diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/Makefile | 3 | ||||
| -rw-r--r-- | net/core/datagram.c | 4 | ||||
| -rw-r--r-- | net/core/dev.c | 149 | ||||
| -rw-r--r-- | net/core/dev_mcast.c | 3 | ||||
| -rw-r--r-- | net/core/dst.c | 3 | ||||
| -rw-r--r-- | net/core/ethtool.c | 48 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 421 | ||||
| -rw-r--r-- | net/core/filter.c | 8 | ||||
| -rw-r--r-- | net/core/flow.c | 13 | ||||
| -rw-r--r-- | net/core/link_watch.c | 1 | ||||
| -rw-r--r-- | net/core/neighbour.c | 616 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 6 | ||||
| -rw-r--r-- | net/core/netevent.c | 69 | ||||
| -rw-r--r-- | net/core/netpoll.c | 38 | ||||
| -rw-r--r-- | net/core/pktgen.c | 329 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 586 | ||||
| -rw-r--r-- | net/core/skbuff.c | 161 | ||||
| -rw-r--r-- | net/core/sock.c | 157 | ||||
| -rw-r--r-- | net/core/stream.c | 16 | ||||
| -rw-r--r-- | net/core/sysctl_net_core.c | 1 | ||||
| -rw-r--r-- | net/core/user_dma.c | 1 | ||||
| -rw-r--r-- | net/core/utils.c | 222 | ||||
| -rw-r--r-- | net/core/wireless.c | 79 |
23 files changed, 2150 insertions, 784 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index e9bd2467d5a9..119568077dab 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -7,7 +7,7 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-y += dev.o ethtool.o dev_mcast.o dst.o \ +obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o obj-$(CONFIG_XFRM) += flow.o @@ -17,3 +17,4 @@ obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_WIRELESS_EXT) += wireless.o obj-$(CONFIG_NETPOLL) += netpoll.o obj-$(CONFIG_NET_DMA) += user_dma.o +obj-$(CONFIG_FIB_RULES) += fib_rules.o diff --git a/net/core/datagram.c b/net/core/datagram.c index aecddcc30401..f558c61aecc7 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -417,7 +417,7 @@ unsigned int __skb_checksum_complete(struct sk_buff *skb) sum = (u16)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum)); if (likely(!sum)) { - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -462,7 +462,7 @@ int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb, goto fault; if ((unsigned short)csum_fold(csum)) goto csum_error; - if (unlikely(skb->ip_summed == CHECKSUM_HW)) + if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE)) netdev_rx_csum_fault(skb->dev); iov->iov_len -= chunk; iov->iov_base += chunk; diff --git a/net/core/dev.c b/net/core/dev.c index ea2469398bd5..4d891beab138 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -76,7 +76,6 @@ #include <asm/system.h> #include <linux/bitops.h> #include <linux/capability.h> -#include <linux/config.h> #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> @@ -117,6 +116,7 @@ #include <linux/audit.h> #include <linux/dmaengine.h> #include <linux/err.h> +#include <linux/ctype.h> /* * The list of packet types we will receive (as opposed to discard) @@ -230,7 +230,7 @@ extern void netdev_unregister_sysfs(struct net_device *); * For efficiency */ -int netdev_nit; +static int netdev_nit; /* * Add a protocol ID to the list. Now that the input handler is @@ -633,14 +633,24 @@ struct net_device * dev_get_by_flags(unsigned short if_flags, unsigned short mas * @name: name string * * Network device names need to be valid file names to - * to allow sysfs to work + * to allow sysfs to work. We also disallow any kind of + * whitespace. */ int dev_valid_name(const char *name) { - return !(*name == '\0' - || !strcmp(name, ".") - || !strcmp(name, "..") - || strchr(name, '/')); + if (*name == '\0') + return 0; + if (strlen(name) >= IFNAMSIZ) + return 0; + if (!strcmp(name, ".") || !strcmp(name, "..")) + return 0; + + while (*name) { + if (*name == '/' || isspace(*name)) + return 0; + name++; + } + return 1; } /** @@ -1158,14 +1168,17 @@ EXPORT_SYMBOL(netif_device_attach); * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. */ -int skb_checksum_help(struct sk_buff *skb, int inward) +int skb_checksum_help(struct sk_buff *skb) { unsigned int csum; int ret = 0, offset = skb->h.raw - skb->data; - if (inward) { - skb->ip_summed = CHECKSUM_NONE; - goto out; + if (skb->ip_summed == CHECKSUM_COMPLETE) + goto out_set_summed; + + if (unlikely(skb_shinfo(skb)->gso_size)) { + /* Let GSO fix up the checksum. */ + goto out_set_summed; } if (skb_cloned(skb)) { @@ -1182,6 +1195,8 @@ int skb_checksum_help(struct sk_buff *skb, int inward) BUG_ON(skb->csum + 2 > offset); *(u16*)(skb->h.raw + skb->csum) = csum_fold(csum); + +out_set_summed: skb->ip_summed = CHECKSUM_NONE; out: return ret; @@ -1190,32 +1205,50 @@ out: /** * skb_gso_segment - Perform segmentation on skb. * @skb: buffer to segment - * @sg: whether scatter-gather is supported on the target. + * @features: features for the output path (see dev->features) * * This function segments the given skb and returns a list of segments. + * + * It may return NULL if the skb requires no segmentation. This is + * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, int sg) +struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; int type = skb->protocol; + int err; BUG_ON(skb_shinfo(skb)->frag_list); - BUG_ON(skb->ip_summed != CHECKSUM_HW); skb->mac.raw = skb->data; skb->mac_len = skb->nh.raw - skb->data; __skb_pull(skb, skb->mac_len); + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + if (skb_header_cloned(skb) && + (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC))) + return ERR_PTR(err); + } + rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & 15], list) { if (ptype->type == type && !ptype->dev && ptype->gso_segment) { - segs = ptype->gso_segment(skb, sg); + if (unlikely(skb->ip_summed != CHECKSUM_PARTIAL)) { + err = ptype->gso_send_check(skb); + segs = ERR_PTR(err); + if (err || skb_gso_ok(skb, features)) + break; + __skb_push(skb, skb->data - skb->nh.raw); + } + segs = ptype->gso_segment(skb, features); break; } } rcu_read_unlock(); + __skb_push(skb, skb->data - skb->mac.raw); + return segs; } @@ -1234,7 +1267,6 @@ void netdev_rx_csum_fault(struct net_device *dev) EXPORT_SYMBOL(netdev_rx_csum_fault); #endif -#ifdef CONFIG_HIGHMEM /* Actually, we should eliminate this check as soon as we know, that: * 1. IOMMU is present and allows to map all the memory. * 2. No high memory really exists on this machine. @@ -1242,6 +1274,7 @@ EXPORT_SYMBOL(netdev_rx_csum_fault); static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) { +#ifdef CONFIG_HIGHMEM int i; if (dev->features & NETIF_F_HIGHDMA) @@ -1251,11 +1284,9 @@ static inline int illegal_highdma(struct net_device *dev, struct sk_buff *skb) if (PageHighMem(skb_shinfo(skb)->frags[i].page)) return 1; +#endif return 0; } -#else -#define illegal_highdma(dev, skb) (0) -#endif struct dev_gso_cb { void (*destructor)(struct sk_buff *skb); @@ -1291,9 +1322,15 @@ static int dev_gso_segment(struct sk_buff *skb) { struct net_device *dev = skb->dev; struct sk_buff *segs; + int features = dev->features & ~(illegal_highdma(dev, skb) ? + NETIF_F_SG : 0); + + segs = skb_gso_segment(skb, features); + + /* Verifying header integrity only. */ + if (!segs) + return 0; - segs = skb_gso_segment(skb, dev->features & NETIF_F_SG && - !illegal_highdma(dev, skb)); if (unlikely(IS_ERR(segs))) return PTR_ERR(segs); @@ -1310,13 +1347,17 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) if (netdev_nit) dev_queue_xmit_nit(skb, dev); - if (!netif_needs_gso(dev, skb)) - return dev->hard_start_xmit(skb, dev); + if (netif_needs_gso(dev, skb)) { + if (unlikely(dev_gso_segment(skb))) + goto out_kfree_skb; + if (skb->next) + goto gso; + } - if (unlikely(dev_gso_segment(skb))) - goto out_kfree_skb; + return dev->hard_start_xmit(skb, dev); } +gso: do { struct sk_buff *nskb = skb->next; int rc; @@ -1325,9 +1366,12 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev) nskb->next = NULL; rc = dev->hard_start_xmit(nskb, dev); if (unlikely(rc)) { + nskb->next = skb->next; skb->next = nskb; return rc; } + if (unlikely(netif_queue_stopped(dev) && skb->next)) + return NETDEV_TX_BUSY; } while (skb->next); skb->destructor = DEV_GSO_CB(skb)->destructor; @@ -1402,11 +1446,11 @@ int dev_queue_xmit(struct sk_buff *skb) /* If packet is not checksummed and device does not support * checksumming for this protocol, complete checksumming here. */ - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_PARTIAL && (!(dev->features & NETIF_F_GEN_CSUM) && (!(dev->features & NETIF_F_IP_CSUM) || skb->protocol != htons(ETH_P_IP)))) - if (skb_checksum_help(skb, 0)) + if (skb_checksum_help(skb)) goto out_kfree_skb; gso: @@ -1436,14 +1480,16 @@ gso: if (q->enqueue) { /* Grab device queue */ spin_lock(&dev->queue_lock); + q = dev->qdisc; + if (q->enqueue) { + rc = q->enqueue(skb, q); + qdisc_run(dev); + spin_unlock(&dev->queue_lock); - rc = q->enqueue(skb, q); - - qdisc_run(dev); - + rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc; + goto out; + } spin_unlock(&dev->queue_lock); - rc = rc == NET_XMIT_BYPASS ? NET_XMIT_SUCCESS : rc; - goto out; } /* The device has no queue. Common case for software devices: @@ -1586,26 +1632,10 @@ static inline struct net_device *skb_bond(struct sk_buff *skb) struct net_device *dev = skb->dev; if (dev->master) { - /* - * On bonding slaves other than the currently active - * slave, suppress duplicates except for 802.3ad - * ETH_P_SLOW and alb non-mcast/bcast. - */ - if (dev->priv_flags & IFF_SLAVE_INACTIVE) { - if (dev->master->priv_flags & IFF_MASTER_ALB) { - if (skb->pkt_type != PACKET_BROADCAST && - skb->pkt_type != PACKET_MULTICAST) - goto keep; - } - - if (dev->master->priv_flags & IFF_MASTER_8023AD && - skb->protocol == __constant_htons(ETH_P_SLOW)) - goto keep; - + if (skb_bond_should_drop(skb)) { kfree_skb(skb); return NULL; } -keep: skb->dev = dev->master; } @@ -1712,7 +1742,7 @@ static int ing_filter(struct sk_buff *skb) if (dev->qdisc_ingress) { __u32 ttl = (__u32) G_TC_RTTL(skb->tc_verd); if (MAX_RED_LOOP < ttl++) { - printk("Redir loop detected Dropping packet (%s->%s)\n", + printk(KERN_WARNING "Redir loop detected Dropping packet (%s->%s)\n", skb->input_dev->name, skb->dev->name); return TC_ACT_SHOT; } @@ -2907,7 +2937,7 @@ int register_netdevice(struct net_device *dev) /* Fix illegal SG+CSUM combinations. */ if ((dev->features & NETIF_F_SG) && !(dev->features & NETIF_F_ALL_CSUM)) { - printk("%s: Dropping NETIF_F_SG since no checksum feature.\n", + printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no checksum feature.\n", dev->name); dev->features &= ~NETIF_F_SG; } @@ -2915,7 +2945,7 @@ int register_netdevice(struct net_device *dev) /* TSO requires that SG is present as well. */ if ((dev->features & NETIF_F_TSO) && !(dev->features & NETIF_F_SG)) { - printk("%s: Dropping NETIF_F_TSO since no SG feature.\n", + printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no SG feature.\n", dev->name); dev->features &= ~NETIF_F_TSO; } @@ -3165,13 +3195,15 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name, struct net_device *dev; int alloc_size; + BUG_ON(strlen(name) >= sizeof(dev->name)); + /* ensure 32-byte alignment of both the device and private area */ alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; alloc_size += sizeof_priv + NETDEV_ALIGN_CONST; p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { - printk(KERN_ERR "alloc_dev: Unable to allocate device.\n"); + printk(KERN_ERR "alloc_netdev: Unable to allocate device.\n"); return NULL; } @@ -3386,12 +3418,9 @@ static void net_dma_rebalance(void) unsigned int cpu, i, n; struct dma_chan *chan; - lock_cpu_hotplug(); - if (net_dma_count == 0) { for_each_online_cpu(cpu) - rcu_assign_pointer(per_cpu(softnet_data.net_dma, cpu), NULL); - unlock_cpu_hotplug(); + rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL); return; } @@ -3404,15 +3433,13 @@ static void net_dma_rebalance(void) + (i < (num_online_cpus() % net_dma_count) ? 1 : 0)); while(n) { - per_cpu(softnet_data.net_dma, cpu) = chan; + per_cpu(softnet_data, cpu).net_dma = chan; cpu = next_cpu(cpu, cpu_online_map); n--; } i++; } rcu_read_unlock(); - - unlock_cpu_hotplug(); } /** diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index c57d887da2ef..b22648d04d36 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -21,8 +21,7 @@ * 2 of the License, or (at your option) any later version. */ -#include <linux/config.h> -#include <linux/module.h> +#include <linux/module.h> #include <asm/uaccess.h> #include <asm/system.h> #include <linux/bitops.h> diff --git a/net/core/dst.c b/net/core/dst.c index 470c05bc4cb2..1a5e49da0e77 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -95,12 +95,11 @@ static void dst_run_gc(unsigned long dummy) dst_gc_timer_inc = DST_GC_INC; dst_gc_timer_expires = DST_GC_MIN; } - dst_gc_timer.expires = jiffies + dst_gc_timer_expires; #if RT_CACHE_DEBUG >= 2 printk("dst_total: %d/%d %ld\n", atomic_read(&dst_total), delayed, dst_gc_timer_expires); #endif - add_timer(&dst_gc_timer); + mod_timer(&dst_gc_timer, jiffies + dst_gc_timer_expires); out: spin_unlock(&dst_lock); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 27ce1683caf5..87dc556fd9d6 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -143,7 +143,7 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) { struct ethtool_drvinfo info; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; if (!ops->get_drvinfo) return -EOPNOTSUPP; @@ -169,7 +169,7 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) { struct ethtool_regs regs; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; void *regbuf; int reglen, ret; @@ -282,7 +282,7 @@ static int ethtool_get_link(struct net_device *dev, void __user *useraddr) static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; u8 *data; int ret; @@ -327,7 +327,7 @@ static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; u8 *data; int ret; @@ -437,7 +437,7 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam; - if (!dev->ethtool_ops->get_pauseparam) + if (!dev->ethtool_ops->set_pauseparam) return -EOPNOTSUPP; if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam))) @@ -640,7 +640,7 @@ static int ethtool_set_gso(struct net_device *dev, char __user *useraddr) static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; u64 *data; int ret; @@ -673,7 +673,7 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) { struct ethtool_gstrings gstrings; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; u8 *data; int ret; @@ -733,7 +733,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) { struct ethtool_stats stats; - struct ethtool_ops *ops = dev->ethtool_ops; + const struct ethtool_ops *ops = dev->ethtool_ops; u64 *data; int ret; @@ -806,13 +806,6 @@ int dev_ethtool(struct ifreq *ifr) int rc; unsigned long old_features; - /* - * XXX: This can be pushed down into the ethtool_* handlers that - * need it. Keep existing behaviour for the moment. - */ - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - if (!dev || !netif_device_present(dev)) return -ENODEV; @@ -822,6 +815,27 @@ int dev_ethtool(struct ifreq *ifr) if (copy_from_user(ðcmd, useraddr, sizeof (ethcmd))) return -EFAULT; + /* Allow some commands to be done by anyone */ + switch(ethcmd) { + case ETHTOOL_GDRVINFO: + case ETHTOOL_GMSGLVL: + case ETHTOOL_GCOALESCE: + case ETHTOOL_GRINGPARAM: + case ETHTOOL_GPAUSEPARAM: + case ETHTOOL_GRXCSUM: + case ETHTOOL_GTXCSUM: + case ETHTOOL_GSG: + case ETHTOOL_GSTRINGS: + case ETHTOOL_GTSO: + case ETHTOOL_GPERMADDR: + case ETHTOOL_GUFO: + case ETHTOOL_GGSO: + break; + default: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + } + if(dev->ethtool_ops->begin) if ((rc = dev->ethtool_ops->begin(dev)) < 0) return rc; @@ -947,6 +961,10 @@ int dev_ethtool(struct ifreq *ifr) return rc; ioctl: + /* Keep existing behaviour for the moment. */ + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + if (dev->do_ioctl) return dev->do_ioctl(dev, ifr, SIOCETHTOOL); return -EOPNOTSUPP; diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c new file mode 100644 index 000000000000..a99d87d82b7f --- /dev/null +++ b/net/core/fib_rules.c @@ -0,0 +1,421 @@ +/* + * net/core/fib_rules.c Generic Routing Rules + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation, version 2. + * + * Authors: Thomas Graf <tgraf@suug.ch> + */ + +#include <linux/config.