diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/datagram.c | 1 | ||||
-rw-r--r-- | net/core/dev.c | 408 | ||||
-rw-r--r-- | net/core/drop_monitor.c | 2 | ||||
-rw-r--r-- | net/core/ethtool.c | 81 | ||||
-rw-r--r-- | net/core/filter.c | 6 | ||||
-rw-r--r-- | net/core/gen_stats.c | 8 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 55 | ||||
-rw-r--r-- | net/core/pktgen.c | 16 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 179 | ||||
-rw-r--r-- | net/core/skbuff.c | 3 | ||||
-rw-r--r-- | net/core/sock.c | 58 |
11 files changed, 523 insertions, 294 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index 4ade301..95c2e08 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 fe10551..d867522 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> @@ -175,7 +176,7 @@ 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 +194,15 @@ 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 +213,26 @@ 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 +588,44 @@ __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 +641,11 @@ 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 +665,42 @@ 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 +717,11 @@ 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 +800,15 @@ 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); @@ -935,7 +987,12 @@ 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 +1095,9 @@ 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); @@ -1701,7 +1758,7 @@ 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 +1806,8 @@ 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 +1817,12 @@ 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 +1849,43 @@ 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); + 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 (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 (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 +2022,8 @@ 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; } @@ -2292,7 +2379,7 @@ 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 */ @@ -2440,7 +2527,7 @@ 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 +2535,7 @@ 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 +2619,8 @@ 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; @@ -2549,24 +2637,25 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) 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 +2675,7 @@ 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 +2694,41 @@ 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 +2769,12 @@ 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 +3019,15 @@ 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 +3097,18 @@ 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 +3117,18 @@ 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 +4337,12 @@ 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 +4574,9 @@ 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 +4719,76 @@ 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); + } 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, @@ -4837,6 +4937,12 @@ 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; @@ -5174,6 +5280,7 @@ 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); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); strcpy(dev->name, name); @@ -5238,25 +5345,48 @@ 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_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); +EXPORT_SYMBOL(unregister_netdevice_many); /** * unregister_netdev - remove device from the kernel @@ -5484,7 +5614,7 @@ 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; @@ -5583,7 +5713,7 @@ restart: /* Delete virtual devices */ if (dev->rtnl_link_ops && dev->rtnl_link_ops->dellink) { - dev->rtnl_link_ops->dellink(dev); + dev->rtnl_link_ops->dellink(dev, NULL); goto restart; } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 0a113f2..b8e9d3a 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 4c12ddb..d8aee58 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/filter.c b/net/core/filter.c index d1d779c..08db7b9 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 8569310..393b1d8 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/net-sysfs.c b/net/core/net-sysfs.c index 427ded8..157645c 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), @@ -500,12 +544,19 @@ 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) diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 6eb8d47..d38470a 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]; /* = { @@ -3434,7 +3435,7 @@ 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 +3447,14 @@ 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: @@ -3459,7 +3462,7 @@ 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()) @@ -3473,6 +3476,7 @@ 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 */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index eb42873..33148a5 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/skbuff.c b/net/core/skbuff.c index 80a9616..941bac9 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; diff --git a/net/core/sock.c b/net/core/sock.c index 7626b6a..76ff58d 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; |