diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/Makefile | 1 | ||||
| -rw-r--r-- | net/core/datagram.c | 1 | ||||
| -rw-r--r-- | net/core/dev.c | 654 | ||||
| -rw-r--r-- | net/core/drop_monitor.c | 2 | ||||
| -rw-r--r-- | net/core/ethtool.c | 81 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 107 | ||||
| -rw-r--r-- | net/core/filter.c | 6 | ||||
| -rw-r--r-- | net/core/gen_stats.c | 8 | ||||
| -rw-r--r-- | net/core/link_watch.c | 94 | ||||
| -rw-r--r-- | net/core/neighbour.c | 49 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 59 | ||||
| -rw-r--r-- | net/core/net_namespace.c | 272 | ||||
| -rw-r--r-- | net/core/pktgen.c | 62 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 179 | ||||
| -rw-r--r-- | net/core/skb_dma_map.c | 65 | ||||
| -rw-r--r-- | net/core/skbuff.c | 5 | ||||
| -rw-r--r-- | net/core/sock.c | 58 | ||||
| -rw-r--r-- | net/core/sysctl_net_core.c | 25 | ||||
| -rw-r--r-- | net/core/utils.c | 2 |
19 files changed, 1037 insertions, 693 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 796f46eece5..08791ac3e05 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -6,7 +6,6 @@ obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \ gen_stats.o gen_estimator.o net_namespace.o obj-$(CONFIG_SYSCTL) += sysctl_net_core.o -obj-$(CONFIG_HAS_DMA) += skb_dma_map.o obj-y += dev.o ethtool.o dev_mcast.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o diff --git a/net/core/datagram.c b/net/core/datagram.c index 4ade3011bb3..95c2e0840d0 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -271,6 +271,7 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) } kfree_skb(skb); + atomic_inc(&sk->sk_drops); sk_mem_reclaim_partial(sk); return err; diff --git a/net/core/dev.c b/net/core/dev.c index fe10551d367..c36a17aafcf 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -79,6 +79,7 @@ #include <linux/cpu.h> #include <linux/types.h> #include <linux/kernel.h> +#include <linux/hash.h> #include <linux/sched.h> #include <linux/mutex.h> #include <linux/string.h> @@ -104,6 +105,7 @@ #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> +#include <net/xfrm.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/kmod.h> @@ -175,7 +177,7 @@ static struct list_head ptype_all __read_mostly; /* Taps */ * The @dev_base_head list is protected by @dev_base_lock and the rtnl * semaphore. * - * Pure readers hold dev_base_lock for reading. + * Pure readers hold dev_base_lock for reading, or rcu_read_lock() * * Writers must hold the rtnl semaphore while they loop through the * dev_base_head list, and hold dev_base_lock for writing when they do the @@ -193,18 +195,15 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); -#define NETDEV_HASHBITS 8 -#define NETDEV_HASHENTRIES (1 << NETDEV_HASHBITS) - static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); - return &net->dev_name_head[hash & ((1 << NETDEV_HASHBITS) - 1)]; + return &net->dev_name_head[hash_32(hash, NETDEV_HASHBITS)]; } static inline struct hlist_head *dev_index_hash(struct net *net, int ifindex) { - return &net->dev_index_head[ifindex & ((1 << NETDEV_HASHBITS) - 1)]; + return &net->dev_index_head[ifindex & (NETDEV_HASHENTRIES - 1)]; } /* Device list insertion */ @@ -215,23 +214,26 @@ static int list_netdevice(struct net_device *dev) ASSERT_RTNL(); write_lock_bh(&dev_base_lock); - list_add_tail(&dev->dev_list, &net->dev_base_head); - hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); - hlist_add_head(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); + list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + hlist_add_head_rcu(&dev->index_hlist, + dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); return 0; } -/* Device list removal */ +/* Device list removal + * caller must respect a RCU grace period before freeing/reusing dev + */ static void unlist_netdevice(struct net_device *dev) { ASSERT_RTNL(); /* Unlink dev from the device chain */ write_lock_bh(&dev_base_lock); - list_del(&dev->dev_list); - hlist_del(&dev->name_hlist); - hlist_del(&dev->index_hlist); + list_del_rcu(&dev->dev_list); + hlist_del_rcu(&dev->name_hlist); + hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); } @@ -587,18 +589,44 @@ __setup("netdev=", netdev_boot_setup); struct net_device *__dev_get_by_name(struct net *net, const char *name) { struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); - hlist_for_each(p, dev_name_hash(net, name)) { - struct net_device *dev - = hlist_entry(p, struct net_device, name_hlist); + hlist_for_each_entry(dev, p, head, name_hlist) if (!strncmp(dev->name, name, IFNAMSIZ)) return dev; - } + return NULL; } EXPORT_SYMBOL(__dev_get_by_name); /** + * dev_get_by_name_rcu - find a device by its name + * @net: the applicable net namespace + * @name: name to find + * + * Find an interface by name. + * If the name is found a pointer to the device is returned. + * If the name is not found then %NULL is returned. + * The reference counters are not incremented so the caller must be + * careful with locks. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) +{ + struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_name_hash(net, name); + + hlist_for_each_entry_rcu(dev, p, head, name_hlist) + if (!strncmp(dev->name, name, IFNAMSIZ)) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_get_by_name_rcu); + +/** * dev_get_by_name - find a device by its name * @net: the applicable net namespace * @name: name to find @@ -614,11 +642,11 @@ struct net_device *dev_get_by_name(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(net, name); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_name); @@ -638,17 +666,42 @@ EXPORT_SYMBOL(dev_get_by_name); struct net_device *__dev_get_by_index(struct net *net, int ifindex) { struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); - hlist_for_each(p, dev_index_hash(net, ifindex)) { - struct net_device *dev - = hlist_entry(p, struct net_device, index_hlist); + hlist_for_each_entry(dev, p, head, index_hlist) if (dev->ifindex == ifindex) return dev; - } + return NULL; } EXPORT_SYMBOL(__dev_get_by_index); +/** + * dev_get_by_index_rcu - find a device by its ifindex + * @net: the applicable net namespace + * @ifindex: index of device + * + * Search for an interface by index. Returns %NULL if the device + * is not found or a pointer to the device. The device has not + * had its reference counter increased so the caller must be careful + * about locking. The caller must hold RCU lock. + */ + +struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex) +{ + struct hlist_node *p; + struct net_device *dev; + struct hlist_head *head = dev_index_hash(net, ifindex); + + hlist_for_each_entry_rcu(dev, p, head, index_hlist) + if (dev->ifindex == ifindex) + return dev; + + return NULL; +} +EXPORT_SYMBOL(dev_get_by_index_rcu); + /** * dev_get_by_index - find a device by its ifindex @@ -665,11 +718,11 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (dev) dev_hold(dev); - read_unlock(&dev_base_lock); + rcu_read_unlock(); return dev; } EXPORT_SYMBOL(dev_get_by_index); @@ -748,15 +801,15 @@ struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags, struct net_device *dev, *ret; ret = NULL; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { dev_hold(dev); ret = dev; break; } } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return ret; } EXPORT_SYMBOL(dev_get_by_flags); @@ -841,7 +894,8 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) free_page((unsigned long) inuse); } - snprintf(buf, IFNAMSIZ, name, i); + if (buf != name) + snprintf(buf, IFNAMSIZ, name, i); if (!__dev_get_by_name(net, buf)) return i; @@ -881,6 +935,21 @@ int dev_alloc_name(struct net_device *dev, const char *name) } EXPORT_SYMBOL(dev_alloc_name); +static int dev_get_valid_name(struct net *net, const char *name, char *buf, + bool fmt) +{ + if (!dev_valid_name(name)) + return -EINVAL; + + if (fmt && strchr(name, '%')) + return __dev_alloc_name(net, name, buf); + else if (__dev_get_by_name(net, name)) + return -EEXIST; + else if (buf != name) + strlcpy(buf, name, IFNAMSIZ); + + return 0; +} /** * dev_change_name - change name of a device @@ -904,28 +973,20 @@ int dev_change_name(struct net_device *dev, const char *newname) if (dev->flags & IFF_UP) return -EBUSY; - if (!dev_valid_name(newname)) - return -EINVAL; - if (strncmp(newname, dev->name, IFNAMSIZ) == 0) return 0; memcpy(oldname, dev->name, IFNAMSIZ); - if (strchr(newname, '%')) { - err = dev_alloc_name(dev, newname); - if (err < 0) - return err; - } else if (__dev_get_by_name(net, newname)) - return -EEXIST; - else - strlcpy(dev->name, newname, IFNAMSIZ); + err = dev_get_valid_name(net, newname, dev->name, 1); + if (err < 0) + return err; rollback: /* For now only devices in the initial network namespace * are in sysfs. */ - if (net == &init_net) { + if (net_eq(net, &init_net)) { ret = device_rename(&dev->dev, dev->name); if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); @@ -935,7 +996,12 @@ rollback: write_lock_bh(&dev_base_lock); hlist_del(&dev->name_hlist); - hlist_add_head(&dev->name_hlist, dev_name_hash(net, dev->name)); + write_unlock_bh(&dev_base_lock); + + synchronize_rcu(); + + write_lock_bh(&dev_base_lock); + hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); write_unlock_bh(&dev_base_lock); ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); @@ -1038,9 +1104,9 @@ void dev_load(struct net *net, const char *name) { struct net_device *dev; - read_lock(&dev_base_lock); - dev = __dev_get_by_name(net, name); - read_unlock(&dev_base_lock); + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, name); + rcu_read_unlock(); if (!dev && capable(CAP_NET_ADMIN)) request_module("%s", name); @@ -1287,6 +1353,7 @@ rollback: nb->notifier_call(nb, NETDEV_DOWN, dev); } nb->notifier_call(nb, NETDEV_UNREGISTER, dev); + nb->notifier_call(nb, NETDEV_UNREGISTER_BATCH, dev); } } @@ -1353,6 +1420,45 @@ static inline void net_timestamp(struct sk_buff *skb) skb->tstamp.tv64 = 0; } +/** + * dev_forward_skb - loopback an skb to another netif + * + * @dev: destination network device + * @skb: buffer to forward + * + * return values: + * NET_RX_SUCCESS (no congestion) + * NET_RX_DROP (packet was dropped) + * + * dev_forward_skb can be used for injecting an skb from the + * start_xmit function of one device into the receive queue + * of another device. + * + * The receiving device may be in another namespace, so + * we have to clear all information in the skb that could + * impact namespace isolation. + */ +int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) +{ + skb_orphan(skb); + + if (!