /* translation table operations */ + DBG_ALL = 7 +}; /* @@ -118,12 +145,6 @@ #include <linux/seq_file.h> #include "types.h" -#ifndef REVISION_VERSION -#define REVISION_VERSION_STR "" -#else -#define REVISION_VERSION_STR " "REVISION_VERSION -#endif - extern struct list_head hardif_list; extern unsigned char broadcast_addr[]; @@ -133,10 +154,10 @@ int mesh_init(struct net_device *soft_iface); void mesh_free(struct net_device *soft_iface); void inc_module_count(void); void dec_module_count(void); -int is_my_mac(uint8_t *addr); +int is_my_mac(const uint8_t *addr); #ifdef CONFIG_BATMAN_ADV_DEBUG -int debug_log(struct bat_priv *bat_priv, char *fmt, ...); +int debug_log(struct bat_priv *bat_priv, const char *fmt, ...) __printf(2, 3); #define bat_dbg(type, bat_priv, fmt, arg...) \ do { \ @@ -145,9 +166,10 @@ int debug_log(struct bat_priv *bat_priv, char *fmt, ...); } \ while (0) #else /* !CONFIG_BATMAN_ADV_DEBUG */ -static inline void bat_dbg(char type __always_unused, +__printf(3, 4) +static inline void bat_dbg(int type __always_unused, struct bat_priv *bat_priv __always_unused, - char *fmt __always_unused, ...) + const char *fmt __always_unused, ...) { } #endif @@ -172,11 +194,32 @@ static inline void bat_dbg(char type __always_unused, * * note: can't use compare_ether_addr() as it requires aligned memory */ -static inline int compare_eth(void *data1, void *data2) + +static inline int compare_eth(const void *data1, const void *data2) { return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } + #define atomic_dec_not_zero(v) atomic_add_unless((v), -1, 0) +/* Returns the smallest signed integer in two's complement with the sizeof x */ +#define smallest_signed_int(x) (1u << (7u + 8u * (sizeof(x) - 1u))) + +/* Checks if a sequence number x is a predecessor/successor of y. + * they handle overflows/underflows and can correctly check for a + * predecessor/successor unless the variable sequence number has grown by + * more then 2**(bitwidth(x)-1)-1. + * This means that for a uint8_t with the maximum value 255, it would think: + * - when adding nothing - it is neither a predecessor nor a successor + * - before adding more than 127 to the starting value - it is a predecessor, + * - when adding 128 - it is neither a predecessor nor a successor, + * - after adding more than 127 to the starting value - it is a successor */ +#define seq_before(x, y) ({typeof(x) _d1 = (x); \ + typeof(y) _d2 = (y); \ + typeof(x) _dummy = (_d1 - _d2); \ + (void) (&_d1 == &_d2); \ + _dummy > smallest_signed_int(_dummy); }) +#define seq_after(x, y) seq_before(y, x) + #endif /* _NET_BATMAN_ADV_MAIN_H_ */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 40a30bbcd14..f3c3f620d19 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -37,6 +37,14 @@ static void start_purge_timer(struct bat_priv *bat_priv) queue_delayed_work(bat_event_workqueue, &bat_priv->orig_work, 1 * HZ); } +/* returns 1 if they are the same originator */ +static int compare_orig(const struct hlist_node *node, const void *data2) +{ + const void *data1 = container_of(node, struct orig_node, hash_entry); + + return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); +} + int originator_init(struct bat_priv *bat_priv) { if (bat_priv->orig_hash) @@ -77,7 +85,7 @@ struct neigh_node *orig_node_get_router(struct orig_node *orig_node) struct neigh_node *create_neighbor(struct orig_node *orig_node, struct orig_node *orig_neigh_node, - uint8_t *neigh, + const uint8_t *neigh, struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); @@ -86,7 +94,7 @@ struct neigh_node *create_neighbor(struct orig_node *orig_node, bat_dbg(DBG_BATMAN, bat_priv, "Creating new last-hop neighbor of originator\n"); - neigh_node = kzalloc(sizeof(struct neigh_node), GFP_ATOMIC); + neigh_node = kzalloc(sizeof(*neigh_node), GFP_ATOMIC); if (!neigh_node) return NULL; @@ -137,6 +145,7 @@ static void orig_node_free_rcu(struct rcu_head *rcu) tt_global_del_orig(orig_node->bat_priv, orig_node, "originator timed out"); + kfree(orig_node->tt_buff); kfree(orig_node->bcast_own); kfree(orig_node->bcast_own_sum); kfree(orig_node); @@ -183,7 +192,7 @@ void originator_free(struct bat_priv *bat_priv) /* this function finds or creates an originator entry for the given * address if it does not exits */ -struct orig_node *get_orig_node(struct bat_priv *bat_priv, uint8_t *addr) +struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr) { struct orig_node *orig_node; int size; @@ -196,7 +205,7 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, uint8_t *addr) bat_dbg(DBG_BATMAN, bat_priv, "Creating new originator: %pM\n", addr); - orig_node = kzalloc(sizeof(struct orig_node), GFP_ATOMIC); + orig_node = kzalloc(sizeof(*orig_node), GFP_ATOMIC); if (!orig_node) return NULL; @@ -205,14 +214,20 @@ struct orig_node *get_orig_node(struct bat_priv *bat_priv, uint8_t *addr) spin_lock_init(&orig_node->ogm_cnt_lock); spin_lock_init(&orig_node->bcast_seqno_lock); spin_lock_init(&orig_node->neigh_list_lock); + spin_lock_init(&orig_node->tt_buff_lock); /* extra reference for return */ atomic_set(&orig_node->refcount, 2); + orig_node->tt_poss_change = false; orig_node->bat_priv = bat_priv; memcpy(orig_node->orig, addr, ETH_ALEN); orig_node->router = NULL; + orig_node->tt_crc = 0; + atomic_set(&orig_node->last_ttvn, 0); orig_node->tt_buff = NULL; + orig_node->tt_buff_len = 0; + atomic_set(&orig_node->tt_size, 0); orig_node->bcast_seqno_reset = jiffies - 1 - msecs_to_jiffies(RESET_PROTECTION_MS); orig_node->batman_seqno_reset = jiffies - 1 @@ -322,9 +337,7 @@ static bool purge_orig_node(struct bat_priv *bat_priv, if (purge_orig_neighbors(bat_priv, orig_node, &best_neigh_node)) { update_routes(bat_priv, orig_node, - best_neigh_node, - orig_node->tt_buff, - orig_node->tt_buff_len); + best_neigh_node); } } @@ -419,9 +432,8 @@ int orig_seq_print_text(struct seq_file *seq, void *offset) goto out; } - seq_printf(seq, "[B.A.T.M.A.N. adv %s%s, MainIF/MAC: %s/%pM (%s)]\n", - SOURCE_VERSION, REVISION_VERSION_STR, - primary_if->net_dev->name, + seq_printf(seq, "[B.A.T.M.A.N. adv %s, MainIF/MAC: %s/%pM (%s)]\n", + SOURCE_VERSION, primary_if->net_dev->name, primary_if->net_dev->dev_addr, net_dev->name); seq_printf(seq, " %-15s %s (%s/%i) %17s [%10s]: %20s ...\n", "Originator", "last-seen", "#", TQ_MAX_VALUE, "Nexthop", @@ -559,7 +571,7 @@ static int orig_node_del_if(struct orig_node *orig_node, memcpy(data_ptr, orig_node->bcast_own, del_if_num * chunk_size); /* copy second part */ - memcpy(data_ptr + del_if_num * chunk_size, + memcpy((char *)data_ptr + del_if_num * chunk_size, orig_node->bcast_own + ((del_if_num + 1) * chunk_size), (max_if_num - del_if_num) * chunk_size); @@ -579,7 +591,7 @@ free_bcast_own: memcpy(data_ptr, orig_node->bcast_own_sum, del_if_num * sizeof(uint8_t)); - memcpy(data_ptr + del_if_num * sizeof(uint8_t), + memcpy((char *)data_ptr + del_if_num * sizeof(uint8_t), orig_node->bcast_own_sum + ((del_if_num + 1) * sizeof(uint8_t)), (max_if_num - del_if_num) * sizeof(uint8_t)); diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index e1d641f27aa..cfc1f60a96a 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -28,10 +28,10 @@ int originator_init(struct bat_priv *bat_priv); void originator_free(struct bat_priv *bat_priv); void purge_orig_ref(struct bat_priv *bat_priv); void orig_node_free_ref(struct orig_node *orig_node); -struct orig_node *get_orig_node(struct bat_priv *bat_priv, uint8_t *addr); +struct orig_node *get_orig_node(struct bat_priv *bat_priv, const uint8_t *addr); struct neigh_node *create_neighbor(struct orig_node *orig_node, struct orig_node *orig_neigh_node, - uint8_t *neigh, + const uint8_t *neigh, struct hard_iface *if_incoming); void neigh_node_free_ref(struct neigh_node *neigh_node); struct neigh_node *orig_node_get_router(struct orig_node *orig_node); @@ -40,19 +40,11 @@ int orig_hash_add_if(struct hard_iface *hard_iface, int max_if_num); int orig_hash_del_if(struct hard_iface *hard_iface, int max_if_num); -/* returns 1 if they are the same originator */ -static inline int compare_orig(struct hlist_node *node, void *data2) -{ - void *data1 = container_of(node, struct orig_node, hash_entry); - - return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); -} - /* hashfunction to choose an entry in a hash table of given size */ /* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static inline int choose_orig(void *data, int32_t size) +static inline int choose_orig(const void *data, int32_t size) { - unsigned char *key = data; + const unsigned char *key = data; uint32_t hash = 0; size_t i; @@ -70,7 +62,7 @@ static inline int choose_orig(void *data, int32_t size) } static inline struct orig_node *orig_hash_find(struct bat_priv *bat_priv, - void *data) + const void *data) { struct hashtable_t *hash = bat_priv->orig_hash; struct hlist_head *head; diff --git a/net/batman-adv/packet.h b/net/batman-adv/packet.h index eda99650e9f..b76b4be10b9 100644 --- a/net/batman-adv/packet.h +++ b/net/batman-adv/packet.h @@ -24,46 +24,84 @@ #define ETH_P_BATMAN 0x4305 /* unofficial/not registered Ethertype */ -#define BAT_PACKET 0x01 -#define BAT_ICMP 0x02 -#define BAT_UNICAST 0x03 -#define BAT_BCAST 0x04 -#define BAT_VIS 0x05 -#define BAT_UNICAST_FRAG 0x06 +enum bat_packettype { + BAT_PACKET = 0x01, + BAT_ICMP = 0x02, + BAT_UNICAST = 0x03, + BAT_BCAST = 0x04, + BAT_VIS = 0x05, + BAT_UNICAST_FRAG = 0x06, + BAT_TT_QUERY = 0x07, + BAT_ROAM_ADV = 0x08 +}; /* this file is included by batctl which needs these defines */ -#define COMPAT_VERSION 12 -#define DIRECTLINK 0x40 -#define VIS_SERVER 0x20 -#define PRIMARIES_FIRST_HOP 0x10 +#define COMPAT_VERSION 14 + +enum batman_flags { + PRIMARIES_FIRST_HOP = 1 << 4, + VIS_SERVER = 1 << 5, + DIRECTLINK = 1 << 6 +}; /* ICMP message types */ -#define ECHO_REPLY 0 -#define DESTINATION_UNREACHABLE 3 -#define ECHO_REQUEST 8 -#define TTL_EXCEEDED 11 -#define PARAMETER_PROBLEM 12 +enum icmp_packettype { + ECHO_REPLY = 0, + DESTINATION_UNREACHABLE = 3, + ECHO_REQUEST = 8, + TTL_EXCEEDED = 11, + PARAMETER_PROBLEM = 12 +}; /* vis defines */ -#define VIS_TYPE_SERVER_SYNC 0 -#define VIS_TYPE_CLIENT_UPDATE 1 +enum vis_packettype { + VIS_TYPE_SERVER_SYNC = 0, + VIS_TYPE_CLIENT_UPDATE = 1 +}; /* fragmentation defines */ -#define UNI_FRAG_HEAD 0x01 -#define UNI_FRAG_LARGETAIL 0x02 +enum unicast_frag_flags { + UNI_FRAG_HEAD = 1 << 0, + UNI_FRAG_LARGETAIL = 1 << 1 +}; + +/* TT_QUERY subtypes */ +#define TT_QUERY_TYPE_MASK 0x3 + +enum tt_query_packettype { + TT_REQUEST = 0, + TT_RESPONSE = 1 +}; + +/* TT_QUERY flags */ +enum tt_query_flags { + TT_FULL_TABLE = 1 << 2 +}; + +/* TT_CLIENT flags. + * Flags from 1 to 1 << 7 are sent on the wire, while flags from 1 << 8 to + * 1 << 15 are used for local computation only */ +enum tt_client_flags { + TT_CLIENT_DEL = 1 << 0, + TT_CLIENT_ROAM = 1 << 1, + TT_CLIENT_NOPURGE = 1 << 8, + TT_CLIENT_NEW = 1 << 9, + TT_CLIENT_PENDING = 1 << 10 +}; struct batman_packet { uint8_t packet_type; uint8_t version; /* batman version field */ + uint8_t ttl; uint8_t flags; /* 0x40: DIRECTLINK flag, 0x20 VIS_SERVER flag... */ - uint8_t tq; uint32_t seqno; uint8_t orig[6]; uint8_t prev_sender[6]; - uint8_t ttl; - uint8_t num_tt; uint8_t gw_flags; /* flags related to gateway class */ - uint8_t align; + uint8_t tq; + uint8_t tt_num_changes; + uint8_t ttvn; /* translation table version number */ + uint16_t tt_crc; } __packed; #define BAT_PACKET_LEN sizeof(struct batman_packet) @@ -71,12 +109,13 @@ struct batman_packet { struct icmp_packet { uint8_t packet_type; uint8_t version; /* batman version field */ - uint8_t msg_type; /* see ICMP message types above */ uint8_t ttl; + uint8_t msg_type; /* see ICMP message types above */ uint8_t dst[6]; uint8_t orig[6]; uint16_t seqno; uint8_t uid; + uint8_t reserved; } __packed; #define BAT_RR_LEN 16 @@ -86,8 +125,8 @@ struct icmp_packet { struct icmp_packet_rr { uint8_t packet_type; uint8_t version; /* batman version field */ - uint8_t msg_type; /* see ICMP message types above */ uint8_t ttl; + uint8_t msg_type; /* see ICMP message types above */ uint8_t dst[6]; uint8_t orig[6]; uint16_t seqno; @@ -99,16 +138,19 @@ struct icmp_packet_rr { struct unicast_packet { uint8_t packet_type; uint8_t version; /* batman version field */ - uint8_t dest[6]; uint8_t ttl; + uint8_t ttvn; /* destination translation table version number */ + uint8_t dest[6]; } __packed; struct unicast_frag_packet { uint8_t packet_type; uint8_t version; /* batman version field */ - uint8_t dest[6]; uint8_t ttl; + uint8_t ttvn; /* destination translation table version number */ + uint8_t dest[6]; uint8_t flags; + uint8_t align; uint8_t orig[6]; uint16_t seqno; } __packed; @@ -116,21 +158,61 @@ struct unicast_frag_packet { struct bcast_packet { uint8_t packet_type; uint8_t version; /* batman version field */ - uint8_t orig[6]; uint8_t ttl; + uint8_t reserved; uint32_t seqno; + uint8_t orig[6]; } __packed; struct vis_packet { uint8_t packet_type; uint8_t version; /* batman version field */ + uint8_t ttl; /* TTL */ uint8_t vis_type; /* which type of vis-participant sent this? */ - uint8_t entries; /* number of entries behind this struct */ uint32_t seqno; /* sequence number */ - uint8_t ttl; /* TTL */ + uint8_t entries; /* number of entries behind this struct */ + uint8_t reserved; uint8_t vis_orig[6]; /* originator that announces its neighbors */ uint8_t target_orig[6]; /* who should receive this packet */ uint8_t sender_orig[6]; /* who sent or rebroadcasted this packet */ } __packed; +struct tt_query_packet { + uint8_t packet_type; + uint8_t version; /* batman version field */ + uint8_t ttl; + /* the flag field is a combination of: + * - TT_REQUEST or TT_RESPONSE + * - TT_FULL_TABLE */ + uint8_t flags; + uint8_t dst[ETH_ALEN]; + uint8_t src[ETH_ALEN]; + /* the ttvn field is: + * if TT_REQUEST: ttvn that triggered the + * request + * if TT_RESPONSE: new ttvn for the src + * orig_node */ + uint8_t ttvn; + /* tt_data field is: + * if TT_REQUEST: crc associated with the + * ttvn + * if TT_RESPONSE: table_size */ + uint16_t tt_data; +} __packed; + +struct roam_adv_packet { + uint8_t packet_type; + uint8_t version; + uint8_t ttl; + uint8_t reserved; + uint8_t dst[ETH_ALEN]; + uint8_t src[ETH_ALEN]; + uint8_t client[ETH_ALEN]; +} __packed; + +struct tt_change { + uint8_t flags; + uint8_t addr[ETH_ALEN]; +} __packed; + #endif /* _NET_BATMAN_ADV_PACKET_H_ */ diff --git a/net/batman-adv/ring_buffer.c b/net/batman-adv/ring_buffer.c index 5bb6a619afe..f1ccfa76ce8 100644 --- a/net/batman-adv/ring_buffer.c +++ b/net/batman-adv/ring_buffer.c @@ -28,9 +28,9 @@ void ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, uint8_t value) *lq_index = (*lq_index + 1) % TQ_GLOBAL_WINDOW_SIZE; } -uint8_t ring_buffer_avg(uint8_t lq_recv[]) +uint8_t ring_buffer_avg(const uint8_t lq_recv[]) { - uint8_t *ptr; + const uint8_t *ptr; uint16_t count = 0, i = 0, sum = 0; ptr = lq_recv; diff --git a/net/batman-adv/ring_buffer.h b/net/batman-adv/ring_buffer.h index 0395b274186..7cdfe62b657 100644 --- a/net/batman-adv/ring_buffer.h +++ b/net/batman-adv/ring_buffer.h @@ -23,6 +23,6 @@ #define _NET_BATMAN_ADV_RING_BUFFER_H_ void ring_buffer_set(uint8_t lq_recv[], uint8_t *lq_index, uint8_t value); -uint8_t ring_buffer_avg(uint8_t lq_recv[]); +uint8_t ring_buffer_avg(const uint8_t lq_recv[]); #endif /* _NET_BATMAN_ADV_RING_BUFFER_H_ */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index bb1c3ec7e3f..0f32c818874 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -64,28 +64,69 @@ void slide_own_bcast_window(struct hard_iface *hard_iface) } } -static void update_TT(struct bat_priv *bat_priv, struct orig_node *orig_node, - unsigned char *tt_buff, int tt_buff_len) +static void update_transtable(struct bat_priv *bat_priv, + struct orig_node *orig_node, + const unsigned char *tt_buff, + uint8_t tt_num_changes, uint8_t ttvn, + uint16_t tt_crc) { - if ((tt_buff_len != orig_node->tt_buff_len) || - ((tt_buff_len > 0) && - (orig_node->tt_buff_len > 0) && - (memcmp(orig_node->tt_buff, tt_buff, tt_buff_len) != 0))) { - - if (orig_node->tt_buff_len > 0) - tt_global_del_orig(bat_priv, orig_node, - "originator changed tt"); - - if ((tt_buff_len > 0) && (tt_buff)) - tt_global_add_orig(bat_priv, orig_node, - tt_buff, tt_buff_len); + uint8_t orig_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + bool full_table = true; + + /* the ttvn increased by one -> we can apply the attached changes */ + if (ttvn - orig_ttvn == 1) { + /* the OGM could not contain the changes because they were too + * many to fit in one frame or because they have already been + * sent TT_OGM_APPEND_MAX times. In this case send a tt + * request */ + if (!tt_num_changes) { + full_table = false; + goto request_table; + } + + tt_update_changes(bat_priv, orig_node, tt_num_changes, ttvn, + (struct tt_change *)tt_buff); + + /* Even if we received the crc into the OGM, we prefer + * to recompute it to spot any possible inconsistency + * in the global table */ + orig_node->tt_crc = tt_global_crc(bat_priv, orig_node); + + /* The ttvn alone is not enough to guarantee consistency + * because a single value could repesent different states + * (due to the wrap around). Thus a node has to check whether + * the resulting table (after applying the changes) is still + * consistent or not. E.g. a node could disconnect while its + * ttvn is X and reconnect on ttvn = X + TTVN_MAX: in this case + * checking the CRC value is mandatory to detect the + * inconsistency */ + if (orig_node->tt_crc != tt_crc) + goto request_table; + + /* Roaming phase is over: tables are in sync again. I can + * unset the flag */ + orig_node->tt_poss_change = false; + } else { + /* if we missed more than one change or our tables are not + * in sync anymore -> request fresh tt data */ + if (ttvn != orig_ttvn || orig_node->tt_crc != tt_crc) { +request_table: + bat_dbg(DBG_TT, bat_priv, "TT inconsistency for %pM. " + "Need to retrieve the correct information " + "(ttvn: %u last_ttvn: %u crc: %u last_crc: " + "%u num_changes: %u)\n", orig_node->orig, ttvn, + orig_ttvn, tt_crc, orig_node->tt_crc, + tt_num_changes); + send_tt_request(bat_priv, orig_node, ttvn, tt_crc, + full_table); + return; + } } } static void update_route(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node, - unsigned char *tt_buff, int tt_buff_len) + struct neigh_node *neigh_node) { struct neigh_node *curr_router; @@ -93,11 +134,10 @@ static void update_route(struct bat_priv *bat_priv, /* route deleted */ if ((curr_router) && (!neigh_node)) { - bat_dbg(DBG_ROUTES, bat_priv, "Deleting route towards: %pM\n", orig_node->orig); tt_global_del_orig(bat_priv, orig_node, - "originator timed out"); + "Deleted route towards originator"); /* route added */ } else if ((!curr_router) && (neigh_node)) { @@ -105,11 +145,8 @@ static void update_route(struct bat_priv *bat_priv, bat_dbg(DBG_ROUTES, bat_priv, "Adding route towards: %pM (via %pM)\n", orig_node->orig, neigh_node->addr); - tt_global_add_orig(bat_priv, orig_node, - tt_buff, tt_buff_len); - /* route changed */ - } else { + } else if (neigh_node && curr_router) { bat_dbg(DBG_ROUTES, bat_priv, "Changing route towards: %pM " "(now via %pM - was via %pM)\n", @@ -133,10 +170,8 @@ static void update_route(struct bat_priv *bat_priv, neigh_node_free_ref(curr_router); } - void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node, unsigned char *tt_buff, - int tt_buff_len) + struct neigh_node *neigh_node) { struct neigh_node *router = NULL; @@ -146,11 +181,7 @@ void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, router = orig_node_get_router(orig_node); if (router != neigh_node) - update_route(bat_priv, orig_node, neigh_node, - tt_buff, tt_buff_len); - /* may be just TT changed */ - else - update_TT(bat_priv, orig_node, tt_buff, tt_buff_len); + update_route(bat_priv, orig_node, neigh_node); out: if (router) @@ -165,7 +196,7 @@ static int is_bidirectional_neigh(struct orig_node *orig_node, struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct neigh_node *neigh_node = NULL, *tmp_neigh_node; struct hlist_node *node; - unsigned char total_count; + uint8_t total_count; uint8_t orig_eq_count, neigh_rq_count, tq_own; int tq_asym_penalty, ret = 0; @@ -348,9 +379,9 @@ out: } /* copy primary address for bonding */ -static void bonding_save_primary(struct orig_node *orig_node, +static void bonding_save_primary(const struct orig_node *orig_node, struct orig_node *orig_neigh_node, - struct batman_packet *batman_packet) + const struct batman_packet *batman_packet) { if (!(batman_packet->flags & PRIMARIES_FIRST_HOP)) return; @@ -358,19 +389,16 @@ static void bonding_save_primary(struct orig_node *orig_node, memcpy(orig_neigh_node->primary_addr, orig_node->orig, ETH_ALEN); } -static void update_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, - struct ethhdr *ethhdr, - struct batman_packet *batman_packet, +static void update_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, + const struct ethhdr *ethhdr, + const struct batman_packet *batman_packet, struct hard_iface *if_incoming, - unsigned char *tt_buff, int tt_buff_len, - char is_duplicate) + const unsigned char *tt_buff, int is_duplicate) { struct neigh_node *neigh_node = NULL, *tmp_neigh_node = NULL; struct neigh_node *router = NULL; struct orig_node *orig_node_tmp; struct hlist_node *node; - int tmp_tt_buff_len; uint8_t bcast_own_sum_orig, bcast_own_sum_neigh; bat_dbg(DBG_BATMAN, bat_priv, "update_originator(): " @@ -435,9 +463,6 @@ static void update_orig(struct bat_priv *bat_priv, bonding_candidate_add(orig_node, neigh_node); - tmp_tt_buff_len = (tt_buff_len > batman_packet->num_tt * ETH_ALEN ? - batman_packet->num_tt * ETH_ALEN : tt_buff_len); - /* if this neighbor already is our next hop there is nothing * to change */ router = orig_node_get_router(orig_node); @@ -467,15 +492,19 @@ static void update_orig(struct bat_priv *bat_priv, goto update_tt; } - update_routes(bat_priv, orig_node, neigh_node, - tt_buff, tmp_tt_buff_len); - goto update_gw; + update_routes(bat_priv, orig_node, neigh_node); update_tt: - update_routes(bat_priv, orig_node, router, - tt_buff, tmp_tt_buff_len); + /* I have to check for transtable changes only if the OGM has been + * sent through a primary interface */ + if (((batman_packet->orig != ethhdr->h_source) && + (batman_packet->ttl > 2)) || + (batman_packet->flags & PRIMARIES_FIRST_HOP)) + update_transtable(bat_priv, orig_node, tt_buff, + batman_packet->tt_num_changes, + batman_packet->ttvn, + batman_packet->tt_crc); -update_gw: if (orig_node->gw_flags != batman_packet->gw_flags) gw_node_update(bat_priv, orig_node, batman_packet->gw_flags); @@ -531,15 +560,15 @@ static int window_protected(struct bat_priv *bat_priv, * -1 the packet is old and has been received while the seqno window * was protected. Caller should drop it. */ -static char count_real_packets(struct ethhdr *ethhdr, - struct batman_packet *batman_packet, - struct hard_iface *if_incoming) +static int count_real_packets(const struct ethhdr *ethhdr, + const struct batman_packet *batman_packet, + const struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct orig_node *orig_node; struct neigh_node *tmp_neigh_node; struct hlist_node *node; - char is_duplicate = 0; + int is_duplicate = 0; int32_t seq_diff; int need_update = 0; int set_mark, ret = -1; @@ -595,9 +624,9 @@ out: return ret; } -void receive_bat_packet(struct ethhdr *ethhdr, +void receive_bat_packet(const struct ethhdr *ethhdr, struct batman_packet *batman_packet, - unsigned char *tt_buff, int tt_buff_len, + const unsigned char *tt_buff, struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); @@ -605,10 +634,10 @@ void receive_bat_packet(struct ethhdr *ethhdr, struct orig_node *orig_neigh_node, *orig_node; struct neigh_node *router = NULL, *router_router = NULL; struct neigh_node *orig_neigh_router = NULL; - char has_directlink_flag; - char is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; - char is_broadcast = 0, is_bidirectional, is_single_hop_neigh; - char is_duplicate; + int has_directlink_flag; + int is_my_addr = 0, is_my_orig = 0, is_my_oldorig = 0; + int is_broadcast = 0, is_bidirectional, is_single_hop_neigh; + int is_duplicate; uint32_t if_incoming_seqno; /* Silently drop when the batman packet is actually not a @@ -636,12 +665,14 @@ void receive_bat_packet(struct ethhdr *ethhdr, bat_dbg(DBG_BATMAN, bat_priv, "Received BATMAN packet via NB: %pM, IF: %s [%pM] " - "(from OG: %pM, via prev OG: %pM, seqno %d, tq %d, " - "TTL %d, V %d, IDF %d)\n", + "(from OG: %pM, via prev OG: %pM, seqno %d, ttvn %u, " + "crc %u, changes %u, td %d, TTL %d, V %d, IDF %d)\n", ethhdr->h_source, if_incoming->net_dev->name, if_incoming->net_dev->dev_addr, batman_packet->orig, batman_packet->prev_sender, batman_packet->seqno, - batman_packet->tq, batman_packet->ttl, batman_packet->version, + batman_packet->ttvn, batman_packet->tt_crc, + batman_packet->tt_num_changes, batman_packet->tq, + batman_packet->ttl, batman_packet->version, has_directlink_flag); rcu_read_lock(); @@ -664,7 +695,7 @@ void receive_bat_packet(struct ethhdr *ethhdr, hard_iface->net_dev->dev_addr)) is_my_oldorig = 1; - if (compare_eth(ethhdr->h_source, broadcast_addr)) + if (is_broadcast_ether_addr(ethhdr->h_source)) is_broadcast = 1; } rcu_read_unlock(); @@ -701,17 +732,16 @@ void receive_bat_packet(struct ethhdr *ethhdr, /* neighbor has to indicate direct link and it has to * come via the corresponding interface */ - /* if received seqno equals last send seqno save new - * seqno for bidirectional check */ + /* save packet seqno for bidirectional check */ if (has_directlink_flag && compare_eth(if_incoming->net_dev->dev_addr, - batman_packet->orig) && - (batman_packet->seqno - if_incoming_seqno + 2 == 0)) { + batman_packet->orig)) { offset = if_incoming->if_num * NUM_WORDS; spin_lock_bh(&orig_neigh_node->ogm_cnt_lock); word = &(orig_neigh_node->bcast_own[offset]); - bit_mark(word, 0); + bit_mark(word, + if_incoming_seqno - batman_packet->seqno - 2); orig_neigh_node->bcast_own_sum[if_incoming->if_num] = bit_packet_count(word); spin_unlock_bh(&orig_neigh_node->ogm_cnt_lock); @@ -794,14 +824,14 @@ void receive_bat_packet(struct ethhdr *ethhdr, ((orig_node->last_real_seqno == batman_packet->seqno) && (orig_node->last_ttl - 3 <= batman_packet->ttl)))) update_orig(bat_priv, orig_node, ethhdr, batman_packet, - if_incoming, tt_buff, tt_buff_len, is_duplicate); + if_incoming, tt_buff, is_duplicate); /* is single hop (direct) neighbor */ if (is_single_hop_neigh) { /* mark direct link on incoming interface */ schedule_forward_packet(orig_node, ethhdr, batman_packet, - 1, tt_buff_len, if_incoming); + 1, if_incoming); bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: " "rebroadcast neighbor packet with direct link flag\n"); @@ -824,7 +854,7 @@ void receive_bat_packet(struct ethhdr *ethhdr, bat_dbg(DBG_BATMAN, bat_priv, "Forwarding packet: rebroadcast originator packet\n"); schedule_forward_packet(orig_node, ethhdr, batman_packet, - 0, tt_buff_len, if_incoming); + 0, if_incoming); out_neigh: if ((orig_neigh_node) && (!is_single_hop_neigh)) @@ -1077,7 +1107,7 @@ out: * This method rotates the bonding list and increases the * returned router's refcount. */ static struct neigh_node *find_bond_router(struct orig_node *primary_orig, - struct hard_iface *recv_if) + const struct hard_iface *recv_if) { struct neigh_node *tmp_neigh_node; struct neigh_node *router = NULL, *first_candidate = NULL; @@ -1128,7 +1158,7 @@ out: * * Increases the returned router's refcount */ static struct neigh_node *find_ifalter_router(struct orig_node *primary_orig, - struct hard_iface *recv_if) + const struct hard_iface *recv_if) { struct neigh_node *tmp_neigh_node; struct neigh_node *router = NULL, *first_candidate = NULL; @@ -1171,12 +1201,124 @@ static struct neigh_node *find_ifalter_router(struct orig_node *primary_orig, return router; } +int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if) +{ + struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct tt_query_packet *tt_query; + struct ethhdr *ethhdr; + + /* drop packet if it has not necessary minimum size */ + if (unlikely(!pskb_may_pull(skb, sizeof(struct tt_query_packet)))) + goto out; + + /* I could need to modify it */ + if (skb_cow(skb, sizeof(struct tt_query_packet)) < 0) + goto out; + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + + /* packet with unicast indication but broadcast recipient */ + if (is_broadcast_ether_addr(ethhdr->h_dest)) + goto out; + + /* packet with broadcast sender address */ + if (is_broadcast_ether_addr(ethhdr->h_source)) + goto out; + + tt_query = (struct tt_query_packet *)skb->data; + + tt_query->tt_data = ntohs(tt_query->tt_data); + + switch (tt_query->flags & TT_QUERY_TYPE_MASK) { + case TT_REQUEST: + /* If we cannot provide an answer the tt_request is + * forwarded */ + if (!send_tt_response(bat_priv, tt_query)) { + bat_dbg(DBG_TT, bat_priv, + "Routing TT_REQUEST to %pM [%c]\n", + tt_query->dst, + (tt_query->flags & TT_FULL_TABLE ? 'F' : '.')); + tt_query->tt_data = htons(tt_query->tt_data); + return route_unicast_packet(skb, recv_if); + } + break; + case TT_RESPONSE: + /* packet needs to be linearised to access the TT changes */ + if (skb_linearize(skb) < 0) + goto out; + + if (is_my_mac(tt_query->dst)) + handle_tt_response(bat_priv, tt_query); + else { + bat_dbg(DBG_TT, bat_priv, + "Routing TT_RESPONSE to %pM [%c]\n", + tt_query->dst, + (tt_query->flags & TT_FULL_TABLE ? 'F' : '.')); + tt_query->tt_data = htons(tt_query->tt_data); + return route_unicast_packet(skb, recv_if); + } + break; + } + +out: + /* returning NET_RX_DROP will make the caller function kfree the skb */ + return NET_RX_DROP; +} + +int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if) +{ + struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); + struct roam_adv_packet *roam_adv_packet; + struct orig_node *orig_node; + struct ethhdr *ethhdr; + + /* drop packet if it has not necessary minimum size */ + if (unlikely(!pskb_may_pull(skb, sizeof(struct roam_adv_packet)))) + goto out; + + ethhdr = (struct ethhdr *)skb_mac_header(skb); + + /* packet with unicast indication but broadcast recipient */ + if (is_broadcast_ether_addr(ethhdr->h_dest)) + goto out; + + /* packet with broadcast sender address */ + if (is_broadcast_ether_addr(ethhdr->h_source)) + goto out; + + roam_adv_packet = (struct roam_adv_packet *)skb->data; + + if (!is_my_mac(roam_adv_packet->dst)) + return route_unicast_packet(skb, recv_if); + + orig_node = orig_hash_find(bat_priv, roam_adv_packet->src); + if (!orig_node) + goto out; + + bat_dbg(DBG_TT, bat_priv, "Received ROAMING_ADV from %pM " + "(client %pM)\n", roam_adv_packet->src, + roam_adv_packet->client); + + tt_global_add(bat_priv, orig_node, roam_adv_packet->client, + atomic_read(&orig_node->last_ttvn) + 1, true); + + /* Roaming phase starts: I have new information but the ttvn has not + * been incremented yet. This flag will make me check all the incoming + * packets for the correct destination. */ + bat_priv->tt_poss_change = true; + + orig_node_free_ref(orig_node); +out: + /* returning NET_RX_DROP will make the caller function kfree the skb */ + return NET_RX_DROP; +} + /* find a suitable router for this originator, and use * bonding if possible. increases the found neighbors * refcount.*/ struct neigh_node *find_router(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct hard_iface *recv_if) + const struct hard_iface *recv_if) { struct orig_node *primary_orig_node; struct orig_node *router_orig; @@ -1240,6 +1382,9 @@ struct neigh_node *find_router(struct bat_priv *bat_priv, router = find_ifalter_router(primary_orig_node, recv_if); return_router: + if (router && router->if_incoming->if_status != IF_ACTIVE) + goto err_unlock; + rcu_read_unlock(); return router; err_unlock: @@ -1354,14 +1499,84 @@ out: return ret; } +static int check_unicast_ttvn(struct bat_priv *bat_priv, + struct sk_buff *skb) { + uint8_t curr_ttvn; + struct orig_node *orig_node; + struct ethhdr *ethhdr; + struct hard_iface *primary_if; + struct unicast_packet *unicast_packet; + bool tt_poss_change; + + /* I could need to modify it */ + if (skb_cow(skb, sizeof(struct unicast_packet)) < 0) + return 0; + + unicast_packet = (struct unicast_packet *)skb->data; + + if (is_my_mac(unicast_packet->dest)) { + tt_poss_change = bat_priv->tt_poss_change; + curr_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); + } else { + orig_node = orig_hash_find(bat_priv, unicast_packet->dest); + + if (!orig_node) + return 0; + + curr_ttvn = (uint8_t)atomic_read(&orig_node->last_ttvn); + tt_poss_change = orig_node->tt_poss_change; + orig_node_free_ref(orig_node); + } + + /* Check whether I have to reroute the packet */ + if (seq_before(unicast_packet->ttvn, curr_ttvn) || tt_poss_change) { + /* Linearize the skb before accessing it */ + if (skb_linearize(skb) < 0) + return 0; + + ethhdr = (struct ethhdr *)(skb->data + + sizeof(struct unicast_packet)); + orig_node = transtable_search(bat_priv, ethhdr->h_dest); + + if (!orig_node) { + if (!is_my_client(bat_priv, ethhdr->h_dest)) + return 0; + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + return 0; + memcpy(unicast_packet->dest, + primary_if->net_dev->dev_addr, ETH_ALEN); + hardif_free_ref(primary_if); + } else { + memcpy(unicast_packet->dest, orig_node->orig, + ETH_ALEN); + curr_ttvn = (uint8_t) + atomic_read(&orig_node->last_ttvn); + orig_node_free_ref(orig_node); + } + + bat_dbg(DBG_ROUTES, bat_priv, "TTVN mismatch (old_ttvn %u " + "new_ttvn %u)! Rerouting unicast packet (for %pM) to " + "%pM\n", unicast_packet->ttvn, curr_ttvn, + ethhdr->h_dest, unicast_packet->dest); + + unicast_packet->ttvn = curr_ttvn; + } + return 1; +} + int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if) { + struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct unicast_packet *unicast_packet; - int hdr_size = sizeof(struct unicast_packet); + int hdr_size = sizeof(*unicast_packet); if (check_unicast_packet(skb, hdr_size) < 0) return NET_RX_DROP; + if (!check_unicast_ttvn(bat_priv, skb)) + return NET_RX_DROP; + unicast_packet = (struct unicast_packet *)skb->data; /* packet for me */ @@ -1377,13 +1592,16 @@ int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if) { struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); struct unicast_frag_packet *unicast_packet; - int hdr_size = sizeof(struct unicast_frag_packet); + int hdr_size = sizeof(*unicast_packet); struct sk_buff *new_skb = NULL; int ret; if (check_unicast_packet(skb, hdr_size) < 0) return NET_RX_DROP; + if (!check_unicast_ttvn(bat_priv, skb)) + return NET_RX_DROP; + unicast_packet = (struct unicast_frag_packet *)skb->data; /* packet for me */ @@ -1413,7 +1631,7 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) struct orig_node *orig_node = NULL; struct bcast_packet *bcast_packet; struct ethhdr *ethhdr; - int hdr_size = sizeof(struct bcast_packet); + int hdr_size = sizeof(*bcast_packet); int ret = NET_RX_DROP; int32_t seq_diff; @@ -1471,7 +1689,7 @@ int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if) spin_unlock_bh(&orig_node->bcast_seqno_lock); /* rebroadcast packet */ - add_bcast_packet_to_list(bat_priv, skb); + add_bcast_packet_to_list(bat_priv, skb, 1); /* broadcast for me */ interface_rx(recv_if->soft_iface, skb, recv_if, hdr_size); @@ -1491,7 +1709,7 @@ int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if) struct vis_packet *vis_packet; struct ethhdr *ethhdr; struct bat_priv *bat_priv = netdev_priv(recv_if->soft_iface); - int hdr_size = sizeof(struct vis_packet); + int hdr_size = sizeof(*vis_packet); /* keep skb linear */ if (skb_linearize(skb) < 0) diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index 870f29842b2..fb14e9579b1 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -23,13 +23,12 @@ #define _NET_BATMAN_ADV_ROUTING_H_ void slide_own_bcast_window(struct hard_iface *hard_iface); -void receive_bat_packet(struct ethhdr *ethhdr, - struct batman_packet *batman_packet, - unsigned char *tt_buff, int tt_buff_len, - struct hard_iface *if_incoming); +void receive_bat_packet(const struct ethhdr *ethhdr, + struct batman_packet *batman_packet, + const unsigned char *tt_buff, + struct hard_iface *if_incoming); void update_routes(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct neigh_node *neigh_node, unsigned char *tt_buff, - int tt_buff_len); + struct neigh_node *neigh_node); int route_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_icmp_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_unicast_packet(struct sk_buff *skb, struct hard_iface *recv_if); @@ -37,9 +36,11 @@ int recv_ucast_frag_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_bcast_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_vis_packet(struct sk_buff *skb, struct hard_iface *recv_if); int recv_bat_packet(struct sk_buff *skb, struct hard_iface *recv_if); +int recv_tt_query(struct sk_buff *skb, struct hard_iface *recv_if); +int recv_roam_adv(struct sk_buff *skb, struct hard_iface *recv_if); struct neigh_node *find_router(struct bat_priv *bat_priv, struct orig_node *orig_node, - struct hard_iface *recv_if); + const struct hard_iface *recv_if); void bonding_candidate_del(struct orig_node *orig_node, struct neigh_node *neigh_node); diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 33779278f1b..58d14472068 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -33,14 +33,14 @@ static void send_outstanding_bcast_packet(struct work_struct *work); /* apply hop penalty for a normal link */ -static uint8_t hop_penalty(const uint8_t tq, struct bat_priv *bat_priv) +static uint8_t hop_penalty(uint8_t tq, const struct bat_priv *bat_priv) { int hop_penalty = atomic_read(&bat_priv->hop_penalty); return (tq * (TQ_MAX_VALUE - hop_penalty)) / (TQ_MAX_VALUE); } /* when do we schedule our own packet to be sent */ -static unsigned long own_send_time(struct bat_priv *bat_priv) +static unsigned long own_send_time(const struct bat_priv *bat_priv) { return jiffies + msecs_to_jiffies( atomic_read(&bat_priv->orig_interval) - @@ -55,9 +55,8 @@ static unsigned long forward_send_time(void) /* send out an already prepared packet to the given address via the * specified batman interface */ -int send_skb_packet(struct sk_buff *skb, - struct hard_iface *hard_iface, - uint8_t *dst_addr) +int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, + const uint8_t *dst_addr) { struct ethhdr *ethhdr; @@ -74,7 +73,7 @@ int send_skb_packet(struct sk_buff *skb, } /* push to the ethernet header. */ - if (my_skb_head_push(skb, sizeof(struct ethhdr)) < 0) + if (my_skb_head_push(skb, sizeof(*ethhdr)) < 0) goto send_skb_err; skb_reset_mac_header(skb); @@ -121,7 +120,7 @@ static void send_packet_to_if(struct forw_packet *forw_packet, /* adjust all flags and log packets */ while (aggregated_packet(buff_pos, forw_packet->packet_len, - batman_packet->num_tt)) { + batman_packet->tt_num_changes)) { /* we might have aggregated direct link packets with an * ordinary base packet */ @@ -136,17 +135,17 @@ static void send_packet_to_if(struct forw_packet *forw_packet, "Forwarding")); bat_dbg(DBG_BATMAN, bat_priv, "%s %spacket (originator %pM, seqno %d, TQ %d, TTL %d," - " IDF %s) on interface %s [%pM]\n", + " IDF %s, hvn %d) on interface %s [%pM]\n", fwd_str, (packet_num > 0 ? "aggregated " : ""), batman_packet->orig, ntohl(batman_packet->seqno), batman_packet->tq, batman_packet->ttl, (batman_packet->flags & DIRECTLINK ? "on" : "off"), - hard_iface->net_dev->name, + batman_packet->ttvn, hard_iface->net_dev->name, hard_iface->net_dev->dev_addr); - buff_pos += sizeof(struct batman_packet) + - (batman_packet->num_tt * ETH_ALEN); + buff_pos += sizeof(*batman_packet) + + tt_len(batman_packet->tt_num_changes); packet_num++; batman_packet = (struct batman_packet *) (forw_packet->skb->data + buff_pos); @@ -164,26 +163,31 @@ static void send_packet(struct forw_packet *forw_packet) struct hard_iface *hard_iface; struct net_device *soft_iface; struct bat_priv *bat_priv; + struct hard_iface *primary_if = NULL; struct batman_packet *batman_packet = (struct batman_packet *)(forw_packet->skb->data); - unsigned char directlink = (batman_packet->flags & DIRECTLINK ? 1 : 0); + int directlink = (batman_packet->flags & DIRECTLINK ? 1 : 0); if (!forw_packet->if_incoming) { pr_err("Error - can't forward packet: incoming iface not " "specified\n"); - return; + goto out; } soft_iface = forw_packet->if_incoming->soft_iface; bat_priv = netdev_priv(soft_iface); if (forw_packet->if_incoming->if_status != IF_ACTIVE) - return; + goto out; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; /* multihomed peer assumed */ /* non-primary OGMs are only broadcasted on their interface */ if ((directlink && (batman_packet->ttl == 1)) || - (forw_packet->own && (forw_packet->if_incoming->if_num > 0))) { + (forw_packet->own && (forw_packet->if_incoming != primary_if))) { /* FIXME: what about aggregated packets ? */ bat_dbg(DBG_BATMAN, bat_priv, @@ -200,7 +204,7 @@ static void send_packet(struct forw_packet *forw_packet) broadcast_addr); forw_packet->skb = NULL; - return; + goto out; } /* broadcast on every interface */ @@ -212,28 +216,24 @@ static void send_packet(struct forw_packet *forw_packet) send_packet_to_if(forw_packet, hard_iface); } rcu_read_unlock(); + +out: + if (primary_if) + hardif_free_ref(primary_if); } -static void rebuild_batman_packet(struct bat_priv *bat_priv, - struct hard_iface *hard_iface) +static void realloc_packet_buffer(struct hard_iface *hard_iface, + int new_len) { - int new_len; unsigned char *new_buff; struct batman_packet *batman_packet; - new_len = sizeof(struct batman_packet) + - (bat_priv->num_local_tt * ETH_ALEN); new_buff = kmalloc(new_len, GFP_ATOMIC); /* keep old buffer if kmalloc should fail */ if (new_buff) { memcpy(new_buff, hard_iface->packet_buff, - sizeof(struct batman_packet)); - batman_packet = (struct batman_packet *)new_buff; - - batman_packet->num_tt = tt_local_fill_buffer(bat_priv, - new_buff + sizeof(struct batman_packet), - new_len - sizeof(struct batman_packet)); + sizeof(*batman_packet)); kfree(hard_iface->packet_buff); hard_iface->packet_buff = new_buff; @@ -241,6 +241,46 @@ static void rebuild_batman_packet(struct bat_priv *bat_priv, } } +/* when calling this function (hard_iface == primary_if) has to be true */ +static void prepare_packet_buffer(struct bat_priv *bat_priv, + struct hard_iface *hard_iface) +{ + int new_len; + struct batman_packet *batman_packet; + + new_len = BAT_PACKET_LEN + + tt_len((uint8_t)atomic_read(&bat_priv->tt_local_changes)); + + /* if we have too many changes for one packet don't send any + * and wait for the tt table request which will be fragmented */ + if (new_len > hard_iface->soft_iface->mtu) + new_len = BAT_PACKET_LEN; + + realloc_packet_buffer(hard_iface, new_len); + batman_packet = (struct batman_packet *)hard_iface->packet_buff; + + atomic_set(&bat_priv->tt_crc, tt_local_crc(bat_priv)); + + /* reset the sending counter */ + atomic_set(&bat_priv->tt_ogm_append_cnt, TT_OGM_APPEND_MAX); + + batman_packet->tt_num_changes = tt_changes_fill_buffer(bat_priv, + hard_iface->packet_buff + BAT_PACKET_LEN, + hard_iface->packet_len - BAT_PACKET_LEN); + +} + +static void reset_packet_buffer(struct bat_priv *bat_priv, + struct hard_iface *hard_iface) +{ + struct batman_packet *batman_packet; + + realloc_packet_buffer(hard_iface, BAT_PACKET_LEN); + + batman_packet = (struct batman_packet *)hard_iface->packet_buff; + batman_packet->tt_num_changes = 0; +} + void schedule_own_packet(struct hard_iface *hard_iface) { struct bat_priv *bat_priv = netdev_priv(hard_iface->soft_iface); @@ -266,14 +306,21 @@ void schedule_own_packet(struct hard_iface *hard_iface) if (hard_iface->if_status == IF_TO_BE_ACTIVATED) hard_iface->if_status = IF_ACTIVE; - /* if local tt has changed and interface is a primary interface */ - if ((atomic_read(&bat_priv->tt_local_changed)) && - (hard_iface == primary_if)) - rebuild_batman_packet(bat_priv, hard_iface); + if (hard_iface == primary_if) { + /* if at least one change happened */ + if (atomic_read(&bat_priv->tt_local_changes) > 0) { + tt_commit_changes(bat_priv); + prepare_packet_buffer(bat_priv, hard_iface); + } + + /* if the changes have been sent enough times */ + if (!atomic_dec_not_zero(&bat_priv->tt_ogm_append_cnt)) + reset_packet_buffer(bat_priv, hard_iface); + } /** * NOTE: packet_buff might just have been re-allocated in - * rebuild_batman_packet() + * prepare_packet_buffer() or in reset_packet_buffer() */ batman_packet = (struct batman_packet *)hard_iface->packet_buff; @@ -281,6 +328,9 @@ void schedule_own_packet(struct hard_iface *hard_iface) batman_packet->seqno = htonl((uint32_t)atomic_read(&hard_iface->seqno)); + batman_packet->ttvn = atomic_read(&bat_priv->ttvn); + batman_packet->tt_crc = htons((uint16_t)atomic_read(&bat_priv->tt_crc)); + if (vis_server == VIS_TYPE_SERVER_SYNC) batman_packet->flags |= VIS_SERVER; else @@ -291,7 +341,7 @@ void schedule_own_packet(struct hard_iface *hard_iface) batman_packet->gw_flags = (uint8_t)atomic_read(&bat_priv->gw_bandwidth); else - batman_packet->gw_flags = 0; + batman_packet->gw_flags = NO_FLAGS; atomic_inc(&hard_iface->seqno); @@ -307,15 +357,16 @@ void schedule_own_packet(struct hard_iface *hard_iface) } void schedule_forward_packet(struct orig_node *orig_node, - struct ethhdr *ethhdr, + const struct ethhdr *ethhdr, struct batman_packet *batman_packet, - uint8_t directlink, int tt_buff_len, + int directlink, struct hard_iface *if_incoming) { struct bat_priv *bat_priv = netdev_priv(if_incoming->soft_iface); struct neigh_node *router; - unsigned char in_tq, in_ttl, tq_avg = 0; + uint8_t in_tq, in_ttl, tq_avg = 0; unsigned long send_time; + uint8_t tt_num_changes; if (batman_packet->ttl <= 1) { bat_dbg(DBG_BATMAN, bat_priv, "ttl exceeded\n"); @@ -326,6 +377,7 @@ void schedule_forward_packet(struct orig_node *orig_node, in_tq = batman_packet->tq; in_ttl = batman_packet->ttl; + tt_num_changes = batman_packet->tt_num_changes; batman_packet->ttl--; memcpy(batman_packet->prev_sender, ethhdr->h_source, ETH_ALEN); @@ -358,6 +410,7 @@ void schedule_forward_packet(struct orig_node *orig_node, batman_packet->ttl); batman_packet->seqno = htonl(batman_packet->seqno); + batman_packet->tt_crc = htons(batman_packet->tt_crc); /* switch of primaries first hop flag when forwarding */ batman_packet->flags &= ~PRIMARIES_FIRST_HOP; @@ -369,7 +422,7 @@ void schedule_forward_packet(struct orig_node *orig_node, send_time = forward_send_time(); add_bat_packet_to_list(bat_priv, (unsigned char *)batman_packet, - sizeof(struct batman_packet) + tt_buff_len, + sizeof(*batman_packet) + tt_len(tt_num_changes), if_incoming, 0, send_time); } @@ -408,11 +461,13 @@ static void _add_bcast_packet_to_list(struct bat_priv *bat_priv, * * The skb is not consumed, so the caller should make sure that the * skb is freed. */ -int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb) +int add_bcast_packet_to_list(struct bat_priv *bat_priv, + const struct sk_buff *skb, unsigned long delay) { struct hard_iface *primary_if = NULL; struct forw_packet *forw_packet; struct bcast_packet *bcast_packet; + struct sk_buff *newskb; if (!atomic_dec_not_zero(&bat_priv->bcast_queue_left)) { bat_dbg(DBG_BATMAN, bat_priv, "bcast packet queue full\n"); @@ -423,28 +478,28 @@ int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb) if (!primary_if) goto out_and_inc; - forw_packet = kmalloc(sizeof(struct forw_packet), GFP_ATOMIC); + forw_packet = kmalloc(sizeof(*forw_packet), GFP_ATOMIC); if (!forw_packet) goto out_and_inc; - skb = skb_copy(skb, GFP_ATOMIC); - if (!skb) + newskb = skb_copy(skb, GFP_ATOMIC); + if (!newskb) goto packet_free; /* as we have a copy now, it is safe to decrease the TTL */ - bcast_packet = (struct bcast_packet *)skb->data; + bcast_packet = (struct bcast_packet *)newskb->data; bcast_packet->ttl--; - skb_reset_mac_header(skb); + skb_reset_mac_header(newskb); - forw_packet->skb = skb; + forw_packet->skb = newskb; forw_packet->if_incoming = primary_if; /* how often did we send the bcast packet ? */ forw_packet->num_packets = 0; - _add_bcast_packet_to_list(bat_priv, forw_packet, 1); + _add_bcast_packet_to_list(bat_priv, forw_packet, delay); return NETDEV_TX_OK; packet_free: @@ -537,7 +592,7 @@ out: } void purge_outstanding_packets(struct bat_priv *bat_priv, - struct hard_iface *hard_iface) + const struct hard_iface *hard_iface) { struct forw_packet *forw_packet; struct hlist_node *tmp_node, *safe_tmp_node; diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 247172d71e4..1f2d1e87766 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -22,18 +22,18 @@ #ifndef _NET_BATMAN_ADV_SEND_H_ #define _NET_BATMAN_ADV_SEND_H_ -int send_skb_packet(struct sk_buff *skb, - struct hard_iface *hard_iface, - uint8_t *dst_addr); +int send_skb_packet(struct sk_buff *skb, struct hard_iface *hard_iface, + const uint8_t *dst_addr); void schedule_own_packet(struct hard_iface *hard_iface); void schedule_forward_packet(struct orig_node *orig_node, - struct ethhdr *ethhdr, + const struct ethhdr *ethhdr, struct batman_packet *batman_packet, - uint8_t directlink, int tt_buff_len, + int directlink, struct hard_iface *if_outgoing); -int add_bcast_packet_to_list(struct bat_priv *bat_priv, struct sk_buff *skb); +int add_bcast_packet_to_list(struct bat_priv *bat_priv, + const struct sk_buff *skb, unsigned long delay); void send_outstanding_bat_packet(struct work_struct *work); void purge_outstanding_packets(struct bat_priv *bat_priv, - struct hard_iface *hard_iface); + const struct hard_iface *hard_iface); #endif /* _NET_BATMAN_ADV_SEND_H_ */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index d5aa60999e8..3e2f91ffa4e 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -30,6 +30,7 @@ #include "gateway_common.h" #include "gateway_client.h" #include "bat_sysfs.h" +#include "originator.h" #include <linux/slab.h> #include <linux/ethtool.h> #include <linux/etherdevice.h> @@ -123,8 +124,7 @@ static struct softif_neigh_vid *softif_neigh_vid_get(struct bat_priv *bat_priv, goto out; } - softif_neigh_vid = kzalloc(sizeof(struct softif_neigh_vid), - GFP_ATOMIC); + softif_neigh_vid = kzalloc(sizeof(*softif_neigh_vid), GFP_ATOMIC); if (!softif_neigh_vid) goto out; @@ -146,7 +146,7 @@ out: } static struct softif_neigh *softif_neigh_get(struct bat_priv *bat_priv, - uint8_t *addr, short vid) + const uint8_t *addr, short vid) { struct softif_neigh_vid *softif_neigh_vid; struct softif_neigh *softif_neigh = NULL; @@ -170,7 +170,7 @@ static struct softif_neigh *softif_neigh_get(struct bat_priv *bat_priv, goto unlock; } - softif_neigh = kzalloc(sizeof(struct softif_neigh), GFP_ATOMIC); + softif_neigh = kzalloc(sizeof(*softif_neigh), GFP_ATOMIC); if (!softif_neigh) goto unlock; @@ -242,7 +242,8 @@ static void softif_neigh_vid_select(struct bat_priv *bat_priv, if (new_neigh && !atomic_inc_not_zero(&new_neigh->refcount)) new_neigh = NULL; - curr_neigh = softif_neigh_vid->softif_neigh; + curr_neigh = rcu_dereference_protected(softif_neigh_vid->softif_neigh, + 1); rcu_assign_pointer(softif_neigh_vid->softif_neigh, new_neigh); if ((curr_neigh) && (!new_neigh)) @@ -380,7 +381,7 @@ void softif_neigh_purge(struct bat_priv *bat_priv) struct softif_neigh *softif_neigh, *curr_softif_neigh; struct softif_neigh_vid *softif_neigh_vid; struct hlist_node *node, *node_tmp, *node_tmp2; - char do_deselect; + int do_deselect; rcu_read_lock(); hlist_for_each_entry_rcu(softif_neigh_vid, node, @@ -534,7 +535,7 @@ static int interface_set_mac_addr(struct net_device *dev, void *p) /* only modify transtable if it has been initialised before */ if (atomic_read(&bat_priv->mesh_state) == MESH_ACTIVE) { tt_local_remove(bat_priv, dev->dev_addr, - "mac address changed"); + "mac address changed", false); tt_local_add(dev, addr->sa_data); } @@ -553,7 +554,7 @@ static int interface_change_mtu(struct net_device *dev, int new_mtu) return 0; } -int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) +static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) { struct ethhdr *ethhdr = (struct ethhdr *)skb->data; struct bat_priv *bat_priv = netdev_priv(soft_iface); @@ -561,6 +562,7 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) struct bcast_packet *bcast_packet; struct vlan_ethhdr *vhdr; struct softif_neigh *curr_softif_neigh = NULL; + struct orig_node *orig_node = NULL; int data_len = skb->len, ret; short vid = -1; bool do_bcast = false; @@ -592,11 +594,13 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) if (curr_softif_neigh) goto dropped; - /* TODO: check this for locks */ + /* Register the client MAC in the transtable */ tt_local_add(soft_iface, ethhdr->h_source); - if (is_multicast_ether_addr(ethhdr->h_dest)) { - ret = gw_is_target(bat_priv, skb); + orig_node = transtable_search(bat_priv, ethhdr->h_dest); + if (is_multicast_ether_addr(ethhdr->h_dest) || + (orig_node && orig_node->gw_flags)) { + ret = gw_is_target(bat_priv, skb, orig_node); if (ret < 0) goto dropped; @@ -611,7 +615,7 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) if (!primary_if) goto dropped; - if (my_skb_head_push(skb, sizeof(struct bcast_packet)) < 0) + if (my_skb_head_push(skb, sizeof(*bcast_packet)) < 0) goto dropped; bcast_packet = (struct bcast_packet *)skb->data; @@ -630,7 +634,7 @@ int interface_tx(struct sk_buff *skb, struct net_device *soft_iface) bcast_packet->seqno = htonl(atomic_inc_return(&bat_priv->bcast_seqno)); - add_bcast_packet_to_list(bat_priv, skb); + add_bcast_packet_to_list(bat_priv, skb, 1); /* a copy is stored in the bcast list, therefore removing * the original skb. */ @@ -656,6 +660,8 @@ end: softif_neigh_free_ref(curr_softif_neigh); if (primary_if) hardif_free_ref(primary_if); + if (orig_node) + orig_node_free_ref(orig_node); return NETDEV_TX_OK; } @@ -744,7 +750,6 @@ out: return; } -#ifdef HAVE_NET_DEVICE_OPS static const struct net_device_ops bat_netdev_ops = { .ndo_open = interface_open, .ndo_stop = interface_release, @@ -754,7 +759,6 @@ static const struct net_device_ops bat_netdev_ops = { .ndo_start_xmit = interface_tx, .ndo_validate_addr = eth_validate_addr }; -#endif static void interface_setup(struct net_device *dev) { @@ -763,16 +767,7 @@ static void interface_setup(struct net_device *dev) ether_setup(dev); -#ifdef HAVE_NET_DEVICE_OPS dev->netdev_ops = &bat_netdev_ops; -#else - dev->open = interface_open; - dev->stop = interface_release; - dev->get_stats = interface_stats; - dev->set_mac_address = interface_set_mac_addr; - dev->change_mtu = interface_change_mtu; - dev->hard_start_xmit = interface_tx; -#endif dev->destructor = free_netdev; dev->tx_queue_len = 0; @@ -790,17 +785,16 @@ static void interface_setup(struct net_device *dev) SET_ETHTOOL_OPS(dev, &bat_ethtool_ops); - memset(priv, 0, sizeof(struct bat_priv)); + memset(priv, 0, sizeof(*priv)); } -struct net_device *softif_create(char *name) +struct net_device *softif_create(const char *name) { struct net_device *soft_iface; struct bat_priv *bat_priv; int ret; - soft_iface = alloc_netdev(sizeof(struct bat_priv) , name, - interface_setup); + soft_iface = alloc_netdev(sizeof(*bat_priv), name, interface_setup); if (!soft_iface) { pr_err("Unable to allocate the batman interface: %s\n", name); @@ -831,7 +825,13 @@ struct net_device *softif_create(char *name) atomic_set(&bat_priv->mesh_state, MESH_INACTIVE); atomic_set(&bat_priv->bcast_seqno, 1); - atomic_set(&bat_priv->tt_local_changed, 0); + atomic_set(&bat_priv->ttvn, 0); + atomic_set(&bat_priv->tt_local_changes, 0); + atomic_set(&bat_priv->tt_ogm_append_cnt, 0); + + bat_priv->tt_buff = NULL; + bat_priv->tt_buff_len = 0; + bat_priv->tt_poss_change = false; bat_priv->primary_if = NULL; bat_priv->num_ifaces = 0; @@ -872,15 +872,10 @@ void softif_destroy(struct net_device *soft_iface) unregister_netdevice(soft_iface); } -int softif_is_valid(struct net_device *net_dev) +int softif_is_valid(const struct net_device *net_dev) { -#ifdef HAVE_NET_DEVICE_OPS if (net_dev->netdev_ops->ndo_start_xmit == interface_tx) return 1; -#else - if (net_dev->hard_start_xmit == interface_tx) - return 1; -#endif return 0; } @@ -924,4 +919,3 @@ static u32 bat_get_link(struct net_device *dev) { return 1; } - diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 4789b6f2a0b..001546fc96f 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -25,12 +25,11 @@ int my_skb_head_push(struct sk_buff *skb, unsigned int len); int softif_neigh_seq_print_text(struct seq_file *seq, void *offset); void softif_neigh_purge(struct bat_priv *bat_priv); -int interface_tx(struct sk_buff *skb, struct net_device *soft_iface); void interface_rx(struct net_device *soft_iface, struct sk_buff *skb, struct hard_iface *recv_if, int hdr_size); -struct net_device *softif_create(char *name); +struct net_device *softif_create(const char *name); void softif_destroy(struct net_device *soft_iface); -int softif_is_valid(struct net_device *net_dev); +int softif_is_valid(const struct net_device *net_dev); #endif /* _NET_BATMAN_ADV_SOFT_INTERFACE_H_ */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 7b729660cbf..fb6931d00cd 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -23,38 +23,45 @@ #include "translation-table.h" #include "soft-interface.h" #include "hard-interface.h" +#include "send.h" #include "hash.h" #include "originator.h" +#include "routing.h" -static void tt_local_purge(struct work_struct *work); -static void _tt_global_del_orig(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - char *message); +#include <linux/crc16.h> + +static void _tt_global_del(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, + const char *message); +static void tt_purge(struct work_struct *work); /* returns 1 if they are the same mac addr */ -static int compare_ltt(struct hlist_node *node, void *data2) +static int compare_ltt(const struct hlist_node *node, const void *data2) { - void *data1 = container_of(node, struct tt_local_entry, hash_entry); + const void *data1 = container_of(node, struct tt_local_entry, + hash_entry); return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } /* returns 1 if they are the same mac addr */ -static int compare_gtt(struct hlist_node *node, void *data2) +static int compare_gtt(const struct hlist_node *node, const void *data2) { - void *data1 = container_of(node, struct tt_global_entry, hash_entry); + const void *data1 = container_of(node, struct tt_global_entry, + hash_entry); return (memcmp(data1, data2, ETH_ALEN) == 0 ? 1 : 0); } -static void tt_local_start_timer(struct bat_priv *bat_priv) +static void tt_start_timer(struct bat_priv *bat_priv) { - INIT_DELAYED_WORK(&bat_priv->tt_work, tt_local_purge); - queue_delayed_work(bat_event_workqueue, &bat_priv->tt_work, 10 * HZ); + INIT_DELAYED_WORK(&bat_priv->tt_work, tt_purge); + queue_delayed_work(bat_event_workqueue, &bat_priv->tt_work, + msecs_to_jiffies(5000)); } static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv, - void *data) + const void *data) { struct hashtable_t *hash = bat_priv->tt_local_hash; struct hlist_head *head; @@ -73,6 +80,9 @@ static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv, if (!compare_eth(tt_local_entry, data)) continue; + if (!atomic_inc_not_zero(&tt_local_entry->refcount)) + continue; + tt_local_entry_tmp = tt_local_entry; break; } @@ -82,7 +92,7 @@ static struct tt_local_entry *tt_local_hash_find(struct bat_priv *bat_priv, } static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, - void *data) + const void *data) { struct hashtable_t *hash = bat_priv->tt_global_hash; struct hlist_head *head; @@ -102,6 +112,9 @@ static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, if (!compare_eth(tt_global_entry, data)) continue; + if (!atomic_inc_not_zero(&tt_global_entry->refcount)) + continue; + tt_global_entry_tmp = tt_global_entry; break; } @@ -110,7 +123,54 @@ static struct tt_global_entry *tt_global_hash_find(struct bat_priv *bat_priv, return tt_global_entry_tmp; } -int tt_local_init(struct bat_priv *bat_priv) +static bool is_out_of_time(unsigned long starting_time, unsigned long timeout) +{ + unsigned long deadline; + deadline = starting_time + msecs_to_jiffies(timeout); + + return time_after(jiffies, deadline); +} + +static void tt_local_entry_free_ref(struct tt_local_entry *tt_local_entry) +{ + if (atomic_dec_and_test(&tt_local_entry->refcount)) + kfree_rcu(tt_local_entry, rcu); +} + +static void tt_global_entry_free_ref(struct tt_global_entry *tt_global_entry) +{ + if (atomic_dec_and_test(&tt_global_entry->refcount)) + kfree_rcu(tt_global_entry, rcu); +} + +static void tt_local_event(struct bat_priv *bat_priv, const uint8_t *addr, + uint8_t flags) +{ + struct tt_change_node *tt_change_node; + + tt_change_node = kmalloc(sizeof(*tt_change_node), GFP_ATOMIC); + + if (!tt_change_node) + return; + + tt_change_node->change.flags = flags; + memcpy(tt_change_node->change.addr, addr, ETH_ALEN); + + spin_lock_bh(&bat_priv->tt_changes_list_lock); + /* track the change in the OGMinterval list */ + list_add_tail(&tt_change_node->list, &bat_priv->tt_changes_list); + atomic_inc(&bat_priv->tt_local_changes); + spin_unlock_bh(&bat_priv->tt_changes_list_lock); + + atomic_set(&bat_priv->tt_ogm_append_cnt, 0); +} + +int tt_len(int changes_num) +{ + return changes_num * sizeof(struct tt_change); +} + +static int tt_local_init(struct bat_priv *bat_priv) { if (bat_priv->tt_local_hash) return 1; @@ -120,116 +180,114 @@ int tt_local_init(struct bat_priv *bat_priv) if (!bat_priv->tt_local_hash) return 0; - atomic_set(&bat_priv->tt_local_changed, 0); - tt_local_start_timer(bat_priv); - return 1; } -void tt_local_add(struct net_device *soft_iface, uint8_t *addr) +void tt_local_add(struct net_device *soft_iface, const uint8_t *addr) { struct bat_priv *bat_priv = netdev_priv(soft_iface); - struct tt_local_entry *tt_local_entry; - struct tt_global_entry *tt_global_entry; - int required_bytes; + struct tt_local_entry *tt_local_entry = NULL; + struct tt_global_entry *tt_global_entry = NULL; - spin_lock_bh(&bat_priv->tt_lhash_lock); tt_local_entry = tt_local_hash_find(bat_priv, addr); - spin_unlock_bh(&bat_priv->tt_lhash_lock); if (tt_local_entry) { tt_local_entry->last_seen = jiffies; - return; - } - - /* only announce as many hosts as possible in the batman-packet and - space in batman_packet->num_tt That also should give a limit to - MAC-flooding. */ - required_bytes = (bat_priv->num_local_tt + 1) * ETH_ALEN; - required_bytes += BAT_PACKET_LEN; - - if ((required_bytes > ETH_DATA_LEN) || - (atomic_read(&bat_priv->aggregated_ogms) && - required_bytes > MAX_AGGREGATION_BYTES) || - (bat_priv->num_local_tt + 1 > 255)) { - bat_dbg(DBG_ROUTES, bat_priv, - "Can't add new local tt entry (%pM): " - "number of local tt entries exceeds packet size\n", - addr); - return; + goto out; } - bat_dbg(DBG_ROUTES, bat_priv, - "Creating new local tt entry: %pM\n", addr); - - tt_local_entry = kmalloc(sizeof(struct tt_local_entry), GFP_ATOMIC); + tt_local_entry = kmalloc(sizeof(*tt_local_entry), GFP_ATOMIC); if (!tt_local_entry) - return; + goto out; + + bat_dbg(DBG_TT, bat_priv, + "Creating new local tt entry: %pM (ttvn: %d)\n", addr, + (uint8_t)atomic_read(&bat_priv->ttvn)); memcpy(tt_local_entry->addr, addr, ETH_ALEN); tt_local_entry->last_seen = jiffies; + tt_local_entry->flags = NO_FLAGS; + atomic_set(&tt_local_entry->refcount, 2); /* the batman interface mac address should never be purged */ if (compare_eth(addr, soft_iface->dev_addr)) - tt_local_entry->never_purge = 1; - else - tt_local_entry->never_purge = 0; + tt_local_entry->flags |= TT_CLIENT_NOPURGE; - spin_lock_bh(&bat_priv->tt_lhash_lock); + tt_local_event(bat_priv, addr, tt_local_entry->flags); + + /* The local entry has to be marked as NEW to avoid to send it in + * a full table response going out before the next ttvn increment + * (consistency check) */ + tt_local_entry->flags |= TT_CLIENT_NEW; hash_add(bat_priv->tt_local_hash, compare_ltt, choose_orig, tt_local_entry, &tt_local_entry->hash_entry); - bat_priv->num_local_tt++; - atomic_set(&bat_priv->tt_local_changed, 1); - - spin_unlock_bh(&bat_priv->tt_lhash_lock); /* remove address from global hash if present */ - spin_lock_bh(&bat_priv->tt_ghash_lock); - tt_global_entry = tt_global_hash_find(bat_priv, addr); + /* Check whether it is a roaming! */ + if (tt_global_entry) { + /* This node is probably going to update its tt table */ + tt_global_entry->orig_node->tt_poss_change = true; + /* The global entry has to be marked as PENDING and has to be + * kept for consistency purpose */ + tt_global_entry->flags |= TT_CLIENT_PENDING; + send_roam_adv(bat_priv, tt_global_entry->addr, + tt_global_entry->orig_node); + } +out: + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); if (tt_global_entry) - _tt_global_del_orig(bat_priv, tt_global_entry, - "local tt received"); - - spin_unlock_bh(&bat_priv->tt_ghash_lock); + tt_global_entry_free_ref(tt_global_entry); } -int tt_local_fill_buffer(struct bat_priv *bat_priv, - unsigned char *buff, int buff_len) +int tt_changes_fill_buffer(struct bat_priv *bat_priv, + unsigned char *buff, int buff_len) { - struct hashtable_t *hash = bat_priv->tt_local_hash; - struct tt_local_entry *tt_local_entry; - struct hlist_node *node; - struct hlist_head *head; - int i, count = 0; + int count = 0, tot_changes = 0; + struct tt_change_node *entry, *safe; - spin_lock_bh(&bat_priv->tt_lhash_lock); + if (buff_len > 0) + tot_changes = buff_len / tt_len(1); - for (i = 0; i < hash->size; i++) { - head = &hash->table[i]; - - rcu_read_lock(); - hlist_for_each_entry_rcu(tt_local_entry, node, - head, hash_entry) { - if (buff_len < (count + 1) * ETH_ALEN) - break; - - memcpy(buff + (count * ETH_ALEN), tt_local_entry->addr, - ETH_ALEN); + spin_lock_bh(&bat_priv->tt_changes_list_lock); + atomic_set(&bat_priv->tt_local_changes, 0); + list_for_each_entry_safe(entry, safe, &bat_priv->tt_changes_list, + list) { + if (count < tot_changes) { + memcpy(buff + tt_len(count), + &entry->change, sizeof(struct tt_change)); count++; } - rcu_read_unlock(); + list_del(&entry->list); + kfree(entry); } + spin_unlock_bh(&bat_priv->tt_changes_list_lock); + + /* Keep the buffer for possible tt_request */ + spin_lock_bh(&bat_priv->tt_buff_lock); + kfree(bat_priv->tt_buff); + bat_priv->tt_buff_len = 0; + bat_priv->tt_buff = NULL; + /* We check whether this new OGM has no changes due to size + * problems */ + if (buff_len > 0) { + /** + * if kmalloc() fails we will reply with the full table + * instead of providing the diff + */ + bat_priv->tt_buff = kmalloc(buff_len, GFP_ATOMIC); + if (bat_priv->tt_buff) { + memcpy(bat_priv->tt_buff, buff, buff_len); + bat_priv->tt_buff_len = buff_len; + } + } + spin_unlock_bh(&bat_priv->tt_buff_lock); - /* if we did not get all new local tts see you next time ;-) */ - if (count == bat_priv->num_local_tt) - atomic_set(&bat_priv->tt_local_changed, 0); - - spin_unlock_bh(&bat_priv->tt_lhash_lock); - return count; + return tot_changes; } int tt_local_seq_print_text(struct seq_file *seq, void *offset) @@ -261,10 +319,8 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) } seq_printf(seq, "Locally retrieved addresses (from %s) " - "announced via TT:\n", - net_dev->name); - - spin_lock_bh(&bat_priv->tt_lhash_lock); + "announced via TT (TTVN: %u):\n", + net_dev->name, (uint8_t)atomic_read(&bat_priv->ttvn)); buf_size = 1; /* Estimate length for: " * xx:xx:xx:xx:xx:xx\n" */ @@ -279,7 +335,6 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) buff = kmalloc(buf_size, GFP_ATOMIC); if (!buff) { - spin_unlock_bh(&bat_priv->tt_lhash_lock); ret = -ENOMEM; goto out; } @@ -299,8 +354,6 @@ int tt_local_seq_print_text(struct seq_file *seq, void *offset) rcu_read_unlock(); } - spin_unlock_bh(&bat_priv->tt_lhash_lock); - seq_printf(seq, "%s", buff); kfree(buff); out: @@ -309,92 +362,109 @@ out: return ret; } -static void _tt_local_del(struct hlist_node *node, void *arg) +static void tt_local_set_pending(struct bat_priv *bat_priv, + struct tt_local_entry *tt_local_entry, + uint16_t flags) { - struct bat_priv *bat_priv = (struct bat_priv *)arg; - void *data = container_of(node, struct tt_local_entry, hash_entry); + tt_local_event(bat_priv, tt_local_entry->addr, + tt_local_entry->flags | flags); - kfree(data); - bat_priv->num_local_tt--; - atomic_set(&bat_priv->tt_local_changed, 1); + /* The local client has to be merked as "pending to be removed" but has + * to be kept in the table in order to send it in an full tables + * response issued before the net ttvn increment (consistency check) */ + tt_local_entry->flags |= TT_CLIENT_PENDING; } -static void tt_local_del(struct bat_priv *bat_priv, - struct tt_local_entry *tt_local_entry, - char *message) +void tt_local_remove(struct bat_priv *bat_priv, const uint8_t *addr, + const char *message, bool roaming) { - bat_dbg(DBG_ROUTES, bat_priv, "Deleting local tt entry (%pM): %s\n", - tt_local_entry->addr, message); - - hash_remove(bat_priv->tt_local_hash, compare_ltt, choose_orig, - tt_local_entry->addr); - _tt_local_del(&tt_local_entry->hash_entry, bat_priv); -} - -void tt_local_remove(struct bat_priv *bat_priv, - uint8_t *addr, char *message) -{ - struct tt_local_entry *tt_local_entry; - - spin_lock_bh(&bat_priv->tt_lhash_lock); + struct tt_local_entry *tt_local_entry = NULL; tt_local_entry = tt_local_hash_find(bat_priv, addr); + if (!tt_local_entry) + goto out; - if (tt_local_entry) - tt_local_del(bat_priv, tt_local_entry, message); + tt_local_set_pending(bat_priv, tt_local_entry, TT_CLIENT_DEL | + (roaming ? TT_CLIENT_ROAM : NO_FLAGS)); - spin_unlock_bh(&bat_priv->tt_lhash_lock); + bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) pending to be removed: " + "%s\n", tt_local_entry->addr, message); +out: + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); } -static void tt_local_purge(struct work_struct *work) +static void tt_local_purge(struct bat_priv *bat_priv) { - struct delayed_work *delayed_work = - container_of(work, struct delayed_work, work); - struct bat_priv *bat_priv = - container_of(delayed_work, struct bat_priv, tt_work); struct hashtable_t *hash = bat_priv->tt_local_hash; struct tt_local_entry *tt_local_entry; struct hlist_node *node, *node_tmp; struct hlist_head *head; - unsigned long timeout; + spinlock_t *list_lock; /* protects write access to the hash lists */ int i; - spin_lock_bh(&bat_priv->tt_lhash_lock); - for (i = 0; i < hash->size; i++) { head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + spin_lock_bh(list_lock); hlist_for_each_entry_safe(tt_local_entry, node, node_tmp, head, hash_entry) { - if (tt_local_entry->never_purge) + if (tt_local_entry->flags & TT_CLIENT_NOPURGE) continue; - timeout = tt_local_entry->last_seen; - timeout += TT_LOCAL_TIMEOUT * HZ; + /* entry already marked for deletion */ + if (tt_local_entry->flags & TT_CLIENT_PENDING) + continue; - if (time_before(jiffies, timeout)) + if (!is_out_of_time(tt_local_entry->last_seen, + TT_LOCAL_TIMEOUT * 1000)) continue; - tt_local_del(bat_priv, tt_local_entry, - "address timed out"); + tt_local_set_pending(bat_priv, tt_local_entry, + TT_CLIENT_DEL); + bat_dbg(DBG_TT, bat_priv, "Local tt entry (%pM) " + "pending to be removed: timed out\n", + tt_local_entry->addr); } + spin_unlock_bh(list_lock); } - spin_unlock_bh(&bat_priv->tt_lhash_lock); - tt_local_start_timer(bat_priv); } -void tt_local_free(struct bat_priv *bat_priv) +static void tt_local_table_free(struct bat_priv *bat_priv) { + struct hashtable_t *hash; + spinlock_t *list_lock; /* protects write access to the hash lists */ + struct tt_local_entry *tt_local_entry; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + int i; + if (!bat_priv->tt_local_hash) return; - cancel_delayed_work_sync(&bat_priv->tt_work); - hash_delete(bat_priv->tt_local_hash, _tt_local_del, bat_priv); + hash = bat_priv->tt_local_hash; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(tt_local_entry, node, node_tmp, + head, hash_entry) { + hlist_del_rcu(node); + tt_local_entry_free_ref(tt_local_entry); + } + spin_unlock_bh(list_lock); + } + + hash_destroy(hash); + bat_priv->tt_local_hash = NULL; } -int tt_global_init(struct bat_priv *bat_priv) +static int tt_global_init(struct bat_priv *bat_priv) { if (bat_priv->tt_global_hash) return 1; @@ -407,74 +477,78 @@ int tt_global_init(struct bat_priv *bat_priv) return 1; } -void tt_global_add_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, - unsigned char *tt_buff, int tt_buff_len) +static void tt_changes_list_free(struct bat_priv *bat_priv) { - struct tt_global_entry *tt_global_entry; - struct tt_local_entry *tt_local_entry; - int tt_buff_count = 0; - unsigned char *tt_ptr; + struct tt_change_node *entry, *safe; - while ((tt_buff_count + 1) * ETH_ALEN <= tt_buff_len) { - spin_lock_bh(&bat_priv->tt_ghash_lock); + spin_lock_bh(&bat_priv->tt_changes_list_lock); - tt_ptr = tt_buff + (tt_buff_count * ETH_ALEN); - tt_global_entry = tt_global_hash_find(bat_priv, tt_ptr); - - if (!tt_global_entry) { - spin_unlock_bh(&bat_priv->tt_ghash_lock); - - tt_global_entry = - kmalloc(sizeof(struct tt_global_entry), - GFP_ATOMIC); - - if (!tt_global_entry) - break; + list_for_each_entry_safe(entry, safe, &bat_priv->tt_changes_list, + list) { + list_del(&entry->list); + kfree(entry); + } - memcpy(tt_global_entry->addr, tt_ptr, ETH_ALEN); + atomic_set(&bat_priv->tt_local_changes, 0); + spin_unlock_bh(&bat_priv->tt_changes_list_lock); +} - bat_dbg(DBG_ROUTES, bat_priv, - "Creating new global tt entry: " - "%pM (via %pM)\n", - tt_global_entry->addr, orig_node->orig); +/* caller must hold orig_node refcount */ +int tt_global_add(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *tt_addr, uint8_t ttvn, bool roaming) +{ + struct tt_global_entry *tt_global_entry; + struct orig_node *orig_node_tmp; + int ret = 0; - spin_lock_bh(&bat_priv->tt_ghash_lock); - hash_add(bat_priv->tt_global_hash, compare_gtt, - choose_orig, tt_global_entry, - &tt_global_entry->hash_entry); + tt_global_entry = tt_global_hash_find(bat_priv, tt_addr); - } + if (!tt_global_entry) { + tt_global_entry = + kmalloc(sizeof(*tt_global_entry), + GFP_ATOMIC); + if (!tt_global_entry) + goto out; + memcpy(tt_global_entry->addr, tt_addr, ETH_ALEN); + /* Assign the new orig_node */ + atomic_inc(&orig_node->refcount); tt_global_entry->orig_node = orig_node; - spin_unlock_bh(&bat_priv->tt_ghash_lock); - - /* remove address from local hash if present */ - spin_lock_bh(&bat_priv->tt_lhash_lock); - - tt_ptr = tt_buff + (tt_buff_count * ETH_ALEN); - tt_local_entry = tt_local_hash_find(bat_priv, tt_ptr); - - if (tt_local_entry) - tt_local_del(bat_priv, tt_local_entry, - "global tt received"); - - spin_unlock_bh(&bat_priv->tt_lhash_lock); - - tt_buff_count++; + tt_global_entry->ttvn = ttvn; + tt_global_entry->flags = NO_FLAGS; + tt_global_entry->roam_at = 0; + atomic_set(&tt_global_entry->refcount, 2); + + hash_add(bat_priv->tt_global_hash, compare_gtt, + choose_orig, tt_global_entry, + &tt_global_entry->hash_entry); + atomic_inc(&orig_node->tt_size); + } else { + if (tt_global_entry->orig_node != orig_node) { + atomic_dec(&tt_global_entry->orig_node->tt_size); + orig_node_tmp = tt_global_entry->orig_node; + atomic_inc(&orig_node->refcount); + tt_global_entry->orig_node = orig_node; + orig_node_free_ref(orig_node_tmp); + atomic_inc(&orig_node->tt_size); + } + tt_global_entry->ttvn = ttvn; + tt_global_entry->flags = NO_FLAGS; + tt_global_entry->roam_at = 0; } - /* initialize, and overwrite if malloc succeeds */ - orig_node->tt_buff = NULL; - orig_node->tt_buff_len = 0; + bat_dbg(DBG_TT, bat_priv, + "Creating new global tt entry: %pM (via %pM)\n", + tt_global_entry->addr, orig_node->orig); - if (tt_buff_len > 0) { - orig_node->tt_buff = kmalloc(tt_buff_len, GFP_ATOMIC); - if (orig_node->tt_buff) { - memcpy(orig_node->tt_buff, tt_buff, tt_buff_len); - orig_node->tt_buff_len = tt_buff_len; - } - } + /* remove address from local hash if present */ + tt_local_remove(bat_priv, tt_global_entry->addr, + "global tt received", roaming); + ret = 1; +out: + if (tt_global_entry) + tt_global_entry_free_ref(tt_global_entry); + return ret; } int tt_global_seq_print_text(struct seq_file *seq, void *offset) @@ -508,26 +582,27 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) seq_printf(seq, "Globally announced TT entries received via the mesh %s\n", net_dev->name); - - spin_lock_bh(&bat_priv->tt_ghash_lock); + seq_printf(seq, " %-13s %s %-15s %s\n", + "Client", "(TTVN)", "Originator", "(Curr TTVN)"); buf_size = 1; - /* Estimate length for: " * xx:xx:xx:xx:xx:xx via xx:xx:xx:xx:xx:xx\n"*/ + /* Estimate length for: " * xx:xx:xx:xx:xx:xx (ttvn) via + * xx:xx:xx:xx:xx:xx (cur_ttvn)\n"*/ for (i = 0; i < hash->size; i++) { head = &hash->table[i]; rcu_read_lock(); __hlist_for_each_rcu(node, head) - buf_size += 43; + buf_size += 59; rcu_read_unlock(); } buff = kmalloc(buf_size, GFP_ATOMIC); if (!buff) { - spin_unlock_bh(&bat_priv->tt_ghash_lock); ret = -ENOMEM; goto out; } + buff[0] = '\0'; pos = 0; @@ -537,16 +612,18 @@ int tt_global_seq_print_text(struct seq_file *seq, void *offset) rcu_read_lock(); hlist_for_each_entry_rcu(tt_global_entry, node, head, hash_entry) { - pos += snprintf(buff + pos, 44, - " * %pM via %pM\n", + pos += snprintf(buff + pos, 61, + " * %pM (%3u) via %pM (%3u)\n", tt_global_entry->addr, - tt_global_entry->orig_node->orig); + tt_global_entry->ttvn, + tt_global_entry->orig_node->orig, + (uint8_t) atomic_read( + &tt_global_entry->orig_node-> + last_ttvn)); } rcu_read_unlock(); } - spin_unlock_bh(&bat_priv->tt_ghash_lock); - seq_printf(seq, "%s", buff); kfree(buff); out: @@ -555,84 +632,1091 @@ out: return ret; } -static void _tt_global_del_orig(struct bat_priv *bat_priv, - struct tt_global_entry *tt_global_entry, - char *message) +static void _tt_global_del(struct bat_priv *bat_priv, + struct tt_global_entry *tt_global_entry, + const char *message) { - bat_dbg(DBG_ROUTES, bat_priv, + if (!tt_global_entry) + goto out; + + bat_dbg(DBG_TT, bat_priv, "Deleting global tt entry %pM (via %pM): %s\n", tt_global_entry->addr, tt_global_entry->orig_node->orig, message); + atomic_dec(&tt_global_entry->orig_node->tt_size); + hash_remove(bat_priv->tt_global_hash, compare_gtt, choose_orig, tt_global_entry->addr); - kfree(tt_global_entry); +out: + if (tt_global_entry) + tt_global_entry_free_ref(tt_global_entry); } -void tt_global_del_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, char *message) +void tt_global_del(struct bat_priv *bat_priv, + struct orig_node *orig_node, const unsigned char *addr, + const char *message, bool roaming) { - struct tt_global_entry *tt_global_entry; - int tt_buff_count = 0; - unsigned char *tt_ptr; + struct tt_global_entry *tt_global_entry = NULL; - if (orig_node->tt_buff_len == 0) - return; + tt_global_entry = tt_global_hash_find(bat_priv, addr); + if (!tt_global_entry) + goto out; - spin_lock_bh(&bat_priv->tt_ghash_lock); + if (tt_global_entry->orig_node == orig_node) { + if (roaming) { + tt_global_entry->flags |= TT_CLIENT_ROAM; + tt_global_entry->roam_at = jiffies; + goto out; + } + _tt_global_del(bat_priv, tt_global_entry, message); + } +out: + if (tt_global_entry) + tt_global_entry_free_ref(tt_global_entry); +} - while ((tt_buff_count + 1) * ETH_ALEN <= orig_node->tt_buff_len) { - tt_ptr = orig_node->tt_buff + (tt_buff_count * ETH_ALEN); - tt_global_entry = tt_global_hash_find(bat_priv, tt_ptr); +void tt_global_del_orig(struct bat_priv *bat_priv, + struct orig_node *orig_node, const char *message) +{ + struct tt_global_entry *tt_global_entry; + int i; + struct hashtable_t *hash = bat_priv->tt_global_hash; + struct hlist_node *node, *safe; + struct hlist_head *head; + spinlock_t *list_lock; /* protects write access to the hash lists */ - if ((tt_global_entry) && - (tt_global_entry->orig_node == orig_node)) - _tt_global_del_orig(bat_priv, tt_global_entry, - message); + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; - tt_buff_count++; + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(tt_global_entry, node, safe, + head, hash_entry) { + if (tt_global_entry->orig_node == orig_node) { + bat_dbg(DBG_TT, bat_priv, + "Deleting global tt entry %pM " + "(via %pM): originator time out\n", + tt_global_entry->addr, + tt_global_entry->orig_node->orig); + hlist_del_rcu(node); + tt_global_entry_free_ref(tt_global_entry); + } + } + spin_unlock_bh(list_lock); } - - spin_unlock_bh(&bat_priv->tt_ghash_lock); - - orig_node->tt_buff_len = 0; - kfree(orig_node->tt_buff); - orig_node->tt_buff = NULL; + atomic_set(&orig_node->tt_size, 0); } -static void tt_global_del(struct hlist_node *node, void *arg) +static void tt_global_roam_purge(struct bat_priv *bat_priv) { - void *data = container_of(node, struct tt_global_entry, hash_entry); + struct hashtable_t *hash = bat_priv->tt_global_hash; + struct tt_global_entry *tt_global_entry; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + spinlock_t *list_lock; /* protects write access to the hash lists */ + int i; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(tt_global_entry, node, node_tmp, + head, hash_entry) { + if (!(tt_global_entry->flags & TT_CLIENT_ROAM)) + continue; + if (!is_out_of_time(tt_global_entry->roam_at, + TT_CLIENT_ROAM_TIMEOUT * 1000)) + continue; + + bat_dbg(DBG_TT, bat_priv, "Deleting global " + "tt entry (%pM): Roaming timeout\n", + tt_global_entry->addr); + atomic_dec(&tt_global_entry->orig_node->tt_size); + hlist_del_rcu(node); + tt_global_entry_free_ref(tt_global_entry); + } + spin_unlock_bh(list_lock); + } - kfree(data); } -void tt_global_free(struct bat_priv *bat_priv) +static void tt_global_table_free(struct bat_priv *bat_priv) { + struct hashtable_t *hash; + spinlock_t *list_lock; /* protects write access to the hash lists */ + struct tt_global_entry *tt_global_entry; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + int i; + if (!bat_priv->tt_global_hash) return; - hash_delete(bat_priv->tt_global_hash, tt_global_del, NULL); + hash = bat_priv->tt_global_hash; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(tt_global_entry, node, node_tmp, + head, hash_entry) { + hlist_del_rcu(node); + tt_global_entry_free_ref(tt_global_entry); + } + spin_unlock_bh(list_lock); + } + + hash_destroy(hash); + bat_priv->tt_global_hash = NULL; } -struct orig_node *transtable_search(struct bat_priv *bat_priv, uint8_t *addr) +struct orig_node *transtable_search(struct bat_priv *bat_priv, + const uint8_t *addr) { struct tt_global_entry *tt_global_entry; struct orig_node *orig_node = NULL; - spin_lock_bh(&bat_priv->tt_ghash_lock); tt_global_entry = tt_global_hash_find(bat_priv, addr); if (!tt_global_entry) goto out; if (!atomic_inc_not_zero(&tt_global_entry->orig_node->refcount)) - goto out; + goto free_tt; + + /* A global client marked as PENDING has already moved from that + * originator */ + if (tt_global_entry->flags & TT_CLIENT_PENDING) + goto free_tt; orig_node = tt_global_entry->orig_node; +free_tt: + tt_global_entry_free_ref(tt_global_entry); out: - spin_unlock_bh(&bat_priv->tt_ghash_lock); return orig_node; } + +/* Calculates the checksum of the local table of a given orig_node */ +uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node) +{ + uint16_t total = 0, total_one; + struct hashtable_t *hash = bat_priv->tt_global_hash; + struct tt_global_entry *tt_global_entry; + struct hlist_node *node; + struct hlist_head *head; + int i, j; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tt_global_entry, node, + head, hash_entry) { + if (compare_eth(tt_global_entry->orig_node, + orig_node)) { + /* Roaming clients are in the global table for + * consistency only. They don't have to be + * taken into account while computing the + * global crc */ + if (tt_global_entry->flags & TT_CLIENT_ROAM) + continue; + total_one = 0; + for (j = 0; j < ETH_ALEN; j++) + total_one = crc16_byte(total_one, + tt_global_entry->addr[j]); + total ^= total_one; + } + } + rcu_read_unlock(); + } + + return total; +} + +/* Calculates the checksum of the local table */ +uint16_t tt_local_crc(struct bat_priv *bat_priv) +{ + uint16_t total = 0, total_one; + struct hashtable_t *hash = bat_priv->tt_local_hash; + struct tt_local_entry *tt_local_entry; + struct hlist_node *node; + struct hlist_head *head; + int i, j; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tt_local_entry, node, + head, hash_entry) { + /* not yet committed clients have not to be taken into + * account while computing the CRC */ + if (tt_local_entry->flags & TT_CLIENT_NEW) + continue; + total_one = 0; + for (j = 0; j < ETH_ALEN; j++) + total_one = crc16_byte(total_one, + tt_local_entry->addr[j]); + total ^= total_one; + } + rcu_read_unlock(); + } + + return total; +} + +static void tt_req_list_free(struct bat_priv *bat_priv) +{ + struct tt_req_node *node, *safe; + + spin_lock_bh(&bat_priv->tt_req_list_lock); + + list_for_each_entry_safe(node, safe, &bat_priv->tt_req_list, list) { + list_del(&node->list); + kfree(node); + } + + spin_unlock_bh(&bat_priv->tt_req_list_lock); +} + +void tt_save_orig_buffer(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *tt_buff, uint8_t tt_num_changes) +{ + uint16_t tt_buff_len = tt_len(tt_num_changes); + + /* Replace the old buffer only if I received something in the + * last OGM (the OGM could carry no changes) */ + spin_lock_bh(&orig_node->tt_buff_lock); + if (tt_buff_len > 0) { + kfree(orig_node->tt_buff); + orig_node->tt_buff_len = 0; + orig_node->tt_buff = kmalloc(tt_buff_len, GFP_ATOMIC); + if (orig_node->tt_buff) { + memcpy(orig_node->tt_buff, tt_buff, tt_buff_len); + orig_node->tt_buff_len = tt_buff_len; + } + } + spin_unlock_bh(&orig_node->tt_buff_lock); +} + +static void tt_req_purge(struct bat_priv *bat_priv) +{ + struct tt_req_node *node, *safe; + + spin_lock_bh(&bat_priv->tt_req_list_lock); + list_for_each_entry_safe(node, safe, &bat_priv->tt_req_list, list) { + if (is_out_of_time(node->issued_at, + TT_REQUEST_TIMEOUT * 1000)) { + list_del(&node->list); + kfree(node); + } + } + spin_unlock_bh(&bat_priv->tt_req_list_lock); +} + +/* returns the pointer to the new tt_req_node struct if no request + * has already been issued for this orig_node, NULL otherwise */ +static struct tt_req_node *new_tt_req_node(struct bat_priv *bat_priv, + struct orig_node *orig_node) +{ + struct tt_req_node *tt_req_node_tmp, *tt_req_node = NULL; + + spin_lock_bh(&bat_priv->tt_req_list_lock); + list_for_each_entry(tt_req_node_tmp, &bat_priv->tt_req_list, list) { + if (compare_eth(tt_req_node_tmp, orig_node) && + !is_out_of_time(tt_req_node_tmp->issued_at, + TT_REQUEST_TIMEOUT * 1000)) + goto unlock; + } + + tt_req_node = kmalloc(sizeof(*tt_req_node), GFP_ATOMIC); + if (!tt_req_node) + goto unlock; + + memcpy(tt_req_node->addr, orig_node->orig, ETH_ALEN); + tt_req_node->issued_at = jiffies; + + list_add(&tt_req_node->list, &bat_priv->tt_req_list); +unlock: + spin_unlock_bh(&bat_priv->tt_req_list_lock); + return tt_req_node; +} + +/* data_ptr is useless here, but has to be kept to respect the prototype */ +static int tt_local_valid_entry(const void *entry_ptr, const void *data_ptr) +{ + const struct tt_local_entry *tt_local_entry = entry_ptr; + + if (tt_local_entry->flags & TT_CLIENT_NEW) + return 0; + return 1; +} + +static int tt_global_valid_entry(const void *entry_ptr, const void *data_ptr) +{ + const struct tt_global_entry *tt_global_entry = entry_ptr; + const struct orig_node *orig_node = data_ptr; + + if (tt_global_entry->flags & TT_CLIENT_ROAM) + return 0; + + return (tt_global_entry->orig_node == orig_node); +} + +static struct sk_buff *tt_response_fill_table(uint16_t tt_len, uint8_t ttvn, + struct hashtable_t *hash, + struct hard_iface *primary_if, + int (*valid_cb)(const void *, + const void *), + void *cb_data) +{ + struct tt_local_entry *tt_local_entry; + struct tt_query_packet *tt_response; + struct tt_change *tt_change; + struct hlist_node *node; + struct hlist_head *head; + struct sk_buff *skb = NULL; + uint16_t tt_tot, tt_count; + ssize_t tt_query_size = sizeof(struct tt_query_packet); + int i; + + if (tt_query_size + tt_len > primary_if->soft_iface->mtu) { + tt_len = primary_if->soft_iface->mtu - tt_query_size; + tt_len -= tt_len % sizeof(struct tt_change); + } + tt_tot = tt_len / sizeof(struct tt_change); + + skb = dev_alloc_skb(tt_query_size + tt_len + ETH_HLEN); + if (!skb) + goto out; + + skb_reserve(skb, ETH_HLEN); + tt_response = (struct tt_query_packet *)skb_put(skb, + tt_query_size + tt_len); + tt_response->ttvn = ttvn; + tt_response->tt_data = htons(tt_tot); + + tt_change = (struct tt_change *)(skb->data + tt_query_size); + tt_count = 0; + + rcu_read_lock(); + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + hlist_for_each_entry_rcu(tt_local_entry, node, + head, hash_entry) { + if (tt_count == tt_tot) + break; + + if ((valid_cb) && (!valid_cb(tt_local_entry, cb_data))) + continue; + + memcpy(tt_change->addr, tt_local_entry->addr, ETH_ALEN); + tt_change->flags = NO_FLAGS; + + tt_count++; + tt_change++; + } + } + rcu_read_unlock(); + +out: + return skb; +} + +int send_tt_request(struct bat_priv *bat_priv, struct orig_node *dst_orig_node, + uint8_t ttvn, uint16_t tt_crc, bool full_table) +{ + struct sk_buff *skb = NULL; + struct tt_query_packet *tt_request; + struct neigh_node *neigh_node = NULL; + struct hard_iface *primary_if; + struct tt_req_node *tt_req_node = NULL; + int ret = 1; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + /* The new tt_req will be issued only if I'm not waiting for a + * reply from the same orig_node yet */ + tt_req_node = new_tt_req_node(bat_priv, dst_orig_node); + if (!tt_req_node) + goto out; + + skb = dev_alloc_skb(sizeof(struct tt_query_packet) + ETH_HLEN); + if (!skb) + goto out; + + skb_reserve(skb, ETH_HLEN); + + tt_request = (struct tt_query_packet *)skb_put(skb, + sizeof(struct tt_query_packet)); + + tt_request->packet_type = BAT_TT_QUERY; + tt_request->version = COMPAT_VERSION; + memcpy(tt_request->src, primary_if->net_dev->dev_addr, ETH_ALEN); + memcpy(tt_request->dst, dst_orig_node->orig, ETH_ALEN); + tt_request->ttl = TTL; + tt_request->ttvn = ttvn; + tt_request->tt_data = tt_crc; + tt_request->flags = TT_REQUEST; + + if (full_table) + tt_request->flags |= TT_FULL_TABLE; + + neigh_node = orig_node_get_router(dst_orig_node); + if (!neigh_node) + goto out; + + bat_dbg(DBG_TT, bat_priv, "Sending TT_REQUEST to %pM via %pM " + "[%c]\n", dst_orig_node->orig, neigh_node->addr, + (full_table ? 'F' : '.')); + + send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + ret = 0; + +out: + if (neigh_node) + neigh_node_free_ref(neigh_node); + if (primary_if) + hardif_free_ref(primary_if); + if (ret) + kfree_skb(skb); + if (ret && tt_req_node) { + spin_lock_bh(&bat_priv->tt_req_list_lock); + list_del(&tt_req_node->list); + spin_unlock_bh(&bat_priv->tt_req_list_lock); + kfree(tt_req_node); + } + return ret; +} + +static bool send_other_tt_response(struct bat_priv *bat_priv, + struct tt_query_packet *tt_request) +{ + struct orig_node *req_dst_orig_node = NULL, *res_dst_orig_node = NULL; + struct neigh_node *neigh_node = NULL; + struct hard_iface *primary_if = NULL; + uint8_t orig_ttvn, req_ttvn, ttvn; + int ret = false; + unsigned char *tt_buff; + bool full_table; + uint16_t tt_len, tt_tot; + struct sk_buff *skb = NULL; + struct tt_query_packet *tt_response; + + bat_dbg(DBG_TT, bat_priv, + "Received TT_REQUEST from %pM for " + "ttvn: %u (%pM) [%c]\n", tt_request->src, + tt_request->ttvn, tt_request->dst, + (tt_request->flags & TT_FULL_TABLE ? 'F' : '.')); + + /* Let's get the orig node of the REAL destination */ + req_dst_orig_node = get_orig_node(bat_priv, tt_request->dst); + if (!req_dst_orig_node) + goto out; + + res_dst_orig_node = get_orig_node(bat_priv, tt_request->src); + if (!res_dst_orig_node) + goto out; + + neigh_node = orig_node_get_router(res_dst_orig_node); + if (!neigh_node) + goto out; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + orig_ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn); + req_ttvn = tt_request->ttvn; + + /* I have not the requested data */ + if (orig_ttvn != req_ttvn || + tt_request->tt_data != req_dst_orig_node->tt_crc) + goto out; + + /* If it has explicitly been requested the full table */ + if (tt_request->flags & TT_FULL_TABLE || + !req_dst_orig_node->tt_buff) + full_table = true; + else + full_table = false; + + /* In this version, fragmentation is not implemented, then + * I'll send only one packet with as much TT entries as I can */ + if (!full_table) { + spin_lock_bh(&req_dst_orig_node->tt_buff_lock); + tt_len = req_dst_orig_node->tt_buff_len; + tt_tot = tt_len / sizeof(struct tt_change); + + skb = dev_alloc_skb(sizeof(struct tt_query_packet) + + tt_len + ETH_HLEN); + if (!skb) + goto unlock; + + skb_reserve(skb, ETH_HLEN); + tt_response = (struct tt_query_packet *)skb_put(skb, + sizeof(struct tt_query_packet) + tt_len); + tt_response->ttvn = req_ttvn; + tt_response->tt_data = htons(tt_tot); + + tt_buff = skb->data + sizeof(struct tt_query_packet); + /* Copy the last orig_node's OGM buffer */ + memcpy(tt_buff, req_dst_orig_node->tt_buff, + req_dst_orig_node->tt_buff_len); + + spin_unlock_bh(&req_dst_orig_node->tt_buff_lock); + } else { + tt_len = (uint16_t)atomic_read(&req_dst_orig_node->tt_size) * + sizeof(struct tt_change); + ttvn = (uint8_t)atomic_read(&req_dst_orig_node->last_ttvn); + + skb = tt_response_fill_table(tt_len, ttvn, + bat_priv->tt_global_hash, + primary_if, tt_global_valid_entry, + req_dst_orig_node); + if (!skb) + goto out; + + tt_response = (struct tt_query_packet *)skb->data; + } + + tt_response->packet_type = BAT_TT_QUERY; + tt_response->version = COMPAT_VERSION; + tt_response->ttl = TTL; + memcpy(tt_response->src, req_dst_orig_node->orig, ETH_ALEN); + memcpy(tt_response->dst, tt_request->src, ETH_ALEN); + tt_response->flags = TT_RESPONSE; + + if (full_table) + tt_response->flags |= TT_FULL_TABLE; + + bat_dbg(DBG_TT, bat_priv, + "Sending TT_RESPONSE %pM via %pM for %pM (ttvn: %u)\n", + res_dst_orig_node->orig, neigh_node->addr, + req_dst_orig_node->orig, req_ttvn); + + send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + ret = true; + goto out; + +unlock: + spin_unlock_bh(&req_dst_orig_node->tt_buff_lock); + +out: + if (res_dst_orig_node) + orig_node_free_ref(res_dst_orig_node); + if (req_dst_orig_node) + orig_node_free_ref(req_dst_orig_node); + if (neigh_node) + neigh_node_free_ref(neigh_node); + if (primary_if) + hardif_free_ref(primary_if); + if (!ret) + kfree_skb(skb); + return ret; + +} +static bool send_my_tt_response(struct bat_priv *bat_priv, + struct tt_query_packet *tt_request) +{ + struct orig_node *orig_node = NULL; + struct neigh_node *neigh_node = NULL; + struct hard_iface *primary_if = NULL; + uint8_t my_ttvn, req_ttvn, ttvn; + int ret = false; + unsigned char *tt_buff; + bool full_table; + uint16_t tt_len, tt_tot; + struct sk_buff *skb = NULL; + struct tt_query_packet *tt_response; + + bat_dbg(DBG_TT, bat_priv, + "Received TT_REQUEST from %pM for " + "ttvn: %u (me) [%c]\n", tt_request->src, + tt_request->ttvn, + (tt_request->flags & TT_FULL_TABLE ? 'F' : '.')); + + + my_ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); + req_ttvn = tt_request->ttvn; + + orig_node = get_orig_node(bat_priv, tt_request->src); + if (!orig_node) + goto out; + + neigh_node = orig_node_get_router(orig_node); + if (!neigh_node) + goto out; + + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + + /* If the full table has been explicitly requested or the gap + * is too big send the whole local translation table */ + if (tt_request->flags & TT_FULL_TABLE || my_ttvn != req_ttvn || + !bat_priv->tt_buff) + full_table = true; + else + full_table = false; + + /* In this version, fragmentation is not implemented, then + * I'll send only one packet with as much TT entries as I can */ + if (!full_table) { + spin_lock_bh(&bat_priv->tt_buff_lock); + tt_len = bat_priv->tt_buff_len; + tt_tot = tt_len / sizeof(struct tt_change); + + skb = dev_alloc_skb(sizeof(struct tt_query_packet) + + tt_len + ETH_HLEN); + if (!skb) + goto unlock; + + skb_reserve(skb, ETH_HLEN); + tt_response = (struct tt_query_packet *)skb_put(skb, + sizeof(struct tt_query_packet) + tt_len); + tt_response->ttvn = req_ttvn; + tt_response->tt_data = htons(tt_tot); + + tt_buff = skb->data + sizeof(struct tt_query_packet); + memcpy(tt_buff, bat_priv->tt_buff, + bat_priv->tt_buff_len); + spin_unlock_bh(&bat_priv->tt_buff_lock); + } else { + tt_len = (uint16_t)atomic_read(&bat_priv->num_local_tt) * + sizeof(struct tt_change); + ttvn = (uint8_t)atomic_read(&bat_priv->ttvn); + + skb = tt_response_fill_table(tt_len, ttvn, + bat_priv->tt_local_hash, + primary_if, tt_local_valid_entry, + NULL); + if (!skb) + goto out; + + tt_response = (struct tt_query_packet *)skb->data; + } + + tt_response->packet_type = BAT_TT_QUERY; + tt_response->version = COMPAT_VERSION; + tt_response->ttl = TTL; + memcpy(tt_response->src, primary_if->net_dev->dev_addr, ETH_ALEN); + memcpy(tt_response->dst, tt_request->src, ETH_ALEN); + tt_response->flags = TT_RESPONSE; + + if (full_table) + tt_response->flags |= TT_FULL_TABLE; + + bat_dbg(DBG_TT, bat_priv, + "Sending TT_RESPONSE to %pM via %pM [%c]\n", + orig_node->orig, neigh_node->addr, + (tt_response->flags & TT_FULL_TABLE ? 'F' : '.')); + + send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + ret = true; + goto out; + +unlock: + spin_unlock_bh(&bat_priv->tt_buff_lock); +out: + if (orig_node) + orig_node_free_ref(orig_node); + if (neigh_node) + neigh_node_free_ref(neigh_node); + if (primary_if) + hardif_free_ref(primary_if); + if (!ret) + kfree_skb(skb); + /* This packet was for me, so it doesn't need to be re-routed */ + return true; +} + +bool send_tt_response(struct bat_priv *bat_priv, + struct tt_query_packet *tt_request) +{ + if (is_my_mac(tt_request->dst)) + return send_my_tt_response(bat_priv, tt_request); + else + return send_other_tt_response(bat_priv, tt_request); +} + +static void _tt_update_changes(struct bat_priv *bat_priv, + struct orig_node *orig_node, + struct tt_change *tt_change, + uint16_t tt_num_changes, uint8_t ttvn) +{ + int i; + + for (i = 0; i < tt_num_changes; i++) { + if ((tt_change + i)->flags & TT_CLIENT_DEL) + tt_global_del(bat_priv, orig_node, + (tt_change + i)->addr, + "tt removed by changes", + (tt_change + i)->flags & TT_CLIENT_ROAM); + else + if (!tt_global_add(bat_priv, orig_node, + (tt_change + i)->addr, ttvn, false)) + /* In case of problem while storing a + * global_entry, we stop the updating + * procedure without committing the + * ttvn change. This will avoid to send + * corrupted data on tt_request + */ + return; + } +} + +static void tt_fill_gtable(struct bat_priv *bat_priv, + struct tt_query_packet *tt_response) +{ + struct orig_node *orig_node = NULL; + + orig_node = orig_hash_find(bat_priv, tt_response->src); + if (!orig_node) + goto out; + + /* Purge the old table first.. */ + tt_global_del_orig(bat_priv, orig_node, "Received full table"); + + _tt_update_changes(bat_priv, orig_node, + (struct tt_change *)(tt_response + 1), + tt_response->tt_data, tt_response->ttvn); + + spin_lock_bh(&orig_node->tt_buff_lock); + kfree(orig_node->tt_buff); + orig_node->tt_buff_len = 0; + orig_node->tt_buff = NULL; + spin_unlock_bh(&orig_node->tt_buff_lock); + + atomic_set(&orig_node->last_ttvn, tt_response->ttvn); + +out: + if (orig_node) + orig_node_free_ref(orig_node); +} + +void tt_update_changes(struct bat_priv *bat_priv, struct orig_node *orig_node, + uint16_t tt_num_changes, uint8_t ttvn, + struct tt_change *tt_change) +{ + _tt_update_changes(bat_priv, orig_node, tt_change, tt_num_changes, + ttvn); + + tt_save_orig_buffer(bat_priv, orig_node, (unsigned char *)tt_change, + tt_num_changes); + atomic_set(&orig_node->last_ttvn, ttvn); +} + +bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr) +{ + struct tt_local_entry *tt_local_entry = NULL; + bool ret = false; + + tt_local_entry = tt_local_hash_find(bat_priv, addr); + if (!tt_local_entry) + goto out; + /* Check if the client has been logically deleted (but is kept for + * consistency purpose) */ + if (tt_local_entry->flags & TT_CLIENT_PENDING) + goto out; + ret = true; +out: + if (tt_local_entry) + tt_local_entry_free_ref(tt_local_entry); + return ret; +} + +void handle_tt_response(struct bat_priv *bat_priv, + struct tt_query_packet *tt_response) +{ + struct tt_req_node *node, *safe; + struct orig_node *orig_node = NULL; + + bat_dbg(DBG_TT, bat_priv, "Received TT_RESPONSE from %pM for " + "ttvn %d t_size: %d [%c]\n", + tt_response->src, tt_response->ttvn, + tt_response->tt_data, + (tt_response->flags & TT_FULL_TABLE ? 'F' : '.')); + + orig_node = orig_hash_find(bat_priv, tt_response->src); + if (!orig_node) + goto out; + + if (tt_response->flags & TT_FULL_TABLE) + tt_fill_gtable(bat_priv, tt_response); + else + tt_update_changes(bat_priv, orig_node, tt_response->tt_data, + tt_response->ttvn, + (struct tt_change *)(tt_response + 1)); + + /* Delete the tt_req_node from pending tt_requests list */ + spin_lock_bh(&bat_priv->tt_req_list_lock); + list_for_each_entry_safe(node, safe, &bat_priv->tt_req_list, list) { + if (!compare_eth(node->addr, tt_response->src)) + continue; + list_del(&node->list); + kfree(node); + } + spin_unlock_bh(&bat_priv->tt_req_list_lock); + + /* Recalculate the CRC for this orig_node and store it */ + orig_node->tt_crc = tt_global_crc(bat_priv, orig_node); + /* Roaming phase is over: tables are in sync again. I can + * unset the flag */ + orig_node->tt_poss_change = false; +out: + if (orig_node) + orig_node_free_ref(orig_node); +} + +int tt_init(struct bat_priv *bat_priv) +{ + if (!tt_local_init(bat_priv)) + return 0; + + if (!tt_global_init(bat_priv)) + return 0; + + tt_start_timer(bat_priv); + + return 1; +} + +static void tt_roam_list_free(struct bat_priv *bat_priv) +{ + struct tt_roam_node *node, *safe; + + spin_lock_bh(&bat_priv->tt_roam_list_lock); + + list_for_each_entry_safe(node, safe, &bat_priv->tt_roam_list, list) { + list_del(&node->list); + kfree(node); + } + + spin_unlock_bh(&bat_priv->tt_roam_list_lock); +} + +static void tt_roam_purge(struct bat_priv *bat_priv) +{ + struct tt_roam_node *node, *safe; + + spin_lock_bh(&bat_priv->tt_roam_list_lock); + list_for_each_entry_safe(node, safe, &bat_priv->tt_roam_list, list) { + if (!is_out_of_time(node->first_time, + ROAMING_MAX_TIME * 1000)) + continue; + + list_del(&node->list); + kfree(node); + } + spin_unlock_bh(&bat_priv->tt_roam_list_lock); +} + +/* This function checks whether the client already reached the + * maximum number of possible roaming phases. In this case the ROAMING_ADV + * will not be sent. + * + * returns true if the ROAMING_ADV can be sent, false otherwise */ +static bool tt_check_roam_count(struct bat_priv *bat_priv, + uint8_t *client) +{ + struct tt_roam_node *tt_roam_node; + bool ret = false; + + spin_lock_bh(&bat_priv->tt_roam_list_lock); + /* The new tt_req will be issued only if I'm not waiting for a + * reply from the same orig_node yet */ + list_for_each_entry(tt_roam_node, &bat_priv->tt_roam_list, list) { + if (!compare_eth(tt_roam_node->addr, client)) + continue; + + if (is_out_of_time(tt_roam_node->first_time, + ROAMING_MAX_TIME * 1000)) + continue; + + if (!atomic_dec_not_zero(&tt_roam_node->counter)) + /* Sorry, you roamed too many times! */ + goto unlock; + ret = true; + break; + } + + if (!ret) { + tt_roam_node = kmalloc(sizeof(*tt_roam_node), GFP_ATOMIC); + if (!tt_roam_node) + goto unlock; + + tt_roam_node->first_time = jiffies; + atomic_set(&tt_roam_node->counter, ROAMING_MAX_COUNT - 1); + memcpy(tt_roam_node->addr, client, ETH_ALEN); + + list_add(&tt_roam_node->list, &bat_priv->tt_roam_list); + ret = true; + } + +unlock: + spin_unlock_bh(&bat_priv->tt_roam_list_lock); + return ret; +} + +void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, + struct orig_node *orig_node) +{ + struct neigh_node *neigh_node = NULL; + struct sk_buff *skb = NULL; + struct roam_adv_packet *roam_adv_packet; + int ret = 1; + struct hard_iface *primary_if; + + /* before going on we have to check whether the client has + * already roamed to us too many times */ + if (!tt_check_roam_count(bat_priv, client)) + goto out; + + skb = dev_alloc_skb(sizeof(struct roam_adv_packet) + ETH_HLEN); + if (!skb) + goto out; + + skb_reserve(skb, ETH_HLEN); + + roam_adv_packet = (struct roam_adv_packet *)skb_put(skb, + sizeof(struct roam_adv_packet)); + + roam_adv_packet->packet_type = BAT_ROAM_ADV; + roam_adv_packet->version = COMPAT_VERSION; + roam_adv_packet->ttl = TTL; + primary_if = primary_if_get_selected(bat_priv); + if (!primary_if) + goto out; + memcpy(roam_adv_packet->src, primary_if->net_dev->dev_addr, ETH_ALEN); + hardif_free_ref(primary_if); + memcpy(roam_adv_packet->dst, orig_node->orig, ETH_ALEN); + memcpy(roam_adv_packet->client, client, ETH_ALEN); + + neigh_node = orig_node_get_router(orig_node); + if (!neigh_node) + goto out; + + bat_dbg(DBG_TT, bat_priv, + "Sending ROAMING_ADV to %pM (client %pM) via %pM\n", + orig_node->orig, client, neigh_node->addr); + + send_skb_packet(skb, neigh_node->if_incoming, neigh_node->addr); + ret = 0; + +out: + if (neigh_node) + neigh_node_free_ref(neigh_node); + if (ret) + kfree_skb(skb); + return; +} + +static void tt_purge(struct work_struct *work) +{ + struct delayed_work *delayed_work = + container_of(work, struct delayed_work, work); + struct bat_priv *bat_priv = + container_of(delayed_work, struct bat_priv, tt_work); + + tt_local_purge(bat_priv); + tt_global_roam_purge(bat_priv); + tt_req_purge(bat_priv); + tt_roam_purge(bat_priv); + + tt_start_timer(bat_priv); +} + +void tt_free(struct bat_priv *bat_priv) +{ + cancel_delayed_work_sync(&bat_priv->tt_work); + + tt_local_table_free(bat_priv); + tt_global_table_free(bat_priv); + tt_req_list_free(bat_priv); + tt_changes_list_free(bat_priv); + tt_roam_list_free(bat_priv); + + kfree(bat_priv->tt_buff); +} + +/* This function will reset the specified flags from all the entries in + * the given hash table and will increment num_local_tt for each involved + * entry */ +static void tt_local_reset_flags(struct bat_priv *bat_priv, uint16_t flags) +{ + int i; + struct hashtable_t *hash = bat_priv->tt_local_hash; + struct hlist_head *head; + struct hlist_node *node; + struct tt_local_entry *tt_local_entry; + + if (!hash) + return; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + + rcu_read_lock(); + hlist_for_each_entry_rcu(tt_local_entry, node, + head, hash_entry) { + tt_local_entry->flags &= ~flags; + atomic_inc(&bat_priv->num_local_tt); + } + rcu_read_unlock(); + } + +} + +/* Purge out all the tt local entries marked with TT_CLIENT_PENDING */ +static void tt_local_purge_pending_clients(struct bat_priv *bat_priv) +{ + struct hashtable_t *hash = bat_priv->tt_local_hash; + struct tt_local_entry *tt_local_entry; + struct hlist_node *node, *node_tmp; + struct hlist_head *head; + spinlock_t *list_lock; /* protects write access to the hash lists */ + int i; + + if (!hash) + return; + + for (i = 0; i < hash->size; i++) { + head = &hash->table[i]; + list_lock = &hash->list_locks[i]; + + spin_lock_bh(list_lock); + hlist_for_each_entry_safe(tt_local_entry, node, node_tmp, + head, hash_entry) { + if (!