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <net/fib_rules.h> + +static LIST_HEAD(rules_ops); +static DEFINE_SPINLOCK(rules_mod_lock); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid); + +static struct fib_rules_ops *lookup_rules_ops(int family) +{ + struct fib_rules_ops *ops; + + rcu_read_lock(); + list_for_each_entry_rcu(ops, &rules_ops, list) { + if (ops->family == family) { + if (!try_module_get(ops->owner)) + ops = NULL; + rcu_read_unlock(); + return ops; + } + } + rcu_read_unlock(); + + return NULL; +} + +static void rules_ops_put(struct fib_rules_ops *ops) +{ + if (ops) + module_put(ops->owner); +} + +int fib_rules_register(struct fib_rules_ops *ops) +{ + int err = -EEXIST; + struct fib_rules_ops *o; + + if (ops->rule_size < sizeof(struct fib_rule)) + return -EINVAL; + + if (ops->match == NULL || ops->configure == NULL || + ops->compare == NULL || ops->fill == NULL || + ops->action == NULL) + return -EINVAL; + + spin_lock(&rules_mod_lock); + list_for_each_entry(o, &rules_ops, list) + if (ops->family == o->family) + goto errout; + + list_add_tail_rcu(&ops->list, &rules_ops); + err = 0; +errout: + spin_unlock(&rules_mod_lock); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_register); + +static void cleanup_ops(struct fib_rules_ops *ops) +{ + struct fib_rule *rule, *tmp; + + list_for_each_entry_safe(rule, tmp, ops->rules_list, list) { + list_del_rcu(&rule->list); + fib_rule_put(rule); + } +} + +int fib_rules_unregister(struct fib_rules_ops *ops) +{ + int err = 0; + struct fib_rules_ops *o; + + spin_lock(&rules_mod_lock); + list_for_each_entry(o, &rules_ops, list) { + if (o == ops) { + list_del_rcu(&o->list); + cleanup_ops(ops); + goto out; + } + } + + err = -ENOENT; +out: + spin_unlock(&rules_mod_lock); + + synchronize_rcu(); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_unregister); + +int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl, + int flags, struct fib_lookup_arg *arg) +{ + struct fib_rule *rule; + int err; + + rcu_read_lock(); + + list_for_each_entry_rcu(rule, ops->rules_list, list) { + if (rule->ifindex && (rule->ifindex != fl->iif)) + continue; + + if (!ops->match(rule, fl, flags)) + continue; + + err = ops->action(rule, fl, flags, arg); + if (err != -EAGAIN) { + fib_rule_get(rule); + arg->rule = rule; + goto out; + } + } + + err = -ENETUNREACH; +out: + rcu_read_unlock(); + + return err; +} + +EXPORT_SYMBOL_GPL(fib_rules_lookup); + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +{ + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule, *r, *last = NULL; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(frh->family); + if (ops == NULL) { + err = EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + rule = kzalloc(ops->rule_size, GFP_KERNEL); + if (rule == NULL) { + err = -ENOMEM; + goto errout; + } + + if (tb[FRA_PRIORITY]) + rule->pref = nla_get_u32(tb[FRA_PRIORITY]); + + if (tb[FRA_IFNAME]) { + struct net_device *dev; + + rule->ifindex = -1; + nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); + dev = __dev_get_by_name(rule->ifname); + if (dev) + rule->ifindex = dev->ifindex; + } + + rule->action = frh->action; + rule->flags = frh->flags; + rule->table = frh_get_table(frh, tb); + + if (!rule->pref && ops->default_pref) + rule->pref = ops->default_pref(); + + err = ops->configure(rule, skb, nlh, frh, tb); + if (err < 0) + goto errout_free; + + list_for_each_entry(r, ops->rules_list, list) { + if (r->pref > rule->pref) + break; + last = r; + } + + fib_rule_get(rule); + + if (last) + list_add_rcu(&rule->list, &last->list); + else + list_add_rcu(&rule->list, ops->rules_list); + + notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); + rules_ops_put(ops); + return 0; + +errout_free: + kfree(rule); +errout: + rules_ops_put(ops); + return err; +} + +int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +{ + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule; + struct nlattr *tb[FRA_MAX+1]; + int err = -EINVAL; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + goto errout; + + ops = lookup_rules_ops(frh->family); + if (ops == NULL) { + err = EAFNOSUPPORT; + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy); + if (err < 0) + goto errout; + + list_for_each_entry(rule, ops->rules_list, list) { + if (frh->action && (frh->action != rule->action)) + continue; + + if (frh->table && (frh_get_table(frh, tb) != rule->table)) + continue; + + if (tb[FRA_PRIORITY] && + (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) + continue; + + if (tb[FRA_IFNAME] && + nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + continue; + + if (!ops->compare(rule, frh, tb)) + continue; + + if (rule->flags & FIB_RULE_PERMANENT) { + err = -EPERM; + goto errout; + } + + list_del_rcu(&rule->list); + synchronize_rcu(); + notify_rule_change(RTM_DELRULE, rule, ops, nlh, + NETLINK_CB(skb).pid); + fib_rule_put(rule); + rules_ops_put(ops); + return 0; + } + + err = -ENOENT; +errout: + rules_ops_put(ops); + return err; +} + +static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, + u32 pid, u32 seq, int type, int flags, + struct fib_rules_ops *ops) +{ + struct nlmsghdr *nlh; + struct fib_rule_hdr *frh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags); + if (nlh == NULL) + return -1; + + frh = nlmsg_data(nlh); + frh->table = rule->table; + NLA_PUT_U32(skb, FRA_TABLE, rule->table); + frh->res1 = 0; + frh->res2 = 0; + frh->action = rule->action; + frh->flags = rule->flags; + + if (rule->ifname[0]) + NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + + if (rule->pref) + NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref); + + if (ops->fill(rule, skb, nlh, frh) < 0) + goto nla_put_failure; + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); +} + +int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family) +{ + int idx = 0; + struct fib_rule *rule; + struct fib_rules_ops *ops; + + ops = lookup_rules_ops(family); + if (ops == NULL) + return -EAFNOSUPPORT; + + rcu_read_lock(); + list_for_each_entry(rule, ops->rules_list, list) { + if (idx < cb->args[0]) + goto skip; + + if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWRULE, + NLM_F_MULTI, ops) < 0) + break; +skip: + idx++; + } + rcu_read_unlock(); + cb->args[0] = idx; + rules_ops_put(ops); + + return skb->len; +} + +EXPORT_SYMBOL_GPL(fib_rules_dump); + +static void notify_rule_change(int event, struct fib_rule *rule, + struct fib_rules_ops *ops, struct nlmsghdr *nlh, + u32 pid) +{ + struct sk_buff *skb; + int err = -ENOBUFS; + + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; + + err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops); + if (err < 0) { + kfree_skb(skb); + goto errout; + } + + err = rtnl_notify(skb, pid, ops->nlgroup, nlh, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(ops->nlgroup, err); +} + +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; + } +} + +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; +} + + +static int fib_rules_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct fib_rules_ops *ops; + + ASSERT_RTNL(); + rcu_read_lock(); + + switch (event) { + case NETDEV_REGISTER: + list_for_each_entry(ops, &rules_ops, list) + attach_rules(ops->rules_list, dev); + break; + + case NETDEV_UNREGISTER: + list_for_each_entry(ops, &rules_ops, list) + detach_rules(ops->rules_list, dev); + break; + } + + rcu_read_unlock(); + + return NOTIFY_DONE; +} + +static struct notifier_block fib_rules_notifier = { + .notifier_call = fib_rules_event, +}; + +static int __init fib_rules_init(void) +{ + return register_netdevice_notifier(&fib_rules_notifier); +} + +subsys_initcall(fib_rules_init); diff --git a/net/core/filter.c b/net/core/filter.c index 5b4486a60cf6..6732782a5a40 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -422,10 +422,10 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) if (!err) { struct sk_filter *old_fp; - spin_lock_bh(&sk->sk_lock.slock); - old_fp = sk->sk_filter; - sk->sk_filter = fp; - spin_unlock_bh(&sk->sk_lock.slock); + rcu_read_lock_bh(); + old_fp = rcu_dereference(sk->sk_filter); + rcu_assign_pointer(sk->sk_filter, fp); + rcu_read_unlock_bh(); fp = old_fp; } diff --git a/net/core/flow.c b/net/core/flow.c index 2191af5f26ac..f23e7e386543 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -32,7 +32,6 @@ struct flow_cache_entry { u8 dir; struct flowi key; u32 genid; - u32 sk_sid; void *object; atomic_t *object_ref; }; @@ -165,7 +164,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) return 0; } -void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, +void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver) { struct flow_cache_entry *fle, **head; @@ -189,7 +188,6 @@ void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, for (fle = *head; fle; fle = fle->next) { if (fle->family == family && fle->dir == dir && - fle->sk_sid == sk_sid && flow_key_compare(key, &fle->key) == 0) { if (fle->genid == atomic_read(&flow_cache_genid)) { void *ret = fle->object; @@ -214,7 +212,6 @@ void *flow_cache_lookup(struct flowi *key, u32 sk_sid, u16 family, u8 dir, *head = fle; fle->family = family; fle->dir = dir; - fle->sk_sid = sk_sid; memcpy(&fle->key, key, sizeof(*key)); fle->object = NULL; flow_count(cpu)++; @@ -226,7 +223,7 @@ nocache: void *obj; atomic_t *obj_ref; - resolver(key, sk_sid, family, dir, &obj, &obj_ref); + resolver(key, family, dir, &obj, &obj_ref); if (fle) { fle->genid = atomic_read(&flow_cache_genid); @@ -346,12 +343,8 @@ static int __init flow_cache_init(void) flow_cachep = kmem_cache_create("flow_cache", sizeof(struct flow_cache_entry), - 0, SLAB_HWCACHE_ALIGN, + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - - if (!flow_cachep) - panic("NET: failed to allocate flow cache slab\n"); - flow_hash_shift = 10; flow_lwm = 2 * flow_hash_size; flow_hwm = 4 * flow_hash_size; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index 0f37266411b5..4b36114744c5 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -11,7 +11,6 @@ * */ -#include <linux/config.h> #include <linux/module.h> #include <linux/netdevice.h> #include <linux/if.h> diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 50a8c73caf97..8ce8c471d868 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -15,7 +15,6 @@ * Harald Welte Add neighbour cache statistics like rtstat */ -#include <linux/config.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/module.h> @@ -30,6 +29,8 @@ #include <net/neighbour.h> #include <net/dst.h> #include <net/sock.h> +#include <net/netevent.h> +#include <net/netlink.h> #include <linux/rtnetlink.h> #include <linux/random.h> #include <linux/string.h> @@ -755,6 +756,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_STALE; neigh->updated = jiffies; neigh_suspect(neigh); + notify = 1; } } else if (state & NUD_DELAY) { if (time_before_eq(now, @@ -763,6 +765,7 @@ static void neigh_timer_handler(unsigned long arg) neigh->nud_state = NUD_REACHABLE; neigh->updated = jiffies; neigh_connect(neigh); + notify = 1; next = neigh->confirmed + neigh->parms->reachable_time; } else { NEIGH_PRINTK2("neigh %p is probed.\n", neigh); @@ -820,6 +823,8 @@ static void neigh_timer_handler(unsigned long arg) out: write_unlock(&neigh->lock); } + if (notify) + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); #ifdef CONFIG_ARPD if (notify && neigh->parms->app_probes) @@ -884,7 +889,7 @@ out_unlock_bh: return rc; } -static __inline__ void neigh_update_hhs(struct neighbour *neigh) +static void neigh_update_hhs(struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, struct net_device*, unsigned char *) = @@ -927,9 +932,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, { u8 old; int err; -#ifdef CONFIG_ARPD int notify = 0; -#endif struct net_device *dev; int update_isrouter = 0; @@ -949,9 +952,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh_suspect(neigh); neigh->nud_state = new; err = 0; -#ifdef CONFIG_ARPD notify = old & NUD_VALID; -#endif goto out; } @@ -1023,9 +1024,7 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - (neigh->parms->base_reachable_time << 1); -#ifdef CONFIG_ARPD notify = 1; -#endif } if (new == old) goto out; @@ -1057,6 +1056,9 @@ out: (neigh->flags & ~NTF_ROUTER); } write_unlock_bh(&neigh->lock); + + if (notify) + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); #ifdef CONFIG_ARPD if (notify && neigh->parms->app_probes) neigh_app_notify(neigh); @@ -1077,7 +1079,7 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, } static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, - u16 protocol) + __be16 protocol) { struct hh_cache *hh; struct net_device *dev = dst->dev; @@ -1337,14 +1339,10 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) neigh_rand_reach_time(tbl->parms.base_reachable_time); if (!tbl->kmem_cachep) - tbl->kmem_cachep = kmem_cache_create(tbl->id, - tbl->entry_size, - 0, SLAB_HWCACHE_ALIGN, - NULL, NULL); - - if (!tbl->kmem_cachep) - panic("cannot create neighbour cache"); - + tbl->kmem_cachep = + kmem_cache_create(tbl->id, tbl->entry_size, 0, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, + NULL, NULL); tbl->stats = alloc_percpu(struct neigh_statistics); if (!tbl->stats) panic("cannot create neighbour cache statistics"); @@ -1431,53 +1429,70 @@ int neigh_table_clear(struct neigh_table *tbl) kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; + free_percpu(tbl->stats); + tbl->stats = NULL; + return 0; } int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct ndmsg *ndm; + struct nlattr *dst_attr; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err = -EINVAL; + + if (nlmsg_len(nlh) < sizeof(*ndm)) + goto out; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + dst_attr = nlmsg_find_attr(nlh, sizeof(*ndm), NDA_DST); + if (dst_attr == NULL) goto out; + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index(ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *dst_attr = nda[NDA_DST - 1]; - struct neighbour *n; + struct neighbour *neigh; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) + if (nla_len(dst_attr) < tbl->key_len) goto out_dev_put; if (ndm->ndm_flags & NTF_PROXY) { - err = pneigh_delete(tbl, RTA_DATA(dst_attr), dev); + err = pneigh_delete(tbl, nla_data(dst_attr), dev); goto out_dev_put; } - if (!dev) - goto