diff options
Diffstat (limited to 'net')
147 files changed, 1492 insertions, 969 deletions
diff --git a/net/802/psnap.c b/net/802/psnap.c index 31128cb92a23..ea4643931446 100644 --- a/net/802/psnap.c +++ b/net/802/psnap.c @@ -20,6 +20,7 @@ #include <linux/mm.h> #include <linux/in.h> #include <linux/init.h> +#include <linux/rculist.h> static LIST_HEAD(snap_list); static DEFINE_SPINLOCK(snap_lock); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index ab2225da0ee2..08f14f6c5fd6 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -27,6 +27,7 @@ #include <linux/mm.h> #include <linux/in.h> #include <linux/init.h> +#include <linux/rculist.h> #include <net/p8022.h> #include <net/arp.h> #include <linux/rtnetlink.h> diff --git a/net/atm/br2684.c b/net/atm/br2684.c index 9d52ebfc1962..05fafdc2eea3 100644 --- a/net/atm/br2684.c +++ b/net/atm/br2684.c @@ -188,10 +188,13 @@ static int br2684_xmit_vcc(struct sk_buff *skb, struct br2684_dev *brdev, return 0; } } - } else { - skb_push(skb, 2); - if (brdev->payload == p_bridged) + } else { /* e_vc */ + if (brdev->payload == p_bridged) { + skb_push(skb, 2); memset(skb->data, 0, 2); + } else { /* p_routed */ + skb_pull(skb, ETH_HLEN); + } } skb_debug(skb); @@ -377,11 +380,8 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) (skb->data + 6, ethertype_ipv4, sizeof(ethertype_ipv4)) == 0) skb->protocol = __constant_htons(ETH_P_IP); - else { - brdev->stats.rx_errors++; - dev_kfree_skb(skb); - return; - } + else + goto error; skb_pull(skb, sizeof(llc_oui_ipv4)); skb_reset_network_header(skb); skb->pkt_type = PACKET_HOST; @@ -394,44 +394,56 @@ static void br2684_push(struct atm_vcc *atmvcc, struct sk_buff *skb) (memcmp(skb->data, llc_oui_pid_pad, 7) == 0)) { skb_pull(skb, sizeof(llc_oui_pid_pad)); skb->protocol = eth_type_trans(skb, net_dev); - } else { - brdev->stats.rx_errors++; - dev_kfree_skb(skb); - return; - } + } else + goto error; - } else { - /* first 2 chars should be 0 */ - if (*((u16 *) (skb->data)) != 0) { - brdev->stats.rx_errors++; - dev_kfree_skb(skb); - return; + } else { /* e_vc */ + if (brdev->payload == p_routed) { + struct iphdr *iph; + + skb_reset_network_header(skb); + iph = ip_hdr(skb); + if (iph->version == 4) + skb->protocol = __constant_htons(ETH_P_IP); + else if (iph->version == 6) + skb->protocol = __constant_htons(ETH_P_IPV6); + else + goto error; + skb->pkt_type = PACKET_HOST; + } else { /* p_bridged */ + /* first 2 chars should be 0 */ + if (*((u16 *) (skb->data)) != 0) + goto error; + skb_pull(skb, BR2684_PAD_LEN); + skb->protocol = eth_type_trans(skb, net_dev); } - skb_pull(skb, BR2684_PAD_LEN + ETH_HLEN); /* pad, dstmac, srcmac, ethtype */ - skb->protocol = eth_type_trans(skb, net_dev); } #ifdef CONFIG_ATM_BR2684_IPFILTER - if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) { - brdev->stats.rx_dropped++; - dev_kfree_skb(skb); - return; - } + if (unlikely(packet_fails_filter(skb->protocol, brvcc, skb))) + goto dropped; #endif /* CONFIG_ATM_BR2684_IPFILTER */ skb->dev = net_dev; ATM_SKB(skb)->vcc = atmvcc; /* needed ? */ pr_debug("received packet's protocol: %x\n", ntohs(skb->protocol)); skb_debug(skb); - if (unlikely(!(net_dev->flags & IFF_UP))) { - /* sigh, interface is down */ - brdev->stats.rx_dropped++; - dev_kfree_skb(skb); - return; - } + /* sigh, interface is down? */ + if (unlikely(!(net_dev->flags & IFF_UP))) + goto dropped; brdev->stats.rx_packets++; brdev->stats.rx_bytes += skb->len; memset(ATM_SKB(skb), 0, sizeof(struct atm_skb_data)); netif_rx(skb); + return; + +dropped: + brdev->stats.rx_dropped++; + goto free_skb; +error: + brdev->stats.rx_errors++; +free_skb: + dev_kfree_skb(skb); + return; } /* @@ -518,9 +530,9 @@ static int br2684_regvcc(struct atm_vcc *atmvcc, void __user * arg) struct sk_buff *next = skb->next; skb->next = skb->prev = NULL; + br2684_push(atmvcc, skb); BRPRIV(skb->dev)->stats.rx_bytes -= skb->len; BRPRIV(skb->dev)->stats.rx_packets--; - br2684_push(atmvcc, skb); skb = next; } diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c index d8f215733175..034aa10a5198 100644 --- a/net/ax25/ax25_subr.c +++ b/net/ax25/ax25_subr.c @@ -64,20 +64,15 @@ void ax25_frames_acked(ax25_cb *ax25, unsigned short nr) void ax25_requeue_frames(ax25_cb *ax25) { - struct sk_buff *skb, *skb_prev = NULL; + struct sk_buff *skb; /* * Requeue all the un-ack-ed frames on the output queue to be picked * up by ax25_kick called from the timer. This arrangement handles the * possibility of an empty output queue. */ - while ((skb = skb_dequeue(&ax25->ack_queue)) != NULL) { - if (skb_prev == NULL) - skb_queue_head(&ax25->write_queue, skb); - else - skb_append(skb_prev, skb, &ax25->write_queue); - skb_prev = skb; - } + while ((skb = skb_dequeue_tail(&ax25->ack_queue)) != NULL) + skb_queue_head(&ax25->write_queue, skb); } /* diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index eb62558e9b09..0c2c93735e93 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -423,8 +423,8 @@ static int __rfcomm_dlc_close(struct rfcomm_dlc *d, int err) rfcomm_dlc_lock(d); d->state = BT_CLOSED; - rfcomm_dlc_unlock(d); d->state_change(d, err); + rfcomm_dlc_unlock(d); skb_queue_purge(&d->tx_queue); rfcomm_dlc_unlink(d); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index c3f749abb2d0..c9191871c1e0 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -566,11 +566,22 @@ static void rfcomm_dev_state_change(struct rfcomm_dlc *dlc, int err) if (dlc->state == BT_CLOSED) { if (!dev->tty) { if (test_bit(RFCOMM_RELEASE_ONHUP, &dev->flags)) { - if (rfcomm_dev_get(dev->id) == NULL) + /* Drop DLC lock here to avoid deadlock + * 1. rfcomm_dev_get will take rfcomm_dev_lock + * but in rfcomm_dev_add there's lock order: + * rfcomm_dev_lock -> dlc lock + * 2. rfcomm_dev_put will deadlock if it's + * the last reference + */ + rfcomm_dlc_unlock(dlc); + if (rfcomm_dev_get(dev->id) == NULL) { + rfcomm_dlc_lock(dlc); return; + } rfcomm_dev_del(dev); rfcomm_dev_put(dev); + rfcomm_dlc_lock(dlc); } } else tty_hangup(dev->tty); diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 72c5976a5ce3..142060f02054 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -15,6 +15,7 @@ #include <linux/kernel.h> #include <linux/init.h> +#include <linux/rculist.h> #include <linux/spinlock.h> #include <linux/times.h> #include <linux/netdevice.h> diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index c2397f503b0f..f38cc5317b88 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -442,12 +442,16 @@ int br_del_if(struct net_bridge *br, struct net_device *dev) void __exit br_cleanup_bridges(void) { - struct net_device *dev, *nxt; + struct net_device *dev; rtnl_lock(); - for_each_netdev_safe(&init_net, dev, nxt) - if (dev->priv_flags & IFF_EBRIDGE) +restart: + for_each_netdev(&init_net, dev) { + if (dev->priv_flags & IFF_EBRIDGE) { del_br(dev->priv); + goto restart; + } + } rtnl_unlock(); } diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index e38034aa56f5..9e96ffcd29a3 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -13,6 +13,7 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/kernel.h> +#include <linux/rculist.h> #include "br_private.h" #include "br_private_stp.h" diff --git a/net/can/af_can.c b/net/can/af_can.c index 7e8ca2836452..484bbf6dd032 100644 --- a/net/can/af_can.c +++ b/net/can/af_can.c @@ -205,12 +205,19 @@ static int can_create(struct net *net, struct socket *sock, int protocol) * -ENOBUFS on full driver queue (see net_xmit_errno()) * -ENOMEM when local loopback failed at calling skb_clone() * -EPERM when trying to send on a non-CAN interface + * -EINVAL when the skb->data does not contain a valid CAN frame */ int can_send(struct sk_buff *skb, int loop) { struct sk_buff *newskb = NULL; + struct can_frame *cf = (struct can_frame *)skb->data; int err; + if (skb->len != sizeof(struct can_frame) || cf->can_dlc > 8) { + kfree_skb(skb); + return -EINVAL; + } + if (skb->dev->type != ARPHRD_CAN) { kfree_skb(skb); return -EPERM; @@ -605,6 +612,7 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { struct dev_rcv_lists *d; + struct can_frame *cf = (struct can_frame *)skb->data; int matches; if (dev->type != ARPHRD_CAN || dev_net(dev) != &init_net) { @@ -612,6 +620,8 @@ static int can_rcv(struct sk_buff *skb, struct net_device *dev, return 0; } + BUG_ON(skb->len != sizeof(struct can_frame) || cf->can_dlc > 8); + /* update statistics */ can_stats.rx_frames++; can_stats.rx_frames_delta++; diff --git a/net/can/bcm.c b/net/can/bcm.c index d9a3a9d13bed..72c2ce904f83 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -298,7 +298,7 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head, if (head->nframes) { /* can_frames starting here */ - firstframe = (struct can_frame *) skb_tail_pointer(skb); + firstframe = (struct can_frame *)skb_tail_pointer(skb); memcpy(skb_put(skb, datalen), frames, datalen); @@ -826,6 +826,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, for (i = 0; i < msg_head->nframes; i++) { err = memcpy_fromiovec((u8 *)&op->frames[i], msg->msg_iov, CFSIZ); + + if (op->frames[i].can_dlc > 8) + err = -EINVAL; + if (err < 0) return err; @@ -858,6 +862,10 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg, for (i = 0; i < msg_head->nframes; i++) { err = memcpy_fromiovec((u8 *)&op->frames[i], msg->msg_iov, CFSIZ); + + if (op->frames[i].can_dlc > 8) + err = -EINVAL; + if (err < 0) { if (op->frames != &op->sframe) kfree(op->frames); @@ -1164,9 +1172,12 @@ static int bcm_tx_send(struct msghdr *msg, int ifindex, struct sock *sk) skb->dev = dev; skb->sk = sk; - can_send(skb, 1); /* send with loopback */ + err = can_send(skb, 1); /* send with loopback */ dev_put(dev); + if (err) + return err; + return CFSIZ + MHSIZ; } @@ -1185,6 +1196,10 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, if (!bo->bound) return -ENOTCONN; + /* check for valid message length from userspace */ + if (size < MHSIZ || (size - MHSIZ) % CFSIZ) + return -EINVAL; + /* check for alternative ifindex for this bcm_op */ if (!ifindex && msg->msg_name) { @@ -1259,8 +1274,8 @@ static int bcm_sendmsg(struct kiocb *iocb, struct socket *sock, break; case TX_SEND: - /* we need at least one can_frame */ - if (msg_head.nframes < 1) + /* we need exactly one can_frame behind the msg head */ + if ((msg_head.nframes != 1) || (size != CFSIZ + MHSIZ)) ret = -EINVAL; else ret = bcm_tx_send(msg, ifindex, sk); diff --git a/net/can/raw.c b/net/can/raw.c index 69877b8e7e9c..3e46ee36a1aa 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -632,6 +632,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct socket *sock, } else ifindex = ro->ifindex; + if (size != sizeof(struct can_frame)) + return -EINVAL; + dev = dev_get_by_index(&init_net, ifindex); if (!dev) return -ENXIO; diff --git a/net/core/dev.c b/net/core/dev.c index 582963077877..821cb1628e5e 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -119,6 +119,7 @@ #include <linux/err.h> #include <linux/ctype.h> #include <linux/if_arp.h> +#include <linux/if_vlan.h> #include "net-sysfs.h" @@ -453,7 +454,7 @@ static int netdev_boot_setup_add(char *name, struct ifmap *map) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] == '\0' || s[i].name[0] == ' ') { memset(s[i].name, 0, sizeof(s[i].name)); - strcpy(s[i].name, name); + strlcpy(s[i].name, name, IFNAMSIZ); memcpy(&s[i].map, map, sizeof(s[i].map)); break; } @@ -478,7 +479,7 @@ int netdev_boot_setup_check(struct net_device *dev) for (i = 0; i < NETDEV_BOOT_SETUP_MAX; i++) { if (s[i].name[0] != '\0' && s[i].name[0] != ' ' && - !strncmp(dev->name, s[i].name, strlen(s[i].name))) { + !strcmp(dev->name, s[i].name)) { dev->irq = s[i].map.irq; dev->base_addr = s[i].map.base_addr; dev->mem_start = s[i].map.mem_start; @@ -1362,6 +1363,29 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); +static bool can_checksum_protocol(unsigned long features, __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_IP_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_IPV6_CSUM) && + protocol == htons(ETH_P_IPV6))); +} + +static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) +{ + if (can_checksum_protocol(dev->features, skb->protocol)) + return true; + + if (skb->protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + if (can_checksum_protocol(dev->features & dev->vlan_features, + veh->h_vlan_encapsulated_proto)) + return true; + } + + return false; +} /* * Invalidate hardware checksum when packet is to be mangled, and @@ -1640,14 +1664,8 @@ int dev_queue_xmit(struct sk_buff *skb) if (skb->ip_summed == CHECKSUM_PARTIAL) { skb_set_transport_header(skb, skb->csum_start - skb_headroom(skb)); - - if (!(dev->features & NETIF_F_GEN_CSUM) && - !((dev->features & NETIF_F_IP_CSUM) && - skb->protocol == htons(ETH_P_IP)) && - !((dev->features & NETIF_F_IPV6_CSUM) && - skb->protocol == htons(ETH_P_IPV6))) - if (skb_checksum_help(skb)) - goto out_kfree_skb; + if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb)) + goto out_kfree_skb; } gso: @@ -2059,6 +2077,10 @@ int netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); + /* Don't receive packets in an exiting network namespace */ + if (!net_alive(dev_net(skb->dev))) + goto out; + #ifdef CONFIG_NET_CLS_ACT if (skb->tc_verd & TC_NCLS) { skb->tc_verd = CLR_TC_NCLS(skb->tc_verd); @@ -2951,7 +2973,7 @@ EXPORT_SYMBOL(dev_unicast_delete); /** * dev_unicast_add - add a secondary unicast address * @dev: device - * @addr: address to delete + * @addr: address to add * @alen: length of @addr * * Add a secondary unicast address to the device or increase @@ -4563,8 +4585,8 @@ static int __init net_dev_init(void) dev_boot_phase = 0; - open_softirq(NET_TX_SOFTIRQ, net_tx_action, NULL); - open_softirq(NET_RX_SOFTIRQ, net_rx_action, NULL); + open_softirq(NET_TX_SOFTIRQ, net_tx_action); + open_softirq(NET_RX_SOFTIRQ, net_rx_action); hotcpu_notifier(dev_cpu_callback, 0); dst_init(); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index e3e9ab0f74e3..277a2302eb3a 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -226,7 +226,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { - err = EAFNOSUPPORT; + err = -EAFNOSUPPORT; goto errout; } @@ -365,7 +365,7 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { - err = EAFNOSUPPORT; + err = -EAFNOSUPPORT; goto errout; } diff --git a/net/core/filter.c b/net/core/filter.c index 4f8369729a4e..df3744355839 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -68,7 +68,6 @@ static inline void *load_pointer(struct sk_buff *skb, int k, * sk_filter - run a packet through a socket filter * @sk: sock associated with &sk_buff * @skb: buffer to filter - * @needlock: set to 1 if the sock is not locked by caller. * * Run the filter code and then cut skb->data to correct size returned by * sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller diff --git a/net/core/flow.c b/net/core/flow.c index 19991175fdeb..5cf81052d044 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -298,7 +298,7 @@ void flow_cache_flush(void) init_completion(&info.completion); local_bh_disable(); - smp_call_function(flow_cache_flush_per_cpu, &info, 1, 0); + smp_call_function(flow_cache_flush_per_cpu, &info, 0); flow_cache_flush_tasklet((unsigned long)&info); local_bh_enable(); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5d9d7130bd6e..65f01f71b3f3 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1714,7 +1714,8 @@ static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) return nla_nest_end(skb, nest); nla_put_failure: - return nla_nest_cancel(skb, nest); + nla_nest_cancel(skb, nest); + return -EMSGSIZE; } static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, @@ -2057,9 +2058,9 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, goto nla_put_failure; } - ci.ndm_used = now - neigh->used; - ci.ndm_confirmed = now - neigh->confirmed; - ci.ndm_updated = now - neigh->updated; + ci.ndm_used = jiffies_to_clock_t(now - neigh->used); + ci.ndm_confirmed = jiffies_to_clock_t(now - neigh->confirmed); + ci.ndm_updated = jiffies_to_clock_t(now - neigh->updated); ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; read_unlock_bh(&neigh->lock); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 72b4c184dd84..7c52fe277b62 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -140,6 +140,9 @@ static void cleanup_net(struct work_struct *work) struct pernet_operations *ops; struct net *net; + /* Be very certain incoming network packets will not find us */ + rcu_barrier(); + net = container_of(work, struct net, work); mutex_lock(&net_mutex); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cf857c4dc7b1..a9a77216310e 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -498,7 +498,8 @@ int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) return nla_nest_end(skb, mx); nla_put_failure: - return nla_nest_cancel(skb, mx); + nla_nest_cancel(skb, mx); + return -EMSGSIZE; } int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5c459f2b7985..366621610e76 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1292,12 +1292,14 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, { unsigned int nr_pages = spd->nr_pages; unsigned int poff, plen, len, toff, tlen; - int headlen, seg; + int headlen, seg, error = 0; toff = *offset; tlen = *total_len; - if (!tlen) + if (!tlen) { + error = 1; goto err; + } /* * if the offset is greater than the linear part, go directly to @@ -1339,7 +1341,8 @@ static int __skb_splice_bits(struct sk_buff *skb, unsigned int *offset, * just jump directly to update and return, no point * in going over fragments when the output is full. */ - if (spd_fill_page(spd, virt_to_page(p), plen, poff, skb)) + error = spd_fill_page(spd, virt_to_page(p), plen, poff, skb); + if (error) goto done; tlen -= plen; @@ -1369,7 +1372,8 @@ map_frag: if (!plen) break; - if (spd_fill_page(spd, f->page, plen, poff, skb)) + error = spd_fill_page(spd, f->page, plen, poff, skb); + if (error) break; tlen -= plen; @@ -1382,7 +1386,10 @@ done: return 0; } err: - return 1; + /* update the offset to reflect the linear part skip, if any */ + if (!error) + *offset = toff; + return error; } /* @@ -1445,6 +1452,7 @@ done: if (spd.nr_pages) { int ret; + struct sock *sk = __skb->sk; /* * Drop the socket lock, otherwise we have reverse @@ -1455,9 +1463,9 @@ done: * we call into ->sendpage() with the i_mutex lock held * and networking will grab the socket lock. */ - release_sock(__skb->sk); + release_sock(sk); ret = splice_to_pipe(pipe, &spd); - lock_sock(__skb->sk); + lock_sock(sk); return ret; } diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 0ad1cd57bc39..c77aff9c6eb3 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -75,7 +75,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, end = start + skb_shinfo(skb)->frags[i].size; copy = end - offset; - if ((copy = end - offset) > 0) { + if (copy > 0) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = frag->page; diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c index 6de4bd195d28..1e8be246ad15 100644 --- a/net/dccp/ackvec.c +++ b/net/dccp/ackvec.c @@ -290,12 +290,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk, while (1) { const u8 len = dccp_ackvec_len(av, index); - const u8 state = dccp_ackvec_state(av, index); + const u8 av_state = dccp_ackvec_state(av, index); /* * valid packets not yet in av_buf have a reserved * entry, with a len equal to 0. */ - if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED && + if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED && len == 0 && delta == 0) { /* Found our reserved seat! */ dccp_pr_debug("Found %llu reserved seat!\n", @@ -325,31 +325,6 @@ out_duplicate: return -EILSEQ; } -#ifdef CONFIG_IP_DCCP_DEBUG -void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len) -{ - dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len, - (unsigned long long)ackno); - - while (len--) { - const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6; - const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK; - - dccp_pr_debug_cat("%d,%d|", state, rl); - ++vector; - } - - dccp_pr_debug_cat("\n"); -} - -void dccp_ackvec_print(const struct dccp_ackvec *av) -{ - dccp_ackvector_print(av->av_buf_ackno, - av->av_buf + av->av_buf_head, - av->av_vec_len); -} -#endif - static void dccp_ackvec_throw_record(struct dccp_ackvec *av, struct dccp_ackvec_record *avr) { diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c index cd61dea2eea1..a1929f33d703 100644 --- a/net/dccp/ccids/ccid3.c +++ b/net/dccp/ccids/ccid3.c @@ -159,8 +159,8 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp) } else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld) - (s64)hctx->ccid3hctx_rtt >= 0) { - hctx->ccid3hctx_x = - max(min(2 * hctx->ccid3hctx_x, min_rate), + hctx->ccid3hctx_x = min(2 * hctx->ccid3hctx_x, min_rate); + hctx->ccid3hctx_x = max(hctx->ccid3hctx_x, scaled_div(((__u64)hctx->ccid3hctx_s) << 6, hctx->ccid3hctx_rtt)); hctx->ccid3hctx_t_ld = now; @@ -193,22 +193,17 @@ static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len) /* * Update Window Counter using the algorithm from [RFC 4342, 8.1]. - * The algorithm is not applicable if RTT < 4 microseconds. + * As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt(). */ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx, ktime_t now) { - u32 quarter_rtts; - - if (unlikely(hctx->ccid3hctx_rtt < 4)) /* avoid divide-by-zero */ - return; - - quarter_rtts = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count); - quarter_rtts /= hctx->ccid3hctx_rtt / 4; + u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count), + quarter_rtts = (4 * delta) / hctx->ccid3hctx_rtt; if (quarter_rtts > 0) { hctx->ccid3hctx_t_last_win_count = now; - hctx->ccid3hctx_last_win_count += min_t(u32, quarter_rtts, 5); + hctx->ccid3hctx_last_win_count += min(quarter_rtts, 5U); hctx->ccid3hctx_last_win_count &= 0xF; /* mod 16 */ } } @@ -334,8 +329,14 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) hctx->ccid3hctx_x = rfc3390_initial_rate(sk); hctx->ccid3hctx_t_ld = now; } else { - /* Sender does not have RTT sample: X_pps = 1 pkt/sec */ - hctx->ccid3hctx_x = hctx->ccid3hctx_s; + /* + * Sender does not have RTT sample: + * - set fallback RTT (RFC 4340, 3.4) since a RTT value + * is needed in several parts (e.g. window counter); + * - set sending rate X_pps = 1pps as per RFC 3448, 4.2. + */ + hctx->ccid3hctx_rtt = DCCP_FALLBACK_RTT; + hctx->ccid3hctx_x = hctx->ccid3hctx_s; hctx->ccid3hctx_x <<= 6; } ccid3_update_send_interval(hctx); diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c index d1dfbb8de64c..97ecec0a8e76 100644 --- a/net/dccp/ccids/lib/tfrc.c +++ b/net/dccp/ccids/lib/tfrc.c @@ -14,14 +14,6 @@ module_param(tfrc_debug, bool, 0444); MODULE_PARM_DESC(tfrc_debug, "Enable debug messages"); #endif -extern int tfrc_tx_packet_history_init(void); -extern void tfrc_tx_packet_history_exit(void); -extern int tfrc_rx_packet_history_init(void); -extern void tfrc_rx_packet_history_exit(void); - -extern int tfrc_li_init(void); -extern void tfrc_li_exit(void); - static int __init tfrc_module_init(void) { int rc = tfrc_li_init(); diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h index 1fb1187bbf1c..ed9857527acf 100644 --- a/net/dccp/ccids/lib/tfrc.h +++ b/net/dccp/ccids/lib/tfrc.h @@ -15,7 +15,7 @@ * (at your option) any later version. */ #include <linux/types.h> -#include <asm/div64.h> +#include <linux/math64.h> #include "../../dccp.h" /* internal includes that this module exports: */ #include "loss_interval.h" @@ -29,21 +29,19 @@ extern int tfrc_debug; #endif /* integer-arithmetic divisions of type (a * 1000000)/b */ -static inline u64 scaled_div(u64 a, u32 b) +static inline u64 scaled_div(u64 a, u64 b) { BUG_ON(b==0); - a *= 1000000; - do_div(a, b); - return a; + return div64_u64(a * 1000000, b); } -static inline u32 scaled_div32(u64 a, u32 b) +static inline u32 scaled_div32(u64 a, u64 b) { u64 result = scaled_div(a, b); if (result > UINT_MAX) { - DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U", - (unsigned long long)a, b); + DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX", + (unsigned long long)a, (unsigned long long)b); return UINT_MAX; } return result; @@ -58,7 +56,14 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight) return avg ? (weight * avg + (10 - weight) * newval) / 10 : newval; } -extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); -extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern u32 tfrc_calc_x(u16 s, u32 R, u32 p); +extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue); +extern int tfrc_tx_packet_history_init(void); +extern void tfrc_tx_packet_history_exit(void); +extern int tfrc_rx_packet_history_init(void); +extern void tfrc_rx_packet_history_exit(void); + +extern int tfrc_li_init(void); +extern void tfrc_li_exit(void); #endif /* _TFRC_H_ */ diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c index e4e64b76c10c..2f20a29cffe4 100644 --- a/net/dccp/ccids/lib/tfrc_equation.c +++ b/net/dccp/ccids/lib/tfrc_equation.c @@ -661,7 +661,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p) EXPORT_SYMBOL_GPL(tfrc_calc_x); -/* +/** * tfrc_calc_x_reverse_lookup - try to find p given f(p) * * @fvalue: function value to match, scaled by 1000000 @@ -676,11 +676,11 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue) /* Error cases. */ if (fvalue < tfrc_calc_x_lookup[0][1]) { - DCCP_WARN("fvalue %d smaller than resolution\n", fvalue); - return tfrc_calc_x_lookup[0][1]; + DCCP_WARN("fvalue %u smaller than resolution\n", fvalue); + return TFRC_SMALLEST_P; } if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) { - DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue); + DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue); return 1000000; } diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b348dd70c685..37d27bcb361f 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -589,7 +589,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&dccp_request_sock_ops); + req = inet_reqsk_alloc(&dccp_request_sock_ops); if (req == NULL) goto drop; @@ -605,7 +605,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; /* * Step 3: Process LISTEN state @@ -739,8 +738,8 @@ int dccp_invalid_packet(struct sk_buff *skb) * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet * has short sequence numbers), drop packet and return */ - if (dh->dccph_type >= DCCP_PKT_DATA && - dh->dccph_type <= DCCP_PKT_DATAACK && dh->dccph_x == 0) { + if ((dh->dccph_type < DCCP_PKT_DATA || + dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0) { DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n", dccp_packet_name(dh->dccph_type)); return 1; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 9b1129bb7ece..f7fe2a572d7b 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -421,7 +421,6 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb) ireq6 = inet6_rsk(req); ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr); - ireq6->pktopts = NULL; if (ipv6_opt_accepted(sk, skb) || np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo || diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c index 33ad48321b08..66dca5bba858 100644 --- a/net/dccp/minisocks.c +++ b/net/dccp/minisocks.c @@ -165,12 +165,12 @@ out_free: /* See dccp_v4_conn_request */ newdmsk->dccpms_sequence_window = req->rcv_wnd; - newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr; - dccp_update_gsr(newsk, dreq->dreq_isr); - - newdp->dccps_iss = dreq->dreq_iss; + newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss; dccp_update_gss(newsk, dreq->dreq_iss); + newdp->dccps_isr = dreq->dreq_isr; + dccp_update_gsr(newsk, dreq->dreq_isr); + /* * SWL and AWL are initially adjusted so that they are not less than * the initial Sequence Numbers received and sent, respectively: diff --git a/net/dccp/options.c b/net/dccp/options.c index d2a84a2fecee..43bc24e761d0 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -107,9 +107,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, * * CCID-specific options are ignored during connection setup, as * negotiation may still be in progress (see RFC 4340, 10.3). + * The same applies to Ack Vectors, as these depend on the CCID. * */ - if (dreq != NULL && opt >= 128) + if (dreq != NULL && (opt >= 128 || + opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1)) goto ignore_option; switch (opt) { diff --git a/net/dccp/output.c b/net/dccp/output.c index 1f8a9b64c083..fe20068c5d8e 100644 --- a/net/dccp/output.c +++ b/net/dccp/output.c @@ -508,6 +508,7 @@ void dccp_send_ack(struct sock *sk) EXPORT_SYMBOL_GPL(dccp_send_ack); +#if 0 /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */ void dccp_send_delayed_ack(struct sock *sk) { @@ -538,6 +539,7 @@ void dccp_send_delayed_ack(struct sock *sk) icsk->icsk_ack.timeout = timeout; sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout); } +#endif void dccp_send_sync(struct sock *sk, const u64 ackno, const enum dccp_pkt_type pkt_type) diff --git a/net/dccp/probe.c b/net/dccp/probe.c index 0bcdc9250279..81368a7f5379 100644 --- a/net/dccp/probe.c +++ b/net/dccp/probe.c @@ -42,7 +42,7 @@ static int bufsize = 64 * 1024; static const char procname[] = "dccpprobe"; -struct { +static struct { struct kfifo *fifo; spinlock_t lock; wait_queue_head_t wait; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 6848e4760f34..79a7ef6209ff 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -90,7 +90,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = { [IFA_LOCAL] = { .type = NLA_U32 }, [IFA_ADDRESS] = { .type = NLA_U32 }, [IFA_BROADCAST] = { .type = NLA_U32 }, - [IFA_ANYCAST] = { .type = NLA_U32 }, [IFA_LABEL] = { .type = NLA_STRING, .len = IFNAMSIZ - 1 }, }; @@ -536,9 +535,6 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh) if (tb[IFA_BROADCAST]) ifa->ifa_broadcast = nla_get_be32(tb[IFA_BROADCAST]); - if (tb[IFA_ANYCAST]) - ifa->ifa_anycast = nla_get_be32(tb[IFA_ANYCAST]); - if (tb[IFA_LABEL]) nla_strlcpy(ifa->ifa_label, tb[IFA_LABEL], IFNAMSIZ); else @@ -745,7 +741,6 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; inet_del_ifa(in_dev, ifap, 0); ifa->ifa_broadcast = 0; - ifa->ifa_anycast = 0; ifa->ifa_scope = 0; } @@ -1113,7 +1108,6 @@ static inline size_t inet_nlmsg_size(void) + nla_total_size(4) /* IFA_ADDRESS */ + nla_total_size(4) /* IFA_LOCAL */ + nla_total_size(4) /* IFA_BROADCAST */ - + nla_total_size(4) /* IFA_ANYCAST */ + nla_total_size(IFNAMSIZ); /* IFA_LABEL */ } @@ -1143,9 +1137,6 @@ static int inet_fill_ifaddr(struct sk_buff *skb, struct in_ifaddr *ifa, if (ifa->ifa_broadcast) NLA_PUT_BE32(skb, IFA_BROADCAST, ifa->ifa_broadcast); - if (ifa->ifa_anycast) - NLA_PUT_BE32(skb, IFA_ANYCAST, ifa->ifa_anycast); - if (ifa->ifa_label[0]) NLA_PUT_STRING(skb, IFA_LABEL, ifa->ifa_label); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 0f1557a4ac7a..0b2ac6a3d903 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -506,7 +506,6 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { [RTA_PREFSRC] = { .type = NLA_U32 }, [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, - [RTA_PROTOINFO] = { .type = NLA_U32 }, [RTA_FLOW] = { .type = NLA_U32 }, }; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3b83c34019fc..0d4d72827e4b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -960,7 +960,10 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, rtm->rtm_dst_len = dst_len; rtm->rtm_src_len = 0; rtm->rtm_tos = tos; - rtm->rtm_table = tb_id; + if (tb_id < 256) + rtm->rtm_table = tb_id; + else + rtm->rtm_table = RT_TABLE_COMPAT; NLA_PUT_U32(skb, RTA_TABLE, tb_id); rtm->rtm_type = type; rtm->rtm_flags = fi->fib_flags; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 4b02d14e7ab9..e1600ad8fb0e 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1359,17 +1359,17 @@ static int check_leaf(struct trie *t, struct leaf *l, t->stats.semantic_match_miss++; #endif if (err <= 0) - return plen; + return err; } - return -1; + return 1; } static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result *res) { struct trie *t = (struct trie *) tb->tb_data; - int plen, ret = 0; + int ret; struct node *n; struct tnode *pn; int pos, bits; @@ -1393,10 +1393,7 @@ static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp, /* Just a leaf? */ if (IS_LEAF(n)) { - plen = check_leaf(t, (struct leaf *)n, key, flp, res); - if (plen < 0) - goto failed; - ret = 0; + ret = check_leaf(t, (struct leaf *)n, key, flp, res); goto found; } @@ -1421,11 +1418,9 @@ static int fn_trie_lookup(struct fib_table *tb, const struct flowi *flp, } if (IS_LEAF(n)) { - plen = check_leaf(t, (struct leaf *)n, key, flp, res); - if (plen < 0) + ret = check_leaf(t, (struct leaf *)n, key, flp, res); + if (ret > 0) goto backtrace; - - ret = 0; goto found; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 828ea211ff21..ec834480abe7 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -419,7 +419,8 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, struct inet_connection_sock *icsk = inet_csk(parent); struct request_sock_queue *queue = &icsk->icsk_accept_queue; struct listen_sock *lopt = queue->listen_opt; - int thresh = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int max_retries = icsk->icsk_syn_retries ? : sysctl_tcp_synack_retries; + int thresh = max_retries; unsigned long now = jiffies; struct request_sock **reqp, *req; int i, budget; @@ -455,6 +456,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } } + if (queue->rskq_defer_accept) + max_retries = queue->rskq_defer_accept; + budget = 2 * (lopt->nr_table_entries / (timeout / interval)); i = lopt->clock_hand; @@ -462,8 +466,9 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, reqp=&lopt->syn_table[i]; while ((req = *reqp) != NULL) { if (time_after_eq(now, req->expires)) { - if (req->retrans < thresh && - !req->rsk_ops->rtx_syn_ack(parent, req)) { + if ((req->retrans < thresh || + (inet_rsk(req)->acked && req->retrans < max_retries)) + && !req->rsk_ops->rtx_syn_ack(parent, req)) { unsigned long timeo; if (req->retrans++ == 0) diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 4ed429bd5951..0546a0bc97ea 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -192,14 +192,21 @@ EXPORT_SYMBOL(inet_frag_evictor); static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf, struct inet_frag_queue *qp_in, struct inet_frags *f, - unsigned int hash, void *arg) + void *arg) { struct inet_frag_queue *qp; #ifdef CONFIG_SMP struct hlist_node *n; #endif + unsigned int hash; write_lock(&f->lock); + /* + * While we stayed w/o the lock other CPU could update + * the rnd seed, so we need to re-calculate the hash + * chain. Fortunatelly the qp_in can be used to get one. + */ + hash = f->hashfn(qp_in); #ifdef CONFIG_SMP /* With SMP race we have to recheck hash table, because * such entry could be created on other cpu, while we @@ -247,7 +254,7 @@ static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf, } static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - struct inet_frags *f, void *arg, unsigned int hash) + struct inet_frags *f, void *arg) { struct inet_frag_queue *q; @@ -255,7 +262,7 @@ static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, if (q == NULL) return NULL; - return inet_frag_intern(nf, q, f, hash, arg); + return inet_frag_intern(nf, q, f, arg); } struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, @@ -264,7 +271,6 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, struct inet_frag_queue *q; struct hlist_node *n; - read_lock(&f->lock); hlist_for_each_entry(q, n, &f->hash[hash], list) { if (q->net == nf && f->match(q, key)) { atomic_inc(&q->refcnt); @@ -274,6 +280,6 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, } read_unlock(&f->lock); - return inet_frag_create(nf, f, key, hash); + return inet_frag_create(nf, f, key); } EXPORT_SYMBOL(inet_frag_find); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index 4a4d49fca1f2..cfd034a2b96e 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -383,8 +383,7 @@ static int __lro_proc_skb(struct net_lro_mgr *lro_mgr, struct sk_buff *skb, out2: /* send aggregated SKBs to stack */ lro_flush(lro_mgr, lro_desc); -out: /* Original SKB has to be posted to stack */ - skb->ip_summed = lro_mgr->ip_summed; +out: return 1; } diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index cd6ce6ac6358..37221f659159 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -229,6 +229,8 @@ static inline struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) arg.iph = iph; arg.user = user; + + read_lock(&ip4_frags.lock); hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 04578593e100..d2a887fc8d9b 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -556,7 +556,6 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) spin_lock_bh(&nf_nat_lock); hlist_del_rcu(&nat->bysource); - nat->ct = NULL; spin_unlock_bh(&nf_nat_lock); } @@ -570,8 +569,8 @@ static void nf_nat_move_storage(void *new, void *old) return; spin_lock_bh(&nf_nat_lock); - hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); new_nat->ct = ct; + hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); spin_unlock_bh(&nf_nat_lock); } diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 5daefad3d193..ffeaffc3fffe 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -232,6 +232,11 @@ static unsigned char asn1_length_decode(struct asn1_ctx *ctx, } } } + + /* don't trust len bigger than ctx buffer */ + if (*len > ctx->end - ctx->pointer) + return 0; + return 1; } @@ -250,6 +255,10 @@ static unsigned char asn1_header_decode(struct asn1_ctx *ctx, if (!asn1_length_decode(ctx, &def, &len)) return 0; + /* primitive shall be definite, indefinite shall be constructed */ + if (*con == ASN1_PRI && !def) + return 0; + if (def) *eoc = ctx->pointer + len; else @@ -430,10 +439,15 @@ static unsigned char asn1_oid_decode(struct asn1_ctx *ctx, unsigned int *len) { unsigned long subid; - unsigned int size; unsigned long *optr; + size_t size; size = eoc - ctx->pointer + 1; + + /* first subid actually encodes first two subids */ + if (size < 2 || size > ULONG_MAX/sizeof(unsigned long)) + return 0; + *oid = kmalloc(size * sizeof(unsigned long), GFP_ATOMIC); if (*oid == NULL) { if (net_ratelimit()) diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index fead049daf43..37a1ecd9d600 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -608,6 +608,14 @@ static void raw_close(struct sock *sk, long timeout) sk_common_release(sk); } +static int raw_destroy(struct sock *sk) +{ + lock_sock(sk); + ip_flush_pending_frames(sk); + release_sock(sk); + return 0; +} + /* This gets rid of all the nasties in af_inet. -DaveM */ static int raw_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { @@ -820,6 +828,7 @@ struct proto raw_prot = { .name = "RAW", .owner = THIS_MODULE, .close = raw_close, + .destroy = raw_destroy, .connect = ip4_datagram_connect, .disconnect = udp_disconnect, .ioctl = raw_ioctl, @@ -925,7 +934,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) srcp = inet->num; seq_printf(seq, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d", + " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", i, src, srcp, dest, destp, sp->sk_state, atomic_read(&sp->sk_wmem_alloc), atomic_read(&sp->sk_rmem_alloc), diff --git a/net/ipv4/route.c b/net/ipv4/route.c index df41026b60db..96be336064fb 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1792,7 +1792,7 @@ static int __mkroute_input(struct sk_buff *skb, if (err) flags |= RTCF_DIRECTSRC; - if (out_dev == in_dev && err && !(flags & RTCF_MASQ) && + if (out_dev == in_dev && err && (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res)))) flags |= RTCF_DOREDIRECT; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 73ba98921d64..d182a2a26291 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -285,7 +285,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, cookie_check_timestamp(&tcp_opt); ret = NULL; - req = reqsk_alloc(&tcp_request_sock_ops); /* for safety */ + req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */ if (!req) goto out; @@ -301,7 +301,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, ireq->rmt_port = th->source; ireq->loc_addr = ip_hdr(skb)->daddr; ireq->rmt_addr = ip_hdr(skb)->saddr; - ireq->opt = NULL; ireq->snd_wscale = tcp_opt.snd_wscale; ireq->rcv_wscale = tcp_opt.rcv_wscale; ireq->sack_ok = tcp_opt.sack_ok; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f88653138621..1d723de18686 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -255,11 +255,14 @@ #include <linux/init.h> #include <linux/fs.h> #include <linux/skbuff.h> +#include <linux/scatterlist.h> #include <linux/splice.h> #include <linux/net.h> #include <linux/socket.h> #include <linux/random.h> #include <linux/bootmem.h> +#include <linux/highmem.h> +#include <linux/swap.h> #include <linux/cache.h> #include <linux/err.h> #include <linux/crypto.h> @@ -1206,7 +1209,8 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, return -ENOTCONN; while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) { if (offset < skb->len) { - size_t used, len; + int used; + size_t len; len = skb->len - offset; /* Stop reading if we hit a patch of urgent data */ @@ -1227,7 +1231,14 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, copied += used; offset += used; } - if (offset != skb->len) + /* + * If recv_actor drops the lock (e.g. TCP splice + * receive) the skb pointer might be invalid when + * getting here: tcp_collapse might have deleted it + * while aggregating skbs from the socket queue. + */ + skb = tcp_recv_skb(sk, seq-1, &offset); + if (!skb || (offset+1 != skb->len)) break; } if (tcp_hdr(skb)->fin) { @@ -2105,12 +2116,15 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; case TCP_DEFER_ACCEPT: - if (val < 0) { - err = -EINVAL; - } else { - if (val > MAX_TCP_ACCEPT_DEFERRED) - val = MAX_TCP_ACCEPT_DEFERRED; - icsk->icsk_accept_queue.rskq_defer_accept = val; + icsk->icsk_accept_queue.rskq_defer_accept = 0; + if (val > 0) { + /* Translate value in seconds to number of + * retransmits */ + while (icsk->icsk_accept_queue.rskq_defer_accept < 32 && + val > ((TCP_TIMEOUT_INIT / HZ) << + icsk->icsk_accept_queue.rskq_defer_accept)) + icsk->icsk_accept_queue.rskq_defer_accept++; + icsk->icsk_accept_queue.rskq_defer_accept++; } break; @@ -2292,7 +2306,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = (val ? : sysctl_tcp_fin_timeout) / HZ; break; case TCP_DEFER_ACCEPT: - val = icsk->icsk_accept_queue.rskq_defer_accept; + val = !icsk->icsk_accept_queue.rskq_defer_accept ? 0 : + ((TCP_TIMEOUT_INIT / HZ) << (icsk->icsk_accept_queue.rskq_defer_accept - 1)); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -2609,7 +2624,7 @@ __setup("thash_entries=", set_thash_entries); void __init tcp_init(void) { struct sk_buff *skb = NULL; - unsigned long limit; + unsigned long nr_pages, limit; int order, i, max_share; BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); @@ -2678,8 +2693,9 @@ void __init tcp_init(void) * is up to 1/2 at 256 MB, decreasing toward zero with the amount of * memory, with a floor of 128 pages. */ - limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_all_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + nr_pages = totalram_pages - totalhigh_pages; + limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); + limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); limit = max(limit, 128UL); sysctl_tcp_mem[0] = limit / 4 * 3; sysctl_tcp_mem[1] = limit; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index b54d9d37b636..cad73b7dfef0 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1392,9 +1392,9 @@ static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, if (before(next_dup->start_seq, skip_to_seq)) { skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count); - tcp_sacktag_walk(skb, sk, NULL, - next_dup->start_seq, next_dup->end_seq, - 1, fack_count, reord, flag); + skb = tcp_sacktag_walk(skb, sk, NULL, + next_dup->start_seq, next_dup->end_seq, + 1, fack_count, reord, flag); } return skb; @@ -2483,6 +2483,20 @@ static inline void tcp_complete_cwr(struct sock *sk) tcp_ca_event(sk, CA_EVENT_COMPLETE_CWR); } +static void tcp_try_keep_open(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + int state = TCP_CA_Open; + + if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) + state = TCP_CA_Disorder; + + if (inet_csk(sk)->icsk_ca_state != state) { + tcp_set_ca_state(sk, state); + tp->high_seq = tp->snd_nxt; + } +} + static void tcp_try_to_open(struct sock *sk, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -2496,15 +2510,7 @@ static void tcp_try_to_open(struct sock *sk, int flag) tcp_enter_cwr(sk, 1); if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { - int state = TCP_CA_Open; - - if (tcp_left_out(tp) || tp->retrans_out || tp->undo_marker) - state = TCP_CA_Disorder; - - if (inet_csk(sk)->icsk_ca_state != state) { - tcp_set_ca_state(sk, state); - tp->high_seq = tp->snd_nxt; - } + tcp_try_keep_open(sk); tcp_moderate_cwnd(tp); } else { tcp_cwnd_down(sk, flag); @@ -3310,8 +3316,11 @@ no_queue: return 1; old_ack: - if (TCP_SKB_CB(skb)->sacked) + if (TCP_SKB_CB(skb)->sacked) { tcp_sacktag_write_queue(sk, skb, prior_snd_una); + if (icsk->icsk_ca_state == TCP_CA_Open) + tcp_try_keep_open(sk); + } uninteresting_ack: SOCK_DEBUG(sk, "Ack %u out of %u:%u\n", ack, tp->snd_una, tp->snd_nxt); @@ -4532,49 +4541,6 @@ static void tcp_urg(struct sock *sk, struct sk_buff *skb, struct tcphdr *th) } } -static int tcp_defer_accept_check(struct sock *sk) -{ - struct tcp_sock *tp = tcp_sk(sk); - - if (tp->defer_tcp_accept.request) { - int queued_data = tp->rcv_nxt - tp->copied_seq; - int hasfin = !skb_queue_empty(&sk->sk_receive_queue) ? - tcp_hdr((struct sk_buff *) - sk->sk_receive_queue.prev)->fin : 0; - - if (queued_data && hasfin) - queued_data--; - - if (queued_data && - tp->defer_tcp_accept.listen_sk->sk_state == TCP_LISTEN) { - if (sock_flag(sk, SOCK_KEEPOPEN)) { - inet_csk_reset_keepalive_timer(sk, - keepalive_time_when(tp)); - } else { - inet_csk_delete_keepalive_timer(sk); - } - - inet_csk_reqsk_queue_add( - tp->defer_tcp_accept.listen_sk, - tp->defer_tcp_accept.request, - sk); - - tp->defer_tcp_accept.listen_sk->sk_data_ready( - tp->defer_tcp_accept.listen_sk, 0); - - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } else if (hasfin || - tp->defer_tcp_accept.listen_sk->sk_state != TCP_LISTEN) { - tcp_reset(sk); - return -1; - } - } - return 0; -} - static int tcp_copy_to_iovec(struct sock *sk, struct sk_buff *skb, int hlen) { struct tcp_sock *tp = tcp_sk(sk); @@ -4935,8 +4901,6 @@ step5: tcp_data_snd_check(sk); tcp_ack_snd_check(sk); - - tcp_defer_accept_check(sk); return 0; csum_error: diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cd601a866c2f..ffe869ac1bcf 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -85,10 +85,6 @@ int sysctl_tcp_tw_reuse __read_mostly; int sysctl_tcp_low_latency __read_mostly; -/* Check TCP sequence numbers in ICMP packets. */ -#define ICMP_MIN_LENGTH 8 - -void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb); #ifdef CONFIG_TCP_MD5SIG static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, @@ -1285,7 +1281,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) goto drop; - req = reqsk_alloc(&tcp_request_sock_ops); + req = inet_reqsk_alloc(&tcp_request_sock_ops); if (!req) goto drop; @@ -1918,14 +1914,6 @@ int tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } - if (tp->defer_tcp_accept.request) { - reqsk_free(tp->defer_tcp_accept.request); - sock_put(tp->defer_tcp_accept.listen_sk); - sock_put(sk); - tp->defer_tcp_accept.listen_sk = NULL; - tp->defer_tcp_accept.request = NULL; - } - atomic_dec(&tcp_sockets_allocated); return 0; @@ -2303,7 +2291,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) } seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " - "%08X %5d %8d %lu %d %p %u %u %u %u %d%n", + "%08X %5d %8d %lu %d %p %lu %lu %u %u %d%n", i, src, srcp, dest, destp, sk->sk_state, tp->write_seq - tp->snd_una, sk->sk_state == TCP_LISTEN ? sk->sk_ack_backlog : @@ -2315,8 +2303,8 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len) icsk->icsk_probes_out, sock_i_ino(sk), atomic_read(&sk->sk_refcnt), sk, - icsk->icsk_rto, - icsk->icsk_ack.ato, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, tp->snd_cwnd, tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 019c8c16e5cc..8245247a6ceb 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -571,8 +571,10 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, does sequence test, SYN is truncated, and thus we consider it a bare ACK. - Both ends (listening sockets) accept the new incoming - connection and try to talk to each other. 