diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/dev.c | 59 | ||||
-rw-r--r-- | net/core/ethtool.c | 16 | ||||
-rw-r--r-- | net/core/neighbour.c | 95 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 2 | ||||
-rw-r--r-- | net/core/net_namespace.c | 35 | ||||
-rw-r--r-- | net/core/netpoll.c | 6 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 21 | ||||
-rw-r--r-- | net/core/skbuff.c | 3 | ||||
-rw-r--r-- | net/core/sock.c | 16 |
9 files changed, 153 insertions, 100 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 6a94475aee8..09fb03fa1ae 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -272,7 +272,7 @@ static const unsigned short netdev_lock_type[] = ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY, ARPHRD_VOID, ARPHRD_NONE}; -static const char *netdev_lock_name[] = +static const char *const netdev_lock_name[] = {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", @@ -1704,7 +1704,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_dst_drop(skb); rc = ops->ndo_start_xmit(skb, dev); - if (rc == 0) + if (rc == NETDEV_TX_OK) txq_trans_update(txq); /* * TODO: if skb_orphan() was called by @@ -1730,7 +1730,7 @@ gso: skb->next = nskb->next; nskb->next = NULL; rc = ops->ndo_start_xmit(nskb, dev); - if (unlikely(rc)) { + if (unlikely(rc != NETDEV_TX_OK)) { nskb->next = skb->next; skb->next = nskb; return rc; @@ -1744,7 +1744,7 @@ gso: out_kfree_skb: kfree_skb(skb); - return 0; + return NETDEV_TX_OK; } static u32 skb_tx_hashrnd; @@ -1786,6 +1786,40 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, return netdev_get_tx_queue(dev, queue_index); } +static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, + struct net_device *dev, + struct netdev_queue *txq) +{ + spinlock_t *root_lock = qdisc_lock(q); + int rc; + + spin_lock(root_lock); + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + kfree_skb(skb); + rc = NET_XMIT_DROP; + } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && + !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { + /* + * This is a work-conserving queue; there are no old skbs + * waiting to be sent out; and the qdisc is not running - + * xmit the skb directly. + */ + __qdisc_update_bstats(q, skb->len); + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) + __qdisc_run(q); + else + clear_bit(__QDISC_STATE_RUNNING, &q->state); + + rc = NET_XMIT_SUCCESS; + } else { + rc = qdisc_enqueue_root(skb, q); + qdisc_run(q); + } + spin_unlock(root_lock); + + return rc; +} + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -1859,19 +1893,7 @@ gso: skb->tc_verd = SET_TC_AT(skb->tc_verd,AT_EGRESS); #endif if (q->enqueue) { - spinlock_t *root_lock = qdisc_lock(q); - - spin_lock(root_lock); - - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { - kfree_skb(skb); - rc = NET_XMIT_DROP; - } else { - rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); - } - spin_unlock(root_lock); - + rc = __dev_xmit_skb(skb, q, dev, txq); goto out; } @@ -3927,6 +3949,7 @@ int __dev_addr_sync(struct dev_addr_list **to, int *to_count, } return err; } +EXPORT_SYMBOL_GPL(__dev_addr_sync); void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, struct dev_addr_list **from, int *from_count) @@ -3946,6 +3969,7 @@ void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, da = next; } } +EXPORT_SYMBOL_GPL(__dev_addr_unsync); /** * dev_unicast_sync - Synchronize device's unicast list to another device @@ -5347,6 +5371,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char out: return err; } +EXPORT_SYMBOL_GPL(dev_change_net_namespace); static int dev_cpu_callback(struct notifier_block *nfb, unsigned long action, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index d9d5160610d..44e571111d3 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -30,10 +30,17 @@ u32 ethtool_op_get_link(struct net_device *dev) return netif_carrier_ok(dev) ? 