out; + if (dev == NULL) + goto out_dev_put; - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - err = neigh_update(n, NULL, NUD_FAILED, - NEIGH_UPDATE_F_OVERRIDE| - NEIGH_UPDATE_F_ADMIN); - neigh_release(n); + neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); + if (neigh == NULL) { + err = -ENOENT; + goto out_dev_put; } + + err = neigh_update(neigh, NULL, NUD_FAILED, + NEIGH_UPDATE_F_OVERRIDE | + NEIGH_UPDATE_F_ADMIN); + neigh_release(neigh); goto out_dev_put; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; + err = -EAFNOSUPPORT; + out_dev_put: if (dev) dev_put(dev); @@ -1487,76 +1502,93 @@ out: int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ndmsg *ndm = NLMSG_DATA(nlh); - struct rtattr **nda = arg; + struct ndmsg *ndm; + struct nlattr *tb[NDA_MAX+1]; struct neigh_table *tbl; struct net_device *dev = NULL; - int err = -ENODEV; + int err; - if (ndm->ndm_ifindex && - (dev = dev_get_by_index(ndm->ndm_ifindex)) == NULL) + err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); + if (err < 0) goto out; + err = -EINVAL; + if (tb[NDA_DST] == NULL) + goto out; + + ndm = nlmsg_data(nlh); + if (ndm->ndm_ifindex) { + dev = dev_get_by_index(ndm->ndm_ifindex); + if (dev == NULL) { + err = -ENODEV; + goto out; + } + + if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) + goto out_dev_put; + } + read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { - struct rtattr *lladdr_attr = nda[NDA_LLADDR - 1]; - struct rtattr *dst_attr = nda[NDA_DST - 1]; - int override = 1; - struct neighbour *n; + int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE; + struct neighbour *neigh; + void *dst, *lladdr; if (tbl->family != ndm->ndm_family) continue; read_unlock(&neigh_tbl_lock); - err = -EINVAL; - if (!dst_attr || RTA_PAYLOAD(dst_attr) < tbl->key_len) + if (nla_len(tb[NDA_DST]) < tbl->key_len) goto out_dev_put; + dst = nla_data(tb[NDA_DST]); + lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; if (ndm->ndm_flags & NTF_PROXY) { + struct pneigh_entry *pn; + err = -ENOBUFS; - if (pneigh_lookup(tbl, RTA_DATA(dst_attr), dev, 1)) + pn = pneigh_lookup(tbl, dst, dev, 1); + if (pn) { + pn->flags = ndm->ndm_flags; err = 0; + } goto out_dev_put; } - err = -EINVAL; - if (!dev) - goto out; - if (lladdr_attr && RTA_PAYLOAD(lladdr_attr) < dev->addr_len) + if (dev == NULL) goto out_dev_put; + + neigh = neigh_lookup(tbl, dst, dev); + if (neigh == NULL) { + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + err = -ENOENT; + goto out_dev_put; + } - n = neigh_lookup(tbl, RTA_DATA(dst_attr), dev); - if (n) { - if (nlh->nlmsg_flags & NLM_F_EXCL) { - err = -EEXIST; - neigh_release(n); + neigh = __neigh_lookup_errno(tbl, dst, dev); + if (IS_ERR(neigh)) { + err = PTR_ERR(neigh); goto out_dev_put; } - - override = nlh->nlmsg_flags & NLM_F_REPLACE; - } else if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { - err = -ENOENT; - goto out_dev_put; } else { - n = __neigh_lookup_errno(tbl, RTA_DATA(dst_attr), dev); - if (IS_ERR(n)) { - err = PTR_ERR(n); + if (nlh->nlmsg_flags & NLM_F_EXCL) { + err = -EEXIST; + neigh_release(neigh); goto out_dev_put; } - } - err = neigh_update(n, - lladdr_attr ? RTA_DATA(lladdr_attr) : NULL, - ndm->ndm_state, - (override ? NEIGH_UPDATE_F_OVERRIDE : 0) | - NEIGH_UPDATE_F_ADMIN); + if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) + flags &= ~NEIGH_UPDATE_F_OVERRIDE; + } - neigh_release(n); + err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); + neigh_release(neigh); goto out_dev_put; } read_unlock(&neigh_tbl_lock); - err = -EADDRNOTAVAIL; + err = -EAFNOSUPPORT; + out_dev_put: if (dev) dev_put(dev); @@ -1566,56 +1598,59 @@ out: static int neightbl_fill_parms(struct sk_buff *skb, struct neigh_parms *parms) { - struct rtattr *nest = NULL; - - nest = RTA_NEST(skb, NDTA_PARMS); + struct nlattr *nest; + + nest = nla_nest_start(skb, NDTA_PARMS); + if (nest == NULL) + return -ENOBUFS; if (parms->dev) - RTA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); - - RTA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); - RTA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); - RTA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); - RTA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); - RTA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); - RTA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); - RTA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); - RTA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, + NLA_PUT_U32(skb, NDTPA_IFINDEX, parms->dev->ifindex); + + NLA_PUT_U32(skb, NDTPA_REFCNT, atomic_read(&parms->refcnt)); + NLA_PUT_U32(skb, NDTPA_QUEUE_LEN, parms->queue_len); + NLA_PUT_U32(skb, NDTPA_PROXY_QLEN, parms->proxy_qlen); + NLA_PUT_U32(skb, NDTPA_APP_PROBES, parms->app_probes); + NLA_PUT_U32(skb, NDTPA_UCAST_PROBES, parms->ucast_probes); + NLA_PUT_U32(skb, NDTPA_MCAST_PROBES, parms->mcast_probes); + NLA_PUT_MSECS(skb, NDTPA_REACHABLE_TIME, parms->reachable_time); + NLA_PUT_MSECS(skb, NDTPA_BASE_REACHABLE_TIME, parms->base_reachable_time); - RTA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); - RTA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); - RTA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); - RTA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); - RTA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); - RTA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); + NLA_PUT_MSECS(skb, NDTPA_GC_STALETIME, parms->gc_staletime); + NLA_PUT_MSECS(skb, NDTPA_DELAY_PROBE_TIME, parms->delay_probe_time); + NLA_PUT_MSECS(skb, NDTPA_RETRANS_TIME, parms->retrans_time); + NLA_PUT_MSECS(skb, NDTPA_ANYCAST_DELAY, parms->anycast_delay); + NLA_PUT_MSECS(skb, NDTPA_PROXY_DELAY, parms->proxy_delay); + NLA_PUT_MSECS(skb, NDTPA_LOCKTIME, parms->locktime); - return RTA_NEST_END(skb, nest); + return nla_nest_end(skb, nest); -rtattr_failure: - return RTA_NEST_CANCEL(skb, nest); +nla_put_failure: + return nla_nest_cancel(skb, nest); } -static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, - struct netlink_callback *cb) +static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, + u32 pid, u32 seq, int type, int flags) { struct nlmsghdr *nlh; struct ndtmsg *ndtmsg; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -ENOBUFS; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - RTA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); - RTA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); - RTA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); - RTA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); + NLA_PUT_STRING(skb, NDTA_NAME, tbl->id); + NLA_PUT_MSECS(skb, NDTA_GC_INTERVAL, tbl->gc_interval); + NLA_PUT_U32(skb, NDTA_THRESH1, tbl->gc_thresh1); + NLA_PUT_U32(skb, NDTA_THRESH2, tbl->gc_thresh2); + NLA_PUT_U32(skb, NDTA_THRESH3, tbl->gc_thresh3); { unsigned long now = jiffies; @@ -1634,7 +1669,7 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; - RTA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); + NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); } { @@ -1659,55 +1694,50 @@ static int neightbl_fill_info(struct neigh_table *tbl, struct sk_buff *skb, ndst.ndts_forced_gc_runs += st->forced_gc_runs; } - RTA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); + NLA_PUT(skb, NDTA_STATS, sizeof(ndst), &ndst); } BUG_ON(tbl->parms.dev); if (neightbl_fill_parms(skb, &tbl->parms) < 0) - goto rtattr_failure; + goto nla_put_failure; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); + return nlmsg_end(skb, nlh); -rtattr_failure: +nla_put_failure: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + return nlmsg_cancel(skb, nlh); } -static int neightbl_fill_param_info(struct neigh_table *tbl, +static int neightbl_fill_param_info(struct sk_buff *skb, + struct neigh_table *tbl, struct neigh_parms *parms, - struct sk_buff *skb, - struct netlink_callback *cb) + u32 pid, u32 seq, int type, + unsigned int flags) { struct ndtmsg *ndtmsg; struct nlmsghdr *nlh; - nlh = NLMSG_NEW_ANSWER(skb, cb, RTM_NEWNEIGHTBL, sizeof(struct ndtmsg), - NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndtmsg), flags); + if (nlh == NULL) + return -ENOBUFS; - ndtmsg = NLMSG_DATA(nlh); + ndtmsg = nlmsg_data(nlh); read_lock_bh(&tbl->lock); ndtmsg->ndtm_family = tbl->family; ndtmsg->ndtm_pad1 = 0; ndtmsg->ndtm_pad2 = 0; - RTA_PUT_STRING(skb, NDTA_NAME, tbl->id); - if (neightbl_fill_parms(skb, parms) < 0) - goto rtattr_failure; + if (nla_put_string(skb, NDTA_NAME, tbl->id) < 0 || + neightbl_fill_parms(skb, parms) < 0) + goto errout; read_unlock_bh(&tbl->lock); - return NLMSG_END(skb, nlh); - -rtattr_failure: + return nlmsg_end(skb, nlh); +errout: read_unlock_bh(&tbl->lock); - return NLMSG_CANCEL(skb, nlh); - -nlmsg_failure: - return -1; + return nlmsg_cancel(skb, nlh); } static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, @@ -1723,28 +1753,61 @@ static inline struct neigh_parms *lookup_neigh_params(struct neigh_table *tbl, return NULL; } +static struct nla_policy nl_neightbl_policy[NDTA_MAX+1] __read_mostly = { + [NDTA_NAME] = { .type = NLA_STRING }, + [NDTA_THRESH1] = { .type = NLA_U32 }, + [NDTA_THRESH2] = { .type = NLA_U32 }, + [NDTA_THRESH3] = { .type = NLA_U32 }, + [NDTA_GC_INTERVAL] = { .type = NLA_U64 }, + [NDTA_PARMS] = { .type = NLA_NESTED }, +}; + +static struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] __read_mostly = { + [NDTPA_IFINDEX] = { .type = NLA_U32 }, + [NDTPA_QUEUE_LEN] = { .type = NLA_U32 }, + [NDTPA_PROXY_QLEN] = { .type = NLA_U32 }, + [NDTPA_APP_PROBES] = { .type = NLA_U32 }, + [NDTPA_UCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_MCAST_PROBES] = { .type = NLA_U32 }, + [NDTPA_BASE_REACHABLE_TIME] = { .type = NLA_U64 }, + [NDTPA_GC_STALETIME] = { .type = NLA_U64 }, + [NDTPA_DELAY_PROBE_TIME] = { .type = NLA_U64 }, + [NDTPA_RETRANS_TIME] = { .type = NLA_U64 }, + [NDTPA_ANYCAST_DELAY] = { .type = NLA_U64 }, + [NDTPA_PROXY_DELAY] = { .type = NLA_U64 }, + [NDTPA_LOCKTIME] = { .type = NLA_U64 }, +}; + int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct neigh_table *tbl; - struct ndtmsg *ndtmsg = NLMSG_DATA(nlh); - struct rtattr **tb = arg; - int err = -EINVAL; + struct ndtmsg *ndtmsg; + struct nlattr *tb[NDTA_MAX+1]; + int err; - if (!tb[NDTA_NAME - 1] || !RTA_PAYLOAD(tb[NDTA_NAME - 1])) - return -EINVAL; + err = nlmsg_parse(nlh, sizeof(*ndtmsg), tb, NDTA_MAX, + nl_neightbl_policy); + if (err < 0) + goto errout; + + if (tb[NDTA_NAME] == NULL) { + err = -EINVAL; + goto errout; + } + ndtmsg = nlmsg_data(nlh); read_lock(&neigh_tbl_lock); for (tbl = neigh_tables; tbl; tbl = tbl->next) { if (ndtmsg->ndtm_family && tbl->family != ndtmsg->ndtm_family) continue; - if (!rtattr_strcmp(tb[NDTA_NAME - 1], tbl->id)) + if (nla_strcmp(tb[NDTA_NAME], tbl->id) == 0) break; } if (tbl == NULL) { err = -ENOENT; - goto errout; + goto errout_locked; } /* @@ -1753,165 +1816,178 @@ int neightbl_set(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) */ write_lock_bh(&tbl->lock); - if (tb[NDTA_THRESH1 - 1]) - tbl->gc_thresh1 = RTA_GET_U32(tb[NDTA_THRESH1 - 1]); - - if (tb[NDTA_THRESH2 - 1]) - tbl->gc_thresh2 = RTA_GET_U32(tb[NDTA_THRESH2 - 1]); - - if (tb[NDTA_THRESH3 - 1]) - tbl->gc_thresh3 = RTA_GET_U32(tb[NDTA_THRESH3 - 1]); - - if (tb[NDTA_GC_INTERVAL - 1]) - tbl->gc_interval = RTA_GET_MSECS(tb[NDTA_GC_INTERVAL - 1]); - - if (tb[NDTA_PARMS - 1]) { - struct rtattr *tbp[NDTPA_MAX]; + if (tb[NDTA_PARMS]) { + struct nlattr *tbp[NDTPA_MAX+1]; struct neigh_parms *p; - u32 ifindex = 0; + int i, ifindex = 0; - if (rtattr_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS - 1]) < 0) - goto rtattr_failure; + err = nla_parse_nested(tbp, NDTPA_MAX, tb[NDTA_PARMS], + nl_ntbl_parm_policy); + if (err < 0) + goto errout_tbl_lock; - if (tbp[NDTPA_IFINDEX - 1]) - ifindex = RTA_GET_U32(tbp[NDTPA_IFINDEX - 1]); + if (tbp[NDTPA_IFINDEX]) + ifindex = nla_get_u32(tbp[NDTPA_IFINDEX]); p = lookup_neigh_params(tbl, ifindex); if (p == NULL) { err = -ENOENT; - goto rtattr_failure; + goto errout_tbl_lock; } - - if (tbp[NDTPA_QUEUE_LEN - 1]) - p->queue_len = RTA_GET_U32(tbp[NDTPA_QUEUE_LEN - 1]); - - if (tbp[NDTPA_PROXY_QLEN - 1]) - p->proxy_qlen = RTA_GET_U32(tbp[NDTPA_PROXY_QLEN - 1]); - - if (tbp[NDTPA_APP_PROBES - 1]) - p->app_probes = RTA_GET_U32(tbp[NDTPA_APP_PROBES - 1]); - - if (tbp[NDTPA_UCAST_PROBES - 1]) - p->ucast_probes = - RTA_GET_U32(tbp[NDTPA_UCAST_PROBES - 1]); - if (tbp[NDTPA_MCAST_PROBES - 1]) - p->mcast_probes = - RTA_GET_U32(tbp[NDTPA_MCAST_PROBES - 1]); - - if (tbp[NDTPA_BASE_REACHABLE_TIME - 1]) - p->base_reachable_time = - RTA_GET_MSECS(tbp[NDTPA_BASE_REACHABLE_TIME - 1]); + for (i = 1; i <= NDTPA_MAX; i++) { + if (tbp[i] == NULL) + continue; - if (tbp[NDTPA_GC_STALETIME - 1]) - p->gc_staletime = - RTA_GET_MSECS(tbp[NDTPA_GC_STALETIME - 1]); + switch (i) { + case NDTPA_QUEUE_LEN: + p->queue_len = nla_get_u32(tbp[i]); + break; + case NDTPA_PROXY_QLEN: + p->proxy_qlen = nla_get_u32(tbp[i]); + break; + case NDTPA_APP_PROBES: + p->app_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_UCAST_PROBES: + p->ucast_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_MCAST_PROBES: + p->mcast_probes = nla_get_u32(tbp[i]); + break; + case NDTPA_BASE_REACHABLE_TIME: + p->base_reachable_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_GC_STALETIME: + p->gc_staletime = nla_get_msecs(tbp[i]); + break; + case NDTPA_DELAY_PROBE_TIME: + p->delay_probe_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_RETRANS_TIME: + p->retrans_time = nla_get_msecs(tbp[i]); + break; + case NDTPA_ANYCAST_DELAY: + p->anycast_delay = nla_get_msecs(tbp[i]); + break; + case NDTPA_PROXY_DELAY: + p->proxy_delay = nla_get_msecs(tbp[i]); + break; + case NDTPA_LOCKTIME: + p->locktime = nla_get_msecs(tbp[i]); + break; + } + } + } - if (tbp[NDTPA_DELAY_PROBE_TIME - 1]) - p->delay_probe_time = - RTA_GET_MSECS(tbp[NDTPA_DELAY_PROBE_TIME - 1]); + if (tb[NDTA_THRESH1]) + tbl->gc_thresh1 = nla_get_u32(tb[NDTA_THRESH1]); - if (tbp[NDTPA_RETRANS_TIME - 1]) - p->retrans_time = - RTA_GET_MSECS(tbp[NDTPA_RETRANS_TIME - 1]); + if (tb[NDTA_THRESH2]) + tbl->gc_thresh2 = nla_get_u32(tb[NDTA_THRESH2]); - if (tbp[NDTPA_ANYCAST_DELAY - 1]) - p->anycast_delay = - RTA_GET_MSECS(tbp[NDTPA_ANYCAST_DELAY - 1]); + if (tb[NDTA_THRESH3]) + tbl->gc_thresh3 = nla_get_u32(tb[NDTA_THRESH3]); - if (tbp[NDTPA_PROXY_DELAY - 1]) - p->proxy_delay = - RTA_GET_MSECS(tbp[NDTPA_PROXY_DELAY - 1]); - - if (tbp[NDTPA_LOCKTIME - 1]) - p->locktime = RTA_GET_MSECS(tbp[NDTPA_LOCKTIME - 1]); - } + if (tb[NDTA_GC_INTERVAL]) + tbl->gc_interval = nla_get_msecs(tb[NDTA_GC_INTERVAL]); err = 0; -rtattr_failure: +errout_tbl_lock: write_unlock_bh(&tbl->lock); -errout: +errout_locked: read_unlock(&neigh_tbl_lock); +errout: return err; } int neightbl_dump_info(struct sk_buff *skb, struct netlink_callback *cb) { - int idx, family; - int s_idx = cb->args[0]; + int family, tidx, nidx = 0; + int tbl_skip = cb->args[0]; + int neigh_skip = cb->args[1]; struct neigh_table *tbl; - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; read_lock(&neigh_tbl_lock); - for (tbl = neigh_tables, idx = 0; tbl; tbl = tbl->next) { + for (tbl = neigh_tables, tidx = 0; tbl; tbl = tbl->next, tidx++) { struct neigh_parms *p; - if (idx < s_idx || (family && tbl->family != family)) + if (tidx < tbl_skip || (family && tbl->family != family)) continue; - if (neightbl_fill_info(tbl, skb, cb) <= 0) + if (neightbl_fill_info(skb, tbl, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) break; - for (++idx, p = tbl->parms.next; p; p = p->next, idx++) { - if (idx < s_idx) + for (nidx = 0, p = tbl->parms.next; p; p = p->next, nidx++) { + if (nidx < neigh_skip) continue; - if (neightbl_fill_param_info(tbl, p, skb, cb) <= 0) + if (neightbl_fill_param_info(skb, tbl, p, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWNEIGHTBL, + NLM_F_MULTI) <= 0) goto out; } + neigh_skip = 0; } out: read_unlock(&neigh_tbl_lock); - cb->args[0] = idx; + cb->args[0] = tidx; + cb->args[1] = nidx; return skb->len; } -static int neigh_fill_info(struct sk_buff *skb, struct neighbour *n, - u32 pid, u32 seq, int event, unsigned int flags) +static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, + u32 pid, u32 seq, int type, unsigned int flags) { unsigned long now = jiffies; - unsigned char *b = skb->tail; struct nda_cacheinfo ci; - int locked = 0; - u32 probes; - struct nlmsghdr *nlh = NLMSG_NEW(skb, pid, seq, event, - sizeof(struct ndmsg), flags); - struct ndmsg *ndm = NLMSG_DATA(nlh); + struct nlmsghdr *nlh; + struct ndmsg *ndm; - ndm->ndm_family = n->ops->family; + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ndm), flags); + if (nlh == NULL) + return -ENOBUFS; + + ndm = nlmsg_data(nlh); + ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = n->flags; - ndm->ndm_type = n->type; - ndm->ndm_ifindex = n->dev->ifindex; - RTA_PUT(skb, NDA_DST, n->tbl->key_len, n->primary_key); - read_lock_bh(&n->lock); - locked = 1; - ndm->ndm_state = n->nud_state; - if (n->nud_state & NUD_VALID) - RTA_PUT(skb, NDA_LLADDR, n->dev->addr_len, n->ha); - ci.ndm_used = now - n->used; - ci.ndm_confirmed = now - n->confirmed; - ci.ndm_updated = now - n->updated; - ci.ndm_refcnt = atomic_read(&n->refcnt) - 1; - probes = atomic_read(&n->probes); - read_unlock_bh(&n->lock); - locked = 0; - RTA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); - RTA_PUT(skb, NDA_PROBES, sizeof(probes), &probes); - nlh->nlmsg_len = skb->tail - b; - return skb->len; + ndm->ndm_flags = neigh->flags; + ndm->ndm_type = neigh->type; + ndm->ndm_ifindex = neigh->dev->ifindex; + + NLA_PUT(skb, NDA_DST, neigh->tbl->key_len, neigh->primary_key); -nlmsg_failure: -rtattr_failure: - if (locked) - read_unlock_bh(&n->lock); - skb_trim(skb, b - skb->data); - return -1; + read_lock_bh(&neigh->lock); + ndm->ndm_state = neigh->nud_state; + if ((neigh->nud_state & NUD_VALID) && + nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) { + read_unlock_bh(&neigh->lock); + goto nla_put_failure; + } + + ci.ndm_used = now - neigh->used; + ci.ndm_confirmed = now - neigh->confirmed; + ci.ndm_updated = now - neigh->updated; + ci.ndm_refcnt = atomic_read(&neigh->refcnt) - 1; + read_unlock_bh(&neigh->lock); + + NLA_PUT_U32(skb, NDA_PROBES, atomic_read(&neigh->probes)); + NLA_PUT(skb, NDA_CACHEINFO, sizeof(ci), &ci); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } @@ -1955,7 +2031,7 @@ int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) int t, family, s_t; read_lock(&neigh_tbl_lock); - family = ((struct rtgenmsg *)NLMSG_DATA(cb->nlh))->rtgen_family; + family = ((struct rtgenmsg *) nlmsg_data(cb->nlh))->rtgen_family; s_t = cb->args[0]; for (tbl = neigh_tables, t = 0; tbl; tbl = tbl->next, t++) { @@ -2334,41 +2410,35 @@ static struct file_operations neigh_stat_seq_fops = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_ARPD -void neigh_app_ns(struct neighbour *n) +static void __neigh_notify(struct neighbour *n, int type, int flags) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); + struct sk_buff *skb; + int err = -ENOBUFS; - if (!skb) - return; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); + if (skb == NULL) + goto errout; - if (neigh_fill_info(skb, n, 0, 0, RTM_GETNEIGH, 0) < 0) { + err = neigh_fill_info(skb, n, 0, 0, type, flags); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - nlh = (struct nlmsghdr *)skb->data; - nlh->nlmsg_flags = NLM_F_REQUEST; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); + + err = rtnl_notify(skb, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_NEIGH, err); } -static void neigh_app_notify(struct neighbour *n) +void neigh_app_ns(struct neighbour *n) { - struct nlmsghdr *nlh; - int size = NLMSG_SPACE(sizeof(struct ndmsg) + 256); - struct sk_buff *skb = alloc_skb(size, GFP_ATOMIC); - - if (!skb) - return; + __neigh_notify(n, RTM_GETNEIGH, NLM_F_REQUEST); +} - if (neigh_fill_info(skb, n, 0, 0, RTM_NEWNEIGH, 0) < 0) { - kfree_skb(skb); - return; - } - nlh = (struct nlmsghdr *)skb->data; - NETLINK_CB(skb).dst_group = RTNLGRP_NEIGH; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_NEIGH, GFP_ATOMIC); +static void neigh_app_notify(struct neighbour *n) +{ + __neigh_notify(n, RTM_NEWNEIGH, 0); } #endif /* CONFIG_ARPD */ @@ -2382,7 +2452,7 @@ static struct neigh_sysctl_table { ctl_table neigh_neigh_dir[2]; ctl_table neigh_proto_dir[2]; ctl_table neigh_root_dir[2]; -} neigh_sysctl_template = { +} neigh_sysctl_template __read_mostly = { .neigh_vars = { { .ctl_name = NET_NEIGH_MCAST_SOLICIT, @@ -2655,7 +2725,6 @@ void neigh_sysctl_unregister(struct neigh_parms *p) #endif /* CONFIG_SYSCTL */ EXPORT_SYMBOL(__neigh_event_send); -EXPORT_SYMBOL(neigh_add); EXPORT_SYMBOL(neigh_changeaddr); EXPORT_SYMBOL(neigh_compat_output); EXPORT_SYMBOL(neigh_connected_output); @@ -2675,11 +2744,8 @@ EXPORT_SYMBOL(neigh_table_clear); EXPORT_SYMBOL(neigh_table_init); EXPORT_SYMBOL(neigh_table_init_no_netlink); EXPORT_SYMBOL(neigh_update); -EXPORT_SYMBOL(neigh_update_hhs); EXPORT_SYMBOL(pneigh_enqueue); EXPORT_SYMBOL(pneigh_lookup); -EXPORT_SYMBOL(neightbl_dump_info); -EXPORT_SYMBOL(neightbl_set); #ifdef CONFIG_ARPD EXPORT_SYMBOL(neigh_app_ns); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 47a6fceb6771..f47f319bb7dc 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -10,7 +10,6 @@ */ #include <linux/capability.h> -#include <linux/config.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/if_arp.h> @@ -345,8 +344,6 @@ static ssize_t wireless_show(struct class_device *cd, char *buf, if(dev->wireless_handlers && dev->wireless_handlers->get_wireless_stats) iw = dev->wireless_handlers->get_wireless_stats(dev); - else if (dev->get_wireless_stats) - iw = dev->get_wireless_stats(dev); if (iw != NULL) ret = (*format)(iw, buf); } @@ -466,8 +463,7 @@ int netdev_register_sysfs(struct net_device *net) *groups++ = &netstat_group; #ifdef WIRELESS_EXT - if (net->get_wireless_stats - || (net->wireless_handlers && net->wireless_handlers->get_wireless_stats)) + if (net->wireless_handlers && net->wireless_handlers->get_wireless_stats) *groups++ = &wireless_group; #endif diff --git a/net/core/netevent.c b/net/core/netevent.c new file mode 100644 index 000000000000..35d02c38554e --- /dev/null +++ b/net/core/netevent.c @@ -0,0 +1,69 @@ +/* + * Network event notifiers + * + * Authors: + * Tom Tucker <tom@opengridcomputing.com> + * Steve Wise <swise@opengridcomputing.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + * Fixes: + */ + +#include <linux/rtnetlink.h> +#include <linux/notifier.h> + +static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain); + +/** + * register_netevent_notifier - register a netevent notifier block + * @nb: notifier + * + * Register a notifier to be called when a netevent occurs. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + */ +int register_netevent_notifier(struct notifier_block *nb) +{ + int err; + + err = atomic_notifier_chain_register(&netevent_notif_chain, nb); + return err; +} + +/** + * netevent_unregister_notifier - unregister a netevent notifier block + * @nb: notifier + * + * Unregister a notifier previously registered by + * register_neigh_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. + */ + +int unregister_netevent_notifier(struct notifier_block *nb) +{ + return atomic_notifier_chain_unregister(&netevent_notif_chain, nb); +} + +/** + * call_netevent_notifiers - call all netevent notifier blocks + * @val: value passed unmodified to notifier function + * @v: pointer passed unmodified to notifier function + * + * Call all neighbour notifier blocks. Parameters and return value + * are as for notifier_call_chain(). + */ + +int call_netevent_notifiers(unsigned long val, void *v) +{ + return atomic_notifier_call_chain(&netevent_notif_chain, val, v); +} + +EXPORT_SYMBOL_GPL(register_netevent_notifier); +EXPORT_SYMBOL_GPL(unregister_netevent_notifier); +EXPORT_SYMBOL_GPL(call_netevent_notifiers); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 9cb781830380..ead5920c26d6 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -54,6 +54,7 @@ static atomic_t trapped; sizeof(struct iphdr) + sizeof(struct ethhdr)) static void zap_completion_queue(void); +static void arp_reply(struct sk_buff *skb); static void queue_process(void *p) { @@ -109,7 +110,7 @@ static int checksum_udp(struct sk_buff *skb, struct udphdr *uh, psum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0); - if (skb->ip_summed == CHECKSUM_HW && + if (skb->ip_summed == CHECKSUM_COMPLETE && !(u16)csum_fold(csum_add(psum, skb->csum))) return 0; @@ -153,6 +154,22 @@ static void poll_napi(struct netpoll *np) } } +static void service_arp_queue(struct netpoll_info *npi) +{ + struct sk_buff *skb; + + if (unlikely(!npi)) + return; + + skb = skb_dequeue(&npi->arp_tx); + + while (skb != NULL) { + arp_reply(skb); + skb = skb_dequeue(&npi->arp_tx); + } + return; +} + void netpoll_poll(struct netpoll *np) { if(!np->dev || !netif_running(np->dev) || !np->dev->poll_controller) @@ -163,6 +180,8 @@ void netpoll_poll(struct netpoll *np) if (np->dev->poll) poll_napi(np); + service_arp_queue(np->dev->npinfo); + zap_completion_queue(); } @@ -279,14 +298,10 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) * network drivers do not expect to be called if the queue is * stopped. */ - if (netif_queue_stopped(np->dev)) { - netif_tx_unlock(np->dev); - netpoll_poll(np); - udelay(50); - continue; - } + status = NETDEV_TX_BUSY; + if (!netif_queue_stopped(np->dev)) + status = np->dev->hard_start_xmit(skb, np->dev); - status = np->dev->hard_start_xmit(skb, np->dev); netif_tx_unlock(np->dev); /* success */ @@ -446,7 +461,9 @@ int __netpoll_rx(struct sk_buff *skb) int proto, len, ulen; struct iphdr *iph; struct udphdr *uh; - struct netpoll *np = skb->dev->npinfo->rx_np; + struct netpoll_info *npi = skb->dev->npinfo; + struct netpoll *np = npi->rx_np; + if (!np) goto out; @@ -456,7 +473,7 @@ int __netpoll_rx(struct sk_buff *skb) /* check if netpoll clients need ARP */ if (skb->protocol == __constant_htons(ETH_P_ARP) && atomic_read(&trapped)) { - arp_reply(skb); + skb_queue_tail(&npi->arp_tx, skb); return 1; } @@ -651,6 +668,7 @@ int netpoll_setup(struct netpoll *np) npinfo->poll_owner = -1; npinfo->tries = MAX_RETRIES; spin_lock_init(&npinfo->rx_lock); + skb_queue_head_init(&npinfo->arp_tx); } else npinfo = ndev->npinfo; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 67ed14ddabd2..dd023fd28304 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -109,6 +109,8 @@ * * MPLS support by Steven Whitehouse <steve@chygwyn.com> * + * 802.1Q/Q-in-Q support by Francesco Fondelli (FF) <francesco.fondelli@gmail.com> + * */ #include <linux/sys.h> #include <linux/types.h> @@ -137,6 +139,7 @@ #include <linux/inetdevice.h> #include <linux/rtnetlink.h> #include <linux/if_arp.h> +#include <linux/if_vlan.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> @@ -157,7 +160,7 @@ #include <asm/div64.h> /* do_div */ #include <asm/timex.h> -#define VERSION "pktgen v2.67: Packet Generator for packet performance testing.\n" +#define VERSION "pktgen v2.68: Packet Generator for packet performance testing.\n" /* #define PG_DEBUG(a) a */ #define PG_DEBUG(a) @@ -178,6 +181,8 @@ #define F_TXSIZE_RND (1<<6) /* Transmit size is random */ #define F_IPV6 (1<<7) /* Interface in IPV6 Mode */ #define F_MPLS_RND (1<<8) /* Random MPLS labels */ +#define F_VID_RND (1<<9) /* Random VLAN ID */ +#define F_SVID_RND (1<<10) /* Random SVLAN ID */ /* Thread control flag bits */ #define T_TERMINATE (1<<0) @@ -198,6 +203,9 @@ static struct proc_dir_entry *pg_proc_dir = NULL; #define MAX_CFLOWS 65536 +#define VLAN_TAG_SIZE(x) ((x)->vlan_id == 0xffff ? 0 : 4) +#define SVLAN_TAG_SIZE(x) ((x)->svlan_id == 0xffff ? 0 : 4) + struct flow_state { __u32 cur_daddr; int count; @@ -284,10 +292,23 @@ struct pktgen_dev { __u16 udp_dst_min; /* inclusive, dest UDP port */ __u16 udp_dst_max; /* exclusive, dest UDP port */ + /* DSCP + ECN */ + __u8 tos; /* six most significant bits of (former) IPv4 TOS are for dscp codepoint */ + __u8 traffic_class; /* ditto for the (former) Traffic Class in IPv6 (see RFC 3260, sec. 4) */ + /* MPLS */ unsigned nr_labels; /* Depth of stack, 0 = no MPLS */ __be32 labels[MAX_MPLS_LABELS]; + /* VLAN/SVLAN (802.1Q/Q-in-Q) */ + __u8 vlan_p; + __u8 vlan_cfi; + __u16 vlan_id; /* 0xffff means no vlan tag */ + + __u8 svlan_p; + __u8 svlan_cfi; + __u16 svlan_id; /* 0xffff means no svlan tag */ + __u32 src_mac_count; /* How many MACs to iterate through */ __u32 dst_mac_count; /* How many MACs to iterate through */ @@ -644,6 +665,24 @@ static int pktgen_if_show(struct seq_file *seq, void *v) i == pkt_dev->nr_labels-1 ? "\n" : ", "); } + if (pkt_dev->vlan_id != 0xffff) { + seq_printf(seq, " vlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->vlan_id, pkt_dev->vlan_p, pkt_dev->vlan_cfi); + } + + if (pkt_dev->svlan_id != 0xffff) { + seq_printf(seq, " svlan_id: %u vlan_p: %u vlan_cfi: %u\n", + pkt_dev->svlan_id, pkt_dev->svlan_p, pkt_dev->svlan_cfi); + } + + if (pkt_dev->tos) { + seq_printf(seq, " tos: 0x%02x\n", pkt_dev->tos); + } + + if (pkt_dev->traffic_class) { + seq_printf(seq, " traffic_class: 0x%02x\n", pkt_dev->traffic_class); + } + seq_printf(seq, " Flags: "); if (pkt_dev->flags & F_IPV6) @@ -673,6 +712,12 @@ static int pktgen_if_show(struct seq_file *seq, void *v) if (pkt_dev->flags & F_MACDST_RND) seq_printf(seq, "MACDST_RND "); + if (pkt_dev->flags & F_VID_RND) + seq_printf(seq, "VID_RND "); + + if (pkt_dev->flags & F_SVID_RND) + seq_printf(seq, "SVID_RND "); + seq_puts(seq, "\n"); sa = pkt_dev->started_at; @@ -715,12 +760,12 @@ static int pktgen_if_show(struct seq_file *seq, void *v) } -static int hex32_arg(const char __user *user_buffer, __u32 *num) +static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, __u32 *num) { int i = 0; *num = 0; - for(; i < 8; i++) { + for(; i < maxlen; i++) { char c; *num <<= 4; if (get_user(c, &user_buffer[i])) @@ -815,7 +860,7 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev) pkt_dev->nr_labels = 0; do { __u32 tmp; - len = hex32_arg(&buffer[i], &tmp); + len = hex32_arg(&buffer[i], 8, &tmp); if (len <= 0) return len; pkt_dev->labels[n] = htonl(tmp); @@ -1140,11 +1185,27 @@ static ssize_t pktgen_if_write(struct file *file, else if (strcmp(f, "!MPLS_RND") == 0) pkt_dev->flags &= ~F_MPLS_RND; + else if (strcmp(f, "VID_RND") == 0) + pkt_dev->flags |= F_VID_RND; + + else if (strcmp(f, "!VID_RND") == 0) + pkt_dev->flags &= ~F_VID_RND; + + else if (strcmp(f, "SVID_RND") == 