8-) + If icsk->icsk_accept_queue.rskq_defer_accept, we silently drop this + bare ACK. Otherwise, we create an established connection. Both + ends (listening sockets) accept the new incoming connection and try + to talk to each other. 8-) Note: This case is both harmless, and rare. Possibility is about the same as us discovering intelligent life on another plant tomorrow. @@ -640,6 +642,13 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, if (!(flg & TCP_FLAG_ACK)) return NULL; + /* If TCP_DEFER_ACCEPT is set, drop bare ACK. */ + if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && + TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { + inet_rsk(req)->acked = 1; + return NULL; + } + /* OK, ACK is valid, create big socket and * feed this segment to it. It will repeat all * the tests. THIS SEGMENT MUST MOVE SOCKET TO @@ -678,24 +687,7 @@ struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, inet_csk_reqsk_queue_unlink(sk, req, prev); inet_csk_reqsk_queue_removed(sk, req); - if (inet_csk(sk)->icsk_accept_queue.rskq_defer_accept && - TCP_SKB_CB(skb)->end_seq == tcp_rsk(req)->rcv_isn + 1) { - - /* the accept queue handling is done is est recv slow - * path so lets make sure to start there - */ - tcp_sk(child)->pred_flags = 0; - sock_hold(sk); - sock_hold(child); - tcp_sk(child)->defer_tcp_accept.listen_sk = sk; - tcp_sk(child)->defer_tcp_accept.request = req; - - inet_csk_reset_keepalive_timer(child, - inet_csk(sk)->icsk_accept_queue.rskq_defer_accept * HZ); - } else { - inet_csk_reqsk_queue_add(sk, req, child); - } - + inet_csk_reqsk_queue_add(sk, req, child); return child; listen_overflow: diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index e399bde7813a..ad993ecb4810 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2131,6 +2131,8 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority) TCP_SKB_CB(skb)->when = tcp_time_stamp; if (tcp_transmit_skb(sk, skb, 0, priority)) NET_INC_STATS(LINUX_MIB_TCPABORTFAILED); + + TCP_INC_STATS(TCP_MIB_OUTRSTS); } /* WARNING: This routine must only be called when we have already sent diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 5ff0ce6e9d39..7ddc30f0744f 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -224,7 +224,7 @@ static __init int tcpprobe_init(void) if (bufsize < 0) return -EINVAL; - tcp_probe.log = kcalloc(sizeof(struct tcp_log), bufsize, GFP_KERNEL); + tcp_probe.log = kcalloc(bufsize, sizeof(struct tcp_log), GFP_KERNEL); if (!tcp_probe.log) goto err0; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4de68cf5f2aa..63ed9d6830e7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -489,11 +489,6 @@ static void tcp_keepalive_timer (unsigned long data) goto death; } - if (tp->defer_tcp_accept.request && sk->sk_state == TCP_ESTABLISHED) { - tcp_send_active_reset(sk, GFP_ATOMIC); - goto death; - } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) goto out; diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index d3b709a6f264..cb1f0e83830b 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -97,7 +97,7 @@ static int tunnel64_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; - if (!pskb_may_pull(skb, sizeof(struct iphdr))) + if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; for (handler = tunnel64_handlers; handler; handler = handler->next) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index db1cb7c96d63..56fcda3694ba 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -420,7 +420,7 @@ void udp_err(struct sk_buff *skb, u32 info) /* * Throw away all pending data and cancel the corking. Socket is locked. */ -static void udp_flush_pending_frames(struct sock *sk) +void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -430,6 +430,7 @@ static void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } +EXPORT_SYMBOL(udp_flush_pending_frames); /** * udp4_hwcsum_outgoing - handle outgoing HW checksumming diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 584e6d74e3a9..7135279f3f84 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -52,7 +52,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) IP_ECN_clear(top_iph); top_iph->frag_off = (flags & XFRM_STATE_NOPMTUDISC) ? - 0 : XFRM_MODE_SKB_CB(skb)->frag_off; + 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); ip_select_ident(top_iph, dst->child, NULL); top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 3a835578fd1c..ff61a5cdb0b3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -731,8 +731,13 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) onlink = -1; spin_lock(&ifa->lock); - lifetime = min_t(unsigned long, - ifa->valid_lft, 0x7fffffffUL/HZ); + + lifetime = addrconf_timeout_fixup(ifa->valid_lft, HZ); + /* + * Note: Because this address is + * not permanent, lifetime < + * LONG_MAX / HZ here. + */ if (time_before(expires, ifa->tstamp + lifetime * HZ)) expires = ifa->tstamp + lifetime * HZ; @@ -744,12 +749,12 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) } write_unlock_bh(&idev->lock); + addrconf_del_timer(ifp); + ipv6_ifa_notify(RTM_DELADDR, ifp); atomic_notifier_call_chain(&inet6addr_chain, NETDEV_DOWN, ifp); - addrconf_del_timer(ifp); - /* * Purge or update corresponding prefix * @@ -1722,7 +1727,6 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) __u32 valid_lft; __u32 prefered_lft; int addr_type; - unsigned long rt_expires; struct inet6_dev *in6_dev; pinfo = (struct prefix_info *) opt; @@ -1764,28 +1768,23 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) * 2) Configure prefixes with the auto flag set */ - if (valid_lft == INFINITY_LIFE_TIME) - rt_expires = ~0UL; - else if (valid_lft >= 0x7FFFFFFF/HZ) { + if (pinfo->onlink) { + struct rt6_info *rt; + unsigned long rt_expires; + /* Avoid arithmetic overflow. Really, we could * save rt_expires in seconds, likely valid_lft, * but it would require division in fib gc, that it * not good. */ - rt_expires = 0x7FFFFFFF - (0x7FFFFFFF % HZ); - } else - rt_expires = valid_lft * HZ; + if (HZ > USER_HZ) + rt_expires = addrconf_timeout_fixup(valid_lft, HZ); + else + rt_expires = addrconf_timeout_fixup(valid_lft, USER_HZ); - /* - * We convert this (in jiffies) to clock_t later. - * Avoid arithmetic overflow there as well. - * Overflow can happen only if HZ < USER_HZ. - */ - if (HZ < USER_HZ && ~rt_expires && rt_expires > 0x7FFFFFFF / USER_HZ) - rt_expires = 0x7FFFFFFF / USER_HZ; + if (addrconf_finite_timeout(rt_expires)) + rt_expires *= HZ; - if (pinfo->onlink) { - struct rt6_info *rt; rt = rt6_lookup(dev_net(dev), &pinfo->prefix, NULL, dev->ifindex, 1); @@ -1794,7 +1793,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (valid_lft == 0) { ip6_del_rt(rt); rt = NULL; - } else if (~rt_expires) { + } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ rt->rt6i_expires = jiffies + rt_expires; rt->rt6i_flags |= RTF_EXPIRES; @@ -1803,9 +1802,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) rt->rt6i_expires = 0; } } else if (valid_lft) { - int flags = RTF_ADDRCONF | RTF_PREFIX_RT; clock_t expires = 0; - if (~rt_expires) { + int flags = RTF_ADDRCONF | RTF_PREFIX_RT; + if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ flags |= RTF_EXPIRES; expires = jiffies_to_clock_t(rt_expires); @@ -2027,7 +2026,7 @@ err_exit: * Manual configuration of address on an interface */ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, - int plen, __u8 ifa_flags, __u32 prefered_lft, + unsigned int plen, __u8 ifa_flags, __u32 prefered_lft, __u32 valid_lft) { struct inet6_ifaddr *ifp; @@ -2036,9 +2035,13 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, int scope; u32 flags; clock_t expires; + unsigned long timeout; ASSERT_RTNL(); + if (plen > 128) + return -EINVAL; + /* check the lifetime */ if (!valid_lft || prefered_lft > valid_lft) return -EINVAL; @@ -2052,22 +2055,23 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, scope = ipv6_addr_scope(pfx); - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; - flags = 0; - expires = 0; - } else { - if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; flags = RTF_EXPIRES; - expires = jiffies_to_clock_t(valid_lft * HZ); + } else { + expires = 0; + flags = 0; + ifa_flags |= IFA_F_PERMANENT; } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } ifp = ipv6_add_addr(idev, pfx, plen, scope, ifa_flags); @@ -2095,12 +2099,15 @@ static int inet6_addr_add(struct net *net, int ifindex, struct in6_addr *pfx, } static int inet6_addr_del(struct net *net, int ifindex, struct in6_addr *pfx, - int plen) + unsigned int plen) { struct inet6_ifaddr *ifp; struct inet6_dev *idev; struct net_device *dev; + if (plen > 128) + return -EINVAL; + dev = __dev_get_by_index(net, ifindex); if (!dev) return -ENODEV; @@ -3169,26 +3176,28 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u8 ifa_flags, { u32 flags; clock_t expires; + unsigned long timeout; if (!valid_lft || (prefered_lft > valid_lft)) return -EINVAL; - if (valid_lft == INFINITY_LIFE_TIME) { - ifa_flags |= IFA_F_PERMANENT; - flags = 0; - expires = 0; - } else { - if (valid_lft >= 0x7FFFFFFF/HZ) - valid_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(valid_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + expires = jiffies_to_clock_t(timeout * HZ); + valid_lft = timeout; flags = RTF_EXPIRES; - expires = jiffies_to_clock_t(valid_lft * HZ); + } else { + expires = 0; + flags = 0; + ifa_flags |= IFA_F_PERMANENT; } - if (prefered_lft == 0) - ifa_flags |= IFA_F_DEPRECATED; - else if ((prefered_lft >= 0x7FFFFFFF/HZ) && - (prefered_lft != INFINITY_LIFE_TIME)) - prefered_lft = 0x7FFFFFFF/HZ; + timeout = addrconf_timeout_fixup(prefered_lft, HZ); + if (addrconf_finite_timeout(timeout)) { + if (timeout == 0) + ifa_flags |= IFA_F_DEPRECATED; + prefered_lft = timeout; + } spin_lock_bh(&ifp->lock); ifp->flags = (ifp->flags & ~(IFA_F_DEPRECATED | IFA_F_PERMANENT | IFA_F_NODAD | IFA_F_HOMEADDRESS)) | ifa_flags; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 3c6aafb02183..e84b3fd17fb4 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -191,7 +191,7 @@ lookup_protocol: np->mcast_hops = -1; np->mc_loop = 1; np->pmtudisc = IPV6_PMTUDISC_WANT; - np->ipv6only = init_net.ipv6.sysctl.bindv6only; + np->ipv6only = net->ipv6.sysctl.bindv6only; /* Init the ipv4 part of the socket since we can have sockets * using v6 API for ipv4. diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 94fa6ae77cfe..0f0f94a40335 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -496,7 +496,8 @@ int datagram_recv_ctl(struct sock *sk, struct msghdr *msg, struct sk_buff *skb) return 0; } -int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, +int datagram_send_ctl(struct net *net, + struct msghdr *msg, struct flowi *fl, struct ipv6_txoptions *opt, int *hlimit, int *tclass) { @@ -509,7 +510,6 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg)) { int addr_type; - struct net_device *dev = NULL; if (!CMSG_OK(msg, cmsg)) { err = -EINVAL; @@ -522,6 +522,9 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, switch (cmsg->cmsg_type) { case IPV6_PKTINFO: case IPV6_2292PKTINFO: + { + struct net_device *dev = NULL; + if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct in6_pktinfo))) { err = -EINVAL; goto exit_f; @@ -535,32 +538,32 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, fl->oif = src_info->ipi6_ifindex; } - addr_type = ipv6_addr_type(&src_info->ipi6_addr); + addr_type = __ipv6_addr_type(&src_info->ipi6_addr); - if (addr_type == IPV6_ADDR_ANY) - break; + if (fl->oif) { + dev = dev_get_by_index(net, fl->oif); + if (!dev) + return -ENODEV; + } else if (addr_type & IPV6_ADDR_LINKLOCAL) + return -EINVAL; - if (addr_type & IPV6_ADDR_LINKLOCAL) { - if (!src_info->ipi6_ifindex) - return -EINVAL; - else { - dev = dev_get_by_index(&init_net, src_info->ipi6_ifindex); - if (!dev) - return -ENODEV; - } - } - if (!ipv6_chk_addr(&init_net, &src_info->ipi6_addr, - dev, 0)) { - if (dev) - dev_put(dev); - err = -EINVAL; - goto exit_f; + if (addr_type != IPV6_ADDR_ANY) { + int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; + if (!ipv6_chk_addr(net, &src_info->ipi6_addr, + strict ? dev : NULL, 0)) + err = -EINVAL; + else + ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); } + if (dev) dev_put(dev); - ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); + if (err) + goto exit_f; + break; + } case IPV6_FLOWINFO: if (cmsg->cmsg_len < CMSG_LEN(4)) { @@ -702,6 +705,11 @@ int datagram_send_ctl(struct msghdr *msg, struct flowi *fl, } *hlimit = *(int *)CMSG_DATA(cmsg); + if (*hlimit < -1 || *hlimit > 0xff) { + err = -EINVAL; + goto exit_f; + } + break; case IPV6_TCLASS: diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 3cd1c993d52b..dcf94fdfb863 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -445,7 +445,7 @@ looped_back: kfree_skb(skb); return -1; } - if (!ipv6_chk_home_addr(&init_net, addr)) { + if (!ipv6_chk_home_addr(dev_net(skb->dst->dev), addr)) { IP6_INC_STATS_BH(ip6_dst_idev(skb->dst), IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index eb7a940310f4..37a4e777e347 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -354,7 +354,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, msg.msg_control = (void*)(fl->opt+1); flowi.oif = 0; - err = datagram_send_ctl(&msg, &flowi, fl->opt, &junk, &junk); + err = datagram_send_ctl(net, &msg, &flowi, fl->opt, &junk, &junk); if (err) goto done; err = -EINVAL; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 4e5c8615832c..17eb48b8e329 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -102,6 +102,15 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt if (hdr->version != 6) goto err; + /* + * RFC4291 2.5.3 + * A packet received on an interface with a destination address + * of loopback must be dropped. + */ + if (!(dev->flags & IFF_LOOPBACK) && + ipv6_addr_loopback(&hdr->daddr)) + goto err; + skb->transport_header = skb->network_header + sizeof(*hdr); IP6CB(skb)->nhoff = offsetof(struct ipv6hdr, nexthdr); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 2de3c464fe75..14796181e8b5 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -197,7 +197,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v) const char *name = vif->dev ? vif->dev->name : "none"; seq_printf(seq, - "%2Zd %-10s %8ld %7ld %8ld %7ld %05X\n", + "%2td %-10s %8ld %7ld %8ld %7ld %05X\n", vif - vif6_table, name, vif->bytes_in, vif->pkt_in, vif->bytes_out, vif->pkt_out, diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 56d55fecf8ec..86e28a75267f 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -67,7 +67,7 @@ int ip6_ra_control(struct sock *sk, int sel, void (*destructor)(struct sock *)) /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW) - return -EINVAL; + return -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -161,9 +161,17 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, struct ipv6_txoptions *opt; struct sk_buff *pktopt; - if (sk->sk_protocol != IPPROTO_UDP && - sk->sk_protocol != IPPROTO_UDPLITE && - sk->sk_protocol != IPPROTO_TCP) + if (sk->sk_type == SOCK_RAW) + break; + + if (sk->sk_protocol == IPPROTO_UDP || + sk->sk_protocol == IPPROTO_UDPLITE) { + struct udp_sock *up = udp_sk(sk); + if (up->pending == AF_INET6) { + retv = -EBUSY; + break; + } + } else if (sk->sk_protocol != IPPROTO_TCP) break; if (sk->sk_state != TCP_ESTABLISHED) { @@ -337,18 +345,21 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_DSTOPTS: { struct ipv6_txoptions *opt; + + /* remove any sticky options header with a zero option + * length, per RFC3542. + */ if (optlen == 0) optval = NULL; + else if (optlen < sizeof(struct ipv6_opt_hdr) || + optlen & 0x7 || optlen > 8 * 255) + goto e_inval; /* hop-by-hop / destination options are privileged option */ retv = -EPERM; if (optname != IPV6_RTHDR && !capable(CAP_NET_RAW)) break; - if (optlen < sizeof(struct ipv6_opt_hdr) || - optlen & 0x7 || optlen > 8 * 255) - goto e_inval; - opt = ipv6_renew_options(sk, np->opt, optname, (struct ipv6_opt_hdr __user *)optval, optlen); @@ -416,7 +427,7 @@ sticky_done: msg.msg_controllen = optlen; msg.msg_control = (void*)(opt+1); - retv = datagram_send_ctl(&msg, &fl, opt, &junk, &junk); + retv = datagram_send_ctl(net, &msg, &fl, opt, &junk, &junk); if (retv) goto done; update: @@ -438,7 +449,7 @@ done: case IPV6_MULTICAST_HOPS: if (sk->sk_type == SOCK_STREAM) - goto e_inval; + break; if (optlen < sizeof(int)) goto e_inval; if (val > 255 || val < -1) @@ -450,13 +461,15 @@ done: case IPV6_MULTICAST_LOOP: if (optlen < sizeof(int)) goto e_inval; + if (val != valbool) + goto e_inval; np->mc_loop = valbool; retv = 0; break; case IPV6_MULTICAST_IF: if (sk->sk_type == SOCK_STREAM) - goto e_inval; + break; if (optlen < sizeof(int)) goto e_inval; @@ -832,7 +845,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, len = min_t(unsigned int, len, ipv6_optlen(hdr)); if (copy_to_user(optval, hdr, len)) return -EFAULT; - return ipv6_optlen(hdr); + return len; } static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, @@ -852,7 +865,7 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_protocol != IPPROTO_UDP && sk->sk_protocol != IPPROTO_UDPLITE && sk->sk_protocol != IPPROTO_TCP) - return -EINVAL; + return -ENOPROTOOPT; if (sk->sk_state != TCP_ESTABLISHED) return -ENOTCONN; val = sk->sk_family; @@ -866,6 +879,8 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, return -EINVAL; if (copy_from_user(&gsf, optval, GROUP_FILTER_SIZE(0))) return -EFAULT; + if (gsf.gf_group.ss_family != AF_INET6) + return -EADDRNOTAVAIL; lock_sock(sk); err = ip6_mc_msfget(sk, &gsf, (struct group_filter __user *)optval, optlen); @@ -975,6 +990,9 @@ static int do_ipv6_getsockopt(struct sock *sk, int level, int optname, len = ipv6_getsockopt_sticky(sk, np->opt, optname, optval, len); release_sock(sk); + /* check if ipv6_getsockopt_sticky() returns err code */ + if (len < 0) + return len; return put_user(len, optlen); } diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 27a5e8b48d93..f405cea21a8b 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -129,7 +129,7 @@ static struct nf_hook_ops ip6t_ops[] __read_mostly = { .priority = NF_IP6_PRI_MANGLE, }, { - .hook = ip6t_local_hook, + .hook = ip6t_route_hook, .owner = THIS_MODULE, .pf = PF_INET6, .hooknum = NF_INET_LOCAL_IN, diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 2dccad48058c..cf20bc4fd60d 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -207,9 +207,12 @@ fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst) arg.id = id; arg.src = src; arg.dst = dst; + + read_lock_bh(&nf_frags.lock); hash = ip6qhashfn(id, src, dst); q = inet_frag_find(&nf_init_frags, &nf_frags, &arg, hash); + local_bh_enable(); if (q == NULL) goto oom; @@ -638,10 +641,10 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) goto ret_orig; } - spin_lock(&fq->q.lock); + spin_lock_bh(&fq->q.lock); if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) { - spin_unlock(&fq->q.lock); + spin_unlock_bh(&fq->q.lock); pr_debug("Can't insert skb to queue\n"); fq_put(fq); goto ret_orig; @@ -653,7 +656,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb) if (ret_skb == NULL) pr_debug("Can't reassemble fragmented packets\n"); } - spin_unlock(&fq->q.lock); + spin_unlock_bh(&fq->q.lock); fq_put(fq); return ret_skb; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 232e0dc45bf5..3aee12310d94 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -813,7 +813,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1164,6 +1164,15 @@ static void rawv6_close(struct sock *sk, long timeout) sk_common_release(sk); } +static int raw6_destroy(struct sock *sk) +{ + lock_sock(sk); + ip6_flush_pending_frames(sk); + release_sock(sk); + + return inet6_destroy_sock(sk); +} + static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); @@ -1187,11 +1196,11 @@ struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, + .destroy = raw6_destroy, .connect = ip6_datagram_connect, .disconnect = udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, - .destroy = inet6_destroy_sock, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 798cabc7535b..a60d7d129713 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -247,6 +247,8 @@ fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst, arg.id = id; arg.src = src; arg.dst = dst; + + read_lock(&ip6_frags.lock); hash = ip6qhashfn(id, src, dst); q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 48534c6c0735..7ff687020fa9 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -240,7 +240,7 @@ static inline int rt6_need_strict(struct in6_addr *daddr) static inline struct rt6_info *rt6_device_match(struct net *net, struct rt6_info *rt, int oif, - int strict) + int flags) { struct rt6_info *local = NULL; struct rt6_info *sprt; @@ -253,7 +253,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (dev->flags & IFF_LOOPBACK) { if (sprt->rt6i_idev == NULL || sprt->rt6i_idev->dev->ifindex != oif) { - if (strict && oif) + if (flags & RT6_LOOKUP_F_IFACE && oif) continue; if (local && (!oif || local->rt6i_idev->dev->ifindex == oif)) @@ -266,7 +266,7 @@ static inline struct rt6_info *rt6_device_match(struct net *net, if (local) return local; - if (strict) + if (flags & RT6_LOOKUP_F_IFACE) return net->ipv6.ip6_null_entry; } return rt; @@ -446,7 +446,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct route_info *rinfo = (struct route_info *) opt; struct in6_addr prefix_buf, *prefix; unsigned int pref; - u32 lifetime; + unsigned long lifetime; struct rt6_info *rt; if (len < sizeof(struct route_info)) { @@ -472,13 +472,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, if (pref == ICMPV6_ROUTER_PREF_INVALID) pref = ICMPV6_ROUTER_PREF_MEDIUM; - lifetime = ntohl(rinfo->lifetime); - if (lifetime == 0xffffffff) { - /* infinity */ - } else if (lifetime > 0x7fffffff/HZ - 1) { - /* Avoid arithmetic overflow */ - lifetime = 0x7fffffff/HZ - 1; - } + lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ); if (rinfo->length == 3) prefix = (struct in6_addr *)rinfo->prefix; @@ -506,7 +500,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { - if (lifetime == 0xffffffff) { + if (!addrconf_finite_timeout(lifetime)) { rt->rt6i_flags &= ~RTF_EXPIRES; } else { rt->rt6i_expires = jiffies + HZ * lifetime; @@ -2202,8 +2196,12 @@ static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric); - expires = (rt->rt6i_flags & RTF_EXPIRES) ? - rt->rt6i_expires - jiffies : 0; + if (!