diff options
Diffstat (limited to 'net')
280 files changed, 8740 insertions, 5402 deletions
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index c7a581a..d24c464 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> @@ -149,13 +151,13 @@ 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; } @@ -205,7 +207,7 @@ int register_vlan_dev(struct net_device *dev) grp->nr_vlans++; if (ngrp) { - if (ops->ndo_vlan_rx_register) + if (ops->ndo_vlan_rx_register && (real_dev->features & NETIF_F_HW_VLAN_RX)) ops->ndo_vlan_rx_register(real_dev, ngrp); rcu_assign_pointer(real_dev->vlgrp, ngrp); } @@ -344,13 +346,12 @@ 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 +375,7 @@ 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_core.c b/net/8021q/vlan_core.c index 41495dc2..fcc6846 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; @@ -31,22 +56,8 @@ 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; @@ -89,18 +100,13 @@ gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, } EXPORT_SYMBOL(vlan_gro_frags); -static struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) +static struct sk_buff *vlan_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 +167,7 @@ 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 f247f5b..d8f45ba 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); @@ -165,7 +167,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb, u64_stats_update_begin(&stats->syncp); stats->tx_packets++; stats->tx_bytes += len; - u64_stats_update_begin(&stats->syncp); + u64_stats_update_end(&stats->syncp); } else { this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped); } @@ -586,9 +588,14 @@ 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; + + if (old_features & NETIF_F_SOFT_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 d940c49..d34b6da 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/TUNABLE b/net/TUNABLE deleted file mode 100644 index 9913211..0000000 --- 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 50dce79..1acc695 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 956a530..b1fe7c3 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/mpc.c b/net/atm/mpc.c index 3ccca42..aa972409f 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 e9aced0..db4a11c 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/hard-interface.c b/net/batman-adv/hard-interface.c index 55b5def..db7aacf 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -563,7 +563,7 @@ static int hard_if_event(struct notifier_block *this, break; default: break; - }; + } hardif_put: hardif_free_ref(hard_iface); diff --git a/net/bluetooth/Kconfig b/net/bluetooth/Kconfig index 6ae5ec5..bfb3dc0 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 f04fe9a..9b67f3d 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 744233c..040f67b 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 3163330..fa48c0b 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) { @@ -447,14 +498,23 @@ 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 +557,7 @@ 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 +608,8 @@ 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 +670,11 @@ 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 +693,7 @@ 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 +736,7 @@ 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 +745,10 @@ 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 815269b..b18db56 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> @@ -59,6 +60,8 @@ static void hci_tx_task(unsigned long arg); static DEFINE_RWLOCK(hci_task_lock); +static int enable_smp; + /* HCI device list */ LIST_HEAD(hci_dev_list); DEFINE_RWLOCK(hci_dev_list_lock); @@ -1202,6 +1205,177 @@ 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(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(hdev); + return err; +} + +int hci_blacklist_del(struct hci_dev *hdev, bdaddr_t *bdaddr) +{ + struct bdaddr_list *entry; + int err = 0; + + hci_dev_lock(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(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; +} + +static struct crypto_blkcipher *alloc_cypher(void) +{ + if (enable_smp) + return crypto_alloc_blkcipher("ecb(aes)", 0, CRYPTO_ALG_ASYNC); + + return ERR_PTR(-ENOTSUPP); +} + /* Register HCI device */ int hci_register_dev(struct hci_dev *hdev) { @@ -1268,6 +1442,10 @@ 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 +1460,11 @@ int hci_register_dev(struct hci_dev *hdev) if (!hdev->workqueue) goto nomem; + hdev->tfm = alloc_cypher(); + 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 +1513,9 @@ 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 +1526,7 @@ 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 +1535,7 @@ 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 +1707,7 @@ int hci_recv_fragment(struct hci_dev *hdev, int type, void *data, int count) data += (count - rem); count = rem; - }; + } return rem; } @@ -1554,7 +1742,7 @@ int hci_recv_stream_fragment(struct hci_dev *hdev, void *data, int count) data += (count - rem); count = rem; - }; + } return rem; } @@ -1891,7 +2079,7 @@ 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 +2218,7 @@ 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]; @@ -2164,3 +2352,6 @@ static void hci_cmd_task(unsigned long arg) } } } + +module_param(enable_smp, bool, 0644); +MODULE_PARM_DESC(enable_smp, "Enable SMP support (LE only)"); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index f13ddbf..ac2c5e8 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -477,14 +477,16 @@ 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 */ @@ -839,6 +841,57 @@ 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_cs_inquiry(struct hci_dev *hdev, __u8 status) { BT_DBG("%s status 0x%x", hdev->name, status); @@ -1207,16 +1260,23 @@ 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 +1520,58 @@ 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 +1622,7 @@ 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; } @@ -1814,6 +1882,18 @@ 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; + default: BT_DBG("%s opcode 0x%x", hdev->name, opcode); break; @@ -1892,6 +1972,10 @@ 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 +2740,8 @@ 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 +2754,7 @@ 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 +2767,49 @@ 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_conn *conn; + + 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)); + + memset(&cp, 0, sizeof(cp)); + cp.handle = cpu_to_le16(conn->handle); + memcpy(cp.ltk, conn->ltk, sizeof(conn->ltk)); + + hci_send_cmd(hdev, HCI_OP_LE_LTK_REPLY, sizeof(cp), &cp); + + 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 +2821,14 @@ 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; } diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 295e4a8..ff02cf5 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/l2cap_core.c b/net/bluetooth/l2cap_core.c index a86f9ba..9ec9c8c 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -54,6 +54,7 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> #include <net/bluetooth/l2cap.h> +#include <net/bluetooth/smp.h> int disable_ertm; @@ -62,18 +63,34 @@ static u8 l2cap_fixed_chan[8] = { 0x02, }; static struct workqueue_struct *_busy_wq; -LIST_HEAD(chan_list); -DEFINE_RWLOCK(chan_list_lock); +static LIST_HEAD(chan_list); +static DEFINE_RWLOCK(chan_list_lock); static void l2cap_busy_work(struct work_struct *work); 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 +221,62 @@ 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 + 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 +291,12 @@ 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 +306,11 @@ 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 +318,7 @@ 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 +329,7 @@ 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 +341,20 @@ 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 +363,13 @@ 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 +381,8 @@ 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); @@ -313,9 +390,9 @@ 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); @@ -327,11 +404,86 @@ 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 +523,7 @@ 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 +545,7 @@ 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 +560,8 @@ 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 +569,11 @@ 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 +584,11 @@ 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 +609,16 @@ 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 +629,7 @@ 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 +647,7 @@ 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 +683,7 @@ 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 +694,9 @@ 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 +704,7 @@ 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 +722,12 @@ 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) || @@ -587,14 +736,13 @@ 