(tt_local_entry->flags & TT_CLIENT_PENDING)) + continue; + + bat_dbg(DBG_TT, bat_priv, "Deleting local tt entry " + "(%pM): pending\n", tt_local_entry->addr); + + atomic_dec(&bat_priv->num_local_tt); + hlist_del_rcu(node); + tt_local_entry_free_ref(tt_local_entry); + } + spin_unlock_bh(list_lock); + } + +} + +void tt_commit_changes(struct bat_priv *bat_priv) +{ + tt_local_reset_flags(bat_priv, TT_CLIENT_NEW); + tt_local_purge_pending_clients(bat_priv); + + /* Increment the TTVN only once per OGM interval */ + atomic_inc(&bat_priv->ttvn); + bat_priv->tt_poss_change = false; +} diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 46152c38cc9..d4122cba53b 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -22,22 +22,45 @@ #ifndef _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ #define _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ -int tt_local_init(struct bat_priv *bat_priv); -void tt_local_add(struct net_device *soft_iface, uint8_t *addr); +int tt_len(int changes_num); +int tt_changes_fill_buffer(struct bat_priv *bat_priv, + unsigned char *buff, int buff_len); +int tt_init(struct bat_priv *bat_priv); +void tt_local_add(struct net_device *soft_iface, const uint8_t *addr); void tt_local_remove(struct bat_priv *bat_priv, - uint8_t *addr, char *message); -int tt_local_fill_buffer(struct bat_priv *bat_priv, - unsigned char *buff, int buff_len); + const uint8_t *addr, const char *message, bool roaming); int tt_local_seq_print_text(struct seq_file *seq, void *offset); -void tt_local_free(struct bat_priv *bat_priv); -int tt_global_init(struct bat_priv *bat_priv); -void tt_global_add_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, - unsigned char *tt_buff, int tt_buff_len); +void tt_global_add_orig(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *tt_buff, int tt_buff_len); +int tt_global_add(struct bat_priv *bat_priv, + struct orig_node *orig_node, const unsigned char *addr, + uint8_t ttvn, bool roaming); int tt_global_seq_print_text(struct seq_file *seq, void *offset); void tt_global_del_orig(struct bat_priv *bat_priv, - struct orig_node *orig_node, char *message); -void tt_global_free(struct bat_priv *bat_priv); -struct orig_node *transtable_search(struct bat_priv *bat_priv, uint8_t *addr); + struct orig_node *orig_node, const char *message); +void tt_global_del(struct bat_priv *bat_priv, + struct orig_node *orig_node, const unsigned char *addr, + const char *message, bool roaming); +struct orig_node *transtable_search(struct bat_priv *bat_priv, + const uint8_t *addr); +void tt_save_orig_buffer(struct bat_priv *bat_priv, struct orig_node *orig_node, + const unsigned char *tt_buff, uint8_t tt_num_changes); +uint16_t tt_local_crc(struct bat_priv *bat_priv); +uint16_t tt_global_crc(struct bat_priv *bat_priv, struct orig_node *orig_node); +void tt_free(struct bat_priv *bat_priv); +int send_tt_request(struct bat_priv *bat_priv, + struct orig_node *dst_orig_node, uint8_t hvn, + uint16_t tt_crc, bool full_table); +bool send_tt_response(struct bat_priv *bat_priv, + struct tt_query_packet *tt_request); +void tt_update_changes(struct bat_priv *bat_priv, struct orig_node *orig_node, + uint16_t tt_num_changes, uint8_t ttvn, + struct tt_change *tt_change); +bool is_my_client(struct bat_priv *bat_priv, const uint8_t *addr); +void handle_tt_response(struct bat_priv *bat_priv, + struct tt_query_packet *tt_response); +void send_roam_adv(struct bat_priv *bat_priv, uint8_t *client, + struct orig_node *orig_node); +void tt_commit_changes(struct bat_priv *bat_priv); #endif /* _NET_BATMAN_ADV_TRANSLATION_TABLE_H_ */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index fab70e8b16e..25bd1db3537 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -75,8 +75,18 @@ struct orig_node { unsigned long batman_seqno_reset; uint8_t gw_flags; uint8_t flags; + atomic_t last_ttvn; /* last seen translation table version number */ + uint16_t tt_crc; unsigned char *tt_buff; int16_t tt_buff_len; + spinlock_t tt_buff_lock; /* protects tt_buff */ + atomic_t tt_size; + /* The tt_poss_change flag is used to detect an ongoing roaming phase. + * If true, then I sent a Roaming_adv to this orig_node and I have to + * inspect every packet directed to it to check whether it is still + * the true destination or not. This flag will be reset to false as + * soon as I receive a new TTVN from this orig_node */ + bool tt_poss_change; uint32_t last_real_seqno; uint8_t last_ttl; unsigned long bcast_bits[NUM_WORDS]; @@ -94,6 +104,7 @@ struct orig_node { spinlock_t ogm_cnt_lock; /* bcast_seqno_lock protects bcast_bits, last_bcast_seqno */ spinlock_t bcast_seqno_lock; + spinlock_t tt_list_lock; /* protects tt_list */ atomic_t bond_candidates; struct list_head bond_list; }; @@ -145,6 +156,15 @@ struct bat_priv { atomic_t bcast_seqno; atomic_t bcast_queue_left; atomic_t batman_queue_left; + atomic_t ttvn; /* tranlation table version number */ + atomic_t tt_ogm_append_cnt; + atomic_t tt_local_changes; /* changes registered in a OGM interval */ + /* The tt_poss_change flag is used to detect an ongoing roaming phase. + * If true, then I received a Roaming_adv and I have to inspect every + * packet directed to me to check whether I am still the true + * destination or not. This flag will be reset to false as soon as I + * increase my TTVN */ + bool tt_poss_change; char num_ifaces; struct debug_log *debug_log; struct kobject *mesh_obj; @@ -153,26 +173,35 @@ struct bat_priv { struct hlist_head forw_bcast_list; struct hlist_head gw_list; struct hlist_head softif_neigh_vids; + struct list_head tt_changes_list; /* tracks changes in a OGM int */ struct list_head vis_send_list; struct hashtable_t *orig_hash; struct hashtable_t *tt_local_hash; struct hashtable_t *tt_global_hash; + struct list_head tt_req_list; /* list of pending tt_requests */ + struct list_head tt_roam_list; struct hashtable_t *vis_hash; spinlock_t forw_bat_list_lock; /* protects forw_bat_list */ spinlock_t forw_bcast_list_lock; /* protects */ - spinlock_t tt_lhash_lock; /* protects tt_local_hash */ - spinlock_t tt_ghash_lock; /* protects tt_global_hash */ + spinlock_t tt_changes_list_lock; /* protects tt_changes */ + spinlock_t tt_req_list_lock; /* protects tt_req_list */ + spinlock_t tt_roam_list_lock; /* protects tt_roam_list */ spinlock_t gw_list_lock; /* protects gw_list and curr_gw */ spinlock_t vis_hash_lock; /* protects vis_hash */ spinlock_t vis_list_lock; /* protects vis_info::recv_list */ spinlock_t softif_neigh_lock; /* protects soft-interface neigh list */ spinlock_t softif_neigh_vid_lock; /* protects soft-interface vid list */ - int16_t num_local_tt; - atomic_t tt_local_changed; + atomic_t num_local_tt; + /* Checksum of the local table, recomputed before sending a new OGM */ + atomic_t tt_crc; + unsigned char *tt_buff; + int16_t tt_buff_len; + spinlock_t tt_buff_lock; /* protects tt_buff */ struct delayed_work tt_work; struct delayed_work orig_work; struct delayed_work vis_work; struct gw_node __rcu *curr_gw; /* rcu protected pointer */ + atomic_t gw_reselect; struct hard_iface __rcu *primary_if; /* rcu protected pointer */ struct vis_info *my_vis_info; }; @@ -195,14 +224,39 @@ struct socket_packet { struct tt_local_entry { uint8_t addr[ETH_ALEN]; unsigned long last_seen; - char never_purge; + uint16_t flags; + atomic_t refcount; + struct rcu_head rcu; struct hlist_node hash_entry; }; struct tt_global_entry { uint8_t addr[ETH_ALEN]; struct orig_node *orig_node; - struct hlist_node hash_entry; + uint8_t ttvn; + uint16_t flags; /* only TT_GLOBAL_ROAM is used */ + unsigned long roam_at; /* time at which TT_GLOBAL_ROAM was set */ + atomic_t refcount; + struct rcu_head rcu; + struct hlist_node hash_entry; /* entry in the global table */ +}; + +struct tt_change_node { + struct list_head list; + struct tt_change change; +}; + +struct tt_req_node { + uint8_t addr[ETH_ALEN]; + unsigned long issued_at; + struct list_head list; +}; + +struct tt_roam_node { + uint8_t addr[ETH_ALEN]; + atomic_t counter; + unsigned long first_time; + struct list_head list; }; /** @@ -246,10 +300,10 @@ struct frag_packet_list_entry { }; struct vis_info { - unsigned long first_seen; - struct list_head recv_list; - /* list of server-neighbors we received a vis-packet - * from. we should not reply to them. */ + unsigned long first_seen; + /* list of server-neighbors we received a vis-packet + * from. we should not reply to them. */ + struct list_head recv_list; struct list_head send_list; struct kref refcount; struct hlist_node hash_entry; diff --git a/net/batman-adv/unicast.c b/net/batman-adv/unicast.c index 19c3daf34ac..32b125fb3d3 100644 --- a/net/batman-adv/unicast.c +++ b/net/batman-adv/unicast.c @@ -39,8 +39,8 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, (struct unicast_frag_packet *)skb->data; struct sk_buff *tmp_skb; struct unicast_packet *unicast_packet; - int hdr_len = sizeof(struct unicast_packet); - int uni_diff = sizeof(struct unicast_frag_packet) - hdr_len; + int hdr_len = sizeof(*unicast_packet); + int uni_diff = sizeof(*up) - hdr_len; /* set skb to the first part and tmp_skb to the second part */ if (up->flags & UNI_FRAG_HEAD) { @@ -53,7 +53,7 @@ static struct sk_buff *frag_merge_packet(struct list_head *head, if (skb_linearize(skb) < 0 || skb_linearize(tmp_skb) < 0) goto err; - skb_pull(tmp_skb, sizeof(struct unicast_frag_packet)); + skb_pull(tmp_skb, sizeof(*up)); if (pskb_expand_head(skb, 0, tmp_skb->len, GFP_ATOMIC) < 0) goto err; @@ -99,8 +99,7 @@ static int frag_create_buffer(struct list_head *head) struct frag_packet_list_entry *tfp; for (i = 0; i < FRAG_BUFFER_SIZE; i++) { - tfp = kmalloc(sizeof(struct frag_packet_list_entry), - GFP_ATOMIC); + tfp = kmalloc(sizeof(*tfp), GFP_ATOMIC); if (!tfp) { frag_list_free(head); return -ENOMEM; @@ -115,7 +114,7 @@ static int frag_create_buffer(struct list_head *head) } static struct frag_packet_list_entry *frag_search_packet(struct list_head *head, - struct unicast_frag_packet *up) + const struct unicast_frag_packet *up) { struct frag_packet_list_entry *tfp; struct unicast_frag_packet *tmp_up = NULL; @@ -218,14 +217,14 @@ out: } int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, - struct hard_iface *hard_iface, uint8_t dstaddr[]) + struct hard_iface *hard_iface, const uint8_t dstaddr[]) { struct unicast_packet tmp_uc, *unicast_packet; struct hard_iface *primary_if; struct sk_buff *frag_skb; struct unicast_frag_packet *frag1, *frag2; - int uc_hdr_len = sizeof(struct unicast_packet); - int ucf_hdr_len = sizeof(struct unicast_frag_packet); + int uc_hdr_len = sizeof(*unicast_packet); + int ucf_hdr_len = sizeof(*frag1); int data_len = skb->len - uc_hdr_len; int large_tail = 0, ret = NET_RX_DROP; uint16_t seqno; @@ -250,14 +249,14 @@ int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, frag1 = (struct unicast_frag_packet *)skb->data; frag2 = (struct unicast_frag_packet *)frag_skb->data; - memcpy(frag1, &tmp_uc, sizeof(struct unicast_packet)); + memcpy(frag1, &tmp_uc, sizeof(tmp_uc)); frag1->ttl--; frag1->version = COMPAT_VERSION; frag1->packet_type = BAT_UNICAST_FRAG; memcpy(frag1->orig, primary_if->net_dev->dev_addr, ETH_ALEN); - memcpy(frag2, frag1, sizeof(struct unicast_frag_packet)); + memcpy(frag2, frag1, sizeof(*frag2)); if (data_len & 1) large_tail = UNI_FRAG_LARGETAIL; @@ -295,7 +294,7 @@ int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv) /* get routing information */ if (is_multicast_ether_addr(ethhdr->h_dest)) { - orig_node = (struct orig_node *)gw_get_selected_orig(bat_priv); + orig_node = gw_get_selected_orig(bat_priv); if (orig_node) goto find_router; } @@ -314,10 +313,7 @@ find_router: if (!neigh_node) goto out; - if (neigh_node->if_incoming->if_status != IF_ACTIVE) - goto out; - - if (my_skb_head_push(skb, sizeof(struct unicast_packet)) < 0) + if (my_skb_head_push(skb, sizeof(*unicast_packet)) < 0) goto out; unicast_packet = (struct unicast_packet *)skb->data; @@ -329,9 +325,12 @@ find_router: unicast_packet->ttl = TTL; /* copy the destination for faster routing */ memcpy(unicast_packet->dest, orig_node->orig, ETH_ALEN); + /* set the destination tt version number */ + unicast_packet->ttvn = + (uint8_t)atomic_read(&orig_node->last_ttvn); if (atomic_read(&bat_priv->fragmentation) && - data_len + sizeof(struct unicast_packet) > + data_len + sizeof(*unicast_packet) > neigh_node->if_incoming->net_dev->mtu) { /* send frag skb decreases ttl */ unicast_packet->ttl++; diff --git a/net/batman-adv/unicast.h b/net/batman-adv/unicast.h index 16ad7a9242b..62f54b95462 100644 --- a/net/batman-adv/unicast.h +++ b/net/batman-adv/unicast.h @@ -32,11 +32,11 @@ int frag_reassemble_skb(struct sk_buff *skb, struct bat_priv *bat_priv, void frag_list_free(struct list_head *head); int unicast_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv); int frag_send_skb(struct sk_buff *skb, struct bat_priv *bat_priv, - struct hard_iface *hard_iface, uint8_t dstaddr[]); + struct hard_iface *hard_iface, const uint8_t dstaddr[]); -static inline int frag_can_reassemble(struct sk_buff *skb, int mtu) +static inline int frag_can_reassemble(const struct sk_buff *skb, int mtu) { - struct unicast_frag_packet *unicast_packet; + const struct unicast_frag_packet *unicast_packet; int uneven_correction = 0; unsigned int merged_size; @@ -49,7 +49,7 @@ static inline int frag_can_reassemble(struct sk_buff *skb, int mtu) uneven_correction = -1; } - merged_size = (skb->len - sizeof(struct unicast_frag_packet)) * 2; + merged_size = (skb->len - sizeof(*unicast_packet)) * 2; merged_size += sizeof(struct unicast_packet) + uneven_correction; return merged_size <= mtu; diff --git a/net/batman-adv/vis.c b/net/batman-adv/vis.c index c39f20cc1ba..8a1b98589d7 100644 --- a/net/batman-adv/vis.c +++ b/net/batman-adv/vis.c @@ -30,22 +30,6 @@ #define MAX_VIS_PACKET_SIZE 1000 -/* Returns the smallest signed integer in two's complement with the sizeof x */ -#define smallest_signed_int(x) (1u << (7u + 8u * (sizeof(x) - 1u))) - -/* Checks if a sequence number x is a predecessor/successor of y. - * they handle overflows/underflows and can correctly check for a - * predecessor/successor unless the variable sequence number has grown by - * more then 2**(bitwidth(x)-1)-1. - * This means that for a uint8_t with the maximum value 255, it would think: - * - when adding nothing - it is neither a predecessor nor a successor - * - before adding more than 127 to the starting value - it is a predecessor, - * - when adding 128 - it is neither a predecessor nor a successor, - * - after adding more than 127 to the starting value - it is a successor */ -#define seq_before(x, y) ({typeof(x) _dummy = (x - y); \ - _dummy > smallest_signed_int(_dummy); }) -#define seq_after(x, y) seq_before(y, x) - static void start_vis_timer(struct bat_priv *bat_priv); /* free the info */ @@ -68,10 +52,10 @@ static void free_info(struct kref *ref) } /* Compare two vis packets, used by the hashing algorithm */ -static int vis_info_cmp(struct hlist_node *node, void *data2) +static int vis_info_cmp(const struct hlist_node *node, const void *data2) { - struct vis_info *d1, *d2; - struct vis_packet *p1, *p2; + const struct vis_info *d1, *d2; + const struct vis_packet *p1, *p2; d1 = container_of(node, struct vis_info, hash_entry); d2 = data2; @@ -82,11 +66,11 @@ static int vis_info_cmp(struct hlist_node *node, void *data2) /* hash function to choose an entry in a hash table of given size */ /* hash algorithm from http://en.wikipedia.org/wiki/Hash_table */ -static int vis_info_choose(void *data, int size) +static int vis_info_choose(const void *data, int size) { - struct vis_info *vis_info = data; - struct vis_packet *packet; - unsigned char *key; + const struct vis_info *vis_info = data; + const struct vis_packet *packet; + const unsigned char *key; uint32_t hash = 0; size_t i; @@ -106,7 +90,7 @@ static int vis_info_choose(void *data, int size) } static struct vis_info *vis_hash_find(struct bat_priv *bat_priv, - void *data) + const void *data) { struct hashtable_t *hash = bat_priv->vis_hash; struct hlist_head *head; @@ -143,7 +127,7 @@ static void vis_data_insert_interface(const uint8_t *interface, struct hlist_node *pos; hlist_for_each_entry(entry, pos, if_list, list) { - if (compare_eth(entry->addr, (void *)interface)) + if (compare_eth(entry->addr, interface)) return; } @@ -156,7 +140,8 @@ static void vis_data_insert_interface(const uint8_t *interface, hlist_add_head(&entry->list, if_list); } -static ssize_t vis_data_read_prim_sec(char *buff, struct hlist_head *if_list) +static ssize_t vis_data_read_prim_sec(char *buff, + const struct hlist_head *if_list) { struct if_list_entry *entry; struct hlist_node *pos; @@ -189,8 +174,9 @@ static size_t vis_data_count_prim_sec(struct hlist_head *if_list) } /* read an entry */ -static ssize_t vis_data_read_entry(char *buff, struct vis_info_entry *entry, - uint8_t *src, bool primary) +static ssize_t vis_data_read_entry(char *buff, + const struct vis_info_entry *entry, + const uint8_t *src, bool primary) { /* maximal length: max(4+17+2, 3+17+1+3+2) == 26 */ if (primary && entry->quality == 0) @@ -239,7 +225,7 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(info, node, head, hash_entry) { packet = (struct vis_packet *)info->skb_packet->data; entries = (struct vis_info_entry *) - ((char *)packet + sizeof(struct vis_packet)); + ((char *)packet + sizeof(*packet)); for (j = 0; j < packet->entries; j++) { if (entries[j].quality == 0) @@ -287,7 +273,7 @@ int vis_seq_print_text(struct seq_file *seq, void *offset) hlist_for_each_entry_rcu(info, node, head, hash_entry) { packet = (struct vis_packet *)info->skb_packet->data; entries = (struct vis_info_entry *) - ((char *)packet + sizeof(struct vis_packet)); + ((char *)packet + sizeof(*packet)); for (j = 0; j < packet->entries; j++) { if (entries[j].quality == 0) @@ -361,11 +347,11 @@ static void send_list_del(struct vis_info *info) /* tries to add one entry to the receive list. */ static void recv_list_add(struct bat_priv *bat_priv, - struct list_head *recv_list, char *mac) + struct list_head *recv_list, const char *mac) { struct recvlist_node *entry; - entry = kmalloc(sizeof(struct recvlist_node), GFP_ATOMIC); + entry = kmalloc(sizeof(*entry), GFP_ATOMIC); if (!entry) return; @@ -377,9 +363,9 @@ static void recv_list_add(struct bat_priv *bat_priv, /* returns 1 if this mac is in the recv_list */ static int recv_list_is_in(struct bat_priv *bat_priv, - struct list_head *recv_list, char *mac) + const struct list_head *recv_list, const char *mac) { - struct recvlist_node *entry; + const struct recvlist_node *entry; spin_lock_bh(&bat_priv->vis_list_lock); list_for_each_entry(entry, recv_list, list) { @@ -412,11 +398,11 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, return NULL; /* see if the packet is already in vis_hash */ - search_elem.skb_packet = dev_alloc_skb(sizeof(struct vis_packet)); + search_elem.skb_packet = dev_alloc_skb(sizeof(*search_packet)); if (!search_elem.skb_packet) return NULL; search_packet = (struct vis_packet *)skb_put(search_elem.skb_packet, - sizeof(struct vis_packet)); + sizeof(*search_packet)); memcpy(search_packet->vis_orig, vis_packet->vis_orig, ETH_ALEN); old_info = vis_hash_find(bat_priv, &search_elem); @@ -442,27 +428,26 @@ static struct vis_info *add_packet(struct bat_priv *bat_priv, kref_put(&old_info->refcount, free_info); } - info = kmalloc(sizeof(struct vis_info), GFP_ATOMIC); + info = kmalloc(sizeof(*info), GFP_ATOMIC); if (!info) return NULL; - info->skb_packet = dev_alloc_skb(sizeof(struct vis_packet) + - vis_info_len + sizeof(struct ethhdr)); + info->skb_packet = dev_alloc_skb(sizeof(*packet) + vis_info_len + + sizeof(struct ethhdr)); if (!info->skb_packet) { kfree(info); return NULL; } skb_reserve(info->skb_packet, sizeof(struct ethhdr)); - packet = (struct vis_packet *)skb_put(info->skb_packet, - sizeof(struct vis_packet) + - vis_info_len); + packet = (struct vis_packet *)skb_put(info->skb_packet, sizeof(*packet) + + vis_info_len); kref_init(&info->refcount); INIT_LIST_HEAD(&info->send_list); INIT_LIST_HEAD(&info->recv_list); info->first_seen = jiffies; info->bat_priv = bat_priv; - memcpy(packet, vis_packet, sizeof(struct vis_packet) + vis_info_len); + memcpy(packet, vis_packet, sizeof(*packet) + vis_info_len); /* initialize and add new packet. */ *is_new = 1; @@ -599,9 +584,9 @@ static int find_best_vis_server(struct bat_priv *bat_priv, } /* Return true if the vis packet is full. */ -static bool vis_packet_full(struct vis_info *info) +static bool vis_packet_full(const struct vis_info *info) { - struct vis_packet *packet; + const struct vis_packet *packet; packet = (struct vis_packet *)info->skb_packet->data; if (MAX_VIS_PACKET_SIZE / sizeof(struct vis_info_entry) @@ -619,7 +604,7 @@ static int generate_vis_packet(struct bat_priv *bat_priv) struct hlist_head *head; struct orig_node *orig_node; struct neigh_node *router; - struct vis_info *info = (struct vis_info *)bat_priv->my_vis_info; + struct vis_info *info = bat_priv->my_vis_info; struct vis_packet *packet = (struct vis_packet *)info->skb_packet->data; struct vis_info_entry *entry; struct tt_local_entry *tt_local_entry; @@ -632,7 +617,7 @@ static int generate_vis_packet(struct bat_priv *bat_priv) packet->ttl = TTL; packet->seqno = htonl(ntohl(packet->seqno) + 1); packet->entries = 0; - skb_trim(info->skb_packet, sizeof(struct vis_packet)); + skb_trim(info->skb_packet, sizeof(*packet)); if (packet->vis_type == VIS_TYPE_CLIENT_UPDATE) { best_tq = find_best_vis_server(bat_priv, info); @@ -680,11 +665,12 @@ next: hash = bat_priv->tt_local_hash; - spin_lock_bh(&bat_priv->tt_lhash_lock); for (i = 0; i < hash->size; i++) { head = &hash->table[i]; - hlist_for_each_entry(tt_local_entry, node, head, hash_entry) { + rcu_read_lock(); + hlist_for_each_entry_rcu(tt_local_entry, node, head, + hash_entry) { entry = (struct vis_info_entry *) skb_put(info->skb_packet, sizeof(*entry)); @@ -693,14 +679,12 @@ next: entry->quality = 0; /* 0 means TT */ packet->entries++; - if (vis_packet_full(info)) { - spin_unlock_bh(&bat_priv->tt_lhash_lock); - return 0; - } + if (vis_packet_full(info)) + goto unlock; } + rcu_read_unlock(); } - spin_unlock_bh(&bat_priv->tt_lhash_lock); return 0; unlock: @@ -908,17 +892,15 @@ int vis_init(struct bat_priv *bat_priv) goto err; } - bat_priv->my_vis_info->skb_packet = dev_alloc_skb( - sizeof(struct vis_packet) + - MAX_VIS_PACKET_SIZE + - sizeof(struct ethhdr)); + bat_priv->my_vis_info->skb_packet = dev_alloc_skb(sizeof(*packet) + + MAX_VIS_PACKET_SIZE + + sizeof(struct ethhdr)); if (!bat_priv->my_vis_info->skb_packet) goto free_info; skb_reserve(bat_priv->my_vis_info->skb_packet, sizeof(struct ethhdr)); - packet = (struct vis_packet *)skb_put( - bat_priv->my_vis_info->skb_packet, - sizeof(struct vis_packet)); + packet = (struct vis_packet *)skb_put(bat_priv->my_vis_info->skb_packet, + sizeof(*packet)); /* prefill the vis info */ bat_priv->my_vis_info->first_seen = jiffies - diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 6ae5ec50858..bfb3dc03c9d 100644 --- a/net/bluetooth/Kconfig +++ b/net/bluetooth/Kconfig @@ -6,6 +6,7 @@ menuconfig BT tristate "Bluetooth subsystem support" depends on NET && !S390 depends on RFKILL || !RFKILL + select CRYPTO help Bluetooth is low-cost, low-power, short-range wireless technology. It was designed as a replacement for cables and other short-range @@ -22,6 +23,7 @@ menuconfig BT BNEP Module (Bluetooth Network Encapsulation Protocol) CMTP Module (CAPI Message Transport Protocol) HIDP Module (Human Interface Device Protocol) + SMP Module (Security Manager Protocol) Say Y here to compile Bluetooth support into the kernel or say M to compile it as module (bluetooth). @@ -36,11 +38,18 @@ if BT != n config BT_L2CAP bool "L2CAP protocol support" select CRC16 + select CRYPTO + select CRYPTO_BLKCIPHER + select CRYPTO_AES + select CRYPTO_ECB help L2CAP (Logical Link Control and Adaptation Protocol) provides connection oriented and connection-less data transport. L2CAP support is required for most Bluetooth applications. + Also included is support for SMP (Security Manager Protocol) which + is the security layer on top of LE (Low Energy) links. + config BT_SCO bool "SCO links support" help diff --git a/net/bluetooth/Makefile b/net/bluetooth/Makefile index f04fe9a9d63..9b67f3d08fa 100644 --- a/net/bluetooth/Makefile +++ b/net/bluetooth/Makefile @@ -9,5 +9,5 @@ obj-$(CONFIG_BT_CMTP) += cmtp/ obj-$(CONFIG_BT_HIDP) += hidp/ bluetooth-y := af_bluetooth.o hci_core.o hci_conn.o hci_event.o mgmt.o hci_sock.o hci_sysfs.o lib.o -bluetooth-$(CONFIG_BT_L2CAP) += l2cap_core.o l2cap_sock.o +bluetooth-$(CONFIG_BT_L2CAP) += l2cap_core.o l2cap_sock.o smp.o bluetooth-$(CONFIG_BT_SCO) += sco.o diff --git a/net/bluetooth/cmtp/capi.c b/net/bluetooth/cmtp/capi.c index 744233cba24..040f67b1297 100644 --- a/net/bluetooth/cmtp/capi.c +++ b/net/bluetooth/cmtp/capi.c @@ -326,7 +326,7 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) { struct capi_ctr *ctrl = &session->ctrl; struct cmtp_application *application; - __u16 cmd, appl; + __u16 appl; __u32 contr; BT_DBG("session %p skb %p len %d", session, skb, skb->len); @@ -344,7 +344,6 @@ void cmtp_recv_capimsg(struct cmtp_session *session, struct sk_buff *skb) return; } - cmd = CAPICMD(CAPIMSG_COMMAND(skb->data), CAPIMSG_SUBCOMMAND(skb->data)); appl = CAPIMSG_APPID(skb->data); contr = CAPIMSG_CONTROL(skb->data); diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 3163330cd4f..ea7f031f3b0 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -53,11 +53,13 @@ static void hci_le_connect(struct hci_conn *conn) conn->state = BT_CONNECT; conn->out = 1; conn->link_mode |= HCI_LM_MASTER; + conn->sec_level = BT_SECURITY_LOW; memset(&cp, 0, sizeof(cp)); cp.scan_interval = cpu_to_le16(0x0004); cp.scan_window = cpu_to_le16(0x0004); bacpy(&cp.peer_addr, &conn->dst); + cp.peer_addr_type = conn->dst_type; cp.conn_interval_min = cpu_to_le16(0x0008); cp.conn_interval_max = cpu_to_le16(0x0100); cp.supervision_timeout = cpu_to_le16(0x0064); @@ -203,6 +205,55 @@ void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, } EXPORT_SYMBOL(hci_le_conn_update); +void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __u8 rand[8], + __u8 ltk[16]) +{ + struct hci_dev *hdev = conn->hdev; + struct hci_cp_le_start_enc cp; + + BT_DBG("%p", conn); + + memset(&cp, 0, sizeof(cp)); + + cp.handle = cpu_to_le16(conn->handle); + memcpy(cp.ltk, ltk, sizeof(cp.ltk)); + cp.ediv = ediv; + memcpy(cp.rand, rand, sizeof(rand)); + + hci_send_cmd(hdev, HCI_OP_LE_START_ENC, sizeof(cp), &cp); +} +EXPORT_SYMBOL(hci_le_start_enc); + +void hci_le_ltk_reply(struct hci_conn *conn, u8 ltk[16]) +{ + struct hci_dev *hdev = conn->hdev; + struct hci_cp_le_ltk_reply cp; + + BT_DBG("%p", conn); + + memset(&cp, 0, sizeof(cp)); + + cp.handle = cpu_to_le16(conn->handle); + memcpy(cp.ltk, ltk, sizeof(ltk)); + + hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); +} +EXPORT_SYMBOL(hci_le_ltk_reply); + +void hci_le_ltk_neg_reply(struct hci_conn *conn) +{ + struct hci_dev *hdev = conn->hdev; + struct hci_cp_le_ltk_neg_reply cp; + + BT_DBG("%p", conn); + + memset(&cp, 0, sizeof(cp)); + + cp.handle = cpu_to_le16(conn->handle); + + hci_send_cmd(hdev, HCI_OP_LE_LTK_NEG_REPLY, sizeof(cp), &cp); +} + /* Device _must_ be locked */ void hci_sco_setup(struct hci_conn *conn, __u8 status) { @@ -393,6 +444,9 @@ int hci_conn_del(struct hci_conn *conn) hci_dev_put(hdev); + if (conn->handle == 0) + kfree(conn); + return 0; } @@ -447,14 +501,23 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 BT_DBG("%s dst %s", hdev->name, batostr(dst)); if (type == LE_LINK) { + struct adv_entry *entry; + le = hci_conn_hash_lookup_ba(hdev, LE_LINK, dst); if (le) return ERR_PTR(-EBUSY); + + entry = hci_find_adv_entry(hdev, dst); + if (!entry) + return ERR_PTR(-EHOSTUNREACH); + le = hci_conn_add(hdev, LE_LINK, dst); if (!le) return ERR_PTR(-ENOMEM); - if (le->state == BT_OPEN) - hci_le_connect(le); + + le->dst_type = entry->bdaddr_type; + + hci_le_connect(le); hci_conn_hold(le); @@ -497,7 +560,7 @@ struct hci_conn *hci_connect(struct hci_dev *hdev, int type, bdaddr_t *dst, __u8 if (acl->state == BT_CONNECTED && (sco->state == BT_OPEN || sco->state == BT_CLOSED)) { acl->power_save = 1; - hci_conn_enter_active_mode(acl); + hci_conn_enter_active_mode(acl, BT_POWER_FORCE_ACTIVE_ON); if (test_bit(HCI_CONN_MODE_CHANGE_PEND, &acl->pend)) { /* defer SCO setup until mode change completed */ @@ -548,6 +611,8 @@ static int hci_conn_auth(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) cp.handle = cpu_to_le16(conn->handle); hci_send_cmd(conn->hdev, HCI_OP_AUTH_REQUESTED, sizeof(cp), &cp); + if (conn->key_type != 0xff) + set_bit(HCI_CONN_REAUTH_PEND, &conn->pend); } return 0; @@ -608,11 +673,11 @@ int hci_conn_security(struct hci_conn *conn, __u8 sec_level, __u8 auth_type) goto encrypt; auth: - if (test_and_set_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) return 0; - hci_conn_auth(conn, sec_level, auth_type); - return 0; + if (!hci_conn_auth(conn, sec_level, auth_type)) + return 0; encrypt: if (conn->link_mode & HCI_LM_ENCRYPT) @@ -631,9 +696,7 @@ int hci_conn_check_secure(struct hci_conn *conn, __u8 sec_level) if (sec_level != BT_SECURITY_HIGH) return 1; /* Accept if non-secure is required */ - if (conn->key_type == HCI_LK_AUTH_COMBINATION || - (conn->key_type == HCI_LK_COMBINATION && - conn->pin_length == 16)) + if (conn->sec_level == BT_SECURITY_HIGH) return 1; return 0; /* Reject not secure link */ @@ -676,7 +739,7 @@ int hci_conn_switch_role(struct hci_conn *conn, __u8 role) EXPORT_SYMBOL(hci_conn_switch_role); /* Enter active mode */ -void hci_conn_enter_active_mode(struct hci_conn *conn) +void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active) { struct hci_dev *hdev = conn->hdev; @@ -685,7 +748,10 @@ void hci_conn_enter_active_mode(struct hci_conn *conn) if (test_bit(HCI_RAW, &hdev->flags)) return; - if (conn->mode != HCI_CM_SNIFF || !conn->power_save) + if (conn->mode != HCI_CM_SNIFF) + goto timer; + + if (!conn->power_save && !force_active) goto timer; if (!test_and_set_bit(HCI_CONN_MODE_CHANGE_PEND, &conn->pend)) { diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 815269b07f2..ec0bc3f60f2 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -42,6 +42,7 @@ #include <linux/notifier.h> #include <linux/rfkill.h> #include <linux/timer.h> +#include <linux/crypto.h> #include <net/sock.h> #include <asm/system.h> @@ -145,7 +146,7 @@ static int __hci_request(struct hci_dev *hdev, void (*req)(struct hci_dev *hdev, switch (hdev->req_status) { case HCI_REQ_DONE: - err = -bt_err(hdev->req_result); + err = -bt_to_errno(hdev->req_result); break; case HCI_REQ_CANCELED: @@ -539,7 +540,7 @@ int hci_dev_open(__u16 dev) ret = __hci_request(hdev, hci_init_req, 0, msecs_to_jiffies(HCI_INIT_TIMEOUT)); - if (lmp_le_capable(hdev)) + if (lmp_host_le_capable(hdev)) ret = __hci_request(hdev, hci_le_init_req, 0, msecs_to_jiffies(HCI_INIT_TIMEOUT)); @@ -1056,6 +1057,42 @@ static int hci_persistent_key(struct hci_dev *hdev, struct hci_conn *conn, return 0; } +struct link_key *hci_find_ltk(struct hci_dev *hdev, __le16 ediv, u8 rand[8]) +{ + struct link_key *k; + + list_for_each_entry(k, &hdev->link_keys, list) { + struct key_master_id *id; + + if (k->type != HCI_LK_SMP_LTK) + continue; + + if (k->dlen != sizeof(*id)) + continue; + + id = (void *) &k->data; + if (id->ediv == ediv && + (memcmp(rand, id->rand, sizeof(id->rand)) == 0)) + return k; + } + + return NULL; +} +EXPORT_SYMBOL(hci_find_ltk); + +struct link_key *hci_find_link_key_type(struct hci_dev *hdev, + bdaddr_t *bdaddr, u8 type) +{ + struct link_key *k; + + list_for_each_entry(k, &hdev->link_keys, list) + if (k->type == type && bacmp(bdaddr, &k->bdaddr) == 0) + return k; + + return NULL; +} +EXPORT_SYMBOL(hci_find_link_key_type); + int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, bdaddr_t *bdaddr, u8 *val, u8 type, u8 pin_len) { @@ -1111,6 +1148,44 @@ int hci_add_link_key(struct hci_dev *hdev, struct hci_conn *conn, int new_key, return 0; } +int hci_add_ltk(struct hci_dev *hdev, int new_key, bdaddr_t *bdaddr, + u8 key_size, __le16 ediv, u8 rand[8], u8 ltk[16]) +{ + struct link_key *key, *old_key; + struct key_master_id *id; + u8 old_key_type; + + BT_DBG("%s addr %s", hdev->name, batostr(bdaddr)); + + old_key = hci_find_link_key_type(hdev, bdaddr, HCI_LK_SMP_LTK); + if (old_key) { + key = old_key; + old_key_type = old_key->type; + } else { + key = kzalloc(sizeof(*key) + sizeof(*id), GFP_ATOMIC); + if (!key) + return -ENOMEM; + list_add(&key->list, &hdev->link_keys); + old_key_type = 0xff; + } + + key->dlen = sizeof(*id); + + bacpy(&key->bdaddr, bdaddr); + memcpy(key->val, ltk, sizeof(key->val)); + key->type = HCI_LK_SMP_LTK; + key->pin_len = key_size; + + id = (void *) &key->data; + id->ediv = ediv; + memcpy(id->rand, rand, sizeof(id->rand)); + + if (new_key) + mgmt_new_key(hdev->id, key, old_key_type); + + return 0; +} + int hci_remove_link_key(struct hci_dev *hdev, bdaddr_t *bdaddr) { struct link_key *key; @@ -1202,6 +1277,169 @@ int hci_add_remote_oob_data(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 *hash, return 0; } +struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, + bdaddr_t *bdaddr) +{ + struct list_head *p; + + list_for_each(p, &hdev->blacklist) { + struct bdaddr_list *b; + + b = list_entry(p, struct bdaddr_list, list); + + if (bacmp(bdaddr, &b->bdaddr) == 0) + return b; + } + + return NULL; +} + +int hci_blacklist_clear(struct hci_dev *hdev) +{ + struct list_head *p, *n; + + list_for_each_safe(p, n, &hdev->blacklist) { + struct bdaddr_list *b; + + b = list_entry(p, struct bdaddr_list, list); + + list_del(p); + kfree(b); + } + + return 0; +} + +int hci_blacklist_add(struct hci_dev *hdev, bdaddr_t *bdaddr) +{ + struct bdaddr_list *entry; + int err; + + if (bacmp(bdaddr, BDADDR_ANY) == 0) + return -EBADF; + + hci_dev_lock_bh(hdev); + + if (hci_blacklist_lookup(hdev, bdaddr)) { + err = -EEXIST; + goto err; + } + + entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); + if (!entry) { + return -ENOMEM; + goto err; + } + + bacpy(&entry->bdaddr, bdaddr); + + list_add(&entry->list, &hdev->blacklist); + + err = 0; + +err: + hci_dev_unlock_bh(hdev); + return err; +} + +int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr) +{ + struct bdaddr_list *entry; + int err = 0; + + hci_dev_lock_bh(hdev); + + if (bacmp(bdaddr, BDADDR_ANY) == 0) { + hci_blacklist_clear(hdev); + goto done; + } + + entry = hci_blacklist_lookup(hdev, bdaddr); + if (!entry) { + err = -ENOENT; + goto done; + } + + list_del(&entry->list); + kfree(entry); + +done: + hci_dev_unlock_bh(hdev); + return err; +} + +static void hci_clear_adv_cache(unsigned long arg) +{ + struct hci_dev *hdev = (void *) arg; + + hci_dev_lock(hdev); + + hci_adv_entries_clear(hdev); + + hci_dev_unlock(hdev); +} + +int hci_adv_entries_clear(struct hci_dev *hdev) +{ + struct adv_entry *entry, *tmp; + + list_for_each_entry_safe(entry, tmp, &hdev->adv_entries, list) { + list_del(&entry->list); + kfree(entry); + } + + BT_DBG("%s adv cache cleared", hdev->name); + + return 0; +} + +struct adv_entry *hci_find_adv_entry(struct hci_dev *hdev, bdaddr_t *bdaddr) +{ + struct adv_entry *entry; + + list_for_each_entry(entry, &hdev->adv_entries, list) + if (bacmp(bdaddr, &entry->bdaddr) == 0) + return entry; + + return NULL; +} + +static inline int is_connectable_adv(u8 evt_type) +{ + if (evt_type == ADV_IND || evt_type == ADV_DIRECT_IND) + return 1; + + return 0; +} + +int hci_add_adv_entry(struct hci_dev *hdev, + struct hci_ev_le_advertising_info *ev) +{ + struct adv_entry *entry; + + if (!is_connectable_adv(ev->evt_type)) + return -EINVAL; + + /* Only new entries should be added to adv_entries. So, if + * bdaddr was found, don't add it. */ + if (hci_find_adv_entry(hdev, &ev->bdaddr)) + return 0; + + entry = kzalloc(sizeof(*entry), GFP_ATOMIC); + if (!entry) + return -ENOMEM; + + bacpy(&entry->bdaddr, &ev->bdaddr); + entry->bdaddr_type = ev->bdaddr_type; + + list_add(&entry->list, &hdev->adv_entries); + + BT_DBG("%s adv entry added: address %s type %u", hdev->name, + batostr(&entry->bdaddr), entry->bdaddr_type); + + return 0; +} + /* Register HCI device */ int hci_register_dev(struct hci_dev *hdev) { @@ -1268,6 +1506,10 @@ int hci_register_dev(struct hci_dev *hdev) INIT_LIST_HEAD(&hdev->remote_oob_data); + INIT_LIST_HEAD(&hdev->adv_entries); + setup_timer(&hdev->adv_timer, hci_clear_adv_cache, + (unsigned long) hdev); + INIT_WORK(&hdev->power_on, hci_power_on); INIT_WORK(&hdev->power_off, hci_power_off); setup_timer(&hdev->off_timer, hci_auto_off, (unsigned long) hdev); @@ -1282,6 +1524,11 @@ int hci_register_dev(struct hci_dev *hdev) if (!hdev->workqueue) goto nomem; + hdev->tfm = crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(hdev->tfm)) + BT_INFO("Failed to load transform for ecb(aes): %ld", + PTR_ERR(hdev->tfm)); + hci_register_sysfs(hdev); hdev->rfkill = rfkill_alloc(hdev->name, &hdev->dev, @@ -1330,6 +1577,9 @@ int hci_unregister_dev(struct hci_dev *hdev) !test_bit(HCI_SETUP, &hdev->flags)) mgmt_index_removed(hdev->id); + if (!IS_ERR(hdev->tfm)) + crypto_free_blkcipher(hdev->tfm); + hci_notify(hdev, HCI_DEV_UNREG); if (hdev->rfkill) { @@ -1340,6 +1590,7 @@ int hci_unregister_dev(struct hci_dev *hdev) hci_unregister_sysfs(hdev); hci_del_off_timer(hdev); + del_timer(&hdev->adv_timer); destroy_workqueue(hdev->workqueue); @@ -1348,6 +1599,7 @@ int hci_unregister_dev(struct hci_dev *hdev) hci_uuids_clear(hdev); hci_link_keys_clear(hdev); hci_remote_oob_data_clear(hdev); + hci_adv_entries_clear(hdev); hci_dev_unlock_bh(hdev); __hci_dev_put(hdev); @@ -1519,7 +1771,7 @@ int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count) data += (count - rem); count = rem; - }; + } return rem; } @@ -1554,7 +1806,7 @@ int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count) data += (count - rem); count = rem; - }; + } return rem; } @@ -1891,7 +2143,7 @@ static inline void hci_sched_acl(struct hci_dev *hdev) while (quote-- && (skb = skb_dequeue(&conn->data_q))) { BT_DBG("skb %p len %d", skb, skb->len); - hci_conn_enter_active_mode(conn); + hci_conn_enter_active_mode(conn, bt_cb(skb)->force_active); hci_send_frame(skb); hdev->acl_last_tx = jiffies; @@ -2030,7 +2282,7 @@ static inline void hci_acldata_packet(struct hci_dev *hdev, struct sk_buff *skb) if (conn) { register struct hci_proto *hp; - hci_conn_enter_active_mode(conn); + hci_conn_enter_active_mode(conn, bt_cb(skb)->force_active); /* Send to upper protocol */ hp = hci_proto[HCI_PROTO_L2CAP]; diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f13ddbf858b..a40170e022e 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -45,6 +45,8 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> +static int enable_le; + /* Handle HCI Event packets */ static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) @@ -477,14 +479,16 @@ static void hci_setup_event_mask(struct hci_dev *hdev) * command otherwise */ u8 events[8] = { 0xff, 0xff, 0xfb, 0xff, 0x00, 0x00, 0x00, 0x00 }; - /* Events for 1.2 and newer controllers */ - if (hdev->lmp_ver > 1) { - events[4] |= 0x01; /* Flow Specification Complete */ - events[4] |= 0x02; /* Inquiry Result with RSSI */ - events[4] |= 0x04; /* Read Remote Extended Features Complete */ - events[5] |= 0x08; /* Synchronous Connection Complete */ - events[5] |= 0x10; /* Synchronous Connection Changed */ - } + /* CSR 1.1 dongles does not accept any bitfield so don't try to set + * any event mask for pre 1.2 devices */ + if (hdev->lmp_ver <= 1) + return; + + events[4] |= 0x01; /* Flow Specification Complete */ + events[4] |= 0x02; /* Inquiry Result with RSSI */ + events[4] |= 0x04; /* Read Remote Extended Features Complete */ + events[5] |= 0x08; /* Synchronous Connection Complete */ + events[5] |= 0x10; /* Synchronous Connection Changed */ if (hdev->features[3] & LMP_RSSI_INQ) events[4] |= 0x04; /* Inquiry Result with RSSI */ @@ -523,6 +527,20 @@ static void hci_setup_event_mask(struct hci_dev *hdev) hci_send_cmd(hdev, HCI_OP_SET_EVENT_MASK, sizeof(events), events); } +static void hci_set_le_support(struct hci_dev *hdev) +{ + struct hci_cp_write_le_host_supported cp; + + memset(&cp, 0, sizeof(cp)); + + if (enable_le) { + cp.le = 1; + cp.simul = !!(hdev->features[6] & LMP_SIMUL_LE_BR); + } + + hci_send_cmd(hdev, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(cp), &cp); +} + static void hci_setup(struct hci_dev *hdev) { hci_setup_event_mask(hdev); @@ -540,6 +558,17 @@ static void hci_setup(struct hci_dev *hdev) if (hdev->features[7] & LMP_INQ_TX_PWR) hci_send_cmd(hdev, HCI_OP_READ_INQ_RSP_TX_POWER, 0, NULL); + + if (hdev->features[7] & LMP_EXTFEATURES) { + struct hci_cp_read_local_ext_features cp; + + cp.page = 0x01; + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_EXT_FEATURES, + sizeof(cp), &cp); + } + + if (hdev->features[4] & LMP_LE) + hci_set_le_support(hdev); } static void hci_cc_read_local_version(struct hci_dev *hdev, struct sk_buff *skb) @@ -656,6 +685,21 @@ static void hci_cc_read_local_features(struct hci_dev *hdev, struct sk_buff *skb hdev->features[6], hdev->features[7]); } +static void hci_cc_read_local_ext_features(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_rp_read_local_ext_features *rp = (void *) skb->data; + + BT_DBG("%s status 0x%x", hdev->name, rp->status); + + if (rp->status) + return; + + memcpy(hdev->extfeatures, rp->features, 8); + + hci_req_complete(hdev, HCI_OP_READ_LOCAL_EXT_FEATURES, rp->status); +} + static void hci_cc_read_buffer_size(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_rp_read_buffer_size *rp = (void *) skb->data; @@ -839,6 +883,72 @@ static void hci_cc_read_local_oob_data_reply(struct hci_dev *hdev, rp->randomizer, rp->status); } +static void hci_cc_le_set_scan_enable(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_le_set_scan_enable *cp; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%x", hdev->name, status); + + if (status) + return; + + cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE); + if (!cp) + return; + + hci_dev_lock(hdev); + + if (cp->enable == 0x01) { + del_timer(&hdev->adv_timer); + hci_adv_entries_clear(hdev); + } else if (cp->enable == 0x00) { + mod_timer(&hdev->adv_timer, jiffies + ADV_CLEAR_TIMEOUT); + } + + hci_dev_unlock(hdev); +} + +static void hci_cc_le_ltk_reply(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_rp_le_ltk_reply *rp = (void *) skb->data; + + BT_DBG("%s status 0x%x", hdev->name, rp->status); + + if (rp->status) + return; + + hci_req_complete(hdev, HCI_OP_LE_LTK_REPLY, rp->status); +} + +static void hci_cc_le_ltk_neg_reply(struct hci_dev *hdev, struct sk_buff *skb) +{ + struct hci_rp_le_ltk_neg_reply *rp = (void *) skb->data; + + BT_DBG("%s status 0x%x", hdev->name, rp->status); + + if (rp->status) + return; + + hci_req_complete(hdev, HCI_OP_LE_LTK_NEG_REPLY, rp->status); +} + +static inline void hci_cc_write_le_host_supported(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_cp_read_local_ext_features cp; + __u8 status = *((__u8 *) skb->data); + + BT_DBG("%s status 0x%x", hdev->name, status); + + if (status) + return; + + cp.page = 0x01; + hci_send_cmd(hdev, HCI_OP_READ_LOCAL_EXT_FEATURES, sizeof(cp), &cp); +} + static inline void hci_cs_inquiry(struct hci_dev *hdev, __u8 status) { BT_DBG("%s status 0x%x", hdev->name, status); @@ -1207,16 +1317,23 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, __u8 status) } else { if (!conn) { conn = hci_conn_add(hdev, LE_LINK, &cp->peer_addr); - if (conn) + if (conn) { + conn->dst_type = cp->peer_addr_type; conn->out = 1; - else + } else { BT_ERR("No memory for new connection"); + } } } hci_dev_unlock(hdev); } +static void hci_cs_le_start_enc(struct hci_dev *hdev, u8 status) +{ + BT_DBG("%s status 0x%x", hdev->name, status); +} + static inline void hci_inquiry_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) { __u8 status = *((__u8 *) skb->data); @@ -1460,51 +1577,58 @@ static inline void hci_auth_complete_evt(struct hci_dev *hdev, struct sk_buff *s hci_dev_lock(hdev); conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); - if (conn) { - if (!ev->status) { + if (!conn) + goto unlock; + + if (!ev->status) { + if (!(conn->ssp_mode > 0 && hdev->ssp_mode > 0) && + test_bit(HCI_CONN_REAUTH_PEND, &conn->pend)) { + BT_INFO("re-auth of legacy device is not possible."); + } else { conn->link_mode |= HCI_LM_AUTH; conn->sec_level = conn->pending_sec_level; - } else { - mgmt_auth_failed(hdev->id, &conn->dst, ev->status); } + } else { + mgmt_auth_failed(hdev->id, &conn->dst, ev->status); + } - clear_bit(HCI_CONN_AUTH_PEND, &conn->pend); + clear_bit(HCI_CONN_AUTH_PEND, &conn->pend); + clear_bit(HCI_CONN_REAUTH_PEND, &conn->pend); - if (conn->state == BT_CONFIG) { - if (!ev->status && hdev->ssp_mode > 0 && - conn->ssp_mode > 0) { - struct hci_cp_set_conn_encrypt cp; - cp.handle = ev->handle; - cp.encrypt = 0x01; - hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, - sizeof(cp), &cp); - } else { - conn->state = BT_CONNECTED; - hci_proto_connect_cfm(conn, ev->status); - hci_conn_put(conn); - } + if (conn->state == BT_CONFIG) { + if (!ev->status && hdev->ssp_mode > 0 && conn->ssp_mode > 0) { + struct hci_cp_set_conn_encrypt cp; + cp.handle = ev->handle; + cp.encrypt = 0x01; + hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), + &cp); } else { - hci_auth_cfm(conn, ev->status); - - hci_conn_hold(conn); - conn->disc_timeout = HCI_DISCONN_TIMEOUT; + conn->state = BT_CONNECTED; + hci_proto_connect_cfm(conn, ev->status); hci_conn_put(conn); } + } else { + hci_auth_cfm(conn, ev->status); - if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) { - if (!ev->status) { - struct hci_cp_set_conn_encrypt cp; - cp.handle = ev->handle; - cp.encrypt = 0x01; - hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, - sizeof(cp), &cp); - } else { - clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend); - hci_encrypt_cfm(conn, ev->status, 0x00); - } + hci_conn_hold(conn); + conn->disc_timeout = HCI_DISCONN_TIMEOUT; + hci_conn_put(conn); + } + + if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend)) { + if (!ev->status) { + struct hci_cp_set_conn_encrypt cp; + cp.handle = ev->handle; + cp.encrypt = 0x01; + hci_send_cmd(hdev, HCI_OP_SET_CONN_ENCRYPT, sizeof(cp), + &cp); + } else { + clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->pend); + hci_encrypt_cfm(conn, ev->status, 0x00); } } +unlock: hci_dev_unlock(hdev); } @@ -1555,6 +1679,7 @@ static inline void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff * /* Encryption implies authentication */ conn->link_mode |= HCI_LM_AUTH; conn->link_mode |= HCI_LM_ENCRYPT; + conn->sec_level = conn->pending_sec_level; } else conn->link_mode &= ~HCI_LM_ENCRYPT; } @@ -1758,6 +1883,10 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk hci_cc_read_local_features(hdev, skb); break; + case HCI_OP_READ_LOCAL_EXT_FEATURES: + hci_cc_read_local_ext_features(hdev, skb); + break; + case HCI_OP_READ_BUFFER_SIZE: hci_cc_read_buffer_size(hdev, skb); break; @@ -1814,6 +1943,22 @@ static inline void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *sk hci_cc_user_confirm_neg_reply(hdev, skb); break; + case HCI_OP_LE_SET_SCAN_ENABLE: + hci_cc_le_set_scan_enable(hdev, skb); + break; + + case HCI_OP_LE_LTK_REPLY: + hci_cc_le_ltk_reply(hdev, skb); + break; + + case HCI_OP_LE_LTK_NEG_REPLY: + hci_cc_le_ltk_neg_reply(hdev, skb); + break; + + case HCI_OP_WRITE_LE_HOST_SUPPORTED: + hci_cc_write_le_host_supported(hdev, skb); + break; + default: BT_DBG("%s opcode 0x%x", hdev->name, opcode); break; @@ -1892,6 +2037,10 @@ static inline void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_cs_le_create_conn(hdev, ev->status); break; + case HCI_OP_LE_START_ENC: + hci_cs_le_start_enc(hdev, ev->status); + break; + default: BT_DBG("%s opcode 0x%x", hdev->name, opcode); break; @@ -2656,6 +2805,8 @@ static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff hci_dev_unlock(hdev); return; } + + conn->dst_type = ev->bdaddr_type; } if (ev->status) { @@ -2668,6 +2819,7 @@ static inline void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff mgmt_connected(hdev->id, &ev->bdaddr); + conn->sec_level = BT_SECURITY_LOW; conn->handle = __le16_to_cpu(ev->handle); conn->state = BT_CONNECTED; @@ -2680,6 +2832,64 @@ unlock: hci_dev_unlock(hdev); } +static inline void hci_le_adv_report_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_advertising_info *ev; + u8 num_reports; + + num_reports = skb->data[0]; + ev = (void *) &skb->data[1]; + + hci_dev_lock(hdev); + + hci_add_adv_entry(hdev, ev); + + while (--num_reports) { + ev = (void *) (ev->data + ev->length + 1); + hci_add_adv_entry(hdev, ev); + } + + hci_dev_unlock(hdev); +} + +static inline void hci_le_ltk_request_evt(struct hci_dev *hdev, + struct sk_buff *skb) +{ + struct hci_ev_le_ltk_req *ev = (void *) skb->data; + struct hci_cp_le_ltk_reply cp; + struct hci_cp_le_ltk_neg_reply neg; + struct hci_conn *conn; + struct link_key *ltk; + + BT_DBG("%s handle %d", hdev->name, cpu_to_le16(ev->handle)); + + hci_dev_lock(hdev); + + conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->handle)); + if (conn == NULL) + goto not_found; + + ltk = hci_find_ltk(hdev, ev->ediv, ev->random); + if (ltk == NULL) + goto not_found; + + memcpy(cp.ltk, ltk->val, sizeof(ltk->val)); + cp.handle = cpu_to_le16(conn->handle); + conn->pin_length = ltk->pin_len; + + hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); + + hci_dev_unlock(hdev); + + return; + +not_found: + neg.handle = ev->handle; + hci_send_cmd(hdev, HCI_OP_LE_LTK_NEG_REPLY, sizeof(neg), &neg); + hci_dev_unlock(hdev); +} + static inline void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) { struct hci_ev_le_meta *le_ev = (void *) skb->data; @@ -2691,6 +2901,14 @@ static inline void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_le_conn_complete_evt(hdev, skb); break; + case HCI_EV_LE_ADVERTISING_REPORT: + hci_le_adv_report_evt(hdev, skb); + break; + + case HCI_EV_LE_LTK_REQ: + hci_le_ltk_request_evt(hdev, skb); + break; + default: break; } @@ -2884,3 +3102,6 @@ void hci_si_event(struct hci_dev *hdev, int type, int dlen, void *data) hci_send_to_sock(hdev, skb, NULL); kfree_skb(skb); } + +module_param(enable_le, bool, 0444); +MODULE_PARM_DESC(enable_le, "Enable LE support"); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 295e4a88fff..ff02cf5e77c 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -180,82 +180,24 @@ static int hci_sock_release(struct socket *sock) return 0; } -struct bdaddr_list *hci_blacklist_lookup(struct hci_dev *hdev, bdaddr_t *bdaddr) -{ - struct list_head *p; - - list_for_each(p, &hdev->blacklist) { - struct bdaddr_list *b; - - b = list_entry(p, struct bdaddr_list, list); - - if (bacmp(bdaddr, &b->bdaddr) == 0) - return b; - } - - return NULL; -} - -static int hci_blacklist_add(struct hci_dev *hdev, void __user *arg) +static int hci_sock_blacklist_add(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; - struct bdaddr_list *entry; if (copy_from_user(&bdaddr, arg, sizeof(bdaddr))) return -EFAULT; - if (bacmp(&bdaddr, BDADDR_ANY) == 0) - return -EBADF; - - if (hci_blacklist_lookup(hdev, &bdaddr)) - return -EEXIST; - - entry = kzalloc(sizeof(struct bdaddr_list), GFP_KERNEL); - if (!entry) - return -ENOMEM; - - bacpy(&entry->bdaddr, &bdaddr); - - list_add(&entry->list, &hdev->blacklist); - - return 0; -} - -int hci_blacklist_clear(struct hci_dev *hdev) -{ - struct list_head *p, *n; - - list_for_each_safe(p, n, &hdev->blacklist) { - struct bdaddr_list *b; - - b = list_entry(p, struct bdaddr_list, list); - - list_del(p); - kfree(b); - } - - return 0; + return hci_blacklist_add(hdev, &bdaddr); } -static int hci_blacklist_del(struct hci_dev *hdev, void __user *arg) +static int hci_sock_blacklist_del(struct hci_dev *hdev, void __user *arg) { bdaddr_t bdaddr; - struct bdaddr_list *entry; if (copy_from_user(&bdaddr, arg, sizeof(bdaddr))) return -EFAULT; - if (bacmp(&bdaddr, BDADDR_ANY) == 0) - return hci_blacklist_clear(hdev); - - entry = hci_blacklist_lookup(hdev, &bdaddr); - if (!entry) - return -ENOENT; - - list_del(&entry->list); - kfree(entry); - - return 0; + return hci_blacklist_del(hdev, &bdaddr); } /* Ioctls that require bound socket */ @@ -290,12 +232,12 @@ static inline int hci_sock_bound_ioctl(struct sock *sk, unsigned int cmd, unsign case HCIBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EACCES; - return hci_blacklist_add(hdev, (void __user *) arg); + return hci_sock_blacklist_add(hdev, (void __user *) arg); case HCIUNBLOCKADDR: if (!capable(CAP_NET_ADMIN)) return -EACCES; - return hci_blacklist_del(hdev, (void __user *) arg); + return hci_sock_blacklist_del(hdev, (void __user *) arg); default: if (hdev->ioctl) diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c index c405a954a60..43b4c2deb7c 100644 --- a/net/bluetooth/hidp/core.c +++ b/net/bluetooth/hidp/core.c @@ -464,7 +464,8 @@ static void hidp_idle_timeout(unsigned long arg) { struct hidp_session *session = (struct hidp_session *) arg; - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); } static void hidp_set_timer(struct hidp_session *session) @@ -535,7 +536,8 @@ static void hidp_process_hid_control(struct hidp_session *session, skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(current); } } @@ -706,9 +708,8 @@ static int hidp_session(void *arg) add_wait_queue(sk_sleep(intr_sk), &intr_wait); session->waiting_for_startup = 0; wake_up_interruptible(&session->startup_queue); - while (!kthread_should_stop()) { - set_current_state(TASK_INTERRUPTIBLE); - + set_current_state(TASK_INTERRUPTIBLE); + while (!atomic_read(&session->terminate)) { if (ctrl_sk->sk_state != BT_CONNECTED || intr_sk->sk_state != BT_CONNECTED) break; @@ -726,6 +727,7 @@ static int hidp_session(void *arg) hidp_process_transmit(session); schedule(); + set_current_state(TASK_INTERRUPTIBLE); } set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(intr_sk), &intr_wait); @@ -1060,7 +1062,8 @@ int hidp_add_connection(struct hidp_connadd_req *req, struct socket *ctrl_sock, err_add_device: hid_destroy_device(session->hid); session->hid = NULL; - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); unlink: hidp_del_timer(session); @@ -1111,7 +1114,8 @@ int hidp_del_connection(struct hidp_conndel_req *req) skb_queue_purge(&session->ctrl_transmit); skb_queue_purge(&session->intr_transmit); - kthread_stop(session->task); + atomic_inc(&session->terminate); + wake_up_process(session->task); } } else err = -ENOENT; diff --git a/net/bluetooth/hidp/hidp.h b/net/bluetooth/hidp/hidp.h index 19e95004b28..af1bcc823f2 100644 --- a/net/bluetooth/hidp/hidp.h +++ b/net/bluetooth/hidp/hidp.h @@ -142,6 +142,7 @@ struct hidp_session { uint ctrl_mtu; uint intr_mtu; + atomic_t terminate; struct task_struct *task; unsigned char keys[8]; diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index e64a1c2df23..3204ba8a701 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -54,26 +54,39 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> +#include <net/bluetooth/smp.h> int disable_ertm; static u32 l2cap_feat_mask = L2CAP_FEAT_FIXED_CHAN; static u8 l2cap_fixed_chan[8] = { 0x02, }; -static struct workqueue_struct *_busy_wq; - -LIST_HEAD(chan_list); -DEFINE_RWLOCK(chan_list_lock); - -static void l2cap_busy_work(struct work_struct *work); +static LIST_HEAD(chan_list); +static DEFINE_RWLOCK(chan_list_lock); static struct sk_buff *l2cap_build_cmd(struct l2cap_conn *conn, u8 code, u8 ident, u16 dlen, void *data); +static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, + void *data); static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data); +static void l2cap_send_disconn_req(struct l2cap_conn *conn, + struct l2cap_chan *chan, int err); static int l2cap_ertm_data_rcv(struct sock *sk, struct sk_buff *skb); /* ---- L2CAP channels ---- */ + +static inline void chan_hold(struct l2cap_chan *c) +{ + atomic_inc(&c->refcnt); +} + +static inline void chan_put(struct l2cap_chan *c) +{ + if (atomic_dec_and_test(&c->refcnt)) + kfree(c); +} + static struct l2cap_chan *__l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 cid) { struct l2cap_chan *c; @@ -204,6 +217,62 @@ static u16 l2cap_alloc_cid(struct l2cap_conn *conn) return 0; } +static void l2cap_set_timer(struct l2cap_chan *chan, struct timer_list *timer, long timeout) +{ + BT_DBG("chan %p state %d timeout %ld", chan->sk, chan->state, timeout); + + if (!mod_timer(timer, jiffies + msecs_to_jiffies(timeout))) + chan_hold(chan); +} + +static void l2cap_clear_timer(struct l2cap_chan *chan, struct timer_list *timer) +{ + BT_DBG("chan %p state %d", chan, chan->state); + + if (timer_pending(timer) && del_timer(timer)) + chan_put(chan); +} + +static void l2cap_state_change(struct l2cap_chan *chan, int state) +{ + chan->state = state; + chan->ops->state_change(chan->data, state); +} + +static void l2cap_chan_timeout(unsigned long arg) +{ + struct l2cap_chan *chan = (struct l2cap_chan *) arg; + struct sock *sk = chan->sk; + int reason; + + BT_DBG("chan %p state %d", chan, chan->state); + + bh_lock_sock(sk); + + if (sock_owned_by_user(sk)) { + /* sk is owned by user. Try again later */ + __set_chan_timer(chan, HZ / 5); + bh_unlock_sock(sk); + chan_put(chan); + return; + } + + if (chan->state == BT_CONNECTED || chan->state == BT_CONFIG) + reason = ECONNREFUSED; + else if (chan->state == BT_CONNECT && + chan->sec_level != BT_SECURITY_SDP) + reason = ECONNREFUSED; + else + reason = ETIMEDOUT; + + l2cap_chan_close(chan, reason); + + bh_unlock_sock(sk); + + chan->ops->close(chan->data); + chan_put(chan); +} + struct l2cap_chan *l2cap_chan_create(struct sock *sk) { struct l2cap_chan *chan; @@ -218,6 +287,12 @@ struct l2cap_chan *l2cap_chan_create(struct sock *sk) list_add(&chan->global_l, &chan_list); write_unlock_bh(&chan_list_lock); + setup_timer(&chan->chan_timer, l2cap_chan_timeout, (unsigned long) chan); + + chan->state = BT_OPEN; + + atomic_set(&chan->refcnt, 1); + return chan; } @@ -227,13 +302,11 @@ void l2cap_chan_destroy(struct l2cap_chan *chan) list_del(&chan->global_l); write_unlock_bh(&chan_list_lock); - kfree(chan); + chan_put(chan); } static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) { - struct sock *sk = chan->sk; - BT_DBG("conn %p, psm 0x%2.2x, dcid 0x%4.4x", conn, chan->psm, chan->dcid); @@ -241,7 +314,7 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->conn = conn; - if (sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM) { + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED) { if (conn->hcon->type == LE_LINK) { /* LE connection */ chan->omtu = L2CAP_LE_DEFAULT_MTU; @@ -252,7 +325,7 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->scid = l2cap_alloc_cid(conn); chan->omtu = L2CAP_DEFAULT_MTU; } - } else if (sk->sk_type == SOCK_DGRAM) { + } else if (chan->chan_type == L2CAP_CHAN_CONN_LESS) { /* Connectionless socket */ chan->scid = L2CAP_CID_CONN_LESS; chan->dcid = L2CAP_CID_CONN_LESS; @@ -264,20 +337,20 @@ static void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) chan->omtu = L2CAP_DEFAULT_MTU; } - sock_hold(sk); + chan_hold(chan); list_add(&chan->list, &conn->chan_l); } /* Delete channel. * Must be called on the locked socket. */ -void l2cap_chan_del(struct l2cap_chan *chan, int err) +static void l2cap_chan_del(struct l2cap_chan *chan, int err) { struct sock *sk = chan->sk; struct l2cap_conn *conn = chan->conn; struct sock *parent = bt_sk(sk)->parent; - l2cap_sock_clear_timer(sk); + __clear_chan_timer(chan); BT_DBG("chan %p, conn %p, err %d", chan, conn, err); @@ -286,13 +359,13 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) write_lock_bh(&conn->chan_lock); list_del(&chan->list); write_unlock_bh(&conn->chan_lock); - __sock_put(sk); + chan_put(chan); chan->conn = NULL; hci_conn_put(conn->hcon); } - sk->sk_state = BT_CLOSED; + l2cap_state_change(chan, BT_CLOSED); sock_set_flag(sk, SOCK_ZAPPED); if (err) @@ -304,8 +377,8 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) } else sk->sk_state_change(sk); - if (!(chan->conf_state & L2CAP_CONF_OUTPUT_DONE && - chan->conf_state & L2CAP_CONF_INPUT_DONE)) + if (!(test_bit(CONF_OUTPUT_DONE, &chan->conf_state) && + test_bit(CONF_INPUT_DONE, &chan->conf_state))) return; skb_queue_purge(&chan->tx_q); @@ -313,12 +386,11 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) if (chan->mode == L2CAP_MODE_ERTM) { struct srej_list *l, *tmp; - del_timer(&chan->retrans_timer); - del_timer(&chan->monitor_timer); - del_timer(&chan->ack_timer); + __clear_retrans_timer(chan); + __clear_monitor_timer(chan); + __clear_ack_timer(chan); skb_queue_purge(&chan->srej_q); - skb_queue_purge(&chan->busy_q); list_for_each_entry_safe(l, tmp, &chan->srej_l, list) { list_del(&l->list); @@ -327,11 +399,86 @@ void l2cap_chan_del(struct l2cap_chan *chan, int err) } } -static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) +static void l2cap_chan_cleanup_listen(struct sock *parent) +{ + struct sock *sk; + + BT_DBG("parent %p", parent); + + /* Close not yet accepted channels */ + while ((sk = bt_accept_dequeue(parent, NULL))) { + struct l2cap_chan *chan = l2cap_pi(sk)->chan; + __clear_chan_timer(chan); + lock_sock(sk); + l2cap_chan_close(chan, ECONNRESET); + release_sock(sk); + chan->ops->close(chan->data); + } +} + +void l2cap_chan_close(struct l2cap_chan *chan, int reason) { + struct l2cap_conn *conn = chan->conn; struct sock *sk = chan->sk; - if (sk->sk_type == SOCK_RAW) { + BT_DBG("chan %p state %d socket %p", chan, chan->state, sk->sk_socket); + + switch (chan->state) { + case BT_LISTEN: + l2cap_chan_cleanup_listen(sk); + + l2cap_state_change(chan, BT_CLOSED); + sock_set_flag(sk, SOCK_ZAPPED); + break; + + case BT_CONNECTED: + case BT_CONFIG: + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && + conn->hcon->type == ACL_LINK) { + __clear_chan_timer(chan); + __set_chan_timer(chan, sk->sk_sndtimeo); + l2cap_send_disconn_req(conn, chan, reason); + } else + l2cap_chan_del(chan, reason); + break; + + case BT_CONNECT2: + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && + conn->hcon->type == ACL_LINK) { + struct l2cap_conn_rsp rsp; + __u16 result; + + if (bt_sk(sk)->defer_setup) + result = L2CAP_CR_SEC_BLOCK; + else + result = L2CAP_CR_BAD_PSM; + l2cap_state_change(chan, BT_DISCONN); + + rsp.scid = cpu_to_le16(chan->dcid); + rsp.dcid = cpu_to_le16(chan->scid); + rsp.result = cpu_to_le16(result); + rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, + sizeof(rsp), &rsp); + } + + l2cap_chan_del(chan, reason); + break; + + case BT_CONNECT: + case BT_DISCONN: + l2cap_chan_del(chan, reason); + break; + + default: + sock_set_flag(sk, SOCK_ZAPPED); + break; + } +} + +static inline u8 l2cap_get_auth_type(struct l2cap_chan *chan) +{ + if (chan->chan_type == L2CAP_CHAN_RAW) { switch (chan->sec_level) { case BT_SECURITY_HIGH: return HCI_AT_DEDICATED_BONDING_MITM; @@ -371,7 +518,7 @@ static inline int l2cap_check_security(struct l2cap_chan *chan) return hci_conn_security(conn->hcon, chan->sec_level, auth_type); } -u8 l2cap_get_ident(struct l2cap_conn *conn) +static u8 l2cap_get_ident(struct l2cap_conn *conn) { u8 id; @@ -393,7 +540,7 @@ u8 l2cap_get_ident(struct l2cap_conn *conn) return id; } -void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data) +static void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *data) { struct sk_buff *skb = l2cap_build_cmd(conn, code, ident, len, data); u8 flags; @@ -408,6 +555,8 @@ void l2cap_send_cmd(struct l2cap_conn *conn, u8 ident, u8 code, u16 len, void *d else flags = ACL_START; + bt_cb(skb)->force_active = BT_POWER_FORCE_ACTIVE_ON; + hci_send_acl(conn->hcon, skb, flags); } @@ -415,13 +564,11 @@ static inline void l2cap_send_sframe(struct l2cap_chan *chan, u16 control) { struct sk_buff *skb; struct l2cap_hdr *lh; - struct l2cap_pinfo *pi = l2cap_pi(chan->sk); struct l2cap_conn *conn = chan->conn; - struct sock *sk = (struct sock *)pi; int count, hlen = L2CAP_HDR_SIZE + 2; u8 flags; - if (sk->sk_state != BT_CONNECTED) + if (chan->state != BT_CONNECTED) return; if (chan->fcs == L2CAP_FCS_CRC16) @@ -432,15 +579,11 @@ static inline void l2cap_send_sframe(struct l2cap_chan *chan, u16 control) count = min_t(unsigned int, conn->mtu, hlen); control |= L2CAP_CTRL_FRAME_TYPE; - if (chan->conn_state & L2CAP_CONN_SEND_FBIT) { + if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) control |= L2CAP_CTRL_FINAL; - chan->conn_state &= ~L2CAP_CONN_SEND_FBIT; - } - if (chan->conn_state & L2CAP_CONN_SEND_PBIT) { + if (test_and_clear_bit(CONN_SEND_PBIT, &chan->conn_state)) control |= L2CAP_CTRL_POLL; - chan->conn_state &= ~L2CAP_CONN_SEND_PBIT; - } skb = bt_skb_alloc(count, GFP_ATOMIC); if (!skb) @@ -461,14 +604,16 @@ static inline void l2cap_send_sframe(struct l2cap_chan *chan, u16 control) else flags = ACL_START; + bt_cb(skb)->force_active = chan->force_active; + hci_send_acl(chan->conn->hcon, skb, flags); } static inline void l2cap_send_rr_or_rnr(struct l2cap_chan *chan, u16 control) { - if (chan->conn_state & L2CAP_CONN_LOCAL_BUSY) { + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { control |= L2CAP_SUPER_RCV_NOT_READY; - chan->conn_state |= L2CAP_CONN_RNR_SENT; + set_bit(CONN_RNR_SENT, &chan->conn_state); } else control |= L2CAP_SUPER_RCV_READY; @@ -479,7 +624,7 @@ static inline void l2cap_send_rr_or_rnr(struct l2cap_chan *chan, u16 control) static inline int __l2cap_no_conn_pending(struct l2cap_chan *chan) { - return !(chan->conf_state & L2CAP_CONF_CONNECT_PEND); + return !test_bit(CONF_CONNECT_PEND, &chan->conf_state); } static void l2cap_do_start(struct l2cap_chan *chan) @@ -497,7 +642,7 @@ static void l2cap_do_start(struct l2cap_chan *chan) req.psm = chan->psm; chan->ident = l2cap_get_ident(conn); - chan->conf_state |= L2CAP_CONF_CONNECT_PEND; + set_bit(CONF_CONNECT_PEND, &chan->conf_state); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); @@ -533,7 +678,7 @@ static inline int l2cap_mode_supported(__u8 mode, __u32 feat_mask) } } -void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *chan, int err) +static void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *chan, int err) { struct sock *sk; struct l2cap_disconn_req req; @@ -544,9 +689,9 @@ void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *chan, in sk = chan->sk; if (chan->mode == L2CAP_MODE_ERTM) { - del_timer(&chan->retrans_timer); - del_timer(&chan->monitor_timer); - del_timer(&chan->ack_timer); + __clear_retrans_timer(chan); + __clear_monitor_timer(chan); + __clear_ack_timer(chan); } req.dcid = cpu_to_le16(chan->dcid); @@ -554,7 +699,7 @@ void l2cap_send_disconn_req(struct l2cap_conn *conn, struct l2cap_chan *chan, in l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_DISCONN_REQ, sizeof(req), &req); - sk->sk_state = BT_DISCONN; + l2cap_state_change(chan, BT_DISCONN); sk->sk_err = err; } @@ -572,13 +717,12 @@ static void l2cap_conn_start(struct l2cap_conn *conn) bh_lock_sock(sk); - if (sk->sk_type != SOCK_SEQPACKET && - sk->sk_type != SOCK_STREAM) { + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { bh_unlock_sock(sk); continue; } - if (sk->sk_state == BT_CONNECT) { + if (chan->state == BT_CONNECT) { struct l2cap_conn_req req; if (!l2cap_check_security(chan) || @@ -587,15 +731,14 @@ static void l2cap_conn_start(struct l2cap_conn *conn) continue; } - if (!l2cap_mode_supported(chan->mode, - conn->feat_mask) - && chan->conf_state & - L2CAP_CONF_STATE2_DEVICE) { - /* __l2cap_sock_close() calls list_del(chan) + if (!l2cap_mode_supported(chan->mode, conn->feat_mask) + && test_bit(CONF_STATE2_DEVICE, + &chan->conf_state)) { + /* l2cap_chan_close() calls list_del(chan) * so release the lock */ - read_unlock_bh(&conn->chan_lock); - __l2cap_sock_close(sk, ECONNRESET); - read_lock_bh(&conn->chan_lock); + read_unlock(&conn->chan_lock); + l2cap_chan_close(chan, ECONNRESET); + read_lock(&conn->chan_lock); bh_unlock_sock(sk); continue; } @@ -604,12 +747,12 @@ static void l2cap_conn_start(struct l2cap_conn *conn) req.psm = chan->psm; chan->ident = l2cap_get_ident(conn); - chan->conf_state |= L2CAP_CONF_CONNECT_PEND; + set_bit(CONF_CONNECT_PEND, &chan->conf_state); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); - } else if (sk->sk_state == BT_CONNECT2) { + } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; char buf[128]; rsp.scid = cpu_to_le16(chan->dcid); @@ -620,10 +763,11 @@ static void l2cap_conn_start(struct l2cap_conn *conn) struct sock *parent = bt_sk(sk)->parent; rsp.result = cpu_to_le16(L2CAP_CR_PEND); rsp.status = cpu_to_le16(L2CAP_CS_AUTHOR_PEND); - parent->sk_data_ready(parent, 0); + if (parent) + parent->sk_data_ready(parent, 0); } else { - sk->sk_state = BT_CONFIG; + l2cap_state_change(chan, BT_CONFIG); rsp.result = cpu_to_le16(L2CAP_CR_SUCCESS); rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); } @@ -635,13 +779,13 @@ static void l2cap_conn_start(struct l2cap_conn *conn) l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); - if (chan->conf_state & L2CAP_CONF_REQ_SENT || + if (test_bit(CONF_REQ_SENT, &chan->conf_state) || rsp.result != L2CAP_CR_SUCCESS) { bh_unlock_sock(sk); continue; } - chan->conf_state |= L2CAP_CONF_REQ_SENT; + set_bit(CONF_REQ_SENT, &chan->conf_state); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; @@ -665,7 +809,7 @@ static struct l2cap_chan *l2cap_global_chan_by_scid(int state, __le16 cid, bdadd list_for_each_entry(c, &chan_list, global_l) { struct sock *sk = c->sk; - if (state && sk->sk_state != state) + if (state && c->state != state) continue; if (c->scid == cid) { @@ -709,24 +853,16 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) goto clean; } - sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); - if (!sk) - goto clean; - - chan = l2cap_chan_create(sk); - if (!chan) { - l2cap_sock_kill(sk); + chan = pchan->ops->new_connection(pchan->data); + if (!chan) goto clean; - } - l2cap_pi(sk)->chan = chan; + sk = chan->sk; write_lock_bh(&conn->chan_lock); hci_conn_hold(conn->hcon); - l2cap_sock_init(sk, parent); - bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); @@ -734,9 +870,9 @@ static void l2cap_le_conn_ready(struct l2cap_conn *conn) __l2cap_chan_add(conn, chan); - l2cap_sock_set_timer(sk, sk->sk_sndtimeo); + __set_chan_timer(chan, sk->sk_sndtimeo); - sk->sk_state = BT_CONNECTED; + l2cap_state_change(chan, BT_CONNECTED); parent->sk_data_ready(parent, 0); write_unlock_bh(&conn->chan_lock); @@ -745,6 +881,23 @@ clean: bh_unlock_sock(parent); } +static void l2cap_chan_ready(struct sock *sk) +{ + struct l2cap_chan *chan = l2cap_pi(sk)->chan; + struct sock *parent = bt_sk(sk)->parent; + + BT_DBG("sk %p, parent %p", sk, parent); + + chan->conf_state = 0; + __clear_chan_timer(chan); + + l2cap_state_change(chan, BT_CONNECTED); + sk->sk_state_change(sk); + + if (parent) + parent->sk_data_ready(parent, 0); +} + static void l2cap_conn_ready(struct l2cap_conn *conn) { struct l2cap_chan *chan; @@ -762,17 +915,15 @@ static void l2cap_conn_ready(struct l2cap_conn *conn) bh_lock_sock(sk); if (conn->hcon->type == LE_LINK) { - l2cap_sock_clear_timer(sk); - sk->sk_state = BT_CONNECTED; - sk->sk_state_change(sk); - } + if (smp_conn_security(conn, chan->sec_level)) + l2cap_chan_ready(sk); - if (sk->sk_type != SOCK_SEQPACKET && - sk->sk_type != SOCK_STREAM) { - l2cap_sock_clear_timer(sk); - sk->sk_state = BT_CONNECTED; + } else if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { + __clear_chan_timer(chan); + l2cap_state_change(chan, BT_CONNECTED); sk->sk_state_change(sk); - } else if (sk->sk_state == BT_CONNECT) + + } else if (chan->state == BT_CONNECT) l2cap_do_start(chan); bh_unlock_sock(sk); @@ -810,6 +961,45 @@ static void l2cap_info_timeout(unsigned long arg) l2cap_conn_start(conn); } +static void l2cap_conn_del(struct hci_conn *hcon, int err) +{ + struct l2cap_conn *conn = hcon->l2cap_data; + struct l2cap_chan *chan, *l; + struct sock *sk; + + if (!conn) + return; + + BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); + + kfree_skb(conn->rx_skb); + + /* Kill channels */ + list_for_each_entry_safe(chan, l, &conn->chan_l, list) { + sk = chan->sk; + bh_lock_sock(sk); + l2cap_chan_del(chan, err); + bh_unlock_sock(sk); + chan->ops->close(chan->data); + } + + if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) + del_timer_sync(&conn->info_timer); + + if (test_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) + del_timer(&conn->security_timer); + + hcon->l2cap_data = NULL; + kfree(conn); +} + +static void security_timeout(unsigned long arg) +{ + struct l2cap_conn *conn = (void *) arg; + + l2cap_conn_del(conn->hcon, ETIMEDOUT); +} + static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) { struct l2cap_conn *conn = hcon->l2cap_data; @@ -841,7 +1031,10 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) INIT_LIST_HEAD(&conn->chan_l); - if (hcon->type != LE_LINK) + if (hcon->type == LE_LINK) + setup_timer(&conn->security_timer, security_timeout, + (unsigned long) conn); + else setup_timer(&conn->info_timer, l2cap_info_timeout, (unsigned long) conn); @@ -850,35 +1043,6 @@ static struct l2cap_conn *l2cap_conn_add(struct hci_conn *hcon, u8 status) return conn; } -static void l2cap_conn_del(struct hci_conn *hcon, int err) -{ - struct l2cap_conn *conn = hcon->l2cap_data; - struct l2cap_chan *chan, *l; - struct sock *sk; - - if (!conn) - return; - - BT_DBG("hcon %p conn %p, err %d", hcon, conn, err); - - kfree_skb(conn->rx_skb); - - /* Kill channels */ - list_for_each_entry_safe(chan, l, &conn->chan_l, list) { - sk = chan->sk; - bh_lock_sock(sk); - l2cap_chan_del(chan, err); - bh_unlock_sock(sk); - l2cap_sock_kill(sk); - } - - if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) - del_timer_sync(&conn->info_timer); - - hcon->l2cap_data = NULL; - kfree(conn); -} - static inline void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan) { write_lock_bh(&conn->chan_lock); @@ -900,7 +1064,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr list_for_each_entry(c, &chan_list, global_l) { struct sock *sk = c->sk; - if (state && sk->sk_state != state) + if (state && c->state != state) continue; if (c->psm == psm) { @@ -967,15 +1131,14 @@ int l2cap_chan_connect(struct l2cap_chan *chan) l2cap_chan_add(conn, chan); - sk->sk_state = BT_CONNECT; - l2cap_sock_set_timer(sk, sk->sk_sndtimeo); + l2cap_state_change(chan, BT_CONNECT); + __set_chan_timer(chan, sk->sk_sndtimeo); if (hcon->state == BT_CONNECTED) { - if (sk->sk_type != SOCK_SEQPACKET && - sk->sk_type != SOCK_STREAM) { - l2cap_sock_clear_timer(sk); + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) { + __clear_chan_timer(chan); if (l2cap_check_security(chan)) - sk->sk_state = BT_CONNECTED; + l2cap_state_change(chan, BT_CONNECTED); } else l2cap_do_start(chan); } @@ -1035,7 +1198,7 @@ static void l2cap_monitor_timeout(unsigned long arg) } chan->retry_count++; - __mod_monitor_timer(); + __set_monitor_timer(chan); l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); bh_unlock_sock(sk); @@ -1050,9 +1213,9 @@ static void l2cap_retrans_timeout(unsigned long arg) bh_lock_sock(sk); chan->retry_count = 1; - __mod_monitor_timer(); + __set_monitor_timer(chan); - chan->conn_state |= L2CAP_CONN_WAIT_F; + set_bit(CONN_WAIT_F, &chan->conn_state); l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_POLL); bh_unlock_sock(sk); @@ -1074,7 +1237,7 @@ static void l2cap_drop_acked_frames(struct l2cap_chan *chan) } if (!chan->unacked_frames) - del_timer(&chan->retrans_timer); + __clear_retrans_timer(chan); } void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) @@ -1089,6 +1252,7 @@ void l2cap_do_send(struct l2cap_chan *chan, struct sk_buff *skb) else flags = ACL_START; + bt_cb(skb)->force_active = chan->force_active; hci_send_acl(hcon, skb, flags); } @@ -1142,10 +1306,8 @@ static void l2cap_retransmit_one_frame(struct l2cap_chan *chan, u8 tx_seq) control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); control &= L2CAP_CTRL_SAR; - if (chan->conn_state & L2CAP_CONN_SEND_FBIT) { + if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) control |= L2CAP_CTRL_FINAL; - chan->conn_state &= ~L2CAP_CONN_SEND_FBIT; - } control |= (chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); @@ -1163,11 +1325,10 @@ static void l2cap_retransmit_one_frame(struct l2cap_chan *chan, u8 tx_seq) int l2cap_ertm_send(struct l2cap_chan *chan) { struct sk_buff *skb, *tx_skb; - struct sock *sk = chan->sk; u16 control, fcs; int nsent = 0; - if (sk->sk_state != BT_CONNECTED) + if (chan->state != BT_CONNECTED) return -ENOTCONN; while ((skb = chan->tx_send_head) && (!l2cap_tx_window_full(chan))) { @@ -1185,10 +1346,9 @@ int l2cap_ertm_send(struct l2cap_chan *chan) control = get_unaligned_le16(tx_skb->data + L2CAP_HDR_SIZE); control &= L2CAP_CTRL_SAR; - if (chan->conn_state & L2CAP_CONN_SEND_FBIT) { + if (test_and_clear_bit(CONN_SEND_FBIT, &chan->conn_state)) control |= L2CAP_CTRL_FINAL; - chan->conn_state &= ~L2CAP_CONN_SEND_FBIT; - } + control |= (chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT) | (chan->next_tx_seq << L2CAP_CTRL_TXSEQ_SHIFT); put_unaligned_le16(control, tx_skb->data + L2CAP_HDR_SIZE); @@ -1201,7 +1361,7 @@ int l2cap_ertm_send(struct l2cap_chan *chan) l2cap_do_send(chan, tx_skb); - __mod_retrans_timer(); + __set_retrans_timer(chan); bt_cb(skb)->tx_seq = chan->next_tx_seq; chan->next_tx_seq = (chan->next_tx_seq + 1) % 64; @@ -1240,9 +1400,9 @@ static void l2cap_send_ack(struct l2cap_chan *chan) control |= chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; - if (chan->conn_state & L2CAP_CONN_LOCAL_BUSY) { + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { control |= L2CAP_SUPER_RCV_NOT_READY; - chan->conn_state |= L2CAP_CONN_RNR_SENT; + set_bit(CONN_RNR_SENT, &chan->conn_state); l2cap_send_sframe(chan, control); return; } @@ -1450,28 +1610,83 @@ int l2cap_sar_segment_sdu(struct l2cap_chan *chan, struct msghdr *msg, size_t le return size; } -static void l2cap_chan_ready(struct sock *sk) +int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len) { - struct sock *parent = bt_sk(sk)->parent; - struct l2cap_chan *chan = l2cap_pi(sk)->chan; + struct sk_buff *skb; + u16 control; + int err; - BT_DBG("sk %p, parent %p", sk, parent); + /* Connectionless channel */ + if (chan->chan_type == L2CAP_CHAN_CONN_LESS) { + skb = l2cap_create_connless_pdu(chan, msg, len); + if (IS_ERR(skb)) + return PTR_ERR(skb); - chan->conf_state = 0; - l2cap_sock_clear_timer(sk); + l2cap_do_send(chan, skb); + return len; + } - if (!parent) { - /* Outgoing channel. - * Wake up socket sleeping on connect. - */ - sk->sk_state = BT_CONNECTED; - sk->sk_state_change(sk); - } else { - /* Incoming channel. - * Wake up socket sleeping on accept. - */ - parent->sk_data_ready(parent, 0); + switch (chan->mode) { + case L2CAP_MODE_BASIC: + /* Check outgoing MTU */ + if (len > chan->omtu) + return -EMSGSIZE; + + /* Create a basic PDU */ + skb = l2cap_create_basic_pdu(chan, msg, len); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + l2cap_do_send(chan, skb); + err = len; + break; + + case L2CAP_MODE_ERTM: + case L2CAP_MODE_STREAMING: + /* Entire SDU fits into one PDU */ + if (len <= chan->remote_mps) { + control = L2CAP_SDU_UNSEGMENTED; + skb = l2cap_create_iframe_pdu(chan, msg, len, control, + 0); + if (IS_ERR(skb)) + return PTR_ERR(skb); + + __skb_queue_tail(&chan->tx_q, skb); + + if (chan->tx_send_head == NULL) + chan->tx_send_head = skb; + + } else { + /* Segment SDU into multiples PDUs */ + err = l2cap_sar_segment_sdu(chan, msg, len); + if (err < 0) + return err; + } + + if (chan->mode == L2CAP_MODE_STREAMING) { + l2cap_streaming_send(chan); + err = len; + break; + } + + if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state) && + test_bit(CONN_WAIT_F, &chan->conn_state)) { + err = len; + break; + } + + err = l2cap_ertm_send(chan); + if (err >= 0) + err = len; + + break; + + default: + BT_DBG("bad state %1.1x", chan->mode); + err = -EBADFD; } + + return err; } /* Copy frame to all raw sockets on that connection */ @@ -1485,7 +1700,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) read_lock(&conn->chan_lock); list_for_each_entry(chan, &conn->chan_l, list) { struct sock *sk = chan->sk; - if (sk->sk_type != SOCK_RAW) + if (chan->chan_type != L2CAP_CHAN_RAW) continue; /* Don't send frame to the socket it came from */ @@ -1495,7 +1710,7 @@ static void l2cap_raw_recv(struct l2cap_conn *conn, struct sk_buff *skb) if (!nskb) continue; - if (sock_queue_rcv_skb(sk, nskb)) + if (chan->ops->recv(chan->data, nskb)) kfree_skb(nskb); } read_unlock(&conn->chan_lock); @@ -1654,11 +1869,9 @@ static inline void l2cap_ertm_init(struct l2cap_chan *chan) setup_timer(&chan->ack_timer, l2cap_ack_timeout, (unsigned long) chan); skb_queue_head_init(&chan->srej_q); - skb_queue_head_init(&chan->busy_q); INIT_LIST_HEAD(&chan->srej_l); - INIT_WORK(&chan->busy_work, l2cap_busy_work); sk->sk_backlog_rcv = l2cap_ertm_data_rcv; } @@ -1690,7 +1903,7 @@ static int l2cap_build_conf_req(struct l2cap_chan *chan, void *data) switch (chan->mode) { case L2CAP_MODE_STREAMING: case L2CAP_MODE_ERTM: - if (chan->conf_state & L2CAP_CONF_STATE2_DEVICE) + if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state)) break; /* fall through */ @@ -1737,7 +1950,7 @@ done: break; if (chan->fcs == L2CAP_FCS_NONE || - chan->conf_state & L2CAP_CONF_NO_FCS_RECV) { + test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) { chan->fcs = L2CAP_FCS_NONE; l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, chan->fcs); } @@ -1760,7 +1973,7 @@ done: break; if (chan->fcs == L2CAP_FCS_NONE || - chan->conf_state & L2CAP_CONF_NO_FCS_RECV) { + test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) { chan->fcs = L2CAP_FCS_NONE; l2cap_add_conf_opt(&ptr, L2CAP_CONF_FCS, 1, chan->fcs); } @@ -1812,7 +2025,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data) case L2CAP_CONF_FCS: if (val == L2CAP_FCS_NONE) - chan->conf_state |= L2CAP_CONF_NO_FCS_RECV; + set_bit(CONF_NO_FCS_RECV, &chan->conf_state); break; @@ -1832,7 +2045,7 @@ static int l2cap_parse_conf_req(struct l2cap_chan *chan, void *data) switch (chan->mode) { case L2CAP_MODE_STREAMING: case L2CAP_MODE_ERTM: - if (!(chan->conf_state & L2CAP_CONF_STATE2_DEVICE)) { + if (!test_bit(CONF_STATE2_DEVICE, &chan->conf_state)) { chan->mode = l2cap_select_mode(rfc.mode, chan->conn->feat_mask); break; @@ -1865,14 +2078,14 @@ done: result = L2CAP_CONF_UNACCEPT; else { chan->omtu = mtu; - chan->conf_state |= L2CAP_CONF_MTU_DONE; + set_bit(CONF_MTU_DONE, &chan->conf_state); } l2cap_add_conf_opt(&ptr, L2CAP_CONF_MTU, 2, chan->omtu); switch (rfc.mode) { case L2CAP_MODE_BASIC: chan->fcs = L2CAP_FCS_NONE; - chan->conf_state |= L2CAP_CONF_MODE_DONE; + set_bit(CONF_MODE_DONE, &chan->conf_state); break; case L2CAP_MODE_ERTM: @@ -1889,7 +2102,7 @@ done: rfc.monitor_timeout = le16_to_cpu(L2CAP_DEFAULT_MONITOR_TO); - chan->conf_state |= L2CAP_CONF_MODE_DONE; + set_bit(CONF_MODE_DONE, &chan->conf_state); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc); @@ -1902,7 +2115,7 @@ done: chan->remote_mps = le16_to_cpu(rfc.max_pdu_size); - chan->conf_state |= L2CAP_CONF_MODE_DONE; + set_bit(CONF_MODE_DONE, &chan->conf_state); l2cap_add_conf_opt(&ptr, L2CAP_CONF_RFC, sizeof(rfc), (unsigned long) &rfc); @@ -1917,7 +2130,7 @@ done: } if (result == L2CAP_CONF_SUCCESS) - chan->conf_state |= L2CAP_CONF_OUTPUT_DONE; + set_bit(CONF_OUTPUT_DONE, &chan->conf_state); } rsp->scid = cpu_to_le16(chan->dcid); rsp->result = cpu_to_le16(result); @@ -1959,7 +2172,7 @@ static int l2cap_parse_conf_rsp(struct l2cap_chan *chan, void *rsp, int len, voi if (olen == sizeof(rfc)) memcpy(&rfc, (void *)val, olen); - if ((chan->conf_state & L2CAP_CONF_STATE2_DEVICE) && + if (test_bit(CONF_STATE2_DEVICE, &chan->conf_state) && rfc.mode != chan->mode) return -ECONNREFUSED; @@ -2021,10 +2234,9 @@ void __l2cap_connect_rsp_defer(struct l2cap_chan *chan) l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); - if (chan->conf_state & L2CAP_CONF_REQ_SENT) + if (test_and_set_bit(CONF_REQ_SENT, &chan->conf_state)) return; - chan->conf_state |= L2CAP_CONF_REQ_SENT; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; @@ -2066,9 +2278,9 @@ done: static inline int l2cap_command_rej(struct l2cap_conn *conn, struct l2cap_cmd_hdr *cmd, u8 *data) { - struct l2cap_cmd_rej *rej = (struct l2cap_cmd_rej *) data; + struct l2cap_cmd_rej_unk *rej = (struct l2cap_cmd_rej_unk *) data; - if (rej->reason != 0x0000) + if (rej->reason != L2CAP_REJ_NOT_UNDERSTOOD) return 0; if ((conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_SENT) && @@ -2124,17 +2336,11 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd goto response; } - sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, GFP_ATOMIC); - if (!sk) - goto response; - - chan = l2cap_chan_create(sk); - if (!chan) { - l2cap_sock_kill(sk); + chan = pchan->ops->new_connection(pchan->data); + if (!chan) goto response; - } - l2cap_pi(sk)->chan = chan; + sk = chan->sk; write_lock_bh(&conn->chan_lock); @@ -2142,13 +2348,12 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd if (__l2cap_get_chan_by_dcid(conn, scid)) { write_unlock_bh(&conn->chan_lock); sock_set_flag(sk, SOCK_ZAPPED); - l2cap_sock_kill(sk); + chan->ops->close(chan->data); goto response; } hci_conn_hold(conn->hcon); - l2cap_sock_init(sk, parent); bacpy(&bt_sk(sk)->src, conn->src); bacpy(&bt_sk(sk)->dst, conn->dst); chan->psm = psm; @@ -2160,29 +2365,29 @@ static inline int l2cap_connect_req(struct l2cap_conn *conn, struct l2cap_cmd_hd dcid = chan->scid; - l2cap_sock_set_timer(sk, sk->sk_sndtimeo); + __set_chan_timer(chan, sk->sk_sndtimeo); chan->ident = cmd->ident; if (conn->info_state & L2CAP_INFO_FEAT_MASK_REQ_DONE) { if (l2cap_check_security(chan)) { if (bt_sk(sk)->defer_setup) { - sk->sk_state = BT_CONNECT2; + l2cap_state_change(chan, BT_CONNECT2); result = L2CAP_CR_PEND; status = L2CAP_CS_AUTHOR_PEND; parent->sk_data_ready(parent, 0); } else { - sk->sk_state = BT_CONFIG; + l2cap_state_change(chan, BT_CONFIG); result = L2CAP_CR_SUCCESS; status = L2CAP_CS_NO_INFO; } } else { - sk->sk_state = BT_CONNECT2; + l2cap_state_change(chan, BT_CONNECT2); result = L2CAP_CR_PEND; status = L2CAP_CS_AUTHEN_PEND; } } else { - sk->sk_state = BT_CONNECT2; + l2cap_state_change(chan, BT_CONNECT2); result = L2CAP_CR_PEND; status = L2CAP_CS_NO_INFO; } @@ -2213,10 +2418,10 @@ sendresp: L2CAP_INFO_REQ, sizeof(info), &info); } - if (chan && !(chan->conf_state & L2CAP_CONF_REQ_SENT) && + if (chan && !test_bit(CONF_REQ_SENT, &chan->conf_state) && result == L2CAP_CR_SUCCESS) { u8 buf[128]; - chan->conf_state |= L2CAP_CONF_REQ_SENT; + set_bit(CONF_REQ_SENT, &chan->conf_state); l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; @@ -2254,31 +2459,29 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd switch (result) { case L2CAP_CR_SUCCESS: - sk->sk_state = BT_CONFIG; + l2cap_state_change(chan, BT_CONFIG); chan->ident = 0; chan->dcid = dcid; - chan->conf_state &= ~L2CAP_CONF_CONNECT_PEND; + clear_bit(CONF_CONNECT_PEND, &chan->conf_state); - if (chan->conf_state & L2CAP_CONF_REQ_SENT) + if (test_and_set_bit(CONF_REQ_SENT, &chan->conf_state)) break; - chan->conf_state |= L2CAP_CONF_REQ_SENT; - l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(chan, req), req); chan->num_conf_req++; break; case L2CAP_CR_PEND: - chan->conf_state |= L2CAP_CONF_CONNECT_PEND; + set_bit(CONF_CONNECT_PEND, &chan->conf_state); break; default: /* don't delete l2cap channel if sk is owned by user */ if (sock_owned_by_user(sk)) { - sk->sk_state = BT_DISCONN; - l2cap_sock_clear_timer(sk); - l2cap_sock_set_timer(sk, HZ / 5); + l2cap_state_change(chan, BT_DISCONN); + __clear_chan_timer(chan); + __set_chan_timer(chan, HZ / 5); break; } @@ -2292,14 +2495,12 @@ static inline int l2cap_connect_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hd static inline void set_default_fcs(struct l2cap_chan *chan) { - struct l2cap_pinfo *pi = l2cap_pi(chan->sk); - /* FCS is enabled only in ERTM or streaming mode, if one or both * sides request it. */ if (chan->mode != L2CAP_MODE_ERTM && chan->mode != L2CAP_MODE_STREAMING) chan->fcs = L2CAP_FCS_NONE; - else if (!(pi->chan->conf_state & L2CAP_CONF_NO_FCS_RECV)) + else if (!test_bit(CONF_NO_FCS_RECV, &chan->conf_state)) chan->fcs = L2CAP_FCS_CRC16; } @@ -2323,10 +2524,13 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr sk = chan->sk; - if (sk->sk_state != BT_CONFIG) { - struct l2cap_cmd_rej rej; + if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) { + struct l2cap_cmd_rej_cid rej; + + rej.reason = cpu_to_le16(L2CAP_REJ_INVALID_CID); + rej.scid = cpu_to_le16(chan->scid); + rej.dcid = cpu_to_le16(chan->dcid); - rej.reason = cpu_to_le16(0x0002); l2cap_send_cmd(conn, cmd->ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); goto unlock; @@ -2334,7 +2538,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr /* Reject if config buffer is too small. */ len = cmd_len - sizeof(*req); - if (chan->conf_len + len > sizeof(chan->conf_req)) { + if (len < 0 || chan->conf_len + len > sizeof(chan->conf_req)) { l2cap_send_cmd(conn, cmd->ident, L2CAP_CONF_RSP, l2cap_build_conf_rsp(chan, rsp, L2CAP_CONF_REJECT, flags), rsp); @@ -2366,13 +2570,13 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr /* Reset config buffer. */ chan->conf_len = 0; - if (!(chan->conf_state & L2CAP_CONF_OUTPUT_DONE)) + if (!test_bit(CONF_OUTPUT_DONE, &chan->conf_state)) goto unlock; - if (chan->conf_state & L2CAP_CONF_INPUT_DONE) { + if (test_bit(CONF_INPUT_DONE, &chan->conf_state)) { set_default_fcs(chan); - sk->sk_state = BT_CONNECTED; + l2cap_state_change(chan, BT_CONNECTED); chan->next_tx_seq = 0; chan->expected_tx_seq = 0; @@ -2384,9 +2588,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr goto unlock; } - if (!(chan->conf_state & L2CAP_CONF_REQ_SENT)) { + if (!test_and_set_bit(CONF_REQ_SENT, &chan->conf_state)) { u8 buf[64]; - chan->conf_state |= L2CAP_CONF_REQ_SENT; l2cap_send_cmd(conn, l2cap_get_ident(conn), L2CAP_CONF_REQ, l2cap_build_conf_req(chan, buf), buf); chan->num_conf_req++; @@ -2451,7 +2654,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr default: sk->sk_err = ECONNRESET; - l2cap_sock_set_timer(sk, HZ * 5); + __set_chan_timer(chan, HZ * 5); l2cap_send_disconn_req(conn, chan, ECONNRESET); goto done; } @@ -2459,12 +2662,12 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, struct l2cap_cmd_hdr if (flags & 0x01) goto done; - chan->conf_state |= L2CAP_CONF_INPUT_DONE; + set_bit(CONF_INPUT_DONE, &chan->conf_state); - if (chan->conf_state & L2CAP_CONF_OUTPUT_DONE) { + if (test_bit(CONF_OUTPUT_DONE, &chan->conf_state)) { set_default_fcs(chan); - sk->sk_state = BT_CONNECTED; + l2cap_state_change(chan, BT_CONNECTED); chan->next_tx_seq = 0; chan->expected_tx_seq = 0; skb_queue_head_init(&chan->tx_q); @@ -2506,9 +2709,9 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd /* don't delete l2cap channel if sk is owned by user */ if (sock_owned_by_user(sk)) { - sk->sk_state = BT_DISCONN; - l2cap_sock_clear_timer(sk); - l2cap_sock_set_timer(sk, HZ / 5); + l2cap_state_change(chan, BT_DISCONN); + __clear_chan_timer(chan); + __set_chan_timer(chan, HZ / 5); bh_unlock_sock(sk); return 0; } @@ -2516,7 +2719,7 @@ static inline int l2cap_disconnect_req(struct l2cap_conn *conn, struct l2cap_cmd l2cap_chan_del(chan, ECONNRESET); bh_unlock_sock(sk); - l2cap_sock_kill(sk); + chan->ops->close(chan->data); return 0; } @@ -2540,9 +2743,9 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd /* don't delete l2cap channel if sk is owned by user */ if (sock_owned_by_user(sk)) { - sk->sk_state = BT_DISCONN; - l2cap_sock_clear_timer(sk); - l2cap_sock_set_timer(sk, HZ / 5); + l2cap_state_change(chan,BT_DISCONN); + __clear_chan_timer(chan); + __set_chan_timer(chan, HZ / 5); bh_unlock_sock(sk); return 0; } @@ -2550,7 +2753,7 @@ static inline int l2cap_disconnect_rsp(struct l2cap_conn *conn, struct l2cap_cmd l2cap_chan_del(chan, 0); bh_unlock_sock(sk); - l2cap_sock_kill(sk); + chan->ops->close(chan->data); return 0; } @@ -2818,12 +3021,12 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, err = l2cap_bredr_sig_cmd(conn, &cmd, cmd_len, data); if (err) { - struct l2cap_cmd_rej rej; + struct l2cap_cmd_rej_unk rej; BT_ERR("Wrong link type (%d)", err); /* FIXME: Map err to a valid reason */ - rej.reason = cpu_to_le16(0); + rej.reason = cpu_to_le16(L2CAP_REJ_NOT_UNDERSTOOD); l2cap_send_cmd(conn, cmd.ident, L2CAP_COMMAND_REJ, sizeof(rej), &rej); } @@ -2858,18 +3061,18 @@ static inline void l2cap_send_i_or_rr_or_rnr(struct l2cap_chan *chan) control |= chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; - if (chan->conn_state & L2CAP_CONN_LOCAL_BUSY) { + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { control |= L2CAP_SUPER_RCV_NOT_READY; l2cap_send_sframe(chan, control); - chan->conn_state |= L2CAP_CONN_RNR_SENT; + set_bit(CONN_RNR_SENT, &chan->conn_state); } - if (chan->conn_state & L2CAP_CONN_REMOTE_BUSY) + if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state)) l2cap_retransmit_frames(chan); l2cap_ertm_send(chan); - if (!(chan->conn_state & L2CAP_CONN_LOCAL_BUSY) && + if (!test_bit(CONN_LOCAL_BUSY, &chan->conn_state) && chan->frames_sent == 0) { control |= L2CAP_SUPER_RCV_READY; l2cap_send_sframe(chan, control); @@ -2925,17 +3128,13 @@ static int l2cap_ertm_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *sk switch (control & L2CAP_CTRL_SAR) { case L2CAP_SDU_UNSEGMENTED: - if (chan->conn_state & L2CAP_CONN_SAR_SDU) + if (test_bit(CONN_SAR_SDU, &chan->conn_state)) goto drop; - err = sock_queue_rcv_skb(chan->sk, skb); - if (!err) - return err; - - break; + return chan->ops->recv(chan->data, skb); case L2CAP_SDU_START: - if (chan->conn_state & L2CAP_CONN_SAR_SDU) + if (test_bit(CONN_SAR_SDU, &chan->conn_state)) goto drop; chan->sdu_len = get_unaligned_le16(skb->data); @@ -2954,12 +3153,12 @@ static int l2cap_ertm_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *sk memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - chan->conn_state |= L2CAP_CONN_SAR_SDU; + set_bit(CONN_SAR_SDU, &chan->conn_state); chan->partial_sdu_len = skb->len; break; case L2CAP_SDU_CONTINUE: - if (!(chan->conn_state & L2CAP_CONN_SAR_SDU)) + if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) goto disconnect; if (!chan->sdu) @@ -2974,39 +3173,34 @@ static int l2cap_ertm_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *sk break; case L2CAP_SDU_END: - if (!(chan->conn_state & L2CAP_CONN_SAR_SDU)) + if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) goto disconnect; if (!chan->sdu) goto disconnect; - if (!(chan->conn_state & L2CAP_CONN_SAR_RETRY)) { - chan->partial_sdu_len += skb->len; + chan->partial_sdu_len += skb->len; - if (chan->partial_sdu_len > chan->imtu) - goto drop; + if (chan->partial_sdu_len > chan->imtu) + goto drop; - if (chan->partial_sdu_len != chan->sdu_len) - goto drop; + if (chan->partial_sdu_len != chan->sdu_len) + goto drop; - memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - } + memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); _skb = skb_clone(chan->sdu, GFP_ATOMIC); if (!_skb) { - chan->conn_state |= L2CAP_CONN_SAR_RETRY; return -ENOMEM; } - err = sock_queue_rcv_skb(chan->sk, _skb); + err = chan->ops->recv(chan->data, _skb); if (err < 0) { kfree_skb(_skb); - chan->conn_state |= L2CAP_CONN_SAR_RETRY; return err; } - chan->conn_state &= ~L2CAP_CONN_SAR_RETRY; - chan->conn_state &= ~L2CAP_CONN_SAR_SDU; + clear_bit(CONN_SAR_SDU, &chan->conn_state); kfree_skb(chan->sdu); break; @@ -3025,128 +3219,55 @@ disconnect: return 0; } -static int l2cap_try_push_rx_skb(struct l2cap_chan *chan) +static void l2cap_ertm_enter_local_busy(struct l2cap_chan *chan) { - struct sk_buff *skb; u16 control; - int err; - - while ((skb = skb_dequeue(&chan->busy_q))) { - control = bt_cb(skb)->sar << L2CAP_CTRL_SAR_SHIFT; - err = l2cap_ertm_reassembly_sdu(chan, skb, control); - if (err < 0) { - skb_queue_head(&chan->busy_q, skb); - return -EBUSY; - } - chan->buffer_seq = (chan->buffer_seq + 1) % 64; - } + BT_DBG("chan %p, Enter local busy", chan); - if (!(chan->conn_state & L2CAP_CONN_RNR_SENT)) - goto done; + set_bit(CONN_LOCAL_BUSY, &chan->conn_state); control = chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; - control |= L2CAP_SUPER_RCV_READY | L2CAP_CTRL_POLL; + control |= L2CAP_SUPER_RCV_NOT_READY; l2cap_send_sframe(chan, control); - chan->retry_count = 1; - del_timer(&chan->retrans_timer); - __mod_monitor_timer(); + set_bit(CONN_RNR_SENT, &chan->conn_state); - chan->conn_state |= L2CAP_CONN_WAIT_F; - -done: - chan->conn_state &= ~L2CAP_CONN_LOCAL_BUSY; - chan->conn_state &= ~L2CAP_CONN_RNR_SENT; - - BT_DBG("chan %p, Exit local busy", chan); - - return 0; + __clear_ack_timer(chan); } -static void l2cap_busy_work(struct work_struct *work) +static void l2cap_ertm_exit_local_busy(struct l2cap_chan *chan) { - DECLARE_WAITQUEUE(wait, current); - struct l2cap_chan *chan = - container_of(work, struct l2cap_chan, busy_work); - struct sock *sk = chan->sk; - int n_tries = 0, timeo = HZ/5, err; - struct sk_buff *skb; - - lock_sock(sk); - - add_wait_queue(sk_sleep(sk), &wait); - while ((skb = skb_peek(&chan->busy_q))) { - set_current_state(TASK_INTERRUPTIBLE); - - if (n_tries++ > L2CAP_LOCAL_BUSY_TRIES) { - err = -EBUSY; - l2cap_send_disconn_req(chan->conn, chan, EBUSY); - break; - } - - if (!timeo) - timeo = HZ/5; + u16 control; - if (signal_pending(current)) { - err = sock_intr_errno(timeo); - break; - } + if (!test_bit(CONN_RNR_SENT, &chan->conn_state)) + goto done; - release_sock(sk); - timeo = schedule_timeout(timeo); - lock_sock(sk); + control = chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; + control |= L2CAP_SUPER_RCV_READY | L2CAP_CTRL_POLL; + l2cap_send_sframe(chan, control); + chan->retry_count = 1; - err = sock_error(sk); - if (err) - break; + __clear_retrans_timer(chan); + __set_monitor_timer(chan); - if (l2cap_try_push_rx_skb(chan) == 0) - break; - } + set_bit(CONN_WAIT_F, &chan->conn_state); - set_current_state(TASK_RUNNING); - remove_wait_queue(sk_sleep(sk), &wait); +done: + clear_bit(CONN_LOCAL_BUSY, &chan->conn_state); + clear_bit(CONN_RNR_SENT, &chan->conn_state); - release_sock(sk); + BT_DBG("chan %p, Exit local busy", chan); } -static int l2cap_push_rx_skb(struct l2cap_chan *chan, struct sk_buff *skb, u16 control) +void l2cap_chan_busy(struct l2cap_chan *chan, int busy) { - int sctrl, err; - - if (chan->conn_state & L2CAP_CONN_LOCAL_BUSY) { - bt_cb(skb)->sar = control >> L2CAP_CTRL_SAR_SHIFT; - __skb_queue_tail(&chan->busy_q, skb); - return l2cap_try_push_rx_skb(chan); - - - } - - err = l2cap_ertm_reassembly_sdu(chan, skb, control); - if (err >= 0) { - chan->buffer_seq = (chan->buffer_seq + 1) % 64; - return err; + if (chan->mode == L2CAP_MODE_ERTM) { + if (busy) + l2cap_ertm_enter_local_busy(chan); + else + l2cap_ertm_exit_local_busy(chan); } - - /* Busy Condition */ - BT_DBG("chan %p, Enter local busy", chan); - - chan->conn_state |= L2CAP_CONN_LOCAL_BUSY; - bt_cb(skb)->sar = control >> L2CAP_CTRL_SAR_SHIFT; - __skb_queue_tail(&chan->busy_q, skb); - - sctrl = chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; - sctrl |= L2CAP_SUPER_RCV_NOT_READY; - l2cap_send_sframe(chan, sctrl); - - chan->conn_state |= L2CAP_CONN_RNR_SENT; - - del_timer(&chan->ack_timer); - - queue_work(_busy_wq, &chan->busy_work); - - return err; } static int l2cap_streaming_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *skb, u16 control) @@ -3161,19 +3282,19 @@ static int l2cap_streaming_reassembly_sdu(struct l2cap_chan *chan, struct sk_buf switch (control & L2CAP_CTRL_SAR) { case L2CAP_SDU_UNSEGMENTED: - if (chan->conn_state & L2CAP_CONN_SAR_SDU) { + if (test_bit(CONN_SAR_SDU, &chan->conn_state)) { kfree_skb(chan->sdu); break; } - err = sock_queue_rcv_skb(chan->sk, skb); + err = chan->ops->recv(chan->data, skb); if (!err) return 0; break; case L2CAP_SDU_START: - if (chan->conn_state & L2CAP_CONN_SAR_SDU) { + if (test_bit(CONN_SAR_SDU, &chan->conn_state)) { kfree_skb(chan->sdu); break; } @@ -3194,13 +3315,13 @@ static int l2cap_streaming_reassembly_sdu(struct l2cap_chan *chan, struct sk_buf memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - chan->conn_state |= L2CAP_CONN_SAR_SDU; + set_bit(CONN_SAR_SDU, &chan->conn_state); chan->partial_sdu_len = skb->len; err = 0; break; case L2CAP_SDU_CONTINUE: - if (!(chan->conn_state & L2CAP_CONN_SAR_SDU)) + if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) break; memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); @@ -3214,12 +3335,12 @@ static int l2cap_streaming_reassembly_sdu(struct l2cap_chan *chan, struct sk_buf break; case L2CAP_SDU_END: - if (!(chan->conn_state & L2CAP_CONN_SAR_SDU)) + if (!test_bit(CONN_SAR_SDU, &chan->conn_state)) break; memcpy(skb_put(chan->sdu, skb->len), skb->data, skb->len); - chan->conn_state &= ~L2CAP_CONN_SAR_SDU; + clear_bit(CONN_SAR_SDU, &chan->conn_state); chan->partial_sdu_len += skb->len; if (chan->partial_sdu_len > chan->imtu) @@ -3227,7 +3348,7 @@ static int l2cap_streaming_reassembly_sdu(struct l2cap_chan *chan, struct sk_buf if (chan->partial_sdu_len == chan->sdu_len) { _skb = skb_clone(chan->sdu, GFP_ATOMIC); - err = sock_queue_rcv_skb(chan->sk, _skb); + err = chan->ops->recv(chan->data, _skb); if (err < 0) kfree_skb(_skb); } @@ -3247,13 +3368,22 @@ static void l2cap_check_srej_gap(struct l2cap_chan *chan, u8 tx_seq) struct sk_buff *skb; u16 control; - while ((skb = skb_peek(&chan->srej_q))) { + while ((skb = skb_peek(&chan->srej_q)) && + !test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { + int err; + if (bt_cb(skb)->tx_seq != tx_seq) break; skb = skb_dequeue(&chan->srej_q); control = bt_cb(skb)->sar << L2CAP_CTRL_SAR_SHIFT; - l2cap_ertm_reassembly_sdu(chan, skb, control); + err = l2cap_ertm_reassembly_sdu(chan, skb, control); + + if (err < 0) { + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + break; + } + chan->buffer_seq_srej = (chan->buffer_seq_srej + 1) % 64; tx_seq = (tx_seq + 1) % 64; @@ -3310,19 +3440,16 @@ static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u16 rx_cont tx_seq, rx_control); if (L2CAP_CTRL_FINAL & rx_control && - chan->conn_state & L2CAP_CONN_WAIT_F) { - del_timer(&chan->monitor_timer); + test_bit(CONN_WAIT_F, &chan->conn_state)) { + __clear_monitor_timer(chan); if (chan->unacked_frames > 0) - __mod_retrans_timer(); - chan->conn_state &= ~L2CAP_CONN_WAIT_F; + __set_retrans_timer(chan); + clear_bit(CONN_WAIT_F, &chan->conn_state); } chan->expected_ack_seq = req_seq; l2cap_drop_acked_frames(chan); - if (tx_seq == chan->expected_tx_seq) - goto expected; - tx_seq_offset = (tx_seq - chan->buffer_seq) % 64; if (tx_seq_offset < 0) tx_seq_offset += 64; @@ -3333,10 +3460,13 @@ static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u16 rx_cont goto drop; } - if (chan->conn_state == L2CAP_CONN_LOCAL_BUSY) + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) goto drop; - if (chan->conn_state & L2CAP_CONN_SREJ_SENT) { + if (tx_seq == chan->expected_tx_seq) + goto expected; + + if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { struct srej_list *first; first = list_first_entry(&chan->srej_l, @@ -3350,7 +3480,7 @@ static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u16 rx_cont if (list_empty(&chan->srej_l)) { chan->buffer_seq = chan->buffer_seq_srej; - chan->conn_state &= ~L2CAP_CONN_SREJ_SENT; + clear_bit(CONN_SREJ_SENT, &chan->conn_state); l2cap_send_ack(chan); BT_DBG("chan %p, Exit SREJ_SENT", chan); } @@ -3379,7 +3509,7 @@ static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u16 rx_cont if (tx_seq_offset < expected_tx_seq_offset) goto drop; - chan->conn_state |= L2CAP_CONN_SREJ_SENT; + set_bit(CONN_SREJ_SENT, &chan->conn_state); BT_DBG("chan %p, Enter SREJ", chan); @@ -3387,39 +3517,39 @@ static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u16 rx_cont chan->buffer_seq_srej = chan->buffer_seq; __skb_queue_head_init(&chan->srej_q); - __skb_queue_head_init(&chan->busy_q); l2cap_add_to_srej_queue(chan, skb, tx_seq, sar); - chan->conn_state |= L2CAP_CONN_SEND_PBIT; + set_bit(CONN_SEND_PBIT, &chan->conn_state); l2cap_send_srejframe(chan, tx_seq); - del_timer(&chan->ack_timer); + __clear_ack_timer(chan); } return 0; expected: chan->expected_tx_seq = (chan->expected_tx_seq + 1) % 64; - if (chan->conn_state & L2CAP_CONN_SREJ_SENT) { + if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { bt_cb(skb)->tx_seq = tx_seq; bt_cb(skb)->sar = sar; __skb_queue_tail(&chan->srej_q, skb); return 0; } - err = l2cap_push_rx_skb(chan, skb, rx_control); - if (err < 0) - return 0; + err = l2cap_ertm_reassembly_sdu(chan, skb, rx_control); + chan->buffer_seq = (chan->buffer_seq + 1) % 64; + if (err < 0) { + l2cap_send_disconn_req(chan->conn, chan, ECONNRESET); + return err; + } if (rx_control & L2CAP_CTRL_FINAL) { - if (chan->conn_state & L2CAP_CONN_REJ_ACT) - chan->conn_state &= ~L2CAP_CONN_REJ_ACT; - else + if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) l2cap_retransmit_frames(chan); } - __mod_ack_timer(); + __set_ack_timer(chan); chan->num_acked = (chan->num_acked + 1) % num_to_ack; if (chan->num_acked == num_to_ack - 1) @@ -3441,33 +3571,31 @@ static inline void l2cap_data_channel_rrframe(struct l2cap_chan *chan, u16 rx_co l2cap_drop_acked_frames(chan); if (rx_control & L2CAP_CTRL_POLL) { - chan->conn_state |= L2CAP_CONN_SEND_FBIT; - if (chan->conn_state & L2CAP_CONN_SREJ_SENT) { - if ((chan->conn_state & L2CAP_CONN_REMOTE_BUSY) && + set_bit(CONN_SEND_FBIT, &chan->conn_state); + if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { + if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state) && (chan->unacked_frames > 0)) - __mod_retrans_timer(); + __set_retrans_timer(chan); - chan->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); l2cap_send_srejtail(chan); } else { l2cap_send_i_or_rr_or_rnr(chan); } } else if (rx_control & L2CAP_CTRL_FINAL) { - chan->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); - if (chan->conn_state & L2CAP_CONN_REJ_ACT) - chan->conn_state &= ~L2CAP_CONN_REJ_ACT; - else + if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) l2cap_retransmit_frames(chan); } else { - if ((chan->conn_state & L2CAP_CONN_REMOTE_BUSY) && + if (test_bit(CONN_REMOTE_BUSY, &chan->conn_state) && (chan->unacked_frames > 0)) - __mod_retrans_timer(); + __set_retrans_timer(chan); - chan->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; - if (chan->conn_state & L2CAP_CONN_SREJ_SENT) + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); + if (test_bit(CONN_SREJ_SENT, &chan->conn_state)) l2cap_send_ack(chan); else l2cap_ertm_send(chan); @@ -3480,21 +3608,19 @@ static inline void l2cap_data_channel_rejframe(struct l2cap_chan *chan, u16 rx_c BT_DBG("chan %p, req_seq %d ctrl 0x%4.4x", chan, tx_seq, rx_control); - chan->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); chan->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(chan); if (rx_control & L2CAP_CTRL_FINAL) { - if (chan->conn_state & L2CAP_CONN_REJ_ACT) - chan->conn_state &= ~L2CAP_CONN_REJ_ACT; - else + if (!test_and_clear_bit(CONN_REJ_ACT, &chan->conn_state)) l2cap_retransmit_frames(chan); } else { l2cap_retransmit_frames(chan); - if (chan->conn_state & L2CAP_CONN_WAIT_F) - chan->conn_state |= L2CAP_CONN_REJ_ACT; + if (test_bit(CONN_WAIT_F, &chan->conn_state)) + set_bit(CONN_REJ_ACT, &chan->conn_state); } } static inline void l2cap_data_channel_srejframe(struct l2cap_chan *chan, u16 rx_control) @@ -3503,32 +3629,32 @@ static inline void l2cap_data_channel_srejframe(struct l2cap_chan *chan, u16 rx_ BT_DBG("chan %p, req_seq %d ctrl 0x%4.4x", chan, tx_seq, rx_control); - chan->conn_state &= ~L2CAP_CONN_REMOTE_BUSY; + clear_bit(CONN_REMOTE_BUSY, &chan->conn_state); if (rx_control & L2CAP_CTRL_POLL) { chan->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(chan); - chan->conn_state |= L2CAP_CONN_SEND_FBIT; + set_bit(CONN_SEND_FBIT, &chan->conn_state); l2cap_retransmit_one_frame(chan, tx_seq); l2cap_ertm_send(chan); - if (chan->conn_state & L2CAP_CONN_WAIT_F) { + if (test_bit(CONN_WAIT_F, &chan->conn_state)) { chan->srej_save_reqseq = tx_seq; - chan->conn_state |= L2CAP_CONN_SREJ_ACT; + set_bit(CONN_SREJ_ACT, &chan->conn_state); } } else if (rx_control & L2CAP_CTRL_FINAL) { - if ((chan->conn_state & L2CAP_CONN_SREJ_ACT) && + if (test_bit(CONN_SREJ_ACT, &chan->conn_state) && chan->srej_save_reqseq == tx_seq) - chan->conn_state &= ~L2CAP_CONN_SREJ_ACT; + clear_bit(CONN_SREJ_ACT, &chan->conn_state); else l2cap_retransmit_one_frame(chan, tx_seq); } else { l2cap_retransmit_one_frame(chan, tx_seq); - if (chan->conn_state & L2CAP_CONN_WAIT_F) { + if (test_bit(CONN_WAIT_F, &chan->conn_state)) { chan->srej_save_reqseq = tx_seq; - chan->conn_state |= L2CAP_CONN_SREJ_ACT; + set_bit(CONN_SREJ_ACT, &chan->conn_state); } } } @@ -3539,15 +3665,15 @@ static inline void l2cap_data_channel_rnrframe(struct l2cap_chan *chan, u16 rx_c BT_DBG("chan %p, req_seq %d ctrl 0x%4.4x", chan, tx_seq, rx_control); - chan->conn_state |= L2CAP_CONN_REMOTE_BUSY; + set_bit(CONN_REMOTE_BUSY, &chan->conn_state); chan->expected_ack_seq = tx_seq; l2cap_drop_acked_frames(chan); if (rx_control & L2CAP_CTRL_POLL) - chan->conn_state |= L2CAP_CONN_SEND_FBIT; + set_bit(CONN_SEND_FBIT, &chan->conn_state); - if (!(chan->conn_state & L2CAP_CONN_SREJ_SENT)) { - del_timer(&chan->retrans_timer); + if (!test_bit(CONN_SREJ_SENT, &chan->conn_state)) { + __clear_retrans_timer(chan); if (rx_control & L2CAP_CTRL_POLL) l2cap_send_rr_or_rnr(chan, L2CAP_CTRL_FINAL); return; @@ -3564,11 +3690,11 @@ static inline int l2cap_data_channel_sframe(struct l2cap_chan *chan, u16 rx_cont BT_DBG("chan %p rx_control 0x%4.4x len %d", chan, rx_control, skb->len); if (L2CAP_CTRL_FINAL & rx_control && - chan->conn_state & L2CAP_CONN_WAIT_F) { - del_timer(&chan->monitor_timer); + test_bit(CONN_WAIT_F, &chan->conn_state)) { + __clear_monitor_timer(chan); if (chan->unacked_frames > 0) - __mod_retrans_timer(); - chan->conn_state &= ~L2CAP_CONN_WAIT_F; + __set_retrans_timer(chan); + clear_bit(CONN_WAIT_F, &chan->conn_state); } switch (rx_control & L2CAP_CTRL_SUPERVISE) { @@ -3667,7 +3793,6 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk { struct l2cap_chan *chan; struct sock *sk = NULL; - struct l2cap_pinfo *pi; u16 control; u8 tx_seq; int len; @@ -3679,11 +3804,10 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk } sk = chan->sk; - pi = l2cap_pi(sk); BT_DBG("chan %p, len %d", chan, skb->len); - if (sk->sk_state != BT_CONNECTED) + if (chan->state != BT_CONNECTED) goto drop; switch (chan->mode) { @@ -3696,7 +3820,7 @@ static inline int l2cap_data_channel(struct l2cap_conn *conn, u16 cid, struct sk if (chan->imtu < skb->len) goto drop; - if (!sock_queue_rcv_skb(sk, skb)) + if (!chan->ops->recv(chan->data, skb)) goto done; break; @@ -3768,13 +3892,13 @@ static inline int l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, str BT_DBG("sk %p, len %d", sk, skb->len); - if (sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECTED) + if (chan->state != BT_BOUND && chan->state != BT_CONNECTED) goto drop; - if (l2cap_pi(sk)->chan->imtu < skb->len) + if (chan->imtu < skb->len) goto drop; - if (!sock_queue_rcv_skb(sk, skb)) + if (!chan->ops->recv(chan->data, skb)) goto done; drop: @@ -3801,13 +3925,13 @@ static inline int l2cap_att_channel(struct l2cap_conn *conn, __le16 cid, struct BT_DBG("sk %p, len %d", sk, skb->len); - if (sk->sk_state != BT_BOUND && sk->sk_state != BT_CONNECTED) + if (chan->state != BT_BOUND && chan->state != BT_CONNECTED) goto drop; - if (l2cap_pi(sk)->chan->imtu < skb->len) + if (chan->imtu < skb->len) goto drop; - if (!sock_queue_rcv_skb(sk, skb)) + if (!chan->ops->recv(chan->data, skb)) goto done; drop: @@ -3852,6 +3976,11 @@ static void l2cap_recv_frame(struct l2cap_conn *conn, struct sk_buff *skb) l2cap_att_channel(conn, cid, skb); break; + case L2CAP_CID_SMP: + if (smp_sig_channel(conn, skb)) + l2cap_conn_del(conn->hcon, EACCES); + break; + default: l2cap_data_channel(conn, cid, skb); break; @@ -3875,7 +4004,7 @@ static int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 type) list_for_each_entry(c, &chan_list, global_l) { struct sock *sk = c->sk; - if (sk->sk_state != BT_LISTEN) + if (c->state != BT_LISTEN) continue; if (!bacmp(&bt_sk(sk)->src, &hdev->bdaddr)) { @@ -3908,7 +4037,7 @@ static int l2cap_connect_cfm(struct hci_conn *hcon, u8 status) if (conn) l2cap_conn_ready(conn); } else - l2cap_conn_del(hcon, bt_err(status)); + l2cap_conn_del(hcon, bt_to_errno(status)); return 0; } @@ -3919,7 +4048,7 @@ static int l2cap_disconn_ind(struct hci_conn *hcon) BT_DBG("hcon %p", hcon); - if (hcon->type != ACL_LINK || !conn) + if ((hcon->type != ACL_LINK && hcon->type != LE_LINK) || !conn) return 0x13; return conn->disc_reason; @@ -3932,27 +4061,25 @@ static int l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) if (!(hcon->type == ACL_LINK || hcon->type == LE_LINK)) return -EINVAL; - l2cap_conn_del(hcon, bt_err(reason)); + l2cap_conn_del(hcon, bt_to_errno(reason)); return 0; } static inline void l2cap_check_encryption(struct l2cap_chan *chan, u8 encrypt) { - struct sock *sk = chan->sk; - - if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM) + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED) return; if (encrypt == 0x00) { if (chan->sec_level == BT_SECURITY_MEDIUM) { - l2cap_sock_clear_timer(sk); - l2cap_sock_set_timer(sk, HZ * 5); + __clear_chan_timer(chan); + __set_chan_timer(chan, HZ * 5); } else if (chan->sec_level == BT_SECURITY_HIGH) - __l2cap_sock_close(sk, ECONNREFUSED); + l2cap_chan_close(chan, ECONNREFUSED); } else { if (chan->sec_level == BT_SECURITY_MEDIUM) - l2cap_sock_clear_timer(sk); + __clear_chan_timer(chan); } } @@ -3973,50 +4100,74 @@ static int l2cap_security_cfm(struct hci_conn *hcon, u8 status, u8 encrypt) bh_lock_sock(sk); - if (chan->conf_state & L2CAP_CONF_CONNECT_PEND) { + BT_DBG("chan->scid %d", chan->scid); + + if (chan->scid == L2CAP_CID_LE_DATA) { + if (!status && encrypt) { + chan->sec_level = hcon->sec_level; + del_timer(&conn->security_timer); + l2cap_chan_ready(sk); + smp_distribute_keys(conn, 0); + } + + bh_unlock_sock(sk); + continue; + } + + if (test_bit(CONF_CONNECT_PEND, &chan->conf_state)) { bh_unlock_sock(sk); continue; } - if (!status && (sk->sk_state == BT_CONNECTED || - sk->sk_state == BT_CONFIG)) { + if (!status && (chan->state == BT_CONNECTED || + chan->state == BT_CONFIG)) { l2cap_check_encryption(chan, encrypt); bh_unlock_sock(sk); continue; } - if (sk->sk_state == BT_CONNECT) { + if (chan->state == BT_CONNECT) { if (!status) { struct l2cap_conn_req req; req.scid = cpu_to_le16(chan->scid); req.psm = chan->psm; chan->ident = l2cap_get_ident(conn); - chan->conf_state |= L2CAP_CONF_CONNECT_PEND; + set_bit(CONF_CONNECT_PEND, &chan->conf_state); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_REQ, sizeof(req), &req); } else { - l2cap_sock_clear_timer(sk); - l2cap_sock_set_timer(sk, HZ / 10); + __clear_chan_timer(chan); + __set_chan_timer(chan, HZ / 10); } - } else if (sk->sk_state == BT_CONNECT2) { + } else if (chan->state == BT_CONNECT2) { struct l2cap_conn_rsp rsp; - __u16 result; + __u16 res, stat; if (!status) { - sk->sk_state = BT_CONFIG; - result = L2CAP_CR_SUCCESS; + if (bt_sk(sk)->defer_setup) { + struct sock *parent = bt_sk(sk)->parent; + res = L2CAP_CR_PEND; + stat = L2CAP_CS_AUTHOR_PEND; + if (parent) + parent->sk_data_ready(parent, 0); + } else { + l2cap_state_change(chan, BT_CONFIG); + res = L2CAP_CR_SUCCESS; + stat = L2CAP_CS_NO_INFO; + } } else { - sk->sk_state = BT_DISCONN; - l2cap_sock_set_timer(sk, HZ / 10); - result = L2CAP_CR_SEC_BLOCK; + l2cap_state_change(chan, BT_DISCONN); + __set_chan_timer(chan, HZ / 10); + res = L2CAP_CR_SEC_BLOCK; + stat = L2CAP_CS_NO_INFO; } rsp.scid = cpu_to_le16(chan->dcid); rsp.dcid = cpu_to_le16(chan->scid); - rsp.result = cpu_to_le16(result); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); + rsp.result = cpu_to_le16(res); + rsp.status = cpu_to_le16(stat); l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, sizeof(rsp), &rsp); } @@ -4152,10 +4303,10 @@ static int l2cap_debugfs_show(struct seq_file *f, void *p) seq_printf(f, "%s %s %d %d 0x%4.4x 0x%4.4x %d %d %d %d\n", batostr(&bt_sk(sk)->src), batostr(&bt_sk(sk)->dst), - sk->sk_state, __le16_to_cpu(c->psm), + c->state, __le16_to_cpu(c->psm), c->scid, c->dcid, c->imtu, c->omtu, c->sec_level, c->mode); - } +} read_unlock_bh(&chan_list_lock); @@ -4195,12 +4346,6 @@ int __init l2cap_init(void) if (err < 0) return err; - _busy_wq = create_singlethread_workqueue("l2cap"); - if (!_busy_wq) { - err = -ENOMEM; - goto error; - } - err = hci_register_proto(&l2cap_hci_proto); if (err < 0) { BT_ERR("L2CAP protocol registration failed"); @@ -4218,7 +4363,6 @@ int __init l2cap_init(void) return 0; error: - destroy_workqueue(_busy_wq); l2cap_cleanup_sockets(); return err; } @@ -4227,9 +4371,6 @@ void l2cap_exit(void) { debugfs_remove(l2cap_debugfs); - flush_workqueue(_busy_wq); - destroy_workqueue(_busy_wq); - if (hci_unregister_proto(&l2cap_hci_proto) < 0) BT_ERR("L2CAP protocol unregistration failed"); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 18dc9888d8c..5c36b3e8739 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -29,54 +29,11 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> +#include <net/bluetooth/smp.h> static const struct proto_ops l2cap_sock_ops; - -/* ---- L2CAP timers ---- */ -static void l2cap_sock_timeout(unsigned long arg) -{ - struct sock *sk = (struct sock *) arg; - int reason; - - BT_DBG("sock %p state %d", sk, sk->sk_state); - - bh_lock_sock(sk); - - if (sock_owned_by_user(sk)) { - /* sk is owned by user. Try again later */ - l2cap_sock_set_timer(sk, HZ / 5); - bh_unlock_sock(sk); - sock_put(sk); - return; - } - - if (sk->sk_state == BT_CONNECTED || sk->sk_state == BT_CONFIG) - reason = ECONNREFUSED; - else if (sk->sk_state == BT_CONNECT && - l2cap_pi(sk)->chan->sec_level != BT_SECURITY_SDP) - reason = ECONNREFUSED; - else - reason = ETIMEDOUT; - - __l2cap_sock_close(sk, reason); - - bh_unlock_sock(sk); - - l2cap_sock_kill(sk); - sock_put(sk); -} - -void l2cap_sock_set_timer(struct sock *sk, long timeout) -{ - BT_DBG("sk %p state %d timeout %ld", sk, sk->sk_state, timeout); - sk_reset_timer(sk, &sk->sk_timer, jiffies + timeout); -} - -void l2cap_sock_clear_timer(struct sock *sk) -{ - BT_DBG("sock %p state %d", sk, sk->sk_state); - sk_stop_timer(sk, &sk->sk_timer); -} +static void l2cap_sock_init(struct sock *sk, struct sock *parent); +static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio); static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) { @@ -133,6 +90,8 @@ static int l2cap_sock_bind(struct socket *sock, struct sockaddr *addr, int alen) chan->sec_level = BT_SECURITY_SDP; bacpy(&bt_sk(sk)->src, &la.l2_bdaddr); + + chan->state = BT_BOUND; sk->sk_state = BT_BOUND; done: @@ -162,7 +121,7 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al lock_sock(sk); - if ((sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM) + if (chan->chan_type == L2CAP_CHAN_CONN_ORIENTED && !