(rt->rt6i_flags & RTF_EXPIRES)) + expires = 0; + else if (rt->rt6i_expires - jiffies < INT_MAX) + expires = rt->rt6i_expires - jiffies; + else + expires = INT_MAX; if (rtnl_put_cacheinfo(skb, &rt->u.dst, 0, 0, 0, expires, rt->u.dst.error) < 0) diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 3de6ffdaedf2..32e871a6c25a 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -222,15 +222,18 @@ __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) } -static int ipip6_tunnel_get_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) +static int ipip6_tunnel_get_prl(struct ip_tunnel *t, + struct ip_tunnel_prl __user *a) { - struct ip_tunnel_prl *kp; + struct ip_tunnel_prl kprl, *kp; struct ip_tunnel_prl_entry *prl; unsigned int cmax, c = 0, ca, len; int ret = 0; - cmax = a->datalen / sizeof(*a); - if (cmax > 1 && a->addr != htonl(INADDR_ANY)) + if (copy_from_user(&kprl, a, sizeof(kprl))) + return -EFAULT; + cmax = kprl.datalen / sizeof(kprl); + if (cmax > 1 && kprl.addr != htonl(INADDR_ANY)) cmax = 1; /* For simple GET or for root users, @@ -261,26 +264,25 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) for (prl = t->prl; prl; prl = prl->next) { if (c > cmax) break; - if (a->addr != htonl(INADDR_ANY) && prl->addr != a->addr) + if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) continue; kp[c].addr = prl->addr; kp[c].flags = prl->flags; c++; - if (a->addr != htonl(INADDR_ANY)) + if (kprl.addr != htonl(INADDR_ANY)) break; } out: read_unlock(&ipip6_lock); len = sizeof(*kp) * c; - ret = len ? copy_to_user(a->data, kp, len) : 0; + ret = 0; + if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen)) + ret = -EFAULT; kfree(kp); - if (ret) - return -EFAULT; - a->datalen = len; - return 0; + return ret; } static int @@ -873,11 +875,20 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; case SIOCGETPRL: + err = -EINVAL; + if (dev == sitn->fb_tunnel_dev) + goto done; + err = -ENOENT; + if (!(t = netdev_priv(dev))) + goto done; + err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data); + break; + case SIOCADDPRL: case SIOCDELPRL: case SIOCCHGPRL: err = -EPERM; - if (cmd != SIOCGETPRL && !capable(CAP_NET_ADMIN)) + if (!capable(CAP_NET_ADMIN)) goto done; err = -EINVAL; if (dev == sitn->fb_tunnel_dev) @@ -890,12 +901,6 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) goto done; switch (cmd) { - case SIOCGETPRL: - err = ipip6_tunnel_get_prl(t, &prl); - if (!err && copy_to_user(ifr->ifr_ifru.ifru_data, - &prl, sizeof(prl))) - err = -EFAULT; - break; case SIOCDELPRL: err = ipip6_tunnel_del_prl(t, &prl); break; @@ -904,8 +909,7 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL); break; } - if (cmd != SIOCGETPRL) - netdev_state_change(dev); + netdev_state_change(dev); break; default: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 938ce4ecde55..3ecc1157994e 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -198,7 +198,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq = inet_rsk(req); ireq6 = inet6_rsk(req); treq = tcp_rsk(req); - ireq6->pktopts = NULL; if (security_inet_conn_request(sk, skb, req)) { reqsk_free(req); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 715965f0fac0..40ea9c36d24b 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1299,7 +1299,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) treq = inet6_rsk(req); ipv6_addr_copy(&treq->rmt_addr, &ipv6_hdr(skb)->saddr); ipv6_addr_copy(&treq->loc_addr, &ipv6_hdr(skb)->daddr); - treq->pktopts = NULL; if (!want_cookie) TCP_ECN_create_request(req, tcp_hdr(skb)); @@ -2037,7 +2036,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " - "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %u %u %u %u %d\n", + "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %lu %lu %u %u %d\n", i, src->s6_addr32[0], src->s6_addr32[1], src->s6_addr32[2], src->s6_addr32[3], srcp, @@ -2053,8 +2052,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) icsk->icsk_probes_out, sock_i_ino(sp), atomic_read(&sp->sk_refcnt), sp, - icsk->icsk_rto, - icsk->icsk_ack.ato, + jiffies_to_clock_t(icsk->icsk_rto), + jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1 ) | icsk->icsk_ack.pingpong, tp->snd_cwnd, tp->snd_ssthresh>=0xFFFF?-1:tp->snd_ssthresh ); diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c index 6323921b40be..669f280989c3 100644 --- a/net/ipv6/tunnel6.c +++ b/net/ipv6/tunnel6.c @@ -109,7 +109,7 @@ static int tunnel46_rcv(struct sk_buff *skb) { struct xfrm6_tunnel *handler; - if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) + if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; for (handler = tunnel46_handlers; handler; handler = handler->next) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1fd784f3e2ec..dd309626ae9a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -534,7 +534,9 @@ static void udp_v6_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); - if (up->pending) { + if (up->pending == AF_INET) + udp_flush_pending_frames(sk); + else if (up->pending) { up->len = 0; up->pending = 0; ip6_flush_pending_frames(sk); @@ -731,7 +733,7 @@ do_udp_sendmsg: memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(*opt); - err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass); + err = datagram_send_ctl(sock_net(sk), msg, &fl, opt, &hlimit, &tclass); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -848,12 +850,14 @@ do_append_data: } else { dst_release(dst); } + dst = NULL; } if (err > 0) err = np->recverr ? net_xmit_errno(err) : 0; release_sock(sk); out: + dst_release(dst); fl6_sock_release(flowlabel); if (!err) return len; diff --git a/net/irda/af_irda.c b/net/irda/af_irda.c index ae54b20d0470..3eb5bcc75f99 100644 --- a/net/irda/af_irda.c +++ b/net/irda/af_irda.c @@ -1093,11 +1093,6 @@ static int irda_create(struct net *net, struct socket *sock, int protocol) init_waitqueue_head(&self->query_wait); - /* Initialise networking socket struct */ - sock_init_data(sock, sk); /* Note : set sk->sk_refcnt to 1 */ - sk->sk_family = PF_IRDA; - sk->sk_protocol = protocol; - switch (sock->type) { case SOCK_STREAM: sock->ops = &irda_stream_ops; @@ -1124,13 +1119,20 @@ static int irda_create(struct net *net, struct socket *sock, int protocol) self->max_sdu_size_rx = TTP_SAR_UNBOUND; break; default: + sk_free(sk); return -ESOCKTNOSUPPORT; } break; default: + sk_free(sk); return -ESOCKTNOSUPPORT; } + /* Initialise networking socket struct */ + sock_init_data(sock, sk); /* Note : set sk->sk_refcnt to 1 */ + sk->sk_family = PF_IRDA; + sk->sk_protocol = protocol; + /* Register as a client with IrLMP */ self->ckey = irlmp_register_client(0, NULL, NULL, NULL); self->mask.word = 0xffff; diff --git a/net/irda/irnet/irnet.h b/net/irda/irnet/irnet.h index b001c361ad30..bccf4d0059f0 100644 --- a/net/irda/irnet/irnet.h +++ b/net/irda/irnet/irnet.h @@ -241,6 +241,7 @@ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/smp_lock.h> #include <linux/skbuff.h> #include <linux/tty.h> #include <linux/proc_fs.h> diff --git a/net/irda/irnet/irnet_ppp.c b/net/irda/irnet/irnet_ppp.c index e0eab5927c4f..e84a70dd346b 100644 --- a/net/irda/irnet/irnet_ppp.c +++ b/net/irda/irnet/irnet_ppp.c @@ -479,6 +479,7 @@ dev_irnet_open(struct inode * inode, ap = kzalloc(sizeof(*ap), GFP_KERNEL); DABORT(ap == NULL, -ENOMEM, FS_ERROR, "Can't allocate struct irnet...\n"); + lock_kernel(); /* initialize the irnet structure */ ap->file = file; @@ -500,6 +501,7 @@ dev_irnet_open(struct inode * inode, { DERROR(FS_ERROR, "Can't setup IrDA link...\n"); kfree(ap); + unlock_kernel(); return err; } @@ -510,6 +512,7 @@ dev_irnet_open(struct inode * inode, file->private_data = ap; DEXIT(FS_TRACE, " - ap=0x%p\n", ap); + unlock_kernel(); return 0; } diff --git a/net/irda/irnetlink.c b/net/irda/irnetlink.c index 9e1fb82e3220..2f05ec1037ab 100644 --- a/net/irda/irnetlink.c +++ b/net/irda/irnetlink.c @@ -101,8 +101,8 @@ static int irda_nl_get_mode(struct sk_buff *skb, struct genl_info *info) hdr = genlmsg_put(msg, info->snd_pid, info->snd_seq, &irda_nl_family, 0, IRDA_NL_CMD_GET_MODE); - if (IS_ERR(hdr)) { - ret = PTR_ERR(hdr); + if (hdr == NULL) { + ret = -EMSGSIZE; goto err_out; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index 7b0038f45b16..bda71015885c 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -1135,8 +1135,7 @@ static void iucv_callback_txdone(struct iucv_path *path, if (this) kfree_skb(this); } - if (!this) - printk(KERN_ERR "AF_IUCV msg tag %u not found\n", msg->tag); + BUG_ON(!this); if (sk->sk_state == IUCV_CLOSING) { if (skb_queue_empty(&iucv_sk(sk)->send_skb_q)) { @@ -1196,7 +1195,7 @@ static int __init afiucv_init(void) } cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err); if (unlikely(err)) { - printk(KERN_ERR "AF_IUCV needs the VM userid\n"); + WARN_ON(err); err = -EPROTONOSUPPORT; goto out; } @@ -1210,7 +1209,6 @@ static int __init afiucv_init(void) err = sock_register(&iucv_sock_family_ops); if (err) goto out_proto; - printk(KERN_INFO "AF_IUCV lowlevel driver initialized\n"); return 0; out_proto: @@ -1226,8 +1224,6 @@ static void __exit afiucv_exit(void) sock_unregister(PF_IUCV); proto_unregister(&iucv_proto); iucv_unregister(&af_iucv_handler, 0); - - printk(KERN_INFO "AF_IUCV lowlevel driver unloaded\n"); } module_init(afiucv_init); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 918970762131..cc34ac769a3c 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -480,7 +480,7 @@ static void iucv_setmask_mp(void) if (cpu_isset(cpu, iucv_buffer_cpumask) && !cpu_isset(cpu, iucv_irq_cpumask)) smp_call_function_single(cpu, iucv_allow_cpu, - NULL, 0, 1); + NULL, 1); preempt_enable(); } @@ -498,7 +498,7 @@ static void iucv_setmask_up(void) cpumask = iucv_irq_cpumask; cpu_clear(first_cpu(iucv_irq_cpumask), cpumask); for_each_cpu_mask(cpu, cpumask) - smp_call_function_single(cpu, iucv_block_cpu, NULL, 0, 1); + smp_call_function_single(cpu, iucv_block_cpu, NULL, 1); } /** @@ -523,7 +523,7 @@ static int iucv_enable(void) rc = -EIO; preempt_disable(); for_each_online_cpu(cpu) - smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1); + smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1); preempt_enable(); if (cpus_empty(iucv_buffer_cpumask)) /* No cpu could declare an iucv buffer. */ @@ -545,7 +545,7 @@ out: */ static void iucv_disable(void) { - on_each_cpu(iucv_retrieve_cpu, NULL, 0, 1); + on_each_cpu(iucv_retrieve_cpu, NULL, 1); kfree(iucv_path_table); } @@ -580,7 +580,7 @@ static int __cpuinit iucv_cpu_notify(struct notifier_block *self, case CPU_ONLINE_FROZEN: case CPU_DOWN_FAILED: case CPU_DOWN_FAILED_FROZEN: - smp_call_function_single(cpu, iucv_declare_cpu, NULL, 0, 1); + smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1); break; case CPU_DOWN_PREPARE: case CPU_DOWN_PREPARE_FROZEN: @@ -589,10 +589,10 @@ static int __cpuinit iucv_cpu_notify(struct notifier_block *self, if (cpus_empty(cpumask)) /* Can't offline last IUCV enabled cpu. */ return NOTIFY_BAD; - smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 0, 1); + smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 1); if (cpus_empty(iucv_irq_cpumask)) smp_call_function_single(first_cpu(iucv_buffer_cpumask), - iucv_allow_cpu, NULL, 0, 1); + iucv_allow_cpu, NULL, 1); break; } return NOTIFY_OK; @@ -652,7 +652,7 @@ static void iucv_cleanup_queue(void) * pending interrupts force them to the work queue by calling * an empty function on all cpus. */ - smp_call_function(__iucv_cleanup_queue, NULL, 0, 1); + smp_call_function(__iucv_cleanup_queue, NULL, 1); spin_lock_irq(&iucv_queue_lock); list_for_each_entry_safe(p, n, &iucv_task_queue, list) { /* Remove stale work items from the task queue. */ @@ -1559,16 +1559,11 @@ static void iucv_external_interrupt(u16 code) p = iucv_irq_data[smp_processor_id()]; if (p->ippathid >= iucv_max_pathid) { - printk(KERN_WARNING "iucv_do_int: Got interrupt with " - "pathid %d > max_connections (%ld)\n", - p->ippathid, iucv_max_pathid - 1); + WARN_ON(p->ippathid >= iucv_max_pathid); iucv_sever_pathid(p->ippathid, iucv_error_no_listener); return; } - if (p->iptype < 0x01 || p->iptype > 0x09) { - printk(KERN_ERR "iucv_do_int: unknown iucv interrupt\n"); - return; - } + BUG_ON(p->iptype < 0x01 || p->iptype > 0x09); work = kmalloc(sizeof(struct iucv_irq_list), GFP_ATOMIC); if (!work) { printk(KERN_WARNING "iucv_external_interrupt: out of memory\n"); diff --git a/net/key/af_key.c b/net/key/af_key.c index 9bba7ac5fee0..7470e367272b 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3030,6 +3030,9 @@ static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c) static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) { + if (atomic_read(&pfkey_socks_nr) == 0) + return 0; + switch (c->event) { case XFRM_MSG_EXPIRE: return key_notify_sa_expire(x, c); diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index e2ddde755019..008de1fc42ca 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -286,12 +286,14 @@ void llc_build_and_send_xid_pkt(struct llc_sap *sap, struct sk_buff *skb, * * Sends received pdus to the sap state machine. */ -static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb) +static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, + struct sock *sk) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); ev->type = LLC_SAP_EV_TYPE_PDU; ev->reason = 0; + skb->sk = sk; llc_sap_state_process(sap, skb); } @@ -360,8 +362,7 @@ static void llc_sap_mcast(struct llc_sap *sap, break; sock_hold(sk); - skb_set_owner_r(skb1, sk); - llc_sap_rcv(sap, skb1); + llc_sap_rcv(sap, skb1, sk); sock_put(sk); } read_unlock_bh(&sap->sk_list.lock); @@ -381,8 +382,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) } else { struct sock *sk = llc_lookup_dgram(sap, &laddr); if (sk) { - skb_set_owner_r(skb, sk); - llc_sap_rcv(sap, skb); + llc_sap_rcv(sap, skb, sk); sock_put(sk); } else kfree_skb(skb); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 699d97b8de5e..a9fce4afdf21 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -672,7 +672,7 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, if (params->vlan) { sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); - if (sdata->vif.type != IEEE80211_IF_TYPE_VLAN || + if (sdata->vif.type != IEEE80211_IF_TYPE_VLAN && sdata->vif.type != IEEE80211_IF_TYPE_AP) return -EINVAL; } else @@ -760,7 +760,7 @@ static int ieee80211_change_station(struct wiphy *wiphy, if (params->vlan && params->vlan != sta->sdata->dev) { vlansdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); - if (vlansdata->vif.type != IEEE80211_IF_TYPE_VLAN || + if (vlansdata->vif.type != IEEE80211_IF_TYPE_VLAN && vlansdata->vif.type != IEEE80211_IF_TYPE_AP) { rcu_read_unlock(); return -EINVAL; diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index c7314bf4bec2..006486b26726 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -899,7 +899,7 @@ extern const struct iw_handler_def ieee80211_iw_handler_def; /* ieee80211_ioctl.c */ -int ieee80211_set_freq(struct ieee80211_local *local, int freq); +int ieee80211_set_freq(struct net_device *dev, int freq); /* ieee80211_sta.c */ void ieee80211_sta_timer(unsigned long data); void ieee80211_sta_work(struct work_struct *work); diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 150d66dbda9d..220e83be3ef4 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -380,6 +380,15 @@ void ieee80211_key_free(struct ieee80211_key *key) if (!key) return; + if (!key->sdata) { + /* The key has not been linked yet, simply free it + * and don't Oops */ + if (key->conf.alg == ALG_CCMP) + ieee80211_aes_key_free(key->u.ccmp.tfm); + kfree(key); + return; + } + spin_lock_irqsave(&key->sdata->local->key_lock, flags); __ieee80211_key_free(key); spin_unlock_irqrestore(&key->sdata->local->key_lock, flags); diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 915afadb0602..df0836ff1a20 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -511,6 +511,7 @@ static int ieee80211_stop(struct net_device *dev) case IEEE80211_IF_TYPE_STA: case IEEE80211_IF_TYPE_IBSS: sdata->u.sta.state = IEEE80211_DISABLED; + memset(sdata->u.sta.bssid, 0, ETH_ALEN); del_timer_sync(&sdata->u.sta.timer); /* * When we get here, the interface is marked down. @@ -529,8 +530,6 @@ static int ieee80211_stop(struct net_device *dev) local->sta_hw_scanning = 0; } - flush_workqueue(local->hw.workqueue); - sdata->u.sta.flags &= ~IEEE80211_STA_PRIVACY_INVOKED; kfree(sdata->u.sta.extra_ie); sdata->u.sta.extra_ie = NULL; @@ -554,6 +553,8 @@ static int ieee80211_stop(struct net_device *dev) ieee80211_led_radio(local, 0); + flush_workqueue(local->hw.workqueue); + tasklet_disable(&local->tx_pending_tasklet); tasklet_disable(&local->tasklet); } @@ -1313,7 +1314,7 @@ static void ieee80211_handle_filtered_frame(struct ieee80211_local *local, /* * Clear the TX filter mask for this STA when sending the next * packet. If the STA went to power save mode, this will happen - * happen when it wakes up for the next time. + * when it wakes up for the next time. */ sta->flags |= WLAN_STA_CLEAR_PS_FILT; diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 7cfd12e0d1e2..b404537c0bcd 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -44,7 +44,7 @@ #define IEEE80211_RETRY_AUTH_INTERVAL (1 * HZ) #define IEEE80211_SCAN_INTERVAL (2 * HZ) #define IEEE80211_SCAN_INTERVAL_SLOW (15 * HZ) -#define IEEE80211_IBSS_JOIN_TIMEOUT (20 * HZ) +#define IEEE80211_IBSS_JOIN_TIMEOUT (7 * HZ) #define IEEE80211_PROBE_DELAY (HZ / 33) #define IEEE80211_CHANNEL_TIME (HZ / 33) @@ -547,15 +547,14 @@ static void ieee80211_set_associated(struct net_device *dev, sdata->bss_conf.ht_bss_conf = &conf->ht_bss_conf; } - netif_carrier_on(dev); ifsta->flags |= IEEE80211_STA_PREV_BSSID_SET; memcpy(ifsta->prev_bssid, sdata->u.sta.bssid, ETH_ALEN); memcpy(wrqu.ap_addr.sa_data, sdata->u.sta.bssid, ETH_ALEN); ieee80211_sta_send_associnfo(dev, ifsta); } else { + netif_carrier_off(dev); ieee80211_sta_tear_down_BA_sessions(dev, ifsta->bssid); ifsta->flags &= ~IEEE80211_STA_ASSOCIATED; - netif_carrier_off(dev); ieee80211_reset_erp_info(dev); sdata->bss_conf.assoc_ht = 0; @@ -569,6 +568,10 @@ static void ieee80211_set_associated(struct net_device *dev, sdata->bss_conf.assoc = assoc; ieee80211_bss_info_change_notify(sdata, changed); + + if (assoc) + netif_carrier_on(dev); + wrqu.ap_addr.sa_family = ARPHRD_ETHER; wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); } @@ -1325,7 +1328,7 @@ static void ieee80211_sta_process_addba_request(struct net_device *dev, /* prepare reordering buffer */ tid_agg_rx->reorder_buf = - kmalloc(buf_size * sizeof(struct sk_buf *), GFP_ATOMIC); + kmalloc(buf_size * sizeof(struct sk_buff *), GFP_ATOMIC); if (!tid_agg_rx->reorder_buf) { if (net_ratelimit()) printk(KERN_ERR "can not allocate reordering buffer " @@ -1334,7 +1337,7 @@ static void ieee80211_sta_process_addba_request(struct net_device *dev, goto end; } memset(tid_agg_rx->reorder_buf, 0, - buf_size * sizeof(struct sk_buf *)); + buf_size * sizeof(struct sk_buff *)); if (local->ops->ampdu_action) ret = local->ops->ampdu_action(hw, IEEE80211_AMPDU_RX_START, @@ -1614,7 +1617,7 @@ void sta_addba_resp_timer_expired(unsigned long data) * only one argument, and both sta_info and TID are needed, so init * flow in sta_info_create gives the TID as data, while the timer_to_id * array gives the sta through container_of */ - u16 tid = *(int *)data; + u16 tid = *(u8 *)data; struct sta_info *temp_sta = container_of((void *)data, struct sta_info, timer_to_tid[tid]); @@ -1662,7 +1665,7 @@ timer_expired_exit: void sta_rx_agg_session_timer_expired(unsigned long data) { /* not an elegant detour, but there is no choice as the timer passes - * only one argument, and verious sta_info are needed here, so init + * only one argument, and various sta_info are needed here, so init * flow in sta_info_create gives the TID as data, while the timer_to_id * array gives the sta through container_of */ u8 *ptid = (u8 *)data; @@ -2336,6 +2339,7 @@ static int ieee80211_sta_join_ibss(struct net_device *dev, u8 *pos; struct ieee80211_sub_if_data *sdata; struct ieee80211_supported_band *sband; + union iwreq_data wrqu; sband = local->hw.wiphy->bands[local->hw.conf.channel->band]; @@ -2358,13 +2362,10 @@ static int ieee80211_sta_join_ibss(struct net_device *dev, sdata->drop_unencrypted = bss->capability & WLAN_CAPABILITY_PRIVACY ? 1 : 0; - res = ieee80211_set_freq(local, bss->freq); + res = ieee80211_set_freq(dev, bss->freq); - if (local->oper_channel->flags & IEEE80211_CHAN_NO_IBSS) { - printk(KERN_DEBUG "%s: IBSS not allowed on frequency " - "%d MHz\n", dev->name, local->oper_channel->center_freq); - return -1; - } + if (res) + return res; /* Set beacon template */ skb = dev_alloc_skb(local->hw.extra_tx_headroom + 400); @@ -2479,7 +2480,9 @@ static int ieee80211_sta_join_ibss(struct net_device *dev, ifsta->state = IEEE80211_IBSS_JOINED; mod_timer(&ifsta->timer, jiffies + IEEE80211_IBSS_MERGE_INTERVAL); - ieee80211_rx_bss_put(dev, bss); + memset(&wrqu, 0, sizeof(wrqu)); + memcpy(wrqu.ap_addr.sa_data, bss->bssid, ETH_ALEN); + wireless_send_event(dev, SIOCGIWAP, &wrqu, NULL); return res; } @@ -3488,7 +3491,7 @@ static int ieee80211_sta_config_auth(struct net_device *dev, spin_unlock_bh(&local->sta_bss_lock); if (selected) { - ieee80211_set_freq(local, selected->freq); + ieee80211_set_freq(dev, selected->freq); if (!(ifsta->flags & IEEE80211_STA_SSID_SET)) ieee80211_sta_set_ssid(dev, selected->ssid, selected->ssid_len); @@ -3523,6 +3526,7 @@ static int ieee80211_sta_create_ibss(struct net_device *dev, struct ieee80211_supported_band *sband; u8 bssid[ETH_ALEN], *pos; int i; + int ret; DECLARE_MAC_BUF(mac); #if 0 @@ -3567,7 +3571,9 @@ static int ieee80211_sta_create_ibss(struct net_device *dev, *pos++ = (u8) (rate / 5); } - return ieee80211_sta_join_ibss(dev, ifsta, bss); + ret = ieee80211_sta_join_ibss(dev, ifsta, bss); + ieee80211_rx_bss_put(dev, bss); + return ret; } @@ -3608,17 +3614,22 @@ static int ieee80211_sta_find_ibss(struct net_device *dev, spin_unlock_bh(&local->sta_bss_lock); #ifdef CONFIG_MAC80211_IBSS_DEBUG - printk(KERN_DEBUG " sta_find_ibss: selected %s current " - "%s\n", print_mac(mac, bssid), print_mac(mac2, ifsta->bssid)); + if (found) + printk(KERN_DEBUG " sta_find_ibss: selected %s current " + "%s\n", print_mac(mac, bssid), + print_mac(mac2, ifsta->bssid)); #endif /* CONFIG_MAC80211_IBSS_DEBUG */ if (found && memcmp(ifsta->bssid, bssid, ETH_ALEN) != 0 && (bss = ieee80211_rx_bss_get(dev, bssid, local->hw.conf.channel->center_freq, ifsta->ssid, ifsta->ssid_len))) { + int ret; printk(KERN_DEBUG "%s: Selected IBSS BSSID %s" " based on configured SSID\n", dev->name, print_mac(mac, bssid)); - return ieee80211_sta_join_ibss(dev, ifsta, bss); + ret = ieee80211_sta_join_ibss(dev, ifsta, bss); + ieee80211_rx_bss_put(dev, bss); + return ret; } #ifdef CONFIG_MAC80211_IBSS_DEBUG printk(KERN_DEBUG " did not try to join ibss\n"); @@ -4095,18 +4106,17 @@ ieee80211_sta_scan_result(struct net_device *dev, memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWFREQ; - iwe.u.freq.m = bss->freq; - iwe.u.freq.e = 6; + iwe.u.freq.m = ieee80211_frequency_to_channel(bss->freq); + iwe.u.freq.e = 0; current_ev = iwe_stream_add_event(current_ev, end_buf, &iwe, IW_EV_FREQ_LEN); memset(&iwe, 0, sizeof(iwe)); iwe.cmd = SIOCGIWFREQ; - iwe.u.freq.m = ieee80211_frequency_to_channel(bss->freq); - iwe.u.freq.e = 0; + iwe.u.freq.m = bss->freq; + iwe.u.freq.e = 6; current_ev = iwe_stream_add_event(current_ev, end_buf, &iwe, IW_EV_FREQ_LEN); - memset(&iwe, 0, sizeof(iwe)); iwe.cmd = IWEVQUAL; iwe.u.qual.qual = bss->signal; diff --git a/net/mac80211/rc80211_pid.h b/net/mac80211/rc80211_pid.h index 04afc13ed825..4ea7b97d1af1 100644 --- a/net/mac80211/rc80211_pid.h +++ b/net/mac80211/rc80211_pid.h @@ -141,7 +141,6 @@ struct rc_pid_events_file_info { * rate behaviour values (lower means we should trust more what we learnt * about behaviour of rates, higher means we should trust more the natural * ordering of rates) - * @fast_start: if Y, push high rates right after initialization */ struct rc_pid_debugfs_entries { struct dentry *dir; @@ -154,7 +153,6 @@ struct rc_pid_debugfs_entries { struct dentry *sharpen_factor; struct dentry *sharpen_duration; struct dentry *norm_offset; - struct dentry *fast_start; }; void rate_control_pid_event_tx_status(struct rc_pid_event_buffer *buf, @@ -267,9 +265,6 @@ struct rc_pid_info { /* Normalization offset. */ unsigned int norm_offset; - /* Fast starst parameter. */ - unsigned int fast_start; - /* Rates information. */ struct rc_pid_rateinfo *rinfo; diff --git a/net/mac80211/rc80211_pid_algo.c b/net/mac80211/rc80211_pid_algo.c index a849b745bdb5..bcd27c1d7594 100644 --- a/net/mac80211/rc80211_pid_algo.c +++ b/net/mac80211/rc80211_pid_algo.c @@ -398,13 +398,25 @@ static void *rate_control_pid_alloc(struct ieee80211_local *local) return NULL; } + pinfo->target = RC_PID_TARGET_PF; + pinfo->sampling_period = RC_PID_INTERVAL; + pinfo->coeff_p = RC_PID_COEFF_P; + pinfo->coeff_i = RC_PID_COEFF_I; + pinfo->coeff_d = RC_PID_COEFF_D; + pinfo->smoothing_shift = RC_PID_SMOOTHING_SHIFT; + pinfo->sharpen_factor = RC_PID_SHARPENING_FACTOR; + pinfo->sharpen_duration = RC_PID_SHARPENING_DURATION; + pinfo->norm_offset = RC_PID_NORM_OFFSET; + pinfo->rinfo = rinfo; + pinfo->oldrate = 0; + /* Sort the rates. This is optimized for the most common case (i.e. * almost-sorted CCK+OFDM rates). Kind of bubble-sort with reversed * mapping too. */ for (i = 0; i < sband->n_bitrates; i++) { rinfo[i].index = i; rinfo[i].rev_index = i; - if (pinfo->fast_start) + if (RC_PID_FAST_START) rinfo[i].diff = 0; else rinfo[i].diff = i * pinfo->norm_offset; @@ -425,19 +437,6 @@ static void *rate_control_pid_alloc(struct ieee80211_local *local) break; } - pinfo->target = RC_PID_TARGET_PF; - pinfo->sampling_period = RC_PID_INTERVAL; - pinfo->coeff_p = RC_PID_COEFF_P; - pinfo->coeff_i = RC_PID_COEFF_I; - pinfo->coeff_d = RC_PID_COEFF_D; - pinfo->smoothing_shift = RC_PID_SMOOTHING_SHIFT; - pinfo->sharpen_factor = RC_PID_SHARPENING_FACTOR; - pinfo->sharpen_duration = RC_PID_SHARPENING_DURATION; - pinfo->norm_offset = RC_PID_NORM_OFFSET; - pinfo->fast_start = RC_PID_FAST_START; - pinfo->rinfo = rinfo; - pinfo->oldrate = 0; - #ifdef CONFIG_MAC80211_DEBUGFS de = &pinfo->dentries; de->dir = debugfs_create_dir("rc80211_pid", @@ -465,9 +464,6 @@ static void *rate_control_pid_alloc(struct ieee80211_local *local) de->norm_offset = debugfs_create_u32("norm_offset", S_IRUSR | S_IWUSR, de->dir, &pinfo->norm_offset); - de->fast_start = debugfs_create_bool("fast_start", - S_IRUSR | S_IWUSR, de->dir, - &pinfo->fast_start); #endif return pinfo; @@ -479,7 +475,6 @@ static void rate_control_pid_free(void *priv) #ifdef CONFIG_MAC80211_DEBUGFS struct rc_pid_debugfs_entries *de = &pinfo->dentries; - debugfs_remove(de->fast_start); debugfs_remove(de->norm_offset); debugfs_remove(de->sharpen_duration); debugfs_remove(de->sharpen_factor); diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 1958bfb361c6..0941e5d6a522 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1091,7 +1091,7 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx) u16 fc, hdrlen, ethertype; u8 *payload; u8 dst[ETH_ALEN]; - u8 src[ETH_ALEN]; + u8 src[ETH_ALEN] __aligned(2); struct sk_buff *skb = rx->skb; struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); DECLARE_MAC_BUF(mac); @@ -1234,7 +1234,7 @@ ieee80211_data_to_8023(struct ieee80211_rx_data *rx) */ static bool ieee80211_frame_allowed(struct ieee80211_rx_data *rx) { - static const u8 pae_group_addr[ETH_ALEN] + static const u8 pae_group_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x80, 0xC2, 0x00, 0x00, 0x03 }; struct ethhdr *ehdr = (struct ethhdr *) rx->skb->data; diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 1d7dd54aacef..c80d5899f279 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1132,7 +1132,7 @@ static int ieee80211_tx(struct net_device *dev, struct sk_buff *skb, ieee80211_tx_handler *handler; struct ieee80211_tx_data tx; ieee80211_tx_result res = TX_DROP, res_prepare; - int ret, i; + int ret, i, retries = 0; WARN_ON(__ieee80211_queue_pending(local, control->queue)); @@ -1216,6 +1216,13 @@ retry: if (!