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); + l2cap_chan_close(chan, ECONNRESET); read_lock_bh(&conn->chan_lock); bh_unlock_sock(sk); continue; @@ -604,12 +752,12 @@ 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); @@ -623,7 +771,7 @@ static void l2cap_conn_start(struct l2cap_conn *conn) 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 +783,13 @@ 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 +813,7 @@ 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 +857,16 @@ 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 +874,9 @@ 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 +885,23 @@ 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 +919,15 @@ 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 +965,45 @@ 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 +1035,10 @@ 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 +1047,6 @@ 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); @@ -900,13 +1068,13 @@ 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) { /* Exact match. */ if (!bacmp(&bt_sk(sk)->src, src)) { - read_unlock_bh(&chan_list_lock); + read_unlock(&chan_list_lock); return c; } @@ -967,15 +1135,14 @@ 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 +1202,7 @@ 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 +1217,9 @@ 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 +1241,7 @@ 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 +1256,7 @@ 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 +1310,8 @@ 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 +1329,10 @@ 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 +1350,9 @@ 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 +1365,7 @@ 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 +1404,9 @@ 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 +1614,83 @@ 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 +1704,7 @@ 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 +1714,7 @@ 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); @@ -1690,7 +1909,7 @@ 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 +1956,7 @@ 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 +1979,7 @@ 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 +2031,7 @@ 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 +2051,7 @@ 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 +2084,14 @@ 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 +2108,7 @@ 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 +2121,7 @@ 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 +2136,7 @@ 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 +2178,7 @@ 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 +2240,9 @@ 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++; @@ -2124,17 +2342,11 @@ 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 +2354,12 @@ 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 +2371,29 @@ 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 +2424,10 @@ 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 +2465,29 @@ 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 +2501,12 @@ 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; } @@ -2323,7 +2530,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, struct l2cap_cmd_hdr sk = chan->sk; - if (sk->sk_state != BT_CONFIG) { + if (chan->state != BT_CONFIG) { struct l2cap_cmd_rej rej; rej.reason = cpu_to_le16(0x0002); @@ -2366,13 +2573,13 @@ 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 +2591,8 @@ 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 +2657,7 @@ 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 +2665,12 @@ 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 +2712,9 @@ 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 +2722,7 @@ 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 +2746,9 @@ 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 +2756,7 @@ 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; } @@ -2858,18 +3064,18 @@ 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 +3131,13 @@ 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 +3156,12 @@ 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) @@ -2974,13 +3176,13 @@ 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)) { + if (!test_bit(CONN_SAR_RETRY, &chan->conn_state)) { chan->partial_sdu_len += skb->len; if (chan->partial_sdu_len > chan->imtu) @@ -2994,19 +3196,19 @@ static int l2cap_ertm_reassembly_sdu(struct l2cap_chan *chan, struct sk_buff *sk _skb = skb_clone(chan->sdu, GFP_ATOMIC); if (!_skb) { - chan->conn_state |= L2CAP_CONN_SAR_RETRY; + set_bit(CONN_SAR_RETRY, &chan->conn_state); 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; + set_bit(CONN_SAR_RETRY, &chan->conn_state); return err; } - chan->conn_state &= ~L2CAP_CONN_SAR_RETRY; - chan->conn_state &= ~L2CAP_CONN_SAR_SDU; + clear_bit(CONN_SAR_RETRY, &chan->conn_state); + clear_bit(CONN_SAR_SDU, &chan->conn_state); kfree_skb(chan->sdu); break; @@ -3042,7 +3244,7 @@ static int l2cap_try_push_rx_skb(struct l2cap_chan *chan) chan->buffer_seq = (chan->buffer_seq + 1) % 64; } - if (!(chan->conn_state & L2CAP_CONN_RNR_SENT)) + if (!test_bit(CONN_RNR_SENT, &chan->conn_state)) goto done; control = chan->buffer_seq << L2CAP_CTRL_REQSEQ_SHIFT; @@ -3050,14 +3252,14 @@ static int l2cap_try_push_rx_skb(struct l2cap_chan *chan) l2cap_send_sframe(chan, control); chan->retry_count = 1; - del_timer(&chan->retrans_timer); - __mod_monitor_timer(); + __clear_retrans_timer(chan); + __set_monitor_timer(chan); - chan->conn_state |= L2CAP_CONN_WAIT_F; + set_bit(CONN_WAIT_F, &chan->conn_state); done: - chan->conn_state &= ~L2CAP_CONN_LOCAL_BUSY; - chan->conn_state &= ~L2CAP_CONN_RNR_SENT; + clear_bit(CONN_LOCAL_BUSY, &chan->conn_state); + clear_bit(CONN_RNR_SENT, &chan->conn_state); BT_DBG("chan %p, Exit local busy", chan); @@ -3115,7 +3317,7 @@ static int l2cap_push_rx_skb(struct l2cap_chan *chan, struct sk_buff *skb, u16 c { int sctrl, err; - if (chan->conn_state & L2CAP_CONN_LOCAL_BUSY) { + if (test_bit(CONN_LOCAL_BUSY, &chan->conn_state)) { bt_cb(skb)->sar = control >> L2CAP_CTRL_SAR_SHIFT; __skb_queue_tail(&chan->busy_q, skb); return l2cap_try_push_rx_skb(chan); @@ -3132,7 +3334,7 @@ static int l2cap_push_rx_skb(struct l2cap_chan *chan, struct sk_buff *skb, u16 c /* Busy Condition */ BT_DBG("chan %p, Enter local busy", chan); - chan->conn_state |= L2CAP_CONN_LOCAL_BUSY; + set_bit(CONN_LOCAL_BUSY, &chan->conn_state); bt_cb(skb)->sar = control >> L2CAP_CTRL_SAR_SHIFT; __skb_queue_tail(&chan->busy_q, skb); @@ -3140,9 +3342,9 @@ static int l2cap_push_rx_skb(struct l2cap_chan *chan, struct sk_buff *skb, u16 c sctrl |= L2CAP_SUPER_RCV_NOT_READY; l2cap_send_sframe(chan, sctrl); - chan->conn_state |= L2CAP_CONN_RNR_SENT; + set_bit(CONN_RNR_SENT, &chan->conn_state); - del_timer(&chan->ack_timer); + __clear_ack_timer(chan); queue_work(_busy_wq, &chan->busy_work); @@ -3161,19 +3363,19 @@ 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 +3396,13 @@ 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 +3416,12 @@ 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 +3429,7 @@ 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); } @@ -3310,11 +3512,11 @@ 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; @@ -3333,10 +3535,10 @@ 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 (test_bit(CONN_SREJ_SENT, &chan->conn_state)) { struct srej_list *first; first = list_first_entry(&chan->srej_l, @@ -3350,7 +3552,7 @@ 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 +3581,7 @@ 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); @@ -3390,18 +3592,18 @@ static inline int l2cap_data_channel_iframe(struct l2cap_chan *chan, u16 rx_cont __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); @@ -3413,13 +3615,11 @@ expected: return 0; 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 +3641,31 @@ 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 +3678,19 @@ 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 +3699,32 @@ 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 +3735,15 @@ 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 +3760,11 @@ 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 +3863,6 @@ 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 +3874,10 @@ 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 +3890,7 @@ 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 +3962,13 @@ 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 +3995,13 @@ 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 +4046,11 @@ 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 +4074,7 @@ 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)) { @@ -3919,7 +4118,7 @@ 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; @@ -3939,20 +4138,18 @@ static int l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason) 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 +4170,72 @@ 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); + } + bh_unlock_sock(sk); continue; } - if (!status && (sk->sk_state == BT_CONNECTED || - sk->sk_state == BT_CONFIG)) { + if (test_bit(CONF_CONNECT_PEND, &chan->conf_state)) { + bh_unlock_sock(sk); + continue; + } + + 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; + 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 +4371,10 @@ 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); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 18dc988..39082d4 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); @@ -453,8 +416,8 @@ 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; } @@ -484,6 +447,21 @@ 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 +512,7 @@ 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 +562,8 @@ 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 +579,8 @@ 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 +600,20 @@ 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 +654,23 @@ 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 +684,6 @@ 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 +698,12 @@ 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; - - } 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; - } + err = l2cap_chan_send(chan, msg, len); -done: release_sock(sk); return err; } @@ -799,7 +733,7 @@ static int l2cap_sock_recvmsg(struct kiocb *iocb, struct socket *sock, struct ms /* 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 +747,6 @@ 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 +764,7 @@ 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, @@ -943,6 +795,49 @@ 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) +{ + struct sock *sk = data; + + return sock_queue_rcv_skb(sk, skb); +} + +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); @@ -951,7 +846,7 @@ static void l2cap_sock_destruct(struct sock *sk) 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 +859,7 @@ 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 +871,27 @@ 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 +902,15 @@ 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 +919,10 @@ 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 +939,13 @@ 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 +954,6 @@ 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 +972,6 @@ 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/mgmt.c b/net/bluetooth/mgmt.c index dae382c..64c0418 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) { @@ -990,7 +990,7 @@ 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: @@ -1092,8 +1092,6 @@ 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); @@ -1101,8 +1099,6 @@ 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: @@ -1112,11 +1108,32 @@ unlock: 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; @@ -1139,6 +1156,25 @@ static int pin_code_reply(struct sock *sk, u16 index, unsigned char *data, 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; @@ -1147,7 +1183,7 @@ 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) @@ -1165,7 +1201,6 @@ 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(""); @@ -1189,17 +1224,7 @@ 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); @@ -1641,6 +1666,70 @@ 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 +1844,12 @@ 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); diff --git a/net/bluetooth/rfcomm/sock.c b/net/bluetooth/rfcomm/sock.c index 386cfaf..8f01e6b 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 42fdffd..cb4fb78 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; diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c new file mode 100644 index 0000000..a36f870 --- /dev/null +++ b/net/bluetooth/smp.c @@ -0,0 +1,534 @@ +/* + 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 *cmd, __u8 authreq) +{ + cmd->io_capability = conn->hcon->io_capability; + cmd->oob_flag = SMP_OOB_NOT_PRESENT; + cmd->max_key_size = SMP_MAX_ENC_KEY_SIZE; + cmd->init_key_dist = 0x00; + cmd->resp_key_dist = 0x00; + cmd->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, &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)); + + memset(hcon->ltk, 0, sizeof(hcon->ltk)); + + 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) { + __le16 ediv; + u8 rand[8]; + + smp_s1(tfm, conn->tk, random, conn->prnd, key); + swap128(key, hcon->ltk); + + memset(hcon->ltk + conn->smp_key_size, 0, + SMP_MAX_ENC_KEY_SIZE - conn->smp_key_size); + + memset(rand, 0, sizeof(rand)); + ediv = 0; + hci_le_start_enc(hcon, ediv, rand, hcon->ltk); + } else { + u8 r[16]; + + 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, hcon->ltk); + + memset(hcon->ltk + conn->smp_key_size, 0, + SMP_MAX_ENC_KEY_SIZE - conn->smp_key_size); + } + + 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, 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 (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; + + build_pairing_cmd(conn, &cp, 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); + } + + hcon->pending_sec_level = sec_level; + set_bit(HCI_CONN_ENCRYPT_PEND, &hcon->pend); + + 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 (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: + case SMP_CMD_MASTER_IDENT: + case SMP_CMD_IDENT_INFO: + case SMP_CMD_IDENT_ADDR_INFO: + case SMP_CMD_SIGN_INFO: + 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; +} diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index a6b2f86..32b8f9f 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 f3ac1e8..f06ee39 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 2f14eaf..2d85ca7 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 3fa1231..56149ec 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -104,10 +104,16 @@ 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 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, }; /* diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index ffb0dc4..6814083 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 682c0fe..7c2fa0a 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 3a66b8c..c23979e 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 649ebac..8656909 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> @@ -139,17 +139,14 @@ static void close_work(struct work_struct *work) struct chnl_net *dev = NULL; struct list_head *list_node; struct list_head *_tmp; - /* May be called with or without RTNL lock held */ - int islocked = rtnl_is_locked(); - if (!islocked) - rtnl_lock(); + + rtnl_lock(); list_for_each_safe(list_node, _tmp, &chnl_net_list) { dev = list_entry(list_node, struct chnl_net, list_field); if (dev->state == CAIF_SHUTDOWN) dev_close(dev->netdev); } - if (!islocked) - rtnl_unlock(); + rtnl_unlock(); } static DECLARE_WORK(close_worker, close_work); diff --git a/net/can/af_can.c b/net/can/af_can.c index 094fc53..8ce926d 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 184a657..d6c8ae5 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/crypto.c b/net/ceph/crypto.c index 5a8009c..85f3bc0 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 6ea2b89..9cb627a 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -1144,6 +1144,13 @@ 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 +1233,8 @@ 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 +1736,7 @@ 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; } diff --git a/net/core/dev.c b/net/core/dev.c index c7e305d..9ca1514 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)); } /* @@ -2096,6 +2106,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, { const struct net_device_ops *ops = dev->netdev_ops; int rc = NETDEV_TX_OK; + unsigned int skb_len; if (likely(!skb->next)) { u32 features; @@ -2146,8 +2157,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, } } + skb_len = skb->len; rc = ops->ndo_start_xmit(skb, dev); - trace_net_dev_xmit(skb, rc); + trace_net_dev_xmit(skb, rc, dev, skb_len); if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; @@ -2167,8 +2179,9 @@ gso: if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(nskb); + skb_len = nskb->len; rc = ops->ndo_start_xmit(nskb, dev); - trace_net_dev_xmit(nskb, rc); + trace_net_dev_xmit(nskb, rc, dev, skb_len); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) goto out_kfree_gso_skb; @@ -2529,7 +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; @@ -3111,7 +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; @@ -5475,11 +5488,12 @@ 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. + /* Enable GSO, GRO and NETIF_F_HIGHDMA for vlans by default, + * vlan_dev_fix_features() will do the features check, + * so NETIF_F_HIGHDMA feature is enabled only if supported + * by underlying device. */ - dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + dev->vlan_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_HIGHDMA); ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); @@ -5864,8 +5878,6 @@ 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); @@ -5929,9 +5941,6 @@ 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); @@ -6175,6 +6184,11 @@ 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(); @@ -6261,29 +6275,23 @@ 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 9ccca03..6135f36 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -190,7 +190,8 @@ 