(la.l2_psm || la.l2_cid)) { err = -EINVAL; goto done; @@ -204,8 +163,8 @@ static int l2cap_sock_connect(struct socket *sock, struct sockaddr *addr, int al } /* PSM must be odd and lsb of upper byte must be 0 */ - if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 && - sk->sk_type != SOCK_RAW && !la.l2_cid) { + if ((__le16_to_cpu(la.l2_psm) & 0x0101) != 0x0001 && !la.l2_cid && + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; goto done; } @@ -258,6 +217,8 @@ static int l2cap_sock_listen(struct socket *sock, int backlog) sk->sk_max_ack_backlog = backlog; sk->sk_ack_backlog = 0; + + chan->state = BT_LISTEN; sk->sk_state = BT_LISTEN; done: @@ -413,6 +374,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, char __us break; } + memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); @@ -436,6 +398,7 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct bt_security sec; + struct bt_power pwr; int len, err = 0; BT_DBG("sk %p", sk); @@ -453,14 +416,18 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch switch (optname) { case BT_SECURITY: - if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM - && sk->sk_type != SOCK_RAW) { + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; } + memset(&sec, 0, sizeof(sec)); sec.level = chan->sec_level; + if (sk->sk_state == BT_CONNECTED) + sec.key_size = chan->conn->hcon->enc_key_size; + len = min_t(unsigned int, len, sizeof(sec)); if (copy_to_user(optval, (char *) &sec, len)) err = -EFAULT; @@ -484,6 +451,21 @@ static int l2cap_sock_getsockopt(struct socket *sock, int level, int optname, ch break; + case BT_POWER: + if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM + && sk->sk_type != SOCK_RAW) { + err = -EINVAL; + break; + } + + pwr.force_active = chan->force_active; + + len = min_t(unsigned int, len, sizeof(pwr)); + if (copy_to_user(optval, (char *) &pwr, len)) + err = -EFAULT; + + break; + default: err = -ENOPROTOOPT; break; @@ -534,7 +516,7 @@ static int l2cap_sock_setsockopt_old(struct socket *sock, int optname, char __us chan->mode = opts.mode; switch (chan->mode) { case L2CAP_MODE_BASIC: - chan->conf_state &= ~L2CAP_CONF_STATE2_DEVICE; + clear_bit(CONF_STATE2_DEVICE, &chan->conf_state); break; case L2CAP_MODE_ERTM: case L2CAP_MODE_STREAMING: @@ -584,6 +566,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct bt_security sec; + struct bt_power pwr; + struct l2cap_conn *conn; int len, err = 0; u32 opt; @@ -599,8 +583,8 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch switch (optname) { case BT_SECURITY: - if (sk->sk_type != SOCK_SEQPACKET && sk->sk_type != SOCK_STREAM - && sk->sk_type != SOCK_RAW) { + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_RAW) { err = -EINVAL; break; } @@ -620,6 +604,20 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch } chan->sec_level = sec.level; + + conn = chan->conn; + if (conn && chan->scid == L2CAP_CID_LE_DATA) { + if (!conn->hcon->out) { + err = -EINVAL; + break; + } + + if (smp_conn_security(conn, sec.level)) + break; + + err = 0; + sk->sk_state = BT_CONFIG; + } break; case BT_DEFER_SETUP: @@ -660,6 +658,23 @@ static int l2cap_sock_setsockopt(struct socket *sock, int level, int optname, ch chan->flushable = opt; break; + case BT_POWER: + if (chan->chan_type != L2CAP_CHAN_CONN_ORIENTED && + chan->chan_type != L2CAP_CHAN_RAW) { + err = -EINVAL; + break; + } + + pwr.force_active = BT_POWER_FORCE_ACTIVE_ON; + + len = min_t(unsigned int, sizeof(pwr), optlen); + if (copy_from_user((char *) &pwr, optval, len)) { + err = -EFAULT; + break; + } + chan->force_active = pwr.force_active; + break; + default: err = -ENOPROTOOPT; break; @@ -673,8 +688,6 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms { struct sock *sk = sock->sk; struct l2cap_chan *chan = l2cap_pi(sk)->chan; - struct sk_buff *skb; - u16 control; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -689,87 +702,12 @@ static int l2cap_sock_sendmsg(struct kiocb *iocb, struct socket *sock, struct ms lock_sock(sk); if (sk->sk_state != BT_CONNECTED) { - err = -ENOTCONN; - goto done; - } - - /* Connectionless channel */ - if (sk->sk_type == SOCK_DGRAM) { - skb = l2cap_create_connless_pdu(chan, msg, len); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - } else { - l2cap_do_send(chan, skb); - err = len; - } - goto done; + release_sock(sk); + return -ENOTCONN; } - switch (chan->mode) { - case L2CAP_MODE_BASIC: - /* Check outgoing MTU */ - if (len > chan->omtu) { - err = -EMSGSIZE; - goto done; - } - - /* Create a basic PDU */ - skb = l2cap_create_basic_pdu(chan, msg, len); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - goto done; - } - - l2cap_do_send(chan, skb); - err = len; - break; - - case L2CAP_MODE_ERTM: - case L2CAP_MODE_STREAMING: - /* Entire SDU fits into one PDU */ - if (len <= chan->remote_mps) { - control = L2CAP_SDU_UNSEGMENTED; - skb = l2cap_create_iframe_pdu(chan, msg, len, control, - 0); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - goto done; - } - __skb_queue_tail(&chan->tx_q, skb); - - if (chan->tx_send_head == NULL) - chan->tx_send_head = skb; + err = l2cap_chan_send(chan, msg, len); - } else { - /* Segment SDU into multiples PDUs */ - err = l2cap_sar_segment_sdu(chan, msg, len); - if (err < 0) - goto done; - } - - if (chan->mode == L2CAP_MODE_STREAMING) { - l2cap_streaming_send(chan); - err = len; - break; - } - - if ((chan->conn_state & L2CAP_CONN_REMOTE_BUSY) && - (chan->conn_state & L2CAP_CONN_WAIT_F)) { - err = len; - break; - } - err = l2cap_ertm_send(chan); - - if (err >= 0) - err = len; - break; - - default: - BT_DBG("bad state %1.1x", chan->mode); - err = -EBADFD; - } - -done: release_sock(sk); return err; } @@ -777,13 +715,15 @@ done: static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len, int flags) { struct sock *sk = sock->sk; + struct l2cap_pinfo *pi = l2cap_pi(sk); + int err; lock_sock(sk); if (sk->sk_state == BT_CONNECT2 && bt_sk(sk)->defer_setup) { sk->sk_state = BT_CONFIG; - __l2cap_connect_rsp_defer(l2cap_pi(sk)->chan); + __l2cap_connect_rsp_defer(pi->chan); release_sock(sk); return 0; } @@ -791,15 +731,43 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms release_sock(sk); if (sock->type == SOCK_STREAM) - return bt_sock_stream_recvmsg(iocb, sock, msg, len, flags); + err = bt_sock_stream_recvmsg(iocb, sock, msg, len, flags); + else + err = bt_sock_recvmsg(iocb, sock, msg, len, flags); - return bt_sock_recvmsg(iocb, sock, msg, len, flags); + if (pi->chan->mode != L2CAP_MODE_ERTM) + return err; + + /* Attempt to put pending rx data in the socket buffer */ + + lock_sock(sk); + + if (!test_bit(CONN_LOCAL_BUSY, &pi->chan->conn_state)) + goto done; + + if (pi->rx_busy_skb) { + if (!sock_queue_rcv_skb(sk, pi->rx_busy_skb)) + pi->rx_busy_skb = NULL; + else + goto done; + } + + /* Restore data flow when half of the receive buffer is + * available. This avoids resending large numbers of + * frames. + */ + if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf >> 1) + l2cap_chan_busy(pi->chan, 0); + +done: + release_sock(sk); + return err; } /* Kill socket (only if zapped and orphan) * Must be called on unlocked socket. */ -void l2cap_sock_kill(struct sock *sk) +static void l2cap_sock_kill(struct sock *sk) { if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket) return; @@ -813,87 +781,6 @@ void l2cap_sock_kill(struct sock *sk) sock_put(sk); } -/* Must be called on unlocked socket. */ -static void l2cap_sock_close(struct sock *sk) -{ - l2cap_sock_clear_timer(sk); - lock_sock(sk); - __l2cap_sock_close(sk, ECONNRESET); - release_sock(sk); - l2cap_sock_kill(sk); -} - -static void l2cap_sock_cleanup_listen(struct sock *parent) -{ - struct sock *sk; - - BT_DBG("parent %p", parent); - - /* Close not yet accepted channels */ - while ((sk = bt_accept_dequeue(parent, NULL))) - l2cap_sock_close(sk); - - parent->sk_state = BT_CLOSED; - sock_set_flag(parent, SOCK_ZAPPED); -} - -void __l2cap_sock_close(struct sock *sk, int reason) -{ - struct l2cap_chan *chan = l2cap_pi(sk)->chan; - struct l2cap_conn *conn = chan->conn; - - BT_DBG("sk %p state %d socket %p", sk, sk->sk_state, sk->sk_socket); - - switch (sk->sk_state) { - case BT_LISTEN: - l2cap_sock_cleanup_listen(sk); - break; - - case BT_CONNECTED: - case BT_CONFIG: - if ((sk->sk_type == SOCK_SEQPACKET || - sk->sk_type == SOCK_STREAM) && - conn->hcon->type == ACL_LINK) { - l2cap_sock_set_timer(sk, sk->sk_sndtimeo); - l2cap_send_disconn_req(conn, chan, reason); - } else - l2cap_chan_del(chan, reason); - break; - - case BT_CONNECT2: - if ((sk->sk_type == SOCK_SEQPACKET || - sk->sk_type == SOCK_STREAM) && - conn->hcon->type == ACL_LINK) { - struct l2cap_conn_rsp rsp; - __u16 result; - - if (bt_sk(sk)->defer_setup) - result = L2CAP_CR_SEC_BLOCK; - else - result = L2CAP_CR_BAD_PSM; - - rsp.scid = cpu_to_le16(chan->dcid); - rsp.dcid = cpu_to_le16(chan->scid); - rsp.result = cpu_to_le16(result); - rsp.status = cpu_to_le16(L2CAP_CS_NO_INFO); - l2cap_send_cmd(conn, chan->ident, L2CAP_CONN_RSP, - sizeof(rsp), &rsp); - } - - l2cap_chan_del(chan, reason); - break; - - case BT_CONNECT: - case BT_DISCONN: - l2cap_chan_del(chan, reason); - break; - - default: - sock_set_flag(sk, SOCK_ZAPPED); - break; - } -} - static int l2cap_sock_shutdown(struct socket *sock, int how) { struct sock *sk = sock->sk; @@ -911,8 +798,7 @@ static int l2cap_sock_shutdown(struct socket *sock, int how) err = __l2cap_wait_ack(sk); sk->sk_shutdown = SHUTDOWN_MASK; - l2cap_sock_clear_timer(sk); - __l2cap_sock_close(sk, 0); + l2cap_chan_close(chan, 0); if (sock_flag(sk, SOCK_LINGER) && sk->sk_lingertime) err = bt_sock_wait_state(sk, BT_CLOSED, @@ -943,15 +829,85 @@ static int l2cap_sock_release(struct socket *sock) return err; } +static struct l2cap_chan *l2cap_sock_new_connection_cb(void *data) +{ + struct sock *sk, *parent = data; + + sk = l2cap_sock_alloc(sock_net(parent), NULL, BTPROTO_L2CAP, + GFP_ATOMIC); + if (!sk) + return NULL; + + l2cap_sock_init(sk, parent); + + return l2cap_pi(sk)->chan; +} + +static int l2cap_sock_recv_cb(void *data, struct sk_buff *skb) +{ + int err; + struct sock *sk = data; + struct l2cap_pinfo *pi = l2cap_pi(sk); + + if (pi->rx_busy_skb) + return -ENOMEM; + + err = sock_queue_rcv_skb(sk, skb); + + /* For ERTM, handle one skb that doesn't fit into the recv + * buffer. This is important to do because the data frames + * have already been acked, so the skb cannot be discarded. + * + * Notify the l2cap core that the buffer is full, so the + * LOCAL_BUSY state is entered and no more frames are + * acked and reassembled until there is buffer space + * available. + */ + if (err < 0 && pi->chan->mode == L2CAP_MODE_ERTM) { + pi->rx_busy_skb = skb; + l2cap_chan_busy(pi->chan, 1); + err = 0; + } + + return err; +} + +static void l2cap_sock_close_cb(void *data) +{ + struct sock *sk = data; + + l2cap_sock_kill(sk); +} + +static void l2cap_sock_state_change_cb(void *data, int state) +{ + struct sock *sk = data; + + sk->sk_state = state; +} + +static struct l2cap_ops l2cap_chan_ops = { + .name = "L2CAP Socket Interface", + .new_connection = l2cap_sock_new_connection_cb, + .recv = l2cap_sock_recv_cb, + .close = l2cap_sock_close_cb, + .state_change = l2cap_sock_state_change_cb, +}; + static void l2cap_sock_destruct(struct sock *sk) { BT_DBG("sk %p", sk); + if (l2cap_pi(sk)->rx_busy_skb) { + kfree_skb(l2cap_pi(sk)->rx_busy_skb); + l2cap_pi(sk)->rx_busy_skb = NULL; + } + skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); } -void l2cap_sock_init(struct sock *sk, struct sock *parent) +static void l2cap_sock_init(struct sock *sk, struct sock *parent) { struct l2cap_pinfo *pi = l2cap_pi(sk); struct l2cap_chan *chan = pi->chan; @@ -964,6 +920,7 @@ void l2cap_sock_init(struct sock *sk, struct sock *parent) sk->sk_type = parent->sk_type; bt_sk(sk)->defer_setup = bt_sk(parent)->defer_setup; + chan->chan_type = pchan->chan_type; chan->imtu = pchan->imtu; chan->omtu = pchan->omtu; chan->conf_state = pchan->conf_state; @@ -975,12 +932,27 @@ void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->role_switch = pchan->role_switch; chan->force_reliable = pchan->force_reliable; chan->flushable = pchan->flushable; + chan->force_active = pchan->force_active; } else { + + switch (sk->sk_type) { + case SOCK_RAW: + chan->chan_type = L2CAP_CHAN_RAW; + break; + case SOCK_DGRAM: + chan->chan_type = L2CAP_CHAN_CONN_LESS; + break; + case SOCK_SEQPACKET: + case SOCK_STREAM: + chan->chan_type = L2CAP_CHAN_CONN_ORIENTED; + break; + } + chan->imtu = L2CAP_DEFAULT_MTU; chan->omtu = 0; if (!disable_ertm && sk->sk_type == SOCK_STREAM) { chan->mode = L2CAP_MODE_ERTM; - chan->conf_state |= L2CAP_CONF_STATE2_DEVICE; + set_bit(CONF_STATE2_DEVICE, &chan->conf_state); } else { chan->mode = L2CAP_MODE_BASIC; } @@ -991,10 +963,15 @@ void l2cap_sock_init(struct sock *sk, struct sock *parent) chan->role_switch = 0; chan->force_reliable = 0; chan->flushable = BT_FLUSHABLE_OFF; + chan->force_active = BT_POWER_FORCE_ACTIVE_ON; + } /* Default config options */ chan->flush_to = L2CAP_DEFAULT_FLUSH_TO; + + chan->data = sk; + chan->ops = &l2cap_chan_ops; } static struct proto l2cap_proto = { @@ -1003,9 +980,10 @@ static struct proto l2cap_proto = { .obj_size = sizeof(struct l2cap_pinfo) }; -struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio) +static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio) { struct sock *sk; + struct l2cap_chan *chan; sk = sk_alloc(net, PF_BLUETOOTH, prio, &l2cap_proto); if (!sk) @@ -1022,7 +1000,13 @@ struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, g sk->sk_protocol = proto; sk->sk_state = BT_OPEN; - setup_timer(&sk->sk_timer, l2cap_sock_timeout, (unsigned long) sk); + chan = l2cap_chan_create(sk); + if (!chan) { + l2cap_sock_kill(sk); + return NULL; + } + + l2cap_pi(sk)->chan = chan; return sk; } @@ -1031,7 +1015,6 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, int kern) { struct sock *sk; - struct l2cap_chan *chan; BT_DBG("sock %p", sock); @@ -1050,14 +1033,6 @@ static int l2cap_sock_create(struct net *net, struct socket *sock, int protocol, if (!sk) return -ENOMEM; - chan = l2cap_chan_create(sk); - if (!chan) { - l2cap_sock_kill(sk); - return -ENOMEM; - } - - l2cap_pi(sk)->chan = chan; - l2cap_sock_init(sk, NULL); return 0; } diff --git a/net/bluetooth/lib.c b/net/bluetooth/lib.c index b826d1bf10d..86a6bed229d 100644 --- a/net/bluetooth/lib.c +++ b/net/bluetooth/lib.c @@ -59,7 +59,7 @@ char *batostr(bdaddr_t *ba) EXPORT_SYMBOL(batostr); /* Bluetooth error codes to Unix errno mapping */ -int bt_err(__u16 code) +int bt_to_errno(__u16 code) { switch (code) { case 0: @@ -149,4 +149,23 @@ int bt_err(__u16 code) return ENOSYS; } } -EXPORT_SYMBOL(bt_err); +EXPORT_SYMBOL(bt_to_errno); + +int bt_printk(const char *level, const char *format, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + r = printk("%sBluetooth: %pV\n", level, &vaf); + + va_end(args); + + return r; +} +EXPORT_SYMBOL(bt_printk); diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index dae382ce702..53e109eb043 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -41,7 +41,7 @@ struct pending_cmd { void *user_data; }; -LIST_HEAD(cmd_list); +static LIST_HEAD(cmd_list); static int cmd_status(struct sock *sk, u16 index, u16 cmd, u8 status) { @@ -179,7 +179,7 @@ static int read_controller_info(struct sock *sk, u16 index) hci_del_off_timer(hdev); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); set_bit(HCI_MGMT, &hdev->flags); @@ -208,7 +208,7 @@ static int read_controller_info(struct sock *sk, u16 index) memcpy(rp.name, hdev->dev_name, sizeof(hdev->dev_name)); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return cmd_complete(sk, index, MGMT_OP_READ_INFO, &rp, sizeof(rp)); @@ -316,7 +316,7 @@ static int set_powered(struct sock *sk, u16 index, unsigned char *data, u16 len) if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_POWERED, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); up = test_bit(HCI_UP, &hdev->flags); if ((cp->val && up) || (!cp->val && !up)) { @@ -343,7 +343,7 @@ static int set_powered(struct sock *sk, u16 index, unsigned char *data, u16 len) err = 0; failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; } @@ -368,7 +368,7 @@ static int set_discoverable(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_DISCOVERABLE, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, MGMT_OP_SET_DISCOVERABLE, ENETDOWN); @@ -403,7 +403,7 @@ static int set_discoverable(struct sock *sk, u16 index, unsigned char *data, mgmt_pending_remove(cmd); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -429,7 +429,7 @@ static int set_connectable(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_CONNECTABLE, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, MGMT_OP_SET_CONNECTABLE, ENETDOWN); @@ -463,7 +463,7 @@ static int set_connectable(struct sock *sk, u16 index, unsigned char *data, mgmt_pending_remove(cmd); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -522,7 +522,7 @@ static int set_pairable(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_PAIRABLE, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (cp->val) set_bit(HCI_PAIRABLE, &hdev->flags); @@ -538,7 +538,7 @@ static int set_pairable(struct sock *sk, u16 index, unsigned char *data, err = mgmt_event(MGMT_EV_PAIRABLE, index, &ev, sizeof(ev), sk); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -739,7 +739,7 @@ static int add_uuid(struct sock *sk, u16 index, unsigned char *data, u16 len) if (!hdev) return cmd_status(sk, index, MGMT_OP_ADD_UUID, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); uuid = kmalloc(sizeof(*uuid), GFP_ATOMIC); if (!uuid) { @@ -763,7 +763,7 @@ static int add_uuid(struct sock *sk, u16 index, unsigned char *data, u16 len) err = cmd_complete(sk, index, MGMT_OP_ADD_UUID, NULL, 0); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -788,7 +788,7 @@ static int remove_uuid(struct sock *sk, u16 index, unsigned char *data, u16 len) if (!hdev) return cmd_status(sk, index, MGMT_OP_REMOVE_UUID, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (memcmp(cp->uuid, bt_uuid_any, 16) == 0) { err = hci_uuids_clear(hdev); @@ -823,7 +823,7 @@ static int remove_uuid(struct sock *sk, u16 index, unsigned char *data, u16 len) err = cmd_complete(sk, index, MGMT_OP_REMOVE_UUID, NULL, 0); unlock: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -847,7 +847,7 @@ static int set_dev_class(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_DEV_CLASS, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); hdev->major_class = cp->major; hdev->minor_class = cp->minor; @@ -857,7 +857,7 @@ static int set_dev_class(struct sock *sk, u16 index, unsigned char *data, if (err == 0) err = cmd_complete(sk, index, MGMT_OP_SET_DEV_CLASS, NULL, 0); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -879,7 +879,7 @@ static int set_service_cache(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_SERVICE_CACHE, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); BT_DBG("hci%u enable %d", index, cp->enable); @@ -897,7 +897,7 @@ static int set_service_cache(struct sock *sk, u16 index, unsigned char *data, err = cmd_complete(sk, index, MGMT_OP_SET_SERVICE_CACHE, NULL, 0); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -908,7 +908,7 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) struct hci_dev *hdev; struct mgmt_cp_load_keys *cp; u16 key_count, expected_len; - int i; + int i, err; cp = (void *) data; @@ -918,9 +918,9 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) key_count = get_unaligned_le16(&cp->key_count); expected_len = sizeof(*cp) + key_count * sizeof(struct mgmt_key_info); - if (expected_len != len) { - BT_ERR("load_keys: expected %u bytes, got %u bytes", - len, expected_len); + if (expected_len > len) { + BT_ERR("load_keys: expected at least %u bytes, got %u bytes", + expected_len, len); return -EINVAL; } @@ -931,7 +931,7 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) BT_DBG("hci%u debug_keys %u key_count %u", index, cp->debug_keys, key_count); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); hci_link_keys_clear(hdev); @@ -942,17 +942,36 @@ static int load_keys(struct sock *sk, u16 index, unsigned char *data, u16 len) else clear_bit(HCI_DEBUG_KEYS, &hdev->flags); - for (i = 0; i < key_count; i++) { - struct mgmt_key_info *key = &cp->keys[i]; + len -= sizeof(*cp); + i = 0; + + while (i < len) { + struct mgmt_key_info *key = (void *) cp->keys + i; + + i += sizeof(*key) + key->dlen; + + if (key->type == HCI_LK_SMP_LTK) { + struct key_master_id *id = (void *) key->data; + + if (key->dlen != sizeof(struct key_master_id)) + continue; + + hci_add_ltk(hdev, 0, &key->bdaddr, key->pin_len, + id->ediv, id->rand, key->val); + + continue; + } hci_add_link_key(hdev, NULL, 0, &key->bdaddr, key->val, key->type, key->pin_len); } - hci_dev_unlock(hdev); + err = cmd_complete(sk, index, MGMT_OP_LOAD_KEYS, NULL, 0); + + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); - return 0; + return err; } static int remove_key(struct sock *sk, u16 index, unsigned char *data, u16 len) @@ -971,7 +990,7 @@ static int remove_key(struct sock *sk, u16 index, unsigned char *data, u16 len) if (!hdev) return cmd_status(sk, index, MGMT_OP_REMOVE_KEY, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); err = hci_remove_link_key(hdev, &cp->bdaddr); if (err < 0) { @@ -990,11 +1009,11 @@ static int remove_key(struct sock *sk, u16 index, unsigned char *data, u16 len) put_unaligned_le16(conn->handle, &dc.handle); dc.reason = 0x13; /* Remote User Terminated Connection */ - err = hci_send_cmd(hdev, HCI_OP_DISCONNECT, 0, NULL); + err = hci_send_cmd(hdev, HCI_OP_DISCONNECT, sizeof(dc), &dc); } unlock: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1020,7 +1039,7 @@ static int disconnect(struct sock *sk, u16 index, unsigned char *data, u16 len) if (!hdev) return cmd_status(sk, index, MGMT_OP_DISCONNECT, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, MGMT_OP_DISCONNECT, ENETDOWN); @@ -1055,7 +1074,7 @@ static int disconnect(struct sock *sk, u16 index, unsigned char *data, u16 len) mgmt_pending_remove(cmd); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1076,7 +1095,7 @@ static int get_connections(struct sock *sk, u16 index) if (!hdev) return cmd_status(sk, index, MGMT_OP_GET_CONNECTIONS, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); count = 0; list_for_each(p, &hdev->conn_hash.list) { @@ -1092,8 +1111,6 @@ static int get_connections(struct sock *sk, u16 index) put_unaligned_le16(count, &rp->conn_count); - read_lock(&hci_dev_list_lock); - i = 0; list_for_each(p, &hdev->conn_hash.list) { struct hci_conn *c = list_entry(p, struct hci_conn, list); @@ -1101,22 +1118,41 @@ static int get_connections(struct sock *sk, u16 index) bacpy(&rp->conn[i++], &c->dst); } - read_unlock(&hci_dev_list_lock); - err = cmd_complete(sk, index, MGMT_OP_GET_CONNECTIONS, rp, rp_len); unlock: kfree(rp); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; } +static int send_pin_code_neg_reply(struct sock *sk, u16 index, + struct hci_dev *hdev, struct mgmt_cp_pin_code_neg_reply *cp) +{ + struct pending_cmd *cmd; + int err; + + cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, index, cp, + sizeof(*cp)); + if (!cmd) + return -ENOMEM; + + err = hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY, sizeof(cp->bdaddr), + &cp->bdaddr); + if (err < 0) + mgmt_pending_remove(cmd); + + return err; +} + static int pin_code_reply(struct sock *sk, u16 index, unsigned char *data, u16 len) { struct hci_dev *hdev; + struct hci_conn *conn; struct mgmt_cp_pin_code_reply *cp; + struct mgmt_cp_pin_code_neg_reply ncp; struct hci_cp_pin_code_reply reply; struct pending_cmd *cmd; int err; @@ -1132,13 +1168,32 @@ static int pin_code_reply(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_PIN_CODE_REPLY, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, MGMT_OP_PIN_CODE_REPLY, ENETDOWN); goto failed; } + conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &cp->bdaddr); + if (!conn) { + err = cmd_status(sk, index, MGMT_OP_PIN_CODE_REPLY, ENOTCONN); + goto failed; + } + + if (conn->pending_sec_level == BT_SECURITY_HIGH && cp->pin_len != 16) { + bacpy(&ncp.bdaddr, &cp->bdaddr); + + BT_ERR("PIN code is not 16 bytes long"); + + err = send_pin_code_neg_reply(sk, index, hdev, &ncp); + if (err >= 0) + err = cmd_status(sk, index, MGMT_OP_PIN_CODE_REPLY, + EINVAL); + + goto failed; + } + cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_REPLY, index, data, len); if (!cmd) { err = -ENOMEM; @@ -1147,14 +1202,14 @@ static int pin_code_reply(struct sock *sk, u16 index, unsigned char *data, bacpy(&reply.bdaddr, &cp->bdaddr); reply.pin_len = cp->pin_len; - memcpy(reply.pin_code, cp->pin_code, 16); + memcpy(reply.pin_code, cp->pin_code, sizeof(reply.pin_code)); err = hci_send_cmd(hdev, HCI_OP_PIN_CODE_REPLY, sizeof(reply), &reply); if (err < 0) mgmt_pending_remove(cmd); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1165,7 +1220,6 @@ static int pin_code_neg_reply(struct sock *sk, u16 index, unsigned char *data, { struct hci_dev *hdev; struct mgmt_cp_pin_code_neg_reply *cp; - struct pending_cmd *cmd; int err; BT_DBG(""); @@ -1181,7 +1235,7 @@ static int pin_code_neg_reply(struct sock *sk, u16 index, unsigned char *data, return cmd_status(sk, index, MGMT_OP_PIN_CODE_NEG_REPLY, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, MGMT_OP_PIN_CODE_NEG_REPLY, @@ -1189,20 +1243,10 @@ static int pin_code_neg_reply(struct sock *sk, u16 index, unsigned char *data, goto failed; } - cmd = mgmt_pending_add(sk, MGMT_OP_PIN_CODE_NEG_REPLY, index, - data, len); - if (!cmd) { - err = -ENOMEM; - goto failed; - } - - err = hci_send_cmd(hdev, HCI_OP_PIN_CODE_NEG_REPLY, sizeof(cp->bdaddr), - &cp->bdaddr); - if (err < 0) - mgmt_pending_remove(cmd); + err = send_pin_code_neg_reply(sk, index, hdev, cp); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1225,14 +1269,14 @@ static int set_io_capability(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_IO_CAPABILITY, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); hdev->io_capability = cp->io_capability; BT_DBG("%s IO capability set to 0x%02x", hdev->name, hdev->io_capability); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return cmd_complete(sk, index, MGMT_OP_SET_IO_CAPABILITY, NULL, 0); @@ -1318,7 +1362,7 @@ static int pair_device(struct sock *sk, u16 index, unsigned char *data, u16 len) if (!hdev) return cmd_status(sk, index, MGMT_OP_PAIR_DEVICE, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (cp->io_cap == 0x03) { sec_level = BT_SECURITY_MEDIUM; @@ -1360,7 +1404,7 @@ static int pair_device(struct sock *sk, u16 index, unsigned char *data, u16 len) err = 0; unlock: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1392,7 +1436,7 @@ static int user_confirm_reply(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, mgmt_op, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, mgmt_op, ENETDOWN); @@ -1410,7 +1454,7 @@ static int user_confirm_reply(struct sock *sk, u16 index, unsigned char *data, mgmt_pending_remove(cmd); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1434,7 +1478,7 @@ static int set_local_name(struct sock *sk, u16 index, unsigned char *data, if (!hdev) return cmd_status(sk, index, MGMT_OP_SET_LOCAL_NAME, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); cmd = mgmt_pending_add(sk, MGMT_OP_SET_LOCAL_NAME, index, data, len); if (!cmd) { @@ -1449,7 +1493,7 @@ static int set_local_name(struct sock *sk, u16 index, unsigned char *data, mgmt_pending_remove(cmd); failed: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1468,7 +1512,7 @@ static int read_local_oob_data(struct sock *sk, u16 index) return cmd_status(sk, index, MGMT_OP_READ_LOCAL_OOB_DATA, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); if (!test_bit(HCI_UP, &hdev->flags)) { err = cmd_status(sk, index, MGMT_OP_READ_LOCAL_OOB_DATA, @@ -1498,7 +1542,7 @@ static int read_local_oob_data(struct sock *sk, u16 index) mgmt_pending_remove(cmd); unlock: - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1522,7 +1566,7 @@ static int add_remote_oob_data(struct sock *sk, u16 index, unsigned char *data, return cmd_status(sk, index, MGMT_OP_ADD_REMOTE_OOB_DATA, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); err = hci_add_remote_oob_data(hdev, &cp->bdaddr, cp->hash, cp->randomizer); @@ -1532,7 +1576,7 @@ static int add_remote_oob_data(struct sock *sk, u16 index, unsigned char *data, err = cmd_complete(sk, index, MGMT_OP_ADD_REMOTE_OOB_DATA, NULL, 0); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1556,7 +1600,7 @@ static int remove_remote_oob_data(struct sock *sk, u16 index, return cmd_status(sk, index, MGMT_OP_REMOVE_REMOTE_OOB_DATA, ENODEV); - hci_dev_lock(hdev); + hci_dev_lock_bh(hdev); err = hci_remove_remote_oob_data(hdev, &cp->bdaddr); if (err < 0) @@ -1566,7 +1610,7 @@ static int remove_remote_oob_data(struct sock *sk, u16 index, err = cmd_complete(sk, index, MGMT_OP_REMOVE_REMOTE_OOB_DATA, NULL, 0); - hci_dev_unlock(hdev); + hci_dev_unlock_bh(hdev); hci_dev_put(hdev); return err; @@ -1641,6 +1685,70 @@ failed: return err; } +static int block_device(struct sock *sk, u16 index, unsigned char *data, + u16 len) +{ + struct hci_dev *hdev; + struct mgmt_cp_block_device *cp; + int err; + + BT_DBG("hci%u", index); + + cp = (void *) data; + + if (len != sizeof(*cp)) + return cmd_status(sk, index, MGMT_OP_BLOCK_DEVICE, + EINVAL); + + hdev = hci_dev_get(index); + if (!hdev) + return cmd_status(sk, index, MGMT_OP_BLOCK_DEVICE, + ENODEV); + + err = hci_blacklist_add(hdev, &cp->bdaddr); + + if (err < 0) + err = cmd_status(sk, index, MGMT_OP_BLOCK_DEVICE, -err); + else + err = cmd_complete(sk, index, MGMT_OP_BLOCK_DEVICE, + NULL, 0); + hci_dev_put(hdev); + + return err; +} + +static int unblock_device(struct sock *sk, u16 index, unsigned char *data, + u16 len) +{ + struct hci_dev *hdev; + struct mgmt_cp_unblock_device *cp; + int err; + + BT_DBG("hci%u", index); + + cp = (void *) data; + + if (len != sizeof(*cp)) + return cmd_status(sk, index, MGMT_OP_UNBLOCK_DEVICE, + EINVAL); + + hdev = hci_dev_get(index); + if (!hdev) + return cmd_status(sk, index, MGMT_OP_UNBLOCK_DEVICE, + ENODEV); + + err = hci_blacklist_del(hdev, &cp->bdaddr); + + if (err < 0) + err = cmd_status(sk, index, MGMT_OP_UNBLOCK_DEVICE, -err); + else + err = cmd_complete(sk, index, MGMT_OP_UNBLOCK_DEVICE, + NULL, 0); + hci_dev_put(hdev); + + return err; +} + int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) { unsigned char *buf; @@ -1755,6 +1863,12 @@ int mgmt_control(struct sock *sk, struct msghdr *msg, size_t msglen) case MGMT_OP_STOP_DISCOVERY: err = stop_discovery(sk, index); break; + case MGMT_OP_BLOCK_DEVICE: + err = block_device(sk, index, buf + sizeof(*hdr), len); + break; + case MGMT_OP_UNBLOCK_DEVICE: + err = unblock_device(sk, index, buf + sizeof(*hdr), len); + break; default: BT_DBG("Unknown op %u", opcode); err = cmd_status(sk, index, opcode, 0x01); @@ -1863,17 +1977,28 @@ int mgmt_connectable(u16 index, u8 connectable) int mgmt_new_key(u16 index, struct link_key *key, u8 persistent) { - struct mgmt_ev_new_key ev; + struct mgmt_ev_new_key *ev; + int err, total; - memset(&ev, 0, sizeof(ev)); + total = sizeof(struct mgmt_ev_new_key) + key->dlen; + ev = kzalloc(total, GFP_ATOMIC); + if (!ev) + return -ENOMEM; - ev.store_hint = persistent; - bacpy(&ev.key.bdaddr, &key->bdaddr); - ev.key.type = key->type; - memcpy(ev.key.val, key->val, 16); - ev.key.pin_len = key->pin_len; + bacpy(&ev->key.bdaddr, &key->bdaddr); + ev->key.type = key->type; + memcpy(ev->key.val, key->val, 16); + ev->key.pin_len = key->pin_len; + ev->key.dlen = key->dlen; + ev->store_hint = persistent; - return mgmt_event(MGMT_EV_NEW_KEY, index, &ev, sizeof(ev), NULL); + memcpy(ev->key.data, key->data, key->dlen); + + err = mgmt_event(MGMT_EV_NEW_KEY, index, ev, total, NULL); + + kfree(ev); + + return err; } int mgmt_connected(u16 index, bdaddr_t *bdaddr) diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 386cfaffd4b..8f01e6b11a7 100644 --- a/net/bluetooth/rfcomm/sock.c +++ b/net/bluetooth/rfcomm/sock.c @@ -679,7 +679,8 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, c { struct sock *sk = sock->sk; struct bt_security sec; - int len, err = 0; + int err = 0; + size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -741,7 +742,6 @@ static int rfcomm_sock_setsockopt(struct socket *sock, int level, int optname, c static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __user *optval, int __user *optlen) { struct sock *sk = sock->sk; - struct sock *l2cap_sk; struct rfcomm_conninfo cinfo; struct l2cap_conn *conn = l2cap_pi(sk)->chan->conn; int len, err = 0; @@ -786,8 +786,7 @@ static int rfcomm_sock_getsockopt_old(struct socket *sock, int optname, char __u break; } - l2cap_sk = rfcomm_pi(sk)->dlc->session->sock->sk; - + memset(&cinfo, 0, sizeof(cinfo)); cinfo.hci_handle = conn->hcon->handle; memcpy(cinfo.dev_class, conn->hcon->dev_class, 3); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 42fdffd1d76..4c3621b5e0a 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -369,6 +369,15 @@ static void __sco_sock_close(struct sock *sk) case BT_CONNECTED: case BT_CONFIG: + if (sco_pi(sk)->conn) { + sk->sk_state = BT_DISCONN; + sco_sock_set_timer(sk, SCO_DISCONN_TIMEOUT); + hci_conn_put(sco_pi(sk)->conn->hcon); + sco_pi(sk)->conn->hcon = NULL; + } else + sco_chan_del(sk, ECONNRESET); + break; + case BT_CONNECT: case BT_DISCONN: sco_chan_del(sk, ECONNRESET); @@ -819,7 +828,9 @@ static void sco_chan_del(struct sock *sk, int err) conn->sk = NULL; sco_pi(sk)->conn = NULL; sco_conn_unlock(conn); - hci_conn_put(conn->hcon); + + if (conn->hcon) + hci_conn_put(conn->hcon); } sk->sk_state = BT_CLOSED; @@ -921,7 +932,7 @@ static int sco_connect_cfm(struct hci_conn *hcon, __u8 status) if (conn) sco_conn_ready(conn); } else - sco_conn_del(hcon, bt_err(status)); + sco_conn_del(hcon, bt_to_errno(status)); return 0; } @@ -933,7 +944,7 @@ static int sco_disconn_cfm(struct hci_conn *hcon, __u8 reason) if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK) return -EINVAL; - sco_conn_del(hcon, bt_err(reason)); + sco_conn_del(hcon, bt_to_errno(reason)); return 0; } diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c new file mode 100644 index 00000000000..391888b88a9 --- /dev/null +++ b/net/bluetooth/smp.c @@ -0,0 +1,702 @@ +/* + BlueZ - Bluetooth protocol stack for Linux + Copyright (C) 2011 Nokia Corporation and/or its subsidiary(-ies). + + 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; + + THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS + OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. + IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY + CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES + WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN + ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF + OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. + + ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, + COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS + SOFTWARE IS DISCLAIMED. +*/ + +#include <net/bluetooth/bluetooth.h> +#include <net/bluetooth/hci_core.h> +#include <net/bluetooth/l2cap.h> +#include <net/bluetooth/smp.h> +#include <linux/crypto.h> +#include <linux/scatterlist.h> +#include <crypto/b128ops.h> + +#define SMP_TIMEOUT 30000 /* 30 seconds */ + +static inline void swap128(u8 src[16], u8 dst[16]) +{ + int i; + for (i = 0; i < 16; i++) + dst[15 - i] = src[i]; +} + +static inline void swap56(u8 src[7], u8 dst[7]) +{ + int i; + for (i = 0; i < 7; i++) + dst[6 - i] = src[i]; +} + +static int smp_e(struct crypto_blkcipher *tfm, const u8 *k, u8 *r) +{ + struct blkcipher_desc desc; + struct scatterlist sg; + int err, iv_len; + unsigned char iv[128]; + + if (tfm == NULL) { + BT_ERR("tfm %p", tfm); + return -EINVAL; + } + + desc.tfm = tfm; + desc.flags = 0; + + err = crypto_blkcipher_setkey(tfm, k, 16); + if (err) { + BT_ERR("cipher setkey failed: %d", err); + return err; + } + + sg_init_one(&sg, r, 16); + + iv_len = crypto_blkcipher_ivsize(tfm); + if (iv_len) { + memset(&iv, 0xff, iv_len); + crypto_blkcipher_set_iv(tfm, iv, iv_len); + } + + err = crypto_blkcipher_encrypt(&desc, &sg, &sg, 16); + if (err) + BT_ERR("Encrypt data error %d", err); + + return err; +} + +static int smp_c1(struct crypto_blkcipher *tfm, u8 k[16], u8 r[16], + u8 preq[7], u8 pres[7], u8 _iat, bdaddr_t *ia, + u8 _rat, bdaddr_t *ra, u8 res[16]) +{ + u8 p1[16], p2[16]; + int err; + + memset(p1, 0, 16); + + /* p1 = pres || preq || _rat || _iat */ + swap56(pres, p1); + swap56(preq, p1 + 7); + p1[14] = _rat; + p1[15] = _iat; + + memset(p2, 0, 16); + + /* p2 = padding || ia || ra */ + baswap((bdaddr_t *) (p2 + 4), ia); + baswap((bdaddr_t *) (p2 + 10), ra); + + /* res = r XOR p1 */ + u128_xor((u128 *) res, (u128 *) r, (u128 *) p1); + + /* res = e(k, res) */ + err = smp_e(tfm, k, res); + if (err) { + BT_ERR("Encrypt data error"); + return err; + } + + /* res = res XOR p2 */ + u128_xor((u128 *) res, (u128 *) res, (u128 *) p2); + + /* res = e(k, res) */ + err = smp_e(tfm, k, res); + if (err) + BT_ERR("Encrypt data error"); + + return err; +} + +static int smp_s1(struct crypto_blkcipher *tfm, u8 k[16], + u8 r1[16], u8 r2[16], u8 _r[16]) +{ + int err; + + /* Just least significant octets from r1 and r2 are considered */ + memcpy(_r, r1 + 8, 8); + memcpy(_r + 8, r2 + 8, 8); + + err = smp_e(tfm, k, _r); + if (err) + BT_ERR("Encrypt data error"); + + return err; +} + +static int smp_rand(u8 *buf) +{ + get_random_bytes(buf, 16); + + return 0; +} + +static struct sk_buff *smp_build_cmd(struct l2cap_conn *conn, u8 code, + u16 dlen, void *data) +{ + struct sk_buff *skb; + struct l2cap_hdr *lh; + int len; + + len = L2CAP_HDR_SIZE + sizeof(code) + dlen; + + if (len > conn->mtu) + return NULL; + + skb = bt_skb_alloc(len, GFP_ATOMIC); + if (!skb) + return NULL; + + lh = (struct l2cap_hdr *) skb_put(skb, L2CAP_HDR_SIZE); + lh->len = cpu_to_le16(sizeof(code) + dlen); + lh->cid = cpu_to_le16(L2CAP_CID_SMP); + + memcpy(skb_put(skb, sizeof(code)), &code, sizeof(code)); + + memcpy(skb_put(skb, dlen), data, dlen); + + return skb; +} + +static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) +{ + struct sk_buff *skb = smp_build_cmd(conn, code, len, data); + + BT_DBG("code 0x%2.2x", code); + + if (!skb) + return; + + hci_send_acl(conn->hcon, skb, 0); +} + +static __u8 seclevel_to_authreq(__u8 level) +{ + switch (level) { + case BT_SECURITY_HIGH: + /* Right now we don't support bonding */ + return SMP_AUTH_MITM; + + default: + return SMP_AUTH_NONE; + } +} + +static void build_pairing_cmd(struct l2cap_conn *conn, + struct smp_cmd_pairing *req, + struct smp_cmd_pairing *rsp, + __u8 authreq) +{ + u8 dist_keys; + + dist_keys = 0; + if (test_bit(HCI_PAIRABLE, &conn->hcon->hdev->flags)) { + dist_keys = SMP_DIST_ENC_KEY | SMP_DIST_ID_KEY | SMP_DIST_SIGN; + authreq |= SMP_AUTH_BONDING; + } + + if (rsp == NULL) { + req->io_capability = conn->hcon->io_capability; + req->oob_flag = SMP_OOB_NOT_PRESENT; + req->max_key_size = SMP_MAX_ENC_KEY_SIZE; + req->init_key_dist = dist_keys; + req->resp_key_dist = dist_keys; + req->auth_req = authreq; + return; + } + + rsp->io_capability = conn->hcon->io_capability; + rsp->oob_flag = SMP_OOB_NOT_PRESENT; + rsp->max_key_size = SMP_MAX_ENC_KEY_SIZE; + rsp->init_key_dist = req->init_key_dist & dist_keys; + rsp->resp_key_dist = req->resp_key_dist & dist_keys; + rsp->auth_req = authreq; +} + +static u8 check_enc_key_size(struct l2cap_conn *conn, __u8 max_key_size) +{ + if ((max_key_size > SMP_MAX_ENC_KEY_SIZE) || + (max_key_size < SMP_MIN_ENC_KEY_SIZE)) + return SMP_ENC_KEY_SIZE; + + conn->smp_key_size = max_key_size; + + return 0; +} + +static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_pairing rsp, *req = (void *) skb->data; + u8 key_size; + + BT_DBG("conn %p", conn); + + conn->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&conn->preq[1], req, sizeof(*req)); + skb_pull(skb, sizeof(*req)); + + if (req->oob_flag) + return SMP_OOB_NOT_AVAIL; + + /* We didn't start the pairing, so no requirements */ + build_pairing_cmd(conn, req, &rsp, SMP_AUTH_NONE); + + key_size = min(req->max_key_size, rsp.max_key_size); + if (check_enc_key_size(conn, key_size)) + return SMP_ENC_KEY_SIZE; + + /* Just works */ + memset(conn->tk, 0, sizeof(conn->tk)); + + conn->prsp[0] = SMP_CMD_PAIRING_RSP; + memcpy(&conn->prsp[1], &rsp, sizeof(rsp)); + + smp_send_cmd(conn, SMP_CMD_PAIRING_RSP, sizeof(rsp), &rsp); + + mod_timer(&conn->security_timer, jiffies + + msecs_to_jiffies(SMP_TIMEOUT)); + + return 0; +} + +static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_pairing *req, *rsp = (void *) skb->data; + struct smp_cmd_pairing_confirm cp; + struct crypto_blkcipher *tfm = conn->hcon->hdev->tfm; + int ret; + u8 res[16], key_size; + + BT_DBG("conn %p", conn); + + skb_pull(skb, sizeof(*rsp)); + + req = (void *) &conn->preq[1]; + + key_size = min(req->max_key_size, rsp->max_key_size); + if (check_enc_key_size(conn, key_size)) + return SMP_ENC_KEY_SIZE; + + if (rsp->oob_flag) + return SMP_OOB_NOT_AVAIL; + + /* Just works */ + memset(conn->tk, 0, sizeof(conn->tk)); + + conn->prsp[0] = SMP_CMD_PAIRING_RSP; + memcpy(&conn->prsp[1], rsp, sizeof(*rsp)); + + ret = smp_rand(conn->prnd); + if (ret) + return SMP_UNSPECIFIED; + + ret = smp_c1(tfm, conn->tk, conn->prnd, conn->preq, conn->prsp, 0, + conn->src, conn->hcon->dst_type, conn->dst, res); + if (ret) + return SMP_UNSPECIFIED; + + swap128(res, cp.confirm_val); + + smp_send_cmd(conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); + + return 0; +} + +static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct crypto_blkcipher *tfm = conn->hcon->hdev->tfm; + + BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); + + memcpy(conn->pcnf, skb->data, sizeof(conn->pcnf)); + skb_pull(skb, sizeof(conn->pcnf)); + + if (conn->hcon->out) { + u8 random[16]; + + swap128(conn->prnd, random); + smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(random), + random); + } else { + struct smp_cmd_pairing_confirm cp; + int ret; + u8 res[16]; + + ret = smp_rand(conn->prnd); + if (ret) + return SMP_UNSPECIFIED; + + ret = smp_c1(tfm, conn->tk, conn->prnd, conn->preq, conn->prsp, + conn->hcon->dst_type, conn->dst, + 0, conn->src, res); + if (ret) + return SMP_CONFIRM_FAILED; + + swap128(res, cp.confirm_val); + + smp_send_cmd(conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp); + } + + mod_timer(&conn->security_timer, jiffies + + msecs_to_jiffies(SMP_TIMEOUT)); + + return 0; +} + +static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct hci_conn *hcon = conn->hcon; + struct crypto_blkcipher *tfm = hcon->hdev->tfm; + int ret; + u8 key[16], res[16], random[16], confirm[16]; + + swap128(skb->data, random); + skb_pull(skb, sizeof(random)); + + if (conn->hcon->out) + ret = smp_c1(tfm, conn->tk, random, conn->preq, conn->prsp, 0, + conn->src, conn->hcon->dst_type, conn->dst, + res); + else + ret = smp_c1(tfm, conn->tk, random, conn->preq, conn->prsp, + conn->hcon->dst_type, conn->dst, 0, conn->src, + res); + if (ret) + return SMP_UNSPECIFIED; + + BT_DBG("conn %p %s", conn, conn->hcon->out ? "master" : "slave"); + + swap128(res, confirm); + + if (memcmp(conn->pcnf, confirm, sizeof(conn->pcnf)) != 0) { + BT_ERR("Pairing failed (confirmation values mismatch)"); + return SMP_CONFIRM_FAILED; + } + + if (conn->hcon->out) { + u8 stk[16], rand[8]; + __le16 ediv; + + memset(rand, 0, sizeof(rand)); + ediv = 0; + + smp_s1(tfm, conn->tk, random, conn->prnd, key); + swap128(key, stk); + + memset(stk + conn->smp_key_size, 0, + SMP_MAX_ENC_KEY_SIZE - conn->smp_key_size); + + hci_le_start_enc(hcon, ediv, rand, stk); + hcon->enc_key_size = conn->smp_key_size; + } else { + u8 stk[16], r[16], rand[8]; + __le16 ediv; + + memset(rand, 0, sizeof(rand)); + ediv = 0; + + swap128(conn->prnd, r); + smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(r), r); + + smp_s1(tfm, conn->tk, conn->prnd, random, key); + swap128(key, stk); + + memset(stk + conn->smp_key_size, 0, + SMP_MAX_ENC_KEY_SIZE - conn->smp_key_size); + + hci_add_ltk(conn->hcon->hdev, 0, conn->dst, conn->smp_key_size, + ediv, rand, stk); + } + + return 0; +} + +static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_security_req *rp = (void *) skb->data; + struct smp_cmd_pairing cp; + struct hci_conn *hcon = conn->hcon; + + BT_DBG("conn %p", conn); + + if (test_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) + return 0; + + skb_pull(skb, sizeof(*rp)); + + memset(&cp, 0, sizeof(cp)); + build_pairing_cmd(conn, &cp, NULL, rp->auth_req); + + conn->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&conn->preq[1], &cp, sizeof(cp)); + + smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + + mod_timer(&conn->security_timer, jiffies + + msecs_to_jiffies(SMP_TIMEOUT)); + + set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend); + + return 0; +} + +int smp_conn_security(struct l2cap_conn *conn, __u8 sec_level) +{ + struct hci_conn *hcon = conn->hcon; + __u8 authreq; + + BT_DBG("conn %p hcon %p level 0x%2.2x", conn, hcon, sec_level); + + if (!lmp_host_le_capable(hcon->hdev)) + return 1; + + if (IS_ERR(hcon->hdev->tfm)) + return 1; + + if (test_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend)) + return 0; + + if (sec_level == BT_SECURITY_LOW) + return 1; + + if (hcon->sec_level >= sec_level) + return 1; + + authreq = seclevel_to_authreq(sec_level); + + if (hcon->link_mode & HCI_LM_MASTER) { + struct smp_cmd_pairing cp; + struct link_key *key; + + key = hci_find_link_key_type(hcon->hdev, conn->dst, + HCI_LK_SMP_LTK); + if (key) { + struct key_master_id *master = (void *) key->data; + + hci_le_start_enc(hcon, master->ediv, master->rand, + key->val); + hcon->enc_key_size = key->pin_len; + + goto done; + } + + build_pairing_cmd(conn, &cp, NULL, authreq); + conn->preq[0] = SMP_CMD_PAIRING_REQ; + memcpy(&conn->preq[1], &cp, sizeof(cp)); + + mod_timer(&conn->security_timer, jiffies + + msecs_to_jiffies(SMP_TIMEOUT)); + + smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp); + } else { + struct smp_cmd_security_req cp; + cp.auth_req = authreq; + smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp); + } + +done: + hcon->pending_sec_level = sec_level; + set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend); + + return 0; +} + +static int smp_cmd_encrypt_info(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_encrypt_info *rp = (void *) skb->data; + + skb_pull(skb, sizeof(*rp)); + + memcpy(conn->tk, rp->ltk, sizeof(conn->tk)); + + return 0; +} + +static int smp_cmd_master_ident(struct l2cap_conn *conn, struct sk_buff *skb) +{ + struct smp_cmd_master_ident *rp = (void *) skb->data; + + skb_pull(skb, sizeof(*rp)); + + hci_add_ltk(conn->hcon->hdev, 1, conn->src, conn->smp_key_size, + rp->ediv, rp->rand, conn->tk); + + smp_distribute_keys(conn, 1); + + return 0; +} + +int smp_sig_channel(struct l2cap_conn *conn, struct sk_buff *skb) +{ + __u8 code = skb->data[0]; + __u8 reason; + int err = 0; + + if (!lmp_host_le_capable(conn->hcon->hdev)) { + err = -ENOTSUPP; + reason = SMP_PAIRING_NOTSUPP; + goto done; + } + + if (IS_ERR(conn->hcon->hdev->tfm)) { + err = PTR_ERR(conn->hcon->hdev->tfm); + reason = SMP_PAIRING_NOTSUPP; + goto done; + } + + skb_pull(skb, sizeof(code)); + + switch (code) { + case SMP_CMD_PAIRING_REQ: + reason = smp_cmd_pairing_req(conn, skb); + break; + + case SMP_CMD_PAIRING_FAIL: + reason = 0; + err = -EPERM; + break; + + case SMP_CMD_PAIRING_RSP: + reason = smp_cmd_pairing_rsp(conn, skb); + break; + + case SMP_CMD_SECURITY_REQ: + reason = smp_cmd_security_req(conn, skb); + break; + + case SMP_CMD_PAIRING_CONFIRM: + reason = smp_cmd_pairing_confirm(conn, skb); + break; + + case SMP_CMD_PAIRING_RANDOM: + reason = smp_cmd_pairing_random(conn, skb); + break; + + case SMP_CMD_ENCRYPT_INFO: + reason = smp_cmd_encrypt_info(conn, skb); + break; + + case SMP_CMD_MASTER_IDENT: + reason = smp_cmd_master_ident(conn, skb); + break; + + case SMP_CMD_IDENT_INFO: + case SMP_CMD_IDENT_ADDR_INFO: + case SMP_CMD_SIGN_INFO: + /* Just ignored */ + reason = 0; + break; + + default: + BT_DBG("Unknown command code 0x%2.2x", code); + + reason = SMP_CMD_NOTSUPP; + err = -EOPNOTSUPP; + goto done; + } + +done: + if (reason) + smp_send_cmd(conn, SMP_CMD_PAIRING_FAIL, sizeof(reason), + &reason); + + kfree_skb(skb); + return err; +} + +int smp_distribute_keys(struct l2cap_conn *conn, __u8 force) +{ + struct smp_cmd_pairing *req, *rsp; + __u8 *keydist; + + BT_DBG("conn %p force %d", conn, force); + + if (IS_ERR(conn->hcon->hdev->tfm)) + return PTR_ERR(conn->hcon->hdev->tfm); + + rsp = (void *) &conn->prsp[1]; + + /* The responder sends its keys first */ + if (!force && conn->hcon->out && (rsp->resp_key_dist & 0x07)) + return 0; + + req = (void *) &conn->preq[1]; + + if (conn->hcon->out) { + keydist = &rsp->init_key_dist; + *keydist &= req->init_key_dist; + } else { + keydist = &rsp->resp_key_dist; + *keydist &= req->resp_key_dist; + } + + + BT_DBG("keydist 0x%x", *keydist); + + if (*keydist & SMP_DIST_ENC_KEY) { + struct smp_cmd_encrypt_info enc; + struct smp_cmd_master_ident ident; + __le16 ediv; + + get_random_bytes(enc.ltk, sizeof(enc.ltk)); + get_random_bytes(&ediv, sizeof(ediv)); + get_random_bytes(ident.rand, sizeof(ident.rand)); + + smp_send_cmd(conn, SMP_CMD_ENCRYPT_INFO, sizeof(enc), &enc); + + hci_add_ltk(conn->hcon->hdev, 1, conn->dst, conn->smp_key_size, + ediv, ident.rand, enc.ltk); + + ident.ediv = cpu_to_le16(ediv); + + smp_send_cmd(conn, SMP_CMD_MASTER_IDENT, sizeof(ident), &ident); + + *keydist &= ~SMP_DIST_ENC_KEY; + } + + if (*keydist & SMP_DIST_ID_KEY) { + struct smp_cmd_ident_addr_info addrinfo; + struct smp_cmd_ident_info idinfo; + + /* Send a dummy key */ + get_random_bytes(idinfo.irk, sizeof(idinfo.irk)); + + smp_send_cmd(conn, SMP_CMD_IDENT_INFO, sizeof(idinfo), &idinfo); + + /* Just public address */ + memset(&addrinfo, 0, sizeof(addrinfo)); + bacpy(&addrinfo.bdaddr, conn->src); + + smp_send_cmd(conn, SMP_CMD_IDENT_ADDR_INFO, sizeof(addrinfo), + &addrinfo); + + *keydist &= ~SMP_DIST_ID_KEY; + } + + if (*keydist & SMP_DIST_SIGN) { + struct smp_cmd_sign_info sign; + + /* Send a dummy key */ + get_random_bytes(sign.csrk, sizeof(sign.csrk)); + + smp_send_cmd(conn, SMP_CMD_SIGN_INFO, sizeof(sign), &sign); + + *keydist &= ~SMP_DIST_SIGN; + } + + return 0; +} diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index a6b2f86378c..32b8f9f7f79 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -49,7 +49,9 @@ netdev_tx_t br_dev_xmit(struct sk_buff *skb, struct net_device *dev) skb_pull(skb, ETH_HLEN); rcu_read_lock(); - if (is_multicast_ether_addr(dest)) { + if (is_broadcast_ether_addr(dest)) + br_flood_deliver(br, skb); + else if (is_multicast_ether_addr(dest)) { if (unlikely(netpoll_tx_running(dev))) { br_flood_deliver(br, skb); goto out; @@ -243,6 +245,7 @@ int br_netpoll_enable(struct net_bridge_port *p) goto out; np->dev = p->dev; + strlcpy(np->dev_name, p->dev->name, IFNAMSIZ); err = __netpoll_setup(np); if (err) { diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c index f3ac1e858ee..f06ee39c73f 100644 --- a/net/bridge/br_input.c +++ b/net/bridge/br_input.c @@ -60,7 +60,7 @@ int br_handle_frame_finish(struct sk_buff *skb) br = p->br; br_fdb_update(br, p, eth_hdr(skb)->h_source); - if (is_multicast_ether_addr(dest) && + if (!is_broadcast_ether_addr(dest) && is_multicast_ether_addr(dest) && br_multicast_rcv(br, p, skb)) goto drop; @@ -77,7 +77,9 @@ int br_handle_frame_finish(struct sk_buff *skb) dst = NULL; - if (is_multicast_ether_addr(dest)) { + if (is_broadcast_ether_addr(dest)) + skb2 = skb; + else if (is_multicast_ether_addr(dest)) { mdst = br_mdb_get(br, skb); if (mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) { if ((mdst && mdst->mglist) || diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 2f14eafdeea..2d85ca7111d 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1379,8 +1379,11 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; - if (iph->protocol != IPPROTO_IGMP) + if (iph->protocol != IPPROTO_IGMP) { + if ((iph->daddr & IGMP_LOCAL_GROUP_MASK) != IGMP_LOCAL_GROUP) + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; return 0; + } len = ntohs(iph->tot_len); if (skb->len < len || len < ip_hdrlen(skb)) @@ -1424,7 +1427,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, switch (ih->type) { case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip4_multicast_add_group(br, port, ih->group); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: @@ -1543,7 +1546,7 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, goto out; } mld = (struct mld_msg *)skb_transport_header(skb2); - BR_INPUT_SKB_CB(skb2)->mrouters_only = 1; + BR_INPUT_SKB_CB(skb)->mrouters_only = 1; err = br_ip6_multicast_add_group(br, port, &mld->mld_mca); break; } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index 3fa123185e8..d6ec3720c77 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -104,10 +104,22 @@ static void fake_update_pmtu(struct dst_entry *dst, u32 mtu) { } +static u32 *fake_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + return NULL; +} + +static struct neighbour *fake_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + return NULL; +} + static struct dst_ops fake_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .update_pmtu = fake_update_pmtu, + .cow_metrics = fake_cow_metrics, + .neigh_lookup = fake_neigh_lookup, }; /* @@ -337,24 +349,26 @@ static int br_nf_pre_routing_finish_ipv6(struct sk_buff *skb) static int br_nf_pre_routing_finish_bridge(struct sk_buff *skb) { struct nf_bridge_info *nf_bridge = skb->nf_bridge; + struct neighbour *neigh; struct dst_entry *dst; skb->dev = bridge_parent(skb->dev); if (!skb->dev) goto free_skb; dst = skb_dst(skb); - if (dst->hh) { - neigh_hh_bridge(dst->hh, skb); + neigh = dst_get_neighbour(dst); + if (neigh->hh.hh_len) { + neigh_hh_bridge(&neigh->hh, skb); skb->dev = nf_bridge->physindev; return br_handle_frame_finish(skb); - } else if (dst->neighbour) { + } else { /* the neighbour function below overwrites the complete * MAC header, so we save the Ethernet source address and * protocol number. */ skb_copy_from_linear_data_offset(skb, -(ETH_HLEN-ETH_ALEN), skb->nf_bridge->data, ETH_HLEN-ETH_ALEN); /* tell br_dev_xmit to continue with forwarding */ nf_bridge->mask |= BRNF_BRIDGED_DNAT; - return dst->neighbour->output(skb); + return neigh->output(neigh, skb); } free_skb: kfree_skb(skb); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ffb0dc4cc0e..6814083a92f 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -218,19 +218,24 @@ int __init br_netlink_init(void) if (err < 0) goto err1; - err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, br_dump_ifinfo); + err = __rtnl_register(PF_BRIDGE, RTM_GETLINK, NULL, + br_dump_ifinfo, NULL); if (err) goto err2; - err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, br_rtm_setlink, NULL); + err = __rtnl_register(PF_BRIDGE, RTM_SETLINK, + br_rtm_setlink, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, br_fdb_add, NULL); + err = __rtnl_register(PF_BRIDGE, RTM_NEWNEIGH, + br_fdb_add, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, br_fdb_delete, NULL); + err = __rtnl_register(PF_BRIDGE, RTM_DELNEIGH, + br_fdb_delete, NULL, NULL); if (err) goto err3; - err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, NULL, br_fdb_dump); + err = __rtnl_register(PF_BRIDGE, RTM_GETNEIGH, + NULL, br_fdb_dump, NULL); if (err) goto err3; diff --git a/net/caif/caif_dev.c b/net/caif/caif_dev.c index 682c0fedf36..7c2fa0a0814 100644 --- a/net/caif/caif_dev.c +++ b/net/caif/caif_dev.c @@ -11,7 +11,6 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ -#include <linux/version.h> #include <linux/kernel.h> #include <linux/if_arp.h> #include <linux/net.h> diff --git a/net/caif/cfmuxl.c b/net/caif/cfmuxl.c index 3a66b8c10e0..c23979e79df 100644 --- a/net/caif/cfmuxl.c +++ b/net/caif/cfmuxl.c @@ -255,7 +255,7 @@ static void cfmuxl_ctrlcmd(struct cflayer *layr, enum caif_ctrlcmd ctrl, if (cfsrvl_phyid_match(layer, phyid) && layer->ctrlcmd) { - if ((ctrl == _CAIF_CTRLCMD_PHYIF_FLOW_OFF_IND || + if ((ctrl == _CAIF_CTRLCMD_PHYIF_DOWN_IND || ctrl == CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND) && layer->id != 0) { diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c index adbb424403d..865690948bb 100644 --- a/net/caif/chnl_net.c +++ b/net/caif/chnl_net.c @@ -7,8 +7,8 @@ #define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__ -#include <linux/version.h> #include <linux/fs.h> +#include <linux/hardirq.h> #include <linux/init.h> #include <linux/module.h> #include <linux/netdevice.h> diff --git a/net/can/af_can.c b/net/can/af_can.c index 094fc5332d4..8ce926d3b2c 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -58,6 +58,7 @@ #include <linux/skbuff.h> #include <linux/can.h> #include <linux/can/core.h> +#include <linux/ratelimit.h> #include <net/net_namespace.h> #include <net/sock.h> @@ -161,8 +162,8 @@ static int can_create(struct net *net, struct socket *sock, int protocol, * return the error code immediately. Below we will * return -EPROTONOSUPPORT */ - if (err && printk_ratelimit()) - printk(KERN_ERR "can: request_module " + if (err) + printk_ratelimited(KERN_ERR "can: request_module " "(can-proto-%d) failed.\n", protocol); cp = can_get_proto(protocol); diff --git a/net/can/bcm.c b/net/can/bcm.c index 184a6572b67..d6c8ae5b2e6 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -43,6 +43,7 @@ #include <linux/module.h> #include <linux/init.h> +#include <linux/interrupt.h> #include <linux/hrtimer.h> #include <linux/list.h> #include <linux/proc_fs.h> diff --git a/net/ceph/ceph_fs.c b/net/ceph/ceph_fs.c index a3a3a31d3c3..41466ccb972 100644 --- a/net/ceph/ceph_fs.c +++ b/net/ceph/ceph_fs.c @@ -36,16 +36,19 @@ int ceph_flags_to_mode(int flags) if ((flags & O_DIRECTORY) == O_DIRECTORY) return CEPH_FILE_MODE_PIN; #endif - if ((flags & O_APPEND) == O_APPEND) - flags |= O_WRONLY; - if ((flags & O_ACCMODE) == O_RDWR) - mode = CEPH_FILE_MODE_RDWR; - else if ((flags & O_ACCMODE) == O_WRONLY) + switch (flags & O_ACCMODE) { + case O_WRONLY: mode = CEPH_FILE_MODE_WR; - else + break; + case O_RDONLY: mode = CEPH_FILE_MODE_RD; - + break; + case O_RDWR: + case O_ACCMODE: /* this is what the VFS does */ + mode = CEPH_FILE_MODE_RDWR; + break; + } #ifdef O_LAZY if (flags & O_LAZY) mode |= CEPH_FILE_MODE_LAZY; diff --git a/net/ceph/crypto.c b/net/ceph/crypto.c index 5a8009c9e0c..85f3bc0a706 100644 --- a/net/ceph/crypto.c +++ b/net/ceph/crypto.c @@ -444,7 +444,7 @@ int ceph_key_instantiate(struct key *key, const void *data, size_t datalen) goto err; /* TODO ceph_crypto_key_decode should really take const input */ - p = (void*)data; + p = (void *)data; ret = ceph_crypto_key_decode(ckey, &p, (char*)data+datalen); if (ret < 0) goto err_ckey; diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 6ea2b892f44..7330c2757c0 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -477,8 +477,9 @@ struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *osdc, calc_layout(osdc, vino, layout, off, plen, req, ops); req->r_file_layout = *layout; /* keep a copy */ - /* in case it differs from natural alignment that calc_layout - filled in for us */ + /* in case it differs from natural (file) alignment that + calc_layout filled in for us */ + req->r_num_pages = calc_pages_for(page_align, *plen); req->r_page_alignment = page_align; ceph_osdc_build_request(req, off, plen, ops, @@ -1144,6 +1145,13 @@ static void handle_osds_timeout(struct work_struct *work) round_jiffies_relative(delay)); } +static void complete_request(struct ceph_osd_request *req) +{ + if (req->r_safe_callback) + req->r_safe_callback(req, NULL); + complete_all(&req->r_safe_completion); /* fsync waiter */ +} + /* * handle osd op reply. either call the callback if it is specified, * or do the completion to wake up the waiting thread. @@ -1226,11 +1234,8 @@ static void handle_reply(struct ceph_osd_client *osdc, struct ceph_msg *msg, else complete_all(&req->r_completion); - if (flags & CEPH_OSD_FLAG_ONDISK) { - if (req->r_safe_callback) - req->r_safe_callback(req, msg); - complete_all(&req->r_safe_completion); /* fsync waiter */ - } + if (flags & CEPH_OSD_FLAG_ONDISK) + complete_request(req); done: dout("req=%p req->r_linger=%d\n", req, req->r_linger); @@ -1732,6 +1737,7 @@ int ceph_osdc_wait_request(struct ceph_osd_client *osdc, __cancel_request(req); __unregister_request(osdc, req); mutex_unlock(&osdc->request_mutex); + complete_request(req); dout("wait_request tid %llu canceled/timed out\n", req->r_tid); return rc; } @@ -2022,8 +2028,9 @@ static struct ceph_msg *get_reply(struct ceph_connection *con, int want = calc_pages_for(req->r_page_alignment, data_len); if (unlikely(req->r_num_pages < want)) { - pr_warning("tid %lld reply %d > expected %d pages\n", - tid, want, m->nr_pages); + pr_warning("tid %lld reply has %d bytes %d pages, we" + " had only %d pages ready\n", tid, data_len, + want, req->r_num_pages); *skip = 1; ceph_msg_put(m); m = NULL; diff --git a/net/core/dev.c b/net/core/dev.c index 939307891e7..9444c5cb413 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -199,6 +199,11 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +static inline void dev_base_seq_inc(struct net *net) +{ + while (++net->dev_base_seq == 0); +} + static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); @@ -237,6 +242,9 @@ static int list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(net); + return 0; } @@ -253,6 +261,8 @@ static void unlist_netdevice(struct net_device *dev) hlist_del_rcu(&dev->name_hlist); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(dev_net(dev)); } /* @@ -2532,7 +2542,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) goto done; ip = (const struct iphdr *) (skb->data + nhoff); - if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip)) ip_proto = 0; else ip_proto = ip->protocol; @@ -3114,7 +3124,7 @@ static int __netif_receive_skb(struct sk_buff *skb) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + skb_reset_mac_len(skb); pt_prev = NULL; @@ -5199,7 +5209,7 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } -u32 netdev_fix_features(struct net_device *dev, u32 features) +static u32 netdev_fix_features(struct net_device *dev, u32 features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && @@ -5258,7 +5268,6 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) return features; } -EXPORT_SYMBOL(netdev_fix_features); int __netdev_update_features(struct net_device *dev) { @@ -5478,11 +5487,9 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_NOCACHE_COPY; } - /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, - * vlan_dev_init() will do the dev->features check, so these features - * are enabled only if supported by underlying device. + /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ - dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + dev->vlan_features |= NETIF_F_HIGHDMA; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); @@ -5867,8 +5874,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_MAX_SIZE; - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); - dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); @@ -5932,9 +5937,6 @@ void free_netdev(struct net_device *dev) /* Flush device addresses */ dev_addr_flush(dev); - /* Clear ethtool n-tuple list */ - ethtool_ntuple_flush(dev); - list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); @@ -6178,6 +6180,11 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } + /* Append NAPI poll list from offline CPU. */ + if (!list_empty(&oldsd->poll_list)) { + list_splice_init(&oldsd->poll_list, &sd->poll_list); + raise_softirq_irqoff(NET_RX_SOFTIRQ); + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); @@ -6264,29 +6271,23 @@ err_name: /** * netdev_drivername - network driver for the device * @dev: network device - * @buffer: buffer for resulting name - * @len: size of buffer * * Determine network driver for device. */ -char *netdev_drivername(const struct net_device *dev, char *buffer, int len) +const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; - - if (len <= 0 || !buffer) - return buffer; - buffer[0] = 0; + const char *empty = ""; parent = dev->dev.parent; - if (!parent) - return buffer; + return empty; driver = parent->driver; if (driver && driver->name) - strlcpy(buffer, driver->name, len); - return buffer; + return driver->name; + return empty; } static int __netdev_printk(const char *level, const struct net_device *dev, diff --git a/net/core/dst.c b/net/core/dst.c index 9ccca038444..14b33baf073 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -171,8 +171,7 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst_init_metrics(dst, dst_default_metrics, true); dst->expires = 0UL; dst->path = dst; - dst->neighbour = NULL; - dst->hh = NULL; + dst->_neighbour = NULL; #ifdef CONFIG_XFRM dst->xfrm = NULL; #endif @@ -190,7 +189,8 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, dst->lastuse = jiffies; dst->flags = flags; dst->next = NULL; - dst_entries_add(ops, 1); + if (!(flags & DST_NOCOUNT)) + dst_entries_add(ops, 1); return dst; } EXPORT_SYMBOL(dst_alloc); @@ -225,25 +225,20 @@ struct dst_entry *dst_destroy(struct dst_entry * dst) { struct dst_entry *child; struct neighbour *neigh; - struct hh_cache *hh; smp_rmb(); again: - neigh = dst->neighbour; - hh = dst->hh; + neigh = dst->_neighbour; child = dst->child; - dst->hh = NULL; - if (hh) - hh_cache_put(hh); - if (neigh) { - dst->neighbour = NULL; + dst->_neighbour = NULL; neigh_release(neigh); } - dst_entries_add(dst->ops, -1); + if (!(dst->flags & DST_NOCOUNT)) + dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); @@ -368,8 +363,8 @@ static void dst_ifdown(struct dst_entry *dst, struct net_device *dev, dst->dev = dev_net(dst->dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); - if (dst->neighbour && dst->neighbour->dev == dev) { - dst->neighbour->dev = dst->dev; + if (dst->_neighbour && dst->_neighbour->dev == dev) { + dst->_neighbour->dev = dst->dev; dev_hold(dst->dev); dev_put(dev); } diff --git a/net/core/ethtool.c b/net/core/ethtool.c index fd14116ad7f..6cdba5fc2be 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -169,18 +169,6 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) } EXPORT_SYMBOL(ethtool_op_set_flags); -void ethtool_ntuple_flush(struct net_device *dev) -{ - struct ethtool_rx_ntuple_flow_spec_container *fsc, *f; - - list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) { - list_del(&fsc->list); - kfree(fsc); - } - dev->ethtool_ntuple_list.count = 0; -} -EXPORT_SYMBOL(ethtool_ntuple_flush); - /* Handlers for each ethtool command */ #define ETHTOOL_DEV_FEATURE_WORDS 1 @@ -865,34 +853,6 @@ out: return ret; } -static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, - struct ethtool_rx_ntuple_flow_spec *spec, - struct ethtool_rx_ntuple_flow_spec_container *fsc) -{ - - /* don't add filters forever */ - if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) { - /* free the container */ - kfree(fsc); - return; - } - - /* Copy the whole filter over */ - fsc->fs.flow_type = spec->flow_type; - memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u)); - memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u)); - - fsc->fs.vlan_tag = spec->vlan_tag; - fsc->fs.vlan_tag_mask = spec->vlan_tag_mask; - fsc->fs.data = spec->data; - fsc->fs.data_mask = spec->data_mask; - fsc->fs.action = spec->action; - - /* add to the list */ - list_add_tail_rcu(&fsc->list, &list->list); - list->count++; -} - /* * ethtool does not (or did not) set masks for flow parameters that are * not specified, so if both value and mask are 0 then this must be @@ -930,8 +890,6 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, { struct ethtool_rx_ntuple cmd; const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL; - int ret; if (!ops->set_rx_ntuple) return -EOPNOTSUPP; @@ -944,269 +902,7 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, rx_ntuple_fix_masks(&cmd.fs); - /* - * Cache filter in dev struct for GET operation only if - * the underlying driver doesn't have its own GET operation, and - * only if the filter was added successfully. First make sure we - * can allocate the filter, then continue if successful. - */ - if (!ops->get_rx_ntuple) { - fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC); - if (!fsc) - return -ENOMEM; - } - - ret = ops->set_rx_ntuple(dev, &cmd); - if (ret) { - kfree(fsc); - return ret; - } - - if (!ops->get_rx_ntuple) - __rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs, fsc); - - return ret; -} - -static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) -{ - struct ethtool_gstrings gstrings; - const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_rx_ntuple_flow_spec_container *fsc; - u8 *data; - char *p; - int ret, i, num_strings = 0; - - if (!ops->get_sset_count) - return -EOPNOTSUPP; - - if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) - return -EFAULT; - - ret = ops->get_sset_count(dev, gstrings.string_set); - if (ret < 0) - return ret; - - gstrings.len = ret; - - data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); - if (!data) - return -ENOMEM; - - if (ops->get_rx_ntuple) { - /* driver-specific filter grab */ - ret = ops->get_rx_ntuple(dev, gstrings.string_set, data); - goto copy; - } - - /* default ethtool filter grab */ - i = 0; - p = (char *)data; - list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) { - sprintf(p, "Filter %d:\n", i); - p += ETH_GSTRING_LEN; - num_strings++; - - switch (fsc->fs.flow_type) { - case TCP_V4_FLOW: - sprintf(p, "\tFlow Type: TCP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case UDP_V4_FLOW: - sprintf(p, "\tFlow Type: UDP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case SCTP_V4_FLOW: - sprintf(p, "\tFlow Type: SCTP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case AH_ESP_V4_FLOW: - sprintf(p, "\tFlow Type: AH ESP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case ESP_V4_FLOW: - sprintf(p, "\tFlow Type: ESP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IP_USER_FLOW: - sprintf(p, "\tFlow Type: Raw IP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IPV4_FLOW: - sprintf(p, "\tFlow Type: IPv4\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - default: - sprintf(p, "\tFlow Type: Unknown\n"); - p += ETH_GSTRING_LEN; - num_strings++; - goto unknown_filter; - } - - /* now the rest of the filters */ - switch (fsc->fs.flow_type) { - case TCP_V4_FLOW: - case UDP_V4_FLOW: - case SCTP_V4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.psrc, - fsc->fs.m_u.tcp_ip4_spec.psrc); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.pdst, - fsc->fs.m_u.tcp_ip4_spec.pdst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.tos, - fsc->fs.m_u.tcp_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case AH_ESP_V4_FLOW: - case ESP_V4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSPI: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.spi, - fsc->fs.m_u.ah_ip4_spec.spi); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.tos, - fsc->fs.m_u.ah_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IP_USER_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IPV4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, - fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.tos, - fsc->fs.m_u.usr_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tIP Version: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip_ver, - fsc->fs.m_u.usr_ip4_spec.ip_ver); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tProtocol: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.proto, - fsc->fs.m_u.usr_ip4_spec.proto); - p += ETH_GSTRING_LEN; - num_strings++; - break; - } - sprintf(p, "\tVLAN: %d, mask: 0x%x\n", - fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask); - p += ETH_GSTRING_LEN; - num_strings++; - if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) - sprintf(p, "\tAction: Drop\n"); - else - sprintf(p, "\tAction: Direct to queue %d\n", - fsc->fs.action); - p += ETH_GSTRING_LEN; - num_strings++; -unknown_filter: - i++; - } -copy: - /* indicate to userspace how many strings we actually have */ - gstrings.len = num_strings; - ret = -EFAULT; - if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) - goto out; - useraddr += sizeof(gstrings); - if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) - goto out; - ret = 0; - -out: - kfree(data); - return ret; + return ops->set_rx_ntuple(dev, &cmd); } static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) @@ -1227,7 +923,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) regs.len = reglen; regbuf = vzalloc(reglen); - if (!regbuf) + if (reglen && !regbuf) return -ENOMEM; ops->get_regs(dev, ®s, regbuf); @@ -1236,7 +932,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (copy_to_user(useraddr, ®s, sizeof(regs))) goto out; useraddr += offsetof(struct ethtool_regs, data); - if (copy_to_user(useraddr, regbuf, regs.len)) + if (regbuf && copy_to_user(useraddr, regbuf, regs.len)) goto out; ret = 0; @@ -2101,9 +1797,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXNTUPLE: rc = ethtool_set_rx_ntuple(dev, useraddr); break; - case ETHTOOL_GRXNTUPLE: - rc = ethtool_get_rx_ntuple(dev, useraddr); - break; case ETHTOOL_GSSET_INFO: rc = ethtool_get_sset_info(dev, useraddr); break; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 008dc70b064..e7ab0c0285b 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -740,9 +740,9 @@ static struct pernet_operations fib_rules_net_ops = { static int __init fib_rules_init(void) { int err; - rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL); - rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL); - rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule); + rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL); err = register_pernet_subsys(&fib_rules_net_ops); if (err < 0) diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 799f06e03a2..8fab9b0bb20 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,7 +98,7 @@ static const struct file_operations neigh_stat_seq_fops; static DEFINE_RWLOCK(neigh_tbl_lock); -static int neigh_blackhole(struct sk_buff *skb) +static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) { kfree_skb(skb); return -ENETDOWN; @@ -137,7 +137,7 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock_bh(&tbl->lock); nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - for (i = 0; i <= nht->hash_mask; i++) { + for (i = 0; i < (1 << nht->hash_shift); i++) { struct neighbour *n; struct neighbour __rcu **np; @@ -210,7 +210,7 @@ static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - for (i = 0; i <= nht->hash_mask; i++) { + for (i = 0; i < (1 << nht->hash_shift); i++) { struct neighbour *n; struct neighbour __rcu **np = &nht->hash_buckets[i]; @@ -297,6 +297,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl) n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; + seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); setup_timer(&n->timer, neigh_timer_handler, (unsigned long)n); @@ -312,9 +313,9 @@ out_entries: goto out; } -static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) +static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift) { - size_t size = entries * sizeof(struct neighbour *); + size_t size = (1 << shift) * sizeof(struct neighbour *); struct neigh_hash_table *ret; struct neighbour __rcu **buckets; @@ -332,8 +333,9 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) return NULL; } ret->hash_buckets = buckets; - ret->hash_mask = entries - 1; + ret->hash_shift = shift; get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); + ret->hash_rnd |= 1; return ret; } @@ -342,7 +344,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table *nht = container_of(head, struct neigh_hash_table, rcu); - size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *); + size_t size = (1 << nht->hash_shift) * sizeof(struct neighbour *); struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) @@ -353,21 +355,20 @@ static void neigh_hash_free_rcu(struct rcu_head *head) } static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, - unsigned long new_entries) + unsigned long new_shift) { unsigned int i, hash; struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); - BUG_ON(!is_power_of_2(new_entries)); old_nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - new_nht = neigh_hash_alloc(new_entries); + new_nht = neigh_hash_alloc(new_shift); if (!new_nht) return old_nht; - for (i = 0; i <= old_nht->hash_mask; i++) { + for (i = 0; i < (1 << old_nht->hash_shift); i++) { struct neighbour *n, *next; for (n = rcu_dereference_protected(old_nht->hash_buckets[i], @@ -377,7 +378,7 @@ static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, hash = tbl->hash(n->primary_key, n->dev, new_nht->hash_rnd); - hash &= new_nht->hash_mask; + hash >>= (32 - new_nht->hash_shift); next = rcu_dereference_protected(n->next, lockdep_is_held(&tbl->lock)); @@ -406,7 +407,7 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; @@ -436,7 +437,7 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) & nht->hash_mask; + hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) >> (32 - nht->hash_shift); for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); n != NULL; @@ -492,10 +493,10 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) > (nht->hash_mask + 1)) - nht = neigh_hash_grow(tbl, (nht->hash_mask + 1) << 1); + if (atomic_read(&tbl->entries) > (1 << nht->hash_shift)) + nht = neigh_hash_grow(tbl, nht->hash_shift + 1); - hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) >> (32 - nht->hash_shift); if (n->parms->dead) { rc = ERR_PTR(-EINVAL); @@ -688,8 +689,6 @@ static void neigh_destroy_rcu(struct rcu_head *head) */ void neigh_destroy(struct neighbour *neigh) { - struct hh_cache *hh; - NEIGH_CACHE_STAT_INC(neigh->tbl, destroys); if (!neigh->dead) { @@ -702,16 +701,6 @@ void neigh_destroy(struct neighbour *neigh) if (neigh_del_timer(neigh)) printk(KERN_WARNING "Impossible event.\n"); - while ((hh = neigh->hh) != NULL) { - neigh->hh = hh->hh_next; - hh->hh_next = NULL; - - write_seqlock_bh(&hh->hh_lock); - hh->hh_output = neigh_blackhole; - write_sequnlock_bh(&hh->hh_lock); - hh_cache_put(hh); - } - skb_queue_purge(&neigh->arp_queue); dev_put(neigh->dev); @@ -731,14 +720,9 @@ EXPORT_SYMBOL(neigh_destroy); */ static void neigh_suspect(struct neighbour *neigh) { - struct hh_cache *hh; - NEIGH_PRINTK2("neigh %p is suspected.\n", neigh); neigh->output = neigh->ops->output; - - for (hh = neigh->hh; hh; hh = hh->hh_next) - hh->hh_output = neigh->ops->output; } /* Neighbour state is OK; @@ -748,14 +732,9 @@ static void neigh_suspect(struct neighbour *neigh) */ static void neigh_connect(struct neighbour *neigh) { - struct hh_cache *hh; - NEIGH_PRINTK2("neigh %p is connected.\n", neigh); neigh->output = neigh->ops->connected_output; - - for (hh = neigh->hh; hh; hh = hh->hh_next) - hh->hh_output = neigh->ops->hh_output; } static void neigh_periodic_work(struct work_struct *work) @@ -784,7 +763,7 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(p->base_reachable_time); } - for (i = 0 ; i <= nht->hash_mask; i++) { + for (i = 0 ; i < (1 << nht->hash_shift); i++) { np = &nht->hash_buckets[i]; while ((n = rcu_dereference_protected(*np, @@ -1015,7 +994,7 @@ out_unlock_bh: } EXPORT_SYMBOL(__neigh_event_send); -static void neigh_update_hhs(const struct neighbour *neigh) +static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) @@ -1025,7 +1004,8 @@ static void neigh_update_hhs(const struct neighbour *neigh) update = neigh->dev->header_ops->cache_update; if (update) { - for (hh = neigh->hh; hh; hh = hh->hh_next) { + hh = &neigh->hh; + if (hh->hh_len) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); @@ -1173,12 +1153,13 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, while (neigh->nud_state & NUD_VALID && (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - struct neighbour *n1 = neigh; + struct dst_entry *dst = skb_dst(skb); + struct neighbour *n2, *n1 = neigh; write_unlock_bh(&neigh->lock); /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb_dst(skb) && skb_dst(skb)->neighbour) - n1 = skb_dst(skb)->neighbour; - n1->output(skb); + if (dst && (n2 = dst_get_neighbour(dst)) != NULL) + n1 = n2; + n1->output(n1, skb); write_lock_bh(&neigh->lock); } skb_queue_purge(&neigh->arp_queue); @@ -1211,67 +1192,21 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, } EXPORT_SYMBOL(neigh_event_ns); -static inline bool neigh_hh_lookup(struct neighbour *n, struct dst_entry *dst, - __be16 protocol) -{ - struct hh_cache *hh; - - smp_rmb(); /* paired with smp_wmb() in neigh_hh_init() */ - for (hh = n->hh; hh; hh = hh->hh_next) { - if (hh->hh_type == protocol) { - atomic_inc(&hh->hh_refcnt); - if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) - hh_cache_put(hh); - return true; - } - } - return false; -} - /* called with read_lock_bh(&n->lock); */ -static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, - __be16 protocol) +static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst) { - struct hh_cache *hh; struct net_device *dev = dst->dev; - - if (likely(neigh_hh_lookup(n, dst, protocol))) - return; - - /* slow path */ - hh = kzalloc(sizeof(*hh), GFP_ATOMIC); - if (!hh) - return; - - seqlock_init(&hh->hh_lock); - hh->hh_type = protocol; - atomic_set(&hh->hh_refcnt, 2); - - if (dev->header_ops->cache(n, hh)) { - kfree(hh); - return; - } + __be16 prot = dst->ops->protocol; + struct hh_cache *hh = &n->hh; write_lock_bh(&n->lock); - /* must check if another thread already did the insert */ - if (neigh_hh_lookup(n, dst, protocol)) { - kfree(hh); - goto end; - } - - if (n->nud_state & NUD_CONNECTED) - hh->hh_output = n->ops->hh_output; - else - hh->hh_output = n->ops->output; - - hh->hh_next = n->hh; - smp_wmb(); /* paired with smp_rmb() in neigh_hh_lookup() */ - n->hh = hh; + /* Only one thread can come in here and initialize the + * hh_cache entry. + */ + if (!hh->hh_len) + dev->header_ops->cache(n, hh, prot); - if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) - hh_cache_put(hh); -end: write_unlock_bh(&n->lock); } @@ -1280,7 +1215,7 @@ end: * but resolution is not made yet. */ -int neigh_compat_output(struct sk_buff *skb) +int neigh_compat_output(struct neighbour *neigh, struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -1297,13 +1232,12 @@ EXPORT_SYMBOL(neigh_compat_output); /* Slow and careful. */ -int neigh_resolve_output(struct sk_buff *skb) +int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh; int rc = 0; - if (!dst || !(neigh = dst->neighbour)) + if (!dst) goto discard; __skb_pull(skb, skb_network_offset(skb)); @@ -1313,10 +1247,8 @@ int neigh_resolve_output(struct sk_buff *skb) struct net_device *dev = neigh->dev; unsigned int seq; - if (dev->header_ops->cache && - !dst->hh && - !(dst->flags & DST_NOCACHE)) - neigh_hh_init(neigh, dst, dst->ops->protocol); + if (dev->header_ops->cache && !neigh->hh.hh_len) + neigh_hh_init(neigh, dst); do { seq = read_seqbegin(&neigh->ha_lock); @@ -1325,7 +1257,7 @@ int neigh_resolve_output(struct sk_buff *skb) } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) - rc = neigh->ops->queue_xmit(skb); + rc = dev_queue_xmit(skb); else goto out_kfree_skb; } @@ -1333,7 +1265,7 @@ out: return rc; discard: NEIGH_PRINTK1("neigh_resolve_output: dst=%p neigh=%p\n", - dst, dst ? dst->neighbour : NULL); + dst, neigh); out_kfree_skb: rc = -EINVAL; kfree_skb(skb); @@ -1343,13 +1275,11 @@ EXPORT_SYMBOL(neigh_resolve_output); /* As fast as possible without hh cache */ -int neigh_connected_output(struct sk_buff *skb) +int neigh_connected_output(struct neighbour *neigh, struct sk_buff *skb) { - int err; - struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; unsigned int seq; + int err; __skb_pull(skb, skb_network_offset(skb)); @@ -1360,7 +1290,7 @@ int neigh_connected_output(struct sk_buff *skb) } while (read_seqretry(&neigh->ha_lock, seq)); if (err >= 0) - err = neigh->ops->queue_xmit(skb); + err = dev_queue_xmit(skb); else { err = -EINVAL; kfree_skb(skb); @@ -1369,6 +1299,12 @@ int neigh_connected_output(struct sk_buff *skb) } EXPORT_SYMBOL(neigh_connected_output); +int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) +{ + return dev_queue_xmit(skb); +} +EXPORT_SYMBOL(neigh_direct_output); + static void neigh_proxy_process(unsigned long arg) { struct neigh_table *tbl = (struct neigh_table *)arg; @@ -1540,7 +1476,7 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot create neighbour proc dir entry"); #endif - RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(8)); + RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(3)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); @@ -1857,7 +1793,7 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); ndc.ndtc_hash_rnd = nht->hash_rnd; - ndc.ndtc_hash_mask = nht->hash_mask; + ndc.ndtc_hash_mask = ((1 << nht->hash_shift) - 1); rcu_read_unlock_bh(); NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); @@ -2200,7 +2136,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, rcu_read_lock_bh(); nht = rcu_dereference_bh(tbl->nht); - for (h = 0; h <= nht->hash_mask; h++) { + for (h = 0; h < (1 << nht->hash_shift); h++) { if (h < s_h) continue; if (h > s_h) @@ -2264,7 +2200,7 @@ void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void nht = rcu_dereference_bh(tbl->nht); read_lock(&tbl->lock); /* avoid resizes */ - for (chain = 0; chain <= nht->hash_mask; chain++) { + for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; for (n = rcu_dereference_bh(nht->hash_buckets[chain]); @@ -2286,7 +2222,7 @@ void __neigh_for_each_release(struct neigh_table *tbl, nht = rcu_dereference_protected(tbl->nht, lockdep_is_held(&tbl->lock)); - for (chain = 0; chain <= nht->hash_mask; chain++) { + for (chain = 0; chain < (1 << nht->hash_shift); chain++) { struct neighbour *n; struct neighbour __rcu **np; @@ -2323,7 +2259,7 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) int bucket = state->bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; - for (bucket = 0; bucket <= nht->hash_mask; bucket++) { + for (bucket = 0; bucket < (1 << nht->hash_shift); bucket++) { n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { @@ -2390,7 +2326,7 @@ next: if (n) break; - if (++state->bucket > nht->hash_mask) + if (++state->bucket >= (1 << nht->hash_shift)) break; n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); @@ -2909,12 +2845,13 @@ EXPORT_SYMBOL(neigh_sysctl_unregister); static int __init neigh_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL); - rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info); + rtnl_register(PF_UNSPEC, RTM_NEWNEIGH, neigh_add, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELNEIGH, neigh_delete, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGH, NULL, neigh_dump_info, NULL); - rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info); - rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL); + rtnl_register(PF_UNSPEC, RTM_GETNEIGHTBL, NULL, neightbl_dump_info, + NULL); + rtnl_register(PF_UNSPEC, RTM_SETNEIGHTBL, neightbl_set, NULL, NULL); return 0; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 11b98bc2aa8..1683e5db2f2 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -100,7 +100,6 @@ NETDEVICE_SHOW(addr_assign_type, fmt_dec); NETDEVICE_SHOW(addr_len, fmt_dec); NETDEVICE_SHOW(iflink, fmt_dec); NETDEVICE_SHOW(ifindex, fmt_dec); -NETDEVICE_SHOW(features, fmt_hex); NETDEVICE_SHOW(type, fmt_dec); NETDEVICE_SHOW(link_mode, fmt_dec); @@ -312,7 +311,6 @@ static struct device_attribute net_class_attributes[] = { __ATTR(ifalias, S_IRUGO | S_IWUSR, show_ifalias, store_ifalias), __ATTR(iflink, S_IRUGO, show_iflink, NULL), __ATTR(ifindex, S_IRUGO, show_ifindex, NULL), - __ATTR(features, S_IRUGO, show_features, NULL), __ATTR(type, S_IRUGO, show_type, NULL), __ATTR(link_mode, S_IRUGO, show_link_mode, NULL), __ATTR(address, S_IRUGO, show_address, NULL), @@ -1179,9 +1177,14 @@ static void remove_queue_kobjects(struct net_device *net) #endif } -static const void *net_current_ns(void) +static void *net_grab_current_ns(void) { - return current->nsproxy->net_ns; + struct net *ns = current->nsproxy->net_ns; +#ifdef CONFIG_NET_NS + if (ns) + atomic_inc(&ns->passive); +#endif + return ns; } static const void *net_initial_ns(void) @@ -1196,22 +1199,13 @@ static const void *net_netlink_ns(struct sock *sk) struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, - .current_ns = net_current_ns, + .grab_current_ns = net_grab_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, + .drop_ns = net_drop_ns, }; EXPORT_SYMBOL_GPL(net_ns_type_operations); -static void net_kobj_ns_exit(struct net *net) -{ - kobj_ns_exit(KOBJ_NS_TYPE_NET, net); -} - -static struct pernet_operations kobj_net_ops = { - .exit = net_kobj_ns_exit, -}; - - #ifdef CONFIG_HOTPLUG static int netdev_uevent(struct device *d, struct kobj_uevent_env *env) { @@ -1339,6 +1333,5 @@ EXPORT_SYMBOL(netdev_class_remove_file); int netdev_kobject_init(void) { kobj_ns_type_register(&net_ns_type_operations); - register_pernet_subsys(&kobj_net_ops); return class_register(&net_class); } diff --git a/net/core/net-traces.c b/net/core/net-traces.c index 7f1bb2aba03..52380b1d552 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -28,6 +28,8 @@ #include <trace/events/skb.h> #include <trace/events/net.h> #include <trace/events/napi.h> +#include <trace/events/sock.h> +#include <trace/events/udp.h> EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 6c6b86d0da1..5bbdbf0d366 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -128,6 +128,8 @@ static __net_init int setup_net(struct net *net) LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); + atomic_set(&net->passive, 1); + net->dev_base_seq = 1; #ifdef NETNS_REFCNT_DEBUG atomic_set(&net->use_count, 0); @@ -210,6 +212,13 @@ static void net_free(struct net *net) kmem_cache_free(net_cachep, net); } +void net_drop_ns(void *p) +{ + struct net *ns = p; + if (ns && atomic_dec_and_test(&ns->passive)) + net_free(ns); +} + struct net *copy_net_ns(unsigned long flags, struct net *old_net) { struct net *net; @@ -230,7 +239,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) } mutex_unlock(&net_mutex); if (rv < 0) { - net_free(net); + net_drop_ns(net); return ERR_PTR(rv); } return net; @@ -286,7 +295,7 @@ static void cleanup_net(struct work_struct *work) /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); - net_free(net); + net_drop_ns(net); } } static DECLARE_WORK(net_cleanup_work, cleanup_net); @@ -310,19 +319,17 @@ struct net *get_net_ns_by_fd(int fd) struct file *file; struct net *net; - net = ERR_PTR(-EINVAL); file = proc_ns_fget(fd); - if (!file) - goto out; + if (IS_ERR(file)) + return ERR_CAST(file); ei = PROC_I(file->f_dentry->d_inode); - if (ei->ns_ops != &netns_operations) - goto out; + if (ei->ns_ops == &netns_operations) + net = get_net(ei->ns); + else + net = ERR_PTR(-EINVAL); - net = get_net(ei->ns); -out: - if (file) - fput(file); + fput(file); return net; } diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2d7d6d47378..adf84dd8c7b 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -177,7 +177,7 @@ static void service_arp_queue(struct netpoll_info *npi) } } -void netpoll_poll_dev(struct net_device *dev) +static void netpoll_poll_dev(struct net_device *dev) { const struct net_device_ops *ops; @@ -208,13 +208,6 @@ void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } -EXPORT_SYMBOL(netpoll_poll_dev); - -void netpoll_poll(struct netpoll *np) -{ - netpoll_poll_dev(np->dev); -} -EXPORT_SYMBOL(netpoll_poll); static void refill_skbs(void) { @@ -275,7 +268,7 @@ repeat: if (!skb) { if (++count < 10) { - netpoll_poll(np); + netpoll_poll_dev(np->dev); goto repeat; } return NULL; @@ -336,7 +329,7 @@ void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, } /* tickle device maybe there is some cleanup */ - netpoll_poll(np); + netpoll_poll_dev(np->dev); udelay(USEC_PER_POLL); } @@ -792,6 +785,13 @@ int netpoll_setup(struct netpoll *np) return -ENODEV; } + if (ndev->master) { + printk(KERN_ERR "%s: %s is a slave device, aborting.\n", + np->name, np->dev_name); + err = -EBUSY; + goto put; + } + if (!netif_running(ndev)) { unsigned long atmost, atleast; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index abd936d8a71..99d9e953fe3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -56,9 +56,11 @@ struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; }; static DEFINE_MUTEX(rtnl_mutex); +static u16 min_ifinfo_dump_size; void rtnl_lock(void) { @@ -144,12 +146,28 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) return tab ? tab[msgindex].dumpit : NULL; } +static rtnl_calcit_func rtnl_get_calcit(int protocol, int msgindex) +{ + struct rtnl_link *tab; + + if (protocol <= RTNL_FAMILY_MAX) + tab = rtnl_msg_handlers[protocol]; + else + tab = NULL; + + if (tab == NULL || tab[msgindex].calcit == NULL) + tab = rtnl_msg_handlers[PF_UNSPEC]; + + return tab ? tab[msgindex].calcit : NULL; +} + /** * __rtnl_register - Register a rtnetlink message type * @protocol: Protocol family or PF_UNSPEC * @msgtype: rtnetlink message type * @doit: Function pointer called for each request message * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @calcit: Function pointer to calc size of dump message * * Registers the specified function pointers (at least one of them has * to be non-NULL) to be called whenever a request message for the @@ -162,7 +180,8 @@ static rtnl_dumpit_func rtnl_get_dumpit(int protocol, int msgindex) * Returns 0 on success or a negative error code. */ int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit) + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) { struct rtnl_link *tab; int msgindex; @@ -185,6 +204,9 @@ int __rtnl_register(int protocol, int msgtype, if (dumpit) tab[msgindex].dumpit = dumpit; + if (calcit) + tab[msgindex].calcit = calcit; + return 0; } EXPORT_SYMBOL_GPL(__rtnl_register); @@ -199,9 +221,10 @@ EXPORT_SYMBOL_GPL(__rtnl_register); * of memory implies no sense in continuing. */ void rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit) + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + rtnl_calcit_func calcit) { - if (__rtnl_register(protocol, msgtype, doit, dumpit) < 0) + if (__rtnl_register(protocol, msgtype, doit, dumpit, calcit) < 0) panic("Unable to register rtnetlink message handler, " "protocol = %d, message type = %d\n", protocol, msgtype); @@ -1009,6 +1032,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) s_idx = cb->args[1]; rcu_read_lock(); + cb->seq = net->dev_base_seq; + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -1020,6 +1045,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) goto out; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } @@ -1818,6 +1845,11 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) return err; } +static u16 rtnl_calcit(struct sk_buff *skb) +{ + return min_ifinfo_dump_size; +} + static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; @@ -1847,11 +1879,14 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) struct net *net = dev_net(dev); struct sk_buff *skb; int err = -ENOBUFS; + size_t if_info_size; - skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); + skb = nlmsg_new((if_info_size = if_nlmsg_size(dev)), GFP_KERNEL); if (skb == NULL) goto errout; + min_ifinfo_dump_size = max_t(u16, if_info_size, min_ifinfo_dump_size); + err = rtnl_fill_ifinfo(skb, dev, type, 0, 0, change, 0); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ @@ -1902,14 +1937,20 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; + rtnl_calcit_func calcit; + u16 min_dump_alloc = 0; dumpit = rtnl_get_dumpit(family, type); if (dumpit == NULL) return -EOPNOTSUPP; + calcit = rtnl_get_calcit(family, type); + if (calcit) + min_dump_alloc = calcit(skb); __rtnl_unlock(); rtnl = net->rtnl; - err = netlink_dump_start(rtnl, skb, nlh, dumpit, NULL); + err = netlink_dump_start(rtnl, skb, nlh, dumpit, + NULL, min_dump_alloc); rtnl_lock(); return err; } @@ -2019,12 +2060,13 @@ void __init rtnetlink_init(void) netlink_set_nonroot(NETLINK_ROUTE, NL_NONROOT_RECV); register_netdevice_notifier(&rtnetlink_dev_notifier); - rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo); - rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL); - rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL); - rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL); + rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, + rtnl_dump_ifinfo, rtnl_calcit); + rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL, NULL); - rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all); - rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all); + rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all, NULL); + rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all, NULL); } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 46cbd28f40f..2beda824636 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -329,6 +329,18 @@ static void skb_release_data(struct sk_buff *skb) put_page(skb_shinfo(skb)->frags[i].page); } + /* + * If skb buf is from userspace, we need to notify the caller + * the lower device DMA has done; + */ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + struct ubuf_info *uarg; + + uarg = skb_shinfo(skb)->destructor_arg; + if (uarg->callback) + uarg->callback(uarg); + } + if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); @@ -481,6 +493,9 @@ bool skb_recycle_check(struct sk_buff *skb, int skb_size) if (irqs_disabled()) return false; + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) + return false; + if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE) return false; @@ -596,6 +611,51 @@ struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src) } EXPORT_SYMBOL_GPL(skb_morph); +/* skb frags copy userspace buffers to kernel */ +static int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask) +{ + int i; + int num_frags = skb_shinfo(skb)->nr_frags; + struct page *page, *head = NULL; + struct ubuf_info *uarg = skb_shinfo(skb)->destructor_arg; + + for (i = 0; i < num_frags; i++) { + u8 *vaddr; + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; + + page = alloc_page(GFP_ATOMIC); + if (!page) { + while (head) { + struct page *next = (struct page *)head->private; + put_page(head); + head = next; + } + return -ENOMEM; + } + vaddr = kmap_skb_frag(&skb_shinfo(skb)->frags[i]); + memcpy(page_address(page), + vaddr + f->page_offset, f->size); + kunmap_skb_frag(vaddr); + page->private = (unsigned long)head; + head = page; + } + + /* skb frags release userspace buffers */ + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + put_page(skb_shinfo(skb)->frags[i].page); + + uarg->callback(uarg); + + /* skb frags point to kernel buffers */ + for (i = skb_shinfo(skb)->nr_frags; i > 0; i--) { + skb_shinfo(skb)->frags[i - 1].page_offset = 0; + skb_shinfo(skb)->frags[i - 1].page = head; + head = (struct page *)head->private; + } + return 0; +} + + /** * skb_clone - duplicate an sk_buff * @skb: buffer to clone @@ -614,6 +674,12 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask) { struct sk_buff *n; + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, gfp_mask)) + return NULL; + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + } + n = skb + 1; if (skb->fclone == SKB_FCLONE_ORIG && n->fclone == SKB_FCLONE_UNAVAILABLE) { @@ -731,6 +797,14 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) if (skb_shinfo(skb)->nr_frags) { int i; + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, gfp_mask)) { + kfree_skb(n); + n = NULL; + goto out; + } + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_shinfo(n)->frags[i] = skb_shinfo(skb)->frags[i]; get_page(skb_shinfo(n)->frags[i].page); @@ -788,7 +862,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, fastpath = true; else { int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; - fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; } @@ -819,6 +892,12 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, if (fastpath) { kfree(skb->head); } else { + /* copy this zero copy skb frags */ + if (skb_shinfo(skb)->tx_flags & SKBTX_DEV_ZEROCOPY) { + if (skb_copy_ubufs(skb, gfp_mask)) + goto nofrags; + skb_shinfo(skb)->tx_flags &= ~SKBTX_DEV_ZEROCOPY; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) get_page(skb_shinfo(skb)->frags[i].page); @@ -853,6 +932,8 @@ adjust_others: atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; +nofrags: + kfree(data); nodata: return -ENOMEM; } @@ -1354,6 +1435,7 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) } start = end; } + if (!len) return 0; diff --git a/net/core/sock.c b/net/core/sock.c index 6e819780c23..bc745d00ea4 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -128,6 +128,8 @@ #include <linux/filter.h> +#include <trace/events/sock.h> + #ifdef CONFIG_INET #include <net/tcp.h> #endif @@ -158,7 +160,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_ALG" , - "sk_lock-AF_MAX" + "sk_lock-AF_NFC" , "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , @@ -174,7 +176,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_ALG" , - "slock-AF_MAX" + "slock-AF_NFC" , "slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , @@ -190,7 +192,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_ALG" , - "clock-AF_MAX" + "clock-AF_NFC" , "clock-AF_MAX" }; /* @@ -292,6 +294,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf) { atomic_inc(&sk->sk_drops); + trace_sock_rcvqueue_full(sk, skb); return -ENOMEM; } @@ -1736,6 +1739,8 @@ suppress_allocation: return 1; } + trace_sock_exceed_buf_limit(sk, prot, allocated); + /* Alas. Undo changes. */ sk->sk_forward_alloc -= amt * SK_MEM_QUANTUM; atomic_long_sub(amt, prot->memory_allocated); diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 7e7ca375d43..98a52640e7c 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -68,6 +68,7 @@ void skb_clone_tx_timestamp(struct sk_buff *skb) break; } } +EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp); void skb_complete_tx_timestamp(struct sk_buff *skb, struct skb_shared_hwtstamps *hwtstamps) @@ -121,6 +122,7 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) return false; } +EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp); void __init skb_timestamping_init(void) { diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c index 3609eacaf4c..3cb56af4e13 100644 --- a/net/dcb/dcbnl.c +++ b/net/dcb/dcbnl.c @@ -1166,64 +1166,6 @@ err: return ret; } -/* Handle IEEE 802.1Qaz SET commands. If any requested operation can not - * be completed the entire msg is aborted and error value is returned. - * No attempt is made to reconcile the case where only part of the - * cmd can be completed. - */ -static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) -{ - const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; - struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; - int err = -EOPNOTSUPP; - - if (!ops) - goto err; - - err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, - tb[DCB_ATTR_IEEE], dcbnl_ieee_policy); - if (err) - goto err; - - if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) { - struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]); - err = ops->ieee_setets(netdev, ets); - if (err) - goto err; - } - - if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { - struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); - err = ops->ieee_setpfc(netdev, pfc); - if (err) - goto err; - } - - if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { - struct nlattr *attr; - int rem; - - nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { - struct dcb_app *app_data; - if (nla_type(attr) != DCB_ATTR_IEEE_APP) - continue; - app_data = nla_data(attr); - if (ops->ieee_setapp) - err = ops->ieee_setapp(netdev, app_data); - else - err = dcb_setapp(netdev, app_data); - if (err) - goto err; - } - } - -err: - dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE, - pid, seq, flags); - return err; -} - static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, int app_nested_type, int app_info_type, int app_entry_type) @@ -1279,29 +1221,13 @@ nla_put_failure: } /* Handle IEEE 802.1Qaz GET commands. */ -static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, - u32 pid, u32 seq, u16 flags) +static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { - struct sk_buff *skb; - struct nlmsghdr *nlh; - struct dcbmsg *dcb; struct nlattr *ieee, *app; struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; - int err; - - if (!ops) - return -EOPNOTSUPP; - - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!skb) - return -ENOBUFS; - - nlh = NLMSG_NEW(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); - - dcb = NLMSG_DATA(nlh); - dcb->dcb_family = AF_UNSPEC; - dcb->cmd = DCB_CMD_IEEE_GET; + int dcbx; + int err = -EMSGSIZE; NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name); @@ -1338,6 +1264,12 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, } } } + + if (netdev->dcbnl_ops->getdcbx) + dcbx = netdev->dcbnl_ops->getdcbx(netdev); + else + dcbx = -EOPNOTSUPP; + spin_unlock(&dcb_lock); nla_nest_end(skb, app); @@ -1366,16 +1298,413 @@ static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, } nla_nest_end(skb, ieee); - nlmsg_end(skb, nlh); + if (dcbx >= 0) { + err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); + if (err) + goto nla_put_failure; + } + + return 0; - return rtnl_unicast(skb, &init_net, pid); nla_put_failure: - nlmsg_cancel(skb, nlh); -nlmsg_failure: - kfree_skb(skb); - return -1; + return err; } +static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, + int dir) +{ + u8 pgid, up_map, prio, tc_pct; + const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; + int i = dir ? DCB_ATTR_CEE_TX_PG : DCB_ATTR_CEE_RX_PG; + struct nlattr *pg = nla_nest_start(skb, i); + + if (!pg) + goto nla_put_failure; + + for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { + struct nlattr *tc_nest = nla_nest_start(skb, i); + + if (!tc_nest) + goto nla_put_failure; + + pgid = DCB_ATTR_VALUE_UNDEFINED; + prio = DCB_ATTR_VALUE_UNDEFINED; + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + up_map = DCB_ATTR_VALUE_UNDEFINED; + + if (!dir) + ops->getpgtccfgrx(dev, i - DCB_PG_ATTR_TC_0, + &prio, &pgid, &tc_pct, &up_map); + else + ops->getpgtccfgtx(dev, i - DCB_PG_ATTR_TC_0, + &prio, &pgid, &tc_pct, &up_map); + + NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_PGID, pgid); + NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map); + NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio); + NLA_PUT_U8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct); + nla_nest_end(skb, tc_nest); + } + + for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { + tc_pct = DCB_ATTR_VALUE_UNDEFINED; + + if (!dir) + ops->getpgbwgcfgrx(dev, i - DCB_PG_ATTR_BW_ID_0, + &tc_pct); + else + ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0, + &tc_pct); + NLA_PUT_U8(skb, i, tc_pct); + } + nla_nest_end(skb, pg); + return 0; + +nla_put_failure: + return -EMSGSIZE; +} + +static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) +{ + struct nlattr *cee, *app; + struct dcb_app_type *itr; + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + int dcbx, i, err = -EMSGSIZE; + u8 value; + + NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name); + + cee = nla_nest_start(skb, DCB_ATTR_CEE); + if (!cee) + goto nla_put_failure; + + /* local pg */ + if (ops->getpgtccfgtx && ops->getpgbwgcfgtx) { + err = dcbnl_cee_pg_fill(skb, netdev, 1); + if (err) + goto nla_put_failure; + } + + if (ops->getpgtccfgrx && ops->getpgbwgcfgrx) { + err = dcbnl_cee_pg_fill(skb, netdev, 0); + if (err) + goto nla_put_failure; + } + + /* local pfc */ + if (ops->getpfccfg) { + struct nlattr *pfc_nest = nla_nest_start(skb, DCB_ATTR_CEE_PFC); + + if (!pfc_nest) + goto nla_put_failure; + + for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { + ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); + NLA_PUT_U8(skb, i, value); + } + nla_nest_end(skb, pfc_nest); + } + + /* local app */ + spin_lock(&dcb_lock); + app = nla_nest_start(skb, DCB_ATTR_CEE_APP_TABLE); + if (!app) + goto dcb_unlock; + + list_for_each_entry(itr, &dcb_app_list, list) { + if (strncmp(itr->name, netdev->name, IFNAMSIZ) == 0) { + struct nlattr *app_nest = nla_nest_start(skb, + DCB_ATTR_APP); + if (!app_nest) + goto dcb_unlock; + + err = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, + itr->app.selector); + if (err) + goto dcb_unlock; + + err = nla_put_u16(skb, DCB_APP_ATTR_ID, + itr->app.protocol); + if (err) + goto dcb_unlock; + + err = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, + itr->app.priority); + if (err) + goto dcb_unlock; + + nla_nest_end(skb, app_nest); + } + } + nla_nest_end(skb, app); + + if (netdev->dcbnl_ops->getdcbx) + dcbx = netdev->dcbnl_ops->getdcbx(netdev); + else + dcbx = -EOPNOTSUPP; + + spin_unlock(&dcb_lock); + + /* features flags */ + if (ops->getfeatcfg) { + struct nlattr *feat = nla_nest_start(skb, DCB_ATTR_CEE_FEAT); + if (!feat) + goto nla_put_failure; + + for (i = DCB_FEATCFG_ATTR_ALL + 1; i <= DCB_FEATCFG_ATTR_MAX; + i++) + if (!ops->getfeatcfg(netdev, i, &value)) + NLA_PUT_U8(skb, i, value); + + nla_nest_end(skb, feat); + } + + /* peer info if available */ + if (ops->cee_peer_getpg) { + struct cee_pg pg; + err = ops->cee_peer_getpg(netdev, &pg); + if (!err) + NLA_PUT(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg); + } + + if (ops->cee_peer_getpfc) { + struct cee_pfc pfc; + err = ops->cee_peer_getpfc(netdev, &pfc); + if (!err) + NLA_PUT(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc); + } + + if (ops->peer_getappinfo && ops->peer_getapptable) { + err = dcbnl_build_peer_app(netdev, skb, + DCB_ATTR_CEE_PEER_APP_TABLE, + DCB_ATTR_CEE_PEER_APP_INFO, + DCB_ATTR_CEE_PEER_APP); + if (err) + goto nla_put_failure; + } + nla_nest_end(skb, cee); + + /* DCBX state */ + if (dcbx >= 0) { + err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); + if (err) + goto nla_put_failure; + } + return 0; + +dcb_unlock: + spin_unlock(&dcb_lock); +nla_put_failure: + return err; +} + +static int dcbnl_notify(struct net_device *dev, int event, int cmd, + u32 seq, u32 pid, int dcbx_ver) +{ + struct net *net = dev_net(dev); + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct dcbmsg *dcb; + const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; + int err; + + if (!ops) + return -EOPNOTSUPP; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + nlh = nlmsg_put(skb, pid, 0, event, sizeof(*dcb), 0); + if (nlh == NULL) { + nlmsg_free(skb); + return -EMSGSIZE; + } + + dcb = NLMSG_DATA(nlh); + dcb->dcb_family = AF_UNSPEC; + dcb->cmd = cmd; + + if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) + err = dcbnl_ieee_fill(skb, dev); + else + err = dcbnl_cee_fill(skb, dev); + + if (err < 0) { + /* Report error to broadcast listeners */ + nlmsg_cancel(skb, nlh); + kfree_skb(skb); + rtnl_set_sk_err(net, RTNLGRP_DCB, err); + } else { + /* End nlmsg and notify broadcast listeners */ + nlmsg_end(skb, nlh); + rtnl_notify(skb, net, 0, RTNLGRP_DCB, NULL, GFP_KERNEL); + } + + return err; +} + +int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, + u32 seq, u32 pid) +{ + return dcbnl_notify(dev, event, cmd, seq, pid, DCB_CAP_DCBX_VER_IEEE); +} +EXPORT_SYMBOL(dcbnl_ieee_notify); + +int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, + u32 seq, u32 pid) +{ + return dcbnl_notify(dev, event, cmd, seq, pid, DCB_CAP_DCBX_VER_CEE); +} +EXPORT_SYMBOL(dcbnl_cee_notify); + +/* Handle IEEE 802.1Qaz SET commands. If any requested operation can not + * be completed the entire msg is aborted and error value is returned. + * No attempt is made to reconcile the case where only part of the + * cmd can be completed. + */ +static int dcbnl_ieee_set(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int err = -EOPNOTSUPP; + + if (!ops) + return err; + + if (!tb[DCB_ATTR_IEEE]) + return -EINVAL; + + err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, + tb[DCB_ATTR_IEEE], dcbnl_ieee_policy); + if (err) + return err; + + if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) { + struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]); + err = ops->ieee_setets(netdev, ets); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { + struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); + err = ops->ieee_setpfc(netdev, pfc); + if (err) + goto err; + } + + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { + struct nlattr *attr; + int rem; + + nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + struct dcb_app *app_data; + if (nla_type(attr) != DCB_ATTR_IEEE_APP) + continue; + app_data = nla_data(attr); + if (ops->ieee_setapp) + err = ops->ieee_setapp(netdev, app_data); + else + err = dcb_ieee_setapp(netdev, app_data); + if (err) + goto err; + } + } + +err: + dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_SET, DCB_ATTR_IEEE, + pid, seq, flags); + dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); + return err; +} + +static int dcbnl_ieee_get(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + struct net *net = dev_net(netdev); + struct sk_buff *skb; + struct nlmsghdr *nlh; + struct dcbmsg *dcb; + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + int err; + + if (!ops) + return -EOPNOTSUPP; + + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); + if (nlh == NULL) { + nlmsg_free(skb); + return -EMSGSIZE; + } + + dcb = NLMSG_DATA(nlh); + dcb->dcb_family = AF_UNSPEC; + dcb->cmd = DCB_CMD_IEEE_GET; + + err = dcbnl_ieee_fill(skb, netdev); + + if (err < 0) { + nlmsg_cancel(skb, nlh); + kfree_skb(skb); + } else { + nlmsg_end(skb, nlh); + err = rtnl_unicast(skb, net, pid); + } + + return err; +} + +static int dcbnl_ieee_del(struct net_device *netdev, struct nlattr **tb, + u32 pid, u32 seq, u16 flags) +{ + const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; + struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; + int err = -EOPNOTSUPP; + + if (!ops) + return -EOPNOTSUPP; + + if (!tb[DCB_ATTR_IEEE]) + return -EINVAL; + + err = nla_parse_nested(ieee, DCB_ATTR_IEEE_MAX, + tb[DCB_ATTR_IEEE], dcbnl_ieee_policy); + if (err) + return err; + + if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { + struct nlattr *attr; + int rem; + + nla_for_each_nested(attr, ieee[DCB_ATTR_IEEE_APP_TABLE], rem) { + struct dcb_app *app_data; + + if (nla_type(attr) != DCB_ATTR_IEEE_APP) + continue; + app_data = nla_data(attr); + if (ops->ieee_delapp) + err = ops->ieee_delapp(netdev, app_data); + else + err = dcb_ieee_delapp(netdev, app_data); + if (err) + goto err; + } + } + +err: + dcbnl_reply(err, RTM_SETDCB, DCB_CMD_IEEE_DEL, DCB_ATTR_IEEE, + pid, seq, flags); + dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0); + return err; +} + + /* DCBX configuration */ static int dcbnl_getdcbx(struct net_device *netdev, struct nlattr **tb, u32 pid, u32 seq, u16 flags) @@ -1522,10 +1851,10 @@ err: static int dcbnl_cee_get(struct net_device *netdev, struct nlattr **tb, u32 pid, u32 seq, u16 flags) { + struct net *net = dev_net(netdev); struct sk_buff *skb; struct nlmsghdr *nlh; struct dcbmsg *dcb; - struct nlattr *cee; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; int err; @@ -1536,51 +1865,26 @@ static int dcbnl_cee_get(struct net_device *netdev, struct nlattr **tb, if (!skb) return -ENOBUFS; - nlh = NLMSG_NEW(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); + nlh = nlmsg_put(skb, pid, seq, RTM_GETDCB, sizeof(*dcb), flags); + if (nlh == NULL) { + nlmsg_free(skb); + return -EMSGSIZE; + } dcb = NLMSG_DATA(nlh); dcb->dcb_family = AF_UNSPEC; dcb->cmd = DCB_CMD_CEE_GET; - NLA_PUT_STRING(skb, DCB_ATTR_IFNAME, netdev->name); + err = dcbnl_cee_fill(skb, netdev); - cee = nla_nest_start(skb, DCB_ATTR_CEE); - if (!cee) - goto nla_put_failure; - - /* get peer info if available */ - if (ops->cee_peer_getpg) { - struct cee_pg pg; - err = ops->cee_peer_getpg(netdev, &pg); - if (!err) - NLA_PUT(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg); - } - - if (ops->cee_peer_getpfc) { - struct cee_pfc pfc; - err = ops->cee_peer_getpfc(netdev, &pfc); - if (!err) - NLA_PUT(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc); - } - - if (ops->peer_getappinfo && ops->peer_getapptable) { - err = dcbnl_build_peer_app(netdev, skb, - DCB_ATTR_CEE_PEER_APP_TABLE, - DCB_ATTR_CEE_PEER_APP_INFO, - DCB_ATTR_CEE_PEER_APP); - if (err) - goto nla_put_failure; + if (err < 0) { + nlmsg_cancel(skb, nlh); + nlmsg_free(skb); + } else { + nlmsg_end(skb, nlh); + err = rtnl_unicast(skb, net, pid); } - - nla_nest_end(skb, cee); - nlmsg_end(skb, nlh); - - return rtnl_unicast(skb, &init_net, pid); -nla_put_failure: - nlmsg_cancel(skb, nlh); -nlmsg_failure: - kfree_skb(skb); - return -1; + return err; } static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) @@ -1690,11 +1994,15 @@ static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto out; case DCB_CMD_IEEE_SET: ret = dcbnl_ieee_set(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); + nlh->nlmsg_flags); goto out; case DCB_CMD_IEEE_GET: ret = dcbnl_ieee_get(netdev, tb, pid, nlh->nlmsg_seq, - nlh->nlmsg_flags); + nlh->nlmsg_flags); + goto out; + case DCB_CMD_IEEE_DEL: + ret = dcbnl_ieee_del(netdev, tb, pid, nlh->nlmsg_seq, + nlh->nlmsg_flags); goto out; case DCB_CMD_GDCBX: ret = dcbnl_getdcbx(netdev, tb, pid, nlh->nlmsg_seq, @@ -1754,12 +2062,13 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) EXPORT_SYMBOL(dcb_getapp); /** - * ixgbe_dcbnl_setapp - add dcb application data to app list + * dcb_setapp - add CEE dcb application data to app list * - * Priority 0 is the default priority this removes applications - * from the app list if the priority is set to zero. + * Priority 0 is an invalid priority in CEE spec. This routine + * removes applications from the app list if the priority is + * set to zero. */ -u8 dcb_setapp(struct net_device *dev, struct dcb_app *new) +int dcb_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type *itr; struct dcb_app_type event; @@ -1802,6 +2111,114 @@ out: } EXPORT_SYMBOL(dcb_setapp); +/** + * dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority + * + * Helper routine which on success returns a non-zero 802.1Qaz user + * priority bitmap otherwise returns 0 to indicate the dcb_app was + * not found in APP list. + */ +u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) +{ + struct dcb_app_type *itr; + u8 prio = 0; + + spin_lock(&dcb_lock); + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == app->selector && + itr->app.protocol == app->protocol && + (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + prio |= 1 << itr->app.priority; + } + } + spin_unlock(&dcb_lock); + + return prio; +} +EXPORT_SYMBOL(dcb_ieee_getapp_mask); + +/** + * dcb_ieee_setapp - add IEEE dcb application data to app list + * + * This adds Application data to the list. Multiple application + * entries may exists for the same selector and protocol as long + * as the priorities are different. + */ +int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) +{ + struct dcb_app_type *itr, *entry; + struct dcb_app_type event; + int err = 0; + + memcpy(&event.name, dev->name, sizeof(event.name)); + memcpy(&event.app, new, sizeof(event.app)); + + spin_lock(&dcb_lock); + /* Search for existing match and abort if found */ + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == new->selector && + itr->app.protocol == new->protocol && + itr->app.priority == new->priority && + (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + err = -EEXIST; + goto out; + } + } + + /* App entry does not exist add new entry */ + entry = kmalloc(sizeof(struct dcb_app_type), GFP_ATOMIC); + if (!entry) { + err = -ENOMEM; + goto out; + } + + memcpy(&entry->app, new, sizeof(*new)); + strncpy(entry->name, dev->name, IFNAMSIZ); + list_add(&entry->list, &dcb_app_list); +out: + spin_unlock(&dcb_lock); + if (!err) + call_dcbevent_notifiers(DCB_APP_EVENT, &event); + return err; +} +EXPORT_SYMBOL(dcb_ieee_setapp); + +/** + * dcb_ieee_delapp - delete IEEE dcb application data from list + * + * This removes a matching APP data from the APP list + */ +int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) +{ + struct dcb_app_type *itr; + struct dcb_app_type event; + int err = -ENOENT; + + memcpy(&event.name, dev->name, sizeof(event.name)); + memcpy(&event.app, del, sizeof(event.app)); + + spin_lock(&dcb_lock); + /* Search for existing match and remove it. */ + list_for_each_entry(itr, &dcb_app_list, list) { + if (itr->app.selector == del->selector && + itr->app.protocol == del->protocol && + itr->app.priority == del->priority && + (strncmp(itr->name, dev->name, IFNAMSIZ) == 0)) { + list_del(&itr->list); + kfree(itr); + err = 0; + goto out; + } + } + +out: + spin_unlock(&dcb_lock); + if (!err) + call_dcbevent_notifiers(DCB_APP_EVENT, &event); + return err; +} +EXPORT_SYMBOL(dcb_ieee_delapp); + static void dcb_flushapp(void) { struct dcb_app_type *app; @@ -1819,8 +2236,8 @@ static int __init dcbnl_init(void) { INIT_LIST_HEAD(&dcb_app_list); - rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL); - rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL); + rtnl_register(PF_UNSPEC, RTM_GETDCB, dcb_doit, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_SETDCB, dcb_doit, NULL, NULL); return 0; } diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c index 36479ca61e0..48b585a5cba 100644 --- a/net/dccp/ccid.c +++ b/net/dccp/ccid.c @@ -118,7 +118,7 @@ static int ccid_activate(struct ccid_operations *ccid_ops) if (ccid_ops->ccid_hc_tx_slab == NULL) goto out_free_rx_slab; - pr_info("CCID: Activated CCID %d (%s)\n", + pr_info("DCCP: Activated CCID %d (%s)\n", ccid_ops->ccid_id, ccid_ops->ccid_name); err = 0; out: @@ -136,7 +136,7 @@ static void ccid_deactivate(struct ccid_operations *ccid_ops) ccid_kmem_cache_destroy(ccid_ops->ccid_hc_rx_slab); ccid_ops->ccid_hc_rx_slab = NULL; - pr_info("CCID: Deactivated CCID %d (%s)\n", + pr_info("DCCP: Deactivated CCID %d (%s)\n", ccid_ops->ccid_id, ccid_ops->ccid_name); } diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index fadecd20d75..0462040fc81 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -153,17 +153,93 @@ out: sock_put(sk); } +/* + * Congestion window validation (RFC 2861). + */ +static int ccid2_do_cwv = 1; +module_param(ccid2_do_cwv, bool, 0644); +MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation"); + +/** + * ccid2_update_used_window - Track how much of cwnd is actually used + * This is done in addition to CWV. The sender needs to have an idea of how many + * packets may be in flight, to set the local Sequence Window value accordingly + * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the + * maximum-used window. We use an EWMA low-pass filter to filter out noise. + */ +static void ccid2_update_used_window(struct ccid2_hc_tx_sock *hc, u32 new_wnd) +{ + hc->tx_expected_wnd = (3 * hc->tx_expected_wnd + new_wnd) / 4; +} + +/* This borrows the code of tcp_cwnd_application_limited() */ +static void ccid2_cwnd_application_limited(struct sock *sk, const u32 now) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + /* don't reduce cwnd below the initial window (IW) */ + u32 init_win = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache), + win_used = max(hc->tx_cwnd_used, init_win); + + if (win_used < hc->tx_cwnd) { + hc->tx_ssthresh = max(hc->tx_ssthresh, + (hc->tx_cwnd >> 1) + (hc->tx_cwnd >> 2)); + hc->tx_cwnd = (hc->tx_cwnd + win_used) >> 1; + } + hc->tx_cwnd_used = 0; + hc->tx_cwnd_stamp = now; +} + +/* This borrows the code of tcp_cwnd_restart() */ +static void ccid2_cwnd_restart(struct sock *sk, const u32 now) +{ + struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + u32 cwnd = hc->tx_cwnd, restart_cwnd, + iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache); + + hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2)); + + /* don't reduce cwnd below the initial window (IW) */ + restart_cwnd = min(cwnd, iwnd); + cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto; + hc->tx_cwnd = max(cwnd, restart_cwnd); + + hc->tx_cwnd_stamp = now; + hc->tx_cwnd_used = 0; +} + static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) { struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); + const u32 now = ccid2_time_stamp; struct ccid2_seq *next; - hc->tx_pipe++; + /* slow-start after idle periods (RFC 2581, RFC 2861) */ + if (ccid2_do_cwv && !hc->tx_pipe && + (s32)(now - hc->tx_lsndtime) >= hc->tx_rto) + ccid2_cwnd_restart(sk, now); + + hc->tx_lsndtime = now; + hc->tx_pipe += 1; + + /* see whether cwnd was fully used (RFC 2861), update expected window */ + if (ccid2_cwnd_network_limited(hc)) { + ccid2_update_used_window(hc, hc->tx_cwnd); + hc->tx_cwnd_used = 0; + hc->tx_cwnd_stamp = now; + } else { + if (hc->tx_pipe > hc->tx_cwnd_used) + hc->tx_cwnd_used = hc->tx_pipe; + + ccid2_update_used_window(hc, hc->tx_cwnd_used); + + if (ccid2_do_cwv && (s32)(now - hc->tx_cwnd_stamp) >= hc->tx_rto) + ccid2_cwnd_application_limited(sk, now); + } hc->tx_seqh->ccid2s_seq = dp->dccps_gss; hc->tx_seqh->ccid2s_acked = 0; - hc->tx_seqh->ccid2s_sent = ccid2_time_stamp; + hc->tx_seqh->ccid2s_sent = now; next = hc->tx_seqh->ccid2s_next; /* check if we need to alloc more space */ @@ -583,15 +659,6 @@ done: dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } -/* - * Convert RFC 3390 larger initial window into an equivalent number of packets. - * This is based on the numbers specified in RFC 5681, 3.1. - */ -static inline u32 rfc3390_bytes_to_packets(const u32 smss) -{ - return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); -} - static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) { struct ccid2_hc_tx_sock *hc = ccid_priv(ccid); @@ -603,6 +670,7 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) /* Use larger initial windows (RFC 4341, section 5). */ hc->tx_cwnd = rfc3390_bytes_to_packets(dp->dccps_mss_cache); + hc->tx_expected_wnd = hc->tx_cwnd; /* Make sure that Ack Ratio is enabled and within bounds. */ max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2); @@ -615,7 +683,8 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) hc->tx_rto = DCCP_TIMEOUT_INIT; hc->tx_rpdupack = -1; - hc->tx_last_cong = ccid2_time_stamp; + hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_time_stamp; + hc->tx_cwnd_used = 0; setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, (unsigned long)sk); INIT_LIST_HEAD(&hc->tx_av_chunks); @@ -636,18 +705,14 @@ static void ccid2_hc_tx_exit(struct sock *sk) static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb) { - const struct dccp_sock *dp = dccp_sk(sk); struct ccid2_hc_rx_sock *hc = ccid2_hc_rx_sk(sk); - switch (DCCP_SKB_CB(skb)->dccpd_type) { - case DCCP_PKT_DATA: - case DCCP_PKT_DATAACK: - hc->rx_data++; - if (hc->rx_data >= dp->dccps_r_ack_ratio) { - dccp_send_ack(sk); - hc->rx_data = 0; - } - break; + if (!dccp_data_packet(skb)) + return; + + if (++hc->rx_num_data_pkts >= dccp_sk(sk)->dccps_r_ack_ratio) { + dccp_send_ack(sk); + hc->rx_num_data_pkts = 0; } } diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h index e9985dafc2c..f585d330e1e 100644 --- a/net/dccp/ccids/ccid2.h +++ b/net/dccp/ccids/ccid2.h @@ -53,6 +53,10 @@ struct ccid2_seq { * @tx_rttvar: moving average/maximum of @mdev_max * @tx_rto: RTO value deriving from SRTT and RTTVAR (RFC 2988) * @tx_rtt_seq: to decay RTTVAR at most once per flight + * @tx_cwnd_used: actually used cwnd, W_used of RFC 2861 + * @tx_expected_wnd: moving average of @tx_cwnd_used + * @tx_cwnd_stamp: to track idle periods in CWV + * @tx_lsndtime: last time (in jiffies) a data packet was sent * @tx_rpseq: last consecutive seqno * @tx_rpdupack: dupacks since rpseq * @tx_av_chunks: list of Ack Vectors received on current skb @@ -76,6 +80,12 @@ struct ccid2_hc_tx_sock { u64 tx_rtt_seq:48; struct timer_list tx_rtotimer; + /* Congestion Window validation (optional, RFC 2861) */ + u32 tx_cwnd_used, + tx_expected_wnd, + tx_cwnd_stamp, + tx_lsndtime; + u64 tx_rpseq; int tx_rpdupack; u32 tx_last_cong; @@ -88,8 +98,21 @@ static inline bool ccid2_cwnd_network_limited(struct ccid2_hc_tx_sock *hc) return hc->tx_pipe >= hc->tx_cwnd; } +/* + * Convert RFC 3390 larger initial window into an equivalent number of packets. + * This is based on the numbers specified in RFC 5681, 3.1. + */ +static inline u32 rfc3390_bytes_to_packets(const u32 smss) +{ + return smss <= 1095 ? 