__ieee80211_queue_stopped(local, control->queue)) { clear_bit(IEEE80211_LINK_STATE_PENDING, &local->state[control->queue]); + retries++; + /* + * Driver bug, it's rejecting packets but + * not stopping queues. + */ + if (WARN_ON_ONCE(retries > 5)) + goto drop; goto retry; } memcpy(&store->control, control, @@ -1562,13 +1569,13 @@ int ieee80211_subif_start_xmit(struct sk_buff *skb, * be cloned. This could happen, e.g., with Linux bridge code passing * us broadcast frames. */ - if (head_need > 0 || skb_header_cloned(skb)) { + if (head_need > 0 || skb_cloned(skb)) { #if 0 printk(KERN_DEBUG "%s: need to reallocate buffer for %d bytes " "of headroom\n", dev->name, head_need); #endif - if (skb_header_cloned(skb)) + if (skb_cloned(skb)) I802_DEBUG_INC(local->tx_expand_skb_head_cloned); else I802_DEBUG_INC(local->tx_expand_skb_head); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 131e9e6c8a32..4e97b266f907 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -34,11 +34,11 @@ void *mac80211_wiphy_privid = &mac80211_wiphy_privid; /* See IEEE 802.1H for LLC/SNAP encapsulation/decapsulation */ /* Ethernet-II snap header (RFC1042 for most EtherTypes) */ -const unsigned char rfc1042_header[] = +const unsigned char rfc1042_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0x00 }; /* Bridge-Tunnel header (for EtherTypes ETH_P_AARP and ETH_P_IPX) */ -const unsigned char bridge_tunnel_header[] = +const unsigned char bridge_tunnel_header[] __aligned(2) = { 0xaa, 0xaa, 0x03, 0x00, 0x00, 0xf8 }; diff --git a/net/mac80211/wext.c b/net/mac80211/wext.c index 457ebf9e85ae..e8404212ad57 100644 --- a/net/mac80211/wext.c +++ b/net/mac80211/wext.c @@ -95,6 +95,13 @@ static int ieee80211_set_encryption(struct net_device *dev, u8 *sta_addr, } } + if (alg == ALG_WEP && + key_len != LEN_WEP40 && key_len != LEN_WEP104) { + ieee80211_key_free(key); + err = -EINVAL; + goto out_unlock; + } + ieee80211_key_link(key, sdata, sta); if (set_tx_key || (!sta && !sdata->default_key && key)) @@ -290,14 +297,22 @@ static int ieee80211_ioctl_giwmode(struct net_device *dev, return 0; } -int ieee80211_set_freq(struct ieee80211_local *local, int freqMHz) +int ieee80211_set_freq(struct net_device *dev, int freqMHz) { int ret = -EINVAL; struct ieee80211_channel *chan; + struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); chan = ieee80211_get_channel(local->hw.wiphy, freqMHz); if (chan && !(chan->flags & IEEE80211_CHAN_DISABLED)) { + if (sdata->vif.type == IEEE80211_IF_TYPE_IBSS && + chan->flags & IEEE80211_CHAN_NO_IBSS) { + printk(KERN_DEBUG "%s: IBSS not allowed on frequency " + "%d MHz\n", dev->name, chan->center_freq); + return ret; + } local->oper_channel = chan; if (local->sta_sw_scanning || local->sta_hw_scanning) @@ -315,7 +330,6 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev, struct iw_request_info *info, struct iw_freq *freq, char *extra) { - struct ieee80211_local *local = wdev_priv(dev->ieee80211_ptr); struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == IEEE80211_IF_TYPE_STA) @@ -329,14 +343,14 @@ static int ieee80211_ioctl_siwfreq(struct net_device *dev, IEEE80211_STA_AUTO_CHANNEL_SEL; return 0; } else - return ieee80211_set_freq(local, + return ieee80211_set_freq(dev, ieee80211_channel_to_frequency(freq->m)); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) div /= 10; if (div > 0) - return ieee80211_set_freq(local, freq->m / div); + return ieee80211_set_freq(dev, freq->m / div); else return -EINVAL; } @@ -489,9 +503,15 @@ static int ieee80211_ioctl_giwap(struct net_device *dev, sdata = IEEE80211_DEV_TO_SUB_IF(dev); if (sdata->vif.type == IEEE80211_IF_TYPE_STA || sdata->vif.type == IEEE80211_IF_TYPE_IBSS) { - ap_addr->sa_family = ARPHRD_ETHER; - memcpy(&ap_addr->sa_data, sdata->u.sta.bssid, ETH_ALEN); - return 0; + if (sdata->u.sta.state == IEEE80211_ASSOCIATED || + sdata->u.sta.state == IEEE80211_IBSS_JOINED) { + ap_addr->sa_family = ARPHRD_ETHER; + memcpy(&ap_addr->sa_data, sdata->u.sta.bssid, ETH_ALEN); + return 0; + } else { + memset(&ap_addr->sa_data, 0, ETH_ALEN); + return 0; + } } else if (sdata->vif.type == IEEE80211_IF_TYPE_WDS) { ap_addr->sa_family = ARPHRD_ETHER; memcpy(&ap_addr->sa_data, sdata->u.wds.remote_addr, ETH_ALEN); diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index dc1598b86004..5d09e8698b57 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -323,8 +323,7 @@ static void wme_qdiscop_destroy(struct Qdisc* qd) struct ieee80211_hw *hw = &local->hw; int queue; - tcf_destroy_chain(q->filter_list); - q->filter_list = NULL; + tcf_destroy_chain(&q->filter_list); for (queue=0; queue < hw->queues; queue++) { skb_queue_purge(&q->requeued[queue]); @@ -673,7 +672,7 @@ int ieee80211_ht_agg_queue_add(struct ieee80211_local *local, #ifdef CONFIG_MAC80211_HT_DEBUG if (net_ratelimit()) printk(KERN_DEBUG "allocated aggregation queue" - " %d tid %d addr %s pool=0x%lX", + " %d tid %d addr %s pool=0x%lX\n", i, tid, print_mac(mac, sta->addr), q->qdisc_pool[0]); #endif /* CONFIG_MAC80211_HT_DEBUG */ diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index c4b1799da5d7..662c1ccfee26 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -196,8 +196,6 @@ destroy_conntrack(struct nf_conntrack *nfct) if (l4proto && l4proto->destroy) l4proto->destroy(ct); - nf_ct_ext_destroy(ct); - rcu_read_unlock(); spin_lock_bh(&nf_conntrack_lock); @@ -520,6 +518,7 @@ static void nf_conntrack_free_rcu(struct rcu_head *head) void nf_conntrack_free(struct nf_conn *ct) { + nf_ct_ext_destroy(ct); call_rcu(&ct->rcu, nf_conntrack_free_rcu); } EXPORT_SYMBOL_GPL(nf_conntrack_free); diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index e31beeb33b2b..e8f0dead267f 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -587,10 +587,10 @@ int __init nf_conntrack_expect_init(void) return 0; err3: + kmem_cache_destroy(nf_ct_expect_cachep); +err2: nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_vmalloc, nf_ct_expect_hsize); -err2: - kmem_cache_destroy(nf_ct_expect_cachep); err1: return err; } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index bcc19fa4ed1e..8a3f8b34e466 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -59,12 +59,19 @@ nf_ct_ext_create(struct nf_ct_ext **ext, enum nf_ct_ext_id id, gfp_t gfp) if (!*ext) return NULL; + INIT_RCU_HEAD(&(*ext)->rcu); (*ext)->offset[id] = off; (*ext)->len = len; return (void *)(*ext) + off; } +static void __nf_ct_ext_free_rcu(struct rcu_head *head) +{ + struct nf_ct_ext *ext = container_of(head, struct nf_ct_ext, rcu); + kfree(ext); +} + void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) { struct nf_ct_ext *new; @@ -106,7 +113,7 @@ void *__nf_ct_ext_add(struct nf_conn *ct, enum nf_ct_ext_id id, gfp_t gfp) (void *)ct->ext + ct->ext->offset[i]); rcu_read_unlock(); } - kfree(ct->ext); + call_rcu(&ct->ext->rcu, __nf_ct_ext_free_rcu); ct->ext = new; } diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c index 95da1a24aab7..2f83c158934d 100644 --- a/net/netfilter/nf_conntrack_h323_main.c +++ b/net/netfilter/nf_conntrack_h323_main.c @@ -619,6 +619,7 @@ static const struct nf_conntrack_expect_policy h245_exp_policy = { static struct nf_conntrack_helper nf_conntrack_helper_h245 __read_mostly = { .name = "H.245", .me = THIS_MODULE, + .tuple.src.l3num = AF_UNSPEC, .tuple.dst.protonum = IPPROTO_UDP, .help = h245_help, .expect_policy = &h245_exp_policy, @@ -1765,6 +1766,7 @@ static void __exit nf_conntrack_h323_fini(void) nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); kfree(h323_buffer); pr_debug("nf_ct_h323: fini\n"); } @@ -1777,28 +1779,34 @@ static int __init nf_conntrack_h323_init(void) h323_buffer = kmalloc(65536, GFP_KERNEL); if (!h323_buffer) return -ENOMEM; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_h245); if (ret < 0) goto err1; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[0]); if (ret < 0) goto err2; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_q931[1]); if (ret < 0) goto err3; - ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]); + ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[0]); if (ret < 0) goto err4; + ret = nf_conntrack_helper_register(&nf_conntrack_helper_ras[1]); + if (ret < 0) + goto err5; pr_debug("nf_ct_h323: init success\n"); return 0; -err4: +err5: nf_conntrack_helper_unregister(&nf_conntrack_helper_ras[0]); -err3: +err4: nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[1]); -err2: +err3: nf_conntrack_helper_unregister(&nf_conntrack_helper_q931[0]); +err2: + nf_conntrack_helper_unregister(&nf_conntrack_helper_h245); err1: + kfree(h323_buffer); return ret; } diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 7d1b11703741..8e0b4c8f62a8 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -20,6 +20,7 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/netdevice.h> +#include <linux/rculist.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_l3proto.h> diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 0edefcfc5949..077bcd228799 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -18,6 +18,7 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/kernel.h> +#include <linux/rculist.h> #include <linux/types.h> #include <linux/timer.h> #include <linux/skbuff.h> diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index ba94004fe323..dd28fb239a60 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -331,12 +331,13 @@ static unsigned int get_conntrack_index(const struct tcphdr *tcph) I. Upper bound for valid data: seq <= sender.td_maxend II. Lower bound for valid data: seq + len >= sender.td_end - receiver.td_maxwin - III. Upper bound for valid ack: sack <= receiver.td_end - IV. Lower bound for valid ack: ack >= receiver.td_end - MAXACKWINDOW + III. Upper bound for valid (s)ack: sack <= receiver.td_end + IV. Lower bound for valid (s)ack: sack >= receiver.td_end - MAXACKWINDOW - where sack is the highest right edge of sack block found in the packet. + where sack is the highest right edge of sack block found in the packet + or ack in the case of packet without SACK option. - The upper bound limit for a valid ack is not ignored - + The upper bound limit for a valid (s)ack is not ignored - we doesn't have to deal with fragments. */ @@ -606,12 +607,12 @@ static bool tcp_in_window(const struct nf_conn *ct, before(seq, sender->td_maxend + 1), after(end, sender->td_end - receiver->td_maxwin - 1), before(sack, receiver->td_end + 1), - after(ack, receiver->td_end - MAXACKWINDOW(sender))); + after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)); if (before(seq, sender->td_maxend + 1) && after(end, sender->td_end - receiver->td_maxwin - 1) && before(sack, receiver->td_end + 1) && - after(ack, receiver->td_end - MAXACKWINDOW(sender))) { + after(sack, receiver->td_end - MAXACKWINDOW(sender) - 1)) { /* * Take into account window scaling (RFC 1323). */ @@ -843,9 +844,15 @@ static int tcp_packet(struct nf_conn *ct, /* Attempt to reopen a closed/aborted connection. * Delete this connection and look up again. */ write_unlock_bh(&tcp_lock); - if (del_timer(&ct->timeout)) + /* Only repeat if we can actually remove the timer. + * Destruction may already be in progress in process + * context and we must give it a chance to terminate. + */ + if (del_timer(&ct->timeout)) { ct->timeout.function((unsigned long)ct); - return -NF_REPEAT; + return -NF_REPEAT; + } + return -NF_DROP; } /* Fall through */ case TCP_CONNTRACK_IGNORE: diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index bc11d7092032..9fda6ee95a31 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -92,10 +92,6 @@ void nf_log_packet(int pf, vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(pf, hooknum, skb, in, out, loginfo, prefix); - } else if (net_ratelimit()) { - printk(KERN_WARNING "nf_log_packet: can\'t log since " - "no backend logging module loaded in! Please either " - "load one, or disable logging explicitly\n"); } rcu_read_unlock(); } diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 2e89a00df92c..70907f6baac3 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -73,7 +73,8 @@ connlimit_iphash6(const union nf_inet_addr *addr, static inline bool already_closed(const struct nf_conn *conn) { if (nf_ct_protonum(conn) == IPPROTO_TCP) - return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT; + return conn->proto.tcp.state == TCP_CONNTRACK_TIME_WAIT || + conn->proto.tcp.state == TCP_CONNTRACK_CLOSE; else return 0; } diff --git a/net/netlabel/netlabel_cipso_v4.c b/net/netlabel/netlabel_cipso_v4.c index fdc14a0d21af..9080c61b71a5 100644 --- a/net/netlabel/netlabel_cipso_v4.c +++ b/net/netlabel/netlabel_cipso_v4.c @@ -584,12 +584,7 @@ list_start: rcu_read_unlock(); genlmsg_end(ans_skb, data); - - ret_val = genlmsg_reply(ans_skb, info); - if (ret_val != 0) - goto list_failure; - - return 0; + return genlmsg_reply(ans_skb, info); list_retry: /* XXX - this limit is a guesstimate */ diff --git a/net/netlabel/netlabel_domainhash.c b/net/netlabel/netlabel_domainhash.c index 02c2f7c0b255..643c032a3a57 100644 --- a/net/netlabel/netlabel_domainhash.c +++ b/net/netlabel/netlabel_domainhash.c @@ -30,8 +30,7 @@ */ #include <linux/types.h> -#include <linux/rcupdate.h> -#include <linux/list.h> +#include <linux/rculist.h> #include <linux/skbuff.h> #include <linux/spinlock.h> #include <linux/string.h> diff --git a/net/netlabel/netlabel_mgmt.c b/net/netlabel/netlabel_mgmt.c index 22c191267808..44be5d5261f4 100644 --- a/net/netlabel/netlabel_mgmt.c +++ b/net/netlabel/netlabel_mgmt.c @@ -386,11 +386,7 @@ static int netlbl_mgmt_listdef(struct sk_buff *skb, struct genl_info *info) rcu_read_unlock(); genlmsg_end(ans_skb, data); - - ret_val = genlmsg_reply(ans_skb, info); - if (ret_val != 0) - goto listdef_failure; - return 0; + return genlmsg_reply(ans_skb, info); listdef_failure_lock: rcu_read_unlock(); @@ -501,11 +497,7 @@ static int netlbl_mgmt_version(struct sk_buff *skb, struct genl_info *info) goto version_failure; genlmsg_end(ans_skb, data); - - ret_val = genlmsg_reply(ans_skb, info); - if (ret_val != 0) - goto version_failure; - return 0; + return genlmsg_reply(ans_skb, info); version_failure: kfree_skb(ans_skb); diff --git a/net/netlabel/netlabel_unlabeled.c b/net/netlabel/netlabel_unlabeled.c index 0099da5b2591..56f80872924e 100644 --- a/net/netlabel/netlabel_unlabeled.c +++ b/net/netlabel/netlabel_unlabeled.c @@ -1107,11 +1107,7 @@ static int netlbl_unlabel_list(struct sk_buff *skb, struct genl_info *info) goto list_failure; genlmsg_end(ans_skb, data); - - ret_val = genlmsg_reply(ans_skb, info); - if (ret_val != 0) - goto list_failure; - return 0; + return genlmsg_reply(ans_skb, info); list_failure: kfree_skb(ans_skb); @@ -1534,7 +1530,7 @@ static int netlbl_unlabel_staticlistdef(struct sk_buff *skb, } } list_for_each_entry_rcu(addr6, &iface->addr6_list, list) { - if (addr6->valid || iter_addr6++ < skip_addr6) + if (!addr6->valid || iter_addr6++ < skip_addr6) continue; if (netlbl_unlabel_staticlist_gen(NLBL_UNLABEL_C_STATICLISTDEF, iface, diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 9b97f8006c9c..349aba189558 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -886,7 +886,7 @@ retry: return netlink_unicast_kernel(sk, skb); if (sk_filter(sk, skb)) { - int err = skb->len; + err = skb->len; kfree_skb(skb); sock_put(sk); return err; diff --git a/net/netlink/attr.c b/net/netlink/attr.c index feb326f4a752..2d106cfe1d27 100644 --- a/net/netlink/attr.c +++ b/net/netlink/attr.c @@ -132,6 +132,7 @@ errout: * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream + * @policy: validation policy * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessable via the attribute type. Attributes with a type @@ -194,7 +195,7 @@ struct nlattr *nla_find(struct nlattr *head, int len, int attrtype) /** * nla_strlcpy - Copy string attribute payload into a sized buffer * @dst: where to copy the string to - * @src: attribute to copy the string from + * @nla: attribute to copy the string from * @dstsize: size of destination buffer * * Copies at most dstsize - 1 bytes into the destination buffer. @@ -340,9 +341,9 @@ struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen) } /** - * nla_reserve - reserve room for attribute without header + * nla_reserve_nohdr - reserve room for attribute without header * @skb: socket buffer to reserve room on - * @len: length of attribute payload + * @attrlen: length of attribute payload * * Reserves room for attribute payload without a header. * @@ -400,13 +401,13 @@ void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute header and payload. */ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < nla_total_size(attrlen))) - return -1; + return -EMSGSIZE; __nla_put(skb, attrtype, attrlen, data); return 0; @@ -418,13 +419,13 @@ int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -1; + return -EMSGSIZE; __nla_put_nohdr(skb, attrlen, data); return 0; @@ -436,13 +437,13 @@ int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data) * @attrlen: length of attribute payload * @data: head of attribute payload * - * Returns -1 if the tailroom of the skb is insufficient to store + * Returns -EMSGSIZE if the tailroom of the skb is insufficient to store * the attribute payload. */ int nla_append(struct sk_buff *skb, int attrlen, const void *data) { if (unlikely(skb_tailroom(skb) < NLA_ALIGN(attrlen))) - return -1; + return -EMSGSIZE; memcpy(skb_put(skb, attrlen), data, attrlen); return 0; diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index d16929c9b4bc..3e1191cecaf0 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -444,8 +444,11 @@ static int genl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (ops->dumpit == NULL) return -EOPNOTSUPP; - return netlink_dump_start(genl_sock, skb, nlh, - ops->dumpit, ops->done); + genl_unlock(); + err = netlink_dump_start(genl_sock, skb, nlh, + ops->dumpit, ops->done); + genl_lock(); + return err; } if (ops->doit == NULL) @@ -554,7 +557,8 @@ static int ctrl_fill_info(struct genl_family *family, u32 pid, u32 seq, return genlmsg_end(skb, hdr); nla_put_failure: - return genlmsg_cancel(skb, hdr); + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; } static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, @@ -590,7 +594,8 @@ static int ctrl_fill_mcgrp_info(struct genl_multicast_group *grp, u32 pid, return genlmsg_end(skb, hdr); nla_put_failure: - return genlmsg_cancel(skb, hdr); + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; } static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) @@ -601,9 +606,6 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) int chains_to_skip = cb->args[0]; int fams_to_skip = cb->args[1]; - if (chains_to_skip != 0) - genl_lock(); - for (i = 0; i < GENL_FAM_TAB_SIZE; i++) { if (i < chains_to_skip) continue; @@ -621,9 +623,6 @@ static int ctrl_dumpfamily(struct sk_buff *skb, struct netlink_callback *cb) } errout: - if (chains_to_skip != 0) - genl_unlock(); - cb->args[0] = i; cb->args[1] = n; @@ -768,7 +767,7 @@ static int __init genl_init(void) /* we'll bump the group number right afterwards */ genl_sock = netlink_kernel_create(&init_net, NETLINK_GENERIC, 0, - genl_rcv, NULL, THIS_MODULE); + genl_rcv, &genl_mutex, THIS_MODULE); if (genl_sock == NULL) panic("GENL: Cannot initialize generic netlink\n"); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 82adfe6447d7..9437b27ff84d 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -106,17 +106,6 @@ config NET_SCH_PRIO To compile this code as a module, choose M here: the module will be called sch_prio. -config NET_SCH_RR - tristate "Multi Band Round Robin Queuing (RR)" - select NET_SCH_PRIO - ---help--- - Say Y here if you want to use an n-band round robin packet - scheduler. - - The module uses sch_prio for its framework and is aliased as - sch_rr, so it will load sch_prio, although it is referred - to using sch_rr. - config NET_SCH_RED tristate "Random Early Detection (RED)" ---help--- diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index c40773cdbe45..10f01ad04380 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1252,12 +1252,12 @@ void tcf_destroy(struct tcf_proto *tp) kfree(tp); } -void tcf_destroy_chain(struct tcf_proto *fl) +void tcf_destroy_chain(struct tcf_proto **fl) { struct tcf_proto *tp; - while ((tp = fl) != NULL) { - fl = tp->next; + while ((tp = *fl) != NULL) { + *fl = tp->next; tcf_destroy(tp); } } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 335273416384..db0e23ae85f8 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -160,7 +160,7 @@ static void atm_tc_put(struct Qdisc *sch, unsigned