0) + pkt_dev->flags |= F_SVID_RND; + + else if (strcmp(f, "!SVID_RND") == 0) + pkt_dev->flags &= ~F_SVID_RND; + + else if (strcmp(f, "!IPV6") == 0) + pkt_dev->flags &= ~F_IPV6; + else { sprintf(pg_result, "Flag -:%s:- unknown\nAvailable flags, (prepend ! to un-set flag):\n%s", f, - "IPSRC_RND, IPDST_RND, TXSIZE_RND, UDPSRC_RND, UDPDST_RND, MACSRC_RND, MACDST_RND\n"); + "IPSRC_RND, IPDST_RND, UDPSRC_RND, UDPDST_RND, " + "MACSRC_RND, MACDST_RND, TXSIZE_RND, IPV6, MPLS_RND, VID_RND, SVID_RND\n"); return count; } sprintf(pg_result, "OK: flags=0x%x", pkt_dev->flags); @@ -1445,6 +1506,160 @@ static ssize_t pktgen_if_write(struct file *file, offset += sprintf(pg_result + offset, "%08x%s", ntohl(pkt_dev->labels[n]), n == pkt_dev->nr_labels-1 ? "" : ","); + + if (pkt_dev->nr_labels && pkt_dev->vlan_id != 0xffff) { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + printk("pktgen: VLAN/SVLAN auto turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) { + return len; + } + i += len; + if (value <= 4095) { + pkt_dev->vlan_id = value; /* turn on VLAN */ + + if (debug) + printk("pktgen: VLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + printk("pktgen: MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: vlan_id=%u", pkt_dev->vlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + printk("pktgen: VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "vlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_p = value; + sprintf(pg_result, "OK: vlan_p=%u", pkt_dev->vlan_p); + } else { + sprintf(pg_result, "ERROR: vlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "vlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_cfi = value; + sprintf(pg_result, "OK: vlan_cfi=%u", pkt_dev->vlan_cfi); + } else { + sprintf(pg_result, "ERROR: vlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "svlan_id")) { + len = num_arg(&user_buffer[i], 4, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) { + pkt_dev->svlan_id = value; /* turn on SVLAN */ + + if (debug) + printk("pktgen: SVLAN turned on\n"); + + if (debug && pkt_dev->nr_labels) + printk("pktgen: MPLS auto turned off\n"); + + pkt_dev->nr_labels = 0; /* turn off MPLS */ + sprintf(pg_result, "OK: svlan_id=%u", pkt_dev->svlan_id); + } else { + pkt_dev->vlan_id = 0xffff; /* turn off VLAN/SVLAN */ + pkt_dev->svlan_id = 0xffff; + + if (debug) + printk("pktgen: VLAN/SVLAN turned off\n"); + } + return count; + } + + if (!strcmp(name, "svlan_p")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_p = value; + sprintf(pg_result, "OK: svlan_p=%u", pkt_dev->svlan_p); + } else { + sprintf(pg_result, "ERROR: svlan_p must be 0-7"); + } + return count; + } + + if (!strcmp(name, "svlan_cfi")) { + len = num_arg(&user_buffer[i], 1, &value); + if (len < 0) { + return len; + } + i += len; + if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_cfi = value; + sprintf(pg_result, "OK: svlan_cfi=%u", pkt_dev->svlan_cfi); + } else { + sprintf(pg_result, "ERROR: svlan_cfi must be 0-1"); + } + return count; + } + + if (!strcmp(name, "tos")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) { + return len; + } + i += len; + if (len == 2) { + pkt_dev->tos = tmp_value; + sprintf(pg_result, "OK: tos=0x%02x", pkt_dev->tos); + } else { + sprintf(pg_result, "ERROR: tos must be 00-ff"); + } + return count; + } + + if (!strcmp(name, "traffic_class")) { + __u32 tmp_value = 0; + len = hex32_arg(&user_buffer[i], 2, &tmp_value); + if (len < 0) { + return len; + } + i += len; + if (len == 2) { + pkt_dev->traffic_class = tmp_value; + sprintf(pg_result, "OK: traffic_class=0x%02x", pkt_dev->traffic_class); + } else { + sprintf(pg_result, "ERROR: traffic_class must be 00-ff"); + } return count; } @@ -1786,7 +2001,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) * use ipv6_get_lladdr if/when it's get exported */ - read_lock(&addrconf_lock); + rcu_read_lock(); if ((idev = __in6_dev_get(pkt_dev->odev)) != NULL) { struct inet6_ifaddr *ifp; @@ -1805,7 +2020,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) } read_unlock_bh(&idev->lock); } - read_unlock(&addrconf_lock); + rcu_read_unlock(); if (err) printk("pktgen: ERROR: IPv6 link address not availble.\n"); } @@ -1949,6 +2164,14 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) htonl(0x000fffff)); } + if ((pkt_dev->flags & F_VID_RND) && (pkt_dev->vlan_id != 0xffff)) { + pkt_dev->vlan_id = pktgen_random() % 4096; + } + + if ((pkt_dev->flags & F_SVID_RND) && (pkt_dev->svlan_id != 0xffff)) { + pkt_dev->svlan_id = pktgen_random() % 4096; + } + if (pkt_dev->udp_src_min < pkt_dev->udp_src_max) { if (pkt_dev->flags & F_UDPSRC_RND) pkt_dev->cur_udp_src = @@ -2092,10 +2315,18 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct pktgen_hdr *pgh = NULL; __be16 protocol = __constant_htons(ETH_P_IP); __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ + if (pkt_dev->nr_labels) protocol = __constant_htons(ETH_P_MPLS_UC); + if (pkt_dev->vlan_id != 0xffff) + protocol = __constant_htons(ETH_P_8021Q); + /* Update any of the values, used when we're incrementing various * fields. */ @@ -2103,7 +2334,9 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, datalen = (odev->hard_header_len + 16) & ~0xf; skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + datalen + - pkt_dev->nr_labels*sizeof(u32), GFP_ATOMIC); + pkt_dev->nr_labels*sizeof(u32) + + VLAN_TAG_SIZE(pkt_dev) + SVLAN_TAG_SIZE(pkt_dev), + GFP_ATOMIC); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -2116,6 +2349,24 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); + + if (pkt_dev->vlan_id != 0xffff) { + if(pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = htons(pkt_dev->svlan_id); + *svlan_tci |= pkt_dev->svlan_p << 5; + *svlan_tci |= pkt_dev->svlan_cfi << 4; + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = __constant_htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = htons(pkt_dev->vlan_id); + *vlan_tci |= pkt_dev->vlan_p << 5; + *vlan_tci |= pkt_dev->vlan_cfi << 4; + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = __constant_htons(ETH_P_IP); + } + iph = (struct iphdr *)skb_put(skb, sizeof(struct iphdr)); udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); @@ -2124,7 +2375,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - 20 - 8 - - pkt_dev->nr_labels*sizeof(u32); + pkt_dev->nr_labels*sizeof(u32) - VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); if (datalen < sizeof(struct pktgen_hdr)) datalen = sizeof(struct pktgen_hdr); @@ -2136,7 +2387,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->ihl = 5; iph->version = 4; iph->ttl = 32; - iph->tos = 0; + iph->tos = pkt_dev->tos; iph->protocol = IPPROTO_UDP; /* UDP */ iph->saddr = pkt_dev->cur_saddr; iph->daddr = pkt_dev->cur_daddr; @@ -2146,9 +2397,12 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, iph->check = 0; iph->check = ip_fast_csum((void *)iph, iph->ihl); skb->protocol = protocol; - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32); + skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32) - + VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); skb->dev = odev; skb->pkt_type = PACKET_HOST; + skb->nh.iph = iph; + skb->h.uh = udph; if (pkt_dev->nfrags <= 0) pgh = (struct pktgen_hdr *)skb_put(skb, datalen); @@ -2216,7 +2470,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, pgh->tv_sec = htonl(timestamp.tv_sec); pgh->tv_usec = htonl(timestamp.tv_usec); } - pkt_dev->seq_num++; return skb; } @@ -2400,17 +2653,26 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct pktgen_hdr *pgh = NULL; __be16 protocol = __constant_htons(ETH_P_IPV6); __be32 *mpls; + __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ + __be16 *vlan_encapsulated_proto = NULL; /* packet type ID field (or len) for VLAN tag */ + __be16 *svlan_tci = NULL; /* Encapsulates priority and SVLAN ID */ + __be16 *svlan_encapsulated_proto = NULL; /* packet type ID field (or len) for SVLAN tag */ if (pkt_dev->nr_labels) protocol = __constant_htons(ETH_P_MPLS_UC); + if (pkt_dev->vlan_id != 0xffff) + protocol = __constant_htons(ETH_P_8021Q); + /* Update any of the values, used when we're incrementing various * fields. */ mod_cur_headers(pkt_dev); skb = alloc_skb(pkt_dev->cur_pkt_size + 64 + 16 + - pkt_dev->nr_labels*sizeof(u32), GFP_ATOMIC); + pkt_dev->nr_labels*sizeof(u32) + + VLAN_TAG_SIZE(pkt_dev) + SVLAN_TAG_SIZE(pkt_dev), + GFP_ATOMIC); if (!skb) { sprintf(pkt_dev->result, "No memory"); return NULL; @@ -2423,16 +2685,34 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, mpls = (__be32 *)skb_put(skb, pkt_dev->nr_labels*sizeof(__u32)); if (pkt_dev->nr_labels) mpls_push(mpls, pkt_dev); + + if (pkt_dev->vlan_id != 0xffff) { + if(pkt_dev->svlan_id != 0xffff) { + svlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_tci = htons(pkt_dev->svlan_id); + *svlan_tci |= pkt_dev->svlan_p << 5; + *svlan_tci |= pkt_dev->svlan_cfi << 4; + svlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *svlan_encapsulated_proto = __constant_htons(ETH_P_8021Q); + } + vlan_tci = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_tci = htons(pkt_dev->vlan_id); + *vlan_tci |= pkt_dev->vlan_p << 5; + *vlan_tci |= pkt_dev->vlan_cfi << 4; + vlan_encapsulated_proto = (__be16 *)skb_put(skb, sizeof(__be16)); + *vlan_encapsulated_proto = __constant_htons(ETH_P_IPV6); + } + iph = (struct ipv6hdr *)skb_put(skb, sizeof(struct ipv6hdr)); udph = (struct udphdr *)skb_put(skb, sizeof(struct udphdr)); memcpy(eth, pkt_dev->hh, 12); - *(u16 *) & eth[12] = __constant_htons(ETH_P_IPV6); + *(u16 *) & eth[12] = protocol; /* Eth + IPh + UDPh + mpls */ datalen = pkt_dev->cur_pkt_size - 14 - sizeof(struct ipv6hdr) - sizeof(struct udphdr) - - pkt_dev->nr_labels*sizeof(u32); + pkt_dev->nr_labels*sizeof(u32) - VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); if (datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); @@ -2448,6 +2728,11 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, *(u32 *) iph = __constant_htonl(0x60000000); /* Version + flow */ + if (pkt_dev->traffic_class) { + /* Version + traffic class + flow (0) */ + *(u32 *)iph |= htonl(0x60000000 | (pkt_dev->traffic_class << 20)); + } + iph->hop_limit = 32; iph->payload_len = htons(sizeof(struct udphdr) + datalen); @@ -2456,10 +2741,13 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, ipv6_addr_copy(&iph->daddr, &pkt_dev->cur_in6_daddr); ipv6_addr_copy(&iph->saddr, &pkt_dev->cur_in6_saddr); - skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32); + skb->mac.raw = ((u8 *) iph) - 14 - pkt_dev->nr_labels*sizeof(u32) - + VLAN_TAG_SIZE(pkt_dev) - SVLAN_TAG_SIZE(pkt_dev); skb->protocol = protocol; skb->dev = odev; skb->pkt_type = PACKET_HOST; + skb->nh.ipv6h = iph; + skb->h.uh = udph; if (pkt_dev->nfrags <= 0) pgh = (struct pktgen_hdr *)skb_put(skb, datalen); @@ -2527,7 +2815,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, pgh->tv_sec = htonl(timestamp.tv_sec); pgh->tv_usec = htonl(timestamp.tv_usec); } - pkt_dev->seq_num++; + /* pkt_dev->seq_num++; FF: you really mean this? */ return skb; } @@ -3173,6 +3461,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->udp_dst_min = 9; pkt_dev->udp_dst_max = 9; + pkt_dev->vlan_p = 0; + pkt_dev->vlan_cfi = 0; + pkt_dev->vlan_id = 0xffff; + pkt_dev->svlan_p = 0; + pkt_dev->svlan_cfi = 0; + pkt_dev->svlan_id = 0xffff; + strncpy(pkt_dev->ifname, ifname, IFNAMSIZ); if (!pktgen_setup_dev(pkt_dev)) { diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3fcfa9c59e1f..221e4038216b 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -16,7 +16,6 @@ * Vitaly E. Lavrov RTA_OK arithmetics was wrong. */ -#include <linux/config.h> #include <linux/errno.h> #include <linux/module.h> #include <linux/types.h> @@ -36,6 +35,7 @@ #include <linux/init.h> #include <linux/security.h> #include <linux/mutex.h> +#include <linux/if_addr.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -50,6 +50,7 @@ #include <net/udp.h> #include <net/sock.h> #include <net/pkt_sched.h> +#include <net/fib_rules.h> #include <net/netlink.h> #ifdef CONFIG_NET_WIRELESS_RTNETLINK #include <linux/wireless.h> @@ -57,6 +58,7 @@ #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ static DEFINE_MUTEX(rtnl_mutex); +static struct sock *rtnl; void rtnl_lock(void) { @@ -94,8 +96,6 @@ int rtattr_parse(struct rtattr *tb[], int maxattr, struct rtattr *rta, int len) return 0; } -struct sock *rtnl; - struct rtnetlink_link * rtnetlink_links[NPROTO]; static const int rtm_min[RTM_NR_FAMILIES] = @@ -103,8 +103,7 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWLINK)] = NLMSG_LENGTH(sizeof(struct ifinfomsg)), [RTM_FAM(RTM_NEWADDR)] = NLMSG_LENGTH(sizeof(struct ifaddrmsg)), [RTM_FAM(RTM_NEWROUTE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), - [RTM_FAM(RTM_NEWNEIGH)] = NLMSG_LENGTH(sizeof(struct ndmsg)), - [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct rtmsg)), + [RTM_FAM(RTM_NEWRULE)] = NLMSG_LENGTH(sizeof(struct fib_rule_hdr)), [RTM_FAM(RTM_NEWQDISC)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTCLASS)] = NLMSG_LENGTH(sizeof(struct tcmsg)), [RTM_FAM(RTM_NEWTFILTER)] = NLMSG_LENGTH(sizeof(struct tcmsg)), @@ -112,7 +111,6 @@ static const int rtm_min[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWPREFIX)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETMULTICAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), [RTM_FAM(RTM_GETANYCAST)] = NLMSG_LENGTH(sizeof(struct rtgenmsg)), - [RTM_FAM(RTM_NEWNEIGHTBL)] = NLMSG_LENGTH(sizeof(struct ndtmsg)), }; static const int rta_max[RTM_NR_FAMILIES] = @@ -120,13 +118,11 @@ static const int rta_max[RTM_NR_FAMILIES] = [RTM_FAM(RTM_NEWLINK)] = IFLA_MAX, [RTM_FAM(RTM_NEWADDR)] = IFA_MAX, [RTM_FAM(RTM_NEWROUTE)] = RTA_MAX, - [RTM_FAM(RTM_NEWNEIGH)] = NDA_MAX, - [RTM_FAM(RTM_NEWRULE)] = RTA_MAX, + [RTM_FAM(RTM_NEWRULE)] = FRA_MAX, [RTM_FAM(RTM_NEWQDISC)] = TCA_MAX, [RTM_FAM(RTM_NEWTCLASS)] = TCA_MAX, [RTM_FAM(RTM_NEWTFILTER)] = TCA_MAX, [RTM_FAM(RTM_NEWACTION)] = TCAA_MAX, - [RTM_FAM(RTM_NEWNEIGHTBL)] = NDTA_MAX, }; void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data) @@ -169,24 +165,52 @@ int rtnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo) return err; } +int rtnl_unicast(struct sk_buff *skb, u32 pid) +{ + return nlmsg_unicast(rtnl, skb, pid); +} + +int rtnl_notify(struct sk_buff *skb, u32 pid, u32 group, + struct nlmsghdr *nlh, gfp_t flags) +{ + int report = 0; + + if (nlh) + report = nlmsg_report(nlh); + + return nlmsg_notify(rtnl, skb, pid, group, report, flags); +} + +void rtnl_set_sk_err(u32 group, int error) +{ + netlink_set_err(rtnl, 0, group, error); +} + int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { - struct rtattr *mx = (struct rtattr*)skb->tail; - int i; + struct nlattr *mx; + int i, valid = 0; + + mx = nla_nest_start(skb, RTA_METRICS); + if (mx == NULL) + return -ENOBUFS; + + for (i = 0; i < RTAX_MAX; i++) { + if (metrics[i]) { + valid++; + NLA_PUT_U32(skb, i+1, metrics[i]); + } + } - RTA_PUT(skb, RTA_METRICS, 0, NULL); - for (i=0; i<RTAX_MAX; i++) { - if (metrics[i]) - RTA_PUT(skb, i+1, sizeof(u32), metrics+i); + if (!valid) { + nla_nest_cancel(skb, mx); + return 0; } - mx->rta_len = skb->tail - (u8*)mx; - if (mx->rta_len == RTA_LENGTH(0)) - skb_trim(skb, (u8*)mx - skb->data); - return 0; -rtattr_failure: - skb_trim(skb, (u8*)mx - skb->data); - return -1; + return nla_nest_end(skb, mx); + +nla_put_failure: + return nla_nest_cancel(skb, mx); } @@ -217,41 +241,73 @@ static void set_operstate(struct net_device *dev, unsigned char transition) } } -static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, - int type, u32 pid, u32 seq, u32 change, - unsigned int flags) +static void copy_rtnl_link_stats(struct rtnl_link_stats *a, + struct net_device_stats *b) { - struct ifinfomsg *r; - struct nlmsghdr *nlh; - unsigned char *b = skb->tail; - - nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*r), flags); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev_get_flags(dev); - r->ifi_change = change; - - RTA_PUT(skb, IFLA_IFNAME, strlen(dev->name)+1, dev->name); - - if (1) { - u32 txqlen = dev->tx_queue_len; - RTA_PUT(skb, IFLA_TXQLEN, sizeof(txqlen), &txqlen); - } + a->rx_packets = b->rx_packets; + a->tx_packets = b->tx_packets; + a->rx_bytes = b->rx_bytes; + a->tx_bytes = b->tx_bytes; + a->rx_errors = b->rx_errors; + a->tx_errors = b->tx_errors; + a->rx_dropped = b->rx_dropped; + a->tx_dropped = b->tx_dropped; + + a->multicast = b->multicast; + a->collisions = b->collisions; + + a->rx_length_errors = b->rx_length_errors; + a->rx_over_errors = b->rx_over_errors; + a->rx_crc_errors = b->rx_crc_errors; + a->rx_frame_errors = b->rx_frame_errors; + a->rx_fifo_errors = b->rx_fifo_errors; + a->rx_missed_errors = b->rx_missed_errors; + + a->tx_aborted_errors = b->tx_aborted_errors; + a->tx_carrier_errors = b->tx_carrier_errors; + a->tx_fifo_errors = b->tx_fifo_errors; + a->tx_heartbeat_errors = b->tx_heartbeat_errors; + a->tx_window_errors = b->tx_window_errors; + + a->rx_compressed = b->rx_compressed; + a->tx_compressed = b->tx_compressed; +}; - if (1) { - u32 weight = dev->weight; - RTA_PUT(skb, IFLA_WEIGHT, sizeof(weight), &weight); - } +static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, + void *iwbuf, int iwbuflen, int type, u32 pid, + u32 seq, u32 change, unsigned int flags) +{ + struct ifinfomsg *ifm; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); + if (nlh == NULL) + return -ENOBUFS; + + ifm = nlmsg_data(nlh); + ifm->ifi_family = AF_UNSPEC; + ifm->__ifi_pad = 0; + ifm->ifi_type = dev->type; + ifm->ifi_index = dev->ifindex; + ifm->ifi_flags = dev_get_flags(dev); + ifm->ifi_change = change; + + NLA_PUT_STRING(skb, IFLA_IFNAME, dev->name); + NLA_PUT_U32(skb, IFLA_TXQLEN, dev->tx_queue_len); + NLA_PUT_U32(skb, IFLA_WEIGHT, dev->weight); + NLA_PUT_U8(skb, IFLA_OPERSTATE, + netif_running(dev) ? dev->operstate : IF_OPER_DOWN); + NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); + NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); + + if (dev->ifindex != dev->iflink) + NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); + + if (dev->master) + NLA_PUT_U32(skb, IFLA_MASTER, dev->master->ifindex); - if (1) { - u8 operstate = netif_running(dev)?dev->operstate:IF_OPER_DOWN; - u8 link_mode = dev->link_mode; - RTA_PUT(skb, IFLA_OPERSTATE, sizeof(operstate), &operstate); - RTA_PUT(skb, IFLA_LINKMODE, sizeof(link_mode), &link_mode); - } + if (dev->qdisc_sleeping) + NLA_PUT_STRING(skb, IFLA_QDISC, dev->qdisc_sleeping->ops->id); if (1) { struct rtnl_link_ifmap map = { @@ -262,58 +318,38 @@ static int rtnetlink_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, .dma = dev->dma, .port = dev->if_port, }; - RTA_PUT(skb, IFLA_MAP, sizeof(map), &map); + NLA_PUT(skb, IFLA_MAP, sizeof(map), &map); } if (dev->addr_len) { - RTA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); - RTA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); - } - - if (1) { - u32 mtu = dev->mtu; - RTA_PUT(skb, IFLA_MTU, sizeof(mtu), &mtu); - } - - if (dev->ifindex != dev->iflink) { - u32 iflink = dev->iflink; - RTA_PUT(skb, IFLA_LINK, sizeof(iflink), &iflink); - } - - if (dev->qdisc_sleeping) - RTA_PUT(skb, IFLA_QDISC, - strlen(dev->qdisc_sleeping->ops->id) + 1, - dev->qdisc_sleeping->ops->id); - - if (dev->master) { - u32 master = dev->master->ifindex; - RTA_PUT(skb, IFLA_MASTER, sizeof(master), &master); + NLA_PUT(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr); + NLA_PUT(skb, IFLA_BROADCAST, dev->addr_len, dev->broadcast); } if (dev->get_stats) { - unsigned long *stats = (unsigned long*)dev->get_stats(dev); + struct net_device_stats *stats = dev->get_stats(dev); if (stats) { - struct rtattr *a; - __u32 *s; - int i; - int n = sizeof(struct rtnl_link_stats)/4; - - a = __RTA_PUT(skb, IFLA_STATS, n*4); - s = RTA_DATA(a); - for (i=0; i<n; i++) - s[i] = stats[i]; + struct nlattr *attr; + + attr = nla_reserve(skb, IFLA_STATS, + sizeof(struct rtnl_link_stats)); + if (attr == NULL) + goto nla_put_failure; + + copy_rtnl_link_stats(nla_data(attr), stats); } } - nlh->nlmsg_len = skb->tail - b; - return skb->len; -nlmsg_failure: -rtattr_failure: - skb_trim(skb, b - skb->data); - return -1; + if (iwbuf) + NLA_PUT(skb, IFLA_WIRELESS, iwbuflen, iwbuf); + + return nlmsg_end(skb, nlh); + +nla_put_failure: + return nlmsg_cancel(skb, nlh); } -static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) +static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->args[0]; @@ -323,10 +359,9 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c for (dev=dev_base, idx=0; dev; dev = dev->next, idx++) { if (idx < s_idx) continue; - if (rtnetlink_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, - NLM_F_MULTI) <= 0) + if (rtnl_fill_ifinfo(skb, dev, NULL, 0, RTM_NEWLINK, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) break; } read_unlock(&dev_base_lock); @@ -335,52 +370,70 @@ static int rtnetlink_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *c return skb->len; } -static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) +static struct nla_policy ifla_policy[IFLA_MAX+1] __read_mostly = { + [IFLA_IFNAME] = { .type = NLA_STRING, .len = IFNAMSIZ-1 }, + [IFLA_MAP] = { .len = sizeof(struct rtnl_link_ifmap) }, + [IFLA_MTU] = { .type = NLA_U32 }, + [IFLA_TXQLEN] = { .type = NLA_U32 }, + [IFLA_WEIGHT] = { .type = NLA_U32 }, + [IFLA_OPERSTATE] = { .type = NLA_U8 }, + [IFLA_LINKMODE] = { .type = NLA_U8 }, +}; + +static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { - struct ifinfomsg *ifm = NLMSG_DATA(nlh); - struct rtattr **ida = arg; + struct ifinfomsg *ifm; struct net_device *dev; - int err, send_addr_notify = 0; + int err, send_addr_notify = 0, modified = 0; + struct nlattr *tb[IFLA_MAX+1]; + char ifname[IFNAMSIZ]; + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + goto errout; + + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + else + ifname[0] = '\0'; + + err = -EINVAL; + ifm = nlmsg_data(nlh); if (ifm->ifi_index >= 0) dev = dev_get_by_index(ifm->ifi_index); - else if (ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; - - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - return -EINVAL; + else if (tb[IFLA_IFNAME]) dev = dev_get_by_name(ifname); - } else - return -EINVAL; + else + goto errout; - if (!dev) - return -ENODEV; + if (dev == NULL) { + err = -ENODEV; + goto errout; + } - err = -EINVAL; + if (tb[IFLA_ADDRESS] && + nla_len(tb[IFLA_ADDRESS]) < dev->addr_len) + goto errout_dev; - if (ifm->ifi_flags) - dev_change_flags(dev, ifm->ifi_flags); + if (tb[IFLA_BROADCAST] && + nla_len(tb[IFLA_BROADCAST]) < dev->addr_len) + goto errout_dev; - if (ida[IFLA_MAP - 1]) { + if (tb[IFLA_MAP]) { struct rtnl_link_ifmap *u_map; struct ifmap k_map; if (!dev->set_config) { err = -EOPNOTSUPP; - goto out; + goto errout_dev; } if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout_dev; } - - if (ida[IFLA_MAP - 1]->rta_len != RTA_LENGTH(sizeof(*u_map))) - goto out; - - u_map = RTA_DATA(ida[IFLA_MAP - 1]); + u_map = nla_data(tb[IFLA_MAP]); k_map.mem_start = (unsigned long) u_map->mem_start; k_map.mem_end = (unsigned long) u_map->mem_end; k_map.base_addr = (unsigned short) u_map->base_addr; @@ -389,187 +442,175 @@ static int do_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) k_map.port = (unsigned char) u_map->port; err = dev->set_config(dev, &k_map); + if (err < 0) + goto errout_dev; - if (err) - goto out; + modified = 1; } - if (ida[IFLA_ADDRESS - 1]) { + if (tb[IFLA_ADDRESS]) { + struct sockaddr *sa; + int len; + if (!dev->set_mac_address) { err = -EOPNOTSUPP; - goto out; + goto errout_dev; } + if (!netif_device_present(dev)) { err = -ENODEV; - goto out; + goto errout_dev; } - if (ida[IFLA_ADDRESS - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; - err = dev->set_mac_address(dev, RTA_DATA(ida[IFLA_ADDRESS - 1])); + len = sizeof(sa_family_t) + dev->addr_len; + sa = kmalloc(len, GFP_KERNEL); + if (!sa) { + err = -ENOMEM; + goto errout_dev; + } + sa->sa_family = dev->type; + memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]), + dev->addr_len); + err = dev->set_mac_address(dev, sa); + kfree(sa); if (err) - goto out; + goto errout_dev; send_addr_notify = 1; + modified = 1; } - if (ida[IFLA_BROADCAST - 1]) { - if (ida[IFLA_BROADCAST - 1]->rta_len != RTA_LENGTH(dev->addr_len)) - goto out; - memcpy(dev->broadcast, RTA_DATA(ida[IFLA_BROADCAST - 1]), - dev->addr_len); - send_addr_notify = 1; + if (tb[IFLA_MTU]) { + err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + if (err < 0) + goto errout_dev; + modified = 1; } - if (ida[IFLA_MTU - 1]) { - if (ida[IFLA_MTU - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - err = dev_set_mtu(dev, *((u32 *) RTA_DATA(ida[IFLA_MTU - 1]))); - - if (err) - goto out; - + /* + * Interface selected by interface index but interface + * name provided implies that a name change has been + * requested. + */ + if (ifm->ifi_index >= 0 && ifname[0]) { + err = dev_change_name(dev, ifname); + if (err < 0) + goto errout_dev; + modified = 1; } - if (ida[IFLA_TXQLEN - 1]) { - if (ida[IFLA_TXQLEN - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; +#ifdef CONFIG_NET_WIRELESS_RTNETLINK + if (tb[IFLA_WIRELESS]) { + /* Call Wireless Extensions. + * Various stuff checked in there... */ + err = wireless_rtnetlink_set(dev, nla_data(tb[IFLA_WIRELESS]), + nla_len(tb[IFLA_WIRELESS])); + if (err < 0) + goto errout_dev; + } +#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - dev->tx_queue_len = *((u32 *) RTA_DATA(ida[IFLA_TXQLEN - 1])); + if (tb[IFLA_BROADCAST]) { + nla_memcpy(dev->broadcast, tb[IFLA_BROADCAST], dev->addr_len); + send_addr_notify = 1; } - if (ida[IFLA_WEIGHT - 1]) { - if (ida[IFLA_WEIGHT - 1]->rta_len != RTA_LENGTH(sizeof(u32))) - goto out; - dev->weight = *((u32 *) RTA_DATA(ida[IFLA_WEIGHT - 1])); - } + if (ifm->ifi_flags) + dev_change_flags(dev, ifm->ifi_flags); - if (ida[IFLA_OPERSTATE - 1]) { - if (ida[IFLA_OPERSTATE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) - goto out; + if (tb[IFLA_TXQLEN]) + dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]); - set_operstate(dev, *((u8 *) RTA_DATA(ida[IFLA_OPERSTATE - 1]))); - } + if (tb[IFLA_WEIGHT]) + dev->weight = nla_get_u32(tb[IFLA_WEIGHT]); - if (ida[IFLA_LINKMODE - 1]) { - if (ida[IFLA_LINKMODE - 1]->rta_len != RTA_LENGTH(sizeof(u8))) - goto out; + if (tb[IFLA_OPERSTATE]) + set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); + if (tb[IFLA_LINKMODE]) { write_lock_bh(&dev_base_lock); - dev->link_mode = *((u8 *) RTA_DATA(ida[IFLA_LINKMODE - 1])); + dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); write_unlock_bh(&dev_base_lock); } - if (ifm->ifi_index >= 0 && ida[IFLA_IFNAME - 1]) { - char ifname[IFNAMSIZ]; - - if (rtattr_strlcpy(ifname, ida[IFLA_IFNAME - 1], - IFNAMSIZ) >= IFNAMSIZ) - goto out; - err = dev_change_name(dev, ifname); - if (err) - goto out; - } - -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (ida[IFLA_WIRELESS - 1]) { - - /* Call Wireless Extensions. - * Various stuff checked in there... */ - err = wireless_rtnetlink_set(dev, RTA_DATA(ida[IFLA_WIRELESS - 1]), ida[IFLA_WIRELESS - 1]->rta_len); - if (err) - goto out; - } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - err = 0; -out: +errout_dev: + if (err < 0 && modified && net_ratelimit()) + printk(KERN_WARNING "A link change request failed with " + "some changes comitted already. Interface %s may " + "have been left with an inconsistent configuration, " + "please check.\n", dev->name); + if (send_addr_notify) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); dev_put(dev); +errout: return err; } -#ifdef CONFIG_NET_WIRELESS_RTNETLINK -static int do_getlink(struct sk_buff *in_skb, struct nlmsghdr* in_nlh, void *arg) +static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct ifinfomsg *ifm = NLMSG_DATA(in_nlh); - struct rtattr **ida = arg; - struct net_device *dev; - struct ifinfomsg *r; - struct nlmsghdr *nlh; - int err = -ENOBUFS; - struct sk_buff *skb; - unsigned char *b; - char *iw_buf = NULL; + struct ifinfomsg *ifm; + struct nlattr *tb[IFLA_MAX+1]; + struct net_device *dev = NULL; + struct sk_buff *nskb; + char *iw_buf = NULL, *iw = NULL; int iw_buf_len = 0; + int err, payload; - if (ifm->ifi_index >= 0) + err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy); + if (err < 0) + return err; + + ifm = nlmsg_data(nlh); + if (ifm->ifi_index >= 0) { dev = dev_get_by_index(ifm->ifi_index); - else + if (dev == NULL) + return -ENODEV; + } else return -EINVAL; - if (!dev) - return -ENODEV; -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - if (ida[IFLA_WIRELESS - 1]) { +#ifdef CONFIG_NET_WIRELESS_RTNETLINK + if (tb[IFLA_WIRELESS]) { /* Call Wireless Extensions. We need to know the size before * we can alloc. Various stuff checked in there... */ - err = wireless_rtnetlink_get(dev, RTA_DATA(ida[IFLA_WIRELESS - 1]), ida[IFLA_WIRELESS - 1]->rta_len, &iw_buf, &iw_buf_len); - if (err) - goto out; + err = wireless_rtnetlink_get(dev, nla_data(tb[IFLA_WIRELESS]), + nla_len(tb[IFLA_WIRELESS]), + &iw_buf, &iw_buf_len); + if (err < 0) + goto errout; + + iw += IW_EV_POINT_OFF; } #endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - /* Create a skb big enough to include all the data. - * Some requests are way bigger than 4k... Jean II */ - skb = alloc_skb((NLMSG_LENGTH(sizeof(*r))) + (RTA_SPACE(iw_buf_len)), - GFP_KERNEL); - if (!skb) - goto out; - b = skb->tail; - - /* Put in the message the usual good stuff */ - nlh = NLMSG_PUT(skb, NETLINK_CB(in_skb).pid, in_nlh->nlmsg_seq, - RTM_NEWLINK, sizeof(*r)); - r = NLMSG_DATA(nlh); - r->ifi_family = AF_UNSPEC; - r->__ifi_pad = 0; - r->ifi_type = dev->type; - r->ifi_index = dev->ifindex; - r->ifi_flags = dev->flags; - r->ifi_change = 0; - - /* Put the wireless payload if it exist */ - if(iw_buf != NULL) - RTA_PUT(skb, IFLA_WIRELESS, iw_buf_len, - iw_buf + IW_EV_POINT_OFF); - - nlh->nlmsg_len = skb->tail - b; - - /* Needed ? */ - NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid; - - err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); - if (err > 0) - err = 0; -out: - if(iw_buf != NULL) - kfree(iw_buf); + payload = NLMSG_ALIGN(sizeof(struct ifinfomsg) + + nla_total_size(iw_buf_len)); + nskb = nlmsg_new(nlmsg_total_size(payload), GFP_KERNEL); + if (nskb == NULL) { + err = -ENOBUFS; + goto errout; + } + + err = rtnl_fill_ifinfo(nskb, dev, iw, iw_buf_len, RTM_NEWLINK, + NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, 0); + if (err <= 0) { + kfree_skb(nskb); + goto errout; + } + + err = rtnl_unicast(skb, NETLINK_CB(skb).pid); +errout: + kfree(iw_buf); dev_put(dev); - return err; -rtattr_failure: -nlmsg_failure: - kfree_skb(skb); - goto out; + return err; } -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ -static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) +static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) { int idx; int s_idx = cb->family; @@ -596,20 +637,22 @@ static int rtnetlink_dump_all(struct sk_buff *skb, struct netlink_callback *cb) void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change) { struct sk_buff *skb; - int size = NLMSG_SPACE(sizeof(struct ifinfomsg) + - sizeof(struct rtnl_link_ifmap) + - sizeof(struct rtnl_link_stats) + 128); + int err = -ENOBUFS; - skb = alloc_skb(size, GFP_KERNEL); - if (!skb) - return; + skb = nlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + if (skb == NULL) + goto errout; - if (rtnetlink_fill_ifinfo(skb, dev, type, 0, 0, change, 0) < 0) { + err = rtnl_fill_ifinfo(skb, dev, NULL, 0, type, 0, 0, change, 0); + if (err < 0) { kfree_skb(skb); - return; + goto errout; } - NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_KERNEL); + + err = rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_KERNEL); +errout: + if (err < 0) + rtnl_set_sk_err(RTNLGRP_LINK, err); } /* Protected by RTNL sempahore. */ @@ -663,7 +706,7 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp) sz_idx = type>>2; kind = type&3; - if (kind != 2 && security_netlink_recv(skb)) { + if (kind != 2 && security_netlink_recv(skb, CAP_NET_ADMIN)) { *errp = -EPERM; return -1; } @@ -734,18 +777,19 @@ static void rtnetlink_rcv(struct sock *sk, int len) static struct rtnetlink_link link_rtnetlink_table[RTM_NR_MSGTYPES] = { - [RTM_GETLINK - RTM_BASE] = { -#ifdef CONFIG_NET_WIRELESS_RTNETLINK - .doit = do_getlink, -#endif /* CONFIG_NET_WIRELESS_RTNETLINK */ - .dumpit = rtnetlink_dump_ifinfo }, - [RTM_SETLINK - RTM_BASE] = { .doit = do_setlink }, - [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, - [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, + [RTM_GETLINK - RTM_BASE] = { .doit = rtnl_getlink, + .dumpit = rtnl_dump_ifinfo }, + [RTM_SETLINK - RTM_BASE] = { .doit = rtnl_setlink }, + [RTM_GETADDR - RTM_BASE] = { .dumpit = rtnl_dump_all }, + [RTM_GETROUTE - RTM_BASE] = { .dumpit = rtnl_dump_all }, [RTM_NEWNEIGH - RTM_BASE] = { .doit = neigh_add }, [RTM_DELNEIGH - RTM_BASE] = { .doit = neigh_delete }, [RTM_GETNEIGH - RTM_BASE] = { .dumpit = neigh_dump_info }, - [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnetlink_dump_all }, +#ifdef CONFIG_FIB_RULES + [RTM_NEWRULE - RTM_BASE] = { .doit = fib_nl_newrule }, + [RTM_DELRULE - RTM_BASE] = { .doit = fib_nl_delrule }, +#endif + [RTM_GETRULE - RTM_BASE] = { .dumpit = rtnl_dump_all }, [RTM_GETNEIGHTBL - RTM_BASE] = { .dumpit = neightbl_dump_info }, [RTM_SETNEIGHTBL - RTM_BASE] = { .doit = neightbl_set }, }; @@ -805,7 +849,9 @@ EXPORT_SYMBOL(rtattr_strlcpy); EXPORT_SYMBOL(rtattr_parse); EXPORT_SYMBOL(rtnetlink_links); EXPORT_SYMBOL(rtnetlink_put_metrics); -EXPORT_SYMBOL(rtnl); EXPORT_SYMBOL(rtnl_lock); EXPORT_SYMBOL(rtnl_trylock); EXPORT_SYMBOL(rtnl_unlock); +EXPORT_SYMBOL(rtnl_unicast); +EXPORT_SYMBOL(rtnl_notify); +EXPORT_SYMBOL(rtnl_set_sk_err); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8e5044ba3ab6..c448c7f6fde2 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -38,7 +38,6 @@ * The functions in this file will not compile correctly with gcc 2.4.x */ -#include <linux/config.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> @@ -250,12 +249,37 @@ nodata: goto out; } +/** + * __netdev_alloc_skb - allocate an skbuff for rx on a specific device + * @dev: network device to receive on + * @length: length to allocate + * @gfp_mask: get_free_pages mask, passed to alloc_skb + * + * Allocate a new &sk_buff and assign it a usage count of one. The + * buffer has unspecified headroom built in. Users should allocate + * the headroom they think they need without accounting for the + * built in space. The built in space is used for optimisations. + * + * %NULL is returned if there is no free memory. + */ +struct sk_buff *__netdev_alloc_skb(struct net_device *dev, + unsigned int length, gfp_t gfp_mask) +{ + struct sk_buff *skb; -static void skb_drop_fraglist(struct sk_buff *skb) + skb = alloc_skb(length + NET_SKB_PAD, gfp_mask); + if (likely(skb)) { + skb_reserve(skb, NET_SKB_PAD); + skb->dev = dev; + } + return skb; +} + +static void skb_drop_list(struct sk_buff **listp) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + struct sk_buff *list = *listp; - skb_shinfo(skb)->frag_list = NULL; + *listp = NULL; do { struct sk_buff *this = list; @@ -264,6 +288,11 @@ static void skb_drop_fraglist(struct sk_buff *skb) } while (list); } +static inline void skb_drop_fraglist(struct sk_buff *skb) +{ + skb_drop_list(&skb_shinfo(skb)->frag_list); +} + static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; @@ -272,7 +301,7 @@ static void skb_clone_fraglist(struct sk_buff *skb) skb_get(list); } -void skb_release_data(struct sk_buff *skb) +static void skb_release_data(struct sk_buff *skb) { if (!skb->cloned || !atomic_sub_return(skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1, @@ -824,41 +853,81 @@ free_skb: int ___pskb_trim(struct sk_buff *skb, unsigned int len) { + struct sk_buff **fragp; + struct sk_buff *frag; int offset = skb_headlen(skb); int nfrags = skb_shinfo(skb)->nr_frags; int i; + int err; - for (i = 0; i < nfrags; i++) { + if (skb_cloned(skb) && + unlikely((err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))) + return err; + + i = 0; + if (offset >= len) + goto drop_pages; + + for (; i < nfrags; i++) { int end = offset + skb_shinfo(skb)->frags[i].size; - if (end > len) { - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) - return -ENOMEM; - } - if (len <= offset) { - put_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->nr_frags--; - } else { - skb_shinfo(skb)->frags[i].size = len - offset; - } + + if (end < len) { + offset = end; + continue; } - offset = end; + + skb_shinfo(skb)->frags[i++].size = len - offset; + +drop_pages: + skb_shinfo(skb)->nr_frags = i; + + for (; i < nfrags; i++) + put_page(skb_shinfo(skb)->frags[i].page); + + if (skb_shinfo(skb)->frag_list) + skb_drop_fraglist(skb); + goto done; + } + + for (fragp = &skb_shinfo(skb)->frag_list; (frag = *fragp); + fragp = &frag->next) { + int end = offset + frag->len; + + if (skb_shared(frag)) { + struct sk_buff *nfrag; + + nfrag = skb_clone(frag, GFP_ATOMIC); + if (unlikely(!nfrag)) + return -ENOMEM; + + nfrag->next = frag->next; + kfree_skb(frag); + frag = nfrag; + *fragp = frag; + } + + if (end < len) { + offset = end; + continue; + } + + if (end > len && + unlikely((err = pskb_trim(frag, len - offset)))) + return err; + + if (frag->next) + skb_drop_list(&frag->next); + break; } - if (offset < len) { +done: + if (len > skb_headlen(skb)) { skb->data_len -= skb->len - len; skb->len = len; } else { - if (len <= skb_headlen(skb)) { - skb->len = len; - skb->data_len = 0; - skb->tail = skb->data + len; - if (skb_shinfo(skb)->frag_list && !skb_cloned(skb)) - skb_drop_fraglist(skb); - } else { - skb->data_len -= skb->len - len; - skb->len = len; - } + skb->len = len; + skb->data_len = 0; + skb->tail = skb->data + len; } return 0; @@ -1328,7 +1397,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) unsigned int csum; long csstart; - if (skb->ip_summed == CHECKSUM_HW) + if (skb->ip_summed == CHECKSUM_PARTIAL) csstart = skb->h.raw - skb->data; else csstart = skb_headlen(skb); @@ -1342,7 +1411,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) csum = skb_copy_and_csum_bits(skb, csstart, to + csstart, skb->len - csstart, 0); - if (skb->ip_summed == CHECKSUM_HW) { + if (skb->ip_summed == CHECKSUM_PARTIAL) { long csstuff = csstart + skb->csum; *((unsigned short *)(to + csstuff)) = csum_fold(csum); @@ -1739,12 +1808,15 @@ unsigned int skb_find_text(struct sk_buff *skb, unsigned int from, unsigned int to, struct ts_config *config, struct ts_state *state) { + unsigned int ret; + config->get_next_block = skb_ts_get_next_block; config->finish = skb_ts_finish; skb_prepare_seq_read(skb, from, to, TS_SKB_CB(state)); - return textsearch_find(config, state); + ret = textsearch_find(config, state); + return (ret <= to - from ? ret : UINT_MAX); } /** @@ -1826,10 +1898,10 @@ int skb_append_datato_frags(struct sock *sk, struct sk_buff *skb, * @len: length of data pulled * * This function performs an skb_pull on the packet and updates - * update the CHECKSUM_HW checksum. It should be used on receive - * path processing instead of skb_pull unless you know that the - * checksum difference is zero (e.g., a valid IP header) or you - * are setting ip_summed to CHECKSUM_NONE. + * update the CHECKSUM_COMPLETE checksum. It should be used on + * receive path processing instead of skb_pull unless you know + * that the checksum difference is zero (e.g., a valid IP header) + * or you are setting ip_summed to CHECKSUM_NONE. */ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) { @@ -1845,13 +1917,13 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); /** * skb_segment - Perform protocol segmentation on skb. * @skb: buffer to segment - * @sg: whether scatter-gather can be used for generated segments + * @features: features for the output path (see dev->features) * * This function performs segmentation on the given skb. It returns * the segment at the given position. It returns NULL if there are * no more segments to generate, or when an error is encountered. */ -struct sk_buff *skb_segment(struct sk_buff *skb, int sg) +struct sk_buff *skb_segment(struct sk_buff *skb, int features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; @@ -1860,6 +1932,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int sg) unsigned int offset = doffset; unsigned int headroom; unsigned int len; + int sg = features & NETIF_F_SG; int nfrags = skb_shinfo(skb)->nr_frags; int err = -ENOMEM; int i = 0; @@ -1921,7 +1994,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int sg) frag = skb_shinfo(nskb)->frags; k = 0; - nskb->ip_summed = CHECKSUM_HW; + nskb->ip_summed = CHECKSUM_PARTIAL; nskb->csum = skb->csum; memcpy(skb_put(nskb, hsize), skb->data + offset, hsize); @@ -1973,19 +2046,14 @@ void __init skb_init(void) skbuff_head_cache = kmem_cache_create("skbuff_head_cache", sizeof(struct sk_buff), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!skbuff_head_cache) - panic("cannot create skbuff cache"); - skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", (2*sizeof(struct sk_buff)) + sizeof(atomic_t), 0, - SLAB_HWCACHE_ALIGN, + SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL, NULL); - if (!skbuff_fclone_cache) - panic("cannot create skbuff cache"); } EXPORT_SYMBOL(___pskb_trim); @@ -1993,6 +2061,7 @@ EXPORT_SYMBOL(__kfree_skb); EXPORT_SYMBOL(kfree_skb); EXPORT_SYMBOL(__pskb_pull_tail); EXPORT_SYMBOL(__alloc_skb); +EXPORT_SYMBOL(__netdev_alloc_skb); EXPORT_SYMBOL(pskb_copy); EXPORT_SYMBOL(pskb_expand_head); EXPORT_SYMBOL(skb_checksum); diff --git a/net/core/sock.c b/net/core/sock.c index 5d820c376653..b77e155cbe6c 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -92,7 +92,6 @@ */ #include <linux/capability.h> -#include <linux/config.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> @@ -130,6 +129,53 @@ #include <net/tcp.h> #endif +/* + * Each address family might have different locking rules, so we have + * one slock key per address family: + */ +static struct lock_class_key af_family_keys[AF_MAX]; +static struct lock_class_key af_family_slock_keys[AF_MAX]; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC +/* + * Make lock validator output more readable. (we pre-construct these + * strings build-time, so that runtime initialization of socket + * locks is fast): + */ +static const char *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" , + "sk_lock-AF_X25" , "sk_lock-AF_INET6" , "sk_lock-AF_ROSE" , + "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI" , "sk_lock-AF_SECURITY" , + "sk_lock-AF_KEY" , "sk_lock-AF_NETLINK" , "sk_lock-AF_PACKET" , + "sk_lock-AF_ASH" , "sk_lock-AF_ECONET" , "sk_lock-AF_ATMSVC" , + "sk_lock-21" , "sk_lock-AF_SNA" , "sk_lock-AF_IRDA" , + "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE" , "sk_lock-AF_LLC" , + "sk_lock-27" , "sk_lock-28" , "sk_lock-29" , + "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-AF_MAX" +}; +static const char *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" , + "slock-AF_X25" , "slock-AF_INET6" , "slock-AF_ROSE" , + "slock-AF_DECnet", "slock-AF_NETBEUI" , "slock-AF_SECURITY" , + "slock-AF_KEY" , "slock-AF_NETLINK" , "slock-AF_PACKET" , + "slock-AF_ASH" , "slock-AF_ECONET" , "slock-AF_ATMSVC" , + "slock-21" , "slock-AF_SNA" , "slock-AF_IRDA" , + "slock-AF_PPPOX" , "slock-AF_WANPIPE" , "slock-AF_LLC" , + "slock-27" , "slock-28" , "slock-29" , + "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_MAX" +}; +#endif + +/* + * sk_callback_lock locking rules are per-address-family, + * so split the lock classes by using a per-AF key: + */ +static struct lock_class_key af_callback_keys[AF_MAX]; + /* Take into consideration the size of the struct sk_buff overhead in the * determination of these values, since that is non-constant across * platforms. This makes socket queueing behavior and performance @@ -141,13 +187,13 @@ #define SK_RMEM_MAX (_SK_MEM_OVERHEAD * _SK_MEM_PACKETS) /* Run time adjustable parameters. */ -__u32 sysctl_wmem_max = SK_WMEM_MAX; -__u32 sysctl_rmem_max = SK_RMEM_MAX; -__u32 sysctl_wmem_default = SK_WMEM_MAX; -__u32 sysctl_rmem_default = SK_RMEM_MAX; +__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX; +__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX; +__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancilliary data plus some space */ -int sysctl_optmem_max = sizeof(unsigned long)*(2*UIO_MAXIOV + 512); +int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -201,11 +247,7 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto out; } - /* It would be deadlock, if sock_queue_rcv_skb is used - with socket lock! We assume that users of this - function are lock free. - */ - err = sk_filter(sk, skb, 1); + err = sk_filter(sk, skb); if (err) goto out; @@ -232,15 +274,22 @@ int sk_receive_skb(struct sock *sk, struct sk_buff *skb) { int rc = NET_RX_SUCCESS; - if (sk_filter(sk, skb, 0)) + if (sk_filter(sk, skb)) goto discard_and_relse; skb->dev = NULL; bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) + if (!sock_owned_by_user(sk)) { + /* + * trylock + unlock semantics: + */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_); + rc = sk->sk_backlog_rcv(sk, skb); - else + + mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + } else sk_add_backlog(sk, skb); bh_unlock_sock(sk); out: @@ -553,18 +602,25 @@ set_rcvbuf: break; case SO_DETACH_FILTER: - spin_lock_bh(&sk->sk_lock.slock); - filter = sk->sk_filter; + rcu_read_lock_bh(); + filter = rcu_dereference(sk->sk_filter); if (filter) { - sk->sk_filter = NULL; - spin_unlock_bh(&sk->sk_lock.slock); + rcu_assign_pointer(sk->sk_filter, NULL); sk_filter_release(sk, filter); + rcu_read_unlock_bh(); break; } - spin_unlock_bh(&sk->sk_lock.slock); + rcu_read_unlock_bh(); ret = -ENONET; break; + case SO_PASSSEC: + if (valbool) + set_bit(SOCK_PASSSEC, &sock->flags); + else + clear_bit(SOCK_PASSSEC, &sock->flags); + break; + /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ default: @@ -723,6 +779,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_state == TCP_LISTEN; break; + case SO_PASSSEC: + v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0; + break; + case SO_PEERSEC: return security_socket_getpeersec_stream(sock, optval, optlen, len); @@ -739,6 +799,33 @@ lenout: return 0; } +/* + * Initialize an sk_lock. + * + * (We also register the sk_lock with the lock validator.) + */ +static void inline sock_lock_init(struct sock *sk) +{ + spin_lock_init(&sk->sk_lock.slock); + sk->sk_lock.owner = NULL; + init_waitqueue_head(&sk->sk_lock.wq); + /* + * Make sure we are not reinitializing a held lock: + */ + debug_check_no_locks_freed((void *)&sk->sk_lock, sizeof(sk->sk_lock)); + + /* + * Mark both the sk_lock and the sk_lock.slock as a + * per-address-family lock class: + */ + lockdep_set_class_and_name(&sk->sk_lock.slock, + af_family_slock_keys + sk->sk_family, + af_family_slock_key_strings[sk->sk_family]); + lockdep_init_map(&sk->sk_lock.dep_map, + af_family_key_strings[sk->sk_family], + af_family_keys + sk->sk_family); +} + /** * sk_alloc - All socket objects are allocated here * @family: protocol family @@ -793,10 +880,10 @@ void sk_free(struct sock *sk) if (sk->sk_destruct) sk->sk_destruct(sk); - filter = sk->sk_filter; + filter = rcu_dereference(sk->sk_filter); if (filter) { sk_filter_release(sk, filter); - sk->sk_filter = NULL; + rcu_assign_pointer(sk->sk_filter, NULL); } sock_disable_timestamp(sk); @@ -820,7 +907,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) if (newsk != NULL) { struct sk_filter *filter; - memcpy(newsk, sk, sk->sk_prot->obj_size); + sock_copy(newsk, sk); /* SANITY */ sk_node_init(&newsk->sk_node); @@ -838,6 +925,8 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) rwlock_init(&newsk->sk_dst_lock); rwlock_init(&newsk->sk_callback_lock); + lockdep_set_class(&newsk->sk_callback_lock, + af_callback_keys + newsk->sk_family); newsk->sk_dst_cache = NULL; newsk->sk_wmem_queued = 0; @@ -1412,6 +1501,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) rwlock_init(&sk->sk_dst_lock); rwlock_init(&sk->sk_callback_lock); + lockdep_set_class(&sk->sk_callback_lock, + af_callback_keys + sk->sk_family); sk->sk_state_change = sock_def_wakeup; sk->sk_data_ready = sock_def_readable; @@ -1439,24 +1530,34 @@ void sock_init_data(struct socket *sock, struct sock *sk) void fastcall lock_sock(struct sock *sk) { might_sleep(); - spin_lock_bh(&(sk->sk_lock.slock)); + spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_lock.owner) __lock_sock(sk); sk->sk_lock.owner = (void *)1; - spin_unlock_bh(&(sk->sk_lock.slock)); + spin_unlock(&sk->sk_lock.slock); + /* + * The sk_lock has mutex_lock() semantics here: + */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + local_bh_enable(); } EXPORT_SYMBOL(lock_sock); void fastcall release_sock(struct sock *sk) { - spin_lock_bh(&(sk->sk_lock.slock)); + /* + * The sk_lock has mutex_unlock() semantics: + */ + mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + + spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); sk->sk_lock.owner = NULL; - if (waitqueue_active(&(sk->sk_lock.wq))) - wake_up(&(sk->sk_lock.wq)); - spin_unlock_bh(&(sk->sk_lock.slock)); + if (waitqueue_active(&sk->sk_lock.wq)) + wake_up(&sk->sk_lock.wq); + spin_unlock_bh(&sk->sk_lock.slock); } EXPORT_SYMBOL(release_sock); diff --git a/net/core/stream.c b/net/core/stream.c index e9489696f694..d1d7decf70b0 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -196,15 +196,13 @@ EXPORT_SYMBOL(sk_stream_error); void __sk_stream_mem_reclaim(struct sock *sk) { - if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM) { - atomic_sub(sk->sk_forward_alloc / SK_STREAM_MEM_QUANTUM, - sk->sk_prot->memory_allocated); - sk->sk_forward_alloc &= SK_STREAM_MEM_QUANTUM - 1; - if (*sk->sk_prot->memory_pressure && - (atomic_read(sk->sk_prot->memory_allocated) < - sk->sk_prot->sysctl_mem[0])) - *sk->sk_prot->memory_pressure = 0; - } + atomic_sub(sk->sk_forward_alloc / SK_STREAM_MEM_QUANTUM, + sk->sk_prot->memory_allocated); + sk->sk_forward_alloc &= SK_STREAM_MEM_QUANTUM - 1; + if (*sk->sk_prot->memory_pressure && + (atomic_read(sk->sk_prot->memory_allocated) < + sk->sk_prot->sysctl_mem[0])) + *sk->sk_prot->memory_pressure = 0; } EXPORT_SYMBOL(__sk_stream_mem_reclaim); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 710453656721..02534131d88e 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -7,7 +7,6 @@ #include <linux/mm.h> #include <linux/sysctl.h> -#include <linux/config.h> #include <linux/module.h> #include <linux/socket.h> #include <net/sock.h> diff --git a/net/core/user_dma.c b/net/core/user_dma.c index b7c98dbcdb81..248a6b666aff 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -29,6 +29,7 @@ #include <linux/socket.h> #include <linux/rtnetlink.h> /* for BUG_TRAP */ #include <net/tcp.h> +#include <net/netdma.h> #define NET_DMA_DEFAULT_COPYBREAK 4096 diff --git a/net/core/utils.c b/net/core/utils.c index 4f96f389243d..94c5d761c830 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -3,7 +3,8 @@ * * Authors: * net_random Alan Cox - * net_ratelimit Andy Kleen + * net_ratelimit Andi Kleen + * in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project * * Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru> * @@ -130,12 +131,13 @@ void __init net_random_init(void) static int net_random_reseed(void) { int i; - unsigned long seed[NR_CPUS]; + unsigned long seed; - get_random_bytes(seed, sizeof(seed)); for_each_possible_cpu(i) { struct nrnd_state *state = &per_cpu(net_rand_state,i); - __net_srandom(state, seed[i]); + + get_random_bytes(&seed, sizeof(seed)); + __net_srandom(state, seed); } return 0; } @@ -190,3 +192,215 @@ __be32 in_aton(const char *str) } EXPORT_SYMBOL(in_aton); + +#define IN6PTON_XDIGIT 0x00010000 +#define IN6PTON_DIGIT 0x00020000 +#define IN6PTON_COLON_MASK 0x00700000 +#define IN6PTON_COLON_1 0x00100000 /* single : requested */ +#define IN6PTON_COLON_2 0x00200000 /* second : requested */ +#define IN6PTON_COLON_1_2 0x00400000 /* :: requested */ +#define IN6PTON_DOT 0x00800000 /* . */ +#define IN6PTON_DELIM 0x10000000 +#define IN6PTON_NULL 0x20000000 /* first/tail */ +#define IN6PTON_UNKNOWN 0x40000000 + +static inline int digit2bin(char c, char delim) +{ + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == '.') + return IN6PTON_DOT; + if (c >= '0' && c <= '9') + return (IN6PTON_DIGIT | (c - '0')); + return IN6PTON_UNKNOWN; +} + +static inline int xdigit2bin(char c, char delim) +{ + if (c == delim || c == '\0') + return IN6PTON_DELIM; + if (c == ':') + return IN6PTON_COLON_MASK; + if (c == '.') + return IN6PTON_DOT; + if (c >= '0' && c <= '9') + return (IN6PTON_XDIGIT | IN6PTON_DIGIT| (c - '0')); + if (c >= 'a' && c <= 'f') + return (IN6PTON_XDIGIT | (c - 'a' + 10)); + if (c >= 'A' && c <= 'F') + return (IN6PTON_XDIGIT | (c - 'A' + 10)); + return IN6PTON_UNKNOWN; +} + +int in4_pton(const char *src, int srclen, + u8 *dst, + char delim, const char **end) +{ + const char *s; + u8 *d; + u8 dbuf[4]; + int ret = 0; + int i; + int w = 0; + + if (srclen < 0) + srclen = strlen(src); + s = src; + d = dbuf; + i = 0; + while(1) { + int c; + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM))) { + goto out; + } + if (c & (IN6PTON_DOT | IN6PTON_DELIM)) { + if (w == 0) + goto out; + *d++ = w & 0xff; + w = 0; + i++; + if (c & IN6PTON_DELIM) { + if (i != 4) + goto out; + break; + } + goto cont; + } + w = (w * 10) + c; + if ((w & 0xffff) > 255) { + goto out; + } +cont: + if (i >= 4) + goto out; + s++; + srclen--; + } + ret = 1; + memcpy(dst, dbuf, sizeof(dbuf)); +out: + if (end) + *end = s; + return ret; +} + +EXPORT_SYMBOL(in4_pton); + +int in6_pton(const char *src, int srclen, + u8 *dst, + char delim, const char **end) +{ + const char *s, *tok = NULL; + u8 *d, *dc = NULL; + u8 dbuf[16]; + int ret = 0; + int i; + int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL; + int w = 0; + + memset(dbuf, 0, sizeof(dbuf)); + + s = src; + d = dbuf; + if (srclen < 0) + srclen = strlen(src); + + while (1) { + int c; + + c = xdigit2bin(srclen > 0 ? *s : '\0', delim); + if (!(c & state)) + goto out; + if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) { + /* process one 16-bit word */ + if (!(state & IN6PTON_NULL)) { + *d++ = (w >> 8) & 0xff; + *d++ = w & 0xff; + } + w = 0; + if (c & IN6PTON_DELIM) { + /* We've processed last word */ + break; + } + /* + * COLON_1 => XDIGIT + * COLON_2 => XDIGIT|DELIM + * COLON_1_2 => COLON_2 + */ + switch (state & IN6PTON_COLON_MASK) { + case IN6PTON_COLON_2: + dc = d; + state = IN6PTON_XDIGIT | IN6PTON_DELIM; + if (dc - dbuf >= sizeof(dbuf)) + state |= IN6PTON_NULL; + break; + case IN6PTON_COLON_1|IN6PTON_COLON_1_2: + state = IN6PTON_XDIGIT | IN6PTON_COLON_2; + break; + case IN6PTON_COLON_1: + state = IN6PTON_XDIGIT; + break; + case IN6PTON_COLON_1_2: + state = IN6PTON_COLON_2; + break; + default: + state = 0; + } + tok = s + 1; + goto cont; + } + + if (c & IN6PTON_DOT) { + ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s); + if (ret > 0) { + d += 4; + break; + } + goto out; + } + + w = (w << 4) | (0xff & c); + state = IN6PTON_COLON_1 | IN6PTON_DELIM; + if (!(w & 0xf000)) { + state |= IN6PTON_XDIGIT; + } + if (!dc && d + 2 < dbuf + sizeof(dbuf)) { + state |= IN6PTON_COLON_1_2; + state &= ~IN6PTON_DELIM; + } + if (d + 2 >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2); + } +cont: + if ((dc && d + 4 < dbuf + sizeof(dbuf)) || + d + 4 == dbuf + sizeof(dbuf)) { + state |= IN6PTON_DOT; + } + if (d >= dbuf + sizeof(dbuf)) { + state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK); + } + s++; + srclen--; + } + + i = 15; d--; + + if (dc) { + while(d >= dc) + dst[i--] = *d--; + while(i >= dc - dbuf) + dst[i--] = 0; + while(i >= 0) + dst[i--] = *d--; + } else + memcpy(dst, dbuf, sizeof(dbuf)); + + ret = 1; +out: + if (end) + *end = s; + return ret; +} + +EXPORT_SYMBOL(in6_pton); diff --git a/net/core/wireless.c b/net/core/wireless.c index d2bc72d318f7..ffff0da46c6e 100644 --- a/net/core/wireless.c +++ b/net/core/wireless.c @@ -68,11 +68,18 @@ * * v8 - 17.02.06 - Jean II * o RtNetlink requests support (SET/GET) + * + * v8b - 03.08.06 - Herbert Xu + * o Fix Wireless Event locking issues. + * + * v9 - 14.3.06 - Jean II + * o Change length in ESSID and NICK to strlen() instead of strlen()+1 + * o Make standard_ioctl_num and standard_event_num unsigned + * o Remove (struct net_device *)->get_wireless_stats() */ /***************************** INCLUDES *****************************/ -#include <linux/config.h> /* Not needed ??? */ #include <linux/module.h> #include <linux/types.h> /* off_t */ #include <linux/netdevice.h> /* struct ifreq, dev_get_by_name() */ @@ -82,9 +89,11 @@ #include <linux/init.h> /* for __init */ #include <linux/if_arp.h> /* ARPHRD_ETHER */ #include <linux/etherdevice.h> /* compare_ether_addr */ +#include <linux/interrupt.h> #include <linux/wireless.h> /* Pretty obvious */ #include <net/iw_handler.h> /* New driver API */ +#include <net/netlink.h> #include <asm/uaccess.h> /* copy_to_user() */ @@ -233,24 +242,24 @@ static const struct iw_ioctl_description standard_ioctl[] = { [SIOCSIWESSID - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_EVENT, }, [SIOCGIWESSID - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, .flags = IW_DESCR_FLAG_DUMP, }, [SIOCSIWNICKN - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, }, [SIOCGIWNICKN - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_POINT, .token_size = 1, - .max_tokens = IW_ESSID_MAX_SIZE + 1, + .max_tokens = IW_ESSID_MAX_SIZE, }, [SIOCSIWRATE - SIOCIWFIRST] = { .header_type = IW_HEADER_TYPE_PARAM, @@ -337,8 +346,8 @@ static const struct iw_ioctl_description standard_ioctl[] = { .max_tokens = sizeof(struct iw_pmksa), }, }; -static const int standard_ioctl_num = (sizeof(standard_ioctl) / - sizeof(struct iw_ioctl_description)); +static const unsigned standard_ioctl_num = (sizeof(standard_ioctl) / + sizeof(struct iw_ioctl_description)); /* * Meta-data about all the additional standard Wireless Extension events @@ -388,8 +397,8 @@ static const struct iw_ioctl_description standard_event[] = { .max_tokens = sizeof(struct iw_pmkid_cand), }, }; -static const int standard_event_num = (sizeof(standard_event) / - sizeof(struct iw_ioctl_description)); +static const unsigned standard_event_num = (sizeof(standard_event) / + sizeof(struct iw_ioctl_description)); /* Size (in bytes) of the various private data types */ static const char iw_priv_type_size[] = { @@ -464,17 +473,6 @@ static inline struct iw_statistics *get_wireless_stats(struct net_device *dev) (dev->wireless_handlers->get_wireless_stats != NULL)) return dev->wireless_handlers->get_wireless_stats(dev); - /* Old location, field to be removed in next WE */ - if(dev->get_wireless_stats) { - static int printed_message; - - if (!printed_message++) - printk(KERN_DEBUG "%s (WE) : Driver using old /proc/net/wireless support, please fix driver !\n", - dev->name); - - return dev->get_wireless_stats(dev); - } - /* Not found */ return (struct iw_statistics *) NULL; } @@ -1844,6 +1842,43 @@ int wireless_rtnetlink_set(struct net_device * dev, #ifdef WE_EVENT_RTNETLINK /* ---------------------------------------------------------------- */ /* + * Locking... + * ---------- + * + * Thanks to Herbert Xu <herbert@gondor.apana.org.au> for fixing + * the locking issue in here and implementing this code ! + * + * The issue : wireless_send_event() is often called in interrupt context, + * while the Netlink layer can never be called in interrupt context. + * The fully formed RtNetlink events are queued, and then a tasklet is run + * to feed those to Netlink. + * The skb_queue is interrupt safe, and its lock is not held while calling + * Netlink, so there is no possibility of dealock. + * Jean II + */ + +static struct sk_buff_head wireless_nlevent_queue; + +static int __init wireless_nlevent_init(void) +{ + skb_queue_head_init(&wireless_nlevent_queue); + return 0; +} + +subsys_initcall(wireless_nlevent_init); + +static void wireless_nlevent_process(unsigned long data) +{ + struct sk_buff *skb; + + while ((skb = skb_dequeue(&wireless_nlevent_queue))) + rtnl_notify(skb, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); +} + +static DECLARE_TASKLET(wireless_nlevent_tasklet, wireless_nlevent_process, 0); + +/* ---------------------------------------------------------------- */ +/* * Fill a rtnetlink message with our event data. * Note that we propage only the specified event and don't dump the * current wireless config. Dumping the wireless config is far too @@ -1904,8 +1939,10 @@ static inline void rtmsg_iwinfo(struct net_device * dev, return; } NETLINK_CB(skb).dst_group = RTNLGRP_LINK; - netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_ATOMIC); + skb_queue_tail(&wireless_nlevent_queue, skb); + tasklet_schedule(&wireless_nlevent_tasklet); } + #endif /* WE_EVENT_RTNETLINK */ /* ---------------------------------------------------------------- */ |