4 : (smss > 2190 ? 2 : 3); +} + +/** + * struct ccid2_hc_rx_sock - Receiving end of CCID-2 half-connection + * @rx_num_data_pkts: number of data packets received since last feedback + */ struct ccid2_hc_rx_sock { - int rx_data; + u32 rx_num_data_pkts; }; static inline struct ccid2_hc_tx_sock *ccid2_hc_tx_sk(const struct sock *sk) diff --git a/net/dccp/input.c b/net/dccp/input.c index 4222e7a654b..51d5fe5fffb 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -619,20 +619,31 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, return 1; } - if (sk->sk_state != DCCP_REQUESTING && sk->sk_state != DCCP_RESPOND) { - if (dccp_check_seqno(sk, skb)) - goto discard; - - /* - * Step 8: Process options and mark acknowledgeable - */ - if (dccp_parse_options(sk, NULL, skb)) - return 1; + /* Step 6: Check sequence numbers (omitted in LISTEN/REQUEST state) */ + if (sk->sk_state != DCCP_REQUESTING && dccp_check_seqno(sk, skb)) + goto discard; - dccp_handle_ackvec_processing(sk, skb); - dccp_deliver_input_to_ccids(sk, skb); + /* + * Step 7: Check for unexpected packet types + * If (S.is_server and P.type == Response) + * or (S.is_client and P.type == Request) + * or (S.state == RESPOND and P.type == Data), + * Send Sync packet acknowledging P.seqno + * Drop packet and return + */ + if ((dp->dccps_role != DCCP_ROLE_CLIENT && + dh->dccph_type == DCCP_PKT_RESPONSE) || + (dp->dccps_role == DCCP_ROLE_CLIENT && + dh->dccph_type == DCCP_PKT_REQUEST) || + (sk->sk_state == DCCP_RESPOND && dh->dccph_type == DCCP_PKT_DATA)) { + dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC); + goto discard; } + /* Step 8: Process options */ + if (dccp_parse_options(sk, NULL, skb)) + return 1; + /* * Step 9: Process Reset * If P.type == Reset, @@ -640,31 +651,15 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, * S.state := TIMEWAIT * Set TIMEWAIT timer * Drop packet and return - */ + */ if (dh->dccph_type == DCCP_PKT_RESET) { dccp_rcv_reset(sk, skb); return 0; - /* - * Step 7: Check for unexpected packet types - * If (S.is_server and P.type == Response) - * or (S.is_client and P.type == Request) - * or (S.state == RESPOND and P.type == Data), - * Send Sync packet acknowledging P.seqno - * Drop packet and return - */ - } else if ((dp->dccps_role != DCCP_ROLE_CLIENT && - dh->dccph_type == DCCP_PKT_RESPONSE) || - (dp->dccps_role == DCCP_ROLE_CLIENT && - dh->dccph_type == DCCP_PKT_REQUEST) || - (sk->sk_state == DCCP_RESPOND && - dh->dccph_type == DCCP_PKT_DATA)) { - dccp_send_sync(sk, dcb->dccpd_seq, DCCP_PKT_SYNC); - goto discard; - } else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) { + } else if (dh->dccph_type == DCCP_PKT_CLOSEREQ) { /* Step 13 */ if (dccp_rcv_closereq(sk, skb)) return 0; goto discard; - } else if (dh->dccph_type == DCCP_PKT_CLOSE) { + } else if (dh->dccph_type == DCCP_PKT_CLOSE) { /* Step 14 */ if (dccp_rcv_close(sk, skb)) return 0; goto discard; @@ -679,8 +674,12 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb, __kfree_skb(skb); return 0; - case DCCP_RESPOND: case DCCP_PARTOPEN: + /* Step 8: if using Ack Vectors, mark packet acknowledgeable */ + dccp_handle_ackvec_processing(sk, skb); + dccp_deliver_input_to_ccids(sk, skb); + /* fall through */ + case DCCP_RESPOND: queued = dccp_rcv_respond_partopen_state_process(sk, skb, dh, len); break; diff --git a/net/dccp/output.c b/net/dccp/output.c index fab108e51e5..dede3edb884 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -27,11 +27,13 @@ static inline void dccp_event_ack_sent(struct sock *sk) inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK); } -static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb) +/* enqueue @skb on sk_send_head for retransmission, return clone to send now */ +static struct sk_buff *dccp_skb_entail(struct sock *sk, struct sk_buff *skb) { skb_set_owner_w(skb, sk); WARN_ON(sk->sk_send_head); sk->sk_send_head = skb; + return skb_clone(sk->sk_send_head, gfp_any()); } /* @@ -552,8 +554,7 @@ int dccp_connect(struct sock *sk) DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_REQUEST; - dccp_skb_entail(sk, skb); - dccp_transmit_skb(sk, skb_clone(skb, GFP_KERNEL)); + dccp_transmit_skb(sk, dccp_skb_entail(sk, skb)); DCCP_INC_STATS(DCCP_MIB_ACTIVEOPENS); /* Timer for repeating the REQUEST until an answer. */ @@ -678,8 +679,7 @@ void dccp_send_close(struct sock *sk, const int active) DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_CLOSE; if (active) { - dccp_skb_entail(sk, skb); - dccp_transmit_skb(sk, skb_clone(skb, prio)); + skb = dccp_skb_entail(sk, skb); /* * Retransmission timer for active-close: RFC 4340, 8.3 requires * to retransmit the Close/CloseReq until the CLOSING/CLOSEREQ @@ -692,6 +692,6 @@ void dccp_send_close(struct sock *sk, const int active) */ inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, DCCP_TIMEOUT_INIT, DCCP_RTO_MAX); - } else - dccp_transmit_skb(sk, skb); + } + dccp_transmit_skb(sk, skb); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index ea3b6ee21fc..19acd00a638 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -291,23 +291,23 @@ int dn_sockaddr2username(struct sockaddr_dn *sdn, unsigned char *buf, unsigned c *buf++ = type; - switch(type) { - case 0: - *buf++ = sdn->sdn_objnum; - break; - case 1: - *buf++ = 0; - *buf++ = le16_to_cpu(sdn->sdn_objnamel); - memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); - len = 3 + le16_to_cpu(sdn->sdn_objnamel); - break; - case 2: - memset(buf, 0, 5); - buf += 5; - *buf++ = le16_to_cpu(sdn->sdn_objnamel); - memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); - len = 7 + le16_to_cpu(sdn->sdn_objnamel); - break; + switch (type) { + case 0: + *buf++ = sdn->sdn_objnum; + break; + case 1: + *buf++ = 0; + *buf++ = le16_to_cpu(sdn->sdn_objnamel); + memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); + len = 3 + le16_to_cpu(sdn->sdn_objnamel); + break; + case 2: + memset(buf, 0, 5); + buf += 5; + *buf++ = le16_to_cpu(sdn->sdn_objnamel); + memcpy(buf, sdn->sdn_objname, le16_to_cpu(sdn->sdn_objnamel)); + len = 7 + le16_to_cpu(sdn->sdn_objnamel); + break; } return len; @@ -337,23 +337,23 @@ int dn_username2sockaddr(unsigned char *data, int len, struct sockaddr_dn *sdn, *fmt = *data++; type = *data++; - switch(*fmt) { - case 0: - sdn->sdn_objnum = type; - return 2; - case 1: - namel = 16; - break; - case 2: - len -= 4; - data += 4; - break; - case 4: - len -= 8; - data += 8; - break; - default: - return -1; + switch (*fmt) { + case 0: + sdn->sdn_objnum = type; + return 2; + case 1: + namel = 16; + break; + case 2: + len -= 4; + data += 4; + break; + case 4: + len -= 8; + data += 8; + break; + default: + return -1; } len -= 1; @@ -575,25 +575,26 @@ int dn_destroy_timer(struct sock *sk) scp->persist = dn_nsp_persist(sk); - switch(scp->state) { - case DN_DI: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); - if (scp->nsp_rxtshift >= decnet_di_count) - scp->state = DN_CN; - return 0; + switch (scp->state) { + case DN_DI: + dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); + if (scp->nsp_rxtshift >= decnet_di_count) + scp->state = DN_CN; + return 0; - case DN_DR: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); - if (scp->nsp_rxtshift >= decnet_dr_count) - scp->state = DN_DRC; - return 0; + case DN_DR: + dn_nsp_send_disc(sk, NSP_DISCINIT, 0, GFP_ATOMIC); + if (scp->nsp_rxtshift >= decnet_dr_count) + scp->state = DN_DRC; + return 0; - case DN_DN: - if (scp->nsp_rxtshift < decnet_dn_count) { - /* printk(KERN_DEBUG "dn_destroy_timer: DN\n"); */ - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, GFP_ATOMIC); - return 0; - } + case DN_DN: + if (scp->nsp_rxtshift < decnet_dn_count) { + /* printk(KERN_DEBUG "dn_destroy_timer: DN\n"); */ + dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, + GFP_ATOMIC); + return 0; + } } scp->persist = (HZ * decnet_time_wait); @@ -623,42 +624,42 @@ static void dn_destroy_sock(struct sock *sk) sk->sk_state = TCP_CLOSE; - switch(scp->state) { - case DN_DN: - dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, - sk->sk_allocation); - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - break; - case DN_CR: - scp->state = DN_DR; - goto disc_reject; - case DN_RUN: - scp->state = DN_DI; - case DN_DI: - case DN_DR: + switch (scp->state) { + case DN_DN: + dn_nsp_send_disc(sk, NSP_DISCCONF, NSP_REASON_DC, + sk->sk_allocation); + scp->persist_fxn = dn_destroy_timer; + scp->persist = dn_nsp_persist(sk); + break; + case DN_CR: + scp->state = DN_DR; + goto disc_reject; + case DN_RUN: + scp->state = DN_DI; + case DN_DI: + case DN_DR: disc_reject: - dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); - case DN_NC: - case DN_NR: - case DN_RJ: - case DN_DIC: - case DN_CN: - case DN_DRC: - case DN_CI: - case DN_CD: - scp->persist_fxn = dn_destroy_timer; - scp->persist = dn_nsp_persist(sk); - break; - default: - printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); - case DN_O: - dn_stop_slow_timer(sk); + dn_nsp_send_disc(sk, NSP_DISCINIT, 0, sk->sk_allocation); + case DN_NC: + case DN_NR: + case DN_RJ: + case DN_DIC: + case DN_CN: + case DN_DRC: + case DN_CI: + case DN_CD: + scp->persist_fxn = dn_destroy_timer; + scp->persist = dn_nsp_persist(sk); + break; + default: + printk(KERN_DEBUG "DECnet: dn_destroy_sock passed socket in invalid state\n"); + case DN_O: + dn_stop_slow_timer(sk); - dn_unhash_sock_bh(sk); - sock_put(sk); + dn_unhash_sock_bh(sk); + sock_put(sk); - break; + break; } } @@ -683,15 +684,15 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, if (!net_eq(net, &init_net)) return -EAFNOSUPPORT; - switch(sock->type) { - case SOCK_SEQPACKET: - if (protocol != DNPROTO_NSP) - return -EPROTONOSUPPORT; - break; - case SOCK_STREAM: - break; - default: - return -ESOCKTNOSUPPORT; + switch (sock->type) { + case SOCK_SEQPACKET: + if (protocol != DNPROTO_NSP) + return -EPROTONOSUPPORT; + break; + case SOCK_STREAM: + break; + default: + return -ESOCKTNOSUPPORT; } @@ -987,16 +988,16 @@ static inline int dn_check_state(struct sock *sk, struct sockaddr_dn *addr, int { struct dn_scp *scp = DN_SK(sk); - switch(scp->state) { - case DN_RUN: - return 0; - case DN_CR: - return dn_confirm_accept(sk, timeo, sk->sk_allocation); - case DN_CI: - case DN_CC: - return dn_wait_run(sk, timeo); - case DN_O: - return __dn_connect(sk, addr, addrlen, timeo, flags); + switch (scp->state) { + case DN_RUN: + return 0; + case DN_CR: + return dn_confirm_accept(sk, timeo, sk->sk_allocation); + case DN_CI: + case DN_CC: + return dn_wait_run(sk, timeo); + case DN_O: + return __dn_connect(sk, addr, addrlen, timeo, flags); } return -EINVAL; @@ -1363,141 +1364,140 @@ static int __dn_setsockopt(struct socket *sock, int level,int optname, char __us if (copy_from_user(&u, optval, optlen)) return -EFAULT; - switch(optname) { - case DSO_CONDATA: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if ((scp->state != DN_O) && (scp->state != DN_CR)) - return -EINVAL; + switch (optname) { + case DSO_CONDATA: + if (sock->state == SS_CONNECTED) + return -EISCONN; + if ((scp->state != DN_O) && (scp->state != DN_CR)) + return -EINVAL; - if (optlen != sizeof(struct optdata_dn)) - return -EINVAL; + if (optlen != sizeof(struct optdata_dn)) + return -EINVAL; - if (le16_to_cpu(u.opt.opt_optl) > 16) - return -EINVAL; + if (le16_to_cpu(u.opt.opt_optl) > 16) + return -EINVAL; - memcpy(&scp->conndata_out, &u.opt, optlen); - break; - - case DSO_DISDATA: - if (sock->state != SS_CONNECTED && scp->accept_mode == ACC_IMMED) - return -ENOTCONN; - - if (optlen != sizeof(struct optdata_dn)) - return -EINVAL; + memcpy(&scp->conndata_out, &u.opt, optlen); + break; - if (le16_to_cpu(u.opt.opt_optl) > 16) - return -EINVAL; + case DSO_DISDATA: + if (sock->state != SS_CONNECTED && + scp->accept_mode == ACC_IMMED) + return -ENOTCONN; - memcpy(&scp->discdata_out, &u.opt, optlen); - break; + if (optlen != sizeof(struct optdata_dn)) + return -EINVAL; - case DSO_CONACCESS: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if (scp->state != DN_O) - return -EINVAL; + if (le16_to_cpu(u.opt.opt_optl) > 16) + return -EINVAL; - if (optlen != sizeof(struct accessdata_dn)) - return -EINVAL; + memcpy(&scp->discdata_out, &u.opt, optlen); + break; - if ((u.acc.acc_accl > DN_MAXACCL) || - (u.acc.acc_passl > DN_MAXACCL) || - (u.acc.acc_userl > DN_MAXACCL)) - return -EINVAL; + case DSO_CONACCESS: + if (sock->state == SS_CONNECTED) + return -EISCONN; + if (scp->state != DN_O) + return -EINVAL; - memcpy(&scp->accessdata, &u.acc, optlen); - break; + if (optlen != sizeof(struct accessdata_dn)) + return -EINVAL; - case DSO_ACCEPTMODE: - if (sock->state == SS_CONNECTED) - return -EISCONN; - if (scp->state != DN_O) - return -EINVAL; + if ((u.acc.acc_accl > DN_MAXACCL) || + (u.acc.acc_passl > DN_MAXACCL) || + (u.acc.acc_userl > DN_MAXACCL)) + return -EINVAL; - if (optlen != sizeof(int)) - return -EINVAL; + memcpy(&scp->accessdata, &u.acc, optlen); + break; - if ((u.mode != ACC_IMMED) && (u.mode != ACC_DEFER)) - return -EINVAL; + case DSO_ACCEPTMODE: + if (sock->state == SS_CONNECTED) + return -EISCONN; + if (scp->state != DN_O) + return -EINVAL; - scp->accept_mode = (unsigned char)u.mode; - break; + if (optlen != sizeof(int)) + return -EINVAL; - case DSO_CONACCEPT: + if ((u.mode != ACC_IMMED) && (u.mode != ACC_DEFER)) + return -EINVAL; - if (scp->state != DN_CR) - return -EINVAL; - timeo = sock_rcvtimeo(sk, 0); - err = dn_confirm_accept(sk, &timeo, sk->sk_allocation); - return err; + scp->accept_mode = (unsigned char)u.mode; + break; - case DSO_CONREJECT: + case DSO_CONACCEPT: + if (scp->state != DN_CR) + return -EINVAL; + timeo = sock_rcvtimeo(sk, 0); + err = dn_confirm_accept(sk, &timeo, sk->sk_allocation); + return err; - if (scp->state != DN_CR) - return -EINVAL; + case DSO_CONREJECT: + if (scp->state != DN_CR) + return -EINVAL; - scp->state = DN_DR; - sk->sk_shutdown = SHUTDOWN_MASK; - dn_nsp_send_disc(sk, 0x38, 0, sk->sk_allocation); - break; + scp->state = DN_DR; + sk->sk_shutdown = SHUTDOWN_MASK; + dn_nsp_send_disc(sk, 0x38, 0, sk->sk_allocation); + break; - default: + default: #ifdef CONFIG_NETFILTER return nf_setsockopt(sk, PF_DECnet, optname, optval, optlen); #endif - case DSO_LINKINFO: - case DSO_STREAM: - case DSO_SEQPACKET: - return -ENOPROTOOPT; - - case DSO_MAXWINDOW: - if (optlen != sizeof(unsigned long)) - return -EINVAL; - if (u.win > NSP_MAX_WINDOW) - u.win = NSP_MAX_WINDOW; - if (u.win == 0) - return -EINVAL; - scp->max_window = u.win; - if (scp->snd_window > u.win) - scp->snd_window = u.win; - break; + case DSO_LINKINFO: + case DSO_STREAM: + case DSO_SEQPACKET: + return -ENOPROTOOPT; + + case DSO_MAXWINDOW: + if (optlen != sizeof(unsigned long)) + return -EINVAL; + if (u.win > NSP_MAX_WINDOW) + u.win = NSP_MAX_WINDOW; + if (u.win == 0) + return -EINVAL; + scp->max_window = u.win; + if (scp->snd_window > u.win) + scp->snd_window = u.win; + break; - case DSO_NODELAY: - if (optlen != sizeof(int)) - return -EINVAL; - if (scp->nonagle == 2) - return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 1; - /* if (scp->nonagle == 1) { Push pending frames } */ - break; + case DSO_NODELAY: + if (optlen != sizeof(int)) + return -EINVAL; + if (scp->nonagle == 2) + return -EINVAL; + scp->nonagle = (u.val == 0) ? 0 : 1; + /* if (scp->nonagle == 1) { Push pending frames } */ + break; - case DSO_CORK: - if (optlen != sizeof(int)) - return -EINVAL; - if (scp->nonagle == 1) - return -EINVAL; - scp->nonagle = (u.val == 0) ? 0 : 2; - /* if (scp->nonagle == 0) { Push pending frames } */ - break; + case DSO_CORK: + if (optlen != sizeof(int)) + return -EINVAL; + if (scp->nonagle == 1) + return -EINVAL; + scp->nonagle = (u.val == 0) ? 0 : 2; + /* if (scp->nonagle == 0) { Push pending frames } */ + break; - case DSO_SERVICES: - if (optlen != sizeof(unsigned char)) - return -EINVAL; - if ((u.services & ~NSP_FC_MASK) != 0x01) - return -EINVAL; - if ((u.services & NSP_FC_MASK) == NSP_FC_MASK) - return -EINVAL; - scp->services_loc = u.services; - break; + case DSO_SERVICES: + if (optlen != sizeof(unsigned char)) + return -EINVAL; + if ((u.services & ~NSP_FC_MASK) != 0x01) + return -EINVAL; + if ((u.services & NSP_FC_MASK) == NSP_FC_MASK) + return -EINVAL; + scp->services_loc = u.services; + break; - case DSO_INFO: - if (optlen != sizeof(unsigned char)) - return -EINVAL; - if (u.info & 0xfc) - return -EINVAL; - scp->info_loc = u.info; - break; + case DSO_INFO: + if (optlen != sizeof(unsigned char)) + return -EINVAL; + if (u.info & 0xfc) + return -EINVAL; + scp->info_loc = u.info; + break; } return 0; @@ -1527,107 +1527,106 @@ static int __dn_getsockopt(struct socket *sock, int level,int optname, char __us if(get_user(r_len , optlen)) return -EFAULT; - switch(optname) { - case DSO_CONDATA: - if (r_len > sizeof(struct optdata_dn)) - r_len = sizeof(struct optdata_dn); - r_data = &scp->conndata_in; - break; - - case DSO_DISDATA: - if (r_len > sizeof(struct optdata_dn)) - r_len = sizeof(struct optdata_dn); - r_data = &scp->discdata_in; - break; + switch (optname) { + case DSO_CONDATA: + if (r_len > sizeof(struct optdata_dn)) + r_len = sizeof(struct optdata_dn); + r_data = &scp->conndata_in; + break; - case DSO_CONACCESS: - if (r_len > sizeof(struct accessdata_dn)) - r_len = sizeof(struct accessdata_dn); - r_data = &scp->accessdata; - break; + case DSO_DISDATA: + if (r_len > sizeof(struct optdata_dn)) + r_len = sizeof(struct optdata_dn); + r_data = &scp->discdata_in; + break; - case DSO_ACCEPTMODE: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->accept_mode; - break; + case DSO_CONACCESS: + if (r_len > sizeof(struct accessdata_dn)) + r_len = sizeof(struct accessdata_dn); + r_data = &scp->accessdata; + break; - case DSO_LINKINFO: - if (r_len > sizeof(struct linkinfo_dn)) - r_len = sizeof(struct linkinfo_dn); + case DSO_ACCEPTMODE: + if (r_len > sizeof(unsigned char)) + r_len = sizeof(unsigned char); + r_data = &scp->accept_mode; + break; - memset(&link, 0, sizeof(link)); + case DSO_LINKINFO: + if (r_len > sizeof(struct linkinfo_dn)) + r_len = sizeof(struct linkinfo_dn); - switch(sock->state) { - case SS_CONNECTING: - link.idn_linkstate = LL_CONNECTING; - break; - case SS_DISCONNECTING: - link.idn_linkstate = LL_DISCONNECTING; - break; - case SS_CONNECTED: - link.idn_linkstate = LL_RUNNING; - break; - default: - link.idn_linkstate = LL_INACTIVE; - } + memset(&link, 0, sizeof(link)); - link.idn_segsize = scp->segsize_rem; - r_data = &link; + switch (sock->state) { + case SS_CONNECTING: + link.idn_linkstate = LL_CONNECTING; + break; + case SS_DISCONNECTING: + link.idn_linkstate = LL_DISCONNECTING; + break; + case SS_CONNECTED: + link.idn_linkstate = LL_RUNNING; break; - default: + link.idn_linkstate = LL_INACTIVE; + } + + link.idn_segsize = scp->segsize_rem; + r_data = &link; + break; + + default: #ifdef CONFIG_NETFILTER - { - int ret, len; + { + int ret, len; - if(get_user(len, optlen)) - return -EFAULT; + if (get_user(len, optlen)) + return -EFAULT; - ret = nf_getsockopt(sk, PF_DECnet, optname, - optval, &len); - if (ret >= 0) - ret = put_user(len, optlen); - return ret; - } + ret = nf_getsockopt(sk, PF_DECnet, optname, optval, &len); + if (ret >= 0) + ret = put_user(len, optlen); + return ret; + } #endif - case DSO_STREAM: - case DSO_SEQPACKET: - case DSO_CONACCEPT: - case DSO_CONREJECT: - return -ENOPROTOOPT; - - case DSO_MAXWINDOW: - if (r_len > sizeof(unsigned long)) - r_len = sizeof(unsigned long); - r_data = &scp->max_window; - break; + case DSO_STREAM: + case DSO_SEQPACKET: + case DSO_CONACCEPT: + case DSO_CONREJECT: + return -ENOPROTOOPT; + + case DSO_MAXWINDOW: + if (r_len > sizeof(unsigned long)) + r_len = sizeof(unsigned long); + r_data = &scp->max_window; + break; - case DSO_NODELAY: - if (r_len > sizeof(int)) - r_len = sizeof(int); - val = (scp->nonagle == 1); - r_data = &val; - break; + case DSO_NODELAY: + if (r_len > sizeof(int)) + r_len = sizeof(int); + val = (scp->nonagle == 1); + r_data = &val; + break; - case DSO_CORK: - if (r_len > sizeof(int)) - r_len = sizeof(int); - val = (scp->nonagle == 2); - r_data = &val; - break; + case DSO_CORK: + if (r_len > sizeof(int)) + r_len = sizeof(int); + val = (scp->nonagle == 2); + r_data = &val; + break; - case DSO_SERVICES: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->services_rem; - break; + case DSO_SERVICES: + if (r_len > sizeof(unsigned char)) + r_len = sizeof(unsigned char); + r_data = &scp->services_rem; + break; - case DSO_INFO: - if (r_len > sizeof(unsigned char)) - r_len = sizeof(unsigned char); - r_data = &scp->info_rem; - break; + case DSO_INFO: + if (r_len > sizeof(unsigned char)) + r_len = sizeof(unsigned char); + r_data = &scp->info_rem; + break; } if (r_data) { @@ -2088,15 +2087,15 @@ static int dn_device_event(struct notifier_block *this, unsigned long event, if (!net_eq(dev_net(dev), &init_net)) return NOTIFY_DONE; - switch(event) { - case NETDEV_UP: - dn_dev_up(dev); - break; - case NETDEV_DOWN: - dn_dev_down(dev); - break; - default: - break; + switch (event) { + case NETDEV_UP: + dn_dev_up(dev); + break; + case NETDEV_DOWN: + dn_dev_down(dev); + break; + default: + break; } return NOTIFY_DONE; @@ -2209,54 +2208,54 @@ static void dn_printable_object(struct sockaddr_dn *dn, unsigned char *buf) int i; switch (le16_to_cpu(dn->sdn_objnamel)) { - case 0: - sprintf(buf, "%d", dn->sdn_objnum); - break; - default: - for (i = 0; i < le16_to_cpu(dn->sdn_objnamel); i++) { - buf[i] = dn->sdn_objname[i]; - if (IS_NOT_PRINTABLE(buf[i])) - buf[i] = '.'; - } - buf[i] = 0; + case 0: + sprintf(buf, "%d", dn->sdn_objnum); + break; + default: + for (i = 0; i < le16_to_cpu(dn->sdn_objnamel); i++) { + buf[i] = dn->sdn_objname[i]; + if (IS_NOT_PRINTABLE(buf[i])) + buf[i] = '.'; + } + buf[i] = 0; } } static char *dn_state2asc(unsigned char state) { - switch(state) { - case DN_O: - return "OPEN"; - case DN_CR: - return " CR"; - case DN_DR: - return " DR"; - case DN_DRC: - return " DRC"; - case DN_CC: - return " CC"; - case DN_CI: - return " CI"; - case DN_NR: - return " NR"; - case DN_NC: - return " NC"; - case DN_CD: - return " CD"; - case DN_RJ: - return " RJ"; - case DN_RUN: - return " RUN"; - case DN_DI: - return " DI"; - case DN_DIC: - return " DIC"; - case DN_DN: - return " DN"; - case DN_CL: - return " CL"; - case DN_CN: - return " CN"; + switch (state) { + case DN_O: + return "OPEN"; + case DN_CR: + return " CR"; + case DN_DR: + return " DR"; + case DN_DRC: + return " DRC"; + case DN_CC: + return " CC"; + case DN_CI: + return " CI"; + case DN_NR: + return " NR"; + case DN_NC: + return " NC"; + case DN_CD: + return " CD"; + case DN_RJ: + return " RJ"; + case DN_RUN: + return " RUN"; + case DN_DI: + return " DI"; + case DN_DIC: + return " DIC"; + case DN_DN: + return " DN"; + case DN_CL: + return " CL"; + case DN_CN: + return " CN"; } return "????"; diff --git a/net/decnet/dn_dev.c b/net/decnet/dn_dev.c index cf26ac74a18..ba4faceec40 100644 --- a/net/decnet/dn_dev.c +++ b/net/decnet/dn_dev.c @@ -437,17 +437,17 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) dev_load(&init_net, ifr->ifr_name); - switch(cmd) { - case SIOCGIFADDR: - break; - case SIOCSIFADDR: - if (!capable(CAP_NET_ADMIN)) - return -EACCES; - if (sdn->sdn_family != AF_DECnet) - return -EINVAL; - break; - default: + switch (cmd) { + case SIOCGIFADDR: + break; + case SIOCSIFADDR: + if (!capable(CAP_NET_ADMIN)) + return -EACCES; + if (sdn->sdn_family != AF_DECnet) return -EINVAL; + break; + default: + return -EINVAL; } rtnl_lock(); @@ -470,27 +470,27 @@ int dn_dev_ioctl(unsigned int cmd, void __user *arg) goto done; } - switch(cmd) { - case SIOCGIFADDR: - *((__le16 *)sdn->sdn_nodeaddr) = ifa->ifa_local; - goto rarok; - - case SIOCSIFADDR: - if (!ifa) { - if ((ifa = dn_dev_alloc_ifa()) == NULL) { - ret = -ENOBUFS; - break; - } - memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); - } else { - if (ifa->ifa_local == dn_saddr2dn(sdn)) - break; - dn_dev_del_ifa(dn_db, ifap, 0); + switch (cmd) { + case SIOCGIFADDR: + *((__le16 *)sdn->sdn_nodeaddr) = ifa->ifa_local; + goto rarok; + + case SIOCSIFADDR: + if (!ifa) { + if ((ifa = dn_dev_alloc_ifa()) == NULL) { + ret = -ENOBUFS; + break; } + memcpy(ifa->ifa_label, dev->name, IFNAMSIZ); + } else { + if (ifa->ifa_local == dn_saddr2dn(sdn)) + break; + dn_dev_del_ifa(dn_db, ifap, 0); + } - ifa->ifa_local = ifa->ifa_address = dn_saddr2dn(sdn); + ifa->ifa_local = ifa->ifa_address = dn_saddr2dn(sdn); - ret = dn_dev_set_ifa(dev, ifa); + ret = dn_dev_set_ifa(dev, ifa); } done: rtnl_unlock(); @@ -1313,7 +1313,7 @@ static void *dn_dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; - dev = (struct net_device *)v; + dev = v; if (v == SEQ_START_TOKEN) dev = net_device_entry(&init_net.dev_base_head); @@ -1335,13 +1335,13 @@ static void dn_dev_seq_stop(struct seq_file *seq, void *v) static char *dn_type2asc(char type) { - switch(type) { - case DN_DEV_BCAST: - return "B"; - case DN_DEV_UCAST: - return "U"; - case DN_DEV_MPOINT: - return "M"; + switch (type) { + case DN_DEV_BCAST: + return "B"; + case DN_DEV_UCAST: + return "U"; + case DN_DEV_MPOINT: + return "M"; } return "?"; @@ -1414,9 +1414,9 @@ void __init dn_dev_init(void) dn_dev_devices_on(); - rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL); - rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL); - rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr); + rtnl_register(PF_DECnet, RTM_NEWADDR, dn_nl_newaddr, NULL, NULL); + rtnl_register(PF_DECnet, RTM_DELADDR, dn_nl_deladdr, NULL, NULL); + rtnl_register(PF_DECnet, RTM_GETADDR, NULL, dn_nl_dump_ifaddr, NULL); proc_net_fops_create(&init_net, "decnet_dev", S_IRUGO, &dn_dev_seq_fops); diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index 1c74ed36ce8..2bd8e53d777 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -414,33 +414,34 @@ int dn_fib_semantic_match(int type, struct dn_fib_info *fi, const struct flowidn res->fi = fi; - switch(type) { - case RTN_NAT: - DN_FIB_RES_RESET(*res); + switch (type) { + case RTN_NAT: + DN_FIB_RES_RESET(*res); + atomic_inc(&fi->fib_clntref); + return 0; + case RTN_UNICAST: + case RTN_LOCAL: + for_nexthops(fi) { + if (nh->nh_flags & RTNH_F_DEAD) + continue; + if (!fld->flowidn_oif || + fld->flowidn_oif == nh->nh_oif) + break; + } + if (nhsel < fi->fib_nhs) { + res->nh_sel = nhsel; atomic_inc(&fi->fib_clntref); return 0; - case RTN_UNICAST: - case RTN_LOCAL: - for_nexthops(fi) { - if (nh->nh_flags & RTNH_F_DEAD) - continue; - if (!fld->flowidn_oif || - fld->flowidn_oif == nh->nh_oif) - break; - } - if (nhsel < fi->fib_nhs) { - res->nh_sel = nhsel; - atomic_inc(&fi->fib_clntref); - return 0; - } - endfor_nexthops(fi); - res->fi = NULL; - return 1; - default: - if (net_ratelimit()) - printk("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n", type); - res->fi = NULL; - return -EINVAL; + } + endfor_nexthops(fi); + res->fi = NULL; + return 1; + default: + if (net_ratelimit()) + printk("DECnet: impossible routing event : dn_fib_semantic_match type=%d\n", + type); + res->fi = NULL; + return -EINVAL; } } return err; @@ -647,20 +648,20 @@ static int dn_fib_dnaddr_event(struct notifier_block *this, unsigned long event, { struct dn_ifaddr *ifa = (struct dn_ifaddr *)ptr; - switch(event) { - case NETDEV_UP: - dn_fib_add_ifaddr(ifa); - dn_fib_sync_up(ifa->ifa_dev->dev); + switch (event) { + case NETDEV_UP: + dn_fib_add_ifaddr(ifa); + dn_fib_sync_up(ifa->ifa_dev->dev); + dn_rt_cache_flush(-1); + break; + case NETDEV_DOWN: + dn_fib_del_ifaddr(ifa); + if (ifa->ifa_dev && ifa->ifa_dev->ifa_list == NULL) { + dn_fib_disable_addr(ifa->ifa_dev->dev, 1); + } else { dn_rt_cache_flush(-1); - break; - case NETDEV_DOWN: - dn_fib_del_ifaddr(ifa); - if (ifa->ifa_dev && ifa->ifa_dev->ifa_list == NULL) { - dn_fib_disable_addr(ifa->ifa_dev->dev, 1); - } else { - dn_rt_cache_flush(-1); - } - break; + } + break; } return NOTIFY_DONE; } @@ -763,8 +764,8 @@ void __init dn_fib_init(void) register_dnaddr_notifier(&dn_fib_dnaddr_notifier); - rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL); - rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL); + rtnl_register(PF_DECnet, RTM_NEWROUTE, dn_fib_rtm_newroute, NULL, NULL); + rtnl_register(PF_DECnet, RTM_DELROUTE, dn_fib_rtm_delroute, NULL, NULL); } diff --git a/net/decnet/dn_neigh.c b/net/decnet/dn_neigh.c index 602dade7e9a..0dc3fe61085 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -51,9 +51,9 @@ static int dn_neigh_construct(struct neighbour *); static void dn_long_error_report(struct neighbour *, struct sk_buff *); static void dn_short_error_report(struct neighbour *, struct sk_buff *); -static int dn_long_output(struct sk_buff *); -static int dn_short_output(struct sk_buff *); -static int dn_phase3_output(struct sk_buff *); +static int dn_long_output(struct neighbour *, struct sk_buff *); +static int dn_short_output(struct neighbour *, struct sk_buff *); +static int dn_phase3_output(struct neighbour *, struct sk_buff *); /* @@ -64,8 +64,6 @@ static const struct neigh_ops dn_long_ops = { .error_report = dn_long_error_report, .output = dn_long_output, .connected_output = dn_long_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; /* @@ -76,8 +74,6 @@ static const struct neigh_ops dn_short_ops = { .error_report = dn_short_error_report, .output = dn_short_output, .connected_output = dn_short_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; /* @@ -88,8 +84,6 @@ static const struct neigh_ops dn_phase3_ops = { .error_report = dn_short_error_report, /* Can use short version here */ .output = dn_phase3_output, .connected_output = dn_phase3_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit }; static u32 dn_neigh_hash(const void *pkey, @@ -208,14 +202,14 @@ static int dn_neigh_output_packet(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct dn_route *rt = (struct dn_route *)dst; - struct neighbour *neigh = dst->neighbour; + struct neighbour *neigh = dst_get_neighbour(dst); struct net_device *dev = neigh->dev; char mac_addr[ETH_ALEN]; dn_dn2eth(mac_addr, rt->rt_local_src); if (dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, mac_addr, skb->len) >= 0) - return neigh->ops->queue_xmit(skb); + return dev_queue_xmit(skb); if (net_ratelimit()) printk(KERN_DEBUG "dn_neigh_output_packet: oops, can't send packet\n"); @@ -224,10 +218,8 @@ static int dn_neigh_output_packet(struct sk_buff *skb) return -EINVAL; } -static int dn_long_output(struct sk_buff *skb) +static int dn_long_output(struct neighbour *neigh, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_long_packet) + 3; unsigned char *data; @@ -271,10 +263,8 @@ static int dn_long_output(struct sk_buff *skb) neigh->dev, dn_neigh_output_packet); } -static int dn_short_output(struct sk_buff *skb) +static int dn_short_output(struct neighbour *neigh, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; struct dn_short_packet *sp; @@ -315,10 +305,8 @@ static int dn_short_output(struct sk_buff *skb) * Phase 3 output is the same is short output, execpt that * it clears the area bits before transmission. */ -static int dn_phase3_output(struct sk_buff *skb) +static int dn_phase3_output(struct neighbour *neigh, struct sk_buff *skb) { - struct dst_entry *dst = skb_dst(skb); - struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; int headroom = dev->hard_header_len + sizeof(struct dn_short_packet) + 2; struct dn_short_packet *sp; @@ -404,13 +392,13 @@ int dn_neigh_router_hello(struct sk_buff *skb) dn->flags &= ~DN_NDFLAG_P3; - switch(msg->iinfo & DN_RT_INFO_TYPE) { - case DN_RT_INFO_L1RT: - dn->flags &=~DN_NDFLAG_R2; - dn->flags |= DN_NDFLAG_R1; - break; - case DN_RT_INFO_L2RT: - dn->flags |= DN_NDFLAG_R2; + switch (msg->iinfo & DN_RT_INFO_TYPE) { + case DN_RT_INFO_L1RT: + dn->flags &=~DN_NDFLAG_R2; + dn->flags |= DN_NDFLAG_R1; + break; + case DN_RT_INFO_L2RT: + dn->flags |= DN_NDFLAG_R2; } } diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c index b430549e2b9..73fa268fe2e 100644 --- a/net/decnet/dn_nsp_in.c +++ b/net/decnet/dn_nsp_in.c @@ -101,23 +101,27 @@ static void dn_ack(struct sock *sk, struct sk_buff *skb, unsigned short ack) unsigned short type = ((ack >> 12) & 0x0003); int wakeup = 0; - switch(type) { - case 0: /* ACK - Data */ - if (dn_after(ack, scp->ackrcv_dat)) { - scp->ackrcv_dat = ack & 0x0fff; - wakeup |= dn_nsp_check_xmit_queue(sk, skb, &scp->data_xmit_queue, ack); - } - break; - case 1: /* NAK - Data */ - break; - case 2: /* ACK - OtherData */ - if (dn_after(ack, scp->ackrcv_oth)) { - scp->ackrcv_oth = ack & 0x0fff; - wakeup |= dn_nsp_check_xmit_queue(sk, skb, &scp->other_xmit_queue, ack); - } - break; - case 3: /* NAK - OtherData */ - break; + switch (type) { + case 0: /* ACK - Data */ + if (dn_after(ack, scp->ackrcv_dat)) { + scp->ackrcv_dat = ack & 0x0fff; + wakeup |= dn_nsp_check_xmit_queue(sk, skb, + &scp->data_xmit_queue, + ack); + } + break; + case 1: /* NAK - Data */ + break; + case 2: /* ACK - OtherData */ + if (dn_after(ack, scp->ackrcv_oth)) { + scp->ackrcv_oth = ack & 0x0fff; + wakeup |= dn_nsp_check_xmit_queue(sk, skb, + &scp->other_xmit_queue, + ack); + } + break; + case 3: /* NAK - OtherData */ + break; } if (wakeup && !sock_flag(sk, SOCK_DEAD)) @@ -417,19 +421,19 @@ static void dn_nsp_disc_init(struct sock *sk, struct sk_buff *skb) scp->addrrem = cb->src_port; sk->sk_state = TCP_CLOSE; - switch(scp->state) { - case DN_CI: - case DN_CD: - scp->state = DN_RJ; - sk->sk_err = ECONNREFUSED; - break; - case DN_RUN: - sk->sk_shutdown |= SHUTDOWN_MASK; - scp->state = DN_DN; - break; - case DN_DI: - scp->state = DN_DIC; - break; + switch (scp->state) { + case DN_CI: + case DN_CD: + scp->state = DN_RJ; + sk->sk_err = ECONNREFUSED; + break; + case DN_RUN: + sk->sk_shutdown |= SHUTDOWN_MASK; + scp->state = DN_DN; + break; + case DN_DI: + scp->state = DN_DIC; + break; } if (!sock_flag(sk, SOCK_DEAD)) { @@ -470,23 +474,23 @@ static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb) sk->sk_state = TCP_CLOSE; - switch(scp->state) { - case DN_CI: - scp->state = DN_NR; - break; - case DN_DR: - if (reason == NSP_REASON_DC) - scp->state = DN_DRC; - if (reason == NSP_REASON_NL) - scp->state = DN_CN; - break; - case DN_DI: - scp->state = DN_DIC; - break; - case DN_RUN: - sk->sk_shutdown |= SHUTDOWN_MASK; - case DN_CC: + switch (scp->state) { + case DN_CI: + scp->state = DN_NR; + break; + case DN_DR: + if (reason == NSP_REASON_DC) + scp->state = DN_DRC; + if (reason == NSP_REASON_NL) scp->state = DN_CN; + break; + case DN_DI: + scp->state = DN_DIC; + break; + case DN_RUN: + sk->sk_shutdown |= SHUTDOWN_MASK; + case DN_CC: + scp->state = DN_CN; } if (!sock_flag(sk, SOCK_DEAD)) { @@ -692,16 +696,16 @@ static int dn_nsp_no_socket(struct sk_buff *skb, unsigned short reason) goto out; if ((reason != NSP_REASON_OK) && ((cb->nsp_flags & 0x0c) == 0x08)) { - switch(cb->nsp_flags & 0x70) { - case 0x10: - case 0x60: /* (Retransmitted) Connect Init */ - dn_nsp_return_disc(skb, NSP_DISCINIT, reason); - ret = NET_RX_SUCCESS; - break; - case 0x20: /* Connect Confirm */ - dn_nsp_return_disc(skb, NSP_DISCCONF, reason); - ret = NET_RX_SUCCESS; - break; + switch (cb->nsp_flags & 0x70) { + case 0x10: + case 0x60: /* (Retransmitted) Connect Init */ + dn_nsp_return_disc(skb, NSP_DISCINIT, reason); + ret = NET_RX_SUCCESS; + break; + case 0x20: /* Connect Confirm */ + dn_nsp_return_disc(skb, NSP_DISCCONF, reason); + ret = NET_RX_SUCCESS; + break; } } @@ -733,17 +737,17 @@ static int dn_nsp_rx_packet(struct sk_buff *skb) * Filter out conninits and useless packet types */ if ((cb->nsp_flags & 0x0c) == 0x08) { - switch(cb->nsp_flags & 0x70) { - case 0x00: /* NOP */ - case 0x70: /* Reserved */ - case 0x50: /* Reserved, Phase II node init */ + switch (cb->nsp_flags & 0x70) { + case 0x00: /* NOP */ + case 0x70: /* Reserved */ + case 0x50: /* Reserved, Phase II node init */ + goto free_out; + case 0x10: + case 0x60: + if (unlikely(cb->rt_flags & DN_RT_F_RTS)) goto free_out; - case 0x10: - case 0x60: - if (unlikely(cb->rt_flags & DN_RT_F_RTS)) - goto free_out; - sk = dn_find_listener(skb, &reason); - goto got_it; + sk = dn_find_listener(skb, &reason); + goto got_it; } } @@ -836,20 +840,20 @@ int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb) * Control packet. */ if ((cb->nsp_flags & 0x0c) == 0x08) { - switch(cb->nsp_flags & 0x70) { - case 0x10: - case 0x60: - dn_nsp_conn_init(sk, skb); - break; - case 0x20: - dn_nsp_conn_conf(sk, skb); - break; - case 0x30: - dn_nsp_disc_init(sk, skb); - break; - case 0x40: - dn_nsp_disc_conf(sk, skb); - break; + switch (cb->nsp_flags & 0x70) { + case 0x10: + case 0x60: + dn_nsp_conn_init(sk, skb); + break; + case 0x20: + dn_nsp_conn_conf(sk, skb); + break; + case 0x30: + dn_nsp_disc_init(sk, skb); + break; + case 0x40: + dn_nsp_disc_conf(sk, skb); + break; } } else if (cb->nsp_flags == 0x24) { @@ -890,15 +894,15 @@ int dn_nsp_backlog_rcv(struct sock *sk, struct sk_buff *skb) if (scp->state != DN_RUN) goto free_out; - switch(cb->nsp_flags) { - case 0x10: /* LS */ - dn_nsp_linkservice(sk, skb); - break; - case 0x30: /* OD */ - dn_nsp_otherdata(sk, skb); - break; - default: - dn_nsp_data(sk, skb); + switch (cb->nsp_flags) { + case 0x10: /* LS */ + dn_nsp_linkservice(sk, skb); + break; + case 0x30: /* OD */ + dn_nsp_otherdata(sk, skb); + break; + default: + dn_nsp_data(sk, skb); } } else { /* Ack, chuck it out here */ diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 74544bc6fde..43450c10022 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -116,6 +116,7 @@ static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu); +static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr); static int dn_route_input(struct sk_buff *); static void dn_run_flush(unsigned long dummy); @@ -139,6 +140,7 @@ static struct dst_ops dn_dst_ops = { .negative_advice = dn_dst_negative_advice, .link_failure = dn_dst_link_failure, .update_pmtu = dn_dst_update_pmtu, + .neigh_lookup = dn_dst_neigh_lookup, }; static void dn_dst_destroy(struct dst_entry *dst) @@ -241,9 +243,11 @@ static int dn_dst_gc(struct dst_ops *ops) */ static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu) { + struct neighbour *n = dst_get_neighbour(dst); u32 min_mtu = 230; - struct dn_dev *dn = dst->neighbour ? - rcu_dereference_raw(dst->neighbour->dev->dn_ptr) : NULL; + struct dn_dev *dn; + + dn = n ? rcu_dereference_raw(n->dev->dn_ptr) : NULL; if (dn && dn->use_long == 0) min_mtu -= 6; @@ -495,11 +499,11 @@ static int dn_route_rx_packet(struct sk_buff *skb) } if ((skb->pkt_type == PACKET_HOST) && (cb->rt_flags & DN_RT_F_RQR)) { - switch(cb->rt_flags & DN_RT_PKT_MSK) { - case DN_RT_PKT_SHORT: - return dn_return_short(skb); - case DN_RT_PKT_LONG: - return dn_return_long(skb); + switch (cb->rt_flags & DN_RT_PKT_MSK) { + case DN_RT_PKT_SHORT: + return dn_return_short(skb); + case DN_RT_PKT_LONG: + return dn_return_long(skb); } } @@ -652,38 +656,38 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type if (unlikely(skb_linearize(skb))) goto dump_it; - switch(flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_INIT: - dn_dev_init_pkt(skb); - break; - case DN_RT_PKT_VERI: - dn_dev_veri_pkt(skb); - break; + switch (flags & DN_RT_CNTL_MSK) { + case DN_RT_PKT_INIT: + dn_dev_init_pkt(skb); + break; + case DN_RT_PKT_VERI: + dn_dev_veri_pkt(skb); + break; } if (dn->parms.state != DN_DEV_S_RU) goto dump_it; - switch(flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_HELO: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - skb, skb->dev, NULL, - dn_route_ptp_hello); - - case DN_RT_PKT_L1RT: - case DN_RT_PKT_L2RT: - return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE, - skb, skb->dev, NULL, - dn_route_discard); - case DN_RT_PKT_ERTH: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - skb, skb->dev, NULL, - dn_neigh_router_hello); - - case DN_RT_PKT_EEDH: - return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, - skb, skb->dev, NULL, - dn_neigh_endnode_hello); + switch (flags & DN_RT_CNTL_MSK) { + case DN_RT_PKT_HELO: + return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, + skb, skb->dev, NULL, + dn_route_ptp_hello); + + case DN_RT_PKT_L1RT: + case DN_RT_PKT_L2RT: + return NF_HOOK(NFPROTO_DECNET, NF_DN_ROUTE, + skb, skb->dev, NULL, + dn_route_discard); + case DN_RT_PKT_ERTH: + return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, + skb, skb->dev, NULL, + dn_neigh_router_hello); + + case DN_RT_PKT_EEDH: + return NF_HOOK(NFPROTO_DECNET, NF_DN_HELLO, + skb, skb->dev, NULL, + dn_neigh_endnode_hello); } } else { if (dn->parms.state != DN_DEV_S_RU) @@ -691,11 +695,11 @@ int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type skb_pull(skb, 1); /* Pull flags */ - switch(flags & DN_RT_PKT_MSK) { - case DN_RT_PKT_LONG: - return dn_route_rx_long(skb); - case DN_RT_PKT_SHORT: - return dn_route_rx_short(skb); + switch (flags & DN_RT_PKT_MSK) { + case DN_RT_PKT_LONG: + return dn_route_rx_long(skb); + case DN_RT_PKT_SHORT: + return dn_route_rx_short(skb); } } @@ -705,6 +709,14 @@ out: return NET_RX_DROP; } +static int dn_to_neigh_output(struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct neighbour *n = dst_get_neighbour(dst); + + return n->output(n, skb); +} + static int dn_output(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -715,7 +727,7 @@ static int dn_output(struct sk_buff *skb) int err = -EINVAL; - if ((neigh = dst->neighbour) == NULL) + if ((neigh = dst_get_neighbour(dst)) == NULL) goto error; skb->dev = dev; @@ -733,7 +745,7 @@ static int dn_output(struct sk_buff *skb) cb->hops = 0; return NF_HOOK(NFPROTO_DECNET, NF_DN_LOCAL_OUT, skb, NULL, dev, - neigh->output); + dn_to_neigh_output); error: if (net_ratelimit()) @@ -750,7 +762,6 @@ static int dn_forward(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct dn_dev *dn_db = rcu_dereference(dst->dev->dn_ptr); struct dn_route *rt; - struct neighbour *neigh = dst->neighbour; int header_len; #ifdef CONFIG_NETFILTER struct net_device *dev = skb->dev; @@ -783,7 +794,7 @@ static int dn_forward(struct sk_buff *skb) cb->rt_flags |= DN_RT_F_IE; return NF_HOOK(NFPROTO_DECNET, NF_DN_FORWARD, skb, dev, skb->dev, - neigh->output); + dn_to_neigh_output); drop: kfree_skb(skb); @@ -818,6 +829,11 @@ static unsigned int dn_dst_default_mtu(const struct dst_entry *dst) return dst->dev->mtu; } +static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + return __neigh_lookup_errno(&dn_neigh_table, daddr, dst->dev); +} + static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) { struct dn_fib_info *fi = res->fi; @@ -833,11 +849,11 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) } rt->rt_type = res->type; - if (dev != NULL && rt->dst.neighbour == NULL) { + if (dev != NULL && dst_get_neighbour(&rt->dst) == NULL) { n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev); if (IS_ERR(n)) return PTR_ERR(n); - rt->dst.neighbour = n; + dst_set_neighbour(&rt->dst, n); } if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) @@ -1144,7 +1160,7 @@ make_route: rt->rt_dst_map = fld.daddr; rt->rt_src_map = fld.saddr; - rt->dst.neighbour = neigh; + dst_set_neighbour(&rt->dst, neigh); neigh = NULL; rt->dst.lastuse = jiffies; @@ -1416,23 +1432,23 @@ make_route: rt->fld.flowidn_iif = in_dev->ifindex; rt->fld.flowidn_mark = fld.flowidn_mark; - rt->dst.neighbour = neigh; + dst_set_neighbour(&rt->dst, neigh); rt->dst.lastuse = jiffies; rt->dst.output = dn_rt_bug; - switch(res.type) { - case RTN_UNICAST: - rt->dst.input = dn_forward; - break; - case RTN_LOCAL: - rt->dst.output = dn_output; - rt->dst.input = dn_nsp_rx; - rt->dst.dev = in_dev; - flags |= RTCF_LOCAL; - break; - default: - case RTN_UNREACHABLE: - case RTN_BLACKHOLE: - rt->dst.input = dst_discard; + switch (res.type) { + case RTN_UNICAST: + rt->dst.input = dn_forward; + break; + case RTN_LOCAL: + rt->dst.output = dn_output; + rt->dst.input = dn_nsp_rx; + rt->dst.dev = in_dev; + flags |= RTCF_LOCAL; + break; + default: + case RTN_UNREACHABLE: + case RTN_BLACKHOLE: + rt->dst.input = dst_discard; } rt->rt_flags = flags; @@ -1841,10 +1857,11 @@ void __init dn_route_init(void) proc_net_fops_create(&init_net, "decnet_cache", S_IRUGO, &dn_rt_cache_seq_fops); #ifdef CONFIG_DECNET_ROUTER - rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, dn_fib_dump); + rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, + dn_fib_dump, NULL); #else rtnl_register(PF_DECnet, RTM_GETROUTE, dn_cache_getroute, - dn_cache_dump); + dn_cache_dump, NULL); #endif } diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index bd0a52dd1d4..cd0354e9bdb 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -147,17 +147,18 @@ static void dn_rehash_zone(struct dn_zone *dz) old_divisor = dz->dz_divisor; - switch(old_divisor) { - case 16: - new_divisor = 256; - new_hashmask = 0xFF; - break; - default: - printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", old_divisor); - case 256: - new_divisor = 1024; - new_hashmask = 0x3FF; - break; + switch (old_divisor) { + case 16: + new_divisor = 256; + new_hashmask = 0xFF; + break; + default: + printk(KERN_DEBUG "DECnet: dn_rehash_zone: BUG! %d\n", + old_divisor); + case 256: + new_divisor = 1024; + new_hashmask = 0x3FF; + break; } ht = kcalloc(new_divisor, sizeof(struct dn_fib_node*), GFP_KERNEL); diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c index 64a7f39e069..69975e0bcde 100644 --- a/net/decnet/netfilter/dn_rtmsg.c +++ b/net/decnet/netfilter/dn_rtmsg.c @@ -69,15 +69,15 @@ static void dnrmg_send_peer(struct sk_buff *skb) int group = 0; unsigned char flags = *skb->data; - switch(flags & DN_RT_CNTL_MSK) { - case DN_RT_PKT_L1RT: - group = DNRNG_NLGRP_L1; - break; - case DN_RT_PKT_L2RT: - group = DNRNG_NLGRP_L2; - break; - default: - return; + switch (flags & DN_RT_CNTL_MSK) { + case DN_RT_PKT_L1RT: + group = DNRNG_NLGRP_L1; + break; + case DN_RT_PKT_L2RT: + group = DNRNG_NLGRP_L2; + break; + default: + return; } skb2 = dnrmg_build_message(skb, &status); diff --git a/net/decnet/sysctl_net_decnet.c b/net/decnet/sysctl_net_decnet.c index 28f8b5e5f73..02e75d11cfb 100644 --- a/net/decnet/sysctl_net_decnet.c +++ b/net/decnet/sysctl_net_decnet.c @@ -68,14 +68,15 @@ static struct ctl_table_header *dn_table_header = NULL; static void strip_it(char *str) { for(;;) { - switch(*str) { - case ' ': - case '\n': - case '\r': - case ':': - *str = 0; - case 0: - return; + switch (*str) { + case ' ': + case '\n': + case '\r': + case ':': + *str = 0; + /* Fallthrough */ + case 0: + return; } str++; } diff --git a/net/dsa/mv88e6131.c b/net/dsa/mv88e6131.c index 45f7411e90b..9bd1061fa4e 100644 --- a/net/dsa/mv88e6131.c +++ b/net/dsa/mv88e6131.c @@ -118,10 +118,14 @@ static int mv88e6131_setup_global(struct dsa_switch *ds) REG_WRITE(REG_GLOBAL, 0x1a, (dsa_upstream_port(ds) * 0x1100) | 0x00f0); /* - * Disable cascade port functionality, and set the switch's + * Disable cascade port functionality unless this device + * is used in a cascade configuration, and set the switch's * DSA device number. */ - REG_WRITE(REG_GLOBAL, 0x1c, 0xe000 | (ds->index & 0x1f)); + if (ds->dst->pd->nr_chips > 1) + REG_WRITE(REG_GLOBAL, 0x1c, 0xf000 | (ds->index & 0x1f)); + else + REG_WRITE(REG_GLOBAL, 0x1c, 0xe000 | (ds->index & 0x1f)); /* * Send all frames with destination addresses matching diff --git a/net/econet/af_econet.c b/net/econet/af_econet.c index a1d9f3787dd..1c1f26c5d67 100644 --- a/net/econet/af_econet.c +++ b/net/econet/af_econet.c @@ -9,6 +9,8 @@ * */ +#define pr_fmt(fmt) fmt + #include <linux/module.h> #include <linux/types.h> @@ -44,7 +46,7 @@ #include <linux/bitops.h> #include <linux/mutex.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <asm/system.h> static const struct proto_ops econet_ops; @@ -63,9 +65,7 @@ static DEFINE_SPINLOCK(aun_queue_lock); static struct socket *udpsock; #define AUN_PORT 0x8000 - -struct aunhdr -{ +struct aunhdr { unsigned char code; /* AUN magic protocol byte */ unsigned char port; unsigned char cb; @@ -82,8 +82,7 @@ static struct timer_list ab_cleanup_timer; #endif /* CONFIG_ECONET_AUNUDP */ /* Per-packet information */ -struct ec_cb -{ +struct ec_cb { struct sockaddr_ec sec; unsigned long cookie; /* Supplied by user. */ #ifdef CONFIG_ECONET_AUNUDP @@ -137,7 +136,7 @@ static int econet_recvmsg(struct kiocb *iocb, struct socket *sock, * but then it will block. */ - skb=skb_recv_datagram(sk,flags,flags&MSG_DONTWAIT,&err); + skb = skb_recv_datagram(sk, flags, flags & MSG_DONTWAIT, &err); /* * An error occurred so return it. Because skb_recv_datagram() @@ -145,7 +144,7 @@ static int econet_recvmsg(struct kiocb *iocb, struct socket *sock, * retries. */ - if(skb==NULL) + if (skb == NULL) goto out; /* @@ -154,10 +153,9 @@ static int econet_recvmsg(struct kiocb *iocb, struct socket *sock, */ copied = skb->len; - if (copied > len) - { - copied=len; - msg->msg_flags|=MSG_TRUNC; + if (copied > len) { + copied = len; + msg->msg_flags |= MSG_TRUNC; } /* We can't use skb_copy_datagram here */ @@ -186,7 +184,8 @@ out: * Bind an Econet socket. */ -static int econet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +static int econet_bind(struct socket *sock, struct sockaddr *uaddr, + int addr_len) { struct sockaddr_ec *sec = (struct sockaddr_ec *)uaddr; struct sock *sk; @@ -226,9 +225,8 @@ static void tx_result(struct sock *sk, unsigned long cookie, int result) struct ec_cb *eb; struct sockaddr_ec *sec; - if (skb == NULL) - { - printk(KERN_DEBUG "ec: memory squeeze, transmit result dropped.\n"); + if (skb == NULL) { + pr_debug("econet: memory squeeze, transmit result dropped\n"); return; } @@ -265,7 +263,7 @@ static void ec_tx_done(struct sk_buff *skb, int result) static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, size_t len) { - struct sockaddr_ec *saddr=(struct sockaddr_ec *)msg->msg_name; + struct sockaddr_ec *saddr = (struct sockaddr_ec *)msg->msg_name; struct net_device *dev; struct ec_addr addr; int err; @@ -298,14 +296,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, mutex_lock(&econet_mutex); - if (saddr == NULL || msg->msg_namelen < sizeof(struct sockaddr_ec)) { - mutex_unlock(&econet_mutex); - return -EINVAL; - } - addr.station = saddr->addr.station; - addr.net = saddr->addr.net; - port = saddr->port; - cb = saddr->cb; + if (saddr == NULL || msg->msg_namelen < sizeof(struct sockaddr_ec)) { + mutex_unlock(&econet_mutex); + return -EINVAL; + } + addr.station = saddr->addr.station; + addr.net = saddr->addr.net; + port = saddr->port; + cb = saddr->cb; /* Look for a device with the right network number. */ dev = net2dev_map[addr.net]; @@ -333,9 +331,9 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, dev_hold(dev); - skb = sock_alloc_send_skb(sk, len+LL_ALLOCATED_SPACE(dev), + skb = sock_alloc_send_skb(sk, len + LL_ALLOCATED_SPACE(dev), msg->msg_flags & MSG_DONTWAIT, &err); - if (skb==NULL) + if (skb == NULL) goto out_unlock; skb_reserve(skb, LL_RESERVED_SPACE(dev)); @@ -355,7 +353,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, struct ec_framehdr *fh; /* Poke in our control byte and port number. Hack, hack. */ - fh = (struct ec_framehdr *)(skb->data); + fh = (struct ec_framehdr *)skb->data; fh->cb = cb; fh->port = port; if (sock->type != SOCK_DGRAM) { @@ -365,7 +363,7 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, } /* Copy the data. Returns -EFAULT on error */ - err = memcpy_fromiovec(skb_put(skb,len), msg->msg_iov, len); + err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); skb->protocol = proto; skb->dev = dev; skb->priority = sk->sk_priority; @@ -385,9 +383,9 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, mutex_unlock(&econet_mutex); return len; - out_free: +out_free: kfree_skb(skb); - out_unlock: +out_unlock: if (dev) dev_put(dev); #else @@ -458,15 +456,14 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, goto error_free_buf; /* Get a skbuff (no data, just holds our cb information) */ - if ((skb = sock_alloc_send_skb(sk, 0, - msg->msg_flags & MSG_DONTWAIT, - &err)) == NULL) + skb = sock_alloc_send_skb(sk, 0, msg->msg_flags & MSG_DONTWAIT, &err); + if (skb == NULL) goto error_free_buf; eb = (struct ec_cb *)&skb->cb; eb->cookie = saddr->cookie; - eb->timeout = (5*HZ); + eb->timeout = 5 * HZ; eb->start = jiffies; ah.handle = aun_seq; eb->seq = (aun_seq++); @@ -480,9 +477,10 @@ static int econet_sendmsg(struct kiocb *iocb, struct socket *sock, udpmsg.msg_iovlen = 2; udpmsg.msg_control = NULL; udpmsg.msg_controllen = 0; - udpmsg.msg_flags=0; + udpmsg.msg_flags = 0; - oldfs = get_fs(); set_fs(KERNEL_DS); /* More privs :-) */ + oldfs = get_fs(); + set_fs(KERNEL_DS); /* More privs :-) */ err = sock_sendmsg(udpsock, &udpmsg, size); set_fs(oldfs); @@ -530,7 +528,7 @@ static int econet_getname(struct socket *sock, struct sockaddr *uaddr, static void econet_destroy_timer(unsigned long data) { - struct sock *sk=(struct sock *)data; + struct sock *sk = (struct sock *)data; if (!sk_has_allocations(sk)) { sk_free(sk); @@ -539,7 +537,7 @@ static void econet_destroy_timer(unsigned long data) sk->sk_timer.expires = jiffies + 10 * HZ; add_timer(&sk->sk_timer); - printk(KERN_DEBUG "econet socket destroy delayed\n"); + pr_debug("econet: socket destroy delayed\n"); } /* @@ -651,7 +649,8 @@ static int ec_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; - if ((dev = dev_get_by_name(&init_net, ifr.ifr_name)) == NULL) + dev = dev_get_by_name(&init_net, ifr.ifr_name); + if (dev == NULL) return -ENODEV; sec = (struct sockaddr_ec *)&ifr.ifr_addr; @@ -715,28 +714,26 @@ static int ec_dev_ioctl(struct socket *sock, unsigned int cmd, void __user *arg) * Handle generic ioctls */ -static int econet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +static int econet_ioctl(struct socket *sock, unsigned int cmd, + unsigned long arg) { struct sock *sk = sock->sk; void __user *argp = (void __user *)arg; - switch(cmd) { - case SIOCGSTAMP: - return sock_get_timestamp(sk, argp); + switch (cmd) { + case SIOCGSTAMP: + return sock_get_timestamp(sk, argp); - case SIOCGSTAMPNS: - return sock_get_timestampns(sk, argp); + case SIOCGSTAMPNS: + return sock_get_timestampns(sk, argp); - case SIOCSIFADDR: - case SIOCGIFADDR: - return ec_dev_ioctl(sock, cmd, argp); - break; + case SIOCSIFADDR: + case SIOCGIFADDR: + return ec_dev_ioctl(sock, cmd, argp); - default: - return -ENOIOCTLCMD; } - /*NOTREACHED*/ - return 0; + + return -ENOIOCTLCMD; } static const struct net_proto_family econet_family_ops = { @@ -836,7 +833,7 @@ static void aun_send_response(__u32 addr, unsigned long seq, int code, int cb) udpmsg.msg_namelen = sizeof(sin); udpmsg.msg_control = NULL; udpmsg.msg_controllen = 0; - udpmsg.msg_flags=0; + udpmsg.msg_flags = 0; kernel_sendmsg(udpsock, &udpmsg, &iov, 1, sizeof(ah)); } @@ -859,26 +856,25 @@ static void aun_incoming(struct sk_buff *skb, struct aunhdr *ah, size_t len) if (dst) edev = dst->dev->ec_ptr; - if (! edev) + if (!edev) goto bad; - if ((sk = ec_listening_socket(ah->port, stn, edev->net)) == NULL) + sk = ec_listening_socket(ah->port, stn, edev->net); + if (sk == NULL) goto bad; /* Nobody wants it */ newskb = alloc_skb((len - sizeof(struct aunhdr) + 15) & ~15, GFP_ATOMIC); - if (newskb == NULL) - { - printk(KERN_DEBUG "AUN: memory squeeze, dropping packet.\n"); + if (newskb == NULL) { + pr_debug("AUN: memory squeeze, dropping packet\n"); /* Send nack and hope sender tries again */ goto bad; } - memcpy(skb_put(newskb, len - sizeof(struct aunhdr)), (void *)(ah+1), + memcpy(skb_put(newskb, len - sizeof(struct aunhdr)), (void *)(ah + 1), len - sizeof(struct aunhdr)); - if (ec_queue_packet(sk, newskb, stn, edev->net, ah->cb, ah->port)) - { + if (ec_queue_packet(sk, newskb, stn, edev->net, ah->cb, ah->port)) { /* Socket is bankrupt. */ kfree_skb(newskb); goto bad; @@ -914,7 +910,7 @@ static void aun_tx_ack(unsigned long seq, int result) goto foundit; } spin_unlock_irqrestore(&aun_queue_lock, flags); - printk(KERN_DEBUG "AUN: unknown sequence %ld\n", seq); + pr_debug("AUN: unknown sequence %ld\n", seq); return; foundit: @@ -939,18 +935,17 @@ static void aun_data_available(struct sock *sk, int slen) while ((skb = skb_recv_datagram(sk, 0, 1, &err)) == NULL) { if (err == -EAGAIN) { - printk(KERN_ERR "AUN: no data available?!"); + pr_err("AUN: no data available?!\n"); return; } - printk(KERN_DEBUG "AUN: recvfrom() error %d\n", -err); + pr_debug("AUN: recvfrom() error %d\n", -err); } data = skb_transport_header(skb) + sizeof(struct udphdr); ah = (struct aunhdr *)data; len = skb->len - sizeof(struct udphdr); - switch (ah->code) - { + switch (ah->code) { case 2: aun_incoming(skb, ah, len); break; @@ -961,7 +956,7 @@ static void aun_data_available(struct sock *sk, int slen) aun_tx_ack(ah->handle, ECTYPE_TRANSMIT_NOT_LISTENING); break; default: - printk(KERN_DEBUG "unknown AUN packet (type %d)\n", data[0]); + pr_debug("AUN: unknown packet type: %d\n", data[0]); } skb_free_datagram(sk, skb); @@ -991,7 +986,7 @@ static void ab_cleanup(unsigned long h) } spin_unlock_irqrestore(&aun_queue_lock, flags); - mod_timer(&ab_cleanup_timer, jiffies + (HZ*2)); + mod_timer(&ab_cleanup_timer, jiffies + (HZ * 2)); } static int __init aun_udp_initialise(void) @@ -1001,7 +996,7 @@ static int __init aun_udp_initialise(void) skb_queue_head_init(&aun_queue); setup_timer(&ab_cleanup_timer, ab_cleanup, 0); - ab_cleanup_timer.expires = jiffies + (HZ*2); + ab_cleanup_timer.expires = jiffies + (HZ * 2); add_timer(&ab_cleanup_timer); memset(&sin, 0, sizeof(sin)); @@ -1009,9 +1004,9 @@ static int __init aun_udp_initialise(void) /* We can count ourselves lucky Acorn machines are too dim to speak IPv6. :-) */ - if ((error = sock_create_kern(PF_INET, SOCK_DGRAM, 0, &udpsock)) < 0) - { - printk("AUN: socket error %d\n", -error); + error = sock_create_kern(PF_INET, SOCK_DGRAM, 0, &udpsock); + if (error < 0) { + pr_err("AUN: socket error %d\n", -error); return error; } @@ -1020,10 +1015,9 @@ static int __init aun_udp_initialise(void) from interrupts */ error = udpsock->ops->bind(udpsock, (struct sockaddr *)&sin, - sizeof(sin)); - if (error < 0) - { - printk("AUN: bind error %d\n", -error); + sizeof(sin)); + if (error < 0) { + pr_err("AUN: bind error %d\n", -error); goto release; } @@ -1044,7 +1038,8 @@ release: * Receive an Econet frame from a device. */ -static int econet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) +static int econet_rcv(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) { struct ec_framehdr *hdr; struct sock *sk = NULL; @@ -1059,13 +1054,14 @@ static int econet_rcv(struct sk_buff *skb, struct net_device *dev, struct packet if (!edev) goto drop; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (skb == NULL) return NET_RX_DROP; if (!pskb_may_pull(skb, sizeof(struct ec_framehdr))) goto drop; - hdr = (struct ec_framehdr *) skb->data; + hdr = (struct ec_framehdr *)skb->data; /* First check for encapsulated IP */ if (hdr->port == EC_PORT_IP) { @@ -1093,8 +1089,8 @@ drop: } static struct packet_type econet_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_ECONET), - .func = econet_rcv, + .type = cpu_to_be16(ETH_P_ECONET), + .func = econet_rcv, }; static void econet_hw_initialise(void) @@ -1104,9 +1100,10 @@ static void econet_hw_initialise(void) #endif -static int econet_notifier(struct notifier_block *this, unsigned long msg, void *data) +static int econet_notifier(struct notifier_block *this, unsigned long msg, + void *data) { - struct net_device *dev = (struct net_device *)data; + struct net_device *dev = data; struct ec_device *edev; if (!net_eq(dev_net(dev), &init_net)) @@ -1116,8 +1113,7 @@ static int econet_notifier(struct notifier_block *this, unsigned long msg, void case NETDEV_UNREGISTER: /* A device has gone down - kill any data we hold for it. */ edev = dev->ec_ptr; - if (edev) - { + if (edev) { if (net2dev_map[0] == dev) net2dev_map[0] = NULL; net2dev_map[edev->net] = NULL; @@ -1131,7 +1127,7 @@ static int econet_notifier(struct notifier_block *this, unsigned long msg, void } static struct notifier_block econet_netdev_notifier = { - .notifier_call =econet_notifier, + .notifier_call = econet_notifier, }; static void __exit econet_proto_exit(void) diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 44d2b42fda5..5cffb63f481 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -233,9 +233,8 @@ EXPORT_SYMBOL(eth_header_parse); * @hh: destination cache entry * Create an Ethernet header template from the neighbour. */ -int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh) +int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 type) { - __be16 type = hh->hh_type; struct ethhdr *eth; const struct net_device *dev = neigh->dev; diff --git a/net/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 6df6ecf4970..40e606f3788 100644 --- a/net/ieee802154/af_ieee802154.c +++ b/net/ieee802154/af_ieee802154.c @@ -302,7 +302,7 @@ static int ieee802154_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { if (!netif_running(dev)) - return -ENODEV; + goto drop; pr_debug("got frame, type %d, dev %p\n", dev->type, dev); #ifdef DEBUG print_hex_dump_bytes("ieee802154_rcv ", DUMP_PREFIX_NONE, skb->data, skb->len); diff --git a/net/ieee802154/dgram.c b/net/ieee802154/dgram.c index 1a3334c2609..faecf648123 100644 --- a/net/ieee802154/dgram.c +++ b/net/ieee802154/dgram.c @@ -1,5 +1,5 @@ /* - * ZigBee socket interface + * IEEE 802.15.4 dgram socket interface * * Copyright 2007, 2008 Siemens AG * diff --git a/net/ieee802154/nl-phy.c b/net/ieee802154/nl-phy.c index ed0eab39f53..c64a38d57aa 100644 --- a/net/ieee802154/nl-phy.c +++ b/net/ieee802154/nl-phy.c @@ -24,6 +24,7 @@ #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/if_arp.h> #include <net/netlink.h> #include <net/genetlink.h> #include <net/wpan-phy.h> @@ -44,7 +45,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, pr_debug("%s\n", __func__); if (!buf) - goto out; + return -EMSGSIZE; hdr = genlmsg_put(msg, 0, seq, &nl802154_family, flags, IEEE802154_LIST_PHY); @@ -65,6 +66,7 @@ static int ieee802154_nl_fill_phy(struct sk_buff *msg, u32 pid, pages * sizeof(uint32_t), buf); mutex_unlock(&phy->pib_lock); + kfree(buf); return genlmsg_end(msg, hdr); nla_put_failure: @@ -212,12 +214,37 @@ static int ieee802154_add_iface(struct sk_buff *skb, goto nla_put_failure; } + if (info->attrs[IEEE802154_ATTR_HW_ADDR] && + nla_len(info->attrs[IEEE802154_ATTR_HW_ADDR]) != + IEEE802154_ADDR_LEN) { + rc = -EINVAL; + goto nla_put_failure; + } + dev = phy->add_iface(phy, devname); if (IS_ERR(dev)) { rc = PTR_ERR(dev); goto nla_put_failure; } + if (info->attrs[IEEE802154_ATTR_HW_ADDR]) { + struct sockaddr addr; + + addr.sa_family = ARPHRD_IEEE802154; + nla_memcpy(&addr.sa_data, info->attrs[IEEE802154_ATTR_HW_ADDR], + IEEE802154_ADDR_LEN); + + /* + * strangely enough, some callbacks (inetdev_event) from + * dev_set_mac_address require RTNL_LOCK + */ + rtnl_lock(); + rc = dev_set_mac_address(dev, &addr); + rtnl_unlock(); + if (rc) + goto dev_unregister; + } + NLA_PUT_STRING(msg, IEEE802154_ATTR_PHY_NAME, wpan_phy_name(phy)); NLA_PUT_STRING(msg, IEEE802154_ATTR_DEV_NAME, dev->name); @@ -227,6 +254,11 @@ static int ieee802154_add_iface(struct sk_buff *skb, return ieee802154_nl_reply(msg, info); +dev_unregister: + rtnl_lock(); /* del_iface must be called with RTNL lock */ + phy->del_iface(phy, dev); + dev_put(dev); + rtnl_unlock(); nla_put_failure: nlmsg_free(msg); out_dev: diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9c1926027a2..1b745d412cf 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -465,8 +465,10 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < sizeof(struct sockaddr_in)) goto out; - if (addr->sin_family != AF_INET) + if (addr->sin_family != AF_INET) { + err = -EAFNOSUPPORT; goto out; + } chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); @@ -676,6 +678,7 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags) lock_sock(sk2); + sock_rps_record_flow(sk2); WARN_ON(!((1 << sk2->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE))); @@ -1437,11 +1440,11 @@ EXPORT_SYMBOL_GPL(inet_ctl_sock_create); unsigned long snmp_fold_field(void __percpu *mib[], int offt) { unsigned long res = 0; - int i; + int i, j; for_each_possible_cpu(i) { - res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt); - res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt); + for (j = 0; j < SNMP_ARRAY_SZ; j++) + res += *(((unsigned long *) per_cpu_ptr(mib[j], i)) + offt); } return res; } @@ -1455,28 +1458,19 @@ u64 snmp_fold_field64(void __percpu *mib[], int offt, size_t syncp_offset) int cpu; for_each_possible_cpu(cpu) { - void *bhptr, *userptr; + void *bhptr; struct u64_stats_sync *syncp; - u64 v_bh, v_user; + u64 v; unsigned int start; - /* first mib used by softirq context, we must use _bh() accessors */ - bhptr = per_cpu_ptr(SNMP_STAT_BHPTR(mib), cpu); + bhptr = per_cpu_ptr(mib[0], cpu); syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); do { start = u64_stats_fetch_begin_bh(syncp); - v_bh = *(((u64 *) bhptr) + offt); + v = *(((u64 *) bhptr) + offt); } while (u64_stats_fetch_retry_bh(syncp, start)); - /* second mib used in USER context */ - userptr = per_cpu_ptr(SNMP_STAT_USRPTR(mib), cpu); - syncp = (struct u64_stats_sync *)(userptr + syncp_offset); - do { - start = u64_stats_fetch_begin(syncp); - v_user = *(((u64 *) userptr) + offt); - } while (u64_stats_fetch_retry(syncp, start)); - - res += v_bh + v_user; + res += v; } return res; } @@ -1488,25 +1482,28 @@ int snmp_mib_init(void __percpu *ptr[2], size_t mibsize, size_t align) BUG_ON(ptr == NULL); ptr[0] = __alloc_percpu(mibsize, align); if (!ptr[0]) - goto err0; + return -ENOMEM; +#if SNMP_ARRAY_SZ == 2 ptr[1] = __alloc_percpu(mibsize, align); - if (!ptr[1]) - goto err1; + if (!ptr[1]) { + free_percpu(ptr[0]); + ptr[0] = NULL; + return -ENOMEM; + } +#endif return 0; -err1: - free_percpu(ptr[0]); - ptr[0] = NULL; -err0: - return -ENOMEM; } EXPORT_SYMBOL_GPL(snmp_mib_init); -void snmp_mib_free(void __percpu *ptr[2]) +void snmp_mib_free(void __percpu *ptr[SNMP_ARRAY_SZ]) { + int i; + BUG_ON(ptr == NULL); - free_percpu(ptr[0]); - free_percpu(ptr[1]); - ptr[0] = ptr[1] = NULL; + for (i = 0; i < SNMP_ARRAY_SZ; i++) { + free_percpu(ptr[i]); + ptr[i] = NULL; + } } EXPORT_SYMBOL_GPL(snmp_mib_free); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 1b74d3b6437..96a164aa136 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -97,7 +97,6 @@ #include <linux/init.h> #include <linux/net.h> #include <linux/rcupdate.h> -#include <linux/jhash.h> #include <linux/slab.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> @@ -139,8 +138,6 @@ static const struct neigh_ops arp_generic_ops = { .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; static const struct neigh_ops arp_hh_ops = { @@ -149,16 +146,12 @@ static const struct neigh_ops arp_hh_ops = { .error_report = arp_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; static const struct neigh_ops arp_direct_ops = { .family = AF_INET, - .output = dev_queue_xmit, - .connected_output = dev_queue_xmit, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, + .output = neigh_direct_output, + .connected_output = neigh_direct_output, }; static const struct neigh_ops arp_broken_ops = { @@ -167,8 +160,6 @@ static const struct neigh_ops arp_broken_ops = { .error_report = arp_error_report, .output = neigh_compat_output, .connected_output = neigh_compat_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; struct neigh_table arp_tbl = { @@ -232,7 +223,7 @@ static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 hash_rnd) { - return jhash_2words(*(u32 *)pkey, dev->ifindex, hash_rnd); + return arp_hashfn(*(u32 *)pkey, dev, hash_rnd); } static int arp_constructor(struct neighbour *neigh) @@ -259,7 +250,7 @@ static int arp_constructor(struct neighbour *neigh) if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &arp_direct_ops; - neigh->output = neigh->ops->queue_xmit; + neigh->output = neigh_direct_output; } else { /* Good devices (checked by reading texts, but only Ethernet is tested) @@ -518,30 +509,6 @@ EXPORT_SYMBOL(arp_find); /* END OF OBSOLETE FUNCTIONS */ -int arp_bind_neighbour(struct dst_entry *dst) -{ - struct net_device *dev = dst->dev; - struct neighbour *n = dst->neighbour; - - if (dev == NULL) - return -EINVAL; - if (n == NULL) { - __be32 nexthop = ((struct rtable *)dst)->rt_gateway; - if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) - nexthop = 0; - n = __neigh_lookup_errno( -#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) - dev->type == ARPHRD_ATM ? - clip_tbl_hook : -#endif - &arp_tbl, &nexthop, dev); - if (IS_ERR(n)) - return PTR_ERR(n); - dst->neighbour = n; - } - return 0; -} - /* * Check if we can use proxy ARP for this path */ diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 0d4a184af16..37b3c188d8b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1833,8 +1833,8 @@ void __init devinet_init(void) rtnl_af_register(&inet_af_ops); - rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL); - rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL); - rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL, NULL); + rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL, NULL); + rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr, NULL); } diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 22524716fe7..92fc5f69f5d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -1124,9 +1124,9 @@ static struct pernet_operations fib_net_ops = { void __init ip_fib_init(void) { - rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL); - rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL); - rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib); + rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, NULL); + rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, NULL); register_pernet_subsys(&fib_net_ops); register_netdevice_notifier(&fib_netdev_notifier); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 58c25ea5a5c..de9e2978476 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -110,9 +110,10 @@ struct leaf { struct leaf_info { struct hlist_node hlist; - struct rcu_head rcu; int plen; + u32 mask_plen; /* ntohl(inet_make_mask(plen)) */ struct list_head falh; + struct rcu_head rcu; }; struct tnode { @@ -451,6 +452,7 @@ static struct leaf_info *leaf_info_new(int plen) struct leaf_info *li = kmalloc(sizeof(struct leaf_info), GFP_KERNEL); if (li) { li->plen = plen; + li->mask_plen = ntohl(inet_make_mask(plen)); INIT_LIST_HEAD(&li->falh); } return li; @@ -1359,10 +1361,8 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, hlist_for_each_entry_rcu(li, node, hhead, hlist) { struct fib_alias *fa; - int plen = li->plen; - __be32 mask = inet_make_mask(plen); - if (l->key != (key & ntohl(mask))) + if (l->key != (key & li->mask_plen)) continue; list_for_each_entry_rcu(fa, &li->falh, fa_list) { @@ -1394,7 +1394,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, #ifdef CONFIG_IP_FIB_TRIE_STATS t->stats.semantic_match_passed++; #endif - res->prefixlen = plen; + res->prefixlen = li->plen; res->nh_sel = nhsel; res->type = fa->fa_type; res->scope = fa->fa_info->fib_scope; @@ -1402,7 +1402,7 @@ static int check_leaf(struct fib_table *tb, struct trie *t, struct leaf *l, res->table = tb; res->fa_head = &li->falh; if (!(fib_flags & FIB_LOOKUP_NOREF)) - atomic_inc(&res->fi->fib_clntref); + atomic_inc(&fi->fib_clntref); return 0; } } diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c index c6933f2ea31..9dbe10875fb 100644 --- a/net/ipv4/gre.c +++ b/net/ipv4/gre.c @@ -16,7 +16,6 @@ #include <linux/skbuff.h> #include <linux/in.h> #include <linux/netdevice.h> -#include <linux/version.h> #include <linux/spinlock.h> #include <net/protocol.h> #include <net/gre.h> diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 5395e45dcce..23ef31baa1a 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -380,6 +380,7 @@ static struct rtable *icmp_route_lookup(struct net *net, struct icmp_bxm *param) { struct rtable *rt, *rt2; + struct flowi4 fl4_dec; int err; memset(fl4, 0, sizeof(*fl4)); @@ -408,19 +409,19 @@ static struct rtable *icmp_route_lookup(struct net *net, } else return rt; - err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(fl4), AF_INET); + err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4_dec), AF_INET); if (err) goto relookup_failed; - if (inet_addr_type(net, fl4->saddr) == RTN_LOCAL) { - rt2 = __ip_route_output_key(net, fl4); + if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) { + rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); } else { struct flowi4 fl4_2 = {}; unsigned long orefdst; - fl4_2.daddr = fl4->saddr; + fl4_2.daddr = fl4_dec.saddr; rt2 = ip_route_output_key(net, &fl4_2); if (IS_ERR(rt2)) { err = PTR_ERR(rt2); @@ -428,7 +429,7 @@ static struct rtable *icmp_route_lookup(struct net *net, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ - err = ip_route_input(skb_in, fl4->daddr, fl4->saddr, + err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); dst_release(&rt2->dst); @@ -440,10 +441,11 @@ static struct rtable *icmp_route_lookup(struct net *net, goto relookup_failed; rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst, - flowi4_to_flowi(fl4), NULL, + flowi4_to_flowi(&fl4_dec), NULL, XFRM_LOOKUP_ICMP); if (!IS_ERR(rt2)) { dst_release(&rt->dst); + memcpy(fl4, &fl4_dec, sizeof(*fl4)); rt = rt2; } else if (PTR_ERR(rt2) == -EPERM) { if (rt) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 6ffe94ca5bc..389a2e6a17f 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -437,7 +437,7 @@ static int valid_cc(const void *bc, int len, int cc) return 0; if (cc == len) return 1; - if (op->yes < 4) + if (op->yes < 4 || op->yes & 3) return 0; len -= op->yes; bc += op->yes; @@ -447,11 +447,11 @@ static int valid_cc(const void *bc, int len, int cc) static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) { - const unsigned char *bc = bytecode; + const void *bc = bytecode; int len = bytecode_len; while (len > 0) { - struct inet_diag_bc_op *op = (struct inet_diag_bc_op *)bc; + const struct inet_diag_bc_op *op = bc; //printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len); switch (op->code) { @@ -462,22 +462,20 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) case INET_DIAG_BC_S_LE: case INET_DIAG_BC_D_GE: case INET_DIAG_BC_D_LE: - if (op->yes < 4 || op->yes > len + 4) - return -EINVAL; case INET_DIAG_BC_JMP: - if (op->no < 4 || op->no > len + 4) + if (op->no < 4 || op->no > len + 4 || op->no & 3) return -EINVAL; if (op->no < len && !valid_cc(bytecode, bytecode_len, len - op->no)) return -EINVAL; break; case INET_DIAG_BC_NOP: - if (op->yes < 4 || op->yes > len + 4) - return -EINVAL; break; default: return -EINVAL; } + if (op->yes < 4 || op->yes > len + 4 || op->yes & 3) + return -EINVAL; bc += op->yes; len -= op->yes; } @@ -871,7 +869,7 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) } return netlink_dump_start(idiagnl, skb, nlh, - inet_diag_dump, NULL); + inet_diag_dump, NULL, 0); } return inet_diag_get_exact(skb, nlh); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 85a0f75dae6..ef7ae6049a5 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -146,8 +146,7 @@ static __wsum lro_tcp_data_csum(struct iphdr *iph, struct tcphdr *tcph, int len) } static void lro_init_desc(struct net_lro_desc *lro_desc, struct sk_buff *skb, - struct iphdr *iph, struct tcphdr *tcph, - u16 vlan_tag, struct vlan_group *vgrp) + struct iphdr *iph, struct tcphdr *tcph) { int nr_frags; __be32 *ptr; @@ -173,8 +172,6 @@ static void lro_init_desc(struct net_lro_desc *lro_desc, struct sk_buff *skb, } lro_desc->mss = tcp_data_len; - lro_desc->vgrp = vgrp; - lro_desc->vlan_tag = vlan_tag; lro_desc->active = 1; lro_desc->data_csum = lro_tcp_data_csum(iph, tcph, @@ -309,29 +306,17 @@ static void lro_flush(struct net_lro_mgr *lro_mgr, skb_shinfo(lro_desc->parent)->gso_size = lro_desc->mss; - if (lro_desc->vgrp) { - if (lro_mgr->features & LRO_F_NAPI) - vlan_hwaccel_receive_skb(lro_desc->parent, - lro_desc->vgrp, - lro_desc->vlan_tag); - else - vlan_hwaccel_rx(lro_desc->parent, - lro_desc->vgrp, - lro_desc->vlan_tag); - - } else { - if (lro_mgr->features & LRO_F_NAPI) - netif_receive_skb(lro_desc->parent); - else - netif_rx(lro_desc->parent); - } + if (lro_mgr->features & LRO_F_NAPI) + netif_receive_skb(lro_desc->parent); + else + netif_rx(lro_desc->parent); LRO_INC_STATS(lro_mgr, flushed); lro_clear_desc(lro_desc); } static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, - struct vlan_group *vgrp, u16 vlan_tag, void *priv) + void *priv) { struct net_lro_desc *lro_desc; struct iphdr *iph; @@ -360,7 +345,7 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, goto out; skb->ip_summed = lro_mgr->ip_summed_aggr; - lro_init_desc(lro_desc, skb, iph, tcph, vlan_tag, vgrp); + lro_init_desc(lro_desc, skb, iph, tcph); LRO_INC_STATS(lro_mgr, aggregated); return 0; } @@ -433,8 +418,7 @@ static struct sk_buff *lro_gen_skb(struct net_lro_mgr *lro_mgr, static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, struct skb_frag_struct *frags, int len, int true_size, - struct vlan_group *vgrp, - u16 vlan_tag, void *priv, __wsum sum) + void *priv, __wsum sum) { struct net_lro_desc *lro_desc; struct iphdr *iph; @@ -480,7 +464,7 @@ static struct sk_buff *__lro_proc_segment(struct net_lro_mgr *lro_mgr, tcph = (void *)((u8 *)skb->data + vlan_hdr_len + IP_HDR_LEN(iph)); - lro_init_desc(lro_desc, skb, iph, tcph, 0, NULL); + lro_init_desc(lro_desc, skb, iph, tcph); LRO_INC_STATS(lro_mgr, aggregated); return NULL; } @@ -514,7 +498,7 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, void *priv) { - if (__lro_proc_skb(lro_mgr, skb, NULL, 0, priv)) { + if (__lro_proc_skb(lro_mgr, skb, priv)) { if (lro_mgr->features & LRO_F_NAPI) netif_receive_skb(skb); else @@ -523,29 +507,13 @@ void lro_receive_skb(struct net_lro_mgr *lro_mgr, } EXPORT_SYMBOL(lro_receive_skb); -void lro_vlan_hwaccel_receive_skb(struct net_lro_mgr *lro_mgr, - struct sk_buff *skb, - struct vlan_group *vgrp, - u16 vlan_tag, - void *priv) -{ - if (__lro_proc_skb(lro_mgr, skb, vgrp, vlan_tag, priv)) { - if (lro_mgr->features & LRO_F_NAPI) - vlan_hwaccel_receive_skb(skb, vgrp, vlan_tag); - else - vlan_hwaccel_rx(skb, vgrp, vlan_tag); - } -} -EXPORT_SYMBOL(lro_vlan_hwaccel_receive_skb); - void lro_receive_frags(struct net_lro_mgr *lro_mgr, struct skb_frag_struct *frags, int len, int true_size, void *priv, __wsum sum) { struct sk_buff *skb; - skb = __lro_proc_segment(lro_mgr, frags, len, true_size, NULL, 0, - priv, sum); + skb = __lro_proc_segment(lro_mgr, frags, len, true_size, priv, sum); if (!skb) return; @@ -556,26 +524,6 @@ void lro_receive_frags(struct net_lro_mgr *lro_mgr, } EXPORT_SYMBOL(lro_receive_frags); -void lro_vlan_hwaccel_receive_frags(struct net_lro_mgr *lro_mgr, - struct skb_frag_struct *frags, - int len, int true_size, - struct vlan_group *vgrp, - u16 vlan_tag, void *priv, __wsum sum) -{ - struct sk_buff *skb; - - skb = __lro_proc_segment(lro_mgr, frags, len, true_size, vgrp, - vlan_tag, priv, sum); - if (!skb) - return; - - if (lro_mgr->features & LRO_F_NAPI) - vlan_hwaccel_receive_skb(skb, vgrp, vlan_tag); - else - vlan_hwaccel_rx(skb, vgrp, vlan_tag); -} -EXPORT_SYMBOL(lro_vlan_hwaccel_receive_frags); - void lro_flush_all(struct net_lro_mgr *lro_mgr) { int i; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index ce616d92cc5..e38213817d0 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -54,15 +54,11 @@ * 1. Nodes may appear in the tree only with the pool lock held. * 2. Nodes may disappear from the tree only with the pool lock held * AND reference count being 0. - * 3. Nodes appears and disappears from unused node list only under - * "inet_peer_unused_lock". - * 4. Global variable peer_total is modified under the pool lock. - * 5. struct inet_peer fields modification: + * 3. Global variable peer_total is modified under the pool lock. + * 4. struct inet_peer fields modification: * avl_left, avl_right, avl_parent, avl_height: pool lock - * unused: unused node list lock * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing - * dtime: unused node list lock * daddr: unchangeable * ip_id_count: atomic value (no lock needed) */ @@ -104,19 +100,6 @@ int inet_peer_threshold __read_mostly = 65536 + 128; /* start to throw entries m * aggressively at this stage */ int inet_peer_minttl __read_mostly = 120 * HZ; /* TTL under high load: 120 sec */ int inet_peer_maxttl __read_mostly = 10 * 60 * HZ; /* usual time to live: 10 min */ -int inet_peer_gc_mintime __read_mostly = 10 * HZ; -int inet_peer_gc_maxtime __read_mostly = 120 * HZ; - -static struct { - struct list_head list; - spinlock_t lock; -} unused_peers = { - .list = LIST_HEAD_INIT(unused_peers.list), - .lock = __SPIN_LOCK_UNLOCKED(unused_peers.lock), -}; - -static void peer_check_expire(unsigned long dummy); -static DEFINE_TIMER(peer_periodic_timer, peer_check_expire, 0, 0); /* Called from ip_output.c:ip_init */ @@ -142,21 +125,6 @@ void __init inet_initpeers(void) 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); - /* All the timers, started at system startup tend - to synchronize. Perturb it a bit. - */ - peer_periodic_timer.expires = jiffies - + net_random() % inet_peer_gc_maxtime - + inet_peer_gc_maxtime; - add_timer(&peer_periodic_timer); -} - -/* Called with or without local BH being disabled. */ -static void unlink_from_unused(struct inet_peer *p) -{ - spin_lock_bh(&unused_peers.lock); - list_del_init(&p->unused); - spin_unlock_bh(&unused_peers.lock); } static int addr_compare(const struct inetpeer_addr *a, @@ -203,20 +171,6 @@ static int addr_compare(const struct inetpeer_addr *a, u; \ }) -static bool atomic_add_unless_return(atomic_t *ptr, int a, int u, int *newv) -{ - int cur, old = atomic_read(ptr); - - while (old != u) { - *newv = old + a; - cur = atomic_cmpxchg(ptr, old, *newv); - if (cur == old) - return true; - old = cur; - } - return false; -} - /* * Called with rcu_read_lock() * Because we hold no lock against a writer, its quite possible we fall @@ -225,8 +179,7 @@ static bool atomic_add_unless_return(atomic_t *ptr, int a, int u, int *newv) * We exit from this function if number of links exceeds PEER_MAXDEPTH */ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, - struct inet_peer_base *base, - int *newrefcnt) + struct inet_peer_base *base) { struct inet_peer *u = rcu_dereference(base->root); int count = 0; @@ -235,11 +188,9 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int cmp = addr_compare(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was - * deleted, unlink_from_pool() sets refcnt=-1 to make - * distinction between an unused entry (refcnt=0) and - * a freed one. + * deleted (refcnt=-1) */ - if (!atomic_add_unless_return(&u->refcnt, 1, -1, newrefcnt)) + if (!atomic_add_unless(&u->refcnt, 1, -1)) u = NULL; return u; } @@ -366,137 +317,99 @@ static void inetpeer_free_rcu(struct rcu_head *head) kmem_cache_free(peer_cachep, container_of(head, struct inet_peer, rcu)); } -/* May be called with local BH enabled. */ static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) { - int do_free; - - do_free = 0; - - write_seqlock_bh(&base->lock); - /* Check the reference counter. It was artificially incremented by 1 - * in cleanup() function to prevent sudden disappearing. If we can - * atomically (because of lockless readers) take this last reference, - * it's safe to remove the node and free it later. - * We use refcnt=-1 to alert lockless readers this entry is deleted. - */ - if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) { - struct inet_peer __rcu ***stackptr, ***delp; - if (lookup(&p->daddr, stack, base) != p) - BUG(); - delp = stackptr - 1; /* *delp[0] == p */ - if (p->avl_left == peer_avl_empty_rcu) { - *delp[0] = p->avl_right; - --stackptr; - } else { - /* look for a node to insert instead of p */ - struct inet_peer *t; - t = lookup_rightempty(p, base); - BUG_ON(rcu_deref_locked(*stackptr[-1], base) != t); - **--stackptr = t->avl_left; - /* t is removed, t->daddr > x->daddr for any - * x in p->avl_left subtree. - * Put t in the old place of p. */ - RCU_INIT_POINTER(*delp[0], t); - t->avl_left = p->avl_left; - t->avl_right = p->avl_right; - t->avl_height = p->avl_height; - BUG_ON(delp[1] != &p->avl_left); - delp[1] = &t->avl_left; /* was &p->avl_left */ - } - peer_avl_rebalance(stack, stackptr, base); - base->total--; - do_free = 1; + struct inet_peer __rcu ***stackptr, ***delp; + + if (lookup(&p->daddr, stack, base) != p) + BUG(); + delp = stackptr - 1; /* *delp[0] == p */ + if (p->avl_left == peer_avl_empty_rcu) { + *delp[0] = p->avl_right; + --stackptr; + } else { + /* look for a node to insert instead of p */ + struct inet_peer *t; + t = lookup_rightempty(p, base); + BUG_ON(rcu_deref_locked(*stackptr[-1], base) != t); + **--stackptr = t->avl_left; + /* t is removed, t->daddr > x->daddr for any + * x in p->avl_left subtree. + * Put t in the old place of p. */ + RCU_INIT_POINTER(*delp[0], t); + t->avl_left = p->avl_left; + t->avl_right = p->avl_right; + t->avl_height = p->avl_height; + BUG_ON(delp[1] != &p->avl_left); + delp[1] = &t->avl_left; /* was &p->avl_left */ } - write_sequnlock_bh(&base->lock); - - if (do_free) - call_rcu(&p->rcu, inetpeer_free_rcu); - else - /* The node is used again. Decrease the reference counter - * back. The loop "cleanup -> unlink_from_unused - * -> unlink_from_pool -> putpeer -> link_to_unused - * -> cleanup (for the same node)" - * doesn't really exist because the entry will have a - * recent deletion time and will not be cleaned again soon. - */ - inet_putpeer(p); + peer_avl_rebalance(stack, stackptr, base); + base->total--; + call_rcu(&p->rcu, inetpeer_free_rcu); } static struct inet_peer_base *family_to_base(int family) { - return (family == AF_INET ? &v4_peers : &v6_peers); -} - -static struct inet_peer_base *peer_to_base(struct inet_peer *p) -{ - return family_to_base(p->daddr.family); + return family == AF_INET ? &v4_peers : &v6_peers; } -/* May be called with local BH enabled. */ -static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) +/* perform garbage collect on all items stacked during a lookup */ +static int inet_peer_gc(struct inet_peer_base *base, + struct inet_peer __rcu **stack[PEER_MAXDEPTH], + struct inet_peer __rcu ***stackptr) { - struct inet_peer *p = NULL; - - /* Remove the first entry from the list of unused nodes. */ - spin_lock_bh(&unused_peers.lock); - if (!list_empty(&unused_peers.list)) { - __u32 delta; - - p = list_first_entry(&unused_peers.list, struct inet_peer, unused); - delta = (__u32)jiffies - p->dtime; + struct inet_peer *p, *gchead = NULL; + __u32 delta, ttl; + int cnt = 0; - if (delta < ttl) { - /* Do not prune fresh entries. */ - spin_unlock_bh(&unused_peers.lock); - return -1; + if (base->total >= inet_peer_threshold) + ttl = 0; /* be aggressive */ + else + ttl = inet_peer_maxttl + - (inet_peer_maxttl - inet_peer_minttl) / HZ * + base->total / inet_peer_threshold * HZ; + stackptr--; /* last stack slot is peer_avl_empty */ + while (stackptr > stack) { + stackptr--; + p = rcu_deref_locked(**stackptr, base); + if (atomic_read(&p->refcnt) == 0) { + smp_rmb(); + delta = (__u32)jiffies - p->dtime; + if (delta >= ttl && + atomic_cmpxchg(&p->refcnt, 0, -1) == 0) { + p->gc_next = gchead; + gchead = p; + } } - - list_del_init(&p->unused); - - /* Grab an extra reference to prevent node disappearing - * before unlink_from_pool() call. */ - atomic_inc(&p->refcnt); } - spin_unlock_bh(&unused_peers.lock); - - if (p == NULL) - /* It means that the total number of USED entries has - * grown over inet_peer_threshold. It shouldn't really - * happen because of entry limits in route cache. */ - return -1; - - unlink_from_pool(p, peer_to_base(p), stack); - return 0; + while ((p = gchead) != NULL) { + gchead = p->gc_next; + cnt++; + unlink_from_pool(p, base, stack); + } + return cnt; } -/* Called with or without local BH being disabled. */ -struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) +struct inet_peer *inet_getpeer(const struct inetpeer_addr *daddr, int create) { struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; struct inet_peer_base *base = family_to_base(daddr->family); struct inet_peer *p; unsigned int sequence; - int invalidated, newrefcnt = 0; + int invalidated, gccnt = 0; - /* Look up for the address quickly, lockless. + /* Attempt a lockless lookup first. * Because of a concurrent writer, we might not find an existing entry. */ rcu_read_lock(); sequence = read_seqbegin(&base->lock); - p = lookup_rcu(daddr, base, &newrefcnt); + p = lookup_rcu(daddr, base); invalidated = read_seqretry(&base->lock, sequence); rcu_read_unlock(); - if (p) { -found: /* The existing node has been found. - * Remove the entry from unused list if it was there. - */ - if (newrefcnt == 1) - unlink_from_unused(p); + if (p) return p; - } /* If no writer did a change during our lookup, we can return early. */ if (!create && !invalidated) @@ -506,18 +419,27 @@ found: /* The existing node has been found. * At least, nodes should be hot in our cache. */ write_seqlock_bh(&base->lock); +relookup: p = lookup(daddr, stack, base); if (p != peer_avl_empty) { - newrefcnt = atomic_inc_return(&p->refcnt); + atomic_inc(&p->refcnt); write_sequnlock_bh(&base->lock); - goto found; + return p; + } + if (!gccnt) { + gccnt = inet_peer_gc(base, stack, stackptr); + if (gccnt && create) + goto relookup; } p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, secure_ip_id(daddr->addr.a4)); + atomic_set(&p->ip_id_count, + (daddr->family == AF_INET) ? + secure_ip_id(daddr->addr.a4) : + secure_ipv6_id(daddr->addr.a6)); p->tcp_ts_stamp = 0; p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; p->rate_tokens = 0; @@ -525,7 +447,6 @@ found: /* The existing node has been found. p->pmtu_expires = 0; p->pmtu_orig = 0; memset(&p->redirect_learned, 0, sizeof(p->redirect_learned)); - INIT_LIST_HEAD(&p->unused); /* Link the node. */ @@ -534,63 +455,15 @@ found: /* The existing node has been found. } write_sequnlock_bh(&base->lock); - if (base->total >= inet_peer_threshold) - /* Remove one less-recently-used entry. */ - cleanup_once(0, stack); - return p; } - -static int compute_total(void) -{ - return v4_peers.total + v6_peers.total; -} EXPORT_SYMBOL_GPL(inet_getpeer); -/* Called with local BH disabled. */ -static void peer_check_expire(unsigned long dummy) -{ - unsigned long now = jiffies; - int ttl, total; - struct inet_peer __rcu **stack[PEER_MAXDEPTH]; - - total = compute_total(); - if (total >= inet_peer_threshold) - ttl = inet_peer_minttl; - else - ttl = inet_peer_maxttl - - (inet_peer_maxttl - inet_peer_minttl) / HZ * - total / inet_peer_threshold * HZ; - while (!cleanup_once(ttl, stack)) { - if (jiffies != now) - break; - } - - /* Trigger the timer after inet_peer_gc_mintime .. inet_peer_gc_maxtime - * interval depending on the total number of entries (more entries, - * less interval). */ - total = compute_total(); - if (total >= inet_peer_threshold) - peer_periodic_timer.expires = jiffies + inet_peer_gc_mintime; - else - peer_periodic_timer.expires = jiffies - + inet_peer_gc_maxtime - - (inet_peer_gc_maxtime - inet_peer_gc_mintime) / HZ * - total / inet_peer_threshold * HZ; - add_timer(&peer_periodic_timer); -} - void inet_putpeer(struct inet_peer *p) { - local_bh_disable(); - - if (atomic_dec_and_lock(&p->refcnt, &unused_peers.lock)) { - list_add_tail(&p->unused, &unused_peers.list); - p->dtime = (__u32)jiffies; - spin_unlock(&unused_peers.lock); - } - - local_bh_enable(); + p->dtime = (__u32)jiffies; + smp_mb__before_atomic_dec(); + atomic_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 0ad6035f636..0e0ab98abc6 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -261,8 +261,9 @@ static void ip_expire(unsigned long arg) * Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ - if (qp->user == IP_DEFRAG_CONNTRACK_IN && - skb_rtable(head)->rt_type != RTN_LOCAL) + if (qp->user == IP_DEFRAG_AF_PACKET || + (qp->user == IP_DEFRAG_CONNTRACK_IN && + skb_rtable(head)->rt_type != RTN_LOCAL)) goto out_rcu_unlock; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 8871067560d..d7bb94c4834 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -731,9 +731,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { + struct neighbour *neigh = dst_get_neighbour(skb_dst(skb)); const struct in6_addr *addr6; int addr_type; - struct neighbour *neigh = skb_dst(skb)->neighbour; if (neigh == NULL) goto tx_error; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index c8f48efc5fd..073a9b01c40 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -165,7 +165,7 @@ int ip_call_ra_chain(struct sk_buff *skb) (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && net_eq(sock_net(sk), dev_net(dev))) { - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) return 1; } @@ -256,7 +256,7 @@ int ip_local_deliver(struct sk_buff *skb) * Reassemble IP fragments. */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER)) return 0; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 98af3697c71..ccaaa851ab4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -182,6 +182,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) struct rtable *rt = (struct rtable *)dst; struct net_device *dev = dst->dev; unsigned int hh_len = LL_RESERVED_SPACE(dev); + struct neighbour *neigh; if (rt->rt_type == RTN_MULTICAST) { IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUTMCAST, skb->len); @@ -203,10 +204,9 @@ static inline int ip_finish_output2(struct sk_buff *skb) skb = skb2; } - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); + neigh = dst_get_neighbour(dst); + if (neigh) + return neigh_output(neigh, skb); if (net_ratelimit()) printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n"); @@ -489,7 +489,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (first_len - hlen > mtu || ((first_len - hlen) & 7) || - (iph->frag_off & htons(IP_MF|IP_OFFSET)) || + ip_is_fragment(iph) || skb_cloned(skb)) goto slow_path; @@ -734,7 +734,7 @@ static inline int ip_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu, unsigned int flags) + int transhdrlen, int maxfraglen, unsigned int flags) { struct sk_buff *skb; int err; @@ -767,7 +767,7 @@ static inline int ip_ufo_append_data(struct sock *sk, skb->csum = 0; /* specify the length of each IP datagram fragment */ - skb_shinfo(skb)->gso_size = mtu - fragheaderlen; + skb_shinfo(skb)->gso_size = maxfraglen - fragheaderlen; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; __skb_queue_tail(queue, skb); } @@ -799,9 +799,9 @@ static int __ip_append_data(struct sock *sk, int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; - exthdrlen = transhdrlen ? rt->dst.header_len : 0; - length += exthdrlen; - transhdrlen += exthdrlen; + skb = skb_peek_tail(queue); + + exthdrlen = !skb ? rt->dst.header_len : 0; mtu = cork->fragsize; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -825,15 +825,13 @@ static int __ip_append_data(struct sock *sk, !exthdrlen) csummode = CHECKSUM_PARTIAL; - skb = skb_peek_tail(queue); - cork->length += length; if (((length > mtu) || (skb && skb_is_gso(skb))) && (sk->sk_protocol == IPPROTO_UDP) && - (rt->dst.dev->features & NETIF_F_UFO)) { + (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) { err = ip_ufo_append_data(sk, queue, getfrag, from, length, hh_len, fragheaderlen, transhdrlen, - mtu, flags); + maxfraglen, flags); if (err) goto error; return 0; @@ -883,17 +881,16 @@ alloc_new_skb: else alloclen = fraglen; + alloclen += exthdrlen; + /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ - if (datalen == length + fraggap) { + if (datalen == length + fraggap) alloclen += rt->dst.trailer_len; - /* make sure mtu is not reached */ - if (datalen > mtu - fragheaderlen - rt->dst.trailer_len) - datalen -= ALIGN(rt->dst.trailer_len, 8); - } + if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len + 15, @@ -926,11 +923,11 @@ alloc_new_skb: /* * Find where to start putting bytes. */ - data = skb_put(skb, fraglen); + data = skb_put(skb, fraglen + exthdrlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); - data += fragheaderlen; + data += fragheaderlen + exthdrlen; if (fraggap) { skb->csum = skb_copy_and_csum_bits( @@ -1064,7 +1061,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, */ *rtp = NULL; cork->fragsize = inet->pmtudisc == IP_PMTUDISC_PROBE ? - rt->dst.dev->mtu : dst_mtu(rt->dst.path); + rt->dst.dev->mtu : dst_mtu(&rt->dst); cork->dst = &rt->dst; cork->length = 0; cork->tx_flags = ipc->tx_flags; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index ab7e5542c1c..472a8c4f1dc 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -861,41 +861,44 @@ static void __init ic_do_bootp_ext(u8 *ext) #endif switch (*ext++) { - case 1: /* Subnet mask */ - if (ic_netmask == NONE) - memcpy(&ic_netmask, ext+1, 4); - break; - case 3: /* Default gateway */ - if (ic_gateway == NONE) - memcpy(&ic_gateway, ext+1, 4); - break; - case 6: /* DNS server */ - servers= *ext/4; - if (servers > CONF_NAMESERVERS_MAX) - servers = CONF_NAMESERVERS_MAX; - for (i = 0; i < servers; i++) { - if (ic_nameservers[i] == NONE) - memcpy(&ic_nameservers[i], ext+1+4*i, 4); - } - break; - case 12: /* Host name */ - ic_bootp_string(utsname()->nodename, ext+1, *ext, __NEW_UTS_LEN); - ic_host_name_set = 1; - break; - case 15: /* Domain name (DNS) */ - ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); - break; - case 17: /* Root path */ - if (!root_server_path[0]) - ic_bootp_string(root_server_path, ext+1, *ext, sizeof(root_server_path)); - break; - case 26: /* Interface MTU */ - memcpy(&mtu, ext+1, sizeof(mtu)); - ic_dev_mtu = ntohs(mtu); - break; - case 40: /* NIS Domain name (_not_ DNS) */ - ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); - break; + case 1: /* Subnet mask */ + if (ic_netmask == NONE) + memcpy(&ic_netmask, ext+1, 4); + break; + case 3: /* Default gateway */ + if (ic_gateway == NONE) + memcpy(&ic_gateway, ext+1, 4); + break; + case 6: /* DNS server */ + servers= *ext/4; + if (servers > CONF_NAMESERVERS_MAX) + servers = CONF_NAMESERVERS_MAX; + for (i = 0; i < servers; i++) { + if (ic_nameservers[i] == NONE) + memcpy(&ic_nameservers[i], ext+1+4*i, 4); + } + break; + case 12: /* Host name */ + ic_bootp_string(utsname()->nodename, ext+1, *ext, + __NEW_UTS_LEN); + ic_host_name_set = 1; + break; + case 15: /* Domain name (DNS) */ + ic_bootp_string(ic_domain, ext+1, *ext, sizeof(ic_domain)); + break; + case 17: /* Root path */ + if (!root_server_path[0]) + ic_bootp_string(root_server_path, ext+1, *ext, + sizeof(root_server_path)); + break; + case 26: /* Interface MTU */ + memcpy(&mtu, ext+1, sizeof(mtu)); + ic_dev_mtu = ntohs(mtu); + break; + case 40: /* NIS Domain name (_not_ DNS) */ + ic_bootp_string(utsname()->domainname, ext+1, *ext, + __NEW_UTS_LEN); + break; } } @@ -932,7 +935,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str goto drop; /* Fragments are not supported */ - if (h->frag_off & htons(IP_OFFSET | IP_MF)) { + if (ip_is_fragment(h)) { if (net_ratelimit()) printk(KERN_ERR "DHCP/BOOTP: Ignoring fragmented " "reply.\n"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 30a7763c400..aae2bd8cd92 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2544,7 +2544,8 @@ int __init ip_mr_init(void) goto add_proto_fail; } #endif - rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, NULL, ipmr_rtm_dumproute); + rtnl_register(RTNL_FAMILY_IPMR, RTM_GETROUTE, + NULL, ipmr_rtm_dumproute, NULL); return 0; #ifdef CONFIG_IP_PIMSM_V2 diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 4614babdc45..2e97e3ec1eb 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -17,51 +17,35 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) const struct iphdr *iph = ip_hdr(skb); struct rtable *rt; struct flowi4 fl4 = {}; - unsigned long orefdst; + __be32 saddr = iph->saddr; + __u8 flags = 0; unsigned int hh_len; - unsigned int type; - type = inet_addr_type(net, iph->saddr); - if (skb->sk && inet_sk(skb->sk)->transparent) - type = RTN_LOCAL; - if (addr_type == RTN_UNSPEC) - addr_type = type; + if (!skb->sk && addr_type != RTN_LOCAL) { + if (addr_type == RTN_UNSPEC) + addr_type = inet_addr_type(net, saddr); + if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) + flags |= FLOWI_FLAG_ANYSRC; + else + saddr = 0; + } /* some non-standard hacks like ipt_REJECT.c:send_reset() can cause * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. */ - if (addr_type == RTN_LOCAL) { - fl4.daddr = iph->daddr; - if (type == RTN_LOCAL) - fl4.saddr = iph->saddr; - fl4.flowi4_tos = RT_TOS(iph->tos); - fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; - fl4.flowi4_mark = skb->mark; - fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return -1; - - /* Drop old route. */ - skb_dst_drop(skb); - skb_dst_set(skb, &rt->dst); - } else { - /* non-local src, find valid iif to satisfy - * rp-filter when calling ip_route_input. */ - fl4.daddr = iph->saddr; - rt = ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - return -1; + fl4.daddr = iph->daddr; + fl4.saddr = saddr; + fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + fl4.flowi4_mark = skb->mark; + fl4.flowi4_flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : flags; + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return -1; - orefdst = skb->_skb_refdst; - if (ip_route_input(skb, iph->daddr, iph->saddr, - RT_TOS(iph->tos), rt->dst.dev) != 0) { - dst_release(&rt->dst); - return -1; - } - dst_release(&rt->dst); - refdst_drop(orefdst); - } + /* Drop old route. */ + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); if (skb_dst(skb)->error) return -1; diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index d2c1311cb28..5c9b9d96391 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -203,7 +203,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) else pmsg->outdev_name[0] = '\0'; - if (entry->indev && entry->skb->dev) { + if (entry->indev && entry->skb->dev && + entry->skb->mac_header != entry->skb->network_header) { pmsg->hw_type = entry->skb->dev->type; pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); @@ -402,7 +403,8 @@ ipq_dev_drop(int ifindex) static inline void __ipq_rcv_skb(struct sk_buff *skb) { - int status, type, pid, flags, nlmsglen, skblen; + int status, type, pid, flags; + unsigned int nlmsglen, skblen; struct nlmsghdr *nlh; skblen = skb->len; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 76474384350..24e556e83a3 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -566,7 +566,7 @@ check_entry(const struct ipt_entry *e, const char *name) const struct xt_entry_target *t; if (!ip_checkentry(&e->ip)) { - duprintf("ip check failed %p %s.\n", e, par->match->name); + duprintf("ip check failed %p %s.\n", e, name); return -EINVAL; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index d609ac3cb9a..db8d22db425 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -307,7 +307,7 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) * error messages (RELATED) and information requests (see below) */ if (ip_hdr(skb)->protocol == IPPROTO_ICMP && (ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)) + ctinfo == IP_CT_RELATED_REPLY)) return XT_CONTINUE; /* ip_conntrack_icmp guarantees us that we only have ICMP_ECHO, @@ -317,19 +317,19 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) hash = clusterip_hashfn(skb, cipinfo->config); switch (ctinfo) { - case IP_CT_NEW: - ct->mark = hash; - break; - case IP_CT_RELATED: - case IP_CT_RELATED+IP_CT_IS_REPLY: - /* FIXME: we don't handle expectations at the - * moment. they can arrive on a different node than - * the master connection (e.g. FTP passive mode) */ - case IP_CT_ESTABLISHED: - case IP_CT_ESTABLISHED+IP_CT_IS_REPLY: - break; - default: - break; + case IP_CT_NEW: + ct->mark = hash; + break; + case IP_CT_RELATED: + case IP_CT_RELATED_REPLY: + /* FIXME: we don't handle expectations at the moment. + * They can arrive on a different node than + * the master connection (e.g. FTP passive mode) */ + case IP_CT_ESTABLISHED: + case IP_CT_ESTABLISHED_REPLY: + break; + default: /* Prevent gcc warnings */ + break; } #ifdef DEBUG diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index d2ed9dc74eb..9931152a78b 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -60,7 +60,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) nat = nfct_nat(ct); NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + ctinfo == IP_CT_RELATED_REPLY)); /* Source address is 0.0.0.0 - locally generated packet that is * probably not supposed to be masqueraded. diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 1ff79e557f9..51f13f8ec72 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -40,7 +40,6 @@ static void send_reset(struct sk_buff *oldskb, int hook) struct iphdr *niph; const struct tcphdr *oth; struct tcphdr _otcph, *tcph; - unsigned int addr_type; /* IP header checks: fragment. */ if (ip_hdr(oldskb)->frag_off & htons(IP_OFFSET)) @@ -55,6 +54,9 @@ static void send_reset(struct sk_buff *oldskb, int hook) if (oth->rst) return; + if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) + return; + /* Check checksum */ if (nf_ip_checksum(oldskb, hook, ip_hdrlen(oldskb), IPPROTO_TCP)) return; @@ -101,19 +103,11 @@ static void send_reset(struct sk_buff *oldskb, int hook) nskb->csum_start = (unsigned char *)tcph - nskb->head; nskb->csum_offset = offsetof(struct tcphdr, check); - addr_type = RTN_UNSPEC; - if (hook != NF_INET_FORWARD -#ifdef CONFIG_BRIDGE_NETFILTER - || (nskb->nf_bridge && nskb->nf_bridge->mask & BRNF_BRIDGED) -#endif - ) - addr_type = RTN_LOCAL; - /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); nskb->protocol = htons(ETH_P_IP); - if (ip_route_me_harder(nskb, addr_type)) + if (ip_route_me_harder(nskb, RTN_UNSPEC)) goto free_nskb; niph->ttl = ip4_dst_hoplimit(skb_dst(nskb)); diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c index af6e9c77834..2b57e52c746 100644 --- a/net/ipv4/netfilter/ipt_ecn.c +++ b/net/ipv4/netfilter/ipt_ecn.c @@ -25,7 +25,8 @@ MODULE_LICENSE("GPL"); static inline bool match_ip(const struct sk_buff *skb, const struct ipt_ecn_info *einfo) { - return (ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect; + return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^ + !!(einfo->invert & IPT_ECN_OP_MATCH_IP); } static inline bool match_tcp(const struct sk_buff *skb, @@ -76,8 +77,6 @@ static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) { - if (ip_hdr(skb)->protocol != IPPROTO_TCP) - return false; if (!match_tcp(skb, info, &par->hotdrop)) return false; } @@ -97,7 +96,7 @@ static int ecn_mt_check(const struct xt_mtchk_param *par) return -EINVAL; if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && - ip->proto != IPPROTO_TCP) { + (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) { pr_info("cannot match TCP bits in rule for non-tcp packets\n"); return -EINVAL; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 5a03c02af99..de9da21113a 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -101,7 +101,7 @@ static unsigned int ipv4_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY) + if (!ct || ctinfo == IP_CT_RELATED_REPLY) goto out; help = nfct_help(ct); @@ -121,7 +121,9 @@ static unsigned int ipv4_confirm(unsigned int hooknum, return ret; } - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status)) { + /* adjust seqs for loopback traffic only in outgoing direction */ + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { typeof(nf_nat_seq_adjust_hook) seq_adjust; seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 7404bde9599..ab5b27a2916 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -160,7 +160,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, /* Update skb to refer to this connection */ skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; skb->nfctinfo = *ctinfo; - return -NF_ACCEPT; + return NF_ACCEPT; } /* Small and modified version of icmp_rcv */ diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index f3a9b42b16c..9bb1b8a37a2 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -82,7 +82,7 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #endif #endif /* Gather fragments. */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb); if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 9c71b2755ce..3346de5d94d 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -433,7 +433,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, /* Must be RELATED */ NF_CT_ASSERT(skb->nfctinfo == IP_CT_RELATED || - skb->nfctinfo == IP_CT_RELATED+IP_CT_IS_REPLY); + skb->nfctinfo == IP_CT_RELATED_REPLY); /* Redirects on non-null nats must be dropped, else they'll start talking to each other without our translation, and be diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 99cfa28b6d3..ebc5f8894f9 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -160,7 +160,7 @@ static void nf_nat_csum(struct sk_buff *skb, const struct iphdr *iph, void *data if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt_flags & RTCF_LOCAL) && - skb->dev->features & NETIF_F_V4_CSUM) { + (!skb->dev || skb->dev->features & NETIF_F_V4_CSUM)) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 21c30426480..733c9abc1cb 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -53,7 +53,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par) /* Connection must be valid and new. */ NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || - ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY)); + ctinfo == IP_CT_RELATED_REPLY)); NF_CT_ASSERT(par->out != NULL); return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC); diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 8812a02078a..076b7c8c4aa 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -719,117 +719,115 @@ static unsigned char snmp_object_decode(struct asn1_ctx *ctx, l = 0; switch (type) { - case SNMP_INTEGER: - len = sizeof(long); - if (!asn1_long_decode(ctx, end, &l)) { - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, - GFP_ATOMIC); - if (*obj == NULL) { - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - (*obj)->syntax.l[0] = l; - break; - case SNMP_OCTETSTR: - case SNMP_OPAQUE: - if (!asn1_octets_decode(ctx, end, &p, &len)) { - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, - GFP_ATOMIC); - if (*obj == NULL) { - kfree(p); - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - memcpy((*obj)->syntax.c, p, len); + case SNMP_INTEGER: + len = sizeof(long); + if (!asn1_long_decode(ctx, end, &l)) { + kfree(id); + return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + (*obj)->syntax.l[0] = l; + break; + case SNMP_OCTETSTR: + case SNMP_OPAQUE: + if (!asn1_octets_decode(ctx, end, &p, &len)) { + kfree(id); + return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { kfree(p); - break; - case SNMP_NULL: - case SNMP_NOSUCHOBJECT: - case SNMP_NOSUCHINSTANCE: - case SNMP_ENDOFMIBVIEW: - len = 0; - *obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC); - if (*obj == NULL) { - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - if (!asn1_null_decode(ctx, end)) { - kfree(id); - kfree(*obj); - *obj = NULL; - return 0; - } - break; - case SNMP_OBJECTID: - if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { - kfree(id); - return 0; - } - len *= sizeof(unsigned long); - *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); - if (*obj == NULL) { - kfree(lp); - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - memcpy((*obj)->syntax.ul, lp, len); + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + memcpy((*obj)->syntax.c, p, len); + kfree(p); + break; + case SNMP_NULL: + case SNMP_NOSUCHOBJECT: + case SNMP_NOSUCHINSTANCE: + case SNMP_ENDOFMIBVIEW: + len = 0; + *obj = kmalloc(sizeof(struct snmp_object), GFP_ATOMIC); + if (*obj == NULL) { + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + if (!asn1_null_decode(ctx, end)) { + kfree(id); + kfree(*obj); + *obj = NULL; + return 0; + } + break; + case SNMP_OBJECTID: + if (!asn1_oid_decode(ctx, end, (unsigned long **)&lp, &len)) { + kfree(id); + return 0; + } + len *= sizeof(unsigned long); + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { kfree(lp); - break; - case SNMP_IPADDR: - if (!asn1_octets_decode(ctx, end, &p, &len)) { - kfree(id); - return 0; - } - if (len != 4) { - kfree(p); - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); - if (*obj == NULL) { - kfree(p); - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - memcpy((*obj)->syntax.uc, p, len); + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + memcpy((*obj)->syntax.ul, lp, len); + kfree(lp); + break; + case SNMP_IPADDR: + if (!asn1_octets_decode(ctx, end, &p, &len)) { + kfree(id); + return 0; + } + if (len != 4) { kfree(p); - break; - case SNMP_COUNTER: - case SNMP_GAUGE: - case SNMP_TIMETICKS: - len = sizeof(unsigned long); - if (!asn1_ulong_decode(ctx, end, &ul)) { - kfree(id); - return 0; - } - *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); - if (*obj == NULL) { - kfree(id); - if (net_ratelimit()) - pr_notice("OOM in bsalg (%d)\n", __LINE__); - return 0; - } - (*obj)->syntax.ul[0] = ul; - break; - default: kfree(id); return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { + kfree(p); + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + memcpy((*obj)->syntax.uc, p, len); + kfree(p); + break; + case SNMP_COUNTER: + case SNMP_GAUGE: + case SNMP_TIMETICKS: + len = sizeof(unsigned long); + if (!asn1_ulong_decode(ctx, end, &ul)) { + kfree(id); + return 0; + } + *obj = kmalloc(sizeof(struct snmp_object) + len, GFP_ATOMIC); + if (*obj == NULL) { + kfree(id); + if (net_ratelimit()) + pr_notice("OOM in bsalg (%d)\n", __LINE__); + return 0; + } + (*obj)->syntax.ul[0] = ul; + break; + default: + kfree(id); + return 0; } (*obj)->syntax_len = len; diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 7317bdf1d45..a6e606e8482 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -88,7 +88,7 @@ nf_nat_fn(unsigned int hooknum, /* We never see fragments: conntrack defrags on pre-routing and local-out, and nf_nat_out protects post-routing. */ - NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))); + NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb))); ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would @@ -116,7 +116,7 @@ nf_nat_fn(unsigned int hooknum, switch (ctinfo) { case IP_CT_RELATED: - case IP_CT_RELATED+IP_CT_IS_REPLY: + case IP_CT_RELATED_REPLY: if (ip_hdr(skb)->protocol == IPPROTO_ICMP) { if (!nf_nat_icmp_reply_translation(ct, ctinfo, hooknum, skb)) @@ -144,7 +144,7 @@ nf_nat_fn(unsigned int hooknum, default: /* ESTABLISHED */ NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED || - ctinfo == (IP_CT_ESTABLISHED+IP_CT_IS_REPLY)); + ctinfo == IP_CT_ESTABLISHED_REPLY); } return nf_nat_packet(ct, ctinfo, hooknum, skb); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9aaa67165f4..39b403f854c 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -41,7 +41,6 @@ #include <linux/proc_fs.h> #include <net/sock.h> #include <net/ping.h> -#include <net/icmp.h> #include <net/udp.h> #include <net/route.h> #include <net/inet_common.h> diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index c9893d43242..08526786dc3 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -825,28 +825,28 @@ static int compat_raw_getsockopt(struct sock *sk, int level, int optname, static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { - case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); + case SIOCOUTQ: { + int amount = sk_wmem_alloc_get(sk); - return put_user(amount, (int __user *)arg); - } - case SIOCINQ: { - struct sk_buff *skb; - int amount = 0; - - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) - amount = skb->len; - spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); - } + return put_user(amount, (int __user *)arg); + } + case SIOCINQ: { + struct sk_buff *skb; + int amount = 0; + + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + if (skb != NULL) + amount = skb->len; + spin_unlock_bh(&sk->sk_receive_queue.lock); + return put_user(amount, (int __user *)arg); + } - default: + default: #ifdef CONFIG_IP_MROUTE - return ipmr_ioctl(sk, cmd, (void __user *)arg); + return ipmr_ioctl(sk, cmd, (void __user *)arg); #else - return -ENOIOCTLCMD; + return -ENOIOCTLCMD; #endif } } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 52b0b956508..33137307d52 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -108,6 +108,7 @@ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif +#include <net/atmclip.h> #define RT_FL_TOS(oldflp4) \ ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) @@ -184,6 +185,8 @@ static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) return p; } +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr); + static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), @@ -198,6 +201,7 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .local_out = __ip_local_out, + .neigh_lookup = ipv4_neigh_lookup, }; #define ECN_OR_COST(class) TC_PRIO_##class @@ -411,8 +415,10 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) "HHUptod\tSpecDst"); else { struct rtable *r = v; + struct neighbour *n; int len; + n = dst_get_neighbour(&r->dst); seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->dst.dev ? r->dst.dev->name : "*", @@ -425,9 +431,8 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) + dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, - r->dst.hh ? atomic_read(&r->dst.hh->hh_refcnt) : -1, - r->dst.hh ? (r->dst.hh->hh_output == - dev_queue_xmit) : 0, + -1, + (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -1006,6 +1011,37 @@ static int slow_chain_length(const struct rtable *head) return length >> FRACT_BITS; } +static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + struct neigh_table *tbl = &arp_tbl; + static const __be32 inaddr_any = 0; + struct net_device *dev = dst->dev; + const __be32 *pkey = daddr; + struct neighbour *n; + +#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) + if (dev->type == ARPHRD_ATM) + tbl = clip_tbl_hook; +#endif + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) + pkey = &inaddr_any; + + n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey); + if (n) + return n; + return neigh_create(tbl, pkey, dev); +} + +static int rt_bind_neighbour(struct rtable *rt) +{ + struct neighbour *n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) + return PTR_ERR(n); + dst_set_neighbour(&rt->dst, n); + + return 0; +} + static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt, struct sk_buff *skb, int ifindex) { @@ -1042,7 +1078,7 @@ restart: rt->dst.flags |= DST_NOCACHE; if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = arp_bind_neighbour(&rt->dst); + int err = rt_bind_neighbour(rt); if (err) { if (net_ratelimit()) printk(KERN_WARNING @@ -1138,7 +1174,7 @@ restart: route or unicast forwarding path. */ if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) { - int err = arp_bind_neighbour(&rt->dst); + int err = rt_bind_neighbour(rt); if (err) { spin_unlock_bh(rt_hash_lock_addr(hash)); @@ -1316,6 +1352,23 @@ reject_redirect: ; } +static bool peer_pmtu_expired(struct inet_peer *peer) +{ + unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); + + return orig && + time_after_eq(jiffies, orig) && + cmpxchg(&peer->pmtu_expires, orig, 0) == orig; +} + +static bool peer_pmtu_cleaned(struct inet_peer *peer) +{ + unsigned long orig = ACCESS_ONCE(peer->pmtu_expires); + + return orig && + cmpxchg(&peer->pmtu_expires, orig, 0) == orig; +} + static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; @@ -1331,14 +1384,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) rt_genid(dev_net(dst->dev))); rt_del(hash, rt); ret = NULL; - } else if (rt->peer && - rt->peer->pmtu_expires && - time_after_eq(jiffies, rt->peer->pmtu_expires)) { - unsigned long orig = rt->peer->pmtu_expires; - - if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) - dst_metric_set(dst, RTAX_MTU, - rt->peer->pmtu_orig); + } else if (rt->peer && peer_pmtu_expired(rt->peer)) { + dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig); } } return ret; @@ -1428,20 +1475,20 @@ static int ip_error(struct sk_buff *skb) int code; switch (rt->dst.error) { - case EINVAL: - default: - goto out; - case EHOSTUNREACH: - code = ICMP_HOST_UNREACH; - break; - case ENETUNREACH: - code = ICMP_NET_UNREACH; - IP_INC_STATS_BH(dev_net(rt->dst.dev), - IPSTATS_MIB_INNOROUTES); - break; - case EACCES: - code = ICMP_PKT_FILTERED; - break; + case EINVAL: + default: + goto out; + case EHOSTUNREACH: + code = ICMP_HOST_UNREACH; + break; + case ENETUNREACH: + code = ICMP_NET_UNREACH; + IP_INC_STATS_BH(dev_net(rt->dst.dev), + IPSTATS_MIB_INNOROUTES); + break; + case EACCES: + code = ICMP_PKT_FILTERED; + break; } if (!rt->peer) @@ -1531,8 +1578,10 @@ unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph, static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer) { - unsigned long expires = peer->pmtu_expires; + unsigned long expires = ACCESS_ONCE(peer->pmtu_expires); + if (!expires) + return; if (time_before(jiffies, expires)) { u32 orig_dst_mtu = dst_mtu(dst); if (peer->pmtu_learned < orig_dst_mtu) { @@ -1555,10 +1604,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) rt_bind_peer(rt, rt->rt_dst, 1); peer = rt->peer; if (peer) { + unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires); + if (mtu < ip_rt_min_pmtu) mtu = ip_rt_min_pmtu; - if (!peer->pmtu_expires || mtu < peer->pmtu_learned) { - unsigned long pmtu_expires; + if (!pmtu_expires || mtu < peer->pmtu_learned) { pmtu_expires = jiffies + ip_rt_mtu_expires; if (!pmtu_expires) @@ -1578,23 +1628,24 @@ static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) { struct rtable *rt = (struct rtable *) dst; __be32 orig_gw = rt->rt_gateway; + struct neighbour *n; dst_confirm(&rt->dst); - neigh_release(rt->dst.neighbour); - rt->dst.neighbour = NULL; + neigh_release(dst_get_neighbour(&rt->dst)); + dst_set_neighbour(&rt->dst, NULL); rt->rt_gateway = peer->redirect_learned.a4; - if (arp_bind_neighbour(&rt->dst) || - !