long cl) *prev = flow->next; pr_debug("atm_tc_put: qdisc %p\n", flow->q); qdisc_destroy(flow->q); - tcf_destroy_chain(flow->filter_list); + tcf_destroy_chain(&flow->filter_list); if (flow->sock) { pr_debug("atm_tc_put: f_count %d\n", file_count(flow->sock->file)); @@ -586,10 +586,11 @@ static void atm_tc_destroy(struct Qdisc *sch) struct atm_flow_data *flow; pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); + for (flow = p->flows; flow; flow = flow->next) + tcf_destroy_chain(&flow->filter_list); + /* races ? */ while ((flow = p->flows)) { - tcf_destroy_chain(flow->filter_list); - flow->filter_list = NULL; if (flow->ref > 1) printk(KERN_ERR "atm_destroy: %p->ref = %d\n", flow, flow->ref); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 09969c1fbc08..2a3c97f7dc63 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1704,7 +1704,7 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) BUG_TRAP(!cl->filters); - tcf_destroy_chain(cl->filter_list); + tcf_destroy_chain(&cl->filter_list); qdisc_destroy(cl->q); qdisc_put_rtab(cl->R_tab); gen_kill_estimator(&cl->bstats, &cl->rate_est); @@ -1728,10 +1728,8 @@ cbq_destroy(struct Qdisc* sch) * be bound to classes which have been destroyed already. --TGR '04 */ for (h = 0; h < 16; h++) { - for (cl = q->classes[h]; cl; cl = cl->next) { - tcf_destroy_chain(cl->filter_list); - cl->filter_list = NULL; - } + for (cl = q->classes[h]; cl; cl = cl->next) + tcf_destroy_chain(&cl->filter_list); } for (h = 0; h < 16; h++) { struct cbq_class *next; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0df911fd67b1..c4c1317cd47d 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -416,7 +416,7 @@ static void dsmark_destroy(struct Qdisc *sch) pr_debug("dsmark_destroy(sch %p,[qdisc %p])\n", sch, p); - tcf_destroy_chain(p->filter_list); + tcf_destroy_chain(&p->filter_list); qdisc_destroy(p->q); kfree(p->mask); } @@ -444,7 +444,8 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -466,7 +467,8 @@ static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static const struct Qdisc_class_ops dsmark_class_ops = { diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index d355e5e47fe3..13afa7214392 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -468,7 +468,7 @@ struct Qdisc *qdisc_alloc(struct net_device *dev, struct Qdisc_ops *ops) return sch; errout: - return ERR_PTR(-err); + return ERR_PTR(err); } struct Qdisc * qdisc_create_dflt(struct net_device *dev, struct Qdisc_ops *ops, diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 3a9d226ff1e4..c89fba56db56 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -582,7 +582,8 @@ append_opt: return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static void gred_destroy(struct Qdisc *sch) diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 87293d0db1d7..e817aa00441d 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -1123,7 +1123,7 @@ hfsc_destroy_class(struct Qdisc *sch, struct hfsc_class *cl) { struct hfsc_sched *q = qdisc_priv(sch); - tcf_destroy_chain(cl->filter_list); + tcf_destroy_chain(&cl->filter_list); qdisc_destroy(cl->qdisc); gen_kill_estimator(&cl->bstats, &cl->rate_est); if (cl != &q->root) @@ -1360,7 +1360,7 @@ hfsc_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, nla_put_failure: nla_nest_cancel(skb, nest); - return -1; + return -EMSGSIZE; } static int @@ -1541,6 +1541,10 @@ hfsc_destroy_qdisc(struct Qdisc *sch) unsigned int i; for (i = 0; i < HFSC_HSIZE; i++) { + list_for_each_entry(cl, &q->clhash[i], hlist) + tcf_destroy_chain(&cl->filter_list); + } + for (i = 0; i < HFSC_HSIZE; i++) { list_for_each_entry_safe(cl, next, &q->clhash[i], hlist) hfsc_destroy_class(sch, cl); } diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index 5bc1ed490180..3fb58f428f72 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -28,6 +28,7 @@ * $Id: sch_htb.c,v 1.25 2003/12/07 11:08:25 devik Exp devik $ */ #include <linux/module.h> +#include <linux/moduleparam.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> @@ -53,13 +54,17 @@ */ #define HTB_HSIZE 16 /* classid hash size */ -#define HTB_HYSTERESIS 1 /* whether to use mode hysteresis for speedup */ +static int htb_hysteresis __read_mostly = 0; /* whether to use mode hysteresis for speedup */ #define HTB_VER 0x30011 /* major must be matched with number suplied by TC as version */ #if HTB_VER >> 16 != TC_HTB_PROTOVER #error "Mismatched sch_htb.c and pkt_sch.h" #endif +/* Module parameter and sysfs export */ +module_param (htb_hysteresis, int, 0640); +MODULE_PARM_DESC(htb_hysteresis, "Hysteresis mode, less CPU load, less accurate"); + /* used internaly to keep status of single class */ enum htb_cmode { HTB_CANT_SEND, /* class can't send and can't borrow */ @@ -462,19 +467,21 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) htb_remove_class_from_row(q, cl, mask); } -#if HTB_HYSTERESIS static inline long htb_lowater(const struct htb_class *cl) { - return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0; + if (htb_hysteresis) + return cl->cmode != HTB_CANT_SEND ? -cl->cbuffer : 0; + else + return 0; } static inline long htb_hiwater(const struct htb_class *cl) { - return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0; + if (htb_hysteresis) + return cl->cmode == HTB_CAN_SEND ? -cl->buffer : 0; + else + return 0; } -#else -#define htb_lowater(cl) (0) -#define htb_hiwater(cl) (0) -#endif + /** * htb_class_mode - computes and returns current class mode @@ -1231,7 +1238,7 @@ static void htb_destroy_class(struct Qdisc *sch, struct htb_class *cl) qdisc_put_rtab(cl->rate); qdisc_put_rtab(cl->ceil); - tcf_destroy_chain(cl->filter_list); + tcf_destroy_chain(&cl->filter_list); while (!list_empty(&cl->children)) htb_destroy_class(sch, list_entry(cl->children.next, @@ -1260,7 +1267,7 @@ static void htb_destroy(struct Qdisc *sch) and surprisingly it worked in 2.4. But it must precede it because filter need its target class alive to be able to call unbind_filter on it (without Oops). */ - tcf_destroy_chain(q->filter_list); + tcf_destroy_chain(&q->filter_list); while (!list_empty(&q->root)) htb_destroy_class(sch, list_entry(q->root.next, diff --git a/net/sched/sch_ingress.c b/net/sched/sch_ingress.c index 274b1ddb160c..956c80ad5965 100644 --- a/net/sched/sch_ingress.c +++ b/net/sched/sch_ingress.c @@ -104,7 +104,7 @@ static void ingress_destroy(struct Qdisc *sch) { struct ingress_qdisc_data *p = qdisc_priv(sch); - tcf_destroy_chain(p->filter_list); + tcf_destroy_chain(&p->filter_list); } static int ingress_dump(struct Qdisc *sch, struct sk_buff *skb) diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 4aa2b45dad0a..5532f1031ab5 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -219,7 +219,7 @@ prio_destroy(struct Qdisc* sch) int prio; struct prio_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(q->filter_list); + tcf_destroy_chain(&q->filter_list); for (prio=0; prio<q->bands; prio++) qdisc_destroy(q->queues[prio]); } diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 3dcd493f4f4a..5c569853b9c0 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -281,7 +281,8 @@ static int red_dump(struct Qdisc *sch, struct sk_buff *skb) return nla_nest_end(skb, opts); nla_put_failure: - return nla_nest_cancel(skb, opts); + nla_nest_cancel(skb, opts); + return -EMSGSIZE; } static int red_dump_stats(struct Qdisc *sch, struct gnet_dump *d) diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index f0463d757a98..6a97afbfb952 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -520,7 +520,7 @@ static void sfq_destroy(struct Qdisc *sch) { struct sfq_sched_data *q = qdisc_priv(sch); - tcf_destroy_chain(q->filter_list); + tcf_destroy_chain(&q->filter_list); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index b4cd2b71953f..024c3ebd9661 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -474,6 +474,15 @@ static void sctp_association_destroy(struct sctp_association *asoc) void sctp_assoc_set_primary(struct sctp_association *asoc, struct sctp_transport *transport) { + int changeover = 0; + + /* it's a changeover only if we already have a primary path + * that we are changing + */ + if (asoc->peer.primary_path != NULL && + asoc->peer.primary_path != transport) + changeover = 1 ; + asoc->peer.primary_path = transport; /* Set a default msg_name for events. */ @@ -499,12 +508,12 @@ void sctp_assoc_set_primary(struct sctp_association *asoc, * double switch to the same destination address. */ if (transport->cacc.changeover_active) - transport->cacc.cycling_changeover = 1; + transport->cacc.cycling_changeover = changeover; /* 2) The sender MUST set CHANGEOVER_ACTIVE to indicate that * a changeover has occurred. */ - transport->cacc.changeover_active = 1; + transport->cacc.changeover_active = changeover; /* 3) The sender MUST store the next TSN to be sent in * next_tsn_at_change. @@ -1203,6 +1212,9 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) struct list_head *head = &asoc->peer.transport_addr_list; struct list_head *pos; + if (asoc->peer.transport_count == 1) + return; + /* Find the next transport in a round-robin fashion. */ t = asoc->peer.retran_path; pos = &t->transports; @@ -1217,6 +1229,15 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) t = list_entry(pos, struct sctp_transport, transports); + /* We have exhausted the list, but didn't find any + * other active transports. If so, use the next + * transport. + */ + if (t == asoc->peer.retran_path) { + t = next; + break; + } + /* Try to find an active transport. */ if ((t->state == SCTP_ACTIVE) || @@ -1229,15 +1250,6 @@ void sctp_assoc_update_retran_path(struct sctp_association *asoc) if (!next) next = t; } - - /* We have exhausted the list, but didn't find any - * other active transports. If so, use the next - * transport. - */ - if (t == asoc->peer.retran_path) { - t = next; - break; - } } asoc->peer.retran_path = t; diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index e45e44c60635..a2f4d4d51593 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -299,7 +299,8 @@ static inline int sctp_v6_addr_match_len(union sctp_addr *s1, /* Fills in the source address(saddr) based on the destination address(daddr) * and asoc's bind address list. */ -static void sctp_v6_get_saddr(struct sctp_association *asoc, +static void sctp_v6_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -318,7 +319,7 @@ static void sctp_v6_get_saddr(struct sctp_association *asoc, if (!asoc) { ipv6_dev_get_saddr(dst ? ip6_dst_idev(dst)->dev : NULL, &daddr->v6.sin6_addr, - inet6_sk(asoc->base.sk)->srcprefs, + inet6_sk(&sk->inet.sk)->srcprefs, &saddr->v6.sin6_addr); SCTP_DEBUG_PRINTK("saddr from ipv6_get_saddr: " NIP6_FMT "\n", NIP6(saddr->v6.sin6_addr)); @@ -726,6 +727,11 @@ static void sctp_v6_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, NIP6_FMT " ", NIP6(addr->v6.sin6_addr)); } +static void sctp_v6_ecn_capable(struct sock *sk) +{ + inet6_sk(sk)->tclass |= INET_ECN_ECT_0; +} + /* Initialize a PF_INET6 socket msg_name. */ static void sctp_inet6_msgname(char *msgname, int *addr_len) { @@ -996,6 +1002,7 @@ static struct sctp_af sctp_af_inet6 = { .skb_iif = sctp_v6_skb_iif, .is_ce = sctp_v6_is_ce, .seq_dump_addr = sctp_v6_seq_dump_addr, + .ecn_capable = sctp_v6_ecn_capable, .net_header_len = sizeof(struct ipv6hdr), .sockaddr_len = sizeof(struct sockaddr_in6), #ifdef CONFIG_COMPAT diff --git a/net/sctp/output.c b/net/sctp/output.c index cf4f9fb6819d..6d45bae93b46 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -548,7 +548,7 @@ int sctp_packet_transmit(struct sctp_packet *packet) * Note: The works for IPv6 layer checks this bit too later * in transmission. See IP6_ECN_flow_xmit(). */ - INET_ECN_xmit(nskb->sk); + (*tp->af_specific->ecn_capable)(nskb->sk); /* Set up the IP options. */ /* BUG: not implemented diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 59edfd25a19c..ace6770e9048 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -208,6 +208,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); + q->fast_rtx = 0; q->outstanding_bytes = 0; q->empty = 1; q->cork = 0; @@ -500,6 +501,7 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, case SCTP_RTXR_FAST_RTX: SCTP_INC_STATS(SCTP_MIB_FAST_RETRANSMITS); sctp_transport_lower_cwnd(transport, SCTP_LOWER_CWND_FAST_RTX); + q->fast_rtx = 1; break; case SCTP_RTXR_PMTUD: SCTP_INC_STATS(SCTP_MIB_PMTUD_RETRANSMITS); @@ -518,9 +520,15 @@ void sctp_retransmit(struct sctp_outq *q, struct sctp_transport *transport, * the sender SHOULD try to advance the "Advanced.Peer.Ack.Point" by * following the procedures outlined in C1 - C5. */ - sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point); + if (reason == SCTP_RTXR_T3_RTX) + sctp_generate_fwdtsn(q, q->asoc->ctsn_ack_point); - error = sctp_outq_flush(q, /* rtx_timeout */ 1); + /* Flush the queues only on timeout, since fast_rtx is only + * triggered during sack processing and the queue + * will be flushed at the end. + */ + if (reason != SCTP_RTXR_FAST_RTX) + error = sctp_outq_flush(q, /* rtx_timeout */ 1); if (error) q->asoc->base.sk->sk_err = -error; @@ -538,17 +546,23 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, int rtx_timeout, int *start_timer) { struct list_head *lqueue; - struct list_head *lchunk; struct sctp_transport *transport = pkt->transport; sctp_xmit_t status; struct sctp_chunk *chunk, *chunk1; struct sctp_association *asoc; + int fast_rtx; int error = 0; + int timer = 0; + int done = 0; asoc = q->asoc; lqueue = &q->retransmit; + fast_rtx = q->fast_rtx; - /* RFC 2960 6.3.3 Handle T3-rtx Expiration + /* This loop handles time-out retransmissions, fast retransmissions, + * and retransmissions due to opening of whindow. + * + * RFC 2960 6.3.3 Handle T3-rtx Expiration * * E3) Determine how many of the earliest (i.e., lowest TSN) * outstanding DATA chunks for the address for which the @@ -563,12 +577,12 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, * [Just to be painfully clear, if we are retransmitting * because a timeout just happened, we should send only ONE * packet of retransmitted data.] + * + * For fast retransmissions we also send only ONE packet. However, + * if we are just flushing the queue due to open window, we'll + * try to send as much as possible. */ - lchunk = sctp_list_dequeue(lqueue); - - while (lchunk) { - chunk = list_entry(lchunk, struct sctp_chunk, - transmitted_list); + list_for_each_entry_safe(chunk, chunk1, lqueue, transmitted_list) { /* Make sure that Gap Acked TSNs are not retransmitted. A * simple approach is just to move such TSNs out of the @@ -576,58 +590,60 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, * next chunk. */ if (chunk->tsn_gap_acked) { - list_add_tail(lchunk, &transport->transmitted); - lchunk = sctp_list_dequeue(lqueue); + list_del(&chunk->transmitted_list); + list_add_tail(&chunk->transmitted_list, + &transport->transmitted); continue; } + /* If we are doing fast retransmit, ignore non-fast_rtransmit + * chunks + */ + if (fast_rtx && !chunk->fast_retransmit) + continue; + /* Attempt to append this chunk to the packet. */ status = sctp_packet_append_chunk(pkt, chunk); switch (status) { case SCTP_XMIT_PMTU_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* If we are retransmitting, we should only * send a single packet. */ - if (rtx_timeout) { - list_add(lchunk, lqueue); - lchunk = NULL; - } + if (rtx_timeout || fast_rtx) + done = 1; - /* Bundle lchunk in the next round. */ + /* Bundle next chunk in the next round. */ break; case SCTP_XMIT_RWND_FULL: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA as there is no more room * at the receiver. */ - list_add(lchunk, lqueue); - lchunk = NULL; + done = 1; break; case SCTP_XMIT_NAGLE_DELAY: /* Send this packet. */ - if ((error = sctp_packet_transmit(pkt)) == 0) - *start_timer = 1; + error = sctp_packet_transmit(pkt); /* Stop sending DATA because of nagle delay. */ - list_add(lchunk, lqueue); - lchunk = NULL; + done = 1; break; default: /* The append was successful, so add this chunk to * the transmitted list. */ - list_add_tail(lchunk, &transport->transmitted); + list_del(&chunk->transmitted_list); + list_add_tail(&chunk->transmitted_list, + &transport->transmitted); /* Mark the chunk as ineligible for fast retransmit * after it is retransmitted. @@ -635,27 +651,44 @@ static int sctp_outq_flush_rtx(struct sctp_outq *q, struct sctp_packet *pkt, if (chunk->fast_retransmit > 0) chunk->fast_retransmit = -1; - *start_timer = 1; - q->empty = 0; + /* Force start T3-rtx timer when fast retransmitting + * the earliest outstanding TSN + */ + if (!timer && fast_rtx && + ntohl(chunk->subh.data_hdr->tsn) == + asoc->ctsn_ack_point + 1) + timer = 2; - /* Retrieve a new chunk to bundle. */ - lchunk = sctp_list_dequeue(lqueue); + q->empty = 0; break; } - /* If we are here due to a retransmit timeout or a fast - * retransmit and if there are any chunks left in the retransmit - * queue that could not fit in the PMTU sized packet, they need - * to be marked as ineligible for a subsequent fast retransmit. - */ - if (rtx_timeout && !lchunk) { - list_for_each_entry(chunk1, lqueue, transmitted_list) { - if (chunk1->fast_retransmit > 0) - chunk1->fast_retransmit = -1; - } + /* Set the timer if there were no errors */ + if (!error && !timer) + timer = 1; + + if (done) + break; + } + + /* If we are here due to a retransmit timeout or a fast + * retransmit and if there are any chunks left in the retransmit + * queue that could not fit in the PMTU sized packet, they need + * to be marked as ineligible for a subsequent fast retransmit. + */ + if (rtx_timeout || fast_rtx) { + list_for_each_entry(chunk1, lqueue, transmitted_list) { + if (chunk1->fast_retransmit > 0) + chunk1->fast_retransmit = -1; } } + *start_timer = timer; + + /* Clear fast retransmit hint */ + if (fast_rtx) + q->fast_rtx = 0; + return error; } @@ -862,7 +895,8 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) rtx_timeout, &start_timer); if (start_timer) - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, + start_timer-1); /* This can happen on COOKIE-ECHO resend. Only * one chunk can get bundled with a COOKIE-ECHO. @@ -977,7 +1011,7 @@ int sctp_outq_flush(struct sctp_outq *q, int rtx_timeout) list_add_tail(&chunk->transmitted_list, &transport->transmitted); - sctp_transport_reset_timers(transport); + sctp_transport_reset_timers(transport, start_timer-1); q->empty = 0; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 0ec234b762c2..9258dfe784ae 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -108,14 +108,23 @@ static __init int sctp_proc_init(void) } if (sctp_snmp_proc_init()) - goto out_nomem; + goto out_snmp_proc_init; if (sctp_eps_proc_init()) - goto out_nomem; + goto out_eps_proc_init; if (sctp_assocs_proc_init()) - goto out_nomem; + goto out_assocs_proc_init; return 0; +out_assocs_proc_init: + sctp_eps_proc_exit(); +out_eps_proc_init: + sctp_snmp_proc_exit(); +out_snmp_proc_init: + if (proc_net_sctp) { + proc_net_sctp = NULL; + remove_proc_entry("sctp", init_net.proc_net); + } out_nomem: return -ENOMEM; } @@ -470,11 +479,11 @@ static struct dst_entry *sctp_v4_get_dst(struct sctp_association *asoc, /* Walk through the bind address list and look for a bind * address that matches the source address of the returned dst. */ + sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); rcu_read_lock(); list_for_each_entry_rcu(laddr, &bp->address_list, list) { if (!laddr->valid || (laddr->state != SCTP_ADDR_SRC)) continue; - sctp_v4_dst_saddr(&dst_saddr, dst, htons(bp->port)); if (sctp_v4_cmp_addr(&dst_saddr, &laddr->a)) goto out_unlock; } @@ -519,7 +528,8 @@ out: /* For v4, the source address is cached in the route entry(dst). So no need * to cache it separately and hence this is an empty routine. */ -static void sctp_v4_get_saddr(struct sctp_association *asoc, +static void sctp_v4_get_saddr(struct sctp_sock *sk, + struct sctp_association *asoc, struct dst_entry *dst, union sctp_addr *daddr, union sctp_addr *saddr) @@ -616,6 +626,11 @@ static void sctp_v4_seq_dump_addr(struct seq_file *seq, union sctp_addr *addr) seq_printf(seq, "%d.%d.%d.%d ", NIPQUAD(addr->v4.sin_addr)); } +static void sctp_v4_ecn_capable(struct sock *sk) +{ + INET_ECN_xmit(sk); +} + /* 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 @@ -934,6 +949,7 @@ static struct sctp_af sctp_af_inet = { .skb_iif = sctp_v4_skb_iif, .is_ce = sctp_v4_is_ce, .seq_dump_addr = sctp_v4_seq_dump_addr, + .ecn_capable = sctp_v4_ecn_capable, .net_header_len = sizeof(struct iphdr), .sockaddr_len = sizeof(struct sockaddr_in), #ifdef CONFIG_COMPAT diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 0c9d5a6950fe..fcdb45d1071b 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -5899,12 +5899,6 @@ static int sctp_eat_data(const struct sctp_association *asoc, return SCTP_IERROR_NO_DATA; } - /* If definately accepting the DATA chunk, record its TSN, otherwise - * wait for renege processing. - */ - if (SCTP_CMD_CHUNK_ULP == deliver) - sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); - chunk->data_accepted = 1; /* Note: Some chunks may get overcounted (if we drop) or overcounted @@ -5924,6 +5918,9 @@ static int sctp_eat_data(const struct sctp_association *asoc, * and discard the DATA chunk. */ if (ntohs(data_hdr->stream) >= asoc->c.sinit_max_instreams) { + /* Mark tsn as received even though we drop it */ + sctp_add_cmd_sf(commands, SCTP_CMD_REPORT_TSN, SCTP_U32(tsn)); + err = sctp_make_op_error(asoc, chunk, SCTP_ERROR_INV_STRM, &data_hdr->stream, sizeof(data_hdr->stream)); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index e7e3baf7009e..0dbcde6758ea 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4401,7 +4401,9 @@ static int sctp_getsockopt_local_addrs_old(struct sock *sk, int len, if (copy_from_user(&getaddrs, optval, len)) return -EFAULT; - if (getaddrs.addr_num <= 0) return -EINVAL; + if (getaddrs.addr_num <= 0 || + getaddrs.addr_num >= (INT_MAX / sizeof(union sctp_addr))) + return -EINVAL; /* * For UDP-style sockets, id specifies the association to query. * If the id field is set to the value '0' then the locally bound diff --git a/net/sctp/transport.c b/net/sctp/transport.c index f4938f6c5abe..3f34f61221ec 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -79,6 +79,7 @@ static struct sctp_transport *sctp_transport_init(struct sctp_transport *peer, peer->rttvar = 0; peer->srtt = 0; peer->rto_pending = 0; + peer->fast_recovery = 0; peer->last_time_heard = jiffies; peer->last_time_used = jiffies; @@ -190,7 +191,7 @@ static void sctp_transport_destroy(struct sctp_transport *transport) /* Start T3_rtx timer if it is not already running and update the heartbeat * timer. This routine is called every time a DATA chunk is sent. */ -void sctp_transport_reset_timers(struct sctp_transport *transport) +void sctp_transport_reset_timers(struct sctp_transport *transport, int force) { /* RFC 2960 6.3.2 Retransmission Timer Rules * @@ -200,7 +201,7 @@ void sctp_transport_reset_timers(struct sctp_transport *transport) * address. */ - if (!timer_pending(&transport->T3_rtx_timer)) + if (force || !timer_pending(&transport->T3_rtx_timer)) if (!mod_timer(&transport->T3_rtx_timer, jiffies + transport->rto)) sctp_transport_hold(transport); @@ -291,7 +292,7 @@ void sctp_transport_route(struct sctp_transport *transport, if (saddr) memcpy(&transport->saddr, saddr, sizeof(union sctp_addr)); else - af->get_saddr(asoc, dst, daddr, &transport->saddr); + af->get_saddr(opt, asoc, dst, daddr, &transport->saddr); transport->dst = dst; if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { @@ -403,11 +404,16 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, cwnd = transport->cwnd; flight_size = transport->flight_size; + /* See if we need to exit Fast Recovery first */ + if (transport->fast_recovery && + TSN_lte(transport->fast_recovery_exit, sack_ctsn)) + transport->fast_recovery = 0; + /* The appropriate cwnd increase algorithm is