1 : 0; } +u32 ethtool_op_get_rx_csum(struct net_device *dev) +{ + return (dev->features & NETIF_F_ALL_CSUM) != 0; +} +EXPORT_SYMBOL(ethtool_op_get_rx_csum); + u32 ethtool_op_get_tx_csum(struct net_device *dev) { return (dev->features & NETIF_F_ALL_CSUM) != 0; } +EXPORT_SYMBOL(ethtool_op_get_tx_csum); int ethtool_op_set_tx_csum(struct net_device *dev, u32 data) { @@ -1004,7 +1011,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) break; case ETHTOOL_GRXCSUM: rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_rx_csum); + (dev->ethtool_ops->get_rx_csum ? + dev->ethtool_ops->get_rx_csum : + ethtool_op_get_rx_csum)); break; case ETHTOOL_SRXCSUM: rc = ethtool_set_rx_csum(dev, useraddr); @@ -1068,7 +1077,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_flags); + (dev->ethtool_ops->get_flags ? + dev->ethtool_ops->get_flags : + ethtool_op_get_flags)); break; case ETHTOOL_SFLAGS: rc = ethtool_set_value(dev, useraddr, @@ -1116,7 +1127,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) EXPORT_SYMBOL(ethtool_op_get_link); EXPORT_SYMBOL(ethtool_op_get_sg); EXPORT_SYMBOL(ethtool_op_get_tso); -EXPORT_SYMBOL(ethtool_op_get_tx_csum); EXPORT_SYMBOL(ethtool_op_set_sg); EXPORT_SYMBOL(ethtool_op_set_tso); EXPORT_SYMBOL(ethtool_op_set_tx_csum); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 163b4f5b036..e587e681969 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -692,75 +692,74 @@ static void neigh_connect(struct neighbour *neigh) hh->hh_output = neigh->ops->hh_output; } -static void neigh_periodic_timer(unsigned long arg) +static void neigh_periodic_work(struct work_struct *work) { - struct neigh_table *tbl = (struct neigh_table *)arg; + struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); struct neighbour *n, **np; - unsigned long expire, now = jiffies; + unsigned int i; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); - write_lock(&tbl->lock); + write_lock_bh(&tbl->lock); /* * periodically recompute ReachableTime from random function */ - if (time_after(now, tbl->last_rand + 300 * HZ)) { + if (time_after(jiffies, tbl->last_rand + 300 * HZ)) { struct neigh_parms *p; - tbl->last_rand = now; + tbl->last_rand = jiffies; for (p = &tbl->parms; p; p = p->next) p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); } - np = &tbl->hash_buckets[tbl->hash_chain_gc]; - tbl->hash_chain_gc = ((tbl->hash_chain_gc + 1) & tbl->hash_mask); + for (i = 0 ; i <= tbl->hash_mask; i++) { + np = &tbl->hash_buckets[i]; - while ((n = *np) != NULL) { - unsigned int state; + while ((n = *np) != NULL) { + unsigned int state; - write_lock(&n->lock); + write_lock(&n->lock); - state = n->nud_state; - if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { - write_unlock(&n->lock); - goto next_elt; - } + state = n->nud_state; + if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { + write_unlock(&n->lock); + goto next_elt; + } - if (time_before(n->used, n->confirmed)) - n->used = n->confirmed; + if (time_before(n->used, n->confirmed)) + n->used = n->confirmed; - if (atomic_read(&n->refcnt) == 1 && - (state == NUD_FAILED || - time_after(now, n->used + n->parms->gc_staletime))) { - *np = n->next; - n->dead = 1; + if (atomic_read(&n->refcnt) == 1 && + (state == NUD_FAILED || + time_after(jiffies, n->used + n->parms->gc_staletime))) { + *np = n->next; + n->dead = 1; + write_unlock(&n->lock); + neigh_cleanup_and_release(n); + continue; + } write_unlock(&n->lock); - neigh_cleanup_and_release(n); - continue; - } - write_unlock(&n->lock); next_elt: - np = &n->next; + np = &n->next; + } + /* + * It's fine to release lock here, even if hash table + * grows while we are preempted. + */ + write_unlock_bh(&tbl->lock); + cond_resched(); + write_lock_bh(&tbl->lock); } - /* Cycle through all hash buckets every base_reachable_time/2 ticks. * ARP entry timeouts range from 1/2 base_reachable_time to 3/2 * base_reachable_time. */ - expire = tbl->parms.base_reachable_time >> 1; - expire /= (tbl->hash_mask + 1); - if (!expire) - expire = 1; - - if (expire>HZ) - mod_timer(&tbl->gc_timer, round_jiffies(now + expire)); - else - mod_timer(&tbl->gc_timer, now + expire); - - write_unlock(&tbl->lock); + schedule_delayed_work(&tbl->gc_work, + tbl->parms.base_reachable_time >> 1); + write_unlock_bh(&tbl->lock); } static __inline__ int neigh_max_probes(struct neighbour *n) @@ -1316,7 +1315,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, } EXPORT_SYMBOL(pneigh_enqueue); -static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, +static inline struct neigh_parms *lookup_neigh_parms(struct neigh_table *tbl, struct net *net, int ifindex) { struct neigh_parms *p; @@ -1337,7 +1336,7 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, struct net *net = dev_net(dev); const struct net_device_ops *ops = dev->netdev_ops; - ref = lookup_neigh_params(tbl, net, 0); + ref = lookup_neigh_parms(tbl, net, 0); if (!ref) return NULL; @@ -1442,10 +1441,8 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); rwlock_init(&tbl->lock); - setup_timer(&tbl->gc_timer, neigh_periodic_timer, (unsigned long)tbl); - tbl->gc_timer.expires = now + 1; - add_timer(&tbl->gc_timer); - + INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); + schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); setup_timer(&tbl->proxy_timer, neigh_proxy_process, (unsigned long)tbl); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1482,7 +1479,8 @@ int neigh_table_clear(struct neigh_table *tbl) struct neigh_table **tp; /* It is not clean... Fix it to unload IPv6 module safely */ - del_timer_sync(&tbl->gc_timer); + cancel_delayed_work(&tbl->gc_work); + flush_scheduled_work(); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); @@ -1752,7 +1750,6 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, .ndtc_last_rand = jiffies_to_msecs(rand_delta), .ndtc_hash_rnd = tbl->hash_rnd, .ndtc_hash_mask = tbl->hash_mask, - .ndtc_hash_chain_gc = tbl->hash_chain_gc, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; @@ -1906,7 +1903,7 @@ static int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (tbp[NDTPA_IFINDEX]) ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); - p = lookup_neigh_params(tbl, net, ifindex); + p = lookup_neigh_parms(tbl, net, ifindex); if (p == NULL) { err = -ENOENT; goto errout_tbl_lock; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 3994680c08b..ad91e9e5f47 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -141,7 +141,7 @@ static ssize_t show_dormant(struct device *dev, return -EINVAL; } -static const char *operstates[] = { +static const char *const operstates[] = { "unknown", "notpresent", /* currently unused */ "down", diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 197283072cc..1c1af2756f3 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -6,6 +6,8 @@ #include <linux/delay.h> #include <linux/sched.h> #include <linux/idr.h> +#include <linux/rculist.h> +#include <linux/nsproxy.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -127,7 +129,7 @@ static struct net *net_create(void) rv = setup_net(net); if (rv == 0) { rtnl_lock(); - list_add_tail(&net->list, &net_namespace_list); + list_add_tail_rcu(&net->list, &net_namespace_list); rtnl_unlock(); } mutex_unlock(&net_mutex); @@ -156,9 +158,16 @@ static void cleanup_net(struct work_struct *work) /* Don't let anyone else find us. */ rtnl_lock(); - list_del(&net->list); + list_del_rcu(&net->list); rtnl_unlock(); + /* + * Another CPU might be rcu-iterating the list, wait for it. + * This needs to be before calling the exit() notifiers, so + * the rcu_barrier() below isn't sufficient alone. + */ + synchronize_rcu(); + /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) { if (ops->exit) @@ -193,6 +202,26 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) } #endif +struct net *get_net_ns_by_pid(pid_t pid) +{ + struct task_struct *tsk; + struct net *net; + + /* Lookup the network namespace */ + net = ERR_PTR(-ESRCH); + rcu_read_lock(); + tsk = find_task_by_vpid(pid); + if (tsk) { + struct nsproxy *nsproxy; + nsproxy = task_nsproxy(tsk); + if (nsproxy) + net = get_net(nsproxy->net_ns); + } + rcu_read_unlock(); + return net; +} +EXPORT_SYMBOL_GPL(get_net_ns_by_pid); + static int __init net_ns_init(void) { struct net_generic *ng; @@ -219,7 +248,7 @@ static int __init net_ns_init(void) panic("Could not setup the initial network namespace"); rtnl_lock(); - list_add_tail(&init_net.list, &net_namespace_list); + list_add_tail_rcu(&init_net.list, &net_namespace_list); rtnl_unlock(); mutex_unlock(&net_mutex); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index df30feb2fc7..0ac309154b0 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -9,6 +9,7 @@ * Copyright (C) 2002 Red Hat, Inc. */ +#include <linux/moduleparam.