(rt->dst.neighbour->nud_state & NUD_VALID)) { - if (rt->dst.neighbour) - neigh_event_send(rt->dst.neighbour, NULL); + rt_bind_neighbour(rt); + n = dst_get_neighbour(&rt->dst); + if (!n || !(n->nud_state & NUD_VALID)) { + if (n) + neigh_event_send(n, NULL); rt->rt_gateway = orig_gw; return -EAGAIN; } else { rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, - rt->dst.neighbour); + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } return 0; } @@ -1612,13 +1663,14 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) rt_bind_peer(rt, rt->rt_dst, 0); peer = rt->peer; - if (peer && peer->pmtu_expires) + if (peer) { check_peer_pmtu(dst, peer); - if (peer && peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - if (check_peer_redir(dst, peer)) - return NULL; + if (peer->redirect_learned.a4 && + peer->redirect_learned.a4 != rt->rt_gateway) { + if (check_peer_redir(dst, peer)) + return NULL; + } } rt->rt_peer_genid = rt_peer_genid(); @@ -1649,14 +1701,8 @@ static void ipv4_link_failure(struct sk_buff *skb) icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0); rt = skb_rtable(skb); - if (rt && - rt->peer && - rt->peer->pmtu_expires) { - unsigned long orig = rt->peer->pmtu_expires; - - if (cmpxchg(&rt->peer->pmtu_expires, orig, 0) == orig) - dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); - } + if (rt && rt->peer && peer_pmtu_cleaned(rt->peer)) + dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig); } static int ip_rt_bug(struct sk_buff *skb) @@ -1770,8 +1816,7 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, sizeof(u32) * RTAX_MAX); dst_init_metrics(&rt->dst, peer->metrics, false); - if (peer->pmtu_expires) - check_peer_pmtu(&rt->dst, peer); + check_peer_pmtu(&rt->dst, peer); if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; @@ -1894,9 +1939,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev))); rth = rt_intern_hash(hash, rth, skb, dev->ifindex); - err = 0; - if (IS_ERR(rth)) - err = PTR_ERR(rth); + return IS_ERR(rth) ? PTR_ERR(rth) : 0; e_nobufs: return -ENOBUFS; @@ -2702,6 +2745,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, + .neigh_lookup = ipv4_neigh_lookup, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) @@ -2775,7 +2819,8 @@ static int rt_fill_info(struct net *net, struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; - long expires; + long expires = 0; + const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags); @@ -2823,15 +2868,16 @@ static int rt_fill_info(struct net *net, NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark); error = rt->dst.error; - expires = (rt->peer && rt->peer->pmtu_expires) ? - rt->peer->pmtu_expires - jiffies : 0; - if (rt->peer) { + if (peer) { inet_peer_refcheck(rt->peer); - id = atomic_read(&rt->peer->ip_id_count) & 0xffff; - if (rt->peer->tcp_ts_stamp) { - ts = rt->peer->tcp_ts; - tsage = get_seconds() - rt->peer->tcp_ts_stamp; + id = atomic_read(&peer->ip_id_count) & 0xffff; + if (peer->tcp_ts_stamp) { + ts = peer->tcp_ts; + tsage = get_seconds() - peer->tcp_ts_stamp; } + expires = ACCESS_ONCE(peer->pmtu_expires); + if (expires) + expires -= jiffies; } if (rt_is_input_route(rt)) { @@ -3295,7 +3341,7 @@ int __init ip_rt_init(void) xfrm_init(); xfrm4_init(ip_rt_max_size); #endif - rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL); + rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 26461492a84..92bb9434b33 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -316,6 +316,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; /* We throwed the options of the initial SYN away, so we hope * the ACK carries the same options again (see RFC1122 4.2.3.8) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 57d0752e239..69fd7201129 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -398,20 +398,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec_jiffies, }, { - .procname = "inet_peer_gc_mintime", - .data = &inet_peer_gc_mintime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "inet_peer_gc_maxtime", - .data = &inet_peer_gc_maxtime, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { .procname = "tcp_orphan_retries", .data = &sysctl_tcp_orphan_retries, .maxlen = sizeof(int), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 054a59d21eb..46febcacb72 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3220,7 +3220,7 @@ __setup("thash_entries=", set_thash_entries); void __init tcp_init(void) { struct sk_buff *skb = NULL; - unsigned long nr_pages, limit; + unsigned long limit; int i, max_share, cnt; unsigned long jiffy = jiffies; @@ -3277,13 +3277,7 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; sysctl_tcp_mem[1] = limit; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bef9f04c22b..ea0d2183df4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -880,6 +880,11 @@ static void tcp_init_metrics(struct sock *sk) tp->snd_ssthresh = dst_metric(dst, RTAX_SSTHRESH); if (tp->snd_ssthresh > tp->snd_cwnd_clamp) tp->snd_ssthresh = tp->snd_cwnd_clamp; + } else { + /* ssthresh may have been reduced unnecessarily during. + * 3WHS. Restore it back to its initial default. + */ + tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; } if (dst_metric(dst, RTAX_REORDERING) && tp->reordering != dst_metric(dst, RTAX_REORDERING)) { @@ -887,10 +892,7 @@ static void tcp_init_metrics(struct sock *sk) tp->reordering = dst_metric(dst, RTAX_REORDERING); } - if (dst_metric(dst, RTAX_RTT) == 0) - goto reset; - - if (!tp->srtt && dst_metric_rtt(dst, RTAX_RTT) < (TCP_TIMEOUT_INIT << 3)) + if (dst_metric(dst, RTAX_RTT) == 0 || tp->srtt == 0) goto reset; /* Initial rtt is determined from SYN,SYN-ACK. @@ -916,19 +918,26 @@ static void tcp_init_metrics(struct sock *sk) tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); } tcp_set_rto(sk); - if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) { reset: - /* Play conservative. If timestamps are not - * supported, TCP will fail to recalculate correct - * rtt, if initial rto is too small. FORGET ALL AND RESET! + if (tp->srtt == 0) { + /* RFC2988bis: We've failed to get a valid RTT sample from + * 3WHS. This is most likely due to retransmission, + * including spurious one. Reset the RTO back to 3secs + * from the more aggressive 1sec to avoid more spurious + * retransmission. */ - if (!tp->rx_opt.saw_tstamp && tp->srtt) { - tp->srtt = 0; - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; - } + tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_FALLBACK; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_FALLBACK; } - tp->snd_cwnd = tcp_init_cwnd(tp, dst); + /* Cut cwnd down to 1 per RFC5681 if SYN or SYN-ACK has been + * retransmitted. In light of RFC2988bis' more aggressive 1sec + * initRTO, we only reset cwnd when more than 1 SYN/SYN-ACK + * retransmission has occurred. + */ + if (tp->total_retrans > 1) + tp->snd_cwnd = 1; + else + tp->snd_cwnd = tcp_init_cwnd(tp, dst); tp->snd_cwnd_stamp = tcp_time_stamp; } @@ -3112,12 +3121,13 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) tcp_xmit_retransmit_queue(sk); } -static void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) +void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) { tcp_rtt_estimator(sk, seq_rtt); tcp_set_rto(sk); inet_csk(sk)->icsk_backoff = 0; } +EXPORT_SYMBOL(tcp_valid_rtt_meas); /* Read draft-ietf-tcplw-high-performance before mucking * with this code. (Supersedes RFC1323) @@ -5806,12 +5816,6 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, tp->rx_opt.snd_wscale; tcp_init_wl(tp, TCP_SKB_CB(skb)->seq); - /* tcp_ack considers this ACK as duplicate - * and does not calculate rtt. - * Force it here. - */ - tcp_ack_update_rtt(sk, 0, 0); - if (tp->rx_opt.tstamp_ok) tp->advmss -= TCPOLEN_TSTAMP_ALIGNED; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7d6671e33b..955b8e65b69 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -429,8 +429,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) << - icsk->icsk_backoff; + inet_csk(sk)->icsk_rto = (tp->srtt ? __tcp_set_rto(tp) : + TCP_TIMEOUT_INIT) << icsk->icsk_backoff; tcp_bound_rto(sk); skb = tcp_write_queue_head(sk); @@ -1384,6 +1384,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v4_init_sequence(skb); } tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->snt_synack = tcp_time_stamp; if (tcp_v4_send_synack(sk, dst, req, (struct request_values *)&tmp_ext) || @@ -1458,6 +1459,10 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; tcp_initialize_rcv_mss(newsk); + if (tcp_rsk(req)->snt_synack) + tcp_valid_rtt_meas(newsk, + tcp_time_stamp - tcp_rsk(req)->snt_synack); + newtp->total_retrans = req->retrans; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1589,6 +1594,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) goto discard; if (nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; @@ -1854,7 +1860,7 @@ static int tcp_v4_init_sock(struct sock *sk) * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ - tp->snd_cwnd = 2; + tp->snd_cwnd = TCP_INIT_CWND; /* See draft-stevens-tcpca-spec-01 for discussion of the * initialization of these values. diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 80b1f80759a..d2fe4e06b47 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -486,7 +486,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, * algorithms that we must have the following bandaid to talk * efficiently to them. -DaveM */ - newtp->snd_cwnd = 2; + newtp->snd_cwnd = TCP_INIT_CWND; newtp->snd_cwnd_cnt = 0; newtp->bytes_acked = 0; @@ -720,6 +720,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDEFERACCEPTDROP); return NULL; } + if (tmp_opt.saw_tstamp && tmp_opt.rcv_tsecr) + tcp_rsk(req)->snt_synack = tmp_opt.rcv_tsecr; + else if (req->retrans) /* don't take RTT sample if retrans && ~TS */ + tcp_rsk(req)->snt_synack = 0; /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index abca870d8ff..1b5a19340a9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -105,6 +105,7 @@ #include <net/route.h> #include <net/checksum.h> #include <net/xfrm.h> +#include <trace/events/udp.h> #include "udp_impl.h" struct udp_table udp_table __read_mostly; @@ -1249,6 +1250,9 @@ csum_copy_err: if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -1363,6 +1367,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) is_udplite); UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); + trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -2206,16 +2211,10 @@ void __init udp_table_init(struct udp_table *table, const char *name) void __init udp_init(void) { - unsigned long nr_pages, limit; + unsigned long limit; udp_table_init(&udp_table, "UDP"); - /* Set the pressure threshold up by the same strategy of TCP. It is a - * fraction of global memory that is up to 1/2 at 256 MB, decreasing - * toward zero with the amount of memory, with a floor of 128 pages. - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2d51840e53a..327a617d594 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -32,7 +32,12 @@ static int xfrm4_tunnel_check_size(struct sk_buff *skb) dst = skb_dst(skb); mtu = dst_mtu(dst); if (skb->len > mtu) { - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); + if (skb->sk) + ip_local_error(skb->sk, EMSGSIZE, ip_hdr(skb)->daddr, + inet_sk(skb->sk)->inet_dport, mtu); + else + icmp_send(skb, ICMP_DEST_UNREACH, + ICMP_FRAG_NEEDED, htonl(mtu)); ret = -EMSGSIZE; } out: diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 981e43eaf70..fc5368ad2b0 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -117,7 +117,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; - if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) { + if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: case IPPROTO_UDPLITE: diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 498b927f68b..a06c53c14d8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -656,7 +656,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, int pfxlen, * layer address of our nexhop router */ - if (rt->rt6i_nexthop == NULL) + if (dst_get_neighbour(&rt->dst) == NULL) ifa->flags &= ~IFA_F_OPTIMISTIC; ifa->idev = idev; @@ -1470,6 +1470,8 @@ void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr) static void addrconf_join_anycast(struct inet6_ifaddr *ifp) { struct in6_addr addr; + if (ifp->prefix_len == 127) /* RFC 6164 */ + return; ipv6_addr_prefix(&addr, &ifp->addr, ifp->prefix_len); if (ipv6_addr_any(&addr)) return; @@ -1559,6 +1561,11 @@ static int addrconf_ifid_sit(u8 *eui, struct net_device *dev) return -1; } +static int addrconf_ifid_gre(u8 *eui, struct net_device *dev) +{ + return __ipv6_isatap_ifid(eui, *(__be32 *)dev->dev_addr); +} + static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) { switch (dev->type) { @@ -1572,6 +1579,8 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) return addrconf_ifid_infiniband(eui, dev); case ARPHRD_SIT: return addrconf_ifid_sit(eui, dev); + case ARPHRD_IPGRE: + return addrconf_ifid_gre(eui, dev); } return -1; } @@ -2423,6 +2432,29 @@ static void addrconf_sit_config(struct net_device *dev) } #endif +#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE) +static void addrconf_gre_config(struct net_device *dev) +{ + struct inet6_dev *idev; + struct in6_addr addr; + + pr_info("ipv6: addrconf_gre_config(%s)\n", dev->name); + + ASSERT_RTNL(); + + if ((idev = ipv6_find_idev(dev)) == NULL) { + printk(KERN_DEBUG "init gre: add_dev failed\n"); + return; + } + + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); + addrconf_prefix_route(&addr, 64, dev, 0, 0); + + if (!ipv6_generate_eui64(addr.s6_addr + 8, dev)) + addrconf_add_linklocal(idev, &addr); +} +#endif + static inline int ipv6_inherit_linklocal(struct inet6_dev *idev, struct net_device *link_dev) { @@ -2539,6 +2571,11 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, addrconf_sit_config(dev); break; #endif +#if defined(CONFIG_NET_IPGRE) || defined(CONFIG_NET_IPGRE_MODULE) + case ARPHRD_IPGRE: + addrconf_gre_config(dev); + break; +#endif case ARPHRD_TUNNEL6: addrconf_ip6_tnl_config(dev); break; @@ -4692,16 +4729,20 @@ int __init addrconf_init(void) if (err < 0) goto errout_af; - err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo); + err = __rtnl_register(PF_INET6, RTM_GETLINK, NULL, inet6_dump_ifinfo, + NULL); if (err < 0) goto errout; /* Only the first call to __rtnl_register can fail */ - __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL); - __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL); - __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, inet6_dump_ifaddr); - __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, inet6_dump_ifmcaddr); - __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, inet6_dump_ifacaddr); + __rtnl_register(PF_INET6, RTM_NEWADDR, inet6_rtm_newaddr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_DELADDR, inet6_rtm_deladdr, NULL, NULL); + __rtnl_register(PF_INET6, RTM_GETADDR, inet6_rtm_getaddr, + inet6_dump_ifaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETMULTICAST, NULL, + inet6_dump_ifmcaddr, NULL); + __rtnl_register(PF_INET6, RTM_GETANYCAST, NULL, + inet6_dump_ifacaddr, NULL); ipv6_addr_label_rtnl_register(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index c8993e5a337..2d8ddba9ee5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -592,8 +592,11 @@ out: void __init ipv6_addr_label_rtnl_register(void) { - __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, NULL); - __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, NULL); - __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, ip6addrlbl_dump); + __rtnl_register(PF_INET6, RTM_NEWADDRLABEL, ip6addrlbl_newdel, + NULL, NULL); + __rtnl_register(PF_INET6, RTM_DELADDRLABEL, ip6addrlbl_newdel, + NULL, NULL); + __rtnl_register(PF_INET6, RTM_GETADDRLABEL, ip6addrlbl_get, + ip6addrlbl_dump, NULL); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b7919f901fb..3b5669a2582 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -272,6 +272,10 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; + + if (addr->sin6_family != AF_INET6) + return -EAFNOSUPPORT; + addr_type = ipv6_addr_type(&addr->sin6_addr); if ((addr_type & IPV6_ADDR_MULTICAST) && sock->type == SOCK_STREAM) return -EINVAL; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 4076a0b14b2..54a4678955b 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -1455,7 +1455,7 @@ static int fib6_age(struct rt6_info *rt, void *arg) RT6_TRACE("aging clone %p\n", rt); return -1; } else if ((rt->rt6i_flags & RTF_GATEWAY) && - (!(rt->rt6i_nexthop->flags & NTF_ROUTER))) { + (!(dst_get_neighbour(&rt->dst)->flags & NTF_ROUTER))) { RT6_TRACE("purging route %p via non-router but gateway\n", rt); return -1; @@ -1586,7 +1586,8 @@ int __init fib6_init(void) if (ret) goto out_kmem_cache_create; - ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib); + ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib, + NULL); if (ret) goto out_unregister_subsys; out: diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 9d4b165837d..32e5339db0c 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -100,6 +100,7 @@ static int ip6_finish_output2(struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); struct net_device *dev = dst->dev; + struct neighbour *neigh; skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; @@ -134,10 +135,9 @@ static int ip6_finish_output2(struct sk_buff *skb) skb->len); } - if (dst->hh) - return neigh_hh_output(dst->hh, skb); - else if (dst->neighbour) - return dst->neighbour->output(skb); + neigh = dst_get_neighbour(dst); + if (neigh) + return neigh_output(neigh, skb); IP6_INC_STATS_BH(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -385,6 +385,7 @@ int ip6_forward(struct sk_buff *skb) struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); struct net *net = dev_net(dst->dev); + struct neighbour *n; u32 mtu; if (net->ipv6.devconf_all->forwarding == 0) @@ -459,11 +460,10 @@ int ip6_forward(struct sk_buff *skb) send redirects to source routed frames. We don't send redirects to frames decapsulated from IPsec. */ - if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 && - !skb_sec_path(skb)) { + n = dst_get_neighbour(dst); + if (skb->dev == dst->dev && n && opt->srcrt == 0 && !skb_sec_path(skb)) { struct in6_addr *target = NULL; struct rt6_info *rt; - struct neighbour *n = dst->neighbour; /* * incoming and outgoing devices are the same @@ -596,6 +596,31 @@ int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr) return offset; } +void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt) +{ + static atomic_t ipv6_fragmentation_id; + int old, new; + + if (rt) { + struct inet_peer *peer; + + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + peer = rt->rt6i_peer; + if (peer) { + fhdr->identification = htonl(inet_getid(peer, 0)); + return; + } + } + do { + old = atomic_read(&ipv6_fragmentation_id); + new = old + 1; + if (!new) + new = 1; + } while (atomic_cmpxchg(&ipv6_fragmentation_id, old, new) != old); + fhdr->identification = htonl(new); +} + int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct sk_buff *frag; @@ -680,7 +705,7 @@ int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) skb_reset_network_header(skb); memcpy(skb_network_header(skb), tmp_hdr, hlen); - ipv6_select_ident(fh); + ipv6_select_ident(fh, rt); fh->nexthdr = nexthdr; fh->reserved = 0; fh->frag_off = htons(IP6_MF); @@ -826,7 +851,7 @@ slow_path: fh->nexthdr = nexthdr; fh->reserved = 0; if (!frag_id) { - ipv6_select_ident(fh); + ipv6_select_ident(fh, rt); frag_id = fh->identification; } else fh->identification = frag_id; @@ -920,8 +945,11 @@ out: static int ip6_dst_lookup_tail(struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6) { - int err; struct net *net = sock_net(sk); +#ifdef CONFIG_IPV6_OPTIMISTIC_DAD + struct neighbour *n; +#endif + int err; if (*dst == NULL) *dst = ip6_route_output(net, sk, fl6); @@ -947,7 +975,8 @@ static int ip6_dst_lookup_tail(struct sock *sk, * dst entry and replace it instead with the * dst entry of the nexthop router */ - if ((*dst)->neighbour && !((*dst)->neighbour->nud_state & NUD_VALID)) { + n = dst_get_neighbour(*dst); + if (n && !(n->nud_state & NUD_VALID)) { struct inet6_ifaddr *ifp; struct flowi6 fl_gw6; int redirect; @@ -1072,7 +1101,8 @@ static inline int ip6_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu,unsigned int flags) + int transhdrlen, int mtu,unsigned int flags, + struct rt6_info *rt) { struct sk_buff *skb; @@ -1116,7 +1146,7 @@ static inline int ip6_ufo_append_data(struct sock *sk, skb_shinfo(skb)->gso_size = (mtu - fragheaderlen - sizeof(struct frag_hdr)) & ~7; skb_shinfo(skb)->gso_type = SKB_GSO_UDP; - ipv6_select_ident(&fhdr); + ipv6_select_ident(&fhdr, rt); skb_shinfo(skb)->ip6_frag_id = fhdr.identification; __skb_queue_tail(&sk->sk_write_queue, skb); @@ -1282,7 +1312,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, err = ip6_ufo_append_data(sk, getfrag, from, length, hh_len, fragheaderlen, - transhdrlen, mtu, flags); + transhdrlen, mtu, flags, rt); if (err) goto error; return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 82a809901f8..705c8288628 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1354,7 +1354,8 @@ int __init ip6_mr_init(void) goto add_proto_fail; } #endif - rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, ip6mr_rtm_dumproute); + rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL, + ip6mr_rtm_dumproute, NULL); return 0; #ifdef CONFIG_IPV6_PIMSM_V2 add_proto_fail: diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 7596f071d30..9da6e02eaae 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -107,8 +107,6 @@ static const struct neigh_ops ndisc_generic_ops = { .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_connected_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; static const struct neigh_ops ndisc_hh_ops = { @@ -117,17 +115,13 @@ static const struct neigh_ops ndisc_hh_ops = { .error_report = ndisc_error_report, .output = neigh_resolve_output, .connected_output = neigh_resolve_output, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, }; static const struct neigh_ops ndisc_direct_ops = { .family = AF_INET6, - .output = dev_queue_xmit, - .connected_output = dev_queue_xmit, - .hh_output = dev_queue_xmit, - .queue_xmit = dev_queue_xmit, + .output = neigh_direct_output, + .connected_output = neigh_direct_output, }; struct neigh_table nd_tbl = { @@ -392,7 +386,7 @@ static int ndisc_constructor(struct neighbour *neigh) if (!dev->header_ops) { neigh->nud_state = NUD_NOARP; neigh->ops = &ndisc_direct_ops; - neigh->output = neigh->ops->queue_xmit; + neigh->output = neigh_direct_output; } else { if (is_multicast) { neigh->nud_state = NUD_NOARP; @@ -1244,7 +1238,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); if (rt) - neigh = rt->rt6i_nexthop; + neigh = dst_get_neighbour(&rt->dst); if (rt && lifetime == 0) { neigh_clone(neigh); @@ -1265,7 +1259,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - neigh = rt->rt6i_nexthop; + neigh = dst_get_neighbour(&rt->dst); if (neigh == NULL) { ND_PRINTK0(KERN_ERR "ICMPv6 RA: %s() got default router without neighbour.\n", diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 413ab0754e1..24939486328 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -204,7 +204,8 @@ ipq_build_packet_message(struct nf_queue_entry *entry, int *errp) else pmsg->outdev_name[0] = '\0'; - if (entry->indev && entry->skb->dev) { + if (entry->indev && entry->skb->dev && + entry->skb->mac_header != entry->skb->network_header) { pmsg->hw_type = entry->skb->dev->type; pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr); } @@ -403,7 +404,8 @@ ipq_dev_drop(int ifindex) static inline void __ipq_rcv_skb(struct sk_buff *skb) { - int status, type, pid, flags, nlmsglen, skblen; + int status, type, pid, flags; + unsigned int nlmsglen, skblen; struct nlmsghdr *nlh; skblen = skb->len; diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c index c8af58b2256..4111050a9fc 100644 --- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c @@ -160,7 +160,7 @@ static unsigned int ipv6_confirm(unsigned int hooknum, /* This is where we call the helper: as the packet goes out. */ ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED + IP_CT_IS_REPLY) + if (!ct || ctinfo == IP_CT_RELATED_REPLY) goto out; help = nfct_help(ct); diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 1df3c8b6bf4..7c05e7eacbc 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -177,7 +177,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, /* Update skb to refer to this connection */ skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general; skb->nfctinfo = *ctinfo; - return -NF_ACCEPT; + return NF_ACCEPT; } static int diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index cc7313b8f7e..6a79f3081bd 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -959,57 +959,54 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, return -EFAULT; switch (optname) { - case IPV6_CHECKSUM: - if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && - level == IPPROTO_IPV6) { - /* - * RFC3542 tells that IPV6_CHECKSUM socket - * option in the IPPROTO_IPV6 level is not - * allowed on ICMPv6 sockets. - * If you want to set it, use IPPROTO_RAW - * level IPV6_CHECKSUM socket option - * (Linux extension). - */ - return -EINVAL; - } + case IPV6_CHECKSUM: + if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && + level == IPPROTO_IPV6) { + /* + * RFC3542 tells that IPV6_CHECKSUM socket + * option in the IPPROTO_IPV6 level is not + * allowed on ICMPv6 sockets. + * If you want to set it, use IPPROTO_RAW + * level IPV6_CHECKSUM socket option + * (Linux extension). + */ + return -EINVAL; + } - /* You may get strange result with a positive odd offset; - RFC2292bis agrees with me. */ - if (val > 0 && (val&1)) - return -EINVAL; - if (val < 0) { - rp->checksum = 0; - } else { - rp->checksum = 1; - rp->offset = val; - } + /* You may get strange result with a positive odd offset; + RFC2292bis agrees with me. */ + if (val > 0 && (val&1)) + return -EINVAL; + if (val < 0) { + rp->checksum = 0; + } else { + rp->checksum = 1; + rp->offset = val; + } - return 0; - break; + return 0; - default: - return -ENOPROTOOPT; + default: + return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { - switch(level) { - case SOL_RAW: - break; + switch (level) { + case SOL_RAW: + break; - case SOL_ICMPV6: - if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_seticmpfilter(sk, level, optname, optval, - optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM) - break; - default: - return ipv6_setsockopt(sk, level, optname, optval, - optlen); + case SOL_ICMPV6: + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_seticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); @@ -1075,21 +1072,19 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { - switch(level) { - case SOL_RAW: - break; + switch (level) { + case SOL_RAW: + break; - case SOL_ICMPV6: - if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) - return -EOPNOTSUPP; - return rawv6_geticmpfilter(sk, level, optname, optval, - optlen); - case SOL_IPV6: - if (optname == IPV6_CHECKSUM) - break; - default: - return ipv6_getsockopt(sk, level, optname, optval, - optlen); + case SOL_ICMPV6: + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) + return -EOPNOTSUPP; + return rawv6_geticmpfilter(sk, level, optname, optval, optlen); + case SOL_IPV6: + if (optname == IPV6_CHECKSUM) + break; + default: + return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); @@ -1119,31 +1114,29 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { - switch(cmd) { - case SIOCOUTQ: - { - int amount = sk_wmem_alloc_get(sk); + switch (cmd) { + case SIOCOUTQ: { + int amount = sk_wmem_alloc_get(sk); - return put_user(amount, (int __user *)arg); - } - case SIOCINQ: - { - struct sk_buff *skb; - int amount = 0; - - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) - amount = skb->tail - skb->transport_header; - spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); - } + return put_user(amount, (int __user *)arg); + } + case SIOCINQ: { + struct sk_buff *skb; + int amount = 0; + + spin_lock_bh(&sk->sk_receive_queue.lock); + skb = skb_peek(&sk->sk_receive_queue); + if (skb != NULL) + amount = skb->tail - skb->transport_header; + spin_unlock_bh(&sk->sk_receive_queue.lock); + return put_user(amount, (int __user *)arg); + } - default: + default: #ifdef CONFIG_IPV6_MROUTE - return ip6mr_ioctl(sk, cmd, (void __user *)arg); + return ip6mr_ioctl(sk, cmd, (void __user *)arg); #else - return -ENOIOCTLCMD; + return -ENOIOCTLCMD; #endif } } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index de2b1decd78..e8987da0666 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -72,7 +72,8 @@ #define RT6_TRACE(x...) do { ; } while (0) #endif -static struct rt6_info * ip6_rt_copy(struct rt6_info *ort); +static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, + const struct in6_addr *dest); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); static unsigned int ip6_default_mtu(const struct dst_entry *dst); @@ -127,6 +128,11 @@ static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) return p; } +static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + return __neigh_lookup_errno(&nd_tbl, daddr, dst->dev); +} + static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -142,6 +148,7 @@ static struct dst_ops ip6_dst_ops_template = { .link_failure = ip6_link_failure, .update_pmtu = ip6_rt_update_pmtu, .local_out = __ip6_local_out, + .neigh_lookup = ip6_neigh_lookup, }; static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst) @@ -168,6 +175,7 @@ static struct dst_ops ip6_dst_blackhole_ops = { .default_advmss = ip6_default_advmss, .update_pmtu = ip6_rt_blackhole_update_pmtu, .cow_metrics = ip6_rt_blackhole_cow_metrics, + .neigh_lookup = ip6_neigh_lookup, }; static const u32 ip6_template_metrics[RTAX_MAX] = { @@ -228,9 +236,10 @@ static struct rt6_info ip6_blk_hole_entry_template = { /* allocate dst with ip6_dst_ops */ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops, - struct net_device *dev) + struct net_device *dev, + int flags) { - struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, 0); + struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags); memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry)); @@ -355,7 +364,7 @@ out: #ifdef CONFIG_IPV6_ROUTER_PREF static void rt6_probe(struct rt6_info *rt) { - struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL; + struct neighbour *neigh = rt ? dst_get_neighbour(&rt->dst) : NULL; /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it @@ -403,7 +412,7 @@ static inline int rt6_check_dev(struct rt6_info *rt, int oif) static inline int rt6_check_neigh(struct rt6_info *rt) { - struct neighbour *neigh = rt->rt6i_nexthop; + struct neighbour *neigh = dst_get_neighbour(&rt->dst); int m; if (rt->rt6i_flags & RTF_NONEXTHOP || !(rt->rt6i_flags & RTF_GATEWAY)) @@ -682,7 +691,8 @@ int ip6_ins_rt(struct rt6_info *rt) return __ip6_ins_rt(rt, &info); } -static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_addr *daddr, +static struct rt6_info *rt6_alloc_cow(const struct rt6_info *ort, + const struct in6_addr *daddr, const struct in6_addr *saddr) { struct rt6_info *rt; @@ -691,7 +701,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_add * Clone the route. */ - rt = ip6_rt_copy(ort); + rt = ip6_rt_copy(ort, daddr); if (rt) { struct neighbour *neigh; @@ -699,12 +709,11 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_add if (!(rt->rt6i_flags&RTF_GATEWAY)) { if (rt->rt6i_dst.plen != 128 && - ipv6_addr_equal(&rt->rt6i_dst.addr, daddr)) + ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; ipv6_addr_copy(&rt->rt6i_gateway, daddr); } - ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; rt->dst.flags |= DST_HOST; @@ -744,22 +753,23 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, const struct in6_add dst_free(&rt->dst); return NULL; } - rt->rt6i_nexthop = neigh; + dst_set_neighbour(&rt->dst, neigh); } return rt; } -static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, const struct in6_addr *daddr) +static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, + const struct in6_addr *daddr) { - struct rt6_info *rt = ip6_rt_copy(ort); + struct rt6_info *rt = ip6_rt_copy(ort, daddr); + if (rt) { - ipv6_addr_copy(&rt->rt6i_dst.addr, daddr); rt->rt6i_dst.plen = 128; rt->rt6i_flags |= RTF_CACHE; rt->dst.flags |= DST_HOST; - rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop); + dst_set_neighbour(&rt->dst, neigh_clone(dst_get_neighbour(&ort->dst))); } return rt; } @@ -793,7 +803,7 @@ restart: dst_hold(&rt->dst); read_unlock_bh(&table->tb6_lock); - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr); else if (!(rt->dst.flags & DST_HOST)) nrt = rt6_alloc_clone(rt, &fl6->daddr); @@ -899,7 +909,10 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori new->input = dst_discard; new->output = dst_discard; - dst_copy_metrics(new, &ort->dst); + if (dst_metrics_read_only(&ort->dst)) + new->_metrics = ort->dst._metrics; + else + dst_copy_metrics(new, &ort->dst); rt->rt6i_idev = ort->rt6i_idev; if (rt->rt6i_idev) in6_dev_hold(rt->rt6i_idev); @@ -1042,7 +1055,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, if (unlikely(idev == NULL)) return NULL; - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, dev, 0); if (unlikely(rt == NULL)) { in6_dev_put(idev); goto out; @@ -1057,19 +1070,12 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, } rt->rt6i_idev = idev; - rt->rt6i_nexthop = neigh; + dst_set_neighbour(&rt->dst, neigh); atomic_set(&rt->dst.__refcnt, 1); + ipv6_addr_copy(&rt->rt6i_dst.addr, addr); dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255); rt->dst.output = ip6_output; -#if 0 /* there's no chance to use these for ndisc */ - rt->dst.flags = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST - ? DST_HOST - : 0; - ipv6_addr_copy(&rt->rt6i_dst.addr, addr); - rt->rt6i_dst.plen = 128; -#endif - spin_lock_bh(&icmp6_dst_lock); rt->dst.next = icmp6_dst_gc_list; icmp6_dst_gc_list = &rt->dst; @@ -1214,7 +1220,7 @@ int ip6_route_add(struct fib6_config *cfg) goto out; } - rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL); + rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, NULL, DST_NOCOUNT); if (rt == NULL) { err = -ENOMEM; @@ -1244,7 +1250,7 @@ int ip6_route_add(struct fib6_config *cfg) ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) - rt->dst.flags = DST_HOST; + rt->dst.flags |= DST_HOST; #ifdef CONFIG_IPV6_SUBTREES ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); @@ -1345,12 +1351,12 @@ int ip6_route_add(struct fib6_config *cfg) rt->rt6i_prefsrc.plen = 0; if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { - rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); - if (IS_ERR(rt->rt6i_nexthop)) { - err = PTR_ERR(rt->rt6i_nexthop); - rt->rt6i_nexthop = NULL; + struct neighbour *n = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); + if (IS_ERR(n)) { + err = PTR_ERR(n); goto out; } + dst_set_neighbour(&rt->dst, n); } rt->rt6i_flags = cfg->fc_flags; @@ -1581,10 +1587,10 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, dst_confirm(&rt->dst); /* Duplicate redirect: silently ignore. */ - if (neigh == rt->dst.neighbour) + if (neigh == dst_get_neighbour(&rt->dst)) goto out; - nrt = ip6_rt_copy(rt); + nrt = ip6_rt_copy(rt, dest); if (nrt == NULL) goto out; @@ -1592,12 +1598,11 @@ void rt6_redirect(const struct in6_addr *dest, const struct in6_addr *src, if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; - ipv6_addr_copy(&nrt->rt6i_dst.addr, dest); nrt->rt6i_dst.plen = 128; nrt->dst.flags |= DST_HOST; ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key); - nrt->rt6i_nexthop = neigh_clone(neigh); + dst_set_neighbour(&nrt->dst, neigh_clone(neigh)); if (ip6_ins_rt(nrt)) goto out; @@ -1677,7 +1682,7 @@ again: 1. It is connected route. Action: COW 2. It is gatewayed route or NONEXTHOP route. Action: clone it. */ - if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP)) + if (!dst_get_neighbour(&rt->dst) && !(rt->rt6i_flags & RTF_NONEXTHOP)) nrt = rt6_alloc_cow(rt, daddr, saddr); else nrt = rt6_alloc_clone(rt, daddr); @@ -1730,16 +1735,19 @@ void rt6_pmtu_discovery(const struct in6_addr *daddr, const struct in6_addr *sad * Misc support functions */ -static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) +static struct rt6_info *ip6_rt_copy(const struct rt6_info *ort, + const struct in6_addr *dest) { struct net *net = dev_net(ort->rt6i_dev); struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - ort->dst.dev); + ort->dst.dev, 0); if (rt) { rt->dst.input = ort->dst.input; rt->dst.output = ort->dst.output; + ipv6_addr_copy(&rt->rt6i_dst.addr, dest); + rt->rt6i_dst.plen = ort->rt6i_dst.plen; dst_copy_metrics(&rt->dst, &ort->dst); rt->dst.error = ort->dst.error; rt->rt6i_idev = ort->rt6i_idev; @@ -1752,7 +1760,6 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES; rt->rt6i_metric = 0; - memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key)); #endif @@ -2013,7 +2020,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, { struct net *net = dev_net(idev->dev); struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops, - net->loopback_dev); + net->loopback_dev, 0); struct neighbour *neigh; if (rt == NULL) { @@ -2025,7 +2032,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, in6_dev_hold(idev); - rt->dst.flags = DST_HOST; + rt->dst.flags |= DST_HOST; rt->dst.input = ip6_input; rt->dst.output = ip6_output; rt->rt6i_idev = idev; @@ -2042,7 +2049,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, return ERR_CAST(neigh); } - rt->rt6i_nexthop = neigh; + dst_set_neighbour(&rt->dst, neigh); ipv6_addr_copy(&rt->rt6i_dst.addr, addr); rt->rt6i_dst.plen = 128; @@ -2407,8 +2414,8 @@ static int rt6_fill_node(struct net *net, if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; - if (rt->dst.neighbour) - NLA_PUT(skb, RTA_GATEWAY, 16, &rt->dst.neighbour->primary_key); + if (dst_get_neighbour(&rt->dst)) + NLA_PUT(skb, RTA_GATEWAY, 16, &dst_get_neighbour(&rt->dst)->primary_key); if (rt->dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex); @@ -2592,6 +2599,7 @@ struct rt6_proc_arg static int rt6_info_route(struct rt6_info *rt, void *p_arg) { struct seq_file *m = p_arg; + struct neighbour *n; seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); @@ -2600,9 +2608,9 @@ static int rt6_info_route(struct rt6_info *rt, void *p_arg) #else seq_puts(m, "00000000000000000000000000000000 00 "); #endif - - if (rt->rt6i_nexthop) { - seq_printf(m, "%pi6", rt->rt6i_nexthop->primary_key); + n = dst_get_neighbour(&rt->dst); + if (n) { + seq_printf(m, "%pi6", n->primary_key); } else { seq_puts(m, "00000000000000000000000000000000"); } @@ -2925,9 +2933,9 @@ int __init ip6_route_init(void) goto xfrm6_init; ret = -ENOBUFS; - if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) || - __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) || - __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL)) + if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL, NULL) || + __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL, NULL) || + __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL, NULL)) goto fib6_rules_init; ret = register_netdevice_notifier(&ip6_route_dev_notifier); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 1cca5761aea..07bf1085458 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -677,7 +677,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct neighbour *neigh = NULL; if (skb_dst(skb)) - neigh = skb_dst(skb)->neighbour; + neigh = dst_get_neighbour(skb_dst(skb)); if (neigh == NULL) { if (net_ratelimit()) @@ -702,7 +702,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct neighbour *neigh = NULL; if (skb_dst(skb)) - neigh = skb_dst(skb)->neighbour; + neigh = dst_get_neighbour(skb_dst(skb)); if (neigh == NULL) { if (net_ratelimit()) diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 8b9644a8b69..89d5bf80622 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -223,6 +223,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->wscale_ok = tcp_opt.wscale_ok; ireq->tstamp_ok = tcp_opt.saw_tstamp; req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + treq->snt_synack = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index d1fd28711ba..78aa53492b3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1341,6 +1341,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) } have_isn: tcp_rsk(req)->snt_isn = isn; + tcp_rsk(req)->snt_synack = tcp_time_stamp; security_inet_conn_request(sk, skb, req); @@ -1509,6 +1510,10 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = dst_metric_advmss(dst); tcp_initialize_rcv_mss(newsk); + if (tcp_rsk(req)->snt_synack) + tcp_valid_rtt_meas(newsk, + tcp_time_stamp - tcp_rsk(req)->snt_synack); + newtp->total_retrans = req->retrans; newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; newinet->inet_rcv_saddr = LOOPBACK4_IPV6; @@ -1644,6 +1649,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) * the new socket.. */ if(nsk != sk) { + sock_rps_save_rxhash(nsk, skb->rxhash); if (tcp_child_process(sk, nsk, skb)) goto reset; if (opt_skb) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 41f8c9c08db..29213b51c49 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -453,8 +453,11 @@ csum_copy_err: } unlock_sock_fast(sk, slow); - if (flags & MSG_DONTWAIT) + if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -1356,7 +1359,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen); fptr->nexthdr = nexthdr; fptr->reserved = 0; - ipv6_select_ident(fptr); + ipv6_select_ident(fptr, (struct rt6_info *)skb_dst(skb)); /* Fragment the skb. ipv6 header and the remaining fields of the * fragment header are updated in ipv6_gso_segment() diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index cc616974a44..c24f25ab67d 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -369,7 +369,7 @@ static void irda_getvalue_confirm(int result, __u16 obj_id, { struct irda_sock *self; - self = (struct irda_sock *) priv; + self = priv; if (!self) { IRDA_WARNING("%s: lost myself!\n", __func__); return; @@ -418,7 +418,7 @@ static void irda_selective_discovery_indication(discinfo_t *discovery, IRDA_DEBUG(2, "%s()\n", __func__); - self = (struct irda_sock *) priv; + self = priv; if (!self) { IRDA_WARNING("%s: lost myself!\n", __func__); return; diff --git a/net/irda/ircomm/ircomm_tty_attach.c b/net/irda/ircomm/ircomm_tty_attach.c index 3c175402302..b65d66e0d81 100644 --- a/net/irda/ircomm/ircomm_tty_attach.c +++ b/net/irda/ircomm/ircomm_tty_attach.c @@ -382,7 +382,7 @@ static void ircomm_tty_discovery_indication(discinfo_t *discovery, info.daddr = discovery->daddr; info.saddr = discovery->saddr; - self = (struct ircomm_tty_cb *) priv; + self = priv; ircomm_tty_do_event(self, IRCOMM_TTY_DISCOVERY_INDICATION, NULL, &info); } diff --git a/net/irda/irda_device.c b/net/irda/irda_device.c index 25cc2e69515..3eca35faf2a 100644 --- a/net/irda/irda_device.c +++ b/net/irda/irda_device.c @@ -262,7 +262,7 @@ static void irda_task_timer_expired(void *data) IRDA_DEBUG(2, "%s()\n", __func__); - task = (struct irda_task *) data; + task = data; irda_task_kick(task); } diff --git a/net/irda/iriap.c b/net/irda/iriap.c index 36477538cea..e71e85ba2bf 100644 --- a/net/irda/iriap.c +++ b/net/irda/iriap.c @@ -87,6 +87,8 @@ static inline void iriap_start_watchdog_timer(struct iriap_cb *self, iriap_watchdog_timer_expired); } +static struct lock_class_key irias_objects_key; + /* * Function iriap_init (void) * @@ -114,6 +116,9 @@ int __init iriap_init(void) return -ENOMEM; } + lockdep_set_class_and_name(&irias_objects->hb_spinlock, &irias_objects_key, + "irias_objects"); + /* * Register some default services for IrLMP */ @@ -300,7 +305,7 @@ static void iriap_disconnect_indication(void *instance, void *sap, IRDA_DEBUG(4, "%s(), reason=%s\n", __func__, irlmp_reasons[reason]); - self = (struct iriap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IAS_MAGIC, return;); @@ -754,7 +759,7 @@ static void iriap_connect_confirm(void *instance, void *sap, { struct iriap_cb *self; - self = (struct iriap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IAS_MAGIC, return;); @@ -786,7 +791,7 @@ static void iriap_connect_indication(void *instance, void *sap, IRDA_DEBUG(1, "%s()\n", __func__); - self = (struct iriap_cb *) instance; + self = instance; IRDA_ASSERT(skb != NULL, return;); IRDA_ASSERT(self != NULL, goto out;); @@ -834,7 +839,7 @@ static int iriap_data_indication(void *instance, void *sap, IRDA_DEBUG(3, "%s()\n", __func__); - self = (struct iriap_cb *) instance; + self = instance; IRDA_ASSERT(skb != NULL, return 0;); IRDA_ASSERT(self != NULL, goto out;); diff --git a/net/irda/irlan/irlan_client.c b/net/irda/irlan/irlan_client.c index 7ed3af95793..ba1a3fc39b5 100644 --- a/net/irda/irlan/irlan_client.c +++ b/net/irda/irlan/irlan_client.c @@ -198,7 +198,7 @@ static int irlan_client_ctrl_data_indication(void *instance, void *sap, IRDA_DEBUG(2, "%s()\n", __func__ ); - self = (struct irlan_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return -1;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;); @@ -226,8 +226,8 @@ static void irlan_client_ctrl_disconnect_indication(void *instance, void *sap, IRDA_DEBUG(4, "%s(), reason=%d\n", __func__ , reason); - self = (struct irlan_cb *) instance; - tsap = (struct tsap_cb *) sap; + self = instance; + tsap = sap; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); @@ -298,7 +298,7 @@ static void irlan_client_ctrl_connect_confirm(void *instance, void *sap, IRDA_DEBUG(4, "%s()\n", __func__ ); - self = (struct irlan_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); @@ -542,7 +542,7 @@ void irlan_client_get_value_confirm(int result, __u16 obj_id, IRDA_ASSERT(priv != NULL, return;); - self = (struct irlan_cb *) priv; + self = priv; IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); /* We probably don't need to make any more queries */ diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index 6130f9d9dbe..77911763627 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -317,8 +317,8 @@ static void irlan_connect_indication(void *instance, void *sap, IRDA_DEBUG(2, "%s()\n", __func__ ); - self = (struct irlan_cb *) instance; - tsap = (struct tsap_cb *) sap; + self = instance; + tsap = sap; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); @@ -361,7 +361,7 @@ static void irlan_connect_confirm(void *instance, void *sap, { struct irlan_cb *self; - self = (struct irlan_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); @@ -406,8 +406,8 @@ static void irlan_disconnect_indication(void *instance, IRDA_DEBUG(0, "%s(), reason=%d\n", __func__ , reason); - self = (struct irlan_cb *) instance; - tsap = (struct tsap_cb *) sap; + self = instance; + tsap = sap; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); diff --git a/net/irda/irlan/irlan_eth.c b/net/irda/irlan/irlan_eth.c index 8ee1ff6c742..e8d5f4405d6 100644 --- a/net/irda/irlan/irlan_eth.c +++ b/net/irda/irlan/irlan_eth.c @@ -272,7 +272,7 @@ void irlan_eth_flow_indication(void *instance, void *sap, LOCAL_FLOW flow) struct irlan_cb *self; struct net_device *dev; - self = (struct irlan_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); diff --git a/net/irda/irlan/irlan_provider.c b/net/irda/irlan/irlan_provider.c index b8af74ab8b6..8b61cf0d8a6 100644 --- a/net/irda/irlan/irlan_provider.c +++ b/net/irda/irlan/irlan_provider.c @@ -73,7 +73,7 @@ static int irlan_provider_data_indication(void *instance, void *sap, IRDA_DEBUG(4, "%s()\n", __func__ ); - self = (struct irlan_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return -1;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return -1;); @@ -131,8 +131,8 @@ static void irlan_provider_connect_indication(void *instance, void *sap, IRDA_DEBUG(0, "%s()\n", __func__ ); - self = (struct irlan_cb *) instance; - tsap = (struct tsap_cb *) sap; + self = instance; + tsap = sap; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); @@ -182,8 +182,8 @@ static void irlan_provider_disconnect_indication(void *instance, void *sap, IRDA_DEBUG(4, "%s(), reason=%d\n", __func__ , reason); - self = (struct irlan_cb *) instance; - tsap = (struct tsap_cb *) sap; + self = instance; + tsap = sap; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == IRLAN_MAGIC, return;); diff --git a/net/irda/irqueue.c b/net/irda/irqueue.c index 9715e6e5900..f06947c4fa8 100644 --- a/net/irda/irqueue.c +++ b/net/irda/irqueue.c @@ -780,7 +780,7 @@ void* hashbin_lock_find( hashbin_t* hashbin, long hashv, const char* name ) /* * Search for entry */ - entry = (irda_queue_t* ) hashbin_find( hashbin, hashv, name ); + entry = hashbin_find(hashbin, hashv, name); /* Release lock */ spin_unlock_irqrestore(&hashbin->hb_spinlock, flags); @@ -813,7 +813,7 @@ void* hashbin_find_next( hashbin_t* hashbin, long hashv, const char* name, * This allow to check if the current item is still in the * hashbin or has been removed. */ - entry = (irda_queue_t* ) hashbin_find( hashbin, hashv, name ); + entry = hashbin_find(hashbin, hashv, name); /* * Trick hashbin_get_next() to return what we want diff --git a/net/irda/irttp.c b/net/irda/irttp.c index 9d9af460697..285ccd623ae 100644 --- a/net/irda/irttp.c +++ b/net/irda/irttp.c @@ -350,7 +350,7 @@ static int irttp_param_max_sdu_size(void *instance, irda_param_t *param, { struct tsap_cb *self; - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return -1;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;); @@ -879,7 +879,7 @@ static int irttp_udata_indication(void *instance, void *sap, IRDA_DEBUG(4, "%s()\n", __func__); - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return -1;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return -1;); @@ -914,7 +914,7 @@ static int irttp_data_indication(void *instance, void *sap, unsigned long flags; int n; - self = (struct tsap_cb *) instance; + self = instance; n = skb->data[0] & 0x7f; /* Extract the credits */ @@ -996,7 +996,7 @@ static void irttp_status_indication(void *instance, IRDA_DEBUG(4, "%s()\n", __func__); - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;); @@ -1025,7 +1025,7 @@ static void irttp_flow_indication(void *instance, void *sap, LOCAL_FLOW flow) { struct tsap_cb *self; - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;); @@ -1208,7 +1208,7 @@ static void irttp_connect_confirm(void *instance, void *sap, IRDA_DEBUG(4, "%s()\n", __func__); - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;); @@ -1292,13 +1292,13 @@ static void irttp_connect_indication(void *instance, void *sap, __u8 plen; __u8 n; - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;); IRDA_ASSERT(skb != NULL, return;); - lsap = (struct lsap_cb *) sap; + lsap = sap; self->max_seg_size = max_seg_size - TTP_HEADER; self->max_header_size = max_header_size+TTP_HEADER; @@ -1602,7 +1602,7 @@ static void irttp_disconnect_indication(void *instance, void *sap, IRDA_DEBUG(4, "%s()\n", __func__); - self = (struct tsap_cb *) instance; + self = instance; IRDA_ASSERT(self != NULL, return;); IRDA_ASSERT(self->magic == TTP_TSAP_MAGIC, return;); diff --git a/net/key/af_key.c b/net/key/af_key.c index 8f92cf8116e..1e733e9073d 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -621,7 +621,7 @@ static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct unsigned short family; xfrm_address_t *xaddr; - sa = (const struct sadb_sa *) ext_hdrs[SADB_EXT_SA-1]; + sa = ext_hdrs[SADB_EXT_SA - 1]; if (sa == NULL) return NULL; @@ -630,7 +630,7 @@ static struct xfrm_state *pfkey_xfrm_state_lookup(struct net *net, const struct return NULL; /* sadb_address_len should be checked by caller */ - addr = (const struct sadb_address *) ext_hdrs[SADB_EXT_ADDRESS_DST-1]; + addr = ext_hdrs[SADB_EXT_ADDRESS_DST - 1]; if (addr == NULL) return NULL; @@ -1039,7 +1039,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, int err; - sa = (const struct sadb_sa *) ext_hdrs[SADB_EXT_SA-1]; + sa = ext_hdrs[SADB_EXT_SA - 1]; if (!sa || !present_and_same_family(ext_hdrs[SADB_EXT_ADDRESS_SRC-1], ext_hdrs[SADB_EXT_ADDRESS_DST-1])) @@ -1078,7 +1078,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, sa->sadb_sa_encrypt > SADB_X_CALG_MAX) || sa->sadb_sa_encrypt > SADB_EALG_MAX) return ERR_PTR(-EINVAL); - key = (const struct sadb_key*) ext_hdrs[SADB_EXT_KEY_AUTH-1]; + key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (key != NULL && sa->sadb_sa_auth != SADB_X_AALG_NULL && ((key->sadb_key_bits+7) / 8 == 0 || @@ -1105,14 +1105,14 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, if (sa->sadb_sa_flags & SADB_SAFLAGS_NOPMTUDISC) x->props.flags |= XFRM_STATE_NOPMTUDISC; - lifetime = (const struct sadb_lifetime*) ext_hdrs[SADB_EXT_LIFETIME_HARD-1]; + lifetime = ext_hdrs[SADB_EXT_LIFETIME_HARD - 1]; if (lifetime != NULL) { x->lft.hard_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.hard_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); x->lft.hard_add_expires_seconds = lifetime->sadb_lifetime_addtime; x->lft.hard_use_expires_seconds = lifetime->sadb_lifetime_usetime; } - lifetime = (const struct sadb_lifetime*) ext_hdrs[SADB_EXT_LIFETIME_SOFT-1]; + lifetime = ext_hdrs[SADB_EXT_LIFETIME_SOFT - 1]; if (lifetime != NULL) { x->lft.soft_packet_limit = _KEY2X(lifetime->sadb_lifetime_allocations); x->lft.soft_byte_limit = _KEY2X(lifetime->sadb_lifetime_bytes); @@ -1120,7 +1120,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, x->lft.soft_use_expires_seconds = lifetime->sadb_lifetime_usetime; } - sec_ctx = (const struct sadb_x_sec_ctx *) ext_hdrs[SADB_X_EXT_SEC_CTX-1]; + sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); @@ -1134,7 +1134,7 @@ static struct xfrm_state * pfkey_msg2xfrm_state(struct net *net, goto out; } - key = (const struct sadb_key*) ext_hdrs[SADB_EXT_KEY_AUTH-1]; + key = ext_hdrs[SADB_EXT_KEY_AUTH - 1]; if (sa->sadb_sa_auth) { int keysize = 0; struct xfrm_algo_desc *a = xfrm_aalg_get_byid(sa->sadb_sa_auth); @@ -2219,7 +2219,7 @@ static int pfkey_spdadd(struct sock *sk, struct sk_buff *skb, const struct sadb_ if (xp->selector.dport) xp->selector.dport_mask = htons(0xffff); - sec_ctx = (struct sadb_x_sec_ctx *) ext_hdrs[SADB_X_EXT_SEC_CTX-1]; + sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); @@ -2323,7 +2323,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa if (sel.dport) sel.dport_mask = htons(0xffff); - sec_ctx = (struct sadb_x_sec_ctx *) ext_hdrs[SADB_X_EXT_SEC_CTX-1]; + sec_ctx = ext_hdrs[SADB_X_EXT_SEC_CTX - 1]; if (sec_ctx != NULL) { struct xfrm_user_sec_ctx *uctx = pfkey_sadb2xfrm_user_sec_ctx(sec_ctx); diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index b8dbae82fab..76130134bfa 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -258,7 +258,7 @@ static int l2tp_dfs_seq_open(struct inode *inode, struct file *file) */ pd->net = get_net_ns_by_pid(current->pid); if (IS_ERR(pd->net)) { - rc = -PTR_ERR(pd->net); + rc = PTR_ERR(pd->net); goto err_free_pd; } diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index b6466e71f5e..d21e7ebd91c 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -480,18 +480,16 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m if (connected) rt = (struct rtable *) __sk_dst_check(sk, 0); + rcu_read_lock(); if (rt == NULL) { - struct ip_options_rcu *inet_opt; + const struct ip_options_rcu *inet_opt; - rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); /* Use correct destination address if we have options. */ if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; - rcu_read_unlock(); - /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times * itself out. @@ -503,12 +501,20 @@ static int l2tp_ip_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *m sk->sk_bound_dev_if); if (IS_ERR(rt)) goto no_route; - sk_setup_caps(sk, &rt->dst); + if (connected) + sk_setup_caps(sk, &rt->dst); + else + dst_release(&rt->dst); /* safe since we hold rcu_read_lock */ } - skb_dst_set(skb, dst_clone(&rt->dst)); + + /* We dont need to clone dst here, it is guaranteed to not disappear. + * __dev_xmit_skb() might force a refcount if needed. + */ + skb_dst_set_noref(skb, &rt->dst); /* Queue the packet to IP for output */ rc = ip_queue_xmit(skb, &inet->cork.fl); + rcu_read_unlock(); error: /* Update stats */ @@ -525,6 +531,7 @@ out: return rc; no_route: + rcu_read_unlock(); IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); kfree_skb(skb); rc = -EHOSTUNREACH; diff --git a/net/lapb/lapb_iface.c b/net/lapb/lapb_iface.c index d5d8d555c41..956b7e47dc5 100644 --- a/net/lapb/lapb_iface.c +++ b/net/lapb/lapb_iface.c @@ -300,26 +300,26 @@ int lapb_disconnect_request(struct net_device *dev) goto out; switch (lapb->state) { - case LAPB_STATE_0: - rc = LAPB_NOTCONNECTED; - goto out_put; + case LAPB_STATE_0: + rc = LAPB_NOTCONNECTED; + goto out_put; - case LAPB_STATE_1: + case LAPB_STATE_1: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX DISC(1)\n", lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S1 TX DISC(1)\n", lapb->dev); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", lapb->dev); #endif - lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); - lapb->state = LAPB_STATE_0; - lapb_start_t1timer(lapb); - rc = LAPB_NOTCONNECTED; - goto out_put; - - case LAPB_STATE_2: - rc = LAPB_OK; - goto out_put; + lapb_send_control(lapb, LAPB_DISC, LAPB_POLLON, LAPB_COMMAND); + lapb->state = LAPB_STATE_0; + lapb_start_t1timer(lapb); + rc = LAPB_NOTCONNECTED; + goto out_put; + + case LAPB_STATE_2: + rc = LAPB_OK; + goto out_put; } lapb_clear_queues(lapb); diff --git a/net/lapb/lapb_in.c b/net/lapb/lapb_in.c index 21904a00244..2ec1af5c36c 100644 --- a/net/lapb/lapb_in.c +++ b/net/lapb/lapb_in.c @@ -44,89 +44,86 @@ static void lapb_state0_machine(struct lapb_cb *lapb, struct sk_buff *skb, struct lapb_frame *frame) { switch (frame->type) { - case LAPB_SABM: + case LAPB_SABM: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 RX SABM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 RX SABM(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } else { + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } else { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", + lapb->dev, frame->pf); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S0 -> S3\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S0 -> S3\n", lapb->dev); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_3; - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_connect_indication(lapb, LAPB_OK); - } - break; + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_3; + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_connect_indication(lapb, LAPB_OK); + } + break; - case LAPB_SABME: + case LAPB_SABME: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 RX SABME(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 RX SABME(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", + lapb->dev, frame->pf); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S0 -> S3\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S0 -> S3\n", lapb->dev); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_3; - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_connect_indication(lapb, LAPB_OK); - } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 TX DM(%d)\n", - lapb->dev, frame->pf); + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_3; + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_connect_indication(lapb, LAPB_OK); + } else { +#if LAPB_DEBUG > 1 + printk(KERN_DEBUG "lapb: (%p) S0 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } - break; + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } + break; - case LAPB_DISC: + case LAPB_DISC: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S0 RX DISC(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 RX DISC(%d)\n", + lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S0 TX UA(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - break; + lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); + break; - default: - break; + default: + break; } kfree_skb(skb); @@ -140,100 +137,97 @@ static void lapb_state1_machine(struct lapb_cb *lapb, struct sk_buff *skb, struct lapb_frame *frame) { switch (frame->type) { - case LAPB_SABM: + case LAPB_SABM: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX SABM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 RX SABM(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", - lapb->dev, frame->pf); -#endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - } - break; - - case LAPB_SABME: + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } else { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX SABME(%d)\n", + printk(KERN_DEBUG "lapb: (%p) S1 TX UA(%d)\n", lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + } + break; + + case LAPB_SABME: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 RX SABME(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - } else { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 TX UA(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } - break; - - case LAPB_DISC: + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + } else { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX DISC(%d)\n", - lapb->dev, frame->pf); printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", lapb->dev, frame->pf); #endif lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); - break; + } + break; - case LAPB_UA: + case LAPB_DISC: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 RX DISC(%d)\n", + lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - if (frame->pf) { -#if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S3\n", - lapb->dev); -#endif - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_3; - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_connect_confirmation(lapb, LAPB_OK); - } - break; + lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); + break; - case LAPB_DM: + case LAPB_UA: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S1 RX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S1 RX UA(%d)\n", + lapb->dev, frame->pf); #endif - if (frame->pf) { + if (frame->pf) { #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", - lapb->dev); -#endif - lapb_clear_queues(lapb); - lapb->state = LAPB_STATE_0; - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb_disconnect_indication(lapb, LAPB_REFUSED); - } - break; + printk(KERN_DEBUG "lapb: (%p) S1 -> S3\n", lapb->dev); +#endif + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_3; + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_connect_confirmation(lapb, LAPB_OK); + } + break; + + case LAPB_DM: +#if LAPB_DEBUG > 1 + printk(KERN_DEBUG "lapb: (%p) S1 RX DM(%d)\n", + lapb->dev, frame->pf); +#endif + if (frame->pf) { +#if LAPB_DEBUG > 0 + printk(KERN_DEBUG "lapb: (%p) S1 -> S0\n", lapb->dev); +#endif + lapb_clear_queues(lapb); + lapb->state = LAPB_STATE_0; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb_disconnect_indication(lapb, LAPB_REFUSED); + } + break; } kfree_skb(skb); @@ -247,78 +241,73 @@ static void lapb_state2_machine(struct lapb_cb *lapb, struct sk_buff *skb, struct lapb_frame *frame) { switch (frame->type) { - case LAPB_SABM: - case LAPB_SABME: + case LAPB_SABM: + case LAPB_SABME: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX {SABM,SABME}(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S2 TX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 RX {SABM,SABME}(%d)\n", + lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - break; + lapb_send_control(lapb, LAPB_DM, frame->pf, LAPB_RESPONSE); + break; - case LAPB_DISC: + case LAPB_DISC: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX DISC(%d)\n", - lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S2 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 RX DISC(%d)\n", + lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 TX UA(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - break; + lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); + break; - case LAPB_UA: + case LAPB_UA: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 RX UA(%d)\n", + lapb->dev, frame->pf); #endif - if (frame->pf) { + if (frame->pf) { #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", lapb->dev); #endif - lapb->state = LAPB_STATE_0; - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb_disconnect_confirmation(lapb, LAPB_OK); - } - break; + lapb->state = LAPB_STATE_0; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb_disconnect_confirmation(lapb, LAPB_OK); + } + break; - case LAPB_DM: + case LAPB_DM: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 RX DM(%d)\n", + lapb->dev, frame->pf); #endif - if (frame->pf) { + if (frame->pf) { #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", - lapb->dev); -#endif - lapb->state = LAPB_STATE_0; - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb_disconnect_confirmation(lapb, - LAPB_NOTCONNECTED); - } - break; + printk(KERN_DEBUG "lapb: (%p) S2 -> S0\n", lapb->dev); +#endif + lapb->state = LAPB_STATE_0; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb_disconnect_confirmation(lapb, LAPB_NOTCONNECTED); + } + break; - case LAPB_I: - case LAPB_REJ: - case LAPB_RNR: - case LAPB_RR: + case LAPB_I: + case LAPB_REJ: + case LAPB_RNR: + case LAPB_RR: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S2 RX {I,REJ,RNR,RR}" - "(%d)\n", lapb->dev, frame->pf); - printk(KERN_DEBUG "lapb: (%p) S2 RX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 RX {I,REJ,RNR,RR}(%d)\n", + lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S2 RX DM(%d)\n", + lapb->dev, frame->pf); #endif - if (frame->pf) - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - break; + if (frame->pf) + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + break; } kfree_skb(skb); @@ -336,277 +325,267 @@ static void lapb_state3_machine(struct lapb_cb *lapb, struct sk_buff *skb, LAPB_SMODULUS; switch (frame->type) { - case LAPB_SABM: + case LAPB_SABM: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX SABM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 RX SABM(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } else { + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } else { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 TX UA(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_requeue_frames(lapb); - } - break; + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_requeue_frames(lapb); + } + break; - case LAPB_SABME: + case LAPB_SABME: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX SABME(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 RX SABME(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 TX UA(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_requeue_frames(lapb); - } else { + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_requeue_frames(lapb); + } else { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 TX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } - break; + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } + break; - case LAPB_DISC: + case LAPB_DISC: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX DISC(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 RX DISC(%d)\n", + lapb->dev, frame->pf); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", lapb->dev); #endif - lapb_clear_queues(lapb); - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_0; - lapb_disconnect_indication(lapb, LAPB_OK); - break; + lapb_clear_queues(lapb); + lapb_send_control(lapb, LAPB_UA, frame->pf, LAPB_RESPONSE); + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_0; + lapb_disconnect_indication(lapb, LAPB_OK); + break; - case LAPB_DM: + case LAPB_DM: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 RX DM(%d)\n", + lapb->dev, frame->pf); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S0\n", lapb->dev); #endif - lapb_clear_queues(lapb); - lapb->state = LAPB_STATE_0; - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb_disconnect_indication(lapb, LAPB_NOTCONNECTED); - break; + lapb_clear_queues(lapb); + lapb->state = LAPB_STATE_0; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb_disconnect_indication(lapb, LAPB_NOTCONNECTED); + break; - case LAPB_RNR: + case LAPB_RNR: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX RNR(%d) R%d\n", - lapb->dev, frame->pf, frame->nr); + printk(KERN_DEBUG "lapb: (%p) S3 RX RNR(%d) R%d\n", + lapb->dev, frame->pf, frame->nr); #endif - lapb->condition |= LAPB_PEER_RX_BUSY_CONDITION; - lapb_check_need_response(lapb, frame->cr, frame->pf); - if (lapb_validate_nr(lapb, frame->nr)) { - lapb_check_iframes_acked(lapb, frame->nr); - } else { - lapb->frmr_data = *frame; - lapb->frmr_type = LAPB_FRMR_Z; - lapb_transmit_frmr(lapb); + lapb->condition |= LAPB_PEER_RX_BUSY_CONDITION; + lapb_check_need_response(lapb, frame->cr, frame->pf); + if (lapb_validate_nr(lapb, frame->nr)) { + lapb_check_iframes_acked(lapb, frame->nr); + } else { + lapb->frmr_data = *frame; + lapb->frmr_type = LAPB_FRMR_Z; + lapb_transmit_frmr(lapb); #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); #endif - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_4; - lapb->n2count = 0; - } - break; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_4; + lapb->n2count = 0; + } + break; - case LAPB_RR: + case LAPB_RR: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX RR(%d) R%d\n", - lapb->dev, frame->pf, frame->nr); + printk(KERN_DEBUG "lapb: (%p) S3 RX RR(%d) R%d\n", + lapb->dev, frame->pf, frame->nr); #endif - lapb->condition &= ~LAPB_PEER_RX_BUSY_CONDITION; - lapb_check_need_response(lapb, frame->cr, frame->pf); - if (lapb_validate_nr(lapb, frame->nr)) { - lapb_check_iframes_acked(lapb, frame->nr); - } else { - lapb->frmr_data = *frame; - lapb->frmr_type = LAPB_FRMR_Z; - lapb_transmit_frmr(lapb); + lapb->condition &= ~LAPB_PEER_RX_BUSY_CONDITION; + lapb_check_need_response(lapb, frame->cr, frame->pf); + if (lapb_validate_nr(lapb, frame->nr)) { + lapb_check_iframes_acked(lapb, frame->nr); + } else { + lapb->frmr_data = *frame; + lapb->frmr_type = LAPB_FRMR_Z; + lapb_transmit_frmr(lapb); #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); #endif - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_4; - lapb->n2count = 0; - } - break; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_4; + lapb->n2count = 0; + } + break; - case LAPB_REJ: + case LAPB_REJ: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX REJ(%d) R%d\n", - lapb->dev, frame->pf, frame->nr); + printk(KERN_DEBUG "lapb: (%p) S3 RX REJ(%d) R%d\n", + lapb->dev, frame->pf, frame->nr); #endif - lapb->condition &= ~LAPB_PEER_RX_BUSY_CONDITION; - lapb_check_need_response(lapb, frame->cr, frame->pf); - if (lapb_validate_nr(lapb, frame->nr)) { - lapb_frames_acked(lapb, frame->nr); - lapb_stop_t1timer(lapb); - lapb->n2count = 0; - lapb_requeue_frames(lapb); - } else { - lapb->frmr_data = *frame; - lapb->frmr_type = LAPB_FRMR_Z; - lapb_transmit_frmr(lapb); + lapb->condition &= ~LAPB_PEER_RX_BUSY_CONDITION; + lapb_check_need_response(lapb, frame->cr, frame->pf); + if (lapb_validate_nr(lapb, frame->nr)) { + lapb_frames_acked(lapb, frame->nr); + lapb_stop_t1timer(lapb); + lapb->n2count = 0; + lapb_requeue_frames(lapb); + } else { + lapb->frmr_data = *frame; + lapb->frmr_type = LAPB_FRMR_Z; + lapb_transmit_frmr(lapb); #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); #endif - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_4; - lapb->n2count = 0; - } - break; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_4; + lapb->n2count = 0; + } + break; - case LAPB_I: + case LAPB_I: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX I(%d) S%d R%d\n", - lapb->dev, frame->pf, frame->ns, frame->nr); + printk(KERN_DEBUG "lapb: (%p) S3 RX I(%d) S%d R%d\n", + lapb->dev, frame->pf, frame->ns, frame->nr); #endif - if (!lapb_validate_nr(lapb, frame->nr)) { - lapb->frmr_data = *frame; - lapb->frmr_type = LAPB_FRMR_Z; - lapb_transmit_frmr(lapb); + if (!lapb_validate_nr(lapb, frame->nr)) { + lapb->frmr_data = *frame; + lapb->frmr_type = LAPB_FRMR_Z; + lapb_transmit_frmr(lapb); #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); #endif - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_4; - lapb->n2count = 0; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_4; + lapb->n2count = 0; + break; + } + if (lapb->condition & LAPB_PEER_RX_BUSY_CONDITION) + lapb_frames_acked(lapb, frame->nr); + else + lapb_check_iframes_acked(lapb, frame->nr); + + if (frame->ns == lapb->vr) { + int cn; + cn = lapb_data_indication(lapb, skb); + queued = 1; + /* + * If upper layer has dropped the frame, we + * basically ignore any further protocol + * processing. This will cause the peer + * to re-transmit the frame later like + * a frame lost on the wire. + */ + if (cn == NET_RX_DROP) { + printk(KERN_DEBUG "LAPB: rx congestion\n"); break; } - if (lapb->condition & LAPB_PEER_RX_BUSY_CONDITION) - lapb_frames_acked(lapb, frame->nr); - else - lapb_check_iframes_acked(lapb, frame->nr); - - if (frame->ns == lapb->vr) { - int cn; - cn = lapb_data_indication(lapb, skb); - queued = 1; - /* - * If upper layer has dropped the frame, we - * basically ignore any further protocol - * processing. This will cause the peer - * to re-transmit the frame later like - * a frame lost on the wire. - */ - if (cn == NET_RX_DROP) { - printk(KERN_DEBUG - "LAPB: rx congestion\n"); - break; + lapb->vr = (lapb->vr + 1) % modulus; + lapb->condition &= ~LAPB_REJECT_CONDITION; + if (frame->pf) + lapb_enquiry_response(lapb); + else { + if (!(lapb->condition & + LAPB_ACK_PENDING_CONDITION)) { + lapb->condition |= LAPB_ACK_PENDING_CONDITION; + lapb_start_t2timer(lapb); } - lapb->vr = (lapb->vr + 1) % modulus; - lapb->condition &= ~LAPB_REJECT_CONDITION; + } + } else { + if (lapb->condition & LAPB_REJECT_CONDITION) { if (frame->pf) lapb_enquiry_response(lapb); - else { - if (!(lapb->condition & - LAPB_ACK_PENDING_CONDITION)) { - lapb->condition |= LAPB_ACK_PENDING_CONDITION; - lapb_start_t2timer(lapb); - } - } } else { - if (lapb->condition & LAPB_REJECT_CONDITION) { - if (frame->pf) - lapb_enquiry_response(lapb); - } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG - "lapb: (%p) S3 TX REJ(%d) R%d\n", - lapb->dev, frame->pf, lapb->vr); -#endif - lapb->condition |= LAPB_REJECT_CONDITION; - lapb_send_control(lapb, LAPB_REJ, - frame->pf, - LAPB_RESPONSE); - lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; - } +#if LAPB_DEBUG > 1 + printk(KERN_DEBUG + "lapb: (%p) S3 TX REJ(%d) R%d\n", + lapb->dev, frame->pf, lapb->vr); +#endif + lapb->condition |= LAPB_REJECT_CONDITION; + lapb_send_control(lapb, LAPB_REJ, frame->pf, + LAPB_RESPONSE); + lapb->condition &= ~LAPB_ACK_PENDING_CONDITION; } - break; + } + break; - case LAPB_FRMR: + case LAPB_FRMR: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX FRMR(%d) %02X " - "%02X %02X %02X %02X\n", lapb->dev, frame->pf, - skb->data[0], skb->data[1], skb->data[2], - skb->data[3], skb->data[4]); + printk(KERN_DEBUG "lapb: (%p) S3 RX FRMR(%d) %02X " + "%02X %02X %02X %02X\n", lapb->dev, frame->pf, + skb->data[0], skb->data[1], skb->data[2], + skb->data[3], skb->data[4]); #endif - lapb_establish_data_link(lapb); + lapb_establish_data_link(lapb); #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S1\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S1\n", lapb->dev); #endif - lapb_requeue_frames(lapb); - lapb->state = LAPB_STATE_1; - break; + lapb_requeue_frames(lapb); + lapb->state = LAPB_STATE_1; + break; - case LAPB_ILLEGAL: + case LAPB_ILLEGAL: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S3 RX ILLEGAL(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S3 RX ILLEGAL(%d)\n", + lapb->dev, frame->pf); #endif - lapb->frmr_data = *frame; - lapb->frmr_type = LAPB_FRMR_W; - lapb_transmit_frmr(lapb); + lapb->frmr_data = *frame; + lapb->frmr_type = LAPB_FRMR_W; + lapb_transmit_frmr(lapb); #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S3 -> S4\n", lapb->dev); #endif - lapb_start_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_4; - lapb->n2count = 0; - break; + lapb_start_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_4; + lapb->n2count = 0; + break; } if (!queued) @@ -621,75 +600,73 @@ static void lapb_state4_machine(struct lapb_cb *lapb, struct sk_buff *skb, struct lapb_frame *frame) { switch (frame->type) { - case LAPB_SABM: + case LAPB_SABM: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 RX SABM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S4 RX SABM(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX DM(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S4 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } else { + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } else { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S4 TX UA(%d)\n", + lapb->dev, frame->pf); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S4 -> S3\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S4 -> S3\n", lapb->dev); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_3; - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_connect_indication(lapb, LAPB_OK); - } - break; + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_3; + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_connect_indication(lapb, LAPB_OK); + } + break; - case LAPB_SABME: + case LAPB_SABME: #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 RX SABME(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S4 RX SABME(%d)\n", + lapb->dev, frame->pf); #endif - if (lapb->mode & LAPB_EXTENDED) { + if (lapb->mode & LAPB_EXTENDED) { #if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX UA(%d)\n", - lapb->dev, frame->pf); + printk(KERN_DEBUG "lapb: (%p) S4 TX UA(%d)\n", + lapb->dev, frame->pf); #endif #if LAPB_DEBUG > 0 - printk(KERN_DEBUG "lapb: (%p) S4 -> S3\n", - lapb->dev); + printk(KERN_DEBUG "lapb: (%p) S4 -> S3\n", lapb->dev); #endif - lapb_send_control(lapb, LAPB_UA, frame->pf, - LAPB_RESPONSE); - lapb_stop_t1timer(lapb); - lapb_stop_t2timer(lapb); - lapb->state = LAPB_STATE_3; - lapb->condition = 0x00; - lapb->n2count = 0; - lapb->vs = 0; - lapb->vr = 0; - lapb->va = 0; - lapb_connect_indication(lapb, LAPB_OK); - } else { -#if LAPB_DEBUG > 1 - printk(KERN_DEBUG "lapb: (%p) S4 TX DM(%d)\n", - lapb->dev, frame->pf); + lapb_send_control(lapb, LAPB_UA, frame->pf, + LAPB_RESPONSE); + lapb_stop_t1timer(lapb); + lapb_stop_t2timer(lapb); + lapb->state = LAPB_STATE_3; + lapb->condition = 0x00; + lapb->n2count = 0; + lapb->vs = 0; + lapb->vr = 0; + lapb->va = 0; + lapb_connect_indication(lapb, LAPB_OK); + } else { +#if LAPB_DEBUG > 1 + printk(KERN_DEBUG "lapb: (%p) S4 TX DM(%d)\n", + lapb->dev, frame->pf); #endif - lapb_send_control(lapb, LAPB_DM, frame->pf, - LAPB_RESPONSE); - } - break; + lapb_send_control(lapb, LAPB_DM, frame->pf, + LAPB_RESPONSE); + } + break; } kfree_skb(skb); diff --git a/net/mac80211/aes_ccm.c b/net/mac80211/aes_ccm.c index b9b595c0811..0785e95c992 100644 --- a/net/mac80211/aes_ccm.c +++ b/net/mac80211/aes_ccm.c @@ -11,6 +11,7 @@ #include <linux/types.h> #include <linux/crypto.h> #include <linux/err.h> +#include <crypto/aes.h> #include <net/mac80211.h> #include "key.h" @@ -21,21 +22,21 @@ static void aes_ccm_prepare(struct crypto_cipher *tfm, u8 *scratch, u8 *a) int i; u8 *b_0, *aad, *b, *s_0; - b_0 = scratch + 3 * AES_BLOCK_LEN; - aad = scratch + 4 * AES_BLOCK_LEN; + b_0 = scratch + 3 * AES_BLOCK_SIZE; + aad = scratch + 4 * AES_BLOCK_SIZE; b = scratch; - s_0 = scratch + AES_BLOCK_LEN; + s_0 = scratch + AES_BLOCK_SIZE; crypto_cipher_encrypt_one(tfm, b, b_0); /* Extra Authenticate-only data (always two AES blocks) */ - for (i = 0; i < AES_BLOCK_LEN; i++) + for (i = 0; i < AES_BLOCK_SIZE; i++) aad[i] ^= b[i]; crypto_cipher_encrypt_one(tfm, b, aad); - aad += AES_BLOCK_LEN; + aad += AES_BLOCK_SIZE; - for (i = 0; i < AES_BLOCK_LEN; i++) + for (i = 0; i < AES_BLOCK_SIZE; i++) aad[i] ^= b[i]; crypto_cipher_encrypt_one(tfm, a, aad); @@ -57,12 +58,12 @@ void ieee80211_aes_ccm_encrypt(struct crypto_cipher *tfm, u8 *scratch, u8 *pos, *cpos, *b, *s_0, *e, *b_0; b = scratch; - s_0 = scratch + AES_BLOCK_LEN; - e = scratch + 2 * AES_BLOCK_LEN; - b_0 = scratch + 3 * AES_BLOCK_LEN; + s_0 = scratch + AES_BLOCK_SIZE; + e = scratch + 2 * AES_BLOCK_SIZE; + b_0 = scratch + 3 * AES_BLOCK_SIZE; - num_blocks = DIV_ROUND_UP(data_len, AES_BLOCK_LEN); - last_len = data_len % AES_BLOCK_LEN; + num_blocks = DIV_ROUND_UP(data_len, AES_BLOCK_SIZE); + last_len = data_len % AES_BLOCK_SIZE; aes_ccm_prepare(tfm, scratch, b); /* Process payload blocks */ @@ -70,7 +71,7 @@ void ieee80211_aes_ccm_encrypt(struct crypto_cipher *tfm, u8 *scratch, cpos = cdata; for (j = 1; j <= num_blocks; j++) { int blen = (j == num_blocks && last_len) ? - last_len : AES_BLOCK_LEN; + last_len : AES_BLOCK_SIZE; /* Authentication followed by encryption */ for (i = 0; i < blen; i++) @@ -96,12 +97,12 @@ int ieee80211_aes_ccm_decrypt(struct crypto_cipher *tfm, u8 *scratch, u8 *pos, *cpos, *b, *s_0, *a, *b_0; b = scratch; - s_0 = scratch + AES_BLOCK_LEN; - a = scratch + 2 * AES_BLOCK_LEN; - b_0 = scratch + 3 * AES_BLOCK_LEN; + s_0 = scratch + AES_BLOCK_SIZE; + a = scratch + 2 * AES_BLOCK_SIZE; + b_0 = scratch + 3 * AES_BLOCK_SIZE; - num_blocks = DIV_ROUND_UP(data_len, AES_BLOCK_LEN); - last_len = data_len % AES_BLOCK_LEN; + num_blocks = DIV_ROUND_UP(data_len, AES_BLOCK_SIZE); + last_len = data_len % AES_BLOCK_SIZE; aes_ccm_prepare(tfm, scratch, a); /* Process payload blocks */ @@ -109,7 +110,7 @@ int ieee80211_aes_ccm_decrypt(struct crypto_cipher *tfm, u8 *scratch, pos = data; for (j = 1; j <= num_blocks; j++) { int blen = (j == num_blocks && last_len) ? - last_len : AES_BLOCK_LEN; + last_len : AES_BLOCK_SIZE; /* Decryption followed by authentication */ b_0[14] = (j >> 8) & 0xff; diff --git a/net/mac80211/aes_ccm.h b/net/mac80211/aes_ccm.h index 6e7820ef344..5b7d744e237 100644 --- a/net/mac80211/aes_ccm.h +++ b/net/mac80211/aes_ccm.h @@ -12,8 +12,6 @@ #include <linux/crypto.h> -#define AES_BLOCK_LEN 16 - struct crypto_cipher *ieee80211_aes_key_setup_encrypt(const u8 key[]); void ieee80211_aes_ccm_encrypt(struct crypto_cipher *tfm, u8 *scratch, u8 *data, size_t data_len, diff --git a/net/mac80211/aes_cmac.c b/net/mac80211/aes_cmac.c index d502b2684a6..8dfd70d8fcf 100644 --- a/net/mac80211/aes_cmac.c +++ b/net/mac80211/aes_cmac.c @@ -11,12 +11,12 @@ #include <linux/types.h> #include <linux/crypto.h> #include <linux/err.h> +#include <crypto/aes.h> #include <net/mac80211.h> #include "key.h" #include "aes_cmac.h" -#define AES_BLOCK_SIZE 16 #define AES_CMAC_KEY_LEN 16 #define CMAC_TLEN 8 /* CMAC TLen = 64 bits (8 octets) */ #define AAD_LEN 20 @@ -35,10 +35,10 @@ static void gf_mulx(u8 *pad) } -static void aes_128_cmac_vector(struct crypto_cipher *tfm, u8 *scratch, - size_t num_elem, +static void aes_128_cmac_vector(struct crypto_cipher *tfm, size_t num_elem, const u8 *addr[], const size_t *len, u8 *mac) { + u8 scratch[2 * AES_BLOCK_SIZE]; u8 *cbc, *pad; const u8 *pos, *end; size_t i, e, left, total_len; @@ -95,7 +95,7 @@ static void aes_128_cmac_vector(struct crypto_cipher *tfm, u8 *scratch, } -void ieee80211_aes_cmac(struct crypto_cipher *tfm, u8 *scratch, const u8 *aad, +void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic) { const u8 *addr[3]; @@ -110,7 +110,7 @@ void ieee80211_aes_cmac(struct crypto_cipher *tfm, u8 *scratch, const u8 *aad, addr[2] = zero; len[2] = CMAC_TLEN; - aes_128_cmac_vector(tfm, scratch, 3, addr, len, mic); + aes_128_cmac_vector(tfm, 3, addr, len, mic); } diff --git a/net/mac80211/aes_cmac.h b/net/mac80211/aes_cmac.h index 0eb9a483150..20785a64725 100644 --- a/net/mac80211/aes_cmac.h +++ b/net/mac80211/aes_cmac.h @@ -12,7 +12,7 @@ #include <linux/crypto.h> struct crypto_cipher * ieee80211_aes_cmac_key_setup(const u8 key[]); -void ieee80211_aes_cmac(struct crypto_cipher *tfm, u8 *scratch, const u8 *aad, +void ieee80211_aes_cmac(struct crypto_cipher *tfm, const u8 *aad, const u8 *data, size_t data_len, u8 *mic); void ieee80211_aes_cmac_key_free(struct crypto_cipher *tfm); diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 9c0d76cdca9..ebadb9ac9a7 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -100,6 +100,21 @@ void __ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, mutex_unlock(&sta->ampdu_mlme.mtx); } +void ieee80211_stop_rx_ba_session(struct ieee80211_vif *vif, u16 ba_rx_bitmap, + const u8 *addr) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + struct sta_info *sta = sta_info_get(sdata, addr); + int i; + + for (i = 0; i < STA_TID_NUM; i++) + if (ba_rx_bitmap & BIT(i)) + set_bit(i, sta->ampdu_mlme.tid_rx_stop_requested); + + ieee80211_queue_work(&sta->local->hw, &sta->ampdu_mlme.work); +} +EXPORT_SYMBOL(ieee80211_stop_rx_ba_session); + /* * After accepting the AddBA Request we activated a timer, * resetting it after each frame that arrives from the originator. @@ -247,7 +262,11 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, "%pM on tid %u\n", mgmt->sa, tid); #endif /* CONFIG_MAC80211_HT_DEBUG */ - goto end; + + /* delete existing Rx BA session on the same tid */ + ___ieee80211_stop_rx_ba_session(sta, tid, WLAN_BACK_RECIPIENT, + WLAN_STATUS_UNSPECIFIED_QOS, + false); } /* prepare A-MPDU MLME for Rx aggregation */ diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index be70c70d3f5..bfc36e90476 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -209,6 +209,7 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, u8 seq[6] = {0}; struct key_params params; struct ieee80211_key *key = NULL; + u64 pn64; u32 iv32; u16 iv16; int err = -ENOENT; @@ -256,22 +257,24 @@ static int ieee80211_get_key(struct wiphy *wiphy, struct net_device *dev, params.seq_len = 6; break; case WLAN_CIPHER_SUITE_CCMP: - seq[0] = key->u.ccmp.tx_pn[5]; - seq[1] = key->u.ccmp.tx_pn[4]; - seq[2] = key->u.ccmp.tx_pn[3]; - seq[3] = key->u.ccmp.tx_pn[2]; - seq[4] = key->u.ccmp.tx_pn[1]; - seq[5] = key->u.ccmp.tx_pn[0]; + pn64 = atomic64_read(&key->u.ccmp.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; params.seq = seq; params.seq_len = 6; break; case WLAN_CIPHER_SUITE_AES_CMAC: - seq[0] = key->u.aes_cmac.tx_pn[5]; - seq[1] = key->u.aes_cmac.tx_pn[4]; - seq[2] = key->u.aes_cmac.tx_pn[3]; - seq[3] = key->u.aes_cmac.tx_pn[2]; - seq[4] = key->u.aes_cmac.tx_pn[1]; - seq[5] = key->u.aes_cmac.tx_pn[0]; + pn64 = atomic64_read(&key->u.aes_cmac.tx_pn); + seq[0] = pn64; + seq[1] = pn64 >> 8; + seq[2] = pn64 >> 16; + seq[3] = pn64 >> 24; + seq[4] = pn64 >> 32; + seq[5] = pn64 >> 40; params.seq = seq; params.seq_len = 6; break; @@ -674,8 +677,11 @@ static void sta_apply_parameters(struct ieee80211_local *local, if (mask & BIT(NL80211_STA_FLAG_WME)) { sta->flags &= ~WLAN_STA_WME; - if (set & BIT(NL80211_STA_FLAG_WME)) + sta->sta.wme = false; + if (set & BIT(NL80211_STA_FLAG_WME)) { sta->flags |= WLAN_STA_WME; + sta->sta.wme = true; + } } if (mask & BIT(NL80211_STA_FLAG_MFP)) { @@ -1554,6 +1560,19 @@ static int ieee80211_testmode_cmd(struct wiphy *wiphy, void *data, int len) return local->ops->testmode_cmd(&local->hw, data, len); } + +static int ieee80211_testmode_dump(struct wiphy *wiphy, + struct sk_buff *skb, + struct netlink_callback *cb, + void *data, int len) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + + if (!local->ops->testmode_dump) + return -EOPNOTSUPP; + + return local->ops->testmode_dump(&local->hw, skb, cb, data, len); +} #endif int __ieee80211_request_smps(struct ieee80211_sub_if_data *sdata, @@ -2085,6 +2104,21 @@ static void ieee80211_get_ringparam(struct wiphy *wiphy, drv_get_ringparam(local, tx, tx_max, rx, rx_max); } +static int ieee80211_set_rekey_data(struct wiphy *wiphy, + struct net_device *dev, + struct cfg80211_gtk_rekey_data *data) +{ + struct ieee80211_local *local = wiphy_priv(wiphy); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + + if (!local->ops->set_rekey_data) + return -EOPNOTSUPP; + + drv_set_rekey_data(local, sdata, data); + + return 0; +} + struct cfg80211_ops mac80211_config_ops = { .add_virtual_intf = ieee80211_add_iface, .del_virtual_intf = ieee80211_del_iface, @@ -2134,6 +2168,7 @@ struct cfg80211_ops mac80211_config_ops = { .set_wds_peer = ieee80211_set_wds_peer, .rfkill_poll = ieee80211_rfkill_poll, CFG80211_TESTMODE_CMD(ieee80211_testmode_cmd) + CFG80211_TESTMODE_DUMP(ieee80211_testmode_dump) .set_power_mgmt = ieee80211_set_power_mgmt, .set_bitrate_mask = ieee80211_set_bitrate_mask, .remain_on_channel = ieee80211_remain_on_channel, @@ -2146,4 +2181,5 @@ struct cfg80211_ops mac80211_config_ops = { .get_antenna = ieee80211_get_antenna, .set_ringparam = ieee80211_set_ringparam, .get_ringparam = ieee80211_get_ringparam, + .set_rekey_data = ieee80211_set_rekey_data, }; diff --git a/net/mac80211/debugfs_key.c b/net/mac80211/debugfs_key.c index 33c58b85c91..38e6101190d 100644 --- a/net/mac80211/debugfs_key.c +++ b/net/mac80211/debugfs_key.c @@ -78,7 +78,7 @@ KEY_OPS(algorithm); static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { - const u8 *tpn; + u64 pn; char buf[20]; int len; struct ieee80211_key *key = file->private_data; @@ -94,15 +94,16 @@ static ssize_t key_tx_spec_read(struct file *file, char __user *userbuf, key->u.tkip.tx.iv16); break; case WLAN_CIPHER_SUITE_CCMP: - tpn = key->u.ccmp.tx_pn; + pn = atomic64_read(&key->u.ccmp.tx_pn); len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", - tpn[0], tpn[1], tpn[2], tpn[3], tpn[4], tpn[5]); + (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), + (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); break; case WLAN_CIPHER_SUITE_AES_CMAC: - tpn = key->u.aes_cmac.tx_pn; + pn = atomic64_read(&key->u.aes_cmac.tx_pn); len = scnprintf(buf, sizeof(buf), "%02x%02x%02x%02x%02x%02x\n", - tpn[0], tpn[1], tpn[2], tpn[3], tpn[4], - tpn[5]); + (u8)(pn >> 40), (u8)(pn >> 32), (u8)(pn >> 24), + (u8)(pn >> 16), (u8)(pn >> 8), (u8)pn); break; default: return 0; diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index eebf7a67daf..b2d6bba4405 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -218,6 +218,16 @@ static inline int drv_hw_scan(struct ieee80211_local *local, return ret; } +static inline void drv_cancel_hw_scan(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata) +{ + might_sleep(); + + trace_drv_cancel_hw_scan(local, sdata); + local->ops->cancel_hw_scan(&local->hw, &sdata->vif); + trace_drv_return_void(local); +} + static inline int drv_sched_scan_start(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, @@ -637,4 +647,22 @@ static inline int drv_set_bitrate_mask(struct ieee80211_local *local, return ret; } +static inline void drv_set_rekey_data(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct cfg80211_gtk_rekey_data *data) +{ + trace_drv_set_rekey_data(local, sdata, data); + if (local->ops->set_rekey_data) + local->ops->set_rekey_data(&local->hw, &sdata->vif, data); + trace_drv_return_void(local); +} + +static inline void drv_rssi_callback(struct ieee80211_local *local, + const enum ieee80211_rssi_event event) +{ + trace_drv_rssi_callback(local, event); + if (local->ops->rssi_callback) + local->ops->rssi_callback(&local->hw, event); + trace_drv_return_void(local); +} #endif /* __MAC80211_DRIVER_OPS */ diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index ed9edcbd9aa..4470f6e8b84 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -460,6 +460,12 @@ DEFINE_EVENT(local_sdata_evt, drv_hw_scan, TP_ARGS(local, sdata) ); +DEFINE_EVENT(local_sdata_evt, drv_cancel_hw_scan, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata), + TP_ARGS(local, sdata) +); + DEFINE_EVENT(local_sdata_evt, drv_sched_scan_start, TP_PROTO(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata), @@ -1018,6 +1024,56 @@ TRACE_EVENT(drv_set_bitrate_mask, ) ); +TRACE_EVENT(drv_set_rekey_data, + TP_PROTO(struct ieee80211_local *local, + struct ieee80211_sub_if_data *sdata, + struct cfg80211_gtk_rekey_data *data), + + TP_ARGS(local, sdata, data), + + TP_STRUCT__entry( + LOCAL_ENTRY + VIF_ENTRY + __array(u8, kek, NL80211_KEK_LEN) + __array(u8, kck, NL80211_KCK_LEN) + __array(u8, replay_ctr, NL80211_REPLAY_CTR_LEN) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + VIF_ASSIGN; + memcpy(__entry->kek, data->kek, NL80211_KEK_LEN); + memcpy(__entry->kck, data->kck, NL80211_KCK_LEN); + memcpy(__entry->replay_ctr, data->replay_ctr, + NL80211_REPLAY_CTR_LEN); + ), + + TP_printk(LOCAL_PR_FMT VIF_PR_FMT, + LOCAL_PR_ARG, VIF_PR_ARG) +); + +TRACE_EVENT(drv_rssi_callback, + TP_PROTO(struct ieee80211_local *local, + enum ieee80211_rssi_event rssi_event), + + TP_ARGS(local, rssi_event), + + TP_STRUCT__entry( + LOCAL_ENTRY + __field(u32, rssi_event) + ), + + TP_fast_assign( + LOCAL_ASSIGN; + __entry->rssi_event = rssi_event; + ), + + TP_printk( + LOCAL_PR_FMT " rssi_event:%d", + LOCAL_PR_ARG, __entry->rssi_event + ) +); + /* * Tracing for API calls that drivers call. */ @@ -1287,6 +1343,51 @@ DEFINE_EVENT(local_only_evt, api_remain_on_channel_expired, TP_ARGS(local) ); +TRACE_EVENT(api_gtk_rekey_notify, + TP_PROTO(struct ieee80211_sub_if_data *sdata, + const u8 *bssid, const u8 *replay_ctr), + + TP_ARGS(sdata, bssid, replay_ctr), + + TP_STRUCT__entry( + VIF_ENTRY + __array(u8, bssid, ETH_ALEN) + __array(u8, replay_ctr, NL80211_REPLAY_CTR_LEN) + ), + + TP_fast_assign( + VIF_ASSIGN; + memcpy(__entry->bssid, bssid, ETH_ALEN); + memcpy(__entry->replay_ctr, replay_ctr, NL80211_REPLAY_CTR_LEN); + ), + + TP_printk(VIF_PR_FMT, VIF_PR_ARG) +); + +TRACE_EVENT(api_enable_rssi_reports, + TP_PROTO(struct ieee80211_sub_if_data *sdata, + int rssi_min_thold, int rssi_max_thold), + + TP_ARGS(sdata, rssi_min_thold, rssi_max_thold), + + TP_STRUCT__entry( + VIF_ENTRY + __field(int, rssi_min_thold) + __field(int, rssi_max_thold) + ), + + TP_fast_assign( + VIF_ASSIGN; + __entry->rssi_min_thold = rssi_min_thold; + __entry->rssi_max_thold = rssi_max_thold; + ), + + TP_printk( + VIF_PR_FMT " rssi_min_thold =%d, rssi_max_thold = %d", + VIF_PR_ARG, __entry->rssi_min_thold, __entry->rssi_max_thold + ) +); + /* * Tracing for internal functions * (which may also be called in response to driver calls) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 591add22bcc..7cfc286946c 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -140,6 +140,12 @@ void ieee80211_ba_session_work(struct work_struct *work) sta, tid, WLAN_BACK_RECIPIENT, WLAN_REASON_QSTA_TIMEOUT, true); + if (test_and_clear_bit(tid, + sta->ampdu_mlme.tid_rx_stop_requested)) + ___ieee80211_stop_rx_ba_session( + sta, tid, WLAN_BACK_RECIPIENT, + WLAN_REASON_UNSPECIFIED, true); + tid_tx = sta->ampdu_mlme.tid_start_tx[tid]; if (tid_tx) { /* diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 421eaa6b0c2..56c24cabf26 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -965,6 +965,10 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->u.ibss.mtx); + sdata->u.ibss.state = IEEE80211_IBSS_MLME_SEARCH; + memset(sdata->u.ibss.bssid, 0, ETH_ALEN); + sdata->u.ibss.ssid_len = 0; + active_ibss = ieee80211_sta_active_ibss(sdata); if (!active_ibss && !is_zero_ether_addr(ifibss->bssid)) { @@ -999,8 +1003,6 @@ int ieee80211_ibss_leave(struct ieee80211_sub_if_data *sdata) kfree_skb(skb); skb_queue_purge(&sdata->skb_queue); - memset(sdata->u.ibss.bssid, 0, ETH_ALEN); - sdata->u.ibss.ssid_len = 0; del_timer_sync(&sdata->u.ibss.timer); diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 2025af52b19..dda0d1ab34f 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -202,7 +202,22 @@ struct ieee80211_rx_data { struct ieee80211_key *key; unsigned int flags; - int queue; + + /* + * Index into sequence numbers array, 0..16 + * since the last (16) is used for non-QoS, + * will be 16 on non-QoS frames. + */ + int seqno_idx; + + /* + * Index into the security IV/PN arrays, 0..16 + * since the last (16) is used for CCMP-encrypted + * management frames, will be set to 16 on mgmt + * frames and 0 on non-QoS frames. + */ + int security_idx; + u32 tkip_iv32; u16 tkip_iv16; }; @@ -417,6 +432,14 @@ struct ieee80211_if_managed { * generated for the current association. */ int last_cqm_event_signal; + + /* + * State variables for keeping track of RSSI of the AP currently + * connected to and informing driver when RSSI has gone + * below/above a certain threshold. + */ + int rssi_min_thold, rssi_max_thold; + int last_ave_beacon_signal; }; struct ieee80211_if_ibss { @@ -515,12 +538,14 @@ struct ieee80211_if_mesh { * @IEEE80211_SDATA_DONT_BRIDGE_PACKETS: bridge packets between * associated stations and deliver multicast frames both * back to wireless media and to the local net stack. + * @IEEE80211_SDATA_DISCONNECT_RESUME: Disconnect after resume. */ enum ieee80211_sub_if_data_flags { IEEE80211_SDATA_ALLMULTI = BIT(0), IEEE80211_SDATA_PROMISC = BIT(1), IEEE80211_SDATA_OPERATING_GMODE = BIT(2), IEEE80211_SDATA_DONT_BRIDGE_PACKETS = BIT(3), + IEEE80211_SDATA_DISCONNECT_RESUME = BIT(4), }; /** @@ -544,6 +569,9 @@ struct ieee80211_sub_if_data { /* keys */ struct list_head key_list; + /* count for keys needing tailroom space allocation */ + int crypto_tx_tailroom_needed_cnt; + struct net_device *dev; struct ieee80211_local *local; @@ -775,9 +803,6 @@ struct ieee80211_local { int tx_headroom; /* required headroom for hardware/radiotap */ - /* count for keys needing tailroom space allocation */ - int crypto_tx_tailroom_needed_cnt; - /* Tasklet and skb queue to process calls from IRQ mode. All frames * added to skb_queue will be processed, but frames in * skb_queue_unreliable may be dropped if the total length of these @@ -1353,10 +1378,12 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len); + const u8 *ie, size_t ie_len, + bool directed); void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len); + const u8 *ie, size_t ie_len, + bool directed); void ieee80211_sta_def_wmm_params(struct ieee80211_sub_if_data *sdata, const size_t supp_rates_len, diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 49d4f869e0b..cd5fb40d3fd 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -363,8 +363,7 @@ static int ieee80211_open(struct net_device *dev) int err; /* fail early if user set an invalid address */ - if (!is_zero_ether_addr(dev->dev_addr) && - !is_valid_ether_addr(dev->dev_addr)) + if (!is_valid_ether_addr(dev->dev_addr)) return -EADDRNOTAVAIL; err = ieee80211_check_concurrent_iface(sdata, sdata->vif.type); @@ -1130,8 +1129,8 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, ASSERT_RTNL(); - ndev = alloc_netdev_mq(sizeof(*sdata) + local->hw.vif_data_size, - name, ieee80211_if_setup, local->hw.queues); + ndev = alloc_netdev_mqs(sizeof(*sdata) + local->hw.vif_data_size, + name, ieee80211_if_setup, local->hw.queues, 1); if (!ndev) return -ENOMEM; dev_net_set(ndev, wiphy_net(local->hw.wiphy)); @@ -1145,6 +1144,10 @@ int ieee80211_if_add(struct ieee80211_local *local, const char *name, + IEEE80211_ENCRYPT_HEADROOM; ndev->needed_tailroom = IEEE80211_ENCRYPT_TAILROOM; + ret = dev_alloc_name(ndev, ndev->name); + if (ret < 0) + goto fail; + ieee80211_assign_perm_addr(local, ndev, type); memcpy(ndev->dev_addr, ndev->perm_addr, ETH_ALEN); SET_NETDEV_DEV(ndev, wiphy_dev(local->hw.wiphy)); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 31afd712930..739bee13e81 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -61,6 +61,36 @@ static struct ieee80211_sta *get_sta_for_key(struct ieee80211_key *key) return NULL; } +static void increment_tailroom_need_count(struct ieee80211_sub_if_data *sdata) +{ + /* + * When this count is zero, SKB resizing for allocating tailroom + * for IV or MMIC is skipped. But, this check has created two race + * cases in xmit path while transiting from zero count to one: + * + * 1. SKB resize was skipped because no key was added but just before + * the xmit key is added and SW encryption kicks off. + * + * 2. SKB resize was skipped because all the keys were hw planted but + * just before xmit one of the key is deleted and SW encryption kicks + * off. + * + * In both the above case SW encryption will find not enough space for + * tailroom and exits with WARN_ON. (See WARN_ONs at wpa.c) + * + * Solution has been explained at + * http://mid.gmane.org/1308590980.4322.19.camel@jlt3.sipsolutions.net + */ + + if (!sdata->crypto_tx_tailroom_needed_cnt++) { + /* + * Flush all XMIT packets currently using HW encryption or no + * encryption at all if the count transition is from 0 -> 1. + */ + synchronize_net(); + } +} + static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) { struct ieee80211_sub_if_data *sdata; @@ -104,7 +134,7 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))) - key->local->crypto_tx_tailroom_needed_cnt--; + sdata->crypto_tx_tailroom_needed_cnt--; return 0; } @@ -147,6 +177,10 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) sta = get_sta_for_key(key); sdata = key->sdata; + if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || + (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))) + increment_tailroom_need_count(sdata); + if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN) sdata = container_of(sdata->bss, struct ieee80211_sub_if_data, @@ -161,10 +195,6 @@ static void ieee80211_key_disable_hw_accel(struct ieee80211_key *key) key->conf.keyidx, sta ? sta->addr : bcast_addr, ret); key->flags &= ~KEY_FLAG_UPLOADED_TO_HARDWARE; - - if (!((key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_MMIC) || - (key->conf.flags & IEEE80211_KEY_FLAG_GENERATE_IV))) - key->local->crypto_tx_tailroom_needed_cnt++; } void ieee80211_key_removed(struct ieee80211_key_conf *key_conf) @@ -339,6 +369,7 @@ struct ieee80211_key *ieee80211_key_alloc(u32 cipher, int idx, size_t key_len, get_unaligned_le16(seq); } } + spin_lock_init(&key->u.tkip.txlock); break; case WLAN_CIPHER_SUITE_CCMP: key->conf.iv_len = CCMP_HDR_LEN; @@ -405,7 +436,7 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key) ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm); if (key->local) { ieee80211_debugfs_key_remove(key); - key->local->crypto_tx_tailroom_needed_cnt--; + key->sdata->crypto_tx_tailroom_needed_cnt--; } kfree(key); @@ -463,13 +494,13 @@ int ieee80211_key_link(struct ieee80211_key *key, else old_key = key_mtx_dereference(sdata->local, sdata->keys[idx]); + increment_tailroom_need_count(sdata); + __ieee80211_key_replace(sdata, sta, pairwise, old_key, key); __ieee80211_key_destroy(old_key); ieee80211_debugfs_key_add(key); - key->local->crypto_tx_tailroom_needed_cnt++; - ret = ieee80211_key_enable_hw_accel(key); mutex_unlock(&sdata->local->key_mtx); @@ -511,16 +542,49 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->local->key_mtx); - sdata->local->crypto_tx_tailroom_needed_cnt = 0; + sdata->crypto_tx_tailroom_needed_cnt = 0; list_for_each_entry(key, &sdata->key_list, list) { - sdata->local->crypto_tx_tailroom_needed_cnt++; + increment_tailroom_need_count(sdata); ieee80211_key_enable_hw_accel(key); } mutex_unlock(&sdata->local->key_mtx); } +void ieee80211_iter_keys(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + void (*iter)(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key, + void *data), + void *iter_data) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct ieee80211_key *key; + struct ieee80211_sub_if_data *sdata; + + ASSERT_RTNL(); + + mutex_lock(&local->key_mtx); + if (vif) { + sdata = vif_to_sdata(vif); + list_for_each_entry(key, &sdata->key_list, list) + iter(hw, &sdata->vif, + key->sta ? &key->sta->sta : NULL, + &key->conf, iter_data); + } else { + list_for_each_entry(sdata, &local->interfaces, list) + list_for_each_entry(key, &sdata->key_list, list) + iter(hw, &sdata->vif, + key->sta ? &key->sta->sta : NULL, + &key->conf, iter_data); + } + mutex_unlock(&local->key_mtx); +} +EXPORT_SYMBOL(ieee80211_iter_keys); + void ieee80211_disable_keys(struct ieee80211_sub_if_data *sdata) { struct ieee80211_key *key; @@ -550,3 +614,89 @@ void ieee80211_free_keys(struct ieee80211_sub_if_data *sdata) mutex_unlock(&sdata->local->key_mtx); } + + +void ieee80211_gtk_rekey_notify(struct ieee80211_vif *vif, const u8 *bssid, + const u8 *replay_ctr, gfp_t gfp) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + trace_api_gtk_rekey_notify(sdata, bssid, replay_ctr); + + cfg80211_gtk_rekey_notify(sdata->dev, bssid, replay_ctr, gfp); +} +EXPORT_SYMBOL_GPL(ieee80211_gtk_rekey_notify); + +void ieee80211_get_key_tx_seq(struct ieee80211_key_conf *keyconf, + struct ieee80211_key_seq *seq) +{ + struct ieee80211_key *key; + u64 pn64; + + if (WARN_ON(!(keyconf->flags & IEEE80211_KEY_FLAG_GENERATE_IV))) + return; + + key = container_of(keyconf, struct ieee80211_key, conf); + + switch (key->conf.cipher) { + case WLAN_CIPHER_SUITE_TKIP: + seq->tkip.iv32 = key->u.tkip.tx.iv32; + seq->tkip.iv16 = key->u.tkip.tx.iv16; + break; + case WLAN_CIPHER_SUITE_CCMP: + pn64 = atomic64_read(&key->u.ccmp.tx_pn); + seq->ccmp.pn[5] = pn64; + seq->ccmp.pn[4] = pn64 >> 8; + seq->ccmp.pn[3] = pn64 >> 16; + seq->ccmp.pn[2] = pn64 >> 24; + seq->ccmp.pn[1] = pn64 >> 32; + seq->ccmp.pn[0] = pn64 >> 40; + break; + case WLAN_CIPHER_SUITE_AES_CMAC: + pn64 = atomic64_read(&key->u.aes_cmac.tx_pn); + seq->ccmp.pn[5] = pn64; + seq->ccmp.pn[4] = pn64 >> 8; + seq->ccmp.pn[3] = pn64 >> 16; + seq->ccmp.pn[2] = pn64 >> 24; + seq->ccmp.pn[1] = pn64 >> 32; + seq->ccmp.pn[0] = pn64 >> 40; + break; + default: + WARN_ON(1); + } +} +EXPORT_SYMBOL(ieee80211_get_key_tx_seq); + +void ieee80211_get_key_rx_seq(struct ieee80211_key_conf *keyconf, + int tid, struct ieee80211_key_seq *seq) +{ + struct ieee80211_key *key; + const u8 *pn; + + key = container_of(keyconf, struct ieee80211_key, conf); + + switch (key->conf.cipher) { + case WLAN_CIPHER_SUITE_TKIP: + if (WARN_ON(tid < 0 || tid >= NUM_RX_DATA_QUEUES)) + return; + seq->tkip.iv32 = key->u.tkip.rx[tid].iv32; + seq->tkip.iv16 = key->u.tkip.rx[tid].iv16; + break; + case WLAN_CIPHER_SUITE_CCMP: + if (WARN_ON(tid < -1 || tid >= NUM_RX_DATA_QUEUES)) + return; + if (tid < 0) + pn = key->u.ccmp.rx_pn[NUM_RX_DATA_QUEUES]; + else + pn = key->u.ccmp.rx_pn[tid]; + memcpy(seq->ccmp.pn, pn, CCMP_PN_LEN); + break; + case WLAN_CIPHER_SUITE_AES_CMAC: + if (WARN_ON(tid != 0)) + return; + pn = key->u.aes_cmac.rx_pn; + memcpy(seq->aes_cmac.pn, pn, CMAC_PN_LEN); + break; + } +} +EXPORT_SYMBOL(ieee80211_get_key_rx_seq); diff --git a/net/mac80211/key.h b/net/mac80211/key.h index d801d535133..7d4e31f037d 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -28,8 +28,9 @@ #define CCMP_PN_LEN 6 #define TKIP_IV_LEN 8 #define TKIP_ICV_LEN 4 +#define CMAC_PN_LEN 6 -#define NUM_RX_DATA_QUEUES 17 +#define NUM_RX_DATA_QUEUES 16 struct ieee80211_local; struct ieee80211_sub_if_data; @@ -40,9 +41,11 @@ struct sta_info; * * @KEY_FLAG_UPLOADED_TO_HARDWARE: Indicates that this key is present * in the hardware for TX crypto hardware acceleration. + * @KEY_FLAG_TAINTED: Key is tainted and packets should be dropped. */ enum ieee80211_internal_key_flags { KEY_FLAG_UPLOADED_TO_HARDWARE = BIT(0), + KEY_FLAG_TAINTED = BIT(1), }; enum ieee80211_internal_tkip_state { @@ -52,9 +55,10 @@ enum ieee80211_internal_tkip_state { }; struct tkip_ctx { - u32 iv32; - u16 iv16; - u16 p1k[5]; + u32 iv32; /* current iv32 */ + u16 iv16; /* current iv16 */ + u16 p1k[5]; /* p1k cache */ + u32 p1k_iv32; /* iv32 for which p1k computed */ enum ieee80211_internal_tkip_state state; }; @@ -71,6 +75,9 @@ struct ieee80211_key { union { struct { + /* protects tx context */ + spinlock_t txlock; + /* last used TSC */ struct tkip_ctx tx; @@ -78,32 +85,23 @@ struct ieee80211_key { struct tkip_ctx rx[NUM_RX_DATA_QUEUES]; } tkip; struct { - u8 tx_pn[6]; + atomic64_t tx_pn; /* * Last received packet number. The first * NUM_RX_DATA_QUEUES counters are used with Data * frames and the last counter is used with Robust * Management frames. */ - u8 rx_pn[NUM_RX_DATA_QUEUES + 1][6]; + u8 rx_pn[NUM_RX_DATA_QUEUES + 1][CCMP_PN_LEN]; struct crypto_cipher *tfm; u32 replays; /* dot11RSNAStatsCCMPReplays */ - /* scratch buffers for virt_to_page() (crypto API) */ -#ifndef AES_BLOCK_LEN -#define AES_BLOCK_LEN 16 -#endif - u8 tx_crypto_buf[6 * AES_BLOCK_LEN]; - u8 rx_crypto_buf[6 * AES_BLOCK_LEN]; } ccmp; struct { - u8 tx_pn[6]; - u8 rx_pn[6]; + atomic64_t tx_pn; + u8 rx_pn[CMAC_PN_LEN]; struct crypto_cipher *tfm; u32 replays; /* dot11RSNAStatsCMACReplays */ u32 icverrors; /* dot11RSNAStatsCMACICVErrors */ - /* scratch buffers for virt_to_page() (crypto API) */ - u8 tx_crypto_buf[2 * AES_BLOCK_LEN]; - u8 rx_crypto_buf[2 * AES_BLOCK_LEN]; } aes_cmac; } u; diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 0d2faacc3e8..068ee651825 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -647,12 +647,12 @@ int mesh_path_del(u8 *addr, struct ieee80211_sub_if_data *sdata) mpath = node->mpath; if (mpath->sdata == sdata && memcmp(addr, mpath->dst, ETH_ALEN) == 0) { - spin_lock_bh(&mpath->state_lock); + spin_lock(&mpath->state_lock); mpath->flags |= MESH_PATH_RESOLVING; hlist_del_rcu(&node->list); call_rcu(&node->rcu, mesh_path_node_reclaim); atomic_dec(&tbl->entries); - spin_unlock_bh(&mpath->state_lock); + spin_unlock(&mpath->state_lock); goto enddel; } } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 456cccf26b5..c99237cd4b9 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -232,9 +232,6 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type)); } - ieee80211_stop_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CSA); - /* channel_type change automatically detected */ ieee80211_hw_config(local, 0); @@ -248,9 +245,6 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, rcu_read_unlock(); } - ieee80211_wake_queues_by_reason(&sdata->local->hw, - IEEE80211_QUEUE_STOP_REASON_CSA); - ht_opmode = le16_to_cpu(hti->operation_mode); /* if bss configuration changed store the new one */ @@ -755,7 +749,7 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work) container_of(work, struct ieee80211_local, dynamic_ps_enable_work); struct ieee80211_sub_if_data *sdata = local->ps_sdata; - struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + struct ieee80211_if_managed *ifmgd; unsigned long flags; int q; @@ -763,26 +757,39 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work) if (!sdata) return; + ifmgd = &sdata->u.mgd; + if (local->hw.conf.flags & IEEE80211_CONF_PS) return; - /* - * transmission can be stopped by others which leads to - * dynamic_ps_timer expiry. Postpond the ps timer if it - * is not the actual idle state. - */ - spin_lock_irqsave(&local->queue_stop_reason_lock, flags); - for (q = 0; q < local->hw.queues; q++) { - if (local->queue_stop_reasons[q]) { - spin_unlock_irqrestore(&local->queue_stop_reason_lock, - flags); + if (!local->disable_dynamic_ps && + local->hw.conf.dynamic_ps_timeout > 0) { + /* don't enter PS if TX frames are pending */ + if (drv_tx_frames_pending(local)) { mod_timer(&local->dynamic_ps_timer, jiffies + msecs_to_jiffies( local->hw.conf.dynamic_ps_timeout)); return; } + + /* + * transmission can be stopped by others which leads to + * dynamic_ps_timer expiry. Postpone the ps timer if it + * is not the actual idle state. + */ + spin_lock_irqsave(&local->queue_stop_reason_lock, flags); + for (q = 0; q < local->hw.queues; q++) { + if (local->queue_stop_reasons[q]) { + spin_unlock_irqrestore(&local->queue_stop_reason_lock, + flags); + mod_timer(&local->dynamic_ps_timer, jiffies + + msecs_to_jiffies( + local->hw.conf.dynamic_ps_timeout)); + return; + } + } + spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); } - spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags); if ((local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) && (!(ifmgd->flags & IEEE80211_STA_NULLFUNC_ACKED))) { @@ -807,7 +814,8 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work) ieee80211_hw_config(local, IEEE80211_CONF_CHANGE_PS); } - netif_tx_wake_all_queues(sdata->dev); + if (local->hw.flags & IEEE80211_HW_PS_NULLFUNC_STACK) + netif_tx_wake_all_queues(sdata->dev); } void ieee80211_dynamic_ps_timer(unsigned long data) @@ -1210,7 +1218,8 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata) ieee80211_send_nullfunc(sdata->local, sdata, 0); } else { ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); - ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid[1], NULL, 0); + ieee80211_send_probe_req(sdata, dst, ssid + 2, ssid[1], NULL, 0, + true); } ifmgd->probe_send_count++; @@ -1295,7 +1304,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw, ssid = ieee80211_bss_get_ie(ifmgd->associated, WLAN_EID_SSID); skb = ieee80211_build_probe_req(sdata, ifmgd->associated->bssid, - ssid + 2, ssid[1], NULL, 0); + ssid + 2, ssid[1], NULL, 0, true); return skb; } @@ -1754,6 +1763,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->ave_beacon_signal = rx_status->signal * 16; ifmgd->last_cqm_event_signal = 0; ifmgd->count_beacon_signal = 1; + ifmgd->last_ave_beacon_signal = 0; } else { ifmgd->ave_beacon_signal = (IEEE80211_SIGNAL_AVE_WEIGHT * rx_status->signal * 16 + @@ -1761,6 +1771,28 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata, ifmgd->ave_beacon_signal) / 16; ifmgd->count_beacon_signal++; } + + if (ifmgd->rssi_min_thold != ifmgd->rssi_max_thold && + ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT) { + int sig = ifmgd->ave_beacon_signal; + int last_sig = ifmgd->last_ave_beacon_signal; + + /* + * if signal crosses either of the boundaries, invoke callback + * with appropriate parameters + */ + if (sig > ifmgd->rssi_max_thold && + (last_sig <= ifmgd->rssi_min_thold || last_sig == 0)) { + ifmgd->last_ave_beacon_signal = sig; + drv_rssi_callback(local, RSSI_EVENT_HIGH); + } else if (sig < ifmgd->rssi_min_thold && + (last_sig >= ifmgd->rssi_max_thold || + last_sig == 0)) { + ifmgd->last_ave_beacon_signal = sig; + drv_rssi_callback(local, RSSI_EVENT_LOW); + } + } + if (bss_conf->cqm_rssi_thold && ifmgd->count_beacon_signal >= IEEE80211_SIGNAL_AVE_MIN_COUNT && !