(dev->flags & IFF_UP)) + return NET_RX_DROP; + + if (skb->len > (dev->mtu + dev->hard_header_len)) + return NET_RX_DROP; + + skb_dst_drop(skb); + skb->tstamp.tv64 = 0; + skb->pkt_type = PACKET_HOST; + skb->protocol = eth_type_trans(skb, dev); + skb->mark = 0; + secpath_reset(skb); + nf_reset(skb); + return netif_rx(skb); +} +EXPORT_SYMBOL_GPL(dev_forward_skb); + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1701,7 +1807,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { const struct net_device_ops *ops = dev->netdev_ops; - int rc; + int rc = NETDEV_TX_OK; if (likely(!skb->next)) { if (!list_empty(&ptype_all)) @@ -1749,6 +1855,8 @@ gso: nskb->next = NULL; rc = ops->ndo_start_xmit(nskb, dev); if (unlikely(rc != NETDEV_TX_OK)) { + if (rc & ~NETDEV_TX_MASK) + goto out_kfree_gso_skb; nskb->next = skb->next; skb->next = nskb; return rc; @@ -1758,11 +1866,12 @@ gso: return NETDEV_TX_BUSY; } while (skb->next); - skb->destructor = DEV_GSO_CB(skb)->destructor; - +out_kfree_gso_skb: + if (likely(skb->next == NULL)) + skb->destructor = DEV_GSO_CB(skb)->destructor; out_kfree_skb: kfree_skb(skb); - return NETDEV_TX_OK; + return rc; } static u32 skb_tx_hashrnd; @@ -1789,16 +1898,43 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) } EXPORT_SYMBOL(skb_tx_hash); +static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) +{ + if (unlikely(queue_index >= dev->real_num_tx_queues)) { + if (net_ratelimit()) { + WARN(1, "%s selects TX queue %d, but " + "real number of TX queues is %d\n", + dev->name, queue_index, + dev->real_num_tx_queues); + } + return 0; + } + return queue_index; +} + static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { - const struct net_device_ops *ops = dev->netdev_ops; - u16 queue_index = 0; + u16 queue_index; + struct sock *sk = skb->sk; + + if (sk_tx_queue_recorded(sk)) { + queue_index = sk_tx_queue_get(sk); + } else { + const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_select_queue) - queue_index = ops->ndo_select_queue(dev, skb); - else if (dev->real_num_tx_queues > 1) - queue_index = skb_tx_hash(dev, skb); + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + queue_index = 0; + if (dev->real_num_tx_queues > 1) + queue_index = skb_tx_hash(dev, skb); + + if (sk && sk->sk_dst_cache) + sk_tx_queue_set(sk, queue_index); + } + } skb_set_queue_mapping(skb, queue_index); return netdev_get_tx_queue(dev, queue_index); @@ -1935,8 +2071,8 @@ gso: HARD_TX_LOCK(dev, txq, cpu); if (!netif_tx_queue_stopped(txq)) { - rc = NET_XMIT_SUCCESS; - if (!dev_hard_start_xmit(skb, dev, txq)) { + rc = dev_hard_start_xmit(skb, dev, txq); + if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; } @@ -2191,7 +2327,7 @@ static int ing_filter(struct sk_buff *skb) if (MAX_RED_LOOP < ttl++) { printk(KERN_WARNING "Redir loop detected Dropping packet (%d->%d)\n", - skb->iif, dev->ifindex); + skb->skb_iif, dev->ifindex); return TC_ACT_SHOT; } @@ -2292,15 +2428,15 @@ int netif_receive_skb(struct sk_buff *skb) if (!skb->tstamp.tv64) net_timestamp(skb); - if (skb->vlan_tci && vlan_hwaccel_do_receive(skb)) + if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb)) return NET_RX_SUCCESS; /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) return NET_RX_DROP; - if (!skb->iif) - skb->iif = skb->dev->ifindex; + if (!skb->skb_iif) + skb->skb_iif = skb->dev->ifindex; null_or_orig = NULL; orig_dev = skb->dev; @@ -2440,7 +2576,7 @@ void napi_gro_flush(struct napi_struct *napi) } EXPORT_SYMBOL(napi_gro_flush); -int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff **pp = NULL; struct packet_type *ptype; @@ -2448,7 +2584,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK]; int same_flow; int mac_len; - int ret; + enum gro_result ret; if (!(skb->dev->features & NETIF_F_GRO)) goto normal; @@ -2532,7 +2668,8 @@ normal: } EXPORT_SYMBOL(dev_gro_receive); -static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +static gro_result_t +__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; @@ -2540,33 +2677,35 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) return GRO_NORMAL; for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev) - && !compare_ether_header(skb_mac_header(p), - skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = + (p->dev == skb->dev) && + !compare_ether_header(skb_mac_header(p), + skb_gro_mac_header(skb)); NAPI_GRO_CB(p)->flush = 0; } return dev_gro_receive(napi, skb); } -int napi_skb_finish(int ret, struct sk_buff *skb) +gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) { - int err = NET_RX_SUCCESS; - switch (ret) { case GRO_NORMAL: - return netif_receive_skb(skb); + if (netif_receive_skb(skb)) + ret = GRO_DROP; + break; case GRO_DROP: - err = NET_RX_DROP; - /* fall through */ - case GRO_MERGED_FREE: kfree_skb(skb); break; + + case GRO_HELD: + case GRO_MERGED: + break; } - return err; + return ret; } EXPORT_SYMBOL(napi_skb_finish); @@ -2586,7 +2725,7 @@ void skb_gro_reset_offset(struct sk_buff *skb) } EXPORT_SYMBOL(skb_gro_reset_offset); -int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) +gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { skb_gro_reset_offset(skb); @@ -2605,49 +2744,41 @@ EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { - struct net_device *dev = napi->dev; struct sk_buff *skb = napi->skb; if (!skb) { - skb = netdev_alloc_skb(dev, GRO_MAX_HEAD + NET_IP_ALIGN); - if (!skb) - goto out; - - skb_reserve(skb, NET_IP_ALIGN); - - napi->skb = skb; + skb = netdev_alloc_skb_ip_align(napi->dev, GRO_MAX_HEAD); + if (skb) + napi->skb = skb; } - -out: return skb; } EXPORT_SYMBOL(napi_get_frags); -int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret) +gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, + gro_result_t ret) { - int err = NET_RX_SUCCESS; - switch (ret) { case GRO_NORMAL: case GRO_HELD: skb->protocol = eth_type_trans(skb, napi->dev); - if (ret == GRO_NORMAL) - return netif_receive_skb(skb); - - skb_gro_pull(skb, -ETH_HLEN); + if (ret == GRO_HELD) + skb_gro_pull(skb, -ETH_HLEN); + else if (netif_receive_skb(skb)) + ret = GRO_DROP; break; case GRO_DROP: - err = NET_RX_DROP; - /* fall through */ - case GRO_MERGED_FREE: napi_reuse_skb(napi, skb); break; + + case GRO_MERGED: + break; } - return err; + return ret; } EXPORT_SYMBOL(napi_frags_finish); @@ -2688,12 +2819,12 @@ out: } EXPORT_SYMBOL(napi_frags_skb); -int napi_gro_frags(struct napi_struct *napi) +gro_result_t napi_gro_frags(struct napi_struct *napi) { struct sk_buff *skb = napi_frags_skb(napi); if (!skb) - return NET_RX_DROP; + return GRO_DROP; return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb)); } @@ -2938,15 +3069,15 @@ static int dev_ifname(struct net *net, struct ifreq __user *arg) if (copy_from_user(&ifr, arg, sizeof(struct ifreq))) return -EFAULT; - read_lock(&dev_base_lock); - dev = __dev_get_by_index(net, ifr.ifr_ifindex); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifr.ifr_ifindex); if (!dev) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); return -ENODEV; } strcpy(ifr.ifr_name, dev->name); - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (copy_to_user(arg, &ifr, sizeof(struct ifreq))) return -EFAULT; @@ -3016,18 +3147,18 @@ static int dev_ifconf(struct net *net, char __user *arg) * in detail. */ void *dev_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { struct net *net = seq_file_net(seq); loff_t off; struct net_device *dev; - read_lock(&dev_base_lock); + rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; off = 1; - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (off++ == *pos) return dev; @@ -3036,16 +3167,18 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos) void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net *net = seq_file_net(seq); + struct net_device *dev = (v == SEQ_START_TOKEN) ? + first_net_device(seq_file_net(seq)) : + next_net_device((struct net_device *)v); + ++*pos; - return v == SEQ_START_TOKEN ? - first_net_device(net) : next_net_device((struct net_device *)v); + return rcu_dereference(dev); } void dev_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) @@ -4254,12 +4387,12 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) EXPORT_SYMBOL(dev_set_mac_address); /* - * Perform the SIOCxIFxxx calls, inside read_lock(dev_base_lock) + * Perform the SIOCxIFxxx calls, inside rcu_read_lock() */ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd) { int err; - struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); + struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name); if (!dev) return -ENODEV; @@ -4491,9 +4624,9 @@ int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg) case SIOCGIFINDEX: case SIOCGIFTXQLEN: dev_load(net, ifr.ifr_name); - read_lock(&dev_base_lock); + rcu_read_lock(); ret = dev_ifsioc_locked(net, &ifr, cmd); - read_unlock(&dev_base_lock); + rcu_read_unlock(); if (!ret) { if (colon) *colon = ':'; @@ -4636,59 +4769,80 @@ static void net_set_todo(struct net_device *dev) list_add_tail(&dev->todo_list, &net_todo_list); } -static void rollback_registered(struct net_device *dev) +static void rollback_registered_many(struct list_head *head) { + struct net_device *dev; + BUG_ON(dev_boot_phase); ASSERT_RTNL(); - /* Some devices call without registering for initialization unwind. */ - if (dev->reg_state == NETREG_UNINITIALIZED) { - printk(KERN_DEBUG "unregister_netdevice: device %s/%p never " - "was registered\n", dev->name, dev); + list_for_each_entry(dev, head, unreg_list) { + /* Some devices call without registering + * for initialization unwind. + */ + if (dev->reg_state == NETREG_UNINITIALIZED) { + pr_debug("unregister_netdevice: device %s/%p never " + "was registered\n", dev->name, dev); - WARN_ON(1); - return; - } + WARN_ON(1); + return; + } - BUG_ON(dev->reg_state != NETREG_REGISTERED); + BUG_ON(dev->reg_state != NETREG_REGISTERED); - /* If device is running, close it first. */ - dev_close(dev); + /* If device is running, close it first. */ + dev_close(dev); - /* And unlink it from device chain. */ - unlist_netdevice(dev); + /* And unlink it from device chain. */ + unlist_netdevice(dev); - dev->reg_state = NETREG_UNREGISTERING; + dev->reg_state = NETREG_UNREGISTERING; + } synchronize_net(); - /* Shutdown queueing discipline. */ - dev_shutdown(dev); + list_for_each_entry(dev, head, unreg_list) { + /* Shutdown queueing discipline. */ + dev_shutdown(dev); - /* Notify protocols, that we are about to destroy - this device. They should clean all the things. - */ - call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + /* Notify protocols, that we are about to destroy + this device. They should clean all the things. + */ + call_netdevice_notifiers(NETDEV_UNREGISTER, dev); - /* - * Flush the unicast and multicast chains - */ - dev_unicast_flush(dev); - dev_addr_discard(dev); + /* + * Flush the unicast and multicast chains + */ + dev_unicast_flush(dev); + dev_addr_discard(dev); - if (dev->netdev_ops->ndo_uninit) - dev->netdev_ops->ndo_uninit(dev); + if (dev->netdev_ops->ndo_uninit) + dev->netdev_ops->ndo_uninit(dev); - /* Notifier chain MUST detach us from master device. */ - WARN_ON(dev->master); + /* Notifier chain MUST detach us from master device. */ + WARN_ON(dev->master); - /* Remove entries from kobject tree */ - netdev_unregister_kobject(dev); + /* Remove entries from kobject tree */ + netdev_unregister_kobject(dev); + } + + /* Process any work delayed until the end of the batch */ + dev = list_entry(head->next, struct net_device, unreg_list); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); synchronize_net(); - dev_put(dev); + list_for_each_entry(dev, head, unreg_list) + dev_put(dev); +} + +static void rollback_registered(struct net_device *dev) +{ + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + rollback_registered_many(&single); } static void __netdev_init_queue_locks_one(struct net_device *dev, @@ -4747,6 +4901,33 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) EXPORT_SYMBOL(netdev_fix_features); /** + * netif_stacked_transfer_operstate - transfer operstate + * @rootdev: the root or lower level device to transfer state from + * @dev: the device to transfer operstate to + * + * Transfer operational state from root to device. This is normally + * called when a stacking relationship exists between the root + * device and the device(a leaf device). + */ +void netif_stacked_transfer_operstate(const struct net_device *rootdev, + struct net_device *dev) +{ + if (rootdev->operstate == IF_OPER_DORMANT) + netif_dormant_on(dev); + else + netif_dormant_off(dev); + + if (netif_carrier_ok(rootdev)) { + if (!netif_carrier_ok(dev)) + netif_carrier_on(dev); + } else { + if (netif_carrier_ok(dev)) + netif_carrier_off(dev); + } +} +EXPORT_SYMBOL(netif_stacked_transfer_operstate); + +/** * register_netdevice - register a network device * @dev: device to register * @@ -4765,8 +4946,6 @@ EXPORT_SYMBOL(netdev_fix_features); int register_netdevice(struct net_device *dev) { - struct hlist_head *head; - struct hlist_node *p; int ret; struct net *net = dev_net(dev); @@ -4795,26 +4974,14 @@ int register_netdevice(struct net_device *dev) } } - if (!dev_valid_name(dev->name)) { - ret = -EINVAL; + ret = dev_get_valid_name(net, dev->name, dev->name, 0); + if (ret) goto err_uninit; - } dev->ifindex = dev_new_index(net); if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Check for existence of name */ - head = dev_name_hash(net, dev->name); - hlist_for_each(p, head) { - struct net_device *d - = hlist_entry(p, struct net_device, name_hlist); - if (!strncmp(d->name, dev->name, IFNAMSIZ)) { - ret = -EEXIST; - goto err_uninit; - } - } - /* Fix illegal checksum combinations */ if ((dev->features & NETIF_F_HW_CSUM) && (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { @@ -4837,6 +5004,12 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_GSO; netdev_initialize_kobject(dev); + + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); + ret = notifier_to_errno(ret); + if (ret) + goto err_uninit; + ret = netdev_register_kobject(dev); if (ret) goto err_uninit; @@ -4961,6 +5134,8 @@ static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; + linkwatch_forget_dev(dev); + rebroadcast_time = warning_time = jiffies; while (atomic_read(&dev->refcnt) != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { @@ -4968,6 +5143,8 @@ static void netdev_wait_allrefs(struct net_device *dev) /* Rebroadcast unregister notification */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + /* don't resend NETDEV_UNREGISTER_BATCH, _BATCH users + * should have already handle it the first time */ if (test_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { @@ -5063,6 +5240,32 @@ void netdev_run_todo(void) } /** + * dev_txq_stats_fold - fold tx_queues stats + * @dev: device to get statistics from + * @stats: struct net_device_stats to hold results + */ +void dev_txq_stats_fold(const struct net_device *dev, + struct net_device_stats *stats) +{ + unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; + unsigned int i; + struct netdev_queue *txq; + + for (i = 0; i < dev->num_tx_queues; i++) { + txq = netdev_get_tx_queue(dev, i); + tx_bytes += txq->tx_bytes; + tx_packets += txq->tx_packets; + tx_dropped += txq->tx_dropped; + } + if (tx_bytes || tx_packets || tx_dropped) { + stats->tx_bytes = tx_bytes; + stats->tx_packets = tx_packets; + stats->tx_dropped = tx_dropped; + } +} +EXPORT_SYMBOL(dev_txq_stats_fold); + +/** * dev_get_stats - get network device statistics * @dev: device to get statistics from * @@ -5076,25 +5279,9 @@ const struct net_device_stats *dev_get_stats(struct net_device *dev) if (ops->ndo_get_stats) return ops->ndo_get_stats(dev); - else { - unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; - struct net_device_stats *stats = &dev->stats; - unsigned int i; - struct netdev_queue *txq; - - for (i = 0; i < dev->num_tx_queues; i++) { - txq = netdev_get_tx_queue(dev, i); - tx_bytes += txq->tx_bytes; - tx_packets += txq->tx_packets; - tx_dropped += txq->tx_dropped; - } - if (tx_bytes || tx_packets || tx_dropped) { - stats->tx_bytes = tx_bytes; - stats->tx_packets = tx_packets; - stats->tx_dropped = tx_dropped; - } - return stats; - } + + dev_txq_stats_fold(dev, &dev->stats); + return &dev->stats; } EXPORT_SYMBOL(dev_get_stats); @@ -5174,6 +5361,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, netdev_init_queues(dev); INIT_LIST_HEAD(&dev->napi_list); + INIT_LIST_HEAD(&dev->unreg_list); + INIT_LIST_HEAD(&dev->link_watch_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); strcpy(dev->name, name); @@ -5238,25 +5427,47 @@ void synchronize_net(void) EXPORT_SYMBOL(synchronize_net); /** - * unregister_netdevice - remove device from the kernel + * unregister_netdevice_queue - remove device from the kernel * @dev: device + * @head: list * * This function shuts down a device interface and removes it * from the kernel tables. + * If head not NULL, device is queued to be unregistered later. * * Callers must hold the rtnl semaphore. You may want * unregister_netdev() instead of this. */ -void unregister_netdevice(struct net_device *dev) +void unregister_netdevice_queue(struct net_device *dev, struct list_head *head) { ASSERT_RTNL(); - rollback_registered(dev); - /* Finish processing unregister after unlock */ - net_set_todo(dev); + if (head) { + list_move_tail(&dev->unreg_list, head); + } else { + rollback_registered(dev); + /* Finish processing unregister after unlock */ + net_set_todo(dev); + } } -EXPORT_SYMBOL(unregister_netdevice); +EXPORT_SYMBOL(unregister_netdevice_queue); + +/** + * unregister_netdevice_many - unregister many devices + * @head: list of devices + */ +void unregister_netdevice_many(struct list_head *head) +{ + struct net_device *dev; + + if (!list_empty(head)) { + rollback_registered_many(head); + list_for_each_entry(dev, head, unreg_list) + net_set_todo(dev); + } +} +EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel @@ -5293,8 +5504,6 @@ EXPORT_SYMBOL(unregister_netdev); int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { - char buf[IFNAMSIZ]; - const char *destname; int err; ASSERT_RTNL(); @@ -5327,20 +5536,11 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char * we can use it in the destination network namespace. */ err = -EEXIST; - destname = dev->name; - if (__dev_get_by_name(net, destname)) { + if (__dev_get_by_name(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; - if (!dev_valid_name(pat)) - goto out; - if (strchr(pat, '%')) { - if (__dev_alloc_name(net, pat, buf) < 0) - goto out; - destname = buf; - } else - destname = pat; - if (__dev_get_by_name(net, destname)) + if (dev_get_valid_name(net, pat, dev->name, 1)) goto out; } @@ -5364,6 +5564,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char this device. They should clean all the things. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); /* * Flush the unicast and multicast chains @@ -5376,10 +5577,6 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Actually switch the network namespace */ dev_net_set(dev, net); - /* Assign the new device name */ - if (destname != dev->name) - strcpy(dev->name, destname); - /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) { int iflink = (dev->iflink == dev->ifindex); @@ -5484,7 +5681,7 @@ unsigned long netdev_increment_features(unsigned long all, unsigned long one, one |= NETIF_F_ALL_CSUM; one |= all & NETIF_F_ONE_FOR_ALL; - all &= one | NETIF_F_LLTX | NETIF_F_GSO; + all &= one | NETIF_F_LLTX | NETIF_F_GSO | NETIF_F_UFO; all |= one & mask & NETIF_F_ONE_FOR_ALL; return all; @@ -5566,14 +5763,13 @@ static struct pernet_operations __net_initdata netdev_net_ops = { static void __net_exit default_device_exit(struct net *net) { - struct net_device *dev; + struct net_device *dev, *aux; /* - * Push all migratable of the network devices back to the + * Push all migratable network devices back to the * initial network namespace */ rtnl_lock(); -restart: - for_each_netdev(net, dev) { + for_each_netdev_safe(net, dev, aux) { int err; char fb_name[IFNAMSIZ]; @@ -5581,11 +5777,9 @@ restart: if (dev->features & NETIF_F_NETNS_LOCAL) continue; - /* Delete virtual devices */ - if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev); - goto restart; - } + /* Leave virtual devices for the generic cleanup */ + if (dev->rtnl_link_ops) + continue; /* Push remaing network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); @@ -5595,13 +5789,37 @@ restart: __func__, dev->name, err); BUG(); } - goto restart; } rtnl_unlock(); } +static void __net_exit default_device_exit_batch(struct list_head *net_list) +{ + /* At exit all network devices most be removed from a network + * namespace. Do this in the reverse order of registeration. + * Do this across as many network namespaces as possible to + * improve batching efficiency. + */ + struct net_device *dev; + struct net *net; + LIST_HEAD(dev_kill_list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) { + for_each_netdev_reverse(net, dev) { + if (dev->rtnl_link_ops) + dev->rtnl_link_ops->dellink(dev, &dev_kill_list); + else + unregister_netdevice_queue(dev, &dev_kill_list); + } + } + unregister_netdevice_many(&dev_kill_list); + rtnl_unlock(); +} + static struct pernet_operations __net_initdata default_device_ops = { .exit = default_device_exit, + .exit_batch = default_device_exit_batch, }; /* diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 0a113f26bc9..b8e9d3a8688 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -41,7 +41,7 @@ static void send_dm_alert(struct work_struct *unused); * netlink alerts */ static int trace_state = TRACE_OFF; -static spinlock_t trace_state_lock = SPIN_LOCK_UNLOCKED; +static DEFINE_SPINLOCK(trace_state_lock); struct per_cpu_dm_data { struct work_struct dm_alert_work; diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4c12ddb5f5e..d8aee584e8d 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -198,13 +198,6 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) rc = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); if (rc >= 0) info.n_priv_flags = rc; - } else { - /* code path for obsolete hooks */ - - if (ops->self_test_count) - info.testinfo_len = ops->self_test_count(dev); - if (ops->get_stats_count) - info.n_stats = ops->get_stats_count(dev); } if (ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); @@ -309,6 +302,26 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) return ret; } +static