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); @@ -243,7 +244,8 @@ again: 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); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index fd14116..b7c12a6 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) @@ -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 008dc70..e7ab0c0 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 799f06e..ceb505b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2909,12 +2909,13 @@ 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 11b98bc..33d2a1f 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1179,9 +1179,14 @@ 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 +1201,13 @@ 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 +1335,5 @@ 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 7f1bb2a..52380b1 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 6c6b86d..5bbdbf0 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 2d7d6d4..adf84dd 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 abd936d..99d9e95 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 46cbd28..a9577a2 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 +674,11 @@ 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; + } + n = skb + 1; if (skb->fclone == SKB_FCLONE_ORIG && n->fclone == SKB_FCLONE_UNAVAILABLE) { @@ -731,6 +796,12 @@ 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(n); + goto out; + } + } 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 +859,6 @@ 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 +889,11 @@ 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; + } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) get_page(skb_shinfo(skb)->frags[i].page); @@ -853,6 +928,8 @@ adjust_others: atomic_set(&skb_shinfo(skb)->dataref, 1); return 0; +nofrags: + kfree(data); nodata: return -ENOMEM; } @@ -1354,6 +1431,7 @@ 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 6e81978..76c4031 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 @@ -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 7e7ca37..98a5264 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 3609eac..6a015f2 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 nla_put_failure; + + 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 36479ca..48b585a 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 fadecd2..0462040 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 e9985da..f585d33 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 4222e7a..51d5fe5 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 fab108e..dede3ed 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 ea3b6ee..19acd00 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 cf26ac7..ba4face 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 1c74ed3..2bd8e53 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 602dade..03eb226 100644 --- a/net/decnet/dn_neigh.c +++ b/net/decnet/dn_neigh.c @@ -404,13 +404,13 @@ 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 b430549..73fa268 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 74544bc..fceb86c 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -495,11 +495,11 @@ 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 +652,38 @@ 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 +691,11 @@ 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); } } @@ -1419,20 +1419,20 @@ make_route: rt->dst.neighbour = 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 +1841,11 @@ 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 bd0a52d..cd0354e 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 64a7f39..69975e0 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 28f8b5e..02e75d1 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 45f7411..9bd1061 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 a1d9f37..1c1f26c 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/ieee802154/af_ieee802154.c b/net/ieee802154/af_ieee802154.c index 6df6ecf4..40e606f 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 1a3334c..faecf64 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 ed0eab3..c64a38d 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 cc14631..1b745d4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -465,6 +465,11 @@ 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) { + err = -EAFNOSUPPORT; + goto out; + } + chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr); /* Not specified by any standard per-se, however it breaks too @@ -673,6 +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))); @@ -1434,11 +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; } @@ -1452,28 +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; } @@ -1485,25 +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/devinet.c b/net/ipv4/devinet.c index 0d4a184..37b3c18 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 2252471..92fc5f6 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/gre.c b/net/ipv4/gre.c index c6933f2..9dbe108 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/inet_diag.c b/net/ipv4/inet_diag.c index 6ffe94c..389a2e6 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/inetpeer.c b/net/ipv4/inetpeer.c index ce616d9..dafbf2c 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 +317,96 @@ 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); + return family == AF_INET ? &v4_peers : &v6_peers; } -static struct inet_peer_base *peer_to_base(struct inet_peer *p) +/* 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) { - return family_to_base(p->daddr.family); -} - -/* May be called with local BH enabled. */ -static int cleanup_once(unsigned long ttl, struct inet_peer __rcu **stack[PEER_MAXDEPTH]) -{ - 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; + struct inet_peer *p, *gchead = NULL; + __u32 delta, ttl; + int cnt = 0; - p = list_first_entry(&unused_peers.list, struct inet_peer, unused); + 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); delta = (__u32)jiffies - p->dtime; - - if (delta < ttl) { - /* Do not prune fresh entries. */ - spin_unlock_bh(&unused_peers.lock); - return -1; + if (atomic_read(&p->refcnt) == 0 && 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 __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) @@ -506,11 +416,17 @@ 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) { @@ -525,7 +441,6 @@ 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 +449,14 @@ 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; + atomic_dec(&p->refcnt); } EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 0ad6035..0e0ab98 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_input.c b/net/ipv4/ip_input.c index c8f48ef..073a9b0 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_options.c b/net/ipv4/ip_options.c index c3118e1..ec93335 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <linux/types.h> #include <asm/uaccess.h> +#include <asm/unaligned.h> #include <linux/skbuff.h> #include <linux/ip.h> #include <linux/icmp.h> @@ -350,7 +351,7 @@ int ip_options_compile(struct net *net, goto error; } if (optptr[2] <= optlen) { - __be32 *timeptr = NULL; + unsigned char *timeptr = NULL; if (optptr[2]+3 > optptr[1]) { pp_ptr = optptr + 2; goto error; @@ -359,7 +360,7 @@ int ip_options_compile(struct net *net, case IPOPT_TS_TSONLY: opt->ts = optptr - iph; if (skb) - timeptr = (__be32*)&optptr[optptr[2]-1]; + timeptr = &optptr[optptr[2]-1]; opt->ts_needtime = 1; optptr[2] += 4; break; @@ -371,7 +372,7 @@ int ip_options_compile(struct net *net, opt->ts = optptr - iph; if (rt) { memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4); - timeptr = (__be32*)&optptr[optptr[2]+3]; + timeptr = &optptr[optptr[2]+3]; } opt->ts_needaddr = 1; opt->ts_needtime = 1; @@ -389,7 +390,7 @@ int ip_options_compile(struct net *net, if (inet_addr_type(net, addr) == RTN_UNICAST) break; if (skb) - timeptr = (__be32*)&optptr[optptr[2]+3]; + timeptr = &optptr[optptr[2]+3]; } opt->ts_needtime = 1; optptr[2] += 8; @@ -403,10 +404,10 @@ int ip_options_compile(struct net *net, } if (timeptr) { struct timespec tv; - __be32 midtime; + u32 midtime; getnstimeofday(&tv); - midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC); - memcpy(timeptr, &midtime, sizeof(__be32)); + midtime = (tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC; + put_unaligned_be32(midtime, timeptr); opt->is_changed = 1; } } else { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 98af369..54119d5 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -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; @@ -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); @@ -825,12 +825,10 @@ 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); @@ -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 ab7e554..472a8c4 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 30a7763..aae2bd8 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 4614bab..2e97e3e 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 d2c1311..5c9b9d9 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 7647438..24e556e 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 