(local->hw.flags & IEEE80211_HW_SUPPORTS_CQM_RSSI)) { @@ -2020,7 +2052,7 @@ static void ieee80211_sta_timer(unsigned long data) } static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, - u8 *bssid) + u8 *bssid, u8 reason) { struct ieee80211_local *local = sdata->local; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; @@ -2038,8 +2070,7 @@ static void ieee80211_sta_connection_lost(struct ieee80211_sub_if_data *sdata, * but that's not a problem. */ ieee80211_send_deauth_disassoc(sdata, bssid, - IEEE80211_STYPE_DEAUTH, - WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY, + IEEE80211_STYPE_DEAUTH, reason, NULL, true); mutex_lock(&ifmgd->mtx); } @@ -2085,7 +2116,8 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) " AP %pM, disconnecting.\n", sdata->name, bssid); #endif - ieee80211_sta_connection_lost(sdata, bssid); + ieee80211_sta_connection_lost(sdata, bssid, + WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); } } else if (time_is_after_jiffies(ifmgd->probe_timeout)) run_again(ifmgd, ifmgd->probe_timeout); @@ -2097,7 +2129,8 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) sdata->name, bssid, probe_wait_ms); #endif - ieee80211_sta_connection_lost(sdata, bssid); + ieee80211_sta_connection_lost(sdata, bssid, + WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); } else if (ifmgd->probe_send_count < max_tries) { #ifdef CONFIG_MAC80211_VERBOSE_DEBUG wiphy_debug(local->hw.wiphy, @@ -2119,7 +2152,8 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) sdata->name, bssid, probe_wait_ms); - ieee80211_sta_connection_lost(sdata, bssid); + ieee80211_sta_connection_lost(sdata, bssid, + WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY); } } @@ -2206,12 +2240,34 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) { struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; + if (!ifmgd->associated) + return; + + if (sdata->flags & IEEE80211_SDATA_DISCONNECT_RESUME) { + sdata->flags &= ~IEEE80211_SDATA_DISCONNECT_RESUME; + mutex_lock(&ifmgd->mtx); + if (ifmgd->associated) { +#ifdef CONFIG_MAC80211_VERBOSE_DEBUG + wiphy_debug(sdata->local->hw.wiphy, + "%s: driver requested disconnect after resume.\n", + sdata->name); +#endif + ieee80211_sta_connection_lost(sdata, + ifmgd->associated->bssid, + WLAN_REASON_UNSPECIFIED); + mutex_unlock(&ifmgd->mtx); + return; + } + mutex_unlock(&ifmgd->mtx); + } + if (test_and_clear_bit(TMR_RUNNING_TIMER, &ifmgd->timers_running)) add_timer(&ifmgd->timer); if (test_and_clear_bit(TMR_RUNNING_CHANSW, &ifmgd->timers_running)) add_timer(&ifmgd->chswitch_timer); ieee80211_sta_reset_beacon_monitor(sdata); ieee80211_restart_sta_timer(sdata); + ieee80211_queue_work(&sdata->local->hw, &sdata->u.mgd.monitor_work); } #endif @@ -2658,3 +2714,10 @@ void ieee80211_cqm_rssi_notify(struct ieee80211_vif *vif, cfg80211_cqm_rssi_notify(sdata->dev, rssi_event, gfp); } EXPORT_SYMBOL(ieee80211_cqm_rssi_notify); + +unsigned char ieee80211_get_operstate(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + return sdata->dev->operstate; +} +EXPORT_SYMBOL(ieee80211_get_operstate); diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c index 730778a2c90..f87e993e713 100644 --- a/net/mac80211/pm.c +++ b/net/mac80211/pm.c @@ -6,6 +6,28 @@ #include "driver-ops.h" #include "led.h" +/* return value indicates whether the driver should be further notified */ +static bool ieee80211_quiesce(struct ieee80211_sub_if_data *sdata) +{ + switch (sdata->vif.type) { + case NL80211_IFTYPE_STATION: + ieee80211_sta_quiesce(sdata); + return true; + case NL80211_IFTYPE_ADHOC: + ieee80211_ibss_quiesce(sdata); + return true; + case NL80211_IFTYPE_MESH_POINT: + ieee80211_mesh_quiesce(sdata); + return true; + case NL80211_IFTYPE_AP_VLAN: + case NL80211_IFTYPE_MONITOR: + /* don't tell driver about this */ + return false; + default: + return true; + } +} + int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) { struct ieee80211_local *local = hw_to_local(hw); @@ -50,11 +72,19 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) local->wowlan = wowlan && local->open_count; if (local->wowlan) { int err = drv_suspend(local, wowlan); - if (err) { + if (err < 0) { local->quiescing = false; return err; + } else if (err > 0) { + WARN_ON(err != 1); + local->wowlan = false; + } else { + list_for_each_entry(sdata, &local->interfaces, list) { + cancel_work_sync(&sdata->work); + ieee80211_quiesce(sdata); + } + goto suspend; } - goto suspend; } /* disable keys */ @@ -82,23 +112,8 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) list_for_each_entry(sdata, &local->interfaces, list) { cancel_work_sync(&sdata->work); - switch(sdata->vif.type) { - case NL80211_IFTYPE_STATION: - ieee80211_sta_quiesce(sdata); - break; - case NL80211_IFTYPE_ADHOC: - ieee80211_ibss_quiesce(sdata); - break; - case NL80211_IFTYPE_MESH_POINT: - ieee80211_mesh_quiesce(sdata); - break; - case NL80211_IFTYPE_AP_VLAN: - case NL80211_IFTYPE_MONITOR: - /* don't tell driver about this */ + if (!ieee80211_quiesce(sdata)) continue; - default: - break; - } if (!ieee80211_sdata_running(sdata)) continue; diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c index 8adac67395f..58a89554b78 100644 --- a/net/mac80211/rc80211_minstrel.c +++ b/net/mac80211/rc80211_minstrel.c @@ -532,12 +532,21 @@ minstrel_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) mp->hw = hw; mp->update_interval = 100; +#ifdef CONFIG_MAC80211_DEBUGFS + mp->fixed_rate_idx = (u32) -1; + mp->dbg_fixed_rate = debugfs_create_u32("fixed_rate_idx", + S_IRUGO | S_IWUGO, debugfsdir, &mp->fixed_rate_idx); +#endif + return mp; } static void minstrel_free(void *priv) { +#ifdef CONFIG_MAC80211_DEBUGFS + debugfs_remove(((struct minstrel_priv *)priv)->dbg_fixed_rate); +#endif kfree(priv); } diff --git a/net/mac80211/rc80211_minstrel.h b/net/mac80211/rc80211_minstrel.h index 0f5a83370aa..5d278eccaef 100644 --- a/net/mac80211/rc80211_minstrel.h +++ b/net/mac80211/rc80211_minstrel.h @@ -78,6 +78,18 @@ struct minstrel_priv { unsigned int update_interval; unsigned int lookaround_rate; unsigned int lookaround_rate_mrr; + +#ifdef CONFIG_MAC80211_DEBUGFS + /* + * enable fixed rate processing per RC + * - write static index to debugfs:ieee80211/phyX/rc/fixed_rate_idx + * - write -1 to enable RC processing again + * - setting will be applied on next update + */ + u32 fixed_rate_idx; + struct dentry *dbg_fixed_rate; +#endif + }; struct minstrel_debugfs_info { diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 333b5118be6..66a1eeb279c 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -609,6 +609,13 @@ minstrel_ht_get_rate(void *priv, struct ieee80211_sta *sta, void *priv_sta, info->flags |= mi->tx_flags; sample_idx = minstrel_get_sample_rate(mp, mi); + +#ifdef CONFIG_MAC80211_DEBUGFS + /* use fixed index if set */ + if (mp->fixed_rate_idx != -1) + sample_idx = mp->fixed_rate_idx; +#endif + if (sample_idx >= 0) { sample = true; minstrel_ht_set_rate(mp, mi, &ar[0], sample_idx, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 7fa8c6be7bf..fe2c2a71779 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -331,15 +331,18 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) { struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb); - int tid; + int tid, seqno_idx, security_idx; /* does the frame have a qos control field? */ if (ieee80211_is_data_qos(hdr->frame_control)) { u8 *qc = ieee80211_get_qos_ctl(hdr); /* frame has qos control */ tid = *qc & IEEE80211_QOS_CTL_TID_MASK; - if (*qc & IEEE80211_QOS_CONTROL_A_MSDU_PRESENT) + if (*qc & IEEE80211_QOS_CTL_A_MSDU_PRESENT) status->rx_flags |= IEEE80211_RX_AMSDU; + + seqno_idx = tid; + security_idx = tid; } else { /* * IEEE 802.11-2007, 7.1.3.4.1 ("Sequence Number field"): @@ -352,10 +355,15 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) * * We also use that counter for non-QoS STAs. */ - tid = NUM_RX_DATA_QUEUES - 1; + seqno_idx = NUM_RX_DATA_QUEUES; + security_idx = 0; + if (ieee80211_is_mgmt(hdr->frame_control)) + security_idx = NUM_RX_DATA_QUEUES; + tid = 0; } - rx->queue = tid; + rx->seqno_idx = seqno_idx; + rx->security_idx = security_idx; /* Set skb->priority to 1d tag if highest order bit of TID is not set. * For now, set skb->priority to 0 for other cases. */ rx->skb->priority = (tid > 7) ? 0 : tid; @@ -810,7 +818,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) /* Drop duplicate 802.11 retransmissions (IEEE 802.11 Chap. 9.2.9) */ if (rx->sta && !is_multicast_ether_addr(hdr->addr1)) { if (unlikely(ieee80211_has_retry(hdr->frame_control) && - rx->sta->last_seq_ctrl[rx->queue] == + rx->sta->last_seq_ctrl[rx->seqno_idx] == hdr->seq_ctrl)) { if (status->rx_flags & IEEE80211_RX_RA_MATCH) { rx->local->dot11FrameDuplicateCount++; @@ -818,7 +826,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx) } return RX_DROP_UNUSABLE; } else - rx->sta->last_seq_ctrl[rx->queue] = hdr->seq_ctrl; + rx->sta->last_seq_ctrl[rx->seqno_idx] = hdr->seq_ctrl; } if (unlikely(rx->skb->len < 16)) { @@ -1011,6 +1019,9 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx) } if (rx->key) { + if (unlikely(rx->key->flags & KEY_FLAG_TAINTED)) + return RX_DROP_MONITOR; + rx->key->tx_rx_count++; /* TODO: add threshold stuff again */ } else { @@ -1374,11 +1385,10 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (frag == 0) { /* This is the first fragment of a new frame. */ entry = ieee80211_reassemble_add(rx->sdata, frag, seq, - rx->queue, &(rx->skb)); + rx->seqno_idx, &(rx->skb)); if (rx->key && rx->key->conf.cipher == WLAN_CIPHER_SUITE_CCMP && ieee80211_has_protected(fc)) { - int queue = ieee80211_is_mgmt(fc) ? - NUM_RX_DATA_QUEUES : rx->queue; + int queue = rx->security_idx; /* Store CCMP PN so that we can verify that the next * fragment has a sequential PN value. */ entry->ccmp = 1; @@ -1392,7 +1402,8 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) /* This is a fragment for a frame that should already be pending in * fragment cache. Add this fragment to the end of the pending entry. */ - entry = ieee80211_reassemble_find(rx->sdata, frag, seq, rx->queue, hdr); + entry = ieee80211_reassemble_find(rx->sdata, frag, seq, + rx->seqno_idx, hdr); if (!entry) { I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag); return RX_DROP_MONITOR; @@ -1412,8 +1423,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx) if (pn[i]) break; } - queue = ieee80211_is_mgmt(fc) ? - NUM_RX_DATA_QUEUES : rx->queue; + queue = rx->security_idx; rpn = rx->key->u.ccmp.rx_pn[queue]; if (memcmp(pn, rpn, CCMP_PN_LEN)) return RX_DROP_UNUSABLE; @@ -2590,7 +2600,9 @@ void ieee80211_release_reorder_timeout(struct sta_info *sta, int tid) .sta = sta, .sdata = sta->sdata, .local = sta->local, - .queue = tid, + /* This is OK -- must be QoS data frame */ + .security_idx = tid, + .seqno_idx = tid, .flags = 0, }; struct tid_ampdu_rx *tid_agg_rx; diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 58ffa7d069c..08a45ac3d6f 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -228,6 +228,7 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) { struct cfg80211_scan_request *req = local->scan_req; + struct ieee80211_sub_if_data *sdata = local->scan_sdata; enum ieee80211_band band; int i, ielen, n_chans; @@ -251,8 +252,8 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local) local->hw_scan_req->n_channels = n_chans; ielen = ieee80211_build_preq_ies(local, (u8 *)local->hw_scan_req->ie, - req->ie, req->ie_len, band, (u32) -1, - 0); + req->ie, req->ie_len, band, + sdata->rc_rateidx_mask[band], 0); local->hw_scan_req->ie_len = ielen; return true; @@ -658,7 +659,8 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local, sdata, NULL, local->scan_req->ssids[i].ssid, local->scan_req->ssids[i].ssid_len, - local->scan_req->ie, local->scan_req->ie_len); + local->scan_req->ie, local->scan_req->ie_len, + false); /* * After sending probe requests, wait for probe responses @@ -821,10 +823,8 @@ int ieee80211_request_internal_scan(struct ieee80211_sub_if_data *sdata, */ void ieee80211_scan_cancel(struct ieee80211_local *local) { - bool abortscan; - /* - * We are only canceling software scan, or deferred scan that was not + * We are canceling software scan, or deferred scan that was not * yet really started (see __ieee80211_start_scan ). * * Regarding hardware scan: @@ -836,23 +836,30 @@ void ieee80211_scan_cancel(struct ieee80211_local *local) * - we can not cancel scan_work since driver can schedule it * by ieee80211_scan_completed(..., true) to finish scan * - * Hence low lever driver is responsible for canceling HW scan. + * Hence we only call the cancel_hw_scan() callback, but the low-level + * driver is still responsible for calling ieee80211_scan_completed() + * after the scan was completed/aborted. */ mutex_lock(&local->mtx); - abortscan = local->scan_req && !test_bit(SCAN_HW_SCANNING, &local->scanning); - if (abortscan) { - /* - * The scan is canceled, but stop work from being pending. - * - * If the work is currently running, it must be blocked on - * the mutex, but we'll set scan_sdata = NULL and it'll - * simply exit once it acquires the mutex. - */ - cancel_delayed_work(&local->scan_work); - /* and clean up */ - __ieee80211_scan_completed(&local->hw, true, false); + if (!local->scan_req) + goto out; + + if (test_bit(SCAN_HW_SCANNING, &local->scanning)) { + if (local->ops->cancel_hw_scan) + drv_cancel_hw_scan(local, local->scan_sdata); + goto out; } + + /* + * If the work is currently running, it must be blocked on + * the mutex, but we'll set scan_sdata = NULL and it'll + * simply exit once it acquires the mutex. + */ + cancel_delayed_work(&local->scan_work); + /* and clean up */ + __ieee80211_scan_completed(&local->hw, true, false); +out: mutex_unlock(&local->mtx); } @@ -877,7 +884,8 @@ int ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata, for (i = 0; i < IEEE80211_NUM_BANDS; i++) { local->sched_scan_ies.ie[i] = kzalloc(2 + IEEE80211_MAX_SSID_LEN + - local->scan_ies_len, + local->scan_ies_len + + req->ie_len, GFP_KERNEL); if (!local->sched_scan_ies.ie[i]) { ret = -ENOMEM; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index c6ae8718bd5..28beb78e601 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -158,6 +158,8 @@ struct tid_ampdu_rx { * @work: work struct for starting/stopping aggregation * @tid_rx_timer_expired: bitmap indicating on which TIDs the * RX timer expired until the work for it runs + * @tid_rx_stop_requested: bitmap indicating which BA sessions per TID the + * driver requested to close until the work for it runs * @mtx: mutex to protect all TX data (except non-NULL assignments * to tid_tx[idx], which are protected by the sta spinlock) */ @@ -166,6 +168,7 @@ struct sta_ampdu_mlme { /* rx */ struct tid_ampdu_rx __rcu *tid_rx[STA_TID_NUM]; unsigned long tid_rx_timer_expired[BITS_TO_LONGS(STA_TID_NUM)]; + unsigned long tid_rx_stop_requested[BITS_TO_LONGS(STA_TID_NUM)]; /* tx */ struct work_struct work; struct tid_ampdu_tx __rcu *tid_tx[STA_TID_NUM]; @@ -284,7 +287,8 @@ struct sta_info { unsigned long rx_dropped; int last_signal; struct ewma avg_signal; - __le16 last_seq_ctrl[NUM_RX_DATA_QUEUES]; + /* Plus 1 for non-QoS frames */ + __le16 last_seq_ctrl[NUM_RX_DATA_QUEUES + 1]; /* Updated from TX status path only, no locking requirements */ unsigned long tx_filtered_count; diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 757e4eb2baf..cc79e697cdb 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -101,6 +101,7 @@ static void tkip_mixing_phase1(const u8 *tk, struct tkip_ctx *ctx, p1k[4] += tkipS(p1k[3] ^ get_unaligned_le16(tk + 0 + j)) + i; } ctx->state = TKIP_STATE_PHASE1_DONE; + ctx->p1k_iv32 = tsc_IV32; } static void tkip_mixing_phase2(const u8 *tk, struct tkip_ctx *ctx, @@ -140,60 +141,69 @@ static void tkip_mixing_phase2(const u8 *tk, struct tkip_ctx *ctx, /* Add TKIP IV and Ext. IV at @pos. @iv0, @iv1, and @iv2 are the first octets * of the IV. Returns pointer to the octet following IVs (i.e., beginning of * the packet payload). */ -u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key *key, u16 iv16) +u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key *key) { - pos = write_tkip_iv(pos, iv16); + lockdep_assert_held(&key->u.tkip.txlock); + + pos = write_tkip_iv(pos, key->u.tkip.tx.iv16); *pos++ = (key->conf.keyidx << 6) | (1 << 5) /* Ext IV */; put_unaligned_le32(key->u.tkip.tx.iv32, pos); return pos + 4; } -void ieee80211_get_tkip_key(struct ieee80211_key_conf *keyconf, - struct sk_buff *skb, enum ieee80211_tkip_key_type type, - u8 *outkey) +static void ieee80211_compute_tkip_p1k(struct ieee80211_key *key, u32 iv32) { - struct ieee80211_key *key = (struct ieee80211_key *) - container_of(keyconf, struct ieee80211_key, conf); - struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - u8 *data; - const u8 *tk; - struct tkip_ctx *ctx; - u16 iv16; - u32 iv32; - - data = (u8 *)hdr + ieee80211_hdrlen(hdr->frame_control); - iv16 = data[2] | (data[0] << 8); - iv32 = get_unaligned_le32(&data[4]); - - tk = &key->conf.key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY]; - ctx = &key->u.tkip.tx; + struct ieee80211_sub_if_data *sdata = key->sdata; + struct tkip_ctx *ctx = &key->u.tkip.tx; + const u8 *tk = &key->conf.key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY]; -#ifdef CONFIG_MAC80211_TKIP_DEBUG - printk(KERN_DEBUG "TKIP encrypt: iv16 = 0x%04x, iv32 = 0x%08x\n", - iv16, iv32); - - if (iv32 != ctx->iv32) { - printk(KERN_DEBUG "skb: iv32 = 0x%08x key: iv32 = 0x%08x\n", - iv32, ctx->iv32); - printk(KERN_DEBUG "Wrap around of iv16 in the middle of a " - "fragmented packet\n"); - } -#endif + lockdep_assert_held(&key->u.tkip.txlock); + + /* + * Update the P1K when the IV32 is different from the value it + * had when we last computed it (or when not initialised yet). + * This might flip-flop back and forth if packets are processed + * out-of-order due to the different ACs, but then we have to + * just compute the P1K more often. + */ + if (ctx->p1k_iv32 != iv32 || ctx->state == TKIP_STATE_NOT_INIT) + tkip_mixing_phase1(tk, ctx, sdata->vif.addr, iv32); +} - /* Update the p1k only when the iv16 in the packet wraps around, this - * might occur after the wrap around of iv16 in the key in case of - * fragmented packets. */ - if (iv16 == 0 || ctx->state == TKIP_STATE_NOT_INIT) - tkip_mixing_phase1(tk, ctx, hdr->addr2, iv32); +void ieee80211_get_tkip_p1k_iv(struct ieee80211_key_conf *keyconf, + u32 iv32, u16 *p1k) +{ + struct ieee80211_key *key = (struct ieee80211_key *) + container_of(keyconf, struct ieee80211_key, conf); + struct tkip_ctx *ctx = &key->u.tkip.tx; + unsigned long flags; - if (type == IEEE80211_TKIP_P1_KEY) { - memcpy(outkey, ctx->p1k, sizeof(u16) * 5); - return; - } + spin_lock_irqsave(&key->u.tkip.txlock, flags); + ieee80211_compute_tkip_p1k(key, iv32); + memcpy(p1k, ctx->p1k, sizeof(ctx->p1k)); + spin_unlock_irqrestore(&key->u.tkip.txlock, flags); +} +EXPORT_SYMBOL(ieee80211_get_tkip_p1k_iv); - tkip_mixing_phase2(tk, ctx, iv16, outkey); +void ieee80211_get_tkip_p2k(struct ieee80211_key_conf *keyconf, + struct sk_buff *skb, u8 *p2k) +{ + struct ieee80211_key *key = (struct ieee80211_key *) + container_of(keyconf, struct ieee80211_key, conf); + const u8 *tk = &key->conf.key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY]; + struct tkip_ctx *ctx = &key->u.tkip.tx; + struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; + const u8 *data = (u8 *)hdr + ieee80211_hdrlen(hdr->frame_control); + u32 iv32 = get_unaligned_le32(&data[4]); + u16 iv16 = data[2] | (data[0] << 8); + unsigned long flags; + + spin_lock_irqsave(&key->u.tkip.txlock, flags); + ieee80211_compute_tkip_p1k(key, iv32); + tkip_mixing_phase2(tk, ctx, iv16, p2k); + spin_unlock_irqrestore(&key->u.tkip.txlock, flags); } -EXPORT_SYMBOL(ieee80211_get_tkip_key); +EXPORT_SYMBOL(ieee80211_get_tkip_p2k); /* * Encrypt packet payload with TKIP using @key. @pos is a pointer to the @@ -204,19 +214,15 @@ EXPORT_SYMBOL(ieee80211_get_tkip_key); */ int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, struct ieee80211_key *key, - u8 *pos, size_t payload_len, u8 *ta) + struct sk_buff *skb, + u8 *payload, size_t payload_len) { u8 rc4key[16]; - struct tkip_ctx *ctx = &key->u.tkip.tx; - const u8 *tk = &key->conf.key[NL80211_TKIP_DATA_OFFSET_ENCR_KEY]; - - /* Calculate per-packet key */ - if (ctx->iv16 == 0 || ctx->state == TKIP_STATE_NOT_INIT) - tkip_mixing_phase1(tk, ctx, ta, ctx->iv32); - tkip_mixing_phase2(tk, ctx, ctx->iv16, rc4key); + ieee80211_get_tkip_p2k(&key->conf, skb, rc4key); - return ieee80211_wep_encrypt_data(tfm, rc4key, 16, pos, payload_len); + return ieee80211_wep_encrypt_data(tfm, rc4key, 16, + payload, payload_len); } /* Decrypt packet payload with TKIP using @key. @pos is a pointer to the diff --git a/net/mac80211/tkip.h b/net/mac80211/tkip.h index 1cab9c86978..e3ecb659b90 100644 --- a/net/mac80211/tkip.h +++ b/net/mac80211/tkip.h @@ -13,11 +13,13 @@ #include <linux/crypto.h> #include "key.h" -u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key *key, u16 iv16); +u8 *ieee80211_tkip_add_iv(u8 *pos, struct ieee80211_key *key); int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, - struct ieee80211_key *key, - u8 *pos, size_t payload_len, u8 *ta); + struct ieee80211_key *key, + struct sk_buff *skb, + u8 *payload, size_t payload_len); + enum { TKIP_DECRYPT_OK = 0, TKIP_DECRYPT_NO_EXT_IV = -1, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 64e0f7587e6..8cb0d2d0ac6 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -589,6 +589,9 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx) break; } + if (unlikely(tx->key && tx->key->flags & KEY_FLAG_TAINTED)) + return TX_DROP; + if (!skip_hw && tx->key && tx->key->flags & KEY_FLAG_UPLOADED_TO_HARDWARE) info->control.hw_key = &tx->key->conf; @@ -1474,13 +1477,14 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata, /* device xmit handlers */ -static int ieee80211_skb_resize(struct ieee80211_local *local, +static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, int head_need, bool may_encrypt) { + struct ieee80211_local *local = sdata->local; int tail_need = 0; - if (may_encrypt && local->crypto_tx_tailroom_needed_cnt) { + if (may_encrypt && sdata->crypto_tx_tailroom_needed_cnt) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); @@ -1573,7 +1577,7 @@ static void ieee80211_xmit(struct ieee80211_sub_if_data *sdata, headroom -= skb_headroom(skb); headroom = max_t(int, 0, headroom); - if (ieee80211_skb_resize(local, skb, headroom, may_encrypt)) { + if (ieee80211_skb_resize(sdata, skb, headroom, may_encrypt)) { dev_kfree_skb(skb); rcu_read_unlock(); return; @@ -1940,7 +1944,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, head_need += IEEE80211_ENCRYPT_HEADROOM; head_need += local->tx_headroom; head_need = max_t(int, 0, head_need); - if (ieee80211_skb_resize(local, skb, head_need, true)) + if (ieee80211_skb_resize(sdata, skb, head_need, true)) goto fail; } diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d3fe2d23748..5bfb80cba63 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1018,7 +1018,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer, struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len) + const u8 *ie, size_t ie_len, + bool directed) { struct ieee80211_local *local = sdata->local; struct sk_buff *skb; @@ -1035,8 +1036,16 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, return NULL; } - chan = ieee80211_frequency_to_channel( - local->hw.conf.channel->center_freq); + /* + * Do not send DS Channel parameter for directed probe requests + * in order to maximize the chance that we get a response. Some + * badly-behaved APs don't respond when this parameter is included. + */ + if (directed) + chan = 0; + else + chan = ieee80211_frequency_to_channel( + local->hw.conf.channel->center_freq); buf_len = ieee80211_build_preq_ies(local, buf, ie, ie_len, local->hw.conf.channel->band, @@ -1062,11 +1071,13 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata, void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata, u8 *dst, const u8 *ssid, size_t ssid_len, - const u8 *ie, size_t ie_len) + const u8 *ie, size_t ie_len, + bool directed) { struct sk_buff *skb; - skb = ieee80211_build_probe_req(sdata, dst, ssid, ssid_len, ie, ie_len); + skb = ieee80211_build_probe_req(sdata, dst, ssid, ssid_len, ie, ie_len, + directed); if (skb) ieee80211_tx_skb(sdata, skb); } @@ -1276,7 +1287,9 @@ int ieee80211_reconfig(struct ieee80211_local *local) if (ieee80211_sdata_running(sdata)) ieee80211_enable_keys(sdata); +#ifdef CONFIG_PM wake_up: +#endif ieee80211_wake_queues_by_reason(hw, IEEE80211_QUEUE_STOP_REASON_SUSPEND); @@ -1321,6 +1334,33 @@ int ieee80211_reconfig(struct ieee80211_local *local) return 0; } +void ieee80211_resume_disconnect(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata; + struct ieee80211_local *local; + struct ieee80211_key *key; + + if (WARN_ON(!vif)) + return; + + sdata = vif_to_sdata(vif); + local = sdata->local; + + if (WARN_ON(!local->resuming)) + return; + + if (WARN_ON(vif->type != NL80211_IFTYPE_STATION)) + return; + + sdata->flags |= IEEE80211_SDATA_DISCONNECT_RESUME; + + mutex_lock(&local->key_mtx); + list_for_each_entry(key, &sdata->key_list, list) + key->flags |= KEY_FLAG_TAINTED; + mutex_unlock(&local->key_mtx); +} +EXPORT_SYMBOL_GPL(ieee80211_resume_disconnect); + static int check_mgd_smps(struct ieee80211_if_managed *ifmgd, enum ieee80211_smps_mode *smps_mode) { @@ -1437,3 +1477,43 @@ size_t ieee80211_ie_split_vendor(const u8 *ies, size_t ielen, size_t offset) return pos; } + +static void _ieee80211_enable_rssi_reports(struct ieee80211_sub_if_data *sdata, + int rssi_min_thold, + int rssi_max_thold) +{ + trace_api_enable_rssi_reports(sdata, rssi_min_thold, rssi_max_thold); + + if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION)) + return; + + /* + * Scale up threshold values before storing it, as the RSSI averaging + * algorithm uses a scaled up value as well. Change this scaling + * factor if the RSSI averaging algorithm changes. + */ + sdata->u.mgd.rssi_min_thold = rssi_min_thold*16; + sdata->u.mgd.rssi_max_thold = rssi_max_thold*16; +} + +void ieee80211_enable_rssi_reports(struct ieee80211_vif *vif, + int rssi_min_thold, + int rssi_max_thold) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + WARN_ON(rssi_min_thold == rssi_max_thold || + rssi_min_thold > rssi_max_thold); + + _ieee80211_enable_rssi_reports(sdata, rssi_min_thold, + rssi_max_thold); +} +EXPORT_SYMBOL(ieee80211_enable_rssi_reports); + +void ieee80211_disable_rssi_reports(struct ieee80211_vif *vif) +{ + struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); + + _ieee80211_enable_rssi_reports(sdata, 0, 0); +} +EXPORT_SYMBOL(ieee80211_disable_rssi_reports); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 28bc084dbfb..7a49532f14c 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -151,8 +151,7 @@ void ieee80211_set_qos_hdr(struct ieee80211_local *local, struct sk_buff *skb) tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK; if (unlikely(local->wifi_wme_noack_test)) - ack_policy |= QOS_CONTROL_ACK_POLICY_NOACK << - QOS_CONTROL_ACK_POLICY_SHIFT; + ack_policy |= IEEE80211_QOS_CTL_ACK_POLICY_NOACK; /* qos header is 2 bytes, second reserved */ *p++ = ack_policy | tid; *p = 0; diff --git a/net/mac80211/wme.h b/net/mac80211/wme.h index 6053b1c9fee..faead6d0202 100644 --- a/net/mac80211/wme.h +++ b/net/mac80211/wme.h @@ -13,11 +13,6 @@ #include <linux/netdevice.h> #include "ieee80211_i.h" -#define QOS_CONTROL_ACK_POLICY_NORMAL 0 -#define QOS_CONTROL_ACK_POLICY_NOACK 1 - -#define QOS_CONTROL_ACK_POLICY_SHIFT 5 - extern const int ieee802_1d_to_ac[8]; u16 ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, diff --git a/net/mac80211/work.c b/net/mac80211/work.c index d2e7f0e8667..edf8583280c 100644 --- a/net/mac80211/work.c +++ b/net/mac80211/work.c @@ -450,7 +450,7 @@ ieee80211_direct_probe(struct ieee80211_work *wk) * will not answer to direct packet in unassociated state. */ ieee80211_send_probe_req(sdata, NULL, wk->probe_auth.ssid, - wk->probe_auth.ssid_len, NULL, 0); + wk->probe_auth.ssid_len, NULL, 0, true); wk->timeout = jiffies + IEEE80211_AUTH_TIMEOUT; run_again(local, wk->timeout); diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index 9dc3b5f26e8..7bc8702808f 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -15,6 +15,7 @@ #include <linux/gfp.h> #include <asm/unaligned.h> #include <net/mac80211.h> +#include <crypto/aes.h> #include "ieee80211_i.h" #include "michael.h" @@ -148,13 +149,19 @@ ieee80211_rx_h_michael_mic_verify(struct ieee80211_rx_data *rx) update_iv: /* update IV in key information to be able to detect replays */ - rx->key->u.tkip.rx[rx->queue].iv32 = rx->tkip_iv32; - rx->key->u.tkip.rx[rx->queue].iv16 = rx->tkip_iv16; + rx->key->u.tkip.rx[rx->security_idx].iv32 = rx->tkip_iv32; + rx->key->u.tkip.rx[rx->security_idx].iv16 = rx->tkip_iv16; return RX_CONTINUE; mic_fail: - mac80211_ev_michael_mic_failure(rx->sdata, rx->key->conf.keyidx, + /* + * In some cases the key can be unset - e.g. a multicast packet, in + * a driver that supports HW encryption. Send up the key idx only if + * the key is set. + */ + mac80211_ev_michael_mic_failure(rx->sdata, + rx->key ? rx->key->conf.keyidx : -1, (void *) skb->data, NULL, GFP_ATOMIC); return RX_DROP_UNUSABLE; } @@ -165,6 +172,7 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data; struct ieee80211_key *key = tx->key; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + unsigned long flags; unsigned int hdrlen; int len, tail; u8 *pos; @@ -192,11 +200,12 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) pos += hdrlen; /* Increase IV for the frame */ + spin_lock_irqsave(&key->u.tkip.txlock, flags); key->u.tkip.tx.iv16++; if (key->u.tkip.tx.iv16 == 0) key->u.tkip.tx.iv32++; - - pos = ieee80211_tkip_add_iv(pos, key, key->u.tkip.tx.iv16); + pos = ieee80211_tkip_add_iv(pos, key); + spin_unlock_irqrestore(&key->u.tkip.txlock, flags); /* hwaccel - with software IV */ if (info->control.hw_key) @@ -205,9 +214,8 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) /* Add room for ICV */ skb_put(skb, TKIP_ICV_LEN); - hdr = (struct ieee80211_hdr *) skb->data; return ieee80211_tkip_encrypt_data(tx->local->wep_tx_tfm, - key, pos, len, hdr->addr2); + key, skb, pos, len); } @@ -255,7 +263,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) res = ieee80211_tkip_decrypt_data(rx->local->wep_rx_tfm, key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, - hdr->addr1, hwaccel, rx->queue, + hdr->addr1, hwaccel, rx->security_idx, &rx->tkip_iv32, &rx->tkip_iv16); if (res != TKIP_DECRYPT_OK) @@ -283,8 +291,10 @@ static void ccmp_special_blocks(struct sk_buff *skb, u8 *pn, u8 *scratch, unsigned int hdrlen; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data; - b_0 = scratch + 3 * AES_BLOCK_LEN; - aad = scratch + 4 * AES_BLOCK_LEN; + memset(scratch, 0, 6 * AES_BLOCK_SIZE); + + b_0 = scratch + 3 * AES_BLOCK_SIZE; + aad = scratch + 4 * AES_BLOCK_SIZE; /* * Mask FC: zero subtype b4 b5 b6 (if not mgmt) @@ -373,8 +383,10 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) struct ieee80211_key *key = tx->key; struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); int hdrlen, len, tail; - u8 *pos, *pn; - int i; + u8 *pos; + u8 pn[6]; + u64 pn64; + u8 scratch[6 * AES_BLOCK_SIZE]; if (info->control.hw_key && !(info->control.hw_key->flags & IEEE80211_KEY_FLAG_GENERATE_IV)) { @@ -402,14 +414,14 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) hdr = (struct ieee80211_hdr *) pos; pos += hdrlen; - /* PN = PN + 1 */ - pn = key->u.ccmp.tx_pn; + pn64 = atomic64_inc_return(&key->u.ccmp.tx_pn); - for (i = CCMP_PN_LEN - 1; i >= 0; i--) { - pn[i]++; - if (pn[i]) - break; - } + pn[5] = pn64; + pn[4] = pn64 >> 8; + pn[3] = pn64 >> 16; + pn[2] = pn64 >> 24; + pn[1] = pn64 >> 32; + pn[0] = pn64 >> 40; ccmp_pn2hdr(pos, pn, key->conf.keyidx); @@ -418,8 +430,8 @@ static int ccmp_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) return 0; pos += CCMP_HDR_LEN; - ccmp_special_blocks(skb, pn, key->u.ccmp.tx_crypto_buf, 0); - ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, key->u.ccmp.tx_crypto_buf, pos, len, + ccmp_special_blocks(skb, pn, scratch, 0); + ieee80211_aes_ccm_encrypt(key->u.ccmp.tfm, scratch, pos, len, pos, skb_put(skb, CCMP_MIC_LEN)); return 0; @@ -466,8 +478,7 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) ccmp_hdr2pn(pn, skb->data + hdrlen); - queue = ieee80211_is_mgmt(hdr->frame_control) ? - NUM_RX_DATA_QUEUES : rx->queue; + queue = rx->security_idx; if (memcmp(pn, key->u.ccmp.rx_pn[queue], CCMP_PN_LEN) <= 0) { key->u.ccmp.replays++; @@ -475,11 +486,12 @@ ieee80211_crypto_ccmp_decrypt(struct ieee80211_rx_data *rx) } if (!(status->flag & RX_FLAG_DECRYPTED)) { + u8 scratch[6 * AES_BLOCK_SIZE]; /* hardware didn't decrypt/verify MIC */ - ccmp_special_blocks(skb, pn, key->u.ccmp.rx_crypto_buf, 1); + ccmp_special_blocks(skb, pn, scratch, 1); if (ieee80211_aes_ccm_decrypt( - key->u.ccmp.tfm, key->u.ccmp.rx_crypto_buf, + key->u.ccmp.tfm, scratch, skb->data + hdrlen + CCMP_HDR_LEN, data_len, skb->data + skb->len - CCMP_MIC_LEN, skb->data + hdrlen + CCMP_HDR_LEN)) @@ -510,6 +522,16 @@ static void bip_aad(struct sk_buff *skb, u8 *aad) } +static inline void bip_ipn_set64(u8 *d, u64 pn) +{ + *d++ = pn; + *d++ = pn >> 8; + *d++ = pn >> 16; + *d++ = pn >> 24; + *d++ = pn >> 32; + *d = pn >> 40; +} + static inline void bip_ipn_swap(u8 *d, const u8 *s) { *d++ = s[5]; @@ -528,8 +550,8 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); struct ieee80211_key *key = tx->key; struct ieee80211_mmie *mmie; - u8 *pn, aad[20]; - int i; + u8 aad[20]; + u64 pn64; if (info->control.hw_key) return 0; @@ -543,22 +565,17 @@ ieee80211_crypto_aes_cmac_encrypt(struct ieee80211_tx_data *tx) mmie->key_id = cpu_to_le16(key->conf.keyidx); /* PN = PN + 1 */ - pn = key->u.aes_cmac.tx_pn; + pn64 = atomic64_inc_return(&key->u.aes_cmac.tx_pn); - for (i = sizeof(key->u.aes_cmac.tx_pn) - 1; i >= 0; i--) { - pn[i]++; - if (pn[i]) - break; - } - bip_ipn_swap(mmie->sequence_number, pn); + bip_ipn_set64(mmie->sequence_number, pn64); bip_aad(skb, aad); /* * MIC = AES-128-CMAC(IGTK, AAD || Management Frame Body || MMIE, 64) */ - ieee80211_aes_cmac(key->u.aes_cmac.tfm, key->u.aes_cmac.tx_crypto_buf, - aad, skb->data + 24, skb->len - 24, mmie->mic); + ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, + skb->data + 24, skb->len - 24, mmie->mic); return TX_CONTINUE; } @@ -596,8 +613,7 @@ ieee80211_crypto_aes_cmac_decrypt(struct ieee80211_rx_data *rx) if (!(status->flag & RX_FLAG_DECRYPTED)) { /* hardware didn't decrypt/verify MIC */ bip_aad(skb, aad); - ieee80211_aes_cmac(key->u.aes_cmac.tfm, - key->u.aes_cmac.rx_crypto_buf, aad, + ieee80211_aes_cmac(key->u.aes_cmac.tfm, aad, skb->data + 24, skb->len - 24, mic); if (memcmp(mic, mmie->mic, sizeof(mmie->mic)) != 0) { key->u.aes_cmac.icverrors++; diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig index 2c5b348eb3a..ba36c283d83 100644 --- a/net/netfilter/ipset/Kconfig +++ b/net/netfilter/ipset/Kconfig @@ -109,6 +109,16 @@ config IP_SET_HASH_NETPORT To compile it as a module, choose M here. If unsure, say N. +config IP_SET_HASH_NETIFACE + tristate "hash:net,iface set support" + depends on IP_SET + help + This option adds the hash:net,iface set type support, by which + one can store IPv4/IPv6 network address/prefix and + interface name pairs as elements in a set. + + To compile it as a module, choose M here. If unsure, say N. + config IP_SET_LIST_SET tristate "list:set set support" depends on IP_SET diff --git a/net/netfilter/ipset/Makefile b/net/netfilter/ipset/Makefile index 5adbdab67bd..6e965ecd544 100644 --- a/net/netfilter/ipset/Makefile +++ b/net/netfilter/ipset/Makefile @@ -19,6 +19,7 @@ obj-$(CONFIG_IP_SET_HASH_IPPORTIP) += ip_set_hash_ipportip.o obj-$(CONFIG_IP_SET_HASH_IPPORTNET) += ip_set_hash_ipportnet.o obj-$(CONFIG_IP_SET_HASH_NET) += ip_set_hash_net.o obj-$(CONFIG_IP_SET_HASH_NETPORT) += ip_set_hash_netport.o +obj-$(CONFIG_IP_SET_HASH_NETIFACE) += ip_set_hash_netiface.o # list types obj-$(CONFIG_IP_SET_LIST_SET) += ip_set_list_set.o diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index ba2d16607f4..e3e73997c3b 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -54,7 +54,7 @@ ip_to_id(const struct bitmap_ip *m, u32 ip) } static int -bitmap_ip_test(struct ip_set *set, void *value, u32 timeout) +bitmap_ip_test(struct ip_set *set, void *value, u32 timeout, u32 flags) { const struct bitmap_ip *map = set->data; u16 id = *(u16 *)value; @@ -63,7 +63,7 @@ bitmap_ip_test(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ip_add(struct ip_set *set, void *value, u32 timeout) +bitmap_ip_add(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ip *map = set->data; u16 id = *(u16 *)value; @@ -75,7 +75,7 @@ bitmap_ip_add(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ip_del(struct ip_set *set, void *value, u32 timeout) +bitmap_ip_del(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ip *map = set->data; u16 id = *(u16 *)value; @@ -131,7 +131,7 @@ nla_put_failure: /* Timeout variant */ static int -bitmap_ip_ttest(struct ip_set *set, void *value, u32 timeout) +bitmap_ip_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) { const struct bitmap_ip *map = set->data; const unsigned long *members = map->members; @@ -141,13 +141,13 @@ bitmap_ip_ttest(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ip_tadd(struct ip_set *set, void *value, u32 timeout) +bitmap_ip_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ip *map = set->data; unsigned long *members = map->members; u16 id = *(u16 *)value; - if (ip_set_timeout_test(members[id])) + if (ip_set_timeout_test(members[id]) && !(flags & IPSET_FLAG_EXIST)) return -IPSET_ERR_EXIST; members[id] = ip_set_timeout_set(timeout); @@ -156,7 +156,7 @@ bitmap_ip_tadd(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ip_tdel(struct ip_set *set, void *value, u32 timeout) +bitmap_ip_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ip *map = set->data; unsigned long *members = map->members; @@ -219,24 +219,25 @@ nla_put_failure: static int bitmap_ip_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { struct bitmap_ip *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; u32 ip; - ip = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); + ip = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC)); if (ip < map->first_ip || ip > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; ip = ip_to_id(map, ip); - return adtfn(set, &ip, map->timeout); + return adtfn(set, &ip, opt_timeout(opt, map), opt->cmdflags); } static int bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct bitmap_ip *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -266,7 +267,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST) { id = ip_to_id(map, ip); - return adtfn(set, &id, timeout); + return adtfn(set, &id, timeout, flags); } if (tb[IPSET_ATTR_IP_TO]) { @@ -283,8 +284,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], if (cidr > 32) return -IPSET_ERR_INVALID_CIDR; - ip &= ip_set_hostmask(cidr); - ip_to = ip | ~ip_set_hostmask(cidr); + ip_set_mask_from_to(ip, ip_to, cidr); } else ip_to = ip; @@ -293,7 +293,7 @@ bitmap_ip_uadt(struct ip_set *set, struct nlattr *tb[], for (; !before(ip_to, ip); ip += map->hosts) { id = ip_to_id(map, ip); - ret = adtfn(set, &id, timeout); + ret = adtfn(set, &id, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -478,7 +478,7 @@ bitmap_ip_create(struct ip_set *set, struct nlattr *tb[], u32 flags) if (cidr >= 32) return -IPSET_ERR_INVALID_CIDR; - last_ip = first_ip | ~ip_set_hostmask(cidr); + ip_set_mask_from_to(first_ip, last_ip, cidr); } else return -IPSET_ERR_PROTOCOL; @@ -551,7 +551,8 @@ static struct ip_set_type bitmap_ip_type __read_mostly = { .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, .family = AF_INET, - .revision = 0, + .revision_min = 0, + .revision_max = 0, .create = bitmap_ip_create, .create_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index a274300b6a5..56096f54497 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -99,7 +99,7 @@ bitmap_ipmac_exist(const struct ipmac_telem *elem) /* Base variant */ static int -bitmap_ipmac_test(struct ip_set *set, void *value, u32 timeout) +bitmap_ipmac_test(struct ip_set *set, void *value, u32 timeout, u32 flags) { const struct bitmap_ipmac *map = set->data; const struct ipmac *data = value; @@ -117,7 +117,7 @@ bitmap_ipmac_test(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ipmac_add(struct ip_set *set, void *value, u32 timeout) +bitmap_ipmac_add(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ipmac *map = set->data; const struct ipmac *data = value; @@ -146,7 +146,7 @@ bitmap_ipmac_add(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ipmac_del(struct ip_set *set, void *value, u32 timeout) +bitmap_ipmac_del(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ipmac *map = set->data; const struct ipmac *data = value; @@ -212,7 +212,7 @@ nla_put_failure: /* Timeout variant */ static int -bitmap_ipmac_ttest(struct ip_set *set, void *value, u32 timeout) +bitmap_ipmac_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) { const struct bitmap_ipmac *map = set->data; const struct ipmac *data = value; @@ -231,15 +231,16 @@ bitmap_ipmac_ttest(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ipmac_tadd(struct ip_set *set, void *value, u32 timeout) +bitmap_ipmac_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ipmac *map = set->data; const struct ipmac *data = value; struct ipmac_telem *elem = bitmap_ipmac_elem(map, data->id); + bool flag_exist = flags & IPSET_FLAG_EXIST; switch (elem->match) { case MAC_UNSET: - if (!data->ether) + if (!(data->ether || flag_exist)) /* Already added without ethernet address */ return -IPSET_ERR_EXIST; /* Fill the MAC address and activate the timer */ @@ -251,7 +252,7 @@ bitmap_ipmac_tadd(struct ip_set *set, void *value, u32 timeout) elem->timeout = ip_set_timeout_set(timeout); break; case MAC_FILLED: - if (!bitmap_expired(map, data->id)) + if (!(bitmap_expired(map, data->id) || flag_exist)) return -IPSET_ERR_EXIST; /* Fall through */ case MAC_EMPTY: @@ -273,7 +274,7 @@ bitmap_ipmac_tadd(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_ipmac_tdel(struct ip_set *set, void *value, u32 timeout) +bitmap_ipmac_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_ipmac *map = set->data; const struct ipmac *data = value; @@ -337,17 +338,18 @@ nla_put_failure: static int bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { struct bitmap_ipmac *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct ipmac data; /* MAC can be src only */ - if (!(flags & IPSET_DIM_TWO_SRC)) + if (!(opt->flags & IPSET_DIM_TWO_SRC)) return 0; - data.id = ntohl(ip4addr(skb, flags & IPSET_DIM_ONE_SRC)); + data.id = ntohl(ip4addr(skb, opt->flags & IPSET_DIM_ONE_SRC)); if (data.id < map->first_ip || data.id > map->last_ip) return -IPSET_ERR_BITMAP_RANGE; @@ -359,12 +361,12 @@ bitmap_ipmac_kadt(struct ip_set *set, const struct sk_buff *skb, data.id -= map->first_ip; data.ether = eth_hdr(skb)->h_source; - return adtfn(set, &data, map->timeout); + return adtfn(set, &data, opt_timeout(opt, map), opt->cmdflags); } static int bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct bitmap_ipmac *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -399,7 +401,7 @@ bitmap_ipmac_uadt(struct ip_set *set, struct nlattr *tb[], data.id -= map->first_ip; - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -577,7 +579,7 @@ bitmap_ipmac_create(struct ip_set *set, struct nlattr *tb[], if (cidr >= 32) return -IPSET_ERR_INVALID_CIDR; - last_ip = first_ip | ~ip_set_hostmask(cidr); + ip_set_mask_from_to(first_ip, last_ip, cidr); } else return -IPSET_ERR_PROTOCOL; @@ -622,7 +624,8 @@ static struct ip_set_type bitmap_ipmac_type = { .features = IPSET_TYPE_IP | IPSET_TYPE_MAC, .dimension = IPSET_DIM_TWO, .family = AF_INET, - .revision = 0, + .revision_min = 0, + .revision_max = 0, .create = bitmap_ipmac_create, .create_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, @@ -632,7 +635,8 @@ static struct ip_set_type bitmap_ipmac_type = { }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, - [IPSET_ATTR_ETHER] = { .type = NLA_BINARY, .len = ETH_ALEN }, + [IPSET_ATTR_ETHER] = { .type = NLA_BINARY, + .len = ETH_ALEN }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, }, diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index 6b38eb8f6ed..29ba93bb94b 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -40,7 +40,7 @@ struct bitmap_port { /* Base variant */ static int -bitmap_port_test(struct ip_set *set, void *value, u32 timeout) +bitmap_port_test(struct ip_set *set, void *value, u32 timeout, u32 flags) { const struct bitmap_port *map = set->data; u16 id = *(u16 *)value; @@ -49,7 +49,7 @@ bitmap_port_test(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_port_add(struct ip_set *set, void *value, u32 timeout) +bitmap_port_add(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_port *map = set->data; u16 id = *(u16 *)value; @@ -61,7 +61,7 @@ bitmap_port_add(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_port_del(struct ip_set *set, void *value, u32 timeout) +bitmap_port_del(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_port *map = set->data; u16 id = *(u16 *)value; @@ -119,7 +119,7 @@ nla_put_failure: /* Timeout variant */ static int -bitmap_port_ttest(struct ip_set *set, void *value, u32 timeout) +bitmap_port_ttest(struct ip_set *set, void *value, u32 timeout, u32 flags) { const struct bitmap_port *map = set->data; const unsigned long *members = map->members; @@ -129,13 +129,13 @@ bitmap_port_ttest(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_port_tadd(struct ip_set *set, void *value, u32 timeout) +bitmap_port_tadd(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_port *map = set->data; unsigned long *members = map->members; u16 id = *(u16 *)value; - if (ip_set_timeout_test(members[id])) + if (ip_set_timeout_test(members[id]) && !(flags & IPSET_FLAG_EXIST)) return -IPSET_ERR_EXIST; members[id] = ip_set_timeout_set(timeout); @@ -144,7 +144,7 @@ bitmap_port_tadd(struct ip_set *set, void *value, u32 timeout) } static int -bitmap_port_tdel(struct ip_set *set, void *value, u32 timeout) +bitmap_port_tdel(struct ip_set *set, void *value, u32 timeout, u32 flags) { struct bitmap_port *map = set->data; unsigned long *members = map->members; @@ -208,14 +208,16 @@ nla_put_failure: static int bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { struct bitmap_port *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; __be16 __port; u16 port = 0; - if (!ip_set_get_ip_port(skb, pf, flags & IPSET_DIM_ONE_SRC, &__port)) + if (!ip_set_get_ip_port(skb, opt->family, + opt->flags & IPSET_DIM_ONE_SRC, &__port)) return -EINVAL; port = ntohs(__port); @@ -225,12 +227,12 @@ bitmap_port_kadt(struct ip_set *set, const struct sk_buff *skb, port -= map->first_port; - return adtfn(set, &port, map->timeout); + return adtfn(set, &port, opt_timeout(opt, map), opt->cmdflags); } static int bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct bitmap_port *map = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -259,7 +261,7 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST) { id = port - map->first_port; - return adtfn(set, &id, timeout); + return adtfn(set, &id, timeout, flags); } if (tb[IPSET_ATTR_PORT_TO]) { @@ -277,7 +279,7 @@ bitmap_port_uadt(struct ip_set *set, struct nlattr *tb[], for (; port <= port_to; port++) { id = port - map->first_port; - ret = adtfn(set, &id, timeout); + ret = adtfn(set, &id, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -482,7 +484,8 @@ static struct ip_set_type bitmap_port_type = { .features = IPSET_TYPE_PORT, .dimension = IPSET_DIM_ONE, .family = AF_UNSPEC, - .revision = 0, + .revision_min = 0, + .revision_max = 0, .create = bitmap_port_create, .create_policy = { [IPSET_ATTR_PORT] = { .type = NLA_U16 }, diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 8041befc655..d7e86ef9d23 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -17,10 +17,10 @@ #include <linux/spinlock.h> #include <linux/netlink.h> #include <linux/rculist.h> -#include <linux/version.h> #include <net/netlink.h> #include <linux/netfilter.h> +#include <linux/netfilter/x_tables.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set.h> @@ -70,7 +70,8 @@ find_set_type(const char *name, u8 family, u8 revision) list_for_each_entry_rcu(type, &ip_set_type_list, list) if (STREQ(type->name, name) && (type->family == family || type->family == AF_UNSPEC) && - type->revision == revision) + revision >= type->revision_min && + revision <= type->revision_max) return type; return NULL; } @@ -135,10 +136,10 @@ find_set_type_minmax(const char *name, u8 family, u8 *min, u8 *max) if (STREQ(type->name, name) && (type->family == family || type->family == AF_UNSPEC)) { found = true; - if (type->revision < *min) - *min = type->revision; - if (type->revision > *max) - *max = type->revision; + if (type->revision_min < *min) + *min = type->revision_min; + if (type->revision_max > *max) + *max = type->revision_max; } rcu_read_unlock(); if (found) @@ -159,25 +160,27 @@ ip_set_type_register(struct ip_set_type *type) int ret = 0; if (type->protocol != IPSET_PROTOCOL) { - pr_warning("ip_set type %s, family %s, revision %u uses " + pr_warning("ip_set type %s, family %s, revision %u:%u uses " "wrong protocol version %u (want %u)\n", type->name, family_name(type->family), - type->revision, type->protocol, IPSET_PROTOCOL); + type->revision_min, type->revision_max, + type->protocol, IPSET_PROTOCOL); return -EINVAL; } ip_set_type_lock(); - if (find_set_type(type->name, type->family, type->revision)) { + if (find_set_type(type->name, type->family, type->revision_min)) { /* Duplicate! */ - pr_warning("ip_set type %s, family %s, revision %u " + pr_warning("ip_set type %s, family %s with revision min %u " "already registered!\n", type->name, - family_name(type->family), type->revision); + family_name(type->family), type->revision_min); ret = -EINVAL; goto unlock; } list_add_rcu(&type->list, &ip_set_type_list); - pr_debug("type %s, family %s, revision %u registered.\n", - type->name, family_name(type->family), type->revision); + pr_debug("type %s, family %s, revision %u:%u registered.\n", + type->name, family_name(type->family), + type->revision_min, type->revision_max); unlock: ip_set_type_unlock(); return ret; @@ -189,15 +192,15 @@ void ip_set_type_unregister(struct ip_set_type *type) { ip_set_type_lock(); - if (!find_set_type(type->name, type->family, type->revision)) { - pr_warning("ip_set type %s, family %s, revision %u " + if (!find_set_type(type->name, type->family, type->revision_min)) { + pr_warning("ip_set type %s, family %s with revision min %u " "not registered\n", type->name, - family_name(type->family), type->revision); + family_name(type->family), type->revision_min); goto unlock; } list_del_rcu(&type->list); - pr_debug("type %s, family %s, revision %u unregistered.\n", - type->name, family_name(type->family), type->revision); + pr_debug("type %s, family %s with revision min %u unregistered.\n", + type->name, family_name(type->family), type->revision_min); unlock: ip_set_type_unlock(); @@ -325,7 +328,8 @@ __ip_set_put(ip_set_id_t index) int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, - u8 family, u8 dim, u8 flags) + const struct xt_action_param *par, + const struct ip_set_adt_opt *opt) { struct ip_set *set = ip_set_list[index]; int ret = 0; @@ -333,19 +337,19 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); - if (dim < set->type->dimension || - !(family == set->family || set->family == AF_UNSPEC)) + if (opt->dim < set->type->dimension || + !(opt->family == set->family || set->family == AF_UNSPEC)) return 0; read_lock_bh(&set->lock); - ret = set->variant->kadt(set, skb, IPSET_TEST, family, dim, flags); + ret = set->variant->kadt(set, skb, par, IPSET_TEST, opt); read_unlock_bh(&set->lock); if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be competed, ADD is triggered\n"); write_lock_bh(&set->lock); - set->variant->kadt(set, skb, IPSET_ADD, family, dim, flags); + set->variant->kadt(set, skb, par, IPSET_ADD, opt); write_unlock_bh(&set->lock); ret = 1; } @@ -357,7 +361,8 @@ EXPORT_SYMBOL_GPL(ip_set_test); int ip_set_add(ip_set_id_t index, const struct sk_buff *skb, - u8 family, u8 dim, u8 flags) + const struct xt_action_param *par, + const struct ip_set_adt_opt *opt) { struct ip_set *set = ip_set_list[index]; int ret; @@ -365,12 +370,12 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); - if (dim < set->type->dimension || - !(family == set->family || set->family == AF_UNSPEC)) + if (opt->dim < set->type->dimension || + !(opt->family == set->family || set->family == AF_UNSPEC)) return 0; write_lock_bh(&set->lock); - ret = set->variant->kadt(set, skb, IPSET_ADD, family, dim, flags); + ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); write_unlock_bh(&set->lock); return ret; @@ -379,7 +384,8 @@ EXPORT_SYMBOL_GPL(ip_set_add); int ip_set_del(ip_set_id_t index, const struct sk_buff *skb, - u8 family, u8 dim, u8 flags) + const struct xt_action_param *par, + const struct ip_set_adt_opt *opt) { struct ip_set *set = ip_set_list[index]; int ret = 0; @@ -387,12 +393,12 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, BUG_ON(set == NULL); pr_debug("set %s, index %u\n", set->name, index); - if (dim < set->type->dimension || - !(family == set->family || set->family == AF_UNSPEC)) + if (opt->dim < set->type->dimension || + !(opt->family == set->family || set->family == AF_UNSPEC)) return 0; write_lock_bh(&set->lock); - ret = set->variant->kadt(set, skb, IPSET_DEL, family, dim, flags); + ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); write_unlock_bh(&set->lock); return ret; @@ -656,6 +662,7 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, rwlock_init(&set->lock); strlcpy(set->name, name, IPSET_MAXNAMELEN); set->family = family; + set->revision = revision; /* * Next, check that we know the type, and take @@ -675,8 +682,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, if (attr[IPSET_ATTR_DATA] && nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy)) { - ret = -IPSET_ERR_PROTOCOL; - goto put_out; + ret = -IPSET_ERR_PROTOCOL; + goto put_out; } ret = set->type->create(set, tb, flags); @@ -696,7 +703,8 @@ ip_set_create(struct sock *ctnl, struct sk_buff *skb, (flags & IPSET_FLAG_EXIST) && STREQ(set->type->name, clash->type->name) && set->type->family == clash->type->family && - set->type->revision == clash->type->revision && + set->type->revision_min == clash->type->revision_min && + set->type->revision_max == clash->type->revision_max && set->variant->same_set(set, clash)) ret = 0; goto cleanup; @@ -767,7 +775,7 @@ ip_set_destroy(struct sock *ctnl, struct sk_buff *skb, if (!attr[IPSET_ATTR_SETNAME]) { for (i = 0; i < ip_set_max; i++) { if (ip_set_list[i] != NULL && ip_set_list[i]->ref) { - ret = IPSET_ERR_BUSY; + ret = -IPSET_ERR_BUSY; goto out; } } @@ -939,10 +947,13 @@ ip_set_swap(struct sock *ctnl, struct sk_buff *skb, /* List/save set data */ -#define DUMP_INIT 0L -#define DUMP_ALL 1L -#define DUMP_ONE 2L -#define DUMP_LAST 3L +#define DUMP_INIT 0 +#define DUMP_ALL 1 +#define DUMP_ONE 2 +#define DUMP_LAST 3 + +#define DUMP_TYPE(arg) (((u32)(arg)) & 0x0000FFFF) +#define DUMP_FLAGS(arg) (((u32)(arg)) >> 16) static int ip_set_dump_done(struct netlink_callback *cb) @@ -973,6 +984,7 @@ dump_init(struct netlink_callback *cb) int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg)); struct nlattr *cda[IPSET_ATTR_CMD_MAX+1]; struct nlattr *attr = (void *)nlh + min_len; + u32 dump_type; ip_set_id_t index; /* Second pass, so parser can't fail */ @@ -984,17 +996,22 @@ dump_init(struct netlink_callback *cb) * [..]: type specific */ - if (!cda[IPSET_ATTR_SETNAME]) { - cb->args[0] = DUMP_ALL; - return 0; - } + if (cda[IPSET_ATTR_SETNAME]) { + index = find_set_id(nla_data(cda[IPSET_ATTR_SETNAME])); + if (index == IPSET_INVALID_ID) + return -ENOENT; - index = find_set_id(nla_data(cda[IPSET_ATTR_SETNAME])); - if (index == IPSET_INVALID_ID) - return -ENOENT; + dump_type = DUMP_ONE; + cb->args[1] = index; + } else + dump_type = DUMP_ALL; + + if (cda[IPSET_ATTR_FLAGS]) { + u32 f = ip_set_get_h32(cda[IPSET_ATTR_FLAGS]); + dump_type |= (f << 16); + } + cb->args[0] = dump_type; - cb->args[0] = DUMP_ONE; - cb->args[1] = index; return 0; } @@ -1005,9 +1022,10 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) struct ip_set *set = NULL; struct nlmsghdr *nlh = NULL; unsigned int flags = NETLINK_CB(cb->skb).pid ? NLM_F_MULTI : 0; + u32 dump_type, dump_flags; int ret = 0; - if (cb->args[0] == DUMP_INIT) { + if (!cb->args[0]) { ret = dump_init(cb); if (ret < 0) { nlh = nlmsg_hdr(cb->skb); @@ -1022,14 +1040,17 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) if (cb->args[1] >= ip_set_max) goto out; - max = cb->args[0] == DUMP_ONE ? cb->args[1] + 1 : ip_set_max; + dump_type = DUMP_TYPE(cb->args[0]); + dump_flags = DUMP_FLAGS(cb->args[0]); + max = dump_type == DUMP_ONE ? cb->args[1] + 1 : ip_set_max; dump_last: - pr_debug("args[0]: %ld args[1]: %ld\n", cb->args[0], cb->args[1]); + pr_debug("args[0]: %u %u args[1]: %ld\n", + dump_type, dump_flags, cb->args[1]); for (; cb->args[1] < max; cb->args[1]++) { index = (ip_set_id_t) cb->args[1]; set = ip_set_list[index]; if (set == NULL) { - if (cb->args[0] == DUMP_ONE) { + if (dump_type == DUMP_ONE) { ret = -ENOENT; goto out; } @@ -1038,8 +1059,8 @@ dump_last: /* When dumping all sets, we must dump "sorted" * so that lists (unions of sets) are dumped last. */ - if (cb->args[0] != DUMP_ONE && - ((cb->args[0] == DUMP_ALL) == + if (dump_type != DUMP_ONE && + ((dump_type == DUMP_ALL) == !!(set->type->features & IPSET_DUMP_LAST))) continue; pr_debug("List set: %s\n", set->name); @@ -1057,6 +1078,8 @@ dump_last: } NLA_PUT_U8(skb, IPSET_ATTR_PROTOCOL, IPSET_PROTOCOL); NLA_PUT_STRING(skb, IPSET_ATTR_SETNAME, set->name); + if (dump_flags & IPSET_FLAG_LIST_SETNAME) + goto next_set; switch (cb->args[2]) { case 0: /* Core header data */ @@ -1065,28 +1088,27 @@ dump_last: NLA_PUT_U8(skb, IPSET_ATTR_FAMILY, set->family); NLA_PUT_U8(skb, IPSET_ATTR_REVISION, - set->type->revision); + set->revision); ret = set->variant->head(set, skb); if (ret < 0) goto release_refcount; + if (dump_flags & IPSET_FLAG_LIST_HEADER) + goto next_set; /* Fall through and add elements */ default: read_lock_bh(&set->lock); ret = set->variant->list(set, skb, cb); read_unlock_bh(&set->lock); - if (!cb->args[2]) { + if (!cb->args[2]) /* Set is done, proceed with next one */ - if (cb->args[0] == DUMP_ONE) - cb->args[1] = IPSET_INVALID_ID; - else - cb->args[1]++; - } + goto next_set; goto release_refcount; } } /* If we dump all sets, continue with dumping last ones */ - if (cb->args[0] == DUMP_ALL) { - cb->args[0] = DUMP_LAST; + if (dump_type == DUMP_ALL) { + dump_type = DUMP_LAST; + cb->args[0] = dump_type | (dump_flags << 16); cb->args[1] = 0; goto dump_last; } @@ -1094,6 +1116,11 @@ dump_last: nla_put_failure: ret = -EFAULT; +next_set: + if (dump_type == DUMP_ONE) + cb->args[1] = IPSET_INVALID_ID; + else + cb->args[1]++; release_refcount: /* If there was an error or set is done, release set */ if (ret || !cb->args[2]) { @@ -1120,7 +1147,7 @@ ip_set_dump(struct sock *ctnl, struct sk_buff *skb, return netlink_dump_start(ctnl, skb, nlh, ip_set_dump_start, - ip_set_dump_done); + ip_set_dump_done, 0); } /* Add, del and test */ @@ -1139,17 +1166,18 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, struct nlattr *tb[], enum ipset_adt adt, u32 flags, bool use_lineno) { - int ret, retried = 0; + int ret; u32 lineno = 0; - bool eexist = flags & IPSET_FLAG_EXIST; + bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { write_lock_bh(&set->lock); - ret = set->variant->uadt(set, tb, adt, &lineno, flags); + ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); write_unlock_bh(&set->lock); + retried = true; } while (ret == -EAGAIN && set->variant->resize && - (ret = set->variant->resize(set, retried++)) == 0); + (ret = set->variant->resize(set, retried)) == 0); if (!ret || (ret == -IPSET_ERR_EXIST && eexist)) return 0; @@ -1322,7 +1350,7 @@ ip_set_utest(struct sock *ctnl, struct sk_buff *skb, return -IPSET_ERR_PROTOCOL; read_lock_bh(&set->lock); - ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0); + ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0, 0); read_unlock_bh(&set->lock); /* Userspace can't trigger element to be re-added */ if (ret == -EAGAIN) @@ -1365,7 +1393,7 @@ ip_set_header(struct sock *ctnl, struct sk_buff *skb, NLA_PUT_STRING(skb2, IPSET_ATTR_SETNAME, set->name); NLA_PUT_STRING(skb2, IPSET_ATTR_TYPENAME, set->type->name); NLA_PUT_U8(skb2, IPSET_ATTR_FAMILY, set->family); - NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, set->type->revision); + NLA_PUT_U8(skb2, IPSET_ATTR_REVISION, set->revision); nlmsg_end(skb2, nlh2); ret = netlink_unicast(ctnl, skb2, NETLINK_CB(skb).pid, MSG_DONTWAIT); diff --git a/net/netfilter/ipset/ip_set_hash_ip.c b/net/netfilter/ipset/ip_set_hash_ip.c index 43bcce20012..f2d576e6b76 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -53,7 +53,8 @@ struct hash_ip4_telem { static inline bool hash_ip4_data_equal(const struct hash_ip4_elem *ip1, - const struct hash_ip4_elem *ip2) + const struct hash_ip4_elem *ip2, + u32 *multi) { return ip1->ip == ip2->ip; } @@ -108,25 +109,32 @@ nla_put_failure: #define HOST_MASK 32 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ip4_data_next(struct ip_set_hash *h, const struct hash_ip4_elem *d) +{ + h->next.ip = ntohl(d->ip); +} + static int hash_ip4_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; __be32 ip; - ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &ip); + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip); ip &= ip_set_netmask(h->netmask); if (ip == 0) return -EINVAL; - return adtfn(set, &ip, h->timeout); + return adtfn(set, &ip, opt_timeout(opt, h), opt->cmdflags); } static int hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -157,7 +165,7 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], nip = htonl(ip); if (nip == 0) return -IPSET_ERR_HASH_ELEM; - return adtfn(set, &nip, timeout); + return adtfn(set, &nip, timeout, flags); } if (tb[IPSET_ATTR_IP_TO]) { @@ -171,18 +179,19 @@ hash_ip4_uadt(struct ip_set *set, struct nlattr *tb[], if (cidr > 32) return -IPSET_ERR_INVALID_CIDR; - ip &= ip_set_hostmask(cidr); - ip_to = ip | ~ip_set_hostmask(cidr); + ip_set_mask_from_to(ip, ip_to, cidr); } else ip_to = ip; hosts = h->netmask == 32 ? 1 : 2 << (32 - h->netmask - 1); + if (retried) + ip = h->next.ip; for (; !before(ip_to, ip); ip += hosts) { nip = htonl(ip); if (nip == 0) return -IPSET_ERR_HASH_ELEM; - ret = adtfn(set, &nip, timeout); + ret = adtfn(set, &nip, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -217,7 +226,8 @@ struct hash_ip6_telem { static inline bool hash_ip6_data_equal(const struct hash_ip6_elem *ip1, - const struct hash_ip6_elem *ip2) + const struct hash_ip6_elem *ip2, + u32 *multi) { return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0; } @@ -281,20 +291,26 @@ nla_put_failure: #define HOST_MASK 128 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ip6_data_next(struct ip_set_hash *h, const struct hash_ip6_elem *d) +{ +} + static int hash_ip6_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; union nf_inet_addr ip; - ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &ip.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &ip.in6); ip6_netmask(&ip, h->netmask); if (ipv6_addr_any(&ip.in6)) return -EINVAL; - return adtfn(set, &ip, h->timeout); + return adtfn(set, &ip, opt_timeout(opt, h), opt->cmdflags); } static const struct nla_policy hash_ip6_adt_policy[IPSET_ATTR_ADT_MAX + 1] = { @@ -305,7 +321,7 @@ static const struct nla_policy hash_ip6_adt_policy[IPSET_ATTR_ADT_MAX + 1] = { static int hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -336,7 +352,7 @@ hash_ip6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - ret = adtfn(set, &ip, timeout); + ret = adtfn(set, &ip, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -428,7 +444,8 @@ static struct ip_set_type hash_ip_type __read_mostly = { .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, .family = AF_UNSPEC, - .revision = 0, + .revision_min = 0, + .revision_max = 0, .create = hash_ip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipport.c b/net/netfilter/ipset/ip_set_hash_ipport.c index 14281b6b807..6ee10f5d59b 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -60,7 +60,8 @@ struct hash_ipport4_telem { static inline bool hash_ipport4_data_equal(const struct hash_ipport4_elem *ip1, - const struct hash_ipport4_elem *ip2) + const struct hash_ipport4_elem *ip2, + u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && @@ -124,31 +125,40 @@ nla_put_failure: #define HOST_MASK 32 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ipport4_data_next(struct ip_set_hash *h, + const struct hash_ipport4_elem *d) +{ + h->next.ip = ntohl(d->ip); + h->next.port = ntohs(d->port); +} + static int hash_ipport4_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem data = { }; - if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport4_elem data = { }; - u32 ip, ip_to, p, port, port_to; + u32 ip, ip_to, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; @@ -192,7 +202,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -208,8 +218,7 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], if (cidr > 32) return -IPSET_ERR_INVALID_CIDR; - ip &= ip_set_hostmask(cidr); - ip_to = ip | ~ip_set_hostmask(cidr); + ip_set_mask_from_to(ip, ip_to, cidr); } else ip_to = ip; @@ -220,17 +229,21 @@ hash_ipport4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - for (; !before(ip_to, ip); ip++) - for (p = port; p <= port_to; p++) { + if (retried) + ip = h->next.ip; + for (; !before(ip_to, ip); ip++) { + p = retried && ip == h->next.ip ? h->next.port : port; + for (; p <= port_to; p++) { data.ip = htonl(ip); data.port = htons(p); - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; else ret = 0; } + } return ret; } @@ -264,7 +277,8 @@ struct hash_ipport6_telem { static inline bool hash_ipport6_data_equal(const struct hash_ipport6_elem *ip1, - const struct hash_ipport6_elem *ip2) + const struct hash_ipport6_elem *ip2, + u32 *multi) { return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && ip1->port == ip2->port && @@ -328,26 +342,34 @@ nla_put_failure: #define HOST_MASK 128 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ipport6_data_next(struct ip_set_hash *h, + const struct hash_ipport6_elem *d) +{ + h->next.port = ntohs(d->port); +} + static int hash_ipport6_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipport6_elem data = { }; - if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -396,7 +418,7 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -405,9 +427,11 @@ hash_ipport6_uadt(struct ip_set *set, struct nlattr *tb[], if (port > port_to) swap(port, port_to); + if (retried) + port = h->next.port; for (; port <= port_to; port++) { data.port = htons(port); - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -491,7 +515,8 @@ static struct ip_set_type hash_ipport_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = AF_UNSPEC, - .revision = 1, + .revision_min = 0, + .revision_max = 1, /* SCTP and UDPLITE support added */ .create = hash_ipport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportip.c b/net/netfilter/ipset/ip_set_hash_ipportip.c index 401c8a2531d..fb90e344e90 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -62,7 +62,8 @@ struct hash_ipportip4_telem { static inline bool hash_ipportip4_data_equal(const struct hash_ipportip4_elem *ip1, - const struct hash_ipportip4_elem *ip2) + const struct hash_ipportip4_elem *ip2, + u32 *multi) { return ip1->ip == ip2->ip && ip1->ip2 == ip2->ip2 && @@ -127,32 +128,41 @@ nla_put_failure: #define HOST_MASK 32 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ipportip4_data_next(struct ip_set_hash *h, + const struct hash_ipportip4_elem *d) +{ + h->next.ip = ntohl(d->ip); + h->next.port = ntohs(d->port); +} + static int hash_ipportip4_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem data = { }; - if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); - ip4addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2); + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip4_elem data = { }; - u32 ip, ip_to, p, port, port_to; + u32 ip, ip_to, p = 0, port, port_to; u32 timeout = h->timeout; bool with_ports = false; int ret; @@ -200,7 +210,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (adt == IPSET_TEST || !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_PORT_TO])) { - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -216,8 +226,7 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], if (cidr > 32) return -IPSET_ERR_INVALID_CIDR; - ip &= ip_set_hostmask(cidr); - ip_to = ip | ~ip_set_hostmask(cidr); + ip_set_mask_from_to(ip, ip_to, cidr); } else ip_to = ip; @@ -228,17 +237,21 @@ hash_ipportip4_uadt(struct ip_set *set, struct nlattr *tb[], swap(port, port_to); } - for (; !before(ip_to, ip); ip++) - for (p = port; p <= port_to; p++) { + if (retried) + ip = h->next.ip; + for (; !before(ip_to, ip); ip++) { + p = retried && ip == h->next.ip ? h->next.port : port; + for (; p <= port_to; p++) { data.ip = htonl(ip); data.port = htons(p); - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; else ret = 0; } + } return ret; } @@ -274,7 +287,8 @@ struct hash_ipportip6_telem { static inline bool hash_ipportip6_data_equal(const struct hash_ipportip6_elem *ip1, - const struct hash_ipportip6_elem *ip2) + const struct hash_ipportip6_elem *ip2, + u32 *multi) { return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && @@ -341,27 +355,35 @@ nla_put_failure: #define HOST_MASK 128 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ipportip6_data_next(struct ip_set_hash *h, + const struct hash_ipportip6_elem *d) +{ + h->next.port = ntohs(d->port); +} + static int hash_ipportip6_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportip6_elem data = { }; - if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); - ip6addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -414,7 +436,7 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -423,9 +445,11 @@ hash_ipportip6_uadt(struct ip_set *set, struct nlattr *tb[], if (port > port_to) swap(port, port_to); + if (retried) + port = h->next.port; for (; port <= port_to; port++) { data.port = htons(port); - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -509,7 +533,8 @@ static struct ip_set_type hash_ipportip_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = AF_UNSPEC, - .revision = 1, + .revision_min = 0, + .revision_max = 1, /* SCTP and UDPLITE support added */ .create = hash_ipportip_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index 4743e540252..deb3e3dfa5f 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -62,7 +62,8 @@ struct hash_ipportnet4_telem { static inline bool hash_ipportnet4_data_equal(const struct hash_ipportnet4_elem *ip1, - const struct hash_ipportnet4_elem *ip2) + const struct hash_ipportnet4_elem *ip2, + u32 *multi) { return ip1->ip == ip2->ip && ip1->ip2 == ip2->ip2 && @@ -140,39 +141,51 @@ nla_put_failure: #define HOST_MASK 32 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ipportnet4_data_next(struct ip_set_hash *h, + const struct hash_ipportnet4_elem *d) +{ + h->next.ip = ntohl(d->ip); + h->next.port = ntohs(d->port); + h->next.ip2 = ntohl(d->ip2); +} + static int hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_ipportnet4_elem data = - { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_ipportnet4_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) data.cidr = HOST_MASK; - if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); - ip4addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2); + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2); data.ip2 &= ip_set_netmask(data.cidr); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_ipportnet4_elem data = { .cidr = HOST_MASK }; - u32 ip, ip_to, p, port, port_to; + u32 ip, ip_to, p = 0, port, port_to; + u32 ip2_from = 0, ip2_to, ip2_last, ip2; u32 timeout = h->timeout; bool with_ports = false; int ret; @@ -186,21 +199,19 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP2], &data.ip2); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2], &ip2_from); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR2]) + if (tb[IPSET_ATTR_CIDR2]) { data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR2]); - - if (!data.cidr) - return -IPSET_ERR_INVALID_CIDR; - - data.ip2 &= ip_set_netmask(data.cidr); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + } if (tb[IPSET_ATTR_PORT]) data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); @@ -225,14 +236,16 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; if (adt == IPSET_TEST || - !(tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR] || - tb[IPSET_ATTR_PORT_TO])) { - ret = adtfn(set, &data, timeout); + !(tb[IPSET_ATTR_CIDR] || tb[IPSET_ATTR_IP_TO] || with_ports || + tb[IPSET_ATTR_IP2_TO])) { + data.ip = htonl(ip); + data.ip2 = htonl(ip2_from & ip_set_hostmask(data.cidr)); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } - ip = ntohl(data.ip); if (tb[IPSET_ATTR_IP_TO]) { ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); if (ret) @@ -244,29 +257,50 @@ hash_ipportnet4_uadt(struct ip_set *set, struct nlattr *tb[], if (cidr > 32) return -IPSET_ERR_INVALID_CIDR; - ip &= ip_set_hostmask(cidr); - ip_to = ip | ~ip_set_hostmask(cidr); - } else - ip_to = ip; + ip_set_mask_from_to(ip, ip_to, cidr); + } port_to = port = ntohs(data.port); - if (with_ports && tb[IPSET_ATTR_PORT_TO]) { + if (tb[IPSET_ATTR_PORT_TO]) { port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); if (port > port_to) swap(port, port_to); } + if (tb[IPSET_ATTR_IP2_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP2_TO], &ip2_to); + if (ret) + return ret; + if (ip2_from > ip2_to) + swap(ip2_from, ip2_to); + if (ip2_from + UINT_MAX == ip2_to) + return -IPSET_ERR_HASH_RANGE; + } else { + ip_set_mask_from_to(ip2_from, ip2_to, data.cidr); + } - for (; !before(ip_to, ip); ip++) - for (p = port; p <= port_to; p++) { - data.ip = htonl(ip); + if (retried) + ip = h->next.ip; + for (; !before(ip_to, ip); ip++) { + data.ip = htonl(ip); + p = retried && ip == h->next.ip ? h->next.port : port; + for (; p <= port_to; p++) { data.port = htons(p); - ret = adtfn(set, &data, timeout); - - if (ret && !ip_set_eexist(ret, flags)) - return ret; - else - ret = 0; + ip2 = retried && ip == h->next.ip && p == h->next.port + ? h->next.ip2 : ip2_from; + while (!after(ip2, ip2_to)) { + data.ip2 = htonl(ip2); + ip2_last = ip_set_range_to_cidr(ip2, ip2_to, + &data.cidr); + ret = adtfn(set, &data, timeout, flags); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + ip2 = ip2_last + 1; + } } + } return ret; } @@ -302,7 +336,8 @@ struct hash_ipportnet6_telem { static inline bool hash_ipportnet6_data_equal(const struct hash_ipportnet6_elem *ip1, - const struct hash_ipportnet6_elem *ip2) + const struct hash_ipportnet6_elem *ip2, + u32 *multi) { return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && ipv6_addr_cmp(&ip1->ip2.in6, &ip2->ip2.in6) == 0 && @@ -388,34 +423,43 @@ nla_put_failure: #define HOST_MASK 128 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_ipportnet6_data_next(struct ip_set_hash *h, + const struct hash_ipportnet6_elem *d) +{ + h->next.port = ntohs(d->port); +} + static int hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_ipportnet6_elem data = - { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_ipportnet6_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) data.cidr = HOST_MASK; - if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); - ip6addrptr(skb, flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_THREE_SRC, &data.ip2.in6); ip6_netmask(&data.ip2, data.cidr); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -432,6 +476,8 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], tb[IPSET_ATTR_IP_TO] || tb[IPSET_ATTR_CIDR])) return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); @@ -476,7 +522,7 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -485,9 +531,11 @@ hash_ipportnet6_uadt(struct ip_set *set, struct nlattr *tb[], if (port > port_to) swap(port, port_to); + if (retried) + port = h->next.port; for (; port <= port_to; port++) { data.port = htons(port); - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -574,7 +622,9 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT | IPSET_TYPE_IP2, .dimension = IPSET_DIM_THREE, .family = AF_UNSPEC, - .revision = 1, + .revision_min = 0, + /* 1 SCTP and UDPLITE support added */ + .revision_max = 2, /* Range as input support for IPv4 added */ .create = hash_ipportnet_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, @@ -587,6 +637,7 @@ static struct ip_set_type hash_ipportnet_type __read_mostly = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_IP2] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP2_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index c4db202b7da..60d016541c5 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -58,7 +58,8 @@ struct hash_net4_telem { static inline bool hash_net4_data_equal(const struct hash_net4_elem *ip1, - const struct hash_net4_elem *ip2) + const struct hash_net4_elem *ip2, + u32 *multi) { return ip1->ip == ip2->ip && ip1->cidr == ip2->cidr; } @@ -125,33 +126,44 @@ nla_put_failure: #define HOST_MASK 32 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_net4_data_next(struct ip_set_hash *h, + const struct hash_net4_elem *d) +{ + h->next.ip = ntohl(d->ip); +} + static int hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_net4_elem data = { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_net4_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) data.cidr = HOST_MASK; - ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); data.ip &= ip_set_netmask(data.cidr); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_net4_elem data = { .cidr = HOST_MASK }; u32 timeout = h->timeout; + u32 ip = 0, ip_to, last; int ret; if (unlikely(!tb[IPSET_ATTR_IP] || @@ -161,17 +173,15 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) + if (tb[IPSET_ATTR_CIDR]) { data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - - if (!data.cidr) - return -IPSET_ERR_INVALID_CIDR; - - data.ip &= ip_set_netmask(data.cidr); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + } if (tb[IPSET_ATTR_TIMEOUT]) { if (!with_timeout(h->timeout)) @@ -179,9 +189,35 @@ hash_net4_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - ret = adtfn(set, &data, timeout); + if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { + data.ip = htonl(ip & ip_set_hostmask(data.cidr)); + ret = adtfn(set, &data, timeout, flags); + return ip_set_eexist(ret, flags) ? 0 : ret; + } - return ip_set_eexist(ret, flags) ? 0 : ret; + ip_to = ip; + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip_to < ip) + swap(ip, ip_to); + if (ip + UINT_MAX == ip_to) + return -IPSET_ERR_HASH_RANGE; + } + if (retried) + ip = h->next.ip; + while (!after(ip, ip_to)) { + data.ip = htonl(ip); + last = ip_set_range_to_cidr(ip, ip_to, &data.cidr); + ret = adtfn(set, &data, timeout, flags); + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + ip = last + 1; + } + return ret; } static bool @@ -214,7 +250,8 @@ struct hash_net6_telem { static inline bool hash_net6_data_equal(const struct hash_net6_elem *ip1, - const struct hash_net6_elem *ip2) + const struct hash_net6_elem *ip2, + u32 *multi) { return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && ip1->cidr == ip2->cidr; @@ -290,28 +327,37 @@ nla_put_failure: #define HOST_MASK 128 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_net6_data_next(struct ip_set_hash *h, + const struct hash_net6_elem *d) +{ +} + static int hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; - struct hash_net6_elem data = { .cidr = h->nets[0].cidr || HOST_MASK }; + struct hash_net6_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) data.cidr = HOST_MASK; - ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); ip6_netmask(&data.ip, data.cidr); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -322,6 +368,8 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], if (unlikely(!tb[IPSET_ATTR_IP] || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); @@ -344,7 +392,7 @@ hash_net6_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -425,7 +473,8 @@ static struct ip_set_type hash_net_type __read_mostly = { .features = IPSET_TYPE_IP, .dimension = IPSET_DIM_ONE, .family = AF_UNSPEC, - .revision = 0, + .revision_min = 0, + .revision_max = 1, /* Range as input support for IPv4 added */ .create = hash_net_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, @@ -436,6 +485,7 @@ static struct ip_set_type hash_net_type __read_mostly = { }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, }, diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c new file mode 100644 index 00000000000..e13095deb50 --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -0,0 +1,786 @@ +/* Copyright (C) 2011 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu> + * + * 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. + */ + +/* Kernel module implementing an IP set type: the hash:net,iface type */ + +#include <linux/jhash.h> +#include <linux/module.h> +#include <linux/ip.h> +#include <linux/skbuff.h> +#include <linux/errno.h> +#include <linux/random.h> +#include <linux/rbtree.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/netlink.h> + +#include <linux/netfilter.h> +#include <linux/netfilter/ipset/pfxlen.h> +#include <linux/netfilter/ipset/ip_set.h> +#include <linux/netfilter/ipset/ip_set_timeout.h> +#include <linux/netfilter/ipset/ip_set_hash.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>"); +MODULE_DESCRIPTION("hash:net,iface type of IP sets"); +MODULE_ALIAS("ip_set_hash:net,iface"); + +/* Interface name rbtree */ + +struct iface_node { + struct rb_node node; + char iface[IFNAMSIZ]; +}; + +#define iface_data(n) (rb_entry(n, struct iface_node, node)->iface) + +static inline long +ifname_compare(const char *_a, const char *_b) +{ + const long *a = (const long *)_a; + const long *b = (const long *)_b; + + BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); + if (a[0] != b[0]) + return a[0] - b[0]; + if (IFNAMSIZ > sizeof(long)) { + if (a[1] != b[1]) + return a[1] - b[1]; + } + if (IFNAMSIZ > 2 * sizeof(long)) { + if (a[2] != b[2]) + return a[2] - b[2]; + } + if (IFNAMSIZ > 3 * sizeof(long)) { + if (a[3] != b[3]) + return a[3] - b[3]; + } + return 0; +} + +static void +rbtree_destroy(struct rb_root *root) +{ + struct rb_node *p, *n = root->rb_node; + struct iface_node *node; + + /* Non-recursive destroy, like in ext3 */ + while (n) { + if (n->rb_left) { + n = n->rb_left; + continue; + } + if (n->rb_right) { + n = n->rb_right; + continue; + } + p = rb_parent(n); + node = rb_entry(n, struct iface_node, node); + if (!p) + *root = RB_ROOT; + else if (p->rb_left == n) + p->rb_left = NULL; + else if (p->rb_right == n) + p->rb_right = NULL; + + kfree(node); + n = p; + } +} + +static int +iface_test(struct rb_root *root, const char **iface) +{ + struct rb_node *n = root->rb_node; + + while (n) { + const char *d = iface_data(n); + long res = ifname_compare(*iface, d); + + if (res < 0) + n = n->rb_left; + else if (res > 0) + n = n->rb_right; + else { + *iface = d; + return 1; + } + } + return 0; +} + +static int +iface_add(struct rb_root *root, const char **iface) +{ + struct rb_node **n = &(root->rb_node), *p = NULL; + struct iface_node *d; + + while (*n) { + char *ifname = iface_data(*n); + long res = ifname_compare(*iface, ifname); + + p = *n; + if (res < 0) + n = &((*n)->rb_left); + else if (res > 0) + n = &((*n)->rb_right); + else { + *iface = ifname; + return 0; + } + } + + d = kzalloc(sizeof(*d), GFP_ATOMIC); + if (!d) + return -ENOMEM; + strcpy(d->iface, *iface); + + rb_link_node(&d->node, p, n); + rb_insert_color(&d->node, root); + + *iface = d->iface; + return 0; +} + +/* Type specific function prefix */ +#define TYPE hash_netiface + +static bool +hash_netiface_same_set(const struct ip_set *a, const struct ip_set *b); + +#define hash_netiface4_same_set hash_netiface_same_set +#define hash_netiface6_same_set hash_netiface_same_set + +#define STREQ(a, b) (strcmp(a, b) == 0) + +/* The type variant functions: IPv4 */ + +struct hash_netiface4_elem_hashed { + __be32 ip; + u8 physdev; + u8 cidr; + u16 padding; +}; + +#define HKEY_DATALEN sizeof(struct hash_netiface4_elem_hashed) + +/* Member elements without timeout */ +struct hash_netiface4_elem { + __be32 ip; + u8 physdev; + u8 cidr; + u16 padding; + const char *iface; +}; + +/* Member elements with timeout support */ +struct hash_netiface4_telem { + __be32 ip; + u8 physdev; + u8 cidr; + u16 padding; + const char *iface; + unsigned long timeout; +}; + +static inline bool +hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1, + const struct hash_netiface4_elem *ip2, + u32 *multi) +{ + return ip1->ip == ip2->ip && + ip1->cidr == ip2->cidr && + (++*multi) && + ip1->physdev == ip2->physdev && + ip1->iface == ip2->iface; +} + +static inline bool +hash_netiface4_data_isnull(const struct hash_netiface4_elem *elem) +{ + return elem->cidr == 0; +} + +static inline void +hash_netiface4_data_copy(struct hash_netiface4_elem *dst, + const struct hash_netiface4_elem *src) { + dst->ip = src->ip; + dst->cidr = src->cidr; + dst->physdev = src->physdev; + dst->iface = src->iface; +} + +static inline void +hash_netiface4_data_netmask(struct hash_netiface4_elem *elem, u8 cidr) +{ + elem->ip &= ip_set_netmask(cidr); + elem->cidr = cidr; +} + +static inline void +hash_netiface4_data_zero_out(struct hash_netiface4_elem *elem) +{ + elem->cidr = 0; +} + +static bool +hash_netiface4_data_list(struct sk_buff *skb, + const struct hash_netiface4_elem *data) +{ + u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_netiface4_data_tlist(struct sk_buff *skb, + const struct hash_netiface4_elem *data) +{ + const struct hash_netiface4_telem *tdata = + (const struct hash_netiface4_telem *)data; + u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + + NLA_PUT_IPADDR4(skb, IPSET_ATTR_IP, data->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(tdata->timeout))); + + return 0; + +nla_put_failure: + return 1; +} + +#define IP_SET_HASH_WITH_NETS +#define IP_SET_HASH_WITH_RBTREE +#define IP_SET_HASH_WITH_MULTI + +#define PF 4 +#define HOST_MASK 32 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static inline void +hash_netiface4_data_next(struct ip_set_hash *h, + const struct hash_netiface4_elem *d) +{ + h->next.ip = ntohl(d->ip); +} + +static int +hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb, + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) +{ + struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netiface4_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; + int ret; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); + data.ip &= ip_set_netmask(data.cidr); + +#define IFACE(dir) (par->dir ? par->dir->name : NULL) +#define PHYSDEV(dir) (nf_bridge->dir ? nf_bridge->dir->name : NULL) +#define SRCDIR (opt->flags & IPSET_DIM_TWO_SRC) + + if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { +#ifdef CONFIG_BRIDGE_NETFILTER + const struct nf_bridge_info *nf_bridge = skb->nf_bridge; + + if (!nf_bridge) + return -EINVAL; + data.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev); + data.physdev = 1; +#else + data.iface = NULL; +#endif + } else + data.iface = SRCDIR ? IFACE(in) : IFACE(out); + + if (!data.iface) + return -EINVAL; + ret = iface_test(&h->rbtree, &data.iface); + if (adt == IPSET_ADD) { + if (!ret) { + ret = iface_add(&h->rbtree, &data.iface); + if (ret) + return ret; + } + } else if (!ret) + return ret; + + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); +} + +static int +hash_netiface4_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) +{ + struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netiface4_elem data = { .cidr = HOST_MASK }; + u32 ip = 0, ip_to, last; + u32 timeout = h->timeout; + char iface[IFNAMSIZ] = {}; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !tb[IPSET_ATTR_IFACE] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) { + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + } + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + strcpy(iface, nla_data(tb[IPSET_ATTR_IFACE])); + data.iface = iface; + ret = iface_test(&h->rbtree, &data.iface); + if (adt == IPSET_ADD) { + if (!ret) { + ret = iface_add(&h->rbtree, &data.iface); + if (ret) + return ret; + } + } else if (!ret) + return ret; + + if (tb[IPSET_ATTR_CADT_FLAGS]) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_PHYSDEV) + data.physdev = 1; + } + + if (adt == IPSET_TEST || !tb[IPSET_ATTR_IP_TO]) { + data.ip = htonl(ip & ip_set_hostmask(data.cidr)); + ret = adtfn(set, &data, timeout, flags); + return ip_set_eexist(ret, flags) ? 0 : ret; + } + + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) + return ret; + if (ip_to < ip) + swap(ip, ip_to); + if (ip + UINT_MAX == ip_to) + return -IPSET_ERR_HASH_RANGE; + } else { + ip_set_mask_from_to(ip, ip_to, data.cidr); + } + + if (retried) + ip = h->next.ip; + while (!after(ip, ip_to)) { + data.ip = htonl(ip); + last = ip_set_range_to_cidr(ip, ip_to, &data.cidr); + ret = adtfn(set, &data, timeout, flags); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + ip = last + 1; + } + return ret; +} + +static bool +hash_netiface_same_set(const struct ip_set *a, const struct ip_set *b) +{ + const struct ip_set_hash *x = a->data; + const struct ip_set_hash *y = b->data; + + /* Resizing changes htable_bits, so we ignore it */ + return x->maxelem == y->maxelem && + x->timeout == y->timeout; +} + +/* The type variant functions: IPv6 */ + +struct hash_netiface6_elem_hashed { + union nf_inet_addr ip; + u8 physdev; + u8 cidr; + u16 padding; +}; + +#define HKEY_DATALEN sizeof(struct hash_netiface6_elem_hashed) + +struct hash_netiface6_elem { + union nf_inet_addr ip; + u8 physdev; + u8 cidr; + u16 padding; + const char *iface; +}; + +struct hash_netiface6_telem { + union nf_inet_addr ip; + u8 physdev; + u8 cidr; + u16 padding; + const char *iface; + unsigned long timeout; +}; + +static inline bool +hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1, + const struct hash_netiface6_elem *ip2, + u32 *multi) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ip1->cidr == ip2->cidr && + (++*multi) && + ip1->physdev == ip2->physdev && + ip1->iface == ip2->iface; +} + +static inline bool +hash_netiface6_data_isnull(const struct hash_netiface6_elem *elem) +{ + return elem->cidr == 0; +} + +static inline void +hash_netiface6_data_copy(struct hash_netiface6_elem *dst, + const struct hash_netiface6_elem *src) +{ + memcpy(dst, src, sizeof(*dst)); +} + +static inline void +hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem) +{ +} + +static inline void +ip6_netmask(union nf_inet_addr *ip, u8 prefix) +{ + ip->ip6[0] &= ip_set_netmask6(prefix)[0]; + ip->ip6[1] &= ip_set_netmask6(prefix)[1]; + ip->ip6[2] &= ip_set_netmask6(prefix)[2]; + ip->ip6[3] &= ip_set_netmask6(prefix)[3]; +} + +static inline void +hash_netiface6_data_netmask(struct hash_netiface6_elem *elem, u8 cidr) +{ + ip6_netmask(&elem->ip, cidr); + elem->cidr = cidr; +} + +static bool +hash_netiface6_data_list(struct sk_buff *skb, + const struct hash_netiface6_elem *data) +{ + u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &data->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + return 0; + +nla_put_failure: + return 1; +} + +static bool +hash_netiface6_data_tlist(struct sk_buff *skb, + const struct hash_netiface6_elem *data) +{ + const struct hash_netiface6_telem *e = + (const struct hash_netiface6_telem *)data; + u32 flags = data->physdev ? IPSET_FLAG_PHYSDEV : 0; + + NLA_PUT_IPADDR6(skb, IPSET_ATTR_IP, &e->ip); + NLA_PUT_U8(skb, IPSET_ATTR_CIDR, data->cidr); + NLA_PUT_STRING(skb, IPSET_ATTR_IFACE, data->iface); + if (flags) + NLA_PUT_NET32(skb, IPSET_ATTR_CADT_FLAGS, flags); + NLA_PUT_NET32(skb, IPSET_ATTR_TIMEOUT, + htonl(ip_set_timeout_get(e->timeout))); + return 0; + +nla_put_failure: + return 1; +} + +#undef PF +#undef HOST_MASK + +#define PF 6 +#define HOST_MASK 128 +#include <linux/netfilter/ipset/ip_set_ahash.h> + +static inline void +hash_netiface6_data_next(struct ip_set_hash *h, + const struct hash_netiface6_elem *d) +{ +} + +static int +hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb, + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) +{ + struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netiface6_elem data = { + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; + int ret; + + if (data.cidr == 0) + return -EINVAL; + if (adt == IPSET_TEST) + data.cidr = HOST_MASK; + + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6_netmask(&data.ip, data.cidr); + + if (opt->cmdflags & IPSET_FLAG_PHYSDEV) { +#ifdef CONFIG_BRIDGE_NETFILTER + const struct nf_bridge_info *nf_bridge = skb->nf_bridge; + + if (!nf_bridge) + return -EINVAL; + data.iface = SRCDIR ? PHYSDEV(physindev) : PHYSDEV(physoutdev); + data.physdev = 1; +#else + data.iface = NULL; +#endif + } else + data.iface = SRCDIR ? IFACE(in) : IFACE(out); + + if (!data.iface) + return -EINVAL; + ret = iface_test(&h->rbtree, &data.iface); + if (adt == IPSET_ADD) { + if (!ret) { + ret = iface_add(&h->rbtree, &data.iface); + if (ret) + return ret; + } + } else if (!ret) + return ret; + + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); +} + +static int +hash_netiface6_uadt(struct ip_set *set, struct nlattr *tb[], + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) +{ + struct ip_set_hash *h = set->data; + ipset_adtfn adtfn = set->variant->adt[adt]; + struct hash_netiface6_elem data = { .cidr = HOST_MASK }; + u32 timeout = h->timeout; + char iface[IFNAMSIZ] = {}; + int ret; + + if (unlikely(!tb[IPSET_ATTR_IP] || + !tb[IPSET_ATTR_IFACE] || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS))) + return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; + + if (tb[IPSET_ATTR_LINENO]) + *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); + + ret = ip_set_get_ipaddr6(tb[IPSET_ATTR_IP], &data.ip); + if (ret) + return ret; + + if (tb[IPSET_ATTR_CIDR]) + data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + ip6_netmask(&data.ip, data.cidr); + + if (tb[IPSET_ATTR_TIMEOUT]) { + if (!with_timeout(h->timeout)) + return -IPSET_ERR_TIMEOUT; + timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + } + + strcpy(iface, nla_data(tb[IPSET_ATTR_IFACE])); + data.iface = iface; + ret = iface_test(&h->rbtree, &data.iface); + if (adt == IPSET_ADD) { + if (!ret) { + ret = iface_add(&h->rbtree, &data.iface); + if (ret) + return ret; + } + } else if (!ret) + return ret; + + if (tb[IPSET_ATTR_CADT_FLAGS]) { + u32 cadt_flags = ip_set_get_h32(tb[IPSET_ATTR_CADT_FLAGS]); + if (cadt_flags & IPSET_FLAG_PHYSDEV) + data.physdev = 1; + } + + ret = adtfn(set, &data, timeout, flags); + + return ip_set_eexist(ret, flags) ? 0 : ret; +} + +/* Create hash:ip type of sets */ + +static int +hash_netiface_create(struct ip_set *set, struct nlattr *tb[], u32 flags) +{ + struct ip_set_hash *h; + u32 hashsize = IPSET_DEFAULT_HASHSIZE, maxelem = IPSET_DEFAULT_MAXELEM; + u8 hbits; + + if (!(set->family == AF_INET || set->family == AF_INET6)) + return -IPSET_ERR_INVALID_FAMILY; + + if (unlikely(!ip_set_optattr_netorder(tb, IPSET_ATTR_HASHSIZE) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_MAXELEM) || + !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) + return -IPSET_ERR_PROTOCOL; + + if (tb[IPSET_ATTR_HASHSIZE]) { + hashsize = ip_set_get_h32(tb[IPSET_ATTR_HASHSIZE]); + if (hashsize < IPSET_MIMINAL_HASHSIZE) + hashsize = IPSET_MIMINAL_HASHSIZE; + } + + if (tb[IPSET_ATTR_MAXELEM]) + maxelem = ip_set_get_h32(tb[IPSET_ATTR_MAXELEM]); + + h = kzalloc(sizeof(*h) + + sizeof(struct ip_set_hash_nets) + * (set->family == AF_INET ? 32 : 128), GFP_KERNEL); + if (!h) + return -ENOMEM; + + h->maxelem = maxelem; + get_random_bytes(&h->initval, sizeof(h->initval)); + h->timeout = IPSET_NO_TIMEOUT; + h->ahash_max = AHASH_MAX_SIZE; + + hbits = htable_bits(hashsize); + h->table = ip_set_alloc( + sizeof(struct htable) + + jhash_size(hbits) * sizeof(struct hbucket)); + if (!h->table) { + kfree(h); + return -ENOMEM; + } + h->table->htable_bits = hbits; + h->rbtree = RB_ROOT; + + set->data = h; + + if (tb[IPSET_ATTR_TIMEOUT]) { + h->timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); + + set->variant = set->family == AF_INET + ? &hash_netiface4_tvariant : &hash_netiface6_tvariant; + + if (set->family == AF_INET) + hash_netiface4_gc_init(set); + else + hash_netiface6_gc_init(set); + } else { + set->variant = set->family == AF_INET + ? &hash_netiface4_variant : &hash_netiface6_variant; + } + + pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", + set->name, jhash_size(h->table->htable_bits), + h->table->htable_bits, h->maxelem, set->data, h->table); + + return 0; +} + +static struct ip_set_type hash_netiface_type __read_mostly = { + .name = "hash:net,iface", + .protocol = IPSET_PROTOCOL, + .features = IPSET_TYPE_IP | IPSET_TYPE_IFACE, + .dimension = IPSET_DIM_TWO, + .family = AF_UNSPEC, + .revision_min = 0, + .create = hash_netiface_create, + .create_policy = { + [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, + [IPSET_ATTR_MAXELEM] = { .type = NLA_U32 }, + [IPSET_ATTR_PROBES] = { .type = NLA_U8 }, + [IPSET_ATTR_RESIZE] = { .type = NLA_U8 }, + [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + }, + .adt_policy = { + [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, + [IPSET_ATTR_IFACE] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, + [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, + [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, + }, + .me = THIS_MODULE, +}; + +static int __init +hash_netiface_init(void) +{ + return ip_set_type_register(&hash_netiface_type); +} + +static void __exit +hash_netiface_fini(void) +{ + ip_set_type_unregister(&hash_netiface_type); +} + +module_init(hash_netiface_init); +module_exit(hash_netiface_fini); diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index d2a40362dd3..8f9de7207ec 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -59,7 +59,8 @@ struct hash_netport4_telem { static inline bool hash_netport4_data_equal(const struct hash_netport4_elem *ip1, - const struct hash_netport4_elem *ip2) + const struct hash_netport4_elem *ip2, + u32 *multi) { return ip1->ip == ip2->ip && ip1->port == ip2->port && @@ -137,38 +138,48 @@ nla_put_failure: #define HOST_MASK 32 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_netport4_data_next(struct ip_set_hash *h, + const struct hash_netport4_elem *d) +{ + h->next.ip = ntohl(d->ip); + h->next.port = ntohs(d->port); +} + static int hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem data = { - .cidr = h->nets[0].cidr || HOST_MASK }; + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) data.cidr = HOST_MASK; - if (!ip_set_get_ip4_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip4_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip4addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip); + ip4addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip); data.ip &= ip_set_netmask(data.cidr); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport4_elem data = { .cidr = HOST_MASK }; - u32 port, port_to; + u32 port, port_to, p = 0, ip = 0, ip_to, last; u32 timeout = h->timeout; bool with_ports = false; int ret; @@ -182,15 +193,15 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); - ret = ip_set_get_ipaddr4(tb[IPSET_ATTR_IP], &data.ip); + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP], &ip); if (ret) return ret; - if (tb[IPSET_ATTR_CIDR]) + if (tb[IPSET_ATTR_CIDR]) { data.cidr = nla_get_u8(tb[IPSET_ATTR_CIDR]); - if (!data.cidr) - return -IPSET_ERR_INVALID_CIDR; - data.ip &= ip_set_netmask(data.cidr); + if (!data.cidr) + return -IPSET_ERR_INVALID_CIDR; + } if (tb[IPSET_ATTR_PORT]) data.port = nla_get_be16(tb[IPSET_ATTR_PORT]); @@ -215,24 +226,47 @@ hash_netport4_uadt(struct ip_set *set, struct nlattr *tb[], timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } - if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { - ret = adtfn(set, &data, timeout); + with_ports = with_ports && tb[IPSET_ATTR_PORT_TO]; + if (adt == IPSET_TEST || !(with_ports || tb[IPSET_ATTR_IP_TO])) { + data.ip = htonl(ip & ip_set_hostmask(data.cidr)); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } - port = ntohs(data.port); - port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); - if (port > port_to) - swap(port, port_to); - - for (; port <= port_to; port++) { - data.port = htons(port); - ret = adtfn(set, &data, timeout); - - if (ret && !ip_set_eexist(ret, flags)) + port = port_to = ntohs(data.port); + if (tb[IPSET_ATTR_PORT_TO]) { + port_to = ip_set_get_h16(tb[IPSET_ATTR_PORT_TO]); + if (port_to < port) + swap(port, port_to); + } + if (tb[IPSET_ATTR_IP_TO]) { + ret = ip_set_get_hostipaddr4(tb[IPSET_ATTR_IP_TO], &ip_to); + if (ret) return ret; - else - ret = 0; + if (ip_to < ip) + swap(ip, ip_to); + if (ip + UINT_MAX == ip_to) + return -IPSET_ERR_HASH_RANGE; + } else { + ip_set_mask_from_to(ip, ip_to, data.cidr); + } + + if (retried) + ip = h->next.ip; + while (!after(ip, ip_to)) { + data.ip = htonl(ip); + last = ip_set_range_to_cidr(ip, ip_to, &data.cidr); + p = retried && ip == h->next.ip ? h->next.port : port; + for (; p <= port_to; p++) { + data.port = htons(p); + ret = adtfn(set, &data, timeout, flags); + + if (ret && !ip_set_eexist(ret, flags)) + return ret; + else + ret = 0; + } + ip = last + 1; } return ret; } @@ -267,7 +301,8 @@ struct hash_netport6_telem { static inline bool hash_netport6_data_equal(const struct hash_netport6_elem *ip1, - const struct hash_netport6_elem *ip2) + const struct hash_netport6_elem *ip2, + u32 *multi) { return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && ip1->port == ip2->port && @@ -350,33 +385,42 @@ nla_put_failure: #define HOST_MASK 128 #include <linux/netfilter/ipset/ip_set_ahash.h> +static inline void +hash_netport6_data_next(struct ip_set_hash *h, + const struct hash_netport6_elem *d) +{ + h->next.port = ntohs(d->port); +} + static int hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; struct hash_netport6_elem data = { - .cidr = h->nets[0].cidr || HOST_MASK }; + .cidr = h->nets[0].cidr ? h->nets[0].cidr : HOST_MASK + }; if (data.cidr == 0) return -EINVAL; if (adt == IPSET_TEST) data.cidr = HOST_MASK; - if (!ip_set_get_ip6_port(skb, flags & IPSET_DIM_TWO_SRC, + if (!ip_set_get_ip6_port(skb, opt->flags & IPSET_DIM_TWO_SRC, &data.port, &data.proto)) return -EINVAL; - ip6addrptr(skb, flags & IPSET_DIM_ONE_SRC, &data.ip.in6); + ip6addrptr(skb, opt->flags & IPSET_DIM_ONE_SRC, &data.ip.in6); ip6_netmask(&data.ip, data.cidr); - return adtfn(set, &data, h->timeout); + return adtfn(set, &data, opt_timeout(opt, h), opt->cmdflags); } static int hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { const struct ip_set_hash *h = set->data; ipset_adtfn adtfn = set->variant->adt[adt]; @@ -391,6 +435,8 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) || !ip_set_optattr_netorder(tb, IPSET_ATTR_TIMEOUT))) return -IPSET_ERR_PROTOCOL; + if (unlikely(tb[IPSET_ATTR_IP_TO])) + return -IPSET_ERR_HASH_RANGE_UNSUPPORTED; if (tb[IPSET_ATTR_LINENO]) *lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]); @@ -429,7 +475,7 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], } if (adt == IPSET_TEST || !with_ports || !tb[IPSET_ATTR_PORT_TO]) { - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); return ip_set_eexist(ret, flags) ? 0 : ret; } @@ -438,9 +484,11 @@ hash_netport6_uadt(struct ip_set *set, struct nlattr *tb[], if (port > port_to) swap(port, port_to); + if (retried) + port = h->next.port; for (; port <= port_to; port++) { data.port = htons(port); - ret = adtfn(set, &data, timeout); + ret = adtfn(set, &data, timeout, flags); if (ret && !ip_set_eexist(ret, flags)) return ret; @@ -526,7 +574,9 @@ static struct ip_set_type hash_netport_type __read_mostly = { .features = IPSET_TYPE_IP | IPSET_TYPE_PORT, .dimension = IPSET_DIM_TWO, .family = AF_UNSPEC, - .revision = 1, + .revision_min = 0, + /* 1 SCTP and UDPLITE support added */ + .revision_max = 2, /* Range as input support for IPv4 added */ .create = hash_netport_create, .create_policy = { [IPSET_ATTR_HASHSIZE] = { .type = NLA_U32 }, @@ -538,6 +588,7 @@ static struct ip_set_type hash_netport_type __read_mostly = { }, .adt_policy = { [IPSET_ATTR_IP] = { .type = NLA_NESTED }, + [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_PORT] = { .type = NLA_U16 }, [IPSET_ATTR_PORT_TO] = { .type = NLA_U16 }, [IPSET_ATTR_PROTO] = { .type = NLA_U8 }, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index e9159e99fc4..4d10819d462 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -72,7 +72,8 @@ list_set_expired(const struct list_set *map, u32 id) static int list_set_kadt(struct ip_set *set, const struct sk_buff *skb, - enum ipset_adt adt, u8 pf, u8 dim, u8 flags) + const struct xt_action_param *par, + enum ipset_adt adt, const struct ip_set_adt_opt *opt) { struct list_set *map = set->data; struct set_elem *elem; @@ -87,17 +88,17 @@ list_set_kadt(struct ip_set *set, const struct sk_buff *skb, continue; switch (adt) { case IPSET_TEST: - ret = ip_set_test(elem->id, skb, pf, dim, flags); + ret = ip_set_test(elem->id, skb, par, opt); if (ret > 0) return ret; break; case IPSET_ADD: - ret = ip_set_add(elem->id, skb, pf, dim, flags); + ret = ip_set_add(elem->id, skb, par, opt); if (ret == 0) return ret; break; case IPSET_DEL: - ret = ip_set_del(elem->id, skb, pf, dim, flags); + ret = ip_set_del(elem->id, skb, par, opt); if (ret == 0) return ret; break; @@ -109,15 +110,28 @@ list_set_kadt(struct ip_set *set, const struct sk_buff *skb, } static bool -next_id_eq(const struct list_set *map, u32 i, ip_set_id_t id) +id_eq(const struct list_set *map, u32 i, ip_set_id_t id) { const struct set_elem *elem; - if (i + 1 < map->size) { - elem = list_set_elem(map, i + 1); + if (i < map->size) { + elem = list_set_elem(map, i); + return elem->id == id; + } + + return 0; +} + +static bool +id_eq_timeout(const struct list_set *map, u32 i, ip_set_id_t id) +{ + const struct set_elem *elem; + + if (i < map->size) { + elem = list_set_elem(map, i); return !!(elem->id == id && !(with_timeout(map->timeout) && - list_set_expired(map, i + 1))); + list_set_expired(map, i))); } return 0; @@ -190,12 +204,26 @@ list_set_del(struct list_set *map, u32 i) return 0; } +static void +cleanup_entries(struct list_set *map) +{ + struct set_telem *e; + u32 i; + + for (i = 0; i < map->size; i++) { + e = list_set_telem(map, i); + if (e->id != IPSET_INVALID_ID && list_set_expired(map, i)) + list_set_del(map, i); + } +} + static int list_set_uadt(struct ip_set *set, struct nlattr *tb[], - enum ipset_adt adt, u32 *lineno, u32 flags) + enum ipset_adt adt, u32 *lineno, u32 flags, bool retried) { struct list_set *map = set->data; bool with_timeout = with_timeout(map->timeout); + bool flag_exist = flags & IPSET_FLAG_EXIST; int before = 0; u32 timeout = map->timeout; ip_set_id_t id, refid = IPSET_INVALID_ID; @@ -248,6 +276,8 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], } timeout = ip_set_timeout_uget(tb[IPSET_ATTR_TIMEOUT]); } + if (with_timeout && adt != IPSET_TEST) + cleanup_entries(map); switch (adt) { case IPSET_TEST: @@ -259,22 +289,37 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], else if (with_timeout && list_set_expired(map, i)) continue; else if (before > 0 && elem->id == id) - ret = next_id_eq(map, i, refid); + ret = id_eq_timeout(map, i + 1, refid); else if (before < 0 && elem->id == refid) - ret = next_id_eq(map, i, id); + ret = id_eq_timeout(map, i + 1, id); else if (before == 0 && elem->id == id) ret = 1; } break; case IPSET_ADD: - for (i = 0; i < map->size && !ret; i++) { + for (i = 0; i < map->size; i++) { elem = list_set_elem(map, i); - if (elem->id == id && - !(with_timeout && list_set_expired(map, i))) + if (elem->id != id) + continue; + if (!(with_timeout && flag_exist)) { ret = -IPSET_ERR_EXIST; + goto finish; + } else { + struct set_telem *e = list_set_telem(map, i); + + if ((before > 1 && + !id_eq(map, i + 1, refid)) || + (before < 0 && + (i == 0 || !id_eq(map, i - 1, refid)))) { + ret = -IPSET_ERR_EXIST; + goto finish; + } + e->timeout = ip_set_timeout_set(timeout); + ip_set_put_byindex(id); + ret = 0; + goto finish; + } } - if (ret == -IPSET_ERR_EXIST) - break; ret = -IPSET_ERR_LIST_FULL; for (i = 0; i < map->size && ret == -IPSET_ERR_LIST_FULL; i++) { elem = list_set_elem(map, i); @@ -283,9 +328,7 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], : list_set_add(map, i, id, timeout); else if (elem->id != refid) continue; - else if (with_timeout && list_set_expired(map, i)) - ret = -IPSET_ERR_REF_EXIST; - else if (before) + else if (before > 0) ret = list_set_add(map, i, id, timeout); else if (i + 1 < map->size) ret = list_set_add(map, i + 1, id, timeout); @@ -299,16 +342,12 @@ list_set_uadt(struct ip_set *set, struct nlattr *tb[], ret = before != 0 ? -IPSET_ERR_REF_EXIST : -IPSET_ERR_EXIST; break; - } else if (with_timeout && list_set_expired(map, i)) - continue; - else if (elem->id == id && - (before == 0 || - (before > 0 && - next_id_eq(map, i, refid)))) + } else if (elem->id == id && + (before == 0 || + (before > 0 && id_eq(map, i + 1, refid)))) ret = list_set_del(map, i); - else if (before < 0 && - elem->id == refid && - next_id_eq(map, i, id)) + else if (elem->id == refid && + before < 0 && id_eq(map, i + 1, id)) ret = list_set_del(map, i + 1); } break; @@ -454,15 +493,9 @@ list_set_gc(unsigned long ul_set) { struct ip_set *set = (struct ip_set *) ul_set; struct list_set *map = set->data; - struct set_telem *e; - u32 i; write_lock_bh(&set->lock); - for (i = 0; i < map->size; i++) { - e = list_set_telem(map, i); - if (e->id != IPSET_INVALID_ID && list_set_expired(map, i)) - list_set_del(map, i); - } + cleanup_entries(map); write_unlock_bh(&set->lock); map->gc.expires = jiffies + IPSET_GC_PERIOD(map->timeout) * HZ; @@ -543,7 +576,8 @@ static struct ip_set_type list_set_type __read_mostly = { .features = IPSET_TYPE_NAME | IPSET_DUMP_LAST, .dimension = IPSET_DIM_ONE, .family = AF_UNSPEC, - .revision = 0, + .revision_min = 0, + .revision_max = 0, .create = list_set_create, .create_policy = { [IPSET_ATTR_SIZE] = { .type = NLA_U32 }, diff --git a/net/netfilter/ipset/pfxlen.c b/net/netfilter/ipset/pfxlen.c index 23f8c816221..bd13d66220f 100644 --- a/net/netfilter/ipset/pfxlen.c +++ b/net/netfilter/ipset/pfxlen.c @@ -148,7 +148,7 @@ const union nf_inet_addr ip_set_netmask_map[] = { EXPORT_SYMBOL_GPL(ip_set_netmask_map); #undef E -#define E(a, b, c, d) \ +#define E(a, b, c, d) \ {.ip6 = { (__force __be32) a, (__force __be32) b, \ (__force __be32) c, (__force __be32) d, \ } } @@ -289,3 +289,24 @@ const union nf_inet_addr ip_set_hostmask_map[] = { E(0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF, 0xFFFFFFFF), }; EXPORT_SYMBOL_GPL(ip_set_hostmask_map); + +/* Find the largest network which matches the range from left, in host order. */ +u32 +ip_set_range_to_cidr(u32 from, u32 to, u8 *cidr) +{ + u32 last; + u8 i; + + for (i = 1; i < 32; i++) { + if ((from & ip_set_hostmask(i)) != from) + continue; + last = from | ~ip_set_hostmask(i); + if (!after(last, to)) { + *cidr = i; + return last; + } + } + *cidr = 32; + return from; +} +EXPORT_SYMBOL_GPL(ip_set_range_to_cidr); diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 059af3120be..fe6cb4304d7 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -int __net_init __ip_vs_app_init(struct net *net) +int __net_init ip_vs_app_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -585,17 +585,7 @@ int __net_init __ip_vs_app_init(struct net *net) return 0; } -void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit ip_vs_app_net_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } - -int __init ip_vs_app_init(void) -{ - return 0; -} - - -void ip_vs_app_cleanup(void) -{ -} diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index bf28ac2fc99..12571fb2881 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -776,8 +776,16 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->control) ip_vs_control_del(cp); - if (cp->flags & IP_VS_CONN_F_NFCT) + if (cp->flags & IP_VS_CONN_F_NFCT) { ip_vs_conn_drop_conntrack(cp); + /* Do not access conntracks during subsys cleanup + * because nf_conntrack_find_get can not be used after + * conntrack cleanup for the net. + */ + smp_rmb(); + if (ipvs->enable) + ip_vs_conn_drop_conntrack(cp); + } ip_vs_pe_put(cp->pe); kfree(cp->pe_data); @@ -1247,7 +1255,7 @@ flush_again: /* * per netns init and exit */ -int __net_init __ip_vs_conn_init(struct net *net) +int __net_init ip_vs_conn_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1258,7 +1266,7 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit ip_vs_conn_net_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index bfa808f4da1..4f77bb16d22 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -852,7 +852,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, *related = 1; /* reassemble IP fragments */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -1156,8 +1156,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } else #endif - if (unlikely(ip_hdr(skb)->frag_off & htons(IP_MF|IP_OFFSET) && - !pp->dont_defrag)) { + if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; @@ -1310,7 +1309,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) *related = 1; /* reassemble IP fragments */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -1384,7 +1383,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) offset += 2 * sizeof(__u16); verdict = ip_vs_icmp_xmit(skb, cp, pp, offset, hooknum); - out: +out: __ip_vs_conn_put(cp); return verdict; @@ -1772,7 +1771,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_IN, - .priority = 99, + .priority = NF_IP_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1782,7 +1781,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_IN, - .priority = 101, + .priority = NF_IP_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { @@ -1790,7 +1789,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_OUT, - .priority = -99, + .priority = NF_IP_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { @@ -1798,7 +1797,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_OUT, - .priority = -98, + .priority = NF_IP_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ @@ -1824,7 +1823,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_IN, - .priority = 99, + .priority = NF_IP6_PRI_NAT_SRC - 2, }, /* After packet filtering, forward packet through VS/DR, VS/TUN, * or VS/NAT(change destination), so that filtering rules can be @@ -1834,7 +1833,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_IN, - .priority = 101, + .priority = NF_IP6_PRI_NAT_SRC - 1, }, /* Before ip_vs_in, change source only for VS/NAT */ { @@ -1842,7 +1841,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET, .hooknum = NF_INET_LOCAL_OUT, - .priority = -99, + .priority = NF_IP6_PRI_NAT_DST + 1, }, /* After mangle, schedule and forward local requests */ { @@ -1850,7 +1849,7 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_OUT, - .priority = -98, + .priority = NF_IP6_PRI_NAT_DST + 2, }, /* After packet filtering (but before ip_vs_out_icmp), catch icmp * destined for 0.0.0.0/0, which is for incoming IPVS connections */ @@ -1891,22 +1890,22 @@ static int __net_init __ip_vs_init(struct net *net) atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; - if (__ip_vs_estimator_init(net) < 0) + if (ip_vs_estimator_net_init(net) < 0) goto estimator_fail; - if (__ip_vs_control_init(net) < 0) + if (ip_vs_control_net_init(net) < 0) goto control_fail; - if (__ip_vs_protocol_init(net) < 0) + if (ip_vs_protocol_net_init(net) < 0) goto protocol_fail; - if (__ip_vs_app_init(net) < 0) + if (ip_vs_app_net_init(net) < 0) goto app_fail; - if (__ip_vs_conn_init(net) < 0) + if (ip_vs_conn_net_init(net) < 0) goto conn_fail; - if (__ip_vs_sync_init(net) < 0) + if (ip_vs_sync_net_init(net) < 0) goto sync_fail; printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", @@ -1917,27 +1916,27 @@ static int __net_init __ip_vs_init(struct net *net) */ sync_fail: - __ip_vs_conn_cleanup(net); + ip_vs_conn_net_cleanup(net); conn_fail: - __ip_vs_app_cleanup(net); + ip_vs_app_net_cleanup(net); app_fail: - __ip_vs_protocol_cleanup(net); + ip_vs_protocol_net_cleanup(net); protocol_fail: - __ip_vs_control_cleanup(net); + ip_vs_control_net_cleanup(net); control_fail: - __ip_vs_estimator_cleanup(net); + ip_vs_estimator_net_cleanup(net); estimator_fail: return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { - __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ - __ip_vs_conn_cleanup(net); - __ip_vs_app_cleanup(net); - __ip_vs_protocol_cleanup(net); - __ip_vs_control_cleanup(net); - __ip_vs_estimator_cleanup(net); + ip_vs_service_net_cleanup(net); /* ip_vs_flush() with locks */ + ip_vs_conn_net_cleanup(net); + ip_vs_app_net_cleanup(net); + ip_vs_protocol_net_cleanup(net); + ip_vs_control_net_cleanup(net); + ip_vs_estimator_net_cleanup(net); IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); } @@ -1945,7 +1944,8 @@ static void __net_exit __ip_vs_dev_cleanup(struct net *net) { EnterFunction(2); net_ipvs(net)->enable = 0; /* Disable packet reception */ - __ip_vs_sync_cleanup(net); + smp_wmb(); + ip_vs_sync_net_cleanup(net); LeaveFunction(2); } @@ -1967,36 +1967,23 @@ static int __init ip_vs_init(void) { int ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); - goto cleanup_estimator; + goto exit; } ip_vs_protocol_init(); - ret = ip_vs_app_init(); - if (ret < 0) { - pr_err("can't setup application helper.\n"); - goto cleanup_protocol; - } - ret = ip_vs_conn_init(); if (ret < 0) { pr_err("can't setup connection table.\n"); - goto cleanup_app; - } - - ret = ip_vs_sync_init(); - if (ret < 0) { - pr_err("can't setup sync data.