int ethtool_reset(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value reset; + int ret; + + if (!dev->ethtool_ops->reset) + return -EOPNOTSUPP; + + if (copy_from_user(&reset, useraddr, sizeof(reset))) + return -EFAULT; + + ret = dev->ethtool_ops->reset(dev, &reset.data); + if (ret) + return ret; + + if (copy_to_user(useraddr, &reset, sizeof(reset))) + return -EFAULT; + return 0; +} + static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol = { ETHTOOL_GWOL }; @@ -684,16 +697,10 @@ static int ethtool_self_test(struct net_device *dev, char __user *useraddr) u64 *data; int ret, test_len; - if (!ops->self_test) - return -EOPNOTSUPP; - if (!ops->get_sset_count && !ops->self_test_count) + if (!ops->self_test || !ops->get_sset_count) return -EOPNOTSUPP; - if (ops->get_sset_count) - test_len = ops->get_sset_count(dev, ETH_SS_TEST); - else - /* code path for obsolete hook */ - test_len = ops->self_test_count(dev); + test_len = ops->get_sset_count(dev, ETH_SS_TEST); if (test_len < 0) return test_len; WARN_ON(test_len == 0); @@ -728,36 +735,17 @@ static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) u8 *data; int ret; - if (!ops->get_strings) + if (!ops->get_strings || !ops->get_sset_count) return -EOPNOTSUPP; if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) return -EFAULT; - if (ops->get_sset_count) { - ret = ops->get_sset_count(dev, gstrings.string_set); - if (ret < 0) - return ret; - - gstrings.len = ret; - } else { - /* code path for obsolete hooks */ - - switch (gstrings.string_set) { - case ETH_SS_TEST: - if (!ops->self_test_count) - return -EOPNOTSUPP; - gstrings.len = ops->self_test_count(dev); - break; - case ETH_SS_STATS: - if (!ops->get_stats_count) - return -EOPNOTSUPP; - gstrings.len = ops->get_stats_count(dev); - break; - default: - return -EINVAL; - } - } + ret = ops->get_sset_count(dev, gstrings.string_set); + if (ret < 0) + return ret; + + gstrings.len = ret; data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); if (!data) @@ -798,16 +786,10 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) u64 *data; int ret, n_stats; - if (!ops->get_ethtool_stats) - return -EOPNOTSUPP; - if (!ops->get_sset_count && !ops->get_stats_count) + if (!ops->get_ethtool_stats || !ops->get_sset_count) return -EOPNOTSUPP; - if (ops->get_sset_count) - n_stats = ops->get_sset_count(dev, ETH_SS_STATS); - else - /* code path for obsolete hook */ - n_stats = ops->get_stats_count(dev); + n_stats = ops->get_sset_count(dev, ETH_SS_STATS); if (n_stats < 0) return n_stats; WARN_ON(n_stats == 0); @@ -1127,6 +1109,9 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_FLASHDEV: rc = ethtool_flash_device(dev, useraddr); break; + case ETHTOOL_RESET: + rc = ethtool_reset(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index bd309384f8b..02a3b2c69c1 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -72,7 +72,7 @@ static void flush_route_cache(struct fib_rules_ops *ops) ops->flush_cache(ops); } -int fib_rules_register(struct fib_rules_ops *ops) +static int __fib_rules_register(struct fib_rules_ops *ops) { int err = -EEXIST; struct fib_rules_ops *o; @@ -102,6 +102,28 @@ errout: return err; } +struct fib_rules_ops * +fib_rules_register(struct fib_rules_ops *tmpl, struct net *net) +{ + struct fib_rules_ops *ops; + int err; + + ops = kmemdup(tmpl, sizeof (*ops), GFP_KERNEL); + if (ops == NULL) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&ops->rules_list); + ops->fro_net = net; + + err = __fib_rules_register(ops); + if (err) { + kfree(ops); + ops = ERR_PTR(err); + } + + return ops; +} + EXPORT_SYMBOL_GPL(fib_rules_register); void fib_rules_cleanup_ops(struct fib_rules_ops *ops) @@ -115,6 +137,15 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops) } EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops); +static void fib_rules_put_rcu(struct rcu_head *head) +{ + struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu); + struct net *net = ops->fro_net; + + release_net(net); + kfree(ops); +} + void fib_rules_unregister(struct fib_rules_ops *ops) { struct net *net = ops->fro_net; @@ -124,8 +155,7 @@ void fib_rules_unregister(struct fib_rules_ops *ops) fib_rules_cleanup_ops(ops); spin_unlock(&net->rules_mod_lock); - synchronize_rcu(); - release_net(net); + call_rcu(&ops->rcu, fib_rules_put_rcu); } EXPORT_SYMBOL_GPL(fib_rules_unregister); @@ -135,7 +165,10 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->ifindex && (rule->ifindex != fl->iif)) + if (rule->iifindex && (rule->iifindex != fl->iif)) + goto out; + + if (rule->oifindex && (rule->oifindex != fl->oif)) goto out; if ((rule->mark ^ fl->mark) & rule->mark_mask) @@ -248,14 +281,24 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (tb[FRA_PRIORITY]) rule->pref = nla_get_u32(tb[FRA_PRIORITY]); - if (tb[FRA_IFNAME]) { + if (tb[FRA_IIFNAME]) { + struct net_device *dev; + + rule->iifindex = -1; + nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->iifname); + if (dev) + rule->iifindex = dev->ifindex; + } + + if (tb[FRA_OIFNAME]) { struct net_device *dev; - rule->ifindex = -1; - nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->ifname); + rule->oifindex = -1; + nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, rule->oifname); if (dev) - rule->ifindex = dev->ifindex; + rule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { @@ -274,7 +317,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rule->flags = frh->flags; rule->table = frh_get_table(frh, tb); - if (!rule->pref && ops->default_pref) + if (!tb[FRA_PRIORITY] && ops->default_pref) rule->pref = ops->default_pref(ops); err = -EINVAL; @@ -388,8 +431,12 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) continue; - if (tb[FRA_IFNAME] && - nla_strcmp(tb[FRA_IFNAME], rule->ifname)) + if (tb[FRA_IIFNAME] && + nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) + continue; + + if (tb[FRA_OIFNAME] && + nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) continue; if (tb[FRA_FWMARK] && @@ -447,7 +494,8 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops, struct fib_rule *rule) { size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr)) - + nla_total_size(IFNAMSIZ) /* FRA_IFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */ + + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */ + nla_total_size(4) /* FRA_PRIORITY */ + nla_total_size(4) /* FRA_TABLE */ + nla_total_size(4) /* FRA_FWMARK */ @@ -481,11 +529,18 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL) frh->flags |= FIB_RULE_UNRESOLVED; - if (rule->ifname[0]) { - NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname); + if (rule->iifname[0]) { + NLA_PUT_STRING(skb, FRA_IIFNAME, rule->iifname); - if (rule->ifindex == -1) - frh->flags |= FIB_RULE_DEV_DETACHED; + if (rule->iifindex == -1) + frh->flags |= FIB_RULE_IIF_DETACHED; + } + + if (rule->oifname[0]) { + NLA_PUT_STRING(skb, FRA_OIFNAME, rule->oifname); + + if (rule->oifindex == -1) + frh->flags |= FIB_RULE_OIF_DETACHED; } if (rule->pref) @@ -600,9 +655,12 @@ static void attach_rules(struct list_head *rules, struct net_device *dev) struct fib_rule *rule; list_for_each_entry(rule, rules, list) { - if (rule->ifindex == -1 && - strcmp(dev->name, rule->ifname) == 0) - rule->ifindex = dev->ifindex; + if (rule->iifindex == -1 && + strcmp(dev->name, rule->iifname) == 0) + rule->iifindex = dev->ifindex; + if (rule->oifindex == -1 && + strcmp(dev->name, rule->oifname) == 0) + rule->oifindex = dev->ifindex; } } @@ -610,9 +668,12 @@ static void detach_rules(struct list_head *rules, struct net_device *dev) { struct fib_rule *rule; - list_for_each_entry(rule, rules, list) - if (rule->ifindex == dev->ifindex) - rule->ifindex = -1; + list_for_each_entry(rule, rules, list) { + if (rule->iifindex == dev->ifindex) + rule->iifindex = -1; + if (rule->oifindex == dev->ifindex) + rule->oifindex = -1; + } } diff --git a/net/core/filter.c b/net/core/filter.c index d1d779ca096..08db7b9143a 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -303,6 +303,12 @@ load_b: case SKF_AD_IFINDEX: A = skb->dev->ifindex; continue; + case SKF_AD_MARK: + A = skb->mark; + continue; + case SKF_AD_QUEUE: + A = skb->queue_mapping; + continue; case SKF_AD_NLATTR: { struct nlattr *nla; diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 8569310268a..393b1d8618e 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -127,6 +127,7 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) /** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV * @d: dumping handle + * @b: basic statistics * @r: rate estimator statistics * * Appends the rate estimator statistics to the top level TLV created by @@ -136,8 +137,13 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) * if the room in the socket buffer was not sufficient. */ int -gnet_stats_copy_rate_est(struct gnet_dump *d, struct gnet_stats_rate_est *r) +gnet_stats_copy_rate_est(struct gnet_dump *d, + const struct gnet_stats_basic_packed *b, + struct gnet_stats_rate_est *r) { + if (b && !gen_estimator_active(b, r)) + return 0; + if (d->compat_tc_stats) { d->tc_stats.bps = r->bps; d->tc_stats.pps = r->pps; diff --git a/net/core/link_watch.c b/net/core/link_watch.c index bf8f7af699d..5910b555a54 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -35,7 +35,7 @@ static unsigned long linkwatch_nextevent; static void linkwatch_event(struct work_struct *dummy); static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event); -static struct net_device *lweventlist; +static LIST_HEAD(lweventlist); static DEFINE_SPINLOCK(lweventlist_lock); static unsigned char default_operstate(const struct net_device *dev) @@ -89,8 +89,10 @@ static void linkwatch_add_event(struct net_device *dev) unsigned long flags; spin_lock_irqsave(&lweventlist_lock, flags); - dev->link_watch_next = lweventlist; - lweventlist = dev; + if (list_empty(&dev->link_watch_list)) { + list_add_tail(&dev->link_watch_list, &lweventlist); + dev_hold(dev); + } spin_unlock_irqrestore(&lweventlist_lock, flags); } @@ -133,9 +135,35 @@ static void linkwatch_schedule_work(int urgent) } +static void linkwatch_do_dev(struct net_device *dev) +{ + /* + * Make sure the above read is complete since it can be + * rewritten as soon as we clear the bit below. + */ + smp_mb__before_clear_bit(); + + /* We are about to handle this device, + * so new events can be accepted + */ + clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); + + rfc2863_policy(dev); + if (dev->flags & IFF_UP) { + if (netif_carrier_ok(dev)) + dev_activate(dev); + else + dev_deactivate(dev); + + netdev_state_change(dev); + } + dev_put(dev); +} + static void __linkwatch_run_queue(int urgent_only) { - struct net_device *next; + struct net_device *dev; + LIST_HEAD(wrk); /* * Limit the number of linkwatch events to one @@ -153,46 +181,40 @@ static void __linkwatch_run_queue(int urgent_only) clear_bit(LW_URGENT, &linkwatch_flags); spin_lock_irq(&lweventlist_lock); - next = lweventlist; - lweventlist = NULL; - spin_unlock_irq(&lweventlist_lock); + list_splice_init(&lweventlist, &wrk); - while (next) { - struct net_device *dev = next; + while (!list_empty(&wrk)) { - next = dev->link_watch_next; + dev = list_first_entry(&wrk, struct net_device, link_watch_list); + list_del_init(&dev->link_watch_list); if (urgent_only && !linkwatch_urgent_event(dev)) { - linkwatch_add_event(dev); + list_add_tail(&dev->link_watch_list, &lweventlist); continue; } - - /* - * Make sure the above read is complete since it can be - * rewritten as soon as we clear the bit below. - */ - smp_mb__before_clear_bit(); - - /* We are about to handle this device, - * so new events can be accepted - */ - clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state); - - rfc2863_policy(dev); - if (dev->flags & IFF_UP) { - if (netif_carrier_ok(dev)) - dev_activate(dev); - else - dev_deactivate(dev); - - netdev_state_change(dev); - } - - dev_put(dev); + spin_unlock_irq(&lweventlist_lock); + linkwatch_do_dev(dev); + spin_lock_irq(&lweventlist_lock); } - if (lweventlist) + if (!list_empty(&lweventlist)) linkwatch_schedule_work(0); + spin_unlock_irq(&lweventlist_lock); +} + +void linkwatch_forget_dev(struct net_device *dev) +{ + unsigned long flags; + int clean = 0; + + spin_lock_irqsave(&lweventlist_lock, flags); + if (!list_empty(&dev->link_watch_list)) { + list_del_init(&dev->link_watch_list); + clean = 1; + } + spin_unlock_irqrestore(&lweventlist_lock, flags); + if (clean) + linkwatch_do_dev(dev); } @@ -216,8 +238,6 @@ void linkwatch_fire_event(struct net_device *dev) bool urgent = linkwatch_urgent_event(dev); if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) { - dev_hold(dev); - linkwatch_add_event(dev); } else if (!urgent) return; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index e587e681969..f35377b643e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2092,7 +2092,7 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, if (h > s_h) s_idx = 0; for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { - if (dev_net(n->dev) != net) + if (!net_eq(dev_net(n->dev), net)) continue; if (idx < s_idx) goto next; @@ -2566,21 +2566,18 @@ static struct neigh_sysctl_table { } neigh_sysctl_template __read_mostly = { .neigh_vars = { { - .ctl_name = NET_NEIGH_MCAST_SOLICIT, .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_UCAST_SOLICIT, .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_APP_SOLICIT, .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, @@ -2593,38 +2590,30 @@ static struct neigh_sysctl_table { .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_REACHABLE_TIME, .procname = "base_reachable_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_DELAY_PROBE_TIME, .procname = "delay_first_probe_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_GC_STALE_TIME, .procname = "gc_stale_time", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_UNRES_QLEN, .procname = "unres_qlen", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_PROXY_QLEN, .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, @@ -2649,45 +2638,36 @@ static struct neigh_sysctl_table { .proc_handler = proc_dointvec_userhz_jiffies, }, { - .ctl_name = NET_NEIGH_RETRANS_TIME_MS, .procname = "retrans_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_NEIGH_REACHABLE_TIME_MS, .procname = "base_reachable_time_ms", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, - .strategy = sysctl_ms_jiffies, }, { - .ctl_name = NET_NEIGH_GC_INTERVAL, .procname = "gc_interval", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_NEIGH_GC_THRESH1, .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_GC_THRESH2, .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { - .ctl_name = NET_NEIGH_GC_THRESH3, .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, @@ -2699,7 +2679,7 @@ static struct neigh_sysctl_table { int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, int p_id, int pdev_id, char *p_name, - proc_handler *handler, ctl_handler *strategy) + proc_handler *handler) { struct neigh_sysctl_table *t; const char *dev_name_source = NULL; @@ -2710,10 +2690,10 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, #define NEIGH_CTL_PATH_DEV 3 struct ctl_path neigh_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "proto", .ctl_name = 0, }, - { .procname = "neigh", .ctl_name = 0, }, - { .procname = "default", .ctl_name = NET_PROTO_CONF_DEFAULT, }, + { .procname = "net", }, + { .procname = "proto", }, + { .procname = "neigh", }, + { .procname = "default", }, { }, }; @@ -2738,7 +2718,6 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, if (dev) { dev_name_source = dev->name; - neigh_path[NEIGH_CTL_PATH_DEV].ctl_name = dev->ifindex; /* Terminate the table early */ memset(&t->neigh_vars[14], 0, sizeof(t->neigh_vars[14])); } else { @@ -2750,31 +2729,19 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, } - if (handler || strategy) { + if (handler) { /* RetransTime */ t->neigh_vars[3].proc_handler = handler; - t->neigh_vars[3].strategy = strategy; t->neigh_vars[3].extra1 = dev; - if (!strategy) - t->neigh_vars[3].ctl_name = CTL_UNNUMBERED; /* ReachableTime */ t->neigh_vars[4].proc_handler = handler; - t->neigh_vars[4].strategy = strategy; t->neigh_vars[4].extra1 = dev; - if (!strategy) - t->neigh_vars[4].ctl_name = CTL_UNNUMBERED; /* RetransTime (in milliseconds)*/ t->neigh_vars[12].proc_handler = handler; - t->neigh_vars[12].strategy = strategy; t->neigh_vars[12].extra1 = dev; - if (!strategy) - t->neigh_vars[12].ctl_name = CTL_UNNUMBERED; /* ReachableTime (in milliseconds) */ t->neigh_vars[13].proc_handler = handler; - t->neigh_vars[13].strategy = strategy; t->neigh_vars[13].extra1 = dev; - if (!strategy) - t->neigh_vars[13].ctl_name = CTL_UNNUMBERED; } t->dev_name = kstrdup(dev_name_source, GFP_KERNEL); @@ -2782,9 +2749,7 @@ int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, goto free; neigh_path[NEIGH_CTL_PATH_DEV].procname = t->dev_name; - neigh_path[NEIGH_CTL_PATH_NEIGH].ctl_name = pdev_id; neigh_path[NEIGH_CTL_PATH_PROTO].procname = p_name; - neigh_path[NEIGH_CTL_PATH_PROTO].ctl_name = p_id; t->sysctl_header = register_net_sysctl_table(neigh_parms_net(p), neigh_path, t->neigh_vars); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 427ded84122..fbc1c7472c5 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -130,6 +130,48 @@ static ssize_t show_carrier(struct device *dev, return -EINVAL; } +static ssize_t show_speed(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (netif_running(netdev) && + netdev->ethtool_ops && + netdev->ethtool_ops->get_settings) { + struct ethtool_cmd cmd = { ETHTOOL_GSET }; + + if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) + ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd)); + } + rtnl_unlock(); + return ret; +} + +static ssize_t show_duplex(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct net_device *netdev = to_net_dev(dev); + int ret = -EINVAL; + + if (!rtnl_trylock()) + return restart_syscall(); + + if (netif_running(netdev) && + netdev->ethtool_ops && + netdev->ethtool_ops->get_settings) { + struct ethtool_cmd cmd = { ETHTOOL_GSET }; + + if (!netdev->ethtool_ops->get_settings(netdev, &cmd)) + ret = sprintf(buf, "%s\n", cmd.duplex ? "full" : "half"); + } + rtnl_unlock(); + return ret; +} + static ssize_t show_dormant(struct device *dev, struct device_attribute *attr, char *buf) { @@ -259,6 +301,8 @@ static struct device_attribute net_class_attributes[] = { __ATTR(address, S_IRUGO, show_address, NULL), __ATTR(broadcast, S_IRUGO, show_broadcast, NULL), __ATTR(carrier, S_IRUGO, show_carrier, NULL), + __ATTR(speed, S_IRUGO, show_speed, NULL), + __ATTR(duplex, S_IRUGO, show_duplex, NULL), __ATTR(dormant, S_IRUGO, show_dormant, NULL), __ATTR(operstate, S_IRUGO, show_operstate, NULL), __ATTR(mtu, S_IRUGO | S_IWUSR, show_mtu, store_mtu), @@ -481,7 +525,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return; device_del(dev); @@ -500,15 +544,22 @@ int netdev_register_kobject(struct net_device *net) dev_set_name(dev, "%s", net->name); #ifdef CONFIG_SYSFS - *groups++ = &netstat_group; + /* Allow for a device specific group */ + if (*groups) + groups++; + *groups++ = &netstat_group; #ifdef CONFIG_WIRELESS_EXT_SYSFS - if (net->wireless_handlers || net->ieee80211_ptr) + if (net->ieee80211_ptr) + *groups++ = &wireless_group; +#ifdef CONFIG_WIRELESS_EXT + else if (net->wireless_handlers) *groups++ = &wireless_group; #endif +#endif #endif /* CONFIG_SYSFS */ - if (dev_net(net) != &init_net) + if (!net_eq(dev_net(net), &init_net)) return 0; return device_add(dev); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 1c1af2756f3..bd8c4712ea2 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -27,14 +27,64 @@ EXPORT_SYMBOL(init_net); #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ +static int ops_init(const struct pernet_operations *ops, struct net *net) +{ + int err; + if (ops->id && ops->size) { + void *data = kzalloc(ops->size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + err = net_assign_generic(net, *ops->id, data); + if (err) { + kfree(data); + return err; + } + } + if (ops->init) + return ops->init(net); + return 0; +} + +static void ops_free(const struct pernet_operations *ops, struct net *net) +{ + if (ops->id && ops->size) { + int id = *ops->id; + kfree(net_generic(net, id)); + } +} + +static void ops_exit_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->exit) { + list_for_each_entry(net, net_exit_list, exit_list) + ops->exit(net); + } + if (ops->exit_batch) + ops->exit_batch(net_exit_list); +} + +static void ops_free_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + if (ops->size && ops->id) { + list_for_each_entry(net, net_exit_list, exit_list) + ops_free(ops, net); + } +} + /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net) { /* Must be called with net_mutex held */ - struct pernet_operations *ops; + const struct pernet_operations *ops, *saved_ops; int error = 0; + LIST_HEAD(net_exit_list); atomic_set(&net->count, 1); @@ -43,11 +93,9 @@ static __net_init int setup_net(struct net *net) #endif list_for_each_entry(ops, &pernet_list, list) { - if (ops->init) { - error = ops->init(net); - if (error < 0) - goto out_undo; - } + error = ops_init(ops, net); + if (error < 0) + goto out_undo; } out: return error; @@ -56,10 +104,14 @@ out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ - list_for_each_entry_continue_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_add(&net->exit_list, &net_exit_list); + saved_ops = ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + ops = saved_ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; @@ -147,18 +199,29 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net) return net_create(); } +static DEFINE_SPINLOCK(cleanup_list_lock); +static LIST_HEAD(cleanup_list); /* Must hold cleanup_list_lock to touch */ + static void cleanup_net(struct work_struct *work) { - struct pernet_operations *ops; - struct net *net; + const struct pernet_operations *ops; + struct net *net, *tmp; + LIST_HEAD(net_kill_list); + LIST_HEAD(net_exit_list); - net = container_of(work, struct net, work); + /* Atomically snapshot the list of namespaces to cleanup */ + spin_lock_irq(&cleanup_list_lock); + list_replace_init(&cleanup_list, &net_kill_list); + spin_unlock_irq(&cleanup_list_lock); mutex_lock(&net_mutex); /* Don't let anyone else find us. */ rtnl_lock(); - list_del_rcu(&net->list); + list_for_each_entry(net, &net_kill_list, cleanup_list) { + list_del_rcu(&net->list); + list_add_tail(&net->exit_list, &net_exit_list); + } rtnl_unlock(); /* @@ -169,10 +232,12 @@ static void cleanup_net(struct work_struct *work) synchronize_rcu(); /* Run all of the network namespace exit methods */ - list_for_each_entry_reverse(ops, &pernet_list, list) { - if (ops->exit) - ops->exit(net); - } + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_exit_list(ops, &net_exit_list); + + /* Free the net generic variables */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_free_list(ops, &net_exit_list); mutex_unlock(&net_mutex); @@ -182,14 +247,23 @@ static void cleanup_net(struct work_struct *work) rcu_barrier(); /* Finally it is safe to free my network namespace structure */ - net_free(net); + list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { + list_del_init(&net->exit_list); + net_free(net); + } } +static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ - INIT_WORK(&net->work, cleanup_net); - queue_work(netns_wq, &net->work); + unsigned long flags; + + spin_lock_irqsave(&cleanup_list_lock, flags); + list_add(&net->cleanup_list, &cleanup_list); + spin_unlock_irqrestore(&cleanup_list_lock, flags); + + queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); @@ -259,18 +333,20 @@ static int __init net_ns_init(void) pure_initcall(net_ns_init); #ifdef CONFIG_NET_NS -static int register_pernet_operations(struct list_head *list, - struct pernet_operations *ops) +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) { - struct net *net, *undo_net; + struct net *net; int error; + LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); - if (ops->init) { + if (ops->init || (ops->id && ops->size)) { for_each_net(net) { - error = ops->init(net); + error = ops_init(ops, net); if (error) goto out_undo; + list_add_tail(&net->exit_list, &net_exit_list); } } return 0; @@ -278,45 +354,82 @@ static int register_pernet_operations(struct list_head *list, out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); - if (ops->exit) { - for_each_net(undo_net) { - if (undo_net == net) - goto undone; - ops->exit(undo_net); - } - } -undone: + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); return error; } -static void unregister_pernet_operations(struct pernet_operations *ops) +static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; + LIST_HEAD(net_exit_list); list_del(&ops->list); - if (ops->exit) - for_each_net(net) - ops->exit(net); + for_each_net(net) + list_add_tail(&net->exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); } #else +static int __register_pernet_operations(struct list_head *list, + struct pernet_operations *ops) +{ + int err = 0; + err = ops_init(ops, &init_net); + if (err) + ops_free(ops, &init_net); + return err; + +} + +static void __unregister_pernet_operations(struct pernet_operations *ops) +{ + LIST_HEAD(net_exit_list); + list_add(&init_net.exit_list, &net_exit_list); + ops_exit_list(ops, &net_exit_list); + ops_free_list(ops, &net_exit_list); +} + +#endif /* CONFIG_NET_NS */ + +static DEFINE_IDA(net_generic_ids); + static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { - if (ops->init == NULL) - return 0; - return ops->init(&init_net); + int error; + + if (ops->id) { +again: + error = ida_get_new_above(&net_generic_ids, 1, ops->id); + if (error < 0) { + if (error == -EAGAIN) { + ida_pre_get(&net_generic_ids, GFP_KERNEL); + goto again; + } + return error; + } + } + error = __register_pernet_operations(list, ops); + if (error) { + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); + } + + return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { - if (ops->exit) - ops->exit(&init_net); + + __unregister_pernet_operations(ops); + rcu_barrier(); + if (ops->id) + ida_remove(&net_generic_ids, *ops->id); } -#endif - -static DEFINE_IDA(net_generic_ids); /** * register_pernet_subsys - register a network namespace subsystem @@ -364,38 +477,6 @@ void unregister_pernet_subsys(struct pernet_operations *module) } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); -int register_pernet_gen_subsys(int *id, struct pernet_operations *ops) -{ - int rv; - - mutex_lock(&net_mutex); -again: - rv = ida_get_new_above(&net_generic_ids, 1, id); - if (rv < 0) { - if (rv == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - rv = register_pernet_operations(first_device, ops); - if (rv < 0) - ida_remove(&net_generic_ids, *id); -out: - mutex_unlock(&net_mutex); - return rv; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_subsys); - -void unregister_pernet_gen_subsys(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_subsys); - /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem @@ -427,30 +508,6 @@ int register_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(register_pernet_device); -int register_pernet_gen_device(int *id, struct pernet_operations *ops) -{ - int error; - mutex_lock(&net_mutex); -again: - error = ida_get_new_above(&net_generic_ids, 1, id); - if (error) { - if (error == -EAGAIN) { - ida_pre_get(&net_generic_ids, GFP_KERNEL); - goto again; - } - goto out; - } - error = register_pernet_operations(&pernet_list, ops); - if (error) - ida_remove(&net_generic_ids, *id); - else if (first_device == &pernet_list) - first_device = &ops->list; -out: - mutex_unlock(&net_mutex); - return error; -} -EXPORT_SYMBOL_GPL(register_pernet_gen_device); - /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate @@ -470,17 +527,6 @@ void unregister_pernet_device(struct pernet_operations *ops) } EXPORT_SYMBOL_GPL(unregister_pernet_device); -void unregister_pernet_gen_device(int id, struct pernet_operations *ops) -{ - mutex_lock(&net_mutex); - if (&ops->list == first_device) - first_device = first_device->next; - unregister_pernet_operations(ops); - ida_remove(&net_generic_ids, id); - mutex_unlock(&net_mutex); -} -EXPORT_SYMBOL_GPL(unregister_pernet_gen_device); - static void net_generic_release(struct rcu_head *rcu) { struct net_generic *ng; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6eb8d47cbf3..a23b45f08ec 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -340,6 +340,7 @@ struct pktgen_dev { __u16 cur_udp_src; __u16 cur_queue_map; __u32 cur_pkt_size; + __u32 last_pkt_size; __u8 hh[14]; /* = { @@ -363,6 +364,7 @@ struct pktgen_dev { * device name (not when the inject is * started as it used to do.) */ + char odevname[32]; struct flow_state *flows; unsigned cflows; /* Concurrent flows (config) */ unsigned lflow; /* Flow length (config) */ @@ -426,7 +428,7 @@ static const char version[] = static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname); + const char *ifname, bool exact); static int pktgen_device_event(struct notifier_block *, unsigned long, void *); static void pktgen_run_all_threads(void); static void pktgen_reset_all_threads(void); @@ -528,7 +530,7 @@ static int pktgen_if_show(struct seq_file *seq, void *v) seq_printf(seq, " frags: %d delay: %llu clone_skb: %d ifname: %s\n", pkt_dev->nfrags, (unsigned long long) pkt_dev->delay, - pkt_dev->clone_skb, pkt_dev->odev->name); + pkt_dev->clone_skb, pkt_dev->odevname); seq_printf(seq, " flows: %u flowlen: %u\n", pkt_dev->cflows, pkt_dev->lflow); @@ -1688,13 +1690,13 @@ static int pktgen_thread_show(struct seq_file *seq, void *v) if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) if (pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); seq_printf(seq, "\nStopped: "); list_for_each_entry(pkt_dev, &t->if_list, list) if (!pkt_dev->running) - seq_printf(seq, "%s ", pkt_dev->odev->name); + seq_printf(seq, "%s ", pkt_dev->odevname); if (t->result[0]) seq_printf(seq, "\nResult: %s\n", t->result); @@ -1817,9 +1819,10 @@ static struct pktgen_dev *__pktgen_NN_threads(const char *ifname, int remove) { struct pktgen_thread *t; struct pktgen_dev *pkt_dev = NULL; + bool exact = (remove == FIND); list_for_each_entry(t, &pktgen_threads, th_list) { - pkt_dev = pktgen_find_dev(t, ifname); + pkt_dev = pktgen_find_dev(t, ifname, exact); if (pkt_dev) { if (remove) { if_lock(t); @@ -1994,7 +1997,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_min (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_min = ntxq - 1; } if (pkt_dev->queue_map_max >= ntxq) { @@ -2002,7 +2005,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) "queue_map_max (zero-based) (%d) exceeds valid range " "[0 - %d] for (%d) queues on %s, resetting\n", pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odev->name); + pkt_dev->odevname); pkt_dev->queue_map_max = ntxq - 1; } @@ -2049,9 +2052,8 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) read_lock_bh(&idev->lock); for (ifp = idev->addr_list; ifp; ifp = ifp->if_next) { - if (ifp->scope == IFA_LINK - && !(ifp-> - flags & IFA_F_TENTATIVE)) { + if (ifp->scope == IFA_LINK && + !(ifp->flags & IFA_F_TENTATIVE)) { ipv6_addr_copy(&pkt_dev-> cur_in6_saddr, &ifp->addr); @@ -3262,7 +3264,7 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) if (!pkt_dev->running) { printk(KERN_WARNING "pktgen: interface: %s is already " - "stopped\n", pkt_dev->odev->name); + "stopped\n", pkt_dev->odevname); return -EINVAL; } @@ -3434,7 +3436,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->clone_count--; /* back out increment, OOM */ return; } - + pkt_dev->last_pkt_size = pkt_dev->skb->len; pkt_dev->allocated_skbs++; pkt_dev->clone_count = 0; /* reset counter */ } @@ -3446,12 +3448,14 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) txq = netdev_get_tx_queue(odev, queue_map); __netif_tx_lock_bh(txq); - atomic_inc(&(pkt_dev->skb->users)); - if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) + if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) { ret = NETDEV_TX_BUSY; - else - ret = (*xmit)(pkt_dev->skb, odev); + pkt_dev->last_ok = 0; + goto unlock; + } + atomic_inc(&(pkt_dev->skb->users)); + ret = (*xmit)(pkt_dev->skb, odev); switch (ret) { case NETDEV_TX_OK: @@ -3459,12 +3463,12 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->last_ok = 1; pkt_dev->sofar++; pkt_dev->seq_num++; - pkt_dev->tx_bytes += pkt_dev->cur_pkt_size; + pkt_dev->tx_bytes += pkt_dev->last_pkt_size; break; default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) pr_info("pktgen: %s xmit error: %d\n", - odev->name, ret); + pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3473,6 +3477,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) atomic_dec(&(pkt_dev->skb->users)); pkt_dev->last_ok = 0; } +unlock: __netif_tx_unlock_bh(txq); /* If pkt_dev->count is zero, then run forever */ @@ -3566,13 +3571,18 @@ static int pktgen_thread_worker(void *arg) } static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, - const char *ifname) + const char *ifname, bool exact) { struct pktgen_dev *p, *pkt_dev = NULL; - if_lock(t); + size_t len = strlen(ifname); + if_lock(t); list_for_each_entry(p, &t->if_list, list) - if (strncmp(p->odev->name, ifname, IFNAMSIZ) == 0) { + if (strncmp(p->odevname, ifname, len) == 0) { + if (p->odevname[len]) { + if (exact || p->odevname[len] != '@') + continue; + } pkt_dev = p; break; } @@ -3615,6 +3625,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) { struct pktgen_dev *pkt_dev; int err; + int node = cpu_to_node(t->cpu); /* We don't allow a device to be on several threads */ @@ -3624,11 +3635,13 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) return -EBUSY; } - pkt_dev = kzalloc(sizeof(struct pktgen_dev), GFP_KERNEL); + pkt_dev = kzalloc_node(sizeof(struct pktgen_dev), GFP_KERNEL, node); if (!pkt_dev) return -ENOMEM; - pkt_dev->flows = vmalloc(MAX_CFLOWS * sizeof(struct flow_state)); + strcpy(pkt_dev->odevname, ifname); + pkt_dev->flows = vmalloc_node(MAX_CFLOWS * sizeof(struct flow_state), + node); if (pkt_dev->flows == NULL) { kfree(pkt_dev); return -ENOMEM; @@ -3690,7 +3703,8 @@ static int __init pktgen_create_thread(int cpu) struct proc_dir_entry *pe; struct task_struct *p; - t = kzalloc(sizeof(struct pktgen_thread), GFP_KERNEL); + t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, + cpu_to_node(cpu)); if (!t) { printk(KERN_ERR "pktgen: ERROR: out of memory, can't " "create new thread.