diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 1 | ||||
-rw-r--r-- | net/core/dev.c | 153 | ||||
-rw-r--r-- | net/core/fib_rules.c | 107 | ||||
-rw-r--r-- | net/core/neighbour.c | 2 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 4 | ||||
-rw-r--r-- | net/core/net_namespace.c | 272 | ||||
-rw-r--r-- | net/core/pktgen.c | 46 | ||||
-rw-r--r-- | net/core/skb_dma_map.c | 65 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 2 |
9 files changed, 387 insertions, 265 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 796f46e..08791ac 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -6,7 +6,6 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ gen_stats.o gen_estimator.o net_namespace.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-$(CONFIG_HAS_DMA) += skb_dma_map.o obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o diff --git a/net/core/dev.c b/net/core/dev.c index ccefa24..c36a17a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -105,6 +105,7 @@ #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> +#include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kmod.h> @@ -985,7 +986,7 @@ rollback: /* For now only devices in the initial network namespace * are in sysfs. */ - if (net == &init_net) { + if (net_eq(net, &init_net)) { ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); @@ -1352,7 +1353,7 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); - nb->notifier_call(nb, NETDEV_UNREGISTER_PERNET, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } @@ -1419,6 +1420,45 @@ static inline void net_timestamp(struct sk_buff *skb) skb->tstamp.tv64 = 0; } +/** + * dev_forward_skb - loopback an skb to another netif + * + * @dev: destination network device + * @skb: buffer to forward + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + * dev_forward_skb can be used for injecting an skb from the + * start_xmit function of one device into the receive queue + * of another device. + * + * The receiving device may be in another namespace, so + * we have to clear all information in the skb that could + * impact namespace isolation. + */ +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + skb_orphan(skb); + + if (!(dev->flags & IFF_UP)) + return NET_RX_DROP; + + if (skb->len > (dev->mtu + dev->hard_header_len)) + return NET_RX_DROP; + + skb_dst_drop(skb); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, dev); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); + return netif_rx(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -2637,9 +2677,10 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) return GRO_NORMAL; for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev) - && !compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = + (p->dev == skb->dev) && + !compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->flush = 0; } @@ -4730,8 +4771,7 @@ static void net_set_todo(struct net_device *dev) static void rollback_registered_many(struct list_head *head) { - struct net_device *dev, *aux, *fdev; - LIST_HEAD(pernet_list); + struct net_device *dev; BUG_ON(dev_boot_phase); ASSERT_RTNL(); @@ -4787,26 +4827,14 @@ static void rollback_registered_many(struct list_head *head) netdev_unregister_kobject(dev); } - synchronize_net(); + /* Process any work delayed until the end of the batch */ + dev = list_entry(head->next, struct net_device, unreg_list); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - list_for_each_entry_safe(dev, aux, head, unreg_list) { - int new_net = 1; - list_for_each_entry(fdev, &pernet_list, unreg_list) { - if (dev_net(dev) == dev_net(fdev)) { - new_net = 0; - dev_put(dev); - break; - } - } - if (new_net) - list_move(&dev->unreg_list, &pernet_list); - } + synchronize_net(); - list_for_each_entry_safe(dev, aux, &pernet_list, unreg_list) { - call_netdevice_notifiers(NETDEV_UNREGISTER_PERNET, dev); - list_move(&dev->unreg_list, head); + list_for_each_entry(dev, head, unreg_list) dev_put(dev); - } } static void rollback_registered(struct net_device *dev) @@ -4873,6 +4901,33 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) EXPORT_SYMBOL(netdev_fix_features); /** + * netif_stacked_transfer_operstate - transfer operstate + * @rootdev: the root or lower level device to transfer state from + * @dev: the device to transfer operstate to + * + * Transfer operational state from root to device. This is normally + * called when a stacking relationship exists between the root + * device and the device(a leaf device). + */ +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev) +{ + if (rootdev->operstate == IF_OPER_DORMANT) + netif_dormant_on(dev); + else + netif_dormant_off(dev); + + if (netif_carrier_ok(rootdev)) { + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); + } else { + if (netif_carrier_ok(dev)) + netif_carrier_off(dev); + } +} +EXPORT_SYMBOL(netif_stacked_transfer_operstate); + +/** * register_netdevice - register a network device * @dev: device to register * @@ -5088,7 +5143,7 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* don't resend NETDEV_UNREGISTER_PERNET, _PERNET users + /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users * should have already handle it the first time */ if (test_bit(__LINK_STATE_LINKWATCH_PENDING, @@ -5401,11 +5456,6 @@ EXPORT_SYMBOL(unregister_netdevice_queue); /** * unregister_netdevice_many - unregister many devices * @head: list of devices - * - * WARNING: Calling this modifies the given list - * (in rollback_registered_many). It may change the order of the elements - * in the list. However, you can assume it does not add or delete elements - * to/from the list. */ void unregister_netdevice_many(struct list_head *head) { @@ -5514,7 +5564,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - call_netdevice_notifiers(NETDEV_UNREGISTER_PERNET, dev); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); /* * Flush the unicast and multicast chains @@ -5713,14 +5763,13 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit(struct net *net) { - struct net_device *dev; + struct net_device *dev, *aux; /* - * Push all migratable of the network devices back to the + * Push all migratable network devices back to the * initial network namespace */ rtnl_lock(); -restart: - for_each_netdev(net, dev) { + for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -5728,11 +5777,9 @@ restart: if (dev->features & NETIF_F_NETNS_LOCAL) continue; - /* Delete virtual devices */ - if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev, NULL); - goto restart; - } + /* Leave virtual devices for the generic cleanup */ + if (dev->rtnl_link_ops) + continue; /* Push remaing network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); @@ -5742,13 +5789,37 @@ restart: __func__, dev->name, err); BUG(); } - goto restart; } rtnl_unlock(); } +static void __net_exit default_device_exit_batch(struct list_head *net_list) +{ + /* At exit all network devices most be removed from a network + * namespace. Do this in the reverse order of registeration. + * Do this across as many network namespaces as possible to + * improve batching efficiency. + */ + struct net_device *dev; + struct net *net; + LIST_HEAD(dev_kill_list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + for_each_netdev_reverse(net, dev) { + if (dev->rtnl_link_ops) + dev->rtnl_link_ops->dellink(dev, &dev_kill_list); + else + unregister_netdevice_queue(dev, &dev_kill_list); + } + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); +} + static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, + .exit_batch = default_device_exit_batch, }; /* diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bd30938..02a3b2c 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -72,7 +72,7 @@ static void flush_route_cache(struct fib_rules_ops *ops) ops->flush_cache(ops); } -int fib_rules_register(struct fib_rules_ops *ops) +static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; @@ -102,6 +102,28 @@ errout: return err; } +struct fib_rules_ops * +fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) +{ + struct fib_rules_ops *ops; + int err; + + ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&ops->rules_list); + ops->fro_net = net; + + err = __fib_rules_register(ops); + if (err) { + kfree(ops); + ops = ERR_PTR(err); + } + + return ops; +} + EXPORT_SYMBOL_GPL(fib_rules_register); void fib_rules_cleanup_ops(struct fib_rules_ops *ops) @@ -115,6 +137,15 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops) } EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops); +static void fib_rules_put_rcu(struct rcu_head *head) +{ + struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); + struct net *net = ops->fro_net; + + release_net(net); + kfree(ops); +} + void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; @@ -124,8 +155,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops) fib_rules_cleanup_ops(ops); spin_unlock(&net->rules_mod_lock); - synchronize_rcu(); - release_net(net); + call_rcu(&ops->rcu, fib_rules_put_rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); @@ -135,7 +165,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->ifindex && (rule->ifindex != fl->iif)) + if (rule->iifindex && (rule->iifindex != fl->iif)) + goto out; + + if (rule->oifindex && (rule->oifindex != fl->oif)) goto out; if ((rule->mark ^ fl->mark) & rule->mark_mask) @@ -248,14 +281,24 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[FRA_PRIORITY]) rule->pref = nla_get_u32(tb[FRA_PRIORITY]); - if (tb[FRA_IFNAME]) { + if (tb[FRA_IIFNAME]) { + struct net_device *dev; + + rule->iifindex = -1; + nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->iifname); + if (dev) + rule->iifindex = dev->ifindex; + } + + if (tb[FRA_OIFNAME]) { struct net_device *dev; - rule->ifindex = -1; - nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->ifname); + rule->oifindex = -1; + nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->oifname); if (dev) - rule->ifindex = dev->ifindex; + rule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { @@ -274,7 +317,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); - if (!rule->pref && ops->default_pref) + if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); err = -EINVAL; @@ -388,8 +431,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) continue; - if (tb[FRA_IFNAME] && - nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + if (tb[FRA_IIFNAME] && + nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) + continue; + + if (tb[FRA_OIFNAME] && + nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) continue; if (tb[FRA_FWMARK] && @@ -447,7 +494,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) - + nla_total_size(IFNAMSIZ) /* FRA_IFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_FWMARK */ @@ -481,11 +529,18 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL) frh->flags |= FIB_RULE_UNRESOLVED; - if (rule->ifname[0]) { - NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + if (rule->iifname[0]) { + NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname); - if (rule->ifindex == -1) - frh->flags |= FIB_RULE_DEV_DETACHED; + if (rule->iifindex == -1) + frh->flags |= FIB_RULE_IIF_DETACHED; + } + + if (rule->oifname[0]) { + NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname); + + if (rule->oifindex == -1) + frh->flags |= FIB_RULE_OIF_DETACHED; } if (rule->pref) @@ -600,9 +655,12 @@ static void attach_rules(struct list_head *rules, struct net_device *dev) struct fib_rule *rule; list_for_each_entry(rule, rules, list) { - if (rule->ifindex == -1 && - strcmp(dev->name, rule->ifname) == 0) - rule->ifindex = dev->ifindex; + if (rule->iifindex == -1 && + strcmp(dev->name, rule->iifname) == 0) + rule->iifindex = dev->ifindex; + if (rule->oifindex == -1 && + strcmp(dev->name, rule->oifname) == 0) + rule->oifindex = dev->ifindex; } } @@ -610,9 +668,12 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; - list_for_each_entry(rule, rules, list) - if (rule->ifindex == dev->ifindex) - rule->ifindex = -1; + list_for_each_entry(rule, rules, list) { + if (rule->iifindex == dev->ifindex) + rule->iifindex = -1; + if (rule->oifindex == dev->ifindex) + rule->oifindex = -1; + } } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e587e68..a08a35b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2092,7 +2092,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { - if (dev_net(n->dev) != net) + if (!net_eq(dev_net(n->dev), net)) continue; if (idx < s_idx) goto next; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 157645c..fbc1c74 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -525,7 +525,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return; device_del(dev); @@ -559,7 +559,7 @@ int netdev_register_kobject(struct net_device *net) #endif #endif /* CONFIG_SYSFS */ - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return 0; return device_add(dev); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1c1af27..bd8c471 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,14 +27,64 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static int ops_init(const struct pernet_operations *ops, struct net *net) +{ + int err; + if (ops->id && ops->size) { + void *data = kzalloc(ops->size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + err = net_assign_generic(net, *ops->id, data); + if (err) { + kfree(data); + return err; + } + } + if (ops->init) + return ops->init(net); + return 0; +} + +static void ops_free(const struct pernet_operations *ops, struct net *net) +{ + if (ops->id && ops->size) { + int id = *ops->id; + kfree(net_generic(net, id)); + } +} + +static void ops_exit_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->exit) { + list_for_each_entry(net, net_exit_list, exit_list) + ops->exit(net); + } + if (ops->exit_batch) + ops->exit_batch(net_exit_list); +} + +static void ops_free_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->size && ops->id) { + list_for_each_entry(net, net_exit_list, exit_list) + ops_free(ops, net); + } +} + /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net) { /* Must be called with net_mutex held */ - struct pernet_operations *ops; + const struct pernet_operations *ops, *saved_ops; int error = 0; + LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); @@ -43,11 +93,9 @@ static __net_init int setup_net(struct net *net) #endif list_for_each_entry(ops, &pernet_list, list) { - if (ops->init) { - error = ops->init(net); - if (error < 0) - goto out_undo; - } + error = ops_init(ops, net); + if (error < 0) + goto out_undo; } out: return error; @@ -56,10 +104,14 @@ out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ - list_for_each_entry_continue_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_add(&net->exit_list, &net_exit_list); + saved_ops = ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + ops = saved_ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; @@ -147,18 +199,29 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) return net_create(); } +static DEFINE_SPINLOCK(cleanup_list_lock); +static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ + static void cleanup_net(struct work_struct *work) { - struct pernet_operations *ops; - struct net *net; + const struct pernet_operations *ops; + struct net *net, *tmp; + LIST_HEAD(net_kill_list); + LIST_HEAD(net_exit_list); - net = container_of(work, struct net, work); + /* Atomically snapshot the list of namespaces to cleanup */ + spin_lock_irq(&cleanup_list_lock); + list_replace_init(&cleanup_list, &net_kill_list); + spin_unlock_irq(&cleanup_list_lock); mutex_lock(&net_mutex); /* Don't let anyone else find us. */ rtnl_lock(); - list_del_rcu(&net->list); + list_for_each_entry(net, &net_kill_list, cleanup_list) { + list_del_rcu(&net->list); + list_add_tail(&net->exit_list, &net_exit_list); + } rtnl_unlock(); /* @@ -169,10 +232,12 @@ static void cleanup_net(struct work_struct *work) synchronize_rcu(); /* Run all of the network namespace exit methods */ - list_for_each_entry_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + /* Free the net generic variables */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); mutex_unlock(&net_mutex); @@ -182,14 +247,23 @@ static void cleanup_net(struct work_struct *work) rcu_barrier(); /* Finally it is safe to free my network namespace structure */ - net_free(net); + list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { + list_del_init(&net->exit_list); + net_free(net); + } } +static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ - INIT_WORK(&net->work, cleanup_net); - queue_work(netns_wq, &net->work); + unsigned long flags; + + spin_lock_irqsave(&cleanup_list_lock, flags); + list_add(&net->cleanup_list, &cleanup_list); + spin_unlock_irqrestore(&cleanup_list_lock, flags); + + queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); @@ -259,18 +333,20 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); #ifdef CONFIG_NET_NS -static int register_pernet_operations(struct list_head *list, - struct pernet_operations *ops) +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) { - struct net *net, *undo_net; + struct net *net; int error; + LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init) { + if (ops->init || (ops->id && ops->size)) { for_each_net(net) { - error = ops->init(net); + error = ops_init(ops, net); if (error) goto out_undo; + list_add_tail(&net->exit_list, &net_exit_list); } } return 0; @@ -278,45 +354,82 @@ static int register_pernet_operations(struct list_head *list, out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); - if (ops->exit) { - for_each_net(undo_net) { - if (undo_net == net) - goto undone; - ops->exit(undo_net); - } - } -undone: + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); return error; } -static void unregister_pernet_operations(struct pernet_operations *ops) +static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; + LIST_HEAD(net_exit_list); list_del(&ops->list); - if (ops->exit) - for_each_net(net) - ops->exit(net); + for_each_net(net) + list_add_tail(&net->exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); } #else +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + int err = 0; + err = ops_init(ops, &init_net); + if (err) + ops_free(ops, &init_net); + return err; + +} + +static void __unregister_pernet_operations(struct pernet_operations *ops) +{ + LIST_HEAD(net_exit_list); + list_add(&init_net.exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); +} + +#endif /* CONFIG_NET_NS */ + +static DEFINE_IDA(net_generic_ids); + static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - if (ops->init == NULL) - return 0; - return ops->init(&init_net); + int error; + + if (ops->id) { +again: + error = ida_get_new_above(&net_generic_ids, 1, ops->id); + if (error < 0) { + if (error == -EAGAIN) { + ida_pre_get(&net_generic_ids, GFP_KERNEL); + goto again; + } + return error; + } + } + error = __register_pernet_operations(list, ops); + if (error) { + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); + } + + return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { - if (ops->exit) - ops->exit(&init_net); + + __unregister_pernet_operations(ops); + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); } -#endif - -static DEFINE_IDA(net_generic_ids); /** * register_pernet_subsys - register a network namespace subsystem @@ -364,38 +477,6 @@ void unregister_pernet_subsys(struct pernet_operations *module) } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); -int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) -{ - int rv; - - mutex_lock(&net_mutex); -again: - rv = ida_get_new_above(&net_generic_ids, 1, id); - if (rv < 0) { - if (rv == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - rv = register_pernet_operations(first_device, ops); - if (rv < 0) - ida_remove(&net_generic_ids, *id); -out: - mutex_unlock(&net_mutex); - return rv; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_subsys); - -void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys); - /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem @@ -427,30 +508,6 @@ int register_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(register_pernet_device); -int register_pernet_gen_device(int *id, struct pernet_operations *ops) -{ - int error; - mutex_lock(&net_mutex); -again: - error = ida_get_new_above(&net_generic_ids, 1, id); - if (error) { - if (error == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - error = register_pernet_operations(&pernet_list, ops); - if (error) - ida_remove(&net_generic_ids, *id); - else if (first_device == &pernet_list) - first_device = &ops->list; -out: - mutex_unlock(&net_mutex); - return error; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_device); - /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate @@ -470,17 +527,6 @@ void unregister_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(unregister_pernet_device); -void unregister_pernet_gen_device(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - if (&ops->list == first_device) - first_device = first_device->next; - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_device); - static void net_generic_release(struct rcu_head *rcu) { struct net_generic *ng; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index d38470a..a23b45f 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -364,6 +364,7 @@ struct pktgen_dev { * device name (not when the inject is * started as it used to do.) */ + char odevname[32]; struct flow_state *flows; unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ @@ -427,7 +428,7 @@ static const char version[] = static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname); + const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(void); static void pktgen_reset_all_threads(void); @@ -529,7 +530,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_printf(seq, " frags: %d delay: %llu clone_skb: %d ifname: %s\n", pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, - pkt_dev->clone_skb, pkt_dev->odev->name); + pkt_dev->clone_skb, pkt_dev->odevname); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); @@ -1689,13 +1690,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); seq_printf(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); @@ -1818,9 +1819,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); list_for_each_entry(t, &pktgen_threads, th_list) { - pkt_dev = pktgen_find_dev(t, ifname); + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { if_lock(t); @@ -1995,7 +1997,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_min (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_min = ntxq - 1; } if (pkt_dev->queue_map_max >= ntxq) { @@ -2003,7 +2005,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_max (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_max = ntxq - 1; } @@ -2050,9 +2052,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) read_lock_bh(&idev->lock); for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { - if (ifp->scope == IFA_LINK - && !(ifp-> - flags & IFA_F_TENTATIVE)) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & IFA_F_TENTATIVE)) { ipv6_addr_copy(&pkt_dev-> cur_in6_saddr, &ifp->addr); @@ -3263,7 +3264,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) if (!pkt_dev->running) { printk(KERN_WARNING "pktgen: interface: %s is already " - "stopped\n", pkt_dev->odev->name); + "stopped\n", pkt_dev->odevname); return -EINVAL; } @@ -3467,7 +3468,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) pr_info("pktgen: %s xmit error: %d\n", - odev->name, ret); + pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3570,13 +3571,18 @@ static int pktgen_thread_worker(void *arg) } static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname) + const char *ifname, bool exact) { struct pktgen_dev *p, *pkt_dev = NULL; - if_lock(t); + size_t len = strlen(ifname); + if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } pkt_dev = p; break; } @@ -3619,6 +3625,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { struct pktgen_dev *pkt_dev; int err; + int node = cpu_to_node(t->cpu); /* We don't allow a device to be on several threads */ @@ -3628,11 +3635,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return -EBUSY; } - pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node); if (!pkt_dev) return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); + strcpy(pkt_dev->odevname, ifname); + pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; @@ -3694,7 +3703,8 @@ static int __init pktgen_create_thread(int cpu) struct proc_dir_entry *pe; struct task_struct *p; - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); + t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, + cpu_to_node(cpu)); if (!t) { printk(KERN_ERR "pktgen: ERROR: out of memory, can't " "create new thread.\n"); diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c deleted file mode 100644 index 79687df..0000000 --- a/net/core/skb_dma_map.c +++ /dev/null @@ -1,65 +0,0 @@ -/* skb_dma_map.c: DMA mapping helpers for socket buffers. - * - * Copyright (C) David S. Miller <davem@davemloft.net> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/dma-mapping.h> -#include <linux/skbuff.h> - -int skb_dma_map(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - dma_addr_t map; - int i; - - map = dma_map_single(dev, skb->data, - skb_headlen(skb), dir); - if (dma_mapping_error(dev, map)) - goto out_err; - - sp->dma_head = map; - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - map = dma_map_page(dev, fp->page, fp->page_offset, - fp->size, dir); - if (dma_mapping_error(dev, map)) - goto unwind; - sp->dma_maps[i] = map; - } - - return 0; - -unwind: - while (--i >= 0) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); -out_err: - return -ENOMEM; -} -EXPORT_SYMBOL(skb_dma_map); - -void skb_dma_unmap(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - int i; - - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } -} -EXPORT_SYMBOL(skb_dma_unmap); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7db1de0..fcfc545 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -134,7 +134,7 @@ static __net_init int sysctl_core_net_init(struct net *net) net->core.sysctl_somaxconn = SOMAXCONN; tbl = netns_core_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; |