\n"); - goto cleanup_conn; + goto cleanup_protocol; } ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ if (ret < 0) - goto cleanup_sync; + goto cleanup_conn; ret = register_pernet_device(&ipvs_core_dev_ops); if (ret < 0) @@ -2016,17 +2003,12 @@ cleanup_dev: unregister_pernet_device(&ipvs_core_dev_ops); cleanup_sub: unregister_pernet_subsys(&ipvs_core_ops); -cleanup_sync: - ip_vs_sync_cleanup(); - cleanup_conn: +cleanup_conn: ip_vs_conn_cleanup(); - cleanup_app: - ip_vs_app_cleanup(); - cleanup_protocol: +cleanup_protocol: ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); - cleanup_estimator: - ip_vs_estimator_cleanup(); +exit: return ret; } @@ -2035,12 +2017,9 @@ static void __exit ip_vs_cleanup(void) nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); unregister_pernet_device(&ipvs_core_dev_ops); unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ - ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); - ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); - ip_vs_estimator_cleanup(); pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 699c79a5565..be43fd805bd 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1334,9 +1334,9 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) ip_vs_bind_pe(svc, pe); } - out_unlock: +out_unlock: write_unlock_bh(&__ip_vs_svc_lock); - out: +out: ip_vs_scheduler_put(old_sched); ip_vs_pe_put(old_pe); return ret; @@ -1483,7 +1483,7 @@ static int ip_vs_flush(struct net *net) * Delete service by {netns} in the service table. * Called by __ip_vs_cleanup() */ -void __ip_vs_service_cleanup(struct net *net) +void ip_vs_service_net_cleanup(struct net *net) { EnterFunction(2); /* Check for "full" addressed entries */ @@ -1662,7 +1662,7 @@ proc_do_sync_mode(ctl_table *table, int write, /* * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/) * Do not change order or insert new entries without - * align with netns init in __ip_vs_control_init() + * align with netns init in ip_vs_control_net_init() */ static struct ctl_table vs_vars[] = { @@ -2469,7 +2469,7 @@ __ip_vs_get_service_entries(struct net *net, count++; } } - out: +out: return ret; } @@ -2707,7 +2707,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; } - out: +out: mutex_unlock(&__ip_vs_mutex); return ret; } @@ -3595,7 +3595,7 @@ static void ip_vs_genl_unregister(void) * per netns intit/exit func. */ #ifdef CONFIG_SYSCTL -int __net_init __ip_vs_control_init_sysctl(struct net *net) +int __net_init ip_vs_control_net_init_sysctl(struct net *net) { int idx; struct netns_ipvs *ipvs = net_ipvs(net); @@ -3654,7 +3654,7 @@ int __net_init __ip_vs_control_init_sysctl(struct net *net) return 0; } -void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) +void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3665,8 +3665,8 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) #else -int __net_init __ip_vs_control_init_sysctl(struct net *net) { return 0; } -void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } +int __net_init ip_vs_control_net_init_sysctl(struct net *net) { return 0; } +void __net_init ip_vs_control_net_cleanup_sysctl(struct net *net) { } #endif @@ -3674,7 +3674,7 @@ static struct notifier_block ip_vs_dst_notifier = { .notifier_call = ip_vs_dst_event, }; -int __net_init __ip_vs_control_init(struct net *net) +int __net_init ip_vs_control_net_init(struct net *net) { int idx; struct netns_ipvs *ipvs = net_ipvs(net); @@ -3702,7 +3702,7 @@ int __net_init __ip_vs_control_init(struct net *net) proc_net_fops_create(net, "ip_vs_stats_percpu", 0, &ip_vs_stats_percpu_fops); - if (__ip_vs_control_init_sysctl(net)) + if (ip_vs_control_net_init_sysctl(net)) goto err; return 0; @@ -3712,13 +3712,13 @@ err: return -ENOMEM; } -void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit ip_vs_control_net_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); ip_vs_trash_cleanup(net); ip_vs_stop_estimator(net, &ipvs->tot_stats); - __ip_vs_control_cleanup_sysctl(net); + ip_vs_control_net_cleanup_sysctl(net); proc_net_remove(net, "ip_vs_stats_percpu"); proc_net_remove(net, "ip_vs_stats"); proc_net_remove(net, "ip_vs"); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 508cce98777..0fac6017b6f 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init ip_vs_estimator_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,16 +203,7 @@ int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -void __net_exit __ip_vs_estimator_cleanup(struct net *net) +void __net_exit ip_vs_estimator_net_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } - -int __init ip_vs_estimator_init(void) -{ - return 0; -} - -void ip_vs_estimator_cleanup(void) -{ -} diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index af63553fa33..4490a32ad5b 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -44,8 +44,8 @@ #include <net/ip_vs.h> -#define SERVER_STRING "227 Entering Passive Mode (" -#define CLIENT_STRING "PORT " +#define SERVER_STRING "227 " +#define CLIENT_STRING "PORT" /* @@ -79,14 +79,17 @@ ip_vs_ftp_done_conn(struct ip_vs_app *app, struct ip_vs_conn *cp) /* * Get <addr,port> from the string "xxx.xxx.xxx.xxx,ppp,ppp", started - * with the "pattern" and terminated with the "term" character. + * with the "pattern", ignoring before "skip" and terminated with + * the "term" character. * <addr,port> is in network order. */ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, - const char *pattern, size_t plen, char term, + const char *pattern, size_t plen, + char skip, char term, __be32 *addr, __be16 *port, char **start, char **end) { + char *s, c; unsigned char p[6]; int i = 0; @@ -101,19 +104,38 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, if (strnicmp(data, pattern, plen) != 0) { return 0; } - *start = data + plen; + s = data + plen; + if (skip) { + int found = 0; + + for (;; s++) { + if (s == data_limit) + return -1; + if (!found) { + if (*s == skip) + found = 1; + } else if (*s != skip) { + break; + } + } + } - for (data = *start; *data != term; data++) { + for (data = s; ; data++) { if (data == data_limit) return -1; + if (*data == term) + break; } *end = data; memset(p, 0, sizeof(p)); - for (data = *start; data != *end; data++) { - if (*data >= '0' && *data <= '9') { - p[i] = p[i]*10 + *data - '0'; - } else if (*data == ',' && i < 5) { + for (data = s; ; data++) { + c = *data; + if (c == term) + break; + if (c >= '0' && c <= '9') { + p[i] = p[i]*10 + c - '0'; + } else if (c == ',' && i < 5) { i++; } else { /* unexpected character */ @@ -124,8 +146,9 @@ static int ip_vs_ftp_get_addrport(char *data, char *data_limit, if (i != 5) return -1; - *addr = get_unaligned((__be32 *)p); - *port = get_unaligned((__be16 *)(p + 4)); + *start = s; + *addr = get_unaligned((__be32 *) p); + *port = get_unaligned((__be16 *) (p + 4)); return 1; } @@ -185,7 +208,8 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, if (ip_vs_ftp_get_addrport(data, data_limit, SERVER_STRING, - sizeof(SERVER_STRING)-1, ')', + sizeof(SERVER_STRING)-1, + '(', ')', &from.ip, &port, &start, &end) != 1) return 1; @@ -345,7 +369,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, */ if (ip_vs_ftp_get_addrport(data_start, data_limit, CLIENT_STRING, sizeof(CLIENT_STRING)-1, - '\r', &to.ip, &port, + ' ', '\r', &to.ip, &port, &start, &end) != 1) return 1; diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index eb86028536f..52d073c105e 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init ip_vs_protocol_net_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit ip_vs_protocol_net_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index e292e5bddc7..7ee7215b8ba 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1663,7 +1663,7 @@ int stop_sync_thread(struct net *net, int state) /* * Initialize data struct for each netns */ -int __net_init __ip_vs_sync_init(struct net *net) +int __net_init ip_vs_sync_net_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1677,7 +1677,7 @@ int __net_init __ip_vs_sync_init(struct net *net) return 0; } -void __ip_vs_sync_cleanup(struct net *net) +void ip_vs_sync_net_cleanup(struct net *net) { int retc; @@ -1689,12 +1689,3 @@ void __ip_vs_sync_cleanup(struct net *net) if (retc && retc != -ESRCH) pr_err("Failed to stop Backup Daemon\n"); } - -int __init ip_vs_sync_init(void) -{ - return 0; -} - -void ip_vs_sync_cleanup(void) -{ -} diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 2e1c11f7841..f7af8b86601 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -850,7 +850,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl, /* It exists; we have (non-exclusive) reference. */ if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY) { - *ctinfo = IP_CT_ESTABLISHED + IP_CT_IS_REPLY; + *ctinfo = IP_CT_ESTABLISHED_REPLY; /* Please set reply bit if this packet OK */ *set_reply = 1; } else { @@ -922,6 +922,9 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum, ret = -ret; goto out; } + /* ICMP[v6] protocol trackers may assign one conntrack. */ + if (skb->nfct) + goto out; } ct = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, @@ -1143,7 +1146,7 @@ static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb) /* This ICMP is in reverse direction to the packet which caused it */ ct = nf_ct_get(skb, &ctinfo); if (CTINFO2DIR(ctinfo) == IP_CT_DIR_ORIGINAL) - ctinfo = IP_CT_RELATED + IP_CT_IS_REPLY; + ctinfo = IP_CT_RELATED_REPLY; else ctinfo = IP_CT_RELATED; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index e17cb7c7dd8..6f5801eac99 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -368,7 +368,7 @@ static int help(struct sk_buff *skb, /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + ctinfo != IP_CT_ESTABLISHED_REPLY) { pr_debug("ftp: Conntrackinfo = %u\n", ctinfo); return NF_ACCEPT; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 18b2ce5c8ce..f03c2d4539f 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -571,10 +571,9 @@ static int h245_help(struct sk_buff *skb, unsigned int protoff, int ret; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; - } + pr_debug("nf_ct_h245: skblen = %u\n", skb->len); spin_lock_bh(&nf_h323_lock); @@ -1125,10 +1124,9 @@ static int q931_help(struct sk_buff *skb, unsigned int protoff, int ret; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) { + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; - } + pr_debug("nf_ct_q931: skblen = %u\n", skb->len); spin_lock_bh(&nf_h323_lock); diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index b394aa31877..4f9390b9869 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -125,8 +125,7 @@ static int help(struct sk_buff *skb, unsigned int protoff, return NF_ACCEPT; /* Until there's been traffic both ways, don't look in packets. */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; /* Not a full tcp header? */ diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 482e90c6185..7dec88a1755 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -970,7 +970,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_DUMP) return netlink_dump_start(ctnl, skb, nlh, ctnetlink_dump_table, - ctnetlink_done); + ctnetlink_done, 0); err = ctnetlink_parse_zone(cda[CTA_ZONE], &zone); if (err < 0) @@ -1840,7 +1840,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb, if (nlh->nlmsg_flags & NLM_F_DUMP) { return netlink_dump_start(ctnl, skb, nlh, ctnetlink_exp_dump_table, - ctnetlink_exp_done); + ctnetlink_exp_done, 0); } err = ctnetlink_parse_zone(cda[CTA_EXPECT_ZONE], &zone); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 088944824e1..2fd4565144d 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -519,8 +519,7 @@ conntrack_pptp_help(struct sk_buff *skb, unsigned int protoff, u_int16_t msg; /* don't do any tracking before tcp handshake complete */ - if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + if (ctinfo != IP_CT_ESTABLISHED && ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; nexthdr_off = protoff; diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index d9e27734b2a..8501823b3f9 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -78,7 +78,7 @@ static int help(struct sk_buff *skb, ct_sane_info = &nfct_help(ct)->help.ct_sane_info; /* Until there's been traffic both ways, don't look in packets. */ if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED+IP_CT_IS_REPLY) + ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; /* Not a full tcp header? */ diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index cb5a2858178..93faf6a3a63 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1423,7 +1423,7 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, typeof(nf_nat_sip_seq_adjust_hook) nf_nat_sip_seq_adjust; if (ctinfo != IP_CT_ESTABLISHED && - ctinfo != IP_CT_ESTABLISHED + IP_CT_IS_REPLY) + ctinfo != IP_CT_ESTABLISHED_REPLY) return NF_ACCEPT; /* No Data ? */ diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index b4a4532823e..1905976b513 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -37,7 +37,7 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_NETFILTER); static char __initdata nfversion[] = "0.30"; -static const struct nfnetlink_subsystem *subsys_table[NFNL_SUBSYS_COUNT]; +static const struct nfnetlink_subsystem __rcu *subsys_table[NFNL_SUBSYS_COUNT]; static DEFINE_MUTEX(nfnl_mutex); void nfnl_lock(void) @@ -59,7 +59,7 @@ int nfnetlink_subsys_register(const struct nfnetlink_subsystem *n) nfnl_unlock(); return -EBUSY; } - subsys_table[n->subsys_id] = n; + rcu_assign_pointer(subsys_table[n->subsys_id], n); nfnl_unlock(); return 0; @@ -71,7 +71,7 @@ int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n) nfnl_lock(); subsys_table[n->subsys_id] = NULL; nfnl_unlock(); - + synchronize_rcu(); return 0; } EXPORT_SYMBOL_GPL(nfnetlink_subsys_unregister); @@ -83,7 +83,7 @@ static inline const struct nfnetlink_subsystem *nfnetlink_get_subsys(u_int16_t t if (subsys_id >= NFNL_SUBSYS_COUNT) return NULL; - return subsys_table[subsys_id]; + return rcu_dereference(subsys_table[subsys_id]); } static inline const struct nfnl_callback * @@ -139,21 +139,27 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) type = nlh->nlmsg_type; replay: + rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) { #ifdef CONFIG_MODULES - nfnl_unlock(); + rcu_read_unlock(); request_module("nfnetlink-subsys-%d", NFNL_SUBSYS_ID(type)); - nfnl_lock(); + rcu_read_lock(); ss = nfnetlink_get_subsys(type); if (!ss) #endif + { + rcu_read_unlock(); return -EINVAL; + } } nc = nfnetlink_find_client(type, ss); - if (!nc) + if (!nc) { + rcu_read_unlock(); return -EINVAL; + } { int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg)); @@ -167,7 +173,23 @@ replay: if (err < 0) return err; - err = nc->call(net->nfnl, skb, nlh, (const struct nlattr **)cda); + if (nc->call_rcu) { + err = nc->call_rcu(net->nfnl, skb, nlh, + (const struct nlattr **)cda); + rcu_read_unlock(); + } else { + rcu_read_unlock(); + nfnl_lock(); + if (rcu_dereference_protected( + subsys_table[NFNL_SUBSYS_ID(type)], + lockdep_is_held(&nfnl_mutex)) != ss || + nfnetlink_find_client(type, ss) != nc) + err = -EAGAIN; + else + err = nc->call(net->nfnl, skb, nlh, + (const struct nlattr **)cda); + nfnl_unlock(); + } if (err == -EAGAIN) goto replay; return err; @@ -176,9 +198,7 @@ replay: static void nfnetlink_rcv(struct sk_buff *skb) { - nfnl_lock(); netlink_rcv_skb(skb, &nfnetlink_rcv_msg); - nfnl_unlock(); } static int __net_init nfnetlink_net_init(struct net *net) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index e0ee010935e..2e7ccbb43dd 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -456,7 +456,8 @@ __build_packet_message(struct nfulnl_instance *inst, if (skb->mark) NLA_PUT_BE32(inst->skb, NFULA_MARK, htonl(skb->mark)); - if (indev && skb->dev) { + if (indev && skb->dev && + skb->mac_header != skb->network_header) { struct nfulnl_msg_packet_hw phw; int len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index b83123f12b4..49132bddd73 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -58,7 +58,7 @@ struct nfqnl_instance { */ spinlock_t lock; unsigned int queue_total; - atomic_t id_sequence; /* 'sequence' of pkt ids */ + unsigned int id_sequence; /* 'sequence' of pkt ids */ struct list_head queue_list; /* packets in queue */ }; @@ -171,6 +171,13 @@ __enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) queue->queue_total++; } +static void +__dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry) +{ + list_del(&entry->list); + queue->queue_total--; +} + static struct nf_queue_entry * find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) { @@ -185,10 +192,8 @@ find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id) } } - if (entry) { - list_del(&entry->list); - queue->queue_total--; - } + if (entry) + __dequeue_entry(queue, entry); spin_unlock_bh(&queue->lock); @@ -213,13 +218,15 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data) static struct sk_buff * nfqnl_build_packet_message(struct nfqnl_instance *queue, - struct nf_queue_entry *entry) + struct nf_queue_entry *entry, + __be32 **packet_id_ptr) { sk_buff_data_t old_tail; size_t size; size_t data_len = 0; struct sk_buff *skb; - struct nfqnl_msg_packet_hdr pmsg; + struct nlattr *nla; + struct nfqnl_msg_packet_hdr *pmsg; struct nlmsghdr *nlh; struct nfgenmsg *nfmsg; struct sk_buff *entskb = entry->skb; @@ -272,12 +279,11 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, nfmsg->version = NFNETLINK_V0; nfmsg->res_id = htons(queue->queue_num); - entry->id = atomic_inc_return(&queue->id_sequence); - pmsg.packet_id = htonl(entry->id); - pmsg.hw_protocol = entskb->protocol; - pmsg.hook = entry->hook; - - NLA_PUT(skb, NFQA_PACKET_HDR, sizeof(pmsg), &pmsg); + nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg)); + pmsg = nla_data(nla); + pmsg->hw_protocol = entskb->protocol; + pmsg->hook = entry->hook; + *packet_id_ptr = &pmsg->packet_id; indev = entry->indev; if (indev) { @@ -335,7 +341,8 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue, if (entskb->mark) NLA_PUT_BE32(skb, NFQA_MARK, htonl(entskb->mark)); - if (indev && entskb->dev) { + if (indev && entskb->dev && + entskb->mac_header != entskb->network_header) { struct nfqnl_msg_packet_hw phw; int len = dev_parse_header(entskb, phw.hw_addr); if (len) { @@ -388,6 +395,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) struct sk_buff *nskb; struct nfqnl_instance *queue; int err = -ENOBUFS; + __be32 *packet_id_ptr; /* rcu_read_lock()ed by nf_hook_slow() */ queue = instance_lookup(queuenum); @@ -401,7 +409,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) goto err_out; } - nskb = nfqnl_build_packet_message(queue, entry); + nskb = nfqnl_build_packet_message(queue, entry, &packet_id_ptr); if (nskb == NULL) { err = -ENOMEM; goto err_out; @@ -420,6 +428,8 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) queue->queue_total); goto err_out_free_nskb; } + entry->id = ++queue->id_sequence; + *packet_id_ptr = htonl(entry->id); /* nfnetlink_unicast will either free the nskb or add it to a socket */ err = nfnetlink_unicast(nskb, &init_net, queue->peer_pid, MSG_DONTWAIT); @@ -607,6 +617,92 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = { [NFQA_PAYLOAD] = { .type = NLA_UNSPEC }, }; +static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = { + [NFQA_VERDICT_HDR] = { .len = sizeof(struct nfqnl_msg_verdict_hdr) }, + [NFQA_MARK] = { .type = NLA_U32 }, +}; + +static struct nfqnl_instance *verdict_instance_lookup(u16 queue_num, int nlpid) +{ + struct nfqnl_instance *queue; + + queue = instance_lookup(queue_num); + if (!queue) + return ERR_PTR(-ENODEV); + + if (queue->peer_pid != nlpid) + return ERR_PTR(-EPERM); + + return queue; +} + +static struct nfqnl_msg_verdict_hdr* +verdicthdr_get(const struct nlattr * const nfqa[]) +{ + struct nfqnl_msg_verdict_hdr *vhdr; + unsigned int verdict; + + if (!nfqa[NFQA_VERDICT_HDR]) + return NULL; + + vhdr = nla_data(nfqa[NFQA_VERDICT_HDR]); + verdict = ntohl(vhdr->verdict); + if ((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT) + return NULL; + return vhdr; +} + +static int nfq_id_after(unsigned int id, unsigned int max) +{ + return (int)(id - max) > 0; +} + +static int +nfqnl_recv_verdict_batch(struct sock *ctnl, struct sk_buff *skb, + const struct nlmsghdr *nlh, + const struct nlattr * const nfqa[]) +{ + struct nfgenmsg *nfmsg = NLMSG_DATA(nlh); + struct nf_queue_entry *entry, *tmp; + unsigned int verdict, maxid; + struct nfqnl_msg_verdict_hdr *vhdr; + struct nfqnl_instance *queue; + LIST_HEAD(batch_list); + u16 queue_num = ntohs(nfmsg->res_id); + + queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).pid); + if (IS_ERR(queue)) + return PTR_ERR(queue); + + vhdr = verdicthdr_get(nfqa); + if (!vhdr) + return -EINVAL; + + verdict = ntohl(vhdr->verdict); + maxid = ntohl(vhdr->id); + + spin_lock_bh(&queue->lock); + + list_for_each_entry_safe(entry, tmp, &queue->queue_list, list) { + if (nfq_id_after(entry->id, maxid)) + break; + __dequeue_entry(queue, entry); + list_add_tail(&entry->list, &batch_list); + } + + spin_unlock_bh(&queue->lock); + + if (list_empty(&batch_list)) + return -ENOENT; + + list_for_each_entry_safe(entry, tmp, &batch_list, list) { + if (nfqa[NFQA_MARK]) + entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK])); + nf_reinject(entry, verdict); + } + return 0; +} + static int nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, @@ -619,39 +715,23 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, struct nfqnl_instance *queue; unsigned int verdict; struct nf_queue_entry *entry; - int err; - rcu_read_lock(); queue = instance_lookup(queue_num); - if (!queue) { - err = -ENODEV; - goto err_out_unlock; - } + if (!queue) - if (queue->peer_pid != NETLINK_CB(skb).pid) { - err = -EPERM; - goto err_out_unlock; - } + queue = verdict_instance_lookup(queue_num, NETLINK_CB(skb).pid); + if (IS_ERR(queue)) + return PTR_ERR(queue); - if (!nfqa[NFQA_VERDICT_HDR]) { - err = -EINVAL; - goto err_out_unlock; - } + vhdr = verdicthdr_get(nfqa); + if (!vhdr) + return -EINVAL; - vhdr = nla_data(nfqa[NFQA_VERDICT_HDR]); verdict = ntohl(vhdr->verdict); - if ((verdict & NF_VERDICT_MASK) > NF_MAX_VERDICT) { - err = -EINVAL; - goto err_out_unlock; - } - entry = find_dequeue_entry(queue, ntohl(vhdr->id)); - if (entry == NULL) { - err = -ENOENT; - goto err_out_unlock; - } - rcu_read_unlock(); + if (entry == NULL) + return -ENOENT; if (nfqa[NFQA_PAYLOAD]) { if (nfqnl_mangle(nla_data(nfqa[NFQA_PAYLOAD]), @@ -664,10 +744,6 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb, nf_reinject(entry, verdict); return 0; - -err_out_unlock: - rcu_read_unlock(); - return err; } static int @@ -780,14 +856,17 @@ err_out_unlock: } static const struct nfnl_callback nfqnl_cb[NFQNL_MSG_MAX] = { - [NFQNL_MSG_PACKET] = { .call = nfqnl_recv_unsupp, + [NFQNL_MSG_PACKET] = { .call_rcu = nfqnl_recv_unsupp, .attr_count = NFQA_MAX, }, - [NFQNL_MSG_VERDICT] = { .call = nfqnl_recv_verdict, + [NFQNL_MSG_VERDICT] = { .call_rcu = nfqnl_recv_verdict, .attr_count = NFQA_MAX, .policy = nfqa_verdict_policy }, [NFQNL_MSG_CONFIG] = { .call = nfqnl_recv_config, .attr_count = NFQA_CFG_MAX, .policy = nfqa_cfg_policy }, + [NFQNL_MSG_VERDICT_BATCH]={ .call_rcu = nfqnl_recv_verdict_batch, + .attr_count = NFQA_MAX, + .policy = nfqa_verdict_batch_policy }, }; static const struct nfnetlink_subsystem nfqnl_subsys = { @@ -869,7 +948,7 @@ static int seq_show(struct seq_file *s, void *v) inst->peer_pid, inst->queue_total, inst->copy_mode, inst->copy_range, inst->queue_dropped, inst->queue_user_dropped, - atomic_read(&inst->id_sequence), 1); + inst->id_sequence, 1); } static const struct seq_operations nfqnl_seq_ops = { diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c index 363a99ec063..4bca15a0c38 100644 --- a/net/netfilter/xt_AUDIT.c +++ b/net/netfilter/xt_AUDIT.c @@ -163,6 +163,11 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par) break; } +#ifdef CONFIG_NETWORK_SECMARK + if (skb->secmark) + audit_log_secctx(ab, skb->secmark); +#endif + audit_log_end(ab); errout: diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 782e51986a6..0221d10de75 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -5,7 +5,7 @@ * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ - +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/gfp.h> #include <linux/skbuff.h> @@ -95,8 +95,11 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par) if (info->helper[0]) { ret = -ENOENT; proto = xt_ct_find_proto(par); - if (!proto) + if (!proto) { + pr_info("You must specify a L4 protocol, " + "and not use inversions on it.\n"); goto err3; + } ret = -ENOMEM; help = nf_ct_helper_ext_add(ct, GFP_KERNEL); @@ -107,8 +110,10 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par) help->helper = nf_conntrack_helper_try_module_get(info->helper, par->family, proto); - if (help->helper == NULL) + if (help->helper == NULL) { + pr_info("No such helper \"%s\"\n", info->helper); goto err3; + } } __set_bit(IPS_TEMPLATE_BIT, &ct->status); diff --git a/net/netfilter/xt_HL.c b/net/netfilter/xt_HL.c index 95b084800fc..1535e87ed9b 100644 --- a/net/netfilter/xt_HL.c +++ b/net/netfilter/xt_HL.c @@ -38,22 +38,22 @@ ttl_tg(struct sk_buff *skb, const struct xt_action_param *par) iph = ip_hdr(skb); switch (info->mode) { - case IPT_TTL_SET: - new_ttl = info->ttl; - break; - case IPT_TTL_INC: - new_ttl = iph->ttl + info->ttl; - if (new_ttl > 255) - new_ttl = 255; - break; - case IPT_TTL_DEC: - new_ttl = iph->ttl - info->ttl; - if (new_ttl < 0) - new_ttl = 0; - break; - default: - new_ttl = iph->ttl; - break; + case IPT_TTL_SET: + new_ttl = info->ttl; + break; + case IPT_TTL_INC: + new_ttl = iph->ttl + info->ttl; + if (new_ttl > 255) + new_ttl = 255; + break; + case IPT_TTL_DEC: + new_ttl = iph->ttl - info->ttl; + if (new_ttl < 0) + new_ttl = 0; + break; + default: + new_ttl = iph->ttl; + break; } if (new_ttl != iph->ttl) { @@ -78,22 +78,22 @@ hl_tg6(struct sk_buff *skb, const struct xt_action_param *par) ip6h = ipv6_hdr(skb); switch (info->mode) { - case IP6T_HL_SET: - new_hl = info->hop_limit; - break; - case IP6T_HL_INC: - new_hl = ip6h->hop_limit + info->hop_limit; - if (new_hl > 255) - new_hl = 255; - break; - case IP6T_HL_DEC: - new_hl = ip6h->hop_limit - info->hop_limit; - if (new_hl < 0) - new_hl = 0; - break; - default: - new_hl = ip6h->hop_limit; - break; + case IP6T_HL_SET: + new_hl = info->hop_limit; + break; + case IP6T_HL_INC: + new_hl = ip6h->hop_limit + info->hop_limit; + if (new_hl > 255) + new_hl = 255; + break; + case IP6T_HL_DEC: + new_hl = ip6h->hop_limit - info->hop_limit; + if (new_hl < 0) + new_hl = 0; + break; + default: + new_hl = ip6h->hop_limit; + break; } ip6h->hop_limit = new_hl; diff --git a/net/netfilter/xt_RATEEST.c b/net/netfilter/xt_RATEEST.c index de079abd5bc..f264032b8c5 100644 --- a/net/netfilter/xt_RATEEST.c +++ b/net/netfilter/xt_RATEEST.c @@ -60,11 +60,6 @@ struct xt_rateest *xt_rateest_lookup(const char *name) } EXPORT_SYMBOL_GPL(xt_rateest_lookup); -static void xt_rateest_free_rcu(struct rcu_head *head) -{ - kfree(container_of(head, struct xt_rateest, rcu)); -} - void xt_rateest_put(struct xt_rateest *est) { mutex_lock(&xt_rateest_mutex); @@ -75,7 +70,7 @@ void xt_rateest_put(struct xt_rateest *est) * gen_estimator est_timer() might access est->lock or bstats, * wait a RCU grace period before freeing 'est' */ - call_rcu(&est->rcu, xt_rateest_free_rcu); + kfree_rcu(est, rcu); } mutex_unlock(&xt_rateest_mutex); } @@ -188,7 +183,6 @@ static int __init xt_rateest_tg_init(void) static void __exit xt_rateest_tg_fini(void) { xt_unregister_target(&xt_rateest_tg_reg); - rcu_barrier(); /* Wait for completion of call_rcu()'s (xt_rateest_free_rcu) */ } diff --git a/net/netfilter/xt_hl.c b/net/netfilter/xt_hl.c index 7d12221ead8..003951149c9 100644 --- a/net/netfilter/xt_hl.c +++ b/net/netfilter/xt_hl.c @@ -31,14 +31,14 @@ static bool ttl_mt(const struct sk_buff *skb, struct xt_action_param *par) const u8 ttl = ip_hdr(skb)->ttl; switch (info->mode) { - case IPT_TTL_EQ: - return ttl == info->ttl; - case IPT_TTL_NE: - return ttl != info->ttl; - case IPT_TTL_LT: - return ttl < info->ttl; - case IPT_TTL_GT: - return ttl > info->ttl; + case IPT_TTL_EQ: + return ttl == info->ttl; + case IPT_TTL_NE: + return ttl != info->ttl; + case IPT_TTL_LT: + return ttl < info->ttl; + case IPT_TTL_GT: + return ttl > info->ttl; } return false; @@ -50,14 +50,14 @@ static bool hl_mt6(const struct sk_buff *skb, struct xt_action_param *par) const struct ipv6hdr *ip6h = ipv6_hdr(skb); switch (info->mode) { - case IP6T_HL_EQ: - return ip6h->hop_limit == info->hop_limit; - case IP6T_HL_NE: - return ip6h->hop_limit != info->hop_limit; - case IP6T_HL_LT: - return ip6h->hop_limit < info->hop_limit; - case IP6T_HL_GT: - return ip6h->hop_limit > info->hop_limit; + case IP6T_HL_EQ: + return ip6h->hop_limit == info->hop_limit; + case IP6T_HL_NE: + return ip6h->hop_limit != info->hop_limit; + case IP6T_HL_LT: + return ip6h->hop_limit < info->hop_limit; + case IP6T_HL_GT: + return ip6h->hop_limit > info->hop_limit; } return false; diff --git a/net/netfilter/xt_set.c b/net/netfilter/xt_set.c index b3babaed771..0ec8138aa47 100644 --- a/net/netfilter/xt_set.c +++ b/net/netfilter/xt_set.c @@ -13,7 +13,6 @@ #include <linux/module.h> #include <linux/skbuff.h> -#include <linux/version.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_set.h> @@ -29,23 +28,33 @@ MODULE_ALIAS("ip6t_SET"); static inline int match_set(ip_set_id_t index, const struct sk_buff *skb, - u8 pf, u8 dim, u8 flags, int inv) + const struct xt_action_param *par, + const struct ip_set_adt_opt *opt, int inv) { - if (ip_set_test(index, skb, pf, dim, flags)) + if (ip_set_test(index, skb, par, opt)) inv = !inv; return inv; } +#define ADT_OPT(n, f, d, fs, cfs, t) \ +const struct ip_set_adt_opt n = { \ + .family = f, \ + .dim = d, \ + .flags = fs, \ + .cmdflags = cfs, \ + .timeout = t, \ +} + /* Revision 0 interface: backward compatible with netfilter/iptables */ static bool set_match_v0(const struct sk_buff *skb, struct xt_action_param *par) { const struct xt_set_info_match_v0 *info = par->matchinfo; + ADT_OPT(opt, par->family, info->match_set.u.compat.dim, + info->match_set.u.compat.flags, 0, UINT_MAX); - return match_set(info->match_set.index, skb, par->family, - info->match_set.u.compat.dim, - info->match_set.u.compat.flags, + return match_set(info->match_set.index, skb, par, &opt, info->match_set.u.compat.flags & IPSET_INV_MATCH); } @@ -103,15 +112,15 @@ static unsigned int set_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_set_info_target_v0 *info = par->targinfo; + ADT_OPT(add_opt, par->family, info->add_set.u.compat.dim, + info->add_set.u.compat.flags, 0, UINT_MAX); + ADT_OPT(del_opt, par->family, info->del_set.u.compat.dim, + info->del_set.u.compat.flags, 0, UINT_MAX); if (info->add_set.index != IPSET_INVALID_ID) - ip_set_add(info->add_set.index, skb, par->family, - info->add_set.u.compat.dim, - info->add_set.u.compat.flags); + ip_set_add(info->add_set.index, skb, par, &add_opt); if (info->del_set.index != IPSET_INVALID_ID) - ip_set_del(info->del_set.index, skb, par->family, - info->del_set.u.compat.dim, - info->del_set.u.compat.flags); + ip_set_del(info->del_set.index, skb, par, &del_opt); return XT_CONTINUE; } @@ -170,23 +179,23 @@ set_target_v0_destroy(const struct xt_tgdtor_param *par) ip_set_nfnl_put(info->del_set.index); } -/* Revision 1: current interface to netfilter/iptables */ +/* Revision 1 match and target */ static bool -set_match(const struct sk_buff *skb, struct xt_action_param *par) +set_match_v1(const struct sk_buff *skb, struct xt_action_param *par) { - const struct xt_set_info_match *info = par->matchinfo; + const struct xt_set_info_match_v1 *info = par->matchinfo; + ADT_OPT(opt, par->family, info->match_set.dim, + info->match_set.flags, 0, UINT_MAX); - return match_set(info->match_set.index, skb, par->family, - info->match_set.dim, - info->match_set.flags, + return match_set(info->match_set.index, skb, par, &opt, info->match_set.flags & IPSET_INV_MATCH); } static int -set_match_checkentry(const struct xt_mtchk_param *par) +set_match_v1_checkentry(const struct xt_mtchk_param *par) { - struct xt_set_info_match *info = par->matchinfo; + struct xt_set_info_match_v1 *info = par->matchinfo; ip_set_id_t index; index = ip_set_nfnl_get_byindex(info->match_set.index); @@ -207,36 +216,34 @@ set_match_checkentry(const struct xt_mtchk_param *par) } static void -set_match_destroy(const struct xt_mtdtor_param *par) +set_match_v1_destroy(const struct xt_mtdtor_param *par) { - struct xt_set_info_match *info = par->matchinfo; + struct xt_set_info_match_v1 *info = par->matchinfo; ip_set_nfnl_put(info->match_set.index); } static unsigned int -set_target(struct sk_buff *skb, const struct xt_action_param *par) +set_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_set_info_target *info = par->targinfo; + const struct xt_set_info_target_v1 *info = par->targinfo; + ADT_OPT(add_opt, par->family, info->add_set.dim, + info->add_set.flags, 0, UINT_MAX); + ADT_OPT(del_opt, par->family, info->del_set.dim, + info->del_set.flags, 0, UINT_MAX); if (info->add_set.index != IPSET_INVALID_ID) - ip_set_add(info->add_set.index, - skb, par->family, - info->add_set.dim, - info->add_set.flags); + ip_set_add(info->add_set.index, skb, par, &add_opt); if (info->del_set.index != IPSET_INVALID_ID) - ip_set_del(info->del_set.index, - skb, par->family, - info->del_set.dim, - info->del_set.flags); + ip_set_del(info->del_set.index, skb, par, &del_opt); return XT_CONTINUE; } static int -set_target_checkentry(const struct xt_tgchk_param *par) +set_target_v1_checkentry(const struct xt_tgchk_param *par) { - const struct xt_set_info_target *info = par->targinfo; + const struct xt_set_info_target_v1 *info = par->targinfo; ip_set_id_t index; if (info->add_set.index != IPSET_INVALID_ID) { @@ -273,9 +280,9 @@ set_target_checkentry(const struct xt_tgchk_param *par) } static void -set_target_destroy(const struct xt_tgdtor_param *par) +set_target_v1_destroy(const struct xt_tgdtor_param *par) { - const struct xt_set_info_target *info = par->targinfo; + const struct xt_set_info_target_v1 *info = par->targinfo; if (info->add_set.index != IPSET_INVALID_ID) ip_set_nfnl_put(info->add_set.index); @@ -283,6 +290,28 @@ set_target_destroy(const struct xt_tgdtor_param *par) ip_set_nfnl_put(info->del_set.index); } +/* Revision 2 target */ + +static unsigned int +set_target_v2(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_set_info_target_v2 *info = par->targinfo; + ADT_OPT(add_opt, par->family, info->add_set.dim, + info->add_set.flags, info->flags, info->timeout); + ADT_OPT(del_opt, par->family, info->del_set.dim, + info->del_set.flags, 0, UINT_MAX); + + if (info->add_set.index != IPSET_INVALID_ID) + ip_set_add(info->add_set.index, skb, par, &add_opt); + if (info->del_set.index != IPSET_INVALID_ID) + ip_set_del(info->del_set.index, skb, par, &del_opt); + + return XT_CONTINUE; +} + +#define set_target_v2_checkentry set_target_v1_checkentry +#define set_target_v2_destroy set_target_v1_destroy + static struct xt_match set_matches[] __read_mostly = { { .name = "set", @@ -298,20 +327,20 @@ static struct xt_match set_matches[] __read_mostly = { .name = "set", .family = NFPROTO_IPV4, .revision = 1, - .match = set_match, - .matchsize = sizeof(struct xt_set_info_match), - .checkentry = set_match_checkentry, - .destroy = set_match_destroy, + .match = set_match_v1, + .matchsize = sizeof(struct xt_set_info_match_v1), + .checkentry = set_match_v1_checkentry, + .destroy = set_match_v1_destroy, .me = THIS_MODULE }, { .name = "set", .family = NFPROTO_IPV6, .revision = 1, - .match = set_match, - .matchsize = sizeof(struct xt_set_info_match), - .checkentry = set_match_checkentry, - .destroy = set_match_destroy, + .match = set_match_v1, + .matchsize = sizeof(struct xt_set_info_match_v1), + .checkentry = set_match_v1_checkentry, + .destroy = set_match_v1_destroy, .me = THIS_MODULE }, }; @@ -331,20 +360,40 @@ static struct xt_target set_targets[] __read_mostly = { .name = "SET", .revision = 1, .family = NFPROTO_IPV4, - .target = set_target, - .targetsize = sizeof(struct xt_set_info_target), - .checkentry = set_target_checkentry, - .destroy = set_target_destroy, + .target = set_target_v1, + .targetsize = sizeof(struct xt_set_info_target_v1), + .checkentry = set_target_v1_checkentry, + .destroy = set_target_v1_destroy, .me = THIS_MODULE }, { .name = "SET", .revision = 1, .family = NFPROTO_IPV6, - .target = set_target, - .targetsize = sizeof(struct xt_set_info_target), - .checkentry = set_target_checkentry, - .destroy = set_target_destroy, + .target = set_target_v1, + .targetsize = sizeof(struct xt_set_info_target_v1), + .checkentry = set_target_v1_checkentry, + .destroy = set_target_v1_destroy, + .me = THIS_MODULE + }, + { + .name = "SET", + .revision = 2, + .family = NFPROTO_IPV4, + .target = set_target_v2, + .targetsize = sizeof(struct xt_set_info_target_v2), + .checkentry = set_target_v2_checkentry, + .destroy = set_target_v2_destroy, + .me = THIS_MODULE + }, + { + .name = "SET", + .revision = 2, + .family = NFPROTO_IPV6, + .target = set_target_v2, + .targetsize = sizeof(struct xt_set_info_target_v2), + .checkentry = set_target_v2_checkentry, + .destroy = set_target_v2_destroy, .me = THIS_MODULE }, }; diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c index 9cc46356b57..fe39f7e913d 100644 --- a/net/netfilter/xt_socket.c +++ b/net/netfilter/xt_socket.c @@ -143,9 +143,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par, ct = nf_ct_get(skb, &ctinfo); if (ct && !nf_ct_is_untracked(ct) && ((iph->protocol != IPPROTO_ICMP && - ctinfo == IP_CT_IS_REPLY + IP_CT_ESTABLISHED) || + ctinfo == IP_CT_ESTABLISHED_REPLY) || (iph->protocol == IPPROTO_ICMP && - ctinfo == IP_CT_IS_REPLY + IP_CT_RELATED)) && + ctinfo == IP_CT_RELATED_REPLY)) && (ct->status & IPS_SRC_NAT_DONE)) { daddr = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip; diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 9c38658fba8..8efd061a0ae 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -426,10 +426,9 @@ int netlbl_unlhsh_add(struct net *net, audit_info); switch (addr_len) { case sizeof(struct in_addr): { - struct in_addr *addr4, *mask4; + const struct in_addr *addr4 = addr; + const struct in_addr *mask4 = mask; - addr4 = (struct in_addr *)addr; - mask4 = (struct in_addr *)mask; ret_val = netlbl_unlhsh_add_addr4(iface, addr4, mask4, secid); if (audit_buf != NULL) netlbl_af4list_audit_addr(audit_buf, 1, @@ -440,10 +439,9 @@ int netlbl_unlhsh_add(struct net *net, } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) case sizeof(struct in6_addr): { - struct in6_addr *addr6, *mask6; + const struct in6_addr *addr6 = addr; + const struct in6_addr *mask6 = mask; - addr6 = (struct in6_addr *)addr; - mask6 = (struct in6_addr *)mask; ret_val = netlbl_unlhsh_add_addr6(iface, addr6, mask6, secid); if (audit_buf != NULL) netlbl_af6list_audit_addr(audit_buf, 1, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 6ef64adf736..0a4db0211da 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1659,13 +1659,10 @@ static int netlink_dump(struct sock *sk) { struct netlink_sock *nlk = nlk_sk(sk); struct netlink_callback *cb; - struct sk_buff *skb; + struct sk_buff *skb = NULL; struct nlmsghdr *nlh; int len, err = -ENOBUFS; - - skb = sock_rmalloc(sk, NLMSG_GOODSIZE, 0, GFP_KERNEL); - if (!skb) - goto errout; + int alloc_size; mutex_lock(nlk->cb_mutex); @@ -1675,6 +1672,12 @@ static int netlink_dump(struct sock *sk) goto errout_skb; } + alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE); + + skb = sock_rmalloc(sk, alloc_size, 0, GFP_KERNEL); + if (!skb) + goto errout_skb; + len = cb->dump(skb, cb); if (len > 0) { @@ -1693,6 +1696,8 @@ static int netlink_dump(struct sock *sk) if (!nlh) goto errout_skb; + nl_dump_check_consistent(cb, nlh); + memcpy(nlmsg_data(nlh), &len, sizeof(len)); if (sk_filter(sk, skb)) @@ -1713,7 +1718,6 @@ static int netlink_dump(struct sock *sk) errout_skb: mutex_unlock(nlk->cb_mutex); kfree_skb(skb); -errout: return err; } @@ -1721,7 +1725,8 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, const struct nlmsghdr *nlh, int (*dump)(struct sk_buff *skb, struct netlink_callback *), - int (*done)(struct netlink_callback *)) + int (*done)(struct netlink_callback *), + u16 min_dump_alloc) { struct netlink_callback *cb; struct sock *sk; @@ -1735,6 +1740,7 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb, cb->dump = dump; cb->done = done; cb->nlh = nlh; + cb->min_dump_alloc = min_dump_alloc; atomic_inc(&skb->users); cb->skb = skb; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index 1781d99145e..482fa571b4e 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -525,7 +525,7 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) genl_unlock(); err = netlink_dump_start(net->genl_sock, skb, nlh, - ops->dumpit, ops->done); + ops->dumpit, ops->done, 0); genl_lock(); return err; } diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 44059d0c8dd..cd5ddb2ebc4 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -257,9 +257,12 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, case 3: if (nr_node->routes[1].quality > nr_node->routes[0].quality) { switch (nr_node->which) { - case 0: nr_node->which = 1; break; - case 1: nr_node->which = 0; break; - default: break; + case 0: + nr_node->which = 1; + break; + case 1: + nr_node->which = 0; + break; } nr_route = nr_node->routes[0]; nr_node->routes[0] = nr_node->routes[1]; @@ -505,12 +508,13 @@ static int nr_dec_obs(void) s->count--; switch (i) { - case 0: - s->routes[0] = s->routes[1]; - case 1: - s->routes[1] = s->routes[2]; - case 2: - break; + case 0: + s->routes[0] = s->routes[1]; + /* Fallthrough */ + case 1: + s->routes[1] = s->routes[2]; + case 2: + break; } break; diff --git a/net/nfc/Kconfig b/net/nfc/Kconfig new file mode 100644 index 00000000000..33e095b124b --- /dev/null +++ b/net/nfc/Kconfig @@ -0,0 +1,16 @@ +# +# NFC sybsystem configuration +# + +menuconfig NFC + depends on NET && EXPERIMENTAL + tristate "NFC subsystem support (EXPERIMENTAL)" + default n + help + Say Y here if you want to build support for NFC (Near field + communication) devices. + + To compile this support as a module, choose M here: the module will + be called nfc. + +source "drivers/nfc/Kconfig" diff --git a/net/nfc/Makefile b/net/nfc/Makefile new file mode 100644 index 00000000000..16250c35385 --- /dev/null +++ b/net/nfc/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for the Linux NFC subsystem. +# + +obj-$(CONFIG_NFC) += nfc.o + +nfc-objs := core.o netlink.o af_nfc.o rawsock.o diff --git a/net/nfc/af_nfc.c b/net/nfc/af_nfc.c new file mode 100644 index 00000000000..e982cef8f49 --- /dev/null +++ b/net/nfc/af_nfc.c @@ -0,0 +1,98 @@ +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> + * Lauro Ramos Venancio <lauro.venancio@openbossa.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include <linux/nfc.h> + +#include "nfc.h" + +static DEFINE_RWLOCK(proto_tab_lock); +static const struct nfc_protocol *proto_tab[NFC_SOCKPROTO_MAX]; + +static int nfc_sock_create(struct net *net, struct socket *sock, int proto, + int kern) +{ + int rc = -EPROTONOSUPPORT; + + if (net != &init_net) + return -EAFNOSUPPORT; + + if (proto < 0 || proto >= NFC_SOCKPROTO_MAX) + return -EINVAL; + + read_lock(&proto_tab_lock); + if (proto_tab[proto] && try_module_get(proto_tab[proto]->owner)) { + rc = proto_tab[proto]->create(net, sock, proto_tab[proto]); + module_put(proto_tab[proto]->owner); + } + read_unlock(&proto_tab_lock); + + return rc; +} + +static struct net_proto_family nfc_sock_family_ops = { + .owner = THIS_MODULE, + .family = PF_NFC, + .create = nfc_sock_create, +}; + +int nfc_proto_register(const struct nfc_protocol *nfc_proto) +{ + int rc; + + if (nfc_proto->id < 0 || nfc_proto->id >= NFC_SOCKPROTO_MAX) + return -EINVAL; + + rc = proto_register(nfc_proto->proto, 0); + if (rc) + return rc; + + write_lock(&proto_tab_lock); + if (proto_tab[nfc_proto->id]) + rc = -EBUSY; + else + proto_tab[nfc_proto->id] = nfc_proto; + write_unlock(&proto_tab_lock); + + return rc; +} +EXPORT_SYMBOL(nfc_proto_register); + +void nfc_proto_unregister(const struct nfc_protocol *nfc_proto) +{ + write_lock(&proto_tab_lock); + proto_tab[nfc_proto->id] = NULL; + write_unlock(&proto_tab_lock); + + proto_unregister(nfc_proto->proto); +} +EXPORT_SYMBOL(nfc_proto_unregister); + +int __init af_nfc_init(void) +{ + return sock_register(&nfc_sock_family_ops); +} + +void af_nfc_exit(void) +{ + sock_unregister(PF_NFC); +} diff --git a/net/nfc/core.c b/net/nfc/core.c new file mode 100644 index 00000000000..b6fd4e1f205 --- /dev/null +++ b/net/nfc/core.c @@ -0,0 +1,468 @@ +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Lauro Ramos Venancio <lauro.venancio@openbossa.org> + * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/slab.h> + +#include "nfc.h" + +#define VERSION "0.1" + +int nfc_devlist_generation; +DEFINE_MUTEX(nfc_devlist_mutex); + +int nfc_printk(const char *level, const char *format, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + r = printk("%sNFC: %pV\n", level, &vaf); + + va_end(args); + + return r; +} +EXPORT_SYMBOL(nfc_printk); + +/** + * nfc_start_poll - start polling for nfc targets + * + * @dev: The nfc device that must start polling + * @protocols: bitset of nfc protocols that must be used for polling + * + * The device remains polling for targets until a target is found or + * the nfc_stop_poll function is called. + */ +int nfc_start_poll(struct nfc_dev *dev, u32 protocols) +{ + int rc; + + nfc_dbg("dev_name=%s protocols=0x%x", dev_name(&dev->dev), protocols); + + if (!protocols) + return -EINVAL; + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + goto error; + } + + if (dev->polling) { + rc = -EBUSY; + goto error; + } + + rc = dev->ops->start_poll(dev, protocols); + if (!rc) + dev->polling = true; + +error: + device_unlock(&dev->dev); + return rc; +} + +/** + * nfc_stop_poll - stop polling for nfc targets + * + * @dev: The nfc device that must stop polling + */ +int nfc_stop_poll(struct nfc_dev *dev) +{ + int rc = 0; + + nfc_dbg("dev_name=%s", dev_name(&dev->dev)); + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + goto error; + } + + if (!dev->polling) { + rc = -EINVAL; + goto error; + } + + dev->ops->stop_poll(dev); + dev->polling = false; + +error: + device_unlock(&dev->dev); + return rc; +} + +/** + * nfc_activate_target - prepare the target for data exchange + * + * @dev: The nfc device that found the target + * @target_idx: index of the target that must be activated + * @protocol: nfc protocol that will be used for data exchange + */ +int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol) +{ + int rc; + + nfc_dbg("dev_name=%s target_idx=%u protocol=%u", dev_name(&dev->dev), + target_idx, protocol); + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + goto error; + } + + rc = dev->ops->activate_target(dev, target_idx, protocol); + +error: + device_unlock(&dev->dev); + return rc; +} + +/** + * nfc_deactivate_target - deactivate a nfc target + * + * @dev: The nfc device that found the target + * @target_idx: index of the target that must be deactivated + */ +int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx) +{ + int rc = 0; + + nfc_dbg("dev_name=%s target_idx=%u", dev_name(&dev->dev), target_idx); + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + goto error; + } + + dev->ops->deactivate_target(dev, target_idx); + +error: + device_unlock(&dev->dev); + return rc; +} + +/** + * nfc_data_exchange - transceive data + * + * @dev: The nfc device that found the target + * @target_idx: index of the target + * @skb: data to be sent + * @cb: callback called when the response is received + * @cb_context: parameter for the callback function + * + * The user must wait for the callback before calling this function again. + */ +int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, + struct sk_buff *skb, + data_exchange_cb_t cb, + void *cb_context) +{ + int rc; + + nfc_dbg("dev_name=%s target_idx=%u skb->len=%u", dev_name(&dev->dev), + target_idx, skb->len); + + device_lock(&dev->dev); + + if (!device_is_registered(&dev->dev)) { + rc = -ENODEV; + kfree_skb(skb); + goto error; + } + + rc = dev->ops->data_exchange(dev, target_idx, skb, cb, cb_context); + +error: + device_unlock(&dev->dev); + return rc; +} + +/** + * nfc_alloc_skb - allocate a skb for data exchange responses + * + * @size: size to allocate + * @gfp: gfp flags + */ +struct sk_buff *nfc_alloc_skb(unsigned int size, gfp_t gfp) +{ + struct sk_buff *skb; + unsigned int total_size; + + total_size = size + 1; + skb = alloc_skb(total_size, gfp); + + if (skb) + skb_reserve(skb, 1); + + return skb; +} +EXPORT_SYMBOL(nfc_alloc_skb); + +/** + * nfc_targets_found - inform that targets were found + * + * @dev: The nfc device that found the targets + * @targets: array of nfc targets found + * @ntargets: targets array size + * + * The device driver must call this function when one or many nfc targets + * are found. After calling this function, the device driver must stop + * polling for targets. + */ +int nfc_targets_found(struct nfc_dev *dev, struct nfc_target *targets, + int n_targets) +{ + int i; + + nfc_dbg("dev_name=%s n_targets=%d", dev_name(&dev->dev), n_targets); + + dev->polling = false; + + for (i = 0; i < n_targets; i++) + targets[i].idx = dev->target_idx++; + + spin_lock_bh(&dev->targets_lock); + + dev->targets_generation++; + + kfree(dev->targets); + dev->targets = kmemdup(targets, n_targets * sizeof(struct nfc_target), + GFP_ATOMIC); + + if (!dev->targets) { + dev->n_targets = 0; + spin_unlock_bh(&dev->targets_lock); + return -ENOMEM; + } + + dev->n_targets = n_targets; + spin_unlock_bh(&dev->targets_lock); + + nfc_genl_targets_found(dev); + + return 0; +} +EXPORT_SYMBOL(nfc_targets_found); + +static void nfc_release(struct device *d) +{ + struct nfc_dev *dev = to_nfc_dev(d); + + nfc_dbg("dev_name=%s", dev_name(&dev->dev)); + + nfc_genl_data_exit(&dev->genl_data); + kfree(dev->targets); + kfree(dev); +} + +struct class nfc_class = { + .name = "nfc", + .dev_release = nfc_release, +}; +EXPORT_SYMBOL(nfc_class); + +static int match_idx(struct device *d, void *data) +{ + struct nfc_dev *dev = to_nfc_dev(d); + unsigned *idx = data; + + return dev->idx == *idx; +} + +struct nfc_dev *nfc_get_device(unsigned idx) +{ + struct device *d; + + d = class_find_device(&nfc_class, NULL, &idx, match_idx); + if (!d) + return NULL; + + return to_nfc_dev(d); +} + +/** + * nfc_allocate_device - allocate a new nfc device + * + * @ops: device operations + * @supported_protocols: NFC protocols supported by the device + */ +struct nfc_dev *nfc_allocate_device(struct nfc_ops *ops, + u32 supported_protocols) +{ + static atomic_t dev_no = ATOMIC_INIT(0); + struct nfc_dev *dev; + + if (!ops->start_poll || !ops->stop_poll || !ops->activate_target || + !ops->deactivate_target || !ops->data_exchange) + return NULL; + + if (!supported_protocols) + return NULL; + + dev = kzalloc(sizeof(struct nfc_dev), GFP_KERNEL); + if (!dev) + return NULL; + + dev->dev.class = &nfc_class; + dev->idx = atomic_inc_return(&dev_no) - 1; + dev_set_name(&dev->dev, "nfc%d", dev->idx); + device_initialize(&dev->dev); + + dev->ops = ops; + dev->supported_protocols = supported_protocols; + + spin_lock_init(&dev->targets_lock); + nfc_genl_data_init(&dev->genl_data); + + /* first generation must not be 0 */ + dev->targets_generation = 1; + + return dev; +} +EXPORT_SYMBOL(nfc_allocate_device); + +/** + * nfc_register_device - register a nfc device in the nfc subsystem + * + * @dev: The nfc device to register + */ +int nfc_register_device(struct nfc_dev *dev) +{ + int rc; + + nfc_dbg("dev_name=%s", dev_name(&dev->dev)); + + mutex_lock(&nfc_devlist_mutex); + nfc_devlist_generation++; + rc = device_add(&dev->dev); + mutex_unlock(&nfc_devlist_mutex); + + if (rc < 0) + return rc; + + rc = nfc_genl_device_added(dev); + if (rc) + nfc_dbg("The userspace won't be notified that the device %s was" + " added", dev_name(&dev->dev)); + + + return 0; +} +EXPORT_SYMBOL(nfc_register_device); + +/** + * nfc_unregister_device - unregister a nfc device in the nfc subsystem + * + * @dev: The nfc device to unregister + */ +void nfc_unregister_device(struct nfc_dev *dev) +{ + int rc; + + nfc_dbg("dev_name=%s", dev_name(&dev->dev)); + + mutex_lock(&nfc_devlist_mutex); + nfc_devlist_generation++; + + /* lock to avoid unregistering a device while an operation + is in progress */ + device_lock(&dev->dev); + device_del(&dev->dev); + device_unlock(&dev->dev); + + mutex_unlock(&nfc_devlist_mutex); + + rc = nfc_genl_device_removed(dev); + if (rc) + nfc_dbg("The userspace won't be notified that the device %s" + " was removed", dev_name(&dev->dev)); + +} +EXPORT_SYMBOL(nfc_unregister_device); + +static int __init nfc_init(void) +{ + int rc; + + nfc_info("NFC Core ver %s", VERSION); + + rc = class_register(&nfc_class); + if (rc) + return rc; + + rc = nfc_genl_init(); + if (rc) + goto err_genl; + + /* the first generation must not be 0 */ + nfc_devlist_generation = 1; + + rc = rawsock_init(); + if (rc) + goto err_rawsock; + + rc = af_nfc_init(); + if (rc) + goto err_af_nfc; + + return 0; + +err_af_nfc: + rawsock_exit(); +err_rawsock: + nfc_genl_exit(); +err_genl: + class_unregister(&nfc_class); + return rc; +} + +static void __exit nfc_exit(void) +{ + af_nfc_exit(); + rawsock_exit(); + nfc_genl_exit(); + class_unregister(&nfc_class); +} + +subsys_initcall(nfc_init); +module_exit(nfc_exit); + +MODULE_AUTHOR("Lauro Ramos Venancio <lauro.venancio@openbossa.org>"); +MODULE_DESCRIPTION("NFC Core ver " VERSION); +MODULE_VERSION(VERSION); +MODULE_LICENSE("GPL"); diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c new file mode 100644 index 00000000000..ccdff7953f7 --- /dev/null +++ b/net/nfc/netlink.c @@ -0,0 +1,537 @@ +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Lauro Ramos Venancio <lauro.venancio@openbossa.org> + * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include <net/genetlink.h> +#include <linux/nfc.h> +#include <linux/slab.h> + +#include "nfc.h" + +static struct genl_multicast_group nfc_genl_event_mcgrp = { + .name = NFC_GENL_MCAST_EVENT_NAME, +}; + +struct genl_family nfc_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = NFC_GENL_NAME, + .version = NFC_GENL_VERSION, + .maxattr = NFC_ATTR_MAX, +}; + +static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { + [NFC_ATTR_DEVICE_INDEX] = { .type = NLA_U32 }, + [NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING, + .len = NFC_DEVICE_NAME_MAXSIZE }, + [NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 }, +}; + +static int nfc_genl_send_target(struct sk_buff *msg, struct nfc_target *target, + struct netlink_callback *cb, int flags) +{ + void *hdr; + + nfc_dbg("entry"); + + hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, + &nfc_genl_family, flags, NFC_CMD_GET_TARGET); + if (!hdr) + return -EMSGSIZE; + + genl_dump_check_consistent(cb, hdr, &nfc_genl_family); + + NLA_PUT_U32(msg, NFC_ATTR_TARGET_INDEX, target->idx); + NLA_PUT_U32(msg, NFC_ATTR_PROTOCOLS, + target->supported_protocols); + NLA_PUT_U16(msg, NFC_ATTR_TARGET_SENS_RES, target->sens_res); + NLA_PUT_U8(msg, NFC_ATTR_TARGET_SEL_RES, target->sel_res); + + return genlmsg_end(msg, hdr); + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static struct nfc_dev *__get_device_from_cb(struct netlink_callback *cb) +{ + struct nfc_dev *dev; + int rc; + u32 idx; + + rc = nlmsg_parse(cb->nlh, GENL_HDRLEN + nfc_genl_family.hdrsize, + nfc_genl_family.attrbuf, + nfc_genl_family.maxattr, + nfc_genl_policy); + if (rc < 0) + return ERR_PTR(rc); + + if (!nfc_genl_family.attrbuf[NFC_ATTR_DEVICE_INDEX]) + return ERR_PTR(-EINVAL); + + idx = nla_get_u32(nfc_genl_family.attrbuf[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return ERR_PTR(-ENODEV); + + return dev; +} + +static int nfc_genl_dump_targets(struct sk_buff *skb, + struct netlink_callback *cb) +{ + int i = cb->args[0]; + struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; + int rc; + + nfc_dbg("entry"); + + if (!dev) { + dev = __get_device_from_cb(cb); + if (IS_ERR(dev)) + return PTR_ERR(dev); + + cb->args[1] = (long) dev; + } + + spin_lock_bh(&dev->targets_lock); + + cb->seq = dev->targets_generation; + + while (i < dev->n_targets) { + rc = nfc_genl_send_target(skb, &dev->targets[i], cb, + NLM_F_MULTI); + if (rc < 0) + break; + + i++; + } + + spin_unlock_bh(&dev->targets_lock); + + cb->args[0] = i; + + return skb->len; +} + +static int nfc_genl_dump_targets_done(struct netlink_callback *cb) +{ + struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; + + nfc_dbg("entry"); + + if (dev) + nfc_put_device(dev); + + return 0; +} + +int nfc_genl_targets_found(struct nfc_dev *dev) +{ + struct sk_buff *msg; + void *hdr; + + nfc_dbg("entry"); + + dev->genl_data.poll_req_pid = 0; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_TARGETS_FOUND); + if (!hdr) + goto free_msg; + + NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + + genlmsg_end(msg, hdr); + + return genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_ATOMIC); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int nfc_genl_device_added(struct nfc_dev *dev) +{ + struct sk_buff *msg; + void *hdr; + + nfc_dbg("entry"); + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_DEVICE_ADDED); + if (!hdr) + goto free_msg; + + NLA_PUT_STRING(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)); + NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + NLA_PUT_U32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols); + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +int nfc_genl_device_removed(struct nfc_dev *dev) +{ + struct sk_buff *msg; + void *hdr; + + nfc_dbg("entry"); + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, 0, 0, &nfc_genl_family, 0, + NFC_EVENT_DEVICE_REMOVED); + if (!hdr) + goto free_msg; + + NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + + genlmsg_end(msg, hdr); + + genlmsg_multicast(msg, 0, nfc_genl_event_mcgrp.id, GFP_KERNEL); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; +} + +static int nfc_genl_send_device(struct sk_buff *msg, struct nfc_dev *dev, + u32 pid, u32 seq, + struct netlink_callback *cb, + int flags) +{ + void *hdr; + + nfc_dbg("entry"); + + hdr = genlmsg_put(msg, pid, seq, &nfc_genl_family, flags, + NFC_CMD_GET_DEVICE); + if (!hdr) + return -EMSGSIZE; + + if (cb) + genl_dump_check_consistent(cb, hdr, &nfc_genl_family); + + NLA_PUT_STRING(msg, NFC_ATTR_DEVICE_NAME, nfc_device_name(dev)); + NLA_PUT_U32(msg, NFC_ATTR_DEVICE_INDEX, dev->idx); + NLA_PUT_U32(msg, NFC_ATTR_PROTOCOLS, dev->supported_protocols); + + return genlmsg_end(msg, hdr); + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int nfc_genl_dump_devices(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; + struct nfc_dev *dev = (struct nfc_dev *) cb->args[1]; + bool first_call = false; + + nfc_dbg("entry"); + + if (!iter) { + first_call = true; + iter = kmalloc(sizeof(struct class_dev_iter), GFP_KERNEL); + if (!iter) + return -ENOMEM; + cb->args[0] = (long) iter; + } + + mutex_lock(&nfc_devlist_mutex); + + cb->seq = nfc_devlist_generation; + + if (first_call) { + nfc_device_iter_init(iter); + dev = nfc_device_iter_next(iter); + } + + while (dev) { + int rc; + + rc = nfc_genl_send_device(skb, dev, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + cb, NLM_F_MULTI); + if (rc < 0) + break; + + dev = nfc_device_iter_next(iter); + } + + mutex_unlock(&nfc_devlist_mutex); + + cb->args[1] = (long) dev; + + return skb->len; +} + +static int nfc_genl_dump_devices_done(struct netlink_callback *cb) +{ + struct class_dev_iter *iter = (struct class_dev_iter *) cb->args[0]; + + nfc_dbg("entry"); + + nfc_device_iter_exit(iter); + kfree(iter); + + return 0; +} + +static int nfc_genl_get_device(struct sk_buff *skb, struct genl_info *info) +{ + struct sk_buff *msg; + struct nfc_dev *dev; + u32 idx; + int rc = -ENOBUFS; + + nfc_dbg("entry"); + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + msg = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (!msg) { + rc = -ENOMEM; + goto out_putdev; + } + + rc = nfc_genl_send_device(msg, dev, info->snd_pid, info->snd_seq, + NULL, 0); + if (rc < 0) + goto out_free; + + nfc_put_device(dev); + + return genlmsg_reply(msg, info); + +out_free: + nlmsg_free(msg); +out_putdev: + nfc_put_device(dev); + return rc; +} + +static int nfc_genl_start_poll(struct sk_buff *skb, struct genl_info *info) +{ + struct nfc_dev *dev; + int rc; + u32 idx; + u32 protocols; + + nfc_dbg("entry"); + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX] || + !info->attrs[NFC_ATTR_PROTOCOLS]) + return -EINVAL; + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + protocols = nla_get_u32(info->attrs[NFC_ATTR_PROTOCOLS]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + mutex_lock(&dev->genl_data.genl_data_mutex); + + rc = nfc_start_poll(dev, protocols); + if (!rc) + dev->genl_data.poll_req_pid = info->snd_pid; + + mutex_unlock(&dev->genl_data.genl_data_mutex); + + nfc_put_device(dev); + return rc; +} + +static int nfc_genl_stop_poll(struct sk_buff *skb, struct genl_info *info) +{ + struct nfc_dev *dev; + int rc; + u32 idx; + + nfc_dbg("entry"); + + if (!info->attrs[NFC_ATTR_DEVICE_INDEX]) + return -EINVAL; + + idx = nla_get_u32(info->attrs[NFC_ATTR_DEVICE_INDEX]); + + dev = nfc_get_device(idx); + if (!dev) + return -ENODEV; + + mutex_lock(&dev->genl_data.genl_data_mutex); + + if (dev->genl_data.poll_req_pid != info->snd_pid) { + rc = -EBUSY; + goto out; + } + + rc = nfc_stop_poll(dev); + dev->genl_data.poll_req_pid = 0; + +out: + mutex_unlock(&dev->genl_data.genl_data_mutex); + nfc_put_device(dev); + return rc; +} + +static struct genl_ops nfc_genl_ops[] = { + { + .cmd = NFC_CMD_GET_DEVICE, + .doit = nfc_genl_get_device, + .dumpit = nfc_genl_dump_devices, + .done = nfc_genl_dump_devices_done, + .policy = nfc_genl_policy, + }, + { + .cmd = NFC_CMD_START_POLL, + .doit = nfc_genl_start_poll, + .policy = nfc_genl_policy, + }, + { + .cmd = NFC_CMD_STOP_POLL, + .doit = nfc_genl_stop_poll, + .policy = nfc_genl_policy, + }, + { + .cmd = NFC_CMD_GET_TARGET, + .dumpit = nfc_genl_dump_targets, + .done = nfc_genl_dump_targets_done, + .policy = nfc_genl_policy, + }, +}; + +static int nfc_genl_rcv_nl_event(struct notifier_block *this, + unsigned long event, void *ptr) +{ + struct netlink_notify *n = ptr; + struct class_dev_iter iter; + struct nfc_dev *dev; + + if (event != NETLINK_URELEASE || n->protocol != NETLINK_GENERIC) + goto out; + + nfc_dbg("NETLINK_URELEASE event from id %d", n->pid); + + nfc_device_iter_init(&iter); + dev = nfc_device_iter_next(&iter); + + while (dev) { + mutex_lock(&dev->genl_data.genl_data_mutex); + if (dev->genl_data.poll_req_pid == n->pid) { + nfc_stop_poll(dev); + dev->genl_data.poll_req_pid = 0; + } + mutex_unlock(&dev->genl_data.genl_data_mutex); + dev = nfc_device_iter_next(&iter); + } + + nfc_device_iter_exit(&iter); + +out: + return NOTIFY_DONE; +} + +void nfc_genl_data_init(struct nfc_genl_data *genl_data) +{ + genl_data->poll_req_pid = 0; + mutex_init(&genl_data->genl_data_mutex); +} + +void nfc_genl_data_exit(struct nfc_genl_data *genl_data) +{ + mutex_destroy(&genl_data->genl_data_mutex); +} + +static struct notifier_block nl_notifier = { + .notifier_call = nfc_genl_rcv_nl_event, +}; + +/** + * nfc_genl_init() - Initialize netlink interface + * + * This initialization function registers the nfc netlink family. + */ +int __init nfc_genl_init(void) +{ + int rc; + + rc = genl_register_family_with_ops(&nfc_genl_family, nfc_genl_ops, + ARRAY_SIZE(nfc_genl_ops)); + if (rc) + return rc; + + rc = genl_register_mc_group(&nfc_genl_family, &nfc_genl_event_mcgrp); + + netlink_register_notifier(&nl_notifier); + + return rc; +} + +/** + * nfc_genl_exit() - Deinitialize netlink interface + * + * This exit function unregisters the nfc netlink family. + */ +void nfc_genl_exit(void) +{ + netlink_unregister_notifier(&nl_notifier); + genl_unregister_family(&nfc_genl_family); +} diff --git a/net/nfc/nfc.h b/net/nfc/nfc.h new file mode 100644 index 00000000000..aaf9832298f --- /dev/null +++ b/net/nfc/nfc.h @@ -0,0 +1,117 @@ +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Lauro Ramos Venancio <lauro.venancio@openbossa.org> + * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#ifndef __LOCAL_NFC_H +#define __LOCAL_NFC_H + +#include <net/nfc.h> +#include <net/sock.h> + +__attribute__((format (printf, 2, 3))) +int nfc_printk(const char *level, const char *fmt, ...); + +#define nfc_info(fmt, arg...) nfc_printk(KERN_INFO, fmt, ##arg) +#define nfc_err(fmt, arg...) nfc_printk(KERN_ERR, fmt, ##arg) +#define nfc_dbg(fmt, arg...) pr_debug(fmt "\n", ##arg) + +struct nfc_protocol { + int id; + struct proto *proto; + struct module *owner; + int (*create)(struct net *net, struct socket *sock, + const struct nfc_protocol *nfc_proto); +}; + +struct nfc_rawsock { + struct sock sk; + struct nfc_dev *dev; + u32 target_idx; + struct work_struct tx_work; + bool tx_work_scheduled; +}; +#define nfc_rawsock(sk) ((struct nfc_rawsock *) sk) +#define to_rawsock_sk(_tx_work) \ + ((struct sock *) container_of(_tx_work, struct nfc_rawsock, tx_work)) + +int __init rawsock_init(void); +void rawsock_exit(void); + +int __init af_nfc_init(void); +void af_nfc_exit(void); +int nfc_proto_register(const struct nfc_protocol *nfc_proto); +void nfc_proto_unregister(const struct nfc_protocol *nfc_proto); + +extern int nfc_devlist_generation; +extern struct mutex nfc_devlist_mutex; + +int __init nfc_genl_init(void); +void nfc_genl_exit(void); + +void nfc_genl_data_init(struct nfc_genl_data *genl_data); +void nfc_genl_data_exit(struct nfc_genl_data *genl_data); + +int nfc_genl_targets_found(struct nfc_dev *dev); + +int nfc_genl_device_added(struct nfc_dev *dev); +int nfc_genl_device_removed(struct nfc_dev *dev); + +struct nfc_dev *nfc_get_device(unsigned idx); + +static inline void nfc_put_device(struct nfc_dev *dev) +{ + put_device(&dev->dev); +} + +static inline void nfc_device_iter_init(struct class_dev_iter *iter) +{ + class_dev_iter_init(iter, &nfc_class, NULL, NULL); +} + +static inline struct nfc_dev *nfc_device_iter_next(struct class_dev_iter *iter) +{ + struct device *d = class_dev_iter_next(iter); + if (!d) + return NULL; + + return to_nfc_dev(d); +} + +static inline void nfc_device_iter_exit(struct class_dev_iter *iter) +{ + class_dev_iter_exit(iter); +} + +int nfc_start_poll(struct nfc_dev *dev, u32 protocols); + +int nfc_stop_poll(struct nfc_dev *dev); + +int nfc_activate_target(struct nfc_dev *dev, u32 target_idx, u32 protocol); + +int nfc_deactivate_target(struct nfc_dev *dev, u32 target_idx); + +int nfc_data_exchange(struct nfc_dev *dev, u32 target_idx, + struct sk_buff *skb, + data_exchange_cb_t cb, + void *cb_context); + +#endif /* __LOCAL_NFC_H */ diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c new file mode 100644 index 00000000000..52de84a5511 --- /dev/null +++ b/net/nfc/rawsock.c @@ -0,0 +1,354 @@ +/* + * Copyright (C) 2011 Instituto Nokia de Tecnologia + * + * Authors: + * Aloisio Almeida Jr <aloisio.almeida@openbossa.org> + * Lauro Ramos Venancio <lauro.venancio@openbossa.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the + * Free Software Foundation, Inc., + * 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. + */ + +#include <net/tcp_states.h> +#include <linux/nfc.h> + +#include "nfc.h" + +static void rawsock_write_queue_purge(struct sock *sk) +{ + nfc_dbg("sk=%p", sk); + + spin_lock_bh(&sk->sk_write_queue.lock); + __skb_queue_purge(&sk->sk_write_queue); + nfc_rawsock(sk)->tx_work_scheduled = false; + spin_unlock_bh(&sk->sk_write_queue.lock); +} + +static void rawsock_report_error(struct sock *sk, int err) +{ + nfc_dbg("sk=%p err=%d", sk, err); + + sk->sk_shutdown = SHUTDOWN_MASK; + sk->sk_err = -err; + sk->sk_error_report(sk); + + rawsock_write_queue_purge(sk); +} + +static int rawsock_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + + nfc_dbg("sock=%p", sock); + + sock_orphan(sk); + sock_put(sk); + + return 0; +} + +static int rawsock_connect(struct socket *sock, struct sockaddr *_addr, + int len, int flags) +{ + struct sock *sk = sock->sk; + struct sockaddr_nfc *addr = (struct sockaddr_nfc *)_addr; + struct nfc_dev *dev; + int rc = 0; + + nfc_dbg("sock=%p sk=%p flags=%d", sock, sk, flags); + + if (!addr || len < sizeof(struct sockaddr_nfc) || + addr->sa_family != AF_NFC) + return -EINVAL; + + nfc_dbg("addr dev_idx=%u target_idx=%u protocol=%u", addr->dev_idx, + addr->target_idx, addr->nfc_protocol); + + lock_sock(sk); + + if (sock->state == SS_CONNECTED) { + rc = -EISCONN; + goto error; + } + + dev = nfc_get_device(addr->dev_idx); + if (!dev) { + rc = -ENODEV; + goto error; + } + + if (addr->target_idx > dev->target_idx - 1 || + addr->target_idx < dev->target_idx - dev->n_targets) { + rc = -EINVAL; + goto error; + } + + if (addr->target_idx > dev->target_idx - 1 || + addr->target_idx < dev->target_idx - dev->n_targets) { + rc = -EINVAL; + goto error; + } + + rc = nfc_activate_target(dev, addr->target_idx, addr->nfc_protocol); + if (rc) + goto put_dev; + + nfc_rawsock(sk)->dev = dev; + nfc_rawsock(sk)->target_idx = addr->target_idx; + sock->state = SS_CONNECTED; + sk->sk_state = TCP_ESTABLISHED; + sk->sk_state_change(sk); + + release_sock(sk); + return 0; + +put_dev: + nfc_put_device(dev); +error: + release_sock(sk); + return rc; +} + +static int rawsock_add_header(struct sk_buff *skb) +{ + + if (skb_cow_head(skb, 1)) + return -ENOMEM; + + *skb_push(skb, 1) = 0; + + return 0; +} + +static void rawsock_data_exchange_complete(void *context, struct sk_buff *skb, + int err) +{ + struct sock *sk = (struct sock *) context; + + BUG_ON(in_irq()); + + nfc_dbg("sk=%p err=%d", sk, err); + + if (err) + goto error; + + err = rawsock_add_header(skb); + if (err) + goto error; + + err = sock_queue_rcv_skb(sk, skb); + if (err) + goto error; + + spin_lock_bh(&sk->sk_write_queue.lock); + if (!skb_queue_empty(&sk->sk_write_queue)) + schedule_work(&nfc_rawsock(sk)->tx_work); + else + nfc_rawsock(sk)->tx_work_scheduled = false; + spin_unlock_bh(&sk->sk_write_queue.lock); + + sock_put(sk); + return; + +error: + rawsock_report_error(sk, err); + sock_put(sk); +} + +static void rawsock_tx_work(struct work_struct *work) +{ + struct sock *sk = to_rawsock_sk(work); + struct nfc_dev *dev = nfc_rawsock(sk)->dev; + u32 target_idx = nfc_rawsock(sk)->target_idx; + struct sk_buff *skb; + int rc; + + nfc_dbg("sk=%p target_idx=%u", sk, target_idx); + + if (sk->sk_shutdown & SEND_SHUTDOWN) { + rawsock_write_queue_purge(sk); + return; + } + + skb = skb_dequeue(&sk->sk_write_queue); + + sock_hold(sk); + rc = nfc_data_exchange(dev, target_idx, skb, + rawsock_data_exchange_complete, sk); + if (rc) { + rawsock_report_error(sk, rc); + sock_put(sk); + } +} + +static int rawsock_sendmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len) +{ + struct sock *sk = sock->sk; + struct sk_buff *skb; + int rc; + + nfc_dbg("sock=%p sk=%p len=%zu", sock, sk, len); + + if (msg->msg_namelen) + return -EOPNOTSUPP; + + if (sock->state != SS_CONNECTED) + return -ENOTCONN; + + skb = sock_alloc_send_skb(sk, len, msg->msg_flags & MSG_DONTWAIT, + &rc); + if (!skb) + return rc; + + rc = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len); + if (rc < 0) { + kfree_skb(skb); + return rc; + } + + spin_lock_bh(&sk->sk_write_queue.lock); + __skb_queue_tail(&sk->sk_write_queue, skb); + if (!nfc_rawsock(sk)->tx_work_scheduled) { + schedule_work(&nfc_rawsock(sk)->tx_work); + nfc_rawsock(sk)->tx_work_scheduled = true; + } + spin_unlock_bh(&sk->sk_write_queue.lock); + + return len; +} + +static int rawsock_recvmsg(struct kiocb *iocb, struct socket *sock, + struct msghdr *msg, size_t len, int flags) +{ + int noblock = flags & MSG_DONTWAIT; + struct sock *sk = sock->sk; + struct sk_buff *skb; + int copied; + int rc; + + nfc_dbg("sock=%p sk=%p len=%zu flags=%d", sock, sk, len, flags); + + skb = skb_recv_datagram(sk, flags, noblock, &rc); + if (!skb) + return rc; + + msg->msg_namelen = 0; + + copied = skb->len; + if (len < copied) { + msg->msg_flags |= MSG_TRUNC; + copied = len; + } + + rc = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, copied); + + skb_free_datagram(sk, skb); + + return rc ? : copied; +} + + +static const struct proto_ops rawsock_ops = { + .family = PF_NFC, + .owner = THIS_MODULE, + .release = rawsock_release, + .bind = sock_no_bind, + .connect = rawsock_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = datagram_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = sock_no_setsockopt, + .getsockopt = sock_no_getsockopt, + .sendmsg = rawsock_sendmsg, + .recvmsg = rawsock_recvmsg, + .mmap = sock_no_mmap, +}; + +static void rawsock_destruct(struct sock *sk) +{ + nfc_dbg("sk=%p", sk); + + if (sk->sk_state == TCP_ESTABLISHED) { + nfc_deactivate_target(nfc_rawsock(sk)->dev, + nfc_rawsock(sk)->target_idx); + nfc_put_device(nfc_rawsock(sk)->dev); + } + + skb_queue_purge(&sk->sk_receive_queue); + + if (!sock_flag(sk, SOCK_DEAD)) { + nfc_err("Freeing alive NFC raw socket %p", sk); + return; + } +} + +static int rawsock_create(struct net *net, struct socket *sock, + const struct nfc_protocol *nfc_proto) +{ + struct sock *sk; + + nfc_dbg("sock=%p", sock); + + if (sock->type != SOCK_SEQPACKET) + return -ESOCKTNOSUPPORT; + + sock->ops = &rawsock_ops; + + sk = sk_alloc(net, PF_NFC, GFP_KERNEL, nfc_proto->proto); + if (!sk) + return -ENOMEM; + + sock_init_data(sock, sk); + sk->sk_protocol = nfc_proto->id; + sk->sk_destruct = rawsock_destruct; + sock->state = SS_UNCONNECTED; + + INIT_WORK(&nfc_rawsock(sk)->tx_work, rawsock_tx_work); + nfc_rawsock(sk)->tx_work_scheduled = false; + + return 0; +} + +static struct proto rawsock_proto = { + .name = "NFC_RAW", + .owner = THIS_MODULE, + .obj_size = sizeof(struct nfc_rawsock), +}; + +static const struct nfc_protocol rawsock_nfc_proto = { + .id = NFC_SOCKPROTO_RAW, + .proto = &rawsock_proto, + .owner = THIS_MODULE, + .create = rawsock_create +}; + +int __init rawsock_init(void) +{ + int rc; + + rc = nfc_proto_register(&rawsock_nfc_proto); + + return rc; +} + +void rawsock_exit(void) +{ + nfc_proto_unregister(&rawsock_nfc_proto); +} diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index ba248d93399..c698cec0a44 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -187,9 +187,11 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg); static void packet_flush_mclist(struct sock *sk); +struct packet_fanout; struct packet_sock { /* struct sock has to be the first member of packet_sock */ struct sock sk; + struct packet_fanout *fanout; struct tpacket_stats stats; struct packet_ring_buffer rx_ring; struct packet_ring_buffer tx_ring; @@ -212,6 +214,24 @@ struct packet_sock { struct packet_type prot_hook ____cacheline_aligned_in_smp; }; +#define PACKET_FANOUT_MAX 256 + +struct packet_fanout { +#ifdef CONFIG_NET_NS + struct net *net; +#endif + unsigned int num_members; + u16 id; + u8 type; + u8 defrag; + atomic_t rr_cur; + struct list_head list; + struct sock *arr[PACKET_FANOUT_MAX]; + spinlock_t lock; + atomic_t sk_ref; + struct packet_type prot_hook ____cacheline_aligned_in_smp; +}; + struct packet_skb_cb { unsigned int origlen; union { @@ -222,6 +242,64 @@ struct packet_skb_cb { #define PACKET_SKB_CB(__skb) ((struct packet_skb_cb *)((__skb)->cb)) +static inline struct packet_sock *pkt_sk(struct sock *sk) +{ + return (struct packet_sock *)sk; +} + +static void __fanout_unlink(struct sock *sk, struct packet_sock *po); +static void __fanout_link(struct sock *sk, struct packet_sock *po); + +/* register_prot_hook must be invoked with the po->bind_lock held, + * or from a context in which asynchronous accesses to the packet + * socket is not possible (packet_create()). + */ +static void register_prot_hook(struct sock *sk) +{ + struct packet_sock *po = pkt_sk(sk); + if (!po->running) { + if (po->fanout) + __fanout_link(sk, po); + else + dev_add_pack(&po->prot_hook); + sock_hold(sk); + po->running = 1; + } +} + +/* {,__}unregister_prot_hook() must be invoked with the po->bind_lock + * held. If the sync parameter is true, we will temporarily drop + * the po->bind_lock and do a synchronize_net to make sure no + * asynchronous packet processing paths still refer to the elements + * of po->prot_hook. If the sync parameter is false, it is the + * callers responsibility to take care of this. + */ +static void __unregister_prot_hook(struct sock *sk, bool sync) +{ + struct packet_sock *po = pkt_sk(sk); + + po->running = 0; + if (po->fanout) + __fanout_unlink(sk, po); + else + __dev_remove_pack(&po->prot_hook); + __sock_put(sk); + + if (sync) { + spin_unlock(&po->bind_lock); + synchronize_net(); + spin_lock(&po->bind_lock); + } +} + +static void unregister_prot_hook(struct sock *sk, bool sync) +{ + struct packet_sock *po = pkt_sk(sk); + + if (po->running) + __unregister_prot_hook(sk, sync); +} + static inline __pure struct page *pgv_to_page(void *addr) { if (is_vmalloc_addr(addr)) @@ -324,11 +402,6 @@ static inline void packet_increment_head(struct packet_ring_buffer *buff) buff->head = buff->head != buff->frame_max ? buff->head+1 : 0; } -static inline struct packet_sock *pkt_sk(struct sock *sk) -{ - return (struct packet_sock *)sk; -} - static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -344,6 +417,240 @@ static void packet_sock_destruct(struct sock *sk) sk_refcnt_debug_dec(sk); } +static int fanout_rr_next(struct packet_fanout *f, unsigned int num) +{ + int x = atomic_read(&f->rr_cur) + 1; + + if (x >= num) + x = 0; + + return x; +} + +static struct sock *fanout_demux_hash(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) +{ + u32 idx, hash = skb->rxhash; + + idx = ((u64)hash * num) >> 32; + + return f->arr[idx]; +} + +static struct sock *fanout_demux_lb(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) +{ + int cur, old; + + cur = atomic_read(&f->rr_cur); + while ((old = atomic_cmpxchg(&f->rr_cur, cur, + fanout_rr_next(f, num))) != cur) + cur = old; + return f->arr[cur]; +} + +static struct sock *fanout_demux_cpu(struct packet_fanout *f, struct sk_buff *skb, unsigned int num) +{ + unsigned int cpu = smp_processor_id(); + + return f->arr[cpu % num]; +} + +static struct sk_buff *fanout_check_defrag(struct sk_buff *skb) +{ +#ifdef CONFIG_INET + const struct iphdr *iph; + u32 len; + + if (skb->protocol != htons(ETH_P_IP)) + return skb; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return skb; + + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return skb; + if (!pskb_may_pull(skb, iph->ihl*4)) + return skb; + iph = ip_hdr(skb); + len = ntohs(iph->tot_len); + if (skb->len < len || len < (iph->ihl * 4)) + return skb; + + if (ip_is_fragment(ip_hdr(skb))) { + skb = skb_share_check(skb, GFP_ATOMIC); + if (skb) { + if (pskb_trim_rcsum(skb, len)) + return skb; + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + if (ip_defrag(skb, IP_DEFRAG_AF_PACKET)) + return NULL; + skb->rxhash = 0; + } + } +#endif + return skb; +} + +static int packet_rcv_fanout(struct sk_buff *skb, struct net_device *dev, + struct packet_type *pt, struct net_device *orig_dev) +{ + struct packet_fanout *f = pt->af_packet_priv; + unsigned int num = f->num_members; + struct packet_sock *po; + struct sock *sk; + + if (!net_eq(dev_net(dev), read_pnet(&f->net)) || + !num) { + kfree_skb(skb); + return 0; + } + + switch (f->type) { + case PACKET_FANOUT_HASH: + default: + if (f->defrag) { + skb = fanout_check_defrag(skb); + if (!skb) + return 0; + } + skb_get_rxhash(skb); + sk = fanout_demux_hash(f, skb, num); + break; + case PACKET_FANOUT_LB: + sk = fanout_demux_lb(f, skb, num); + break; + case PACKET_FANOUT_CPU: + sk = fanout_demux_cpu(f, skb, num); + break; + } + + po = pkt_sk(sk); + + return po->prot_hook.func(skb, dev, &po->prot_hook, orig_dev); +} + +static DEFINE_MUTEX(fanout_mutex); +static LIST_HEAD(fanout_list); + +static void __fanout_link(struct sock *sk, struct packet_sock *po) +{ + struct packet_fanout *f = po->fanout; + + spin_lock(&f->lock); + f->arr[f->num_members] = sk; + smp_wmb(); + f->num_members++; + spin_unlock(&f->lock); +} + +static void __fanout_unlink(struct sock *sk, struct packet_sock *po) +{ + struct packet_fanout *f = po->fanout; + int i; + + spin_lock(&f->lock); + for (i = 0; i < f->num_members; i++) { + if (f->arr[i] == sk) + break; + } + BUG_ON(i >= f->num_members); + f->arr[i] = f->arr[f->num_members - 1]; + f->num_members--; + spin_unlock(&f->lock); +} + +static int fanout_add(struct sock *sk, u16 id, u16 type_flags) +{ + struct packet_sock *po = pkt_sk(sk); + struct packet_fanout *f, *match; + u8 type = type_flags & 0xff; + u8 defrag = (type_flags & PACKET_FANOUT_FLAG_DEFRAG) ? 1 : 0; + int err; + + switch (type) { + case PACKET_FANOUT_HASH: + case PACKET_FANOUT_LB: + case PACKET_FANOUT_CPU: + break; + default: + return -EINVAL; + } + + if (!po->running) + return -EINVAL; + + if (po->fanout) + return -EALREADY; + + mutex_lock(&fanout_mutex); + match = NULL; + list_for_each_entry(f, &fanout_list, list) { + if (f->id == id && + read_pnet(&f->net) == sock_net(sk)) { + match = f; + break; + } + } + err = -EINVAL; + if (match && match->defrag != defrag) + goto out; + if (!match) { + err = -ENOMEM; + match = kzalloc(sizeof(*match), GFP_KERNEL); + if (!match) + goto out; + write_pnet(&match->net, sock_net(sk)); + match->id = id; + match->type = type; + match->defrag = defrag; + atomic_set(&match->rr_cur, 0); + INIT_LIST_HEAD(&match->list); + spin_lock_init(&match->lock); + atomic_set(&match->sk_ref, 0); + match->prot_hook.type = po->prot_hook.type; + match->prot_hook.dev = po->prot_hook.dev; + match->prot_hook.func = packet_rcv_fanout; + match->prot_hook.af_packet_priv = match; + dev_add_pack(&match->prot_hook); + list_add(&match->list, &fanout_list); + } + err = -EINVAL; + if (match->type == type && + match->prot_hook.type == po->prot_hook.type && + match->prot_hook.dev == po->prot_hook.dev) { + err = -ENOSPC; + if (atomic_read(&match->sk_ref) < PACKET_FANOUT_MAX) { + __dev_remove_pack(&po->prot_hook); + po->fanout = match; + atomic_inc(&match->sk_ref); + __fanout_link(sk, po); + err = 0; + } + } +out: + mutex_unlock(&fanout_mutex); + return err; +} + +static void fanout_release(struct sock *sk) +{ + struct packet_sock *po = pkt_sk(sk); + struct packet_fanout *f; + + f = po->fanout; + if (!f) + return; + + po->fanout = NULL; + + mutex_lock(&fanout_mutex); + if (atomic_dec_and_test(&f->sk_ref)) { + list_del(&f->list); + dev_remove_pack(&f->prot_hook); + kfree(f); + } + mutex_unlock(&fanout_mutex); +} static const struct proto_ops packet_ops; @@ -804,6 +1111,7 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } else { h.h2->tp_vlan_tci = 0; } + h.h2->tp_padding = 0; hdrlen = sizeof(*h.h2); break; default: @@ -821,7 +1129,6 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, else sll->sll_ifindex = dev->ifindex; - __packet_set_status(po, h.raw, status); smp_mb(); #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1 { @@ -830,8 +1137,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, end = (u8 *)PAGE_ALIGN((unsigned long)h.raw + macoff + snaplen); for (start = h.raw; start < end; start += PAGE_SIZE) flush_dcache_page(pgv_to_page(start)); + smp_wmb(); } #endif + __packet_set_status(po, h.raw, status); sk->sk_data_ready(sk, 0); @@ -974,7 +1283,8 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) struct sk_buff *skb; struct net_device *dev; __be16 proto; - int ifindex, err, reserve = 0; + bool need_rls_dev = false; + int err, reserve = 0; void *ph; struct sockaddr_ll *saddr = (struct sockaddr_ll *)msg->msg_name; int tp_len, size_max; @@ -986,7 +1296,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) err = -EBUSY; if (saddr == NULL) { - ifindex = po->ifindex; + dev = po->prot_hook.dev; proto = po->num; addr = NULL; } else { @@ -997,12 +1307,12 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg) + offsetof(struct sockaddr_ll, sll_addr))) goto out; - ifindex = saddr->sll_ifindex; proto = saddr->sll_protocol; addr = saddr->sll_addr; + dev = dev_get_by_index(sock_net(&po->sk), saddr->sll_ifindex); + need_rls_dev = true; } - dev = dev_get_by_index(sock_net(&po->sk), ifindex); err = -ENXIO; if (unlikely(dev == NULL)) goto out; @@ -1088,7 +1398,8 @@ out_status: __packet_set_status(po, ph, status); kfree_skb(skb); out_put: - dev_put(dev); + if (need_rls_dev) + dev_put(dev); out: mutex_unlock(&po->pg_vec_lock); return err; @@ -1126,8 +1437,9 @@ static int packet_snd(struct socket *sock, struct sk_buff *skb; struct net_device *dev; __be16 proto; + bool need_rls_dev = false; unsigned char *addr; - int ifindex, err, reserve = 0; + int err, reserve = 0; struct virtio_net_hdr vnet_hdr = { 0 }; int offset = 0; int vnet_hdr_len; @@ -1139,7 +1451,7 @@ static int packet_snd(struct socket *sock, */ if (saddr == NULL) { - ifindex = po->ifindex; + dev = po->prot_hook.dev; proto = po->num; addr = NULL; } else { @@ -1148,13 +1460,12 @@ static int packet_snd(struct socket *sock, goto out; if (msg->msg_namelen < (saddr->sll_halen + offsetof(struct sockaddr_ll, sll_addr))) goto out; - ifindex = saddr->sll_ifindex; proto = saddr->sll_protocol; addr = saddr->sll_addr; + dev = dev_get_by_index(sock_net(sk), saddr->sll_ifindex); + need_rls_dev = true; } - - dev = dev_get_by_index(sock_net(sk), ifindex); err = -ENXIO; if (dev == NULL) goto out_unlock; @@ -1285,14 +1596,15 @@ static int packet_snd(struct socket *sock, if (err > 0 && (err = net_xmit_errno(err)) != 0) goto out_unlock; - dev_put(dev); + if (need_rls_dev) + dev_put(dev); return len; out_free: kfree_skb(skb); out_unlock: - if (dev) + if (dev && need_rls_dev) dev_put(dev); out: return err; @@ -1333,14 +1645,10 @@ static int packet_release(struct socket *sock) spin_unlock_bh(&net->packet.sklist_lock); spin_lock(&po->bind_lock); - if (po->running) { - /* - * Remove from protocol table - */ - po->running = 0; - po->num = 0; - __dev_remove_pack(&po->prot_hook); - __sock_put(sk); + unregister_prot_hook(sk, false); + if (po->prot_hook.dev) { + dev_put(po->prot_hook.dev); + po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -1354,6 +1662,8 @@ static int packet_release(struct socket *sock) if (po->tx_ring.pg_vec) packet_set_ring(sk, &req, 1, 1); + fanout_release(sk); + synchronize_net(); /* * Now the socket is dead. No more input will appear. @@ -1377,24 +1687,18 @@ static int packet_release(struct socket *sock) static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protocol) { struct packet_sock *po = pkt_sk(sk); - /* - * Detach an existing hook if present. - */ + + if (po->fanout) + return -EINVAL; lock_sock(sk); spin_lock(&po->bind_lock); - if (po->running) { - __sock_put(sk); - po->running = 0; - po->num = 0; - spin_unlock(&po->bind_lock); - dev_remove_pack(&po->prot_hook); - spin_lock(&po->bind_lock); - } - + unregister_prot_hook(sk, true); po->num = protocol; po->prot_hook.type = protocol; + if (po->prot_hook.dev) + dev_put(po->prot_hook.dev); po->prot_hook.dev = dev; po->ifindex = dev ? dev->ifindex : 0; @@ -1403,9 +1707,7 @@ static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 protoc goto out_unlock; if (!dev || (dev->flags & IFF_UP)) { - dev_add_pack(&po->prot_hook); - sock_hold(sk); - po->running = 1; + register_prot_hook(sk); } else { sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) @@ -1439,10 +1741,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, strlcpy(name, uaddr->sa_data, sizeof(name)); dev = dev_get_by_name(sock_net(sk), name); - if (dev) { + if (dev) err = packet_do_bind(sk, dev, pkt_sk(sk)->num); - dev_put(dev); - } return err; } @@ -1470,8 +1770,6 @@ static int packet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len goto out; } err = packet_do_bind(sk, dev, sll->sll_protocol ? : pkt_sk(sk)->num); - if (dev) - dev_put(dev); out: return err; @@ -1536,9 +1834,7 @@ static int packet_create(struct net *net, struct socket *sock, int protocol, if (proto) { po->prot_hook.type = proto; - dev_add_pack(&po->prot_hook); - sock_hold(sk); - po->running = 1; + register_prot_hook(sk); } spin_lock_bh(&net->packet.sklist_lock); @@ -1680,6 +1976,8 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, vnet_hdr.flags = VIRTIO_NET_HDR_F_NEEDS_CSUM; vnet_hdr.csum_start = skb_checksum_start_offset(skb); vnet_hdr.csum_offset = skb->csum_offset; + } else if (skb->ip_summed == CHECKSUM_UNNECESSARY) { + vnet_hdr.flags = VIRTIO_NET_HDR_F_DATA_VALID; } /* else everything is zero */ err = memcpy_toiovec(msg->msg_iov, (void *)&vnet_hdr, @@ -1736,6 +2034,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, } else { aux.tp_vlan_tci = 0; } + aux.tp_padding = 0; put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } @@ -2100,6 +2399,17 @@ packet_setsockopt(struct socket *sock, int level, int optname, char __user *optv po->tp_tstamp = val; return 0; } + case PACKET_FANOUT: + { + int val; + + if (optlen != sizeof(val)) + return -EINVAL; + if (copy_from_user(&val, optval, sizeof(val))) + return -EFAULT; + + return fanout_add(sk, val & 0xffff, val >> 16); + } default: return -ENOPROTOOPT; } @@ -2198,6 +2508,15 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, val = po->tp_tstamp; data = &val; break; + case PACKET_FANOUT: + if (len > sizeof(int)) + len = sizeof(int); + val = (po->fanout ? + ((u32)po->fanout->id | + ((u32)po->fanout->type << 16)) : + 0); + data = &val; + break; default: return -ENOPROTOOPT; } @@ -2231,15 +2550,15 @@ static int packet_notifier(struct notifier_block *this, unsigned long msg, void if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); if (po->running) { - __dev_remove_pack(&po->prot_hook); - __sock_put(sk); - po->running = 0; + __unregister_prot_hook(sk, false); sk->sk_err = ENETDOWN; if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); } if (msg == NETDEV_UNREGISTER) { po->ifindex = -1; + if (po->prot_hook.dev) + dev_put(po->prot_hook.dev); po->prot_hook.dev = NULL; } spin_unlock(&po->bind_lock); @@ -2248,11 +2567,8 @@ static int packet_notifier(struct notifier_block *this, unsigned long msg, void case NETDEV_UP: if (dev->ifindex == po->ifindex) { spin_lock(&po->bind_lock); - if (po->num && !po->running) { - dev_add_pack(&po->prot_hook); - sock_hold(sk); - po->running = 1; - } + if (po->num) + register_prot_hook(sk); spin_unlock(&po->bind_lock); } break; @@ -2519,10 +2835,8 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, was_running = po->running; num = po->num; if (was_running) { - __dev_remove_pack(&po->prot_hook); po->num = 0; - po->running = 0; - __sock_put(sk); + __unregister_prot_hook(sk, false); } spin_unlock(&po->bind_lock); @@ -2553,11 +2867,9 @@ static int packet_set_ring(struct sock *sk, struct tpacket_req *req, mutex_unlock(&po->pg_vec_lock); spin_lock(&po->bind_lock); - if (was_running && !po->running) { - sock_hold(sk); - po->running = 1; + if (was_running) { po->num = num; - dev_add_pack(&po->prot_hook); + register_prot_hook(sk); } spin_unlock(&po->bind_lock); diff --git a/net/phonet/pn_netlink.c b/net/phonet/pn_netlink.c index 438accb7a5a..d61f6761777 100644 --- a/net/phonet/pn_netlink.c +++ b/net/phonet/pn_netlink.c @@ -289,15 +289,16 @@ out: int __init phonet_netlink_register(void) { - int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit, NULL); + int err = __rtnl_register(PF_PHONET, RTM_NEWADDR, addr_doit, + NULL, NULL); if (err) return err; /* Further __rtnl_register() cannot fail */ - __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL); - __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit); - __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL); - __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL); - __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit); + __rtnl_register(PF_PHONET, RTM_DELADDR, addr_doit, NULL, NULL); + __rtnl_register(PF_PHONET, RTM_GETADDR, NULL, getaddr_dumpit, NULL); + __rtnl_register(PF_PHONET, RTM_NEWROUTE, route_doit, NULL, NULL); + __rtnl_register(PF_PHONET, RTM_DELROUTE, route_doit, NULL, NULL); + __rtnl_register(PF_PHONET, RTM_GETROUTE, NULL, route_dumpit, NULL); return 0; } diff --git a/net/rds/bind.c b/net/rds/bind.c index 2f6b3fcc79f..637bde56c9d 100644 --- a/net/rds/bind.c +++ b/net/rds/bind.c @@ -35,6 +35,7 @@ #include <linux/in.h> #include <linux/if_arp.h> #include <linux/jhash.h> +#include <linux/ratelimit.h> #include "rds.h" #define BIND_HASH_SIZE 1024 @@ -185,8 +186,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!trans) { ret = -EADDRNOTAVAIL; rds_remove_bound(rs); - if (printk_ratelimit()) - printk(KERN_INFO "RDS: rds_bind() could not find a transport, " + printk_ratelimited(KERN_INFO "RDS: rds_bind() could not find a transport, " "load rds_tcp or rds_rdma?\n"); goto out; } diff --git a/net/rds/ib.h b/net/rds/ib.h index 4297d92788d..edfaaaf164e 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -3,6 +3,7 @@ #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> +#include <linux/interrupt.h> #include <linux/pci.h> #include <linux/slab.h> #include "rds.h" diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index fd453dd5124..cd67026be2d 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -34,6 +34,7 @@ #include <linux/in.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/ratelimit.h> #include "rds.h" #include "ib.h" @@ -435,13 +436,12 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event) version = RDS_PROTOCOL_3_0; while ((common >>= 1) != 0) version++; - } else if (printk_ratelimit()) { - printk(KERN_NOTICE "RDS: Connection from %pI4 using " + } + printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using " "incompatible protocol version %u.%u\n", &dp->dp_saddr, dp->dp_protocol_major, dp->dp_protocol_minor); - } return version; } diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 7c4dce8fa5e..e5909498117 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -34,6 +34,7 @@ #include <linux/in.h> #include <linux/device.h> #include <linux/dmapool.h> +#include <linux/ratelimit.h> #include "rds.h" #include "ib.h" @@ -207,8 +208,7 @@ static struct rds_message *rds_ib_send_unmap_op(struct rds_ib_connection *ic, } break; default: - if (printk_ratelimit()) - printk(KERN_NOTICE + printk_ratelimited(KERN_NOTICE "RDS/IB: %s: unexpected opcode 0x%x in WR!\n", __func__, send->s_wr.opcode); break; diff --git a/net/rds/iw.h b/net/rds/iw.h index 90151922178..04ce3b193f7 100644 --- a/net/rds/iw.h +++ b/net/rds/iw.h @@ -1,6 +1,7 @@ #ifndef _RDS_IW_H #define _RDS_IW_H +#include <linux/interrupt.h> #include <rdma/ib_verbs.h> #include <rdma/rdma_cm.h> #include "rds.h" diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c index c12db66f24c..9556d2895f7 100644 --- a/net/rds/iw_cm.c +++ b/net/rds/iw_cm.c @@ -34,6 +34,7 @@ #include <linux/in.h> #include <linux/slab.h> #include <linux/vmalloc.h> +#include <linux/ratelimit.h> #include "rds.h" #include "iw.h" @@ -258,8 +259,7 @@ static int rds_iw_setup_qp(struct rds_connection *conn) */ rds_iwdev = ib_get_client_data(dev, &rds_iw_client); if (!rds_iwdev) { - if (printk_ratelimit()) - printk(KERN_NOTICE "RDS/IW: No client_data for device %s\n", + printk_ratelimited(KERN_NOTICE "RDS/IW: No client_data for device %s\n", dev->name); return -EOPNOTSUPP; } @@ -365,13 +365,12 @@ static u32 rds_iw_protocol_compatible(const struct rds_iw_connect_private *dp) version = RDS_PROTOCOL_3_0; while ((common >>= 1) != 0) version++; - } else if (printk_ratelimit()) { - printk(KERN_NOTICE "RDS: Connection from %pI4 using " + } + printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using " "incompatible protocol version %u.%u\n", &dp->dp_saddr, dp->dp_protocol_major, dp->dp_protocol_minor); - } return version; } diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c index 6deaa77495e..8b77edbab27 100644 --- a/net/rds/iw_rdma.c +++ b/net/rds/iw_rdma.c @@ -32,6 +32,7 @@ */ #include <linux/kernel.h> #include <linux/slab.h> +#include <linux/ratelimit.h> #include "rds.h" #include "iw.h" @@ -729,8 +730,8 @@ static int rds_iw_rdma_build_fastreg(struct rds_iw_mapping *mapping) failed_wr = &f_wr; ret = ib_post_send(ibmr->cm_id->qp, &f_wr, &failed_wr); BUG_ON(failed_wr != &f_wr); - if (ret && printk_ratelimit()) - printk(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n", + if (ret) + printk_ratelimited(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n", __func__, __LINE__, ret); return ret; } @@ -751,8 +752,8 @@ static int rds_iw_rdma_fastreg_inv(struct rds_iw_mr *ibmr) failed_wr = &s_wr; ret = ib_post_send(ibmr->cm_id->qp, &s_wr, &failed_wr); - if (ret && printk_ratelimit()) { - printk(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n", + if (ret) { + printk_ratelimited(KERN_WARNING "RDS/IW: %s:%d ib_post_send returned %d\n", __func__, __LINE__, ret); goto out; } diff --git a/net/rds/iw_send.c b/net/rds/iw_send.c index 545d8ee3efb..e40c3c5db2c 100644 --- a/net/rds/iw_send.c +++ b/net/rds/iw_send.c @@ -34,6 +34,7 @@ #include <linux/in.h> #include <linux/device.h> #include <linux/dmapool.h> +#include <linux/ratelimit.h> #include "rds.h" #include "iw.h" @@ -258,8 +259,7 @@ void rds_iw_send_cq_comp_handler(struct ib_cq *cq, void *context) * when the SEND completes. */ break; default: - if (printk_ratelimit()) - printk(KERN_NOTICE + printk_ratelimited(KERN_NOTICE "RDS/IW: %s: unexpected opcode 0x%x in WR!\n", __func__, send->s_wr.opcode); break; diff --git a/net/rds/send.c b/net/rds/send.c index d58ae5f9339..aa57e22539e 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -35,6 +35,7 @@ #include <net/sock.h> #include <linux/in.h> #include <linux/list.h> +#include <linux/ratelimit.h> #include "rds.h" @@ -1006,16 +1007,14 @@ int rds_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg, goto out; if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { - if (printk_ratelimit()) - printk(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", + printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", &rm->rdma, conn->c_trans->xmit_rdma); ret = -EOPNOTSUPP; goto out; } if (rm->atomic.op_active && !conn->c_trans->xmit_atomic) { - if (printk_ratelimit()) - printk(KERN_NOTICE "atomic_op %p conn xmit_atomic %p\n", + printk_ratelimited(KERN_NOTICE "atomic_op %p conn xmit_atomic %p\n", &rm->atomic, conn->c_trans->xmit_atomic); ret = -EOPNOTSUPP; goto out; diff --git a/net/rds/tcp_stats.c b/net/rds/tcp_stats.c index d5898d03cd6..f8a7954f1f5 100644 --- a/net/rds/tcp_stats.c +++ b/net/rds/tcp_stats.c @@ -40,7 +40,7 @@ DEFINE_PER_CPU(struct rds_tcp_statistics, rds_tcp_stats) ____cacheline_aligned; -static const char const *rds_tcp_stat_names[] = { +static const char * const rds_tcp_stat_names[] = { "tcp_data_ready_calls", "tcp_write_space_calls", "tcp_sndbuf_full", diff --git a/net/rose/rose_link.c b/net/rose/rose_link.c index fa5f5641a2c..7a02bd1cc5a 100644 --- a/net/rose/rose_link.c +++ b/net/rose/rose_link.c @@ -266,13 +266,6 @@ void rose_transmit_link(struct sk_buff *skb, struct rose_neigh *neigh) { unsigned char *dptr; -#if 0 - if (call_fw_firewall(PF_ROSE, skb->dev, skb->data, NULL, &skb) != FW_ACCEPT) { - kfree_skb(skb); - return; - } -#endif - if (neigh->loopback) { rose_loopback_queue(skb, neigh); return; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index 479cae57d18..d389de19708 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -864,11 +864,6 @@ int rose_route_frame(struct sk_buff *skb, ax25_cb *ax25) int res = 0; char buf[11]; -#if 0 - if (call_in_firewall(PF_ROSE, skb->dev, skb->data, NULL, &skb) != FW_ACCEPT) - return res; -#endif - if (skb->len < ROSE_MIN_LEN) return res; frametype = skb->data[2]; diff --git a/net/sched/act_api.c b/net/sched/act_api.c index a606025814a..f2fb67e701a 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -365,10 +365,10 @@ static struct tc_action_ops *tc_lookup_action_id(u32 type) } #endif -int tcf_action_exec(struct sk_buff *skb, struct tc_action *act, +int tcf_action_exec(struct sk_buff *skb, const struct tc_action *act, struct tcf_result *res) { - struct tc_action *a; + const struct tc_action *a; int ret = -1; if (skb->tc_verd & TC_NCLS) { @@ -1115,9 +1115,10 @@ nlmsg_failure: static int __init tc_action_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL); - rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL); - rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action); + rtnl_register(PF_UNSPEC, RTM_NEWACTION, tc_ctl_action, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELACTION, tc_ctl_action, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETACTION, tc_ctl_action, tc_dump_action, + NULL); return 0; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 6cdf9abe475..453a73431ac 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -500,7 +500,7 @@ fail: } static int tcf_csum(struct sk_buff *skb, - struct tc_action *a, struct tcf_result *res) + const struct tc_action *a, struct tcf_result *res) { struct tcf_csum *p = a->priv; int action; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index 2b4ab4b05ce..b77f5a06a65 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -125,7 +125,8 @@ static int tcf_gact_cleanup(struct tc_action *a, int bind) return 0; } -static int tcf_gact(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) +static int tcf_gact(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) { struct tcf_gact *gact = a->priv; int action = TC_ACT_SHOT; diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 9fc211a1b20..60f8f616e8f 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -195,7 +195,7 @@ static int tcf_ipt_cleanup(struct tc_action *a, int bind) return tcf_ipt_release(ipt, bind); } -static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, +static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { int ret = 0, result = 0; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 961386e2f2c..102fc212cd6 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -154,7 +154,7 @@ static int tcf_mirred_cleanup(struct tc_action *a, int bind) return 0; } -static int tcf_mirred(struct sk_buff *skb, struct tc_action *a, +static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mirred *m = a->priv; diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 762b027650a..001d1b35486 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -102,7 +102,7 @@ static int tcf_nat_cleanup(struct tc_action *a, int bind) return tcf_hash_release(&p->common, bind, &nat_hash_info); } -static int tcf_nat(struct sk_buff *skb, struct tc_action *a, +static int tcf_nat(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_nat *p = a->priv; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 7affe9a9275..10d3aed8656 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -120,7 +120,7 @@ static int tcf_pedit_cleanup(struct tc_action *a, int bind) return 0; } -static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, +static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_pedit *p = a->priv; diff --git a/net/sched/act_police.c b/net/sched/act_police.c index b3b9b32f4e0..6fb3f5af0f8 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -282,7 +282,7 @@ static int tcf_act_police_cleanup(struct tc_action *a, int bind) return ret; } -static int tcf_act_police(struct sk_buff *skb, struct tc_action *a, +static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_police *police = a->priv; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index a34a22de60b..73e0a3ab4d5 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -36,7 +36,8 @@ static struct tcf_hashinfo simp_hash_info = { }; #define SIMP_MAX_DATA 32 -static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result *res) +static int tcf_simp(struct sk_buff *skb, const struct tc_action *a, + struct tcf_result *res) { struct tcf_defact *d = a->priv; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 5f6f0c7c390..35dbbe91027 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -39,7 +39,7 @@ static struct tcf_hashinfo skbedit_hash_info = { .lock = &skbedit_lock, }; -static int tcf_skbedit(struct sk_buff *skb, struct tc_action *a, +static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbedit *d = a->priv; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index bb2c523f815..a69d44f1dac 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -40,9 +40,9 @@ static DEFINE_RWLOCK(cls_mod_lock); /* Find classifier type by string name */ -static struct tcf_proto_ops *tcf_proto_lookup_ops(struct nlattr *kind) +static const struct tcf_proto_ops *tcf_proto_lookup_ops(struct nlattr *kind) { - struct tcf_proto_ops *t = NULL; + const struct tcf_proto_ops *t = NULL; if (kind) { read_lock(&cls_mod_lock); @@ -132,7 +132,7 @@ static int tc_ctl_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *q; struct tcf_proto **back, **chain; struct tcf_proto *tp; - struct tcf_proto_ops *tp_ops; + const struct tcf_proto_ops *tp_ops; const struct Qdisc_class_ops *cops; unsigned long cl; unsigned long fh; @@ -610,10 +610,10 @@ EXPORT_SYMBOL(tcf_exts_dump_stats); static int __init tc_filter_init(void) { - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_ctl_tfilter, NULL, NULL); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_ctl_tfilter, - tc_dump_tfilter); + tc_dump_tfilter, NULL); return 0; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 8be8872dd57..ea1f70b5a5f 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -39,7 +39,7 @@ static const struct tcf_ext_map basic_ext_map = { .police = TCA_BASIC_POLICE }; -static int basic_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { int r; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 32a335194ca..f84fdc3a7f2 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -101,7 +101,7 @@ struct cls_cgroup_head { struct tcf_ematch_tree ematches; }; -static int cls_cgroup_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int cls_cgroup_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct cls_cgroup_head *head = tp->root; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 8ec01391d98..6994214db8f 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -121,7 +121,7 @@ static u32 flow_get_proto_src(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -356,7 +356,7 @@ static u32 flow_key_get(struct sk_buff *skb, int key) } } -static int flow_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int flow_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct flow_head *head = tp->root; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 26e7bc4ffb7..389af152ec4 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -77,7 +77,7 @@ static inline int fw_hash(u32 handle) return handle & (HTSIZE - 1); } -static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int fw_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct fw_head *head = (struct fw_head *)tp->root; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index a907905376d..13ab66e9df5 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -125,7 +125,7 @@ static inline int route4_hash_wild(void) return 0; \ } -static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int route4_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct route4_head *head = (struct route4_head *)tp->root; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 402c44b241a..be4505ee67a 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -130,7 +130,7 @@ static struct tcf_ext_map rsvp_ext_map = { return r; \ } -static int rsvp_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int rsvp_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; @@ -167,7 +167,7 @@ restart: dst = &nhptr->daddr; protocol = nhptr->protocol; xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (nhptr->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(nhptr)) return -1; #endif diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 36667fa6423..dbe199234c6 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -79,7 +79,7 @@ tcindex_lookup(struct tcindex_data *p, u16 key) } -static int tcindex_classify(struct sk_buff *skb, struct tcf_proto *tp, +static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct tcindex_data *p = PRIV(tp); diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 3b93fc0c895..939b627b479 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -93,7 +93,7 @@ static inline unsigned int u32_hash_fold(__be32 key, return h; } -static int u32_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) +static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { struct { struct tc_u_knode *knode; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 49130e8abff..1363bf14e61 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -404,12 +404,6 @@ META_COLLECTOR(int_sk_alloc) dst->value = (__force int) skb->sk->sk_allocation; } -META_COLLECTOR(int_sk_route_caps) -{ - SKIP_NONLOCAL(skb); - dst->value = skb->sk->sk_route_caps; -} - META_COLLECTOR(int_sk_hash) { SKIP_NONLOCAL(skb); @@ -530,7 +524,6 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX + 1][TCF_META_ID_MAX + 1] = [META_ID(SK_ERR_QLEN)] = META_FUNC(int_sk_err_qlen), [META_ID(SK_FORWARD_ALLOCS)] = META_FUNC(int_sk_fwd_alloc), [META_ID(SK_ALLOCS)] = META_FUNC(int_sk_alloc), - [META_ID(SK_ROUTE_CAPS)] = META_FUNC(int_sk_route_caps), [META_ID(SK_HASH)] = META_FUNC(int_sk_hash), [META_ID(SK_LINGERTIME)] = META_FUNC(int_sk_lingertime), [META_ID(SK_ACK_BACKLOG)] = META_FUNC(int_sk_ack_bl), diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 6b8627661c9..dca6c1a576f 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1644,7 +1644,7 @@ done: * to this qdisc, (optionally) tests for protocol and asks * specific classifiers. */ -int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp, +int tc_classify_compat(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { __be16 protocol = skb->protocol; @@ -1668,12 +1668,12 @@ int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp, } EXPORT_SYMBOL(tc_classify_compat); -int tc_classify(struct sk_buff *skb, struct tcf_proto *tp, +int tc_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res) { int err = 0; #ifdef CONFIG_NET_CLS_ACT - struct tcf_proto *otp = tp; + const struct tcf_proto *otp = tp; reclassify: #endif @@ -1792,12 +1792,12 @@ static int __init pktsched_init(void) register_qdisc(&pfifo_head_drop_qdisc_ops); register_qdisc(&mq_qdisc_ops); - rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL); - rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL); - rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc); - rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL); - rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL); - rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass); + rtnl_register(PF_UNSPEC, RTM_NEWQDISC, tc_modify_qdisc, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELQDISC, tc_get_qdisc, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETQDISC, tc_get_qdisc, tc_dump_qdisc, NULL); + rtnl_register(PF_UNSPEC, RTM_NEWTCLASS, tc_ctl_tclass, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_DELTCLASS, tc_ctl_tclass, NULL, NULL); + rtnl_register(PF_UNSPEC, RTM_GETTCLASS, tc_ctl_tclass, tc_dump_tclass, NULL); return 0; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 3f08158b868..e25e49061a0 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -5,6 +5,7 @@ #include <linux/module.h> #include <linux/slab.h> #include <linux/init.h> +#include <linux/interrupt.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 06afbaeb4c8..3422b25df9e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -181,7 +181,7 @@ static bool choke_match_flow(struct sk_buff *skb1, ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr) return false; - if ((ip1->frag_off | ip2->frag_off) & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip1) | ip_is_fragment(ip2)) ip_proto = 0; off1 += ip1->ihl * 4; off2 += ip2->ihl * 4; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index b1721d71c27..69fca279880 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -189,15 +189,15 @@ static inline int qdisc_restart(struct Qdisc *q) void __qdisc_run(struct Qdisc *q) { - unsigned long start_time = jiffies; + int quota = weight_p; while (qdisc_restart(q)) { /* - * Postpone processing if - * 1. another process needs the CPU; - * 2. we've been doing it for too long. + * Ordered by possible occurrence: Postpone processing if + * 1. we've exceeded packet quota + * 2. another process needs the CPU; */ - if (need_resched() || jiffies != start_time) { + if (--quota <= 0 || need_resched()) { __netif_schedule(q); break; } @@ -251,9 +251,8 @@ static void dev_watchdog(unsigned long arg) } if (some_queue_timedout) { - char drivername[64]; WARN_ONCE(1, KERN_INFO "NETDEV WATCHDOG: %s (%s): transmit queue %u timed out\n", - dev->name, netdev_drivername(dev, drivername, 64), i); + dev->name, netdev_drivername(dev), i); dev->netdev_ops->ndo_tx_timeout(dev); } if (!mod_timer(&dev->watchdog_timer, diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 69c35f6cd13..eb3b9a86c6e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -13,6 +13,7 @@ * Catalin(ux aka Dino) BOIE <catab at umbrella dot ro> */ +#include <linux/mm.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/types.h> diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b6ea6afa55b..4536ee64383 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -157,7 +157,7 @@ static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) iph = ip_hdr(skb); h = (__force u32)iph->daddr; h2 = (__force u32)iph->saddr ^ iph->protocol; - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 45cd30098e3..a3b7120fcc7 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -229,7 +229,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, struct net_device * { struct netdev_queue *dev_queue = netdev_get_tx_queue(dev, 0); struct teql_sched_data *q = qdisc_priv(dev_queue->qdisc); - struct neighbour *mn = skb_dst(skb)->neighbour; + struct neighbour *mn = dst_get_neighbour(skb_dst(skb)); struct neighbour *n = q->ncache; if (mn->tbl == NULL) @@ -270,7 +270,7 @@ static inline int teql_resolve(struct sk_buff *skb, if (dev->header_ops == NULL || skb_dst(skb) == NULL || - skb_dst(skb)->neighbour == NULL) + dst_get_neighbour(skb_dst(skb)) == NULL) return 0; return __teql_resolve(skb, skb_res, dev); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 4a62888f2e4..dc16b90ddb6 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -280,6 +280,8 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->peer.asconf_capable = 0; if (sctp_addip_noauth) asoc->peer.asconf_capable = 1; + asoc->asconf_addr_del_pending = NULL; + asoc->src_out_of_asoc_ok = 0; /* Create an input queue. */ sctp_inq_init(&asoc->base.inqueue); @@ -446,6 +448,10 @@ void sctp_association_free(struct sctp_association *asoc) sctp_asconf_queue_teardown(asoc); + /* Free pending address space being deleted */ + if (asoc->asconf_addr_del_pending != NULL) + kfree(asoc->asconf_addr_del_pending); + /* AUTH - Free the endpoint shared keys */ sctp_auth_destroy_keys(&asoc->endpoint_shared_keys); diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 83e3011c19c..4ece451c8d2 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -430,7 +430,7 @@ union sctp_addr *sctp_find_unmatch_addr(struct sctp_bind_addr *bp, list_for_each_entry(laddr, &bp->address_list, list) { addr_buf = (union sctp_addr *)addrs; for (i = 0; i < addrcnt; i++) { - addr = (union sctp_addr *)addr_buf; + addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) break; @@ -534,6 +534,21 @@ int sctp_in_scope(const union sctp_addr *addr, sctp_scope_t scope) return 0; } +int sctp_is_ep_boundall(struct sock *sk) +{ + struct sctp_bind_addr *bp; + struct sctp_sockaddr_entry *addr; + + bp = &sctp_sk(sk)->ep->base.bind_addr; + if (sctp_list_single_entry(&bp->address_list)) { + addr = list_entry(bp->address_list.next, + struct sctp_sockaddr_entry, list); + if (sctp_is_any(sk, &addr->a)) + return 1; + } + return 0; +} + /******************************************************************** * 3rd Level Abstractions ********************************************************************/ diff --git a/net/sctp/input.c b/net/sctp/input.c index 741ed164883..b7692aab6e9 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -510,8 +510,7 @@ struct sock *sctp_err_lookup(int family, struct sk_buff *skb, * discard the packet. */ if (vtag == 0) { - chunkhdr = (struct sctp_init_chunk *)((void *)sctphdr - + sizeof(struct sctphdr)); + chunkhdr = (void *)sctphdr + sizeof(struct sctphdr); if (len < sizeof(struct sctphdr) + sizeof(sctp_chunkhdr_t) + sizeof(__be32) || chunkhdr->chunk_hdr.type != SCTP_CID_INIT || diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 0bb0d7cb9f1..aabaee41dd3 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -112,6 +112,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, addr->valid = 1; spin_lock_bh(&sctp_local_addr_lock); list_add_tail_rcu(&addr->list, &sctp_local_addr_list); + sctp_addr_wq_mgmt(addr, SCTP_ADDR_NEW); spin_unlock_bh(&sctp_local_addr_lock); } break; @@ -122,6 +123,7 @@ static int sctp_inet6addr_event(struct notifier_block *this, unsigned long ev, if (addr->a.sa.sa_family == AF_INET6 && ipv6_addr_equal(&addr->a.v6.sin6_addr, &ifa->addr)) { + sctp_addr_wq_mgmt(addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); diff --git a/net/sctp/output.c b/net/sctp/output.c index b4f3cf06d8d..08b3cead650 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -500,23 +500,20 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: Adler-32 is no longer applicable, as has been replaced * by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>. */ - if (!sctp_checksum_disable && - !