\n"); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eb42873f2a3..33148a56819 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -38,7 +38,6 @@ #include <asm/uaccess.h> #include <asm/system.h> -#include <asm/string.h> #include <linux/inet.h> #include <linux/netdevice.h> @@ -53,8 +52,7 @@ #include <net/rtnetlink.h> #include <net/net_namespace.h> -struct rtnl_link -{ +struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; }; @@ -65,6 +63,7 @@ void rtnl_lock(void) { mutex_lock(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_lock); void __rtnl_unlock(void) { @@ -76,16 +75,19 @@ void rtnl_unlock(void) /* This fellow will unlock it for us. */ netdev_run_todo(); } +EXPORT_SYMBOL(rtnl_unlock); int rtnl_trylock(void) { return mutex_trylock(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_trylock); int rtnl_is_locked(void) { return mutex_is_locked(&rtnl_mutex); } +EXPORT_SYMBOL(rtnl_is_locked); static struct rtnl_link *rtnl_msg_handlers[NPROTO]; @@ -168,7 +170,6 @@ int __rtnl_register(int protocol, int msgtype, return 0; } - EXPORT_SYMBOL_GPL(__rtnl_register); /** @@ -188,7 +189,6 @@ void rtnl_register(int protocol, int msgtype, "protocol = %d, message type = %d\n", protocol, msgtype); } - EXPORT_SYMBOL_GPL(rtnl_register); /** @@ -213,7 +213,6 @@ int rtnl_unregister(int protocol, int msgtype) return 0; } - EXPORT_SYMBOL_GPL(rtnl_unregister); /** @@ -230,7 +229,6 @@ void rtnl_unregister_all(int protocol) kfree(rtnl_msg_handlers[protocol]); rtnl_msg_handlers[protocol] = NULL; } - EXPORT_SYMBOL_GPL(rtnl_unregister_all); static LIST_HEAD(link_ops); @@ -248,12 +246,11 @@ static LIST_HEAD(link_ops); int __rtnl_link_register(struct rtnl_link_ops *ops) { if (!ops->dellink) - ops->dellink = unregister_netdevice; + ops->dellink = unregister_netdevice_queue; list_add_tail(&ops->list, &link_ops); return 0; } - EXPORT_SYMBOL_GPL(__rtnl_link_register); /** @@ -271,19 +268,18 @@ int rtnl_link_register(struct rtnl_link_ops *ops) rtnl_unlock(); return err; } - EXPORT_SYMBOL_GPL(rtnl_link_register); static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) { struct net_device *dev; -restart: + LIST_HEAD(list_kill); + for_each_netdev(net, dev) { - if (dev->rtnl_link_ops == ops) { - ops->dellink(dev); - goto restart; - } + if (dev->rtnl_link_ops == ops) + ops->dellink(dev, &list_kill); } + unregister_netdevice_many(&list_kill); } void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) @@ -309,7 +305,6 @@ void __rtnl_link_unregister(struct rtnl_link_ops *ops) } list_del(&ops->list); } - EXPORT_SYMBOL_GPL(__rtnl_link_unregister); /** @@ -322,7 +317,6 @@ void rtnl_link_unregister(struct rtnl_link_ops *ops) __rtnl_link_unregister(ops); rtnl_unlock(); } - EXPORT_SYMBOL_GPL(rtnl_link_unregister); static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind) @@ -427,12 +421,13 @@ void __rta_fill(struct sk_buff *skb, int attrtype, int attrlen, const void *data struct rtattr *rta; int size = RTA_LENGTH(attrlen); - rta = (struct rtattr*)skb_put(skb, RTA_ALIGN(size)); + rta = (struct rtattr *)skb_put(skb, RTA_ALIGN(size)); rta->rta_type = attrtype; rta->rta_len = size; memcpy(RTA_DATA(rta), data, attrlen); memset(RTA_DATA(rta) + attrlen, 0, RTA_ALIGN(size) - size); } +EXPORT_SYMBOL(__rta_fill); int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, unsigned group, int echo) { @@ -454,6 +449,7 @@ int rtnl_unicast(struct sk_buff *skb, struct net *net, u32 pid) return nlmsg_unicast(rtnl, skb, pid); } +EXPORT_SYMBOL(rtnl_unicast); void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, struct nlmsghdr *nlh, gfp_t flags) @@ -466,6 +462,7 @@ void rtnl_notify(struct sk_buff *skb, struct net *net, u32 pid, u32 group, nlmsg_notify(rtnl, skb, pid, group, report, flags); } +EXPORT_SYMBOL(rtnl_notify); void rtnl_set_sk_err(struct net *net, u32 group, int error) { @@ -473,6 +470,7 @@ void rtnl_set_sk_err(struct net *net, u32 group, int error) netlink_set_err(rtnl, 0, group, error); } +EXPORT_SYMBOL(rtnl_set_sk_err); int rtnetlink_put_metrics(struct sk_buff *skb, u32 *metrics) { @@ -501,6 +499,7 @@ nla_put_failure: nla_nest_cancel(skb, mx); return -EMSGSIZE; } +EXPORT_SYMBOL(rtnetlink_put_metrics); int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, u32 ts, u32 tsage, long expires, u32 error) @@ -520,14 +519,13 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, return nla_put(skb, RTA_CACHEINFO, sizeof(ci), &ci); } - EXPORT_SYMBOL_GPL(rtnl_put_cacheinfo); static void set_operstate(struct net_device *dev, unsigned char transition) { unsigned char operstate = dev->operstate; - switch(transition) { + switch (transition) { case IF_OPER_UP: if ((operstate == IF_OPER_DORMANT || operstate == IF_OPER_UNKNOWN) && @@ -682,22 +680,33 @@ nla_put_failure: static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int idx; - int s_idx = cb->args[0]; + int h, s_h; + int idx = 0, s_idx; struct net_device *dev; - - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) - break; + struct hlist_head *head; + struct hlist_node *node; + + s_h = cb->args[0]; + s_idx = cb->args[1]; + + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (rtnl_fill_ifinfo(skb, dev, RTM_NEWLINK, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, 0, + NLM_F_MULTI) <= 0) + goto out; cont: - idx++; + idx++; + } } - cb->args[0] = idx; +out: + cb->args[1] = idx; + cb->args[0] = h; return skb->len; } @@ -717,12 +726,27 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, }; +EXPORT_SYMBOL(ifla_policy); static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = { [IFLA_INFO_KIND] = { .type = NLA_STRING }, [IFLA_INFO_DATA] = { .type = NLA_NESTED }, }; +struct net *rtnl_link_get_net(struct net *src_net, struct nlattr *tb[]) +{ + struct net *net; + /* Examine the link attributes and figure out which + * network namespace we are talking about. + */ + if (tb[IFLA_NET_NS_PID]) + net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); + else + net = get_net(src_net); + return net; +} +EXPORT_SYMBOL(rtnl_link_get_net); + static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) { if (dev) { @@ -746,8 +770,7 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, int err; if (tb[IFLA_NET_NS_PID]) { - struct net *net; - net = get_net_ns_by_pid(nla_get_u32(tb[IFLA_NET_NS_PID])); + struct net *net = rtnl_link_get_net(dev_net(dev), tb); if (IS_ERR(net)) { err = PTR_ERR(net); goto errout; @@ -910,9 +933,9 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) err = -EINVAL; ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) - dev = dev_get_by_index(net, ifm->ifi_index); + dev = __dev_get_by_index(net, ifm->ifi_index); else if (tb[IFLA_IFNAME]) - dev = dev_get_by_name(net, ifname); + dev = __dev_get_by_name(net, ifname); else goto errout; @@ -921,12 +944,11 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) goto errout; } - if ((err = validate_linkmsg(dev, tb)) < 0) - goto errout_dev; + err = validate_linkmsg(dev, tb); + if (err < 0) + goto errout; err = do_setlink(dev, ifm, tb, ifname, 0); -errout_dev: - dev_put(dev); errout: return err; } @@ -963,12 +985,12 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) if (!ops) return -EOPNOTSUPP; - ops->dellink(dev); + ops->dellink(dev, NULL); return 0; } -struct net_device *rtnl_create_link(struct net *net, char *ifname, - const struct rtnl_link_ops *ops, struct nlattr *tb[]) +struct net_device *rtnl_create_link(struct net *src_net, struct net *net, + char *ifname, const struct rtnl_link_ops *ops, struct nlattr *tb[]) { int err; struct net_device *dev; @@ -976,7 +998,8 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, unsigned int real_num_queues = 1; if (ops->get_tx_queues) { - err = ops->get_tx_queues(net, tb, &num_queues, &real_num_queues); + err = ops->get_tx_queues(src_net, tb, &num_queues, + &real_num_queues); if (err) goto err; } @@ -985,16 +1008,16 @@ struct net_device *rtnl_create_link(struct net *net, char *ifname, if (!dev) goto err; + dev_net_set(dev, net); + dev->rtnl_link_ops = ops; dev->real_num_tx_queues = real_num_queues; + if (strchr(dev->name, '%')) { err = dev_alloc_name(dev, dev->name); if (err < 0) goto err_free; } - dev_net_set(dev, net); - dev->rtnl_link_ops = ops; - if (tb[IFLA_MTU]) dev->mtu = nla_get_u32(tb[IFLA_MTU]); if (tb[IFLA_ADDRESS]) @@ -1017,6 +1040,7 @@ err_free: err: return ERR_PTR(err); } +EXPORT_SYMBOL(rtnl_create_link); static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { @@ -1050,7 +1074,8 @@ replay: else dev = NULL; - if ((err = validate_linkmsg(dev, tb)) < 0) + err = validate_linkmsg(dev, tb); + if (err < 0) return err; if (tb[IFLA_LINKINFO]) { @@ -1071,6 +1096,7 @@ replay: if (1) { struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL; + struct net *dest_net; if (ops) { if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) { @@ -1135,17 +1161,19 @@ replay: if (!ifname[0]) snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind); - dev = rtnl_create_link(net, ifname, ops, tb); + dest_net = rtnl_link_get_net(net, tb); + dev = rtnl_create_link(net, dest_net, ifname, ops, tb); if (IS_ERR(dev)) err = PTR_ERR(dev); else if (ops->newlink) - err = ops->newlink(dev, tb, data); + err = ops->newlink(net, dev, tb, data); else err = register_netdevice(dev); - if (err < 0 && !IS_ERR(dev)) free_netdev(dev); + + put_net(dest_net); return err; } } @@ -1154,6 +1182,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; + char ifname[IFNAMSIZ]; struct nlattr *tb[IFLA_MAX+1]; struct net_device *dev = NULL; struct sk_buff *nskb; @@ -1163,19 +1192,23 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (err < 0) return err; + if (tb[IFLA_IFNAME]) + nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ); + ifm = nlmsg_data(nlh); - if (ifm->ifi_index > 0) { - dev = dev_get_by_index(net, ifm->ifi_index); - if (dev == NULL) - return -ENODEV; - } else + if (ifm->ifi_index > 0) + dev = __dev_get_by_index(net, ifm->ifi_index); + else if (tb[IFLA_IFNAME]) + dev = __dev_get_by_name(net, ifname); + else return -EINVAL; + if (dev == NULL) + return -ENODEV; + nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL); - if (nskb == NULL) { - err = -ENOBUFS; - goto errout; - } + if (nskb == NULL) + return -ENOBUFS; err = rtnl_fill_ifinfo(nskb, dev, RTM_NEWLINK, NETLINK_CB(skb).pid, nlh->nlmsg_seq, 0, 0); @@ -1183,11 +1216,8 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); kfree_skb(nskb); - goto errout; - } - err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); -errout: - dev_put(dev); + } else + err = rtnl_unicast(nskb, net, NETLINK_CB(skb).pid); return err; } @@ -1199,7 +1229,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb) if (s_idx == 0) s_idx = 1; - for (idx=1; idx<NPROTO; idx++) { + for (idx = 1; idx < NPROTO; idx++) { int type = cb->nlh->nlmsg_type-RTM_BASE; if (idx < s_idx || idx == PF_PACKET) continue; @@ -1266,7 +1296,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct rtgenmsg))) return 0; - family = ((struct rtgenmsg*)NLMSG_DATA(nlh))->rtgen_family; + family = ((struct rtgenmsg *)NLMSG_DATA(nlh))->rtgen_family; if (family >= NPROTO) return -EAFNOSUPPORT; @@ -1299,7 +1329,7 @@ static int rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) if (nlh->nlmsg_len > min_len) { int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len); - struct rtattr *attr = (void*)nlh + NLMSG_ALIGN(min_len); + struct rtattr *attr = (void *)nlh + NLMSG_ALIGN(min_len); while (RTA_OK(attr, attrlen)) { unsigned flavor = attr->rta_type; @@ -1405,14 +1435,3 @@ void __init rtnetlink_init(void) rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all); } -EXPORT_SYMBOL(__rta_fill); -EXPORT_SYMBOL(rtnetlink_put_metrics); -EXPORT_SYMBOL(rtnl_lock); -EXPORT_SYMBOL(rtnl_trylock); -EXPORT_SYMBOL(rtnl_unlock); -EXPORT_SYMBOL(rtnl_is_locked); -EXPORT_SYMBOL(rtnl_unicast); -EXPORT_SYMBOL(rtnl_notify); -EXPORT_SYMBOL(rtnl_set_sk_err); -EXPORT_SYMBOL(rtnl_create_link); -EXPORT_SYMBOL(ifla_policy); diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c deleted file mode 100644 index 79687dfd695..00000000000 --- a/net/core/skb_dma_map.c +++ /dev/null @@ -1,65 +0,0 @@ -/* skb_dma_map.c: DMA mapping helpers for socket buffers. - * - * Copyright (C) David S. Miller <davem@davemloft.net> - */ - -#include <linux/kernel.h> -#include <linux/module.h> -#include <linux/dma-mapping.h> -#include <linux/skbuff.h> - -int skb_dma_map(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - dma_addr_t map; - int i; - - map = dma_map_single(dev, skb->data, - skb_headlen(skb), dir); - if (dma_mapping_error(dev, map)) - goto out_err; - - sp->dma_head = map; - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - map = dma_map_page(dev, fp->page, fp->page_offset, - fp->size, dir); - if (dma_mapping_error(dev, map)) - goto unwind; - sp->dma_maps[i] = map; - } - - return 0; - -unwind: - while (--i >= 0) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); -out_err: - return -ENOMEM; -} -EXPORT_SYMBOL(skb_dma_map); - -void skb_dma_unmap(struct device *dev, struct sk_buff *skb, - enum dma_data_direction dir) -{ - struct skb_shared_info *sp = skb_shinfo(skb); - int i; - - dma_unmap_single(dev, sp->dma_head, - skb_headlen(skb), dir); - for (i = 0; i < sp->nr_frags; i++) { - skb_frag_t *fp = &sp->frags[i]; - - dma_unmap_page(dev, sp->dma_maps[i], - fp->size, dir); - } -} -EXPORT_SYMBOL(skb_dma_unmap); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ec85681a7dd..bfa3e7865a8 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -493,6 +493,9 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size) { struct skb_shared_info *shinfo; + if (irqs_disabled()) + return 0; + if (skb_is_nonlinear(skb) || skb->fclone != SKB_FCLONE_UNAVAILABLE) return 0; @@ -546,7 +549,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) #endif new->protocol = old->protocol; new->mark = old->mark; - new->iif = old->iif; + new->skb_iif = old->skb_iif; __nf_copy(new, old); #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \ defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE) diff --git a/net/core/sock.c b/net/core/sock.c index 7626b6aacd6..76ff58d43e2 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -274,25 +274,27 @@ static void sock_disable_timestamp(struct sock *sk, int flag) int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - int err = 0; + int err; int skb_len; + unsigned long flags; + struct sk_buff_head *list = &sk->sk_receive_queue; /* Cast sk->rcvbuf to unsigned... It's pointless, but reduces number of warnings when compiling with -W --ANK */ if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= (unsigned)sk->sk_rcvbuf) { - err = -ENOMEM; - goto out; + atomic_inc(&sk->sk_drops); + return -ENOMEM; } err = sk_filter(sk, skb); if (err) - goto out; + return err; if (!sk_rmem_schedule(sk, skb->truesize)) { - err = -ENOBUFS; - goto out; + atomic_inc(&sk->sk_drops); + return -ENOBUFS; } skb->dev = NULL; @@ -305,12 +307,14 @@ int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ skb_len = skb->len; - skb_queue_tail(&sk->sk_receive_queue, skb); + spin_lock_irqsave(&list->lock, flags); + skb->dropcount = atomic_read(&sk->sk_drops); + __skb_queue_tail(list, skb); + spin_unlock_irqrestore(&list->lock, flags); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_data_ready(sk, skb_len); -out: - return err; + return 0; } EXPORT_SYMBOL(sock_queue_rcv_skb); @@ -348,11 +352,18 @@ discard_and_relse: } EXPORT_SYMBOL(sk_receive_skb); +void sk_reset_txq(struct sock *sk) +{ + sk_tx_queue_clear(sk); +} +EXPORT_SYMBOL(sk_reset_txq); + struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie) { struct dst_entry *dst = sk->sk_dst_cache; if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) { + sk_tx_queue_clear(sk); sk->sk_dst_cache = NULL; dst_release(dst); return NULL; @@ -406,17 +417,18 @@ static int sock_bindtodevice(struct sock *sk, char __user *optval, int optlen) if (copy_from_user(devname, optval, optlen)) goto out; - if (devname[0] == '\0') { - index = 0; - } else { - struct net_device *dev = dev_get_by_name(net, devname); + index = 0; + if (devname[0] != '\0') { + struct net_device *dev; + rcu_read_lock(); + dev = dev_get_by_name_rcu(net, devname); + if (dev) + index = dev->ifindex; + rcu_read_unlock(); ret = -ENODEV; if (!dev) goto out; - - index = dev->ifindex; - dev_put(dev); } lock_sock(sk); @@ -702,6 +714,12 @@ set_rcvbuf: /* We implement the SO_SNDLOWAT etc to not be settable (1003.1g 5.3) */ + case SO_RXQ_OVFL: + if (valbool) + sock_set_flag(sk, SOCK_RXQ_OVFL); + else + sock_reset_flag(sk, SOCK_RXQ_OVFL); + break; default: ret = -ENOPROTOOPT; break; @@ -901,6 +919,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_mark; break; + case SO_RXQ_OVFL: + v.val = !!sock_flag(sk, SOCK_RXQ_OVFL); + break; + default: return -ENOPROTOOPT; } @@ -939,7 +961,8 @@ static void sock_copy(struct sock *nsk, const struct sock *osk) void *sptr = nsk->sk_security; #endif BUILD_BUG_ON(offsetof(struct sock, sk_copy_start) != - sizeof(osk->sk_node) + sizeof(osk->sk_refcnt)); + sizeof(osk->sk_node) + sizeof(osk->sk_refcnt) + + sizeof(osk->sk_tx_queue_mapping)); memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); #ifdef CONFIG_SECURITY_NETWORK @@ -983,6 +1006,7 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!try_module_get(prot->owner)) goto out_free_sec; + sk_tx_queue_clear(sk); } return sk; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 7db1de0497c..06124872af5 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -10,14 +10,15 @@ #include <linux/module.h> #include <linux/socket.h> #include <linux/netdevice.h> +#include <linux/ratelimit.h> #include <linux/init.h> + #include <net/ip.h> #include <net/sock.h> static struct ctl_table net_core_table[] = { #ifdef CONFIG_NET { - .ctl_name = NET_CORE_WMEM_MAX, .procname = "wmem_max", .data = &sysctl_wmem_max, .maxlen = sizeof(int), @@ -25,7 +26,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_RMEM_MAX, .procname = "rmem_max", .data = &sysctl_rmem_max, .maxlen = sizeof(int), @@ -33,7 +33,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_WMEM_DEFAULT, .procname = "wmem_default", .data = &sysctl_wmem_default, .maxlen = sizeof(int), @@ -41,7 +40,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_RMEM_DEFAULT, .procname = "rmem_default", .data = &sysctl_rmem_default, .maxlen = sizeof(int), @@ -49,7 +47,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_DEV_WEIGHT, .procname = "dev_weight", .data = &weight_p, .maxlen = sizeof(int), @@ -57,7 +54,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_MAX_BACKLOG, .procname = "netdev_max_backlog", .data = &netdev_max_backlog, .maxlen = sizeof(int), @@ -65,16 +61,13 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_MSG_COST, .procname = "message_cost", .data = &net_ratelimit_state.interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, - .strategy = sysctl_jiffies, }, { - .ctl_name = NET_CORE_MSG_BURST, .procname = "message_burst", .data = &net_ratelimit_state.burst, .maxlen = sizeof(int), @@ -82,7 +75,6 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec, }, { - .ctl_name = NET_CORE_OPTMEM_MAX, .procname = "optmem_max", .data = &sysctl_optmem_max, .maxlen = sizeof(int), @@ -91,7 +83,6 @@ static struct ctl_table net_core_table[] = { }, #endif /* CONFIG_NET */ { - .ctl_name = NET_CORE_BUDGET, .procname = "netdev_budget", .data = &netdev_budget, .maxlen = sizeof(int), @@ -99,31 +90,29 @@ static struct ctl_table net_core_table[] = { .proc_handler = proc_dointvec }, { - .ctl_name = NET_CORE_WARNINGS, .procname = "warnings", .data = &net_msg_warn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; static struct ctl_table netns_core_table[] = { { - .ctl_name = NET_CORE_SOMAXCONN, .procname = "somaxconn", .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec }, - { .ctl_name = 0 } + { } }; __net_initdata struct ctl_path net_core_path[] = { - { .procname = "net", .ctl_name = CTL_NET, }, - { .procname = "core", .ctl_name = NET_CORE, }, + { .procname = "net", }, + { .procname = "core", }, { }, }; @@ -134,7 +123,7 @@ static __net_init int sysctl_core_net_init(struct net *net) net->core.sysctl_somaxconn = SOMAXCONN; tbl = netns_core_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL); if (tbl == NULL) goto err_dup; diff --git a/net/core/utils.c b/net/core/utils.c index 83221aee708..838250241d2 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -24,6 +24,8 @@ #include <linux/types.h> #include <linux/percpu.h> #include <linux/init.h> +#include <linux/ratelimit.h> + #include <net/sock.h> #include <asm/byteorder.h> |