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/string.h> @@ -50,6 +51,9 @@ static atomic_t trapped; static void zap_completion_queue(void); static void arp_reply(struct sk_buff *skb); +static unsigned int carrier_timeout = 4; +module_param(carrier_timeout, uint, 0644); + static void queue_process(struct work_struct *work) { struct netpoll_info *npinfo = @@ -732,7 +736,7 @@ int netpoll_setup(struct netpoll *np) } atleast = jiffies + HZ/10; - atmost = jiffies + 4*HZ; + atmost = jiffies + carrier_timeout * HZ; while (!netif_carrier_ok(ndev)) { if (time_after(jiffies, atmost)) { printk(KERN_NOTICE diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index d78030f88bd..b44775f9f2b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,7 +35,6 @@ #include <linux/security.h> #include <linux/mutex.h> #include <linux/if_addr.h> -#include <linux/nsproxy.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -52,6 +51,7 @@ #include <net/pkt_sched.h> #include <net/fib_rules.h> #include <net/rtnetlink.h> +#include <net/net_namespace.h> struct rtnl_link { @@ -725,25 +725,6 @@ static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_DATA] = { .type = NLA_NESTED }, }; -static struct net *get_net_ns_by_pid(pid_t pid) -{ - struct task_struct *tsk; - struct net *net; - - /* Lookup the network namespace */ - net = ERR_PTR(-ESRCH); - rcu_read_lock(); - tsk = find_task_by_vpid(pid); - if (tsk) { - struct nsproxy *nsproxy; - nsproxy = task_nsproxy(tsk); - if (nsproxy) - net = get_net(nsproxy->net_ns); - } - rcu_read_unlock(); - return net; -} - static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) { if (dev) { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 9e0597d189b..80a96166df3 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -559,9 +559,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif #endif new->vlan_tci = old->vlan_tci; -#if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) - new->do_not_encrypt = old->do_not_encrypt; -#endif skb_copy_secmark(new, old); } diff --git a/net/core/sock.c b/net/core/sock.c index bbb25be7ddf..3ac34ea6ec0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -142,7 +142,7 @@ static struct lock_class_key af_family_slock_keys[AF_MAX]; * strings build-time, so that runtime initialization of socket * locks is fast): */ -static const char *af_family_key_strings[AF_MAX+1] = { +static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX" , "sk_lock-AF_INET" , "sk_lock-AF_AX25" , "sk_lock-AF_IPX" , "sk_lock-AF_APPLETALK", "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE" , "sk_lock-AF_ATMPVC" , @@ -158,7 +158,7 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-AF_IEEE802154", "sk_lock-AF_MAX" }; -static const char *af_family_slock_key_strings[AF_MAX+1] = { +static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_UNSPEC", "slock-AF_UNIX" , "slock-AF_INET" , "slock-AF_AX25" , "slock-AF_IPX" , "slock-AF_APPLETALK", "slock-AF_NETROM", "slock-AF_BRIDGE" , "slock-AF_ATMPVC" , @@ -174,7 +174,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-AF_IEEE802154", "slock-AF_MAX" }; -static const char *af_family_clock_key_strings[AF_MAX+1] = { +static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-AF_UNSPEC", "clock-AF_UNIX" , "clock-AF_INET" , "clock-AF_AX25" , "clock-AF_IPX" , "clock-AF_APPLETALK", "clock-AF_NETROM", "clock-AF_BRIDGE" , "clock-AF_ATMPVC" , @@ -482,6 +482,8 @@ int sock_setsockopt(struct socket *sock, int level, int optname, sk->sk_reuse = valbool; break; case SO_TYPE: + case SO_PROTOCOL: + case SO_DOMAIN: case SO_ERROR: ret = -ENOPROTOOPT; break; @@ -764,6 +766,14 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_type; break; + case SO_PROTOCOL: + v.val = sk->sk_protocol; + break; + + case SO_DOMAIN: + v.val = sk->sk_family; + break; + case SO_ERROR: v.val = -sock_error(sk); if (v.val == 0) |