d609ac3..db8d22d 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 d2ed9dc..9931152 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 1ff79e5..51f13f8 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 af6e9c7..2b57e52 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 5a03c02..de9da21 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 7404bde..ab5b27a 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 f3a9b42..9bb1b8a 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 9c71b27..3346de5 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 99cfa28..ebc5f88 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 21c3042..733c9ab 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 8812a02..076b7c8 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 7317bdf..a6e606e 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 9aaa671..39b403f 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 c9893d4..0852678 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 52b0b95..a8ccd9b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1316,6 +1316,23 @@ 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 +1348,8 @@ 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 +1439,20 @@ 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 +1542,10 @@ 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 +1568,11 @@ 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) @@ -1612,13 +1626,14 @@ 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 +1664,8 @@ 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 +1779,7 @@ 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 +1902,7 @@ 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; @@ -2775,7 +2781,8 @@ 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 +2830,16 @@ 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 +3303,7 @@ 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 2646149..92bb943 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 57d0752..69fd720 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_input.c b/net/ipv4/tcp_input.c index bef9f04..ea0d218 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 a7d6671..955b8e6 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 80b1f80..d2fe4e0 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 abca870..95e0d3b8 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; } diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 2d51840..327a617 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 981e43e..fc5368a 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 498b927..fc6d377 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -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 c8993e5..2d8ddba 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 b7919f9..3b5669a 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 4076a0b..3030bdf 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -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/ip6mr.c b/net/ipv6/ip6mr.c index 82a8099..705c828 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/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 413ab07..2493948 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 c8af58b..4111050 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 1df3c8b..7c05e7e 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 cc7313b..6a79f308 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 de2b1de..f032d77 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -228,9 +228,10 @@ 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)); @@ -1042,7 +1043,7 @@ 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; @@ -1062,14 +1063,6 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, 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 +1207,7 @@ 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 +1237,7 @@ 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); @@ -1734,7 +1727,7 @@ static struct rt6_info * ip6_rt_copy(struct rt6_info *ort) { 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; @@ -2013,7 +2006,7 @@ 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 +2018,7 @@ 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; @@ -2925,9 +2918,9 @@ 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/syncookies.c b/net/ipv6/syncookies.c index 8b9644a..89d5bf8 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 d1fd287..78aa534 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 41f8c9c..328985c 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; } diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index cc61697..c24f25a 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 3c17540..b65d66e 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 25cc2e6..3eca35f 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 3647753..e71e85b 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 7ed3af9..ba1a3fc 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 6130f9d..7791176 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 8ee1ff6..e8d5f44 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 b8af74a..8b61cf0 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 9715e6e..f06947c 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 9d9af46..285ccd6 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 8f92cf8..1e733e9 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 b8dbae8..7613013 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 b6466e7..d21e7eb 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 d5d8d55..956b7e4 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 21904a0..2ec1af5 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/agg-rx.c b/net/mac80211/agg-rx.c index 9c0d76c..ebadb9a 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 be70c70..9fe22cc 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -674,8 +674,11 @@ 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 +1557,19 @@ 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, @@ -2134,6 +2150,7 @@ 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, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index eebf7a6..0e7e426 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, diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index ed9edcb..3cb6795 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), diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index 591add2..7cfc286 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 421eaa6..56c24ca 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 2025af5..25c15cc 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -775,9 +775,6 @@ 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 +1350,12 @@ 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 49d4f86..dee30ae 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -1145,6 +1145,10 @@ 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 31afd712..f825e2f 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -101,11 +101,6 @@ static int ieee80211_key_enable_hw_accel(struct ieee80211_key *key) if (!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--; - return 0; } @@ -161,10 +156,6 @@ 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) @@ -403,10 +394,8 @@ static void __ieee80211_key_destroy(struct ieee80211_key *key) ieee80211_aes_key_free(key->u.ccmp.tfm); if (key->conf.cipher == WLAN_CIPHER_SUITE_AES_CMAC) ieee80211_aes_cmac_key_free(key->u.aes_cmac.tfm); - if (key->local) { + if (key->local) ieee80211_debugfs_key_remove(key); - key->local->crypto_tx_tailroom_needed_cnt--; - } kfree(key); } @@ -468,8 +457,6 @@ int ieee80211_key_link(struct ieee80211_key *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); @@ -511,12 +498,8 @@ void ieee80211_enable_keys(struct ieee80211_sub_if_data *sdata) mutex_lock(&sdata->local->key_mtx); - sdata->local->crypto_tx_tailroom_needed_cnt = 0; - - list_for_each_entry(key, &sdata->key_list, list) { - sdata->local->crypto_tx_tailroom_needed_cnt++; + list_for_each_entry(key, &sdata->key_list, list) ieee80211_key_enable_hw_accel(key); - } mutex_unlock(&sdata->local->key_mtx); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 4f6b267..b874200 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -760,23 +760,34 @@ void ieee80211_dynamic_ps_enable_work(struct work_struct *work) 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))) { @@ -801,7 +812,8 @@ 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) @@ -1089,6 +1101,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata, local->hw.conf.flags &= ~IEEE80211_CONF_PS; config_changed |= IEEE80211_CONF_CHANGE_PS; } + local->ps_sdata = NULL; ieee80211_hw_config(local, config_changed); @@ -1203,7 +1216,8 @@ 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++; @@ -1288,7 +1302,7 @@ 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; } @@ -2205,6 +2219,7 @@ void ieee80211_sta_restart(struct ieee80211_sub_if_data *sdata) 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 @@ -2651,3 +2666,10 @@ 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 730778a..67839eb 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); @@ -54,6 +76,10 @@ int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan) local->quiescing = false; return err; } + list_for_each_entry(sdata, &local->interfaces, list) { + cancel_work_sync(&sdata->work); + ieee80211_quiesce(sdata); + } goto suspend; } @@ -82,23 +108,8 @@ 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 8adac67..58a8955 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 0f5a833..5d278ec 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 333b511..66a1eeb 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 7fa8c6b..b5493ec 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -338,7 +338,7 @@ static void ieee80211_parse_qos(struct ieee80211_rx_data *rx) 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; } else { /* diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index 27af672..e5a6ea4 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -15,7 +15,6 @@ #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/pm_qos_params.h> -#include <linux/slab.h> #include <net/sch_generic.h> #include <linux/slab.h> #include <net/mac80211.h> @@ -229,6 +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; @@ -252,8 +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; @@ -659,7 +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 @@ -822,10 +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: @@ -837,23 +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); } diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index c6ae871..a06d64e 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]; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 64e0f75..3104c84 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1480,7 +1480,12 @@ static int ieee80211_skb_resize(struct ieee80211_local *local, { int tail_need = 0; - if (may_encrypt && local->crypto_tx_tailroom_needed_cnt) { + /* + * This could be optimised, devices that do full hardware + * crypto (including TKIP MMIC) need no tailroom... But we + * have no drivers for such devices currently. + */ + if (may_encrypt) { tail_need = IEEE80211_ENCRYPT_TAILROOM; tail_need -= skb_tailroom(skb); tail_need = max_t(int, tail_need, 0); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index d3fe2d2..652e569 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); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 28bc084..7a49532f 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 6053b1c..faead6d 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 d2e7f0e..edf8583 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 9dc3b5f..d91c1a2 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -154,7 +154,13 @@ update_iv: 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; } diff --git a/net/netfilter/ipset/Kconfig b/net/netfilter/ipset/Kconfig index 2c5b348..ba36c28 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 5adbdab..6e965ec 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 ba2d166..e3e7399 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 a274300..56096f5 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 6b38eb8..29ba93b 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 8041bef..d7e86ef 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 43bcce2..fa80bb9 100644 --- a/net/netfilter/ipset/ip_set_hash_ip.c +++ b/net/netfilter/ipset/ip_set_hash_ip.c @@ -108,25 +108,32 @@ 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 +164,7 @@ 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 +178,19 @@ 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; @@ -281,20 +289,26 @@ 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 +319,7 @@ 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 +350,7 @@ 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 +442,8 @@ 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 14281b6..bbf51b6 100644 --- a/net/netfilter/ipset/ip_set_hash_ipport.c +++ b/net/netfilter/ipset/ip_set_hash_ipport.c @@ -124,31 +124,40 @@ 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 +201,7 @@ 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 +217,7 @@ 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 +228,21 @@ 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; } @@ -328,26 +340,34 @@ 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 +416,7 @@ 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 +425,11 @@ 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 +513,8 @@ 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 401c8a2..96525f5 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportip.c +++ b/net/netfilter/ipset/ip_set_hash_ipportip.c @@ -127,32 +127,41 @@ 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 +209,7 @@ 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 +225,7 @@ 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 +236,21 @@ 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; } @@ -341,27 +353,35 @@ 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 +434,7 @@ 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 +443,11 @@ 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 +531,8 @@ 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 4743e54..d2d6ab8 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -140,39 +140,51 @@ 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 +198,19 @@ 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 +235,16 @@ 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 +256,50 @@ 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; } @@ -388,34 +421,43 @@ 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 +474,8 @@ 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 +520,7 @@ 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 +529,11 @@ 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 +620,9 @@ 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 +635,7 @@ 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 c4db202..2d4b1f4 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -125,33 +125,44 @@ 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 +172,15 @@ 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 +188,35 @@ 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 @@ -290,28 +325,37 @@ 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 +366,8 @@ 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 +390,7 @@ 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 +471,8 @@ 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 +483,7 @@ 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 0000000..3d6c53b --- /dev/null +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -0,0 +1,762 @@ +/* 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); + int 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); + int 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 */ + +/* Member elements without timeout */ +struct hash_netiface4_elem { + __be32 ip; + const char *iface; + u8 physdev; + u8 cidr; + u16 padding; +}; + +/* Member elements with timeout support */ +struct hash_netiface4_telem { + __be32 ip; + const char *iface; + u8 physdev; + u8 cidr; + u16 padding; + unsigned long timeout; +}; + +static inline bool +hash_netiface4_data_equal(const struct hash_netiface4_elem *ip1, + const struct hash_netiface4_elem *ip2) +{ + return ip1->ip == ip2->ip && + ip1->cidr == ip2->cidr && + 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 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 { + union nf_inet_addr ip; + const char *iface; + u8 physdev; + u8 cidr; + u16 padding; +}; + +struct hash_netiface6_telem { + union nf_inet_addr ip; + const char *iface; + u8 physdev; + u8 cidr; + u16 padding; + unsigned long timeout; +}; + +static inline bool +hash_netiface6_data_equal(const struct hash_netiface6_elem *ip1, + const struct hash_netiface6_elem *ip2) +{ + return ipv6_addr_cmp(&ip1->ip.in6, &ip2->ip.in6) == 0 && + ip1->cidr == ip2->cidr && + 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; + + 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 d2a4036..fe203d1 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -137,38 +137,48 @@ 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 +192,15 @@ 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 +225,47 @@ 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; } @@ -350,33 +383,42 @@ 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 +433,8 @@ 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 +473,7 @@ 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 +482,11 @@ 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 +572,9 @@ 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 +586,7 @@ 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 e9159e9..4d10819 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 23f8c81..bd13d66 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 059af31..fe6cb43 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 bf28ac2..12571fb 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 bfa808f..4f77bb1 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 699c79a..be43fd8 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 