(dst->dev->features & (NETIF_F_NO_CSUM | NETIF_F_SCTP_CSUM))) { - __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); + if (!sctp_checksum_disable) { + if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) { + __u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len); - /* 3) Put the resultant value into the checksum field in the - * common header, and leave the rest of the bits unchanged. - */ - sh->checksum = sctp_end_cksum(crc32); - } else { - if (dst->dev->features & NETIF_F_SCTP_CSUM) { + /* 3) Put the resultant value into the checksum field in the + * common header, and leave the rest of the bits unchanged. + */ + sh->checksum = sctp_end_cksum(crc32); + } else { /* no need to seed pseudo checksum for SCTP */ nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum_start = (skb_transport_header(nskb) - nskb->head); nskb->csum_offset = offsetof(struct sctphdr, checksum); - } else { - nskb->ip_summed = CHECKSUM_UNNECESSARY; } } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 1c88c8911dc..a6d27bf563a 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -754,6 +754,16 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) */ list_for_each_entry_safe(chunk, tmp, &q->control_chunk_list, list) { + /* RFC 5061, 5.3 + * F1) This means that until such time as the ASCONF + * containing the add is acknowledged, the sender MUST + * NOT use the new IP address as a source for ANY SCTP + * packet except on carrying an ASCONF Chunk. + */ + if (asoc->src_out_of_asoc_ok && + chunk->chunk_hdr->type != SCTP_CID_ASCONF) + continue; + list_del_init(&chunk->list); /* Pick the right transport to use. */ @@ -881,6 +891,9 @@ static int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) } } + if (q->asoc->src_out_of_asoc_ok) + goto sctp_flush_out; + /* Is it OK to send data chunks? */ switch (asoc->state) { case SCTP_STATE_COOKIE_ECHOED: @@ -1582,6 +1595,8 @@ static void sctp_check_transmitted(struct sctp_outq *q, #endif /* SCTP_DEBUG */ if (transport) { if (bytes_acked) { + struct sctp_association *asoc = transport->asoc; + /* We may have counted DATA that was migrated * to this transport due to DEL-IP operation. * Subtract those bytes, since the were never @@ -1600,6 +1615,17 @@ static void sctp_check_transmitted(struct sctp_outq *q, transport->error_count = 0; transport->asoc->overall_error_count = 0; + /* + * While in SHUTDOWN PENDING, we may have started + * the T5 shutdown guard timer after reaching the + * retransmission limit. Stop that timer as soon + * as the receiver acknowledged any data. + */ + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING && + del_timer(&asoc->timers + [SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD])) + sctp_association_put(asoc); + /* Mark the destination transport address as * active if it is not so marked. */ @@ -1629,10 +1655,15 @@ static void sctp_check_transmitted(struct sctp_outq *q, * A sender is doing zero window probing when the * receiver's advertised window is zero, and there is * only one data chunk in flight to the receiver. + * + * Allow the association to timeout while in SHUTDOWN + * PENDING or SHUTDOWN RECEIVED in case the receiver + * stays in zero window mode forever. */ if (!q->asoc->peer.rwnd && !list_empty(&tlist) && - (sack_ctsn+2 == q->asoc->next_tsn)) { + (sack_ctsn+2 == q->asoc->next_tsn) && + q->asoc->state < SCTP_STATE_SHUTDOWN_PENDING) { SCTP_DEBUG_PRINTK("%s: SACK received for zero " "window probe: %u\n", __func__, sack_ctsn); diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 67380a29e2e..91784f44a2e 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -503,7 +503,9 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, sctp_v4_dst_saddr(&dst_saddr, fl4, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { - if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) + if (!laddr->valid || (laddr->state == SCTP_ADDR_DEL) || + (laddr->state != SCTP_ADDR_SRC && + !asoc->src_out_of_asoc_ok)) continue; if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a)) goto out_unlock; @@ -623,6 +625,143 @@ static void sctp_v4_ecn_capable(struct sock *sk) INET_ECN_xmit(sk); } +void sctp_addr_wq_timeout_handler(unsigned long arg) +{ + struct sctp_sockaddr_entry *addrw, *temp; + struct sctp_sock *sp; + + spin_lock_bh(&sctp_addr_wq_lock); + + list_for_each_entry_safe(addrw, temp, &sctp_addr_waitq, list) { + SCTP_DEBUG_PRINTK_IPADDR("sctp_addrwq_timo_handler: the first ent in wq %p is ", + " for cmd %d at entry %p\n", &sctp_addr_waitq, &addrw->a, addrw->state, + addrw); + +#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + /* Now we send an ASCONF for each association */ + /* Note. we currently don't handle link local IPv6 addressees */ + if (addrw->a.sa.sa_family == AF_INET6) { + struct in6_addr *in6; + + if (ipv6_addr_type(&addrw->a.v6.sin6_addr) & + IPV6_ADDR_LINKLOCAL) + goto free_next; + + in6 = (struct in6_addr *)&addrw->a.v6.sin6_addr; + if (ipv6_chk_addr(&init_net, in6, NULL, 0) == 0 && + addrw->state == SCTP_ADDR_NEW) { + unsigned long timeo_val; + + SCTP_DEBUG_PRINTK("sctp_timo_handler: this is on DAD, trying %d sec later\n", + SCTP_ADDRESS_TICK_DELAY); + timeo_val = jiffies; + timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY); + mod_timer(&sctp_addr_wq_timer, timeo_val); + break; + } + } +#endif + list_for_each_entry(sp, &sctp_auto_asconf_splist, auto_asconf_list) { + struct sock *sk; + + sk = sctp_opt2sk(sp); + /* ignore bound-specific endpoints */ + if (!sctp_is_ep_boundall(sk)) + continue; + sctp_bh_lock_sock(sk); + if (sctp_asconf_mgmt(sp, addrw) < 0) + SCTP_DEBUG_PRINTK("sctp_addrwq_timo_handler: sctp_asconf_mgmt failed\n"); + sctp_bh_unlock_sock(sk); + } +free_next: + list_del(&addrw->list); + kfree(addrw); + } + spin_unlock_bh(&sctp_addr_wq_lock); +} + +static void sctp_free_addr_wq(void) +{ + struct sctp_sockaddr_entry *addrw; + struct sctp_sockaddr_entry *temp; + + spin_lock_bh(&sctp_addr_wq_lock); + del_timer(&sctp_addr_wq_timer); + list_for_each_entry_safe(addrw, temp, &sctp_addr_waitq, list) { + list_del(&addrw->list); + kfree(addrw); + } + spin_unlock_bh(&sctp_addr_wq_lock); +} + +/* lookup the entry for the same address in the addr_waitq + * sctp_addr_wq MUST be locked + */ +static struct sctp_sockaddr_entry *sctp_addr_wq_lookup(struct sctp_sockaddr_entry *addr) +{ + struct sctp_sockaddr_entry *addrw; + + list_for_each_entry(addrw, &sctp_addr_waitq, list) { + if (addrw->a.sa.sa_family != addr->a.sa.sa_family) + continue; + if (addrw->a.sa.sa_family == AF_INET) { + if (addrw->a.v4.sin_addr.s_addr == + addr->a.v4.sin_addr.s_addr) + return addrw; + } else if (addrw->a.sa.sa_family == AF_INET6) { + if (ipv6_addr_equal(&addrw->a.v6.sin6_addr, + &addr->a.v6.sin6_addr)) + return addrw; + } + } + return NULL; +} + +void sctp_addr_wq_mgmt(struct sctp_sockaddr_entry *addr, int cmd) +{ + struct sctp_sockaddr_entry *addrw; + unsigned long timeo_val; + + /* first, we check if an opposite message already exist in the queue. + * If we found such message, it is removed. + * This operation is a bit stupid, but the DHCP client attaches the + * new address after a couple of addition and deletion of that address + */ + + spin_lock_bh(&sctp_addr_wq_lock); + /* Offsets existing events in addr_wq */ + addrw = sctp_addr_wq_lookup(addr); + if (addrw) { + if (addrw->state != cmd) { + SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt offsets existing entry for %d ", + " in wq %p\n", addrw->state, &addrw->a, + &sctp_addr_waitq); + list_del(&addrw->list); + kfree(addrw); + } + spin_unlock_bh(&sctp_addr_wq_lock); + return; + } + + /* OK, we have to add the new address to the wait queue */ + addrw = kmemdup(addr, sizeof(struct sctp_sockaddr_entry), GFP_ATOMIC); + if (addrw == NULL) { + spin_unlock_bh(&sctp_addr_wq_lock); + return; + } + addrw->state = cmd; + list_add_tail(&addrw->list, &sctp_addr_waitq); + SCTP_DEBUG_PRINTK_IPADDR("sctp_addr_wq_mgmt add new entry for cmd:%d ", + " in wq %p\n", addrw->state, &addrw->a, &sctp_addr_waitq); + + if (!timer_pending(&sctp_addr_wq_timer)) { + timeo_val = jiffies; + timeo_val += msecs_to_jiffies(SCTP_ADDRESS_TICK_DELAY); + mod_timer(&sctp_addr_wq_timer, timeo_val); + } + spin_unlock_bh(&sctp_addr_wq_lock); +} + /* Event handler for inet address addition/deletion events. * The sctp_local_addr_list needs to be protocted by a spin lock since * multiple notifiers (say IPv4 and IPv6) may be running at the same @@ -650,6 +789,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, addr->valid = 1; spin_lock_bh(&sctp_local_addr_lock); list_add_tail_rcu(&addr->list, &sctp_local_addr_list); + sctp_addr_wq_mgmt(addr, SCTP_ADDR_NEW); spin_unlock_bh(&sctp_local_addr_lock); } break; @@ -660,6 +800,7 @@ static int sctp_inetaddr_event(struct notifier_block *this, unsigned long ev, if (addr->a.sa.sa_family == AF_INET && addr->a.v4.sin_addr.s_addr == ifa->ifa_local) { + sctp_addr_wq_mgmt(addr, SCTP_ADDR_DEL); found = 1; addr->valid = 0; list_del_rcu(&addr->list); @@ -1058,7 +1199,6 @@ SCTP_STATIC __init int sctp_init(void) int status = -EINVAL; unsigned long goal; unsigned long limit; - unsigned long nr_pages; int max_share; int order; @@ -1148,15 +1288,7 @@ SCTP_STATIC __init int sctp_init(void) /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); - /* Set the pressure threshold to be a fraction of global memory that - * is up to 1/2 at 256 MB, decreasing toward zero with the amount of - * memory, with a floor of 128 pages. - * Note this initializes the data in sctpv6_prot too - * Unabashedly stolen from tcp_init - */ - nr_pages = totalram_pages - totalhigh_pages; - limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_sctp_mem[0] = limit / 4 * 3; sysctl_sctp_mem[1] = limit; @@ -1242,6 +1374,7 @@ SCTP_STATIC __init int sctp_init(void) /* Disable ADDIP by default. */ sctp_addip_enable = 0; sctp_addip_noauth = 0; + sctp_default_auto_asconf = 0; /* Enable PR-SCTP by default. */ sctp_prsctp_enable = 1; @@ -1266,6 +1399,13 @@ SCTP_STATIC __init int sctp_init(void) spin_lock_init(&sctp_local_addr_lock); sctp_get_local_addr_list(); + /* Initialize the address event list */ + INIT_LIST_HEAD(&sctp_addr_waitq); + INIT_LIST_HEAD(&sctp_auto_asconf_splist); + spin_lock_init(&sctp_addr_wq_lock); + sctp_addr_wq_timer.expires = 0; + setup_timer(&sctp_addr_wq_timer, sctp_addr_wq_timeout_handler, 0); + status = sctp_v4_protosw_init(); if (status) @@ -1337,6 +1477,7 @@ SCTP_STATIC __exit void sctp_exit(void) /* Unregister with inet6/inet layers. */ sctp_v6_del_protocol(); sctp_v4_del_protocol(); + sctp_free_addr_wq(); /* Free the control endpoint. */ inet_ctl_sock_destroy(sctp_ctl_sock); diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 58eb27fed4b..81db4e38535 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -2768,11 +2768,12 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, int addr_param_len = 0; int totallen = 0; int i; + int del_pickup = 0; /* Get total length of all the address parameters. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { - addr = (union sctp_addr *)addr_buf; + addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); addr_param_len = af->to_addr_param(addr, &addr_param); @@ -2780,6 +2781,13 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, totallen += addr_param_len; addr_buf += af->sockaddr_len; + if (asoc->asconf_addr_del_pending && !del_pickup) { + /* reuse the parameter length from the same scope one */ + totallen += paramlen; + totallen += addr_param_len; + del_pickup = 1; + SCTP_DEBUG_PRINTK("mkasconf_update_ip: picked same-scope del_pending addr, totallen for all addresses is %d\n", totallen); + } } /* Create an asconf chunk with the required length. */ @@ -2790,7 +2798,7 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, /* Add the address parameters to the asconf chunk. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { - addr = (union sctp_addr *)addr_buf; + addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); addr_param_len = af->to_addr_param(addr, &addr_param); param.param_hdr.type = flags; @@ -2802,6 +2810,17 @@ struct sctp_chunk *sctp_make_asconf_update_ip(struct sctp_association *asoc, addr_buf += af->sockaddr_len; } + if (flags == SCTP_PARAM_ADD_IP && del_pickup) { + addr = asoc->asconf_addr_del_pending; + af = sctp_get_af_specific(addr->v4.sin_family); + addr_param_len = af->to_addr_param(addr, &addr_param); + param.param_hdr.type = SCTP_PARAM_DEL_IP; + param.param_hdr.length = htons(paramlen + addr_param_len); + param.crr_id = i; + + sctp_addto_chunk(retval, paramlen, ¶m); + sctp_addto_chunk(retval, addr_param_len, &addr_param); + } return retval; } @@ -2939,8 +2958,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, union sctp_addr addr; union sctp_addr_param *addr_param; - addr_param = (union sctp_addr_param *) - ((void *)asconf_param + sizeof(sctp_addip_param_t)); + addr_param = (void *)asconf_param + sizeof(sctp_addip_param_t); if (asconf_param->param_hdr.type != SCTP_PARAM_ADD_IP && asconf_param->param_hdr.type != SCTP_PARAM_DEL_IP && @@ -3014,7 +3032,7 @@ static __be16 sctp_process_asconf_param(struct sctp_association *asoc, * an Error Cause TLV set to the new error code 'Request to * Delete Source IP Address' */ - if (sctp_cmp_addr_exact(sctp_source(asconf), &addr)) + if (sctp_cmp_addr_exact(&asconf->source, &addr)) return SCTP_ERROR_DEL_SRC_IP; /* Section 4.2.2 @@ -3125,7 +3143,7 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, * asconf parameter. */ length = ntohs(addr_param->p.length); - asconf_param = (sctp_addip_param_t *)((void *)addr_param + length); + asconf_param = (void *)addr_param + length; chunk_len -= length; /* create an ASCONF_ACK chunk. @@ -3166,8 +3184,7 @@ struct sctp_chunk *sctp_process_asconf(struct sctp_association *asoc, /* Move to the next ASCONF param. */ length = ntohs(asconf_param->param_hdr.length); - asconf_param = (sctp_addip_param_t *)((void *)asconf_param + - length); + asconf_param = (void *)asconf_param + length; chunk_len -= length; } @@ -3197,8 +3214,7 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, struct sctp_transport *transport; struct sctp_sockaddr_entry *saddr; - addr_param = (union sctp_addr_param *) - ((void *)asconf_param + sizeof(sctp_addip_param_t)); + addr_param = (void *)asconf_param + sizeof(sctp_addip_param_t); /* We have checked the packet before, so we do not check again. */ af = sctp_get_af_specific(param_type2af(addr_param->p.type)); @@ -3224,6 +3240,11 @@ static void sctp_asconf_param_success(struct sctp_association *asoc, case SCTP_PARAM_DEL_IP: local_bh_disable(); sctp_del_bind_addr(bp, &addr); + if (asoc->asconf_addr_del_pending != NULL && + sctp_cmp_addr_exact(asoc->asconf_addr_del_pending, &addr)) { + kfree(asoc->asconf_addr_del_pending); + asoc->asconf_addr_del_pending = NULL; + } local_bh_enable(); list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { @@ -3278,8 +3299,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, return SCTP_ERROR_NO_ERROR; case SCTP_PARAM_ERR_CAUSE: length = sizeof(sctp_addip_param_t); - err_param = (sctp_errhdr_t *) - ((void *)asconf_ack_param + length); + err_param = (void *)asconf_ack_param + length; asconf_ack_len -= length; if (asconf_ack_len > 0) return err_param->cause; @@ -3292,8 +3312,7 @@ static __be16 sctp_get_asconf_response(struct sctp_chunk *asconf_ack, } length = ntohs(asconf_ack_param->param_hdr.length); - asconf_ack_param = (sctp_addip_param_t *) - ((void *)asconf_ack_param + length); + asconf_ack_param = (void *)asconf_ack_param + length; asconf_ack_len -= length; } @@ -3325,7 +3344,7 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, * pointer to the first asconf parameter. */ length = ntohs(addr_param->p.length); - asconf_param = (sctp_addip_param_t *)((void *)addr_param + length); + asconf_param = (void *)addr_param + length; asconf_len -= length; /* ADDIP 4.1 @@ -3376,11 +3395,13 @@ int sctp_process_asconf_ack(struct sctp_association *asoc, * one. */ length = ntohs(asconf_param->param_hdr.length); - asconf_param = (sctp_addip_param_t *)((void *)asconf_param + - length); + asconf_param = (void *)asconf_param + length; asconf_len -= length; } + if (no_err && asoc->src_out_of_asoc_ok) + asoc->src_out_of_asoc_ok = 0; + /* Free the cached last sent asconf chunk. */ list_del_init(&asconf->transmitted_list); sctp_chunk_free(asconf); diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index 534c2e5feb0..167c880cf8d 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -670,10 +670,19 @@ static void sctp_cmd_transport_on(sctp_cmd_seq_t *cmds, /* 8.3 Upon the receipt of the HEARTBEAT ACK, the sender of the * HEARTBEAT should clear the error counter of the destination * transport address to which the HEARTBEAT was sent. - * The association's overall error count is also cleared. */ t->error_count = 0; - t->asoc->overall_error_count = 0; + + /* + * Although RFC4960 specifies that the overall error count must + * be cleared when a HEARTBEAT ACK is received, we make an + * exception while in SHUTDOWN PENDING. If the peer keeps its + * window shut forever, we may never be able to transmit our + * outstanding data and rely on the retransmission limit be reached + * to shutdown the association. + */ + if (t->asoc->state != SCTP_STATE_SHUTDOWN_PENDING) + t->asoc->overall_error_count = 0; /* Clear the hb_sent flag to signal that we had a good * acknowledgement. @@ -1201,7 +1210,7 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, int local_cork = 0; if (SCTP_EVENT_T_TIMEOUT != event_type) - chunk = (struct sctp_chunk *) event_arg; + chunk = event_arg; /* Note: This whole file is a huge candidate for rework. * For example, each command could either have its own handler, so @@ -1437,6 +1446,13 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, sctp_cmd_setup_t2(commands, asoc, cmd->obj.ptr); break; + case SCTP_CMD_TIMER_START_ONCE: + timer = &asoc->timers[cmd->obj.to]; + + if (timer_pending(timer)) + break; + /* fall through */ + case SCTP_CMD_TIMER_START: timer = &asoc->timers[cmd->obj.to]; timeout = asoc->timeouts[cmd->obj.to]; diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index a297283154d..49b847b00f9 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -4008,31 +4008,32 @@ sctp_disposition_t sctp_sf_eat_auth(const struct sctp_endpoint *ep, auth_hdr = (struct sctp_authhdr *)chunk->skb->data; error = sctp_sf_authenticate(ep, asoc, type, chunk); switch (error) { - case SCTP_IERROR_AUTH_BAD_HMAC: - /* Generate the ERROR chunk and discard the rest - * of the packet - */ - err_chunk = sctp_make_op_error(asoc, chunk, - SCTP_ERROR_UNSUP_HMAC, - &auth_hdr->hmac_id, - sizeof(__u16), 0); - if (err_chunk) { - sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, - SCTP_CHUNK(err_chunk)); - } - /* Fall Through */ - case SCTP_IERROR_AUTH_BAD_KEYID: - case SCTP_IERROR_BAD_SIG: - return sctp_sf_pdiscard(ep, asoc, type, arg, commands); - break; - case SCTP_IERROR_PROTO_VIOLATION: - return sctp_sf_violation_chunklen(ep, asoc, type, arg, - commands); - break; - case SCTP_IERROR_NOMEM: - return SCTP_DISPOSITION_NOMEM; - default: - break; + case SCTP_IERROR_AUTH_BAD_HMAC: + /* Generate the ERROR chunk and discard the rest + * of the packet + */ + err_chunk = sctp_make_op_error(asoc, chunk, + SCTP_ERROR_UNSUP_HMAC, + &auth_hdr->hmac_id, + sizeof(__u16), 0); + if (err_chunk) { + sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, + SCTP_CHUNK(err_chunk)); + } + /* Fall Through */ + case SCTP_IERROR_AUTH_BAD_KEYID: + case SCTP_IERROR_BAD_SIG: + return sctp_sf_pdiscard(ep, asoc, type, arg, commands); + + case SCTP_IERROR_PROTO_VIOLATION: + return sctp_sf_violation_chunklen(ep, asoc, type, arg, + commands); + + case SCTP_IERROR_NOMEM: + return SCTP_DISPOSITION_NOMEM; + + default: /* Prevent gcc warnings */ + break; } if (asoc->active_key_id != ntohs(auth_hdr->shkey_id)) { @@ -5154,7 +5155,7 @@ sctp_disposition_t sctp_sf_do_9_2_start_shutdown( * The sender of the SHUTDOWN MAY also start an overall guard timer * 'T5-shutdown-guard' to bound the overall time for shutdown sequence. */ - sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START, + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_RESTART, SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); if (asoc->autoclose) @@ -5299,14 +5300,28 @@ sctp_disposition_t sctp_sf_do_6_3_3_rtx(const struct sctp_endpoint *ep, SCTP_INC_STATS(SCTP_MIB_T3_RTX_EXPIREDS); if (asoc->overall_error_count >= asoc->max_retrans) { - sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, - SCTP_ERROR(ETIMEDOUT)); - /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ - sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, - SCTP_PERR(SCTP_ERROR_NO_ERROR)); - SCTP_INC_STATS(SCTP_MIB_ABORTEDS); - SCTP_DEC_STATS(SCTP_MIB_CURRESTAB); - return SCTP_DISPOSITION_DELETE_TCB; + if (asoc->state == SCTP_STATE_SHUTDOWN_PENDING) { + /* + * We are here likely because the receiver had its rwnd + * closed for a while and we have not been able to + * transmit the locally queued data within the maximum + * retransmission attempts limit. Start the T5 + * shutdown guard timer to give the receiver one last + * chance and some additional time to recover before + * aborting. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_START_ONCE, + SCTP_TO(SCTP_EVENT_TIMEOUT_T5_SHUTDOWN_GUARD)); + } else { + sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, + SCTP_ERROR(ETIMEDOUT)); + /* CMD_ASSOC_FAILED calls CMD_DELETE_TCB. */ + sctp_add_cmd_sf(commands, SCTP_CMD_ASSOC_FAILED, + SCTP_PERR(SCTP_ERROR_NO_ERROR)); + SCTP_INC_STATS(SCTP_MIB_ABORTEDS); + SCTP_DEC_STATS(SCTP_MIB_CURRESTAB); + return SCTP_DISPOSITION_DELETE_TCB; + } } /* E1) For the destination address for which the timer diff --git a/net/sctp/sm_statetable.c b/net/sctp/sm_statetable.c index 0338dc6fdc9..7c211a7f90f 100644 --- a/net/sctp/sm_statetable.c +++ b/net/sctp/sm_statetable.c @@ -827,7 +827,7 @@ static const sctp_sm_table_entry_t other_event_table[SCTP_NUM_OTHER_TYPES][SCTP_ /* SCTP_STATE_ESTABLISHED */ \ TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ /* SCTP_STATE_SHUTDOWN_PENDING */ \ - TYPE_SCTP_FUNC(sctp_sf_timer_ignore), \ + TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_SENT */ \ TYPE_SCTP_FUNC(sctp_sf_t5_timer_expire), \ /* SCTP_STATE_SHUTDOWN_RECEIVED */ \ diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6766913a53e..836aa63ee12 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -476,7 +476,7 @@ static int sctp_bindx_add(struct sock *sk, struct sockaddr *addrs, int addrcnt) /* The list may contain either IPv4 or IPv6 address; * determine the address length for walking thru the list. */ - sa_addr = (struct sockaddr *)addr_buf; + sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); if (!af) { retval = -EINVAL; @@ -555,7 +555,7 @@ static int sctp_send_asconf_add_ip(struct sock *sk, */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { - addr = (union sctp_addr *)addr_buf; + addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); if (!af) { retval = -EINVAL; @@ -583,22 +583,35 @@ static int sctp_send_asconf_add_ip(struct sock *sk, goto out; } - retval = sctp_send_asconf(asoc, chunk); - if (retval) - goto out; - /* Add the new addresses to the bind address list with * use_as_src set to 0. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { - addr = (union sctp_addr *)addr_buf; + addr = addr_buf; af = sctp_get_af_specific(addr->v4.sin_family); memcpy(&saveaddr, addr, af->sockaddr_len); retval = sctp_add_bind_addr(bp, &saveaddr, SCTP_ADDR_NEW, GFP_ATOMIC); addr_buf += af->sockaddr_len; } + if (asoc->src_out_of_asoc_ok) { + struct sctp_transport *trans; + + list_for_each_entry(trans, + &asoc->peer.transport_addr_list, transports) { + /* Clear the source and route cache */ + dst_release(trans->dst); + trans->cwnd = min(4*asoc->pathmtu, max_t(__u32, + 2*asoc->pathmtu, 4380)); + trans->ssthresh = asoc->peer.i.a_rwnd; + trans->rto = asoc->rto_initial; + trans->rtt = trans->srtt = trans->rttvar = 0; + sctp_transport_route(trans, NULL, + sctp_sk(asoc->base.sk)); + } + } + retval = sctp_send_asconf(asoc, chunk); } out: @@ -646,7 +659,7 @@ static int sctp_bindx_rem(struct sock *sk, struct sockaddr *addrs, int addrcnt) goto err_bindx_rem; } - sa_addr = (union sctp_addr *)addr_buf; + sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa.sa_family); if (!af) { retval = -EINVAL; @@ -715,7 +728,9 @@ static int sctp_send_asconf_del_ip(struct sock *sk, struct sctp_sockaddr_entry *saddr; int i; int retval = 0; + int stored = 0; + chunk = NULL; if (!sctp_addip_enable) return retval; @@ -743,7 +758,7 @@ static int sctp_send_asconf_del_ip(struct sock *sk, */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { - laddr = (union sctp_addr *)addr_buf; + laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); if (!af) { retval = -EINVAL; @@ -766,8 +781,37 @@ static int sctp_send_asconf_del_ip(struct sock *sk, bp = &asoc->base.bind_addr; laddr = sctp_find_unmatch_addr(bp, (union sctp_addr *)addrs, addrcnt, sp); - if (!laddr) - continue; + if ((laddr == NULL) && (addrcnt == 1)) { + if (asoc->asconf_addr_del_pending) + continue; + asoc->asconf_addr_del_pending = + kzalloc(sizeof(union sctp_addr), GFP_ATOMIC); + if (asoc->asconf_addr_del_pending == NULL) { + retval = -ENOMEM; + goto out; + } + asoc->asconf_addr_del_pending->sa.sa_family = + addrs->sa_family; + asoc->asconf_addr_del_pending->v4.sin_port = + htons(bp->port); + if (addrs->sa_family == AF_INET) { + struct sockaddr_in *sin; + + sin = (struct sockaddr_in *)addrs; + asoc->asconf_addr_del_pending->v4.sin_addr.s_addr = sin->sin_addr.s_addr; + } else if (addrs->sa_family == AF_INET6) { + struct sockaddr_in6 *sin6; + + sin6 = (struct sockaddr_in6 *)addrs; + ipv6_addr_copy(&asoc->asconf_addr_del_pending->v6.sin6_addr, &sin6->sin6_addr); + } + SCTP_DEBUG_PRINTK_IPADDR("send_asconf_del_ip: keep the last address asoc: %p ", + " at %p\n", asoc, asoc->asconf_addr_del_pending, + asoc->asconf_addr_del_pending); + asoc->src_out_of_asoc_ok = 1; + stored = 1; + goto skip_mkasconf; + } /* We do not need RCU protection throughout this loop * because this is done under a socket lock from the @@ -780,12 +824,13 @@ static int sctp_send_asconf_del_ip(struct sock *sk, goto out; } +skip_mkasconf: /* Reset use_as_src flag for the addresses in the bind address * list that are to be deleted. */ addr_buf = addrs; for (i = 0; i < addrcnt; i++) { - laddr = (union sctp_addr *)addr_buf; + laddr = addr_buf; af = sctp_get_af_specific(laddr->v4.sin_family); list_for_each_entry(saddr, &bp->address_list, list) { if (sctp_cmp_addr_exact(&saddr->a, laddr)) @@ -805,12 +850,37 @@ static int sctp_send_asconf_del_ip(struct sock *sk, sctp_sk(asoc->base.sk)); } + if (stored) + /* We don't need to transmit ASCONF */ + continue; retval = sctp_send_asconf(asoc, chunk); } out: return retval; } +/* set addr events to assocs in the endpoint. ep and addr_wq must be locked */ +int sctp_asconf_mgmt(struct sctp_sock *sp, struct sctp_sockaddr_entry *addrw) +{ + struct sock *sk = sctp_opt2sk(sp); + union sctp_addr *addr; + struct sctp_af *af; + + /* It is safe to write port space in caller. */ + addr = &addrw->a; + addr->v4.sin_port = htons(sp->ep->base.bind_addr.port); + af = sctp_get_af_specific(addr->sa.sa_family); + if (!af) + return -EINVAL; + if (sctp_verify_addr(sk, addr, af->sockaddr_len)) + return -EINVAL; + + if (addrw->state == SCTP_ADDR_NEW) + return sctp_send_asconf_add_ip(sk, (struct sockaddr *)addr, 1); + else + return sctp_send_asconf_del_ip(sk, (struct sockaddr *)addr, 1); +} + /* Helper for tunneling sctp_bindx() requests through sctp_setsockopt() * * API 8.1 @@ -927,7 +997,7 @@ SCTP_STATIC int sctp_setsockopt_bindx(struct sock* sk, return -EINVAL; } - sa_addr = (struct sockaddr *)addr_buf; + sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa_family); /* If the address family is not supported or if this address @@ -1018,7 +1088,7 @@ static int __sctp_connect(struct sock* sk, goto out_free; } - sa_addr = (union sctp_addr *)addr_buf; + sa_addr = addr_buf; af = sctp_get_af_specific(sa_addr->sa.sa_family); /* If the address family is not supported or if this address @@ -1384,6 +1454,7 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) struct sctp_endpoint *ep; struct sctp_association *asoc; struct list_head *pos, *temp; + unsigned int data_was_unread; SCTP_DEBUG_PRINTK("sctp_close(sk: 0x%p, timeout:%ld)\n", sk, timeout); @@ -1393,6 +1464,10 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) ep = sctp_sk(sk)->ep; + /* Clean up any skbs sitting on the receive queue. */ + data_was_unread = sctp_queue_purge_ulpevents(&sk->sk_receive_queue); + data_was_unread += sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); + /* Walk all associations on an endpoint. */ list_for_each_safe(pos, temp, &ep->asocs) { asoc = list_entry(pos, struct sctp_association, asocs); @@ -1410,7 +1485,9 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) } } - if (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime) { + if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) || + !skb_queue_empty(&asoc->ulpq.reasm) || + (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { struct sctp_chunk *chunk; chunk = sctp_make_abort_user(asoc, NULL, 0); @@ -1420,10 +1497,6 @@ SCTP_STATIC void sctp_close(struct sock *sk, long timeout) sctp_primitive_SHUTDOWN(asoc, NULL); } - /* Clean up any skbs sitting on the receive queue. */ - sctp_queue_purge_ulpevents(&sk->sk_receive_queue); - sctp_queue_purge_ulpevents(&sctp_sk(sk)->pd_lobby); - /* On a TCP-style socket, block for at most linger_time if set. */ if (sctp_style(sk, TCP) && timeout) sctp_wait_for_close(sk, timeout); @@ -2073,10 +2146,33 @@ static int sctp_setsockopt_disable_fragments(struct sock *sk, static int sctp_setsockopt_events(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_association *asoc; + struct sctp_ulpevent *event; + if (optlen > sizeof(struct sctp_event_subscribe)) return -EINVAL; if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen)) return -EFAULT; + + /* + * At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT, + * if there is no data to be sent or retransmit, the stack will + * immediately send up this notification. + */ + if (sctp_ulpevent_type_enabled(SCTP_SENDER_DRY_EVENT, + &sctp_sk(sk)->subscribe)) { + asoc = sctp_id2assoc(sk, 0); + + if (asoc && sctp_outq_is_empty(&asoc->outqueue)) { + event = sctp_ulpevent_make_sender_dry_event(asoc, + GFP_ATOMIC); + if (!event) + return -ENOMEM; + + sctp_ulpq_tail_event(&asoc->ulpq, event); + } + } + return 0; } @@ -3187,11 +3283,11 @@ static int sctp_setsockopt_auth_chunk(struct sock *sk, return -EFAULT; switch (val.sauth_chunk) { - case SCTP_CID_INIT: - case SCTP_CID_INIT_ACK: - case SCTP_CID_SHUTDOWN_COMPLETE: - case SCTP_CID_AUTH: - return -EINVAL; + case SCTP_CID_INIT: + case SCTP_CID_INIT_ACK: + case SCTP_CID_SHUTDOWN_COMPLETE: + case SCTP_CID_AUTH: + return -EINVAL; } /* add this chunk id to the endpoint */ @@ -3334,6 +3430,46 @@ static int sctp_setsockopt_del_key(struct sock *sk, } +/* + * 8.1.23 SCTP_AUTO_ASCONF + * + * This option will enable or disable the use of the automatic generation of + * ASCONF chunks to add and delete addresses to an existing association. Note + * that this option has two caveats namely: a) it only affects sockets that + * are bound to all addresses available to the SCTP stack, and b) the system + * administrator may have an overriding control that turns the ASCONF feature + * off no matter what setting the socket option may have. + * This option expects an integer boolean flag, where a non-zero value turns on + * the option, and a zero value turns off the option. + * Note. In this implementation, socket operation overrides default parameter + * being set by sysctl as well as FreeBSD implementation + */ +static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval, + unsigned int optlen) +{ + int val; + struct sctp_sock *sp = sctp_sk(sk); + + if (optlen < sizeof(int)) + return -EINVAL; + if (get_user(val, (int __user *)optval)) + return -EFAULT; + if (!sctp_is_ep_boundall(sk) && val) + return -EINVAL; + if ((val && sp->do_auto_asconf) || (!val && !sp->do_auto_asconf)) + return 0; + + if (val == 0 && sp->do_auto_asconf) { + list_del(&sp->auto_asconf_list); + sp->do_auto_asconf = 0; + } else if (val && !sp->do_auto_asconf) { + list_add_tail(&sp->auto_asconf_list, + &sctp_auto_asconf_splist); + sp->do_auto_asconf = 1; + } + return 0; +} + /* API 6.2 setsockopt(), getsockopt() * @@ -3481,6 +3617,9 @@ SCTP_STATIC int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_AUTH_DELETE_KEY: retval = sctp_setsockopt_del_key(sk, optval, optlen); break; + case SCTP_AUTO_ASCONF: + retval = sctp_setsockopt_auto_asconf(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -3763,6 +3902,12 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) local_bh_disable(); percpu_counter_inc(&sctp_sockets_allocated); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + if (sctp_default_auto_asconf) { + list_add_tail(&sp->auto_asconf_list, + &sctp_auto_asconf_splist); + sp->do_auto_asconf = 1; + } else + sp->do_auto_asconf = 0; local_bh_enable(); return 0; @@ -3771,13 +3916,17 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) /* Cleanup any SCTP per socket resources. */ SCTP_STATIC void sctp_destroy_sock(struct sock *sk) { - struct sctp_endpoint *ep; + struct sctp_sock *sp; SCTP_DEBUG_PRINTK("sctp_destroy_sock(sk: %p)\n", sk); /* Release our hold on the endpoint. */ - ep = sctp_sk(sk)->ep; - sctp_endpoint_free(ep); + sp = sctp_sk(sk); + if (sp->do_auto_asconf) { + sp->do_auto_asconf = 0; + list_del(&sp->auto_asconf_list); + } + sctp_endpoint_free(sp->ep); local_bh_disable(); percpu_counter_dec(&sctp_sockets_allocated); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); @@ -5277,6 +5426,28 @@ static int sctp_getsockopt_assoc_number(struct sock *sk, int len, } /* + * 8.1.23 SCTP_AUTO_ASCONF + * See the corresponding setsockopt entry as description + */ +static int sctp_getsockopt_auto_asconf(struct sock *sk, int len, + char __user *optval, int __user *optlen) +{ + int val = 0; + + if (len < sizeof(int)) + return -EINVAL; + + len = sizeof(int); + if (sctp_sk(sk)->do_auto_asconf && sctp_is_ep_boundall(sk)) + val = 1; + if (put_user(len, optlen)) + return -EFAULT; + if (copy_to_user(optval, &val, len)) + return -EFAULT; + return 0; +} + +/* * 8.2.6. Get the Current Identifiers of Associations * (SCTP_GET_ASSOC_ID_LIST) * @@ -5460,6 +5631,9 @@ SCTP_STATIC int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_GET_ASSOC_ID_LIST: retval = sctp_getsockopt_assoc_ids(sk, len, optval, optlen); break; + case SCTP_AUTO_ASCONF: + retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -6512,6 +6686,7 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, struct sk_buff *skb, *tmp; struct sctp_ulpevent *event; struct sctp_bind_hashbucket *head; + struct list_head tmplist; /* Migrate socket buffer sizes and all the socket level options to the * new socket. @@ -6519,7 +6694,12 @@ static void sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, newsk->sk_sndbuf = oldsk->sk_sndbuf; newsk->sk_rcvbuf = oldsk->sk_rcvbuf; /* Brute force copy old sctp opt. */ - inet_sk_copy_descendant(newsk, oldsk); + if (oldsp->do_auto_asconf) { + memcpy(&tmplist, &newsp->auto_asconf_list, sizeof(tmplist)); + inet_sk_copy_descendant(newsk, oldsk); + memcpy(&newsp->auto_asconf_list, &tmplist, sizeof(tmplist)); + } else + inet_sk_copy_descendant(newsk, oldsk); /* Restore the ep value that was overwritten with the above structure * copy. diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 50cb57f0919..6b3952961b8 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -183,6 +183,13 @@ static ctl_table sctp_table[] = { .proc_handler = proc_dointvec, }, { + .procname = "default_auto_asconf", + .data = &sctp_default_auto_asconf, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { .procname = "prsctp_enable", .data = &sctp_prsctp_enable, .maxlen = sizeof(int), diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index e70e5fc8789..8a84017834c 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -1081,9 +1081,19 @@ void sctp_ulpevent_free(struct sctp_ulpevent *event) } /* Purge the skb lists holding ulpevents. */ -void sctp_queue_purge_ulpevents(struct sk_buff_head *list) +unsigned int sctp_queue_purge_ulpevents(struct sk_buff_head *list) { struct sk_buff *skb; - while ((skb = skb_dequeue(list)) != NULL) - sctp_ulpevent_free(sctp_skb2event(skb)); + unsigned int data_unread = 0; + + while ((skb = skb_dequeue(list)) != NULL) { + struct sctp_ulpevent *event = sctp_skb2event(skb); + + if (!sctp_ulpevent_is_notification(event)) + data_unread += skb->len; + + sctp_ulpevent_free(event); + } + + return data_unread; } diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index cd6e4aa19db..727e506cacd 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -626,7 +626,7 @@ rpcauth_refreshcred(struct rpc_task *task) if (err < 0) goto out; cred = task->tk_rqstp->rq_cred; - }; + } dprintk("RPC: %5u refreshing %s cred %p\n", task->tk_pid, cred->cr_auth->au_ops->au_name, cred); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 339ba64cce1..364eb45e989 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -577,13 +577,13 @@ retry: } inode = &gss_msg->inode->vfs_inode; for (;;) { - prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_INTERRUPTIBLE); + prepare_to_wait(&gss_msg->waitqueue, &wait, TASK_KILLABLE); spin_lock(&inode->i_lock); if (gss_msg->ctx != NULL || gss_msg->msg.errno < 0) { break; } spin_unlock(&inode->i_lock); - if (signalled()) { + if (fatal_signal_pending(current)) { err = -ERESTARTSYS; goto out_intr; } @@ -1421,18 +1421,16 @@ gss_wrap_req(struct rpc_task *task, goto out; } switch (gss_cred->gc_service) { - case RPC_GSS_SVC_NONE: - gss_wrap_req_encode(encode, rqstp, p, obj); - status = 0; - break; - case RPC_GSS_SVC_INTEGRITY: - status = gss_wrap_req_integ(cred, ctx, encode, - rqstp, p, obj); - break; - case RPC_GSS_SVC_PRIVACY: - status = gss_wrap_req_priv(cred, ctx, encode, - rqstp, p, obj); - break; + case RPC_GSS_SVC_NONE: + gss_wrap_req_encode(encode, rqstp, p, obj); + status = 0; + break; + case RPC_GSS_SVC_INTEGRITY: + status = gss_wrap_req_integ(cred, ctx, encode, rqstp, p, obj); + break; + case RPC_GSS_SVC_PRIVACY: + status = gss_wrap_req_priv(cred, ctx, encode, rqstp, p, obj); + break; } out: gss_put_ctx(ctx); @@ -1531,18 +1529,18 @@ gss_unwrap_resp(struct rpc_task *task, if (ctx->gc_proc != RPC_GSS_PROC_DATA) goto out_decode; switch (gss_cred->gc_service) { - case RPC_GSS_SVC_NONE: - break; - case RPC_GSS_SVC_INTEGRITY: - status = gss_unwrap_resp_integ(cred, ctx, rqstp, &p); - if (status) - goto out; - break; - case RPC_GSS_SVC_PRIVACY: - status = gss_unwrap_resp_priv(cred, ctx, rqstp, &p); - if (status) - goto out; - break; + case RPC_GSS_SVC_NONE: + break; + case RPC_GSS_SVC_INTEGRITY: + status = gss_unwrap_resp_integ(cred, ctx, rqstp, &p); + if (status) + goto out; + break; + case RPC_GSS_SVC_PRIVACY: + status = gss_unwrap_resp_priv(cred, ctx, rqstp, &p); + if (status) + goto out; + break; } /* take into account extra slack for integrity and privacy cases: */ cred->cr_auth->au_rslack = cred->cr_auth->au_verfsize + (p - savedp) diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 0a9a2ec2e46..c3b75333b82 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -43,6 +43,7 @@ #include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/xdr.h> #include <linux/crypto.h> +#include <linux/sunrpc/gss_krb5_enctypes.h> #ifdef RPC_DEBUG # define RPCDBG_FACILITY RPCDBG_AUTH @@ -750,7 +751,7 @@ static struct gss_api_mech gss_kerberos_mech = { .gm_ops = &gss_kerberos_ops, .gm_pf_num = ARRAY_SIZE(gss_kerberos_pfs), .gm_pfs = gss_kerberos_pfs, - .gm_upcall_enctypes = "18,17,16,23,3,1,2", + .gm_upcall_enctypes = KRB5_SUPPORTED_ENCTYPES, }; static int __init init_kerberos_module(void) diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index b84d7395535..7389b7da3a8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1061,7 +1061,7 @@ call_allocate(struct rpc_task *task) dprintk("RPC: %5u rpc_buffer allocation failed\n", task->tk_pid); - if (RPC_IS_ASYNC(task) || !signalled()) { + if (RPC_IS_ASYNC(task) || !fatal_signal_pending(current)) { task->tk_action = call_allocate; rpc_delay(task, HZ>>4); return; @@ -1175,6 +1175,9 @@ call_bind_status(struct rpc_task *task) status = -EOPNOTSUPP; break; } + if (task->tk_rebind_retry == 0) + break; + task->tk_rebind_retry--; rpc_delay(task, 3*HZ); goto retry_timeout; case -ETIMEDOUT: @@ -1663,19 +1666,18 @@ rpc_verify_header(struct rpc_task *task) if (--len < 0) goto out_overflow; switch ((n = ntohl(*p++))) { - case RPC_AUTH_ERROR: - break; - case RPC_MISMATCH: - dprintk("RPC: %5u %s: RPC call version " - "mismatch!\n", - task->tk_pid, __func__); - error = -EPROTONOSUPPORT; - goto out_err; - default: - dprintk("RPC: %5u %s: RPC call rejected, " - "unknown error: %x\n", - task->tk_pid, __func__, n); - goto out_eio; + case RPC_AUTH_ERROR: + break; + case RPC_MISMATCH: + dprintk("RPC: %5u %s: RPC call version mismatch!\n", + task->tk_pid, __func__); + error = -EPROTONOSUPPORT; + goto out_err; + default: + dprintk("RPC: %5u %s: RPC call rejected, " + "unknown error: %x\n", + task->tk_pid, __func__, n); + goto out_eio; } if (--len < 0) goto out_overflow; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 72bc5368396..b181e344132 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -456,13 +456,13 @@ rpc_get_inode(struct super_block *sb, umode_t mode) inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; - switch(mode & S_IFMT) { - case S_IFDIR: - inode->i_fop = &simple_dir_operations; - inode->i_op = &simple_dir_inode_operations; - inc_nlink(inode); - default: - break; + switch (mode & S_IFMT) { + case S_IFDIR: + inode->i_fop = &simple_dir_operations; + inode->i_op = &simple_dir_inode_operations; + inc_nlink(inode); + default: + break; } return inode; } diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 9a80a922c52..e45d2fbbe5a 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -597,7 +597,7 @@ void rpcb_getport_async(struct rpc_task *task) u32 bind_version; struct rpc_xprt *xprt; struct rpc_clnt *rpcb_clnt; - static struct rpcbind_args *map; + struct rpcbind_args *map; struct rpc_task *child; struct sockaddr_storage addr; struct sockaddr *sap = (struct sockaddr *)&addr; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6b43ee7221d..4814e246a87 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -616,30 +616,25 @@ static void __rpc_execute(struct rpc_task *task) BUG_ON(RPC_IS_QUEUED(task)); for (;;) { + void (*do_action)(struct rpc_task *); /* - * Execute any pending callback. + * Execute any pending callback first. */ - if (task->tk_callback) { - void (*save_callback)(struct rpc_task *); - - /* - * We set tk_callback to NULL before calling it, - * in case it sets the tk_callback field itself: - */ - save_callback = task->tk_callback; - task->tk_callback = NULL; - save_callback(task); - } else { + do_action = task->tk_callback; + task->tk_callback = NULL; + if (do_action == NULL) { /* * Perform the next FSM step. - * tk_action may be NULL when the task has been killed - * by someone else. + * tk_action may be NULL if the task has been killed. + * In particular, note that rpc_killall_tasks may + * do this at any time, so beware when dereferencing. */ - if (task->tk_action == NULL) + do_action = task->tk_action; + if (do_action == NULL) break; - task->tk_action(task); } + do_action(task); /* * Lockless check for whether task is sleeping or not. @@ -792,6 +787,7 @@ static void rpc_init_task(struct rpc_task *task, const struct rpc_task_setup *ta /* Initialize retry counters */ task->tk_garb_retry = 2; task->tk_cred_retry = 2; + task->tk_rebind_retry = 2; task->tk_priority = task_setup_data->priority - RPC_PRIORITY_LOW; task->tk_owner = current->tgid; diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index c3c232a88d9..a385430c722 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -42,6 +42,7 @@ #include <linux/sunrpc/svc_xprt.h> #include <linux/sunrpc/debug.h> #include <linux/sunrpc/rpc_rdma.h> +#include <linux/interrupt.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/spinlock.h> diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 80f8da344df..28236bab57f 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -47,6 +47,7 @@ * o buffer memory */ +#include <linux/interrupt.h> #include <linux/pci.h> /* for Tavor hack below */ #include <linux/slab.h> diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index fa68d1e9ff4..759b318b5ff 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -552,12 +552,16 @@ static int tipc_bcbearer_send(struct sk_buff *buf, if (likely(!msg_non_seq(buf_msg(buf)))) { struct tipc_msg *msg; - assert(tipc_bcast_nmap.count != 0); bcbuf_set_acks(buf, tipc_bcast_nmap.count); msg = buf_msg(buf); msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tipc_net_id); bcl->stats.sent_info++; + + if (WARN_ON(!tipc_bcast_nmap.count)) { + dump_stack(); + return 0; + } } /* Send buffer over bearers until all targets reached */ diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 85209eadfae..85eba9c08ee 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -402,7 +402,6 @@ void tipc_bearer_lock_push(struct tipc_bearer *b_ptr) void tipc_continue(struct tipc_bearer *b_ptr) { spin_lock_bh(&b_ptr->lock); - b_ptr->continue_count++; if (!list_empty(&b_ptr->cong_links)) tipc_k_signal((Handler)tipc_bearer_lock_push, (unsigned long)b_ptr); b_ptr->blocked = 0; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 31d6172b20f..5ad70eff1eb 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -107,7 +107,6 @@ struct media { * @link_req: ptr to (optional) structure making periodic link setup requests * @links: list of non-congested links associated with bearer * @cong_links: list of congested links associated with bearer - * @continue_count: # of times bearer has resumed after congestion or blocking * @active: non-zero if bearer structure is represents a bearer * @net_plane: network plane ('A' through 'H') currently associated with bearer * @nodes: indicates which nodes in cluster can be reached through bearer @@ -129,7 +128,6 @@ struct tipc_bearer { struct link_req *link_req; struct list_head links; struct list_head cong_links; - u32 continue_count; int active; char net_plane; struct tipc_node_map nodes; diff --git a/net/tipc/core.h b/net/tipc/core.h index 436dda1159d..d234a98a460 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -62,12 +62,6 @@ struct tipc_msg; /* msg.h */ struct print_buf; /* log.h */ /* - * TIPC sanity test macros - */ - -#define assert(i) BUG_ON(!(i)) - -/* * TIPC system monitoring code */ diff --git a/net/tipc/link.c b/net/tipc/link.c index 5ed4b4f7452..f89570c54f5 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1572,7 +1572,7 @@ static struct sk_buff *link_insert_deferred_queue(struct link *l_ptr, static int link_recv_buf_validate(struct sk_buff *buf) { static u32 min_data_hdr_size[8] = { - SHORT_H_SIZE, MCAST_H_SIZE, LONG_H_SIZE, DIR_MSG_H_SIZE, + SHORT_H_SIZE, MCAST_H_SIZE, NAMED_H_SIZE, BASIC_H_SIZE, MAX_H_SIZE, MAX_H_SIZE, MAX_H_SIZE, MAX_H_SIZE }; @@ -2553,7 +2553,7 @@ int tipc_link_recv_fragment(struct sk_buff **pending, struct sk_buff **fb, u32 msg_sz = msg_size(imsg); u32 fragm_sz = msg_data_sz(fragm); u32 exp_fragm_cnt = msg_sz/fragm_sz + !!(msg_sz % fragm_sz); - u32 max = TIPC_MAX_USER_MSG_SIZE + LONG_H_SIZE; + u32 max = TIPC_MAX_USER_MSG_SIZE + NAMED_H_SIZE; if (msg_type(imsg) == TIPC_MCAST_MSG) max = TIPC_MAX_USER_MSG_SIZE + MCAST_H_SIZE; if (msg_size(imsg) > max) { @@ -2882,7 +2882,7 @@ static int tipc_link_stats(const char *name, char *buf, const u32 buf_size) profile_total = 1; tipc_printf(&pb, " TX profile sample:%u packets average:%u octets\n" " 0-64:%u%% -256:%u%% -1024:%u%% -4096:%u%% " - "-16354:%u%% -32768:%u%% -66000:%u%%\n", + "-16384:%u%% -32768:%u%% -66000:%u%%\n", l_ptr->stats.msg_length_counts, l_ptr->stats.msg_lengths_total / profile_total, percent(l_ptr->stats.msg_length_profile[0], profile_total), diff --git a/net/tipc/msg.c b/net/tipc/msg.c index 03e57bf92c7..83d50967910 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -61,10 +61,8 @@ void tipc_msg_init(struct tipc_msg *m, u32 user, u32 type, msg_set_size(m, hsize); msg_set_prevnode(m, tipc_own_addr); msg_set_type(m, type); - if (!msg_short(m)) { - msg_set_orignode(m, tipc_own_addr); - msg_set_destnode(m, destnode); - } + msg_set_orignode(m, tipc_own_addr); + msg_set_destnode(m, destnode); } /** diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 8452454731f..d93178f2e85 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -68,10 +68,10 @@ * Message header sizes */ -#define SHORT_H_SIZE 24 /* Connected, in-cluster messages */ -#define DIR_MSG_H_SIZE 32 /* Directly addressed messages */ -#define LONG_H_SIZE 40 /* Named messages */ -#define MCAST_H_SIZE 44 /* Multicast messages */ +#define SHORT_H_SIZE 24 /* In-cluster basic payload message */ +#define BASIC_H_SIZE 32 /* Basic payload message */ +#define NAMED_H_SIZE 40 /* Named payload message */ +#define MCAST_H_SIZE 44 /* Multicast payload message */ #define INT_H_SIZE 40 /* Internal messages */ #define MIN_H_SIZE 24 /* Smallest legal TIPC header size */ #define MAX_H_SIZE 60 /* Largest possible TIPC header size */ @@ -311,26 +311,6 @@ static inline void msg_set_seqno(struct tipc_msg *m, u32 n) } /* - * TIPC may utilize the "link ack #" and "link seq #" fields of a short - * message header to hold the destination node for the message, since the - * normal "dest node" field isn't present. This cache is only referenced - * when required, so populating the cache of a longer message header is - * harmless (as long as the header has the two link sequence fields present). - * - * Note: Host byte order is OK here, since the info never goes off-card. - */ - -static inline u32 msg_destnode_cache(struct tipc_msg *m) -{ - return m->hdr[2]; -} - -static inline void msg_set_destnode_cache(struct tipc_msg *m, u32 dnode) -{ - m->hdr[2] = dnode; -} - -/* * Words 3-10 */ @@ -377,7 +357,7 @@ static inline void msg_set_mc_netid(struct tipc_msg *m, u32 p) static inline int msg_short(struct tipc_msg *m) { - return msg_hdr_sz(m) == 24; + return msg_hdr_sz(m) == SHORT_H_SIZE; } static inline u32 msg_orignode(struct tipc_msg *m) @@ -635,7 +615,7 @@ static inline u32 msg_link_selector(struct tipc_msg *m) static inline void msg_set_link_selector(struct tipc_msg *m, u32 n) { - msg_set_bits(m, 4, 0, 1, (n & 1)); + msg_set_bits(m, 4, 0, 1, n); } /* @@ -659,7 +639,7 @@ static inline u32 msg_probe(struct tipc_msg *m) static inline void msg_set_probe(struct tipc_msg *m, u32 val) { - msg_set_bits(m, 5, 0, 1, (val & 1)); + msg_set_bits(m, 5, 0, 1, val); } static inline char msg_net_plane(struct tipc_msg *m) diff --git a/net/tipc/name_distr.c b/net/tipc/name_distr.c index 80025a1b3bf..cd356e50433 100644 --- a/net/tipc/name_distr.c +++ b/net/tipc/name_distr.c @@ -94,13 +94,13 @@ static void publ_to_item(struct distr_item *i, struct publication *p) static struct sk_buff *named_prepare_buf(u32 type, u32 size, u32 dest) { - struct sk_buff *buf = tipc_buf_acquire(LONG_H_SIZE + size); + struct sk_buff *buf = tipc_buf_acquire(INT_H_SIZE + size); struct tipc_msg *msg; if (buf != NULL) { msg = buf_msg(buf); - tipc_msg_init(msg, NAME_DISTRIBUTOR, type, LONG_H_SIZE, dest); - msg_set_size(msg, LONG_H_SIZE + size); + tipc_msg_init(msg, NAME_DISTRIBUTOR, type, INT_H_SIZE, dest); + msg_set_size(msg, INT_H_SIZE + size); } return buf; } diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index 205ed4a4e18..46e6b6c2ecc 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -2,7 +2,7 @@ * net/tipc/name_table.c: TIPC name table code * * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2004-2008, Wind River Systems + * Copyright (c) 2004-2008, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -44,9 +44,7 @@ static int tipc_nametbl_size = 1024; /* must be a power of 2 */ /** - * struct sub_seq - container for all published instances of a name sequence - * @lower: name sequence lower bound - * @upper: name sequence upper bound + * struct name_info - name sequence publication info * @node_list: circular list of publications made by own node * @cluster_list: circular list of publications made by own cluster * @zone_list: circular list of publications made by own zone @@ -59,18 +57,29 @@ static int tipc_nametbl_size = 1024; /* must be a power of 2 */ * (The cluster and node lists may be empty.) */ -struct sub_seq { - u32 lower; - u32 upper; - struct publication *node_list; - struct publication *cluster_list; - struct publication *zone_list; +struct name_info { + struct list_head node_list; + struct list_head cluster_list; + struct list_head zone_list; u32 node_list_size; u32 cluster_list_size; u32 zone_list_size; }; /** + * struct sub_seq - container for all published instances of a name sequence + * @lower: name sequence lower bound + * @upper: name sequence upper bound + * @info: pointer to name sequence publication info + */ + +struct sub_seq { + u32 lower; + u32 upper; + struct name_info *info; +}; + +/** * struct name_seq - container for all published instances of a name type * @type: 32 bit 'type' value for name sequence * @sseq: pointer to dynamically-sized array of sub-sequences of this 'type'; @@ -246,6 +255,7 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, struct subscription *st; struct publication *publ; struct sub_seq *sseq; + struct name_info *info; int created_subseq = 0; sseq = nameseq_find_subseq(nseq, lower); @@ -258,6 +268,8 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, type, lower, upper); return NULL; } + + info = sseq->info; } else { u32 inspos; struct sub_seq *freesseq; @@ -292,6 +304,17 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, nseq->alloc *= 2; } + info = kzalloc(sizeof(*info), GFP_ATOMIC); + if (!info) { + warn("Cannot publish {%u,%u,%u}, no memory\n", + type, lower, upper); + return NULL; + } + + INIT_LIST_HEAD(&info->node_list); + INIT_LIST_HEAD(&info->cluster_list); + INIT_LIST_HEAD(&info->zone_list); + /* Insert new sub-sequence */ sseq = &nseq->sseqs[inspos]; @@ -301,6 +324,7 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, nseq->first_free++; sseq->lower = lower; sseq->upper = upper; + sseq->info = info; created_subseq = 1; } @@ -310,33 +334,17 @@ static struct publication *tipc_nameseq_insert_publ(struct name_seq *nseq, if (!publ) return NULL; - sseq->zone_list_size++; - if (!sseq->zone_list) - sseq->zone_list = publ->zone_list_next = publ; - else { - publ->zone_list_next = sseq->zone_list->zone_list_next; - sseq->zone_list->zone_list_next = publ; - } + list_add(&publ->zone_list, &info->zone_list); + info->zone_list_size++; if (in_own_cluster(node)) { - sseq->cluster_list_size++; - if (!sseq->cluster_list) - sseq->cluster_list = publ->cluster_list_next = publ; - else { - publ->cluster_list_next = - sseq->cluster_list->cluster_list_next; - sseq->cluster_list->cluster_list_next = publ; - } + list_add(&publ->cluster_list, &info->cluster_list); + info->cluster_list_size++; } if (node == tipc_own_addr) { - sseq->node_list_size++; - if (!sseq->node_list) - sseq->node_list = publ->node_list_next = publ; - else { - publ->node_list_next = sseq->node_list->node_list_next; - sseq->node_list->node_list_next = publ; - } + list_add(&publ->node_list, &info->node_list); + info->node_list_size++; } /* @@ -370,9 +378,8 @@ static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 i u32 node, u32 ref, u32 key) { struct publication *publ; - struct publication *curr; - struct publication *prev; struct sub_seq *sseq = nameseq_find_subseq(nseq, inst); + struct name_info *info; struct sub_seq *free; struct subscription *s, *st; int removed_subseq = 0; @@ -380,96 +387,41 @@ static struct publication *tipc_nameseq_remove_publ(struct name_seq *nseq, u32 i if (!sseq) return NULL; - /* Remove publication from zone scope list */ + info = sseq->info; - prev = sseq->zone_list; - publ = sseq->zone_list->zone_list_next; - while ((publ->key != key) || (publ->ref != ref) || - (publ->node && (publ->node != node))) { - prev = publ; - publ = publ->zone_list_next; - if (prev == sseq->zone_list) { + /* Locate publication, if it exists */ - /* Prevent endless loop if publication not found */ - - return NULL; - } - } - if (publ != sseq->zone_list) - prev->zone_list_next = publ->zone_list_next; - else if (publ->zone_list_next != publ) { - prev->zone_list_next = publ->zone_list_next; - sseq->zone_list = publ->zone_list_next; - } else { - sseq->zone_list = NULL; + list_for_each_entry(publ, &info->zone_list, zone_list) { + if ((publ->key == key) && (publ->ref == ref) && + (!publ->node || (publ->node == node))) + goto found; } - sseq->zone_list_size--; + return NULL; + +found: + /* Remove publication from zone scope list */ + + list_del(&publ->zone_list); + info->zone_list_size--; /* Remove publication from cluster scope list, if present */ if (in_own_cluster(node)) { - prev = sseq->cluster_list; - curr = sseq->cluster_list->cluster_list_next; - while (curr != publ) { - prev = curr; - curr = curr->cluster_list_next; - if (prev == sseq->cluster_list) { - - /* Prevent endless loop for malformed list */ - - err("Unable to de-list cluster publication\n" - "{%u%u}, node=0x%x, ref=%u, key=%u)\n", - publ->type, publ->lower, publ->node, - publ->ref, publ->key); - goto end_cluster; - } - } - if (publ != sseq->cluster_list) - prev->cluster_list_next = publ->cluster_list_next; - else if (publ->cluster_list_next != publ) { - prev->cluster_list_next = publ->cluster_list_next; - sseq->cluster_list = publ->cluster_list_next; - } else { - sseq->cluster_list = NULL; - } - sseq->cluster_list_size--; + list_del(&publ->cluster_list); + info->cluster_list_size--; } -end_cluster: /* Remove publication from node scope list, if present */ if (node == tipc_own_addr) { - prev = sseq->node_list; - curr = sseq->node_list->node_list_next; - while (curr != publ) { - prev = curr; - curr = curr->node_list_next; - if (prev == sseq->node_list) { - - /* Prevent endless loop for malformed list */ - - err("Unable to de-list node publication\n" - "{%u%u}, node=0x%x, ref=%u, key=%u)\n", - publ->type, publ->lower, publ->node, - publ->ref, publ->key); - goto end_node; - } - } - if (publ != sseq->node_list) - prev->node_list_next = publ->node_list_next; - else if (publ->node_list_next != publ) { - prev->node_list_next = publ->node_list_next; - sseq->node_list = publ->node_list_next; - } else { - sseq->node_list = NULL; - } - sseq->node_list_size--; + list_del(&publ->node_list); + info->node_list_size--; } -end_node: /* Contract subseq list if no more publications for that subseq */ - if (!sseq->zone_list) { + if (list_empty(&info->zone_list)) { + kfree(info); free = &nseq->sseqs[nseq->first_free--]; memmove(sseq, sseq + 1, (free - (sseq + 1)) * sizeof(*sseq)); removed_subseq = 1; @@ -506,12 +458,12 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, struct subscription *s return; while (sseq != &nseq->sseqs[nseq->first_free]) { - struct publication *zl = sseq->zone_list; - if (zl && tipc_subscr_overlap(s, sseq->lower, sseq->upper)) { - struct publication *crs = zl; + if (tipc_subscr_overlap(s, sseq->lower, sseq->upper)) { + struct publication *crs; + struct name_info *info = sseq->info; int must_report = 1; - do { + list_for_each_entry(crs, &info->zone_list, zone_list) { tipc_subscr_report_overlap(s, sseq->lower, sseq->upper, @@ -520,8 +472,7 @@ static void tipc_nameseq_subscribe(struct name_seq *nseq, struct subscription *s crs->node, must_report); must_report = 0; - crs = crs->zone_list_next; - } while (crs != zl); + } } sseq++; } @@ -591,9 +542,10 @@ struct publication *tipc_nametbl_remove_publ(u32 type, u32 lower, u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) { struct sub_seq *sseq; - struct publication *publ = NULL; + struct name_info *info; + struct publication *publ; struct name_seq *seq; - u32 ref; + u32 ref = 0; if (!tipc_in_scope(*destnode, tipc_own_addr)) return 0; @@ -606,55 +558,57 @@ u32 tipc_nametbl_translate(u32 type, u32 instance, u32 *destnode) if (unlikely(!sseq)) goto not_found; spin_lock_bh(&seq->lock); + info = sseq->info; /* Closest-First Algorithm: */ if (likely(!*destnode)) { - publ = sseq->node_list; - if (publ) { - sseq->node_list = publ->node_list_next; -found: - ref = publ->ref; - *destnode = publ->node; - spin_unlock_bh(&seq->lock); - read_unlock_bh(&tipc_nametbl_lock); - return ref; - } - publ = sseq->cluster_list; - if (publ) { - sseq->cluster_list = publ->cluster_list_next; - goto found; - } - publ = sseq->zone_list; - if (publ) { - sseq->zone_list = publ->zone_list_next; - goto found; + if (!list_empty(&info->node_list)) { + publ = list_first_entry(&info->node_list, + struct publication, + node_list); + list_move_tail(&publ->node_list, + &info->node_list); + } else if (!list_empty(&info->cluster_list)) { + publ = list_first_entry(&info->cluster_list, + struct publication, + cluster_list); + list_move_tail(&publ->cluster_list, + &info->cluster_list); + } else { + publ = list_first_entry(&info->zone_list, + struct publication, + zone_list); + list_move_tail(&publ->zone_list, + &info->zone_list); } } /* Round-Robin Algorithm: */ else if (*destnode == tipc_own_addr) { - publ = sseq->node_list; - if (publ) { - sseq->node_list = publ->node_list_next; - goto found; - } + if (list_empty(&info->node_list)) + goto no_match; + publ = list_first_entry(&info->node_list, struct publication, + node_list); + list_move_tail(&publ->node_list, &info->node_list); } else if (in_own_cluster(*destnode)) { - publ = sseq->cluster_list; - if (publ) { - sseq->cluster_list = publ->cluster_list_next; - goto found; - } + if (list_empty(&info->cluster_list)) + goto no_match; + publ = list_first_entry(&info->cluster_list, struct publication, + cluster_list); + list_move_tail(&publ->cluster_list, &info->cluster_list); } else { - publ = sseq->zone_list; - if (publ) { - sseq->zone_list = publ->zone_list_next; - goto found; - } + publ = list_first_entry(&info->zone_list, struct publication, + zone_list); + list_move_tail(&publ->zone_list, &info->zone_list); } + + ref = publ->ref; + *destnode = publ->node; +no_match: spin_unlock_bh(&seq->lock); not_found: read_unlock_bh(&tipc_nametbl_lock); - return 0; + return ref; } /** @@ -676,6 +630,7 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, struct name_seq *seq; struct sub_seq *sseq; struct sub_seq *sseq_stop; + struct name_info *info; int res = 0; read_lock_bh(&tipc_nametbl_lock); @@ -693,16 +648,13 @@ int tipc_nametbl_mc_translate(u32 type, u32 lower, u32 upper, u32 limit, if (sseq->lower > upper) break; - publ = sseq->node_list; - if (publ) { - do { - if (publ->scope <= limit) - tipc_port_list_add(dports, publ->ref); - publ = publ->node_list_next; - } while (publ != sseq->node_list); + info = sseq->info; + list_for_each_entry(publ, &info->node_list, node_list) { + if (publ->scope <= limit) + tipc_port_list_add(dports, publ->ref); } - if (sseq->cluster_list_size != sseq->node_list_size) + if (info->cluster_list_size != info->node_list_size) res = 1; } @@ -840,16 +792,19 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, { char portIdStr[27]; const char *scope_str[] = {"", " zone", " cluster", " node"}; - struct publication *publ = sseq->zone_list; + struct publication *publ; + struct name_info *info; tipc_printf(buf, "%-10u %-10u ", sseq->lower, sseq->upper); - if (depth == 2 || !publ) { + if (depth == 2) { tipc_printf(buf, "\n"); return; } - do { + info = sseq->info; + + list_for_each_entry(publ, &info->zone_list, zone_list) { sprintf(portIdStr, "<%u.%u.%u:%u>", tipc_zone(publ->node), tipc_cluster(publ->node), tipc_node(publ->node), publ->ref); @@ -858,13 +813,9 @@ static void subseq_list(struct sub_seq *sseq, struct print_buf *buf, u32 depth, tipc_printf(buf, "%-10u %s", publ->key, scope_str[publ->scope]); } - - publ = publ->zone_list_next; - if (publ == sseq->zone_list) - break; - - tipc_printf(buf, "\n%33s", " "); - } while (1); + if (!list_is_last(&publ->zone_list, &info->zone_list)) + tipc_printf(buf, "\n%33s", " "); + }; tipc_printf(buf, "\n"); } diff --git a/net/tipc/name_table.h b/net/tipc/name_table.h index d228bd68265..62d77e5e902 100644 --- a/net/tipc/name_table.h +++ b/net/tipc/name_table.h @@ -2,7 +2,7 @@ * net/tipc/name_table.h: Include file for TIPC name table code * * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2004-2005, Wind River Systems + * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -61,9 +61,9 @@ struct port_list; * @subscr: subscription to "node down" event (for off-node publications only) * @local_list: adjacent entries in list of publications made by this node * @pport_list: adjacent entries in list of publications made by this port - * @node_list: next matching name seq publication with >= node scope - * @cluster_list: next matching name seq publication with >= cluster scope - * @zone_list: next matching name seq publication with >= zone scope + * @node_list: adjacent matching name seq publications with >= node scope + * @cluster_list: adjacent matching name seq publications with >= cluster scope + * @zone_list: adjacent matching name seq publications with >= zone scope * * Note that the node list, cluster list, and zone list are circular lists. */ @@ -79,9 +79,9 @@ struct publication { struct tipc_node_subscr subscr; struct list_head local_list; struct list_head pport_list; - struct publication *node_list_next; - struct publication *cluster_list_next; - struct publication *zone_list_next; + struct list_head node_list; + struct list_head cluster_list; + struct list_head zone_list; }; diff --git a/net/tipc/port.c b/net/tipc/port.c index c68dc956a42..54d812a5a4d 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -222,7 +222,7 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, p_ptr->max_pkt = MAX_PKT_DEFAULT; p_ptr->ref = ref; msg = &p_ptr->phdr; - tipc_msg_init(msg, importance, TIPC_NAMED_MSG, LONG_H_SIZE, 0); + tipc_msg_init(msg, importance, TIPC_NAMED_MSG, NAMED_H_SIZE, 0); msg_set_origport(msg, ref); INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); @@ -327,26 +327,23 @@ int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) } /* - * port_build_proto_msg(): build a port level protocol - * or a connection abortion message. Called with - * tipc_port lock on. + * port_build_proto_msg(): create connection protocol message for port + * + * On entry the port must be locked and connected. */ -static struct sk_buff *port_build_proto_msg(u32 destport, u32 destnode, - u32 origport, u32 orignode, - u32 usr, u32 type, u32 err, - u32 ack) +static struct sk_buff *port_build_proto_msg(struct tipc_port *p_ptr, + u32 type, u32 ack) { struct sk_buff *buf; struct tipc_msg *msg; - buf = tipc_buf_acquire(LONG_H_SIZE); + buf = tipc_buf_acquire(INT_H_SIZE); if (buf) { msg = buf_msg(buf); - tipc_msg_init(msg, usr, type, LONG_H_SIZE, destnode); - msg_set_errcode(msg, err); - msg_set_destport(msg, destport); - msg_set_origport(msg, origport); - msg_set_orignode(msg, orignode); + tipc_msg_init(msg, CONN_MANAGER, type, INT_H_SIZE, + port_peernode(p_ptr)); + msg_set_destport(msg, port_peerport(p_ptr)); + msg_set_origport(msg, p_ptr->ref); msg_set_msgcnt(msg, ack); } return buf; @@ -358,45 +355,48 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) struct sk_buff *rbuf; struct tipc_msg *rmsg; int hdr_sz; - u32 imp = msg_importance(msg); + u32 imp; u32 data_sz = msg_data_sz(msg); - - if (data_sz > MAX_REJECT_SIZE) - data_sz = MAX_REJECT_SIZE; - if (msg_connected(msg) && (imp < TIPC_CRITICAL_IMPORTANCE)) - imp++; + u32 src_node; + u32 rmsg_sz; /* discard rejected message if it shouldn't be returned to sender */ - if (msg_errcode(msg) || msg_dest_droppable(msg)) { - buf_discard(buf); - return data_sz; - } - /* construct rejected message */ - if (msg_mcast(msg)) - hdr_sz = MCAST_H_SIZE; - else - hdr_sz = LONG_H_SIZE; - rbuf = tipc_buf_acquire(data_sz + hdr_sz); - if (rbuf == NULL) { - buf_discard(buf); - return data_sz; + if (WARN(!msg_isdata(msg), + "attempt to reject message with user=%u", msg_user(msg))) { + dump_stack(); + goto exit; } + if (msg_errcode(msg) || msg_dest_droppable(msg)) + goto exit; + + /* + * construct returned message by copying rejected message header and + * data (or subset), then updating header fields that need adjusting + */ + + hdr_sz = msg_hdr_sz(msg); + rmsg_sz = hdr_sz + min_t(u32, data_sz, MAX_REJECT_SIZE); + + rbuf = tipc_buf_acquire(rmsg_sz); + if (rbuf == NULL) + goto exit; + rmsg = buf_msg(rbuf); - tipc_msg_init(rmsg, imp, msg_type(msg), hdr_sz, msg_orignode(msg)); - msg_set_errcode(rmsg, err); - msg_set_destport(rmsg, msg_origport(msg)); - msg_set_origport(rmsg, msg_destport(msg)); - if (msg_short(msg)) { - msg_set_orignode(rmsg, tipc_own_addr); - /* leave name type & instance as zeroes */ - } else { - msg_set_orignode(rmsg, msg_destnode(msg)); - msg_set_nametype(rmsg, msg_nametype(msg)); - msg_set_nameinst(rmsg, msg_nameinst(msg)); + skb_copy_to_linear_data(rbuf, msg, rmsg_sz); + + if (msg_connected(rmsg)) { + imp = msg_importance(rmsg); + if (imp < TIPC_CRITICAL_IMPORTANCE) + msg_set_importance(rmsg, ++imp); } - msg_set_size(rmsg, data_sz + hdr_sz); - skb_copy_to_linear_data_offset(rbuf, hdr_sz, msg_data(msg), data_sz); + msg_set_non_seq(rmsg, 0); + msg_set_size(rmsg, rmsg_sz); + msg_set_errcode(rmsg, err); + msg_set_prevnode(rmsg, tipc_own_addr); + msg_swap_words(rmsg, 4, 5); + if (!msg_short(rmsg)) + msg_swap_words(rmsg, 6, 7); /* send self-abort message when rejecting on a connected port */ if (msg_connected(msg)) { @@ -411,9 +411,15 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) tipc_net_route_msg(abuf); } - /* send rejected message */ + /* send returned message & dispose of rejected message */ + + src_node = msg_prevnode(msg); + if (src_node == tipc_own_addr) + tipc_port_recv_msg(rbuf); + else + tipc_link_send(rbuf, src_node, msg_link_selector(rmsg)); +exit: buf_discard(buf); - tipc_net_route_msg(rbuf); return data_sz; } @@ -449,14 +455,7 @@ static void port_timeout(unsigned long ref) if (p_ptr->probing_state == PROBING) { buf = port_build_self_abort_msg(p_ptr, TIPC_ERR_NO_PORT); } else { - buf = port_build_proto_msg(port_peerport(p_ptr), - port_peernode(p_ptr), - p_ptr->ref, - tipc_own_addr, - CONN_MANAGER, - CONN_PROBE, - TIPC_OK, - 0); + buf = port_build_proto_msg(p_ptr, CONN_PROBE, 0); p_ptr->probing_state = PROBING; k_start_timer(&p_ptr->timer, p_ptr->probing_interval); } @@ -480,100 +479,94 @@ static void port_handle_node_down(unsigned long ref) static struct sk_buff *port_build_self_abort_msg(struct tipc_port *p_ptr, u32 err) { - u32 imp = msg_importance(&p_ptr->phdr); + struct sk_buff *buf = port_build_peer_abort_msg(p_ptr, err); - if (!p_ptr->connected) - return NULL; - if (imp < TIPC_CRITICAL_IMPORTANCE) - imp++; - return port_build_proto_msg(p_ptr->ref, - tipc_own_addr, - port_peerport(p_ptr), - port_peernode(p_ptr), - imp, - TIPC_CONN_MSG, - err, - 0); + if (buf) { + struct tipc_msg *msg = buf_msg(buf); + msg_swap_words(msg, 4, 5); + msg_swap_words(msg, 6, 7); + } + return buf; } static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 err) { - u32 imp = msg_importance(&p_ptr->phdr); + struct sk_buff *buf; + struct tipc_msg *msg; + u32 imp; if (!p_ptr->connected) return NULL; - if (imp < TIPC_CRITICAL_IMPORTANCE) - imp++; - return port_build_proto_msg(port_peerport(p_ptr), - port_peernode(p_ptr), - p_ptr->ref, - tipc_own_addr, - imp, - TIPC_CONN_MSG, - err, - 0); + + buf = tipc_buf_acquire(BASIC_H_SIZE); + if (buf) { + msg = buf_msg(buf); + memcpy(msg, &p_ptr->phdr, BASIC_H_SIZE); + msg_set_hdr_sz(msg, BASIC_H_SIZE); + msg_set_size(msg, BASIC_H_SIZE); + imp = msg_importance(msg); + if (imp < TIPC_CRITICAL_IMPORTANCE) + msg_set_importance(msg, ++imp); + msg_set_errcode(msg, err); + } + return buf; } void tipc_port_recv_proto_msg(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); - struct tipc_port *p_ptr = tipc_port_lock(msg_destport(msg)); - u32 err = TIPC_OK; + struct tipc_port *p_ptr; struct sk_buff *r_buf = NULL; - struct sk_buff *abort_buf = NULL; - - if (!p_ptr) { - err = TIPC_ERR_NO_PORT; - } else if (p_ptr->connected) { - if ((port_peernode(p_ptr) != msg_orignode(msg)) || - (port_peerport(p_ptr) != msg_origport(msg))) { - err = TIPC_ERR_NO_PORT; - } else if (msg_type(msg) == CONN_ACK) { - int wakeup = tipc_port_congested(p_ptr) && - p_ptr->congested && - p_ptr->wakeup; - p_ptr->acked += msg_msgcnt(msg); - if (tipc_port_congested(p_ptr)) - goto exit; - p_ptr->congested = 0; - if (!wakeup) - goto exit; - p_ptr->wakeup(p_ptr); - goto exit; + u32 orignode = msg_orignode(msg); + u32 origport = msg_origport(msg); + u32 destport = msg_destport(msg); + int wakeable; + + /* Validate connection */ + + p_ptr = tipc_port_lock(destport); + if (!p_ptr || !p_ptr->connected || + (port_peernode(p_ptr) != orignode) || + (port_peerport(p_ptr) != origport)) { + r_buf = tipc_buf_acquire(BASIC_H_SIZE); + if (r_buf) { + msg = buf_msg(r_buf); + tipc_msg_init(msg, TIPC_HIGH_IMPORTANCE, TIPC_CONN_MSG, + BASIC_H_SIZE, orignode); + msg_set_errcode(msg, TIPC_ERR_NO_PORT); + msg_set_origport(msg, destport); + msg_set_destport(msg, origport); } - } else if (p_ptr->published) { - err = TIPC_ERR_NO_PORT; - } - if (err) { - r_buf = port_build_proto_msg(msg_origport(msg), - msg_orignode(msg), - msg_destport(msg), - tipc_own_addr, - TIPC_HIGH_IMPORTANCE, - TIPC_CONN_MSG, - err, - 0); + if (p_ptr) + tipc_port_unlock(p_ptr); goto exit; } - /* All is fine */ - if (msg_type(msg) == CONN_PROBE) { - r_buf = port_build_proto_msg(msg_origport(msg), - msg_orignode(msg), - msg_destport(msg), - tipc_own_addr, - CONN_MANAGER, - CONN_PROBE_REPLY, - TIPC_OK, - 0); + /* Process protocol message sent by peer */ + + switch (msg_type(msg)) { + case CONN_ACK: + wakeable = tipc_port_congested(p_ptr) && p_ptr->congested && + p_ptr->wakeup; + p_ptr->acked += msg_msgcnt(msg); + if (!tipc_port_congested(p_ptr)) { + p_ptr->congested = 0; + if (wakeable) + p_ptr->wakeup(p_ptr); + } + break; + case CONN_PROBE: + r_buf = port_build_proto_msg(p_ptr, CONN_PROBE_REPLY, 0); + break; + default: + /* CONN_PROBE_REPLY or unrecognized - no action required */ + break; } p_ptr->probing_state = CONFIRMED; + tipc_port_unlock(p_ptr); exit: - if (p_ptr) - tipc_port_unlock(p_ptr); tipc_net_route_msg(r_buf); - tipc_net_route_msg(abort_buf); buf_discard(buf); } @@ -889,14 +882,7 @@ void tipc_acknowledge(u32 ref, u32 ack) return; if (p_ptr->connected) { p_ptr->conn_unacked -= ack; - buf = port_build_proto_msg(port_peerport(p_ptr), - port_peernode(p_ptr), - ref, - tipc_own_addr, - CONN_MANAGER, - CONN_ACK, - TIPC_OK, - ack); + buf = port_build_proto_msg(p_ptr, CONN_ACK, ack); } tipc_port_unlock(p_ptr); tipc_net_route_msg(buf); @@ -1140,19 +1126,7 @@ int tipc_shutdown(u32 ref) if (!p_ptr) return -EINVAL; - if (p_ptr->connected) { - u32 imp = msg_importance(&p_ptr->phdr); - if (imp < TIPC_CRITICAL_IMPORTANCE) - imp++; - buf = port_build_proto_msg(port_peerport(p_ptr), - port_peernode(p_ptr), - ref, - tipc_own_addr, - imp, - TIPC_CONN_MSG, - TIPC_CONN_SHUTDOWN, - 0); - } + buf = port_build_peer_abort_msg(p_ptr, TIPC_CONN_SHUTDOWN); tipc_port_unlock(p_ptr); tipc_net_route_msg(buf); return tipc_disconnect(ref); @@ -1238,7 +1212,7 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, msg_set_type(msg, TIPC_NAMED_MSG); msg_set_orignode(msg, tipc_own_addr); msg_set_origport(msg, ref); - msg_set_hdr_sz(msg, LONG_H_SIZE); + msg_set_hdr_sz(msg, NAMED_H_SIZE); msg_set_nametype(msg, name->type); msg_set_nameinst(msg, name->instance); msg_set_lookup_scope(msg, tipc_addr_scope(domain)); @@ -1291,7 +1265,7 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, msg_set_origport(msg, ref); msg_set_destnode(msg, dest->node); msg_set_destport(msg, dest->ref); - msg_set_hdr_sz(msg, DIR_MSG_H_SIZE); + msg_set_hdr_sz(msg, BASIC_H_SIZE); if (dest->node == tipc_own_addr) res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect, @@ -1331,13 +1305,13 @@ int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, msg_set_origport(msg, ref); msg_set_destnode(msg, dest->node); msg_set_destport(msg, dest->ref); - msg_set_hdr_sz(msg, DIR_MSG_H_SIZE); - msg_set_size(msg, DIR_MSG_H_SIZE + dsz); - if (skb_cow(buf, DIR_MSG_H_SIZE)) + msg_set_hdr_sz(msg, BASIC_H_SIZE); + msg_set_size(msg, BASIC_H_SIZE + dsz); + if (skb_cow(buf, BASIC_H_SIZE)) return -ENOMEM; - skb_push(buf, DIR_MSG_H_SIZE); - skb_copy_to_linear_data(buf, msg, DIR_MSG_H_SIZE); + skb_push(buf, BASIC_H_SIZE); + skb_copy_to_linear_data(buf, msg, BASIC_H_SIZE); if (dest->node == tipc_own_addr) res = tipc_port_recv_msg(buf); diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 33883739664..adb2eff4a10 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -36,9 +36,6 @@ #include <net/sock.h> -#include <linux/tipc.h> -#include <linux/tipc_config.h> - #include "core.h" #include "port.h" diff --git a/net/wireless/core.c b/net/wireless/core.c index c22ef3492ee..880dbe2e6f9 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -366,6 +366,7 @@ struct wiphy *wiphy_new(const struct cfg80211_ops *ops, int sizeof_priv) mutex_init(&rdev->mtx); mutex_init(&rdev->devlist_mtx); + mutex_init(&rdev->sched_scan_mtx); INIT_LIST_HEAD(&rdev->netdev_list); spin_lock_init(&rdev->bss_lock); INIT_LIST_HEAD(&rdev->bss_list); @@ -701,6 +702,7 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev) rfkill_destroy(rdev->rfkill); mutex_destroy(&rdev->mtx); mutex_destroy(&rdev->devlist_mtx); + mutex_destroy(&rdev->sched_scan_mtx); list_for_each_entry_safe(scan, tmp, &rdev->bss_list, list) cfg80211_put_bss(&scan->pub); cfg80211_rdev_free_wowlan(rdev); @@ -737,12 +739,16 @@ static void wdev_cleanup_work(struct work_struct *work) ___cfg80211_scan_done(rdev, true); } + cfg80211_unlock_rdev(rdev); + + mutex_lock(&rdev->sched_scan_mtx); + if (WARN_ON(rdev->sched_scan_req && rdev->sched_scan_req->dev == wdev->netdev)) { __cfg80211_stop_sched_scan(rdev, false); } - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); mutex_lock(&rdev->devlist_mtx); rdev->opencount--; @@ -830,9 +836,9 @@ static int cfg80211_netdev_notifier_call(struct notifier_block * nb, break; case NL80211_IFTYPE_P2P_CLIENT: case NL80211_IFTYPE_STATION: - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); __cfg80211_stop_sched_scan(rdev, false); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); wdev_lock(wdev); #ifdef CONFIG_CFG80211_WEXT diff --git a/net/wireless/core.h b/net/wireless/core.h index 3dce1f167eb..a570ff9214e 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -65,6 +65,8 @@ struct cfg80211_registered_device { struct work_struct scan_done_wk; struct work_struct sched_scan_results_wk; + struct mutex sched_scan_mtx; + #ifdef CONFIG_NL80211_TESTMODE struct genl_info *testmode_info; #endif diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c index 493b939970c..832f6574e4e 100644 --- a/net/wireless/mlme.c +++ b/net/wireless/mlme.c @@ -170,7 +170,9 @@ void __cfg80211_send_deauth(struct net_device *dev, break; } if (wdev->authtry_bsses[i] && - memcmp(wdev->authtry_bsses[i]->pub.bssid, bssid, ETH_ALEN) == 0) { + memcmp(wdev->authtry_bsses[i]->pub.bssid, bssid, + ETH_ALEN) == 0 && + memcmp(mgmt->sa, dev->dev_addr, ETH_ALEN) == 0) { cfg80211_unhold_bss(wdev->authtry_bsses[i]); cfg80211_put_bss(&wdev->authtry_bsses[i]->pub); wdev->authtry_bsses[i] = NULL; @@ -1082,3 +1084,14 @@ void cfg80211_cqm_pktloss_notify(struct net_device *dev, nl80211_send_cqm_pktloss_notify(rdev, dev, peer, num_packets, gfp); } EXPORT_SYMBOL(cfg80211_cqm_pktloss_notify); + +void cfg80211_gtk_rekey_notify(struct net_device *dev, const u8 *bssid, + const u8 *replay_ctr, gfp_t gfp) +{ + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct wiphy *wiphy = wdev->wiphy; + struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); + + nl80211_gtk_rekey_notify(rdev, dev, bssid, replay_ctr, gfp); +} +EXPORT_SYMBOL(cfg80211_gtk_rekey_notify); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 88a565f130a..6a82c898f83 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -176,6 +176,7 @@ static const struct nla_policy nl80211_policy[NL80211_ATTR_MAX+1] = { [NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_PLINK_STATE] = { .type = NLA_U8 }, [NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 }, + [NL80211_ATTR_REKEY_DATA] = { .type = NLA_NESTED }, }; /* policy for the key attributes */ @@ -206,6 +207,14 @@ nl80211_wowlan_policy[NUM_NL80211_WOWLAN_TRIG] = { [NL80211_WOWLAN_TRIG_PKT_PATTERN] = { .type = NLA_NESTED }, }; +/* policy for GTK rekey offload attributes */ +static const struct nla_policy +nl80211_rekey_policy[NUM_NL80211_REKEY_DATA] = { + [NL80211_REKEY_DATA_KEK] = { .len = NL80211_KEK_LEN }, + [NL80211_REKEY_DATA_KCK] = { .len = NL80211_KCK_LEN }, + [NL80211_REKEY_DATA_REPLAY_CTR] = { .len = NL80211_REPLAY_CTR_LEN }, +}; + /* ifidx get helper */ static int nl80211_get_ifidx(struct netlink_callback *cb) { @@ -3406,11 +3415,11 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info) i = 0; if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) { nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) { - request->ssids[i].ssid_len = nla_len(attr); - if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) { + if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; goto out_free; } + request->ssids[i].ssid_len = nla_len(attr); memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr)); i++; } @@ -3461,9 +3470,6 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (!is_valid_ie_attr(info->attrs[NL80211_ATTR_IE])) return -EINVAL; - if (rdev->sched_scan_req) - return -EINPROGRESS; - if (!info->attrs[NL80211_ATTR_SCHED_SCAN_INTERVAL]) return -EINVAL; @@ -3502,12 +3508,21 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (ie_len > wiphy->max_scan_ie_len) return -EINVAL; + mutex_lock(&rdev->sched_scan_mtx); + + if (rdev->sched_scan_req) { + err = -EINPROGRESS; + goto out; + } + request = kzalloc(sizeof(*request) + sizeof(*request->ssids) * n_ssids + sizeof(*request->channels) * n_channels + ie_len, GFP_KERNEL); - if (!request) - return -ENOMEM; + if (!request) { + err = -ENOMEM; + goto out; + } if (n_ssids) request->ssids = (void *)&request->channels[n_channels]; @@ -3572,12 +3587,11 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) { nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) { - request->ssids[i].ssid_len = nla_len(attr); - if (request->ssids[i].ssid_len > - IEEE80211_MAX_SSID_LEN) { + if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; goto out_free; } + request->ssids[i].ssid_len = nla_len(attr); memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr)); i++; @@ -3606,6 +3620,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb, out_free: kfree(request); out: + mutex_unlock(&rdev->sched_scan_mtx); return err; } @@ -3613,15 +3628,21 @@ static int nl80211_stop_sched_scan(struct sk_buff *skb, struct genl_info *info) { struct cfg80211_registered_device *rdev = info->user_ptr[0]; + int err; if (!(rdev->wiphy.flags & WIPHY_FLAG_SUPPORTS_SCHED_SCAN) || !rdev->ops->sched_scan_stop) return -EOPNOTSUPP; - return __cfg80211_stop_sched_scan(rdev, false); + mutex_lock(&rdev->sched_scan_mtx); + err = __cfg80211_stop_sched_scan(rdev, false); + mutex_unlock(&rdev->sched_scan_mtx); + + return err; } -static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, +static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, + u32 seq, int flags, struct cfg80211_registered_device *rdev, struct wireless_dev *wdev, struct cfg80211_internal_bss *intbss) @@ -3633,11 +3654,13 @@ static int nl80211_send_bss(struct sk_buff *msg, u32 pid, u32 seq, int flags, ASSERT_WDEV_LOCK(wdev); - hdr = nl80211hdr_put(msg, pid, seq, flags, + hdr = nl80211hdr_put(msg, NETLINK_CB(cb->skb).pid, seq, flags, NL80211_CMD_NEW_SCAN_RESULTS); if (!hdr) return -1; + genl_dump_check_consistent(cb, hdr, &nl80211_fam); + NLA_PUT_U32(msg, NL80211_ATTR_GENERATION, rdev->bss_generation); NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, wdev->netdev->ifindex); @@ -3726,11 +3749,12 @@ static int nl80211_dump_scan(struct sk_buff *skb, spin_lock_bh(&rdev->bss_lock); cfg80211_bss_expire(rdev); + cb->seq = rdev->bss_generation; + list_for_each_entry(scan, &rdev->bss_list, list) { if (++idx <= start) continue; - if (nl80211_send_bss(skb, - NETLINK_CB(cb->skb).pid, + if (nl80211_send_bss(skb, cb, cb->nlh->nlmsg_seq, NLM_F_MULTI, rdev, wdev, scan) < 0) { idx--; @@ -3754,10 +3778,6 @@ static int nl80211_send_survey(struct sk_buff *msg, u32 pid, u32 seq, void *hdr; struct nlattr *infoattr; - /* Survey without a channel doesn't make sense */ - if (!survey->channel) - return -EINVAL; - hdr = nl80211hdr_put(msg, pid, seq, flags, NL80211_CMD_NEW_SURVEY_RESULTS); if (!hdr) @@ -3820,6 +3840,8 @@ static int nl80211_dump_survey(struct sk_buff *skb, } while (1) { + struct ieee80211_channel *chan; + res = dev->ops->dump_survey(&dev->wiphy, netdev, survey_idx, &survey); if (res == -ENOENT) @@ -3827,6 +3849,19 @@ static int nl80211_dump_survey(struct sk_buff *skb, if (res) goto out_err; + /* Survey without a channel doesn't make sense */ + if (!survey.channel) { + res = -EINVAL; + goto out; + } + + chan = ieee80211_get_channel(&dev->wiphy, + survey.channel->center_freq); + if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) { + survey_idx++; + continue; + } + if (nl80211_send_survey(skb, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, @@ -4361,6 +4396,93 @@ static int nl80211_testmode_do(struct sk_buff *skb, struct genl_info *info) return err; } +static int nl80211_testmode_dump(struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct cfg80211_registered_device *dev; + int err; + long phy_idx; + void *data = NULL; + int data_len = 0; + + if (cb->args[0]) { + /* + * 0 is a valid index, but not valid for args[0], + * so we need to offset by 1. + */ + phy_idx = cb->args[0] - 1; + } else { + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + nl80211_fam.hdrsize, + nl80211_fam.attrbuf, nl80211_fam.maxattr, + nl80211_policy); + if (err) + return err; + if (!nl80211_fam.attrbuf[NL80211_ATTR_WIPHY]) + return -EINVAL; + phy_idx = nla_get_u32(nl80211_fam.attrbuf[NL80211_ATTR_WIPHY]); + if (nl80211_fam.attrbuf[NL80211_ATTR_TESTDATA]) + cb->args[1] = + (long)nl80211_fam.attrbuf[NL80211_ATTR_TESTDATA]; + } + + if (cb->args[1]) { + data = nla_data((void *)cb->args[1]); + data_len = nla_len((void *)cb->args[1]); + } + + mutex_lock(&cfg80211_mutex); + dev = cfg80211_rdev_by_wiphy_idx(phy_idx); + if (!dev) { + mutex_unlock(&cfg80211_mutex); + return -ENOENT; + } + cfg80211_lock_rdev(dev); + mutex_unlock(&cfg80211_mutex); + + if (!dev->ops->testmode_dump) { + err = -EOPNOTSUPP; + goto out_err; + } + + while (1) { + void *hdr = nl80211hdr_put(skb, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + NL80211_CMD_TESTMODE); + struct nlattr *tmdata; + + if (nla_put_u32(skb, NL80211_ATTR_WIPHY, dev->wiphy_idx) < 0) { + genlmsg_cancel(skb, hdr); + break; + } + + tmdata = nla_nest_start(skb, NL80211_ATTR_TESTDATA); + if (!tmdata) { + genlmsg_cancel(skb, hdr); + break; + } + err = dev->ops->testmode_dump(&dev->wiphy, skb, cb, + data, data_len); + nla_nest_end(skb, tmdata); + + if (err == -ENOBUFS || err == -ENOENT) { + genlmsg_cancel(skb, hdr); + break; + } else if (err) { + genlmsg_cancel(skb, hdr); + goto out_err; + } + + genlmsg_end(skb, hdr); + } + + err = skb->len; + /* see above */ + cb->args[0] = phy_idx + 1; + out_err: + cfg80211_unlock_rdev(dev); + return err; +} + static struct sk_buff * __cfg80211_testmode_alloc_skb(struct cfg80211_registered_device *rdev, int approxlen, u32 pid, u32 seq, gfp_t gfp) @@ -5307,6 +5429,57 @@ static int nl80211_set_wowlan(struct sk_buff *skb, struct genl_info *info) return err; } +static int nl80211_set_rekey_data(struct sk_buff *skb, struct genl_info *info) +{ + struct cfg80211_registered_device *rdev = info->user_ptr[0]; + struct net_device *dev = info->user_ptr[1]; + struct wireless_dev *wdev = dev->ieee80211_ptr; + struct nlattr *tb[NUM_NL80211_REKEY_DATA]; + struct cfg80211_gtk_rekey_data rekey_data; + int err; + + if (!info->attrs[NL80211_ATTR_REKEY_DATA]) + return -EINVAL; + + err = nla_parse(tb, MAX_NL80211_REKEY_DATA, + nla_data(info->attrs[NL80211_ATTR_REKEY_DATA]), + nla_len(info->attrs[NL80211_ATTR_REKEY_DATA]), + nl80211_rekey_policy); + if (err) + return err; + + if (nla_len(tb[NL80211_REKEY_DATA_REPLAY_CTR]) != NL80211_REPLAY_CTR_LEN) + return -ERANGE; + if (nla_len(tb[NL80211_REKEY_DATA_KEK]) != NL80211_KEK_LEN) + return -ERANGE; + if (nla_len(tb[NL80211_REKEY_DATA_KCK]) != NL80211_KCK_LEN) + return -ERANGE; + + memcpy(rekey_data.kek, nla_data(tb[NL80211_REKEY_DATA_KEK]), + NL80211_KEK_LEN); + memcpy(rekey_data.kck, nla_data(tb[NL80211_REKEY_DATA_KCK]), + NL80211_KCK_LEN); + memcpy(rekey_data.replay_ctr, + nla_data(tb[NL80211_REKEY_DATA_REPLAY_CTR]), + NL80211_REPLAY_CTR_LEN); + + wdev_lock(wdev); + if (!wdev->current_bss) { + err = -ENOTCONN; + goto out; + } + + if (!rdev->ops->set_rekey_data) { + err = -EOPNOTSUPP; + goto out; + } + + err = rdev->ops->set_rekey_data(&rdev->wiphy, dev, &rekey_data); + out: + wdev_unlock(wdev); + return err; +} + #define NL80211_FLAG_NEED_WIPHY 0x01 #define NL80211_FLAG_NEED_NETDEV 0x02 #define NL80211_FLAG_NEED_RTNL 0x04 @@ -5658,6 +5831,7 @@ static struct genl_ops nl80211_ops[] = { { .cmd = NL80211_CMD_TESTMODE, .doit = nl80211_testmode_do, + .dumpit = nl80211_testmode_dump, .policy = nl80211_policy, .flags = GENL_ADMIN_PERM, .internal_flags = NL80211_FLAG_NEED_WIPHY | @@ -5837,6 +6011,14 @@ static struct genl_ops nl80211_ops[] = { .internal_flags = NL80211_FLAG_NEED_WIPHY | NL80211_FLAG_NEED_RTNL, }, + { + .cmd = NL80211_CMD_SET_REKEY_OFFLOAD, + .doit = nl80211_set_rekey_data, + .policy = nl80211_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = NL80211_FLAG_NEED_NETDEV_UP | + NL80211_FLAG_NEED_RTNL, + }, }; static struct genl_multicast_group nl80211_mlme_mcgrp = { @@ -6464,7 +6646,8 @@ void nl80211_michael_mic_failure(struct cfg80211_registered_device *rdev, if (addr) NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, addr); NLA_PUT_U32(msg, NL80211_ATTR_KEY_TYPE, key_type); - NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_id); + if (key_id != -1) + NLA_PUT_U8(msg, NL80211_ATTR_KEY_IDX, key_id); if (tsc) NLA_PUT(msg, NL80211_ATTR_KEY_SEQ, 6, tsc); @@ -6780,6 +6963,51 @@ nl80211_send_cqm_rssi_notify(struct cfg80211_registered_device *rdev, nlmsg_free(msg); } +void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + const u8 *replay_ctr, gfp_t gfp) +{ + struct sk_buff *msg; + struct nlattr *rekey_attr; + void *hdr; + + msg = nlmsg_new(NLMSG_GOODSIZE, gfp); + if (!msg) + return; + + hdr = nl80211hdr_put(msg, 0, 0, 0, NL80211_CMD_SET_REKEY_OFFLOAD); + if (!hdr) { + nlmsg_free(msg); + return; + } + + NLA_PUT_U32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx); + NLA_PUT_U32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex); + NLA_PUT(msg, NL80211_ATTR_MAC, ETH_ALEN, bssid); + + rekey_attr = nla_nest_start(msg, NL80211_ATTR_REKEY_DATA); + if (!rekey_attr) + goto nla_put_failure; + + NLA_PUT(msg, NL80211_REKEY_DATA_REPLAY_CTR, + NL80211_REPLAY_CTR_LEN, replay_ctr); + + nla_nest_end(msg, rekey_attr); + + if (genlmsg_end(msg, hdr) < 0) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(wiphy_net(&rdev->wiphy), msg, 0, + nl80211_mlme_mcgrp.id, gfp); + return; + + nla_put_failure: + genlmsg_cancel(msg, hdr); + nlmsg_free(msg); +} + void nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, diff --git a/net/wireless/nl80211.h b/net/wireless/nl80211.h index 2f1bfb87a65..5d69c56400a 100644 --- a/net/wireless/nl80211.h +++ b/net/wireless/nl80211.h @@ -109,4 +109,8 @@ nl80211_send_cqm_pktloss_notify(struct cfg80211_registered_device *rdev, struct net_device *netdev, const u8 *peer, u32 num_packets, gfp_t gfp); +void nl80211_gtk_rekey_notify(struct cfg80211_registered_device *rdev, + struct net_device *netdev, const u8 *bssid, + const u8 *replay_ctr, gfp_t gfp); + #endif /* __NET_WIRELESS_NL80211_H */ diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 7a6c67667d7..1c4672e3514 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -100,14 +100,14 @@ void __cfg80211_sched_scan_results(struct work_struct *wk) rdev = container_of(wk, struct cfg80211_registered_device, sched_scan_results_wk); - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); /* we don't have sched_scan_req anymore if the scan is stopping */ if (rdev->sched_scan_req) nl80211_send_sched_scan_results(rdev, rdev->sched_scan_req->dev); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); } void cfg80211_sched_scan_results(struct wiphy *wiphy) @@ -123,27 +123,26 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy) { struct cfg80211_registered_device *rdev = wiphy_to_dev(wiphy); - cfg80211_lock_rdev(rdev); + mutex_lock(&rdev->sched_scan_mtx); __cfg80211_stop_sched_scan(rdev, true); - cfg80211_unlock_rdev(rdev); + mutex_unlock(&rdev->sched_scan_mtx); } EXPORT_SYMBOL(cfg80211_sched_scan_stopped); int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, bool driver_initiated) { - int err; struct net_device *dev; - ASSERT_RDEV_LOCK(rdev); + lockdep_assert_held(&rdev->sched_scan_mtx); if (!rdev->sched_scan_req) - return 0; + return -ENOENT; dev = rdev->sched_scan_req->dev; if (!driver_initiated) { - err = rdev->ops->sched_scan_stop(&rdev->wiphy, dev); + int err = rdev->ops->sched_scan_stop(&rdev->wiphy, dev); if (err) return err; } @@ -153,7 +152,7 @@ int __cfg80211_stop_sched_scan(struct cfg80211_registered_device *rdev, kfree(rdev->sched_scan_req); rdev->sched_scan_req = NULL; - return err; + return 0; } static void bss_release(struct kref *ref) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 4680b1e4c79..d30615419b4 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -237,21 +237,21 @@ static int x25_device_event(struct notifier_block *this, unsigned long event, #endif ) { switch (event) { - case NETDEV_UP: - x25_link_device_up(dev); - break; - case NETDEV_GOING_DOWN: - nb = x25_get_neigh(dev); - if (nb) { - x25_terminate_link(nb); - x25_neigh_put(nb); - } - break; - case NETDEV_DOWN: - x25_kill_by_device(dev); - x25_route_device_down(dev); - x25_link_device_down(dev); - break; + case NETDEV_UP: + x25_link_device_up(dev); + break; + case NETDEV_GOING_DOWN: + nb = x25_get_neigh(dev); + if (nb) { + x25_terminate_link(nb); + x25_neigh_put(nb); + } + break; + case NETDEV_DOWN: + x25_kill_by_device(dev); + x25_route_device_down(dev); + x25_link_device_down(dev); + break; } } @@ -1336,256 +1336,253 @@ static int x25_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) int rc; switch (cmd) { - case TIOCOUTQ: { - int amount; + case TIOCOUTQ: { + int amount; - amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); - if (amount < 0) - amount = 0; - rc = put_user(amount, (unsigned int __user *)argp); - break; - } + amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); + if (amount < 0) + amount = 0; + rc = put_user(amount, (unsigned int __user *)argp); + break; + } - case TIOCINQ: { - struct sk_buff *skb; - int amount = 0; - /* - * These two are safe on a single CPU system as - * only user tasks fiddle here - */ - lock_sock(sk); - if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) - amount = skb->len; - release_sock(sk); - rc = put_user(amount, (unsigned int __user *)argp); - break; - } + case TIOCINQ: { + struct sk_buff *skb; + int amount = 0; + /* + * These two are safe on a single CPU system as + * only user tasks fiddle here + */ + lock_sock(sk); + if ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) + amount = skb->len; + release_sock(sk); + rc = put_user(amount, (unsigned int __user *)argp); + break; + } - case SIOCGSTAMP: - rc = -EINVAL; - if (sk) - rc = sock_get_timestamp(sk, + case SIOCGSTAMP: + rc = -EINVAL; + if (sk) + rc = sock_get_timestamp(sk, (struct timeval __user *)argp); + break; + case SIOCGSTAMPNS: + rc = -EINVAL; + if (sk) + rc = sock_get_timestampns(sk, + (struct timespec __user *)argp); + break; + case SIOCGIFADDR: + case SIOCSIFADDR: + case SIOCGIFDSTADDR: + case SIOCSIFDSTADDR: + case SIOCGIFBRDADDR: + case SIOCSIFBRDADDR: + case SIOCGIFNETMASK: + case SIOCSIFNETMASK: + case SIOCGIFMETRIC: + case SIOCSIFMETRIC: + rc = -EINVAL; + break; + case SIOCADDRT: + case SIOCDELRT: + rc = -EPERM; + if (!capable(CAP_NET_ADMIN)) break; - case SIOCGSTAMPNS: - rc = -EINVAL; - if (sk) - rc = sock_get_timestampns(sk, - (struct timespec __user *)argp); - break; - case SIOCGIFADDR: - case SIOCSIFADDR: - case SIOCGIFDSTADDR: - case SIOCSIFDSTADDR: - case SIOCGIFBRDADDR: - case SIOCSIFBRDADDR: - case SIOCGIFNETMASK: - case SIOCSIFNETMASK: - case SIOCGIFMETRIC: - case SIOCSIFMETRIC: - rc = -EINVAL; - break; - case SIOCADDRT: - case SIOCDELRT: - rc = -EPERM; - if (!capable(CAP_NET_ADMIN)) - break; - rc = x25_route_ioctl(cmd, argp); - break; - case SIOCX25GSUBSCRIP: - rc = x25_subscr_ioctl(cmd, argp); - break; - case SIOCX25SSUBSCRIP: - rc = -EPERM; - if (!capable(CAP_NET_ADMIN)) - break; - rc = x25_subscr_ioctl(cmd, argp); - break; - case SIOCX25GFACILITIES: { - lock_sock(sk); - rc = copy_to_user(argp, &x25->facilities, - sizeof(x25->facilities)) - ? -EFAULT : 0; - release_sock(sk); + rc = x25_route_ioctl(cmd, argp); + break; + case SIOCX25GSUBSCRIP: + rc = x25_subscr_ioctl(cmd, argp); + break; + case SIOCX25SSUBSCRIP: + rc = -EPERM; + if (!capable(CAP_NET_ADMIN)) break; - } + rc = x25_subscr_ioctl(cmd, argp); + break; + case SIOCX25GFACILITIES: { + lock_sock(sk); + rc = copy_to_user(argp, &x25->facilities, + sizeof(x25->facilities)) + ? -EFAULT : 0; + release_sock(sk); + break; + } - case SIOCX25SFACILITIES: { - struct x25_facilities facilities; - rc = -EFAULT; - if (copy_from_user(&facilities, argp, - sizeof(facilities))) - break; - rc = -EINVAL; - lock_sock(sk); - if (sk->sk_state != TCP_LISTEN && - sk->sk_state != TCP_CLOSE) - goto out_fac_release; - if (facilities.pacsize_in < X25_PS16 || - facilities.pacsize_in > X25_PS4096) - goto out_fac_release; - if (facilities.pacsize_out < X25_PS16 || - facilities.pacsize_out > X25_PS4096) - goto out_fac_release; - if (facilities.winsize_in < 1 || - facilities.winsize_in > 127) + case SIOCX25SFACILITIES: { + struct x25_facilities facilities; + rc = -EFAULT; + if (copy_from_user(&facilities, argp, sizeof(facilities))) + break; + rc = -EINVAL; + lock_sock(sk); + if (sk->sk_state != TCP_LISTEN && + sk->sk_state != TCP_CLOSE) + goto out_fac_release; + if (facilities.pacsize_in < X25_PS16 || + facilities.pacsize_in > X25_PS4096) + goto out_fac_release; + if (facilities.pacsize_out < X25_PS16 || + facilities.pacsize_out > X25_PS4096) + goto out_fac_release; + if (facilities.winsize_in < 1 || + facilities.winsize_in > 127) + goto out_fac_release; + if (facilities.throughput) { + int out = facilities.throughput & 0xf0; + int in = facilities.throughput & 0x0f; + if (!out) + facilities.throughput |= + X25_DEFAULT_THROUGHPUT << 4; + else if (out < 0x30 || out > 0xD0) goto out_fac_release; - if (facilities.throughput) { - int out = facilities.throughput & 0xf0; - int in = facilities.throughput & 0x0f; - if (!out) - facilities.throughput |= - X25_DEFAULT_THROUGHPUT << 4; - else if (out < 0x30 || out > 0xD0) - goto out_fac_release; - if (!in) - facilities.throughput |= - X25_DEFAULT_THROUGHPUT; - else if (in < 0x03 || in > 0x0D) - goto out_fac_release; - } - if (facilities.reverse && - (facilities.reverse & 0x81) != 0x81) + if (!in) + facilities.throughput |= + X25_DEFAULT_THROUGHPUT; + else if (in < 0x03 || in > 0x0D) goto out_fac_release; - x25->facilities = facilities; - rc = 0; -out_fac_release: - release_sock(sk); - break; - } - - case SIOCX25GDTEFACILITIES: { - lock_sock(sk); - rc = copy_to_user(argp, &x25->dte_facilities, - sizeof(x25->dte_facilities)); - release_sock(sk); - if (rc) - rc = -EFAULT; - break; } + if (facilities.reverse && + (facilities.reverse & 0x81) != 0x81) + goto out_fac_release; + x25->facilities = facilities; + rc = 0; +out_fac_release: + release_sock(sk); + break; + } - case SIOCX25SDTEFACILITIES: { - struct x25_dte_facilities dtefacs; + case SIOCX25GDTEFACILITIES: { + lock_sock(sk); + rc = copy_to_user(argp, &x25->dte_facilities, + sizeof(x25->dte_facilities)); + release_sock(sk); + if (rc) rc = -EFAULT; - if (copy_from_user(&dtefacs, argp, sizeof(dtefacs))) - break; - rc = -EINVAL; - lock_sock(sk); - if (sk->sk_state != TCP_LISTEN && - sk->sk_state != TCP_CLOSE) - goto out_dtefac_release; - if (dtefacs.calling_len > X25_MAX_AE_LEN) - goto out_dtefac_release; - if (dtefacs.calling_ae == NULL) - goto out_dtefac_release; - if (dtefacs.called_len > X25_MAX_AE_LEN) - goto out_dtefac_release; - if (dtefacs.called_ae == NULL) - goto out_dtefac_release; - x25->dte_facilities = dtefacs; - rc = 0; -out_dtefac_release: - release_sock(sk); - break; - } + break; + } - case SIOCX25GCALLUSERDATA: { - lock_sock(sk); - rc = copy_to_user(argp, &x25->calluserdata, - sizeof(x25->calluserdata)) - ? -EFAULT : 0; - release_sock(sk); + case SIOCX25SDTEFACILITIES: { + struct x25_dte_facilities dtefacs; + rc = -EFAULT; + if (copy_from_user(&dtefacs, argp, sizeof(dtefacs))) break; - } + rc = -EINVAL; + lock_sock(sk); + if (sk->sk_state != TCP_LISTEN && + sk->sk_state != TCP_CLOSE) + goto out_dtefac_release; + if (dtefacs.calling_len > X25_MAX_AE_LEN) + goto out_dtefac_release; + if (dtefacs.calling_ae == NULL) + goto out_dtefac_release; + if (dtefacs.called_len > X25_MAX_AE_LEN) + goto out_dtefac_release; + if (dtefacs.called_ae == NULL) + goto out_dtefac_release; + x25->dte_facilities = dtefacs; + rc = 0; +out_dtefac_release: + release_sock(sk); + break; + } - case SIOCX25SCALLUSERDATA: { - struct x25_calluserdata calluserdata; + case SIOCX25GCALLUSERDATA: { + lock_sock(sk); + rc = copy_to_user(argp, &x25->calluserdata, + sizeof(x25->calluserdata)) + ? -EFAULT : 0; + release_sock(sk); + break; + } - rc = -EFAULT; - if (copy_from_user(&calluserdata, argp, - sizeof(calluserdata))) - break; - rc = -EINVAL; - if (calluserdata.cudlength > X25_MAX_CUD_LEN) - break; - lock_sock(sk); - x25->calluserdata = calluserdata; - release_sock(sk); - rc = 0; - break; - } + case SIOCX25SCALLUSERDATA: { + struct x25_calluserdata calluserdata; - case SIOCX25GCAUSEDIAG: { - lock_sock(sk); - rc = copy_to_user(argp, &x25->causediag, - sizeof(x25->causediag)) - ? -EFAULT : 0; - release_sock(sk); + rc = -EFAULT; + if (copy_from_user(&calluserdata, argp, sizeof(calluserdata))) break; - } + rc = -EINVAL; + if (calluserdata.cudlength > X25_MAX_CUD_LEN) + break; + lock_sock(sk); + x25->calluserdata = calluserdata; + release_sock(sk); + rc = 0; + break; + } - case SIOCX25SCAUSEDIAG: { - struct x25_causediag causediag; - rc = -EFAULT; - if (copy_from_user(&causediag, argp, sizeof(causediag))) - break; - lock_sock(sk); - x25->causediag = causediag; - release_sock(sk); - rc = 0; + case SIOCX25GCAUSEDIAG: { + lock_sock(sk); + rc = copy_to_user(argp, &x25->causediag, sizeof(x25->causediag)) + ? -EFAULT : 0; + release_sock(sk); + break; + } + + case SIOCX25SCAUSEDIAG: { + struct x25_causediag causediag; + rc = -EFAULT; + if (copy_from_user(&causediag, argp, sizeof(causediag))) break; + lock_sock(sk); + x25->causediag = causediag; + release_sock(sk); + rc = 0; + break; - } + } - case SIOCX25SCUDMATCHLEN: { - struct x25_subaddr sub_addr; - rc = -EINVAL; - lock_sock(sk); - if(sk->sk_state != TCP_CLOSE) - goto out_cud_release; - rc = -EFAULT; - if (copy_from_user(&sub_addr, argp, - sizeof(sub_addr))) - goto out_cud_release; - rc = -EINVAL; - if(sub_addr.cudmatchlength > X25_MAX_CUD_LEN) - goto out_cud_release; - x25->cudmatchlength = sub_addr.cudmatchlength; - rc = 0; + case SIOCX25SCUDMATCHLEN: { + struct x25_subaddr sub_addr; + rc = -EINVAL; + lock_sock(sk); + if(sk->sk_state != TCP_CLOSE) + goto out_cud_release; + rc = -EFAULT; + if (copy_from_user(&sub_addr, argp, + sizeof(sub_addr))) + goto out_cud_release; + rc = -EINVAL; + if (sub_addr.cudmatchlength > X25_MAX_CUD_LEN) + goto out_cud_release; + x25->cudmatchlength = sub_addr.cudmatchlength; + rc = 0; out_cud_release: - release_sock(sk); - break; - } + release_sock(sk); + break; + } - case SIOCX25CALLACCPTAPPRV: { - rc = -EINVAL; - lock_sock(sk); - if (sk->sk_state != TCP_CLOSE) - break; - clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); - release_sock(sk); - rc = 0; + case SIOCX25CALLACCPTAPPRV: { + rc = -EINVAL; + lock_sock(sk); + if (sk->sk_state != TCP_CLOSE) break; - } + clear_bit(X25_ACCPT_APPRV_FLAG, &x25->flags); + release_sock(sk); + rc = 0; + break; + } - case SIOCX25SENDCALLACCPT: { - rc = -EINVAL; - lock_sock(sk); - if (sk->sk_state != TCP_ESTABLISHED) - break; - /* must call accptapprv above */ - if (test_bit(X25_ACCPT_APPRV_FLAG, &x25->flags)) - break; - x25_write_internal(sk, X25_CALL_ACCEPTED); - x25->state = X25_STATE_3; - release_sock(sk); - rc = 0; + case SIOCX25SENDCALLACCPT: { + rc = -EINVAL; + lock_sock(sk); + if (sk->sk_state != TCP_ESTABLISHED) break; - } - - default: - rc = -ENOIOCTLCMD; + /* must call accptapprv above */ + if (test_bit(X25_ACCPT_APPRV_FLAG, &x25->flags)) break; + x25_write_internal(sk, X25_CALL_ACCEPTED); + x25->state = X25_STATE_3; + release_sock(sk); + rc = 0; + break; + } + + default: + rc = -ENOIOCTLCMD; + break; } return rc; diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 9005f6daeab..e547ca1578c 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -146,21 +146,21 @@ void x25_establish_link(struct x25_neigh *nb) unsigned char *ptr; switch (nb->dev->type) { - case ARPHRD_X25: - if ((skb = alloc_skb(1, GFP_ATOMIC)) == NULL) { - printk(KERN_ERR "x25_dev: out of memory\n"); - return; - } - ptr = skb_put(skb, 1); - *ptr = X25_IFACE_CONNECT; - break; + case ARPHRD_X25: + if ((skb = alloc_skb(1, GFP_ATOMIC)) == NULL) { + printk(KERN_ERR "x25_dev: out of memory\n"); + return; + } + ptr = skb_put(skb, 1); + *ptr = X25_IFACE_CONNECT; + break; #if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE) - case ARPHRD_ETHER: - return; + case ARPHRD_ETHER: + return; #endif - default: - return; + default: + return; } skb->protocol = htons(ETH_P_X25); @@ -202,19 +202,19 @@ void x25_send_frame(struct sk_buff *skb, struct x25_neigh *nb) skb_reset_network_header(skb); switch (nb->dev->type) { - case ARPHRD_X25: - dptr = skb_push(skb, 1); - *dptr = X25_IFACE_DATA; - break; + case ARPHRD_X25: + dptr = skb_push(skb, 1); + *dptr = X25_IFACE_DATA; + break; #if defined(CONFIG_LLC) || defined(CONFIG_LLC_MODULE) - case ARPHRD_ETHER: - kfree_skb(skb); - return; + case ARPHRD_ETHER: + kfree_skb(skb); + return; #endif - default: - kfree_skb(skb); - return; + default: + kfree_skb(skb); + return; } skb->protocol = htons(ETH_P_X25); diff --git a/net/x25/x25_in.c b/net/x25/x25_in.c index 15de65f0471..0b073b51b18 100644 --- a/net/x25/x25_in.c +++ b/net/x25/x25_in.c @@ -94,55 +94,55 @@ static int x25_state1_machine(struct sock *sk, struct sk_buff *skb, int frametyp struct x25_sock *x25 = x25_sk(sk); switch (frametype) { - case X25_CALL_ACCEPTED: { - - x25_stop_timer(sk); - x25->condition = 0x00; - x25->vs = 0; - x25->va = 0; - x25->vr = 0; - x25->vl = 0; - x25->state = X25_STATE_3; - sk->sk_state = TCP_ESTABLISHED; - /* - * Parse the data in the frame. - */ - skb_pull(skb, X25_STD_MIN_LEN); - - len = x25_parse_address_block(skb, &source_addr, - &dest_addr); - if (len > 0) - skb_pull(skb, len); - else if (len < 0) - goto out_clear; - - len = x25_parse_facilities(skb, &x25->facilities, - &x25->dte_facilities, - &x25->vc_facil_mask); - if (len > 0) - skb_pull(skb, len); - else if (len < 0) - goto out_clear; - /* - * Copy any Call User Data. - */ - if (skb->len > 0) { - skb_copy_from_linear_data(skb, - x25->calluserdata.cuddata, - skb->len); - x25->calluserdata.cudlength = skb->len; - } - if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_state_change(sk); - break; + case X25_CALL_ACCEPTED: { + + x25_stop_timer(sk); + x25->condition = 0x00; + x25->vs = 0; + x25->va = 0; + x25->vr = 0; + x25->vl = 0; + x25->state = X25_STATE_3; + sk->sk_state = TCP_ESTABLISHED; + /* + * Parse the data in the frame. + */ + skb_pull(skb, X25_STD_MIN_LEN); + + len = x25_parse_address_block(skb, &source_addr, + &dest_addr); + if (len > 0) + skb_pull(skb, len); + else if (len < 0) + goto out_clear; + + len = x25_parse_facilities(skb, &x25->facilities, + &x25->dte_facilities, + &x25->vc_facil_mask); + if (len > 0) + skb_pull(skb, len); + else if (len < 0) + goto out_clear; + /* + * Copy any Call User Data. + */ + if (skb->len > 0) { + skb_copy_from_linear_data(skb, + x25->calluserdata.cuddata, + skb->len); + x25->calluserdata.cudlength = skb->len; } - case X25_CLEAR_REQUEST: - x25_write_internal(sk, X25_CLEAR_CONFIRMATION); - x25_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]); - break; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_state_change(sk); + break; + } + case X25_CLEAR_REQUEST: + x25_write_internal(sk, X25_CLEAR_CONFIRMATION); + x25_disconnect(sk, ECONNREFUSED, skb->data[3], skb->data[4]); + break; - default: - break; + default: + break; } return 0; @@ -354,18 +354,18 @@ int x25_process_rx_frame(struct sock *sk, struct sk_buff *skb) frametype = x25_decode(sk, skb, &ns, &nr, &q, &d, &m); switch (x25->state) { - case X25_STATE_1: - queued = x25_state1_machine(sk, skb, frametype); - break; - case X25_STATE_2: - queued = x25_state2_machine(sk, skb, frametype); - break; - case X25_STATE_3: - queued = x25_state3_machine(sk, skb, frametype, ns, nr, q, d, m); - break; - case X25_STATE_4: - queued = x25_state4_machine(sk, skb, frametype); - break; + case X25_STATE_1: + queued = x25_state1_machine(sk, skb, frametype); + break; + case X25_STATE_2: + queued = x25_state2_machine(sk, skb, frametype); + break; + case X25_STATE_3: + queued = x25_state3_machine(sk, skb, frametype, ns, nr, q, d, m); + break; + case X25_STATE_4: + queued = x25_state4_machine(sk, skb, frametype); + break; } x25_kick(sk); diff --git a/net/x25/x25_link.c b/net/x25/x25_link.c index 21306928d47..037958ff8ee 100644 --- a/net/x25/x25_link.c +++ b/net/x25/x25_link.c @@ -76,30 +76,29 @@ void x25_link_control(struct sk_buff *skb, struct x25_neigh *nb, int confirm; switch (frametype) { - case X25_RESTART_REQUEST: - confirm = !x25_t20timer_pending(nb); - x25_stop_t20timer(nb); - nb->state = X25_LINK_STATE_3; - if (confirm) - x25_transmit_restart_confirmation(nb); - break; - - case X25_RESTART_CONFIRMATION: - x25_stop_t20timer(nb); - nb->state = X25_LINK_STATE_3; - break; - - case X25_DIAGNOSTIC: - printk(KERN_WARNING "x25: diagnostic #%d - " - "%02X %02X %02X\n", - skb->data[3], skb->data[4], - skb->data[5], skb->data[6]); - break; - - default: - printk(KERN_WARNING "x25: received unknown %02X " - "with LCI 000\n", frametype); - break; + case X25_RESTART_REQUEST: + confirm = !x25_t20timer_pending(nb); + x25_stop_t20timer(nb); + nb->state = X25_LINK_STATE_3; + if (confirm) + x25_transmit_restart_confirmation(nb); + break; + + case X25_RESTART_CONFIRMATION: + x25_stop_t20timer(nb); + nb->state = X25_LINK_STATE_3; + break; + + case X25_DIAGNOSTIC: + printk(KERN_WARNING "x25: diagnostic #%d - %02X %02X %02X\n", + skb->data[3], skb->data[4], + skb->data[5], skb->data[6]); + break; + + default: + printk(KERN_WARNING "x25: received unknown %02X with LCI 000\n", + frametype); + break; } if (nb->state == X25_LINK_STATE_3) @@ -193,18 +192,18 @@ void x25_transmit_clear_request(struct x25_neigh *nb, unsigned int lci, void x25_transmit_link(struct sk_buff *skb, struct x25_neigh *nb) { switch (nb->state) { - case X25_LINK_STATE_0: - skb_queue_tail(&nb->queue, skb); - nb->state = X25_LINK_STATE_1; - x25_establish_link(nb); - break; - case X25_LINK_STATE_1: - case X25_LINK_STATE_2: - skb_queue_tail(&nb->queue, skb); - break; - case X25_LINK_STATE_3: - x25_send_frame(skb, nb); - break; + case X25_LINK_STATE_0: + skb_queue_tail(&nb->queue, skb); + nb->state = X25_LINK_STATE_1; + x25_establish_link(nb); + break; + case X25_LINK_STATE_1: + case X25_LINK_STATE_2: + skb_queue_tail(&nb->queue, skb); + break; + case X25_LINK_STATE_3: + x25_send_frame(skb, nb); + break; } } @@ -214,14 +213,14 @@ void x25_transmit_link(struct sk_buff *skb, struct x25_neigh *nb) void x25_link_established(struct x25_neigh *nb) { switch (nb->state) { - case X25_LINK_STATE_0: - nb->state = X25_LINK_STATE_2; - break; - case X25_LINK_STATE_1: - x25_transmit_restart_request(nb); - nb->state = X25_LINK_STATE_2; - x25_start_t20timer(nb); - break; + case X25_LINK_STATE_0: + nb->state = X25_LINK_STATE_2; + break; + case X25_LINK_STATE_1: + x25_transmit_restart_request(nb); + nb->state = X25_LINK_STATE_2; + x25_start_t20timer(nb); + break; } } diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index dc20cf12f39..24a342ebc7f 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -126,32 +126,30 @@ void x25_write_internal(struct sock *sk, int frametype) * Adjust frame size. */ switch (frametype) { - case X25_CALL_REQUEST: - len += 1 + X25_ADDR_LEN + X25_MAX_FAC_LEN + - X25_MAX_CUD_LEN; - break; - case X25_CALL_ACCEPTED: /* fast sel with no restr on resp */ - if(x25->facilities.reverse & 0x80) { - len += 1 + X25_MAX_FAC_LEN + X25_MAX_CUD_LEN; - } else { - len += 1 + X25_MAX_FAC_LEN; - } - break; - case X25_CLEAR_REQUEST: - case X25_RESET_REQUEST: - len += 2; - break; - case X25_RR: - case X25_RNR: - case X25_REJ: - case X25_CLEAR_CONFIRMATION: - case X25_INTERRUPT_CONFIRMATION: - case X25_RESET_CONFIRMATION: - break; - default: - printk(KERN_ERR "X.25: invalid frame type %02X\n", - frametype); - return; + case X25_CALL_REQUEST: + len += 1 + X25_ADDR_LEN + X25_MAX_FAC_LEN + X25_MAX_CUD_LEN; + break; + case X25_CALL_ACCEPTED: /* fast sel with no restr on resp */ + if (x25->facilities.reverse & 0x80) { + len += 1 + X25_MAX_FAC_LEN + X25_MAX_CUD_LEN; + } else { + len += 1 + X25_MAX_FAC_LEN; + } + break; + case X25_CLEAR_REQUEST: + case X25_RESET_REQUEST: + len += 2; + break; + case X25_RR: + case X25_RNR: + case X25_REJ: + case X25_CLEAR_CONFIRMATION: + case X25_INTERRUPT_CONFIRMATION: + case X25_RESET_CONFIRMATION: + break; + default: + printk(KERN_ERR "X.25: invalid frame type %02X\n", frametype); + return; } if ((skb = alloc_skb(len, GFP_ATOMIC)) == NULL) @@ -276,20 +274,20 @@ int x25_decode(struct sock *sk, struct sk_buff *skb, int *ns, int *nr, int *q, *ns = *nr = *q = *d = *m = 0; switch (frame[2]) { - case X25_CALL_REQUEST: - case X25_CALL_ACCEPTED: - case X25_CLEAR_REQUEST: - case X25_CLEAR_CONFIRMATION: - case X25_INTERRUPT: - case X25_INTERRUPT_CONFIRMATION: - case X25_RESET_REQUEST: - case X25_RESET_CONFIRMATION: - case X25_RESTART_REQUEST: - case X25_RESTART_CONFIRMATION: - case X25_REGISTRATION_REQUEST: - case X25_REGISTRATION_CONFIRMATION: - case X25_DIAGNOSTIC: - return frame[2]; + case X25_CALL_REQUEST: + case X25_CALL_ACCEPTED: + case X25_CLEAR_REQUEST: + case X25_CLEAR_CONFIRMATION: + case X25_INTERRUPT: + case X25_INTERRUPT_CONFIRMATION: + case X25_RESET_REQUEST: + case X25_RESET_CONFIRMATION: + case X25_RESTART_REQUEST: + case X25_RESTART_CONFIRMATION: + case X25_REGISTRATION_REQUEST: + case X25_REGISTRATION_CONFIRMATION: + case X25_DIAGNOSTIC: + return frame[2]; } if (x25->neighbour->extended) { diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 9bec2e8a838..94fdcc7f103 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -50,7 +50,7 @@ static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family); static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); -static int xfrm_bundle_ok(struct xfrm_dst *xdst, int family); +static int xfrm_bundle_ok(struct xfrm_dst *xdst); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, @@ -1497,7 +1497,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto free_dst; /* Copy neighbour for reachability confirmation */ - dst0->neighbour = neigh_clone(dst->neighbour); + dst_set_neighbour(dst0, neigh_clone(dst_get_neighbour(dst))); xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len); xfrm_init_pmtu(dst_prev); @@ -2241,7 +2241,7 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) static int stale_bundle(struct dst_entry *dst) { - return !xfrm_bundle_ok((struct xfrm_dst *)dst, AF_UNSPEC); + return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) @@ -2313,7 +2313,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) * still valid. */ -static int xfrm_bundle_ok(struct xfrm_dst *first, int family) +static int xfrm_bundle_ok(struct xfrm_dst *first) { struct dst_entry *dst = &first->u.dst; struct xfrm_dst *last; @@ -2385,6 +2385,11 @@ static unsigned int xfrm_default_mtu(const struct dst_entry *dst) return dst_mtu(dst->path); } +static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, const void *daddr) +{ + return dst_neigh_lookup(dst->path, daddr); +} + int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { struct net *net; @@ -2410,6 +2415,8 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) dst_ops->link_failure = xfrm_link_failure; + if (likely(dst_ops->neigh_lookup == NULL)) + dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(afinfo->garbage_collect == NULL)) afinfo->garbage_collect = __xfrm_garbage_collect; xfrm_policy_afinfo[afinfo->family] = afinfo; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 47f1b8638df..b11ea692bd7 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -265,7 +265,7 @@ static void xfrm_replay_advance_bmp(struct xfrm_state *x, __be32 net_seq) bitnr = bitnr & 0x1F; replay_esn->bmp[nr] |= (1U << bitnr); } else { - nr = replay_esn->replay_window >> 5; + nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; @@ -471,7 +471,7 @@ static void xfrm_replay_advance_esn(struct xfrm_state *x, __be32 net_seq) bitnr = bitnr & 0x1F; replay_esn->bmp[nr] |= (1U << bitnr); } else { - nr = replay_esn->replay_window >> 5; + nr = (replay_esn->replay_window - 1) >> 5; for (i = 0; i <= nr; i++) replay_esn->bmp[i] = 0; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d70f85eb786..9414b9c5b1e 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1345,6 +1345,8 @@ out: xfrm_state_check_expire(x1); err = 0; + x->km.state = XFRM_STATE_DEAD; + __xfrm_state_put(x); } spin_unlock_bh(&x1->lock); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c658cb3bc7c..0256b8a0a7c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2299,7 +2299,8 @@ static int xfrm_user_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (link->dump == NULL) return -EINVAL; - return netlink_dump_start(net->xfrm.nlsk, skb, nlh, link->dump, link->done); + return netlink_dump_start(net->xfrm.nlsk, skb, nlh, + link->dump, link->done, 0); } err = nlmsg_parse(nlh, xfrm_msg_min[type], attrs, XFRMA_MAX, |