performed if, and only - * if the cumulative TSN has advanced and the congestion window is + * if the cumulative TSN whould advanced and the congestion window is * being fully utilized. */ - if ((transport->asoc->ctsn_ack_point >= sack_ctsn) || + if (TSN_lte(sack_ctsn, transport->asoc->ctsn_ack_point) || (flight_size < cwnd)) return; @@ -416,17 +422,23 @@ void sctp_transport_raise_cwnd(struct sctp_transport *transport, pmtu = transport->asoc->pathmtu; if (cwnd <= ssthresh) { - /* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less - * than or equal to ssthresh an SCTP endpoint MUST use the - * slow start algorithm to increase cwnd only if the current - * congestion window is being fully utilized and an incoming - * SACK advances the Cumulative TSN Ack Point. Only when these - * two conditions are met can the cwnd be increased otherwise - * the cwnd MUST not be increased. If these conditions are met - * then cwnd MUST be increased by at most the lesser of - * 1) the total size of the previously outstanding DATA - * chunk(s) acknowledged, and 2) the destination's path MTU. + /* RFC 4960 7.2.1 + * o When cwnd is less than or equal to ssthresh, an SCTP + * endpoint MUST use the slow-start algorithm to increase + * cwnd only if the current congestion window is being fully + * utilized, an incoming SACK advances the Cumulative TSN + * Ack Point, and the data sender is not in Fast Recovery. + * Only when these three conditions are met can the cwnd be + * increased; otherwise, the cwnd MUST not be increased. + * If these conditions are met, then cwnd MUST be increased + * by, at most, the lesser of 1) the total size of the + * previously outstanding DATA chunk(s) acknowledged, and + * 2) the destination's path MTU. This upper bound protects + * against the ACK-Splitting attack outlined in [SAVAGE99]. */ + if (transport->fast_recovery) + return; + if (bytes_acked > pmtu) cwnd += pmtu; else @@ -502,6 +514,13 @@ void sctp_transport_lower_cwnd(struct sctp_transport *transport, * cwnd = ssthresh * partial_bytes_acked = 0 */ + if (transport->fast_recovery) + return; + + /* Mark Fast recovery */ + transport->fast_recovery = 1; + transport->fast_recovery_exit = transport->asoc->next_tsn - 1; + transport->ssthresh = max(transport->cwnd/2, 4*transport->asoc->pathmtu); transport->cwnd = transport->ssthresh; @@ -586,6 +605,7 @@ void sctp_transport_reset(struct sctp_transport *t) t->flight_size = 0; t->error_count = 0; t->rto_pending = 0; + t->fast_recovery = 0; /* Initialize the state information for SFR-CACC */ t->cacc.changeover_active = 0; diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index ce6cda6b6994..a1f654aea268 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -710,6 +710,11 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, if (!skb) goto fail; + /* Now that all memory allocations for this chunk succeeded, we + * can mark it as received so the tsn_map is updated correctly. + */ + sctp_tsnmap_mark(&asoc->peer.tsn_map, ntohl(chunk->subh.data_hdr->tsn)); + /* First calculate the padding, so we don't inadvertently * pass up the wrong length to the user. * diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index cc12d5f5d5da..834a83199bdf 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -63,22 +63,11 @@ static const struct rpc_credops gss_nullops; # define RPCDBG_FACILITY RPCDBG_AUTH #endif -#define NFS_NGROUPS 16 - -#define GSS_CRED_SLACK 1024 /* XXX: unused */ +#define GSS_CRED_SLACK 1024 /* length of a krb5 verifier (48), plus data added before arguments when * using integrity (two 4-byte integers): */ #define GSS_VERF_SLACK 100 -/* XXX this define must match the gssd define -* as it is passed to gssd to signal the use of -* machine creds should be part of the shared rpc interface */ - -#define CA_RUN_AS_MACHINE 0x00000200 - -/* dump the buffer in `emacs-hexl' style */ -#define isprint(c) ((c > 0x1f) && (c < 0x7f)) - struct gss_auth { struct kref kref; struct rpc_auth rpc_auth; @@ -146,7 +135,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest) q = (const void *)((const char *)p + len); if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); - dest->data = kmemdup(p, len, GFP_KERNEL); + dest->data = kmemdup(p, len, GFP_NOFS); if (unlikely(dest->data == NULL)) return ERR_PTR(-ENOMEM); dest->len = len; @@ -171,7 +160,7 @@ gss_alloc_context(void) { struct gss_cl_ctx *ctx; - ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + ctx = kzalloc(sizeof(*ctx), GFP_NOFS); if (ctx != NULL) { ctx->gc_proc = RPC_GSS_PROC_DATA; ctx->gc_seq = 1; /* NetApp 6.4R1 doesn't accept seq. no. 0 */ @@ -272,7 +261,7 @@ __gss_find_upcall(struct rpc_inode *rpci, uid_t uid) return NULL; } -/* Try to add a upcall to the pipefs queue. +/* Try to add an upcall to the pipefs queue. * If an upcall owned by our uid already exists, then we return a reference * to that upcall instead of adding the new upcall. */ @@ -341,7 +330,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, uid_t uid) { struct gss_upcall_msg *gss_msg; - gss_msg = kzalloc(sizeof(*gss_msg), GFP_KERNEL); + gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS); if (gss_msg != NULL) { INIT_LIST_HEAD(&gss_msg->list); rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq"); @@ -493,7 +482,6 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { const void *p, *end; void *buf; - struct rpc_clnt *clnt; struct gss_upcall_msg *gss_msg; struct inode *inode = filp->f_path.dentry->d_inode; struct gss_cl_ctx *ctx; @@ -503,11 +491,10 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) if (mlen > MSG_BUF_MAXSIZE) goto out; err = -ENOMEM; - buf = kmalloc(mlen, GFP_KERNEL); + buf = kmalloc(mlen, GFP_NOFS); if (!buf) goto out; - clnt = RPC_I(inode)->private; err = -EFAULT; if (copy_from_user(buf, src, mlen)) goto err; @@ -806,7 +793,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) dprintk("RPC: gss_create_cred for uid %d, flavor %d\n", acred->uid, auth->au_flavor); - if (!(cred = kzalloc(sizeof(*cred), GFP_KERNEL))) + if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS))) goto out_err; rpcauth_init_cred(&cred->gc_base, acred, auth, &gss_credops); diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 60c3dba545d7..ef45eba22485 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -70,7 +70,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res) q = (const void *)((const char *)p + len); if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); - res->data = kmemdup(p, len, GFP_KERNEL); + res->data = kmemdup(p, len, GFP_NOFS); if (unlikely(res->data == NULL)) return ERR_PTR(-ENOMEM); res->len = len; @@ -131,7 +131,7 @@ gss_import_sec_context_kerberos(const void *p, struct krb5_ctx *ctx; int tmp; - if (!(ctx = kzalloc(sizeof(*ctx), GFP_KERNEL))) + if (!(ctx = kzalloc(sizeof(*ctx), GFP_NOFS))) goto out_err; p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate)); diff --git a/net/sunrpc/auth_gss/gss_spkm3_mech.c b/net/sunrpc/auth_gss/gss_spkm3_mech.c index 5deb4b6e4514..035e1dd6af1b 100644 --- a/net/sunrpc/auth_gss/gss_spkm3_mech.c +++ b/net/sunrpc/auth_gss/gss_spkm3_mech.c @@ -76,7 +76,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res) q = (const void *)((const char *)p + len); if (unlikely(q > end || q < p)) return ERR_PTR(-EFAULT); - res->data = kmemdup(p, len, GFP_KERNEL); + res->data = kmemdup(p, len, GFP_NOFS); if (unlikely(res->data == NULL)) return ERR_PTR(-ENOMEM); return q; @@ -90,7 +90,7 @@ gss_import_sec_context_spkm3(const void *p, size_t len, struct spkm3_ctx *ctx; int version; - if (!(ctx = kzalloc(sizeof(*ctx), GFP_KERNEL))) + if (!(ctx = kzalloc(sizeof(*ctx), GFP_NOFS))) goto out_err; p = simple_get_bytes(p, end, &version, sizeof(version)); diff --git a/net/sunrpc/auth_gss/gss_spkm3_token.c b/net/sunrpc/auth_gss/gss_spkm3_token.c index 6cdd241ad267..3308157436d2 100644 --- a/net/sunrpc/auth_gss/gss_spkm3_token.c +++ b/net/sunrpc/auth_gss/gss_spkm3_token.c @@ -90,7 +90,7 @@ asn1_bitstring_len(struct xdr_netobj *in, int *enclen, int *zerobits) int decode_asn1_bitstring(struct xdr_netobj *out, char *in, int enclen, int explen) { - if (!(out->data = kzalloc(explen,GFP_KERNEL))) + if (!(out->data = kzalloc(explen,GFP_NOFS))) return 0; out->len = explen; memcpy(out->data, in, enclen); diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 5905d56737d6..81ae3d62a0cc 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -1144,20 +1144,20 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) case RPC_GSS_SVC_NONE: break; case RPC_GSS_SVC_INTEGRITY: + /* placeholders for length and seq. number: */ + svc_putnl(resv, 0); + svc_putnl(resv, 0); if (unwrap_integ_data(&rqstp->rq_arg, gc->gc_seq, rsci->mechctx)) goto garbage_args; + break; + case RPC_GSS_SVC_PRIVACY: /* placeholders for length and seq. number: */ svc_putnl(resv, 0); svc_putnl(resv, 0); - break; - case RPC_GSS_SVC_PRIVACY: if (unwrap_priv_data(rqstp, &rqstp->rq_arg, gc->gc_seq, rsci->mechctx)) goto garbage_args; - /* placeholders for length and seq. number: */ - svc_putnl(resv, 0); - svc_putnl(resv, 0); break; default: goto auth_err; @@ -1170,8 +1170,6 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp) goto out; } garbage_args: - /* Restore write pointer to its original value: */ - xdr_ressize_check(rqstp, reject_stat); ret = SVC_GARBAGE; goto out; auth_err: diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index 44920b90bdc4..46b2647c5bd2 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -66,7 +66,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags) dprintk("RPC: allocating UNIX cred for uid %d gid %d\n", acred->uid, acred->gid); - if (!(cred = kmalloc(sizeof(*cred), GFP_KERNEL))) + if (!(cred = kmalloc(sizeof(*cred), GFP_NOFS))) return ERR_PTR(-ENOMEM); rpcauth_init_cred(&cred->uc_base, acred, auth, &unix_credops); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 8945307556ec..76739e928d0d 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -25,6 +25,7 @@ #include <linux/module.h> #include <linux/types.h> +#include <linux/kallsyms.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/smp_lock.h> @@ -58,7 +59,6 @@ static void call_start(struct rpc_task *task); static void call_reserve(struct rpc_task *task); static void call_reserveresult(struct rpc_task *task); static void call_allocate(struct rpc_task *task); -static void call_encode(struct rpc_task *task); static void call_decode(struct rpc_task *task); static void call_bind(struct rpc_task *task); static void call_bind_status(struct rpc_task *task); @@ -70,9 +70,9 @@ static void call_refreshresult(struct rpc_task *task); static void call_timeout(struct rpc_task *task); static void call_connect(struct rpc_task *task); static void call_connect_status(struct rpc_task *task); -static __be32 * call_header(struct rpc_task *task); -static __be32 * call_verify(struct rpc_task *task); +static __be32 *rpc_encode_header(struct rpc_task *task); +static __be32 *rpc_verify_header(struct rpc_task *task); static int rpc_ping(struct rpc_clnt *clnt, int flags); static void rpc_register_client(struct rpc_clnt *clnt) @@ -324,6 +324,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) clnt->cl_autobind = 1; if (args->flags & RPC_CLNT_CREATE_DISCRTRY) clnt->cl_discrtry = 1; + if (!(args->flags & RPC_CLNT_CREATE_QUIET)) + clnt->cl_chatty = 1; return clnt; } @@ -690,6 +692,21 @@ rpc_restart_call(struct rpc_task *task) } EXPORT_SYMBOL_GPL(rpc_restart_call); +#ifdef RPC_DEBUG +static const char *rpc_proc_name(const struct rpc_task *task) +{ + const struct rpc_procinfo *proc = task->tk_msg.rpc_proc; + + if (proc) { + if (proc->p_name) + return proc->p_name; + else + return "NULL"; + } else + return "no proc"; +} +#endif + /* * 0. Initial state * @@ -701,9 +718,9 @@ call_start(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; - dprintk("RPC: %5u call_start %s%d proc %d (%s)\n", task->tk_pid, + dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid, clnt->cl_protname, clnt->cl_vers, - task->tk_msg.rpc_proc->p_proc, + rpc_proc_name(task), (RPC_IS_ASYNC(task) ? "async" : "sync")); /* Increment call count */ @@ -861,7 +878,7 @@ rpc_xdr_buf_init(struct xdr_buf *buf, void *start, size_t len) * 3. Encode arguments of an RPC call */ static void -call_encode(struct rpc_task *task) +rpc_xdr_encode(struct rpc_task *task) { struct rpc_rqst *req = task->tk_rqstp; kxdrproc_t encode; @@ -876,23 +893,19 @@ call_encode(struct rpc_task *task) (char *)req->rq_buffer + req->rq_callsize, req->rq_rcvsize); - /* Encode header and provided arguments */ - encode = task->tk_msg.rpc_proc->p_encode; - if (!(p = call_header(task))) { - printk(KERN_INFO "RPC: call_header failed, exit EIO\n"); + p = rpc_encode_header(task); + if (p == NULL) { + printk(KERN_INFO "RPC: couldn't encode RPC header, exit EIO\n"); rpc_exit(task, -EIO); return; } + + encode = task->tk_msg.rpc_proc->p_encode; if (encode == NULL) return; task->tk_status = rpcauth_wrap_req(task, encode, req, p, task->tk_msg.rpc_argp); - if (task->tk_status == -ENOMEM) { - /* XXX: Is this sane? */ - rpc_delay(task, 3*HZ); - task->tk_status = -EAGAIN; - } } /* @@ -929,11 +942,9 @@ call_bind_status(struct rpc_task *task) } switch (task->tk_status) { - case -EAGAIN: - dprintk("RPC: %5u rpcbind waiting for another request " - "to finish\n", task->tk_pid); - /* avoid busy-waiting here -- could be a network outage. */ - rpc_delay(task, 5*HZ); + case -ENOMEM: + dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid); + rpc_delay(task, HZ >> 2); goto retry_timeout; case -EACCES: dprintk("RPC: %5u remote rpcbind: RPC program/version " @@ -1046,10 +1057,16 @@ call_transmit(struct rpc_task *task) /* Encode here so that rpcsec_gss can use correct sequence number. */ if (rpc_task_need_encode(task)) { BUG_ON(task->tk_rqstp->rq_bytes_sent != 0); - call_encode(task); + rpc_xdr_encode(task); /* Did the encode result in an error condition? */ - if (task->tk_status != 0) + if (task->tk_status != 0) { + /* Was the error nonfatal? */ + if (task->tk_status == -EAGAIN) + rpc_delay(task, HZ >> 4); + else + rpc_exit(task, task->tk_status); return; + } } xprt_transmit(task); if (task->tk_status < 0) @@ -1132,7 +1149,8 @@ call_status(struct rpc_task *task) rpc_exit(task, status); break; default: - printk("%s: RPC call returned error %d\n", + if (clnt->cl_chatty) + printk("%s: RPC call returned error %d\n", clnt->cl_protname, -status); rpc_exit(task, status); } @@ -1157,7 +1175,8 @@ call_timeout(struct rpc_task *task) task->tk_timeouts++; if (RPC_IS_SOFT(task)) { - printk(KERN_NOTICE "%s: server %s not responding, timed out\n", + if (clnt->cl_chatty) + printk(KERN_NOTICE "%s: server %s not responding, timed out\n", clnt->cl_protname, clnt->cl_server); rpc_exit(task, -EIO); return; @@ -1165,7 +1184,8 @@ call_timeout(struct rpc_task *task) if (!(task->tk_flags & RPC_CALL_MAJORSEEN)) { task->tk_flags |= RPC_CALL_MAJORSEEN; - printk(KERN_NOTICE "%s: server %s not responding, still trying\n", + if (clnt->cl_chatty) + printk(KERN_NOTICE "%s: server %s not responding, still trying\n", clnt->cl_protname, clnt->cl_server); } rpc_force_rebind(clnt); @@ -1196,8 +1216,9 @@ call_decode(struct rpc_task *task) task->tk_pid, task->tk_status); if (task->tk_flags & RPC_CALL_MAJORSEEN) { - printk(KERN_NOTICE "%s: server %s OK\n", - clnt->cl_protname, clnt->cl_server); + if (clnt->cl_chatty) + printk(KERN_NOTICE "%s: server %s OK\n", + clnt->cl_protname, clnt->cl_server); task->tk_flags &= ~RPC_CALL_MAJORSEEN; } @@ -1224,8 +1245,7 @@ call_decode(struct rpc_task *task) goto out_retry; } - /* Verify the RPC header */ - p = call_verify(task); + p = rpc_verify_header(task); if (IS_ERR(p)) { if (p == ERR_PTR(-EAGAIN)) goto out_retry; @@ -1243,7 +1263,7 @@ call_decode(struct rpc_task *task) return; out_retry: task->tk_status = 0; - /* Note: call_verify() may have freed the RPC slot */ + /* Note: rpc_verify_header() may have freed the RPC slot */ if (task->tk_rqstp == req) { req->rq_received = req->rq_rcv_buf.len = 0; if (task->tk_client->cl_discrtry) @@ -1290,11 +1310,8 @@ call_refreshresult(struct rpc_task *task) return; } -/* - * Call header serialization - */ static __be32 * -call_header(struct rpc_task *task) +rpc_encode_header(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; struct rpc_rqst *req = task->tk_rqstp; @@ -1314,11 +1331,8 @@ call_header(struct rpc_task *task) return p; } -/* - * Reply header verification - */ static __be32 * -call_verify(struct rpc_task *task) +rpc_verify_header(struct rpc_task *task) { struct kvec *iov = &task->tk_rqstp->rq_rcv_buf.head[0]; int len = task->tk_rqstp->rq_rcv_buf.len >> 2; @@ -1392,7 +1406,7 @@ call_verify(struct rpc_task *task) task->tk_action = call_bind; goto out_retry; case RPC_AUTH_TOOWEAK: - printk(KERN_NOTICE "call_verify: server %s requires stronger " + printk(KERN_NOTICE "RPC: server %s requires stronger " "authentication.\n", task->tk_client->cl_server); break; default: @@ -1431,10 +1445,10 @@ call_verify(struct rpc_task *task) error = -EPROTONOSUPPORT; goto out_err; case RPC_PROC_UNAVAIL: - dprintk("RPC: %5u %s: proc %p unsupported by program %u, " + dprintk("RPC: %5u %s: proc %s unsupported by program %u, " "version %u on server %s\n", task->tk_pid, __func__, - task->tk_msg.rpc_proc, + rpc_proc_name(task), task->tk_client->cl_prog, task->tk_client->cl_vers, task->tk_client->cl_server); @@ -1517,44 +1531,53 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int EXPORT_SYMBOL_GPL(rpc_call_null); #ifdef RPC_DEBUG +static void rpc_show_header(void) +{ + printk(KERN_INFO "-pid- flgs status -client- --rqstp- " + "-timeout ---ops--\n"); +} + +static void rpc_show_task(const struct rpc_clnt *clnt, + const struct rpc_task *task) +{ + const char *rpc_waitq = "none"; + char *p, action[KSYM_SYMBOL_LEN]; + + if (RPC_IS_QUEUED(task)) + rpc_waitq = rpc_qname(task->tk_waitqueue); + + /* map tk_action pointer to a function name; then trim off + * the "+0x0 [sunrpc]" */ + sprint_symbol(action, (unsigned long)task->tk_action); + p = strchr(action, '+'); + if (p) + *p = '\0'; + + printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%s q:%s\n", + task->tk_pid, task->tk_flags, task->tk_status, + clnt, task->tk_rqstp, task->tk_timeout, task->tk_ops, + clnt->cl_protname, clnt->cl_vers, rpc_proc_name(task), + action, rpc_waitq); +} + void rpc_show_tasks(void) { struct rpc_clnt *clnt; - struct rpc_task *t; + struct rpc_task *task; + int header = 0; spin_lock(&rpc_client_lock); - if (list_empty(&all_clients)) - goto out; - printk("-pid- proc flgs status -client- -prog- --rqstp- -timeout " - "-rpcwait -action- ---ops--\n"); list_for_each_entry(clnt, &all_clients, cl_clients) { - if (list_empty(&clnt->cl_tasks)) - continue; spin_lock(&clnt->cl_lock); - list_for_each_entry(t, &clnt->cl_tasks, tk_task) { - const char *rpc_waitq = "none"; - int proc; - - if (t->tk_msg.rpc_proc) - proc = t->tk_msg.rpc_proc->p_proc; - else - proc = -1; - - if (RPC_IS_QUEUED(t)) - rpc_waitq = rpc_qname(t->tk_waitqueue); - - printk("%5u %04d %04x %6d %8p %6d %8p %8ld %8s %8p %8p\n", - t->tk_pid, proc, - t->tk_flags, t->tk_status, - t->tk_client, - (t->tk_client ? t->tk_client->cl_prog : 0), - t->tk_rqstp, t->tk_timeout, - rpc_waitq, - t->tk_action, t->tk_ops); + list_for_each_entry(task, &clnt->cl_tasks, tk_task) { + if (!header) { + rpc_show_header(); + header++; + } + rpc_show_task(clnt, task); } spin_unlock(&clnt->cl_lock); } -out: spin_unlock(&rpc_client_lock); } #endif diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 0517967a68bf..24db2b4d12d3 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -32,6 +32,10 @@ #define RPCBIND_PROGRAM (100000u) #define RPCBIND_PORT (111u) +#define RPCBVERS_2 (2u) +#define RPCBVERS_3 (3u) +#define RPCBVERS_4 (4u) + enum { RPCBPROC_NULL, RPCBPROC_SET, @@ -64,6 +68,7 @@ enum { #define RPCB_MAXOWNERLEN sizeof(RPCB_OWNER_STRING) static void rpcb_getport_done(struct rpc_task *, void *); +static void rpcb_map_release(void *data); static struct rpc_program rpcb_program; struct rpcbind_args { @@ -76,41 +81,73 @@ struct rpcbind_args { const char * r_netid; const char * r_addr; const char * r_owner; + + int r_status; }; static struct rpc_procinfo rpcb_procedures2[]; static struct rpc_procinfo rpcb_procedures3[]; +static struct rpc_procinfo rpcb_procedures4[]; struct rpcb_info { - int rpc_vers; + u32 rpc_vers; struct rpc_procinfo * rpc_proc; }; static struct rpcb_info rpcb_next_version[]; static struct rpcb_info rpcb_next_version6[]; +static const struct rpc_call_ops rpcb_getport_ops = { + .rpc_call_done = rpcb_getport_done, + .rpc_release = rpcb_map_release, +}; + +static void rpcb_wake_rpcbind_waiters(struct rpc_xprt *xprt, int status) +{ + xprt_clear_binding(xprt); + rpc_wake_up_status(&xprt->binding, status); +} + static void rpcb_map_release(void *data) { struct rpcbind_args *map = data; + rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status); xprt_put(map->r_xprt); kfree(map); } -static const struct rpc_call_ops rpcb_getport_ops = { - .rpc_call_done = rpcb_getport_done, - .rpc_release = rpcb_map_release, +static const struct sockaddr_in rpcb_inaddr_loopback = { + .sin_family = AF_INET, + .sin_addr.s_addr = htonl(INADDR_LOOPBACK), + .sin_port = htons(RPCBIND_PORT), }; -static void rpcb_wake_rpcbind_waiters(struct rpc_xprt *xprt, int status) +static const struct sockaddr_in6 rpcb_in6addr_loopback = { + .sin6_family = AF_INET6, + .sin6_addr = IN6ADDR_LOOPBACK_INIT, + .sin6_port = htons(RPCBIND_PORT), +}; + +static struct rpc_clnt *rpcb_create_local(struct sockaddr *addr, + size_t addrlen, u32 version) { - xprt_clear_binding(xprt); - rpc_wake_up_status(&xprt->binding, status); + struct rpc_create_args args = { + .protocol = XPRT_TRANSPORT_UDP, + .address = addr, + .addrsize = addrlen, + .servername = "localhost", + .program = &rpcb_program, + .version = version, + .authflavor = RPC_AUTH_UNIX, + .flags = RPC_CLNT_CREATE_NOPING, + }; + + return rpc_create(&args); } static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, - size_t salen, int proto, u32 version, - int privileged) + size_t salen, int proto, u32 version) { struct rpc_create_args args = { .protocol = proto, @@ -120,7 +157,8 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, .program = &rpcb_program, .version = version, .authflavor = RPC_AUTH_UNIX, - .flags = RPC_CLNT_CREATE_NOPING, + .flags = (RPC_CLNT_CREATE_NOPING | + RPC_CLNT_CREATE_NONPRIVPORT), }; switch (srvaddr->sa_family) { @@ -134,29 +172,72 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr, return NULL; } - if (!privileged) - args.flags |= RPC_CLNT_CREATE_NONPRIVPORT; return rpc_create(&args); } +static int rpcb_register_call(struct sockaddr *addr, size_t addrlen, + u32 version, struct rpc_message *msg, + int *result) +{ + struct rpc_clnt *rpcb_clnt; + int error = 0; + + *result = 0; + + rpcb_clnt = rpcb_create_local(addr, addrlen, version); + if (!IS_ERR(rpcb_clnt)) { + error = rpc_call_sync(rpcb_clnt, msg, 0); + rpc_shutdown_client(rpcb_clnt); + } else + error = PTR_ERR(rpcb_clnt); + + if (error < 0) + printk(KERN_WARNING "RPC: failed to contact local rpcbind " + "server (errno %d).