508cce9..0fac601 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 af63553..4490a32 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 eb86028..52d073c 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 e292e5b..7ee7215 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 2e1c11f..f7af8b8 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 e17cb7c..6f5801e 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 18b2ce5..f03c2d4 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 b394aa3..4f9390b 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 482e90c..7dec88a 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 0889448..2fd4565 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 d9e2773..8501823 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 cb5a285..93faf6a 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_log.c b/net/netfilter/nfnetlink_log.c index e0ee010..2e7ccbb 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 b83123f..fdd2faf 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -335,7 +335,8 @@ 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) { diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 782e5198..0221d10 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 95b08480..1535e87 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_hl.c b/net/netfilter/xt_hl.c index 7d12221..0039511 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 b3babae..0ec8138 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 9cc4635..fe39f7e 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 9c38658..8efd061 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 6ef64ad..0a4db02 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 1781d99..482fa57 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 44059d0..cd5ddb2 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/packet/af_packet.c b/net/packet/af_packet.c index 925f715..d2294ad1 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; @@ -798,7 +1105,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, getnstimeofday(&ts); h.h2->tp_sec = ts.tv_sec; h.h2->tp_nsec = ts.tv_nsec; - h.h2->tp_vlan_tci = vlan_tx_tag_get(skb); + if (vlan_tx_tag_present(skb)) { + h.h2->tp_vlan_tci = vlan_tx_tag_get(skb); + status |= TP_STATUS_VLAN_VALID; + } else { + h.h2->tp_vlan_tci = 0; + } + h.h2->tp_padding = 0; hdrlen = sizeof(*h.h2); break; default: @@ -969,7 +1282,8 @@ 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; @@ -981,7 +1295,7 @@ 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 { @@ -992,12 +1306,12 @@ 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; @@ -1083,7 +1397,8 @@ 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; @@ -1121,8 +1436,9 @@ 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; @@ -1134,7 +1450,7 @@ static int packet_snd(struct socket *sock, */ if (saddr == NULL) { - ifindex = po->ifindex; + dev = po->prot_hook.dev; proto = po->num; addr = NULL; } else { @@ -1143,13 +1459,12 @@ 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; @@ -1280,14 +1595,15 @@ 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; @@ -1328,14 +1644,10 @@ 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); @@ -1349,6 +1661,8 @@ 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. @@ -1372,24 +1686,18 @@ 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; @@ -1398,9 +1706,7 @@ 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)) @@ -1434,10 +1740,8 @@ 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; } @@ -1465,8 +1769,6 @@ 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; @@ -1531,9 +1833,7 @@ 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); @@ -1675,6 +1975,8 @@ 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, @@ -1725,8 +2027,13 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock, aux.tp_snaplen = skb->len; aux.tp_mac = 0; aux.tp_net = skb_network_offset(skb); - aux.tp_vlan_tci = vlan_tx_tag_get(skb); - + if (vlan_tx_tag_present(skb)) { + aux.tp_vlan_tci = vlan_tx_tag_get(skb); + aux.tp_status |= TP_STATUS_VLAN_VALID; + } else { + aux.tp_vlan_tci = 0; + } + aux.tp_padding = 0; put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux); } @@ -2091,6 +2398,17 @@ 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; } @@ -2189,6 +2507,15 @@ 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; } @@ -2222,15 +2549,15 @@ 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); @@ -2239,11 +2566,8 @@ 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; @@ -2510,10 +2834,8 @@ 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); @@ -2544,11 +2866,9 @@ 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 438accb..d61f676 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 2f6b3fc..637bde5 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 4297d92..edfaaaf 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 fd453dd..cd67026 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 7c4dce8..e590949 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 9015192..04ce3b1 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 c12db66..9556d28 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 6deaa77..8b77edb 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 545d8ee..e40c3c5 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 d58ae5f..aa57e22 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 d5898d0..f8a7954 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 fa5f564..7a02bd1 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 479cae5..d389de1 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 a606025..f2fb67e 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 6cdf9ab..453a734 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 2b4ab4b..b77f5a0 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 9fc211a..60f8f61 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 961386e..102fc21 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 762b027..001d1b3 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 7affe9a..10d3aed 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 b3b9b32..6fb3f5a 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 a34a22d..73e0a3a 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 5f6f0c7..35dbbe9 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 bb2c523..a69d44f 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 8be8872..ea1f70b 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 32a3351..f84fdc3 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 8ec0139..6994214 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 26e7bc4..389af15 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 a9079053..13ab66e 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 402c44b..be4505e 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 36667fa..dbe1992 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 3b93fc0c..939b627 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/sch_api.c b/net/sched/sch_api.c index 6b86276..dca6c1a5 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 3f08158..e25e490 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 06afbae..3422b25 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 b1721d7..d253c16 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -189,15 +189,17 @@ static inline int qdisc_restart(struct Qdisc *q) void __qdisc_run(struct Qdisc *q) { - unsigned long start_time = jiffies; + int quota = weight_p; + int work = 0; while (qdisc_restart(q)) { + work++; /* - * 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 (work >= quota || need_resched()) { __netif_schedule(q); break; } @@ -251,9 +253,8 @@ 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 69c35f6..eb3b9a8 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 b6ea6af..4536ee6 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/sctp/associola.c b/net/sctp/associola.c index 525f97c..dc16b90 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); @@ -444,15 +446,11 @@ void sctp_association_free(struct sctp_association *asoc) asoc->peer.transport_count = 0; - /* Free any cached ASCONF_ACK chunk. */ - sctp_assoc_free_asconf_acks(asoc); - - /* Free the ASCONF queue. */ - sctp_assoc_free_asconf_queue(asoc); + sctp_asconf_queue_teardown(asoc); - /* Free any cached ASCONF chunk. */ - if (asoc->addip_last_asconf) - sctp_chunk_free(asoc->addip_last_asconf); + /* 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); @@ -1646,3 +1644,16 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack( return NULL; } + +void sctp_asconf_queue_teardown(struct sctp_association *asoc) +{ + /* Free any cached ASCONF_ACK chunk. */ + sctp_assoc_free_asconf_acks(asoc); + + /* Free the ASCONF queue. */ + sctp_assoc_free_asconf_queue(asoc); + + /* Free any cached ASCONF chunk. */ + if (asoc->addip_last_asconf) + sctp_chunk_free(asoc->addip_last_asconf); +} diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index 83e3011..4ece451 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 741ed16..b7692aa 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 0bb0d7c..aabaee4 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/outqueue.c b/net/sctp/outqueue.c index 1c88c89..edc7532 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: diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 67380a2..ab5ded2 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); @@ -1242,6 +1383,7 @@ 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 +1408,13 @@ 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 +1486,7 @@ 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 58eb27f..81db4e3 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 d612ca1..1b2bb64 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1201,7 +1201,7 @@ 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 @@ -1670,6 +1670,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type, case SCTP_CMD_SEND_NEXT_ASCONF: sctp_cmd_send_asconf(asoc); break; + case SCTP_CMD_PURGE_ASCONF_QUEUE: + sctp_asconf_queue_teardown(asoc); + break; default: pr_warn("Impossible command: %u, %p\n", cmd->verb, cmd->obj.ptr); diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 7f4a4f8..7d00b17 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1718,11 +1718,21 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep, return SCTP_DISPOSITION_CONSUME; } - /* For now, fail any unsent/unacked data. Consider the optional - * choice of resending of this data. + /* For now, stop pending T3-rtx and SACK timers, fail any unsent/unacked + * data. Consider the optional choice of resending of this data. */ + sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL()); + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, + SCTP_TO(SCTP_EVENT_TIMEOUT_SACK)); sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL()); + /* Stop pending T4-rto timer, teardown ASCONF queue, ASCONF-ACK queue + * and ASCONF-ACK cache. + */ + sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, + SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO)); + sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL()); + repl = sctp_make_cookie_ack(new_asoc, chunk); if (!repl) goto nomem; @@ -3998,31 +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)) { diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6766913..1c6aec1 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 @@ -3187,11 +3257,11 @@ 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 +3404,46 @@ 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 +3591,9 @@ 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 +3876,12 @@ 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 +3890,17 @@ 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 +5400,28 @@ 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 +5605,9 @@ 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 +6660,7 @@ 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 +6668,12 @@ 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 50cb57f..6b39529 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/sunrpc/auth.c b/net/sunrpc/auth.c index cd6e4aa..727e506 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 339ba64..364eb45 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 0a9a2ec..c3b7533 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 b84d739..7389b7d 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 72bc536..b181e34 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/sched.c b/net/sunrpc/sched.c index 6b43ee7..a27406b 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -792,6 +792,7 @@ 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 c3c232a..a385430 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 80f8da3..28236ba 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 fa68d1e..759b318 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 85209ea..85eba9c 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 31d6172..5ad70ef 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 436dda1..d234a98 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 5ed4b4f..f89570c 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 03e57bf..83d5096 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 8452454..d93178f 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 80025a1..cd356e5 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 205ed4a..46e6b6c 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 d228bd6..62d77e5 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 c68dc95..54d812a 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 3388373..adb2eff 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/mlme.c b/net/wireless/mlme.c index 493b939..3633ab6 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; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index ec83f41..50ff82a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3406,12 +3406,12 @@ 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) { - if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) { + if (nla_len(attr) > IEEE80211_MAX_SSID_LEN) { err = -EINVAL; goto out_free; } - memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr)); request->ssids[i].ssid_len = nla_len(attr); + memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr)); i++; } } @@ -3572,14 +3572,13 @@ 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) { - 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)); - request->ssids[i].ssid_len = nla_len(attr); i++; } } @@ -3621,7 +3620,8 @@ static int nl80211_stop_sched_scan(struct sk_buff *skb, return __cfg80211_stop_sched_scan(rdev, false); } -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 +3633,13 @@ 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 +3728,12 @@ 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 +3757,6 @@ 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 +3819,8 @@ 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 +3828,19 @@ 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 +4375,93 @@ 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) @@ -5658,6 +5759,7 @@ 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 | @@ -6464,7 +6566,8 @@ 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); diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 73a441d..7a6c676 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -267,13 +267,35 @@ static bool is_bss(struct cfg80211_bss *a, return memcmp(ssidie + 2, ssid, ssid_len) == 0; } +static bool is_mesh_bss(struct cfg80211_bss *a) +{ + const u8 *ie; + + if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability)) + return false; + + ie = cfg80211_find_ie(WLAN_EID_MESH_ID, + a->information_elements, + a->len_information_elements); + if (!ie) + return false; + + ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, + a->information_elements, + a->len_information_elements); + if (!ie) + return false; + + return true; +} + static bool is_mesh(struct cfg80211_bss *a, const u8 *meshid, size_t meshidlen, const u8 *meshcfg) { const u8 *ie; - if (!WLAN_CAPABILITY_IS_MBSS(a->capability)) + if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability)) return false; ie = cfg80211_find_ie(WLAN_EID_MESH_ID, @@ -311,7 +333,7 @@ static int cmp_bss(struct cfg80211_bss *a, if (a->channel != b->channel) return b->channel->center_freq - a->channel->center_freq; - if (WLAN_CAPABILITY_IS_MBSS(a->capability | b->capability)) { + if (is_mesh_bss(a) && is_mesh_bss(b)) { r = cmp_ies(WLAN_EID_MESH_ID, a->information_elements, a->len_information_elements, @@ -457,7 +479,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, struct cfg80211_internal_bss *res) { struct cfg80211_internal_bss *found = NULL; - const u8 *meshid, *meshcfg; /* * The reference to "res" is donated to this function. @@ -470,22 +491,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev, res->ts = jiffies; - if (WLAN_CAPABILITY_IS_MBSS(res->pub.capability)) { - /* must be mesh, verify */ - meshid = cfg80211_find_ie(WLAN_EID_MESH_ID, - res->pub.information_elements, - res->pub.len_information_elements); - meshcfg = cfg80211_find_ie(WLAN_EID_MESH_CONFIG, - res->pub.information_elements, - res->pub.len_information_elements); - if (!meshid || !meshcfg || - meshcfg[1] != sizeof(struct ieee80211_meshconf_ie)) { - /* bogus mesh */ - kref_put(&res->ref, bss_release); - return NULL; - } - } - spin_lock_bh(&dev->bss_lock); found = rb_find_bss(dev, res); diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 4680b1e..d306154 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 9005f6d..e547ca1 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 15de65f..0b073b5 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 2130692..037958f 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 dc20cf1..24a342e 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 9bec2e8..5ce74a3 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, @@ -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; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index 47f1b86..b11ea69 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_user.c b/net/xfrm/xfrm_user.c index c658cb3..0256b8a 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, |