\n", -error); + dprintk("RPC: registration status %d/%d\n", error, *result); + + return error; +} + /** * rpcb_register - set or unset a port registration with the local rpcbind svc * @prog: RPC program number to bind * @vers: RPC version number to bind - * @prot: transport protocol to use to make this request + * @prot: transport protocol to register * @port: port value to register - * @okay: result code + * @okay: OUT: result code + * + * RPC services invoke this function to advertise their contact + * information via the system's rpcbind daemon. RPC services + * invoke this function once for each [program, version, transport] + * tuple they wish to advertise. + * + * Callers may also unregister RPC services that are no longer + * available by setting the passed-in port to zero. This removes + * all registered transports for [program, version] from the local + * rpcbind database. + * + * Returns zero if the registration request was dispatched + * successfully and a reply was received. The rpcbind daemon's + * boolean result code is stored in *okay. + * + * Returns an errno value and sets *result to zero if there was + * some problem that prevented the rpcbind request from being + * dispatched, or if the rpcbind daemon did not respond within + * the timeout. * - * port == 0 means unregister, port != 0 means register. + * This function uses rpcbind protocol version 2 to contact the + * local rpcbind daemon. * - * This routine supports only rpcbind version 2. + * Registration works over both AF_INET and AF_INET6, and services + * registered via this function are advertised as available for any + * address. If the local rpcbind daemon is listening on AF_INET6, + * services registered via this function will be advertised on + * IN6ADDR_ANY (ie available for all AF_INET and AF_INET6 + * addresses). */ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay) { - struct sockaddr_in sin = { - .sin_family = AF_INET, - .sin_addr.s_addr = htonl(INADDR_LOOPBACK), - }; struct rpcbind_args map = { .r_prog = prog, .r_vers = vers, @@ -164,32 +245,159 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay) .r_port = port, }; struct rpc_message msg = { - .rpc_proc = &rpcb_procedures2[port ? - RPCBPROC_SET : RPCBPROC_UNSET], .rpc_argp = &map, .rpc_resp = okay, }; - struct rpc_clnt *rpcb_clnt; - int error = 0; dprintk("RPC: %sregistering (%u, %u, %d, %u) with local " "rpcbind\n", (port ? "" : "un"), prog, vers, prot, port); - rpcb_clnt = rpcb_create("localhost", (struct sockaddr *) &sin, - sizeof(sin), XPRT_TRANSPORT_UDP, 2, 1); - if (IS_ERR(rpcb_clnt)) - return PTR_ERR(rpcb_clnt); + msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET]; + if (port) + msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET]; - error = rpc_call_sync(rpcb_clnt, &msg, 0); + return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback, + sizeof(rpcb_inaddr_loopback), + RPCBVERS_2, &msg, okay); +} - rpc_shutdown_client(rpcb_clnt); - if (error < 0) - printk(KERN_WARNING "RPC: failed to contact local rpcbind " - "server (errno %d).\n", -error); - dprintk("RPC: registration status %d/%d\n", error, *okay); +/* + * Fill in AF_INET family-specific arguments to register + */ +static int rpcb_register_netid4(struct sockaddr_in *address_to_register, + struct rpc_message *msg) +{ + struct rpcbind_args *map = msg->rpc_argp; + unsigned short port = ntohs(address_to_register->sin_port); + char buf[32]; + + /* Construct AF_INET universal address */ + snprintf(buf, sizeof(buf), + NIPQUAD_FMT".%u.%u", + NIPQUAD(address_to_register->sin_addr.s_addr), + port >> 8, port & 0xff); + map->r_addr = buf; + + dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " + "local rpcbind\n", (port ? "" : "un"), + map->r_prog, map->r_vers, + map->r_addr, map->r_netid); + + msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; + if (port) + msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + + return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback, + sizeof(rpcb_inaddr_loopback), + RPCBVERS_4, msg, msg->rpc_resp); +} - return error; +/* + * Fill in AF_INET6 family-specific arguments to register + */ +static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register, + struct rpc_message *msg) +{ + struct rpcbind_args *map = msg->rpc_argp; + unsigned short port = ntohs(address_to_register->sin6_port); + char buf[64]; + + /* Construct AF_INET6 universal address */ + snprintf(buf, sizeof(buf), + NIP6_FMT".%u.%u", + NIP6(address_to_register->sin6_addr), + port >> 8, port & 0xff); + map->r_addr = buf; + + dprintk("RPC: %sregistering [%u, %u, %s, '%s'] with " + "local rpcbind\n", (port ? "" : "un"), + map->r_prog, map->r_vers, + map->r_addr, map->r_netid); + + msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET]; + if (port) + msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET]; + + return rpcb_register_call((struct sockaddr *)&rpcb_in6addr_loopback, + sizeof(rpcb_in6addr_loopback), + RPCBVERS_4, msg, msg->rpc_resp); +} + +/** + * rpcb_v4_register - set or unset a port registration with the local rpcbind + * @program: RPC program number of service to (un)register + * @version: RPC version number of service to (un)register + * @address: address family, IP address, and port to (un)register + * @netid: netid of transport protocol to (un)register + * @result: result code from rpcbind RPC call + * + * RPC services invoke this function to advertise their contact + * information via the system's rpcbind daemon. RPC services + * invoke this function once for each [program, version, address, + * netid] tuple they wish to advertise. + * + * Callers may also unregister RPC services that are no longer + * available by setting the port number in the passed-in address + * to zero. Callers pass a netid of "" to unregister all + * transport netids associated with [program, version, address]. + * + * Returns zero if the registration request was dispatched + * successfully and a reply was received. The rpcbind daemon's + * result code is stored in *result. + * + * Returns an errno value and sets *result to zero if there was + * some problem that prevented the rpcbind request from being + * dispatched, or if the rpcbind daemon did not respond within + * the timeout. + * + * This function uses rpcbind protocol version 4 to contact the + * local rpcbind daemon. The local rpcbind daemon must support + * version 4 of the rpcbind protocol in order for these functions + * to register a service successfully. + * + * Supported netids include "udp" and "tcp" for UDP and TCP over + * IPv4, and "udp6" and "tcp6" for UDP and TCP over IPv6, + * respectively. + * + * The contents of @address determine the address family and the + * port to be registered. The usual practice is to pass INADDR_ANY + * as the raw address, but specifying a non-zero address is also + * supported by this API if the caller wishes to advertise an RPC + * service on a specific network interface. + * + * Note that passing in INADDR_ANY does not create the same service + * registration as IN6ADDR_ANY. The former advertises an RPC + * service on any IPv4 address, but not on IPv6. The latter + * advertises the service on all IPv4 and IPv6 addresses. + */ +int rpcb_v4_register(const u32 program, const u32 version, + const struct sockaddr *address, const char *netid, + int *result) +{ + struct rpcbind_args map = { + .r_prog = program, + .r_vers = version, + .r_netid = netid, + .r_owner = RPCB_OWNER_STRING, + }; + struct rpc_message msg = { + .rpc_argp = &map, + .rpc_resp = result, + }; + + *result = 0; + + switch (address->sa_family) { + case AF_INET: + return rpcb_register_netid4((struct sockaddr_in *)address, + &msg); + case AF_INET6: + return rpcb_register_netid6((struct sockaddr_in6 *)address, + &msg); + } + + return -EAFNOSUPPORT; } /** @@ -227,7 +435,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) __func__, NIPQUAD(sin->sin_addr.s_addr), prog, vers, prot); rpcb_clnt = rpcb_create(NULL, (struct sockaddr *)sin, - sizeof(*sin), prot, 2, 0); + sizeof(*sin), prot, RPCBVERS_2); if (IS_ERR(rpcb_clnt)) return PTR_ERR(rpcb_clnt); @@ -243,10 +451,10 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot) } EXPORT_SYMBOL_GPL(rpcb_getport_sync); -static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, int version) +static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbind_args *map, struct rpc_procinfo *proc) { struct rpc_message msg = { - .rpc_proc = rpcb_next_version[version].rpc_proc, + .rpc_proc = proc, .rpc_argp = map, .rpc_resp = &map->r_port, }; @@ -271,6 +479,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi void rpcb_getport_async(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + struct rpc_procinfo *proc; u32 bind_version; struct rpc_xprt *xprt = task->tk_xprt; struct rpc_clnt *rpcb_clnt; @@ -280,7 +489,6 @@ void rpcb_getport_async(struct rpc_task *task) struct sockaddr *sap = (struct sockaddr *)&addr; size_t salen; int status; - struct rpcb_info *info; dprintk("RPC: %5u %s(%s, %u, %u, %d)\n", task->tk_pid, __func__, @@ -289,17 +497,16 @@ void rpcb_getport_async(struct rpc_task *task) /* Autobind on cloned rpc clients is discouraged */ BUG_ON(clnt->cl_parent != clnt); + /* Put self on the wait queue to ensure we get notified if + * some other task is already attempting to bind the port */ + rpc_sleep_on(&xprt->binding, task, NULL); + if (xprt_test_and_set_binding(xprt)) { - status = -EAGAIN; /* tell caller to check again */ dprintk("RPC: %5u %s: waiting for another binder\n", task->tk_pid, __func__); - goto bailout_nowake; + return; } - /* Put self on queue before sending rpcbind request, in case - * rpcb_getport_done completes before we return from rpc_run_task */ - rpc_sleep_on(&xprt->binding, task, NULL); - /* Someone else may have bound if we slept */ if (xprt_bound(xprt)) { status = 0; @@ -313,10 +520,12 @@ void rpcb_getport_async(struct rpc_task *task) /* Don't ever use rpcbind v2 for AF_INET6 requests */ switch (sap->sa_family) { case AF_INET: - info = rpcb_next_version; + proc = rpcb_next_version[xprt->bind_index].rpc_proc; + bind_version = rpcb_next_version[xprt->bind_index].rpc_vers; break; case AF_INET6: - info = rpcb_next_version6; + proc = rpcb_next_version6[xprt->bind_index].rpc_proc; + bind_version = rpcb_next_version6[xprt->bind_index].rpc_vers; break; default: status = -EAFNOSUPPORT; @@ -324,20 +533,19 @@ void rpcb_getport_async(struct rpc_task *task) task->tk_pid, __func__); goto bailout_nofree; } - if (info[xprt->bind_index].rpc_proc == NULL) { + if (proc == NULL) { xprt->bind_index = 0; status = -EPFNOSUPPORT; dprintk("RPC: %5u %s: no more getport versions available\n", task->tk_pid, __func__); goto bailout_nofree; } - bind_version = info[xprt->bind_index].rpc_vers; dprintk("RPC: %5u %s: trying rpcbind version %u\n", task->tk_pid, __func__, bind_version); rpcb_clnt = rpcb_create(clnt->cl_server, sap, salen, xprt->prot, - bind_version, 0); + bind_version); if (IS_ERR(rpcb_clnt)) { status = PTR_ERR(rpcb_clnt); dprintk("RPC: %5u %s: rpcb_create failed, error %ld\n", @@ -360,26 +568,23 @@ void rpcb_getport_async(struct rpc_task *task) map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID); map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR); map->r_owner = RPCB_OWNER_STRING; /* ignored for GETADDR */ + map->r_status = -EIO; - child = rpcb_call_async(rpcb_clnt, map, xprt->bind_index); + child = rpcb_call_async(rpcb_clnt, map, proc); rpc_release_client(rpcb_clnt); if (IS_ERR(child)) { - status = -EIO; + /* rpcb_map_release() has freed the arguments */ dprintk("RPC: %5u %s: rpc_run_task failed\n", task->tk_pid, __func__); - goto bailout; + return; } rpc_put_task(child); task->tk_xprt->stat.bind_count++; return; -bailout: - kfree(map); - xprt_put(xprt); bailout_nofree: rpcb_wake_rpcbind_waiters(xprt, status); -bailout_nowake: task->tk_status = status; } EXPORT_SYMBOL_GPL(rpcb_getport_async); @@ -418,9 +623,13 @@ static void rpcb_getport_done(struct rpc_task *child, void *data) dprintk("RPC: %5u rpcb_getport_done(status %d, port %u)\n", child->tk_pid, status, map->r_port); - rpcb_wake_rpcbind_waiters(xprt, status); + map->r_status = status; } +/* + * XDR functions for rpcbind + */ + static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p, struct rpcbind_args *rpcb) { @@ -439,7 +648,7 @@ static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p, unsigned short *portp) { *portp = (unsigned short) ntohl(*p++); - dprintk("RPC: rpcb_decode_getport result %u\n", + dprintk("RPC: rpcb_decode_getport result %u\n", *portp); return 0; } @@ -448,8 +657,8 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p, unsigned int *boolp) { *boolp = (unsigned int) ntohl(*p++); - dprintk("RPC: rpcb_decode_set result %u\n", - *boolp); + dprintk("RPC: rpcb_decode_set: call %s\n", + (*boolp ? "succeeded" : "failed")); return 0; } @@ -572,52 +781,60 @@ out_err: static struct rpc_procinfo rpcb_procedures2[] = { PROC(SET, mapping, set), PROC(UNSET, mapping, set), - PROC(GETADDR, mapping, getport), + PROC(GETPORT, mapping, getport), }; static struct rpc_procinfo rpcb_procedures3[] = { - PROC(SET, mapping, set), - PROC(UNSET, mapping, set), + PROC(SET, getaddr, set), + PROC(UNSET, getaddr, set), PROC(GETADDR, getaddr, getaddr), }; static struct rpc_procinfo rpcb_procedures4[] = { - PROC(SET, mapping, set), - PROC(UNSET, mapping, set), + PROC(SET, getaddr, set), + PROC(UNSET, getaddr, set), + PROC(GETADDR, getaddr, getaddr), PROC(GETVERSADDR, getaddr, getaddr), }; static struct rpcb_info rpcb_next_version[] = { -#ifdef CONFIG_SUNRPC_BIND34 - { 4, &rpcb_procedures4[RPCBPROC_GETVERSADDR] }, - { 3, &rpcb_procedures3[RPCBPROC_GETADDR] }, -#endif - { 2, &rpcb_procedures2[RPCBPROC_GETPORT] }, - { 0, NULL }, + { + .rpc_vers = RPCBVERS_2, + .rpc_proc = &rpcb_procedures2[RPCBPROC_GETPORT], + }, + { + .rpc_proc = NULL, + }, }; static struct rpcb_info rpcb_next_version6[] = { -#ifdef CONFIG_SUNRPC_BIND34 - { 4, &rpcb_procedures4[RPCBPROC_GETVERSADDR] }, - { 3, &rpcb_procedures3[RPCBPROC_GETADDR] }, -#endif - { 0, NULL }, + { + .rpc_vers = RPCBVERS_4, + .rpc_proc = &rpcb_procedures4[RPCBPROC_GETADDR], + }, + { + .rpc_vers = RPCBVERS_3, + .rpc_proc = &rpcb_procedures3[RPCBPROC_GETADDR], + }, + { + .rpc_proc = NULL, + }, }; static struct rpc_version rpcb_version2 = { - .number = 2, + .number = RPCBVERS_2, .nrprocs = RPCB_HIGHPROC_2, .procs = rpcb_procedures2 }; static struct rpc_version rpcb_version3 = { - .number = 3, + .number = RPCBVERS_3, .nrprocs = RPCB_HIGHPROC_3, .procs = rpcb_procedures3 }; static struct rpc_version rpcb_version4 = { - .number = 4, + .number = RPCBVERS_4, .nrprocs = RPCB_HIGHPROC_4, .procs = rpcb_procedures4 }; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 6eab9bf94baf..385f427bedad 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -576,9 +576,7 @@ EXPORT_SYMBOL_GPL(rpc_delay); */ static void rpc_prepare_task(struct rpc_task *task) { - lock_kernel(); task->tk_ops->rpc_call_prepare(task, task->tk_calldata); - unlock_kernel(); } /* @@ -588,9 +586,7 @@ void rpc_exit_task(struct rpc_task *task) { task->tk_action = NULL; if (task->tk_ops->rpc_call_done != NULL) { - lock_kernel(); task->tk_ops->rpc_call_done(task, task->tk_calldata); - unlock_kernel(); if (task->tk_action != NULL) { WARN_ON(RPC_ASSASSINATED(task)); /* Always release the RPC slot and buffer memory */ @@ -602,11 +598,8 @@ EXPORT_SYMBOL_GPL(rpc_exit_task); void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata) { - if (ops->rpc_release != NULL) { - lock_kernel(); + if (ops->rpc_release != NULL) ops->rpc_release(calldata); - unlock_kernel(); - } } /* @@ -626,19 +619,15 @@ static void __rpc_execute(struct rpc_task *task) /* * Execute any pending callback. */ - if (RPC_DO_CALLBACK(task)) { - /* Define a callback save pointer */ + if (task->tk_callback) { void (*save_callback)(struct rpc_task *); /* - * If a callback exists, save it, reset it, - * call it. - * The save is needed to stop from resetting - * another callback set within the callback handler - * - Dave + * We set tk_callback to NULL before calling it, + * in case it sets the tk_callback field itself: */ - save_callback=task->tk_callback; - task->tk_callback=NULL; + save_callback = task->tk_callback; + task->tk_callback = NULL; save_callback(task); } diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index e1770f7ba0b3..99a52aabe332 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -690,7 +690,7 @@ static void xprt_connect_status(struct rpc_task *task) { struct rpc_xprt *xprt = task->tk_xprt; - if (task->tk_status >= 0) { + if (task->tk_status == 0) { xprt->stat.connect_count++; xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start; dprintk("RPC: %5u xprt_connect_status: connection established\n", @@ -699,12 +699,6 @@ static void xprt_connect_status(struct rpc_task *task) } switch (task->tk_status) { - case -ECONNREFUSED: - case -ECONNRESET: - dprintk("RPC: %5u xprt_connect_status: server %s refused " - "connection\n", task->tk_pid, - task->tk_client->cl_server); - break; case -ENOTCONN: dprintk("RPC: %5u xprt_connect_status: connection broken\n", task->tk_pid); @@ -878,6 +872,7 @@ void xprt_transmit(struct rpc_task *task) return; req->rq_connect_cookie = xprt->connect_cookie; + req->rq_xtime = jiffies; status = xprt->ops->send_request(task); if (status == 0) { dprintk("RPC: %5u xmit complete\n", task->tk_pid); diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index ddbe981ab516..4486c59c3aca 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -579,7 +579,6 @@ static int xs_udp_send_request(struct rpc_task *task) req->rq_svec->iov_base, req->rq_svec->iov_len); - req->rq_xtime = jiffies; status = xs_sendpages(transport->sock, xs_addr(xprt), xprt->addrlen, xdr, @@ -671,7 +670,6 @@ static int xs_tcp_send_request(struct rpc_task *task) * to cope with writespace callbacks arriving _after_ we have * called sendmsg(). */ while (1) { - req->rq_xtime = jiffies; status = xs_sendpages(transport->sock, NULL, 0, xdr, req->rq_bytes_sent); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index e18cd3628db4..783317dacd30 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -169,6 +169,11 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return (unix_peer(osk) == NULL || unix_our_peer(sk, osk)); } +static inline int unix_recvq_full(struct sock const *sk) +{ + return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; +} + static struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -482,6 +487,8 @@ static int unix_socketpair(struct socket *, struct socket *); static int unix_accept(struct socket *, struct socket *, int); static int unix_getname(struct socket *, struct sockaddr *, int *, int); static unsigned int unix_poll(struct file *, struct socket *, poll_table *); +static unsigned int unix_dgram_poll(struct file *, struct socket *, + poll_table *); static int unix_ioctl(struct socket *, unsigned int, unsigned long); static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct kiocb *, struct socket *, @@ -527,7 +534,7 @@ static const struct proto_ops unix_dgram_ops = { .socketpair = unix_socketpair, .accept = sock_no_accept, .getname = unix_getname, - .poll = datagram_poll, + .poll = unix_dgram_poll, .ioctl = unix_ioctl, .listen = sock_no_listen, .shutdown = unix_shutdown, @@ -548,7 +555,7 @@ static const struct proto_ops unix_seqpacket_ops = { .socketpair = unix_socketpair, .accept = unix_accept, .getname = unix_getname, - .poll = datagram_poll, + .poll = unix_dgram_poll, .ioctl = unix_ioctl, .listen = unix_listen, .shutdown = unix_shutdown, @@ -983,8 +990,7 @@ static long unix_wait_for_peer(struct sock *other, long timeo) sched = !sock_flag(other, SOCK_DEAD) && !(other->sk_shutdown & RCV_SHUTDOWN) && - (skb_queue_len(&other->sk_receive_queue) > - other->sk_max_ack_backlog); + unix_recvq_full(other); unix_state_unlock(other); @@ -1058,8 +1064,7 @@ restart: if (other->sk_state != TCP_LISTEN) goto out_unlock; - if (skb_queue_len(&other->sk_receive_queue) > - other->sk_max_ack_backlog) { + if (unix_recvq_full(other)) { err = -EAGAIN; if (!timeo) goto out_unlock; @@ -1428,9 +1433,7 @@ restart: goto out_unlock; } - if (unix_peer(other) != sk && - (skb_queue_len(&other->sk_receive_queue) > - other->sk_max_ack_backlog)) { + if (unix_peer(other) != sk && unix_recvq_full(other)) { if (!timeo) { err = -EAGAIN; goto out_unlock; @@ -1991,6 +1994,60 @@ static unsigned int unix_poll(struct file * file, struct socket *sock, poll_tabl return mask; } +static unsigned int unix_dgram_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + struct sock *sk = sock->sk, *other; + unsigned int mask, writable; + + poll_wait(file, sk->sk_sleep, wait); + mask = 0; + + /* exceptional events? */ + if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + mask |= POLLERR; + if (sk->sk_shutdown & RCV_SHUTDOWN) + mask |= POLLRDHUP; + if (sk->sk_shutdown == SHUTDOWN_MASK) + mask |= POLLHUP; + + /* readable? */ + if (!skb_queue_empty(&sk->sk_receive_queue) || + (sk->sk_shutdown & RCV_SHUTDOWN)) + mask |= POLLIN | POLLRDNORM; + + /* Connection-based need to check for termination and startup */ + if (sk->sk_type == SOCK_SEQPACKET) { + if (sk->sk_state == TCP_CLOSE) + mask |= POLLHUP; + /* connection hasn't started yet? */ + if (sk->sk_state == TCP_SYN_SENT) + return mask; + } + + /* writable? */ + writable = unix_writable(sk); + if (writable) { + other = unix_peer_get(sk); + if (other) { + if (unix_peer(other) != sk) { + poll_wait(file, &unix_sk(other)->peer_wait, + wait); + if (unix_recvq_full(other)) + writable = 0; + } + + sock_put(other); + } + } + + if (writable) + mask |= POLLOUT | POLLWRNORM | POLLWRBAND; + else + set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags); + + return mask; +} #ifdef CONFIG_PROC_FS static struct sock *first_unix_socket(int *i) diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 2bdd4dddc0e1..fb75f265b39c 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -187,7 +187,8 @@ static int nl80211_send_wiphy(struct sk_buff *msg, u32 pid, u32 seq, int flags, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_wiphy(struct sk_buff *skb, struct netlink_callback *cb) @@ -273,7 +274,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 pid, u32 seq, int flags, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback *cb) @@ -928,7 +930,8 @@ static int nl80211_send_station(struct sk_buff *msg, u32 pid, u32 seq, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_station(struct sk_buff *skb, @@ -1267,7 +1270,8 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 pid, u32 seq, return genlmsg_end(msg, hdr); nla_put_failure: - return genlmsg_cancel(msg, hdr); + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } static int nl80211_dump_mpath(struct sk_buff *skb, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 185488da2466..855bff4b3250 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -80,6 +80,23 @@ static const struct ieee80211_channel_range ieee80211_JP_channels[] = { IEEE80211_CHAN_RADAR), }; +static const struct ieee80211_channel_range ieee80211_EU_channels[] = { + /* IEEE 802.11b/g, channels 1..13 */ + RANGE_PWR(2412, 2472, 20, 6, 0), + /* IEEE 802.11a, channel 36*/ + RANGE_PWR(5180, 5180, 23, 6, IEEE80211_CHAN_PASSIVE_SCAN), + /* IEEE 802.11a, channel 40*/ + RANGE_PWR(5200, 5200, 23, 6, IEEE80211_CHAN_PASSIVE_SCAN), + /* IEEE 802.11a, channel 44*/ + RANGE_PWR(5220, 5220, 23, 6, IEEE80211_CHAN_PASSIVE_SCAN), + /* IEEE 802.11a, channels 48..64 */ + RANGE_PWR(5240, 5320, 23, 6, IEEE80211_CHAN_NO_IBSS | + IEEE80211_CHAN_RADAR), + /* IEEE 802.11a, channels 100..140 */ + RANGE_PWR(5500, 5700, 30, 6, IEEE80211_CHAN_NO_IBSS | + IEEE80211_CHAN_RADAR), +}; + #define REGDOM(_code) \ { \ .code = __stringify(_code), \ @@ -90,6 +107,7 @@ static const struct ieee80211_channel_range ieee80211_JP_channels[] = { static const struct ieee80211_regdomain ieee80211_regdoms[] = { REGDOM(US), REGDOM(JP), + REGDOM(EU), }; diff --git a/net/xfrm/xfrm_algo.c b/net/xfrm/xfrm_algo.c index ac765dd9c7f5..23a2cc04b8cd 100644 --- a/net/xfrm/xfrm_algo.c +++ b/net/xfrm/xfrm_algo.c @@ -200,8 +200,8 @@ static struct xfrm_algo_desc aalg_list[] = { } }, { - .name = "hmac(ripemd160)", - .compat = "ripemd160", + .name = "hmac(rmd160)", + .compat = "rmd160", .uinfo = { .auth = { diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b976d9ed10e4..04c41504f84c 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -277,9 +277,8 @@ static void copy_from_user_state(struct xfrm_state *x, struct xfrm_usersa_info * memcpy(&x->props.saddr, &p->saddr, sizeof(x->props.saddr)); x->props.flags = p->flags; - if (!x->sel.family) + if (!x->sel.family && !(p->flags & XFRM_STATE_AF_UNSPEC)) x->sel.family = p->family; - } /* |